Contact: linux-wireless@vger.kernel.org,
Description: The rfkill class subsystem folder.
Each registered rfkill driver is represented by an rfkillX
- subfolder (X being an integer > 0).
+ subfolder (X being an integer >= 0).
What: /sys/class/rfkill/rfkill[0-9]+/name
Description: Current state of the transmitter.
This file was scheduled to be removed in 2014, but due to its
large number of users it will be sticking around for a bit
- longer. Despite it being marked as stabe, the newer "hard" and
- "soft" interfaces should be preffered, since it is not possible
+ longer. Despite it being marked as stable, the newer "hard" and
+ "soft" interfaces should be preferred, since it is not possible
to express the 'soft and hard block' state of the rfkill driver
through this interface. There will likely be another attempt to
remove it in the future.
network device transmit queue. Possible vaules depend on the
number of available CPU(s) in the system.
+What: /sys/class/<iface>/queues/tx-<queue>/xps_rxqs
+Date: June 2018
+KernelVersion: 4.18.0
+Contact: netdev@vger.kernel.org
+Description:
+ Mask of the receive queue(s) currently enabled to participate
+ into the Transmit Packet Steering packet processing flow for this
+ network device transmit queue. Possible values depend on the
+ number of available receive queue(s) in the network device.
+ Default is disabled.
+
What: /sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/hold_time
Date: November 2011
KernelVersion: 3.3
``intel_pstate`` exposes several global attributes (files) in ``sysfs`` to
control its functionality at the system level. They are located in the
-``/sys/devices/system/cpu/cpufreq/intel_pstate/`` directory and affect all
-CPUs.
+``/sys/devices/system/cpu/intel_pstate/`` directory and affect all CPUs.
Some of them are not present if the ``intel_pstate=per_cpu_perf_limits``
argument is passed to the kernel in the command line.
but it affects the maximum possible value of per-policy P-state limits
(see `Interpretation of Policy Attributes`_ below for details).
+``hwp_dynamic_boost``
+ This attribute is only present if ``intel_pstate`` works in the
+ `active mode with the HWP feature enabled <Active Mode With HWP_>`_ in
+ the processor. If set (equal to 1), it causes the minimum P-state limit
+ to be increased dynamically for a short time whenever a task previously
+ waiting on I/O is selected to run on a given logical CPU (the purpose
+ of this mechanism is to improve performance).
+
+ This setting has no effect on logical CPUs whose minimum P-state limit
+ is directly set to the highest non-turbo P-state or above it.
+
.. _status_attr:
``status``
That only is supported in some configurations, though (for example, if
the `HWP feature is enabled in the processor <Active Mode With HWP_>`_,
the operation mode of the driver cannot be changed), and if it is not
- supported in the current configuration, writes to this attribute with
+ supported in the current configuration, writes to this attribute will
fail with an appropriate error.
Interpretation of Policy Attributes
MTRR Handling
-------------
-.. kernel-doc:: arch/x86/kernel/cpu/mtrr/main.c
+.. kernel-doc:: arch/x86/kernel/cpu/mtrr/mtrr.c
:export:
Security Framework
--- /dev/null
+Spreadtrum SC27xx PMIC Vibrator
+
+Required properties:
+- compatible: should be "sprd,sc2731-vibrator".
+- reg: address of vibrator control register.
+
+Example :
+
+ sc2731_pmic: pmic@0 {
+ compatible = "sprd,sc2731";
+ reg = <0>;
+ spi-max-frequency = <26000000>;
+ interrupts = <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-controller;
+ #interrupt-cells = <2>;
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ vibrator@eb4 {
+ compatible = "sprd,sc2731-vibrator";
+ reg = <0xeb4>;
+ };
+ };
--- /dev/null
+Realtek SMI-based Switches
+==========================
+
+The SMI "Simple Management Interface" is a two-wire protocol using
+bit-banged GPIO that while it reuses the MDIO lines MCK and MDIO does
+not use the MDIO protocol. This binding defines how to specify the
+SMI-based Realtek devices.
+
+Required properties:
+
+- compatible: must be exactly one of:
+ "realtek,rtl8366"
+ "realtek,rtl8366rb" (4+1 ports)
+ "realtek,rtl8366s" (4+1 ports)
+ "realtek,rtl8367"
+ "realtek,rtl8367b"
+ "realtek,rtl8368s" (8 port)
+ "realtek,rtl8369"
+ "realtek,rtl8370" (8 port)
+
+Required properties:
+- mdc-gpios: GPIO line for the MDC clock line.
+- mdio-gpios: GPIO line for the MDIO data line.
+- reset-gpios: GPIO line for the reset signal.
+
+Optional properties:
+- realtek,disable-leds: if the LED drivers are not used in the
+ hardware design this will disable them so they are not turned on
+ and wasting power.
+
+Required subnodes:
+
+- interrupt-controller
+
+ This defines an interrupt controller with an IRQ line (typically
+ a GPIO) that will demultiplex and handle the interrupt from the single
+ interrupt line coming out of one of the SMI-based chips. It most
+ importantly provides link up/down interrupts to the PHY blocks inside
+ the ASIC.
+
+Required properties of interrupt-controller:
+
+- interrupt: parent interrupt, see interrupt-controller/interrupts.txt
+- interrupt-controller: see interrupt-controller/interrupts.txt
+- #address-cells: should be <0>
+- #interrupt-cells: should be <1>
+
+- mdio
+
+ This defines the internal MDIO bus of the SMI device, mostly for the
+ purpose of being able to hook the interrupts to the right PHY and
+ the right PHY to the corresponding port.
+
+Required properties of mdio:
+
+- compatible: should be set to "realtek,smi-mdio" for all SMI devices
+
+See net/mdio.txt for additional MDIO bus properties.
+
+See net/dsa/dsa.txt for a list of additional required and optional properties
+and subnodes of DSA switches.
+
+Examples:
+
+switch {
+ compatible = "realtek,rtl8366rb";
+ /* 22 = MDIO (has input reads), 21 = MDC (clock, output only) */
+ mdc-gpios = <&gpio0 21 GPIO_ACTIVE_HIGH>;
+ mdio-gpios = <&gpio0 22 GPIO_ACTIVE_HIGH>;
+ reset-gpios = <&gpio0 14 GPIO_ACTIVE_LOW>;
+
+ switch_intc: interrupt-controller {
+ /* GPIO 15 provides the interrupt */
+ interrupt-parent = <&gpio0>;
+ interrupts = <15 IRQ_TYPE_LEVEL_LOW>;
+ interrupt-controller;
+ #address-cells = <0>;
+ #interrupt-cells = <1>;
+ };
+
+ ports {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ reg = <0>;
+ port@0 {
+ reg = <0>;
+ label = "lan0";
+ phy-handle = <&phy0>;
+ };
+ port@1 {
+ reg = <1>;
+ label = "lan1";
+ phy-handle = <&phy1>;
+ };
+ port@2 {
+ reg = <2>;
+ label = "lan2";
+ phy-handle = <&phy2>;
+ };
+ port@3 {
+ reg = <3>;
+ label = "lan3";
+ phy-handle = <&phy3>;
+ };
+ port@4 {
+ reg = <4>;
+ label = "wan";
+ phy-handle = <&phy4>;
+ };
+ port@5 {
+ reg = <5>;
+ label = "cpu";
+ ethernet = <&gmac0>;
+ phy-mode = "rgmii";
+ fixed-link {
+ speed = <1000>;
+ full-duplex;
+ };
+ };
+ };
+
+ mdio {
+ compatible = "realtek,smi-mdio", "dsa-mdio";
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ phy0: phy@0 {
+ reg = <0>;
+ interrupt-parent = <&switch_intc>;
+ interrupts = <0>;
+ };
+ phy1: phy@1 {
+ reg = <1>;
+ interrupt-parent = <&switch_intc>;
+ interrupts = <1>;
+ };
+ phy2: phy@2 {
+ reg = <2>;
+ interrupt-parent = <&switch_intc>;
+ interrupts = <2>;
+ };
+ phy3: phy@3 {
+ reg = <3>;
+ interrupt-parent = <&switch_intc>;
+ interrupts = <3>;
+ };
+ phy4: phy@4 {
+ reg = <4>;
+ interrupt-parent = <&switch_intc>;
+ interrupts = <12>;
+ };
+ };
+};
--- /dev/null
+Vitesse VSC73xx Switches
+========================
+
+This defines device tree bindings for the Vitesse VSC73xx switch chips.
+The Vitesse company has been acquired by Microsemi and Microsemi in turn
+acquired by Microchip but retains this vendor branding.
+
+The currently supported switch chips are:
+Vitesse VSC7385 SparX-G5 5+1-port Integrated Gigabit Ethernet Switch
+Vitesse VSC7388 SparX-G8 8-port Integrated Gigabit Ethernet Switch
+Vitesse VSC7395 SparX-G5e 5+1-port Integrated Gigabit Ethernet Switch
+Vitesse VSC7398 SparX-G8e 8-port Integrated Gigabit Ethernet Switch
+
+The device tree node is an SPI device so it must reside inside a SPI bus
+device tree node, see spi/spi-bus.txt
+
+Required properties:
+
+- compatible: must be exactly one of:
+ "vitesse,vsc7385"
+ "vitesse,vsc7388"
+ "vitesse,vsc7395"
+ "vitesse,vsc7398"
+- gpio-controller: indicates that this switch is also a GPIO controller,
+ see gpio/gpio.txt
+- #gpio-cells: this must be set to <2> and indicates that we are a twocell
+ GPIO controller, see gpio/gpio.txt
+
+Optional properties:
+
+- reset-gpios: a handle to a GPIO line that can issue reset of the chip.
+ It should be tagged as active low.
+
+Required subnodes:
+
+See net/dsa/dsa.txt for a list of additional required and optional properties
+and subnodes of DSA switches.
+
+Examples:
+
+switch@0 {
+ compatible = "vitesse,vsc7395";
+ reg = <0>;
+ /* Specified for 2.5 MHz or below */
+ spi-max-frequency = <2500000>;
+ gpio-controller;
+ #gpio-cells = <2>;
+
+ ports {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ port@0 {
+ reg = <0>;
+ label = "lan1";
+ };
+ port@1 {
+ reg = <1>;
+ label = "lan2";
+ };
+ port@2 {
+ reg = <2>;
+ label = "lan3";
+ };
+ port@3 {
+ reg = <3>;
+ label = "lan4";
+ };
+ vsc: port@6 {
+ reg = <6>;
+ label = "cpu";
+ ethernet = <&gmac1>;
+ phy-mode = "rgmii";
+ fixed-link {
+ speed = <1000>;
+ full-duplex;
+ pause;
+ };
+ };
+ };
+};
============================================================================
FMan IEEE 1588 Node
-DESCRIPTION
-
-The FMan interface to support IEEE 1588
-
-
-PROPERTIES
-
-- compatible
- Usage: required
- Value type: <stringlist>
- Definition: A standard property.
- Must include "fsl,fman-ptp-timer".
-
-- reg
- Usage: required
- Value type: <prop-encoded-array>
- Definition: A standard property.
-
-EXAMPLE
-
-ptp-timer@fe000 {
- compatible = "fsl,fman-ptp-timer";
- reg = <0xfe000 0x1000>;
-};
+Refer to Documentation/devicetree/bindings/ptp/ptp-qoriq.txt
=============================================================================
FMan MDIO Node
Required properties:
- compatible: should be "rockchip,<name>-gamc"
+ "rockchip,px30-gmac": found on PX30 SoCs
"rockchip,rk3128-gmac": found on RK312x SoCs
"rockchip,rk3228-gmac": found on RK322x SoCs
"rockchip,rk3288-gmac": found on RK3288 SoCs
General Properties:
- - compatible Should be "fsl,etsec-ptp"
+ - compatible Should be "fsl,etsec-ptp" for eTSEC
+ Should be "fsl,fman-ptp-timer" for DPAA FMan
- reg Offset and length of the register set for the device
- interrupts There should be at least two interrupts. Some devices
have as many as four PTP related interrupts.
value, which will be directly written in those bits, that is why,
according to reference manual, the next clock sources can be used:
+ For eTSEC,
<0> - external high precision timer reference clock (TSEC_TMR_CLK
input is used for this purpose);
<1> - eTSEC system clock;
<2> - eTSEC1 transmit clock;
<3> - RTC clock input.
- When this attribute is not used, eTSEC system clock will serve as
- IEEE 1588 timer reference clock.
+ For DPAA FMan,
+ <0> - external high precision timer reference clock (TMR_1588_CLK)
+ <1> - MAC system clock (1/2 FMan clock)
+ <2> - reserved
+ <3> - RTC clock oscillator
+
+ When this attribute is not used, the IEEE 1588 timer reference clock
+ will use the eTSEC system clock (for Gianfar) or the MAC system
+ clock (for DPAA).
Example:
variscite Variscite Ltd.
via VIA Technologies, Inc.
virtio Virtual I/O Device Specification, developed by the OASIS consortium
+vitesse Vitesse Semiconductor Corporation
vivante Vivante Corporation
vocore VoCore Studio
voipac Voipac Technologies s.r.o.
Device Drivers DMA Management
-----------------------------
-.. kernel-doc:: drivers/base/dma-coherent.c
+.. kernel-doc:: kernel/dma/coherent.c
:export:
-.. kernel-doc:: drivers/base/dma-mapping.c
+.. kernel-doc:: kernel/dma/mapping.c
:export:
Device drivers PnP support
int (*iterate) (struct file *, struct dir_context *);
int (*iterate_shared) (struct file *, struct dir_context *);
__poll_t (*poll) (struct file *, struct poll_table_struct *);
- struct wait_queue_head * (*get_poll_head)(struct file *, __poll_t);
- __poll_t (*poll_mask) (struct file *, __poll_t);
long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
int (*mmap) (struct file *, struct vm_area_struct *);
};
locking rules:
- All except for ->poll_mask may block.
+ All may block.
->llseek() locking has moved from llseek to the individual llseek
implementations. If your fs is not using generic_file_llseek, you
the lease within the individual filesystem to record the result of the
operation
-->poll_mask can be called with or without the waitqueue lock for the waitqueue
-returned from ->get_poll_head.
-
--------------------------- dquot_operations -------------------------------
prototypes:
int (*write_dquot) (struct dquot *);
Scott Lovenberg
Pavel Shilovsky (for great work adding SMB2 support, and various SMB3 features)
Aurelien Aptel (for DFS SMB3 work and some key bug fixes)
-Ronnie Sahlberg (for SMB3 xattr work and bug fixes)
+Ronnie Sahlberg (for SMB3 xattr work, bug fixes, and lots of great work on compounding)
Shirish Pargaonkar (for many ACL patches over the years)
Sachin Prabhu (many bug fixes, including for reconnect, copy offload and security)
+Paulo Alcantara
+Long Li (some great work on RDMA, SMB Direct)
Test case and Bug Report contributors
bugs in error paths. Valuable suggestions also have come from Al Viro
and Dave Miller.
-And thanks to the IBM LTC and Power test teams and SuSE testers for
-finding multiple bugs during excellent stress test runs.
+And thanks to the IBM LTC and Power test teams and SuSE and Citrix and RedHat testers for finding multiple bugs during excellent stress test runs.
+See https://wiki.samba.org/index.php/LinuxCIFSKernel for
+more current information.
+
Version 1.62
------------
Add sockopt=TCP_NODELAY mount option. EA (xattr) routines hardened
a) SMB3 (and SMB3.02) missing optional features:
- multichannel (started), integration with RDMA
- - directory leases (improved metadata caching)
- - T10 copy offload (copy chunk, and "Duplicate Extents" ioctl
+ - directory leases (improved metadata caching), started (root dir only)
+ - T10 copy offload ie "ODX" (copy chunk, and "Duplicate Extents" ioctl
currently the only two server side copy mechanisms supported)
b) improved sparse file support
c) Directory entry caching relies on a 1 second timer, rather than
-using Directory Leases
+using Directory Leases, currently only the root file handle is cached longer
d) quota support (needs minor kernel change since quota calls
to make it to network filesystems or deviceless filesystems)
exists. Also better integration with winbind for resolving SID owners
k) Add tools to take advantage of more smb3 specific ioctls and features
+(passthrough ioctl/fsctl for sending various SMB3 fsctls to the server
+is in progress)
l) encrypted file support
secure) CIFS dialect can be disabled in environments that don't need it
and simplify the code.
-u) Finish up SMB3.1.1 dialect support
-
-v) POSIX Extensions for SMB3.1.1
+v) POSIX Extensions for SMB3.1.1 (started, create and mkdir support added
+so far).
KNOWN BUGS
====================================
1) check out max path names and max path name components against various server
types. Try nested symlinks (8 deep). Return max path name in stat -f information
-2) Improve xfstest's cifs enablement and adapt xfstests where needed to test
-cifs better
+2) Improve xfstest's cifs/smb3 enablement and adapt xfstests where needed to test
+cifs/smb3 better
3) Additional performance testing and optimization using iozone and similar -
there are some easy changes that can be done to parallelize sequential writes,
ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
int (*iterate) (struct file *, struct dir_context *);
__poll_t (*poll) (struct file *, struct poll_table_struct *);
- struct wait_queue_head * (*get_poll_head)(struct file *, __poll_t);
- __poll_t (*poll_mask) (struct file *, __poll_t);
long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
int (*mmap) (struct file *, struct vm_area_struct *);
activity on this file and (optionally) go to sleep until there
is activity. Called by the select(2) and poll(2) system calls
- get_poll_head: Returns the struct wait_queue_head that callers can
- wait on. Callers need to check the returned events using ->poll_mask
- once woken. Can return NULL to indicate polling is not supported,
- or any error code using the ERR_PTR convention to indicate that a
- grave error occured and ->poll_mask shall not be called.
-
- poll_mask: return the mask of EPOLL* values describing the file descriptor
- state. Called either before going to sleep on the waitqueue returned by
- get_poll_head, or after it has been woken. If ->get_poll_head and
- ->poll_mask are implemented ->poll does not need to be implement.
-
unlocked_ioctl: called by the ioctl(2) system call.
compat_ioctl: called by the ioctl(2) system call when 32 bit system calls
to use it. It should be placed at the top of the configuration, before any
other statement.
+'#' Kconfig source file comment:
+
+An unquoted '#' character anywhere in a source file line indicates
+the beginning of a source file comment. The remainder of that line
+is a comment.
+
Kconfig hints
-------------
+==============================================================
Linux* Base Driver for the Intel(R) PRO/100 Family of Adapters
==============================================================
Additional Configurations
=========================
- Configuring the Driver on Different Distributions
- -------------------------------------------------
+Configuring the Driver on Different Distributions
+-------------------------------------------------
- Configuring a network driver to load properly when the system is started is
- distribution dependent. Typically, the configuration process involves adding
- an alias line to /etc/modprobe.d/*.conf as well as editing other system
- startup scripts and/or configuration files. Many popular Linux
- distributions ship with tools to make these changes for you. To learn the
- proper way to configure a network device for your system, refer to your
- distribution documentation. If during this process you are asked for the
- driver or module name, the name for the Linux Base Driver for the Intel
- PRO/100 Family of Adapters is e100.
+Configuring a network driver to load properly when the system is started
+is distribution dependent. Typically, the configuration process involves
+adding an alias line to /etc/modprobe.d/*.conf as well as editing other
+system startup scripts and/or configuration files. Many popular Linux
+distributions ship with tools to make these changes for you. To learn
+the proper way to configure a network device for your system, refer to
+your distribution documentation. If during this process you are asked
+for the driver or module name, the name for the Linux Base Driver for
+the Intel PRO/100 Family of Adapters is e100.
- As an example, if you install the e100 driver for two PRO/100 adapters
- (eth0 and eth1), add the following to a configuration file in /etc/modprobe.d/
+As an example, if you install the e100 driver for two PRO/100 adapters
+(eth0 and eth1), add the following to a configuration file in
+/etc/modprobe.d/::
alias eth0 e100
alias eth1 e100
- Viewing Link Messages
- ---------------------
- In order to see link messages and other Intel driver information on your
- console, you must set the dmesg level up to six. This can be done by
- entering the following on the command line before loading the e100 driver::
-
- dmesg -n 6
+Viewing Link Messages
+---------------------
- If you wish to see all messages issued by the driver, including debug
- messages, set the dmesg level to eight.
+In order to see link messages and other Intel driver information on your
+console, you must set the dmesg level up to six. This can be done by
+entering the following on the command line before loading the e100
+driver::
- NOTE: This setting is not saved across reboots.
+ dmesg -n 6
+If you wish to see all messages issued by the driver, including debug
+messages, set the dmesg level to eight.
- ethtool
- -------
+NOTE: This setting is not saved across reboots.
- The driver utilizes the ethtool interface for driver configuration and
- diagnostics, as well as displaying statistical information. The ethtool
- version 1.6 or later is required for this functionality.
+ethtool
+-------
- The latest release of ethtool can be found from
- https://www.kernel.org/pub/software/network/ethtool/
+The driver utilizes the ethtool interface for driver configuration and
+diagnostics, as well as displaying statistical information. The ethtool
+version 1.6 or later is required for this functionality.
- Enabling Wake on LAN* (WoL)
- ---------------------------
- WoL is provided through the ethtool* utility. For instructions on enabling
- WoL with ethtool, refer to the ethtool man page.
+The latest release of ethtool can be found from
+https://www.kernel.org/pub/software/network/ethtool/
- WoL will be enabled on the system during the next shut down or reboot. For
- this driver version, in order to enable WoL, the e100 driver must be
- loaded when shutting down or rebooting the system.
+Enabling Wake on LAN* (WoL)
+---------------------------
+WoL is provided through the ethtool* utility. For instructions on
+enabling WoL with ethtool, refer to the ethtool man page. WoL will be
+enabled on the system during the next shut down or reboot. For this
+driver version, in order to enable WoL, the e100 driver must be loaded
+when shutting down or rebooting the system.
- NAPI
- ----
+NAPI
+----
- NAPI (Rx polling mode) is supported in the e100 driver.
+NAPI (Rx polling mode) is supported in the e100 driver.
- See https://wiki.linuxfoundation.org/networking/napi for more information
- on NAPI.
+See https://wiki.linuxfoundation.org/networking/napi for more
+information on NAPI.
- Multiple Interfaces on Same Ethernet Broadcast Network
- ------------------------------------------------------
+Multiple Interfaces on Same Ethernet Broadcast Network
+------------------------------------------------------
- Due to the default ARP behavior on Linux, it is not possible to have
- one system on two IP networks in the same Ethernet broadcast domain
- (non-partitioned switch) behave as expected. All Ethernet interfaces
- will respond to IP traffic for any IP address assigned to the system.
- This results in unbalanced receive traffic.
+Due to the default ARP behavior on Linux, it is not possible to have one
+system on two IP networks in the same Ethernet broadcast domain
+(non-partitioned switch) behave as expected. All Ethernet interfaces
+will respond to IP traffic for any IP address assigned to the system.
+This results in unbalanced receive traffic.
- If you have multiple interfaces in a server, either turn on ARP
- filtering by
+If you have multiple interfaces in a server, either turn on ARP
+filtering by
- (1) entering:: echo 1 > /proc/sys/net/ipv4/conf/all/arp_filter
- (this only works if your kernel's version is higher than 2.4.5), or
+(1) entering:: echo 1 > /proc/sys/net/ipv4/conf/all/arp_filter
+ (this only works if your kernel's version is higher than 2.4.5), or
- (2) installing the interfaces in separate broadcast domains (either
- in different switches or in a switch partitioned to VLANs).
+(2) installing the interfaces in separate broadcast domains (either
+ in different switches or in a switch partitioned to VLANs).
Support
+===========================================================
Linux* Base Driver for Intel(R) Ethernet Network Connection
===========================================================
Additional Configurations
=========================
- Jumbo Frames
- ------------
- Jumbo Frames support is enabled by changing the MTU to a value larger than
- the default of 1500. Use the ifconfig command to increase the MTU size.
- For example::
+Jumbo Frames
+------------
+Jumbo Frames support is enabled by changing the MTU to a value larger
+than the default of 1500. Use the ifconfig command to increase the MTU
+size. For example::
ifconfig eth<x> mtu 9000 up
- This setting is not saved across reboots. It can be made permanent if
- you add::
+This setting is not saved across reboots. It can be made permanent if
+you add::
MTU=9000
- to the file /etc/sysconfig/network-scripts/ifcfg-eth<x>. This example
- applies to the Red Hat distributions; other distributions may store this
- setting in a different location.
+to the file /etc/sysconfig/network-scripts/ifcfg-eth<x>. This example
+applies to the Red Hat distributions; other distributions may store this
+setting in a different location.
+
+Notes: Degradation in throughput performance may be observed in some
+Jumbo frames environments. If this is observed, increasing the
+application's socket buffer size and/or increasing the
+/proc/sys/net/ipv4/tcp_*mem entry values may help. See the specific
+application manual and /usr/src/linux*/Documentation/
+networking/ip-sysctl.txt for more details.
- Notes:
- Degradation in throughput performance may be observed in some Jumbo frames
- environments. If this is observed, increasing the application's socket buffer
- size and/or increasing the /proc/sys/net/ipv4/tcp_*mem entry values may help.
- See the specific application manual and /usr/src/linux*/Documentation/
- networking/ip-sysctl.txt for more details.
+- The maximum MTU setting for Jumbo Frames is 16110. This value
+ coincides with the maximum Jumbo Frames size of 16128.
- - The maximum MTU setting for Jumbo Frames is 16110. This value coincides
- with the maximum Jumbo Frames size of 16128.
+- Using Jumbo frames at 10 or 100 Mbps is not supported and may result
+ in poor performance or loss of link.
- - Using Jumbo frames at 10 or 100 Mbps is not supported and may result in
- poor performance or loss of link.
+- Adapters based on the Intel(R) 82542 and 82573V/E controller do not
+ support Jumbo Frames. These correspond to the following product names:
+ Intel(R) PRO/1000 Gigabit Server Adapter Intel(R) PRO/1000 PM Network
+ Connection
- - Adapters based on the Intel(R) 82542 and 82573V/E controller do not
- support Jumbo Frames. These correspond to the following product names:
- Intel(R) PRO/1000 Gigabit Server Adapter
- Intel(R) PRO/1000 PM Network Connection
+ethtool
+-------
+The driver utilizes the ethtool interface for driver configuration and
+diagnostics, as well as displaying statistical information. The ethtool
+version 1.6 or later is required for this functionality.
- ethtool
- -------
- The driver utilizes the ethtool interface for driver configuration and
- diagnostics, as well as displaying statistical information. The ethtool
- version 1.6 or later is required for this functionality.
+The latest release of ethtool can be found from
+https://www.kernel.org/pub/software/network/ethtool/
- The latest release of ethtool can be found from
- https://www.kernel.org/pub/software/network/ethtool/
+Enabling Wake on LAN* (WoL)
+---------------------------
+WoL is configured through the ethtool* utility.
- Enabling Wake on LAN* (WoL)
- ---------------------------
- WoL is configured through the ethtool* utility.
+WoL will be enabled on the system during the next shut down or reboot.
+For this driver version, in order to enable WoL, the e1000 driver must be
+loaded when shutting down or rebooting the system.
- WoL will be enabled on the system during the next shut down or reboot.
- For this driver version, in order to enable WoL, the e1000 driver must be
- loaded when shutting down or rebooting the system.
Support
=======
kapi
z8530book
msg_zerocopy
+ failover
+ net_failover
.. only:: subproject
Controls TCP Small Queue limit per tcp socket.
TCP bulk sender tends to increase packets in flight until it
gets losses notifications. With SNDBUF autotuning, this can
- result in a large amount of packets queued in qdisc/device
- on the local machine, hurting latency of other flows, for
- typical pfifo_fast qdiscs.
- tcp_limit_output_bytes limits the number of bytes on qdisc
- or device to reduce artificial RTT/cwnd and reduce bufferbloat.
+ result in a large amount of packets queued on the local machine
+ (e.g.: qdiscs, CPU backlog, or device) hurting latency of other
+ flows, for typical pfifo_fast qdiscs. tcp_limit_output_bytes
+ limits the number of bytes on qdisc or device to reduce artificial
+ RTT/cwnd and reduce bufferbloat.
Default: 262144
tcp_challenge_ack_limit - INTEGER
By default the stable secret is unset.
+addr_gen_mode - INTEGER
+ Defines how link-local and autoconf addresses are generated.
+
+ 0: generate address based on EUI64 (default)
+ 1: do no generate a link-local address, use EUI64 for addresses generated
+ from autoconf
+ 2: generate stable privacy addresses, using the secret from
+ stable_secret (RFC7217)
+ 3: generate stable privacy addresses, using a random secret if unset
+
drop_unicast_in_l2_multicast - BOOLEAN
Drop any unicast IPv6 packets that are received in link-layer
multicast (or broadcast) frames.
virtio-net and VF interfaces.
Here is an example XML snippet that shows such configuration.
-
- <interface type='network'>
- <mac address='52:54:00:00:12:53'/>
- <source network='enp66s0f0_br'/>
- <target dev='tap01'/>
- <model type='virtio'/>
- <driver name='vhost' queues='4'/>
- <link state='down'/>
- <address type='pci' domain='0x0000' bus='0x00' slot='0x0a' function='0x0'/>
- </interface>
- <interface type='hostdev' managed='yes'>
- <mac address='52:54:00:00:12:53'/>
- <source>
- <address type='pci' domain='0x0000' bus='0x42' slot='0x02' function='0x5'/>
- </source>
- <address type='pci' domain='0x0000' bus='0x00' slot='0x0b' function='0x0'/>
- </interface>
+::
+
+ <interface type='network'>
+ <mac address='52:54:00:00:12:53'/>
+ <source network='enp66s0f0_br'/>
+ <target dev='tap01'/>
+ <model type='virtio'/>
+ <driver name='vhost' queues='4'/>
+ <link state='down'/>
+ <address type='pci' domain='0x0000' bus='0x00' slot='0x0a' function='0x0'/>
+ </interface>
+ <interface type='hostdev' managed='yes'>
+ <mac address='52:54:00:00:12:53'/>
+ <source>
+ <address type='pci' domain='0x0000' bus='0x42' slot='0x02' function='0x5'/>
+ </source>
+ <address type='pci' domain='0x0000' bus='0x00' slot='0x0b' function='0x0'/>
+ </interface>
Booting a VM with the above configuration will result in the following 3
netdevs created in the VM.
-
-4: ens10: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc noqueue state UP group default qlen 1000
- link/ether 52:54:00:00:12:53 brd ff:ff:ff:ff:ff:ff
- inet 192.168.12.53/24 brd 192.168.12.255 scope global dynamic ens10
- valid_lft 42482sec preferred_lft 42482sec
- inet6 fe80::97d8:db2:8c10:b6d6/64 scope link
- valid_lft forever preferred_lft forever
-5: ens10nsby: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc fq_codel master ens10 state UP group default qlen 1000
- link/ether 52:54:00:00:12:53 brd ff:ff:ff:ff:ff:ff
-7: ens11: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc mq master ens10 state UP group default qlen 1000
- link/ether 52:54:00:00:12:53 brd ff:ff:ff:ff:ff:ff
+::
+
+ 4: ens10: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc noqueue state UP group default qlen 1000
+ link/ether 52:54:00:00:12:53 brd ff:ff:ff:ff:ff:ff
+ inet 192.168.12.53/24 brd 192.168.12.255 scope global dynamic ens10
+ valid_lft 42482sec preferred_lft 42482sec
+ inet6 fe80::97d8:db2:8c10:b6d6/64 scope link
+ valid_lft forever preferred_lft forever
+ 5: ens10nsby: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc fq_codel master ens10 state UP group default qlen 1000
+ link/ether 52:54:00:00:12:53 brd ff:ff:ff:ff:ff:ff
+ 7: ens11: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc mq master ens10 state UP group default qlen 1000
+ link/ether 52:54:00:00:12:53 brd ff:ff:ff:ff:ff:ff
ens10 is the 'failover' master netdev, ens10nsby and ens11 are the slave
'standby' and 'primary' netdevs respectively.
Here is a sample script that shows the steps to initiate live migration on
the source hypervisor.
+::
-# cat vf_xml
-<interface type='hostdev' managed='yes'>
- <mac address='52:54:00:00:12:53'/>
- <source>
- <address type='pci' domain='0x0000' bus='0x42' slot='0x02' function='0x5'/>
- </source>
- <address type='pci' domain='0x0000' bus='0x00' slot='0x0b' function='0x0'/>
-</interface>
+ # cat vf_xml
+ <interface type='hostdev' managed='yes'>
+ <mac address='52:54:00:00:12:53'/>
+ <source>
+ <address type='pci' domain='0x0000' bus='0x42' slot='0x02' function='0x5'/>
+ </source>
+ <address type='pci' domain='0x0000' bus='0x00' slot='0x0b' function='0x0'/>
+ </interface>
-# Source Hypervisor
-#!/bin/bash
+ # Source Hypervisor
+ #!/bin/bash
-DOMAIN=fedora27-tap01
-PF=enp66s0f0
-VF_NUM=5
-TAP_IF=tap01
-VF_XML=
+ DOMAIN=fedora27-tap01
+ PF=enp66s0f0
+ VF_NUM=5
+ TAP_IF=tap01
+ VF_XML=
-MAC=52:54:00:00:12:53
-ZERO_MAC=00:00:00:00:00:00
+ MAC=52:54:00:00:12:53
+ ZERO_MAC=00:00:00:00:00:00
-virsh domif-setlink $DOMAIN $TAP_IF up
-bridge fdb del $MAC dev $PF master
-virsh detach-device $DOMAIN $VF_XML
-ip link set $PF vf $VF_NUM mac $ZERO_MAC
+ virsh domif-setlink $DOMAIN $TAP_IF up
+ bridge fdb del $MAC dev $PF master
+ virsh detach-device $DOMAIN $VF_XML
+ ip link set $PF vf $VF_NUM mac $ZERO_MAC
-virsh migrate --live $DOMAIN qemu+ssh://$REMOTE_HOST/system
+ virsh migrate --live $DOMAIN qemu+ssh://$REMOTE_HOST/system
-# Destination Hypervisor
-#!/bin/bash
+ # Destination Hypervisor
+ #!/bin/bash
-virsh attach-device $DOMAIN $VF_XML
-virsh domif-setlink $DOMAIN $TAP_IF down
+ virsh attach-device $DOMAIN $VF_XML
+ virsh domif-setlink $DOMAIN $TAP_IF down
Transmit Packet Steering is a mechanism for intelligently selecting
which transmit queue to use when transmitting a packet on a multi-queue
-device. To accomplish this, a mapping from CPU to hardware queue(s) is
-recorded. The goal of this mapping is usually to assign queues
+device. This can be accomplished by recording two kinds of maps, either
+a mapping of CPU to hardware queue(s) or a mapping of receive queue(s)
+to hardware transmit queue(s).
+
+1. XPS using CPUs map
+
+The goal of this mapping is usually to assign queues
exclusively to a subset of CPUs, where the transmit completions for
these queues are processed on a CPU within this set. This choice
provides two benefits. First, contention on the device queue lock is
reduced, in particular for data cache lines that hold the sk_buff
structures.
-XPS is configured per transmit queue by setting a bitmap of CPUs that
-may use that queue to transmit. The reverse mapping, from CPUs to
-transmit queues, is computed and maintained for each network device.
-When transmitting the first packet in a flow, the function
-get_xps_queue() is called to select a queue. This function uses the ID
-of the running CPU as a key into the CPU-to-queue lookup table. If the
+2. XPS using receive queues map
+
+This mapping is used to pick transmit queue based on the receive
+queue(s) map configuration set by the administrator. A set of receive
+queues can be mapped to a set of transmit queues (many:many), although
+the common use case is a 1:1 mapping. This will enable sending packets
+on the same queue associations for transmit and receive. This is useful for
+busy polling multi-threaded workloads where there are challenges in
+associating a given CPU to a given application thread. The application
+threads are not pinned to CPUs and each thread handles packets
+received on a single queue. The receive queue number is cached in the
+socket for the connection. In this model, sending the packets on the same
+transmit queue corresponding to the associated receive queue has benefits
+in keeping the CPU overhead low. Transmit completion work is locked into
+the same queue-association that a given application is polling on. This
+avoids the overhead of triggering an interrupt on another CPU. When the
+application cleans up the packets during the busy poll, transmit completion
+may be processed along with it in the same thread context and so result in
+reduced latency.
+
+XPS is configured per transmit queue by setting a bitmap of
+CPUs/receive-queues that may use that queue to transmit. The reverse
+mapping, from CPUs to transmit queues or from receive-queues to transmit
+queues, is computed and maintained for each network device. When
+transmitting the first packet in a flow, the function get_xps_queue() is
+called to select a queue. This function uses the ID of the receive queue
+for the socket connection for a match in the receive queue-to-transmit queue
+lookup table. Alternatively, this function can also use the ID of the
+running CPU as a key into the CPU-to-queue lookup table. If the
ID matches a single queue, that is used for transmission. If multiple
queues match, one is selected by using the flow hash to compute an index
-into the set.
+into the set. When selecting the transmit queue based on receive queue(s)
+map, the transmit device is not validated against the receive device as it
+requires expensive lookup operation in the datapath.
The queue chosen for transmitting a particular flow is saved in the
corresponding socket structure for the flow (e.g. a TCP connection).
XPS is only available if the kconfig symbol CONFIG_XPS is enabled (on by
default for SMP). The functionality remains disabled until explicitly
-configured. To enable XPS, the bitmap of CPUs that may use a transmit
-queue is configured using the sysfs file entry:
+configured. To enable XPS, the bitmap of CPUs/receive-queues that may
+use a transmit queue is configured using the sysfs file entry:
+For selection based on CPUs map:
/sys/class/net/<dev>/queues/tx-<n>/xps_cpus
+For selection based on receive-queues map:
+/sys/class/net/<dev>/queues/tx-<n>/xps_rxqs
+
== Suggested Configuration
For a network device with a single transmission queue, XPS configuration
with the CPU that processes transmit completions for that queue
(transmit interrupts).
+For transmit queue selection based on receive queue(s), XPS has to be
+explicitly configured mapping receive-queue(s) to transmit queue(s). If the
+user configuration for receive-queue map does not apply, then the transmit
+queue is selected based on the CPUs map.
+
Per TX Queue rate limitation:
=============================
Temporarily pause a stream parser. Message parsing is suspended
and no new messages are delivered to the upper layer.
-void strp_pause(struct strparser *strp)
+void strp_unpause(struct strparser *strp)
Unpause a paused stream parser.
Introduction
============
-The rfkill subsystem provides a generic interface to disabling any radio
+The rfkill subsystem provides a generic interface for disabling any radio
transmitter in the system. When a transmitter is blocked, it shall not
radiate any power.
* the rfkill drivers.
The rfkill core provides API for kernel drivers to register their radio
-transmitter with the kernel, methods for turning it on and off and, letting
+transmitter with the kernel, methods for turning it on and off, and letting
the system know about hardware-disabled states that may be implemented on
the device.
section below.
When the device is hard-blocked (either by a call to rfkill_set_hw_state()
-or from query_hw_block) set_block() will be invoked for additional software
+or from query_hw_block), set_block() will be invoked for additional software
block, but drivers can ignore the method call since they can use the return
value of the function rfkill_set_hw_state() to sync the software state
instead of keeping track of calls to set_block(). In fact, drivers should
Kernel API
==========
-
Drivers for radio transmitters normally implement an rfkill driver.
Platform drivers might implement input devices if the rfkill button is just
For some platforms, it is possible that the hardware state changes during
suspend/hibernation, in which case it will be necessary to update the rfkill
-core with the current state is at resume time.
+core with the current state at resume time.
To create an rfkill driver, driver's Kconfig needs to have::
depends on RFKILL || !RFKILL
to ensure the driver cannot be built-in when rfkill is modular. The !RFKILL
-case allows the driver to be built when rfkill is not configured, which
+case allows the driver to be built when rfkill is not configured, in which
case all rfkill API can still be used but will be provided by static inlines
which compile to almost nothing.
assign the poll_hw_block() callback (then the rfkill core will poll the
device). Don't do this unless you cannot get the event in any other way.
-RFKill provides per-switch LED triggers, which can be used to drive LEDs
+rfkill provides per-switch LED triggers, which can be used to drive LEDs
according to the switch state (LED_FULL when blocked, LED_OFF otherwise).
hotplugged devices.
After an application opens /dev/rfkill, it can read the current state of all
-devices. Changes can be either obtained by either polling the descriptor for
+devices. Changes can be obtained by either polling the descriptor for
hotplug or state change events or by listening for uevents emitted by the
rfkill core framework.
RFKILL_STATE
RFKILL_TYPE
-The contents of these variables corresponds to the "name", "state" and
+The content of these variables corresponds to the "name", "state" and
"type" sysfs files explained above.
-
For further details consult Documentation/ABI/stable/sysfs-class-rfkill.
associated event field will be saved in a variable but won't be summed
as a value:
- # echo 'hist:keys=next_pid:ts1=common_timestamp ... >> event/trigger
+ # echo 'hist:keys=next_pid:ts1=common_timestamp ...' >> event/trigger
Multiple variables can be assigned at the same time. The below would
result in both ts0 and b being created as variables, with both
common_timestamp and field1 additionally being summed as values:
- # echo 'hist:keys=pid:vals=$ts0,$b:ts0=common_timestamp,b=field1 ... >> \
+ # echo 'hist:keys=pid:vals=$ts0,$b:ts0=common_timestamp,b=field1 ...' >> \
event/trigger
Note that variable assignments can appear either preceding or
following their use. The command below behaves identically to the
command above:
- # echo 'hist:keys=pid:ts0=common_timestamp,b=field1:vals=$ts0,$b ... >> \
+ # echo 'hist:keys=pid:ts0=common_timestamp,b=field1:vals=$ts0,$b ...' >> \
event/trigger
Any number of variables not bound to a 'vals=' prefix can also be
assigned by simply separating them with colons. Below is the same
thing but without the values being summed in the histogram:
- # echo 'hist:keys=pid:ts0=common_timestamp:b=field1 ... >> event/trigger
+ # echo 'hist:keys=pid:ts0=common_timestamp:b=field1 ...' >> event/trigger
Variables set as above can be referenced and used in expressions on
another event.
For example, here's how a latency can be calculated:
- # echo 'hist:keys=pid,prio:ts0=common_timestamp ... >> event1/trigger
- # echo 'hist:keys=next_pid:wakeup_lat=common_timestamp-$ts0 ... >> event2/trigger
+ # echo 'hist:keys=pid,prio:ts0=common_timestamp ...' >> event1/trigger
+ # echo 'hist:keys=next_pid:wakeup_lat=common_timestamp-$ts0 ...' >> event2/trigger
In the first line above, the event's timetamp is saved into the
variable ts0. In the next line, ts0 is subtracted from the second
makes use of the wakeup_lat variable to compute a combined latency
using the same key and variable from yet another event:
- # echo 'hist:key=pid:wakeupswitch_lat=$wakeup_lat+$switchtime_lat ... >> event3/trigger
+ # echo 'hist:key=pid:wakeupswitch_lat=$wakeup_lat+$switchtime_lat ...' >> event3/trigger
2.2.2 Synthetic Events
----------------------
At this point, there isn't yet an actual 'wakeup_latency' event
instantiated in the event subsytem - for this to happen, a 'hist
trigger action' needs to be instantiated and bound to actual fields
-and variables defined on other events (see Section 6.3.3 below).
+and variables defined on other events (see Section 2.2.3 below on
+how that is done using hist trigger 'onmatch' action). Once that is
+done, the 'wakeup_latency' synthetic event instance is created.
-Once that is done, an event instance is created, and a histogram can
-be defined using it:
+A histogram can now be defined for the new synthetic event:
# echo 'hist:keys=pid,prio,lat.log2:sort=pid,lat' >> \
/sys/kernel/debug/tracing/events/synthetic/wakeup_latency/trigger
back to that pid, the timestamp difference is calculated. If the
resulting latency, stored in wakeup_lat, exceeds the current
maximum latency, the values specified in the save() fields are
- recoreded:
+ recorded:
# echo 'hist:keys=pid:ts0=common_timestamp.usecs \
if comm=="cyclictest"' >> \
where <config name>.<number> specify the configuration and <function> is
a symlink to a function being removed from the configuration, e.g.:
-$ rm configfs/c.1/ncm.usb0
+$ rm configs/c.1/ncm.usb0
...
...
reset, migration and nested KVM for branch prediction blocking. The stfle
facility 82 should not be provided to the guest without this capability.
-8.14 KVM_CAP_HYPERV_TLBFLUSH
+8.18 KVM_CAP_HYPERV_TLBFLUSH
Architectures: x86
N: bcm586*
N: bcm88312
N: hr2
-F: arch/arm64/boot/dts/broadcom/ns2*
+N: stingray
+F: arch/arm64/boot/dts/broadcom/northstar2/*
+F: arch/arm64/boot/dts/broadcom/stingray/*
F: drivers/clk/bcm/clk-ns*
+F: drivers/clk/bcm/clk-sr*
F: drivers/pinctrl/bcm/pinctrl-ns*
+F: include/dt-bindings/clock/bcm-sr*
BROADCOM KONA GPIO DRIVER
M: Ray Jui <rjui@broadcom.com>
T: git git://git.infradead.org/users/hch/dma-mapping.git
W: http://git.infradead.org/users/hch/dma-mapping.git
S: Supported
-F: lib/dma-debug.c
-F: lib/dma-direct.c
-F: lib/dma-noncoherent.c
-F: lib/dma-virt.c
-F: drivers/base/dma-mapping.c
-F: drivers/base/dma-coherent.c
+F: kernel/dma/
F: include/asm-generic/dma-mapping.h
F: include/linux/dma-direct.h
F: include/linux/dma-mapping.h
F: Documentation/devicetree/bindings/crypto/fsl-sec4.txt
FREESCALE DIU FRAMEBUFFER DRIVER
-M: Timur Tabi <timur@tabi.org>
+M: Timur Tabi <timur@kernel.org>
L: linux-fbdev@vger.kernel.org
S: Maintained
F: drivers/video/fbdev/fsl-diu-fb.*
F: drivers/net/wan/fsl_ucc_hdlc*
FREESCALE QUICC ENGINE UCC UART DRIVER
-M: Timur Tabi <timur@tabi.org>
+M: Timur Tabi <timur@kernel.org>
L: linuxppc-dev@lists.ozlabs.org
S: Maintained
F: drivers/tty/serial/ucc_uart.c
F: include/linux/fs_enet_pd.h
FREESCALE SOC SOUND DRIVERS
-M: Timur Tabi <timur@tabi.org>
+M: Timur Tabi <timur@kernel.org>
M: Nicolin Chen <nicoleotsuka@gmail.com>
M: Xiubo Li <Xiubo.Lee@gmail.com>
R: Fabio Estevam <fabio.estevam@nxp.com>
W: http://www.mellanox.com
Q: http://patchwork.ozlabs.org/project/netdev/list/
F: drivers/net/ethernet/mellanox/mlxsw/
+F: tools/testing/selftests/drivers/net/mlxsw/
MELLANOX FIRMWARE FLASH LIBRARY (mlxfw)
M: mlxsw@mellanox.com
S: Maintained
F: drivers/scsi/NCR_D700.*
+NCSI LIBRARY:
+M: Samuel Mendoza-Jonas <sam@mendozajonas.com>
+S: Maintained
+F: net/ncsi/
+
NCT6775 HARDWARE MONITOR DRIVER
M: Guenter Roeck <linux@roeck-us.net>
L: linux-hwmon@vger.kernel.org
M: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
M: Florian Fainelli <f.fainelli@gmail.com>
S: Maintained
+F: Documentation/devicetree/bindings/net/dsa/
F: net/dsa/
F: include/net/dsa.h
F: include/linux/dsa/
S: Obsolete
F: drivers/net/wireless/intersil/prism54/
+PROC FILESYSTEM
+R: Alexey Dobriyan <adobriyan@gmail.com>
+L: linux-kernel@vger.kernel.org
+L: linux-fsdevel@vger.kernel.org
+S: Maintained
+F: fs/proc/
+F: include/linux/proc_fs.h
+F: tools/testing/selftests/proc/
+
PROC SYSCTL
M: "Luis R. Rodriguez" <mcgrof@kernel.org>
M: Kees Cook <keescook@chromium.org>
F: drivers/cpufreq/qcom-cpufreq-kryo.c
QUALCOMM EMAC GIGABIT ETHERNET DRIVER
-M: Timur Tabi <timur@codeaurora.org>
+M: Timur Tabi <timur@kernel.org>
L: netdev@vger.kernel.org
-S: Supported
+S: Maintained
F: drivers/net/ethernet/qualcomm/emac/
QUALCOMM HEXAGON ARCHITECTURE
F: sound/soc/codecs/rt*
F: include/sound/rt*.h
+REALTEK RTL83xx SMI DSA ROUTER CHIPS
+M: Linus Walleij <linus.walleij@linaro.org>
+S: Maintained
+F: Documentation/devicetree/bindings/net/dsa/realtek-smi.txt
+F: drivers/net/dsa/realtek-smi*
+F: drivers/net/dsa/rtl83*
+
REGISTER MAP ABSTRACTION
M: Mark Brown <broonie@kernel.org>
L: linux-kernel@vger.kernel.org
F: Documentation/rfkill.txt
F: Documentation/ABI/stable/sysfs-class-rfkill
F: net/rfkill/
+F: include/linux/rfkill.h
+F: include/uapi/linux/rfkill.h
RHASHTABLE
M: Thomas Graf <tgraf@suug.ch>
L: netdev@vger.kernel.org
S: Maintained
F: lib/rhashtable.c
+F: lib/test_rhashtable.c
F: include/linux/rhashtable.h
+F: include/linux/rhashtable-types.h
RICOH R5C592 MEMORYSTICK DRIVER
M: Maxim Levitsky <maximlevitsky@gmail.com>
L: iommu@lists.linux-foundation.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/konrad/swiotlb.git
S: Supported
-F: lib/swiotlb.c
+F: kernel/dma/swiotlb.c
F: arch/*/kernel/pci-swiotlb.c
F: include/linux/swiotlb.h
L: linux-kernel@vger.kernel.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/core
S: Maintained
+F: Documentation/devicetree/bindings/x86/
F: Documentation/x86/
F: arch/x86/
+X86 ENTRY CODE
+M: Andy Lutomirski <luto@kernel.org>
+L: linux-kernel@vger.kernel.org
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/asm
+S: Maintained
+F: arch/x86/entry/
+
X86 MCE INFRASTRUCTURE
M: Tony Luck <tony.luck@intel.com>
M: Borislav Petkov <bp@alien8.de>
F: drivers/platform/olpc/
X86 VDSO
-M: Andy Lutomirski <luto@amacapital.net>
+M: Andy Lutomirski <luto@kernel.org>
L: linux-kernel@vger.kernel.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/vdso
S: Maintained
VERSION = 4
PATCHLEVEL = 18
SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc3
NAME = Merciless Moray
# *DOCUMENTATION*
KBUILD_AFLAGS += -DCC_HAVE_ASM_GOTO
endif
-ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/cc-can-link.sh $(CC)), y)
- CC_CAN_LINK := y
- export CC_CAN_LINK
-endif
-
# The expansion should be delayed until arch/$(SRCARCH)/Makefile is included.
# Some architectures define CROSS_COMPILE in arch/$(SRCARCH)/Makefile.
# CC_VERSION_TEXT is referenced from Kconfig (so it needs export),
If you don't know what to do here, say N.
-config HAVE_DEC_LOCK
- bool
- depends on SMP
- default y
-
config NR_CPUS
int "Maximum number of CPUs (2-32)"
range 2 32
#define SO_ZEROCOPY 60
+#define SO_TXTIME 61
+#define SCM_TXTIME SO_TXTIME
+
#endif /* _UAPI_ASM_SOCKET_H */
callback_srm.o srm_puts.o srm_printk.o \
fls.o
-lib-$(CONFIG_SMP) += dec_and_lock.o
-
# The division routines are built from single source, with different defines.
AFLAGS___divqu.o = -DDIV
AFLAGS___remqu.o = -DREM
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0
-/*
- * arch/alpha/lib/dec_and_lock.c
- *
- * ll/sc version of atomic_dec_and_lock()
- *
- */
-
-#include <linux/spinlock.h>
-#include <linux/atomic.h>
-#include <linux/export.h>
-
- asm (".text \n\
- .global _atomic_dec_and_lock \n\
- .ent _atomic_dec_and_lock \n\
- .align 4 \n\
-_atomic_dec_and_lock: \n\
- .prologue 0 \n\
-1: ldl_l $1, 0($16) \n\
- subl $1, 1, $1 \n\
- beq $1, 2f \n\
- stl_c $1, 0($16) \n\
- beq $1, 4f \n\
- mb \n\
- clr $0 \n\
- ret \n\
-2: br $29, 3f \n\
-3: ldgp $29, 0($29) \n\
- br $atomic_dec_and_lock_1..ng \n\
- .subsection 2 \n\
-4: br 1b \n\
- .previous \n\
- .end _atomic_dec_and_lock");
-
-static int __used atomic_dec_and_lock_1(atomic_t *atomic, spinlock_t *lock)
-{
- /* Slow path */
- spin_lock(lock);
- if (atomic_dec_and_test(atomic))
- return 1;
- spin_unlock(lock);
- return 0;
-}
-EXPORT_SYMBOL(_atomic_dec_and_lock);
VESA. If you have PCI, say Y, otherwise N.
config PCI_DOMAINS
- bool
+ bool "Support for multiple PCI domains"
depends on PCI
+ help
+ Enable PCI domains kernel management. Say Y if your machine
+ has a PCI bus hierarchy that requires more than one PCI
+ domain (aka segment) to be correctly managed. Say N otherwise.
+
+ If you don't know what to do here, say N.
config PCI_DOMAINS_GENERIC
def_bool PCI_DOMAINS
3700 5
3900 6
4000 7>;
- cooling-cells = <2>;
+ #cooling-cells = <2>;
};
gpio-leds {
reg = <0x18008000 0x100>;
#address-cells = <1>;
#size-cells = <0>;
- interrupts = <GIC_SPI 85 IRQ_TYPE_NONE>;
+ interrupts = <GIC_SPI 85 IRQ_TYPE_LEVEL_HIGH>;
clock-frequency = <100000>;
status = "disabled";
};
reg = <0x1800b000 0x100>;
#address-cells = <1>;
#size-cells = <0>;
- interrupts = <GIC_SPI 86 IRQ_TYPE_NONE>;
+ interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>;
clock-frequency = <100000>;
status = "disabled";
};
#interrupt-cells = <1>;
interrupt-map-mask = <0 0 0 0>;
- interrupt-map = <0 0 0 0 &gic GIC_SPI 100 IRQ_TYPE_NONE>;
+ interrupt-map = <0 0 0 0 &gic GIC_SPI 100 IRQ_TYPE_LEVEL_HIGH>;
linux,pci-domain = <0>;
compatible = "brcm,iproc-msi";
msi-controller;
interrupt-parent = <&gic>;
- interrupts = <GIC_SPI 96 IRQ_TYPE_NONE>,
- <GIC_SPI 97 IRQ_TYPE_NONE>,
- <GIC_SPI 98 IRQ_TYPE_NONE>,
- <GIC_SPI 99 IRQ_TYPE_NONE>;
+ interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 97 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 98 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 99 IRQ_TYPE_LEVEL_HIGH>;
};
};
#interrupt-cells = <1>;
interrupt-map-mask = <0 0 0 0>;
- interrupt-map = <0 0 0 0 &gic GIC_SPI 106 IRQ_TYPE_NONE>;
+ interrupt-map = <0 0 0 0 &gic GIC_SPI 106 IRQ_TYPE_LEVEL_HIGH>;
linux,pci-domain = <1>;
compatible = "brcm,iproc-msi";
msi-controller;
interrupt-parent = <&gic>;
- interrupts = <GIC_SPI 102 IRQ_TYPE_NONE>,
- <GIC_SPI 103 IRQ_TYPE_NONE>,
- <GIC_SPI 104 IRQ_TYPE_NONE>,
- <GIC_SPI 105 IRQ_TYPE_NONE>;
+ interrupts = <GIC_SPI 102 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 103 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 104 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 105 IRQ_TYPE_LEVEL_HIGH>;
};
};
reg = <0x38000 0x50>;
#address-cells = <1>;
#size-cells = <0>;
- interrupts = <GIC_SPI 95 IRQ_TYPE_NONE>;
+ interrupts = <GIC_SPI 95 IRQ_TYPE_LEVEL_HIGH>;
clock-frequency = <100000>;
};
reg = <0x3b000 0x50>;
#address-cells = <1>;
#size-cells = <0>;
- interrupts = <GIC_SPI 96 IRQ_TYPE_NONE>;
+ interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>;
clock-frequency = <100000>;
};
};
#interrupt-cells = <1>;
interrupt-map-mask = <0 0 0 0>;
- interrupt-map = <0 0 0 0 &gic GIC_SPI 186 IRQ_TYPE_NONE>;
+ interrupt-map = <0 0 0 0 &gic GIC_SPI 186 IRQ_TYPE_LEVEL_HIGH>;
linux,pci-domain = <0>;
compatible = "brcm,iproc-msi";
msi-controller;
interrupt-parent = <&gic>;
- interrupts = <GIC_SPI 182 IRQ_TYPE_NONE>,
- <GIC_SPI 183 IRQ_TYPE_NONE>,
- <GIC_SPI 184 IRQ_TYPE_NONE>,
- <GIC_SPI 185 IRQ_TYPE_NONE>;
+ interrupts = <GIC_SPI 182 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 183 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 184 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 185 IRQ_TYPE_LEVEL_HIGH>;
brcm,pcie-msi-inten;
};
};
#interrupt-cells = <1>;
interrupt-map-mask = <0 0 0 0>;
- interrupt-map = <0 0 0 0 &gic GIC_SPI 192 IRQ_TYPE_NONE>;
+ interrupt-map = <0 0 0 0 &gic GIC_SPI 192 IRQ_TYPE_LEVEL_HIGH>;
linux,pci-domain = <1>;
compatible = "brcm,iproc-msi";
msi-controller;
interrupt-parent = <&gic>;
- interrupts = <GIC_SPI 188 IRQ_TYPE_NONE>,
- <GIC_SPI 189 IRQ_TYPE_NONE>,
- <GIC_SPI 190 IRQ_TYPE_NONE>,
- <GIC_SPI 191 IRQ_TYPE_NONE>;
+ interrupts = <GIC_SPI 188 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 189 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 190 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 191 IRQ_TYPE_LEVEL_HIGH>;
brcm,pcie-msi-inten;
};
};
reg = <0x38000 0x50>;
#address-cells = <1>;
#size-cells = <0>;
- interrupts = <GIC_SPI 89 IRQ_TYPE_NONE>;
+ interrupts = <GIC_SPI 89 IRQ_TYPE_LEVEL_HIGH>;
clock-frequency = <100000>;
dma-coherent;
status = "disabled";
#interrupt-cells = <1>;
interrupt-map-mask = <0 0 0 0>;
- interrupt-map = <0 0 0 0 &gic GIC_SPI 131 IRQ_TYPE_NONE>;
+ interrupt-map = <0 0 0 0 &gic GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>;
linux,pci-domain = <0>;
compatible = "brcm,iproc-msi";
msi-controller;
interrupt-parent = <&gic>;
- interrupts = <GIC_SPI 127 IRQ_TYPE_NONE>,
- <GIC_SPI 128 IRQ_TYPE_NONE>,
- <GIC_SPI 129 IRQ_TYPE_NONE>,
- <GIC_SPI 130 IRQ_TYPE_NONE>;
+ interrupts = <GIC_SPI 127 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 128 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 129 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>;
brcm,pcie-msi-inten;
};
};
#interrupt-cells = <1>;
interrupt-map-mask = <0 0 0 0>;
- interrupt-map = <0 0 0 0 &gic GIC_SPI 137 IRQ_TYPE_NONE>;
+ interrupt-map = <0 0 0 0 &gic GIC_SPI 137 IRQ_TYPE_LEVEL_HIGH>;
linux,pci-domain = <1>;
compatible = "brcm,iproc-msi";
msi-controller;
interrupt-parent = <&gic>;
- interrupts = <GIC_SPI 133 IRQ_TYPE_NONE>,
- <GIC_SPI 134 IRQ_TYPE_NONE>,
- <GIC_SPI 135 IRQ_TYPE_NONE>,
- <GIC_SPI 136 IRQ_TYPE_NONE>;
+ interrupts = <GIC_SPI 133 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 134 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 135 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>;
brcm,pcie-msi-inten;
};
};
#interrupt-cells = <1>;
interrupt-map-mask = <0 0 0 0>;
- interrupt-map = <0 0 0 0 &gic GIC_SPI 143 IRQ_TYPE_NONE>;
+ interrupt-map = <0 0 0 0 &gic GIC_SPI 143 IRQ_TYPE_LEVEL_HIGH>;
linux,pci-domain = <2>;
compatible = "brcm,iproc-msi";
msi-controller;
interrupt-parent = <&gic>;
- interrupts = <GIC_SPI 139 IRQ_TYPE_NONE>,
- <GIC_SPI 140 IRQ_TYPE_NONE>,
- <GIC_SPI 141 IRQ_TYPE_NONE>,
- <GIC_SPI 142 IRQ_TYPE_NONE>;
+ interrupts = <GIC_SPI 139 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 140 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 141 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 142 IRQ_TYPE_LEVEL_HIGH>;
brcm,pcie-msi-inten;
};
};
i2c0: i2c@18009000 {
compatible = "brcm,iproc-i2c";
reg = <0x18009000 0x50>;
- interrupts = <GIC_SPI 121 IRQ_TYPE_NONE>;
+ interrupts = <GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>;
#address-cells = <1>;
#size-cells = <0>;
clock-frequency = <100000>;
gpio-controller;
#gpio-cells = <2>;
reg = <0x226000 0x1000>;
- interrupts = <42 IRQ_TYPE_EDGE_BOTH
- 43 IRQ_TYPE_EDGE_BOTH 44 IRQ_TYPE_EDGE_BOTH
- 45 IRQ_TYPE_EDGE_BOTH 46 IRQ_TYPE_EDGE_BOTH
- 47 IRQ_TYPE_EDGE_BOTH 48 IRQ_TYPE_EDGE_BOTH
- 49 IRQ_TYPE_EDGE_BOTH 50 IRQ_TYPE_EDGE_BOTH>;
+ interrupts = <42 43 44 45 46 47 48 49 50>;
ti,ngpio = <144>;
ti,davinci-gpio-unbanked = <0>;
status = "disabled";
};
};
+ /* This is a RealTek RTL8366RB switch and PHY using SMI over GPIO */
+ switch {
+ compatible = "realtek,rtl8366rb";
+ /* 22 = MDIO (has input reads), 21 = MDC (clock, output only) */
+ mdc-gpios = <&gpio0 21 GPIO_ACTIVE_HIGH>;
+ mdio-gpios = <&gpio0 22 GPIO_ACTIVE_HIGH>;
+ reset-gpios = <&gpio0 14 GPIO_ACTIVE_LOW>;
+ realtek,disable-leds;
+
+ switch_intc: interrupt-controller {
+ /* GPIO 15 provides the interrupt */
+ interrupt-parent = <&gpio0>;
+ interrupts = <15 IRQ_TYPE_LEVEL_LOW>;
+ interrupt-controller;
+ #address-cells = <0>;
+ #interrupt-cells = <1>;
+ };
+
+ ports {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ port@0 {
+ reg = <0>;
+ label = "lan0";
+ phy-handle = <&phy0>;
+ };
+ port@1 {
+ reg = <1>;
+ label = "lan1";
+ phy-handle = <&phy1>;
+ };
+ port@2 {
+ reg = <2>;
+ label = "lan2";
+ phy-handle = <&phy2>;
+ };
+ port@3 {
+ reg = <3>;
+ label = "lan3";
+ phy-handle = <&phy3>;
+ };
+ port@4 {
+ reg = <4>;
+ label = "wan";
+ phy-handle = <&phy4>;
+ };
+ rtl8366rb_cpu_port: port@5 {
+ reg = <5>;
+ label = "cpu";
+ ethernet = <&gmac0>;
+ phy-mode = "rgmii";
+ fixed-link {
+ speed = <1000>;
+ full-duplex;
+ pause;
+ };
+ };
+
+ };
+
+ mdio {
+ compatible = "realtek,smi-mdio";
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ phy0: phy@0 {
+ reg = <0>;
+ interrupt-parent = <&switch_intc>;
+ interrupts = <0>;
+ };
+ phy1: phy@1 {
+ reg = <1>;
+ interrupt-parent = <&switch_intc>;
+ interrupts = <1>;
+ };
+ phy2: phy@2 {
+ reg = <2>;
+ interrupt-parent = <&switch_intc>;
+ interrupts = <2>;
+ };
+ phy3: phy@3 {
+ reg = <3>;
+ interrupt-parent = <&switch_intc>;
+ interrupts = <3>;
+ };
+ phy4: phy@4 {
+ reg = <4>;
+ interrupt-parent = <&switch_intc>;
+ interrupts = <12>;
+ };
+ };
+ };
+
soc {
flash@30000000 {
/*
* gpio0bgrp cover line 7 used by WPS LED
* gpio0cgrp cover line 8, 13 used by keys
* and 11, 12 used by the HD LEDs
+ * and line 14, 15 used by RTL8366
+ * RESET and phy ready
* gpio0egrp cover line 16 used by VDISP
* gpio0fgrp cover line 17 used by TK IRQ
* gpio0ggrp cover line 20 used by panel CS
- * gpio0hgrp cover line 21,22 used by RTL8366RB
+ * gpio0hgrp cover line 21,22 used by RTL8366RB MDIO
*/
gpio0_default_pins: pinctrl-gpio0 {
mux {
groups = "gpio1bgrp";
};
};
+ pinctrl-gmii {
+ mux {
+ function = "gmii";
+ groups = "gmii_gmac0_grp";
+ };
+ conf0 {
+ pins = "V8 GMAC0 RXDV", "T10 GMAC1 RXDV",
+ "Y7 GMAC0 RXC", "Y11 GMAC1 RXC",
+ "T8 GMAC0 TXEN", "W11 GMAC1 TXEN",
+ "U8 GMAC0 TXC", "V11 GMAC1 TXC",
+ "W8 GMAC0 RXD0", "V9 GMAC0 RXD1",
+ "Y8 GMAC0 RXD2", "U9 GMAC0 RXD3",
+ "T7 GMAC0 TXD0", "U6 GMAC0 TXD1",
+ "V7 GMAC0 TXD2", "U7 GMAC0 TXD3",
+ "Y12 GMAC1 RXD0", "V12 GMAC1 RXD1",
+ "T11 GMAC1 RXD2", "W12 GMAC1 RXD3",
+ "U10 GMAC1 TXD0", "Y10 GMAC1 TXD1",
+ "W10 GMAC1 TXD2", "T9 GMAC1 TXD3";
+ skew-delay = <7>;
+ };
+ /* Set up drive strength on GMAC0 to 16 mA */
+ conf1 {
+ groups = "gmii_gmac0_grp";
+ drive-strength = <16>;
+ };
+ };
};
};
<0x6000 0 0 4 &pci_intc 2>;
};
+ ethernet@60000000 {
+ status = "okay";
+
+ ethernet-port@0 {
+ phy-mode = "rgmii";
+ fixed-link {
+ speed = <1000>;
+ full-duplex;
+ pause;
+ };
+ };
+ ethernet-port@1 {
+ /* Not used in this platform */
+ };
+ };
+
ata@63000000 {
status = "okay";
};
clocks = <&clks IMX6Q_CLK_ECSPI5>,
<&clks IMX6Q_CLK_ECSPI5>;
clock-names = "ipg", "per";
- dmas = <&sdma 11 7 1>, <&sdma 12 7 2>;
+ dmas = <&sdma 11 8 1>, <&sdma 12 8 2>;
dma-names = "rx", "tx";
status = "disabled";
};
ranges = <0x81000000 0 0 0x08f80000 0 0x00010000 /* downstream I/O */
0x82000000 0 0x08000000 0x08000000 0 0x00f00000>; /* non-prefetchable memory */
num-lanes = <1>;
- interrupts = <GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>;
interrupt-names = "msi";
#interrupt-cells = <1>;
interrupt-map-mask = <0 0 0 0x7>;
nand0: nand@ff900000 {
#address-cells = <0x1>;
#size-cells = <0x1>;
- compatible = "denali,denali-nand-dt";
+ compatible = "altr,socfpga-denali-nand";
reg = <0xff900000 0x100000>,
<0xffb80000 0x10000>;
reg-names = "nand_data", "denali_reg";
interrupts = <0x0 0x90 0x4>;
dma-mask = <0xffffffff>;
- clocks = <&nand_clk>;
+ clocks = <&nand_x_clk>;
status = "disabled";
};
#size-cells = <0>;
reg = <0xffda5000 0x100>;
interrupts = <0 102 4>;
- num-chipselect = <4>;
- bus-num = <0>;
+ num-cs = <4>;
/*32bit_access;*/
tx-dma-channel = <&pdma 16>;
rx-dma-channel = <&pdma 17>;
nand: nand@ffb90000 {
#address-cells = <1>;
#size-cells = <1>;
- compatible = "denali,denali-nand-dt", "altr,socfpga-denali-nand";
+ compatible = "altr,socfpga-denali-nand";
reg = <0xffb90000 0x72000>,
<0xffb80000 0x10000>;
reg-names = "nand_data", "denali_reg";
obj-$(CONFIG_SHARP_LOCOMO) += locomo.o
obj-$(CONFIG_SHARP_PARAM) += sharpsl_param.o
obj-$(CONFIG_SHARP_SCOOP) += scoop.o
-obj-$(CONFIG_SMP) += secure_cntvoff.o
+obj-$(CONFIG_CPU_V7) += secure_cntvoff.o
obj-$(CONFIG_PCI_HOST_ITE8152) += it8152.o
obj-$(CONFIG_MCPM) += mcpm_head.o mcpm_entry.o mcpm_platsmp.o vlock.o
CFLAGS_REMOVE_mcpm_entry.o = -pg
CONFIG_SYSVIPC=y
-CONFIG_FHANDLE=y
CONFIG_NO_HZ=y
CONFIG_HIGH_RES_TIMERS=y
CONFIG_CGROUPS=y
CONFIG_MODULE_UNLOAD=y
CONFIG_PARTITION_ADVANCED=y
CONFIG_CMDLINE_PARTITION=y
-CONFIG_ARCH_MULTI_V7=y
-# CONFIG_ARCH_MULTI_V5 is not set
-# CONFIG_ARCH_MULTI_V4 is not set
CONFIG_ARCH_VIRT=y
CONFIG_ARCH_ALPINE=y
CONFIG_ARCH_ARTPEC=y
CONFIG_MACH_ARTPEC6=y
-CONFIG_ARCH_MVEBU=y
-CONFIG_MACH_ARMADA_370=y
-CONFIG_MACH_ARMADA_375=y
-CONFIG_MACH_ARMADA_38X=y
-CONFIG_MACH_ARMADA_39X=y
-CONFIG_MACH_ARMADA_XP=y
-CONFIG_MACH_DOVE=y
CONFIG_ARCH_AT91=y
CONFIG_SOC_SAMA5D2=y
CONFIG_SOC_SAMA5D3=y
CONFIG_ARCH_BCM_CYGNUS=y
CONFIG_ARCH_BCM_HR2=y
CONFIG_ARCH_BCM_NSP=y
-CONFIG_ARCH_BCM_21664=y
-CONFIG_ARCH_BCM_281XX=y
CONFIG_ARCH_BCM_5301X=y
+CONFIG_ARCH_BCM_281XX=y
+CONFIG_ARCH_BCM_21664=y
CONFIG_ARCH_BCM2835=y
CONFIG_ARCH_BCM_63XX=y
CONFIG_ARCH_BRCMSTB=y
CONFIG_MACH_BERLIN_BG2CD=y
CONFIG_MACH_BERLIN_BG2Q=y
CONFIG_ARCH_DIGICOLOR=y
+CONFIG_ARCH_EXYNOS=y
+CONFIG_EXYNOS5420_MCPM=y
CONFIG_ARCH_HIGHBANK=y
CONFIG_ARCH_HISI=y
CONFIG_ARCH_HI3xxx=y
-CONFIG_ARCH_HIX5HD2=y
CONFIG_ARCH_HIP01=y
CONFIG_ARCH_HIP04=y
-CONFIG_ARCH_KEYSTONE=y
-CONFIG_ARCH_MESON=y
+CONFIG_ARCH_HIX5HD2=y
CONFIG_ARCH_MXC=y
CONFIG_SOC_IMX50=y
CONFIG_SOC_IMX51=y
CONFIG_SOC_IMX6SX=y
CONFIG_SOC_IMX6UL=y
CONFIG_SOC_IMX7D=y
-CONFIG_SOC_VF610=y
CONFIG_SOC_LS1021A=y
+CONFIG_SOC_VF610=y
+CONFIG_ARCH_KEYSTONE=y
+CONFIG_ARCH_MEDIATEK=y
+CONFIG_ARCH_MESON=y
+CONFIG_ARCH_MVEBU=y
+CONFIG_MACH_ARMADA_370=y
+CONFIG_MACH_ARMADA_375=y
+CONFIG_MACH_ARMADA_38X=y
+CONFIG_MACH_ARMADA_39X=y
+CONFIG_MACH_ARMADA_XP=y
+CONFIG_MACH_DOVE=y
CONFIG_ARCH_OMAP3=y
CONFIG_ARCH_OMAP4=y
CONFIG_SOC_OMAP5=y
CONFIG_SOC_AM33XX=y
CONFIG_SOC_AM43XX=y
CONFIG_SOC_DRA7XX=y
+CONFIG_ARCH_SIRF=y
CONFIG_ARCH_QCOM=y
-CONFIG_ARCH_MEDIATEK=y
CONFIG_ARCH_MSM8X60=y
CONFIG_ARCH_MSM8960=y
CONFIG_ARCH_MSM8974=y
CONFIG_ARCH_ROCKCHIP=y
-CONFIG_ARCH_SOCFPGA=y
-CONFIG_PLAT_SPEAR=y
-CONFIG_ARCH_SPEAR13XX=y
-CONFIG_MACH_SPEAR1310=y
-CONFIG_MACH_SPEAR1340=y
-CONFIG_ARCH_STI=y
-CONFIG_ARCH_STM32=y
-CONFIG_ARCH_EXYNOS=y
-CONFIG_EXYNOS5420_MCPM=y
CONFIG_ARCH_RENESAS=y
CONFIG_ARCH_EMEV2=y
CONFIG_ARCH_R7S72100=y
CONFIG_ARCH_R8A7793=y
CONFIG_ARCH_R8A7794=y
CONFIG_ARCH_SH73A0=y
+CONFIG_ARCH_SOCFPGA=y
+CONFIG_PLAT_SPEAR=y
+CONFIG_ARCH_SPEAR13XX=y
+CONFIG_MACH_SPEAR1310=y
+CONFIG_MACH_SPEAR1340=y
+CONFIG_ARCH_STI=y
+CONFIG_ARCH_STM32=y
CONFIG_ARCH_SUNXI=y
-CONFIG_ARCH_SIRF=y
CONFIG_ARCH_TEGRA=y
-CONFIG_ARCH_TEGRA_2x_SOC=y
-CONFIG_ARCH_TEGRA_3x_SOC=y
-CONFIG_ARCH_TEGRA_114_SOC=y
-CONFIG_ARCH_TEGRA_124_SOC=y
CONFIG_ARCH_UNIPHIER=y
CONFIG_ARCH_U8500=y
-CONFIG_MACH_HREFV60=y
-CONFIG_MACH_SNOWBALL=y
CONFIG_ARCH_VEXPRESS=y
CONFIG_ARCH_VEXPRESS_TC2_PM=y
CONFIG_ARCH_WM8850=y
CONFIG_ARCH_ZYNQ=y
-CONFIG_TRUSTED_FOUNDATIONS=y
-CONFIG_PCI=y
-CONFIG_PCI_HOST_GENERIC=y
-CONFIG_PCI_DRA7XX=y
-CONFIG_PCI_DRA7XX_EP=y
-CONFIG_PCI_KEYSTONE=y
-CONFIG_PCI_MSI=y
+CONFIG_PCIEPORTBUS=y
CONFIG_PCI_MVEBU=y
CONFIG_PCI_TEGRA=y
CONFIG_PCI_RCAR_GEN2=y
CONFIG_PCIE_RCAR=y
-CONFIG_PCIEPORTBUS=y
+CONFIG_PCI_DRA7XX_EP=y
+CONFIG_PCI_KEYSTONE=y
CONFIG_PCI_ENDPOINT=y
CONFIG_PCI_ENDPOINT_CONFIGFS=y
CONFIG_PCI_EPF_TEST=m
CONFIG_SMP=y
CONFIG_NR_CPUS=16
-CONFIG_HIGHPTE=y
-CONFIG_CMA=y
CONFIG_SECCOMP=y
CONFIG_ARM_APPENDED_DTB=y
CONFIG_ARM_ATAG_DTB_COMPAT=y
CONFIG_CPU_FREQ_GOV_USERSPACE=m
CONFIG_CPU_FREQ_GOV_CONSERVATIVE=m
CONFIG_CPU_FREQ_GOV_SCHEDUTIL=y
+CONFIG_CPUFREQ_DT=y
CONFIG_ARM_IMX6Q_CPUFREQ=y
CONFIG_QORIQ_CPUFREQ=y
CONFIG_CPU_IDLE=y
CONFIG_ARM_CPUIDLE=y
-CONFIG_NEON=y
-CONFIG_KERNEL_MODE_NEON=y
CONFIG_ARM_ZYNQ_CPUIDLE=y
CONFIG_ARM_EXYNOS_CPUIDLE=y
+CONFIG_KERNEL_MODE_NEON=y
CONFIG_NET=y
CONFIG_PACKET=y
CONFIG_UNIX=y
CONFIG_IPV6_TUNNEL=m
CONFIG_IPV6_MULTIPLE_TABLES=y
CONFIG_NET_DSA=m
-CONFIG_NET_SWITCHDEV=y
CONFIG_CAN=y
-CONFIG_CAN_RAW=y
-CONFIG_CAN_BCM=y
-CONFIG_CAN_DEV=y
CONFIG_CAN_AT91=m
CONFIG_CAN_FLEXCAN=m
-CONFIG_CAN_RCAR=m
+CONFIG_CAN_SUN4I=y
CONFIG_CAN_XILINXCAN=y
+CONFIG_CAN_RCAR=m
CONFIG_CAN_MCP251X=y
-CONFIG_NET_DSA_BCM_SF2=m
-CONFIG_B53=m
-CONFIG_B53_SPI_DRIVER=m
-CONFIG_B53_MDIO_DRIVER=m
-CONFIG_B53_MMAP_DRIVER=m
-CONFIG_B53_SRAB_DRIVER=m
-CONFIG_CAN_SUN4I=y
CONFIG_BT=m
CONFIG_BT_HCIUART=m
CONFIG_BT_HCIUART_BCM=y
CONFIG_RFKILL_GPIO=y
CONFIG_DEVTMPFS=y
CONFIG_DEVTMPFS_MOUNT=y
-CONFIG_DMA_CMA=y
CONFIG_CMA_SIZE_MBYTES=64
CONFIG_OMAP_OCP2SCP=y
CONFIG_SIMPLE_PM_BUS=y
-CONFIG_SUNXI_RSB=y
CONFIG_MTD=y
CONFIG_MTD_CMDLINE_PARTS=y
CONFIG_MTD_BLOCK=y
CONFIG_EEPROM_AT24=y
CONFIG_BLK_DEV_SD=y
CONFIG_BLK_DEV_SR=y
-CONFIG_SCSI_MULTI_LUN=y
CONFIG_ATA=y
CONFIG_SATA_AHCI=y
CONFIG_SATA_AHCI_PLATFORM=y
CONFIG_SATA_RCAR=y
CONFIG_NETDEVICES=y
CONFIG_VIRTIO_NET=y
-CONFIG_HIX5HD2_GMAC=y
+CONFIG_B53_SPI_DRIVER=m
+CONFIG_B53_MDIO_DRIVER=m
+CONFIG_B53_MMAP_DRIVER=m
+CONFIG_B53_SRAB_DRIVER=m
+CONFIG_NET_DSA_BCM_SF2=m
CONFIG_SUN4I_EMAC=y
-CONFIG_MACB=y
CONFIG_BCMGENET=m
CONFIG_BGMAC_BCMA=y
CONFIG_SYSTEMPORT=m
+CONFIG_MACB=y
CONFIG_NET_CALXEDA_XGMAC=y
CONFIG_GIANFAR=y
+CONFIG_HIX5HD2_GMAC=y
+CONFIG_E1000E=y
CONFIG_IGB=y
CONFIG_MV643XX_ETH=y
CONFIG_MVNETA=y
CONFIG_SH_ETH=y
CONFIG_SMSC911X=y
CONFIG_STMMAC_ETH=y
-CONFIG_STMMAC_PLATFORM=y
CONFIG_DWMAC_DWC_QOS_ETH=y
CONFIG_TI_CPSW=y
CONFIG_XILINX_EMACLITE=y
CONFIG_AT803X_PHY=y
-CONFIG_MARVELL_PHY=y
-CONFIG_SMSC_PHY=y
CONFIG_BROADCOM_PHY=y
CONFIG_ICPLUS_PHY=y
-CONFIG_REALTEK_PHY=y
+CONFIG_MARVELL_PHY=y
CONFIG_MICREL_PHY=y
-CONFIG_FIXED_PHY=y
+CONFIG_REALTEK_PHY=y
CONFIG_ROCKCHIP_PHY=y
+CONFIG_SMSC_PHY=y
CONFIG_USB_PEGASUS=y
CONFIG_USB_RTL8152=m
CONFIG_USB_LAN78XX=m
CONFIG_USB_NET_SMSC75XX=y
CONFIG_USB_NET_SMSC95XX=y
CONFIG_BRCMFMAC=m
-CONFIG_RT2X00=m
-CONFIG_RT2800USB=m
CONFIG_MWIFIEX=m
CONFIG_MWIFIEX_SDIO=m
+CONFIG_RT2X00=m
+CONFIG_RT2800USB=m
CONFIG_INPUT_JOYDEV=y
CONFIG_INPUT_EVDEV=y
CONFIG_KEYBOARD_QT1070=m
CONFIG_KEYBOARD_GPIO=y
CONFIG_KEYBOARD_TEGRA=y
-CONFIG_KEYBOARD_SPEAR=y
+CONFIG_KEYBOARD_SAMSUNG=m
CONFIG_KEYBOARD_ST_KEYSCAN=y
+CONFIG_KEYBOARD_SPEAR=y
CONFIG_KEYBOARD_CROS_EC=m
-CONFIG_KEYBOARD_SAMSUNG=m
CONFIG_MOUSE_PS2_ELANTECH=y
CONFIG_MOUSE_CYAPA=m
CONFIG_MOUSE_ELAN_I2C=y
CONFIG_INPUT_TOUCHSCREEN=y
CONFIG_TOUCHSCREEN_ATMEL_MXT=m
CONFIG_TOUCHSCREEN_MMS114=m
+CONFIG_TOUCHSCREEN_WM97XX=m
CONFIG_TOUCHSCREEN_ST1232=m
CONFIG_TOUCHSCREEN_STMPE=y
CONFIG_TOUCHSCREEN_SUN4I=y
-CONFIG_TOUCHSCREEN_WM97XX=m
CONFIG_INPUT_MISC=y
CONFIG_INPUT_MAX77693_HAPTIC=m
CONFIG_INPUT_MAX8997_HAPTIC=m
CONFIG_SERIAL_8250_EM=y
CONFIG_SERIAL_8250_MT6577=y
CONFIG_SERIAL_8250_UNIPHIER=y
+CONFIG_SERIAL_OF_PLATFORM=y
CONFIG_SERIAL_AMBA_PL011=y
CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
CONFIG_SERIAL_ATMEL=y
CONFIG_SERIAL_ATMEL_CONSOLE=y
CONFIG_SERIAL_ATMEL_TTYAT=y
-CONFIG_SERIAL_BCM63XX=y
-CONFIG_SERIAL_BCM63XX_CONSOLE=y
CONFIG_SERIAL_MESON=y
CONFIG_SERIAL_MESON_CONSOLE=y
CONFIG_SERIAL_SAMSUNG=y
CONFIG_SERIAL_IMX_CONSOLE=y
CONFIG_SERIAL_SH_SCI=y
CONFIG_SERIAL_SH_SCI_NR_UARTS=20
-CONFIG_SERIAL_SH_SCI_CONSOLE=y
-CONFIG_SERIAL_SH_SCI_DMA=y
CONFIG_SERIAL_MSM=y
CONFIG_SERIAL_MSM_CONSOLE=y
CONFIG_SERIAL_VT8500=y
CONFIG_SERIAL_VT8500_CONSOLE=y
-CONFIG_SERIAL_OF_PLATFORM=y
CONFIG_SERIAL_OMAP=y
CONFIG_SERIAL_OMAP_CONSOLE=y
+CONFIG_SERIAL_BCM63XX=y
+CONFIG_SERIAL_BCM63XX_CONSOLE=y
CONFIG_SERIAL_XILINX_PS_UART=y
CONFIG_SERIAL_XILINX_PS_UART_CONSOLE=y
CONFIG_SERIAL_FSL_LPUART=y
CONFIG_SERIAL_STM32=y
CONFIG_SERIAL_STM32_CONSOLE=y
CONFIG_SERIAL_DEV_BUS=y
-CONFIG_HVC_DRIVER=y
CONFIG_VIRTIO_CONSOLE=y
+CONFIG_HW_RANDOM=y
+CONFIG_HW_RANDOM_ST=y
CONFIG_I2C_CHARDEV=y
-CONFIG_I2C_DAVINCI=y
-CONFIG_I2C_MESON=y
-CONFIG_I2C_MUX=y
CONFIG_I2C_ARB_GPIO_CHALLENGE=m
CONFIG_I2C_MUX_PCA954x=y
CONFIG_I2C_MUX_PINCTRL=y
CONFIG_I2C_AT91=m
CONFIG_I2C_BCM2835=y
CONFIG_I2C_CADENCE=y
+CONFIG_I2C_DAVINCI=y
CONFIG_I2C_DESIGNWARE_PLATFORM=y
CONFIG_I2C_DIGICOLOR=m
CONFIG_I2C_EMEV2=m
CONFIG_I2C_GPIO=m
-CONFIG_I2C_EXYNOS5=y
CONFIG_I2C_IMX=y
+CONFIG_I2C_MESON=y
CONFIG_I2C_MV64XXX=y
CONFIG_I2C_RIIC=y
CONFIG_I2C_RK3X=y
CONFIG_SPMI=y
CONFIG_PINCTRL_AS3722=y
CONFIG_PINCTRL_PALMAS=y
-CONFIG_PINCTRL_BCM2835=y
CONFIG_PINCTRL_APQ8064=y
CONFIG_PINCTRL_APQ8084=y
CONFIG_PINCTRL_IPQ8064=y
CONFIG_PINCTRL_MSM8916=y
CONFIG_PINCTRL_QCOM_SPMI_PMIC=y
CONFIG_PINCTRL_QCOM_SSBI_PMIC=y
-CONFIG_GPIO_GENERIC_PLATFORM=y
CONFIG_GPIO_DAVINCI=y
CONFIG_GPIO_DWAPB=y
CONFIG_GPIO_EM=y
CONFIG_GPIO_RCAR=y
+CONFIG_GPIO_SYSCON=y
CONFIG_GPIO_UNIPHIER=y
CONFIG_GPIO_XILINX=y
CONFIG_GPIO_ZYNQ=y
CONFIG_GPIO_PCA953X=y
CONFIG_GPIO_PCA953X_IRQ=y
CONFIG_GPIO_PCF857X=y
-CONFIG_GPIO_TWL4030=y
CONFIG_GPIO_PALMAS=y
-CONFIG_GPIO_SYSCON=y
CONFIG_GPIO_TPS6586X=y
CONFIG_GPIO_TPS65910=y
+CONFIG_GPIO_TWL4030=y
+CONFIG_POWER_AVS=y
+CONFIG_ROCKCHIP_IODOMAIN=y
+CONFIG_POWER_RESET_AS3722=y
+CONFIG_POWER_RESET_GPIO=y
+CONFIG_POWER_RESET_GPIO_RESTART=y
+CONFIG_POWER_RESET_ST=y
+CONFIG_POWER_RESET_KEYSTONE=y
+CONFIG_POWER_RESET_RMOBILE=y
CONFIG_BATTERY_ACT8945A=y
CONFIG_BATTERY_CPCAP=m
CONFIG_BATTERY_SBS=y
+CONFIG_AXP20X_POWER=m
CONFIG_BATTERY_MAX17040=m
CONFIG_BATTERY_MAX17042=m
CONFIG_CHARGER_CPCAP=m
CONFIG_CHARGER_MAX8997=m
CONFIG_CHARGER_MAX8998=m
CONFIG_CHARGER_TPS65090=y
-CONFIG_AXP20X_POWER=m
-CONFIG_POWER_RESET_AS3722=y
-CONFIG_POWER_RESET_GPIO=y
-CONFIG_POWER_RESET_GPIO_RESTART=y
-CONFIG_POWER_RESET_KEYSTONE=y
-CONFIG_POWER_RESET_RMOBILE=y
-CONFIG_POWER_RESET_ST=y
-CONFIG_POWER_AVS=y
-CONFIG_ROCKCHIP_IODOMAIN=y
CONFIG_SENSORS_IIO_HWMON=y
CONFIG_SENSORS_LM90=y
CONFIG_SENSORS_LM95245=y
CONFIG_SENSORS_PWM_FAN=m
CONFIG_SENSORS_INA2XX=m
CONFIG_CPU_THERMAL=y
-CONFIG_BCM2835_THERMAL=m
-CONFIG_BRCMSTB_THERMAL=m
CONFIG_IMX_THERMAL=y
CONFIG_ROCKCHIP_THERMAL=y
CONFIG_RCAR_THERMAL=y
CONFIG_ARMADA_THERMAL=y
-CONFIG_DAVINCI_WATCHDOG=m
-CONFIG_EXYNOS_THERMAL=m
+CONFIG_BCM2835_THERMAL=m
+CONFIG_BRCMSTB_THERMAL=m
CONFIG_ST_THERMAL_MEMMAP=y
CONFIG_WATCHDOG=y
CONFIG_DA9063_WATCHDOG=m
CONFIG_ARM_SP805_WATCHDOG=y
CONFIG_AT91SAM9X_WATCHDOG=y
CONFIG_SAMA5D4_WATCHDOG=y
+CONFIG_DW_WATCHDOG=y
+CONFIG_DAVINCI_WATCHDOG=m
CONFIG_ORION_WATCHDOG=y
CONFIG_RN5T618_WATCHDOG=y
-CONFIG_ST_LPC_WATCHDOG=y
CONFIG_SUNXI_WATCHDOG=y
CONFIG_IMX2_WDT=y
+CONFIG_ST_LPC_WATCHDOG=y
CONFIG_TEGRA_WATCHDOG=m
CONFIG_MESON_WATCHDOG=y
-CONFIG_DW_WATCHDOG=y
CONFIG_DIGICOLOR_WATCHDOG=y
CONFIG_RENESAS_WDT=m
-CONFIG_BCM2835_WDT=y
CONFIG_BCM47XX_WDT=y
-CONFIG_BCM7038_WDT=m
+CONFIG_BCM2835_WDT=y
CONFIG_BCM_KONA_WDT=y
+CONFIG_BCM7038_WDT=m
+CONFIG_BCMA_HOST_SOC=y
+CONFIG_BCMA_DRIVER_GMAC_CMN=y
+CONFIG_BCMA_DRIVER_GPIO=y
CONFIG_MFD_ACT8945A=y
CONFIG_MFD_AS3711=y
CONFIG_MFD_AS3722=y
CONFIG_MFD_ATMEL_HLCDC=m
CONFIG_MFD_BCM590XX=y
CONFIG_MFD_AC100=y
-CONFIG_MFD_AXP20X=y
CONFIG_MFD_AXP20X_I2C=y
CONFIG_MFD_AXP20X_RSB=y
CONFIG_MFD_CROS_EC=m
CONFIG_MFD_MAX8907=y
CONFIG_MFD_MAX8997=y
CONFIG_MFD_MAX8998=y
-CONFIG_MFD_RK808=y
CONFIG_MFD_CPCAP=y
CONFIG_MFD_PM8XXX=y
CONFIG_MFD_QCOM_RPM=y
CONFIG_MFD_SPMI_PMIC=y
+CONFIG_MFD_RK808=y
CONFIG_MFD_RN5T618=y
CONFIG_MFD_SEC_CORE=y
CONFIG_MFD_STMPE=y
CONFIG_MFD_TPS65218=y
CONFIG_MFD_TPS6586X=y
CONFIG_MFD_TPS65910=y
-CONFIG_REGULATOR_ACT8945A=y
-CONFIG_REGULATOR_AB8500=y
CONFIG_REGULATOR_ACT8865=y
+CONFIG_REGULATOR_ACT8945A=y
CONFIG_REGULATOR_ANATOP=y
+CONFIG_REGULATOR_AB8500=y
CONFIG_REGULATOR_AS3711=y
CONFIG_REGULATOR_AS3722=y
CONFIG_REGULATOR_AXP20X=y
CONFIG_REGULATOR_CPCAP=y
CONFIG_REGULATOR_DA9210=y
CONFIG_REGULATOR_FAN53555=y
-CONFIG_REGULATOR_RK808=y
CONFIG_REGULATOR_GPIO=y
-CONFIG_MFD_SYSCON=y
-CONFIG_POWER_RESET_SYSCON=y
CONFIG_REGULATOR_LP872X=y
CONFIG_REGULATOR_MAX14577=m
CONFIG_REGULATOR_MAX8907=y
CONFIG_REGULATOR_PBIAS=y
CONFIG_REGULATOR_PWM=y
CONFIG_REGULATOR_QCOM_RPM=y
-CONFIG_REGULATOR_QCOM_SMD_RPM=y
+CONFIG_REGULATOR_QCOM_SMD_RPM=m
+CONFIG_REGULATOR_RK808=y
CONFIG_REGULATOR_RN5T618=y
CONFIG_REGULATOR_S2MPS11=y
CONFIG_REGULATOR_S5M8767=y
CONFIG_MEDIA_CONTROLLER=y
CONFIG_VIDEO_V4L2_SUBDEV_API=y
CONFIG_MEDIA_USB_SUPPORT=y
-CONFIG_USB_VIDEO_CLASS=y
-CONFIG_USB_GSPCA=y
+CONFIG_USB_VIDEO_CLASS=m
CONFIG_V4L_PLATFORM_DRIVERS=y
CONFIG_SOC_CAMERA=m
CONFIG_SOC_CAMERA_PLATFORM=m
-CONFIG_VIDEO_RCAR_VIN=m
-CONFIG_VIDEO_ATMEL_ISI=m
CONFIG_VIDEO_SAMSUNG_EXYNOS4_IS=m
CONFIG_VIDEO_S5P_FIMC=m
CONFIG_VIDEO_S5P_MIPI_CSIS=m
CONFIG_VIDEO_EXYNOS_FIMC_LITE=m
CONFIG_VIDEO_EXYNOS4_FIMC_IS=m
+CONFIG_VIDEO_RCAR_VIN=m
+CONFIG_VIDEO_ATMEL_ISI=m
CONFIG_V4L_MEM2MEM_DRIVERS=y
CONFIG_VIDEO_SAMSUNG_S5P_JPEG=m
CONFIG_VIDEO_SAMSUNG_S5P_MFC=m
CONFIG_VIDEO_RENESAS_JPU=m
CONFIG_VIDEO_RENESAS_VSP1=m
CONFIG_V4L_TEST_DRIVERS=y
+CONFIG_VIDEO_VIVID=m
CONFIG_CEC_PLATFORM_DRIVERS=y
CONFIG_VIDEO_SAMSUNG_S5P_CEC=m
# CONFIG_MEDIA_SUBDRV_AUTOSELECT is not set
CONFIG_VIDEO_ADV7180=m
CONFIG_VIDEO_ML86V7667=m
CONFIG_DRM=y
-CONFIG_DRM_I2C_ADV7511=m
-CONFIG_DRM_I2C_ADV7511_AUDIO=y
# CONFIG_DRM_I2C_CH7006 is not set
# CONFIG_DRM_I2C_SIL164 is not set
-CONFIG_DRM_DUMB_VGA_DAC=m
-CONFIG_DRM_NXP_PTN3460=m
-CONFIG_DRM_PARADE_PS8622=m
CONFIG_DRM_NOUVEAU=m
CONFIG_DRM_EXYNOS=m
CONFIG_DRM_EXYNOS_FIMD=y
CONFIG_DRM_SUN4I=m
CONFIG_DRM_FSL_DCU=m
CONFIG_DRM_TEGRA=y
+CONFIG_DRM_PANEL_SIMPLE=y
CONFIG_DRM_PANEL_SAMSUNG_LD9040=m
CONFIG_DRM_PANEL_SAMSUNG_S6E63J0X03=m
CONFIG_DRM_PANEL_SAMSUNG_S6E8AA0=m
-CONFIG_DRM_PANEL_SIMPLE=y
+CONFIG_DRM_DUMB_VGA_DAC=m
+CONFIG_DRM_NXP_PTN3460=m
+CONFIG_DRM_PARADE_PS8622=m
CONFIG_DRM_SII9234=m
+CONFIG_DRM_I2C_ADV7511=m
+CONFIG_DRM_I2C_ADV7511_AUDIO=y
CONFIG_DRM_STI=m
-CONFIG_DRM_VC4=y
+CONFIG_DRM_VC4=m
CONFIG_DRM_ETNAVIV=m
CONFIG_DRM_MXSFB=m
CONFIG_FB_ARMCLCD=y
CONFIG_FB_WM8505=y
CONFIG_FB_SH_MOBILE_LCDC=y
CONFIG_FB_SIMPLE=y
-CONFIG_BACKLIGHT_LCD_SUPPORT=y
-CONFIG_BACKLIGHT_CLASS_DEVICE=y
CONFIG_LCD_PLATFORM=m
CONFIG_BACKLIGHT_PWM=y
CONFIG_BACKLIGHT_AS3711=y
CONFIG_FRAMEBUFFER_CONSOLE_ROTATION=y
CONFIG_SOUND=m
CONFIG_SND=m
-CONFIG_SND_DYNAMIC_MINORS=y
CONFIG_SND_HDA_TEGRA=m
CONFIG_SND_HDA_INPUT_BEEP=y
CONFIG_SND_HDA_PATCH_LOADER=y
CONFIG_SND_SOC_ODROID=m
CONFIG_SND_SOC_SH4_FSI=m
CONFIG_SND_SOC_RCAR=m
-CONFIG_SND_SIMPLE_SCU_CARD=m
+CONFIG_SND_SOC_STI=m
CONFIG_SND_SUN4I_CODEC=m
CONFIG_SND_SOC_TEGRA=m
CONFIG_SND_SOC_TEGRA20_I2S=m
CONFIG_SND_SOC_TEGRA_WM9712=m
CONFIG_SND_SOC_TEGRA_TRIMSLICE=m
CONFIG_SND_SOC_TEGRA_ALC5632=m
-CONFIG_SND_SOC_CPCAP=m
CONFIG_SND_SOC_TEGRA_MAX98090=m
CONFIG_SND_SOC_AK4642=m
+CONFIG_SND_SOC_CPCAP=m
CONFIG_SND_SOC_SGTL5000=m
CONFIG_SND_SOC_SPDIF=m
-CONFIG_SND_SOC_WM8978=m
-CONFIG_SND_SOC_STI=m
CONFIG_SND_SOC_STI_SAS=m
-CONFIG_SND_SIMPLE_CARD=m
+CONFIG_SND_SOC_WM8978=m
+CONFIG_SND_SIMPLE_SCU_CARD=m
CONFIG_USB=y
CONFIG_USB_OTG=y
CONFIG_USB_XHCI_HCD=y
CONFIG_USB_XHCI_MVEBU=y
-CONFIG_USB_XHCI_RCAR=m
CONFIG_USB_XHCI_TEGRA=m
CONFIG_USB_EHCI_HCD=y
-CONFIG_USB_EHCI_MSM=m
-CONFIG_USB_EHCI_EXYNOS=y
-CONFIG_USB_EHCI_TEGRA=y
CONFIG_USB_EHCI_HCD_STI=y
-CONFIG_USB_EHCI_HCD_PLATFORM=y
-CONFIG_USB_ISP1760=y
+CONFIG_USB_EHCI_TEGRA=y
+CONFIG_USB_EHCI_EXYNOS=y
CONFIG_USB_OHCI_HCD=y
CONFIG_USB_OHCI_HCD_STI=y
-CONFIG_USB_OHCI_HCD_PLATFORM=y
CONFIG_USB_OHCI_EXYNOS=m
CONFIG_USB_R8A66597_HCD=m
CONFIG_USB_RENESAS_USBHS=m
CONFIG_USB_TUSB_OMAP_DMA=y
CONFIG_USB_DWC3=y
CONFIG_USB_DWC2=y
-CONFIG_USB_HSIC_USB3503=y
CONFIG_USB_CHIPIDEA=y
CONFIG_USB_CHIPIDEA_UDC=y
CONFIG_USB_CHIPIDEA_HOST=y
+CONFIG_USB_ISP1760=y
+CONFIG_USB_HSIC_USB3503=y
CONFIG_AB8500_USB=y
-CONFIG_KEYSTONE_USB_PHY=y
+CONFIG_KEYSTONE_USB_PHY=m
CONFIG_NOP_USB_XCEIV=m
CONFIG_AM335X_PHY_USB=m
CONFIG_TWL6030_USB=m
CONFIG_USB_GPIO_VBUS=y
CONFIG_USB_ISP1301=y
-CONFIG_USB_MSM_OTG=m
CONFIG_USB_MXS_PHY=y
CONFIG_USB_GADGET=y
CONFIG_USB_FSL_USB2=y
CONFIG_MMC_SDHCI_ESDHC_IMX=y
CONFIG_MMC_SDHCI_DOVE=y
CONFIG_MMC_SDHCI_TEGRA=y
+CONFIG_MMC_SDHCI_S3C=y
CONFIG_MMC_SDHCI_PXAV3=y
CONFIG_MMC_SDHCI_SPEAR=y
-CONFIG_MMC_SDHCI_S3C=y
CONFIG_MMC_SDHCI_S3C_DMA=y
CONFIG_MMC_SDHCI_BCM_KONA=y
+CONFIG_MMC_MESON_MX_SDIO=y
CONFIG_MMC_SDHCI_ST=y
CONFIG_MMC_OMAP=y
CONFIG_MMC_OMAP_HS=y
CONFIG_MMC_ATMELMCI=y
CONFIG_MMC_SDHCI_MSM=y
-CONFIG_MMC_MESON_MX_SDIO=y
CONFIG_MMC_MVSDIO=y
CONFIG_MMC_SDHI=y
CONFIG_MMC_DW=y
-CONFIG_MMC_DW_PLTFM=y
CONFIG_MMC_DW_EXYNOS=y
CONFIG_MMC_DW_ROCKCHIP=y
CONFIG_MMC_SH_MMCIF=y
CONFIG_RTC_DRV_RK808=m
CONFIG_RTC_DRV_RS5C372=m
CONFIG_RTC_DRV_BQ32K=m
-CONFIG_RTC_DRV_PALMAS=y
-CONFIG_RTC_DRV_ST_LPC=y
CONFIG_RTC_DRV_TWL4030=y
+CONFIG_RTC_DRV_PALMAS=y
CONFIG_RTC_DRV_TPS6586X=y
CONFIG_RTC_DRV_TPS65910=y
CONFIG_RTC_DRV_S35390A=m
CONFIG_RTC_DRV_RX8581=m
CONFIG_RTC_DRV_EM3027=y
+CONFIG_RTC_DRV_S5M=m
CONFIG_RTC_DRV_DA9063=m
CONFIG_RTC_DRV_EFI=m
CONFIG_RTC_DRV_DIGICOLOR=m
-CONFIG_RTC_DRV_S5M=m
CONFIG_RTC_DRV_S3C=m
CONFIG_RTC_DRV_PL031=y
CONFIG_RTC_DRV_AT91RM9200=m
CONFIG_RTC_DRV_AT91SAM9=m
CONFIG_RTC_DRV_VT8500=y
-CONFIG_RTC_DRV_SUN6I=y
CONFIG_RTC_DRV_SUNXI=y
CONFIG_RTC_DRV_MV=y
CONFIG_RTC_DRV_TEGRA=y
+CONFIG_RTC_DRV_ST_LPC=y
CONFIG_RTC_DRV_CPCAP=m
CONFIG_DMADEVICES=y
-CONFIG_DW_DMAC=y
CONFIG_AT_HDMAC=y
CONFIG_AT_XDMAC=y
+CONFIG_DMA_BCM2835=y
+CONFIG_DMA_SUN6I=y
CONFIG_FSL_EDMA=y
+CONFIG_IMX_DMA=y
+CONFIG_IMX_SDMA=y
CONFIG_MV_XOR=y
+CONFIG_MXS_DMA=y
+CONFIG_PL330_DMA=y
+CONFIG_SIRF_DMA=y
+CONFIG_STE_DMA40=y
+CONFIG_ST_FDMA=m
CONFIG_TEGRA20_APB_DMA=y
+CONFIG_XILINX_DMA=y
+CONFIG_QCOM_BAM_DMA=y
+CONFIG_DW_DMAC=y
CONFIG_SH_DMAE=y
CONFIG_RCAR_DMAC=y
CONFIG_RENESAS_USB_DMAC=m
-CONFIG_STE_DMA40=y
-CONFIG_SIRF_DMA=y
-CONFIG_TI_EDMA=y
-CONFIG_PL330_DMA=y
-CONFIG_IMX_SDMA=y
-CONFIG_IMX_DMA=y
-CONFIG_MXS_DMA=y
-CONFIG_DMA_BCM2835=y
-CONFIG_DMA_OMAP=y
-CONFIG_QCOM_BAM_DMA=y
-CONFIG_XILINX_DMA=y
-CONFIG_DMA_SUN6I=y
-CONFIG_ST_FDMA=m
+CONFIG_VIRTIO_PCI=y
+CONFIG_VIRTIO_MMIO=y
CONFIG_STAGING=y
-CONFIG_SENSORS_ISL29018=y
-CONFIG_SENSORS_ISL29028=y
CONFIG_MFD_NVEC=y
CONFIG_KEYBOARD_NVEC=y
CONFIG_SERIO_NVEC_PS2=y
CONFIG_NVEC_POWER=y
CONFIG_NVEC_PAZ00=y
-CONFIG_BCMA=y
-CONFIG_BCMA_HOST_SOC=y
-CONFIG_BCMA_DRIVER_GMAC_CMN=y
-CONFIG_BCMA_DRIVER_GPIO=y
-CONFIG_QCOM_GSBI=y
-CONFIG_QCOM_PM=y
-CONFIG_QCOM_SMEM=y
-CONFIG_QCOM_SMD_RPM=y
-CONFIG_QCOM_SMP2P=y
-CONFIG_QCOM_SMSM=y
-CONFIG_QCOM_WCNSS_CTRL=m
-CONFIG_ROCKCHIP_PM_DOMAINS=y
-CONFIG_COMMON_CLK_QCOM=y
-CONFIG_QCOM_CLK_RPM=y
-CONFIG_CHROME_PLATFORMS=y
CONFIG_STAGING_BOARD=y
-CONFIG_CROS_EC_CHARDEV=m
CONFIG_COMMON_CLK_MAX77686=y
CONFIG_COMMON_CLK_RK808=m
CONFIG_COMMON_CLK_S2MPS11=m
+CONFIG_COMMON_CLK_QCOM=y
+CONFIG_QCOM_CLK_RPM=y
CONFIG_APQ_MMCC_8084=y
CONFIG_MSM_GCC_8660=y
CONFIG_MSM_MMCC_8960=y
CONFIG_MSM_MMCC_8974=y
-CONFIG_HWSPINLOCK_QCOM=y
+CONFIG_BCM2835_MBOX=y
CONFIG_ROCKCHIP_IOMMU=y
CONFIG_TEGRA_IOMMU_GART=y
CONFIG_TEGRA_IOMMU_SMMU=y
CONFIG_REMOTEPROC=m
CONFIG_ST_REMOTEPROC=m
CONFIG_RPMSG_VIRTIO=m
+CONFIG_RASPBERRYPI_POWER=y
+CONFIG_QCOM_GSBI=y
+CONFIG_QCOM_PM=y
+CONFIG_QCOM_SMD_RPM=m
+CONFIG_QCOM_WCNSS_CTRL=m
+CONFIG_ROCKCHIP_PM_DOMAINS=y
+CONFIG_ARCH_TEGRA_2x_SOC=y
+CONFIG_ARCH_TEGRA_3x_SOC=y
+CONFIG_ARCH_TEGRA_114_SOC=y
+CONFIG_ARCH_TEGRA_124_SOC=y
CONFIG_PM_DEVFREQ=y
CONFIG_ARM_TEGRA_DEVFREQ=m
-CONFIG_MEMORY=y
-CONFIG_EXTCON=y
CONFIG_TI_AEMIF=y
CONFIG_IIO=y
CONFIG_IIO_SW_TRIGGER=y
CONFIG_XILINX_XADC=y
CONFIG_MPU3050_I2C=y
CONFIG_CM36651=m
+CONFIG_SENSORS_ISL29018=y
+CONFIG_SENSORS_ISL29028=y
CONFIG_AK8975=y
-CONFIG_RASPBERRYPI_POWER=y
CONFIG_IIO_HRTIMER_TRIGGER=y
CONFIG_PWM=y
CONFIG_PWM_ATMEL=m
CONFIG_PWM_ATMEL_HLCDC_PWM=m
CONFIG_PWM_ATMEL_TCB=m
+CONFIG_PWM_BCM2835=y
+CONFIG_PWM_BRCMSTB=m
CONFIG_PWM_FSL_FTM=m
CONFIG_PWM_MESON=m
CONFIG_PWM_RCAR=m
CONFIG_PWM_RENESAS_TPU=y
CONFIG_PWM_ROCKCHIP=m
CONFIG_PWM_SAMSUNG=m
+CONFIG_PWM_STI=y
CONFIG_PWM_SUN4I=y
CONFIG_PWM_TEGRA=y
CONFIG_PWM_VT8500=y
+CONFIG_KEYSTONE_IRQ=y
+CONFIG_PHY_SUN4I_USB=y
+CONFIG_PHY_SUN9I_USB=y
CONFIG_PHY_HIX5HD2_SATA=y
-CONFIG_E1000E=y
-CONFIG_PWM_STI=y
-CONFIG_PWM_BCM2835=y
-CONFIG_PWM_BRCMSTB=m
-CONFIG_PHY_DM816X_USB=m
-CONFIG_OMAP_USB2=y
-CONFIG_TI_PIPE3=y
-CONFIG_TWL4030_USB=m
+CONFIG_PHY_BERLIN_SATA=y
CONFIG_PHY_BERLIN_USB=y
CONFIG_PHY_CPCAP_USB=m
-CONFIG_PHY_BERLIN_SATA=y
+CONFIG_PHY_QCOM_APQ8064_SATA=m
+CONFIG_PHY_RCAR_GEN2=m
CONFIG_PHY_ROCKCHIP_DP=m
CONFIG_PHY_ROCKCHIP_USB=y
-CONFIG_PHY_QCOM_APQ8064_SATA=m
+CONFIG_PHY_SAMSUNG_USB2=m
CONFIG_PHY_MIPHY28LP=y
-CONFIG_PHY_RCAR_GEN2=m
CONFIG_PHY_STIH407_USB=y
CONFIG_PHY_STM32_USBPHYC=y
-CONFIG_PHY_SUN4I_USB=y
-CONFIG_PHY_SUN9I_USB=y
-CONFIG_PHY_SAMSUNG_USB2=m
CONFIG_PHY_TEGRA_XUSB=y
-CONFIG_PHY_BRCM_SATA=y
-CONFIG_NVMEM=y
+CONFIG_PHY_DM816X_USB=m
+CONFIG_OMAP_USB2=y
+CONFIG_TI_PIPE3=y
+CONFIG_TWL4030_USB=m
CONFIG_NVMEM_IMX_OCOTP=y
CONFIG_NVMEM_SUNXI_SID=y
CONFIG_NVMEM_VF610_OCOTP=y
-CONFIG_BCM2835_MBOX=y
CONFIG_RASPBERRYPI_FIRMWARE=y
-CONFIG_EFI_VARS=m
-CONFIG_EFI_CAPSULE_LOADER=m
CONFIG_BCM47XX_NVRAM=y
CONFIG_BCM47XX_SPROM=y
+CONFIG_EFI_VARS=m
+CONFIG_EFI_CAPSULE_LOADER=m
CONFIG_EXT4_FS=y
CONFIG_AUTOFS4_FS=y
CONFIG_MSDOS_FS=y
CONFIG_NTFS_FS=y
CONFIG_TMPFS_POSIX_ACL=y
CONFIG_UBIFS_FS=y
-CONFIG_TMPFS=y
CONFIG_SQUASHFS=y
CONFIG_SQUASHFS_LZO=y
CONFIG_SQUASHFS_XZ=y
CONFIG_NLS_ISO8859_1=y
CONFIG_NLS_UTF8=y
CONFIG_PRINTK_TIME=y
-CONFIG_DEBUG_FS=y
CONFIG_MAGIC_SYSRQ=y
-CONFIG_LOCKUP_DETECTOR=y
-CONFIG_CPUFREQ_DT=y
-CONFIG_KEYSTONE_IRQ=y
-CONFIG_HW_RANDOM=y
-CONFIG_HW_RANDOM_ST=y
CONFIG_CRYPTO_USER=m
CONFIG_CRYPTO_USER_API_HASH=m
CONFIG_CRYPTO_USER_API_SKCIPHER=m
CONFIG_CRYPTO_DEV_MARVELL_CESA=m
CONFIG_CRYPTO_DEV_EXYNOS_RNG=m
CONFIG_CRYPTO_DEV_S5P=m
+CONFIG_CRYPTO_DEV_ATMEL_AES=m
+CONFIG_CRYPTO_DEV_ATMEL_TDES=m
+CONFIG_CRYPTO_DEV_ATMEL_SHA=m
CONFIG_CRYPTO_DEV_SUN4I_SS=m
CONFIG_CRYPTO_DEV_ROCKCHIP=m
CONFIG_ARM_CRYPTO=y
-CONFIG_CRYPTO_SHA1_ARM=m
CONFIG_CRYPTO_SHA1_ARM_NEON=m
CONFIG_CRYPTO_SHA1_ARM_CE=m
CONFIG_CRYPTO_SHA2_ARM_CE=m
-CONFIG_CRYPTO_SHA256_ARM=m
CONFIG_CRYPTO_SHA512_ARM=m
CONFIG_CRYPTO_AES_ARM=m
CONFIG_CRYPTO_AES_ARM_BS=m
CONFIG_CRYPTO_AES_ARM_CE=m
-CONFIG_CRYPTO_CHACHA20_NEON=m
-CONFIG_CRYPTO_CRC32_ARM_CE=m
-CONFIG_CRYPTO_CRCT10DIF_ARM_CE=m
CONFIG_CRYPTO_GHASH_ARM_CE=m
-CONFIG_CRYPTO_DEV_ATMEL_AES=m
-CONFIG_CRYPTO_DEV_ATMEL_TDES=m
-CONFIG_CRYPTO_DEV_ATMEL_SHA=m
-CONFIG_VIDEO_VIVID=m
-CONFIG_VIRTIO=y
-CONFIG_VIRTIO_PCI=y
-CONFIG_VIRTIO_PCI_LEGACY=y
-CONFIG_VIRTIO_MMIO=y
+CONFIG_CRYPTO_CRC32_ARM_CE=m
+CONFIG_CRYPTO_CHACHA20_NEON=m
* Increment event counter and perform fixup for the pre-signal
* frame.
*/
- rseq_signal_deliver(regs);
+ rseq_signal_deliver(ksig, regs);
/*
* Set up the stack frame
} else {
clear_thread_flag(TIF_NOTIFY_RESUME);
tracehook_notify_resume(regs);
- rseq_handle_notify_resume(regs);
+ rseq_handle_notify_resume(NULL, regs);
}
}
local_irq_disable();
select GPIOLIB
select ARM_AMBA
select PINCTRL
+ select PCI_DOMAINS if PCI
help
This enables support for systems based on Broadcom IPROC architected SoCs.
The IPROC complex contains one or more ARM CPUs along with common
GPIO_LOOKUP("davinci_gpio.0", DA850_MMCSD_CD_PIN, "cd",
GPIO_ACTIVE_LOW),
GPIO_LOOKUP("davinci_gpio.0", DA850_MMCSD_WP_PIN, "wp",
- GPIO_ACTIVE_LOW),
+ GPIO_ACTIVE_HIGH),
},
};
select HAVE_ARM_SCU
select HAVE_ARM_TWD if SMP
select MFD_SYSCON
+ select PCI_DOMAINS if PCI
if ARCH_SOCFPGA
config SOCFPGA_SUSPEND
#include <asm/cacheflush.h>
#include <asm/hwcap.h>
#include <asm/opcodes.h>
+#include <asm/system_info.h>
#include "bpf_jit_32.h"
* The callee saved registers depends on whether frame pointers are enabled.
* With frame pointers (to be compliant with the ABI):
*
- * high
- * original ARM_SP => +------------------+ \
- * | pc | |
- * current ARM_FP => +------------------+ } callee saved registers
- * |r4-r8,r10,fp,ip,lr| |
- * +------------------+ /
- * low
+ * high
+ * original ARM_SP => +--------------+ \
+ * | pc | |
+ * current ARM_FP => +--------------+ } callee saved registers
+ * |r4-r9,fp,ip,lr| |
+ * +--------------+ /
+ * low
*
* Without frame pointers:
*
- * high
- * original ARM_SP => +------------------+
- * | r4-r8,r10,fp,lr | callee saved registers
- * current ARM_FP => +------------------+
- * low
+ * high
+ * original ARM_SP => +--------------+
+ * | r4-r9,fp,lr | callee saved registers
+ * current ARM_FP => +--------------+
+ * low
*
* When popping registers off the stack at the end of a BPF function, we
* reference them via the current ARM_FP register.
*/
#define CALLEE_MASK (1 << ARM_R4 | 1 << ARM_R5 | 1 << ARM_R6 | \
- 1 << ARM_R7 | 1 << ARM_R8 | 1 << ARM_R10 | \
+ 1 << ARM_R7 | 1 << ARM_R8 | 1 << ARM_R9 | \
1 << ARM_FP)
#define CALLEE_PUSH_MASK (CALLEE_MASK | 1 << ARM_LR)
#define CALLEE_POP_MASK (CALLEE_MASK | 1 << ARM_PC)
-#define STACK_OFFSET(k) (k)
+enum {
+ /* Stack layout - these are offsets from (top of stack - 4) */
+ BPF_R2_HI,
+ BPF_R2_LO,
+ BPF_R3_HI,
+ BPF_R3_LO,
+ BPF_R4_HI,
+ BPF_R4_LO,
+ BPF_R5_HI,
+ BPF_R5_LO,
+ BPF_R7_HI,
+ BPF_R7_LO,
+ BPF_R8_HI,
+ BPF_R8_LO,
+ BPF_R9_HI,
+ BPF_R9_LO,
+ BPF_FP_HI,
+ BPF_FP_LO,
+ BPF_TC_HI,
+ BPF_TC_LO,
+ BPF_AX_HI,
+ BPF_AX_LO,
+ /* Stack space for BPF_REG_2, BPF_REG_3, BPF_REG_4,
+ * BPF_REG_5, BPF_REG_7, BPF_REG_8, BPF_REG_9,
+ * BPF_REG_FP and Tail call counts.
+ */
+ BPF_JIT_SCRATCH_REGS,
+};
+
+/*
+ * Negative "register" values indicate the register is stored on the stack
+ * and are the offset from the top of the eBPF JIT scratch space.
+ */
+#define STACK_OFFSET(k) (-4 - (k) * 4)
+#define SCRATCH_SIZE (BPF_JIT_SCRATCH_REGS * 4)
+
+#ifdef CONFIG_FRAME_POINTER
+#define EBPF_SCRATCH_TO_ARM_FP(x) ((x) - 4 * hweight16(CALLEE_PUSH_MASK) - 4)
+#else
+#define EBPF_SCRATCH_TO_ARM_FP(x) (x)
+#endif
+
#define TMP_REG_1 (MAX_BPF_JIT_REG + 0) /* TEMP Register 1 */
#define TMP_REG_2 (MAX_BPF_JIT_REG + 1) /* TEMP Register 2 */
#define TCALL_CNT (MAX_BPF_JIT_REG + 2) /* Tail Call Count */
* scratch memory space and we have to build eBPF 64 bit register from those.
*
*/
-static const u8 bpf2a32[][2] = {
+static const s8 bpf2a32[][2] = {
/* return value from in-kernel function, and exit value from eBPF */
[BPF_REG_0] = {ARM_R1, ARM_R0},
/* arguments from eBPF program to in-kernel function */
[BPF_REG_1] = {ARM_R3, ARM_R2},
/* Stored on stack scratch space */
- [BPF_REG_2] = {STACK_OFFSET(0), STACK_OFFSET(4)},
- [BPF_REG_3] = {STACK_OFFSET(8), STACK_OFFSET(12)},
- [BPF_REG_4] = {STACK_OFFSET(16), STACK_OFFSET(20)},
- [BPF_REG_5] = {STACK_OFFSET(24), STACK_OFFSET(28)},
+ [BPF_REG_2] = {STACK_OFFSET(BPF_R2_HI), STACK_OFFSET(BPF_R2_LO)},
+ [BPF_REG_3] = {STACK_OFFSET(BPF_R3_HI), STACK_OFFSET(BPF_R3_LO)},
+ [BPF_REG_4] = {STACK_OFFSET(BPF_R4_HI), STACK_OFFSET(BPF_R4_LO)},
+ [BPF_REG_5] = {STACK_OFFSET(BPF_R5_HI), STACK_OFFSET(BPF_R5_LO)},
/* callee saved registers that in-kernel function will preserve */
[BPF_REG_6] = {ARM_R5, ARM_R4},
/* Stored on stack scratch space */
- [BPF_REG_7] = {STACK_OFFSET(32), STACK_OFFSET(36)},
- [BPF_REG_8] = {STACK_OFFSET(40), STACK_OFFSET(44)},
- [BPF_REG_9] = {STACK_OFFSET(48), STACK_OFFSET(52)},
+ [BPF_REG_7] = {STACK_OFFSET(BPF_R7_HI), STACK_OFFSET(BPF_R7_LO)},
+ [BPF_REG_8] = {STACK_OFFSET(BPF_R8_HI), STACK_OFFSET(BPF_R8_LO)},
+ [BPF_REG_9] = {STACK_OFFSET(BPF_R9_HI), STACK_OFFSET(BPF_R9_LO)},
/* Read only Frame Pointer to access Stack */
- [BPF_REG_FP] = {STACK_OFFSET(56), STACK_OFFSET(60)},
+ [BPF_REG_FP] = {STACK_OFFSET(BPF_FP_HI), STACK_OFFSET(BPF_FP_LO)},
/* Temporary Register for internal BPF JIT, can be used
* for constant blindings and others.
*/
[TMP_REG_1] = {ARM_R7, ARM_R6},
- [TMP_REG_2] = {ARM_R10, ARM_R8},
+ [TMP_REG_2] = {ARM_R9, ARM_R8},
/* Tail call count. Stored on stack scratch space. */
- [TCALL_CNT] = {STACK_OFFSET(64), STACK_OFFSET(68)},
+ [TCALL_CNT] = {STACK_OFFSET(BPF_TC_HI), STACK_OFFSET(BPF_TC_LO)},
/* temporary register for blinding constants.
* Stored on stack scratch space.
*/
- [BPF_REG_AX] = {STACK_OFFSET(72), STACK_OFFSET(76)},
+ [BPF_REG_AX] = {STACK_OFFSET(BPF_AX_HI), STACK_OFFSET(BPF_AX_LO)},
};
#define dst_lo dst[1]
unsigned int idx;
unsigned int prologue_bytes;
unsigned int epilogue_offset;
+ unsigned int cpu_architecture;
u32 flags;
u32 *offsets;
u32 *target;
_emit(ARM_COND_AL, inst, ctx);
}
+/*
+ * This is rather horrid, but necessary to convert an integer constant
+ * to an immediate operand for the opcodes, and be able to detect at
+ * build time whether the constant can't be converted (iow, usable in
+ * BUILD_BUG_ON()).
+ */
+#define imm12val(v, s) (rol32(v, (s)) | (s) << 7)
+#define const_imm8m(x) \
+ ({ int r; \
+ u32 v = (x); \
+ if (!(v & ~0x000000ff)) \
+ r = imm12val(v, 0); \
+ else if (!(v & ~0xc000003f)) \
+ r = imm12val(v, 2); \
+ else if (!(v & ~0xf000000f)) \
+ r = imm12val(v, 4); \
+ else if (!(v & ~0xfc000003)) \
+ r = imm12val(v, 6); \
+ else if (!(v & ~0xff000000)) \
+ r = imm12val(v, 8); \
+ else if (!(v & ~0x3fc00000)) \
+ r = imm12val(v, 10); \
+ else if (!(v & ~0x0ff00000)) \
+ r = imm12val(v, 12); \
+ else if (!(v & ~0x03fc0000)) \
+ r = imm12val(v, 14); \
+ else if (!(v & ~0x00ff0000)) \
+ r = imm12val(v, 16); \
+ else if (!(v & ~0x003fc000)) \
+ r = imm12val(v, 18); \
+ else if (!(v & ~0x000ff000)) \
+ r = imm12val(v, 20); \
+ else if (!(v & ~0x0003fc00)) \
+ r = imm12val(v, 22); \
+ else if (!(v & ~0x0000ff00)) \
+ r = imm12val(v, 24); \
+ else if (!(v & ~0x00003fc0)) \
+ r = imm12val(v, 26); \
+ else if (!(v & ~0x00000ff0)) \
+ r = imm12val(v, 28); \
+ else if (!(v & ~0x000003fc)) \
+ r = imm12val(v, 30); \
+ else \
+ r = -1; \
+ r; })
+
/*
* Checks if immediate value can be converted to imm12(12 bits) value.
*/
-static int16_t imm8m(u32 x)
+static int imm8m(u32 x)
{
u32 rot;
return -1;
}
+#define imm8m(x) (__builtin_constant_p(x) ? const_imm8m(x) : imm8m(x))
+
+static u32 arm_bpf_ldst_imm12(u32 op, u8 rt, u8 rn, s16 imm12)
+{
+ op |= rt << 12 | rn << 16;
+ if (imm12 >= 0)
+ op |= ARM_INST_LDST__U;
+ else
+ imm12 = -imm12;
+ return op | (imm12 & ARM_INST_LDST__IMM12);
+}
+
+static u32 arm_bpf_ldst_imm8(u32 op, u8 rt, u8 rn, s16 imm8)
+{
+ op |= rt << 12 | rn << 16;
+ if (imm8 >= 0)
+ op |= ARM_INST_LDST__U;
+ else
+ imm8 = -imm8;
+ return op | (imm8 & 0xf0) << 4 | (imm8 & 0x0f);
+}
+
+#define ARM_LDR_I(rt, rn, off) arm_bpf_ldst_imm12(ARM_INST_LDR_I, rt, rn, off)
+#define ARM_LDRB_I(rt, rn, off) arm_bpf_ldst_imm12(ARM_INST_LDRB_I, rt, rn, off)
+#define ARM_LDRD_I(rt, rn, off) arm_bpf_ldst_imm8(ARM_INST_LDRD_I, rt, rn, off)
+#define ARM_LDRH_I(rt, rn, off) arm_bpf_ldst_imm8(ARM_INST_LDRH_I, rt, rn, off)
+
+#define ARM_STR_I(rt, rn, off) arm_bpf_ldst_imm12(ARM_INST_STR_I, rt, rn, off)
+#define ARM_STRB_I(rt, rn, off) arm_bpf_ldst_imm12(ARM_INST_STRB_I, rt, rn, off)
+#define ARM_STRD_I(rt, rn, off) arm_bpf_ldst_imm8(ARM_INST_STRD_I, rt, rn, off)
+#define ARM_STRH_I(rt, rn, off) arm_bpf_ldst_imm8(ARM_INST_STRH_I, rt, rn, off)
+
/*
* Initializes the JIT space with undefined instructions.
*/
#define STACK_ALIGNMENT 4
#endif
-/* Stack space for BPF_REG_2, BPF_REG_3, BPF_REG_4,
- * BPF_REG_5, BPF_REG_7, BPF_REG_8, BPF_REG_9,
- * BPF_REG_FP and Tail call counts.
- */
-#define SCRATCH_SIZE 80
-
/* total stack size used in JITed code */
#define _STACK_SIZE (ctx->prog->aux->stack_depth + SCRATCH_SIZE)
#define STACK_SIZE ALIGN(_STACK_SIZE, STACK_ALIGNMENT)
-/* Get the offset of eBPF REGISTERs stored on scratch space. */
-#define STACK_VAR(off) (STACK_SIZE - off)
-
#if __LINUX_ARM_ARCH__ < 7
static u16 imm_offset(u32 k, struct jit_ctx *ctx)
static inline void emit_udivmod(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx, u8 op)
{
- const u8 *tmp = bpf2a32[TMP_REG_1];
+ const s8 *tmp = bpf2a32[TMP_REG_1];
#if __LINUX_ARM_ARCH__ == 7
if (elf_hwcap & HWCAP_IDIVA) {
emit(ARM_MOV_R(ARM_R0, tmp[1]), ctx);
}
-/* Checks whether BPF register is on scratch stack space or not. */
-static inline bool is_on_stack(u8 bpf_reg)
+/* Is the translated BPF register on stack? */
+static bool is_stacked(s8 reg)
+{
+ return reg < 0;
+}
+
+/* If a BPF register is on the stack (stk is true), load it to the
+ * supplied temporary register and return the temporary register
+ * for subsequent operations, otherwise just use the CPU register.
+ */
+static s8 arm_bpf_get_reg32(s8 reg, s8 tmp, struct jit_ctx *ctx)
+{
+ if (is_stacked(reg)) {
+ emit(ARM_LDR_I(tmp, ARM_FP, EBPF_SCRATCH_TO_ARM_FP(reg)), ctx);
+ reg = tmp;
+ }
+ return reg;
+}
+
+static const s8 *arm_bpf_get_reg64(const s8 *reg, const s8 *tmp,
+ struct jit_ctx *ctx)
{
- static u8 stack_regs[] = {BPF_REG_AX, BPF_REG_3, BPF_REG_4, BPF_REG_5,
- BPF_REG_7, BPF_REG_8, BPF_REG_9, TCALL_CNT,
- BPF_REG_2, BPF_REG_FP};
- int i, reg_len = sizeof(stack_regs);
-
- for (i = 0 ; i < reg_len ; i++) {
- if (bpf_reg == stack_regs[i])
- return true;
+ if (is_stacked(reg[1])) {
+ if (__LINUX_ARM_ARCH__ >= 6 ||
+ ctx->cpu_architecture >= CPU_ARCH_ARMv5TE) {
+ emit(ARM_LDRD_I(tmp[1], ARM_FP,
+ EBPF_SCRATCH_TO_ARM_FP(reg[1])), ctx);
+ } else {
+ emit(ARM_LDR_I(tmp[1], ARM_FP,
+ EBPF_SCRATCH_TO_ARM_FP(reg[1])), ctx);
+ emit(ARM_LDR_I(tmp[0], ARM_FP,
+ EBPF_SCRATCH_TO_ARM_FP(reg[0])), ctx);
+ }
+ reg = tmp;
+ }
+ return reg;
+}
+
+/* If a BPF register is on the stack (stk is true), save the register
+ * back to the stack. If the source register is not the same, then
+ * move it into the correct register.
+ */
+static void arm_bpf_put_reg32(s8 reg, s8 src, struct jit_ctx *ctx)
+{
+ if (is_stacked(reg))
+ emit(ARM_STR_I(src, ARM_FP, EBPF_SCRATCH_TO_ARM_FP(reg)), ctx);
+ else if (reg != src)
+ emit(ARM_MOV_R(reg, src), ctx);
+}
+
+static void arm_bpf_put_reg64(const s8 *reg, const s8 *src,
+ struct jit_ctx *ctx)
+{
+ if (is_stacked(reg[1])) {
+ if (__LINUX_ARM_ARCH__ >= 6 ||
+ ctx->cpu_architecture >= CPU_ARCH_ARMv5TE) {
+ emit(ARM_STRD_I(src[1], ARM_FP,
+ EBPF_SCRATCH_TO_ARM_FP(reg[1])), ctx);
+ } else {
+ emit(ARM_STR_I(src[1], ARM_FP,
+ EBPF_SCRATCH_TO_ARM_FP(reg[1])), ctx);
+ emit(ARM_STR_I(src[0], ARM_FP,
+ EBPF_SCRATCH_TO_ARM_FP(reg[0])), ctx);
+ }
+ } else {
+ if (reg[1] != src[1])
+ emit(ARM_MOV_R(reg[1], src[1]), ctx);
+ if (reg[0] != src[0])
+ emit(ARM_MOV_R(reg[0], src[0]), ctx);
}
- return false;
}
-static inline void emit_a32_mov_i(const u8 dst, const u32 val,
- bool dstk, struct jit_ctx *ctx)
+static inline void emit_a32_mov_i(const s8 dst, const u32 val,
+ struct jit_ctx *ctx)
{
- const u8 *tmp = bpf2a32[TMP_REG_1];
+ const s8 *tmp = bpf2a32[TMP_REG_1];
- if (dstk) {
+ if (is_stacked(dst)) {
emit_mov_i(tmp[1], val, ctx);
- emit(ARM_STR_I(tmp[1], ARM_SP, STACK_VAR(dst)), ctx);
+ arm_bpf_put_reg32(dst, tmp[1], ctx);
} else {
emit_mov_i(dst, val, ctx);
}
}
+static void emit_a32_mov_i64(const s8 dst[], u64 val, struct jit_ctx *ctx)
+{
+ const s8 *tmp = bpf2a32[TMP_REG_1];
+ const s8 *rd = is_stacked(dst_lo) ? tmp : dst;
+
+ emit_mov_i(rd[1], (u32)val, ctx);
+ emit_mov_i(rd[0], val >> 32, ctx);
+
+ arm_bpf_put_reg64(dst, rd, ctx);
+}
+
/* Sign extended move */
-static inline void emit_a32_mov_i64(const bool is64, const u8 dst[],
- const u32 val, bool dstk,
- struct jit_ctx *ctx) {
- u32 hi = 0;
+static inline void emit_a32_mov_se_i64(const bool is64, const s8 dst[],
+ const u32 val, struct jit_ctx *ctx) {
+ u64 val64 = val;
if (is64 && (val & (1<<31)))
- hi = (u32)~0;
- emit_a32_mov_i(dst_lo, val, dstk, ctx);
- emit_a32_mov_i(dst_hi, hi, dstk, ctx);
+ val64 |= 0xffffffff00000000ULL;
+ emit_a32_mov_i64(dst, val64, ctx);
}
static inline void emit_a32_add_r(const u8 dst, const u8 src,
/* ALU operation (32 bit)
* dst = dst (op) src
*/
-static inline void emit_a32_alu_r(const u8 dst, const u8 src,
- bool dstk, bool sstk,
+static inline void emit_a32_alu_r(const s8 dst, const s8 src,
struct jit_ctx *ctx, const bool is64,
const bool hi, const u8 op) {
- const u8 *tmp = bpf2a32[TMP_REG_1];
- u8 rn = sstk ? tmp[1] : src;
-
- if (sstk)
- emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src)), ctx);
+ const s8 *tmp = bpf2a32[TMP_REG_1];
+ s8 rn, rd;
+ rn = arm_bpf_get_reg32(src, tmp[1], ctx);
+ rd = arm_bpf_get_reg32(dst, tmp[0], ctx);
/* ALU operation */
- if (dstk) {
- emit(ARM_LDR_I(tmp[0], ARM_SP, STACK_VAR(dst)), ctx);
- emit_alu_r(tmp[0], rn, is64, hi, op, ctx);
- emit(ARM_STR_I(tmp[0], ARM_SP, STACK_VAR(dst)), ctx);
- } else {
- emit_alu_r(dst, rn, is64, hi, op, ctx);
- }
+ emit_alu_r(rd, rn, is64, hi, op, ctx);
+ arm_bpf_put_reg32(dst, rd, ctx);
}
/* ALU operation (64 bit) */
-static inline void emit_a32_alu_r64(const bool is64, const u8 dst[],
- const u8 src[], bool dstk,
- bool sstk, struct jit_ctx *ctx,
+static inline void emit_a32_alu_r64(const bool is64, const s8 dst[],
+ const s8 src[], struct jit_ctx *ctx,
const u8 op) {
- emit_a32_alu_r(dst_lo, src_lo, dstk, sstk, ctx, is64, false, op);
- if (is64)
- emit_a32_alu_r(dst_hi, src_hi, dstk, sstk, ctx, is64, true, op);
- else
- emit_a32_mov_i(dst_hi, 0, dstk, ctx);
+ const s8 *tmp = bpf2a32[TMP_REG_1];
+ const s8 *tmp2 = bpf2a32[TMP_REG_2];
+ const s8 *rd;
+
+ rd = arm_bpf_get_reg64(dst, tmp, ctx);
+ if (is64) {
+ const s8 *rs;
+
+ rs = arm_bpf_get_reg64(src, tmp2, ctx);
+
+ /* ALU operation */
+ emit_alu_r(rd[1], rs[1], true, false, op, ctx);
+ emit_alu_r(rd[0], rs[0], true, true, op, ctx);
+ } else {
+ s8 rs;
+
+ rs = arm_bpf_get_reg32(src_lo, tmp2[1], ctx);
+
+ /* ALU operation */
+ emit_alu_r(rd[1], rs, true, false, op, ctx);
+ emit_a32_mov_i(rd[0], 0, ctx);
+ }
+
+ arm_bpf_put_reg64(dst, rd, ctx);
}
-/* dst = imm (4 bytes)*/
-static inline void emit_a32_mov_r(const u8 dst, const u8 src,
- bool dstk, bool sstk,
+/* dst = src (4 bytes)*/
+static inline void emit_a32_mov_r(const s8 dst, const s8 src,
struct jit_ctx *ctx) {
- const u8 *tmp = bpf2a32[TMP_REG_1];
- u8 rt = sstk ? tmp[0] : src;
+ const s8 *tmp = bpf2a32[TMP_REG_1];
+ s8 rt;
- if (sstk)
- emit(ARM_LDR_I(tmp[0], ARM_SP, STACK_VAR(src)), ctx);
- if (dstk)
- emit(ARM_STR_I(rt, ARM_SP, STACK_VAR(dst)), ctx);
- else
- emit(ARM_MOV_R(dst, rt), ctx);
+ rt = arm_bpf_get_reg32(src, tmp[0], ctx);
+ arm_bpf_put_reg32(dst, rt, ctx);
}
/* dst = src */
-static inline void emit_a32_mov_r64(const bool is64, const u8 dst[],
- const u8 src[], bool dstk,
- bool sstk, struct jit_ctx *ctx) {
- emit_a32_mov_r(dst_lo, src_lo, dstk, sstk, ctx);
- if (is64) {
+static inline void emit_a32_mov_r64(const bool is64, const s8 dst[],
+ const s8 src[],
+ struct jit_ctx *ctx) {
+ if (!is64) {
+ emit_a32_mov_r(dst_lo, src_lo, ctx);
+ /* Zero out high 4 bytes */
+ emit_a32_mov_i(dst_hi, 0, ctx);
+ } else if (__LINUX_ARM_ARCH__ < 6 &&
+ ctx->cpu_architecture < CPU_ARCH_ARMv5TE) {
/* complete 8 byte move */
- emit_a32_mov_r(dst_hi, src_hi, dstk, sstk, ctx);
+ emit_a32_mov_r(dst_lo, src_lo, ctx);
+ emit_a32_mov_r(dst_hi, src_hi, ctx);
+ } else if (is_stacked(src_lo) && is_stacked(dst_lo)) {
+ const u8 *tmp = bpf2a32[TMP_REG_1];
+
+ emit(ARM_LDRD_I(tmp[1], ARM_FP, EBPF_SCRATCH_TO_ARM_FP(src_lo)), ctx);
+ emit(ARM_STRD_I(tmp[1], ARM_FP, EBPF_SCRATCH_TO_ARM_FP(dst_lo)), ctx);
+ } else if (is_stacked(src_lo)) {
+ emit(ARM_LDRD_I(dst[1], ARM_FP, EBPF_SCRATCH_TO_ARM_FP(src_lo)), ctx);
+ } else if (is_stacked(dst_lo)) {
+ emit(ARM_STRD_I(src[1], ARM_FP, EBPF_SCRATCH_TO_ARM_FP(dst_lo)), ctx);
} else {
- /* Zero out high 4 bytes */
- emit_a32_mov_i(dst_hi, 0, dstk, ctx);
+ emit(ARM_MOV_R(dst[0], src[0]), ctx);
+ emit(ARM_MOV_R(dst[1], src[1]), ctx);
}
}
/* Shift operations */
-static inline void emit_a32_alu_i(const u8 dst, const u32 val, bool dstk,
+static inline void emit_a32_alu_i(const s8 dst, const u32 val,
struct jit_ctx *ctx, const u8 op) {
- const u8 *tmp = bpf2a32[TMP_REG_1];
- u8 rd = dstk ? tmp[0] : dst;
+ const s8 *tmp = bpf2a32[TMP_REG_1];
+ s8 rd;
- if (dstk)
- emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst)), ctx);
+ rd = arm_bpf_get_reg32(dst, tmp[0], ctx);
/* Do shift operation */
switch (op) {
break;
}
- if (dstk)
- emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst)), ctx);
+ arm_bpf_put_reg32(dst, rd, ctx);
}
/* dst = ~dst (64 bit) */
-static inline void emit_a32_neg64(const u8 dst[], bool dstk,
+static inline void emit_a32_neg64(const s8 dst[],
struct jit_ctx *ctx){
- const u8 *tmp = bpf2a32[TMP_REG_1];
- u8 rd = dstk ? tmp[1] : dst[1];
- u8 rm = dstk ? tmp[0] : dst[0];
+ const s8 *tmp = bpf2a32[TMP_REG_1];
+ const s8 *rd;
/* Setup Operand */
- if (dstk) {
- emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
- emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
- }
+ rd = arm_bpf_get_reg64(dst, tmp, ctx);
/* Do Negate Operation */
- emit(ARM_RSBS_I(rd, rd, 0), ctx);
- emit(ARM_RSC_I(rm, rm, 0), ctx);
+ emit(ARM_RSBS_I(rd[1], rd[1], 0), ctx);
+ emit(ARM_RSC_I(rd[0], rd[0], 0), ctx);
- if (dstk) {
- emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
- emit(ARM_STR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
- }
+ arm_bpf_put_reg64(dst, rd, ctx);
}
/* dst = dst << src */
-static inline void emit_a32_lsh_r64(const u8 dst[], const u8 src[], bool dstk,
- bool sstk, struct jit_ctx *ctx) {
- const u8 *tmp = bpf2a32[TMP_REG_1];
- const u8 *tmp2 = bpf2a32[TMP_REG_2];
+static inline void emit_a32_lsh_r64(const s8 dst[], const s8 src[],
+ struct jit_ctx *ctx) {
+ const s8 *tmp = bpf2a32[TMP_REG_1];
+ const s8 *tmp2 = bpf2a32[TMP_REG_2];
+ const s8 *rd;
+ s8 rt;
/* Setup Operands */
- u8 rt = sstk ? tmp2[1] : src_lo;
- u8 rd = dstk ? tmp[1] : dst_lo;
- u8 rm = dstk ? tmp[0] : dst_hi;
-
- if (sstk)
- emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(src_lo)), ctx);
- if (dstk) {
- emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
- emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
- }
+ rt = arm_bpf_get_reg32(src_lo, tmp2[1], ctx);
+ rd = arm_bpf_get_reg64(dst, tmp, ctx);
/* Do LSH operation */
emit(ARM_SUB_I(ARM_IP, rt, 32), ctx);
emit(ARM_RSB_I(tmp2[0], rt, 32), ctx);
- emit(ARM_MOV_SR(ARM_LR, rm, SRTYPE_ASL, rt), ctx);
- emit(ARM_ORR_SR(ARM_LR, ARM_LR, rd, SRTYPE_ASL, ARM_IP), ctx);
- emit(ARM_ORR_SR(ARM_IP, ARM_LR, rd, SRTYPE_LSR, tmp2[0]), ctx);
- emit(ARM_MOV_SR(ARM_LR, rd, SRTYPE_ASL, rt), ctx);
-
- if (dstk) {
- emit(ARM_STR_I(ARM_LR, ARM_SP, STACK_VAR(dst_lo)), ctx);
- emit(ARM_STR_I(ARM_IP, ARM_SP, STACK_VAR(dst_hi)), ctx);
- } else {
- emit(ARM_MOV_R(rd, ARM_LR), ctx);
- emit(ARM_MOV_R(rm, ARM_IP), ctx);
- }
+ emit(ARM_MOV_SR(ARM_LR, rd[0], SRTYPE_ASL, rt), ctx);
+ emit(ARM_ORR_SR(ARM_LR, ARM_LR, rd[1], SRTYPE_ASL, ARM_IP), ctx);
+ emit(ARM_ORR_SR(ARM_IP, ARM_LR, rd[1], SRTYPE_LSR, tmp2[0]), ctx);
+ emit(ARM_MOV_SR(ARM_LR, rd[1], SRTYPE_ASL, rt), ctx);
+
+ arm_bpf_put_reg32(dst_lo, ARM_LR, ctx);
+ arm_bpf_put_reg32(dst_hi, ARM_IP, ctx);
}
/* dst = dst >> src (signed)*/
-static inline void emit_a32_arsh_r64(const u8 dst[], const u8 src[], bool dstk,
- bool sstk, struct jit_ctx *ctx) {
- const u8 *tmp = bpf2a32[TMP_REG_1];
- const u8 *tmp2 = bpf2a32[TMP_REG_2];
+static inline void emit_a32_arsh_r64(const s8 dst[], const s8 src[],
+ struct jit_ctx *ctx) {
+ const s8 *tmp = bpf2a32[TMP_REG_1];
+ const s8 *tmp2 = bpf2a32[TMP_REG_2];
+ const s8 *rd;
+ s8 rt;
+
/* Setup Operands */
- u8 rt = sstk ? tmp2[1] : src_lo;
- u8 rd = dstk ? tmp[1] : dst_lo;
- u8 rm = dstk ? tmp[0] : dst_hi;
-
- if (sstk)
- emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(src_lo)), ctx);
- if (dstk) {
- emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
- emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
- }
+ rt = arm_bpf_get_reg32(src_lo, tmp2[1], ctx);
+ rd = arm_bpf_get_reg64(dst, tmp, ctx);
/* Do the ARSH operation */
emit(ARM_RSB_I(ARM_IP, rt, 32), ctx);
emit(ARM_SUBS_I(tmp2[0], rt, 32), ctx);
- emit(ARM_MOV_SR(ARM_LR, rd, SRTYPE_LSR, rt), ctx);
- emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_ASL, ARM_IP), ctx);
+ emit(ARM_MOV_SR(ARM_LR, rd[1], SRTYPE_LSR, rt), ctx);
+ emit(ARM_ORR_SR(ARM_LR, ARM_LR, rd[0], SRTYPE_ASL, ARM_IP), ctx);
_emit(ARM_COND_MI, ARM_B(0), ctx);
- emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_ASR, tmp2[0]), ctx);
- emit(ARM_MOV_SR(ARM_IP, rm, SRTYPE_ASR, rt), ctx);
- if (dstk) {
- emit(ARM_STR_I(ARM_LR, ARM_SP, STACK_VAR(dst_lo)), ctx);
- emit(ARM_STR_I(ARM_IP, ARM_SP, STACK_VAR(dst_hi)), ctx);
- } else {
- emit(ARM_MOV_R(rd, ARM_LR), ctx);
- emit(ARM_MOV_R(rm, ARM_IP), ctx);
- }
+ emit(ARM_ORR_SR(ARM_LR, ARM_LR, rd[0], SRTYPE_ASR, tmp2[0]), ctx);
+ emit(ARM_MOV_SR(ARM_IP, rd[0], SRTYPE_ASR, rt), ctx);
+
+ arm_bpf_put_reg32(dst_lo, ARM_LR, ctx);
+ arm_bpf_put_reg32(dst_hi, ARM_IP, ctx);
}
/* dst = dst >> src */
-static inline void emit_a32_rsh_r64(const u8 dst[], const u8 src[], bool dstk,
- bool sstk, struct jit_ctx *ctx) {
- const u8 *tmp = bpf2a32[TMP_REG_1];
- const u8 *tmp2 = bpf2a32[TMP_REG_2];
+static inline void emit_a32_rsh_r64(const s8 dst[], const s8 src[],
+ struct jit_ctx *ctx) {
+ const s8 *tmp = bpf2a32[TMP_REG_1];
+ const s8 *tmp2 = bpf2a32[TMP_REG_2];
+ const s8 *rd;
+ s8 rt;
+
/* Setup Operands */
- u8 rt = sstk ? tmp2[1] : src_lo;
- u8 rd = dstk ? tmp[1] : dst_lo;
- u8 rm = dstk ? tmp[0] : dst_hi;
-
- if (sstk)
- emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(src_lo)), ctx);
- if (dstk) {
- emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
- emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
- }
+ rt = arm_bpf_get_reg32(src_lo, tmp2[1], ctx);
+ rd = arm_bpf_get_reg64(dst, tmp, ctx);
/* Do RSH operation */
emit(ARM_RSB_I(ARM_IP, rt, 32), ctx);
emit(ARM_SUBS_I(tmp2[0], rt, 32), ctx);
- emit(ARM_MOV_SR(ARM_LR, rd, SRTYPE_LSR, rt), ctx);
- emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_ASL, ARM_IP), ctx);
- emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_LSR, tmp2[0]), ctx);
- emit(ARM_MOV_SR(ARM_IP, rm, SRTYPE_LSR, rt), ctx);
- if (dstk) {
- emit(ARM_STR_I(ARM_LR, ARM_SP, STACK_VAR(dst_lo)), ctx);
- emit(ARM_STR_I(ARM_IP, ARM_SP, STACK_VAR(dst_hi)), ctx);
- } else {
- emit(ARM_MOV_R(rd, ARM_LR), ctx);
- emit(ARM_MOV_R(rm, ARM_IP), ctx);
- }
+ emit(ARM_MOV_SR(ARM_LR, rd[1], SRTYPE_LSR, rt), ctx);
+ emit(ARM_ORR_SR(ARM_LR, ARM_LR, rd[0], SRTYPE_ASL, ARM_IP), ctx);
+ emit(ARM_ORR_SR(ARM_LR, ARM_LR, rd[0], SRTYPE_LSR, tmp2[0]), ctx);
+ emit(ARM_MOV_SR(ARM_IP, rd[0], SRTYPE_LSR, rt), ctx);
+
+ arm_bpf_put_reg32(dst_lo, ARM_LR, ctx);
+ arm_bpf_put_reg32(dst_hi, ARM_IP, ctx);
}
/* dst = dst << val */
-static inline void emit_a32_lsh_i64(const u8 dst[], bool dstk,
- const u32 val, struct jit_ctx *ctx){
- const u8 *tmp = bpf2a32[TMP_REG_1];
- const u8 *tmp2 = bpf2a32[TMP_REG_2];
- /* Setup operands */
- u8 rd = dstk ? tmp[1] : dst_lo;
- u8 rm = dstk ? tmp[0] : dst_hi;
+static inline void emit_a32_lsh_i64(const s8 dst[],
+ const u32 val, struct jit_ctx *ctx){
+ const s8 *tmp = bpf2a32[TMP_REG_1];
+ const s8 *tmp2 = bpf2a32[TMP_REG_2];
+ const s8 *rd;
- if (dstk) {
- emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
- emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
- }
+ /* Setup operands */
+ rd = arm_bpf_get_reg64(dst, tmp, ctx);
/* Do LSH operation */
if (val < 32) {
- emit(ARM_MOV_SI(tmp2[0], rm, SRTYPE_ASL, val), ctx);
- emit(ARM_ORR_SI(rm, tmp2[0], rd, SRTYPE_LSR, 32 - val), ctx);
- emit(ARM_MOV_SI(rd, rd, SRTYPE_ASL, val), ctx);
+ emit(ARM_MOV_SI(tmp2[0], rd[0], SRTYPE_ASL, val), ctx);
+ emit(ARM_ORR_SI(rd[0], tmp2[0], rd[1], SRTYPE_LSR, 32 - val), ctx);
+ emit(ARM_MOV_SI(rd[1], rd[1], SRTYPE_ASL, val), ctx);
} else {
if (val == 32)
- emit(ARM_MOV_R(rm, rd), ctx);
+ emit(ARM_MOV_R(rd[0], rd[1]), ctx);
else
- emit(ARM_MOV_SI(rm, rd, SRTYPE_ASL, val - 32), ctx);
- emit(ARM_EOR_R(rd, rd, rd), ctx);
+ emit(ARM_MOV_SI(rd[0], rd[1], SRTYPE_ASL, val - 32), ctx);
+ emit(ARM_EOR_R(rd[1], rd[1], rd[1]), ctx);
}
- if (dstk) {
- emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
- emit(ARM_STR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
- }
+ arm_bpf_put_reg64(dst, rd, ctx);
}
/* dst = dst >> val */
-static inline void emit_a32_rsh_i64(const u8 dst[], bool dstk,
+static inline void emit_a32_rsh_i64(const s8 dst[],
const u32 val, struct jit_ctx *ctx) {
- const u8 *tmp = bpf2a32[TMP_REG_1];
- const u8 *tmp2 = bpf2a32[TMP_REG_2];
- /* Setup operands */
- u8 rd = dstk ? tmp[1] : dst_lo;
- u8 rm = dstk ? tmp[0] : dst_hi;
+ const s8 *tmp = bpf2a32[TMP_REG_1];
+ const s8 *tmp2 = bpf2a32[TMP_REG_2];
+ const s8 *rd;
- if (dstk) {
- emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
- emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
- }
+ /* Setup operands */
+ rd = arm_bpf_get_reg64(dst, tmp, ctx);
/* Do LSR operation */
if (val < 32) {
- emit(ARM_MOV_SI(tmp2[1], rd, SRTYPE_LSR, val), ctx);
- emit(ARM_ORR_SI(rd, tmp2[1], rm, SRTYPE_ASL, 32 - val), ctx);
- emit(ARM_MOV_SI(rm, rm, SRTYPE_LSR, val), ctx);
+ emit(ARM_MOV_SI(tmp2[1], rd[1], SRTYPE_LSR, val), ctx);
+ emit(ARM_ORR_SI(rd[1], tmp2[1], rd[0], SRTYPE_ASL, 32 - val), ctx);
+ emit(ARM_MOV_SI(rd[0], rd[0], SRTYPE_LSR, val), ctx);
} else if (val == 32) {
- emit(ARM_MOV_R(rd, rm), ctx);
- emit(ARM_MOV_I(rm, 0), ctx);
+ emit(ARM_MOV_R(rd[1], rd[0]), ctx);
+ emit(ARM_MOV_I(rd[0], 0), ctx);
} else {
- emit(ARM_MOV_SI(rd, rm, SRTYPE_LSR, val - 32), ctx);
- emit(ARM_MOV_I(rm, 0), ctx);
+ emit(ARM_MOV_SI(rd[1], rd[0], SRTYPE_LSR, val - 32), ctx);
+ emit(ARM_MOV_I(rd[0], 0), ctx);
}
- if (dstk) {
- emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
- emit(ARM_STR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
- }
+ arm_bpf_put_reg64(dst, rd, ctx);
}
/* dst = dst >> val (signed) */
-static inline void emit_a32_arsh_i64(const u8 dst[], bool dstk,
+static inline void emit_a32_arsh_i64(const s8 dst[],
const u32 val, struct jit_ctx *ctx){
- const u8 *tmp = bpf2a32[TMP_REG_1];
- const u8 *tmp2 = bpf2a32[TMP_REG_2];
- /* Setup operands */
- u8 rd = dstk ? tmp[1] : dst_lo;
- u8 rm = dstk ? tmp[0] : dst_hi;
-
- if (dstk) {
- emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
- emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
- }
+ const s8 *tmp = bpf2a32[TMP_REG_1];
+ const s8 *tmp2 = bpf2a32[TMP_REG_2];
+ const s8 *rd;
+
+ /* Setup operands */
+ rd = arm_bpf_get_reg64(dst, tmp, ctx);
/* Do ARSH operation */
if (val < 32) {
- emit(ARM_MOV_SI(tmp2[1], rd, SRTYPE_LSR, val), ctx);
- emit(ARM_ORR_SI(rd, tmp2[1], rm, SRTYPE_ASL, 32 - val), ctx);
- emit(ARM_MOV_SI(rm, rm, SRTYPE_ASR, val), ctx);
+ emit(ARM_MOV_SI(tmp2[1], rd[1], SRTYPE_LSR, val), ctx);
+ emit(ARM_ORR_SI(rd[1], tmp2[1], rd[0], SRTYPE_ASL, 32 - val), ctx);
+ emit(ARM_MOV_SI(rd[0], rd[0], SRTYPE_ASR, val), ctx);
} else if (val == 32) {
- emit(ARM_MOV_R(rd, rm), ctx);
- emit(ARM_MOV_SI(rm, rm, SRTYPE_ASR, 31), ctx);
+ emit(ARM_MOV_R(rd[1], rd[0]), ctx);
+ emit(ARM_MOV_SI(rd[0], rd[0], SRTYPE_ASR, 31), ctx);
} else {
- emit(ARM_MOV_SI(rd, rm, SRTYPE_ASR, val - 32), ctx);
- emit(ARM_MOV_SI(rm, rm, SRTYPE_ASR, 31), ctx);
+ emit(ARM_MOV_SI(rd[1], rd[0], SRTYPE_ASR, val - 32), ctx);
+ emit(ARM_MOV_SI(rd[0], rd[0], SRTYPE_ASR, 31), ctx);
}
- if (dstk) {
- emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
- emit(ARM_STR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
- }
+ arm_bpf_put_reg64(dst, rd, ctx);
}
-static inline void emit_a32_mul_r64(const u8 dst[], const u8 src[], bool dstk,
- bool sstk, struct jit_ctx *ctx) {
- const u8 *tmp = bpf2a32[TMP_REG_1];
- const u8 *tmp2 = bpf2a32[TMP_REG_2];
+static inline void emit_a32_mul_r64(const s8 dst[], const s8 src[],
+ struct jit_ctx *ctx) {
+ const s8 *tmp = bpf2a32[TMP_REG_1];
+ const s8 *tmp2 = bpf2a32[TMP_REG_2];
+ const s8 *rd, *rt;
+
/* Setup operands for multiplication */
- u8 rd = dstk ? tmp[1] : dst_lo;
- u8 rm = dstk ? tmp[0] : dst_hi;
- u8 rt = sstk ? tmp2[1] : src_lo;
- u8 rn = sstk ? tmp2[0] : src_hi;
-
- if (dstk) {
- emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
- emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
- }
- if (sstk) {
- emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(src_lo)), ctx);
- emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src_hi)), ctx);
- }
+ rd = arm_bpf_get_reg64(dst, tmp, ctx);
+ rt = arm_bpf_get_reg64(src, tmp2, ctx);
/* Do Multiplication */
- emit(ARM_MUL(ARM_IP, rd, rn), ctx);
- emit(ARM_MUL(ARM_LR, rm, rt), ctx);
+ emit(ARM_MUL(ARM_IP, rd[1], rt[0]), ctx);
+ emit(ARM_MUL(ARM_LR, rd[0], rt[1]), ctx);
emit(ARM_ADD_R(ARM_LR, ARM_IP, ARM_LR), ctx);
- emit(ARM_UMULL(ARM_IP, rm, rd, rt), ctx);
- emit(ARM_ADD_R(rm, ARM_LR, rm), ctx);
- if (dstk) {
- emit(ARM_STR_I(ARM_IP, ARM_SP, STACK_VAR(dst_lo)), ctx);
- emit(ARM_STR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
- } else {
- emit(ARM_MOV_R(rd, ARM_IP), ctx);
- }
+ emit(ARM_UMULL(ARM_IP, rd[0], rd[1], rt[1]), ctx);
+ emit(ARM_ADD_R(rd[0], ARM_LR, rd[0]), ctx);
+
+ arm_bpf_put_reg32(dst_lo, ARM_IP, ctx);
+ arm_bpf_put_reg32(dst_hi, rd[0], ctx);
}
/* *(size *)(dst + off) = src */
-static inline void emit_str_r(const u8 dst, const u8 src, bool dstk,
- const s32 off, struct jit_ctx *ctx, const u8 sz){
- const u8 *tmp = bpf2a32[TMP_REG_1];
- u8 rd = dstk ? tmp[1] : dst;
-
- if (dstk)
- emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst)), ctx);
- if (off) {
- emit_a32_mov_i(tmp[0], off, false, ctx);
- emit(ARM_ADD_R(tmp[0], rd, tmp[0]), ctx);
+static inline void emit_str_r(const s8 dst, const s8 src[],
+ s32 off, struct jit_ctx *ctx, const u8 sz){
+ const s8 *tmp = bpf2a32[TMP_REG_1];
+ s32 off_max;
+ s8 rd;
+
+ rd = arm_bpf_get_reg32(dst, tmp[1], ctx);
+
+ if (sz == BPF_H)
+ off_max = 0xff;
+ else
+ off_max = 0xfff;
+
+ if (off < 0 || off > off_max) {
+ emit_a32_mov_i(tmp[0], off, ctx);
+ emit(ARM_ADD_R(tmp[0], tmp[0], rd), ctx);
rd = tmp[0];
+ off = 0;
}
switch (sz) {
- case BPF_W:
- /* Store a Word */
- emit(ARM_STR_I(src, rd, 0), ctx);
+ case BPF_B:
+ /* Store a Byte */
+ emit(ARM_STRB_I(src_lo, rd, off), ctx);
break;
case BPF_H:
/* Store a HalfWord */
- emit(ARM_STRH_I(src, rd, 0), ctx);
+ emit(ARM_STRH_I(src_lo, rd, off), ctx);
break;
- case BPF_B:
- /* Store a Byte */
- emit(ARM_STRB_I(src, rd, 0), ctx);
+ case BPF_W:
+ /* Store a Word */
+ emit(ARM_STR_I(src_lo, rd, off), ctx);
+ break;
+ case BPF_DW:
+ /* Store a Double Word */
+ emit(ARM_STR_I(src_lo, rd, off), ctx);
+ emit(ARM_STR_I(src_hi, rd, off + 4), ctx);
break;
}
}
/* dst = *(size*)(src + off) */
-static inline void emit_ldx_r(const u8 dst[], const u8 src, bool dstk,
+static inline void emit_ldx_r(const s8 dst[], const s8 src,
s32 off, struct jit_ctx *ctx, const u8 sz){
- const u8 *tmp = bpf2a32[TMP_REG_1];
- const u8 *rd = dstk ? tmp : dst;
- u8 rm = src;
+ const s8 *tmp = bpf2a32[TMP_REG_1];
+ const s8 *rd = is_stacked(dst_lo) ? tmp : dst;
+ s8 rm = src;
s32 off_max;
if (sz == BPF_H)
off_max = 0xfff;
if (off < 0 || off > off_max) {
- emit_a32_mov_i(tmp[0], off, false, ctx);
+ emit_a32_mov_i(tmp[0], off, ctx);
emit(ARM_ADD_R(tmp[0], tmp[0], src), ctx);
rm = tmp[0];
off = 0;
case BPF_B:
/* Load a Byte */
emit(ARM_LDRB_I(rd[1], rm, off), ctx);
- emit_a32_mov_i(dst[0], 0, dstk, ctx);
+ emit_a32_mov_i(rd[0], 0, ctx);
break;
case BPF_H:
/* Load a HalfWord */
emit(ARM_LDRH_I(rd[1], rm, off), ctx);
- emit_a32_mov_i(dst[0], 0, dstk, ctx);
+ emit_a32_mov_i(rd[0], 0, ctx);
break;
case BPF_W:
/* Load a Word */
emit(ARM_LDR_I(rd[1], rm, off), ctx);
- emit_a32_mov_i(dst[0], 0, dstk, ctx);
+ emit_a32_mov_i(rd[0], 0, ctx);
break;
case BPF_DW:
/* Load a Double Word */
emit(ARM_LDR_I(rd[0], rm, off + 4), ctx);
break;
}
- if (dstk)
- emit(ARM_STR_I(rd[1], ARM_SP, STACK_VAR(dst[1])), ctx);
- if (dstk && sz == BPF_DW)
- emit(ARM_STR_I(rd[0], ARM_SP, STACK_VAR(dst[0])), ctx);
+ arm_bpf_put_reg64(dst, rd, ctx);
}
/* Arithmatic Operation */
{
/* bpf_tail_call(void *prog_ctx, struct bpf_array *array, u64 index) */
- const u8 *r2 = bpf2a32[BPF_REG_2];
- const u8 *r3 = bpf2a32[BPF_REG_3];
- const u8 *tmp = bpf2a32[TMP_REG_1];
- const u8 *tmp2 = bpf2a32[TMP_REG_2];
- const u8 *tcc = bpf2a32[TCALL_CNT];
+ const s8 *r2 = bpf2a32[BPF_REG_2];
+ const s8 *r3 = bpf2a32[BPF_REG_3];
+ const s8 *tmp = bpf2a32[TMP_REG_1];
+ const s8 *tmp2 = bpf2a32[TMP_REG_2];
+ const s8 *tcc = bpf2a32[TCALL_CNT];
+ const s8 *tc;
const int idx0 = ctx->idx;
#define cur_offset (ctx->idx - idx0)
#define jmp_offset (out_offset - (cur_offset) - 2)
- u32 off, lo, hi;
+ u32 lo, hi;
+ s8 r_array, r_index;
+ int off;
/* if (index >= array->map.max_entries)
* goto out;
*/
+ BUILD_BUG_ON(offsetof(struct bpf_array, map.max_entries) >
+ ARM_INST_LDST__IMM12);
off = offsetof(struct bpf_array, map.max_entries);
- /* array->map.max_entries */
- emit_a32_mov_i(tmp[1], off, false, ctx);
- emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(r2[1])), ctx);
- emit(ARM_LDR_R(tmp[1], tmp2[1], tmp[1]), ctx);
+ r_array = arm_bpf_get_reg32(r2[1], tmp2[0], ctx);
/* index is 32-bit for arrays */
- emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(r3[1])), ctx);
+ r_index = arm_bpf_get_reg32(r3[1], tmp2[1], ctx);
+ /* array->map.max_entries */
+ emit(ARM_LDR_I(tmp[1], r_array, off), ctx);
/* index >= array->map.max_entries */
- emit(ARM_CMP_R(tmp2[1], tmp[1]), ctx);
+ emit(ARM_CMP_R(r_index, tmp[1]), ctx);
_emit(ARM_COND_CS, ARM_B(jmp_offset), ctx);
+ /* tmp2[0] = array, tmp2[1] = index */
+
/* if (tail_call_cnt > MAX_TAIL_CALL_CNT)
* goto out;
* tail_call_cnt++;
*/
lo = (u32)MAX_TAIL_CALL_CNT;
hi = (u32)((u64)MAX_TAIL_CALL_CNT >> 32);
- emit(ARM_LDR_I(tmp[1], ARM_SP, STACK_VAR(tcc[1])), ctx);
- emit(ARM_LDR_I(tmp[0], ARM_SP, STACK_VAR(tcc[0])), ctx);
- emit(ARM_CMP_I(tmp[0], hi), ctx);
- _emit(ARM_COND_EQ, ARM_CMP_I(tmp[1], lo), ctx);
+ tc = arm_bpf_get_reg64(tcc, tmp, ctx);
+ emit(ARM_CMP_I(tc[0], hi), ctx);
+ _emit(ARM_COND_EQ, ARM_CMP_I(tc[1], lo), ctx);
_emit(ARM_COND_HI, ARM_B(jmp_offset), ctx);
- emit(ARM_ADDS_I(tmp[1], tmp[1], 1), ctx);
- emit(ARM_ADC_I(tmp[0], tmp[0], 0), ctx);
- emit(ARM_STR_I(tmp[1], ARM_SP, STACK_VAR(tcc[1])), ctx);
- emit(ARM_STR_I(tmp[0], ARM_SP, STACK_VAR(tcc[0])), ctx);
+ emit(ARM_ADDS_I(tc[1], tc[1], 1), ctx);
+ emit(ARM_ADC_I(tc[0], tc[0], 0), ctx);
+ arm_bpf_put_reg64(tcc, tmp, ctx);
/* prog = array->ptrs[index]
* if (prog == NULL)
* goto out;
*/
- off = offsetof(struct bpf_array, ptrs);
- emit_a32_mov_i(tmp[1], off, false, ctx);
- emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(r2[1])), ctx);
- emit(ARM_ADD_R(tmp[1], tmp2[1], tmp[1]), ctx);
- emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(r3[1])), ctx);
- emit(ARM_MOV_SI(tmp[0], tmp2[1], SRTYPE_ASL, 2), ctx);
- emit(ARM_LDR_R(tmp[1], tmp[1], tmp[0]), ctx);
+ BUILD_BUG_ON(imm8m(offsetof(struct bpf_array, ptrs)) < 0);
+ off = imm8m(offsetof(struct bpf_array, ptrs));
+ emit(ARM_ADD_I(tmp[1], r_array, off), ctx);
+ emit(ARM_LDR_R_SI(tmp[1], tmp[1], r_index, SRTYPE_ASL, 2), ctx);
emit(ARM_CMP_I(tmp[1], 0), ctx);
_emit(ARM_COND_EQ, ARM_B(jmp_offset), ctx);
/* goto *(prog->bpf_func + prologue_size); */
+ BUILD_BUG_ON(offsetof(struct bpf_prog, bpf_func) >
+ ARM_INST_LDST__IMM12);
off = offsetof(struct bpf_prog, bpf_func);
- emit_a32_mov_i(tmp2[1], off, false, ctx);
- emit(ARM_LDR_R(tmp[1], tmp[1], tmp2[1]), ctx);
+ emit(ARM_LDR_I(tmp[1], tmp[1], off), ctx);
emit(ARM_ADD_I(tmp[1], tmp[1], ctx->prologue_bytes), ctx);
emit_bx_r(tmp[1], ctx);
static inline void emit_rev16(const u8 rd, const u8 rn, struct jit_ctx *ctx)
{
#if __LINUX_ARM_ARCH__ < 6
- const u8 *tmp2 = bpf2a32[TMP_REG_2];
+ const s8 *tmp2 = bpf2a32[TMP_REG_2];
emit(ARM_AND_I(tmp2[1], rn, 0xff), ctx);
emit(ARM_MOV_SI(tmp2[0], rn, SRTYPE_LSR, 8), ctx);
static inline void emit_rev32(const u8 rd, const u8 rn, struct jit_ctx *ctx)
{
#if __LINUX_ARM_ARCH__ < 6
- const u8 *tmp2 = bpf2a32[TMP_REG_2];
+ const s8 *tmp2 = bpf2a32[TMP_REG_2];
emit(ARM_AND_I(tmp2[1], rn, 0xff), ctx);
emit(ARM_MOV_SI(tmp2[0], rn, SRTYPE_LSR, 24), ctx);
}
// push the scratch stack register on top of the stack
-static inline void emit_push_r64(const u8 src[], const u8 shift,
- struct jit_ctx *ctx)
+static inline void emit_push_r64(const s8 src[], struct jit_ctx *ctx)
{
- const u8 *tmp2 = bpf2a32[TMP_REG_2];
+ const s8 *tmp2 = bpf2a32[TMP_REG_2];
+ const s8 *rt;
u16 reg_set = 0;
- emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(src[1]+shift)), ctx);
- emit(ARM_LDR_I(tmp2[0], ARM_SP, STACK_VAR(src[0]+shift)), ctx);
+ rt = arm_bpf_get_reg64(src, tmp2, ctx);
- reg_set = (1 << tmp2[1]) | (1 << tmp2[0]);
+ reg_set = (1 << rt[1]) | (1 << rt[0]);
emit(ARM_PUSH(reg_set), ctx);
}
static void build_prologue(struct jit_ctx *ctx)
{
- const u8 r0 = bpf2a32[BPF_REG_0][1];
- const u8 r2 = bpf2a32[BPF_REG_1][1];
- const u8 r3 = bpf2a32[BPF_REG_1][0];
- const u8 r4 = bpf2a32[BPF_REG_6][1];
- const u8 fplo = bpf2a32[BPF_REG_FP][1];
- const u8 fphi = bpf2a32[BPF_REG_FP][0];
- const u8 *tcc = bpf2a32[TCALL_CNT];
+ const s8 r0 = bpf2a32[BPF_REG_0][1];
+ const s8 r2 = bpf2a32[BPF_REG_1][1];
+ const s8 r3 = bpf2a32[BPF_REG_1][0];
+ const s8 r4 = bpf2a32[BPF_REG_6][1];
+ const s8 fplo = bpf2a32[BPF_REG_FP][1];
+ const s8 fphi = bpf2a32[BPF_REG_FP][0];
+ const s8 *tcc = bpf2a32[TCALL_CNT];
/* Save callee saved registers. */
#ifdef CONFIG_FRAME_POINTER
emit(ARM_SUB_I(ARM_SP, ARM_SP, ctx->stack_size), ctx);
/* Set up BPF prog stack base register */
- emit_a32_mov_r(fplo, ARM_IP, true, false, ctx);
- emit_a32_mov_i(fphi, 0, true, ctx);
+ emit_a32_mov_r(fplo, ARM_IP, ctx);
+ emit_a32_mov_i(fphi, 0, ctx);
/* mov r4, 0 */
emit(ARM_MOV_I(r4, 0), ctx);
emit(ARM_MOV_R(r3, r4), ctx);
emit(ARM_MOV_R(r2, r0), ctx);
/* Initialize Tail Count */
- emit(ARM_STR_I(r4, ARM_SP, STACK_VAR(tcc[0])), ctx);
- emit(ARM_STR_I(r4, ARM_SP, STACK_VAR(tcc[1])), ctx);
+ emit(ARM_STR_I(r4, ARM_FP, EBPF_SCRATCH_TO_ARM_FP(tcc[0])), ctx);
+ emit(ARM_STR_I(r4, ARM_FP, EBPF_SCRATCH_TO_ARM_FP(tcc[1])), ctx);
/* end of prologue */
}
static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
{
const u8 code = insn->code;
- const u8 *dst = bpf2a32[insn->dst_reg];
- const u8 *src = bpf2a32[insn->src_reg];
- const u8 *tmp = bpf2a32[TMP_REG_1];
- const u8 *tmp2 = bpf2a32[TMP_REG_2];
+ const s8 *dst = bpf2a32[insn->dst_reg];
+ const s8 *src = bpf2a32[insn->src_reg];
+ const s8 *tmp = bpf2a32[TMP_REG_1];
+ const s8 *tmp2 = bpf2a32[TMP_REG_2];
const s16 off = insn->off;
const s32 imm = insn->imm;
const int i = insn - ctx->prog->insnsi;
const bool is64 = BPF_CLASS(code) == BPF_ALU64;
- const bool dstk = is_on_stack(insn->dst_reg);
- const bool sstk = is_on_stack(insn->src_reg);
- u8 rd, rt, rm, rn;
+ const s8 *rd, *rs;
+ s8 rd_lo, rt, rm, rn;
s32 jmp_offset;
#define check_imm(bits, imm) do { \
case BPF_ALU64 | BPF_MOV | BPF_X:
switch (BPF_SRC(code)) {
case BPF_X:
- emit_a32_mov_r64(is64, dst, src, dstk, sstk, ctx);
+ emit_a32_mov_r64(is64, dst, src, ctx);
break;
case BPF_K:
/* Sign-extend immediate value to destination reg */
- emit_a32_mov_i64(is64, dst, imm, dstk, ctx);
+ emit_a32_mov_se_i64(is64, dst, imm, ctx);
break;
}
break;
case BPF_ALU64 | BPF_XOR | BPF_X:
switch (BPF_SRC(code)) {
case BPF_X:
- emit_a32_alu_r64(is64, dst, src, dstk, sstk,
- ctx, BPF_OP(code));
+ emit_a32_alu_r64(is64, dst, src, ctx, BPF_OP(code));
break;
case BPF_K:
/* Move immediate value to the temporary register
* value into temporary reg and then it would be
* safe to do the operation on it.
*/
- emit_a32_mov_i64(is64, tmp2, imm, false, ctx);
- emit_a32_alu_r64(is64, dst, tmp2, dstk, false,
- ctx, BPF_OP(code));
+ emit_a32_mov_se_i64(is64, tmp2, imm, ctx);
+ emit_a32_alu_r64(is64, dst, tmp2, ctx, BPF_OP(code));
break;
}
break;
case BPF_ALU | BPF_DIV | BPF_X:
case BPF_ALU | BPF_MOD | BPF_K:
case BPF_ALU | BPF_MOD | BPF_X:
- rt = src_lo;
- rd = dstk ? tmp2[1] : dst_lo;
- if (dstk)
- emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
+ rd_lo = arm_bpf_get_reg32(dst_lo, tmp2[1], ctx);
switch (BPF_SRC(code)) {
case BPF_X:
- rt = sstk ? tmp2[0] : rt;
- if (sstk)
- emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(src_lo)),
- ctx);
+ rt = arm_bpf_get_reg32(src_lo, tmp2[0], ctx);
break;
case BPF_K:
rt = tmp2[0];
- emit_a32_mov_i(rt, imm, false, ctx);
+ emit_a32_mov_i(rt, imm, ctx);
+ break;
+ default:
+ rt = src_lo;
break;
}
- emit_udivmod(rd, rd, rt, ctx, BPF_OP(code));
- if (dstk)
- emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
- emit_a32_mov_i(dst_hi, 0, dstk, ctx);
+ emit_udivmod(rd_lo, rd_lo, rt, ctx, BPF_OP(code));
+ arm_bpf_put_reg32(dst_lo, rd_lo, ctx);
+ emit_a32_mov_i(dst_hi, 0, ctx);
break;
case BPF_ALU64 | BPF_DIV | BPF_K:
case BPF_ALU64 | BPF_DIV | BPF_X:
if (unlikely(imm > 31))
return -EINVAL;
if (imm)
- emit_a32_alu_i(dst_lo, imm, dstk, ctx, BPF_OP(code));
- emit_a32_mov_i(dst_hi, 0, dstk, ctx);
+ emit_a32_alu_i(dst_lo, imm, ctx, BPF_OP(code));
+ emit_a32_mov_i(dst_hi, 0, ctx);
break;
/* dst = dst << imm */
case BPF_ALU64 | BPF_LSH | BPF_K:
if (unlikely(imm > 63))
return -EINVAL;
- emit_a32_lsh_i64(dst, dstk, imm, ctx);
+ emit_a32_lsh_i64(dst, imm, ctx);
break;
/* dst = dst >> imm */
case BPF_ALU64 | BPF_RSH | BPF_K:
if (unlikely(imm > 63))
return -EINVAL;
- emit_a32_rsh_i64(dst, dstk, imm, ctx);
+ emit_a32_rsh_i64(dst, imm, ctx);
break;
/* dst = dst << src */
case BPF_ALU64 | BPF_LSH | BPF_X:
- emit_a32_lsh_r64(dst, src, dstk, sstk, ctx);
+ emit_a32_lsh_r64(dst, src, ctx);
break;
/* dst = dst >> src */
case BPF_ALU64 | BPF_RSH | BPF_X:
- emit_a32_rsh_r64(dst, src, dstk, sstk, ctx);
+ emit_a32_rsh_r64(dst, src, ctx);
break;
/* dst = dst >> src (signed) */
case BPF_ALU64 | BPF_ARSH | BPF_X:
- emit_a32_arsh_r64(dst, src, dstk, sstk, ctx);
+ emit_a32_arsh_r64(dst, src, ctx);
break;
/* dst = dst >> imm (signed) */
case BPF_ALU64 | BPF_ARSH | BPF_K:
if (unlikely(imm > 63))
return -EINVAL;
- emit_a32_arsh_i64(dst, dstk, imm, ctx);
+ emit_a32_arsh_i64(dst, imm, ctx);
break;
/* dst = ~dst */
case BPF_ALU | BPF_NEG:
- emit_a32_alu_i(dst_lo, 0, dstk, ctx, BPF_OP(code));
- emit_a32_mov_i(dst_hi, 0, dstk, ctx);
+ emit_a32_alu_i(dst_lo, 0, ctx, BPF_OP(code));
+ emit_a32_mov_i(dst_hi, 0, ctx);
break;
/* dst = ~dst (64 bit) */
case BPF_ALU64 | BPF_NEG:
- emit_a32_neg64(dst, dstk, ctx);
+ emit_a32_neg64(dst, ctx);
break;
/* dst = dst * src/imm */
case BPF_ALU64 | BPF_MUL | BPF_X:
case BPF_ALU64 | BPF_MUL | BPF_K:
switch (BPF_SRC(code)) {
case BPF_X:
- emit_a32_mul_r64(dst, src, dstk, sstk, ctx);
+ emit_a32_mul_r64(dst, src, ctx);
break;
case BPF_K:
/* Move immediate value to the temporary register
* reg then it would be safe to do the operation
* on it.
*/
- emit_a32_mov_i64(is64, tmp2, imm, false, ctx);
- emit_a32_mul_r64(dst, tmp2, dstk, false, ctx);
+ emit_a32_mov_se_i64(is64, tmp2, imm, ctx);
+ emit_a32_mul_r64(dst, tmp2, ctx);
break;
}
break;
/* dst = htobe(dst) */
case BPF_ALU | BPF_END | BPF_FROM_LE:
case BPF_ALU | BPF_END | BPF_FROM_BE:
- rd = dstk ? tmp[0] : dst_hi;
- rt = dstk ? tmp[1] : dst_lo;
- if (dstk) {
- emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(dst_lo)), ctx);
- emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_hi)), ctx);
- }
+ rd = arm_bpf_get_reg64(dst, tmp, ctx);
if (BPF_SRC(code) == BPF_FROM_LE)
goto emit_bswap_uxt;
switch (imm) {
case 16:
- emit_rev16(rt, rt, ctx);
+ emit_rev16(rd[1], rd[1], ctx);
goto emit_bswap_uxt;
case 32:
- emit_rev32(rt, rt, ctx);
+ emit_rev32(rd[1], rd[1], ctx);
goto emit_bswap_uxt;
case 64:
- emit_rev32(ARM_LR, rt, ctx);
- emit_rev32(rt, rd, ctx);
- emit(ARM_MOV_R(rd, ARM_LR), ctx);
+ emit_rev32(ARM_LR, rd[1], ctx);
+ emit_rev32(rd[1], rd[0], ctx);
+ emit(ARM_MOV_R(rd[0], ARM_LR), ctx);
break;
}
goto exit;
case 16:
/* zero-extend 16 bits into 64 bits */
#if __LINUX_ARM_ARCH__ < 6
- emit_a32_mov_i(tmp2[1], 0xffff, false, ctx);
- emit(ARM_AND_R(rt, rt, tmp2[1]), ctx);
+ emit_a32_mov_i(tmp2[1], 0xffff, ctx);
+ emit(ARM_AND_R(rd[1], rd[1], tmp2[1]), ctx);
#else /* ARMv6+ */
- emit(ARM_UXTH(rt, rt), ctx);
+ emit(ARM_UXTH(rd[1], rd[1]), ctx);
#endif
- emit(ARM_EOR_R(rd, rd, rd), ctx);
+ emit(ARM_EOR_R(rd[0], rd[0], rd[0]), ctx);
break;
case 32:
/* zero-extend 32 bits into 64 bits */
- emit(ARM_EOR_R(rd, rd, rd), ctx);
+ emit(ARM_EOR_R(rd[0], rd[0], rd[0]), ctx);
break;
case 64:
/* nop */
break;
}
exit:
- if (dstk) {
- emit(ARM_STR_I(rt, ARM_SP, STACK_VAR(dst_lo)), ctx);
- emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_hi)), ctx);
- }
+ arm_bpf_put_reg64(dst, rd, ctx);
break;
/* dst = imm64 */
case BPF_LD | BPF_IMM | BPF_DW:
{
- const struct bpf_insn insn1 = insn[1];
- u32 hi, lo = imm;
+ u64 val = (u32)imm | (u64)insn[1].imm << 32;
- hi = insn1.imm;
- emit_a32_mov_i(dst_lo, lo, dstk, ctx);
- emit_a32_mov_i(dst_hi, hi, dstk, ctx);
+ emit_a32_mov_i64(dst, val, ctx);
return 1;
}
case BPF_LDX | BPF_MEM | BPF_H:
case BPF_LDX | BPF_MEM | BPF_B:
case BPF_LDX | BPF_MEM | BPF_DW:
- rn = sstk ? tmp2[1] : src_lo;
- if (sstk)
- emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src_lo)), ctx);
- emit_ldx_r(dst, rn, dstk, off, ctx, BPF_SIZE(code));
+ rn = arm_bpf_get_reg32(src_lo, tmp2[1], ctx);
+ emit_ldx_r(dst, rn, off, ctx, BPF_SIZE(code));
break;
/* ST: *(size *)(dst + off) = imm */
case BPF_ST | BPF_MEM | BPF_W:
switch (BPF_SIZE(code)) {
case BPF_DW:
/* Sign-extend immediate value into temp reg */
- emit_a32_mov_i64(true, tmp2, imm, false, ctx);
- emit_str_r(dst_lo, tmp2[1], dstk, off, ctx, BPF_W);
- emit_str_r(dst_lo, tmp2[0], dstk, off+4, ctx, BPF_W);
+ emit_a32_mov_se_i64(true, tmp2, imm, ctx);
break;
case BPF_W:
case BPF_H:
case BPF_B:
- emit_a32_mov_i(tmp2[1], imm, false, ctx);
- emit_str_r(dst_lo, tmp2[1], dstk, off, ctx,
- BPF_SIZE(code));
+ emit_a32_mov_i(tmp2[1], imm, ctx);
break;
}
+ emit_str_r(dst_lo, tmp2, off, ctx, BPF_SIZE(code));
break;
/* STX XADD: lock *(u32 *)(dst + off) += src */
case BPF_STX | BPF_XADD | BPF_W:
case BPF_STX | BPF_MEM | BPF_H:
case BPF_STX | BPF_MEM | BPF_B:
case BPF_STX | BPF_MEM | BPF_DW:
- {
- u8 sz = BPF_SIZE(code);
-
- rn = sstk ? tmp2[1] : src_lo;
- rm = sstk ? tmp2[0] : src_hi;
- if (sstk) {
- emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src_lo)), ctx);
- emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(src_hi)), ctx);
- }
-
- /* Store the value */
- if (BPF_SIZE(code) == BPF_DW) {
- emit_str_r(dst_lo, rn, dstk, off, ctx, BPF_W);
- emit_str_r(dst_lo, rm, dstk, off+4, ctx, BPF_W);
- } else {
- emit_str_r(dst_lo, rn, dstk, off, ctx, sz);
- }
+ rs = arm_bpf_get_reg64(src, tmp2, ctx);
+ emit_str_r(dst_lo, rs, off, ctx, BPF_SIZE(code));
break;
- }
/* PC += off if dst == src */
/* PC += off if dst > src */
/* PC += off if dst >= src */
case BPF_JMP | BPF_JSLT | BPF_X:
case BPF_JMP | BPF_JSLE | BPF_X:
/* Setup source registers */
- rm = sstk ? tmp2[0] : src_hi;
- rn = sstk ? tmp2[1] : src_lo;
- if (sstk) {
- emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src_lo)), ctx);
- emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(src_hi)), ctx);
- }
+ rm = arm_bpf_get_reg32(src_hi, tmp2[0], ctx);
+ rn = arm_bpf_get_reg32(src_lo, tmp2[1], ctx);
goto go_jmp;
/* PC += off if dst == imm */
/* PC += off if dst > imm */
rm = tmp2[0];
rn = tmp2[1];
/* Sign-extend immediate value */
- emit_a32_mov_i64(true, tmp2, imm, false, ctx);
+ emit_a32_mov_se_i64(true, tmp2, imm, ctx);
go_jmp:
/* Setup destination register */
- rd = dstk ? tmp[0] : dst_hi;
- rt = dstk ? tmp[1] : dst_lo;
- if (dstk) {
- emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(dst_lo)), ctx);
- emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_hi)), ctx);
- }
+ rd = arm_bpf_get_reg64(dst, tmp, ctx);
/* Check for the condition */
- emit_ar_r(rd, rt, rm, rn, ctx, BPF_OP(code));
+ emit_ar_r(rd[0], rd[1], rm, rn, ctx, BPF_OP(code));
/* Setup JUMP instruction */
jmp_offset = bpf2a32_offset(i+off, i, ctx);
/* function call */
case BPF_JMP | BPF_CALL:
{
- const u8 *r0 = bpf2a32[BPF_REG_0];
- const u8 *r1 = bpf2a32[BPF_REG_1];
- const u8 *r2 = bpf2a32[BPF_REG_2];
- const u8 *r3 = bpf2a32[BPF_REG_3];
- const u8 *r4 = bpf2a32[BPF_REG_4];
- const u8 *r5 = bpf2a32[BPF_REG_5];
+ const s8 *r0 = bpf2a32[BPF_REG_0];
+ const s8 *r1 = bpf2a32[BPF_REG_1];
+ const s8 *r2 = bpf2a32[BPF_REG_2];
+ const s8 *r3 = bpf2a32[BPF_REG_3];
+ const s8 *r4 = bpf2a32[BPF_REG_4];
+ const s8 *r5 = bpf2a32[BPF_REG_5];
const u32 func = (u32)__bpf_call_base + (u32)imm;
- emit_a32_mov_r64(true, r0, r1, false, false, ctx);
- emit_a32_mov_r64(true, r1, r2, false, true, ctx);
- emit_push_r64(r5, 0, ctx);
- emit_push_r64(r4, 8, ctx);
- emit_push_r64(r3, 16, ctx);
+ emit_a32_mov_r64(true, r0, r1, ctx);
+ emit_a32_mov_r64(true, r1, r2, ctx);
+ emit_push_r64(r5, ctx);
+ emit_push_r64(r4, ctx);
+ emit_push_r64(r3, ctx);
- emit_a32_mov_i(tmp[1], func, false, ctx);
+ emit_a32_mov_i(tmp[1], func, ctx);
emit_blx_r(tmp[1], ctx);
emit(ARM_ADD_I(ARM_SP, ARM_SP, imm8m(24)), ctx); // callee clean
memset(&ctx, 0, sizeof(ctx));
ctx.prog = prog;
+ ctx.cpu_architecture = cpu_architecture();
/* Not able to allocate memory for offsets[] , then
* we must fall back to the interpreter
/* there are 2 passes here */
bpf_jit_dump(prog->len, image_size, 2, ctx.target);
- set_memory_ro((unsigned long)header, header->pages);
+ bpf_jit_binary_lock_ro(header);
prog->bpf_func = (void *)ctx.target;
prog->jited = 1;
prog->jited_len = image_size;
#define ARM_INST_EOR_R 0x00200000
#define ARM_INST_EOR_I 0x02200000
-#define ARM_INST_LDRB_I 0x05d00000
+#define ARM_INST_LDST__U 0x00800000
+#define ARM_INST_LDST__IMM12 0x00000fff
+#define ARM_INST_LDRB_I 0x05500000
#define ARM_INST_LDRB_R 0x07d00000
-#define ARM_INST_LDRH_I 0x01d000b0
+#define ARM_INST_LDRD_I 0x014000d0
+#define ARM_INST_LDRH_I 0x015000b0
#define ARM_INST_LDRH_R 0x019000b0
-#define ARM_INST_LDR_I 0x05900000
+#define ARM_INST_LDR_I 0x05100000
#define ARM_INST_LDR_R 0x07900000
#define ARM_INST_LDM 0x08900000
#define ARM_INST_SBC_R 0x00c00000
#define ARM_INST_SBCS_R 0x00d00000
-#define ARM_INST_STR_I 0x05800000
-#define ARM_INST_STRB_I 0x05c00000
-#define ARM_INST_STRH_I 0x01c000b0
+#define ARM_INST_STR_I 0x05000000
+#define ARM_INST_STRB_I 0x05400000
+#define ARM_INST_STRD_I 0x014000f0
+#define ARM_INST_STRH_I 0x014000b0
#define ARM_INST_TST_R 0x01100000
#define ARM_INST_TST_I 0x03100000
#define ARM_EOR_R(rd, rn, rm) _AL3_R(ARM_INST_EOR, rd, rn, rm)
#define ARM_EOR_I(rd, rn, imm) _AL3_I(ARM_INST_EOR, rd, rn, imm)
-#define ARM_LDR_I(rt, rn, off) (ARM_INST_LDR_I | (rt) << 12 | (rn) << 16 \
- | ((off) & 0xfff))
-#define ARM_LDR_R(rt, rn, rm) (ARM_INST_LDR_R | (rt) << 12 | (rn) << 16 \
+#define ARM_LDR_R(rt, rn, rm) (ARM_INST_LDR_R | ARM_INST_LDST__U \
+ | (rt) << 12 | (rn) << 16 \
| (rm))
-#define ARM_LDRB_I(rt, rn, off) (ARM_INST_LDRB_I | (rt) << 12 | (rn) << 16 \
- | (off))
-#define ARM_LDRB_R(rt, rn, rm) (ARM_INST_LDRB_R | (rt) << 12 | (rn) << 16 \
+#define ARM_LDR_R_SI(rt, rn, rm, type, imm) \
+ (ARM_INST_LDR_R | ARM_INST_LDST__U \
+ | (rt) << 12 | (rn) << 16 \
+ | (imm) << 7 | (type) << 5 | (rm))
+#define ARM_LDRB_R(rt, rn, rm) (ARM_INST_LDRB_R | ARM_INST_LDST__U \
+ | (rt) << 12 | (rn) << 16 \
| (rm))
-#define ARM_LDRH_I(rt, rn, off) (ARM_INST_LDRH_I | (rt) << 12 | (rn) << 16 \
- | (((off) & 0xf0) << 4) | ((off) & 0xf))
-#define ARM_LDRH_R(rt, rn, rm) (ARM_INST_LDRH_R | (rt) << 12 | (rn) << 16 \
+#define ARM_LDRH_R(rt, rn, rm) (ARM_INST_LDRH_R | ARM_INST_LDST__U \
+ | (rt) << 12 | (rn) << 16 \
| (rm))
#define ARM_LDM(rn, regs) (ARM_INST_LDM | (rn) << 16 | (regs))
#define ARM_SUBS_I(rd, rn, imm) _AL3_I(ARM_INST_SUBS, rd, rn, imm)
#define ARM_SBC_I(rd, rn, imm) _AL3_I(ARM_INST_SBC, rd, rn, imm)
-#define ARM_STR_I(rt, rn, off) (ARM_INST_STR_I | (rt) << 12 | (rn) << 16 \
- | ((off) & 0xfff))
-#define ARM_STRH_I(rt, rn, off) (ARM_INST_STRH_I | (rt) << 12 | (rn) << 16 \
- | (((off) & 0xf0) << 4) | ((off) & 0xf))
-#define ARM_STRB_I(rt, rn, off) (ARM_INST_STRB_I | (rt) << 12 | (rn) << 16 \
- | (((off) & 0xf0) << 4) | ((off) & 0xf))
-
#define ARM_TST_R(rn, rm) _AL3_R(ARM_INST_TST, 0, rn, rm)
#define ARM_TST_I(rn, imm) _AL3_I(ARM_INST_TST, 0, rn, imm)
static __read_mostly unsigned int xen_events_irq;
+uint32_t xen_start_flags;
+EXPORT_SYMBOL(xen_start_flags);
+
int xen_remap_domain_gfn_array(struct vm_area_struct *vma,
unsigned long addr,
xen_pfn_t *gfn, int nr,
xen_setup_features();
if (xen_feature(XENFEAT_dom0))
- xen_start_info->flags |= SIF_INITDOMAIN|SIF_PRIVILEGED;
- else
- xen_start_info->flags &= ~(SIF_INITDOMAIN|SIF_PRIVILEGED);
+ xen_start_flags |= SIF_INITDOMAIN|SIF_PRIVILEGED;
if (!console_set_on_cmdline && !xen_initial_domain())
add_preferred_console("hvc", 0, NULL);
interrupts = <0 99 4>;
resets = <&rst SPIM0_RESET>;
reg-io-width = <4>;
- num-chipselect = <4>;
- bus-num = <0>;
+ num-cs = <4>;
status = "disabled";
};
interrupts = <0 100 4>;
resets = <&rst SPIM1_RESET>;
reg-io-width = <4>;
- num-chipselect = <4>;
- bus-num = <0>;
+ num-cs = <4>;
status = "disabled";
};
ðmac {
status = "okay";
- phy-mode = "rgmii";
pinctrl-0 = <ð_rgmii_y_pins>;
pinctrl-names = "default";
+ phy-handle = <ð_phy0>;
+ phy-mode = "rgmii";
+
+ mdio {
+ compatible = "snps,dwmac-mdio";
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ eth_phy0: ethernet-phy@0 {
+ /* Realtek RTL8211F (0x001cc916) */
+ reg = <0>;
+ eee-broken-1000t;
+ };
+ };
};
&uart_A {
sd_emmc_b: sd@5000 {
compatible = "amlogic,meson-axg-mmc";
- reg = <0x0 0x5000 0x0 0x2000>;
+ reg = <0x0 0x5000 0x0 0x800>;
interrupts = <GIC_SPI 217 IRQ_TYPE_EDGE_RISING>;
status = "disabled";
clocks = <&clkc CLKID_SD_EMMC_B>,
sd_emmc_c: mmc@7000 {
compatible = "amlogic,meson-axg-mmc";
- reg = <0x0 0x7000 0x0 0x2000>;
+ reg = <0x0 0x7000 0x0 0x800>;
interrupts = <GIC_SPI 218 IRQ_TYPE_EDGE_RISING>;
status = "disabled";
clocks = <&clkc CLKID_SD_EMMC_C>,
no-map;
};
+ /* Alternate 3 MiB reserved for ARM Trusted Firmware (BL31) */
+ secmon_reserved_alt: secmon@5000000 {
+ reg = <0x0 0x05000000 0x0 0x300000>;
+ no-map;
+ };
+
linux,cma {
compatible = "shared-dma-pool";
reusable;
sd_emmc_a: mmc@70000 {
compatible = "amlogic,meson-gx-mmc", "amlogic,meson-gxbb-mmc";
- reg = <0x0 0x70000 0x0 0x2000>;
+ reg = <0x0 0x70000 0x0 0x800>;
interrupts = <GIC_SPI 216 IRQ_TYPE_EDGE_RISING>;
status = "disabled";
};
sd_emmc_b: mmc@72000 {
compatible = "amlogic,meson-gx-mmc", "amlogic,meson-gxbb-mmc";
- reg = <0x0 0x72000 0x0 0x2000>;
+ reg = <0x0 0x72000 0x0 0x800>;
interrupts = <GIC_SPI 217 IRQ_TYPE_EDGE_RISING>;
status = "disabled";
};
sd_emmc_c: mmc@74000 {
compatible = "amlogic,meson-gx-mmc", "amlogic,meson-gxbb-mmc";
- reg = <0x0 0x74000 0x0 0x2000>;
+ reg = <0x0 0x74000 0x0 0x800>;
interrupts = <GIC_SPI 218 IRQ_TYPE_EDGE_RISING>;
status = "disabled";
};
&apb {
mali: gpu@c0000 {
- compatible = "amlogic,meson-gxbb-mali", "arm,mali-450";
+ compatible = "amlogic,meson-gxl-mali", "arm,mali-450";
reg = <0x0 0xc0000 0x0 0x40000>;
interrupts = <GIC_SPI 160 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 161 IRQ_TYPE_LEVEL_HIGH>,
bus-width = <4>;
cap-sd-highspeed;
- sd-uhs-sdr12;
- sd-uhs-sdr25;
- sd-uhs-sdr50;
max-frequency = <100000000>;
disable-wp;
&usb0 {
status = "okay";
};
+
+&usb2_phy0 {
+ /*
+ * HDMI_5V is also used as supply for the USB VBUS.
+ */
+ phy-supply = <&hdmi_5v>;
+};
/ {
compatible = "amlogic,meson-gxl";
- reserved-memory {
- /* Alternate 3 MiB reserved for ARM Trusted Firmware (BL31) */
- secmon_reserved_alt: secmon@5000000 {
- reg = <0x0 0x05000000 0x0 0x300000>;
- no-map;
- };
- };
-
soc {
usb0: usb@c9000000 {
status = "disabled";
#interrupt-cells = <1>;
interrupt-map-mask = <0 0 0 0>;
- interrupt-map = <0 0 0 0 &gic 0 GIC_SPI 281 IRQ_TYPE_NONE>;
+ interrupt-map = <0 0 0 0 &gic 0 GIC_SPI 281 IRQ_TYPE_LEVEL_HIGH>;
linux,pci-domain = <0>;
#interrupt-cells = <1>;
interrupt-map-mask = <0 0 0 0>;
- interrupt-map = <0 0 0 0 &gic 0 GIC_SPI 305 IRQ_TYPE_NONE>;
+ interrupt-map = <0 0 0 0 &gic 0 GIC_SPI 305 IRQ_TYPE_LEVEL_HIGH>;
linux,pci-domain = <4>;
reg = <0x66080000 0x100>;
#address-cells = <1>;
#size-cells = <0>;
- interrupts = <GIC_SPI 394 IRQ_TYPE_NONE>;
+ interrupts = <GIC_SPI 394 IRQ_TYPE_LEVEL_HIGH>;
clock-frequency = <100000>;
status = "disabled";
};
reg = <0x660b0000 0x100>;
#address-cells = <1>;
#size-cells = <0>;
- interrupts = <GIC_SPI 395 IRQ_TYPE_NONE>;
+ interrupts = <GIC_SPI 395 IRQ_TYPE_LEVEL_HIGH>;
clock-frequency = <100000>;
status = "disabled";
};
enet-phy-lane-swap;
};
+&sdio0 {
+ mmc-ddr-1_8v;
+};
+
&uart2 {
status = "okay";
};
&gphy0 {
enet-phy-lane-swap;
};
+
+&sdio0 {
+ mmc-ddr-1_8v;
+};
reg = <0x000b0000 0x100>;
#address-cells = <1>;
#size-cells = <0>;
- interrupts = <GIC_SPI 177 IRQ_TYPE_NONE>;
+ interrupts = <GIC_SPI 177 IRQ_TYPE_LEVEL_HIGH>;
clock-frequency = <100000>;
status = "disabled";
};
reg = <0x000e0000 0x100>;
#address-cells = <1>;
#size-cells = <0>;
- interrupts = <GIC_SPI 178 IRQ_TYPE_NONE>;
+ interrupts = <GIC_SPI 178 IRQ_TYPE_LEVEL_HIGH>;
clock-frequency = <100000>;
status = "disabled";
};
#size-cells = <1>;
cell-index = <0>;
compatible = "fsl,fman";
- ranges = <0x0 0x0 0x1a00000 0x100000>;
- reg = <0x0 0x1a00000 0x0 0x100000>;
+ ranges = <0x0 0x0 0x1a00000 0xfe000>;
+ reg = <0x0 0x1a00000 0x0 0xfe000>;
interrupts = <GIC_SPI 44 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 45 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&clockgen 3 0>;
clock-names = "fmanclk";
fsl,qman-channel-range = <0x800 0x10>;
+ ptimer-handle = <&ptp_timer0>;
muram@0 {
compatible = "fsl,fman-muram";
compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
reg = <0xfd000 0x1000>;
};
+};
- ptp_timer0: ptp-timer@fe000 {
- compatible = "fsl,fman-ptp-timer";
- reg = <0xfe000 0x1000>;
- };
+ptp_timer0: ptp-timer@1afe000 {
+ compatible = "fsl,fman-ptp-timer";
+ reg = <0x0 0x1afe000 0x0 0x1000>;
+ interrupts = <GIC_SPI 44 IRQ_TYPE_LEVEL_HIGH>;
};
vmmc-supply = <&wlan_en>;
ti,non-removable;
non-removable;
+ cap-power-off-card;
+ keep-power-in-suspend;
#address-cells = <0x1>;
#size-cells = <0x0>;
status = "ok";
dwmmc_2: dwmmc2@f723f000 {
bus-width = <0x4>;
non-removable;
+ cap-power-off-card;
+ keep-power-in-suspend;
vmmc-supply = <®_vdd_3v3>;
mmc-pwrseq = <&wl1835_pwrseq>;
CP110_LABEL(icu): interrupt-controller@1e0000 {
compatible = "marvell,cp110-icu";
- reg = <0x1e0000 0x10>;
+ reg = <0x1e0000 0x440>;
#interrupt-cells = <3>;
interrupt-controller;
msi-parent = <&gicp>;
serial@75b1000 {
label = "LS-UART0";
- status = "okay";
+ status = "disabled";
pinctrl-names = "default", "sleep";
pinctrl-0 = <&blsp2_uart2_4pins_default>;
pinctrl-1 = <&blsp2_uart2_4pins_sleep>;
port@0 {
reg = <0>;
- etf_out: endpoint {
+ etf_in: endpoint {
slave-mode;
remote-endpoint = <&funnel0_out>;
};
};
port@1 {
reg = <0>;
- etf_in: endpoint {
+ etf_out: endpoint {
remote-endpoint = <&replicator_in>;
};
};
sound {
compatible = "audio-graph-card";
label = "UniPhier LD11";
- widgets = "Headphone", "Headphone Jack";
+ widgets = "Headphone", "Headphones";
dais = <&i2s_port2
&i2s_port3
&i2s_port4
sound {
compatible = "audio-graph-card";
label = "UniPhier LD20";
- widgets = "Headphone", "Headphone Jack";
+ widgets = "Headphone", "Headphones";
dais = <&i2s_port2
&i2s_port3
&i2s_port4
CONFIG_ARCH_QCOM=y
CONFIG_ARCH_ROCKCHIP=y
CONFIG_ARCH_SEATTLE=y
+CONFIG_ARCH_SYNQUACER=y
CONFIG_ARCH_RENESAS=y
CONFIG_ARCH_R8A7795=y
CONFIG_ARCH_R8A7796=y
CONFIG_ARCH_STRATIX10=y
CONFIG_ARCH_TEGRA=y
CONFIG_ARCH_SPRD=y
-CONFIG_ARCH_SYNQUACER=y
CONFIG_ARCH_THUNDER=y
CONFIG_ARCH_THUNDER2=y
CONFIG_ARCH_UNIPHIER=y
CONFIG_ARCH_ZX=y
CONFIG_ARCH_ZYNQMP=y
CONFIG_PCI=y
-CONFIG_HOTPLUG_PCI_PCIE=y
CONFIG_PCI_IOV=y
CONFIG_HOTPLUG_PCI=y
CONFIG_HOTPLUG_PCI_ACPI=y
-CONFIG_PCI_LAYERSCAPE=y
-CONFIG_PCI_HISI=y
-CONFIG_PCIE_QCOM=y
-CONFIG_PCIE_KIRIN=y
-CONFIG_PCIE_ARMADA_8K=y
-CONFIG_PCIE_HISI_STB=y
CONFIG_PCI_AARDVARK=y
CONFIG_PCI_TEGRA=y
CONFIG_PCIE_RCAR=y
-CONFIG_PCIE_ROCKCHIP=y
-CONFIG_PCIE_ROCKCHIP_HOST=m
CONFIG_PCI_HOST_GENERIC=y
CONFIG_PCI_XGENE=y
CONFIG_PCI_HOST_THUNDER_PEM=y
CONFIG_PCI_HOST_THUNDER_ECAM=y
+CONFIG_PCIE_ROCKCHIP_HOST=m
+CONFIG_PCI_LAYERSCAPE=y
+CONFIG_PCI_HISI=y
+CONFIG_PCIE_QCOM=y
+CONFIG_PCIE_ARMADA_8K=y
+CONFIG_PCIE_KIRIN=y
+CONFIG_PCIE_HISI_STB=y
CONFIG_ARM64_VA_BITS_48=y
CONFIG_SCHED_MC=y
CONFIG_NUMA=y
CONFIG_WQ_POWER_EFFICIENT_DEFAULT=y
CONFIG_ARM_CPUIDLE=y
CONFIG_CPU_FREQ=y
-CONFIG_CPU_FREQ_GOV_ATTR_SET=y
-CONFIG_CPU_FREQ_GOV_COMMON=y
CONFIG_CPU_FREQ_STAT=y
CONFIG_CPU_FREQ_GOV_POWERSAVE=m
CONFIG_CPU_FREQ_GOV_USERSPACE=y
CONFIG_CPU_FREQ_GOV_CONSERVATIVE=m
CONFIG_CPU_FREQ_GOV_SCHEDUTIL=y
CONFIG_CPUFREQ_DT=y
+CONFIG_ACPI_CPPC_CPUFREQ=m
CONFIG_ARM_ARMADA_37XX_CPUFREQ=y
CONFIG_ARM_BIG_LITTLE_CPUFREQ=y
CONFIG_ARM_SCPI_CPUFREQ=y
CONFIG_ARM_TEGRA186_CPUFREQ=y
-CONFIG_ACPI_CPPC_CPUFREQ=m
CONFIG_NET=y
CONFIG_PACKET=y
CONFIG_UNIX=y
CONFIG_SNI_AVE=y
CONFIG_SNI_NETSEC=y
CONFIG_STMMAC_ETH=m
-CONFIG_DWMAC_IPQ806X=m
-CONFIG_DWMAC_MESON=m
-CONFIG_DWMAC_ROCKCHIP=m
-CONFIG_DWMAC_SUNXI=m
-CONFIG_DWMAC_SUN8I=m
CONFIG_MDIO_BUS_MUX_MMIOREG=y
CONFIG_AT803X_PHY=m
CONFIG_MARVELL_PHY=m
CONFIG_WLCORE_SDIO=m
CONFIG_INPUT_EVDEV=y
CONFIG_KEYBOARD_ADC=m
-CONFIG_KEYBOARD_CROS_EC=y
CONFIG_KEYBOARD_GPIO=y
+CONFIG_KEYBOARD_CROS_EC=y
CONFIG_INPUT_TOUCHSCREEN=y
CONFIG_TOUCHSCREEN_ATMEL_MXT=m
CONFIG_INPUT_MISC=y
CONFIG_SERIAL_SAMSUNG_CONSOLE=y
CONFIG_SERIAL_TEGRA=y
CONFIG_SERIAL_SH_SCI=y
-CONFIG_SERIAL_SH_SCI_NR_UARTS=11
-CONFIG_SERIAL_SH_SCI_CONSOLE=y
CONFIG_SERIAL_MSM=y
CONFIG_SERIAL_MSM_CONSOLE=y
CONFIG_SERIAL_XILINX_PS_UART=y
CONFIG_SERIAL_XILINX_PS_UART_CONSOLE=y
CONFIG_SERIAL_MVEBU_UART=y
CONFIG_SERIAL_DEV_BUS=y
-CONFIG_SERIAL_DEV_CTRL_TTYPORT=y
CONFIG_VIRTIO_CONSOLE=y
-CONFIG_I2C_HID=m
CONFIG_I2C_CHARDEV=y
CONFIG_I2C_MUX=y
CONFIG_I2C_MUX_PCA954x=y
CONFIG_I2C_CROS_EC_TUNNEL=y
CONFIG_SPI=y
CONFIG_SPI_ARMADA_3700=y
-CONFIG_SPI_MESON_SPICC=m
-CONFIG_SPI_MESON_SPIFC=m
CONFIG_SPI_BCM2835=m
CONFIG_SPI_BCM2835AUX=m
+CONFIG_SPI_MESON_SPICC=m
+CONFIG_SPI_MESON_SPIFC=m
CONFIG_SPI_ORION=y
CONFIG_SPI_PL022=y
-CONFIG_SPI_QUP=y
CONFIG_SPI_ROCKCHIP=y
+CONFIG_SPI_QUP=y
CONFIG_SPI_S3C64XX=y
CONFIG_SPI_SPIDEV=m
CONFIG_SPMI=y
-CONFIG_PINCTRL_IPQ8074=y
CONFIG_PINCTRL_SINGLE=y
CONFIG_PINCTRL_MAX77620=y
+CONFIG_PINCTRL_IPQ8074=y
CONFIG_PINCTRL_MSM8916=y
CONFIG_PINCTRL_MSM8994=y
CONFIG_PINCTRL_MSM8996=y
-CONFIG_PINCTRL_MT7622=y
CONFIG_PINCTRL_QDF2XXX=y
CONFIG_PINCTRL_QCOM_SPMI_PMIC=y
+CONFIG_PINCTRL_MT7622=y
CONFIG_GPIO_DWAPB=y
CONFIG_GPIO_MB86S7X=y
CONFIG_GPIO_PL061=y
CONFIG_THERMAL_GOV_POWER_ALLOCATOR=y
CONFIG_CPU_THERMAL=y
CONFIG_THERMAL_EMULATION=y
+CONFIG_ROCKCHIP_THERMAL=m
+CONFIG_RCAR_GEN3_THERMAL=y
CONFIG_ARMADA_THERMAL=y
CONFIG_BRCMSTB_THERMAL=m
CONFIG_EXYNOS_THERMAL=y
-CONFIG_RCAR_GEN3_THERMAL=y
-CONFIG_QCOM_TSENS=y
-CONFIG_ROCKCHIP_THERMAL=m
CONFIG_TEGRA_BPMP_THERMAL=m
+CONFIG_QCOM_TSENS=y
CONFIG_UNIPHIER_THERMAL=y
CONFIG_WATCHDOG=y
CONFIG_S3C2410_WATCHDOG=y
CONFIG_MFD_SPMI_PMIC=y
CONFIG_MFD_RK808=y
CONFIG_MFD_SEC_CORE=y
+CONFIG_REGULATOR_FIXED_VOLTAGE=y
CONFIG_REGULATOR_AXP20X=y
CONFIG_REGULATOR_FAN53555=y
-CONFIG_REGULATOR_FIXED_VOLTAGE=y
CONFIG_REGULATOR_GPIO=y
CONFIG_REGULATOR_HI6421V530=y
CONFIG_REGULATOR_HI655X=y
CONFIG_REGULATOR_QCOM_SPMI=y
CONFIG_REGULATOR_RK808=y
CONFIG_REGULATOR_S2MPS11=y
+CONFIG_RC_CORE=m
+CONFIG_RC_DECODERS=y
+CONFIG_RC_DEVICES=y
+CONFIG_IR_MESON=m
CONFIG_MEDIA_SUPPORT=m
CONFIG_MEDIA_CAMERA_SUPPORT=y
CONFIG_MEDIA_ANALOG_TV_SUPPORT=y
CONFIG_MEDIA_DIGITAL_TV_SUPPORT=y
CONFIG_MEDIA_CONTROLLER=y
-CONFIG_MEDIA_RC_SUPPORT=y
-CONFIG_RC_CORE=m
-CONFIG_RC_DEVICES=y
-CONFIG_RC_DECODERS=y
-CONFIG_IR_MESON=m
CONFIG_VIDEO_V4L2_SUBDEV_API=y
# CONFIG_DVB_NET is not set
CONFIG_V4L_MEM2MEM_DRIVERS=y
CONFIG_ROCKCHIP_DW_MIPI_DSI=y
CONFIG_ROCKCHIP_INNO_HDMI=y
CONFIG_DRM_RCAR_DU=m
-CONFIG_DRM_RCAR_LVDS=y
-CONFIG_DRM_RCAR_VSP=y
+CONFIG_DRM_RCAR_LVDS=m
CONFIG_DRM_TEGRA=m
CONFIG_DRM_PANEL_SIMPLE=m
CONFIG_DRM_I2C_ADV7511=m
CONFIG_BACKLIGHT_GENERIC=m
CONFIG_BACKLIGHT_PWM=m
CONFIG_BACKLIGHT_LP855X=m
-CONFIG_FRAMEBUFFER_CONSOLE=y
CONFIG_LOGO=y
# CONFIG_LOGO_LINUX_MONO is not set
# CONFIG_LOGO_LINUX_VGA16 is not set
CONFIG_SND_SOC_AK4613=m
CONFIG_SND_SIMPLE_CARD=m
CONFIG_SND_AUDIO_GRAPH_CARD=m
+CONFIG_I2C_HID=m
CONFIG_USB=y
CONFIG_USB_OTG=y
CONFIG_USB_XHCI_HCD=y
CONFIG_MMC_ARMMMCI=y
CONFIG_MMC_SDHCI=y
CONFIG_MMC_SDHCI_ACPI=y
-CONFIG_MMC_SDHCI_F_SDH30=y
CONFIG_MMC_SDHCI_PLTFM=y
CONFIG_MMC_SDHCI_OF_ARASAN=y
CONFIG_MMC_SDHCI_OF_ESDHC=y
CONFIG_MMC_SDHCI_CADENCE=y
CONFIG_MMC_SDHCI_TEGRA=y
+CONFIG_MMC_SDHCI_F_SDH30=y
CONFIG_MMC_MESON_GX=y
CONFIG_MMC_SDHCI_MSM=y
CONFIG_MMC_SPI=y
CONFIG_LEDS_GPIO=y
CONFIG_LEDS_PWM=y
CONFIG_LEDS_SYSCON=y
+CONFIG_LEDS_TRIGGER_DISK=y
CONFIG_LEDS_TRIGGER_HEARTBEAT=y
CONFIG_LEDS_TRIGGER_CPU=y
CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
CONFIG_LEDS_TRIGGER_PANIC=y
-CONFIG_LEDS_TRIGGER_DISK=y
CONFIG_EDAC=y
CONFIG_EDAC_GHES=y
CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_S5M=y
CONFIG_RTC_DRV_DS3232=y
CONFIG_RTC_DRV_EFI=y
+CONFIG_RTC_DRV_CROS_EC=y
CONFIG_RTC_DRV_S3C=y
CONFIG_RTC_DRV_PL031=y
CONFIG_RTC_DRV_SUN6I=y
CONFIG_RTC_DRV_ARMADA38X=y
CONFIG_RTC_DRV_TEGRA=y
CONFIG_RTC_DRV_XGENE=y
-CONFIG_RTC_DRV_CROS_EC=y
CONFIG_DMADEVICES=y
CONFIG_DMA_BCM2835=m
CONFIG_K3_DMA=y
CONFIG_ARM_MHU=y
CONFIG_PLATFORM_MHU=y
CONFIG_BCM2835_MBOX=y
-CONFIG_HI6220_MBOX=y
CONFIG_QCOM_APCS_IPC=y
CONFIG_ROCKCHIP_IOMMU=y
CONFIG_TEGRA_IOMMU_SMMU=y
CONFIG_EXTCON_USB_GPIO=y
CONFIG_EXTCON_USBC_CROS_EC=y
CONFIG_MEMORY=y
-CONFIG_TEGRA_MC=y
CONFIG_IIO=y
CONFIG_EXYNOS_ADC=y
CONFIG_ROCKCHIP_SARADC=m
CONFIG_PWM_ROCKCHIP=y
CONFIG_PWM_SAMSUNG=y
CONFIG_PWM_TEGRA=m
+CONFIG_PHY_XGENE=y
+CONFIG_PHY_SUN4I_USB=y
+CONFIG_PHY_HI6220_USB=y
CONFIG_PHY_HISTB_COMBPHY=y
CONFIG_PHY_HISI_INNO_USB2=y
-CONFIG_PHY_RCAR_GEN3_USB2=y
-CONFIG_PHY_RCAR_GEN3_USB3=m
-CONFIG_PHY_HI6220_USB=y
-CONFIG_PHY_QCOM_USB_HS=y
-CONFIG_PHY_SUN4I_USB=y
CONFIG_PHY_MVEBU_CP110_COMPHY=y
CONFIG_PHY_QCOM_QMP=m
-CONFIG_PHY_ROCKCHIP_INNO_USB2=y
+CONFIG_PHY_QCOM_USB_HS=y
+CONFIG_PHY_RCAR_GEN3_USB2=y
+CONFIG_PHY_RCAR_GEN3_USB3=m
CONFIG_PHY_ROCKCHIP_EMMC=y
+CONFIG_PHY_ROCKCHIP_INNO_USB2=y
CONFIG_PHY_ROCKCHIP_PCIE=m
CONFIG_PHY_ROCKCHIP_TYPEC=y
-CONFIG_PHY_XGENE=y
CONFIG_PHY_TEGRA_XUSB=y
CONFIG_QCOM_L2_PMU=y
CONFIG_QCOM_L3_PMU=y
-CONFIG_MESON_EFUSE=m
CONFIG_QCOM_QFPROM=y
CONFIG_ROCKCHIP_EFUSE=y
CONFIG_UNIPHIER_EFUSE=y
+CONFIG_MESON_EFUSE=m
CONFIG_TEE=y
CONFIG_OPTEE=y
CONFIG_ARM_SCPI_PROTOCOL=y
CONFIG_ACPI=y
CONFIG_ACPI_APEI=y
CONFIG_ACPI_APEI_GHES=y
-CONFIG_ACPI_APEI_PCIEAER=y
CONFIG_ACPI_APEI_MEMORY_FAILURE=y
CONFIG_ACPI_APEI_EINJ=y
CONFIG_EXT2_FS=y
CONFIG_DEBUG_FS=y
CONFIG_MAGIC_SYSRQ=y
CONFIG_DEBUG_KERNEL=y
-CONFIG_LOCKUP_DETECTOR=y
# CONFIG_SCHED_DEBUG is not set
# CONFIG_DEBUG_PREEMPT is not set
# CONFIG_FTRACE is not set
CONFIG_CRYPTO_ECHAINIV=y
CONFIG_CRYPTO_ANSI_CPRNG=y
CONFIG_ARM64_CRYPTO=y
-CONFIG_CRYPTO_SHA256_ARM64=m
-CONFIG_CRYPTO_SHA512_ARM64=m
CONFIG_CRYPTO_SHA1_ARM64_CE=y
CONFIG_CRYPTO_SHA2_ARM64_CE=y
+CONFIG_CRYPTO_SHA512_ARM64_CE=m
+CONFIG_CRYPTO_SHA3_ARM64=m
+CONFIG_CRYPTO_SM3_ARM64_CE=m
CONFIG_CRYPTO_GHASH_ARM64_CE=y
CONFIG_CRYPTO_CRCT10DIF_ARM64_CE=m
CONFIG_CRYPTO_CRC32_ARM64_CE=m
-CONFIG_CRYPTO_AES_ARM64=m
-CONFIG_CRYPTO_AES_ARM64_CE=m
CONFIG_CRYPTO_AES_ARM64_CE_CCM=y
CONFIG_CRYPTO_AES_ARM64_CE_BLK=y
-CONFIG_CRYPTO_AES_ARM64_NEON_BLK=m
CONFIG_CRYPTO_CHACHA20_NEON=m
CONFIG_CRYPTO_AES_ARM64_BS=m
-CONFIG_CRYPTO_SHA512_ARM64_CE=m
-CONFIG_CRYPTO_SHA3_ARM64=m
-CONFIG_CRYPTO_SM3_ARM64_CE=m
kernel_neon_begin();
aes_ctr_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
(u8 *)ctx->key_enc, rounds, blocks, walk.iv);
- err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
kernel_neon_end();
+ err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
}
if (walk.nbytes) {
u8 __aligned(8) tail[AES_BLOCK_SIZE];
__le32 *origptr, __le32 *updptr, int nr_inst);
void __init apply_alternatives_all(void);
-void apply_alternatives(void *start, size_t length);
+
+#ifdef CONFIG_MODULES
+void apply_alternatives_module(void *start, size_t length);
+#else
+static inline void apply_alternatives_module(void *start, size_t length) { }
+#endif
#define ALTINSTR_ENTRY(feature,cb) \
" .word 661b - .\n" /* label */ \
#define KVM_ARM64_FP_ENABLED (1 << 1) /* guest FP regs loaded */
#define KVM_ARM64_FP_HOST (1 << 2) /* host FP regs loaded */
#define KVM_ARM64_HOST_SVE_IN_USE (1 << 3) /* backup for host TIF_SVE */
+#define KVM_ARM64_HOST_SVE_ENABLED (1 << 4) /* SVE enabled for EL0 */
#define vcpu_gp_regs(v) (&(v)->arch.ctxt.gp_regs)
* Only if the new pte is valid and kernel, otherwise TLB maintenance
* or update_mmu_cache() have the necessary barriers.
*/
- if (pte_valid_not_user(pte)) {
+ if (pte_valid_not_user(pte))
dsb(ishst);
- isb();
- }
}
extern void __sync_icache_dcache(pte_t pteval);
{
WRITE_ONCE(*pmdp, pmd);
dsb(ishst);
- isb();
}
static inline void pmd_clear(pmd_t *pmdp)
{
WRITE_ONCE(*pudp, pud);
dsb(ishst);
- isb();
}
static inline void pud_clear(pud_t *pudp)
asm volatile("msr_s " __stringify(r) ", %x0" : : "rZ" (__val)); \
} while (0)
+/*
+ * Modify bits in a sysreg. Bits in the clear mask are zeroed, then bits in the
+ * set mask are set. Other bits are left as-is.
+ */
+#define sysreg_clear_set(sysreg, clear, set) do { \
+ u64 __scs_val = read_sysreg(sysreg); \
+ u64 __scs_new = (__scs_val & ~(u64)(clear)) | (set); \
+ if (__scs_new != __scs_val) \
+ write_sysreg(__scs_new, sysreg); \
+} while (0)
+
static inline void config_sctlr_el1(u32 clear, u32 set)
{
u32 val;
}
}
-static void __apply_alternatives(void *alt_region, bool use_linear_alias)
+/*
+ * We provide our own, private D-cache cleaning function so that we don't
+ * accidentally call into the cache.S code, which is patched by us at
+ * runtime.
+ */
+static void clean_dcache_range_nopatch(u64 start, u64 end)
+{
+ u64 cur, d_size, ctr_el0;
+
+ ctr_el0 = read_sanitised_ftr_reg(SYS_CTR_EL0);
+ d_size = 4 << cpuid_feature_extract_unsigned_field(ctr_el0,
+ CTR_DMINLINE_SHIFT);
+ cur = start & ~(d_size - 1);
+ do {
+ /*
+ * We must clean+invalidate to the PoC in order to avoid
+ * Cortex-A53 errata 826319, 827319, 824069 and 819472
+ * (this corresponds to ARM64_WORKAROUND_CLEAN_CACHE)
+ */
+ asm volatile("dc civac, %0" : : "r" (cur) : "memory");
+ } while (cur += d_size, cur < end);
+}
+
+static void __apply_alternatives(void *alt_region, bool is_module)
{
struct alt_instr *alt;
struct alt_region *region = alt_region;
pr_info_once("patching kernel code\n");
origptr = ALT_ORIG_PTR(alt);
- updptr = use_linear_alias ? lm_alias(origptr) : origptr;
+ updptr = is_module ? origptr : lm_alias(origptr);
nr_inst = alt->orig_len / AARCH64_INSN_SIZE;
if (alt->cpufeature < ARM64_CB_PATCH)
alt_cb(alt, origptr, updptr, nr_inst);
- flush_icache_range((uintptr_t)origptr,
- (uintptr_t)(origptr + nr_inst));
+ if (!is_module) {
+ clean_dcache_range_nopatch((u64)origptr,
+ (u64)(origptr + nr_inst));
+ }
+ }
+
+ /*
+ * The core module code takes care of cache maintenance in
+ * flush_module_icache().
+ */
+ if (!is_module) {
+ dsb(ish);
+ __flush_icache_all();
+ isb();
}
}
isb();
} else {
BUG_ON(alternatives_applied);
- __apply_alternatives(®ion, true);
+ __apply_alternatives(®ion, false);
/* Barriers provided by the cache flushing */
WRITE_ONCE(alternatives_applied, 1);
}
stop_machine(__apply_alternatives_multi_stop, NULL, cpu_online_mask);
}
-void apply_alternatives(void *start, size_t length)
+#ifdef CONFIG_MODULES
+void apply_alternatives_module(void *start, size_t length)
{
struct alt_region region = {
.begin = start,
.end = start + length,
};
- __apply_alternatives(®ion, false);
+ __apply_alternatives(®ion, true);
}
+#endif
__kpti_forced = enabled ? 1 : -1;
return 0;
}
-__setup("kpti=", parse_kpti);
+early_param("kpti", parse_kpti);
#endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */
#ifdef CONFIG_ARM64_HW_AFDBM
const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
for (s = sechdrs, se = sechdrs + hdr->e_shnum; s < se; s++) {
- if (strcmp(".altinstructions", secstrs + s->sh_name) == 0) {
- apply_alternatives((void *)s->sh_addr, s->sh_size);
- }
+ if (strcmp(".altinstructions", secstrs + s->sh_name) == 0)
+ apply_alternatives_module((void *)s->sh_addr, s->sh_size);
#ifdef CONFIG_ARM64_MODULE_PLTS
if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE) &&
!strcmp(".text.ftrace_trampoline", secstrs + s->sh_name))
* This is the secondary CPU boot entry. We're using this CPUs
* idle thread stack, but a set of temporary page tables.
*/
-asmlinkage void secondary_start_kernel(void)
+asmlinkage notrace void secondary_start_kernel(void)
{
u64 mpidr = read_cpuid_mpidr() & MPIDR_HWID_BITMASK;
struct mm_struct *mm = &init_mm;
* Copyright 2018 Arm Limited
* Author: Dave Martin <Dave.Martin@arm.com>
*/
-#include <linux/bottom_half.h>
+#include <linux/irqflags.h>
#include <linux/sched.h>
#include <linux/thread_info.h>
#include <linux/kvm_host.h>
#include <asm/kvm_asm.h>
#include <asm/kvm_host.h>
#include <asm/kvm_mmu.h>
+#include <asm/sysreg.h>
/*
* Called on entry to KVM_RUN unless this vcpu previously ran at least
{
BUG_ON(!current->mm);
- vcpu->arch.flags &= ~(KVM_ARM64_FP_ENABLED | KVM_ARM64_HOST_SVE_IN_USE);
+ vcpu->arch.flags &= ~(KVM_ARM64_FP_ENABLED |
+ KVM_ARM64_HOST_SVE_IN_USE |
+ KVM_ARM64_HOST_SVE_ENABLED);
vcpu->arch.flags |= KVM_ARM64_FP_HOST;
+
if (test_thread_flag(TIF_SVE))
vcpu->arch.flags |= KVM_ARM64_HOST_SVE_IN_USE;
+
+ if (read_sysreg(cpacr_el1) & CPACR_EL1_ZEN_EL0EN)
+ vcpu->arch.flags |= KVM_ARM64_HOST_SVE_ENABLED;
}
/*
*/
void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu)
{
- local_bh_disable();
+ unsigned long flags;
- update_thread_flag(TIF_SVE,
- vcpu->arch.flags & KVM_ARM64_HOST_SVE_IN_USE);
+ local_irq_save(flags);
if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) {
/* Clean guest FP state to memory and invalidate cpu view */
fpsimd_save();
fpsimd_flush_cpu_state();
- } else if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) {
- /* Ensure user trap controls are correctly restored */
- fpsimd_bind_task_to_cpu();
+ } else if (system_supports_sve()) {
+ /*
+ * The FPSIMD/SVE state in the CPU has not been touched, and we
+ * have SVE (and VHE): CPACR_EL1 (alias CPTR_EL2) has been
+ * reset to CPACR_EL1_DEFAULT by the Hyp code, disabling SVE
+ * for EL0. To avoid spurious traps, restore the trap state
+ * seen by kvm_arch_vcpu_load_fp():
+ */
+ if (vcpu->arch.flags & KVM_ARM64_HOST_SVE_ENABLED)
+ sysreg_clear_set(CPACR_EL1, 0, CPACR_EL1_ZEN_EL0EN);
+ else
+ sysreg_clear_set(CPACR_EL1, CPACR_EL1_ZEN_EL0EN, 0);
}
- local_bh_enable();
+ update_thread_flag(TIF_SVE,
+ vcpu->arch.flags & KVM_ARM64_HOST_SVE_IN_USE);
+
+ local_irq_restore(flags);
}
size >> PAGE_SHIFT);
return NULL;
}
- if (!coherent)
- __dma_flush_area(page_to_virt(page), iosize);
-
addr = dma_common_contiguous_remap(page, size, VM_USERMAP,
prot,
__builtin_return_address(0));
- if (!addr) {
+ if (addr) {
+ memset(addr, 0, size);
+ if (!coherent)
+ __dma_flush_area(page_to_virt(page), iosize);
+ } else {
iommu_dma_unmap_page(dev, *handle, iosize, 0, attrs);
dma_release_from_contiguous(dev, page,
size >> PAGE_SHIFT);
.macro __idmap_kpti_put_pgtable_ent_ng, type
orr \type, \type, #PTE_NG // Same bit for blocks and pages
- str \type, [cur_\()\type\()p] // Update the entry and ensure it
- dc civac, cur_\()\type\()p // is visible to all CPUs.
+ str \type, [cur_\()\type\()p] // Update the entry and ensure
+ dmb sy // that it is visible to all
+ dc civac, cur_\()\type\()p // CPUs.
.endm
/*
#define SO_ZEROCOPY 60
+#define SO_TXTIME 61
+#define SCM_TXTIME SO_TXTIME
+
#endif /* _ASM_IA64_SOCKET_H */
source "lib/Kconfig.debug"
-config HEART_BEAT
- bool "Heart beat function for kernel"
- default n
- help
- This option turns on/off heart beat kernel functionality.
- First GPIO node is taken.
-
endmenu
extern char *klimit;
-void microblaze_heartbeat(void);
-void microblaze_setup_heartbeat(void);
-
# ifdef CONFIG_MMU
extern void mmu_reset(void);
# endif /* CONFIG_MMU */
-extern void of_platform_reset_gpio_probe(void);
-
void time_init(void);
void init_IRQ(void);
void machine_early_init(const char *cmdline, unsigned int ram,
#endif /* __ASSEMBLY__ */
-#define __NR_syscalls 399
+#define __NR_syscalls 401
#endif /* _ASM_MICROBLAZE_UNISTD_H */
#define __NR_pkey_alloc 396
#define __NR_pkey_free 397
#define __NR_statx 398
+#define __NR_io_pgetevents 399
+#define __NR_rseq 400
#endif /* _UAPI_ASM_MICROBLAZE_UNISTD_H */
CFLAGS_REMOVE_timer.o = -pg
CFLAGS_REMOVE_intc.o = -pg
CFLAGS_REMOVE_early_printk.o = -pg
-CFLAGS_REMOVE_heartbeat.o = -pg
CFLAGS_REMOVE_ftrace.o = -pg
CFLAGS_REMOVE_process.o = -pg
endif
obj-y += dma.o exceptions.o \
hw_exception_handler.o irq.o \
- platform.o process.o prom.o ptrace.o \
+ process.o prom.o ptrace.o \
reset.o setup.o signal.o sys_microblaze.o timer.o traps.o unwind.o
obj-y += cpu/
-obj-$(CONFIG_HEART_BEAT) += heartbeat.o
obj-$(CONFIG_MODULES) += microblaze_ksyms.o module.o
obj-$(CONFIG_MMU) += misc.o
obj-$(CONFIG_STACKTRACE) += stacktrace.o
+++ /dev/null
-/*
- * Copyright (C) 2007-2009 Michal Simek <monstr@monstr.eu>
- * Copyright (C) 2007-2009 PetaLogix
- * Copyright (C) 2006 Atmark Techno, Inc.
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- */
-
-#include <linux/sched.h>
-#include <linux/sched/loadavg.h>
-#include <linux/io.h>
-
-#include <asm/setup.h>
-#include <asm/page.h>
-#include <asm/prom.h>
-
-static unsigned int base_addr;
-
-void microblaze_heartbeat(void)
-{
- static unsigned int cnt, period, dist;
-
- if (base_addr) {
- if (cnt == 0 || cnt == dist)
- out_be32(base_addr, 1);
- else if (cnt == 7 || cnt == dist + 7)
- out_be32(base_addr, 0);
-
- if (++cnt > period) {
- cnt = 0;
- /*
- * The hyperbolic function below modifies the heartbeat
- * period length in dependency of the current (5min)
- * load. It goes through the points f(0)=126, f(1)=86,
- * f(5)=51, f(inf)->30.
- */
- period = ((672 << FSHIFT) / (5 * avenrun[0] +
- (7 << FSHIFT))) + 30;
- dist = period / 4;
- }
- }
-}
-
-void microblaze_setup_heartbeat(void)
-{
- struct device_node *gpio = NULL;
- int *prop;
- int j;
- const char * const gpio_list[] = {
- "xlnx,xps-gpio-1.00.a",
- NULL
- };
-
- for (j = 0; gpio_list[j] != NULL; j++) {
- gpio = of_find_compatible_node(NULL, NULL, gpio_list[j]);
- if (gpio)
- break;
- }
-
- if (gpio) {
- base_addr = be32_to_cpup(of_get_property(gpio, "reg", NULL));
- base_addr = (unsigned long) ioremap(base_addr, PAGE_SIZE);
- pr_notice("Heartbeat GPIO at 0x%x\n", base_addr);
-
- /* GPIO is configured as output */
- prop = (int *) of_get_property(gpio, "xlnx,is-bidir", NULL);
- if (prop)
- out_be32(base_addr + 4, 0);
- }
-}
+++ /dev/null
-/*
- * Copyright 2008 Michal Simek <monstr@monstr.eu>
- *
- * based on virtex.c file
- *
- * Copyright 2007 Secret Lab Technologies Ltd.
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2. This program is licensed "as is" without any warranty of any
- * kind, whether express or implied.
- */
-
-#include <linux/init.h>
-#include <linux/of_platform.h>
-#include <asm/setup.h>
-
-static struct of_device_id xilinx_of_bus_ids[] __initdata = {
- { .compatible = "simple-bus", },
- { .compatible = "xlnx,compound", },
- {}
-};
-
-static int __init microblaze_device_probe(void)
-{
- of_platform_bus_probe(NULL, xilinx_of_bus_ids, NULL);
- of_platform_reset_gpio_probe();
- return 0;
-}
-device_initcall(microblaze_device_probe);
static int handle; /* reset pin handle */
static unsigned int reset_val;
-void of_platform_reset_gpio_probe(void)
+static int of_platform_reset_gpio_probe(void)
{
int ret;
handle = of_get_named_gpio(of_find_node_by_path("/"),
if (!gpio_is_valid(handle)) {
pr_info("Skipping unavailable RESET gpio %d (%s)\n",
handle, "reset");
- return;
+ return -ENODEV;
}
ret = gpio_request(handle, "reset");
if (ret < 0) {
pr_info("GPIO pin is already allocated\n");
- return;
+ return ret;
}
/* get current setup value */
pr_info("RESET: Registered gpio device: %d, current val: %d\n",
handle, reset_val);
- return;
+ return 0;
err:
gpio_free(handle);
- return;
+ return ret;
}
+device_initcall(of_platform_reset_gpio_probe);
static void gpio_system_reset(void)
.long sys_pkey_alloc
.long sys_pkey_free
.long sys_statx
+ .long sys_io_pgetevents
+ .long sys_rseq
static irqreturn_t timer_interrupt(int irq, void *dev_id)
{
struct clock_event_device *evt = &clockevent_xilinx_timer;
-#ifdef CONFIG_HEART_BEAT
- microblaze_heartbeat();
-#endif
timer_ack();
evt->event_handler(evt);
return IRQ_HANDLED;
return ret;
}
-#ifdef CONFIG_HEART_BEAT
- microblaze_setup_heartbeat();
-#endif
-
ret = xilinx_clocksource_init();
if (ret)
return ret;
select HAVE_OPROFILE
select HAVE_PERF_EVENTS
select HAVE_REGS_AND_STACK_ACCESS_API
+ select HAVE_RSEQ
select HAVE_STACKPROTECTOR
select HAVE_SYSCALL_TRACEPOINTS
select HAVE_VIRT_CPU_ACCOUNTING_GEN if 64BIT || !SMP
#define PB44_KEYS_DEBOUNCE_INTERVAL (3 * PB44_KEYS_POLL_INTERVAL)
static struct gpiod_lookup_table pb44_i2c_gpiod_table = {
- .dev_id = "i2c-gpio",
+ .dev_id = "i2c-gpio.0",
.table = {
GPIO_LOOKUP_IDX("ath79-gpio", PB44_GPIO_I2C_SDA,
NULL, 0, GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),
*/
if (bcm47xx_bus.bcma.bus.chipinfo.id == BCMA_CHIP_ID_BCM4706)
cpu_wait = NULL;
+
+ /*
+ * BCM47XX Erratum "R10: PCIe Transactions Periodically Fail"
+ * Enable ExternalSync for sync instruction to take effect
+ */
+ set_c0_config7(MIPS_CONF7_ES);
break;
#endif
}
__val = *__addr; \
slow; \
\
+ /* prevent prefetching of coherent DMA data prematurely */ \
+ rmb(); \
return pfx##ioswab##bwlq(__addr, __val); \
}
#define MIPS_CONF7_WII (_ULCAST_(1) << 31)
#define MIPS_CONF7_RPS (_ULCAST_(1) << 2)
+/* ExternalSync */
+#define MIPS_CONF7_ES (_ULCAST_(1) << 8)
#define MIPS_CONF7_IAR (_ULCAST_(1) << 10)
#define MIPS_CONF7_AR (_ULCAST_(1) << 16)
__BUILD_SET_C0(cause)
__BUILD_SET_C0(config)
__BUILD_SET_C0(config5)
+__BUILD_SET_C0(config7)
__BUILD_SET_C0(intcontrol)
__BUILD_SET_C0(intctl)
__BUILD_SET_C0(srsmap)
#define SO_ZEROCOPY 60
+#define SO_TXTIME 61
+#define SCM_TXTIME SO_TXTIME
+
#endif /* _UAPI_ASM_SOCKET_H */
#define __NR_pkey_alloc (__NR_Linux + 364)
#define __NR_pkey_free (__NR_Linux + 365)
#define __NR_statx (__NR_Linux + 366)
+#define __NR_rseq (__NR_Linux + 367)
+#define __NR_io_pgetevents (__NR_Linux + 368)
/*
* Offset of the last Linux o32 flavoured syscall
*/
-#define __NR_Linux_syscalls 366
+#define __NR_Linux_syscalls 368
#endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */
#define __NR_O32_Linux 4000
-#define __NR_O32_Linux_syscalls 366
+#define __NR_O32_Linux_syscalls 368
#if _MIPS_SIM == _MIPS_SIM_ABI64
#define __NR_pkey_alloc (__NR_Linux + 324)
#define __NR_pkey_free (__NR_Linux + 325)
#define __NR_statx (__NR_Linux + 326)
+#define __NR_rseq (__NR_Linux + 327)
+#define __NR_io_pgetevents (__NR_Linux + 328)
/*
* Offset of the last Linux 64-bit flavoured syscall
*/
-#define __NR_Linux_syscalls 326
+#define __NR_Linux_syscalls 328
#endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */
#define __NR_64_Linux 5000
-#define __NR_64_Linux_syscalls 326
+#define __NR_64_Linux_syscalls 328
#if _MIPS_SIM == _MIPS_SIM_NABI32
#define __NR_pkey_alloc (__NR_Linux + 328)
#define __NR_pkey_free (__NR_Linux + 329)
#define __NR_statx (__NR_Linux + 330)
+#define __NR_rseq (__NR_Linux + 331)
+#define __NR_io_pgetevents (__NR_Linux + 332)
/*
* Offset of the last N32 flavoured syscall
*/
-#define __NR_Linux_syscalls 330
+#define __NR_Linux_syscalls 332
#endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */
#define __NR_N32_Linux 6000
-#define __NR_N32_Linux_syscalls 330
+#define __NR_N32_Linux_syscalls 332
#endif /* _UAPI_ASM_UNISTD_H */
jal schedule_tail # a0 = struct task_struct *prev
FEXPORT(syscall_exit)
+#ifdef CONFIG_DEBUG_RSEQ
+ move a0, sp
+ jal rseq_syscall
+#endif
local_irq_disable # make sure need_resched and
# signals dont change between
# sampling and return
j resume_userspace_check
FEXPORT(syscall_exit_partial)
+#ifdef CONFIG_DEBUG_RSEQ
+ move a0, sp
+ jal rseq_syscall
+#endif
local_irq_disable # make sure need_resched doesn't
# change between and return
LONG_L a2, TI_FLAGS($28) # current->work
EXPORT_SYMBOL(_mcount)
PTR_LA t1, ftrace_stub
PTR_L t2, ftrace_trace_function /* Prepare t2 for (1) */
- bne t1, t2, static_trace
+ beq t1, t2, fgraph_trace
nop
+ MCOUNT_SAVE_REGS
+
+ move a0, ra /* arg1: self return address */
+ jalr t2 /* (1) call *ftrace_trace_function */
+ move a1, AT /* arg2: parent's return address */
+
+ MCOUNT_RESTORE_REGS
+
+fgraph_trace:
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ PTR_LA t1, ftrace_stub
PTR_L t3, ftrace_graph_return
bne t1, t3, ftrace_graph_caller
nop
bne t1, t3, ftrace_graph_caller
nop
#endif
- b ftrace_stub
-#ifdef CONFIG_32BIT
- addiu sp, sp, 8
-#else
- nop
-#endif
-static_trace:
- MCOUNT_SAVE_REGS
-
- move a0, ra /* arg1: self return address */
- jalr t2 /* (1) call *ftrace_trace_function */
- move a1, AT /* arg2: parent's return address */
-
- MCOUNT_RESTORE_REGS
#ifdef CONFIG_32BIT
addiu sp, sp, 8
#endif
+
.globl ftrace_stub
ftrace_stub:
RETURN_BACK
PTR sys_pkey_alloc
PTR sys_pkey_free /* 4365 */
PTR sys_statx
+ PTR sys_rseq
+ PTR sys_io_pgetevents
PTR sys_pkey_alloc
PTR sys_pkey_free /* 5325 */
PTR sys_statx
+ PTR sys_rseq
+ PTR sys_io_pgetevents
.size sys_call_table,.-sys_call_table
PTR sys_pkey_alloc
PTR sys_pkey_free
PTR sys_statx /* 6330 */
+ PTR sys_rseq
+ PTR compat_sys_io_pgetevents
.size sysn32_call_table,.-sysn32_call_table
PTR sys_pkey_alloc
PTR sys_pkey_free /* 4365 */
PTR sys_statx
+ PTR sys_rseq
+ PTR compat_sys_io_pgetevents
.size sys32_call_table,.-sys32_call_table
regs->regs[0] = 0; /* Don't deal with this again. */
}
+ rseq_signal_deliver(ksig, regs);
+
if (sig_uses_siginfo(&ksig->ka, abi))
ret = abi->setup_rt_frame(vdso + abi->vdso->off_rt_sigreturn,
ksig, regs, oldset);
if (thread_info_flags & _TIF_NOTIFY_RESUME) {
clear_thread_flag(TIF_NOTIFY_RESUME);
tracehook_notify_resume(regs);
+ rseq_handle_notify_resume(NULL, regs);
}
user_enter();
__free_page(pte);
}
+#define __pte_free_tlb(tlb, pte, addr) \
+do { \
+ pgtable_page_dtor(pte); \
+ tlb_remove_page((tlb), (pte)); \
+} while (0)
-#define __pte_free_tlb(tlb, pte, addr) tlb_remove_page((tlb), (pte))
#define pmd_pgtable(pmd) pmd_page(pmd)
#define check_pgt_cache() do { } while (0)
l.addi r3,r1,0 // pt_regs
/* r4 set be EXCEPTION_HANDLE */ // effective address of fault
- /*
- * __PHX__: TODO
- *
- * all this can be written much simpler. look at
- * DTLB miss handler in the CONFIG_GUARD_PROTECTED_CORE part
- */
#ifdef CONFIG_OPENRISC_NO_SPR_SR_DSX
l.lwz r6,PT_PC(r3) // address of an offending insn
l.lwz r6,0(r6) // instruction that caused pf
#else
- l.lwz r6,PT_SR(r3) // SR
+ l.mfspr r6,r0,SPR_SR // SR
l.andi r6,r6,SPR_SR_DSX // check for delay slot exception
l.sfne r6,r0 // exception happened in delay slot
l.bnf 7f
* r4 - EEAR exception EA
* r10 - current pointing to current_thread_info struct
* r12 - syscall 0, since we didn't come from syscall
- * r13 - temp it actually contains new SR, not needed anymore
- * r31 - handler address of the handler we'll jump to
+ * r30 - handler address of the handler we'll jump to
*
* handler has to save remaining registers to the exception
* ksp frame *before* tainting them!
/* r1 is KSP, r30 is __pa(KSP) */ ;\
tophys (r30,r1) ;\
l.sw PT_GPR12(r30),r12 ;\
+ /* r4 use for tmp before EA */ ;\
l.mfspr r12,r0,SPR_EPCR_BASE ;\
l.sw PT_PC(r30),r12 ;\
l.mfspr r12,r0,SPR_ESR_BASE ;\
/* r12 == 1 if we come from syscall */ ;\
CLEAR_GPR(r12) ;\
/* ----- turn on MMU ----- */ ;\
- l.ori r30,r0,(EXCEPTION_SR) ;\
+ /* Carry DSX into exception SR */ ;\
+ l.mfspr r30,r0,SPR_SR ;\
+ l.andi r30,r30,SPR_SR_DSX ;\
+ l.ori r30,r30,(EXCEPTION_SR) ;\
l.mtspr r0,r30,SPR_ESR_BASE ;\
/* r30: EA address of handler */ ;\
LOAD_SYMBOL_2_GPR(r30,handler) ;\
return 0;
}
#else
- return regs->sr & SPR_SR_DSX;
+ return mfspr(SPR_SR) & SPR_SR_DSX;
#endif
}
config PARISC_PAGE_SIZE_16KB
bool "16KB"
- depends on PA8X00
+ depends on PA8X00 && BROKEN
config PARISC_PAGE_SIZE_64KB
bool "64KB"
- depends on PA8X00
+ depends on PA8X00 && BROKEN
endchoice
int "Maximum number of CPUs (2-32)"
range 2 32
depends on SMP
- default "32"
+ default "4"
endmenu
# kernel.
cflags-y += -mdisable-fpregs
-# Without this, "ld -r" results in .text sections that are too big
-# (> 0x40000) for branches to reach stubs.
-cflags-y += -ffunction-sections
-
# Use long jumps instead of long branches (needed if your linker fails to
# link a too big vmlinux executable). Not enabled for building modules.
ifdef CONFIG_MLONGCALLS
unsigned long sig[_NSIG_WORDS];
} sigset_t;
-#ifndef __KERNEL__
-struct sigaction {
- __sighandler_t sa_handler;
- unsigned long sa_flags;
- sigset_t sa_mask; /* mask last for extensibility */
-};
-#endif
-
#include <asm/sigcontext.h>
#endif /* !__ASSEMBLY */
#define SO_ZEROCOPY 0x4035
+#define SO_TXTIME 0x4036
+#define SCM_TXTIME SO_TXTIME
+
#endif /* _UAPI_ASM_SOCKET_H */
#define __NR_preadv2 (__NR_Linux + 347)
#define __NR_pwritev2 (__NR_Linux + 348)
#define __NR_statx (__NR_Linux + 349)
+#define __NR_io_pgetevents (__NR_Linux + 350)
-#define __NR_Linux_syscalls (__NR_statx + 1)
+#define __NR_Linux_syscalls (__NR_io_pgetevents + 1)
#define __IGNORE_select /* newselect */
{
/* FIXME: we need this because apparently the sti
* driver can be registered twice */
- if(driver->drv.name) {
- printk(KERN_WARNING
- "BUG: skipping previously registered driver %s\n",
- driver->name);
+ if (driver->drv.name) {
+ pr_warn("BUG: skipping previously registered driver %s\n",
+ driver->name);
return 1;
}
if (!driver->probe) {
- printk(KERN_WARNING
- "BUG: driver %s has no probe routine\n",
- driver->name);
+ pr_warn("BUG: driver %s has no probe routine\n", driver->name);
return 1;
}
dev = create_parisc_device(mod_path);
if (dev->id.hw_type != HPHW_FAULTY) {
- printk(KERN_ERR "Two devices have hardware path [%s]. "
- "IODC data for second device: "
- "%02x%02x%02x%02x%02x%02x\n"
- "Rearranging GSC cards sometimes helps\n",
- parisc_pathname(dev), iodc_data[0], iodc_data[1],
- iodc_data[3], iodc_data[4], iodc_data[5], iodc_data[6]);
+ pr_err("Two devices have hardware path [%s]. IODC data for second device: %7phN\n"
+ "Rearranging GSC cards sometimes helps\n",
+ parisc_pathname(dev), iodc_data);
return NULL;
}
* the keyboard controller
*/
if ((hpa & 0xfff) == 0 && insert_resource(&iomem_resource, &dev->hpa))
- printk("Unable to claim HPA %lx for device %s\n",
- hpa, name);
+ pr_warn("Unable to claim HPA %lx for device %s\n", hpa, name);
return dev;
}
static int count;
print_pa_hwpath(dev, hw_path);
- printk(KERN_INFO "%d. %s at 0x%px [%s] { %d, 0x%x, 0x%.3x, 0x%.5x }",
+ pr_info("%d. %s at 0x%px [%s] { %d, 0x%x, 0x%.3x, 0x%.5x }",
++count, dev->name, (void*) dev->hpa.start, hw_path, dev->id.hw_type,
dev->id.hversion_rev, dev->id.hversion, dev->id.sversion);
ENTRY_COMP(preadv2)
ENTRY_COMP(pwritev2)
ENTRY_SAME(statx)
+ ENTRY_COMP(io_pgetevents) /* 350 */
.ifne (. - 90b) - (__NR_Linux_syscalls * (91b - 90b))
/* #define DEBUG 1 */
#ifdef DEBUG
-#define dbg(x...) printk(x)
+#define dbg(x...) pr_debug(x)
#else
#define dbg(x...)
#endif
start = (long)&__start___unwind[0];
stop = (long)&__stop___unwind[0];
- printk("unwind_init: start = 0x%lx, end = 0x%lx, entries = %lu\n",
+ dbg("unwind_init: start = 0x%lx, end = 0x%lx, entries = %lu\n",
start, stop,
(stop - start) / sizeof(struct unwind_table_entry));
cpu-as-$(CONFIG_ALTIVEC) += $(call as-option,-Wa$(comma)-maltivec)
cpu-as-$(CONFIG_E200) += -Wa,-me200
cpu-as-$(CONFIG_PPC_BOOK3S_64) += -Wa,-mpower4
+cpu-as-$(CONFIG_PPC_E500MC) += $(call as-option,-Wa$(comma)-me500mc)
KBUILD_AFLAGS += $(cpu-as-y)
KBUILD_CFLAGS += $(cpu-as-y)
#size-cells = <1>;
cell-index = <0>;
compatible = "fsl,fman";
- ranges = <0 0x400000 0x100000>;
- reg = <0x400000 0x100000>;
+ ranges = <0 0x400000 0xfe000>;
+ reg = <0x400000 0xfe000>;
interrupts = <96 2 0 0>, <16 2 1 1>;
clocks = <&clockgen 3 0>;
clock-names = "fmanclk";
fsl,qman-channel-range = <0x40 0xc>;
+ ptimer-handle = <&ptp_timer0>;
muram@0 {
compatible = "fsl,fman-muram";
reg = <0x87000 0x1000>;
status = "disabled";
};
+};
- ptp_timer0: ptp-timer@fe000 {
- compatible = "fsl,fman-ptp-timer";
- reg = <0xfe000 0x1000>;
- };
+ptp_timer0: ptp-timer@4fe000 {
+ compatible = "fsl,fman-ptp-timer";
+ reg = <0x4fe000 0x1000>;
+ interrupts = <96 2 0 0>;
};
#size-cells = <1>;
cell-index = <1>;
compatible = "fsl,fman";
- ranges = <0 0x500000 0x100000>;
- reg = <0x500000 0x100000>;
+ ranges = <0 0x500000 0xfe000>;
+ reg = <0x500000 0xfe000>;
interrupts = <97 2 0 0>, <16 2 1 0>;
clocks = <&clockgen 3 1>;
clock-names = "fmanclk";
fsl,qman-channel-range = <0x60 0xc>;
+ ptimer-handle = <&ptp_timer1>;
muram@0 {
compatible = "fsl,fman-muram";
reg = <0x87000 0x1000>;
status = "disabled";
};
+};
- ptp_timer1: ptp-timer@fe000 {
- compatible = "fsl,fman-ptp-timer";
- reg = <0xfe000 0x1000>;
- };
+ptp_timer1: ptp-timer@5fe000 {
+ compatible = "fsl,fman-ptp-timer";
+ reg = <0x5fe000 0x1000>;
+ interrupts = <97 2 0 0>;
};
#size-cells = <1>;
cell-index = <0>;
compatible = "fsl,fman";
- ranges = <0 0x400000 0x100000>;
- reg = <0x400000 0x100000>;
+ ranges = <0 0x400000 0xfe000>;
+ reg = <0x400000 0xfe000>;
interrupts = <96 2 0 0>, <16 2 1 1>;
clocks = <&clockgen 3 0>;
clock-names = "fmanclk";
fsl,qman-channel-range = <0x800 0x10>;
+ ptimer-handle = <&ptp_timer0>;
muram@0 {
compatible = "fsl,fman-muram";
compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
reg = <0xfd000 0x1000>;
};
+};
- ptp_timer0: ptp-timer@fe000 {
- compatible = "fsl,fman-ptp-timer";
- reg = <0xfe000 0x1000>;
- };
+ptp_timer0: ptp-timer@4fe000 {
+ compatible = "fsl,fman-ptp-timer";
+ reg = <0x4fe000 0x1000>;
+ interrupts = <96 2 0 0>;
};
#size-cells = <1>;
cell-index = <1>;
compatible = "fsl,fman";
- ranges = <0 0x500000 0x100000>;
- reg = <0x500000 0x100000>;
+ ranges = <0 0x500000 0xfe000>;
+ reg = <0x500000 0xfe000>;
interrupts = <97 2 0 0>, <16 2 1 0>;
clocks = <&clockgen 3 1>;
clock-names = "fmanclk";
fsl,qman-channel-range = <0x820 0x10>;
+ ptimer-handle = <&ptp_timer1>;
muram@0 {
compatible = "fsl,fman-muram";
compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
reg = <0xfd000 0x1000>;
};
+};
- ptp_timer1: ptp-timer@fe000 {
- compatible = "fsl,fman-ptp-timer";
- reg = <0xfe000 0x1000>;
- };
+ptp_timer1: ptp-timer@5fe000 {
+ compatible = "fsl,fman-ptp-timer";
+ reg = <0x5fe000 0x1000>;
+ interrupts = <97 2 0 0>;
};
#size-cells = <1>;
cell-index = <0>;
compatible = "fsl,fman";
- ranges = <0 0x400000 0x100000>;
- reg = <0x400000 0x100000>;
+ ranges = <0 0x400000 0xfe000>;
+ reg = <0x400000 0xfe000>;
interrupts = <96 2 0 0>, <16 2 1 1>;
clocks = <&clockgen 3 0>;
clock-names = "fmanclk";
fsl,qman-channel-range = <0x800 0x10>;
+ ptimer-handle = <&ptp_timer0>;
muram@0 {
compatible = "fsl,fman-muram";
compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
reg = <0xfd000 0x1000>;
};
+};
- ptp_timer0: ptp-timer@fe000 {
- compatible = "fsl,fman-ptp-timer";
- reg = <0xfe000 0x1000>;
- };
+ptp_timer0: ptp-timer@4fe000 {
+ compatible = "fsl,fman-ptp-timer";
+ reg = <0x4fe000 0x1000>;
+ interrupts = <96 2 0 0>;
};
}
#define check_pgt_cache() do { } while (0)
+#define get_hugepd_cache_index(x) (x)
#ifdef CONFIG_SMP
static inline void pgtable_free_tlb(struct mmu_gather *tlb,
static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
unsigned long address)
{
- pgtable_page_dtor(table);
pgtable_free_tlb(tlb, page_address(table), 0);
}
#endif /* _ASM_POWERPC_BOOK3S_32_PGALLOC_H */
}
#define is_hugepd(hpd) (hugepd_ok(hpd))
+/*
+ * 16M and 16G huge page directory tables are allocated from slab cache
+ *
+ */
+#define H_16M_CACHE_INDEX (PAGE_SHIFT + H_PTE_INDEX_SIZE + H_PMD_INDEX_SIZE - 24)
+#define H_16G_CACHE_INDEX \
+ (PAGE_SHIFT + H_PTE_INDEX_SIZE + H_PMD_INDEX_SIZE + H_PUD_INDEX_SIZE - 34)
+
+static inline int get_hugepd_cache_index(int index)
+{
+ switch (index) {
+ case H_16M_CACHE_INDEX:
+ return HTLB_16M_INDEX;
+ case H_16G_CACHE_INDEX:
+ return HTLB_16G_INDEX;
+ default:
+ BUG();
+ }
+ /* should not reach */
+}
+
#else /* !CONFIG_HUGETLB_PAGE */
static inline int pmd_huge(pmd_t pmd) { return 0; }
static inline int pud_huge(pud_t pud) { return 0; }
{
return 0;
}
+
#define is_hugepd(pdep) 0
+/*
+ * This should never get called
+ */
+static inline int get_hugepd_cache_index(int index)
+{
+ BUG();
+}
+
#else /* !CONFIG_HUGETLB_PAGE */
static inline int pmd_huge(pmd_t pmd) { return 0; }
static inline int pud_huge(pud_t pud) { return 0; }
PMD_INDEX,
PUD_INDEX,
PGD_INDEX,
+ /*
+ * Below are used with 4k page size and hugetlb
+ */
+ HTLB_16M_INDEX,
+ HTLB_16G_INDEX,
};
extern unsigned long __vmalloc_start;
static inline void arch_touch_nmi_watchdog(void) {}
#endif
-#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_STACKTRACE)
+#if defined(CONFIG_NMI_IPI) && defined(CONFIG_STACKTRACE)
extern void arch_trigger_cpumask_backtrace(const cpumask_t *mask,
bool exclude_self);
#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace
}
#define check_pgt_cache() do { } while (0)
+#define get_hugepd_cache_index(x) (x)
#ifdef CONFIG_SMP
static inline void pgtable_free_tlb(struct mmu_gather *tlb,
unsigned long address)
{
tlb_flush_pgtable(tlb, address);
- pgtable_page_dtor(table);
pgtable_free_tlb(tlb, page_address(table), 0);
}
#endif /* _ASM_POWERPC_PGALLOC_32_H */
}
}
+#define get_hugepd_cache_index(x) (x)
#ifdef CONFIG_SMP
static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift)
{
SYSCALL(pkey_free)
SYSCALL(pkey_mprotect)
SYSCALL(rseq)
+COMPAT_SYS(io_pgetevents)
#include <uapi/asm/unistd.h>
-#define NR_syscalls 388
+#define NR_syscalls 389
#define __NR__exit __NR_exit
#define __NR_pkey_free 385
#define __NR_pkey_mprotect 386
#define __NR_rseq 387
+#define __NR_io_pgetevents 388
#endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */
cur_cpu_spec->cpu_features |= CPU_FTR_P9_TM_HV_ASSIST;
cur_cpu_spec->cpu_features |= CPU_FTR_P9_TM_XER_SO_BUG;
cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1;
- } else /* DD2.1 and up have DD2_1 */
+ } else if ((version & 0xffff0000) == 0x004e0000)
+ /* DD2.1 and up have DD2_1 */
cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1;
if ((version & 0xffff0000) == 0x004e0000) {
* Note that the returned IO or memory base is a physical address
*/
-#pragma GCC diagnostic push
-#pragma GCC diagnostic ignored "-Wpragmas"
-#pragma GCC diagnostic ignored "-Wattribute-alias"
SYSCALL_DEFINE3(pciconfig_iobase, long, which,
unsigned long, bus, unsigned long, devfn)
{
return result;
}
-#pragma GCC diagnostic pop
#define IOBASE_ISA_IO 3
#define IOBASE_ISA_MEM 4
-#pragma GCC diagnostic push
-#pragma GCC diagnostic ignored "-Wpragmas"
-#pragma GCC diagnostic ignored "-Wattribute-alias"
SYSCALL_DEFINE3(pciconfig_iobase, long, which, unsigned long, in_bus,
unsigned long, in_devfn)
{
return -EOPNOTSUPP;
}
-#pragma GCC diagnostic pop
#ifdef CONFIG_NUMA
int pcibus_to_node(struct pci_bus *bus)
}
/* We assume to be passed big endian arguments */
-#pragma GCC diagnostic push
-#pragma GCC diagnostic ignored "-Wpragmas"
-#pragma GCC diagnostic ignored "-Wattribute-alias"
SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs)
{
struct rtas_args args;
return 0;
}
-#pragma GCC diagnostic pop
/*
* Call early during boot, before mem init, to retrieve the RTAS
static int ppc_panic_event(struct notifier_block *this,
unsigned long event, void *ptr)
{
+ /*
+ * panic does a local_irq_disable, but we really
+ * want interrupts to be hard disabled.
+ */
+ hard_irq_disable();
+
/*
* If firmware-assisted dump has been registered then trigger
* firmware-assisted dump and let firmware handle everything else.
*/
crash_fadump(NULL, ptr);
- ppc_md.panic(ptr); /* May not return */
+ if (ppc_md.panic)
+ ppc_md.panic(ptr); /* May not return */
return NOTIFY_DONE;
}
void __init setup_panic(void)
{
- if (!ppc_md.panic)
+ /* PPC64 always does a hard irq disable in its panic handler */
+ if (!IS_ENABLED(CONFIG_PPC64) && !ppc_md.panic)
return;
atomic_notifier_chain_register(&panic_notifier_list, &ppc_panic_block);
}
#endif /* CONFIG_SMP */
+void panic_smp_self_stop(void)
+{
+ hard_irq_disable();
+ spin_begin();
+ while (1)
+ spin_cpu_relax();
+}
+
#if defined(CONFIG_SMP) || defined(CONFIG_KEXEC_CORE)
static bool use_spinloop(void)
{
/* Re-enable the breakpoints for the signal stack */
thread_change_pc(tsk, tsk->thread.regs);
- rseq_signal_deliver(tsk->thread.regs);
+ rseq_signal_deliver(&ksig, tsk->thread.regs);
if (is32) {
if (ksig.ka.sa.sa_flags & SA_SIGINFO)
if (thread_info_flags & _TIF_NOTIFY_RESUME) {
clear_thread_flag(TIF_NOTIFY_RESUME);
tracehook_notify_resume(regs);
- rseq_handle_notify_resume(regs);
+ rseq_handle_notify_resume(NULL, regs);
}
user_enter();
}
#endif
-#pragma GCC diagnostic push
-#pragma GCC diagnostic ignored "-Wpragmas"
-#pragma GCC diagnostic ignored "-Wattribute-alias"
#ifdef CONFIG_PPC64
COMPAT_SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx,
struct ucontext __user *, new_ctx, int, ctx_size)
set_thread_flag(TIF_RESTOREALL);
return 0;
}
-#pragma GCC diagnostic pop
#ifdef CONFIG_PPC64
COMPAT_SYSCALL_DEFINE0(rt_sigreturn)
return 0;
}
-#pragma GCC diagnostic push
-#pragma GCC diagnostic ignored "-Wpragmas"
-#pragma GCC diagnostic ignored "-Wattribute-alias"
#ifdef CONFIG_PPC32
SYSCALL_DEFINE3(debug_setcontext, struct ucontext __user *, ctx,
int, ndbg, struct sig_dbg_op __user *, dbg)
return 0;
}
#endif
-#pragma GCC diagnostic pop
/*
* OK, we're invoking a handler
/*
* Handle {get,set,swap}_context operations
*/
-#pragma GCC diagnostic push
-#pragma GCC diagnostic ignored "-Wpragmas"
-#pragma GCC diagnostic ignored "-Wattribute-alias"
SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx,
struct ucontext __user *, new_ctx, long, ctx_size)
{
set_thread_flag(TIF_RESTOREALL);
return 0;
}
-#pragma GCC diagnostic pop
/*
nmi_ipi_busy_count--;
nmi_ipi_unlock();
- /* Remove this CPU */
- set_cpu_online(smp_processor_id(), false);
-
spin_begin();
while (1)
spin_cpu_relax();
static void stop_this_cpu(void *dummy)
{
- /* Remove this CPU */
- set_cpu_online(smp_processor_id(), false);
-
hard_irq_disable();
spin_begin();
while (1)
EXPORT_SYMBOL_GPL(save_stack_trace_tsk_reliable);
#endif /* CONFIG_HAVE_RELIABLE_STACKTRACE */
-#ifdef CONFIG_PPC_BOOK3S_64
+#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_NMI_IPI)
static void handle_backtrace_ipi(struct pt_regs *regs)
{
nmi_cpu_backtrace(regs);
{
nmi_trigger_cpumask_backtrace(mask, exclude_self, raise_backtrace_ipi);
}
-#endif /* CONFIG_PPC64 */
+#endif /* defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_NMI_IPI) */
return ret;
}
-#pragma GCC diagnostic push
-#pragma GCC diagnostic ignored "-Wpragmas"
-#pragma GCC diagnostic ignored "-Wattribute-alias"
SYSCALL_DEFINE6(mmap2, unsigned long, addr, size_t, len,
unsigned long, prot, unsigned long, flags,
unsigned long, fd, unsigned long, pgoff)
{
return do_mmap2(addr, len, prot, flags, fd, offset, PAGE_SHIFT);
}
-#pragma GCC diagnostic pop
#ifdef CONFIG_PPC32
/*
if (shift >= pdshift)
hugepd_free(tlb, hugepte);
else
- pgtable_free_tlb(tlb, hugepte, pdshift - shift);
+ pgtable_free_tlb(tlb, hugepte,
+ get_hugepd_cache_index(pdshift - shift));
}
static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
case PUD_INDEX:
kmem_cache_free(PGT_CACHE(PUD_CACHE_INDEX), table);
break;
+#if defined(CONFIG_PPC_4K_PAGES) && defined(CONFIG_HUGETLB_PAGE)
+ /* 16M hugepd directory at pud level */
+ case HTLB_16M_INDEX:
+ BUILD_BUG_ON(H_16M_CACHE_INDEX <= 0);
+ kmem_cache_free(PGT_CACHE(H_16M_CACHE_INDEX), table);
+ break;
+ /* 16G hugepd directory at the pgd level */
+ case HTLB_16G_INDEX:
+ BUILD_BUG_ON(H_16G_CACHE_INDEX <= 0);
+ kmem_cache_free(PGT_CACHE(H_16G_CACHE_INDEX), table);
+ break;
+#endif
/* We don't free pgd table via RCU callback */
default:
BUG();
* in a 2-bit field won't allow writes to a page that is otherwise
* write-protected.
*/
-#pragma GCC diagnostic push
-#pragma GCC diagnostic ignored "-Wpragmas"
-#pragma GCC diagnostic ignored "-Wattribute-alias"
SYSCALL_DEFINE3(subpage_prot, unsigned long, addr,
unsigned long, len, u32 __user *, map)
{
up_write(&mm->mmap_sem);
return err;
}
-#pragma GCC diagnostic pop
static unsigned long tlb_single_page_flush_ceiling __read_mostly = 33;
static unsigned long tlb_local_single_page_flush_ceiling __read_mostly = POWER9_TLB_SETS_RADIX * 2;
-void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
- unsigned long end)
+static inline void __radix__flush_tlb_range(struct mm_struct *mm,
+ unsigned long start, unsigned long end,
+ bool flush_all_sizes)
{
- struct mm_struct *mm = vma->vm_mm;
unsigned long pid;
unsigned int page_shift = mmu_psize_defs[mmu_virtual_psize].shift;
unsigned long page_size = 1UL << page_shift;
unsigned long nr_pages = (end - start) >> page_shift;
bool local, full;
-#ifdef CONFIG_HUGETLB_PAGE
- if (is_vm_hugetlb_page(vma))
- return radix__flush_hugetlb_tlb_range(vma, start, end);
-#endif
-
pid = mm->context.id;
if (unlikely(pid == MMU_NO_CONTEXT))
return;
_tlbie_pid(pid, RIC_FLUSH_TLB);
}
} else {
- bool hflush = false;
+ bool hflush = flush_all_sizes;
+ bool gflush = flush_all_sizes;
unsigned long hstart, hend;
+ unsigned long gstart, gend;
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
- hstart = (start + HPAGE_PMD_SIZE - 1) >> HPAGE_PMD_SHIFT;
- hend = end >> HPAGE_PMD_SHIFT;
- if (hstart < hend) {
- hstart <<= HPAGE_PMD_SHIFT;
- hend <<= HPAGE_PMD_SHIFT;
+ if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
hflush = true;
+
+ if (hflush) {
+ hstart = (start + PMD_SIZE - 1) & PMD_MASK;
+ hend = end & PMD_MASK;
+ if (hstart == hend)
+ hflush = false;
+ }
+
+ if (gflush) {
+ gstart = (start + PUD_SIZE - 1) & PUD_MASK;
+ gend = end & PUD_MASK;
+ if (gstart == gend)
+ gflush = false;
}
-#endif
asm volatile("ptesync": : :"memory");
if (local) {
__tlbiel_va_range(start, end, pid, page_size, mmu_virtual_psize);
if (hflush)
__tlbiel_va_range(hstart, hend, pid,
- HPAGE_PMD_SIZE, MMU_PAGE_2M);
+ PMD_SIZE, MMU_PAGE_2M);
+ if (gflush)
+ __tlbiel_va_range(gstart, gend, pid,
+ PUD_SIZE, MMU_PAGE_1G);
asm volatile("ptesync": : :"memory");
} else {
__tlbie_va_range(start, end, pid, page_size, mmu_virtual_psize);
if (hflush)
__tlbie_va_range(hstart, hend, pid,
- HPAGE_PMD_SIZE, MMU_PAGE_2M);
+ PMD_SIZE, MMU_PAGE_2M);
+ if (gflush)
+ __tlbie_va_range(gstart, gend, pid,
+ PUD_SIZE, MMU_PAGE_1G);
fixup_tlbie();
asm volatile("eieio; tlbsync; ptesync": : :"memory");
}
}
preempt_enable();
}
+
+void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
+ unsigned long end)
+
+{
+#ifdef CONFIG_HUGETLB_PAGE
+ if (is_vm_hugetlb_page(vma))
+ return radix__flush_hugetlb_tlb_range(vma, start, end);
+#endif
+
+ __radix__flush_tlb_range(vma->vm_mm, start, end, false);
+}
EXPORT_SYMBOL(radix__flush_tlb_range);
static int radix_get_mmu_psize(int page_size)
int psize = 0;
struct mm_struct *mm = tlb->mm;
int page_size = tlb->page_size;
+ unsigned long start = tlb->start;
+ unsigned long end = tlb->end;
/*
* if page size is not something we understand, do a full mm flush
*/
if (tlb->fullmm) {
__flush_all_mm(mm, true);
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLB_PAGE)
+ } else if (mm_tlb_flush_nested(mm)) {
+ /*
+ * If there is a concurrent invalidation that is clearing ptes,
+ * then it's possible this invalidation will miss one of those
+ * cleared ptes and miss flushing the TLB. If this invalidate
+ * returns before the other one flushes TLBs, that can result
+ * in it returning while there are still valid TLBs inside the
+ * range to be invalidated.
+ *
+ * See mm/memory.c:tlb_finish_mmu() for more details.
+ *
+ * The solution to this is ensure the entire range is always
+ * flushed here. The problem for powerpc is that the flushes
+ * are page size specific, so this "forced flush" would not
+ * do the right thing if there are a mix of page sizes in
+ * the range to be invalidated. So use __flush_tlb_range
+ * which invalidates all possible page sizes in the range.
+ *
+ * PWC flush probably is not be required because the core code
+ * shouldn't free page tables in this path, but accounting
+ * for the possibility makes us a bit more robust.
+ *
+ * need_flush_all is an uncommon case because page table
+ * teardown should be done with exclusive locks held (but
+ * after locks are dropped another invalidate could come
+ * in), it could be optimized further if necessary.
+ */
+ if (!tlb->need_flush_all)
+ __radix__flush_tlb_range(mm, start, end, true);
+ else
+ radix__flush_all_mm(mm);
+#endif
} else if ( (psize = radix_get_mmu_psize(page_size)) == -1) {
if (!tlb->need_flush_all)
radix__flush_tlb_mm(mm);
else
radix__flush_all_mm(mm);
} else {
- unsigned long start = tlb->start;
- unsigned long end = tlb->end;
-
if (!tlb->need_flush_all)
radix__flush_tlb_range_psize(mm, start, end, psize);
else
for (; sib <= cpu_last_thread_sibling(cpu) && !flush; sib++) {
if (sib == cpu)
continue;
+ if (!cpu_possible(sib))
+ continue;
if (paca_ptrs[sib]->kvm_hstate.kvm_vcpu)
flush = true;
}
#define DBG(x...)
#endif
-/* Apparently the RTC stores seconds since 1 Jan 1904 */
+/*
+ * Offset between Unix time (1970-based) and Mac time (1904-based). Cuda and PMU
+ * times wrap in 2040. If we need to handle later times, the read_time functions
+ * need to be changed to interpret wrapped times as post-2040.
+ */
#define RTC_OFFSET 2082844800
/*
if (req.reply_len != 7)
printk(KERN_ERR "cuda_get_time: got %d byte reply\n",
req.reply_len);
- now = (req.reply[3] << 24) + (req.reply[4] << 16)
- + (req.reply[5] << 8) + req.reply[6];
+ now = (u32)((req.reply[3] << 24) + (req.reply[4] << 16) +
+ (req.reply[5] << 8) + req.reply[6]);
+ /* it's either after year 2040, or the RTC has gone backwards */
+ WARN_ON(now < RTC_OFFSET);
+
return now - RTC_OFFSET;
}
static int cuda_set_rtc_time(struct rtc_time *tm)
{
- time64_t nowtime;
+ u32 nowtime;
struct adb_request req;
- nowtime = rtc_tm_to_time64(tm) + RTC_OFFSET;
+ nowtime = lower_32_bits(rtc_tm_to_time64(tm) + RTC_OFFSET);
if (cuda_request(&req, NULL, 6, CUDA_PACKET, CUDA_SET_TIME,
nowtime >> 24, nowtime >> 16, nowtime >> 8,
nowtime) < 0)
if (req.reply_len != 4)
printk(KERN_ERR "pmu_get_time: got %d byte reply from PMU\n",
req.reply_len);
- now = (req.reply[0] << 24) + (req.reply[1] << 16)
- + (req.reply[2] << 8) + req.reply[3];
+ now = (u32)((req.reply[0] << 24) + (req.reply[1] << 16) +
+ (req.reply[2] << 8) + req.reply[3]);
+
+ /* it's either after year 2040, or the RTC has gone backwards */
+ WARN_ON(now < RTC_OFFSET);
+
return now - RTC_OFFSET;
}
static int pmu_set_rtc_time(struct rtc_time *tm)
{
- time64_t nowtime;
+ u32 nowtime;
struct adb_request req;
- nowtime = rtc_tm_to_time64(tm) + RTC_OFFSET;
+ nowtime = lower_32_bits(rtc_tm_to_time64(tm) + RTC_OFFSET);
if (pmu_request(&req, NULL, 5, PMU_SET_RTC, nowtime >> 24,
nowtime >> 16, nowtime >> 8, nowtime) < 0)
return -ENXIO;
struct css_general_char {
u64 : 12;
- u32 dynio : 1; /* bit 12 */
- u32 : 4;
- u32 eadm : 1; /* bit 17 */
- u32 : 23;
- u32 aif : 1; /* bit 41 */
- u32 : 3;
- u32 mcss : 1; /* bit 45 */
- u32 fcs : 1; /* bit 46 */
- u32 : 1;
- u32 ext_mb : 1; /* bit 48 */
- u32 : 7;
- u32 aif_tdd : 1; /* bit 56 */
- u32 : 1;
- u32 qebsm : 1; /* bit 58 */
- u32 : 2;
- u32 aiv : 1; /* bit 61 */
- u32 : 5;
- u32 aif_osa : 1; /* bit 67 */
- u32 : 12;
- u32 eadm_rf : 1; /* bit 80 */
- u32 : 1;
- u32 cib : 1; /* bit 82 */
- u32 : 5;
- u32 fcx : 1; /* bit 88 */
- u32 : 19;
- u32 alt_ssi : 1; /* bit 108 */
- u32 : 1;
- u32 narf : 1; /* bit 110 */
- u32 : 12;
- u32 util_str : 1;/* bit 123 */
+ u64 dynio : 1; /* bit 12 */
+ u64 : 4;
+ u64 eadm : 1; /* bit 17 */
+ u64 : 23;
+ u64 aif : 1; /* bit 41 */
+ u64 : 3;
+ u64 mcss : 1; /* bit 45 */
+ u64 fcs : 1; /* bit 46 */
+ u64 : 1;
+ u64 ext_mb : 1; /* bit 48 */
+ u64 : 7;
+ u64 aif_tdd : 1; /* bit 56 */
+ u64 : 1;
+ u64 qebsm : 1; /* bit 58 */
+ u64 : 2;
+ u64 aiv : 1; /* bit 61 */
+ u64 : 2;
+
+ u64 : 3;
+ u64 aif_osa : 1; /* bit 67 */
+ u64 : 12;
+ u64 eadm_rf : 1; /* bit 80 */
+ u64 : 1;
+ u64 cib : 1; /* bit 82 */
+ u64 : 5;
+ u64 fcx : 1; /* bit 88 */
+ u64 : 19;
+ u64 alt_ssi : 1; /* bit 108 */
+ u64 : 1;
+ u64 narf : 1; /* bit 110 */
+ u64 : 12;
+ u64 util_str : 1;/* bit 123 */
} __packed;
extern struct css_general_char css_general_characteristics;
#define SO_ZEROCOPY 60
+#define SO_TXTIME 61
+#define SCM_TXTIME SO_TXTIME
+
#endif /* _ASM_SOCKET_H */
goto free_addrs;
}
if (bpf_jit_prog(&jit, fp)) {
+ bpf_jit_binary_free(header);
fp = orig_fp;
goto free_addrs;
}
#define SO_ZEROCOPY 0x003e
+#define SO_TXTIME 0x003f
+#define SCM_TXTIME SO_TXTIME
+
/* Security levels - as per NRL IPv6 - don't actually do anything */
#define SO_SECURITY_AUTHENTICATION 0x5001
#define SO_SECURITY_ENCRYPTION_TRANSPORT 0x5002
archheaders:
$(Q)$(MAKE) $(build)=arch/x86/entry/syscalls all
-archprepare:
-ifeq ($(CONFIG_KEXEC_FILE),y)
- $(Q)$(MAKE) $(build)=arch/x86/purgatory arch/x86/purgatory/kexec-purgatory.c
-endif
-
###
# Kernel objects
$(Q)rm -rf $(objtree)/arch/x86_64
$(Q)$(MAKE) $(clean)=$(boot)
$(Q)$(MAKE) $(clean)=arch/x86/tools
- $(Q)$(MAKE) $(clean)=arch/x86/purgatory
define archhelp
echo '* bzImage - Compressed kernel image (arch/x86/boot/bzImage)'
void *romimage;
status = efi_call_proto(efi_pci_io_protocol, attributes, pci,
- EfiPciIoAttributeOperationGet, 0, 0,
+ EfiPciIoAttributeOperationGet, 0ULL,
&attributes);
if (status != EFI_SUCCESS)
return status;
if (cached_flags & _TIF_NOTIFY_RESUME) {
clear_thread_flag(TIF_NOTIFY_RESUME);
tracehook_notify_resume(regs);
- rseq_handle_notify_resume(regs);
+ rseq_handle_notify_resume(NULL, regs);
}
if (cached_flags & _TIF_USER_RETURN_NOTIFY)
* whereas POPF does not.)
*/
addl $PT_EFLAGS-PT_DS, %esp /* point esp at pt_regs->flags */
- btr $X86_EFLAGS_IF_BIT, (%esp)
+ btrl $X86_EFLAGS_IF_BIT, (%esp)
popfl
/*
pushq %rdx /* pt_regs->dx */
pushq %rcx /* pt_regs->cx */
pushq $-ENOSYS /* pt_regs->ax */
- pushq %r8 /* pt_regs->r8 */
+ pushq $0 /* pt_regs->r8 = 0 */
xorl %r8d, %r8d /* nospec r8 */
- pushq %r9 /* pt_regs->r9 */
+ pushq $0 /* pt_regs->r9 = 0 */
xorl %r9d, %r9d /* nospec r9 */
- pushq %r10 /* pt_regs->r10 */
+ pushq $0 /* pt_regs->r10 = 0 */
xorl %r10d, %r10d /* nospec r10 */
- pushq %r11 /* pt_regs->r11 */
+ pushq $0 /* pt_regs->r11 = 0 */
xorl %r11d, %r11d /* nospec r11 */
pushq %rbx /* pt_regs->rbx */
xorl %ebx, %ebx /* nospec rbx */
pushq %rcx /* pt_regs->cx */
xorl %ecx, %ecx /* nospec cx */
pushq $-ENOSYS /* pt_regs->ax */
- pushq $0 /* pt_regs->r8 = 0 */
+ pushq %r8 /* pt_regs->r8 */
xorl %r8d, %r8d /* nospec r8 */
- pushq $0 /* pt_regs->r9 = 0 */
+ pushq %r9 /* pt_regs->r9 */
xorl %r9d, %r9d /* nospec r9 */
- pushq $0 /* pt_regs->r10 = 0 */
+ pushq %r10 /* pt_regs->r10*/
xorl %r10d, %r10d /* nospec r10 */
- pushq $0 /* pt_regs->r11 = 0 */
+ pushq %r11 /* pt_regs->r11 */
xorl %r11d, %r11d /* nospec r11 */
pushq %rbx /* pt_regs->rbx */
xorl %ebx, %ebx /* nospec rbx */
{
unsigned long mask;
- asm ("cmp %1,%2; sbb %0,%0;"
+ asm volatile ("cmp %1,%2; sbb %0,%0;"
:"=r" (mask)
:"g"(size),"r" (index)
:"cc");
static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d)
{
+ if (!pgtable_l5_enabled())
+ return;
+
BUG_ON((unsigned long)p4d & (PAGE_SIZE-1));
free_page((unsigned long)p4d);
}
#define pgd_page(pgd) pfn_to_page(pgd_pfn(pgd))
/* to find an entry in a page-table-directory. */
-static __always_inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
+static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
{
if (!pgtable_l5_enabled())
return (p4d_t *)pgd;
}
#endif
-static __always_inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d)
+static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d)
{
pgd_t pgd;
*p4dp = native_make_p4d(native_pgd_val(pgd));
}
-static __always_inline void native_p4d_clear(p4d_t *p4d)
+static inline void native_p4d_clear(p4d_t *p4d)
{
native_set_p4d(p4d, native_make_p4d(0));
}
#define VMX_MISC_PREEMPTION_TIMER_RATE_MASK 0x0000001f
#define VMX_MISC_SAVE_EFER_LMA 0x00000020
#define VMX_MISC_ACTIVITY_HLT 0x00000040
+#define VMX_MISC_ZERO_LEN_INS 0x40000000
/* VMFUNC functions */
#define VMX_VMFUNC_EPTP_SWITCHING 0x00000001
#define VECTORING_INFO_VALID_MASK INTR_INFO_VALID_MASK
#define INTR_TYPE_EXT_INTR (0 << 8) /* external interrupt */
+#define INTR_TYPE_RESERVED (1 << 8) /* reserved */
#define INTR_TYPE_NMI_INTR (2 << 8) /* NMI */
#define INTR_TYPE_HARD_EXCEPTION (3 << 8) /* processor exception */
#define INTR_TYPE_SOFT_INTR (4 << 8) /* software interrupt */
#define INTR_TYPE_PRIV_SW_EXCEPTION (5 << 8) /* ICE breakpoint - undocumented */
#define INTR_TYPE_SOFT_EXCEPTION (6 << 8) /* software exception */
+#define INTR_TYPE_OTHER_EVENT (7 << 8) /* other event */
/* GUEST_INTERRUPTIBILITY_INFO flags. */
#define GUEST_INTR_STATE_STI 0x00000001
#include <linux/delay.h>
#include <linux/crash_dump.h>
#include <linux/reboot.h>
+#include <linux/memory.h>
#include <asm/uv/uv_mmrs.h>
#include <asm/uv/uv_hub.h>
}
EXPORT_SYMBOL(uv_hub_info_version);
+/* Default UV memory block size is 2GB */
+static unsigned long mem_block_size = (2UL << 30);
+
+/* Kernel parameter to specify UV mem block size */
+static int parse_mem_block_size(char *ptr)
+{
+ unsigned long size = memparse(ptr, NULL);
+
+ /* Size will be rounded down by set_block_size() below */
+ mem_block_size = size;
+ return 0;
+}
+early_param("uv_memblksize", parse_mem_block_size);
+
+static __init int adj_blksize(u32 lgre)
+{
+ unsigned long base = (unsigned long)lgre << UV_GAM_RANGE_SHFT;
+ unsigned long size;
+
+ for (size = mem_block_size; size > MIN_MEMORY_BLOCK_SIZE; size >>= 1)
+ if (IS_ALIGNED(base, size))
+ break;
+
+ if (size >= mem_block_size)
+ return 0;
+
+ mem_block_size = size;
+ return 1;
+}
+
+static __init void set_block_size(void)
+{
+ unsigned int order = ffs(mem_block_size);
+
+ if (order) {
+ /* adjust for ffs return of 1..64 */
+ set_memory_block_size_order(order - 1);
+ pr_info("UV: mem_block_size set to 0x%lx\n", mem_block_size);
+ } else {
+ /* bad or zero value, default to 1UL << 31 (2GB) */
+ pr_err("UV: mem_block_size error with 0x%lx\n", mem_block_size);
+ set_memory_block_size_order(31);
+ }
+}
+
/* Build GAM range lookup table: */
static __init void build_uv_gr_table(void)
{
<< UV_GAM_RANGE_SHFT);
int order = 0;
char suffix[] = " KMGTPE";
+ int flag = ' ';
while (size > 9999 && order < sizeof(suffix)) {
size /= 1024;
order++;
}
+ /* adjust max block size to current range start */
+ if (gre->type == 1 || gre->type == 2)
+ if (adj_blksize(lgre))
+ flag = '*';
+
if (!index) {
pr_info("UV: GAM Range Table...\n");
- pr_info("UV: # %20s %14s %5s %4s %5s %3s %2s\n", "Range", "", "Size", "Type", "NASID", "SID", "PN");
+ pr_info("UV: # %20s %14s %6s %4s %5s %3s %2s\n", "Range", "", "Size", "Type", "NASID", "SID", "PN");
}
- pr_info("UV: %2d: 0x%014lx-0x%014lx %5lu%c %3d %04x %02x %02x\n",
+ pr_info("UV: %2d: 0x%014lx-0x%014lx%c %5lu%c %3d %04x %02x %02x\n",
index++,
(unsigned long)lgre << UV_GAM_RANGE_SHFT,
(unsigned long)gre->limit << UV_GAM_RANGE_SHFT,
- size, suffix[order],
+ flag, size, suffix[order],
gre->type, gre->nasid, gre->sockid, gre->pnode);
+ /* update to next range start */
lgre = gre->limit;
if (sock_min > gre->sockid)
sock_min = gre->sockid;
build_socket_tables();
build_uv_gr_table();
+ set_block_size();
uv_init_hub_info(&hub_info);
uv_possible_blades = num_possible_nodes();
if (!_node_to_pnode)
#include <asm/pgtable.h>
#include <asm/set_memory.h>
#include <asm/intel-family.h>
+#include <asm/hypervisor.h>
static void __init spectre_v2_select_mitigation(void);
static void __init ssb_select_mitigation(void);
if (boot_cpu_has(X86_FEATURE_PTI))
return sprintf(buf, "Mitigation: PTI\n");
+ if (hypervisor_is_type(X86_HYPER_XEN_PV))
+ return sprintf(buf, "Unknown (XEN PV detected, hypervisor mitigation required)\n");
+
break;
case X86_BUG_SPECTRE_V1:
num_sharing_cache = ((eax >> 14) & 0xfff) + 1;
if (num_sharing_cache) {
- int bits = get_count_order(num_sharing_cache) - 1;
+ int bits = get_count_order(num_sharing_cache);
per_cpu(cpu_llc_id, cpu) = c->apicid >> bits;
}
+/* cpu_feature_enabled() cannot be used this early */
+#define USE_EARLY_PGTABLE_L5
+
#include <linux/bootmem.h>
#include <linux/linkage.h>
#include <linux/bitops.h>
SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_INSTR),
USER
),
+ MCESEV(
+ PANIC, "Data load in unrecoverable area of kernel",
+ SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA),
+ KERNEL
+ ),
#endif
MCESEV(
PANIC, "Action required: unknown MCACOD",
static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp,
struct pt_regs *regs)
{
- int i, ret = 0;
char *tmp;
+ int i;
for (i = 0; i < mca_cfg.banks; i++) {
m->status = mce_rdmsrl(msr_ops.status(i));
- if (m->status & MCI_STATUS_VAL) {
- __set_bit(i, validp);
- if (quirk_no_way_out)
- quirk_no_way_out(i, m, regs);
- }
+ if (!(m->status & MCI_STATUS_VAL))
+ continue;
+
+ __set_bit(i, validp);
+ if (quirk_no_way_out)
+ quirk_no_way_out(i, m, regs);
if (mce_severity(m, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) {
+ mce_read_aux(m, i);
*msg = tmp;
- ret = 1;
+ return 1;
}
}
- return ret;
+ return 0;
}
/*
lmce = m.mcgstatus & MCG_STATUS_LMCES;
/*
+ * Local machine check may already know that we have to panic.
+ * Broadcast machine check begins rendezvous in mce_start()
* Go through all banks in exclusion of the other CPUs. This way we
* don't report duplicated events on shared banks because the first one
- * to see it will clear it. If this is a Local MCE, then no need to
- * perform rendezvous.
+ * to see it will clear it.
*/
- if (!lmce)
+ if (lmce) {
+ if (no_way_out)
+ mce_panic("Fatal local machine check", &m, msg);
+ } else {
order = mce_start(&no_way_out);
+ }
for (i = 0; i < cfg->banks; i++) {
__clear_bit(i, toclear);
no_way_out = worst >= MCE_PANIC_SEVERITY;
} else {
/*
- * Local MCE skipped calling mce_reign()
- * If we found a fatal error, we need to panic here.
+ * If there was a fatal machine check we should have
+ * already called mce_panic earlier in this function.
+ * Since we re-read the banks, we might have found
+ * something new. Check again to see if we found a
+ * fatal error. We call "mce_severity()" again to
+ * make sure we have the right "msg".
*/
- if (worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3)
- mce_panic("Machine check from unknown source",
- NULL, NULL);
+ if (worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3) {
+ mce_severity(&m, cfg->tolerant, &msg, true);
+ mce_panic("Local fatal machine check!", &m, msg);
+ }
}
/*
p = memdup_patch(data, size);
if (!p)
pr_err("Error allocating buffer %p\n", data);
- else
+ else {
list_replace(&iter->plist, &p->plist);
+ kfree(iter->data);
+ kfree(iter);
+ }
}
}
{
int i;
u64 end;
+ u64 addr = 0;
/*
* The bootstrap memblock region count maximum is 128 entries
struct e820_entry *entry = &e820_table->entries[i];
end = entry->addr + entry->size;
+ if (addr < entry->addr)
+ memblock_reserve(addr, entry->addr - addr);
+ addr = end;
if (end != (resource_size_t)end)
continue;
+ /*
+ * all !E820_TYPE_RAM ranges (including gap ranges) are put
+ * into memblock.reserved to make sure that struct pages in
+ * such regions are not left uninitialized after bootup.
+ */
if (entry->type != E820_TYPE_RAM && entry->type != E820_TYPE_RESERVED_KERN)
- continue;
-
- memblock_add(entry->addr, entry->size);
+ memblock_reserve(entry->addr, entry->size);
+ else
+ memblock_add(entry->addr, entry->size);
}
/* Throw away partial pages: */
pmdval_t early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX);
#ifdef CONFIG_X86_5LEVEL
-unsigned int __pgtable_l5_enabled __initdata;
+unsigned int __pgtable_l5_enabled __ro_after_init;
unsigned int pgdir_shift __ro_after_init = 39;
EXPORT_SYMBOL(pgdir_shift);
unsigned int ptrs_per_p4d __ro_after_init = 1;
/* Skylake */
static void quirk_intel_purley_xeon_ras_cap(struct pci_dev *pdev)
{
- u32 capid0;
+ u32 capid0, capid5;
pci_read_config_dword(pdev, 0x84, &capid0);
+ pci_read_config_dword(pdev, 0x98, &capid5);
- if ((capid0 & 0xc0) == 0xc0)
+ /*
+ * CAPID0{7:6} indicate whether this is an advanced RAS SKU
+ * CAPID5{8:5} indicate that various NVDIMM usage modes are
+ * enabled, so memory machine check recovery is also enabled.
+ */
+ if ((capid0 & 0xc0) == 0xc0 || (capid5 & 0x1e0))
static_branch_inc(&mcsafe_key);
+
}
DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x0ec3, quirk_intel_brickland_xeon_ras_cap);
DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2fc0, quirk_intel_brickland_xeon_ras_cap);
* Increment event counter and perform fixup for the pre-signal
* frame.
*/
- rseq_signal_deliver(regs);
+ rseq_signal_deliver(ksig, regs);
/* Set up the stack frame */
if (is_ia32_frame(ksig)) {
char *str = (trapnr == X86_TRAP_MF) ? "fpu exception" :
"simd exception";
- if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, SIGFPE) == NOTIFY_STOP)
- return;
cond_local_irq_enable(regs);
if (!user_mode(regs)) {
- if (!fixup_exception(regs, trapnr)) {
- task->thread.error_code = error_code;
- task->thread.trap_nr = trapnr;
+ if (fixup_exception(regs, trapnr))
+ return;
+
+ task->thread.error_code = error_code;
+ task->thread.trap_nr = trapnr;
+
+ if (notify_die(DIE_TRAP, str, regs, error_code,
+ trapnr, SIGFPE) != NOTIFY_STOP)
die(str, regs, error_code);
- }
return;
}
insn_init(insn, auprobe->insn, sizeof(auprobe->insn), x86_64);
/* has the side-effect of processing the entire instruction */
insn_get_length(insn);
- if (WARN_ON_ONCE(!insn_complete(insn)))
+ if (!insn_complete(insn))
return -ENOEXEC;
if (is_prefix_bad(insn))
MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS;
}
+static inline bool nested_cpu_has_zero_length_injection(struct kvm_vcpu *vcpu)
+{
+ return to_vmx(vcpu)->nested.msrs.misc_low & VMX_MISC_ZERO_LEN_INS;
+}
+
+static inline bool nested_cpu_supports_monitor_trap_flag(struct kvm_vcpu *vcpu)
+{
+ return to_vmx(vcpu)->nested.msrs.procbased_ctls_high &
+ CPU_BASED_MONITOR_TRAP_FLAG;
+}
+
static inline bool nested_cpu_has(struct vmcs12 *vmcs12, u32 bit)
{
return vmcs12->cpu_based_vm_exec_control & bit;
!nested_cr3_valid(vcpu, vmcs12->host_cr3))
return VMXERR_ENTRY_INVALID_HOST_STATE_FIELD;
+ /*
+ * From the Intel SDM, volume 3:
+ * Fields relevant to VM-entry event injection must be set properly.
+ * These fields are the VM-entry interruption-information field, the
+ * VM-entry exception error code, and the VM-entry instruction length.
+ */
+ if (vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK) {
+ u32 intr_info = vmcs12->vm_entry_intr_info_field;
+ u8 vector = intr_info & INTR_INFO_VECTOR_MASK;
+ u32 intr_type = intr_info & INTR_INFO_INTR_TYPE_MASK;
+ bool has_error_code = intr_info & INTR_INFO_DELIVER_CODE_MASK;
+ bool should_have_error_code;
+ bool urg = nested_cpu_has2(vmcs12,
+ SECONDARY_EXEC_UNRESTRICTED_GUEST);
+ bool prot_mode = !urg || vmcs12->guest_cr0 & X86_CR0_PE;
+
+ /* VM-entry interruption-info field: interruption type */
+ if (intr_type == INTR_TYPE_RESERVED ||
+ (intr_type == INTR_TYPE_OTHER_EVENT &&
+ !nested_cpu_supports_monitor_trap_flag(vcpu)))
+ return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+
+ /* VM-entry interruption-info field: vector */
+ if ((intr_type == INTR_TYPE_NMI_INTR && vector != NMI_VECTOR) ||
+ (intr_type == INTR_TYPE_HARD_EXCEPTION && vector > 31) ||
+ (intr_type == INTR_TYPE_OTHER_EVENT && vector != 0))
+ return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+
+ /* VM-entry interruption-info field: deliver error code */
+ should_have_error_code =
+ intr_type == INTR_TYPE_HARD_EXCEPTION && prot_mode &&
+ x86_exception_has_error_code(vector);
+ if (has_error_code != should_have_error_code)
+ return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+
+ /* VM-entry exception error code */
+ if (has_error_code &&
+ vmcs12->vm_entry_exception_error_code & GENMASK(31, 15))
+ return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+
+ /* VM-entry interruption-info field: reserved bits */
+ if (intr_info & INTR_INFO_RESVD_BITS_MASK)
+ return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+
+ /* VM-entry instruction length */
+ switch (intr_type) {
+ case INTR_TYPE_SOFT_EXCEPTION:
+ case INTR_TYPE_SOFT_INTR:
+ case INTR_TYPE_PRIV_SW_EXCEPTION:
+ if ((vmcs12->vm_entry_instruction_len > 15) ||
+ (vmcs12->vm_entry_instruction_len == 0 &&
+ !nested_cpu_has_zero_length_injection(vcpu)))
+ return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+ }
+ }
+
return 0;
}
#endif
}
+static inline bool x86_exception_has_error_code(unsigned int vector)
+{
+ static u32 exception_has_error_code = BIT(DF_VECTOR) | BIT(TS_VECTOR) |
+ BIT(NP_VECTOR) | BIT(SS_VECTOR) | BIT(GP_VECTOR) |
+ BIT(PF_VECTOR) | BIT(AC_VECTOR);
+
+ return (1U << vector) & exception_has_error_code;
+}
+
static inline bool mmu_is_nested(struct kvm_vcpu *vcpu)
{
return vcpu->arch.walk_mmu == &vcpu->arch.nested_mmu;
return 0;
}
-static const char nx_warning[] = KERN_CRIT
-"kernel tried to execute NX-protected page - exploit attempt? (uid: %d)\n";
-static const char smep_warning[] = KERN_CRIT
-"unable to execute userspace code (SMEP?) (uid: %d)\n";
-
static void
show_fault_oops(struct pt_regs *regs, unsigned long error_code,
unsigned long address)
pte = lookup_address_in_pgd(pgd, address, &level);
if (pte && pte_present(*pte) && !pte_exec(*pte))
- printk(nx_warning, from_kuid(&init_user_ns, current_uid()));
+ pr_crit("kernel tried to execute NX-protected page - exploit attempt? (uid: %d)\n",
+ from_kuid(&init_user_ns, current_uid()));
if (pte && pte_present(*pte) && pte_exec(*pte) &&
(pgd_flags(*pgd) & _PAGE_USER) &&
(__read_cr4() & X86_CR4_SMEP))
- printk(smep_warning, from_kuid(&init_user_ns, current_uid()));
+ pr_crit("unable to execute userspace code (SMEP?) (uid: %d)\n",
+ from_kuid(&init_user_ns, current_uid()));
}
- printk(KERN_ALERT "BUG: unable to handle kernel ");
- if (address < PAGE_SIZE)
- printk(KERN_CONT "NULL pointer dereference");
- else
- printk(KERN_CONT "paging request");
-
- printk(KERN_CONT " at %px\n", (void *) address);
+ pr_alert("BUG: unable to handle kernel %s at %px\n",
+ address < PAGE_SIZE ? "NULL pointer dereference" : "paging request",
+ (void *)address);
dump_pagetable(address);
}
/* Amount of ram needed to start using large blocks */
#define MEM_SIZE_FOR_LARGE_BLOCK (64UL << 30)
+/* Adjustable memory block size */
+static unsigned long set_memory_block_size;
+int __init set_memory_block_size_order(unsigned int order)
+{
+ unsigned long size = 1UL << order;
+
+ if (size > MEM_SIZE_FOR_LARGE_BLOCK || size < MIN_MEMORY_BLOCK_SIZE)
+ return -EINVAL;
+
+ set_memory_block_size = size;
+ return 0;
+}
+
static unsigned long probe_memory_block_size(void)
{
unsigned long boot_mem_end = max_pfn << PAGE_SHIFT;
unsigned long bz;
- /* If this is UV system, always set 2G block size */
- if (is_uv_system()) {
- bz = MAX_BLOCK_SIZE;
+ /* If memory block size has been set, then use it */
+ bz = set_memory_block_size;
+ if (bz)
goto done;
- }
/* Use regular block if RAM is smaller than MEM_SIZE_FOR_LARGE_BLOCK */
if (boot_mem_end < MEM_SIZE_FOR_LARGE_BLOCK) {
pgd = pgd_offset_k(pgd_idx * PGDIR_SIZE);
set_pgd(pgd_offset_k(pgd_idx * PGDIR_SIZE), save_pgd[pgd_idx]);
- if (!(pgd_val(*pgd) & _PAGE_PRESENT))
+ if (!pgd_present(*pgd))
continue;
for (i = 0; i < PTRS_PER_P4D; i++) {
p4d = p4d_offset(pgd,
pgd_idx * PGDIR_SIZE + i * P4D_SIZE);
- if (!(p4d_val(*p4d) & _PAGE_PRESENT))
+ if (!p4d_present(*p4d))
continue;
pud = (pud_t *)p4d_page_vaddr(*p4d);
__read_mostly int xen_have_vector_callback;
EXPORT_SYMBOL_GPL(xen_have_vector_callback);
+/*
+ * NB: needs to live in .data because it's used by xen_prepare_pvh which runs
+ * before clearing the bss.
+ */
+uint32_t xen_start_flags __attribute__((section(".data"))) = 0;
+EXPORT_SYMBOL(xen_start_flags);
+
/*
* Point at some empty memory to start with. We map the real shared_info
* page as soon as fixmap is up and running.
return;
xen_domain_type = XEN_PV_DOMAIN;
+ xen_start_flags = xen_start_info->flags;
xen_setup_features();
}
xen_pvh = 1;
+ xen_start_flags = pvh_start_info.flags;
msr = cpuid_ebx(xen_cpuid_base() + 2);
pfn = __pa(hypercall_page);
#include <xen/interface/vcpu.h>
#include <xen/interface/xenpmu.h>
+#include <asm/spec-ctrl.h>
#include <asm/xen/interface.h>
#include <asm/xen/hypercall.h>
cpu_data(cpu).x86_max_cores = 1;
set_cpu_sibling_map(cpu);
+ speculative_store_bypass_ht_init();
+
xen_setup_cpu_clockevents();
notify_cpu_starting(cpu);
}
set_cpu_sibling_map(0);
+ speculative_store_bypass_ht_init();
+
xen_pmu_init(0);
if (xen_smp_intr_init(0) || xen_smp_intr_init_pv(0))
#define SO_ZEROCOPY 60
+#define SO_TXTIME 61
+#define SCM_TXTIME SO_TXTIME
+
#endif /* _XTENSA_SOCKET_H */
if (!bio_integrity_endio(bio))
return;
- if (WARN_ONCE(bio->bi_next, "driver left bi_next not NULL"))
- bio->bi_next = NULL;
-
/*
* Need to have a real endio function for chained bios, otherwise
* various corner cases will break (like stacking block devices that
bio_advance(bio, nbytes);
/* don't actually finish bio if it's part of flush sequence */
- /*
- * XXX this code looks suspicious - it's not consistent with advancing
- * req->bio in caller
- */
if (bio->bi_iter.bi_size == 0 && !(rq->rq_flags & RQF_FLUSH_SEQ))
bio_endio(bio);
}
struct bio *bio = req->bio;
unsigned bio_bytes = min(bio->bi_iter.bi_size, nr_bytes);
- if (bio_bytes == bio->bi_iter.bi_size) {
+ if (bio_bytes == bio->bi_iter.bi_size)
req->bio = bio->bi_next;
- bio->bi_next = NULL;
- }
/* Completion has already been traced */
bio_clear_flag(bio, BIO_TRACE_COMPLETION);
dst->cpu = src->cpu;
dst->__sector = blk_rq_pos(src);
dst->__data_len = blk_rq_bytes(src);
+ if (src->rq_flags & RQF_SPECIAL_PAYLOAD) {
+ dst->rq_flags |= RQF_SPECIAL_PAYLOAD;
+ dst->special_vec = src->special_vec;
+ }
dst->nr_phys_segments = src->nr_phys_segments;
dst->ioprio = src->ioprio;
dst->extra_len = src->extra_len;
static const char *blk_mq_rq_state_name(enum mq_rq_state rq_state)
{
- if (WARN_ON_ONCE((unsigned int)rq_state >
+ if (WARN_ON_ONCE((unsigned int)rq_state >=
ARRAY_SIZE(blk_mq_rq_state_name_array)))
return "(?)";
return blk_mq_rq_state_name_array[rq_state];
WARN_ON_ONCE(ret != BLK_EH_RESET_TIMER);
}
- req->rq_flags &= ~RQF_TIMED_OUT;
blk_add_timer(req);
}
#define BLK_MQ_RESOURCE_DELAY 3 /* ms units */
+/*
+ * Returns true if we did some work AND can potentially do more.
+ */
bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
bool got_budget)
{
blk_mq_run_hw_queue(hctx, true);
else if (needs_restart && (ret == BLK_STS_RESOURCE))
blk_mq_delay_run_hw_queue(hctx, BLK_MQ_RESOURCE_DELAY);
+
+ return false;
}
+ /*
+ * If the host/device is unable to accept more work, inform the
+ * caller of that.
+ */
+ if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE)
+ return false;
+
return (queued + errors) != 0;
}
local_irq_restore(flags);
}
+EXPORT_SYMBOL(__blk_complete_request);
/**
* blk_complete_request - end I/O on a request
if (!req->timeout)
req->timeout = q->rq_timeout;
+ req->rq_flags &= ~RQF_TIMED_OUT;
blk_rq_set_deadline(req, jiffies + req->timeout);
/*
return 0;
}
- if (n > resp->num) {
+ if (n >= resp->num) {
pr_debug("Response has %d tokens. Can't access %d\n",
resp->num, n);
return 0;
return 0;
}
- if (n > resp->num) {
+ if (n >= resp->num) {
pr_debug("Response has %d tokens. Can't access %d\n",
resp->num, n);
return 0;
#include <linux/kernel.h>
-extern const char __initdata *const blacklist_hashes[];
+extern const char __initconst *const blacklist_hashes[];
}
EXPORT_SYMBOL_GPL(af_alg_async_cb);
-__poll_t af_alg_poll_mask(struct socket *sock, __poll_t events)
+/**
+ * af_alg_poll - poll system call handler
+ */
+__poll_t af_alg_poll(struct file *file, struct socket *sock,
+ poll_table *wait)
{
struct sock *sk = sock->sk;
struct alg_sock *ask = alg_sk(sk);
struct af_alg_ctx *ctx = ask->private;
- __poll_t mask = 0;
+ __poll_t mask;
+
+ sock_poll_wait(file, sk_sleep(sk), wait);
+ mask = 0;
if (!ctx->more || ctx->used)
mask |= EPOLLIN | EPOLLRDNORM;
return mask;
}
-EXPORT_SYMBOL_GPL(af_alg_poll_mask);
+EXPORT_SYMBOL_GPL(af_alg_poll);
/**
* af_alg_alloc_areq - allocate struct af_alg_async_req
.sendmsg = aead_sendmsg,
.sendpage = af_alg_sendpage,
.recvmsg = aead_recvmsg,
- .poll_mask = af_alg_poll_mask,
+ .poll = af_alg_poll,
};
static int aead_check_key(struct socket *sock)
.sendmsg = aead_sendmsg_nokey,
.sendpage = aead_sendpage_nokey,
.recvmsg = aead_recvmsg_nokey,
- .poll_mask = af_alg_poll_mask,
+ .poll = af_alg_poll,
};
static void *aead_bind(const char *name, u32 type, u32 mask)
.sendmsg = skcipher_sendmsg,
.sendpage = af_alg_sendpage,
.recvmsg = skcipher_recvmsg,
- .poll_mask = af_alg_poll_mask,
+ .poll = af_alg_poll,
};
static int skcipher_check_key(struct socket *sock)
.sendmsg = skcipher_sendmsg_nokey,
.sendpage = skcipher_sendpage_nokey,
.recvmsg = skcipher_recvmsg_nokey,
- .poll_mask = af_alg_poll_mask,
+ .poll = af_alg_poll,
};
static void *skcipher_bind(const char *name, u32 type, u32 mask)
return -EINVAL;
}
+ if (strcmp(ctx->cert->sig->pkey_algo, "rsa") == 0) {
+ /* Discard the BIT STRING metadata */
+ if (vlen < 1 || *(const u8 *)value != 0)
+ return -EBADMSG;
+
+ value++;
+ vlen--;
+ }
+
ctx->cert->raw_sig = value;
ctx->cert->raw_sig_size = vlen;
return 0;
union morus640_block_in tail;
memcpy(tail.bytes, src, size);
+ memset(tail.bytes + size, 0, MORUS640_BLOCK_SIZE - size);
- crypto_morus640_load_a(&m, src);
+ crypto_morus640_load_a(&m, tail.bytes);
crypto_morus640_core(state, &m);
crypto_morus640_store_a(tail.bytes, &m);
memset(tail.bytes + size, 0, MORUS640_BLOCK_SIZE - size);
st[24] ^= bc[ 4];
}
-static void __optimize("O3") keccakf(u64 st[25])
+static void keccakf(u64 st[25])
{
int round;
#include <linux/pm_domain.h>
#include <linux/pm_runtime.h>
#include <linux/pwm.h>
+#include <linux/suspend.h>
#include <linux/delay.h>
#include "internal.h"
mutex_unlock(&lpss_iosf_mutex);
}
-static int acpi_lpss_suspend(struct device *dev, bool wakeup)
+static int acpi_lpss_suspend(struct device *dev, bool runtime)
{
struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
+ bool wakeup = runtime || device_may_wakeup(dev);
int ret;
if (pdata->dev_desc->flags & LPSS_SAVE_CTX)
* wrong status for devices being about to be powered off. See
* lpss_iosf_enter_d3_state() for further information.
*/
- if (lpss_quirks & LPSS_QUIRK_ALWAYS_POWER_ON && iosf_mbi_available())
+ if ((runtime || !pm_suspend_via_firmware()) &&
+ lpss_quirks & LPSS_QUIRK_ALWAYS_POWER_ON && iosf_mbi_available())
lpss_iosf_enter_d3_state();
return ret;
}
-static int acpi_lpss_resume(struct device *dev)
+static int acpi_lpss_resume(struct device *dev, bool runtime)
{
struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
int ret;
* This call is kept first to be in symmetry with
* acpi_lpss_runtime_suspend() one.
*/
- if (lpss_quirks & LPSS_QUIRK_ALWAYS_POWER_ON && iosf_mbi_available())
+ if ((runtime || !pm_resume_via_firmware()) &&
+ lpss_quirks & LPSS_QUIRK_ALWAYS_POWER_ON && iosf_mbi_available())
lpss_iosf_exit_d3_state();
ret = acpi_dev_resume(dev);
return 0;
ret = pm_generic_suspend_late(dev);
- return ret ? ret : acpi_lpss_suspend(dev, device_may_wakeup(dev));
+ return ret ? ret : acpi_lpss_suspend(dev, false);
}
static int acpi_lpss_resume_early(struct device *dev)
{
- int ret = acpi_lpss_resume(dev);
+ int ret = acpi_lpss_resume(dev, false);
return ret ? ret : pm_generic_resume_early(dev);
}
static int acpi_lpss_runtime_resume(struct device *dev)
{
- int ret = acpi_lpss_resume(dev);
+ int ret = acpi_lpss_resume(dev, true);
return ret ? ret : pm_generic_runtime_resume(dev);
}
}
}
+static const struct dmi_system_id acpi_ec_no_wakeup[] = {
+ {
+ .ident = "Thinkpad X1 Carbon 6th",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "20KGS3JF01"),
+ },
+ },
+ { },
+};
+
int __init acpi_ec_init(void)
{
int result;
if (result)
return result;
+ /*
+ * Disable EC wakeup on following systems to prevent periodic
+ * wakeup from EC GPE.
+ */
+ if (dmi_check_system(acpi_ec_no_wakeup)) {
+ ec_no_wakeup = true;
+ pr_debug("Disabling EC wakeup on suspend-to-idle\n");
+ }
+
/* Drivers must be started after acpi_ec_query_init() */
dsdt_fail = acpi_bus_register_driver(&acpi_ec_driver);
/*
#include <linux/uaccess.h>
#include <linux/io-64-nonatomic-lo-hi.h>
+#include "acpica/accommon.h"
+#include "acpica/acnamesp.h"
#include "internal.h"
#define _COMPONENT ACPI_OS_SERVICES
}
EXPORT_SYMBOL(acpi_check_region);
+static acpi_status acpi_deactivate_mem_region(acpi_handle handle, u32 level,
+ void *_res, void **return_value)
+{
+ struct acpi_mem_space_context **mem_ctx;
+ union acpi_operand_object *handler_obj;
+ union acpi_operand_object *region_obj2;
+ union acpi_operand_object *region_obj;
+ struct resource *res = _res;
+ acpi_status status;
+
+ region_obj = acpi_ns_get_attached_object(handle);
+ if (!region_obj)
+ return AE_OK;
+
+ handler_obj = region_obj->region.handler;
+ if (!handler_obj)
+ return AE_OK;
+
+ if (region_obj->region.space_id != ACPI_ADR_SPACE_SYSTEM_MEMORY)
+ return AE_OK;
+
+ if (!(region_obj->region.flags & AOPOBJ_SETUP_COMPLETE))
+ return AE_OK;
+
+ region_obj2 = acpi_ns_get_secondary_object(region_obj);
+ if (!region_obj2)
+ return AE_OK;
+
+ mem_ctx = (void *)®ion_obj2->extra.region_context;
+
+ if (!(mem_ctx[0]->address >= res->start &&
+ mem_ctx[0]->address < res->end))
+ return AE_OK;
+
+ status = handler_obj->address_space.setup(region_obj,
+ ACPI_REGION_DEACTIVATE,
+ NULL, (void **)mem_ctx);
+ if (ACPI_SUCCESS(status))
+ region_obj->region.flags &= ~(AOPOBJ_SETUP_COMPLETE);
+
+ return status;
+}
+
+/**
+ * acpi_release_memory - Release any mappings done to a memory region
+ * @handle: Handle to namespace node
+ * @res: Memory resource
+ * @level: A level that terminates the search
+ *
+ * Walks through @handle and unmaps all SystemMemory Operation Regions that
+ * overlap with @res and that have already been activated (mapped).
+ *
+ * This is a helper that allows drivers to place special requirements on memory
+ * region that may overlap with operation regions, primarily allowing them to
+ * safely map the region as non-cached memory.
+ *
+ * The unmapped Operation Regions will be automatically remapped next time they
+ * are called, so the drivers do not need to do anything else.
+ */
+acpi_status acpi_release_memory(acpi_handle handle, struct resource *res,
+ u32 level)
+{
+ if (!(res->flags & IORESOURCE_MEM))
+ return AE_TYPE;
+
+ return acpi_walk_namespace(ACPI_TYPE_REGION, handle, level,
+ acpi_deactivate_mem_region, NULL, res, NULL);
+}
+EXPORT_SYMBOL_GPL(acpi_release_memory);
+
/*
* Let drivers know whether the resource checks are effective
*/
skb_queue_head_init(&iadev->rx_dma_q);
iadev->rx_free_desc_qhead = NULL;
- iadev->rx_open = kcalloc(4, iadev->num_vc, GFP_KERNEL);
+ iadev->rx_open = kcalloc(iadev->num_vc, sizeof(void *), GFP_KERNEL);
if (!iadev->rx_open) {
printk(KERN_ERR DEV_LABEL "itf %d couldn't get free page\n",
dev->number);
static int zatm_open(struct atm_vcc *vcc)
{
- struct zatm_dev *zatm_dev;
struct zatm_vcc *zatm_vcc;
short vpi = vcc->vpi;
int vci = vcc->vci;
int error;
DPRINTK(">zatm_open\n");
- zatm_dev = ZATM_DEV(vcc->dev);
if (!test_bit(ATM_VF_PARTIAL,&vcc->flags))
vcc->dev_data = NULL;
if (vci != ATM_VPI_UNSPEC && vpi != ATM_VCI_UNSPEC)
return -EFAULT;
if (pool < 0 || pool > ZATM_LAST_POOL)
return -EINVAL;
+ pool = array_index_nospec(pool,
+ ZATM_LAST_POOL + 1);
if (copy_from_user(&info,
&((struct zatm_pool_req __user *) arg)->info,
sizeof(info))) return -EFAULT;
topology.o container.o property.o cacheinfo.o \
devcon.o
obj-$(CONFIG_DEVTMPFS) += devtmpfs.o
-obj-$(CONFIG_DMA_CMA) += dma-contiguous.o
obj-y += power/
-obj-$(CONFIG_HAS_DMA) += dma-mapping.o
-obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o
obj-$(CONFIG_ISA_BUS_API) += isa.o
obj-y += firmware_loader/
obj-$(CONFIG_NUMA) += node.o
link->rpm_active = true;
}
pm_runtime_new_link(consumer);
+ /*
+ * If the link is being added by the consumer driver at probe
+ * time, balance the decrementation of the supplier's runtime PM
+ * usage counter after consumer probe in driver_probe_device().
+ */
+ if (consumer->links.status == DL_DEV_PROBING)
+ pm_runtime_get_noresume(supplier);
}
get_device(supplier);
link->supplier = supplier;
switch (consumer->links.status) {
case DL_DEV_PROBING:
/*
- * Balance the decrementation of the supplier's
- * runtime PM usage counter after consumer probe
- * in driver_probe_device().
+ * Some callers expect the link creation during
+ * consumer driver probe to resume the supplier
+ * even without DL_FLAG_RPM_ACTIVE.
*/
if (flags & DL_FLAG_PM_RUNTIME)
- pm_runtime_get_sync(supplier);
+ pm_runtime_resume(supplier);
link->status = DL_STATE_CONSUMER_PROBE;
break;
* power domain corresponding to a DT node's "required-opps" property.
*
* @dev: Device for which the performance-state needs to be found.
- * @opp_node: DT node where the "required-opps" property is present. This can be
+ * @np: DT node where the "required-opps" property is present. This can be
* the device node itself (if it doesn't have an OPP table) or a node
* within the OPP table of a device (if device has an OPP table).
- * @state: Pointer to return performance state.
*
* Returns performance state corresponding to the "required-opps" property of
* a DT node. This calls platform specific genpd->opp_to_performance_state()
* Returns performance state on success and 0 on failure.
*/
unsigned int of_genpd_opp_to_performance_state(struct device *dev,
- struct device_node *opp_node)
+ struct device_node *np)
{
struct generic_pm_domain *genpd;
struct dev_pm_opp *opp;
genpd_lock(genpd);
- opp = of_dev_pm_opp_find_required_opp(&genpd->dev, opp_node);
+ opp = of_dev_pm_opp_find_required_opp(&genpd->dev, np);
if (IS_ERR(opp)) {
dev_err(dev, "Failed to find required OPP: %ld\n",
PTR_ERR(opp));
_drbd_start_io_acct(device, req);
/* process discards always from our submitter thread */
- if ((bio_op(bio) & REQ_OP_WRITE_ZEROES) ||
- (bio_op(bio) & REQ_OP_DISCARD))
+ if (bio_op(bio) == REQ_OP_WRITE_ZEROES ||
+ bio_op(bio) == REQ_OP_DISCARD)
goto queue_for_submitter_thread;
if (rw == WRITE && req->private_bio && req->i.size
#define NBD_HAS_CONFIG_REF 4
#define NBD_BOUND 5
#define NBD_DESTROY_ON_DISCONNECT 6
+#define NBD_DISCONNECT_ON_CLOSE 7
struct nbd_config {
u32 flags;
static void nbd_connect_reply(struct genl_info *info, int index);
static int nbd_genl_status(struct sk_buff *skb, struct genl_info *info);
static void nbd_dead_link_work(struct work_struct *work);
+static void nbd_disconnect_and_put(struct nbd_device *nbd);
static inline struct device *nbd_to_dev(struct nbd_device *nbd)
{
static void nbd_release(struct gendisk *disk, fmode_t mode)
{
struct nbd_device *nbd = disk->private_data;
+ struct block_device *bdev = bdget_disk(disk, 0);
+
+ if (test_bit(NBD_DISCONNECT_ON_CLOSE, &nbd->config->runtime_flags) &&
+ bdev->bd_openers == 0)
+ nbd_disconnect_and_put(nbd);
+
nbd_config_put(nbd);
nbd_put(nbd);
}
&config->runtime_flags);
put_dev = true;
}
+ if (flags & NBD_CFLAG_DISCONNECT_ON_CLOSE) {
+ set_bit(NBD_DISCONNECT_ON_CLOSE,
+ &config->runtime_flags);
+ }
}
if (info->attrs[NBD_ATTR_SOCKETS]) {
return ret;
}
+static void nbd_disconnect_and_put(struct nbd_device *nbd)
+{
+ mutex_lock(&nbd->config_lock);
+ nbd_disconnect(nbd);
+ nbd_clear_sock(nbd);
+ mutex_unlock(&nbd->config_lock);
+ if (test_and_clear_bit(NBD_HAS_CONFIG_REF,
+ &nbd->config->runtime_flags))
+ nbd_config_put(nbd);
+}
+
static int nbd_genl_disconnect(struct sk_buff *skb, struct genl_info *info)
{
struct nbd_device *nbd;
nbd_put(nbd);
return 0;
}
- mutex_lock(&nbd->config_lock);
- nbd_disconnect(nbd);
- nbd_clear_sock(nbd);
- mutex_unlock(&nbd->config_lock);
- if (test_and_clear_bit(NBD_HAS_CONFIG_REF,
- &nbd->config->runtime_flags))
- nbd_config_put(nbd);
+ nbd_disconnect_and_put(nbd);
nbd_config_put(nbd);
nbd_put(nbd);
return 0;
struct nbd_device *nbd = NULL;
struct nbd_config *config;
int index;
- int ret = -EINVAL;
+ int ret = 0;
bool put_dev = false;
if (!netlink_capable(skb, CAP_SYS_ADMIN))
!nbd->task_recv) {
dev_err(nbd_to_dev(nbd),
"not configured, cannot reconfigure\n");
+ ret = -EINVAL;
goto out;
}
&config->runtime_flags))
refcount_inc(&nbd->refs);
}
+
+ if (flags & NBD_CFLAG_DISCONNECT_ON_CLOSE) {
+ set_bit(NBD_DISCONNECT_ON_CLOSE,
+ &config->runtime_flags);
+ } else {
+ clear_bit(NBD_DISCONNECT_ON_CLOSE,
+ &config->runtime_flags);
+ }
}
if (info->attrs[NBD_ATTR_SOCKETS]) {
static enum blk_eh_timer_return null_rq_timed_out_fn(struct request *rq)
{
pr_info("null: rq %p timed out\n", rq);
- blk_mq_complete_request(rq);
+ __blk_complete_request(rq);
return BLK_EH_DONE;
}
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/types.h>
-#include <linux/unaligned/le_struct.h>
+#include <asm/unaligned.h>
#include <net/bluetooth/bluetooth.h>
#include <net/bluetooth/hci_core.h>
void hwrng_unregister(struct hwrng *rng)
{
+ int err;
+
mutex_lock(&rng_mutex);
list_del(&rng->list);
- if (current_rng == rng)
- enable_best_rng();
+ if (current_rng == rng) {
+ err = enable_best_rng();
+ if (err) {
+ drop_current_rng();
+ cur_rng_set_by_user = 0;
+ }
+ }
if (list_empty(&rng_list)) {
mutex_unlock(&rng_mutex);
/*
* Static global variables
*/
-static DECLARE_WAIT_QUEUE_HEAD(random_wait);
+static DECLARE_WAIT_QUEUE_HEAD(random_read_wait);
+static DECLARE_WAIT_QUEUE_HEAD(random_write_wait);
static struct fasync_struct *fasync;
static DEFINE_SPINLOCK(random_ready_list_lock);
/* should we wake readers? */
if (entropy_bits >= random_read_wakeup_bits &&
- wq_has_sleeper(&random_wait)) {
- wake_up_interruptible_poll(&random_wait, POLLIN);
+ wq_has_sleeper(&random_read_wait)) {
+ wake_up_interruptible(&random_read_wait);
kill_fasync(&fasync, SIGIO, POLL_IN);
}
/* If the input pool is getting full, send some
trace_debit_entropy(r->name, 8 * ibytes);
if (ibytes &&
(r->entropy_count >> ENTROPY_SHIFT) < random_write_wakeup_bits) {
- wake_up_interruptible_poll(&random_wait, POLLOUT);
+ wake_up_interruptible(&random_write_wait);
kill_fasync(&fasync, SIGIO, POLL_OUT);
}
if (nonblock)
return -EAGAIN;
- wait_event_interruptible(random_wait,
+ wait_event_interruptible(random_read_wait,
ENTROPY_BITS(&input_pool) >=
random_read_wakeup_bits);
if (signal_pending(current))
return ret;
}
-static struct wait_queue_head *
-random_get_poll_head(struct file *file, __poll_t events)
-{
- return &random_wait;
-}
-
static __poll_t
-random_poll_mask(struct file *file, __poll_t events)
+random_poll(struct file *file, poll_table * wait)
{
- __poll_t mask = 0;
+ __poll_t mask;
+ poll_wait(file, &random_read_wait, wait);
+ poll_wait(file, &random_write_wait, wait);
+ mask = 0;
if (ENTROPY_BITS(&input_pool) >= random_read_wakeup_bits)
mask |= EPOLLIN | EPOLLRDNORM;
if (ENTROPY_BITS(&input_pool) < random_write_wakeup_bits)
const struct file_operations random_fops = {
.read = random_read,
.write = random_write,
- .get_poll_head = random_get_poll_head,
- .poll_mask = random_poll_mask,
+ .poll = random_poll,
.unlocked_ioctl = random_ioctl,
.fasync = random_fasync,
.llseek = noop_llseek,
* We'll be woken up again once below random_write_wakeup_thresh,
* or when the calling thread is about to terminate.
*/
- wait_event_interruptible(random_wait, kthread_should_stop() ||
+ wait_event_interruptible(random_write_wait, kthread_should_stop() ||
ENTROPY_BITS(&input_pool) <= random_write_wakeup_bits);
mix_pool_bytes(poolp, buffer, count);
credit_entropy_bits(poolp, entropy);
to->private_data = kzalloc(sizeof(struct stm32_timer_private),
GFP_KERNEL);
- if (!to->private_data)
+ if (!to->private_data) {
+ ret = -ENOMEM;
goto deinit;
+ }
rstc = of_reset_control_get(node, NULL);
if (!IS_ERR(rstc)) {
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
+#include <linux/compiler.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/list.h>
}
EXPORT_SYMBOL_GPL(cn_del_callback);
-static int cn_proc_show(struct seq_file *m, void *v)
+static int __maybe_unused cn_proc_show(struct seq_file *m, void *v)
{
struct cn_queue_dev *dev = cdev.cbdev;
struct cn_callback_entry *cbq;
static struct pstate_funcs pstate_funcs __read_mostly;
static int hwp_active __read_mostly;
+static int hwp_mode_bdw __read_mostly;
static bool per_cpu_limits __read_mostly;
static bool hwp_boost __read_mostly;
cpu->pstate.turbo_pstate = pstate_funcs.get_turbo();
cpu->pstate.scaling = pstate_funcs.get_scaling();
cpu->pstate.max_freq = cpu->pstate.max_pstate * cpu->pstate.scaling;
- cpu->pstate.turbo_freq = cpu->pstate.turbo_pstate * cpu->pstate.scaling;
+
+ if (hwp_active && !hwp_mode_bdw) {
+ unsigned int phy_max, current_max;
+
+ intel_pstate_get_hwp_max(cpu->cpu, &phy_max, ¤t_max);
+ cpu->pstate.turbo_freq = phy_max * cpu->pstate.scaling;
+ } else {
+ cpu->pstate.turbo_freq = cpu->pstate.turbo_pstate * cpu->pstate.scaling;
+ }
if (pstate_funcs.get_aperf_mperf_shift)
cpu->aperf_mperf_shift = pstate_funcs.get_aperf_mperf_shift();
static inline void intel_pstate_request_control_from_smm(void) {}
#endif /* CONFIG_ACPI */
+#define INTEL_PSTATE_HWP_BROADWELL 0x01
+
+#define ICPU_HWP(model, hwp_mode) \
+ { X86_VENDOR_INTEL, 6, model, X86_FEATURE_HWP, hwp_mode }
+
static const struct x86_cpu_id hwp_support_ids[] __initconst = {
- { X86_VENDOR_INTEL, 6, X86_MODEL_ANY, X86_FEATURE_HWP },
+ ICPU_HWP(INTEL_FAM6_BROADWELL_X, INTEL_PSTATE_HWP_BROADWELL),
+ ICPU_HWP(INTEL_FAM6_BROADWELL_XEON_D, INTEL_PSTATE_HWP_BROADWELL),
+ ICPU_HWP(X86_MODEL_ANY, 0),
{}
};
static int __init intel_pstate_init(void)
{
+ const struct x86_cpu_id *id;
int rc;
if (no_load)
return -ENODEV;
- if (x86_match_cpu(hwp_support_ids)) {
+ id = x86_match_cpu(hwp_support_ids);
+ if (id) {
copy_cpu_funcs(&core_funcs);
if (!no_hwp) {
hwp_active++;
+ hwp_mode_bdw = id->driver_data;
intel_pstate.attr = hwp_cpufreq_attrs;
goto hwp_cpu_matched;
}
} else {
- const struct x86_cpu_id *id;
-
id = x86_match_cpu(intel_pstate_cpu_ids);
if (!id)
return -ENODEV;
NUM_OF_MSM8996_VERSIONS,
};
+struct platform_device *cpufreq_dt_pdev, *kryo_cpufreq_pdev;
+
static enum _msm8996_version __init qcom_cpufreq_kryo_get_msm_id(void)
{
size_t len;
static int qcom_cpufreq_kryo_probe(struct platform_device *pdev)
{
struct opp_table *opp_tables[NR_CPUS] = {0};
- struct platform_device *cpufreq_dt_pdev;
enum _msm8996_version msm8996_version;
struct nvmem_cell *speedbin_nvmem;
struct device_node *np;
int ret;
cpu_dev = get_cpu_device(0);
- if (NULL == cpu_dev)
- ret = -ENODEV;
+ if (!cpu_dev)
+ return -ENODEV;
msm8996_version = qcom_cpufreq_kryo_get_msm_id();
if (NUM_OF_MSM8996_VERSIONS == msm8996_version) {
}
np = dev_pm_opp_of_get_opp_desc_node(cpu_dev);
- if (IS_ERR(np))
- return PTR_ERR(np);
+ if (!np)
+ return -ENOENT;
ret = of_device_is_compatible(np, "operating-points-v2-kryo-cpu");
if (!ret) {
speedbin = nvmem_cell_read(speedbin_nvmem, &len);
nvmem_cell_put(speedbin_nvmem);
+ if (IS_ERR(speedbin))
+ return PTR_ERR(speedbin);
switch (msm8996_version) {
case MSM8996_V3:
BUG();
break;
}
+ kfree(speedbin);
for_each_possible_cpu(cpu) {
cpu_dev = get_cpu_device(cpu);
return ret;
}
+static int qcom_cpufreq_kryo_remove(struct platform_device *pdev)
+{
+ platform_device_unregister(cpufreq_dt_pdev);
+ return 0;
+}
+
static struct platform_driver qcom_cpufreq_kryo_driver = {
.probe = qcom_cpufreq_kryo_probe,
+ .remove = qcom_cpufreq_kryo_remove,
.driver = {
.name = "qcom-cpufreq-kryo",
},
if (unlikely(ret < 0))
return ret;
- ret = PTR_ERR_OR_ZERO(platform_device_register_simple(
- "qcom-cpufreq-kryo", -1, NULL, 0));
+ kryo_cpufreq_pdev = platform_device_register_simple(
+ "qcom-cpufreq-kryo", -1, NULL, 0);
+ ret = PTR_ERR_OR_ZERO(kryo_cpufreq_pdev);
if (0 == ret)
return 0;
}
module_init(qcom_cpufreq_kryo_init);
+static void __init qcom_cpufreq_kryo_exit(void)
+{
+ platform_device_unregister(kryo_cpufreq_pdev);
+ platform_driver_unregister(&qcom_cpufreq_kryo_driver);
+}
+module_exit(qcom_cpufreq_kryo_exit);
+
MODULE_DESCRIPTION("Qualcomm Technologies, Inc. Kryo CPUfreq driver");
MODULE_LICENSE("GPL v2");
struct tcp_sock *tp = tcp_sk(sk);
tp->rcv_nxt++;
- tp->rx_opt.ts_recent_stamp = get_seconds();
+ tp->rx_opt.ts_recent_stamp = ktime_get_seconds();
tp->srtt_us = 0;
tcp_time_wait(sk, TCP_TIME_WAIT, 0);
}
tp->urg_data = 0;
if ((avail + offset) >= skb->len) {
- if (likely(skb))
- chtls_free_skb(sk, skb);
- buffers_freed++;
if (ULP_SKB_CB(skb)->flags & ULPCB_FLAG_TLS_HDR) {
tp->copied_seq += skb->len;
hws->rcvpld = skb->hdr_len;
} else {
tp->copied_seq += hws->rcvpld;
}
+ chtls_free_skb(sk, skb);
+ buffers_freed++;
hws->copied_seq = 0;
if (copied >= target &&
!skb_peek(&sk->sk_receive_queue))
{
struct dax_device *dax_dev;
bool dax_enabled = false;
+ struct request_queue *q;
pgoff_t pgoff;
int err, id;
void *kaddr;
return false;
}
+ q = bdev_get_queue(bdev);
+ if (!q || !blk_queue_dax(q)) {
+ pr_debug("%s: error: request queue doesn't support dax\n",
+ bdevname(bdev, buf));
+ return false;
+ }
+
err = bdev_dax_pgoff(bdev, 0, PAGE_SIZE, &pgoff);
if (err) {
pr_debug("%s: error: unaligned partition for dax\n",
DEFINE_DMI_ATTR_WITH_SHOW(product_version, 0444, DMI_PRODUCT_VERSION);
DEFINE_DMI_ATTR_WITH_SHOW(product_serial, 0400, DMI_PRODUCT_SERIAL);
DEFINE_DMI_ATTR_WITH_SHOW(product_uuid, 0400, DMI_PRODUCT_UUID);
+DEFINE_DMI_ATTR_WITH_SHOW(product_sku, 0444, DMI_PRODUCT_SKU);
DEFINE_DMI_ATTR_WITH_SHOW(product_family, 0444, DMI_PRODUCT_FAMILY);
DEFINE_DMI_ATTR_WITH_SHOW(board_vendor, 0444, DMI_BOARD_VENDOR);
DEFINE_DMI_ATTR_WITH_SHOW(board_name, 0444, DMI_BOARD_NAME);
ADD_DMI_ATTR(product_serial, DMI_PRODUCT_SERIAL);
ADD_DMI_ATTR(product_uuid, DMI_PRODUCT_UUID);
ADD_DMI_ATTR(product_family, DMI_PRODUCT_FAMILY);
+ ADD_DMI_ATTR(product_sku, DMI_PRODUCT_SKU);
ADD_DMI_ATTR(board_vendor, DMI_BOARD_VENDOR);
ADD_DMI_ATTR(board_name, DMI_BOARD_NAME);
ADD_DMI_ATTR(board_version, DMI_BOARD_VERSION);
dmi_save_ident(dm, DMI_PRODUCT_VERSION, 6);
dmi_save_ident(dm, DMI_PRODUCT_SERIAL, 7);
dmi_save_uuid(dm, DMI_PRODUCT_UUID, 8);
+ dmi_save_ident(dm, DMI_PRODUCT_SKU, 25);
dmi_save_ident(dm, DMI_PRODUCT_FAMILY, 26);
break;
case 2: /* Base Board Information */
efi_guid_t tcg2_guid = EFI_TCG2_PROTOCOL_GUID;
efi_guid_t linux_eventlog_guid = LINUX_EFI_TPM_EVENT_LOG_GUID;
efi_status_t status;
- efi_physical_addr_t log_location, log_last_entry;
+ efi_physical_addr_t log_location = 0, log_last_entry = 0;
struct linux_efi_tpm_eventlog *log_tbl = NULL;
unsigned long first_entry_addr, last_entry_addr;
size_t log_size, last_entry_size;
switch (asic_type) {
#if defined(CONFIG_DRM_AMD_DC)
case CHIP_BONAIRE:
- case CHIP_HAWAII:
case CHIP_KAVERI:
case CHIP_KABINI:
case CHIP_MULLINS:
+ /*
+ * We have systems in the wild with these ASICs that require
+ * LVDS and VGA support which is not supported with DC.
+ *
+ * Fallback to the non-DC driver here by default so as not to
+ * cause regressions.
+ */
+ return amdgpu_dc > 0;
+ case CHIP_HAWAII:
case CHIP_CARRIZO:
case CHIP_STONEY:
case CHIP_POLARIS10:
struct amdgpu_device *adev = ring->adev;
uint64_t index;
- if (ring != &adev->uvd.inst[ring->me].ring) {
+ if (ring->funcs->type != AMDGPU_RING_TYPE_UVD) {
ring->fence_drv.cpu_addr = &adev->wb.wb[ring->fence_offs];
ring->fence_drv.gpu_addr = adev->wb.gpu_addr + (ring->fence_offs * 4);
} else {
domain = amdgpu_mem_type_to_domain(bo->tbo.mem.mem_type);
if (domain == AMDGPU_GEM_DOMAIN_VRAM) {
adev->vram_pin_size += amdgpu_bo_size(bo);
- if (bo->flags & AMDGPU_GEM_CREATE_NO_CPU_ACCESS)
- adev->invisible_pin_size += amdgpu_bo_size(bo);
+ adev->invisible_pin_size += amdgpu_vram_mgr_bo_invisible_size(bo);
} else if (domain == AMDGPU_GEM_DOMAIN_GTT) {
adev->gart_pin_size += amdgpu_bo_size(bo);
}
bo->pin_count--;
if (bo->pin_count)
return 0;
- for (i = 0; i < bo->placement.num_placement; i++) {
- bo->placements[i].lpfn = 0;
- bo->placements[i].flags &= ~TTM_PL_FLAG_NO_EVICT;
- }
- r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
- if (unlikely(r)) {
- dev_err(adev->dev, "%p validate failed for unpin\n", bo);
- goto error;
- }
if (bo->tbo.mem.mem_type == TTM_PL_VRAM) {
adev->vram_pin_size -= amdgpu_bo_size(bo);
- if (bo->flags & AMDGPU_GEM_CREATE_NO_CPU_ACCESS)
- adev->invisible_pin_size -= amdgpu_bo_size(bo);
+ adev->invisible_pin_size -= amdgpu_vram_mgr_bo_invisible_size(bo);
} else if (bo->tbo.mem.mem_type == TTM_PL_TT) {
adev->gart_pin_size -= amdgpu_bo_size(bo);
}
-error:
+ for (i = 0; i < bo->placement.num_placement; i++) {
+ bo->placements[i].lpfn = 0;
+ bo->placements[i].flags &= ~TTM_PL_FLAG_NO_EVICT;
+ }
+ r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
+ if (unlikely(r))
+ dev_err(adev->dev, "%p validate failed for unpin\n", bo);
+
return r;
}
uint64_t amdgpu_gtt_mgr_usage(struct ttm_mem_type_manager *man);
int amdgpu_gtt_mgr_recover(struct ttm_mem_type_manager *man);
+u64 amdgpu_vram_mgr_bo_invisible_size(struct amdgpu_bo *bo);
uint64_t amdgpu_vram_mgr_usage(struct ttm_mem_type_manager *man);
uint64_t amdgpu_vram_mgr_vis_usage(struct ttm_mem_type_manager *man);
unsigned version_major, version_minor, family_id;
int i, j, r;
- INIT_DELAYED_WORK(&adev->uvd.inst->idle_work, amdgpu_uvd_idle_work_handler);
+ INIT_DELAYED_WORK(&adev->uvd.idle_work, amdgpu_uvd_idle_work_handler);
switch (adev->asic_type) {
#ifdef CONFIG_DRM_AMDGPU_CIK
void *ptr;
int i, j;
+ cancel_delayed_work_sync(&adev->uvd.idle_work);
+
for (j = 0; j < adev->uvd.num_uvd_inst; ++j) {
if (adev->uvd.inst[j].vcpu_bo == NULL)
continue;
- cancel_delayed_work_sync(&adev->uvd.inst[j].idle_work);
-
/* only valid for physical mode */
if (adev->asic_type < CHIP_POLARIS10) {
for (i = 0; i < adev->uvd.max_handles; ++i)
static void amdgpu_uvd_idle_work_handler(struct work_struct *work)
{
struct amdgpu_device *adev =
- container_of(work, struct amdgpu_device, uvd.inst->idle_work.work);
+ container_of(work, struct amdgpu_device, uvd.idle_work.work);
unsigned fences = 0, i, j;
for (i = 0; i < adev->uvd.num_uvd_inst; ++i) {
AMD_CG_STATE_GATE);
}
} else {
- schedule_delayed_work(&adev->uvd.inst->idle_work, UVD_IDLE_TIMEOUT);
+ schedule_delayed_work(&adev->uvd.idle_work, UVD_IDLE_TIMEOUT);
}
}
if (amdgpu_sriov_vf(adev))
return;
- set_clocks = !cancel_delayed_work_sync(&adev->uvd.inst->idle_work);
+ set_clocks = !cancel_delayed_work_sync(&adev->uvd.idle_work);
if (set_clocks) {
if (adev->pm.dpm_enabled) {
amdgpu_dpm_enable_uvd(adev, true);
void amdgpu_uvd_ring_end_use(struct amdgpu_ring *ring)
{
if (!amdgpu_sriov_vf(ring->adev))
- schedule_delayed_work(&ring->adev->uvd.inst->idle_work, UVD_IDLE_TIMEOUT);
+ schedule_delayed_work(&ring->adev->uvd.idle_work, UVD_IDLE_TIMEOUT);
}
/**
void *saved_bo;
atomic_t handles[AMDGPU_MAX_UVD_HANDLES];
struct drm_file *filp[AMDGPU_MAX_UVD_HANDLES];
- struct delayed_work idle_work;
struct amdgpu_ring ring;
struct amdgpu_ring ring_enc[AMDGPU_MAX_UVD_ENC_RINGS];
struct amdgpu_irq_src irq;
bool address_64_bit;
bool use_ctx_buf;
struct amdgpu_uvd_inst inst[AMDGPU_MAX_UVD_INSTANCES];
+ struct delayed_work idle_work;
};
int amdgpu_uvd_sw_init(struct amdgpu_device *adev);
unsigned long bo_size;
const char *fw_name;
const struct common_firmware_header *hdr;
- unsigned version_major, version_minor, family_id;
+ unsigned char fw_check;
int r;
INIT_DELAYED_WORK(&adev->vcn.idle_work, amdgpu_vcn_idle_work_handler);
hdr = (const struct common_firmware_header *)adev->vcn.fw->data;
adev->vcn.fw_version = le32_to_cpu(hdr->ucode_version);
- family_id = le32_to_cpu(hdr->ucode_version) & 0xff;
- version_major = (le32_to_cpu(hdr->ucode_version) >> 24) & 0xff;
- version_minor = (le32_to_cpu(hdr->ucode_version) >> 8) & 0xff;
- DRM_INFO("Found VCN firmware Version: %hu.%hu Family ID: %hu\n",
- version_major, version_minor, family_id);
+ /* Bit 20-23, it is encode major and non-zero for new naming convention.
+ * This field is part of version minor and DRM_DISABLED_FLAG in old naming
+ * convention. Since the l:wq!atest version minor is 0x5B and DRM_DISABLED_FLAG
+ * is zero in old naming convention, this field is always zero so far.
+ * These four bits are used to tell which naming convention is present.
+ */
+ fw_check = (le32_to_cpu(hdr->ucode_version) >> 20) & 0xf;
+ if (fw_check) {
+ unsigned int dec_ver, enc_major, enc_minor, vep, fw_rev;
+
+ fw_rev = le32_to_cpu(hdr->ucode_version) & 0xfff;
+ enc_minor = (le32_to_cpu(hdr->ucode_version) >> 12) & 0xff;
+ enc_major = fw_check;
+ dec_ver = (le32_to_cpu(hdr->ucode_version) >> 24) & 0xf;
+ vep = (le32_to_cpu(hdr->ucode_version) >> 28) & 0xf;
+ DRM_INFO("Found VCN firmware Version ENC: %hu.%hu DEC: %hu VEP: %hu Revision: %hu\n",
+ enc_major, enc_minor, dec_ver, vep, fw_rev);
+ } else {
+ unsigned int version_major, version_minor, family_id;
+
+ family_id = le32_to_cpu(hdr->ucode_version) & 0xff;
+ version_major = (le32_to_cpu(hdr->ucode_version) >> 24) & 0xff;
+ version_minor = (le32_to_cpu(hdr->ucode_version) >> 8) & 0xff;
+ DRM_INFO("Found VCN firmware Version: %hu.%hu Family ID: %hu\n",
+ version_major, version_minor, family_id);
+ }
bo_size = AMDGPU_GPU_PAGE_ALIGN(le32_to_cpu(hdr->ucode_size_bytes) + 8)
+ AMDGPU_VCN_STACK_SIZE + AMDGPU_VCN_HEAP_SIZE
uint64_t count;
max_entries = min(max_entries, 16ull * 1024ull);
- for (count = 1; count < max_entries; ++count) {
+ for (count = 1;
+ count < max_entries / (PAGE_SIZE / AMDGPU_GPU_PAGE_SIZE);
+ ++count) {
uint64_t idx = pfn + count;
if (pages_addr[idx] !=
dma_addr = pages_addr;
} else {
addr = pages_addr[pfn];
- max_entries = count;
+ max_entries = count * (PAGE_SIZE / AMDGPU_GPU_PAGE_SIZE);
}
} else if (flags & AMDGPU_PTE_VALID) {
if (r)
return r;
- pfn += last - start + 1;
+ pfn += (last - start + 1) / (PAGE_SIZE / AMDGPU_GPU_PAGE_SIZE);
if (nodes && nodes->size == pfn) {
pfn = 0;
++nodes;
adev->gmc.visible_vram_size : end) - start;
}
+/**
+ * amdgpu_vram_mgr_bo_invisible_size - CPU invisible BO size
+ *
+ * @bo: &amdgpu_bo buffer object (must be in VRAM)
+ *
+ * Returns:
+ * How much of the given &amdgpu_bo buffer object lies in CPU invisible VRAM.
+ */
+u64 amdgpu_vram_mgr_bo_invisible_size(struct amdgpu_bo *bo)
+{
+ struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
+ struct ttm_mem_reg *mem = &bo->tbo.mem;
+ struct drm_mm_node *nodes = mem->mm_node;
+ unsigned pages = mem->num_pages;
+ u64 usage = 0;
+
+ if (adev->gmc.visible_vram_size == adev->gmc.real_vram_size)
+ return 0;
+
+ if (mem->start >= adev->gmc.visible_vram_size >> PAGE_SHIFT)
+ return amdgpu_bo_size(bo);
+
+ while (nodes && pages) {
+ usage += nodes->size << PAGE_SHIFT;
+ usage -= amdgpu_vram_mgr_vis_size(adev, nodes);
+ pages -= nodes->size;
+ ++nodes;
+ }
+
+ return usage;
+}
+
/**
* amdgpu_vram_mgr_new - allocate new ranges
*
num_nodes = DIV_ROUND_UP(mem->num_pages, pages_per_node);
}
- nodes = kcalloc(num_nodes, sizeof(*nodes), GFP_KERNEL);
+ nodes = kvmalloc_array(num_nodes, sizeof(*nodes),
+ GFP_KERNEL | __GFP_ZERO);
if (!nodes)
return -ENOMEM;
drm_mm_remove_node(&nodes[i]);
spin_unlock(&mgr->lock);
- kfree(nodes);
+ kvfree(nodes);
return r == -ENOSPC ? 0 : r;
}
atomic64_sub(usage, &mgr->usage);
atomic64_sub(vis_usage, &mgr->vis_usage);
- kfree(mem->mm_node);
+ kvfree(mem->mm_node);
mem->mm_node = NULL;
}
if (acrtc->base.state->event)
prepare_flip_isr(acrtc);
+ spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
+
surface_updates->surface = dc_stream_get_status(acrtc_state->stream)->plane_states[0];
surface_updates->flip_addr = &addr;
-
dc_commit_updates_for_stream(adev->dm.dc,
surface_updates,
1,
__func__,
addr.address.grph.addr.high_part,
addr.address.grph.addr.low_part);
-
-
- spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
}
/*
struct drm_connector *connector;
struct drm_connector_state *old_con_state, *new_con_state;
struct dm_crtc_state *dm_old_crtc_state, *dm_new_crtc_state;
+ int crtc_disable_count = 0;
drm_atomic_helper_update_legacy_modeset_state(dev, state);
struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc);
bool modeset_needed;
+ if (old_crtc_state->active && !new_crtc_state->active)
+ crtc_disable_count++;
+
dm_new_crtc_state = to_dm_crtc_state(new_crtc_state);
dm_old_crtc_state = to_dm_crtc_state(old_crtc_state);
modeset_needed = modeset_required(
* so we can put the GPU into runtime suspend if we're not driving any
* displays anymore
*/
+ for (i = 0; i < crtc_disable_count; i++)
+ pm_runtime_put_autosuspend(dev->dev);
pm_runtime_mark_last_busy(dev->dev);
- for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
- if (old_crtc_state->active && !new_crtc_state->active)
- pm_runtime_put_autosuspend(dev->dev);
- }
}
static int vega10_enable_psm_gc_edc_config(struct pp_hwmgr *hwmgr)
{
struct amdgpu_device *adev = hwmgr->adev;
- int result;
+ int result = 0;
uint32_t num_se = 0;
uint32_t count, data;
static void malidp_fini(struct drm_device *drm)
{
- drm_atomic_helper_shutdown(drm);
drm_mode_config_cleanup(drm);
}
malidp_de_irq_fini(drm);
drm->irq_enabled = false;
irq_init_fail:
+ drm_atomic_helper_shutdown(drm);
component_unbind_all(dev, drm);
bind_fail:
of_node_put(malidp->crtc.port);
malidp_se_irq_fini(drm);
malidp_de_irq_fini(drm);
drm->irq_enabled = false;
+ drm_atomic_helper_shutdown(drm);
component_unbind_all(dev, drm);
of_node_put(malidp->crtc.port);
malidp->crtc.port = NULL;
.vsync_irq = MALIDP500_DE_IRQ_VSYNC,
},
.se_irq_map = {
- .irq_mask = MALIDP500_SE_IRQ_CONF_MODE,
+ .irq_mask = MALIDP500_SE_IRQ_CONF_MODE |
+ MALIDP500_SE_IRQ_GLOBAL,
.vsync_irq = 0,
},
.dc_irq_map = {
/* Layer specific register offsets */
#define MALIDP_LAYER_FORMAT 0x000
+#define LAYER_FORMAT_MASK 0x3f
#define MALIDP_LAYER_CONTROL 0x004
#define LAYER_ENABLE (1 << 0)
#define LAYER_FLOWCFG_MASK 7
if (state->rotation & MALIDP_ROTATED_MASK) {
int val;
- val = mp->hwdev->hw->rotmem_required(mp->hwdev, state->crtc_h,
- state->crtc_w,
+ val = mp->hwdev->hw->rotmem_required(mp->hwdev, state->crtc_w,
+ state->crtc_h,
fb->format->format);
if (val < 0)
return val;
dest_w = plane->state->crtc_w;
dest_h = plane->state->crtc_h;
- malidp_hw_write(mp->hwdev, ms->format, mp->layer->base);
+ val = malidp_hw_read(mp->hwdev, mp->layer->base);
+ val = (val & ~LAYER_FORMAT_MASK) | ms->format;
+ malidp_hw_write(mp->hwdev, val, mp->layer->base);
for (i = 0; i < ms->n_planes; i++) {
/* calculate the offset for the layer's plane registers */
return ret;
}
- if (desc->layout.xstride && desc->layout.pstride) {
+ if (desc->layout.xstride[0] && desc->layout.pstride[0]) {
int ret;
ret = drm_plane_create_rotation_property(&plane->base,
#define SII8620_BURST_BUF_LEN 288
#define VAL_RX_HDMI_CTRL2_DEFVAL VAL_RX_HDMI_CTRL2_IDLE_CNT(3)
-#define MHL1_MAX_LCLK 225000
-#define MHL3_MAX_LCLK 600000
+
+#define MHL1_MAX_PCLK 75000
+#define MHL1_MAX_PCLK_PP_MODE 150000
+#define MHL3_MAX_PCLK 200000
+#define MHL3_MAX_PCLK_PP_MODE 300000
enum sii8620_mode {
CM_DISCONNECTED,
u8 devcap[MHL_DCAP_SIZE];
u8 xdevcap[MHL_XDC_SIZE];
u8 avif[HDMI_INFOFRAME_SIZE(AVI)];
+ bool feature_complete;
+ bool devcap_read;
+ bool sink_detected;
struct edid *edid;
unsigned int gen2_write_burst:1;
enum sii8620_mt_state mt_state;
}
}
-static void sii8620_sink_detected(struct sii8620 *ctx, int ret)
+static void sii8620_identify_sink(struct sii8620 *ctx)
{
static const char * const sink_str[] = {
[SINK_NONE] = "NONE",
char sink_name[20];
struct device *dev = ctx->dev;
- if (ret < 0)
+ if (!ctx->sink_detected || !ctx->devcap_read)
return;
sii8620_fetch_edid(ctx);
sii8620_mhl_disconnected(ctx);
return;
}
+ sii8620_set_upstream_edid(ctx);
if (drm_detect_hdmi_monitor(ctx->edid))
ctx->sink_type = SINK_HDMI;
sink_str[ctx->sink_type], sink_name);
}
-static void sii8620_hsic_init(struct sii8620 *ctx)
-{
- if (!sii8620_is_mhl3(ctx))
- return;
-
- sii8620_write(ctx, REG_FCGC,
- BIT_FCGC_HSIC_HOSTMODE | BIT_FCGC_HSIC_ENABLE);
- sii8620_setbits(ctx, REG_HRXCTRL3,
- BIT_HRXCTRL3_HRX_STAY_RESET | BIT_HRXCTRL3_STATUS_EN, ~0);
- sii8620_setbits(ctx, REG_TTXNUMB, MSK_TTXNUMB_TTX_NUMBPS, 4);
- sii8620_setbits(ctx, REG_TRXCTRL, BIT_TRXCTRL_TRX_FROM_SE_COC, ~0);
- sii8620_setbits(ctx, REG_HTXCTRL, BIT_HTXCTRL_HTX_DRVCONN1, 0);
- sii8620_setbits(ctx, REG_KEEPER, MSK_KEEPER_MODE, VAL_KEEPER_MODE_HOST);
- sii8620_write_seq_static(ctx,
- REG_TDMLLCTL, 0,
- REG_UTSRST, BIT_UTSRST_HRX_SRST | BIT_UTSRST_HTX_SRST |
- BIT_UTSRST_KEEPER_SRST | BIT_UTSRST_FC_SRST,
- REG_UTSRST, BIT_UTSRST_HRX_SRST | BIT_UTSRST_HTX_SRST,
- REG_HRXINTL, 0xff,
- REG_HRXINTH, 0xff,
- REG_TTXINTL, 0xff,
- REG_TTXINTH, 0xff,
- REG_TRXINTL, 0xff,
- REG_TRXINTH, 0xff,
- REG_HTXINTL, 0xff,
- REG_HTXINTH, 0xff,
- REG_FCINTR0, 0xff,
- REG_FCINTR1, 0xff,
- REG_FCINTR2, 0xff,
- REG_FCINTR3, 0xff,
- REG_FCINTR4, 0xff,
- REG_FCINTR5, 0xff,
- REG_FCINTR6, 0xff,
- REG_FCINTR7, 0xff
- );
-}
-
-static void sii8620_edid_read(struct sii8620 *ctx, int ret)
-{
- if (ret < 0)
- return;
-
- sii8620_set_upstream_edid(ctx);
- sii8620_hsic_init(ctx);
- sii8620_enable_hpd(ctx);
-}
-
static void sii8620_mr_devcap(struct sii8620 *ctx)
{
u8 dcap[MHL_DCAP_SIZE];
dcap[MHL_DCAP_ADOPTER_ID_H], dcap[MHL_DCAP_ADOPTER_ID_L],
dcap[MHL_DCAP_DEVICE_ID_H], dcap[MHL_DCAP_DEVICE_ID_L]);
sii8620_update_array(ctx->devcap, dcap, MHL_DCAP_SIZE);
+ ctx->devcap_read = true;
+ sii8620_identify_sink(ctx);
}
static void sii8620_mr_xdevcap(struct sii8620 *ctx)
static void sii8620_fetch_edid(struct sii8620 *ctx)
{
u8 lm_ddc, ddc_cmd, int3, cbus;
+ unsigned long timeout;
int fetched, i;
int edid_len = EDID_LENGTH;
u8 *edid;
REG_DDC_CMD, ddc_cmd | VAL_DDC_CMD_ENH_DDC_READ_NO_ACK
);
- do {
- int3 = sii8620_readb(ctx, REG_INTR3);
+ int3 = 0;
+ timeout = jiffies + msecs_to_jiffies(200);
+ for (;;) {
cbus = sii8620_readb(ctx, REG_CBUS_STATUS);
-
- if (int3 & BIT_DDC_CMD_DONE)
- break;
-
- if (!(cbus & BIT_CBUS_STATUS_CBUS_CONNECTED)) {
+ if (~cbus & BIT_CBUS_STATUS_CBUS_CONNECTED) {
+ kfree(edid);
+ edid = NULL;
+ goto end;
+ }
+ if (int3 & BIT_DDC_CMD_DONE) {
+ if (sii8620_readb(ctx, REG_DDC_DOUT_CNT)
+ >= FETCH_SIZE)
+ break;
+ } else {
+ int3 = sii8620_readb(ctx, REG_INTR3);
+ }
+ if (time_is_before_jiffies(timeout)) {
+ ctx->error = -ETIMEDOUT;
+ dev_err(ctx->dev, "timeout during EDID read\n");
kfree(edid);
edid = NULL;
goto end;
}
- } while (1);
-
- sii8620_readb(ctx, REG_DDC_STATUS);
- while (sii8620_readb(ctx, REG_DDC_DOUT_CNT) < FETCH_SIZE)
usleep_range(10, 20);
+ }
sii8620_read_buf(ctx, REG_DDC_DATA, edid + fetched, FETCH_SIZE);
if (fetched + FETCH_SIZE == EDID_LENGTH) {
ret = regulator_bulk_enable(ARRAY_SIZE(ctx->supplies), ctx->supplies);
if (ret)
return ret;
+
usleep_range(10000, 20000);
- return clk_prepare_enable(ctx->clk_xtal);
+ ret = clk_prepare_enable(ctx->clk_xtal);
+ if (ret)
+ return ret;
+
+ msleep(100);
+ gpiod_set_value(ctx->gpio_reset, 0);
+ msleep(100);
+
+ return 0;
}
static int sii8620_hw_off(struct sii8620 *ctx)
return regulator_bulk_disable(ARRAY_SIZE(ctx->supplies), ctx->supplies);
}
-static void sii8620_hw_reset(struct sii8620 *ctx)
-{
- usleep_range(10000, 20000);
- gpiod_set_value(ctx->gpio_reset, 0);
- usleep_range(5000, 20000);
- gpiod_set_value(ctx->gpio_reset, 1);
- usleep_range(10000, 20000);
- gpiod_set_value(ctx->gpio_reset, 0);
- msleep(300);
-}
-
static void sii8620_cbus_reset(struct sii8620 *ctx)
{
sii8620_write(ctx, REG_PWD_SRST, BIT_PWD_SRST_CBUS_RST
static void sii8620_set_format(struct sii8620 *ctx)
{
- u8 out_fmt;
-
if (sii8620_is_mhl3(ctx)) {
sii8620_setbits(ctx, REG_M3_P0CTRL,
BIT_M3_P0CTRL_MHL3_P0_PIXEL_MODE_PACKED,
ctx->use_packed_pixel ? ~0 : 0);
} else {
- if (ctx->use_packed_pixel)
- sii8620_write_seq_static(ctx,
- REG_VID_MODE, BIT_VID_MODE_M1080P,
- REG_MHL_TOP_CTL, BIT_MHL_TOP_CTL_MHL_PP_SEL | 1,
- REG_MHLTX_CTL6, 0x60
- );
- else
sii8620_write_seq_static(ctx,
REG_VID_MODE, 0,
REG_MHL_TOP_CTL, 1,
);
}
- if (ctx->use_packed_pixel)
- out_fmt = VAL_TPI_FORMAT(YCBCR422, FULL) |
- BIT_TPI_OUTPUT_CSCMODE709;
- else
- out_fmt = VAL_TPI_FORMAT(RGB, FULL);
-
sii8620_write_seq(ctx,
REG_TPI_INPUT, VAL_TPI_FORMAT(RGB, FULL),
- REG_TPI_OUTPUT, out_fmt,
+ REG_TPI_OUTPUT, VAL_TPI_FORMAT(RGB, FULL),
);
}
int clk = ctx->pixel_clock * (ctx->use_packed_pixel ? 2 : 3);
int i;
- for (i = 0; i < ARRAY_SIZE(clk_spec); ++i)
+ for (i = 0; i < ARRAY_SIZE(clk_spec) - 1; ++i)
if (clk < clk_spec[i].max_clk)
break;
);
}
+static void sii8620_hpd_unplugged(struct sii8620 *ctx)
+{
+ sii8620_disable_hpd(ctx);
+ ctx->sink_type = SINK_NONE;
+ ctx->sink_detected = false;
+ ctx->feature_complete = false;
+ kfree(ctx->edid);
+ ctx->edid = NULL;
+}
+
static void sii8620_disconnect(struct sii8620 *ctx)
{
sii8620_disable_gen2_write_burst(ctx);
REG_MHL_DP_CTL6, 0x2A,
REG_MHL_DP_CTL7, 0x03
);
- sii8620_disable_hpd(ctx);
+ sii8620_hpd_unplugged(ctx);
sii8620_write_seq_static(ctx,
REG_M3_CTRL, VAL_M3_CTRL_MHL3_VALUE,
REG_MHL_COC_CTL1, 0x07,
memset(ctx->xstat, 0, sizeof(ctx->xstat));
memset(ctx->devcap, 0, sizeof(ctx->devcap));
memset(ctx->xdevcap, 0, sizeof(ctx->xdevcap));
+ ctx->devcap_read = false;
ctx->cbus_status = 0;
- ctx->sink_type = SINK_NONE;
- kfree(ctx->edid);
- ctx->edid = NULL;
sii8620_mt_cleanup(ctx);
}
sii8620_mt_write_stat(ctx, MHL_DST_REG(LINK_MODE),
MHL_DST_LM_CLK_MODE_NORMAL
| MHL_DST_LM_PATH_ENABLED);
- if (!sii8620_is_mhl3(ctx))
- sii8620_mt_read_devcap(ctx, false);
- sii8620_mt_set_cont(ctx, sii8620_sink_detected);
} else {
sii8620_mt_write_stat(ctx, MHL_DST_REG(LINK_MODE),
MHL_DST_LM_CLK_MODE_NORMAL);
sii8620_update_array(ctx->stat, st, MHL_DST_SIZE);
sii8620_update_array(ctx->xstat, xst, MHL_XDS_SIZE);
- if (ctx->stat[MHL_DST_CONNECTED_RDY] & MHL_DST_CONN_DCAP_RDY)
+ if (ctx->stat[MHL_DST_CONNECTED_RDY] & st[MHL_DST_CONNECTED_RDY] &
+ MHL_DST_CONN_DCAP_RDY) {
sii8620_status_dcap_ready(ctx);
+ if (!sii8620_is_mhl3(ctx))
+ sii8620_mt_read_devcap(ctx, false);
+ }
+
if (st[MHL_DST_LINK_MODE] & MHL_DST_LM_PATH_ENABLED)
sii8620_status_changed_path(ctx);
}
}
if (ints[MHL_INT_RCHANGE] & MHL_INT_RC_FEAT_REQ)
sii8620_send_features(ctx);
- if (ints[MHL_INT_RCHANGE] & MHL_INT_RC_FEAT_COMPLETE)
- sii8620_edid_read(ctx, 0);
+ if (ints[MHL_INT_RCHANGE] & MHL_INT_RC_FEAT_COMPLETE) {
+ ctx->feature_complete = true;
+ if (ctx->edid)
+ sii8620_enable_hpd(ctx);
+ }
}
static struct sii8620_mt_msg *sii8620_msc_msg_first(struct sii8620 *ctx)
if (stat & BIT_CBUS_MSC_MR_WRITE_STAT)
sii8620_msc_mr_write_stat(ctx);
+ if (stat & BIT_CBUS_HPD_CHG) {
+ if (ctx->cbus_status & BIT_CBUS_STATUS_CBUS_HPD) {
+ ctx->sink_detected = true;
+ sii8620_identify_sink(ctx);
+ } else {
+ sii8620_hpd_unplugged(ctx);
+ }
+ }
+
if (stat & BIT_CBUS_MSC_MR_SET_INT)
sii8620_msc_mr_set_int(ctx);
ctx->mt_state = MT_STATE_DONE;
}
-static void sii8620_scdt_high(struct sii8620 *ctx)
-{
- sii8620_write_seq_static(ctx,
- REG_INTR8_MASK, BIT_CEA_NEW_AVI | BIT_CEA_NEW_VSI,
- REG_TPI_SC, BIT_TPI_SC_TPI_OUTPUT_MODE_0_HDMI,
- );
-}
-
static void sii8620_irq_scdt(struct sii8620 *ctx)
{
u8 stat = sii8620_readb(ctx, REG_INTR5);
if (stat & BIT_INTR_SCDT_CHANGE) {
u8 cstat = sii8620_readb(ctx, REG_TMDS_CSTAT_P3);
- if (cstat & BIT_TMDS_CSTAT_P3_SCDT) {
- if (ctx->sink_type == SINK_HDMI)
- /* enable infoframe interrupt */
- sii8620_scdt_high(ctx);
- else
- sii8620_start_video(ctx);
- }
+ if (cstat & BIT_TMDS_CSTAT_P3_SCDT)
+ sii8620_start_video(ctx);
}
sii8620_write(ctx, REG_INTR5, stat);
}
-static void sii8620_new_vsi(struct sii8620 *ctx)
-{
- u8 vsif[11];
-
- sii8620_write(ctx, REG_RX_HDMI_CTRL2,
- VAL_RX_HDMI_CTRL2_DEFVAL |
- BIT_RX_HDMI_CTRL2_VSI_MON_SEL_VSI);
- sii8620_read_buf(ctx, REG_RX_HDMI_MON_PKT_HEADER1, vsif,
- ARRAY_SIZE(vsif));
-}
-
-static void sii8620_new_avi(struct sii8620 *ctx)
-{
- sii8620_write(ctx, REG_RX_HDMI_CTRL2, VAL_RX_HDMI_CTRL2_DEFVAL);
- sii8620_read_buf(ctx, REG_RX_HDMI_MON_PKT_HEADER1, ctx->avif,
- ARRAY_SIZE(ctx->avif));
-}
-
-static void sii8620_irq_infr(struct sii8620 *ctx)
-{
- u8 stat = sii8620_readb(ctx, REG_INTR8)
- & (BIT_CEA_NEW_VSI | BIT_CEA_NEW_AVI);
-
- sii8620_write(ctx, REG_INTR8, stat);
-
- if (stat & BIT_CEA_NEW_VSI)
- sii8620_new_vsi(ctx);
-
- if (stat & BIT_CEA_NEW_AVI)
- sii8620_new_avi(ctx);
-
- if (stat & (BIT_CEA_NEW_VSI | BIT_CEA_NEW_AVI))
- sii8620_start_video(ctx);
-}
-
static void sii8620_got_xdevcap(struct sii8620 *ctx, int ret)
{
if (ret < 0)
if (stat & BIT_DDC_CMD_DONE) {
sii8620_write(ctx, REG_INTR3_MASK, 0);
- if (sii8620_is_mhl3(ctx))
+ if (sii8620_is_mhl3(ctx) && !ctx->feature_complete)
sii8620_mt_set_int(ctx, MHL_INT_REG(RCHANGE),
MHL_INT_RC_FEAT_REQ);
else
- sii8620_edid_read(ctx, 0);
+ sii8620_enable_hpd(ctx);
}
sii8620_write(ctx, REG_INTR3, stat);
}
{ BIT_FAST_INTR_STAT_EDID, sii8620_irq_edid },
{ BIT_FAST_INTR_STAT_DDC, sii8620_irq_ddc },
{ BIT_FAST_INTR_STAT_SCDT, sii8620_irq_scdt },
- { BIT_FAST_INTR_STAT_INFR, sii8620_irq_infr },
};
struct sii8620 *ctx = data;
u8 stats[LEN_FAST_INTR_STAT];
dev_err(dev, "Error powering on, %d.\n", ret);
return;
}
- sii8620_hw_reset(ctx);
sii8620_read_buf(ctx, REG_VND_IDL, ver, ARRAY_SIZE(ver));
ret = sii8620_clear_error(ctx);
rc_unregister_device(ctx->rc_dev);
}
+static int sii8620_is_packing_required(struct sii8620 *ctx,
+ const struct drm_display_mode *mode)
+{
+ int max_pclk, max_pclk_pp_mode;
+
+ if (sii8620_is_mhl3(ctx)) {
+ max_pclk = MHL3_MAX_PCLK;
+ max_pclk_pp_mode = MHL3_MAX_PCLK_PP_MODE;
+ } else {
+ max_pclk = MHL1_MAX_PCLK;
+ max_pclk_pp_mode = MHL1_MAX_PCLK_PP_MODE;
+ }
+
+ if (mode->clock < max_pclk)
+ return 0;
+ else if (mode->clock < max_pclk_pp_mode)
+ return 1;
+ else
+ return -1;
+}
+
static enum drm_mode_status sii8620_mode_valid(struct drm_bridge *bridge,
const struct drm_display_mode *mode)
{
struct sii8620 *ctx = bridge_to_sii8620(bridge);
+ int pack_required = sii8620_is_packing_required(ctx, mode);
bool can_pack = ctx->devcap[MHL_DCAP_VID_LINK_MODE] &
MHL_DCAP_VID_LINK_PPIXEL;
- unsigned int max_pclk = sii8620_is_mhl3(ctx) ? MHL3_MAX_LCLK :
- MHL1_MAX_LCLK;
- max_pclk /= can_pack ? 2 : 3;
- return (mode->clock > max_pclk) ? MODE_CLOCK_HIGH : MODE_OK;
+ switch (pack_required) {
+ case 0:
+ return MODE_OK;
+ case 1:
+ return (can_pack) ? MODE_OK : MODE_CLOCK_HIGH;
+ default:
+ return MODE_CLOCK_HIGH;
+ }
}
static bool sii8620_mode_fixup(struct drm_bridge *bridge,
struct drm_display_mode *adjusted_mode)
{
struct sii8620 *ctx = bridge_to_sii8620(bridge);
- int max_lclk;
- bool ret = true;
mutex_lock(&ctx->lock);
- max_lclk = sii8620_is_mhl3(ctx) ? MHL3_MAX_LCLK : MHL1_MAX_LCLK;
- if (max_lclk > 3 * adjusted_mode->clock) {
- ctx->use_packed_pixel = 0;
- goto end;
- }
- if ((ctx->devcap[MHL_DCAP_VID_LINK_MODE] & MHL_DCAP_VID_LINK_PPIXEL) &&
- max_lclk > 2 * adjusted_mode->clock) {
- ctx->use_packed_pixel = 1;
- goto end;
- }
- ret = false;
-end:
- if (ret) {
- u8 vic = drm_match_cea_mode(adjusted_mode);
-
- if (!vic) {
- union hdmi_infoframe frm;
- u8 mhl_vic[] = { 0, 95, 94, 93, 98 };
-
- /* FIXME: We need the connector here */
- drm_hdmi_vendor_infoframe_from_display_mode(
- &frm.vendor.hdmi, NULL, adjusted_mode);
- vic = frm.vendor.hdmi.vic;
- if (vic >= ARRAY_SIZE(mhl_vic))
- vic = 0;
- vic = mhl_vic[vic];
- }
- ctx->video_code = vic;
- ctx->pixel_clock = adjusted_mode->clock;
- }
+ ctx->use_packed_pixel = sii8620_is_packing_required(ctx, adjusted_mode);
+ ctx->video_code = drm_match_cea_mode(adjusted_mode);
+ ctx->pixel_clock = adjusted_mode->clock;
+
mutex_unlock(&ctx->lock);
- return ret;
+
+ return true;
}
static const struct drm_bridge_funcs sii8620_bridge_funcs = {
*/
void drm_dev_unplug(struct drm_device *dev)
{
- drm_dev_unregister(dev);
-
- mutex_lock(&drm_global_mutex);
- if (dev->open_count == 0)
- drm_dev_put(dev);
- mutex_unlock(&drm_global_mutex);
-
/*
* After synchronizing any critical read section is guaranteed to see
* the new value of ->unplugged, and any critical section which might
*/
dev->unplugged = true;
synchronize_srcu(&drm_unplug_srcu);
+
+ drm_dev_unregister(dev);
+
+ mutex_lock(&drm_global_mutex);
+ if (dev->open_count == 0)
+ drm_dev_put(dev);
+ mutex_unlock(&drm_global_mutex);
}
EXPORT_SYMBOL(drm_dev_unplug);
unsigned int bsd_engine;
-/* Client can have a maximum of 3 contexts banned before
- * it is denied of creating new contexts. As one context
- * ban needs 4 consecutive hangs, and more if there is
- * progress in between, this is a last resort stop gap measure
- * to limit the badly behaving clients access to gpu.
+/*
+ * Every context ban increments per client ban score. Also
+ * hangs in short succession increments ban score. If ban threshold
+ * is reached, client is considered banned and submitting more work
+ * will fail. This is a stop gap measure to limit the badly behaving
+ * clients access to gpu. Note that unbannable contexts never increment
+ * the client ban score.
*/
-#define I915_MAX_CLIENT_CONTEXT_BANS 3
- atomic_t context_bans;
+#define I915_CLIENT_SCORE_HANG_FAST 1
+#define I915_CLIENT_FAST_HANG_JIFFIES (60 * HZ)
+#define I915_CLIENT_SCORE_CONTEXT_BAN 3
+#define I915_CLIENT_SCORE_BANNED 9
+ /** ban_score: Accumulated score of all ctx bans and fast hangs. */
+ atomic_t ban_score;
+ unsigned long hang_timestamp;
};
/* Interface history:
**/
static inline struct scatterlist *__sg_next(struct scatterlist *sg)
{
-#ifdef CONFIG_DEBUG_SG
- BUG_ON(sg->sg_magic != SG_MAGIC);
-#endif
return sg_is_last(sg) ? NULL : ____sg_next(sg);
}
return 0;
}
+static void i915_gem_client_mark_guilty(struct drm_i915_file_private *file_priv,
+ const struct i915_gem_context *ctx)
+{
+ unsigned int score;
+ unsigned long prev_hang;
+
+ if (i915_gem_context_is_banned(ctx))
+ score = I915_CLIENT_SCORE_CONTEXT_BAN;
+ else
+ score = 0;
+
+ prev_hang = xchg(&file_priv->hang_timestamp, jiffies);
+ if (time_before(jiffies, prev_hang + I915_CLIENT_FAST_HANG_JIFFIES))
+ score += I915_CLIENT_SCORE_HANG_FAST;
+
+ if (score) {
+ atomic_add(score, &file_priv->ban_score);
+
+ DRM_DEBUG_DRIVER("client %s: gained %u ban score, now %u\n",
+ ctx->name, score,
+ atomic_read(&file_priv->ban_score));
+ }
+}
+
static void i915_gem_context_mark_guilty(struct i915_gem_context *ctx)
{
- bool banned;
+ unsigned int score;
+ bool banned, bannable;
atomic_inc(&ctx->guilty_count);
- banned = false;
- if (i915_gem_context_is_bannable(ctx)) {
- unsigned int score;
+ bannable = i915_gem_context_is_bannable(ctx);
+ score = atomic_add_return(CONTEXT_SCORE_GUILTY, &ctx->ban_score);
+ banned = score >= CONTEXT_SCORE_BAN_THRESHOLD;
- score = atomic_add_return(CONTEXT_SCORE_GUILTY,
- &ctx->ban_score);
- banned = score >= CONTEXT_SCORE_BAN_THRESHOLD;
+ DRM_DEBUG_DRIVER("context %s: guilty %d, score %u, ban %s\n",
+ ctx->name, atomic_read(&ctx->guilty_count),
+ score, yesno(banned && bannable));
- DRM_DEBUG_DRIVER("context %s marked guilty (score %d) banned? %s\n",
- ctx->name, score, yesno(banned));
- }
- if (!banned)
+ /* Cool contexts don't accumulate client ban score */
+ if (!bannable)
return;
- i915_gem_context_set_banned(ctx);
- if (!IS_ERR_OR_NULL(ctx->file_priv)) {
- atomic_inc(&ctx->file_priv->context_bans);
- DRM_DEBUG_DRIVER("client %s has had %d context banned\n",
- ctx->name, atomic_read(&ctx->file_priv->context_bans));
- }
+ if (banned)
+ i915_gem_context_set_banned(ctx);
+
+ if (!IS_ERR_OR_NULL(ctx->file_priv))
+ i915_gem_client_mark_guilty(ctx->file_priv, ctx);
}
static void i915_gem_context_mark_innocent(struct i915_gem_context *ctx)
INIT_LIST_HEAD(&file_priv->mm.request_list);
file_priv->bsd_engine = -1;
+ file_priv->hang_timestamp = jiffies;
ret = i915_gem_context_open(i915, file);
if (ret)
static bool client_is_banned(struct drm_i915_file_private *file_priv)
{
- return atomic_read(&file_priv->context_bans) > I915_MAX_CLIENT_CONTEXT_BANS;
+ return atomic_read(&file_priv->ban_score) >= I915_CLIENT_SCORE_BANNED;
}
int i915_gem_context_create_ioctl(struct drm_device *dev, void *data,
}
static int
-eb_add_vma(struct i915_execbuffer *eb, unsigned int i, struct i915_vma *vma)
+eb_add_vma(struct i915_execbuffer *eb,
+ unsigned int i, unsigned batch_idx,
+ struct i915_vma *vma)
{
struct drm_i915_gem_exec_object2 *entry = &eb->exec[i];
int err;
eb->flags[i] = entry->flags;
vma->exec_flags = &eb->flags[i];
+ /*
+ * SNA is doing fancy tricks with compressing batch buffers, which leads
+ * to negative relocation deltas. Usually that works out ok since the
+ * relocate address is still positive, except when the batch is placed
+ * very low in the GTT. Ensure this doesn't happen.
+ *
+ * Note that actual hangs have only been observed on gen7, but for
+ * paranoia do it everywhere.
+ */
+ if (i == batch_idx) {
+ if (!(eb->flags[i] & EXEC_OBJECT_PINNED))
+ eb->flags[i] |= __EXEC_OBJECT_NEEDS_BIAS;
+ if (eb->reloc_cache.has_fence)
+ eb->flags[i] |= EXEC_OBJECT_NEEDS_FENCE;
+
+ eb->batch = vma;
+ }
+
err = 0;
if (eb_pin_vma(eb, entry, vma)) {
if (entry->offset != vma->node.start) {
{
struct radix_tree_root *handles_vma = &eb->ctx->handles_vma;
struct drm_i915_gem_object *obj;
- unsigned int i;
+ unsigned int i, batch;
int err;
if (unlikely(i915_gem_context_is_closed(eb->ctx)))
INIT_LIST_HEAD(&eb->relocs);
INIT_LIST_HEAD(&eb->unbound);
+ batch = eb_batch_index(eb);
+
for (i = 0; i < eb->buffer_count; i++) {
u32 handle = eb->exec[i].handle;
struct i915_lut_handle *lut;
lut->handle = handle;
add_vma:
- err = eb_add_vma(eb, i, vma);
+ err = eb_add_vma(eb, i, batch, vma);
if (unlikely(err))
goto err_vma;
GEM_BUG_ON(vma != eb->vma[i]);
GEM_BUG_ON(vma->exec_flags != &eb->flags[i]);
+ GEM_BUG_ON(drm_mm_node_allocated(&vma->node) &&
+ eb_vma_misplaced(&eb->exec[i], vma, eb->flags[i]));
}
- /* take note of the batch buffer before we might reorder the lists */
- i = eb_batch_index(eb);
- eb->batch = eb->vma[i];
- GEM_BUG_ON(eb->batch->exec_flags != &eb->flags[i]);
-
- /*
- * SNA is doing fancy tricks with compressing batch buffers, which leads
- * to negative relocation deltas. Usually that works out ok since the
- * relocate address is still positive, except when the batch is placed
- * very low in the GTT. Ensure this doesn't happen.
- *
- * Note that actual hangs have only been observed on gen7, but for
- * paranoia do it everywhere.
- */
- if (!(eb->flags[i] & EXEC_OBJECT_PINNED))
- eb->flags[i] |= __EXEC_OBJECT_NEEDS_BIAS;
- if (eb->reloc_cache.has_fence)
- eb->flags[i] |= EXEC_OBJECT_NEEDS_FENCE;
-
eb->args->flags |= __EXEC_VALIDATED;
return eb_reserve(eb);
/*
* Clear the PIPE*STAT regs before the IIR
+ *
+ * Toggle the enable bits to make sure we get an
+ * edge in the ISR pipe event bit if we don't clear
+ * all the enabled status bits. Otherwise the edge
+ * triggered IIR on i965/g4x wouldn't notice that
+ * an interrupt is still pending.
*/
- if (pipe_stats[pipe])
- I915_WRITE(reg, enable_mask | pipe_stats[pipe]);
+ if (pipe_stats[pipe]) {
+ I915_WRITE(reg, pipe_stats[pipe]);
+ I915_WRITE(reg, enable_mask);
+ }
}
spin_unlock(&dev_priv->irq_lock);
}
#define _3D_CHICKEN _MMIO(0x2084)
#define _3D_CHICKEN_HIZ_PLANE_DISABLE_MSAA_4X_SNB (1 << 10)
#define _3D_CHICKEN2 _MMIO(0x208c)
+
+#define FF_SLICE_CHICKEN _MMIO(0x2088)
+#define FF_SLICE_CHICKEN_CL_PROVOKING_VERTEX_FIX (1 << 1)
+
/* Disables pipelining of read flushes past the SF-WIZ interface.
* Required on all Ironlake steppings according to the B-Spec, but the
* particular danger of not doing so is not specified.
*/
# define _3D_CHICKEN2_WM_READ_PIPELINED (1 << 14)
#define _3D_CHICKEN3 _MMIO(0x2090)
+#define _3D_CHICKEN_SF_PROVOKING_VERTEX_FIX (1 << 12)
#define _3D_CHICKEN_SF_DISABLE_OBJEND_CULL (1 << 10)
#define _3D_CHICKEN3_AA_LINE_QUALITY_FIX_ENABLE (1 << 5)
#define _3D_CHICKEN3_SF_DISABLE_FASTCLIP_CULL (1 << 5)
int max_dotclk = dev_priv->max_dotclk_freq;
int max_clock;
+ if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ return MODE_NO_DBLESCAN;
+
if (mode->clock < 25000)
return MODE_CLOCK_LOW;
struct intel_crtc_state *pipe_config,
struct drm_connector_state *conn_state)
{
+ struct drm_display_mode *adjusted_mode =
+ &pipe_config->base.adjusted_mode;
+
+ if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ return false;
+
return true;
}
struct intel_crtc_state *pipe_config,
struct drm_connector_state *conn_state)
{
+ struct drm_display_mode *adjusted_mode =
+ &pipe_config->base.adjusted_mode;
+
+ if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ return false;
+
pipe_config->has_pch_encoder = true;
return true;
struct drm_connector_state *conn_state)
{
struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+ struct drm_display_mode *adjusted_mode =
+ &pipe_config->base.adjusted_mode;
+
+ if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ return false;
pipe_config->has_pch_encoder = true;
intel_mode_valid(struct drm_device *dev,
const struct drm_display_mode *mode)
{
+ /*
+ * Can't reject DBLSCAN here because Xorg ddxen can add piles
+ * of DBLSCAN modes to the output's mode list when they detect
+ * the scaling mode property on the connector. And they don't
+ * ask the kernel to validate those modes in any way until
+ * modeset time at which point the client gets a protocol error.
+ * So in order to not upset those clients we silently ignore the
+ * DBLSCAN flag on such connectors. For other connectors we will
+ * reject modes with the DBLSCAN flag in encoder->compute_config().
+ * And we always reject DBLSCAN modes in connector->mode_valid()
+ * as we never want such modes on the connector's mode list.
+ */
+
if (mode->vscan > 1)
return MODE_NO_VSCAN;
- if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
- return MODE_NO_DBLESCAN;
-
if (mode->flags & DRM_MODE_FLAG_HSKEW)
return MODE_H_ILLEGAL;
int max_rate, mode_rate, max_lanes, max_link_clock;
int max_dotclk;
+ if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ return MODE_NO_DBLESCAN;
+
max_dotclk = intel_dp_downstream_max_dotclock(intel_dp);
if (intel_dp_is_edp(intel_dp) && fixed_mode) {
conn_state->scaling_mode);
}
- if ((IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) &&
+ if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ return false;
+
+ if (HAS_GMCH_DISPLAY(dev_priv) &&
adjusted_mode->flags & DRM_MODE_FLAG_INTERLACE)
return false;
static void g4x_disable_dp(struct intel_encoder *encoder,
const struct intel_crtc_state *old_crtc_state,
const struct drm_connector_state *old_conn_state)
-{
- intel_disable_dp(encoder, old_crtc_state, old_conn_state);
-
- /* disable the port before the pipe on g4x */
- intel_dp_link_down(encoder, old_crtc_state);
-}
-
-static void ilk_disable_dp(struct intel_encoder *encoder,
- const struct intel_crtc_state *old_crtc_state,
- const struct drm_connector_state *old_conn_state)
{
intel_disable_dp(encoder, old_crtc_state, old_conn_state);
}
intel_disable_dp(encoder, old_crtc_state, old_conn_state);
}
-static void ilk_post_disable_dp(struct intel_encoder *encoder,
+static void g4x_post_disable_dp(struct intel_encoder *encoder,
const struct intel_crtc_state *old_crtc_state,
const struct drm_connector_state *old_conn_state)
{
struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
enum port port = encoder->port;
+ /*
+ * Bspec does not list a specific disable sequence for g4x DP.
+ * Follow the ilk+ sequence (disable pipe before the port) for
+ * g4x DP as it does not suffer from underruns like the normal
+ * g4x modeset sequence (disable pipe after the port).
+ */
intel_dp_link_down(encoder, old_crtc_state);
/* Only ilk+ has port A */
drm_connector_init(dev, connector, &intel_dp_connector_funcs, type);
drm_connector_helper_add(connector, &intel_dp_connector_helper_funcs);
- if (!IS_VALLEYVIEW(dev_priv) && !IS_CHERRYVIEW(dev_priv))
+ if (!HAS_GMCH_DISPLAY(dev_priv))
connector->interlace_allowed = true;
connector->doublescan_allowed = 0;
intel_encoder->enable = vlv_enable_dp;
intel_encoder->disable = vlv_disable_dp;
intel_encoder->post_disable = vlv_post_disable_dp;
- } else if (INTEL_GEN(dev_priv) >= 5) {
- intel_encoder->pre_enable = g4x_pre_enable_dp;
- intel_encoder->enable = g4x_enable_dp;
- intel_encoder->disable = ilk_disable_dp;
- intel_encoder->post_disable = ilk_post_disable_dp;
} else {
intel_encoder->pre_enable = g4x_pre_enable_dp;
intel_encoder->enable = g4x_enable_dp;
intel_encoder->disable = g4x_disable_dp;
+ intel_encoder->post_disable = g4x_post_disable_dp;
}
intel_dig_port->dp.output_reg = output_reg;
bool reduce_m_n = drm_dp_has_quirk(&intel_dp->desc,
DP_DPCD_QUIRK_LIMITED_M_N);
+ if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ return false;
+
pipe_config->has_pch_encoder = false;
bpp = 24;
if (intel_dp->compliance.test_data.bpc) {
if (!intel_dp)
return MODE_ERROR;
+ if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ return MODE_NO_DBLESCAN;
+
max_link_clock = intel_dp_max_link_rate(intel_dp);
max_lanes = intel_dp_max_lane_count(intel_dp);
conn_state->scaling_mode);
}
+ if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ return false;
+
/* DSI uses short packets for sync events, so clear mode flags for DSI */
adjusted_mode->flags = 0;
DRM_DEBUG_KMS("\n");
+ if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ return MODE_NO_DBLESCAN;
+
if (fixed_mode) {
if (mode->hdisplay > fixed_mode->hdisplay)
return MODE_PANEL;
int max_dotclk = to_i915(connector->dev)->max_dotclk_freq;
int target_clock = mode->clock;
+ if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ return MODE_NO_DBLESCAN;
+
/* XXX: Validate clock range */
if (fixed_mode) {
if (fixed_mode)
intel_fixed_panel_mode(fixed_mode, adjusted_mode);
+ if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ return false;
+
return true;
}
bool force_dvi =
READ_ONCE(to_intel_digital_connector_state(connector->state)->force_audio) == HDMI_AUDIO_OFF_DVI;
+ if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ return MODE_NO_DBLESCAN;
+
clock = mode->clock;
if ((mode->flags & DRM_MODE_FLAG_3D_MASK) == DRM_MODE_FLAG_3D_FRAME_PACKING)
int desired_bpp;
bool force_dvi = intel_conn_state->force_audio == HDMI_AUDIO_OFF_DVI;
+ if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ return false;
+
pipe_config->has_hdmi_sink = !force_dvi && intel_hdmi->has_hdmi_sink;
if (pipe_config->has_hdmi_sink)
/* WaFlushCoherentL3CacheLinesAtContextSwitch:skl,bxt,glk */
batch = gen8_emit_flush_coherentl3_wa(engine, batch);
+ *batch++ = MI_LOAD_REGISTER_IMM(3);
+
/* WaDisableGatherAtSetShaderCommonSlice:skl,bxt,kbl,glk */
- *batch++ = MI_LOAD_REGISTER_IMM(1);
*batch++ = i915_mmio_reg_offset(COMMON_SLICE_CHICKEN2);
*batch++ = _MASKED_BIT_DISABLE(
GEN9_DISABLE_GATHER_AT_SET_SHADER_COMMON_SLICE);
+
+ /* BSpec: 11391 */
+ *batch++ = i915_mmio_reg_offset(FF_SLICE_CHICKEN);
+ *batch++ = _MASKED_BIT_ENABLE(FF_SLICE_CHICKEN_CL_PROVOKING_VERTEX_FIX);
+
+ /* BSpec: 11299 */
+ *batch++ = i915_mmio_reg_offset(_3D_CHICKEN3);
+ *batch++ = _MASKED_BIT_ENABLE(_3D_CHICKEN_SF_PROVOKING_VERTEX_FIX);
+
*batch++ = MI_NOOP;
/* WaClearSlmSpaceAtContextSwitch:kbl */
context_size += LRC_HEADER_PAGES * PAGE_SIZE;
ctx_obj = i915_gem_object_create(ctx->i915, context_size);
- if (IS_ERR(ctx_obj)) {
- ret = PTR_ERR(ctx_obj);
- goto error_deref_obj;
- }
+ if (IS_ERR(ctx_obj))
+ return PTR_ERR(ctx_obj);
vma = i915_vma_instance(ctx_obj, &ctx->i915->ggtt.base, NULL);
if (IS_ERR(vma)) {
struct drm_display_mode *fixed_mode = intel_connector->panel.fixed_mode;
int max_pixclk = to_i915(connector->dev)->max_dotclk_freq;
+ if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ return MODE_NO_DBLESCAN;
if (mode->hdisplay > fixed_mode->hdisplay)
return MODE_PANEL;
if (mode->vdisplay > fixed_mode->vdisplay)
intel_fixed_panel_mode(intel_connector->panel.fixed_mode,
adjusted_mode);
+ if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ return false;
+
if (HAS_PCH_SPLIT(dev_priv)) {
pipe_config->has_pch_encoder = true;
adjusted_mode);
}
+ if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ return false;
+
/*
* Make the CRTC code factor in the SDVO pixel multiplier. The
* SDVO device will factor out the multiplier during mode_set.
struct intel_sdvo *intel_sdvo = intel_attached_sdvo(connector);
int max_dotclk = to_i915(connector->dev)->max_dotclk_freq;
+ if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ return MODE_NO_DBLESCAN;
+
if (intel_sdvo->pixel_clock_min > mode->clock)
return MODE_CLOCK_LOW;
const struct tv_mode *tv_mode = intel_tv_mode_find(connector->state);
int max_dotclk = to_i915(connector->dev)->max_dotclk_freq;
+ if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ return MODE_NO_DBLESCAN;
+
if (mode->clock > max_dotclk)
return MODE_CLOCK_HIGH;
struct drm_connector_state *conn_state)
{
const struct tv_mode *tv_mode = intel_tv_mode_find(conn_state);
+ struct drm_display_mode *adjusted_mode =
+ &pipe_config->base.adjusted_mode;
if (!tv_mode)
return false;
- pipe_config->base.adjusted_mode.crtc_clock = tv_mode->clock;
+ if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ return false;
+
+ adjusted_mode->crtc_clock = tv_mode->clock;
DRM_DEBUG_KMS("forcing bpc to 8 for TV\n");
pipe_config->pipe_bpp = 8*3;
/* TV has it's own notion of sync and other mode flags, so clear them. */
- pipe_config->base.adjusted_mode.flags = 0;
+ adjusted_mode->flags = 0;
/*
* FIXME: We don't check whether the input mode is actually what we want
priv->io_base = regs;
res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "hhi");
- if (!res)
- return -EINVAL;
+ if (!res) {
+ ret = -EINVAL;
+ goto free_drm;
+ }
/* Simply ioremap since it may be a shared register zone */
regs = devm_ioremap(dev, res->start, resource_size(res));
if (!regs) {
}
res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dmc");
- if (!res)
- return -EINVAL;
+ if (!res) {
+ ret = -EINVAL;
+ goto free_drm;
+ }
/* Simply ioremap since it may be a shared register zone */
regs = devm_ioremap(dev, res->start, resource_size(res));
if (!regs) {
nvif_object_map(&wndw->wimm.base.user, NULL, 0);
wndw->immd = func;
- wndw->ctxdma.parent = &disp->core->chan.base.user;
+ wndw->ctxdma.parent = NULL;
return 0;
}
if (ret)
return ret;
- ctxdma = nv50_wndw_ctxdma_new(wndw, fb);
- if (IS_ERR(ctxdma)) {
- nouveau_bo_unpin(fb->nvbo);
- return PTR_ERR(ctxdma);
+ if (wndw->ctxdma.parent) {
+ ctxdma = nv50_wndw_ctxdma_new(wndw, fb);
+ if (IS_ERR(ctxdma)) {
+ nouveau_bo_unpin(fb->nvbo);
+ return PTR_ERR(ctxdma);
+ }
+
+ asyw->image.handle[0] = ctxdma->object.handle;
}
asyw->state.fence = reservation_object_get_excl_rcu(fb->nvbo->bo.resv);
- asyw->image.handle[0] = ctxdma->object.handle;
asyw->image.offset[0] = fb->nvbo->bo.offset;
if (wndw->func->prepare) {
struct qxl_cursor_cmd *cmd;
struct qxl_cursor *cursor;
struct drm_gem_object *obj;
- struct qxl_bo *cursor_bo = NULL, *user_bo = NULL;
+ struct qxl_bo *cursor_bo = NULL, *user_bo = NULL, *old_cursor_bo = NULL;
int ret;
void *user_ptr;
int size = 64*64*4;
cursor_bo, 0);
cmd->type = QXL_CURSOR_SET;
- qxl_bo_unref(&qcrtc->cursor_bo);
+ old_cursor_bo = qcrtc->cursor_bo;
qcrtc->cursor_bo = cursor_bo;
cursor_bo = NULL;
} else {
qxl_push_cursor_ring_release(qdev, release, QXL_CMD_CURSOR, false);
qxl_release_fence_buffer_objects(release);
+ if (old_cursor_bo)
+ qxl_bo_unref(&old_cursor_bo);
+
qxl_bo_unref(&cursor_bo);
return;
#include <drm/drm_encoder.h>
#include <drm/drm_modes.h>
#include <drm/drm_of.h>
-#include <drm/drm_panel.h>
#include <uapi/drm/drm_mode.h>
static void sun4i_tcon0_mode_set_rgb(struct sun4i_tcon *tcon,
const struct drm_display_mode *mode)
{
- struct drm_panel *panel = tcon->panel;
- struct drm_connector *connector = panel->connector;
- struct drm_display_info display_info = connector->display_info;
unsigned int bp, hsync, vsync;
u8 clk_delay;
u32 val = 0;
if (mode->flags & DRM_MODE_FLAG_PVSYNC)
val |= SUN4I_TCON0_IO_POL_VSYNC_POSITIVE;
- /*
- * On A20 and similar SoCs, the only way to achieve Positive Edge
- * (Rising Edge), is setting dclk clock phase to 2/3(240°).
- * By default TCON works in Negative Edge(Falling Edge),
- * this is why phase is set to 0 in that case.
- * Unfortunately there's no way to logically invert dclk through
- * IO_POL register.
- * The only acceptable way to work, triple checked with scope,
- * is using clock phase set to 0° for Negative Edge and set to 240°
- * for Positive Edge.
- * On A33 and similar SoCs there would be a 90° phase option,
- * but it divides also dclk by 2.
- * Following code is a way to avoid quirks all around TCON
- * and DOTCLOCK drivers.
- */
- if (display_info.bus_flags & DRM_BUS_FLAG_PIXDATA_POSEDGE)
- clk_set_phase(tcon->dclk, 240);
-
- if (display_info.bus_flags & DRM_BUS_FLAG_PIXDATA_NEGEDGE)
- clk_set_phase(tcon->dclk, 0);
-
regmap_update_bits(tcon->regs, SUN4I_TCON0_IO_POL_REG,
SUN4I_TCON0_IO_POL_HSYNC_POSITIVE | SUN4I_TCON0_IO_POL_VSYNC_POSITIVE,
val);
USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_STAFF) },
{ HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_WAND) },
+ { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
+ USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_WHISKERS) },
{ }
};
MODULE_DEVICE_TABLE(hid, hammer_devices);
#define USB_DEVICE_ID_GOOGLE_TOUCH_ROSE 0x5028
#define USB_DEVICE_ID_GOOGLE_STAFF 0x502b
#define USB_DEVICE_ID_GOOGLE_WAND 0x502d
+#define USB_DEVICE_ID_GOOGLE_WHISKERS 0x5030
#define USB_VENDOR_ID_GOTOP 0x08f2
#define USB_DEVICE_ID_SUPER_Q2 0x007f
static int steam_client_ll_parse(struct hid_device *hdev)
{
- struct steam_device *steam = hid_get_drvdata(hdev);
+ struct steam_device *steam = hdev->driver_data;
return hid_parse_report(hdev, steam->hdev->dev_rdesc,
steam->hdev->dev_rsize);
static int steam_client_ll_open(struct hid_device *hdev)
{
- struct steam_device *steam = hid_get_drvdata(hdev);
+ struct steam_device *steam = hdev->driver_data;
int ret;
ret = hid_hw_open(steam->hdev);
static void steam_client_ll_close(struct hid_device *hdev)
{
- struct steam_device *steam = hid_get_drvdata(hdev);
+ struct steam_device *steam = hdev->driver_data;
mutex_lock(&steam->mutex);
steam->client_opened = false;
size_t count, unsigned char report_type,
int reqtype)
{
- struct steam_device *steam = hid_get_drvdata(hdev);
+ struct steam_device *steam = hdev->driver_data;
return hid_hw_raw_request(steam->hdev, reportnum, buf, count,
report_type, reqtype);
ret = PTR_ERR(steam->client_hdev);
goto client_hdev_fail;
}
- hid_set_drvdata(steam->client_hdev, steam);
+ steam->client_hdev->driver_data = steam;
/*
* With the real steam controller interface, do not connect hidraw.
kfree(ishtp_dev);
}
-#ifdef CONFIG_PM
-static struct device *ish_resume_device;
+static struct device __maybe_unused *ish_resume_device;
/* 50ms to get resume response */
#define WAIT_FOR_RESUME_ACK_MS 50
* in that case a simple resume message is enough, others we need
* a reset sequence.
*/
-static void ish_resume_handler(struct work_struct *work)
+static void __maybe_unused ish_resume_handler(struct work_struct *work)
{
struct pci_dev *pdev = to_pci_dev(ish_resume_device);
struct ishtp_device *dev = pci_get_drvdata(pdev);
*
* Return: 0 to the pm core
*/
-static int ish_suspend(struct device *device)
+static int __maybe_unused ish_suspend(struct device *device)
{
struct pci_dev *pdev = to_pci_dev(device);
struct ishtp_device *dev = pci_get_drvdata(pdev);
return 0;
}
-static DECLARE_WORK(resume_work, ish_resume_handler);
+static __maybe_unused DECLARE_WORK(resume_work, ish_resume_handler);
/**
* ish_resume() - ISH resume callback
* @device: device pointer
*
* Return: 0 to the pm core
*/
-static int ish_resume(struct device *device)
+static int __maybe_unused ish_resume(struct device *device)
{
struct pci_dev *pdev = to_pci_dev(device);
struct ishtp_device *dev = pci_get_drvdata(pdev);
return 0;
}
-static const struct dev_pm_ops ish_pm_ops = {
- .suspend = ish_suspend,
- .resume = ish_resume,
-};
-#define ISHTP_ISH_PM_OPS (&ish_pm_ops)
-#else
-#define ISHTP_ISH_PM_OPS NULL
-#endif /* CONFIG_PM */
+static SIMPLE_DEV_PM_OPS(ish_pm_ops, ish_suspend, ish_resume);
static struct pci_driver ish_driver = {
.name = KBUILD_MODNAME,
.id_table = ish_pci_tbl,
.probe = ish_probe,
.remove = ish_remove,
- .driver.pm = ISHTP_ISH_PM_OPS,
+ .driver.pm = &ish_pm_ops,
};
module_pci_driver(ish_driver);
}
}
+ /* 2nd-generation Intuos Pro Large has incorrect Y maximum */
+ if (hdev->vendor == USB_VENDOR_ID_WACOM &&
+ hdev->product == 0x0358 &&
+ WACOM_PEN_FIELD(field) &&
+ wacom_equivalent_usage(usage->hid) == HID_GD_Y) {
+ field->logical_maximum = 43200;
+ }
+
switch (usage->hid) {
case HID_GD_X:
features->x_max = field->logical_maximum;
DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Vostro 3360"),
},
},
+ {
+ .ident = "Dell XPS13 9333",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "XPS13 9333"),
+ },
+ },
{ }
};
[hwmon_power_cap_hyst] = "power%d_cap_hyst",
[hwmon_power_cap_max] = "power%d_cap_max",
[hwmon_power_cap_min] = "power%d_cap_min",
+ [hwmon_power_min] = "power%d_min",
[hwmon_power_max] = "power%d_max",
+ [hwmon_power_lcrit] = "power%d_lcrit",
[hwmon_power_crit] = "power%d_crit",
[hwmon_power_label] = "power%d_label",
[hwmon_power_alarm] = "power%d_alarm",
[hwmon_power_cap_alarm] = "power%d_cap_alarm",
+ [hwmon_power_min_alarm] = "power%d_min_alarm",
[hwmon_power_max_alarm] = "power%d_max_alarm",
+ [hwmon_power_lcrit_alarm] = "power%d_lcrit_alarm",
[hwmon_power_crit_alarm] = "power%d_crit_alarm",
};
* The temperature is already monitored if the respective bit in <mask>
* is set.
*/
- for (i = 0; i < 32; i++) {
+ for (i = 0; i < 31; i++) {
if (!(data->temp_mask & BIT(i + 1)))
continue;
if (!reg_temp_alternate[i])
if (bit_adap->getscl == NULL)
adap->quirks = &i2c_bit_quirk_no_clk_stretch;
- /* Bring bus to a known state. Looks like STOP if bus is not free yet */
- setscl(bit_adap, 1);
- udelay(bit_adap->udelay);
- setsda(bit_adap, 1);
+ /*
+ * We tried forcing SCL/SDA to an initial state here. But that caused a
+ * regression, sadly. Check Bugzilla #200045 for details.
+ */
ret = add_adapter(adap);
if (ret < 0)
* required for an I2C bus.
*/
if (pdata->scl_is_open_drain)
- gflags = GPIOD_OUT_LOW;
+ gflags = GPIOD_OUT_HIGH;
else
- gflags = GPIOD_OUT_LOW_OPEN_DRAIN;
+ gflags = GPIOD_OUT_HIGH_OPEN_DRAIN;
priv->scl = i2c_gpio_get_desc(dev, "scl", 1, gflags);
if (IS_ERR(priv->scl))
return PTR_ERR(priv->scl);
status = i2c_transfer(adapter, msg, num);
if (status < 0)
- return status;
- if (status != num)
- return -EIO;
+ goto cleanup;
+ if (status != num) {
+ status = -EIO;
+ goto cleanup;
+ }
+ status = 0;
/* Check PEC if last message is a read */
if (i && (msg[num-1].flags & I2C_M_RD)) {
status = i2c_smbus_check_pec(partial_pec, &msg[num-1]);
if (status < 0)
- return status;
+ goto cleanup;
}
if (read_write == I2C_SMBUS_READ)
break;
}
+cleanup:
if (msg[0].flags & I2C_M_DMA_SAFE)
kfree(msg[0].buf);
if (msg[1].flags & I2C_M_DMA_SAFE)
kfree(msg[1].buf);
- return 0;
+ return status;
}
/**
if (src < 0)
return IRQ_NONE;
- if (!(src & data->chip_info->enabled_events))
+ if (!(src & (data->chip_info->enabled_events | MMA8452_INT_DRDY)))
return IRQ_NONE;
if (src & MMA8452_INT_DRDY) {
}
irq_type = irqd_get_trigger_type(desc);
+ if (!irq_type)
+ irq_type = IRQF_TRIGGER_RISING;
if (irq_type == IRQF_TRIGGER_RISING)
st->irq_mask = INV_MPU6050_ACTIVE_HIGH;
else if (irq_type == IRQF_TRIGGER_FALLING)
"%s: failed to get lux\n", __func__);
return lux_val;
}
+ if (lux_val == 0)
+ return -ERANGE;
ret = (chip->settings.als_cal_target * chip->settings.als_gain_trim) /
lux_val;
}
comp_humidity = bmp280_compensate_humidity(data, adc_humidity);
- *val = comp_humidity;
- *val2 = 1024;
+ *val = comp_humidity * 1000 / 1024;
- return IIO_VAL_FRACTIONAL;
+ return IIO_VAL_INT;
}
static int bmp280_read_raw(struct iio_dev *indio_dev,
if (ret)
return ret;
- if (!file->ucontext &&
- (command != IB_USER_VERBS_CMD_GET_CONTEXT || extended))
- return -EINVAL;
-
if (extended) {
if (count < (sizeof(hdr) + sizeof(ex_hdr)))
return -EINVAL;
goto out;
}
+ /*
+ * Must be after the ib_dev check, as once the RCU clears ib_dev ==
+ * NULL means ucontext == NULL
+ */
+ if (!file->ucontext &&
+ (command != IB_USER_VERBS_CMD_GET_CONTEXT || extended)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
if (!verify_command_mask(ib_dev, command, extended)) {
ret = -EOPNOTSUPP;
goto out;
/* Completion queues */
-struct ib_cq *ib_create_cq(struct ib_device *device,
- ib_comp_handler comp_handler,
- void (*event_handler)(struct ib_event *, void *),
- void *cq_context,
- const struct ib_cq_init_attr *cq_attr)
+struct ib_cq *__ib_create_cq(struct ib_device *device,
+ ib_comp_handler comp_handler,
+ void (*event_handler)(struct ib_event *, void *),
+ void *cq_context,
+ const struct ib_cq_init_attr *cq_attr,
+ const char *caller)
{
struct ib_cq *cq;
cq->cq_context = cq_context;
atomic_set(&cq->usecnt, 0);
cq->res.type = RDMA_RESTRACK_CQ;
+ cq->res.kern_name = caller;
rdma_restrack_add(&cq->res);
}
return cq;
}
-EXPORT_SYMBOL(ib_create_cq);
+EXPORT_SYMBOL(__ib_create_cq);
int rdma_set_cq_moderation(struct ib_cq *cq, u16 cq_count, u16 cq_period)
{
static u16 hfi1_vnic_select_queue(struct net_device *netdev,
struct sk_buff *skb,
- void *accel_priv,
+ struct net_device *sb_dev,
select_queue_fallback_t fallback)
{
struct hfi1_vnic_vport_info *vinfo = opa_vnic_dev_priv(netdev);
}
if (flags & IB_MR_REREG_ACCESS) {
- if (ib_access_writable(mr_access_flags) && !mmr->umem->writable)
- return -EPERM;
+ if (ib_access_writable(mr_access_flags) &&
+ !mmr->umem->writable) {
+ err = -EPERM;
+ goto release_mpt_entry;
+ }
err = mlx4_mr_hw_change_access(dev->dev, *pmpt_entry,
convert_access(mr_access_flags));
if (!mcounters->hw_cntrs_hndl) {
mcounters->hw_cntrs_hndl = mlx5_fc_create(
to_mdev(ibcounters->device)->mdev, false);
- if (!mcounters->hw_cntrs_hndl) {
- ret = -ENOMEM;
+ if (IS_ERR(mcounters->hw_cntrs_hndl)) {
+ ret = PTR_ERR(mcounters->hw_cntrs_hndl);
goto free;
}
hw_hndl = true;
return ERR_PTR(-ENOMEM);
err = ib_copy_from_udata(ucmd, udata, required_ucmd_sz);
- if (err) {
- kfree(ucmd);
- return ERR_PTR(err);
- }
+ if (err)
+ goto free_ucmd;
}
- if (flow_attr->priority > MLX5_IB_FLOW_LAST_PRIO)
- return ERR_PTR(-ENOMEM);
+ if (flow_attr->priority > MLX5_IB_FLOW_LAST_PRIO) {
+ err = -ENOMEM;
+ goto free_ucmd;
+ }
if (domain != IB_FLOW_DOMAIN_USER ||
flow_attr->port > dev->num_ports ||
(flow_attr->flags & ~(IB_FLOW_ATTR_FLAGS_DONT_TRAP |
- IB_FLOW_ATTR_FLAGS_EGRESS)))
- return ERR_PTR(-EINVAL);
+ IB_FLOW_ATTR_FLAGS_EGRESS))) {
+ err = -EINVAL;
+ goto free_ucmd;
+ }
if (is_egress &&
(flow_attr->type == IB_FLOW_ATTR_ALL_DEFAULT ||
- flow_attr->type == IB_FLOW_ATTR_MC_DEFAULT))
- return ERR_PTR(-EINVAL);
+ flow_attr->type == IB_FLOW_ATTR_MC_DEFAULT)) {
+ err = -EINVAL;
+ goto free_ucmd;
+ }
dst = kzalloc(sizeof(*dst), GFP_KERNEL);
- if (!dst)
- return ERR_PTR(-ENOMEM);
+ if (!dst) {
+ err = -ENOMEM;
+ goto free_ucmd;
+ }
mutex_lock(&dev->flow_db->lock);
unlock:
mutex_unlock(&dev->flow_db->lock);
kfree(dst);
+free_ucmd:
kfree(ucmd);
- kfree(handler);
return ERR_PTR(err);
}
dev->num_ports = max(MLX5_CAP_GEN(mdev, num_ports),
MLX5_CAP_GEN(mdev, num_vhca_ports));
- if (MLX5_VPORT_MANAGER(mdev) &&
+ if (MLX5_ESWITCH_MANAGER(mdev) &&
mlx5_ib_eswitch_mode(mdev->priv.eswitch) == SRIOV_OFFLOADS) {
dev->rep = mlx5_ib_vport_rep(mdev->priv.eswitch, 0);
}
if (attr_mask & (IB_QP_AV | IB_QP_PATH_MTU)) {
+ if (rdma_protocol_iwarp(&dev->ibdev, 1))
+ return -EINVAL;
+
if (attr_mask & IB_QP_PATH_MTU) {
if (attr->path_mtu < IB_MTU_256 ||
attr->path_mtu > IB_MTU_4096) {
} else {
goto exit;
}
+ if ((wqe->wr.send_flags & IB_SEND_SIGNALED) ||
+ qp->sq_sig_type == IB_SIGNAL_ALL_WR)
+ rxe_run_task(&qp->comp.task, 1);
qp->req.wqe_index = next_index(qp->sq.queue,
qp->req.wqe_index);
goto next_wqe;
if (fill_packet(qp, wqe, &pkt, skb, payload)) {
pr_debug("qp#%d Error during fill packet\n", qp_num(qp));
+ kfree_skb(skb);
goto err;
}
goto next_wqe;
err:
- kfree_skb(skb);
wqe->status = IB_WC_LOC_PROT_ERR;
wqe->state = wqe_state_error;
__rxe_do_task(&qp->comp.task);
}
static u16 opa_vnic_select_queue(struct net_device *netdev, struct sk_buff *skb,
- void *accel_priv,
+ struct net_device *sb_dev,
select_queue_fallback_t fallback)
{
struct opa_vnic_adapter *adapter = opa_vnic_priv(netdev);
mdata->entropy = opa_vnic_calc_entropy(skb);
mdata->vl = opa_vnic_get_vl(adapter, skb);
rc = adapter->rn_ops->ndo_select_queue(netdev, skb,
- accel_priv, fallback);
+ sb_dev, fallback);
skb_pull(skb, sizeof(*mdata));
return rc;
}
* inactive, or if the tool type is changed, a new tracking id is
* assigned to the slot. The tool type is only reported if the
* corresponding absbit field is set.
+ *
+ * Returns true if contact is active.
*/
-void input_mt_report_slot_state(struct input_dev *dev,
+bool input_mt_report_slot_state(struct input_dev *dev,
unsigned int tool_type, bool active)
{
struct input_mt *mt = dev->mt;
int id;
if (!mt)
- return;
+ return false;
slot = &mt->slots[mt->slot];
slot->frame = mt->frame;
if (!active) {
input_event(dev, EV_ABS, ABS_MT_TRACKING_ID, -1);
- return;
+ return false;
}
id = input_mt_get_value(slot, ABS_MT_TRACKING_ID);
- if (id < 0 || input_mt_get_value(slot, ABS_MT_TOOL_TYPE) != tool_type)
+ if (id < 0)
id = input_mt_new_trkid(mt);
input_event(dev, EV_ABS, ABS_MT_TRACKING_ID, id);
input_event(dev, EV_ABS, ABS_MT_TOOL_TYPE, tool_type);
+
+ return true;
}
EXPORT_SYMBOL(input_mt_report_slot_state);
u8 mapping;
u8 xtype;
} xpad_device[] = {
- { 0x0079, 0x18d4, "GPD Win 2 Controller", 0, XTYPE_XBOX360 },
+ { 0x0079, 0x18d4, "GPD Win 2 X-Box Controller", 0, XTYPE_XBOX360 },
{ 0x044f, 0x0f00, "Thrustmaster Wheel", 0, XTYPE_XBOX },
{ 0x044f, 0x0f03, "Thrustmaster Wheel", 0, XTYPE_XBOX },
{ 0x044f, 0x0f07, "Thrustmaster, Inc. Controller", 0, XTYPE_XBOX },
static irqreturn_t events_interrupt(int irq, void *dev_id)
{
struct event_dev *edev = dev_id;
- unsigned type, code, value;
+ unsigned int type, code, value;
type = __raw_readl(edev->addr + REG_READ);
code = __raw_readl(edev->addr + REG_READ);
}
static void events_import_bits(struct event_dev *edev,
- unsigned long bits[], unsigned type, size_t count)
+ unsigned long bits[], unsigned int type, size_t count)
{
void __iomem *addr = edev->addr;
int i, j;
for (j = 0; j < ARRAY_SIZE(val); j++) {
int offset = (i * ARRAY_SIZE(val) + j) * sizeof(u32);
+
val[j] = __raw_readl(edev->addr + REG_DATA + offset);
}
struct input_dev *input_dev;
struct event_dev *edev;
struct resource *res;
- unsigned keymapnamelen;
+ unsigned int keymapnamelen;
void __iomem *addr;
int irq;
int i;
for (i = 0; i < keymapnamelen; i++)
edev->name[i] = __raw_readb(edev->addr + REG_DATA + i);
- pr_debug("events_probe() keymap=%s\n", edev->name);
+ pr_debug("%s: keymap=%s\n", __func__, edev->name);
input_dev->name = edev->name;
input_dev->id.bustype = BUS_HOST;
To compile this driver as a module, choose M here: the
module will be called rave-sp-pwrbutton.
+config INPUT_SC27XX_VIBRA
+ tristate "Spreadtrum sc27xx vibrator support"
+ depends on MFD_SC27XX_PMIC || COMPILE_TEST
+ select INPUT_FF_MEMLESS
+ help
+ This option enables support for Spreadtrum sc27xx vibrator driver.
+
+ To compile this driver as a module, choose M here. The module will
+ be called sc27xx_vibra.
+
endif
obj-$(CONFIG_INPUT_AXP20X_PEK) += axp20x-pek.o
obj-$(CONFIG_INPUT_GPIO_ROTARY_ENCODER) += rotary_encoder.o
obj-$(CONFIG_INPUT_RK805_PWRKEY) += rk805-pwrkey.o
+obj-$(CONFIG_INPUT_SC27XX_VIBRA) += sc27xx-vibra.o
obj-$(CONFIG_INPUT_SGI_BTNS) += sgi_btns.o
obj-$(CONFIG_INPUT_SIRFSOC_ONKEY) += sirfsoc-onkey.o
obj-$(CONFIG_INPUT_SOC_BUTTON_ARRAY) += soc_button_array.o
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2018 Spreadtrum Communications Inc.
+ */
+
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/input.h>
+#include <linux/workqueue.h>
+
+#define CUR_DRV_CAL_SEL GENMASK(13, 12)
+#define SLP_LDOVIBR_PD_EN BIT(9)
+#define LDO_VIBR_PD BIT(8)
+
+struct vibra_info {
+ struct input_dev *input_dev;
+ struct work_struct play_work;
+ struct regmap *regmap;
+ u32 base;
+ u32 strength;
+ bool enabled;
+};
+
+static void sc27xx_vibra_set(struct vibra_info *info, bool on)
+{
+ if (on) {
+ regmap_update_bits(info->regmap, info->base, LDO_VIBR_PD, 0);
+ regmap_update_bits(info->regmap, info->base,
+ SLP_LDOVIBR_PD_EN, 0);
+ info->enabled = true;
+ } else {
+ regmap_update_bits(info->regmap, info->base, LDO_VIBR_PD,
+ LDO_VIBR_PD);
+ regmap_update_bits(info->regmap, info->base,
+ SLP_LDOVIBR_PD_EN, SLP_LDOVIBR_PD_EN);
+ info->enabled = false;
+ }
+}
+
+static int sc27xx_vibra_hw_init(struct vibra_info *info)
+{
+ return regmap_update_bits(info->regmap, info->base, CUR_DRV_CAL_SEL, 0);
+}
+
+static void sc27xx_vibra_play_work(struct work_struct *work)
+{
+ struct vibra_info *info = container_of(work, struct vibra_info,
+ play_work);
+
+ if (info->strength && !info->enabled)
+ sc27xx_vibra_set(info, true);
+ else if (info->strength == 0 && info->enabled)
+ sc27xx_vibra_set(info, false);
+}
+
+static int sc27xx_vibra_play(struct input_dev *input, void *data,
+ struct ff_effect *effect)
+{
+ struct vibra_info *info = input_get_drvdata(input);
+
+ info->strength = effect->u.rumble.weak_magnitude;
+ schedule_work(&info->play_work);
+
+ return 0;
+}
+
+static void sc27xx_vibra_close(struct input_dev *input)
+{
+ struct vibra_info *info = input_get_drvdata(input);
+
+ cancel_work_sync(&info->play_work);
+ if (info->enabled)
+ sc27xx_vibra_set(info, false);
+}
+
+static int sc27xx_vibra_probe(struct platform_device *pdev)
+{
+ struct vibra_info *info;
+ int error;
+
+ info = devm_kzalloc(&pdev->dev, sizeof(*info), GFP_KERNEL);
+ if (!info)
+ return -ENOMEM;
+
+ info->regmap = dev_get_regmap(pdev->dev.parent, NULL);
+ if (!info->regmap) {
+ dev_err(&pdev->dev, "failed to get vibrator regmap.\n");
+ return -ENODEV;
+ }
+
+ error = device_property_read_u32(&pdev->dev, "reg", &info->base);
+ if (error) {
+ dev_err(&pdev->dev, "failed to get vibrator base address.\n");
+ return error;
+ }
+
+ info->input_dev = devm_input_allocate_device(&pdev->dev);
+ if (!info->input_dev) {
+ dev_err(&pdev->dev, "failed to allocate input device.\n");
+ return -ENOMEM;
+ }
+
+ info->input_dev->name = "sc27xx:vibrator";
+ info->input_dev->id.version = 0;
+ info->input_dev->close = sc27xx_vibra_close;
+
+ input_set_drvdata(info->input_dev, info);
+ input_set_capability(info->input_dev, EV_FF, FF_RUMBLE);
+ INIT_WORK(&info->play_work, sc27xx_vibra_play_work);
+ info->enabled = false;
+
+ error = sc27xx_vibra_hw_init(info);
+ if (error) {
+ dev_err(&pdev->dev, "failed to initialize the vibrator.\n");
+ return error;
+ }
+
+ error = input_ff_create_memless(info->input_dev, NULL,
+ sc27xx_vibra_play);
+ if (error) {
+ dev_err(&pdev->dev, "failed to register vibrator to FF.\n");
+ return error;
+ }
+
+ error = input_register_device(info->input_dev);
+ if (error) {
+ dev_err(&pdev->dev, "failed to register input device.\n");
+ return error;
+ }
+
+ return 0;
+}
+
+static const struct of_device_id sc27xx_vibra_of_match[] = {
+ { .compatible = "sprd,sc2731-vibrator", },
+ {}
+};
+MODULE_DEVICE_TABLE(of, sc27xx_vibra_of_match);
+
+static struct platform_driver sc27xx_vibra_driver = {
+ .driver = {
+ .name = "sc27xx-vibrator",
+ .of_match_table = sc27xx_vibra_of_match,
+ },
+ .probe = sc27xx_vibra_probe,
+};
+
+module_platform_driver(sc27xx_vibra_driver);
+
+MODULE_DESCRIPTION("Spreadtrum SC27xx Vibrator Driver");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Xiaotong Lu <xiaotong.lu@spreadtrum.com>");
#define ETP_DISABLE_POWER 0x0001
#define ETP_PRESSURE_OFFSET 25
+#define ETP_CALIBRATE_MAX_LEN 3
+
/* IAP Firmware handling */
#define ETP_PRODUCT_ID_FORMAT_STRING "%d.0"
#define ETP_FW_NAME "elan_i2c_" ETP_PRODUCT_ID_FORMAT_STRING ".bin"
int tries = 20;
int retval;
int error;
- u8 val[3];
+ u8 val[ETP_CALIBRATE_MAX_LEN];
retval = mutex_lock_interruptible(&data->sysfs_mutex);
if (retval)
{ "ELAN060C", 0 },
{ "ELAN0611", 0 },
{ "ELAN0612", 0 },
+ { "ELAN0618", 0 },
{ "ELAN1000", 0 },
{ }
};
static int elan_smbus_initialize(struct i2c_client *client)
{
u8 check[ETP_SMBUS_HELLOPACKET_LEN] = { 0x55, 0x55, 0x55, 0x55, 0x55 };
- u8 values[ETP_SMBUS_HELLOPACKET_LEN] = { 0, 0, 0, 0, 0 };
+ u8 values[I2C_SMBUS_BLOCK_MAX] = {0};
int len, error;
/* Get hello packet */
static int elan_smbus_calibrate_result(struct i2c_client *client, u8 *val)
{
int error;
+ u8 buf[I2C_SMBUS_BLOCK_MAX] = {0};
+
+ BUILD_BUG_ON(ETP_CALIBRATE_MAX_LEN > sizeof(buf));
error = i2c_smbus_read_block_data(client,
- ETP_SMBUS_CALIBRATE_QUERY, val);
+ ETP_SMBUS_CALIBRATE_QUERY, buf);
if (error < 0)
return error;
+ memcpy(val, buf, ETP_CALIBRATE_MAX_LEN);
return 0;
}
{
int len;
+ BUILD_BUG_ON(I2C_SMBUS_BLOCK_MAX > ETP_SMBUS_REPORT_LEN);
+
len = i2c_smbus_read_block_data(client,
ETP_SMBUS_PACKET_QUERY,
&report[ETP_SMBUS_REPORT_OFFSET]);
else if (ic_version == 7 && etd->info.samples[1] == 0x2A)
sanity_check = ((packet[3] & 0x1c) == 0x10);
else
- sanity_check = ((packet[0] & 0x0c) == 0x04 &&
+ sanity_check = ((packet[0] & 0x08) == 0x00 &&
(packet[3] & 0x1c) == 0x10);
if (!sanity_check)
{ }
};
+static const char * const middle_button_pnp_ids[] = {
+ "LEN2131", /* ThinkPad P52 w/ NFC */
+ "LEN2132", /* ThinkPad P52 */
+ NULL
+};
+
/*
* Set the appropriate event bits for the input subsystem
*/
__clear_bit(EV_REL, dev->evbit);
__set_bit(BTN_LEFT, dev->keybit);
- if (dmi_check_system(elantech_dmi_has_middle_button))
+ if (dmi_check_system(elantech_dmi_has_middle_button) ||
+ psmouse_matches_pnp_id(psmouse, middle_button_pnp_ids))
__set_bit(BTN_MIDDLE, dev->keybit);
__set_bit(BTN_RIGHT, dev->keybit);
else
input_report_rel(dev, REL_WHEEL, -wheel);
- input_report_key(dev, BTN_SIDE, BIT(4));
- input_report_key(dev, BTN_EXTRA, BIT(5));
+ input_report_key(dev, BTN_SIDE, packet[3] & BIT(4));
+ input_report_key(dev, BTN_EXTRA, packet[3] & BIT(5));
break;
}
break;
input_report_rel(dev, REL_WHEEL, -(s8) packet[3]);
/* Extra buttons on Genius NewNet 3D */
- input_report_key(dev, BTN_SIDE, BIT(6));
- input_report_key(dev, BTN_EXTRA, BIT(7));
+ input_report_key(dev, BTN_SIDE, packet[0] & BIT(6));
+ input_report_key(dev, BTN_EXTRA, packet[0] & BIT(7));
break;
case PSMOUSE_THINKPS:
/* Extra button on ThinkingMouse */
- input_report_key(dev, BTN_EXTRA, BIT(3));
+ input_report_key(dev, BTN_EXTRA, packet[0] & BIT(3));
/*
* Without this bit of weirdness moving up gives wildly
* Cortron PS2 Trackball reports SIDE button in the
* 4th bit of the first byte.
*/
- input_report_key(dev, BTN_SIDE, BIT(3));
+ input_report_key(dev, BTN_SIDE, packet[0] & BIT(3));
packet[0] |= BIT(3);
break;
#
config RMI4_CORE
tristate "Synaptics RMI4 bus support"
+ select IRQ_DOMAIN
help
Say Y here if you want to support the Synaptics RMI4 bus. This is
required for all RMI4 device support.
if (obj->type == RMI_2D_OBJECT_NONE)
return;
- if (axis_align->swap_axes)
- swap(obj->x, obj->y);
-
if (axis_align->flip_x)
obj->x = sensor->max_x - obj->x;
if (axis_align->flip_y)
obj->y = sensor->max_y - obj->y;
+ if (axis_align->swap_axes)
+ swap(obj->x, obj->y);
+
/*
* Here checking if X offset or y offset are specified is
* redundant. We just add the offsets or clip the values.
x = min(RMI_2D_REL_POS_MAX, max(RMI_2D_REL_POS_MIN, (int)x));
y = min(RMI_2D_REL_POS_MAX, max(RMI_2D_REL_POS_MIN, (int)y));
- if (axis_align->swap_axes)
- swap(x, y);
-
if (axis_align->flip_x)
x = min(RMI_2D_REL_POS_MAX, -x);
if (axis_align->flip_y)
y = min(RMI_2D_REL_POS_MAX, -y);
+ if (axis_align->swap_axes)
+ swap(x, y);
+
if (x || y) {
input_report_rel(sensor->input, REL_X, x);
input_report_rel(sensor->input, REL_Y, y);
struct input_dev *input = sensor->input;
int res_x;
int res_y;
+ int max_x, max_y;
int input_flags = 0;
if (sensor->report_abs) {
- if (sensor->axis_align.swap_axes) {
- swap(sensor->max_x, sensor->max_y);
- swap(sensor->axis_align.clip_x_low,
- sensor->axis_align.clip_y_low);
- swap(sensor->axis_align.clip_x_high,
- sensor->axis_align.clip_y_high);
- }
-
sensor->min_x = sensor->axis_align.clip_x_low;
if (sensor->axis_align.clip_x_high)
sensor->max_x = min(sensor->max_x,
sensor->axis_align.clip_y_high);
set_bit(EV_ABS, input->evbit);
- input_set_abs_params(input, ABS_MT_POSITION_X, 0, sensor->max_x,
- 0, 0);
- input_set_abs_params(input, ABS_MT_POSITION_Y, 0, sensor->max_y,
- 0, 0);
+
+ max_x = sensor->max_x;
+ max_y = sensor->max_y;
+ if (sensor->axis_align.swap_axes)
+ swap(max_x, max_y);
+ input_set_abs_params(input, ABS_MT_POSITION_X, 0, max_x, 0, 0);
+ input_set_abs_params(input, ABS_MT_POSITION_Y, 0, max_y, 0, 0);
if (sensor->x_mm && sensor->y_mm) {
res_x = (sensor->max_x - sensor->min_x) / sensor->x_mm;
res_y = (sensor->max_y - sensor->min_y) / sensor->y_mm;
+ if (sensor->axis_align.swap_axes)
+ swap(res_x, res_y);
input_abs_set_res(input, ABS_X, res_x);
input_abs_set_res(input, ABS_Y, res_y);
#include <linux/kernel.h>
#include <linux/device.h>
+#include <linux/irq.h>
+#include <linux/irqdomain.h>
#include <linux/list.h>
#include <linux/pm.h>
#include <linux/rmi.h>
{}
#endif
+static struct irq_chip rmi_irq_chip = {
+ .name = "rmi4",
+};
+
+static int rmi_create_function_irq(struct rmi_function *fn,
+ struct rmi_function_handler *handler)
+{
+ struct rmi_driver_data *drvdata = dev_get_drvdata(&fn->rmi_dev->dev);
+ int i, error;
+
+ for (i = 0; i < fn->num_of_irqs; i++) {
+ set_bit(fn->irq_pos + i, fn->irq_mask);
+
+ fn->irq[i] = irq_create_mapping(drvdata->irqdomain,
+ fn->irq_pos + i);
+
+ irq_set_chip_data(fn->irq[i], fn);
+ irq_set_chip_and_handler(fn->irq[i], &rmi_irq_chip,
+ handle_simple_irq);
+ irq_set_nested_thread(fn->irq[i], 1);
+
+ error = devm_request_threaded_irq(&fn->dev, fn->irq[i], NULL,
+ handler->attention, IRQF_ONESHOT,
+ dev_name(&fn->dev), fn);
+ if (error) {
+ dev_err(&fn->dev, "Error %d registering IRQ\n", error);
+ return error;
+ }
+ }
+
+ return 0;
+}
+
static int rmi_function_probe(struct device *dev)
{
struct rmi_function *fn = to_rmi_function(dev);
if (handler->probe) {
error = handler->probe(fn);
- return error;
+ if (error)
+ return error;
+ }
+
+ if (fn->num_of_irqs && handler->attention) {
+ error = rmi_create_function_irq(fn, handler);
+ if (error)
+ return error;
}
return 0;
void rmi_unregister_function(struct rmi_function *fn)
{
+ int i;
+
rmi_dbg(RMI_DEBUG_CORE, &fn->dev, "Unregistering F%02X.\n",
fn->fd.function_number);
device_del(&fn->dev);
of_node_put(fn->dev.of_node);
put_device(&fn->dev);
+
+ for (i = 0; i < fn->num_of_irqs; i++)
+ irq_dispose_mapping(fn->irq[i]);
+
}
/**
struct rmi_device;
+/*
+ * The interrupt source count in the function descriptor can represent up to
+ * 6 interrupt sources in the normal manner.
+ */
+#define RMI_FN_MAX_IRQS 6
+
/**
* struct rmi_function - represents the implementation of an RMI4
* function for a particular device (basically, a driver for that RMI4 function)
* @irq_pos: The position in the irq bitfield this function holds
* @irq_mask: For convenience, can be used to mask IRQ bits off during ATTN
* interrupt handling.
+ * @irqs: assigned virq numbers (up to num_of_irqs)
*
* @node: entry in device's list of functions
*/
struct list_head node;
unsigned int num_of_irqs;
+ int irq[RMI_FN_MAX_IRQS];
unsigned int irq_pos;
unsigned long irq_mask[];
};
void (*remove)(struct rmi_function *fn);
int (*config)(struct rmi_function *fn);
int (*reset)(struct rmi_function *fn);
- int (*attention)(struct rmi_function *fn, unsigned long *irq_bits);
+ irqreturn_t (*attention)(int irq, void *ctx);
int (*suspend)(struct rmi_function *fn);
int (*resume)(struct rmi_function *fn);
};
#include <linux/pm.h>
#include <linux/slab.h>
#include <linux/of.h>
+#include <linux/irqdomain.h>
#include <uapi/linux/input.h>
#include <linux/rmi.h>
#include "rmi_bus.h"
return 0;
}
-static void process_one_interrupt(struct rmi_driver_data *data,
- struct rmi_function *fn)
-{
- struct rmi_function_handler *fh;
-
- if (!fn || !fn->dev.driver)
- return;
-
- fh = to_rmi_function_handler(fn->dev.driver);
- if (fh->attention) {
- bitmap_and(data->fn_irq_bits, data->irq_status, fn->irq_mask,
- data->irq_count);
- if (!bitmap_empty(data->fn_irq_bits, data->irq_count))
- fh->attention(fn, data->fn_irq_bits);
- }
-}
-
static int rmi_process_interrupt_requests(struct rmi_device *rmi_dev)
{
struct rmi_driver_data *data = dev_get_drvdata(&rmi_dev->dev);
struct device *dev = &rmi_dev->dev;
- struct rmi_function *entry;
+ int i;
int error;
if (!data)
*/
mutex_unlock(&data->irq_mutex);
- /*
- * It would be nice to be able to use irq_chip to handle these
- * nested IRQs. Unfortunately, most of the current customers for
- * this driver are using older kernels (3.0.x) that don't support
- * the features required for that. Once they've shifted to more
- * recent kernels (say, 3.3 and higher), this should be switched to
- * use irq_chip.
- */
- list_for_each_entry(entry, &data->function_list, node)
- process_one_interrupt(data, entry);
+ for_each_set_bit(i, data->irq_status, data->irq_count)
+ handle_nested_irq(irq_find_mapping(data->irqdomain, i));
if (data->input)
input_sync(data->input);
static int rmi_driver_remove(struct device *dev)
{
struct rmi_device *rmi_dev = to_rmi_device(dev);
+ struct rmi_driver_data *data = dev_get_drvdata(&rmi_dev->dev);
rmi_disable_irq(rmi_dev, false);
+ irq_domain_remove(data->irqdomain);
+ data->irqdomain = NULL;
+
rmi_f34_remove_sysfs(rmi_dev);
rmi_free_function_list(rmi_dev);
{
struct rmi_device *rmi_dev = data->rmi_dev;
struct device *dev = &rmi_dev->dev;
- int irq_count;
+ struct fwnode_handle *fwnode = rmi_dev->xport->dev->fwnode;
+ int irq_count = 0;
size_t size;
int retval;
* being accessed.
*/
rmi_dbg(RMI_DEBUG_CORE, dev, "%s: Counting IRQs.\n", __func__);
- irq_count = 0;
data->bootloader_mode = false;
retval = rmi_scan_pdt(rmi_dev, &irq_count, rmi_count_irqs);
if (data->bootloader_mode)
dev_warn(dev, "Device in bootloader mode.\n");
+ /* Allocate and register a linear revmap irq_domain */
+ data->irqdomain = irq_domain_create_linear(fwnode, irq_count,
+ &irq_domain_simple_ops,
+ data);
+ if (!data->irqdomain) {
+ dev_err(&rmi_dev->dev, "Failed to create IRQ domain\n");
+ return -ENOMEM;
+ }
+
data->irq_count = irq_count;
data->num_of_irq_regs = (data->irq_count + 7) / 8;
{
struct rmi_device *rmi_dev = data->rmi_dev;
struct device *dev = &rmi_dev->dev;
- int irq_count;
+ int irq_count = 0;
int retval;
- irq_count = 0;
rmi_dbg(RMI_DEBUG_CORE, dev, "%s: Creating functions.\n", __func__);
retval = rmi_scan_pdt(rmi_dev, &irq_count, rmi_create_function);
if (retval < 0) {
return 0;
}
-static int rmi_f01_attention(struct rmi_function *fn,
- unsigned long *irq_bits)
+static irqreturn_t rmi_f01_attention(int irq, void *ctx)
{
+ struct rmi_function *fn = ctx;
struct rmi_device *rmi_dev = fn->rmi_dev;
int error;
u8 device_status;
if (error) {
dev_err(&fn->dev,
"Failed to read device status: %d.\n", error);
- return error;
+ return IRQ_RETVAL(error);
}
if (RMI_F01_STATUS_BOOTLOADER(device_status))
error = rmi_dev->driver->reset_handler(rmi_dev);
if (error) {
dev_err(&fn->dev, "Device reset failed: %d\n", error);
- return error;
+ return IRQ_RETVAL(error);
}
}
- return 0;
+ return IRQ_HANDLED;
}
struct rmi_function_handler rmi_f01_handler = {
return 0;
}
-static int rmi_f03_attention(struct rmi_function *fn, unsigned long *irq_bits)
+static irqreturn_t rmi_f03_attention(int irq, void *ctx)
{
+ struct rmi_function *fn = ctx;
struct rmi_device *rmi_dev = fn->rmi_dev;
struct rmi_driver_data *drvdata = dev_get_drvdata(&rmi_dev->dev);
struct f03_data *f03 = dev_get_drvdata(&fn->dev);
/* First grab the data passed by the transport device */
if (drvdata->attn_data.size < ob_len) {
dev_warn(&fn->dev, "F03 interrupted, but data is missing!\n");
- return 0;
+ return IRQ_HANDLED;
}
memcpy(obs, drvdata->attn_data.data, ob_len);
"%s: Failed to read F03 output buffers: %d\n",
__func__, error);
serio_interrupt(f03->serio, 0, SERIO_TIMEOUT);
- return error;
+ return IRQ_RETVAL(error);
}
}
serio_interrupt(f03->serio, ob_data, serio_flags);
}
- return 0;
+ return IRQ_HANDLED;
}
static void rmi_f03_remove(struct rmi_function *fn)
}
static void rmi_f11_finger_handler(struct f11_data *f11,
- struct rmi_2d_sensor *sensor,
- unsigned long *irq_bits, int num_irq_regs,
- int size)
+ struct rmi_2d_sensor *sensor, int size)
{
const u8 *f_state = f11->data.f_state;
u8 finger_state;
int rel_fingers;
int abs_size = sensor->nbr_fingers * RMI_F11_ABS_BYTES;
- int abs_bits = bitmap_and(f11->result_bits, irq_bits, f11->abs_mask,
- num_irq_regs * 8);
- int rel_bits = bitmap_and(f11->result_bits, irq_bits, f11->rel_mask,
- num_irq_regs * 8);
-
- if (abs_bits) {
+ if (sensor->report_abs) {
if (abs_size > size)
abs_fingers = size / RMI_F11_ABS_BYTES;
else
rmi_f11_abs_pos_process(f11, sensor, &sensor->objs[i],
finger_state, i);
}
- }
- if (rel_bits) {
- if ((abs_size + sensor->nbr_fingers * RMI_F11_REL_BYTES) > size)
- rel_fingers = (size - abs_size) / RMI_F11_REL_BYTES;
- else
- rel_fingers = sensor->nbr_fingers;
-
- for (i = 0; i < rel_fingers; i++)
- rmi_f11_rel_pos_report(f11, i);
- }
-
- if (abs_bits) {
/*
* the absolute part is made in 2 parts to allow the kernel
* tracking to take place.
}
input_mt_sync_frame(sensor->input);
+ } else if (sensor->report_rel) {
+ if ((abs_size + sensor->nbr_fingers * RMI_F11_REL_BYTES) > size)
+ rel_fingers = (size - abs_size) / RMI_F11_REL_BYTES;
+ else
+ rel_fingers = sensor->nbr_fingers;
+
+ for (i = 0; i < rel_fingers; i++)
+ rmi_f11_rel_pos_report(f11, i);
}
+
}
static int f11_2d_construct_data(struct f11_data *f11)
return 0;
}
-static int rmi_f11_attention(struct rmi_function *fn, unsigned long *irq_bits)
+static irqreturn_t rmi_f11_attention(int irq, void *ctx)
{
+ struct rmi_function *fn = ctx;
struct rmi_device *rmi_dev = fn->rmi_dev;
struct rmi_driver_data *drvdata = dev_get_drvdata(&rmi_dev->dev);
struct f11_data *f11 = dev_get_drvdata(&fn->dev);
data_base_addr, f11->sensor.data_pkt,
f11->sensor.pkt_size);
if (error < 0)
- return error;
+ return IRQ_RETVAL(error);
}
- rmi_f11_finger_handler(f11, &f11->sensor, irq_bits,
- drvdata->num_of_irq_regs, valid_bytes);
+ rmi_f11_finger_handler(f11, &f11->sensor, valid_bytes);
- return 0;
+ return IRQ_HANDLED;
}
static int rmi_f11_resume(struct rmi_function *fn)
rmi_2d_sensor_abs_report(sensor, &sensor->objs[i], i);
}
-static int rmi_f12_attention(struct rmi_function *fn,
- unsigned long *irq_nr_regs)
+static irqreturn_t rmi_f12_attention(int irq, void *ctx)
{
int retval;
+ struct rmi_function *fn = ctx;
struct rmi_device *rmi_dev = fn->rmi_dev;
struct rmi_driver_data *drvdata = dev_get_drvdata(&rmi_dev->dev);
struct f12_data *f12 = dev_get_drvdata(&fn->dev);
if (retval < 0) {
dev_err(&fn->dev, "Failed to read object data. Code: %d.\n",
retval);
- return retval;
+ return IRQ_RETVAL(retval);
}
}
input_mt_sync_frame(sensor->input);
- return 0;
+ return IRQ_HANDLED;
}
static int rmi_f12_write_control_regs(struct rmi_function *fn)
}
}
-static int rmi_f30_attention(struct rmi_function *fn, unsigned long *irq_bits)
+static irqreturn_t rmi_f30_attention(int irq, void *ctx)
{
+ struct rmi_function *fn = ctx;
struct f30_data *f30 = dev_get_drvdata(&fn->dev);
struct rmi_driver_data *drvdata = dev_get_drvdata(&fn->rmi_dev->dev);
int error;
if (drvdata->attn_data.size < f30->register_count) {
dev_warn(&fn->dev,
"F30 interrupted, but data is missing\n");
- return 0;
+ return IRQ_HANDLED;
}
memcpy(f30->data_regs, drvdata->attn_data.data,
f30->register_count);
dev_err(&fn->dev,
"%s: Failed to read F30 data registers: %d\n",
__func__, error);
- return error;
+ return IRQ_RETVAL(error);
}
}
rmi_f03_commit_buttons(f30->f03);
}
- return 0;
+ return IRQ_HANDLED;
}
static int rmi_f30_config(struct rmi_function *fn)
return 0;
}
-static int rmi_f34_attention(struct rmi_function *fn, unsigned long *irq_bits)
+static irqreturn_t rmi_f34_attention(int irq, void *ctx)
{
+ struct rmi_function *fn = ctx;
struct f34_data *f34 = dev_get_drvdata(&fn->dev);
int ret;
u8 status;
complete(&f34->v7.cmd_done);
}
- return 0;
+ return IRQ_HANDLED;
}
static int rmi_f34_write_blocks(struct f34_data *f34, const void *data,
mutex_unlock(&f54->data_mutex);
}
-static int rmi_f54_attention(struct rmi_function *fn, unsigned long *irqbits)
-{
- return 0;
-}
-
static int rmi_f54_config(struct rmi_function *fn)
{
struct rmi_driver *drv = fn->rmi_dev->driver;
.func = 0x54,
.probe = rmi_f54_probe,
.config = rmi_f54_config,
- .attention = rmi_f54_attention,
.remove = rmi_f54_remove,
};
{ "GSL3692", 0 },
{ "MSSL1680", 0 },
{ "MSSL0001", 0 },
+ { "MSSL0002", 0 },
{ }
};
MODULE_DEVICE_TABLE(acpi, silead_ts_acpi_match);
fail:
irq_domain_free_irqs_parent(domain, virq, nr_irqs);
- gicv2m_unalloc_msi(v2m, hwirq, get_count_order(nr_irqs));
+ gicv2m_unalloc_msi(v2m, hwirq, nr_irqs);
return err;
}
return its->collections + its_dev->event_map.col_map[event];
}
+static struct its_collection *valid_col(struct its_collection *col)
+{
+ if (WARN_ON_ONCE(col->target_address & GENMASK_ULL(0, 15)))
+ return NULL;
+
+ return col;
+}
+
+static struct its_vpe *valid_vpe(struct its_node *its, struct its_vpe *vpe)
+{
+ if (valid_col(its->collections + vpe->col_idx))
+ return vpe;
+
+ return NULL;
+}
+
/*
* ITS command descriptors - parameters to be encoded in a command
* block.
its_fixup_cmd(cmd);
- return col;
+ return valid_col(col);
}
static struct its_collection *its_build_movi_cmd(struct its_node *its,
its_fixup_cmd(cmd);
- return col;
+ return valid_col(col);
}
static struct its_collection *its_build_discard_cmd(struct its_node *its,
its_fixup_cmd(cmd);
- return col;
+ return valid_col(col);
}
static struct its_collection *its_build_inv_cmd(struct its_node *its,
its_fixup_cmd(cmd);
- return col;
+ return valid_col(col);
}
static struct its_collection *its_build_int_cmd(struct its_node *its,
its_fixup_cmd(cmd);
- return col;
+ return valid_col(col);
}
static struct its_collection *its_build_clear_cmd(struct its_node *its,
its_fixup_cmd(cmd);
- return col;
+ return valid_col(col);
}
static struct its_collection *its_build_invall_cmd(struct its_node *its,
its_fixup_cmd(cmd);
- return desc->its_vinvall_cmd.vpe;
+ return valid_vpe(its, desc->its_vinvall_cmd.vpe);
}
static struct its_vpe *its_build_vmapp_cmd(struct its_node *its,
its_fixup_cmd(cmd);
- return desc->its_vmapp_cmd.vpe;
+ return valid_vpe(its, desc->its_vmapp_cmd.vpe);
}
static struct its_vpe *its_build_vmapti_cmd(struct its_node *its,
its_fixup_cmd(cmd);
- return desc->its_vmapti_cmd.vpe;
+ return valid_vpe(its, desc->its_vmapti_cmd.vpe);
}
static struct its_vpe *its_build_vmovi_cmd(struct its_node *its,
its_fixup_cmd(cmd);
- return desc->its_vmovi_cmd.vpe;
+ return valid_vpe(its, desc->its_vmovi_cmd.vpe);
}
static struct its_vpe *its_build_vmovp_cmd(struct its_node *its,
its_fixup_cmd(cmd);
- return desc->its_vmovp_cmd.vpe;
+ return valid_vpe(its, desc->its_vmovp_cmd.vpe);
}
static u64 its_cmd_ptr_to_offset(struct its_node *its,
static int its_alloc_collections(struct its_node *its)
{
+ int i;
+
its->collections = kcalloc(nr_cpu_ids, sizeof(*its->collections),
GFP_KERNEL);
if (!its->collections)
return -ENOMEM;
+ for (i = 0; i < nr_cpu_ids; i++)
+ its->collections[i].target_address = ~0ULL;
+
return 0;
}
cpu_mask = cpumask_of_node(its_dev->its->numa_node);
/* Bind the LPI to the first possible CPU */
- cpu = cpumask_first(cpu_mask);
+ cpu = cpumask_first_and(cpu_mask, cpu_online_mask);
+ if (cpu >= nr_cpu_ids) {
+ if (its_dev->its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_23144)
+ return -EINVAL;
+
+ cpu = cpumask_first(cpu_online_mask);
+ }
+
its_dev->event_map.col_map[event] = cpu;
irq_data_update_effective_affinity(d, cpumask_of(cpu));
u64 timeout = USEC_PER_SEC;
u64 val;
+ /*
+ * If coming via a CPU hotplug event, we don't need to disable
+ * LPIs before trying to re-enable them. They are already
+ * configured and all is well in the world. Detect this case
+ * by checking the allocation of the pending table for the
+ * current CPU.
+ */
+ if (gic_data_rdist()->pend_page)
+ return 0;
+
if (!gic_rdists_supports_plpis()) {
pr_info("CPU%d: LPIs not supported\n", smp_processor_id());
return -ENXIO;
msg->address_lo = lower_32_bits(msi_data->msiir_addr);
msg->data = data->hwirq;
- if (msi_affinity_flag)
- msg->data |= cpumask_first(data->common->affinity);
+ if (msi_affinity_flag) {
+ const struct cpumask *mask;
+
+ mask = irq_data_get_effective_affinity_mask(data);
+ msg->data |= cpumask_first(mask);
+ }
iommu_dma_map_msi_msg(data->irq, msg);
}
return -EINVAL;
}
- cpumask_copy(irq_data->common->affinity, mask);
+ irq_data_update_effective_affinity(irq_data, cpumask_of(cpu));
return IRQ_SET_MASK_OK;
}
*
*/
+#include <linux/compiler.h>
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/kernel.h>
* /proc/capi/capi20:
* minor applid nrecvctlpkt nrecvdatapkt nsendctlpkt nsenddatapkt
*/
-static int capi20_proc_show(struct seq_file *m, void *v)
+static int __maybe_unused capi20_proc_show(struct seq_file *m, void *v)
{
struct capidev *cdev;
struct list_head *l;
* /proc/capi/capi20ncci:
* applid ncci
*/
-static int capi20ncci_proc_show(struct seq_file *m, void *v)
+static int __maybe_unused capi20ncci_proc_show(struct seq_file *m, void *v)
{
struct capidev *cdev;
struct capincci *np;
*
*/
+#include <linux/compiler.h>
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/kernel.h>
* /proc/capi/capidrv:
* nrecvctlpkt nrecvdatapkt nsendctlpkt nsenddatapkt
*/
-static int capidrv_proc_show(struct seq_file *m, void *v)
+static int __maybe_unused capidrv_proc_show(struct seq_file *m, void *v)
{
seq_printf(m, "%lu %lu %lu %lu\n",
global.ap.nrecvctlpkt,
case HD_OPEN_B2CHANNEL_ACK:
++channel;
+ /* fall through */
case HD_OPEN_B1CHANNEL_ACK:
bcs = cs->bcs + channel;
update_basstate(ucs, BS_B1OPEN << channel, 0);
case HD_CLOSE_B2CHANNEL_ACK:
++channel;
+ /* fall through */
case HD_CLOSE_B1CHANNEL_ACK:
bcs = cs->bcs + channel;
update_basstate(ucs, 0, BS_B1OPEN << channel);
case HD_B2_FLOW_CONTROL:
++channel;
+ /* fall through */
case HD_B1_FLOW_CONTROL:
bcs = cs->bcs + channel;
atomic_add((l - BAS_NORMFRAME) * BAS_CORRFRAMES,
rc = -EFAULT;
goto error;
}
+ usb_fill_int_urb(urb, bcs->cs->hw.bas->udev,
+ usb_rcvisocpipe(urb->dev, 3 + 2 * bcs->channel),
+ ubc->isoinbuf + k * BAS_INBUFSIZE,
+ BAS_INBUFSIZE, read_iso_callback, bcs,
+ BAS_FRAMETIME);
- urb->dev = bcs->cs->hw.bas->udev;
- urb->pipe = usb_rcvisocpipe(urb->dev, 3 + 2 * bcs->channel);
urb->transfer_flags = URB_ISO_ASAP;
- urb->transfer_buffer = ubc->isoinbuf + k * BAS_INBUFSIZE;
- urb->transfer_buffer_length = BAS_INBUFSIZE;
urb->number_of_packets = BAS_NUMFRAMES;
- urb->interval = BAS_FRAMETIME;
- urb->complete = read_iso_callback;
- urb->context = bcs;
for (j = 0; j < BAS_NUMFRAMES; j++) {
urb->iso_frame_desc[j].offset = j * BAS_MAXFRAME;
urb->iso_frame_desc[j].length = BAS_MAXFRAME;
rc = -EFAULT;
goto error;
}
- urb->dev = bcs->cs->hw.bas->udev;
- urb->pipe = usb_sndisocpipe(urb->dev, 4 + 2 * bcs->channel);
+ usb_fill_int_urb(urb, bcs->cs->hw.bas->udev,
+ usb_sndisocpipe(urb->dev, 4 + 2 * bcs->channel),
+ ubc->isooutbuf->data,
+ sizeof(ubc->isooutbuf->data),
+ write_iso_callback, &ubc->isoouturbs[k],
+ BAS_FRAMETIME);
+
urb->transfer_flags = URB_ISO_ASAP;
- urb->transfer_buffer = ubc->isooutbuf->data;
- urb->transfer_buffer_length = sizeof(ubc->isooutbuf->data);
urb->number_of_packets = BAS_NUMFRAMES;
- urb->interval = BAS_FRAMETIME;
- urb->complete = write_iso_callback;
- urb->context = &ubc->isoouturbs[k];
for (j = 0; j < BAS_NUMFRAMES; ++j) {
urb->iso_frame_desc[j].offset = BAS_OUTBUFSIZE;
urb->iso_frame_desc[j].length = BAS_NORMFRAME;
switch (protocol) {
case -1: /* used for init */
bch->state = -1;
+ /* fall through */
case ISDN_P_NONE:
if (bch->state == ISDN_P_NONE)
break;
case (-1): /* used for init */
bch->state = -1;
bch->nr = bc;
+ /* fall through */
case (ISDN_P_NONE):
if (bch->state == ISDN_P_NONE)
return 0;
int fifon = fifo->fifonum;
int i;
int hdlc = 0;
+ unsigned long flags;
if (debug & DBG_HFC_CALL_TRACE)
printk(KERN_DEBUG "%s: %s: fifo(%i) len(%i) "
return;
}
- spin_lock(&hw->lock);
+ spin_lock_irqsave(&hw->lock, flags);
if (fifo->dch) {
rx_skb = fifo->dch->rx_skb;
maxlen = fifo->dch->maxlen;
if (fifo->bch) {
if (test_bit(FLG_RX_OFF, &fifo->bch->Flags)) {
fifo->bch->dropcnt += len;
- spin_unlock(&hw->lock);
+ spin_unlock_irqrestore(&hw->lock, flags);
return;
}
maxlen = bchannel_get_rxbuf(fifo->bch, len);
skb_trim(rx_skb, 0);
pr_warning("%s.B%d: No bufferspace for %d bytes\n",
hw->name, fifo->bch->nr, len);
- spin_unlock(&hw->lock);
+ spin_unlock_irqrestore(&hw->lock, flags);
return;
}
maxlen = fifo->bch->maxlen;
} else {
printk(KERN_DEBUG "%s: %s: No mem for rx_skb\n",
hw->name, __func__);
- spin_unlock(&hw->lock);
+ spin_unlock_irqrestore(&hw->lock, flags);
return;
}
}
"for fifo(%d) HFCUSB_D_RX\n",
hw->name, __func__, fifon);
skb_trim(rx_skb, 0);
- spin_unlock(&hw->lock);
+ spin_unlock_irqrestore(&hw->lock, flags);
return;
}
}
/* deliver transparent data to layer2 */
recv_Bchannel(fifo->bch, MISDN_ID_ANY, false);
}
- spin_unlock(&hw->lock);
+ spin_unlock_irqrestore(&hw->lock, flags);
}
static void
__u8 *buf;
static __u8 eof[8];
__u8 s0_state;
+ unsigned long flags;
fifon = fifo->fifonum;
status = urb->status;
- spin_lock(&hw->lock);
+ spin_lock_irqsave(&hw->lock, flags);
if (fifo->stop_gracefull) {
fifo->stop_gracefull = 0;
fifo->active = 0;
- spin_unlock(&hw->lock);
+ spin_unlock_irqrestore(&hw->lock, flags);
return;
}
- spin_unlock(&hw->lock);
+ spin_unlock_irqrestore(&hw->lock, flags);
/*
* ISO transfer only partially completed,
struct usb_fifo *fifo = (struct usb_fifo *) urb->context;
struct hfcsusb *hw = fifo->hw;
static __u8 eof[8];
+ unsigned long flags;
- spin_lock(&hw->lock);
+ spin_lock_irqsave(&hw->lock, flags);
if (fifo->stop_gracefull) {
fifo->stop_gracefull = 0;
fifo->active = 0;
- spin_unlock(&hw->lock);
+ spin_unlock_irqrestore(&hw->lock, flags);
return;
}
- spin_unlock(&hw->lock);
+ spin_unlock_irqrestore(&hw->lock, flags);
fifon = fifo->fifonum;
if ((!fifo->active) || (urb->status)) {
int *tx_idx;
int frame_complete, fifon, status, fillempty = 0;
__u8 threshbit, *p;
+ unsigned long flags;
- spin_lock(&hw->lock);
+ spin_lock_irqsave(&hw->lock, flags);
if (fifo->stop_gracefull) {
fifo->stop_gracefull = 0;
fifo->active = 0;
- spin_unlock(&hw->lock);
+ spin_unlock_irqrestore(&hw->lock, flags);
return;
}
} else {
printk(KERN_DEBUG "%s: %s: neither BCH nor DCH\n",
hw->name, __func__);
- spin_unlock(&hw->lock);
+ spin_unlock_irqrestore(&hw->lock, flags);
return;
}
hw->name, __func__,
symbolic(urb_errlist, status), status, fifon);
}
- spin_unlock(&hw->lock);
+ spin_unlock_irqrestore(&hw->lock, flags);
}
/*
release_card(card->sc[i]);
card->sc[i] = NULL;
}
+ /* fall through */
default:
pci_disable_device(card->pdev);
pci_set_drvdata(card->pdev, NULL);
break;
case PCTRL_CMD_FTM:
p1 = 2;
+ /* fall through */
case PCTRL_CMD_FTH:
send_mbox(ch->is, dps | ISAR_HIS_PUMPCTRL,
PCTRL_CMD_SILON, 1, &p1);
send_mbox(ch->is, dps | ISAR_HIS_PUMPCFG,
PMOD_DTMF, 1, param);
}
+ /* fall through */
case ISDN_P_B_MODEM_ASYNC:
ctrl = PMOD_DATAMODEM;
if (test_bit(FLG_ORIGIN, &ch->bch.Flags)) {
case ISDN_P_B_MODEM_ASYNC:
case ISDN_P_B_T30_FAX:
cmsb |= IOM_CTRL_RCV;
+ /* fall through */
case ISDN_P_B_L2DTMF:
if (test_bit(FLG_DTMFSEND, &ch->bch.Flags))
cmsb |= IOM_CTRL_RCV;
ich->is->name, hh->id);
ret = -EINVAL;
}
+ /* fall through */
default:
pr_info("%s: %s unknown prim(%x,%x)\n",
ich->is->name, __func__, hh->prim, hh->id);
bcs->mode = 1;
bcs->channel = bc;
bc = 0;
+ /* fall through */
case (L1_MODE_NULL):
if (bcs->mode == L1_MODE_NULL)
return;
case (PH_ACTIVATE | INDICATION):
case (PH_ACTIVATE | CONFIRM):
event = EV_LEASED;
+ /* fall through */
case (PH_DEACTIVATE | INDICATION):
case (PH_DEACTIVATE | CONFIRM):
if (test_bit(FLG_TWO_DCHAN, &chanp->cs->HW_Flags))
case PH_DEACTIVATE | REQUEST:
test_and_clear_bit(BC_FLG_BUSY, &bcs->Flag);
skb_queue_purge(&bcs->squeue);
+ /* fall through */
default:
B_L2L1(b_if, pr, arg);
break;
switch (cs->subtyp) {
case R647:
off2 = ((off2 << 8 & 0xf000) | (off2 & 0xf));
+ /* fall through */
case R685:
return (readreg(cs->hw.gazel.isac, off2));
case R753:
switch (cs->subtyp) {
case R647:
off2 = ((off2 << 8 & 0xf000) | (off2 & 0xf));
+ /* fall through */
case R685:
writereg(cs->hw.gazel.isac, off2, value);
break;
switch (cs->subtyp) {
case R647:
off2 = ((off2 << 8 & 0xf000) | (off2 & 0xf));
+ /* fall through */
case R685:
return (readreg(cs->hw.gazel.hscx[hscx], off2));
case R753:
switch (cs->subtyp) {
case R647:
off2 = ((off2 << 8 & 0xf000) | (off2 & 0xf));
+ /* fall through */
case R685:
writereg(cs->hw.gazel.hscx[hscx], off2, value);
break;
{
int k;
- urb->dev = dev;
- urb->pipe = pipe;
- urb->complete = complete;
+ usb_fill_int_urb(urb, dev, pipe, buf, packet_size * num_packets,
+ complete, context, interval);
+
urb->number_of_packets = num_packets;
- urb->transfer_buffer_length = packet_size * num_packets;
- urb->context = context;
- urb->transfer_buffer = buf;
urb->transfer_flags = URB_ISO_ASAP;
urb->actual_length = 0;
- urb->interval = interval;
for (k = 0; k < num_packets; k++) {
urb->iso_frame_desc[k].offset = packet_size * k;
urb->iso_frame_desc[k].length = packet_size;
break;
case PCTRL_CMD_FTM:
p1 = 2;
+ /* fall through */
case PCTRL_CMD_FTH:
sendmsg(cs, dps | ISAR_HIS_PUMPCTRL,
PCTRL_CMD_SILON, 1, &p1);
case PCTRL_CMD_FRM:
if (frm_extra_delay)
mdelay(frm_extra_delay);
+ /* fall through */
case PCTRL_CMD_FRH:
p1 = bcs->hw.isar.mod = bcs->hw.isar.newmod;
bcs->hw.isar.newmod = 0;
break;
case 'C':
channel = 0x08;
+ /* fall through */
case 'P':
channel |= 0x80;
teln++;
switch (0x5f & *teln) {
case 'C':
channel = 0x08;
+ /* fall through */
case 'P':
channel |= 0x80;
teln++;
{
int k;
- urb->dev = dev;
- urb->pipe = pipe;
- urb->interval = 1;
- urb->transfer_buffer = buf;
+ usb_fill_int_urb(urb, dev, pipe, buf, num_packets * packet_size,
+ complete, context, 1);
+
urb->number_of_packets = num_packets;
- urb->transfer_buffer_length = num_packets * packet_size;
- urb->actual_length = 0;
- urb->complete = complete;
- urb->context = context;
urb->transfer_flags = URB_ISO_ASAP;
for (k = 0; k < num_packets; k++) {
urb->iso_frame_desc[k].offset = packet_size * k;
case TAG_CBOOTDTA:
DecryptBuf(boot, datlen); /* we need to encrypt the buffer */
+ /* fall through */
case TAG_BOOTDTA:
if (card->debug_flags & LOG_POF_RECORD)
hysdn_addlog(card, "POF got %s len=%d offs=0x%lx",
case TAG_CABSDATA:
DecryptBuf(boot, datlen); /* we need to encrypt the buffer */
+ /* fall through */
case TAG_ABSDATA:
if (card->debug_flags & LOG_POF_RECORD)
hysdn_addlog(card, "POF got %s len=%d offs=0x%lx",
cmd.parm.cmsg.para[3] = 4; /* 16 bit 0x0004 Suspend */
cmd.parm.cmsg.para[4] = 0;
cmd.parm.cmsg.para[5] = l;
- strncpy(&cmd.parm.cmsg.para[6], id, l);
+ memcpy(&cmd.parm.cmsg.para[6], id, l);
cmd.command = CAPI_PUT_MESSAGE;
cmd.driver = info->isdn_driver;
cmd.arg = info->isdn_channel;
cmd.parm.cmsg.para[3] = 5; /* 16 bit 0x0005 Resume */
cmd.parm.cmsg.para[4] = 0;
cmd.parm.cmsg.para[5] = l;
- strncpy(&cmd.parm.cmsg.para[6], id, l);
+ memcpy(&cmd.parm.cmsg.para[6], id, l);
cmd.command = CAPI_PUT_MESSAGE;
info->dialing = 1;
// strcpy(dev->num[i], n);
printk(KERN_WARNING "isdn_v110 (EncodeMatrix): buffer full!\n");
return line;
}
+ /* else: fall through */
case 128:
m[line] = 128; /* leftmost -> set byte to 1000000 */
mbit = 64; /* current bit in the matrix line */
switch (++line % 10) {
case 1:
m[line++] = 0xfe;
+ /* fall through */
case 2:
m[line++] = 0xfe;
+ /* fall through */
case 3:
m[line++] = 0xfe;
+ /* fall through */
case 4:
m[line++] = 0xfe;
+ /* fall through */
case 5:
m[line++] = 0xbf;
+ /* fall through */
case 6:
m[line++] = 0xfe;
+ /* fall through */
case 7:
m[line++] = 0xfe;
+ /* fall through */
case 8:
m[line++] = 0xfe;
+ /* fall through */
case 9:
m[line++] = 0xfe;
}
.getname = data_sock_getname,
.sendmsg = mISDN_sock_sendmsg,
.recvmsg = mISDN_sock_recvmsg,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.setsockopt = data_sock_setsockopt,
rq.protocol = ISDN_P_NT_S0;
if (dev->Dprotocols & (1 << ISDN_P_NT_E1))
rq.protocol = ISDN_P_NT_E1;
+ /* fall through */
case ISDN_P_LAPD_TE:
ch->recv = mISDN_queue_message;
ch->peer = &dev->D.st->own;
menuconfig NVM
bool "Open-Channel SSD target support"
- depends on BLOCK && HAS_DMA && PCI
+ depends on BLOCK && PCI
select BLK_DEV_NVME
help
Say Y here to get to enable Open-channel SSDs.
}
/* Return md raid10 algorithm for @name */
-static const int raid10_name_to_format(const char *name)
+static int raid10_name_to_format(const char *name)
{
if (!strcasecmp(name, "near"))
return ALGORITHM_RAID10_NEAR;
static int device_supports_dax(struct dm_target *ti, struct dm_dev *dev,
sector_t start, sector_t len, void *data)
{
- struct request_queue *q = bdev_get_queue(dev->bdev);
-
- return q && blk_queue_dax(q);
+ return bdev_dax_supported(dev->bdev, PAGE_SIZE);
}
static bool dm_table_supports_dax(struct dm_table *t)
if (dm_table_supports_dax(t))
blk_queue_flag_set(QUEUE_FLAG_DAX, q);
+ else
+ blk_queue_flag_clear(QUEUE_FLAG_DAX, q);
+
if (dm_table_supports_dax_write_cache(t))
dax_write_cache(t->md->dax_dev, true);
static int __commit_transaction(struct dm_pool_metadata *pmd)
{
int r;
- size_t metadata_len, data_len;
struct thin_disk_superblock *disk_super;
struct dm_block *sblock;
if (r < 0)
return r;
- r = dm_sm_root_size(pmd->metadata_sm, &metadata_len);
- if (r < 0)
- return r;
-
- r = dm_sm_root_size(pmd->data_sm, &data_len);
- if (r < 0)
- return r;
-
r = save_sm_roots(pmd);
if (r < 0)
return r;
static void set_pool_mode(struct pool *pool, enum pool_mode new_mode);
+static void requeue_bios(struct pool *pool);
+
static void check_for_space(struct pool *pool)
{
int r;
if (r)
return;
- if (nr_free)
+ if (nr_free) {
set_pool_mode(pool, PM_WRITE);
+ requeue_bios(pool);
+ }
}
/*
r = dm_pool_alloc_data_block(pool->pmd, result);
if (r) {
- metadata_operation_failed(pool, "dm_pool_alloc_data_block", r);
+ if (r == -ENOSPC)
+ set_pool_mode(pool, PM_OUT_OF_DATA_SPACE);
+ else
+ metadata_operation_failed(pool, "dm_pool_alloc_data_block", r);
return r;
}
if (da != p) {
long i;
wc->memory_map = NULL;
- pages = kvmalloc(p * sizeof(struct page *), GFP_KERNEL);
+ pages = kvmalloc_array(p, sizeof(struct page *), GFP_KERNEL);
if (!pages) {
r = -ENOMEM;
goto err2;
if (wc->entries)
return 0;
- wc->entries = vmalloc(sizeof(struct wc_entry) * wc->n_blocks);
+ wc->entries = vmalloc(array_size(sizeof(struct wc_entry), wc->n_blocks));
if (!wc->entries)
return -ENOMEM;
for (b = 0; b < wc->n_blocks; b++) {
wb->bio.bi_iter.bi_sector = read_original_sector(wc, e);
wb->page_offset = PAGE_SIZE;
if (max_pages <= WB_LIST_INLINE ||
- unlikely(!(wb->wc_list = kmalloc(max_pages * sizeof(struct wc_entry *),
- GFP_NOIO | __GFP_NORETRY |
- __GFP_NOMEMALLOC | __GFP_NOWARN)))) {
+ unlikely(!(wb->wc_list = kmalloc_array(max_pages, sizeof(struct wc_entry *),
+ GFP_NOIO | __GFP_NORETRY |
+ __GFP_NOMEMALLOC | __GFP_NOWARN)))) {
wb->wc_list = wb->wc_list_inline;
max_pages = WB_LIST_INLINE;
}
/* Chunk BIO work */
mutex_init(&dmz->chunk_lock);
- INIT_RADIX_TREE(&dmz->chunk_rxtree, GFP_KERNEL);
+ INIT_RADIX_TREE(&dmz->chunk_rxtree, GFP_NOIO);
dmz->chunk_wq = alloc_workqueue("dmz_cwq_%s", WQ_MEM_RECLAIM | WQ_UNBOUND,
0, dev->name);
if (!dmz->chunk_wq) {
if (len < 1)
goto out;
nr_pages = min(len, nr_pages);
- if (ti->type->direct_access)
- ret = ti->type->direct_access(ti, pgoff, nr_pages, kaddr, pfn);
+ ret = ti->type->direct_access(ti, pgoff, nr_pages, kaddr, pfn);
out:
dm_put_live_table(md, srcu_idx);
* the usage of io->orig_bio in dm_remap_zone_report()
* won't be affected by this reassignment.
*/
- struct bio *b = bio_clone_bioset(bio, GFP_NOIO,
- &md->queue->bio_split);
+ struct bio *b = bio_split(bio, bio_sectors(bio) - ci.sector_count,
+ GFP_NOIO, &md->queue->bio_split);
ci.io->orig_bio = b;
- bio_advance(bio, (bio_sectors(bio) - ci.sector_count) << 9);
bio_chain(b, bio);
ret = generic_make_request(bio);
break;
else
pr_warn("md: personality for level %s is not loaded!\n",
mddev->clevel);
- return -EINVAL;
+ err = -EINVAL;
+ goto abort;
}
spin_unlock(&pers_lock);
if (mddev->level != pers->level) {
pers->start_reshape == NULL) {
/* This personality cannot handle reshaping... */
module_put(pers->owner);
- return -EINVAL;
+ err = -EINVAL;
+ goto abort;
}
if (pers->sync_request) {
mddev->private = NULL;
module_put(pers->owner);
bitmap_destroy(mddev);
- return err;
+ goto abort;
}
if (mddev->queue) {
bool nonrot = true;
disk->rdev->saved_raid_disk < 0)
conf->fullsync = 1;
}
+
+ if (disk->replacement &&
+ !test_bit(In_sync, &disk->replacement->flags) &&
+ disk->replacement->saved_raid_disk < 0) {
+ conf->fullsync = 1;
+ }
+
disk->recovery_disabled = mddev->recovery_disabled - 1;
}
bpf_prog_array_free(rcdev->raw->progs);
}
-int lirc_prog_attach(const union bpf_attr *attr)
+int lirc_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog)
{
- struct bpf_prog *prog;
struct rc_dev *rcdev;
int ret;
if (attr->attach_flags)
return -EINVAL;
- prog = bpf_prog_get_type(attr->attach_bpf_fd,
- BPF_PROG_TYPE_LIRC_MODE2);
- if (IS_ERR(prog))
- return PTR_ERR(prog);
-
rcdev = rc_dev_get_from_fd(attr->target_fd);
- if (IS_ERR(rcdev)) {
- bpf_prog_put(prog);
+ if (IS_ERR(rcdev))
return PTR_ERR(rcdev);
- }
ret = lirc_bpf_attach(rcdev, prog);
- if (ret)
- bpf_prog_put(prog);
put_device(&rcdev->dev);
struct ppb_lock {
struct flchip *chip;
- loff_t offset;
+ unsigned long adr;
int locked;
};
unsigned long timeo;
int ret;
+ adr += chip->start;
mutex_lock(&chip->mutex);
- ret = get_chip(map, chip, adr + chip->start, FL_LOCKING);
+ ret = get_chip(map, chip, adr, FL_LOCKING);
if (ret) {
mutex_unlock(&chip->mutex);
return ret;
if (thunk == DO_XXLOCK_ONEBLOCK_LOCK) {
chip->state = FL_LOCKING;
- map_write(map, CMD(0xA0), chip->start + adr);
- map_write(map, CMD(0x00), chip->start + adr);
+ map_write(map, CMD(0xA0), adr);
+ map_write(map, CMD(0x00), adr);
} else if (thunk == DO_XXLOCK_ONEBLOCK_UNLOCK) {
/*
* Unlocking of one specific sector is not supported, so we
map_write(map, CMD(0x00), chip->start);
chip->state = FL_READY;
- put_chip(map, chip, adr + chip->start);
+ put_chip(map, chip, adr);
mutex_unlock(&chip->mutex);
return ret;
* sectors shall be unlocked, so lets keep their locking
* status at "unlocked" (locked=0) for the final re-locking.
*/
- if ((adr < ofs) || (adr >= (ofs + len))) {
+ if ((offset < ofs) || (offset >= (ofs + len))) {
sect[sectors].chip = &cfi->chips[chipnum];
- sect[sectors].offset = offset;
+ sect[sectors].adr = adr;
sect[sectors].locked = do_ppb_xxlock(
map, &cfi->chips[chipnum], adr, 0,
DO_XXLOCK_ONEBLOCK_GETLOCK);
i++;
if (adr >> cfi->chipshift) {
+ if (offset >= (ofs + len))
+ break;
adr = 0;
chipnum++;
*/
for (i = 0; i < sectors; i++) {
if (sect[i].locked)
- do_ppb_xxlock(map, sect[i].chip, sect[i].offset, 0,
+ do_ppb_xxlock(map, sect[i].chip, sect[i].adr, 0,
DO_XXLOCK_ONEBLOCK_LOCK);
}
{ "AT45DB642x", 0x1f2800, 8192, 1056, 11, SUP_POW2PS},
{ "at45db642d", 0x1f2800, 8192, 1024, 10, SUP_POW2PS | IS_POW2PS},
- { "AT45DB641E", 0x1f28000100, 32768, 264, 9, SUP_EXTID | SUP_POW2PS},
- { "at45db641e", 0x1f28000100, 32768, 256, 8, SUP_EXTID | SUP_POW2PS | IS_POW2PS},
+ { "AT45DB641E", 0x1f28000100ULL, 32768, 264, 9, SUP_EXTID | SUP_POW2PS},
+ { "at45db641e", 0x1f28000100ULL, 32768, 256, 8, SUP_EXTID | SUP_POW2PS | IS_POW2PS},
};
static struct flash_info *jedec_lookup(struct spi_device *spi,
if (ret)
return ret;
- denali->clk_x_rate = clk_get_rate(dt->clk);
+ /*
+ * Hardcode the clock rate for the backward compatibility.
+ * This works for both SOCFPGA and UniPhier.
+ */
+ denali->clk_x_rate = 200000000;
ret = denali_init(denali);
if (ret)
#define NFC_V1_V2_CONFIG (host->regs + 0x0a)
#define NFC_V1_V2_ECC_STATUS_RESULT (host->regs + 0x0c)
#define NFC_V1_V2_RSLTMAIN_AREA (host->regs + 0x0e)
-#define NFC_V1_V2_RSLTSPARE_AREA (host->regs + 0x10)
+#define NFC_V21_RSLTSPARE_AREA (host->regs + 0x10)
#define NFC_V1_V2_WRPROT (host->regs + 0x12)
#define NFC_V1_UNLOCKSTART_BLKADDR (host->regs + 0x14)
#define NFC_V1_UNLOCKEND_BLKADDR (host->regs + 0x16)
writew(config1, NFC_V1_V2_CONFIG1);
/* preset operation */
+ /* spare area size in 16-bit half-words */
+ writew(mtd->oobsize / 2, NFC_V21_RSLTSPARE_AREA);
+
/* Unlock the internal RAM Buffer */
writew(0x2, NFC_V1_V2_CONFIG);
for (; page < page_end; page++) {
res = chip->ecc.read_oob(mtd, chip, page);
- if (res)
+ if (res < 0)
return res;
bad = chip->oob_poi[chip->badblockpos];
#include <linux/mtd/rawnand.h>
+/*
+ * Macronix AC series does not support using SET/GET_FEATURES to change
+ * the timings unlike what is declared in the parameter page. Unflag
+ * this feature to avoid unnecessary downturns.
+ */
+static void macronix_nand_fix_broken_get_timings(struct nand_chip *chip)
+{
+ unsigned int i;
+ static const char * const broken_get_timings[] = {
+ "MX30LF1G18AC",
+ "MX30LF1G28AC",
+ "MX30LF2G18AC",
+ "MX30LF2G28AC",
+ "MX30LF4G18AC",
+ "MX30LF4G28AC",
+ "MX60LF8G18AC",
+ };
+
+ if (!chip->parameters.supports_set_get_features)
+ return;
+
+ for (i = 0; i < ARRAY_SIZE(broken_get_timings); i++) {
+ if (!strcmp(broken_get_timings[i], chip->parameters.model))
+ break;
+ }
+
+ if (i == ARRAY_SIZE(broken_get_timings))
+ return;
+
+ bitmap_clear(chip->parameters.get_feature_list,
+ ONFI_FEATURE_ADDR_TIMING_MODE, 1);
+ bitmap_clear(chip->parameters.set_feature_list,
+ ONFI_FEATURE_ADDR_TIMING_MODE, 1);
+}
+
static int macronix_nand_init(struct nand_chip *chip)
{
if (nand_is_slc(chip))
chip->bbt_options |= NAND_BBT_SCAN2NDPAGE;
- /*
- * MX30LF2G18AC chip does not support using SET/GET_FEATURES to change
- * the timings unlike what is declared in the parameter page. Unflag
- * this feature to avoid unnecessary downturns.
- */
- if (chip->parameters.supports_set_get_features &&
- !strcmp("MX30LF2G18AC", chip->parameters.model)) {
- bitmap_clear(chip->parameters.get_feature_list,
- ONFI_FEATURE_ADDR_TIMING_MODE, 1);
- bitmap_clear(chip->parameters.set_feature_list,
- ONFI_FEATURE_ADDR_TIMING_MODE, 1);
- }
+ macronix_nand_fix_broken_get_timings(chip);
return 0;
}
if (p->supports_set_get_features) {
set_bit(ONFI_FEATURE_ADDR_READ_RETRY, p->set_feature_list);
+ set_bit(ONFI_FEATURE_ON_DIE_ECC, p->set_feature_list);
set_bit(ONFI_FEATURE_ADDR_READ_RETRY, p->get_feature_list);
+ set_bit(ONFI_FEATURE_ON_DIE_ECC, p->get_feature_list);
}
return 0;
static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb,
- void *accel_priv, select_queue_fallback_t fallback)
+ struct net_device *sb_dev,
+ select_queue_fallback_t fallback)
{
/* This helper function exists to help dev_pick_tx get the correct
* destination queue. Using a helper function skips a call to
This enables support for the Qualcomm Atheros QCA8K Ethernet
switch chips.
+config NET_DSA_REALTEK_SMI
+ tristate "Realtek SMI Ethernet switch family support"
+ depends on NET_DSA
+ select FIXED_PHY
+ select IRQ_DOMAIN
+ select REALTEK_PHY
+ select REGMAP
+ ---help---
+ This enables support for the Realtek SMI-based switch
+ chips, currently only RTL8366RB.
+
config NET_DSA_SMSC_LAN9303
tristate
select NET_DSA_TAG_LAN9303
Enable access functions if the SMSC/Microchip LAN9303 is configured
for MDIO managed mode.
+config NET_DSA_VITESSE_VSC73XX
+ tristate "Vitesse VSC7385/7388/7395/7398 support"
+ depends on OF && SPI
+ depends on NET_DSA
+ select FIXED_PHY
+ select VITESSE_PHY
+ select GPIOLIB
+ ---help---
+ This enables support for the Vitesse VSC7385, VSC7388,
+ VSC7395 and VSC7398 SparX integrated ethernet switches.
+
endmenu
obj-$(CONFIG_NET_DSA_MT7530) += mt7530.o
obj-$(CONFIG_NET_DSA_MV88E6060) += mv88e6060.o
obj-$(CONFIG_NET_DSA_QCA8K) += qca8k.o
+obj-$(CONFIG_NET_DSA_REALTEK_SMI) += realtek.o
+realtek-objs := realtek-smi.o rtl8366.o rtl8366rb.o
obj-$(CONFIG_NET_DSA_SMSC_LAN9303) += lan9303-core.o
obj-$(CONFIG_NET_DSA_SMSC_LAN9303_I2C) += lan9303_i2c.o
obj-$(CONFIG_NET_DSA_SMSC_LAN9303_MDIO) += lan9303_mdio.o
+obj-$(CONFIG_NET_DSA_VITESSE_VSC73XX) += vitesse-vsc73xx.o
obj-y += b53/
obj-y += microchip/
obj-y += mv88e6xxx/
struct phy_device *phy)
{
struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
- u32 off, reg;
+ u32 reg;
if (priv->wol_ports_mask & (1 << port))
return;
if (priv->int_phy_mask & 1 << port && priv->hw_params.num_gphy == 1)
bcm_sf2_gphy_enable_set(ds, false);
- if (dsa_is_cpu_port(ds, port))
- off = CORE_IMP_CTL;
- else
- off = CORE_G_PCTL_PORT(port);
-
b53_disable_port(ds, port, phy);
/* Power down the port memory */
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0+
+/* Realtek Simple Management Interface (SMI) driver
+ * It can be discussed how "simple" this interface is.
+ *
+ * The SMI protocol piggy-backs the MDIO MDC and MDIO signals levels
+ * but the protocol is not MDIO at all. Instead it is a Realtek
+ * pecularity that need to bit-bang the lines in a special way to
+ * communicate with the switch.
+ *
+ * ASICs we intend to support with this driver:
+ *
+ * RTL8366 - The original version, apparently
+ * RTL8369 - Similar enough to have the same datsheet as RTL8366
+ * RTL8366RB - Probably reads out "RTL8366 revision B", has a quite
+ * different register layout from the other two
+ * RTL8366S - Is this "RTL8366 super"?
+ * RTL8367 - Has an OpenWRT driver as well
+ * RTL8368S - Seems to be an alternative name for RTL8366RB
+ * RTL8370 - Also uses SMI
+ *
+ * Copyright (C) 2017 Linus Walleij <linus.walleij@linaro.org>
+ * Copyright (C) 2010 Antti Seppälä <a.seppala@gmail.com>
+ * Copyright (C) 2010 Roman Yeryomin <roman@advem.lv>
+ * Copyright (C) 2011 Colin Leitner <colin.leitner@googlemail.com>
+ * Copyright (C) 2009-2010 Gabor Juhos <juhosg@openwrt.org>
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/spinlock.h>
+#include <linux/skbuff.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_mdio.h>
+#include <linux/delay.h>
+#include <linux/gpio/consumer.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/bitops.h>
+#include <linux/if_bridge.h>
+
+#include "realtek-smi.h"
+
+#define REALTEK_SMI_ACK_RETRY_COUNT 5
+#define REALTEK_SMI_HW_STOP_DELAY 25 /* msecs */
+#define REALTEK_SMI_HW_START_DELAY 100 /* msecs */
+
+static inline void realtek_smi_clk_delay(struct realtek_smi *smi)
+{
+ ndelay(smi->clk_delay);
+}
+
+static void realtek_smi_start(struct realtek_smi *smi)
+{
+ /* Set GPIO pins to output mode, with initial state:
+ * SCK = 0, SDA = 1
+ */
+ gpiod_direction_output(smi->mdc, 0);
+ gpiod_direction_output(smi->mdio, 1);
+ realtek_smi_clk_delay(smi);
+
+ /* CLK 1: 0 -> 1, 1 -> 0 */
+ gpiod_set_value(smi->mdc, 1);
+ realtek_smi_clk_delay(smi);
+ gpiod_set_value(smi->mdc, 0);
+ realtek_smi_clk_delay(smi);
+
+ /* CLK 2: */
+ gpiod_set_value(smi->mdc, 1);
+ realtek_smi_clk_delay(smi);
+ gpiod_set_value(smi->mdio, 0);
+ realtek_smi_clk_delay(smi);
+ gpiod_set_value(smi->mdc, 0);
+ realtek_smi_clk_delay(smi);
+ gpiod_set_value(smi->mdio, 1);
+}
+
+static void realtek_smi_stop(struct realtek_smi *smi)
+{
+ realtek_smi_clk_delay(smi);
+ gpiod_set_value(smi->mdio, 0);
+ gpiod_set_value(smi->mdc, 1);
+ realtek_smi_clk_delay(smi);
+ gpiod_set_value(smi->mdio, 1);
+ realtek_smi_clk_delay(smi);
+ gpiod_set_value(smi->mdc, 1);
+ realtek_smi_clk_delay(smi);
+ gpiod_set_value(smi->mdc, 0);
+ realtek_smi_clk_delay(smi);
+ gpiod_set_value(smi->mdc, 1);
+
+ /* Add a click */
+ realtek_smi_clk_delay(smi);
+ gpiod_set_value(smi->mdc, 0);
+ realtek_smi_clk_delay(smi);
+ gpiod_set_value(smi->mdc, 1);
+
+ /* Set GPIO pins to input mode */
+ gpiod_direction_input(smi->mdio);
+ gpiod_direction_input(smi->mdc);
+}
+
+static void realtek_smi_write_bits(struct realtek_smi *smi, u32 data, u32 len)
+{
+ for (; len > 0; len--) {
+ realtek_smi_clk_delay(smi);
+
+ /* Prepare data */
+ gpiod_set_value(smi->mdio, !!(data & (1 << (len - 1))));
+ realtek_smi_clk_delay(smi);
+
+ /* Clocking */
+ gpiod_set_value(smi->mdc, 1);
+ realtek_smi_clk_delay(smi);
+ gpiod_set_value(smi->mdc, 0);
+ }
+}
+
+static void realtek_smi_read_bits(struct realtek_smi *smi, u32 len, u32 *data)
+{
+ gpiod_direction_input(smi->mdio);
+
+ for (*data = 0; len > 0; len--) {
+ u32 u;
+
+ realtek_smi_clk_delay(smi);
+
+ /* Clocking */
+ gpiod_set_value(smi->mdc, 1);
+ realtek_smi_clk_delay(smi);
+ u = !!gpiod_get_value(smi->mdio);
+ gpiod_set_value(smi->mdc, 0);
+
+ *data |= (u << (len - 1));
+ }
+
+ gpiod_direction_output(smi->mdio, 0);
+}
+
+static int realtek_smi_wait_for_ack(struct realtek_smi *smi)
+{
+ int retry_cnt;
+
+ retry_cnt = 0;
+ do {
+ u32 ack;
+
+ realtek_smi_read_bits(smi, 1, &ack);
+ if (ack == 0)
+ break;
+
+ if (++retry_cnt > REALTEK_SMI_ACK_RETRY_COUNT) {
+ dev_err(smi->dev, "ACK timeout\n");
+ return -ETIMEDOUT;
+ }
+ } while (1);
+
+ return 0;
+}
+
+static int realtek_smi_write_byte(struct realtek_smi *smi, u8 data)
+{
+ realtek_smi_write_bits(smi, data, 8);
+ return realtek_smi_wait_for_ack(smi);
+}
+
+static int realtek_smi_write_byte_noack(struct realtek_smi *smi, u8 data)
+{
+ realtek_smi_write_bits(smi, data, 8);
+ return 0;
+}
+
+static int realtek_smi_read_byte0(struct realtek_smi *smi, u8 *data)
+{
+ u32 t;
+
+ /* Read data */
+ realtek_smi_read_bits(smi, 8, &t);
+ *data = (t & 0xff);
+
+ /* Send an ACK */
+ realtek_smi_write_bits(smi, 0x00, 1);
+
+ return 0;
+}
+
+static int realtek_smi_read_byte1(struct realtek_smi *smi, u8 *data)
+{
+ u32 t;
+
+ /* Read data */
+ realtek_smi_read_bits(smi, 8, &t);
+ *data = (t & 0xff);
+
+ /* Send an ACK */
+ realtek_smi_write_bits(smi, 0x01, 1);
+
+ return 0;
+}
+
+static int realtek_smi_read_reg(struct realtek_smi *smi, u32 addr, u32 *data)
+{
+ unsigned long flags;
+ u8 lo = 0;
+ u8 hi = 0;
+ int ret;
+
+ spin_lock_irqsave(&smi->lock, flags);
+
+ realtek_smi_start(smi);
+
+ /* Send READ command */
+ ret = realtek_smi_write_byte(smi, smi->cmd_read);
+ if (ret)
+ goto out;
+
+ /* Set ADDR[7:0] */
+ ret = realtek_smi_write_byte(smi, addr & 0xff);
+ if (ret)
+ goto out;
+
+ /* Set ADDR[15:8] */
+ ret = realtek_smi_write_byte(smi, addr >> 8);
+ if (ret)
+ goto out;
+
+ /* Read DATA[7:0] */
+ realtek_smi_read_byte0(smi, &lo);
+ /* Read DATA[15:8] */
+ realtek_smi_read_byte1(smi, &hi);
+
+ *data = ((u32)lo) | (((u32)hi) << 8);
+
+ ret = 0;
+
+ out:
+ realtek_smi_stop(smi);
+ spin_unlock_irqrestore(&smi->lock, flags);
+
+ return ret;
+}
+
+static int realtek_smi_write_reg(struct realtek_smi *smi,
+ u32 addr, u32 data, bool ack)
+{
+ unsigned long flags;
+ int ret;
+
+ spin_lock_irqsave(&smi->lock, flags);
+
+ realtek_smi_start(smi);
+
+ /* Send WRITE command */
+ ret = realtek_smi_write_byte(smi, smi->cmd_write);
+ if (ret)
+ goto out;
+
+ /* Set ADDR[7:0] */
+ ret = realtek_smi_write_byte(smi, addr & 0xff);
+ if (ret)
+ goto out;
+
+ /* Set ADDR[15:8] */
+ ret = realtek_smi_write_byte(smi, addr >> 8);
+ if (ret)
+ goto out;
+
+ /* Write DATA[7:0] */
+ ret = realtek_smi_write_byte(smi, data & 0xff);
+ if (ret)
+ goto out;
+
+ /* Write DATA[15:8] */
+ if (ack)
+ ret = realtek_smi_write_byte(smi, data >> 8);
+ else
+ ret = realtek_smi_write_byte_noack(smi, data >> 8);
+ if (ret)
+ goto out;
+
+ ret = 0;
+
+ out:
+ realtek_smi_stop(smi);
+ spin_unlock_irqrestore(&smi->lock, flags);
+
+ return ret;
+}
+
+/* There is one single case when we need to use this accessor and that
+ * is when issueing soft reset. Since the device reset as soon as we write
+ * that bit, no ACK will come back for natural reasons.
+ */
+int realtek_smi_write_reg_noack(struct realtek_smi *smi, u32 addr,
+ u32 data)
+{
+ return realtek_smi_write_reg(smi, addr, data, false);
+}
+EXPORT_SYMBOL_GPL(realtek_smi_write_reg_noack);
+
+/* Regmap accessors */
+
+static int realtek_smi_write(void *ctx, u32 reg, u32 val)
+{
+ struct realtek_smi *smi = ctx;
+
+ return realtek_smi_write_reg(smi, reg, val, true);
+}
+
+static int realtek_smi_read(void *ctx, u32 reg, u32 *val)
+{
+ struct realtek_smi *smi = ctx;
+
+ return realtek_smi_read_reg(smi, reg, val);
+}
+
+static const struct regmap_config realtek_smi_mdio_regmap_config = {
+ .reg_bits = 10, /* A4..A0 R4..R0 */
+ .val_bits = 16,
+ .reg_stride = 1,
+ /* PHY regs are at 0x8000 */
+ .max_register = 0xffff,
+ .reg_format_endian = REGMAP_ENDIAN_BIG,
+ .reg_read = realtek_smi_read,
+ .reg_write = realtek_smi_write,
+ .cache_type = REGCACHE_NONE,
+};
+
+static int realtek_smi_mdio_read(struct mii_bus *bus, int addr, int regnum)
+{
+ struct realtek_smi *smi = bus->priv;
+
+ return smi->ops->phy_read(smi, addr, regnum);
+}
+
+static int realtek_smi_mdio_write(struct mii_bus *bus, int addr, int regnum,
+ u16 val)
+{
+ struct realtek_smi *smi = bus->priv;
+
+ return smi->ops->phy_write(smi, addr, regnum, val);
+}
+
+int realtek_smi_setup_mdio(struct realtek_smi *smi)
+{
+ struct device_node *mdio_np;
+ int ret;
+
+ mdio_np = of_find_compatible_node(smi->dev->of_node, NULL,
+ "realtek,smi-mdio");
+ if (!mdio_np) {
+ dev_err(smi->dev, "no MDIO bus node\n");
+ return -ENODEV;
+ }
+
+ smi->slave_mii_bus = devm_mdiobus_alloc(smi->dev);
+ if (!smi->slave_mii_bus)
+ return -ENOMEM;
+ smi->slave_mii_bus->priv = smi;
+ smi->slave_mii_bus->name = "SMI slave MII";
+ smi->slave_mii_bus->read = realtek_smi_mdio_read;
+ smi->slave_mii_bus->write = realtek_smi_mdio_write;
+ snprintf(smi->slave_mii_bus->id, MII_BUS_ID_SIZE, "SMI-%d",
+ smi->ds->index);
+ smi->slave_mii_bus->dev.of_node = mdio_np;
+ smi->slave_mii_bus->parent = smi->dev;
+ smi->ds->slave_mii_bus = smi->slave_mii_bus;
+
+ ret = of_mdiobus_register(smi->slave_mii_bus, mdio_np);
+ if (ret) {
+ dev_err(smi->dev, "unable to register MDIO bus %s\n",
+ smi->slave_mii_bus->id);
+ of_node_put(mdio_np);
+ }
+
+ return 0;
+}
+
+static int realtek_smi_probe(struct platform_device *pdev)
+{
+ const struct realtek_smi_variant *var;
+ struct device *dev = &pdev->dev;
+ struct realtek_smi *smi;
+ struct device_node *np;
+ int ret;
+
+ var = of_device_get_match_data(dev);
+ np = dev->of_node;
+
+ smi = devm_kzalloc(dev, sizeof(*smi), GFP_KERNEL);
+ if (!smi)
+ return -ENOMEM;
+ smi->map = devm_regmap_init(dev, NULL, smi,
+ &realtek_smi_mdio_regmap_config);
+ if (IS_ERR(smi->map)) {
+ ret = PTR_ERR(smi->map);
+ dev_err(dev, "regmap init failed: %d\n", ret);
+ return ret;
+ }
+
+ /* Link forward and backward */
+ smi->dev = dev;
+ smi->clk_delay = var->clk_delay;
+ smi->cmd_read = var->cmd_read;
+ smi->cmd_write = var->cmd_write;
+ smi->ops = var->ops;
+
+ dev_set_drvdata(dev, smi);
+ spin_lock_init(&smi->lock);
+
+ /* TODO: if power is software controlled, set up any regulators here */
+
+ /* Assert then deassert RESET */
+ smi->reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH);
+ if (IS_ERR(smi->reset)) {
+ dev_err(dev, "failed to get RESET GPIO\n");
+ return PTR_ERR(smi->reset);
+ }
+ msleep(REALTEK_SMI_HW_STOP_DELAY);
+ gpiod_set_value(smi->reset, 0);
+ msleep(REALTEK_SMI_HW_START_DELAY);
+ dev_info(dev, "deasserted RESET\n");
+
+ /* Fetch MDIO pins */
+ smi->mdc = devm_gpiod_get_optional(dev, "mdc", GPIOD_OUT_LOW);
+ if (IS_ERR(smi->mdc))
+ return PTR_ERR(smi->mdc);
+ smi->mdio = devm_gpiod_get_optional(dev, "mdio", GPIOD_OUT_LOW);
+ if (IS_ERR(smi->mdio))
+ return PTR_ERR(smi->mdio);
+
+ smi->leds_disabled = of_property_read_bool(np, "realtek,disable-leds");
+
+ ret = smi->ops->detect(smi);
+ if (ret) {
+ dev_err(dev, "unable to detect switch\n");
+ return ret;
+ }
+
+ smi->ds = dsa_switch_alloc(dev, smi->num_ports);
+ if (!smi->ds)
+ return -ENOMEM;
+ smi->ds->priv = smi;
+
+ smi->ds->ops = var->ds_ops;
+ ret = dsa_register_switch(smi->ds);
+ if (ret) {
+ dev_err(dev, "unable to register switch ret = %d\n", ret);
+ return ret;
+ }
+ return 0;
+}
+
+static int realtek_smi_remove(struct platform_device *pdev)
+{
+ struct realtek_smi *smi = dev_get_drvdata(&pdev->dev);
+
+ dsa_unregister_switch(smi->ds);
+ gpiod_set_value(smi->reset, 1);
+
+ return 0;
+}
+
+static const struct of_device_id realtek_smi_of_match[] = {
+ {
+ .compatible = "realtek,rtl8366rb",
+ .data = &rtl8366rb_variant,
+ },
+ {
+ /* FIXME: add support for RTL8366S and more */
+ .compatible = "realtek,rtl8366s",
+ .data = NULL,
+ },
+ { /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, realtek_smi_of_match);
+
+static struct platform_driver realtek_smi_driver = {
+ .driver = {
+ .name = "realtek-smi",
+ .of_match_table = of_match_ptr(realtek_smi_of_match),
+ },
+ .probe = realtek_smi_probe,
+ .remove = realtek_smi_remove,
+};
+module_platform_driver(realtek_smi_driver);
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0+ */
+/* Realtek SMI interface driver defines
+ *
+ * Copyright (C) 2017 Linus Walleij <linus.walleij@linaro.org>
+ * Copyright (C) 2009-2010 Gabor Juhos <juhosg@openwrt.org>
+ */
+
+#ifndef _REALTEK_SMI_H
+#define _REALTEK_SMI_H
+
+#include <linux/phy.h>
+#include <linux/platform_device.h>
+#include <linux/gpio/consumer.h>
+#include <net/dsa.h>
+
+struct realtek_smi_ops;
+struct dentry;
+struct inode;
+struct file;
+
+struct rtl8366_mib_counter {
+ unsigned int base;
+ unsigned int offset;
+ unsigned int length;
+ const char *name;
+};
+
+struct rtl8366_vlan_mc {
+ u16 vid;
+ u16 untag;
+ u16 member;
+ u8 fid;
+ u8 priority;
+};
+
+struct rtl8366_vlan_4k {
+ u16 vid;
+ u16 untag;
+ u16 member;
+ u8 fid;
+};
+
+struct realtek_smi {
+ struct device *dev;
+ struct gpio_desc *reset;
+ struct gpio_desc *mdc;
+ struct gpio_desc *mdio;
+ struct regmap *map;
+ struct mii_bus *slave_mii_bus;
+
+ unsigned int clk_delay;
+ u8 cmd_read;
+ u8 cmd_write;
+ spinlock_t lock; /* Locks around command writes */
+ struct dsa_switch *ds;
+ struct irq_domain *irqdomain;
+ bool leds_disabled;
+
+ unsigned int cpu_port;
+ unsigned int num_ports;
+ unsigned int num_vlan_mc;
+ unsigned int num_mib_counters;
+ struct rtl8366_mib_counter *mib_counters;
+
+ const struct realtek_smi_ops *ops;
+
+ int vlan_enabled;
+ int vlan4k_enabled;
+
+ char buf[4096];
+};
+
+/**
+ * struct realtek_smi_ops - vtable for the per-SMI-chiptype operations
+ * @detect: detects the chiptype
+ */
+struct realtek_smi_ops {
+ int (*detect)(struct realtek_smi *smi);
+ int (*reset_chip)(struct realtek_smi *smi);
+ int (*setup)(struct realtek_smi *smi);
+ void (*cleanup)(struct realtek_smi *smi);
+ int (*get_mib_counter)(struct realtek_smi *smi,
+ int port,
+ struct rtl8366_mib_counter *mib,
+ u64 *mibvalue);
+ int (*get_vlan_mc)(struct realtek_smi *smi, u32 index,
+ struct rtl8366_vlan_mc *vlanmc);
+ int (*set_vlan_mc)(struct realtek_smi *smi, u32 index,
+ const struct rtl8366_vlan_mc *vlanmc);
+ int (*get_vlan_4k)(struct realtek_smi *smi, u32 vid,
+ struct rtl8366_vlan_4k *vlan4k);
+ int (*set_vlan_4k)(struct realtek_smi *smi,
+ const struct rtl8366_vlan_4k *vlan4k);
+ int (*get_mc_index)(struct realtek_smi *smi, int port, int *val);
+ int (*set_mc_index)(struct realtek_smi *smi, int port, int index);
+ bool (*is_vlan_valid)(struct realtek_smi *smi, unsigned int vlan);
+ int (*enable_vlan)(struct realtek_smi *smi, bool enable);
+ int (*enable_vlan4k)(struct realtek_smi *smi, bool enable);
+ int (*enable_port)(struct realtek_smi *smi, int port, bool enable);
+ int (*phy_read)(struct realtek_smi *smi, int phy, int regnum);
+ int (*phy_write)(struct realtek_smi *smi, int phy, int regnum,
+ u16 val);
+};
+
+struct realtek_smi_variant {
+ const struct dsa_switch_ops *ds_ops;
+ const struct realtek_smi_ops *ops;
+ unsigned int clk_delay;
+ u8 cmd_read;
+ u8 cmd_write;
+};
+
+/* SMI core calls */
+int realtek_smi_write_reg_noack(struct realtek_smi *smi, u32 addr,
+ u32 data);
+int realtek_smi_setup_mdio(struct realtek_smi *smi);
+
+/* RTL8366 library helpers */
+int rtl8366_mc_is_used(struct realtek_smi *smi, int mc_index, int *used);
+int rtl8366_set_vlan(struct realtek_smi *smi, int vid, u32 member,
+ u32 untag, u32 fid);
+int rtl8366_get_pvid(struct realtek_smi *smi, int port, int *val);
+int rtl8366_set_pvid(struct realtek_smi *smi, unsigned int port,
+ unsigned int vid);
+int rtl8366_enable_vlan4k(struct realtek_smi *smi, bool enable);
+int rtl8366_enable_vlan(struct realtek_smi *smi, bool enable);
+int rtl8366_reset_vlan(struct realtek_smi *smi);
+int rtl8366_init_vlan(struct realtek_smi *smi);
+int rtl8366_vlan_filtering(struct dsa_switch *ds, int port,
+ bool vlan_filtering);
+int rtl8366_vlan_prepare(struct dsa_switch *ds, int port,
+ const struct switchdev_obj_port_vlan *vlan);
+void rtl8366_vlan_add(struct dsa_switch *ds, int port,
+ const struct switchdev_obj_port_vlan *vlan);
+int rtl8366_vlan_del(struct dsa_switch *ds, int port,
+ const struct switchdev_obj_port_vlan *vlan);
+void rtl8366_get_strings(struct dsa_switch *ds, int port, u32 stringset,
+ uint8_t *data);
+int rtl8366_get_sset_count(struct dsa_switch *ds, int port, int sset);
+void rtl8366_get_ethtool_stats(struct dsa_switch *ds, int port, uint64_t *data);
+
+extern const struct realtek_smi_variant rtl8366rb_variant;
+
+#endif /* _REALTEK_SMI_H */
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Realtek SMI library helpers for the RTL8366x variants
+ * RTL8366RB and RTL8366S
+ *
+ * Copyright (C) 2017 Linus Walleij <linus.walleij@linaro.org>
+ * Copyright (C) 2009-2010 Gabor Juhos <juhosg@openwrt.org>
+ * Copyright (C) 2010 Antti Seppälä <a.seppala@gmail.com>
+ * Copyright (C) 2010 Roman Yeryomin <roman@advem.lv>
+ * Copyright (C) 2011 Colin Leitner <colin.leitner@googlemail.com>
+ */
+#include <linux/if_bridge.h>
+#include <net/dsa.h>
+
+#include "realtek-smi.h"
+
+int rtl8366_mc_is_used(struct realtek_smi *smi, int mc_index, int *used)
+{
+ int ret;
+ int i;
+
+ *used = 0;
+ for (i = 0; i < smi->num_ports; i++) {
+ int index = 0;
+
+ ret = smi->ops->get_mc_index(smi, i, &index);
+ if (ret)
+ return ret;
+
+ if (mc_index == index) {
+ *used = 1;
+ break;
+ }
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(rtl8366_mc_is_used);
+
+int rtl8366_set_vlan(struct realtek_smi *smi, int vid, u32 member,
+ u32 untag, u32 fid)
+{
+ struct rtl8366_vlan_4k vlan4k;
+ int ret;
+ int i;
+
+ /* Update the 4K table */
+ ret = smi->ops->get_vlan_4k(smi, vid, &vlan4k);
+ if (ret)
+ return ret;
+
+ vlan4k.member = member;
+ vlan4k.untag = untag;
+ vlan4k.fid = fid;
+ ret = smi->ops->set_vlan_4k(smi, &vlan4k);
+ if (ret)
+ return ret;
+
+ /* Try to find an existing MC entry for this VID */
+ for (i = 0; i < smi->num_vlan_mc; i++) {
+ struct rtl8366_vlan_mc vlanmc;
+
+ ret = smi->ops->get_vlan_mc(smi, i, &vlanmc);
+ if (ret)
+ return ret;
+
+ if (vid == vlanmc.vid) {
+ /* update the MC entry */
+ vlanmc.member = member;
+ vlanmc.untag = untag;
+ vlanmc.fid = fid;
+
+ ret = smi->ops->set_vlan_mc(smi, i, &vlanmc);
+ break;
+ }
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(rtl8366_set_vlan);
+
+int rtl8366_get_pvid(struct realtek_smi *smi, int port, int *val)
+{
+ struct rtl8366_vlan_mc vlanmc;
+ int ret;
+ int index;
+
+ ret = smi->ops->get_mc_index(smi, port, &index);
+ if (ret)
+ return ret;
+
+ ret = smi->ops->get_vlan_mc(smi, index, &vlanmc);
+ if (ret)
+ return ret;
+
+ *val = vlanmc.vid;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(rtl8366_get_pvid);
+
+int rtl8366_set_pvid(struct realtek_smi *smi, unsigned int port,
+ unsigned int vid)
+{
+ struct rtl8366_vlan_mc vlanmc;
+ struct rtl8366_vlan_4k vlan4k;
+ int ret;
+ int i;
+
+ /* Try to find an existing MC entry for this VID */
+ for (i = 0; i < smi->num_vlan_mc; i++) {
+ ret = smi->ops->get_vlan_mc(smi, i, &vlanmc);
+ if (ret)
+ return ret;
+
+ if (vid == vlanmc.vid) {
+ ret = smi->ops->set_vlan_mc(smi, i, &vlanmc);
+ if (ret)
+ return ret;
+
+ ret = smi->ops->set_mc_index(smi, port, i);
+ return ret;
+ }
+ }
+
+ /* We have no MC entry for this VID, try to find an empty one */
+ for (i = 0; i < smi->num_vlan_mc; i++) {
+ ret = smi->ops->get_vlan_mc(smi, i, &vlanmc);
+ if (ret)
+ return ret;
+
+ if (vlanmc.vid == 0 && vlanmc.member == 0) {
+ /* Update the entry from the 4K table */
+ ret = smi->ops->get_vlan_4k(smi, vid, &vlan4k);
+ if (ret)
+ return ret;
+
+ vlanmc.vid = vid;
+ vlanmc.member = vlan4k.member;
+ vlanmc.untag = vlan4k.untag;
+ vlanmc.fid = vlan4k.fid;
+ ret = smi->ops->set_vlan_mc(smi, i, &vlanmc);
+ if (ret)
+ return ret;
+
+ ret = smi->ops->set_mc_index(smi, port, i);
+ return ret;
+ }
+ }
+
+ /* MC table is full, try to find an unused entry and replace it */
+ for (i = 0; i < smi->num_vlan_mc; i++) {
+ int used;
+
+ ret = rtl8366_mc_is_used(smi, i, &used);
+ if (ret)
+ return ret;
+
+ if (!used) {
+ /* Update the entry from the 4K table */
+ ret = smi->ops->get_vlan_4k(smi, vid, &vlan4k);
+ if (ret)
+ return ret;
+
+ vlanmc.vid = vid;
+ vlanmc.member = vlan4k.member;
+ vlanmc.untag = vlan4k.untag;
+ vlanmc.fid = vlan4k.fid;
+ ret = smi->ops->set_vlan_mc(smi, i, &vlanmc);
+ if (ret)
+ return ret;
+
+ ret = smi->ops->set_mc_index(smi, port, i);
+ return ret;
+ }
+ }
+
+ dev_err(smi->dev,
+ "all VLAN member configurations are in use\n");
+
+ return -ENOSPC;
+}
+EXPORT_SYMBOL_GPL(rtl8366_set_pvid);
+
+int rtl8366_enable_vlan4k(struct realtek_smi *smi, bool enable)
+{
+ int ret;
+
+ /* To enable 4k VLAN, ordinary VLAN must be enabled first,
+ * but if we disable 4k VLAN it is fine to leave ordinary
+ * VLAN enabled.
+ */
+ if (enable) {
+ /* Make sure VLAN is ON */
+ ret = smi->ops->enable_vlan(smi, true);
+ if (ret)
+ return ret;
+
+ smi->vlan_enabled = true;
+ }
+
+ ret = smi->ops->enable_vlan4k(smi, enable);
+ if (ret)
+ return ret;
+
+ smi->vlan4k_enabled = enable;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(rtl8366_enable_vlan4k);
+
+int rtl8366_enable_vlan(struct realtek_smi *smi, bool enable)
+{
+ int ret;
+
+ ret = smi->ops->enable_vlan(smi, enable);
+ if (ret)
+ return ret;
+
+ smi->vlan_enabled = enable;
+
+ /* If we turn VLAN off, make sure that we turn off
+ * 4k VLAN as well, if that happened to be on.
+ */
+ if (!enable) {
+ smi->vlan4k_enabled = false;
+ ret = smi->ops->enable_vlan4k(smi, false);
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(rtl8366_enable_vlan);
+
+int rtl8366_reset_vlan(struct realtek_smi *smi)
+{
+ struct rtl8366_vlan_mc vlanmc;
+ int ret;
+ int i;
+
+ rtl8366_enable_vlan(smi, false);
+ rtl8366_enable_vlan4k(smi, false);
+
+ /* Clear the 16 VLAN member configurations */
+ vlanmc.vid = 0;
+ vlanmc.priority = 0;
+ vlanmc.member = 0;
+ vlanmc.untag = 0;
+ vlanmc.fid = 0;
+ for (i = 0; i < smi->num_vlan_mc; i++) {
+ ret = smi->ops->set_vlan_mc(smi, i, &vlanmc);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(rtl8366_reset_vlan);
+
+int rtl8366_init_vlan(struct realtek_smi *smi)
+{
+ int port;
+ int ret;
+
+ ret = rtl8366_reset_vlan(smi);
+ if (ret)
+ return ret;
+
+ /* Loop over the available ports, for each port, associate
+ * it with the VLAN (port+1)
+ */
+ for (port = 0; port < smi->num_ports; port++) {
+ u32 mask;
+
+ if (port == smi->cpu_port)
+ /* For the CPU port, make all ports members of this
+ * VLAN.
+ */
+ mask = GENMASK(smi->num_ports - 1, 0);
+ else
+ /* For all other ports, enable itself plus the
+ * CPU port.
+ */
+ mask = BIT(port) | BIT(smi->cpu_port);
+
+ /* For each port, set the port as member of VLAN (port+1)
+ * and untagged, except for the CPU port: the CPU port (5) is
+ * member of VLAN 6 and so are ALL the other ports as well.
+ * Use filter 0 (no filter).
+ */
+ dev_info(smi->dev, "VLAN%d port mask for port %d, %08x\n",
+ (port + 1), port, mask);
+ ret = rtl8366_set_vlan(smi, (port + 1), mask, mask, 0);
+ if (ret)
+ return ret;
+
+ dev_info(smi->dev, "VLAN%d port %d, PVID set to %d\n",
+ (port + 1), port, (port + 1));
+ ret = rtl8366_set_pvid(smi, port, (port + 1));
+ if (ret)
+ return ret;
+ }
+
+ return rtl8366_enable_vlan(smi, true);
+}
+EXPORT_SYMBOL_GPL(rtl8366_init_vlan);
+
+int rtl8366_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering)
+{
+ struct realtek_smi *smi = ds->priv;
+ struct rtl8366_vlan_4k vlan4k;
+ int ret;
+
+ if (!smi->ops->is_vlan_valid(smi, port))
+ return -EINVAL;
+
+ dev_info(smi->dev, "%s filtering on port %d\n",
+ vlan_filtering ? "enable" : "disable",
+ port);
+
+ /* TODO:
+ * The hardware support filter ID (FID) 0..7, I have no clue how to
+ * support this in the driver when the callback only says on/off.
+ */
+ ret = smi->ops->get_vlan_4k(smi, port, &vlan4k);
+ if (ret)
+ return ret;
+
+ /* Just set the filter to FID 1 for now then */
+ ret = rtl8366_set_vlan(smi, port,
+ vlan4k.member,
+ vlan4k.untag,
+ 1);
+ if (ret)
+ return ret;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(rtl8366_vlan_filtering);
+
+int rtl8366_vlan_prepare(struct dsa_switch *ds, int port,
+ const struct switchdev_obj_port_vlan *vlan)
+{
+ struct realtek_smi *smi = ds->priv;
+ int ret;
+
+ if (!smi->ops->is_vlan_valid(smi, port))
+ return -EINVAL;
+
+ dev_info(smi->dev, "prepare VLANs %04x..%04x\n",
+ vlan->vid_begin, vlan->vid_end);
+
+ /* Enable VLAN in the hardware
+ * FIXME: what's with this 4k business?
+ * Just rtl8366_enable_vlan() seems inconclusive.
+ */
+ ret = rtl8366_enable_vlan4k(smi, true);
+ if (ret)
+ return ret;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(rtl8366_vlan_prepare);
+
+void rtl8366_vlan_add(struct dsa_switch *ds, int port,
+ const struct switchdev_obj_port_vlan *vlan)
+{
+ bool untagged = !!(vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED);
+ bool pvid = !!(vlan->flags & BRIDGE_VLAN_INFO_PVID);
+ struct realtek_smi *smi = ds->priv;
+ u32 member = 0;
+ u32 untag = 0;
+ u16 vid;
+ int ret;
+
+ if (!smi->ops->is_vlan_valid(smi, port))
+ return;
+
+ dev_info(smi->dev, "add VLAN on port %d, %s, %s\n",
+ port,
+ untagged ? "untagged" : "tagged",
+ pvid ? " PVID" : "no PVID");
+
+ if (dsa_is_dsa_port(ds, port) || dsa_is_cpu_port(ds, port))
+ dev_err(smi->dev, "port is DSA or CPU port\n");
+
+ for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) {
+ int pvid_val = 0;
+
+ dev_info(smi->dev, "add VLAN %04x\n", vid);
+ member |= BIT(port);
+
+ if (untagged)
+ untag |= BIT(port);
+
+ /* To ensure that we have a valid MC entry for this VLAN,
+ * initialize the port VLAN ID here.
+ */
+ ret = rtl8366_get_pvid(smi, port, &pvid_val);
+ if (ret < 0) {
+ dev_err(smi->dev, "could not lookup PVID for port %d\n",
+ port);
+ return;
+ }
+ if (pvid_val == 0) {
+ ret = rtl8366_set_pvid(smi, port, vid);
+ if (ret < 0)
+ return;
+ }
+ }
+
+ ret = rtl8366_set_vlan(smi, port, member, untag, 0);
+ if (ret)
+ dev_err(smi->dev,
+ "failed to set up VLAN %04x",
+ vid);
+}
+EXPORT_SYMBOL_GPL(rtl8366_vlan_add);
+
+int rtl8366_vlan_del(struct dsa_switch *ds, int port,
+ const struct switchdev_obj_port_vlan *vlan)
+{
+ struct realtek_smi *smi = ds->priv;
+ u16 vid;
+ int ret;
+
+ dev_info(smi->dev, "del VLAN on port %d\n", port);
+
+ for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) {
+ int i;
+
+ dev_info(smi->dev, "del VLAN %04x\n", vid);
+
+ for (i = 0; i < smi->num_vlan_mc; i++) {
+ struct rtl8366_vlan_mc vlanmc;
+
+ ret = smi->ops->get_vlan_mc(smi, i, &vlanmc);
+ if (ret)
+ return ret;
+
+ if (vid == vlanmc.vid) {
+ /* clear VLAN member configurations */
+ vlanmc.vid = 0;
+ vlanmc.priority = 0;
+ vlanmc.member = 0;
+ vlanmc.untag = 0;
+ vlanmc.fid = 0;
+
+ ret = smi->ops->set_vlan_mc(smi, i, &vlanmc);
+ if (ret) {
+ dev_err(smi->dev,
+ "failed to remove VLAN %04x\n",
+ vid);
+ return ret;
+ }
+ break;
+ }
+ }
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(rtl8366_vlan_del);
+
+void rtl8366_get_strings(struct dsa_switch *ds, int port, u32 stringset,
+ uint8_t *data)
+{
+ struct realtek_smi *smi = ds->priv;
+ struct rtl8366_mib_counter *mib;
+ int i;
+
+ if (port >= smi->num_ports)
+ return;
+
+ for (i = 0; i < smi->num_mib_counters; i++) {
+ mib = &smi->mib_counters[i];
+ strncpy(data + i * ETH_GSTRING_LEN,
+ mib->name, ETH_GSTRING_LEN);
+ }
+}
+EXPORT_SYMBOL_GPL(rtl8366_get_strings);
+
+int rtl8366_get_sset_count(struct dsa_switch *ds, int port, int sset)
+{
+ struct realtek_smi *smi = ds->priv;
+
+ /* We only support SS_STATS */
+ if (sset != ETH_SS_STATS)
+ return 0;
+ if (port >= smi->num_ports)
+ return -EINVAL;
+
+ return smi->num_mib_counters;
+}
+EXPORT_SYMBOL_GPL(rtl8366_get_sset_count);
+
+void rtl8366_get_ethtool_stats(struct dsa_switch *ds, int port, uint64_t *data)
+{
+ struct realtek_smi *smi = ds->priv;
+ int i;
+ int ret;
+
+ if (port >= smi->num_ports)
+ return;
+
+ for (i = 0; i < smi->num_mib_counters; i++) {
+ struct rtl8366_mib_counter *mib;
+ u64 mibvalue = 0;
+
+ mib = &smi->mib_counters[i];
+ ret = smi->ops->get_mib_counter(smi, port, mib, &mibvalue);
+ if (ret) {
+ dev_err(smi->dev, "error reading MIB counter %s\n",
+ mib->name);
+ }
+ data[i] = mibvalue;
+ }
+}
+EXPORT_SYMBOL_GPL(rtl8366_get_ethtool_stats);
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Realtek SMI subdriver for the Realtek RTL8366RB ethernet switch
+ *
+ * This is a sparsely documented chip, the only viable documentation seems
+ * to be a patched up code drop from the vendor that appear in various
+ * GPL source trees.
+ *
+ * Copyright (C) 2017 Linus Walleij <linus.walleij@linaro.org>
+ * Copyright (C) 2009-2010 Gabor Juhos <juhosg@openwrt.org>
+ * Copyright (C) 2010 Antti Seppälä <a.seppala@gmail.com>
+ * Copyright (C) 2010 Roman Yeryomin <roman@advem.lv>
+ * Copyright (C) 2011 Colin Leitner <colin.leitner@googlemail.com>
+ */
+
+#include <linux/bitops.h>
+#include <linux/etherdevice.h>
+#include <linux/interrupt.h>
+#include <linux/irqdomain.h>
+#include <linux/irqchip/chained_irq.h>
+#include <linux/of_irq.h>
+#include <linux/regmap.h>
+
+#include "realtek-smi.h"
+
+#define RTL8366RB_PORT_NUM_CPU 5
+#define RTL8366RB_NUM_PORTS 6
+#define RTL8366RB_PHY_NO_MAX 4
+#define RTL8366RB_PHY_ADDR_MAX 31
+
+/* Switch Global Configuration register */
+#define RTL8366RB_SGCR 0x0000
+#define RTL8366RB_SGCR_EN_BC_STORM_CTRL BIT(0)
+#define RTL8366RB_SGCR_MAX_LENGTH(a) ((a) << 4)
+#define RTL8366RB_SGCR_MAX_LENGTH_MASK RTL8366RB_SGCR_MAX_LENGTH(0x3)
+#define RTL8366RB_SGCR_MAX_LENGTH_1522 RTL8366RB_SGCR_MAX_LENGTH(0x0)
+#define RTL8366RB_SGCR_MAX_LENGTH_1536 RTL8366RB_SGCR_MAX_LENGTH(0x1)
+#define RTL8366RB_SGCR_MAX_LENGTH_1552 RTL8366RB_SGCR_MAX_LENGTH(0x2)
+#define RTL8366RB_SGCR_MAX_LENGTH_9216 RTL8366RB_SGCR_MAX_LENGTH(0x3)
+#define RTL8366RB_SGCR_EN_VLAN BIT(13)
+#define RTL8366RB_SGCR_EN_VLAN_4KTB BIT(14)
+
+/* Port Enable Control register */
+#define RTL8366RB_PECR 0x0001
+
+/* Switch Security Control registers */
+#define RTL8366RB_SSCR0 0x0002
+#define RTL8366RB_SSCR1 0x0003
+#define RTL8366RB_SSCR2 0x0004
+#define RTL8366RB_SSCR2_DROP_UNKNOWN_DA BIT(0)
+
+/* Port Mirror Control Register */
+#define RTL8366RB_PMCR 0x0007
+#define RTL8366RB_PMCR_SOURCE_PORT(a) (a)
+#define RTL8366RB_PMCR_SOURCE_PORT_MASK 0x000f
+#define RTL8366RB_PMCR_MONITOR_PORT(a) ((a) << 4)
+#define RTL8366RB_PMCR_MONITOR_PORT_MASK 0x00f0
+#define RTL8366RB_PMCR_MIRROR_RX BIT(8)
+#define RTL8366RB_PMCR_MIRROR_TX BIT(9)
+#define RTL8366RB_PMCR_MIRROR_SPC BIT(10)
+#define RTL8366RB_PMCR_MIRROR_ISO BIT(11)
+
+/* bits 0..7 = port 0, bits 8..15 = port 1 */
+#define RTL8366RB_PAACR0 0x0010
+/* bits 0..7 = port 2, bits 8..15 = port 3 */
+#define RTL8366RB_PAACR1 0x0011
+/* bits 0..7 = port 4, bits 8..15 = port 5 */
+#define RTL8366RB_PAACR2 0x0012
+#define RTL8366RB_PAACR_SPEED_10M 0
+#define RTL8366RB_PAACR_SPEED_100M 1
+#define RTL8366RB_PAACR_SPEED_1000M 2
+#define RTL8366RB_PAACR_FULL_DUPLEX BIT(2)
+#define RTL8366RB_PAACR_LINK_UP BIT(4)
+#define RTL8366RB_PAACR_TX_PAUSE BIT(5)
+#define RTL8366RB_PAACR_RX_PAUSE BIT(6)
+#define RTL8366RB_PAACR_AN BIT(7)
+
+#define RTL8366RB_PAACR_CPU_PORT (RTL8366RB_PAACR_SPEED_1000M | \
+ RTL8366RB_PAACR_FULL_DUPLEX | \
+ RTL8366RB_PAACR_LINK_UP | \
+ RTL8366RB_PAACR_TX_PAUSE | \
+ RTL8366RB_PAACR_RX_PAUSE)
+
+/* bits 0..7 = port 0, bits 8..15 = port 1 */
+#define RTL8366RB_PSTAT0 0x0014
+/* bits 0..7 = port 2, bits 8..15 = port 3 */
+#define RTL8366RB_PSTAT1 0x0015
+/* bits 0..7 = port 4, bits 8..15 = port 5 */
+#define RTL8366RB_PSTAT2 0x0016
+
+#define RTL8366RB_POWER_SAVING_REG 0x0021
+
+/* CPU port control reg */
+#define RTL8368RB_CPU_CTRL_REG 0x0061
+#define RTL8368RB_CPU_PORTS_MSK 0x00FF
+/* Enables inserting custom tag length/type 0x8899 */
+#define RTL8368RB_CPU_INSTAG BIT(15)
+
+#define RTL8366RB_SMAR0 0x0070 /* bits 0..15 */
+#define RTL8366RB_SMAR1 0x0071 /* bits 16..31 */
+#define RTL8366RB_SMAR2 0x0072 /* bits 32..47 */
+
+#define RTL8366RB_RESET_CTRL_REG 0x0100
+#define RTL8366RB_CHIP_CTRL_RESET_HW BIT(0)
+#define RTL8366RB_CHIP_CTRL_RESET_SW BIT(1)
+
+#define RTL8366RB_CHIP_ID_REG 0x0509
+#define RTL8366RB_CHIP_ID_8366 0x5937
+#define RTL8366RB_CHIP_VERSION_CTRL_REG 0x050A
+#define RTL8366RB_CHIP_VERSION_MASK 0xf
+
+/* PHY registers control */
+#define RTL8366RB_PHY_ACCESS_CTRL_REG 0x8000
+#define RTL8366RB_PHY_CTRL_READ BIT(0)
+#define RTL8366RB_PHY_CTRL_WRITE 0
+#define RTL8366RB_PHY_ACCESS_BUSY_REG 0x8001
+#define RTL8366RB_PHY_INT_BUSY BIT(0)
+#define RTL8366RB_PHY_EXT_BUSY BIT(4)
+#define RTL8366RB_PHY_ACCESS_DATA_REG 0x8002
+#define RTL8366RB_PHY_EXT_CTRL_REG 0x8010
+#define RTL8366RB_PHY_EXT_WRDATA_REG 0x8011
+#define RTL8366RB_PHY_EXT_RDDATA_REG 0x8012
+
+#define RTL8366RB_PHY_REG_MASK 0x1f
+#define RTL8366RB_PHY_PAGE_OFFSET 5
+#define RTL8366RB_PHY_PAGE_MASK (0xf << 5)
+#define RTL8366RB_PHY_NO_OFFSET 9
+#define RTL8366RB_PHY_NO_MASK (0x1f << 9)
+
+#define RTL8366RB_VLAN_INGRESS_CTRL2_REG 0x037f
+
+/* LED control registers */
+#define RTL8366RB_LED_BLINKRATE_REG 0x0430
+#define RTL8366RB_LED_BLINKRATE_MASK 0x0007
+#define RTL8366RB_LED_BLINKRATE_28MS 0x0000
+#define RTL8366RB_LED_BLINKRATE_56MS 0x0001
+#define RTL8366RB_LED_BLINKRATE_84MS 0x0002
+#define RTL8366RB_LED_BLINKRATE_111MS 0x0003
+#define RTL8366RB_LED_BLINKRATE_222MS 0x0004
+#define RTL8366RB_LED_BLINKRATE_446MS 0x0005
+
+#define RTL8366RB_LED_CTRL_REG 0x0431
+#define RTL8366RB_LED_OFF 0x0
+#define RTL8366RB_LED_DUP_COL 0x1
+#define RTL8366RB_LED_LINK_ACT 0x2
+#define RTL8366RB_LED_SPD1000 0x3
+#define RTL8366RB_LED_SPD100 0x4
+#define RTL8366RB_LED_SPD10 0x5
+#define RTL8366RB_LED_SPD1000_ACT 0x6
+#define RTL8366RB_LED_SPD100_ACT 0x7
+#define RTL8366RB_LED_SPD10_ACT 0x8
+#define RTL8366RB_LED_SPD100_10_ACT 0x9
+#define RTL8366RB_LED_FIBER 0xa
+#define RTL8366RB_LED_AN_FAULT 0xb
+#define RTL8366RB_LED_LINK_RX 0xc
+#define RTL8366RB_LED_LINK_TX 0xd
+#define RTL8366RB_LED_MASTER 0xe
+#define RTL8366RB_LED_FORCE 0xf
+#define RTL8366RB_LED_0_1_CTRL_REG 0x0432
+#define RTL8366RB_LED_1_OFFSET 6
+#define RTL8366RB_LED_2_3_CTRL_REG 0x0433
+#define RTL8366RB_LED_3_OFFSET 6
+
+#define RTL8366RB_MIB_COUNT 33
+#define RTL8366RB_GLOBAL_MIB_COUNT 1
+#define RTL8366RB_MIB_COUNTER_PORT_OFFSET 0x0050
+#define RTL8366RB_MIB_COUNTER_BASE 0x1000
+#define RTL8366RB_MIB_CTRL_REG 0x13F0
+#define RTL8366RB_MIB_CTRL_USER_MASK 0x0FFC
+#define RTL8366RB_MIB_CTRL_BUSY_MASK BIT(0)
+#define RTL8366RB_MIB_CTRL_RESET_MASK BIT(1)
+#define RTL8366RB_MIB_CTRL_PORT_RESET(_p) BIT(2 + (_p))
+#define RTL8366RB_MIB_CTRL_GLOBAL_RESET BIT(11)
+
+#define RTL8366RB_PORT_VLAN_CTRL_BASE 0x0063
+#define RTL8366RB_PORT_VLAN_CTRL_REG(_p) \
+ (RTL8366RB_PORT_VLAN_CTRL_BASE + (_p) / 4)
+#define RTL8366RB_PORT_VLAN_CTRL_MASK 0xf
+#define RTL8366RB_PORT_VLAN_CTRL_SHIFT(_p) (4 * ((_p) % 4))
+
+#define RTL8366RB_VLAN_TABLE_READ_BASE 0x018C
+#define RTL8366RB_VLAN_TABLE_WRITE_BASE 0x0185
+
+#define RTL8366RB_TABLE_ACCESS_CTRL_REG 0x0180
+#define RTL8366RB_TABLE_VLAN_READ_CTRL 0x0E01
+#define RTL8366RB_TABLE_VLAN_WRITE_CTRL 0x0F01
+
+#define RTL8366RB_VLAN_MC_BASE(_x) (0x0020 + (_x) * 3)
+
+#define RTL8366RB_PORT_LINK_STATUS_BASE 0x0014
+#define RTL8366RB_PORT_STATUS_SPEED_MASK 0x0003
+#define RTL8366RB_PORT_STATUS_DUPLEX_MASK 0x0004
+#define RTL8366RB_PORT_STATUS_LINK_MASK 0x0010
+#define RTL8366RB_PORT_STATUS_TXPAUSE_MASK 0x0020
+#define RTL8366RB_PORT_STATUS_RXPAUSE_MASK 0x0040
+#define RTL8366RB_PORT_STATUS_AN_MASK 0x0080
+
+#define RTL8366RB_NUM_VLANS 16
+#define RTL8366RB_NUM_LEDGROUPS 4
+#define RTL8366RB_NUM_VIDS 4096
+#define RTL8366RB_PRIORITYMAX 7
+#define RTL8366RB_FIDMAX 7
+
+#define RTL8366RB_PORT_1 BIT(0) /* In userspace port 0 */
+#define RTL8366RB_PORT_2 BIT(1) /* In userspace port 1 */
+#define RTL8366RB_PORT_3 BIT(2) /* In userspace port 2 */
+#define RTL8366RB_PORT_4 BIT(3) /* In userspace port 3 */
+#define RTL8366RB_PORT_5 BIT(4) /* In userspace port 4 */
+
+#define RTL8366RB_PORT_CPU BIT(5) /* CPU port */
+
+#define RTL8366RB_PORT_ALL (RTL8366RB_PORT_1 | \
+ RTL8366RB_PORT_2 | \
+ RTL8366RB_PORT_3 | \
+ RTL8366RB_PORT_4 | \
+ RTL8366RB_PORT_5 | \
+ RTL8366RB_PORT_CPU)
+
+#define RTL8366RB_PORT_ALL_BUT_CPU (RTL8366RB_PORT_1 | \
+ RTL8366RB_PORT_2 | \
+ RTL8366RB_PORT_3 | \
+ RTL8366RB_PORT_4 | \
+ RTL8366RB_PORT_5)
+
+#define RTL8366RB_PORT_ALL_EXTERNAL (RTL8366RB_PORT_1 | \
+ RTL8366RB_PORT_2 | \
+ RTL8366RB_PORT_3 | \
+ RTL8366RB_PORT_4)
+
+#define RTL8366RB_PORT_ALL_INTERNAL RTL8366RB_PORT_CPU
+
+/* First configuration word per member config, VID and prio */
+#define RTL8366RB_VLAN_VID_MASK 0xfff
+#define RTL8366RB_VLAN_PRIORITY_SHIFT 12
+#define RTL8366RB_VLAN_PRIORITY_MASK 0x7
+/* Second configuration word per member config, member and untagged */
+#define RTL8366RB_VLAN_UNTAG_SHIFT 8
+#define RTL8366RB_VLAN_UNTAG_MASK 0xff
+#define RTL8366RB_VLAN_MEMBER_MASK 0xff
+/* Third config word per member config, STAG currently unused */
+#define RTL8366RB_VLAN_STAG_MBR_MASK 0xff
+#define RTL8366RB_VLAN_STAG_MBR_SHIFT 8
+#define RTL8366RB_VLAN_STAG_IDX_MASK 0x7
+#define RTL8366RB_VLAN_STAG_IDX_SHIFT 5
+#define RTL8366RB_VLAN_FID_MASK 0x7
+
+/* Port ingress bandwidth control */
+#define RTL8366RB_IB_BASE 0x0200
+#define RTL8366RB_IB_REG(pnum) (RTL8366RB_IB_BASE + (pnum))
+#define RTL8366RB_IB_BDTH_MASK 0x3fff
+#define RTL8366RB_IB_PREIFG BIT(14)
+
+/* Port egress bandwidth control */
+#define RTL8366RB_EB_BASE 0x02d1
+#define RTL8366RB_EB_REG(pnum) (RTL8366RB_EB_BASE + (pnum))
+#define RTL8366RB_EB_BDTH_MASK 0x3fff
+#define RTL8366RB_EB_PREIFG_REG 0x02f8
+#define RTL8366RB_EB_PREIFG BIT(9)
+
+#define RTL8366RB_BDTH_SW_MAX 1048512 /* 1048576? */
+#define RTL8366RB_BDTH_UNIT 64
+#define RTL8366RB_BDTH_REG_DEFAULT 16383
+
+/* QOS */
+#define RTL8366RB_QOS BIT(15)
+/* Include/Exclude Preamble and IFG (20 bytes). 0:Exclude, 1:Include. */
+#define RTL8366RB_QOS_DEFAULT_PREIFG 1
+
+/* Interrupt handling */
+#define RTL8366RB_INTERRUPT_CONTROL_REG 0x0440
+#define RTL8366RB_INTERRUPT_POLARITY BIT(0)
+#define RTL8366RB_P4_RGMII_LED BIT(2)
+#define RTL8366RB_INTERRUPT_MASK_REG 0x0441
+#define RTL8366RB_INTERRUPT_LINK_CHGALL GENMASK(11, 0)
+#define RTL8366RB_INTERRUPT_ACLEXCEED BIT(8)
+#define RTL8366RB_INTERRUPT_STORMEXCEED BIT(9)
+#define RTL8366RB_INTERRUPT_P4_FIBER BIT(12)
+#define RTL8366RB_INTERRUPT_P4_UTP BIT(13)
+#define RTL8366RB_INTERRUPT_VALID (RTL8366RB_INTERRUPT_LINK_CHGALL | \
+ RTL8366RB_INTERRUPT_ACLEXCEED | \
+ RTL8366RB_INTERRUPT_STORMEXCEED | \
+ RTL8366RB_INTERRUPT_P4_FIBER | \
+ RTL8366RB_INTERRUPT_P4_UTP)
+#define RTL8366RB_INTERRUPT_STATUS_REG 0x0442
+#define RTL8366RB_NUM_INTERRUPT 14 /* 0..13 */
+
+/* bits 0..5 enable force when cleared */
+#define RTL8366RB_MAC_FORCE_CTRL_REG 0x0F11
+
+#define RTL8366RB_OAM_PARSER_REG 0x0F14
+#define RTL8366RB_OAM_MULTIPLEXER_REG 0x0F15
+
+#define RTL8366RB_GREEN_FEATURE_REG 0x0F51
+#define RTL8366RB_GREEN_FEATURE_MSK 0x0007
+#define RTL8366RB_GREEN_FEATURE_TX BIT(0)
+#define RTL8366RB_GREEN_FEATURE_RX BIT(2)
+
+static struct rtl8366_mib_counter rtl8366rb_mib_counters[] = {
+ { 0, 0, 4, "IfInOctets" },
+ { 0, 4, 4, "EtherStatsOctets" },
+ { 0, 8, 2, "EtherStatsUnderSizePkts" },
+ { 0, 10, 2, "EtherFragments" },
+ { 0, 12, 2, "EtherStatsPkts64Octets" },
+ { 0, 14, 2, "EtherStatsPkts65to127Octets" },
+ { 0, 16, 2, "EtherStatsPkts128to255Octets" },
+ { 0, 18, 2, "EtherStatsPkts256to511Octets" },
+ { 0, 20, 2, "EtherStatsPkts512to1023Octets" },
+ { 0, 22, 2, "EtherStatsPkts1024to1518Octets" },
+ { 0, 24, 2, "EtherOversizeStats" },
+ { 0, 26, 2, "EtherStatsJabbers" },
+ { 0, 28, 2, "IfInUcastPkts" },
+ { 0, 30, 2, "EtherStatsMulticastPkts" },
+ { 0, 32, 2, "EtherStatsBroadcastPkts" },
+ { 0, 34, 2, "EtherStatsDropEvents" },
+ { 0, 36, 2, "Dot3StatsFCSErrors" },
+ { 0, 38, 2, "Dot3StatsSymbolErrors" },
+ { 0, 40, 2, "Dot3InPauseFrames" },
+ { 0, 42, 2, "Dot3ControlInUnknownOpcodes" },
+ { 0, 44, 4, "IfOutOctets" },
+ { 0, 48, 2, "Dot3StatsSingleCollisionFrames" },
+ { 0, 50, 2, "Dot3StatMultipleCollisionFrames" },
+ { 0, 52, 2, "Dot3sDeferredTransmissions" },
+ { 0, 54, 2, "Dot3StatsLateCollisions" },
+ { 0, 56, 2, "EtherStatsCollisions" },
+ { 0, 58, 2, "Dot3StatsExcessiveCollisions" },
+ { 0, 60, 2, "Dot3OutPauseFrames" },
+ { 0, 62, 2, "Dot1dBasePortDelayExceededDiscards" },
+ { 0, 64, 2, "Dot1dTpPortInDiscards" },
+ { 0, 66, 2, "IfOutUcastPkts" },
+ { 0, 68, 2, "IfOutMulticastPkts" },
+ { 0, 70, 2, "IfOutBroadcastPkts" },
+};
+
+static int rtl8366rb_get_mib_counter(struct realtek_smi *smi,
+ int port,
+ struct rtl8366_mib_counter *mib,
+ u64 *mibvalue)
+{
+ u32 addr, val;
+ int ret;
+ int i;
+
+ addr = RTL8366RB_MIB_COUNTER_BASE +
+ RTL8366RB_MIB_COUNTER_PORT_OFFSET * (port) +
+ mib->offset;
+
+ /* Writing access counter address first
+ * then ASIC will prepare 64bits counter wait for being retrived
+ */
+ ret = regmap_write(smi->map, addr, 0); /* Write whatever */
+ if (ret)
+ return ret;
+
+ /* Read MIB control register */
+ ret = regmap_read(smi->map, RTL8366RB_MIB_CTRL_REG, &val);
+ if (ret)
+ return -EIO;
+
+ if (val & RTL8366RB_MIB_CTRL_BUSY_MASK)
+ return -EBUSY;
+
+ if (val & RTL8366RB_MIB_CTRL_RESET_MASK)
+ return -EIO;
+
+ /* Read each individual MIB 16 bits at the time */
+ *mibvalue = 0;
+ for (i = mib->length; i > 0; i--) {
+ ret = regmap_read(smi->map, addr + (i - 1), &val);
+ if (ret)
+ return ret;
+ *mibvalue = (*mibvalue << 16) | (val & 0xFFFF);
+ }
+ return 0;
+}
+
+static u32 rtl8366rb_get_irqmask(struct irq_data *d)
+{
+ int line = irqd_to_hwirq(d);
+ u32 val;
+
+ /* For line interrupts we combine link down in bits
+ * 6..11 with link up in bits 0..5 into one interrupt.
+ */
+ if (line < 12)
+ val = BIT(line) | BIT(line + 6);
+ else
+ val = BIT(line);
+ return val;
+}
+
+static void rtl8366rb_mask_irq(struct irq_data *d)
+{
+ struct realtek_smi *smi = irq_data_get_irq_chip_data(d);
+ int ret;
+
+ ret = regmap_update_bits(smi->map, RTL8366RB_INTERRUPT_MASK_REG,
+ rtl8366rb_get_irqmask(d), 0);
+ if (ret)
+ dev_err(smi->dev, "could not mask IRQ\n");
+}
+
+static void rtl8366rb_unmask_irq(struct irq_data *d)
+{
+ struct realtek_smi *smi = irq_data_get_irq_chip_data(d);
+ int ret;
+
+ ret = regmap_update_bits(smi->map, RTL8366RB_INTERRUPT_MASK_REG,
+ rtl8366rb_get_irqmask(d),
+ rtl8366rb_get_irqmask(d));
+ if (ret)
+ dev_err(smi->dev, "could not unmask IRQ\n");
+}
+
+static irqreturn_t rtl8366rb_irq(int irq, void *data)
+{
+ struct realtek_smi *smi = data;
+ u32 stat;
+ int ret;
+
+ /* This clears the IRQ status register */
+ ret = regmap_read(smi->map, RTL8366RB_INTERRUPT_STATUS_REG,
+ &stat);
+ if (ret) {
+ dev_err(smi->dev, "can't read interrupt status\n");
+ return IRQ_NONE;
+ }
+ stat &= RTL8366RB_INTERRUPT_VALID;
+ if (!stat)
+ return IRQ_NONE;
+ while (stat) {
+ int line = __ffs(stat);
+ int child_irq;
+
+ stat &= ~BIT(line);
+ /* For line interrupts we combine link down in bits
+ * 6..11 with link up in bits 0..5 into one interrupt.
+ */
+ if (line < 12 && line > 5)
+ line -= 5;
+ child_irq = irq_find_mapping(smi->irqdomain, line);
+ handle_nested_irq(child_irq);
+ }
+ return IRQ_HANDLED;
+}
+
+static struct irq_chip rtl8366rb_irq_chip = {
+ .name = "RTL8366RB",
+ .irq_mask = rtl8366rb_mask_irq,
+ .irq_unmask = rtl8366rb_unmask_irq,
+};
+
+static int rtl8366rb_irq_map(struct irq_domain *domain, unsigned int irq,
+ irq_hw_number_t hwirq)
+{
+ irq_set_chip_data(irq, domain->host_data);
+ irq_set_chip_and_handler(irq, &rtl8366rb_irq_chip, handle_simple_irq);
+ irq_set_nested_thread(irq, 1);
+ irq_set_noprobe(irq);
+
+ return 0;
+}
+
+static void rtl8366rb_irq_unmap(struct irq_domain *d, unsigned int irq)
+{
+ irq_set_nested_thread(irq, 0);
+ irq_set_chip_and_handler(irq, NULL, NULL);
+ irq_set_chip_data(irq, NULL);
+}
+
+static const struct irq_domain_ops rtl8366rb_irqdomain_ops = {
+ .map = rtl8366rb_irq_map,
+ .unmap = rtl8366rb_irq_unmap,
+ .xlate = irq_domain_xlate_onecell,
+};
+
+static int rtl8366rb_setup_cascaded_irq(struct realtek_smi *smi)
+{
+ struct device_node *intc;
+ unsigned long irq_trig;
+ int irq;
+ int ret;
+ u32 val;
+ int i;
+
+ intc = of_get_child_by_name(smi->dev->of_node, "interrupt-controller");
+ if (!intc) {
+ dev_err(smi->dev, "missing child interrupt-controller node\n");
+ return -EINVAL;
+ }
+ /* RB8366RB IRQs cascade off this one */
+ irq = of_irq_get(intc, 0);
+ if (irq <= 0) {
+ dev_err(smi->dev, "failed to get parent IRQ\n");
+ return irq ? irq : -EINVAL;
+ }
+
+ /* This clears the IRQ status register */
+ ret = regmap_read(smi->map, RTL8366RB_INTERRUPT_STATUS_REG,
+ &val);
+ if (ret) {
+ dev_err(smi->dev, "can't read interrupt status\n");
+ return ret;
+ }
+
+ /* Fetch IRQ edge information from the descriptor */
+ irq_trig = irqd_get_trigger_type(irq_get_irq_data(irq));
+ switch (irq_trig) {
+ case IRQF_TRIGGER_RISING:
+ case IRQF_TRIGGER_HIGH:
+ dev_info(smi->dev, "active high/rising IRQ\n");
+ val = 0;
+ break;
+ case IRQF_TRIGGER_FALLING:
+ case IRQF_TRIGGER_LOW:
+ dev_info(smi->dev, "active low/falling IRQ\n");
+ val = RTL8366RB_INTERRUPT_POLARITY;
+ break;
+ }
+ ret = regmap_update_bits(smi->map, RTL8366RB_INTERRUPT_CONTROL_REG,
+ RTL8366RB_INTERRUPT_POLARITY,
+ val);
+ if (ret) {
+ dev_err(smi->dev, "could not configure IRQ polarity\n");
+ return ret;
+ }
+
+ ret = devm_request_threaded_irq(smi->dev, irq, NULL,
+ rtl8366rb_irq, IRQF_ONESHOT,
+ "RTL8366RB", smi);
+ if (ret) {
+ dev_err(smi->dev, "unable to request irq: %d\n", ret);
+ return ret;
+ }
+ smi->irqdomain = irq_domain_add_linear(intc,
+ RTL8366RB_NUM_INTERRUPT,
+ &rtl8366rb_irqdomain_ops,
+ smi);
+ if (!smi->irqdomain) {
+ dev_err(smi->dev, "failed to create IRQ domain\n");
+ return -EINVAL;
+ }
+ for (i = 0; i < smi->num_ports; i++)
+ irq_set_parent(irq_create_mapping(smi->irqdomain, i), irq);
+
+ return 0;
+}
+
+static int rtl8366rb_set_addr(struct realtek_smi *smi)
+{
+ u8 addr[ETH_ALEN];
+ u16 val;
+ int ret;
+
+ eth_random_addr(addr);
+
+ dev_info(smi->dev, "set MAC: %02X:%02X:%02X:%02X:%02X:%02X\n",
+ addr[0], addr[1], addr[2], addr[3], addr[4], addr[5]);
+ val = addr[0] << 8 | addr[1];
+ ret = regmap_write(smi->map, RTL8366RB_SMAR0, val);
+ if (ret)
+ return ret;
+ val = addr[2] << 8 | addr[3];
+ ret = regmap_write(smi->map, RTL8366RB_SMAR1, val);
+ if (ret)
+ return ret;
+ val = addr[4] << 8 | addr[5];
+ ret = regmap_write(smi->map, RTL8366RB_SMAR2, val);
+ if (ret)
+ return ret;
+
+ return 0;
+}
+
+/* Found in a vendor driver */
+
+/* For the "version 0" early silicon, appear in most source releases */
+static const u16 rtl8366rb_init_jam_ver_0[] = {
+ 0x000B, 0x0001, 0x03A6, 0x0100, 0x03A7, 0x0001, 0x02D1, 0x3FFF,
+ 0x02D2, 0x3FFF, 0x02D3, 0x3FFF, 0x02D4, 0x3FFF, 0x02D5, 0x3FFF,
+ 0x02D6, 0x3FFF, 0x02D7, 0x3FFF, 0x02D8, 0x3FFF, 0x022B, 0x0688,
+ 0x022C, 0x0FAC, 0x03D0, 0x4688, 0x03D1, 0x01F5, 0x0000, 0x0830,
+ 0x02F9, 0x0200, 0x02F7, 0x7FFF, 0x02F8, 0x03FF, 0x0080, 0x03E8,
+ 0x0081, 0x00CE, 0x0082, 0x00DA, 0x0083, 0x0230, 0xBE0F, 0x2000,
+ 0x0231, 0x422A, 0x0232, 0x422A, 0x0233, 0x422A, 0x0234, 0x422A,
+ 0x0235, 0x422A, 0x0236, 0x422A, 0x0237, 0x422A, 0x0238, 0x422A,
+ 0x0239, 0x422A, 0x023A, 0x422A, 0x023B, 0x422A, 0x023C, 0x422A,
+ 0x023D, 0x422A, 0x023E, 0x422A, 0x023F, 0x422A, 0x0240, 0x422A,
+ 0x0241, 0x422A, 0x0242, 0x422A, 0x0243, 0x422A, 0x0244, 0x422A,
+ 0x0245, 0x422A, 0x0246, 0x422A, 0x0247, 0x422A, 0x0248, 0x422A,
+ 0x0249, 0x0146, 0x024A, 0x0146, 0x024B, 0x0146, 0xBE03, 0xC961,
+ 0x024D, 0x0146, 0x024E, 0x0146, 0x024F, 0x0146, 0x0250, 0x0146,
+ 0xBE64, 0x0226, 0x0252, 0x0146, 0x0253, 0x0146, 0x024C, 0x0146,
+ 0x0251, 0x0146, 0x0254, 0x0146, 0xBE62, 0x3FD0, 0x0084, 0x0320,
+ 0x0255, 0x0146, 0x0256, 0x0146, 0x0257, 0x0146, 0x0258, 0x0146,
+ 0x0259, 0x0146, 0x025A, 0x0146, 0x025B, 0x0146, 0x025C, 0x0146,
+ 0x025D, 0x0146, 0x025E, 0x0146, 0x025F, 0x0146, 0x0260, 0x0146,
+ 0x0261, 0xA23F, 0x0262, 0x0294, 0x0263, 0xA23F, 0x0264, 0x0294,
+ 0x0265, 0xA23F, 0x0266, 0x0294, 0x0267, 0xA23F, 0x0268, 0x0294,
+ 0x0269, 0xA23F, 0x026A, 0x0294, 0x026B, 0xA23F, 0x026C, 0x0294,
+ 0x026D, 0xA23F, 0x026E, 0x0294, 0x026F, 0xA23F, 0x0270, 0x0294,
+ 0x02F5, 0x0048, 0xBE09, 0x0E00, 0xBE1E, 0x0FA0, 0xBE14, 0x8448,
+ 0xBE15, 0x1007, 0xBE4A, 0xA284, 0xC454, 0x3F0B, 0xC474, 0x3F0B,
+ 0xBE48, 0x3672, 0xBE4B, 0x17A7, 0xBE4C, 0x0B15, 0xBE52, 0x0EDD,
+ 0xBE49, 0x8C00, 0xBE5B, 0x785C, 0xBE5C, 0x785C, 0xBE5D, 0x785C,
+ 0xBE61, 0x368A, 0xBE63, 0x9B84, 0xC456, 0xCC13, 0xC476, 0xCC13,
+ 0xBE65, 0x307D, 0xBE6D, 0x0005, 0xBE6E, 0xE120, 0xBE2E, 0x7BAF,
+};
+
+/* This v1 init sequence is from Belkin F5D8235 U-Boot release */
+static const u16 rtl8366rb_init_jam_ver_1[] = {
+ 0x0000, 0x0830, 0x0001, 0x8000, 0x0400, 0x8130, 0xBE78, 0x3C3C,
+ 0x0431, 0x5432, 0xBE37, 0x0CE4, 0x02FA, 0xFFDF, 0x02FB, 0xFFE0,
+ 0xC44C, 0x1585, 0xC44C, 0x1185, 0xC44C, 0x1585, 0xC46C, 0x1585,
+ 0xC46C, 0x1185, 0xC46C, 0x1585, 0xC451, 0x2135, 0xC471, 0x2135,
+ 0xBE10, 0x8140, 0xBE15, 0x0007, 0xBE6E, 0xE120, 0xBE69, 0xD20F,
+ 0xBE6B, 0x0320, 0xBE24, 0xB000, 0xBE23, 0xFF51, 0xBE22, 0xDF20,
+ 0xBE21, 0x0140, 0xBE20, 0x00BB, 0xBE24, 0xB800, 0xBE24, 0x0000,
+ 0xBE24, 0x7000, 0xBE23, 0xFF51, 0xBE22, 0xDF60, 0xBE21, 0x0140,
+ 0xBE20, 0x0077, 0xBE24, 0x7800, 0xBE24, 0x0000, 0xBE2E, 0x7B7A,
+ 0xBE36, 0x0CE4, 0x02F5, 0x0048, 0xBE77, 0x2940, 0x000A, 0x83E0,
+ 0xBE79, 0x3C3C, 0xBE00, 0x1340,
+};
+
+/* This v2 init sequence is from Belkin F5D8235 U-Boot release */
+static const u16 rtl8366rb_init_jam_ver_2[] = {
+ 0x0450, 0x0000, 0x0400, 0x8130, 0x000A, 0x83ED, 0x0431, 0x5432,
+ 0xC44F, 0x6250, 0xC46F, 0x6250, 0xC456, 0x0C14, 0xC476, 0x0C14,
+ 0xC44C, 0x1C85, 0xC44C, 0x1885, 0xC44C, 0x1C85, 0xC46C, 0x1C85,
+ 0xC46C, 0x1885, 0xC46C, 0x1C85, 0xC44C, 0x0885, 0xC44C, 0x0881,
+ 0xC44C, 0x0885, 0xC46C, 0x0885, 0xC46C, 0x0881, 0xC46C, 0x0885,
+ 0xBE2E, 0x7BA7, 0xBE36, 0x1000, 0xBE37, 0x1000, 0x8000, 0x0001,
+ 0xBE69, 0xD50F, 0x8000, 0x0000, 0xBE69, 0xD50F, 0xBE6E, 0x0320,
+ 0xBE77, 0x2940, 0xBE78, 0x3C3C, 0xBE79, 0x3C3C, 0xBE6E, 0xE120,
+ 0x8000, 0x0001, 0xBE15, 0x1007, 0x8000, 0x0000, 0xBE15, 0x1007,
+ 0xBE14, 0x0448, 0xBE1E, 0x00A0, 0xBE10, 0x8160, 0xBE10, 0x8140,
+ 0xBE00, 0x1340, 0x0F51, 0x0010,
+};
+
+/* Appears in a DDWRT code dump */
+static const u16 rtl8366rb_init_jam_ver_3[] = {
+ 0x0000, 0x0830, 0x0400, 0x8130, 0x000A, 0x83ED, 0x0431, 0x5432,
+ 0x0F51, 0x0017, 0x02F5, 0x0048, 0x02FA, 0xFFDF, 0x02FB, 0xFFE0,
+ 0xC456, 0x0C14, 0xC476, 0x0C14, 0xC454, 0x3F8B, 0xC474, 0x3F8B,
+ 0xC450, 0x2071, 0xC470, 0x2071, 0xC451, 0x226B, 0xC471, 0x226B,
+ 0xC452, 0xA293, 0xC472, 0xA293, 0xC44C, 0x1585, 0xC44C, 0x1185,
+ 0xC44C, 0x1585, 0xC46C, 0x1585, 0xC46C, 0x1185, 0xC46C, 0x1585,
+ 0xC44C, 0x0185, 0xC44C, 0x0181, 0xC44C, 0x0185, 0xC46C, 0x0185,
+ 0xC46C, 0x0181, 0xC46C, 0x0185, 0xBE24, 0xB000, 0xBE23, 0xFF51,
+ 0xBE22, 0xDF20, 0xBE21, 0x0140, 0xBE20, 0x00BB, 0xBE24, 0xB800,
+ 0xBE24, 0x0000, 0xBE24, 0x7000, 0xBE23, 0xFF51, 0xBE22, 0xDF60,
+ 0xBE21, 0x0140, 0xBE20, 0x0077, 0xBE24, 0x7800, 0xBE24, 0x0000,
+ 0xBE2E, 0x7BA7, 0xBE36, 0x1000, 0xBE37, 0x1000, 0x8000, 0x0001,
+ 0xBE69, 0xD50F, 0x8000, 0x0000, 0xBE69, 0xD50F, 0xBE6B, 0x0320,
+ 0xBE77, 0x2800, 0xBE78, 0x3C3C, 0xBE79, 0x3C3C, 0xBE6E, 0xE120,
+ 0x8000, 0x0001, 0xBE10, 0x8140, 0x8000, 0x0000, 0xBE10, 0x8140,
+ 0xBE15, 0x1007, 0xBE14, 0x0448, 0xBE1E, 0x00A0, 0xBE10, 0x8160,
+ 0xBE10, 0x8140, 0xBE00, 0x1340, 0x0450, 0x0000, 0x0401, 0x0000,
+};
+
+/* Belkin F5D8235 v1, "belkin,f5d8235-v1" */
+static const u16 rtl8366rb_init_jam_f5d8235[] = {
+ 0x0242, 0x02BF, 0x0245, 0x02BF, 0x0248, 0x02BF, 0x024B, 0x02BF,
+ 0x024E, 0x02BF, 0x0251, 0x02BF, 0x0254, 0x0A3F, 0x0256, 0x0A3F,
+ 0x0258, 0x0A3F, 0x025A, 0x0A3F, 0x025C, 0x0A3F, 0x025E, 0x0A3F,
+ 0x0263, 0x007C, 0x0100, 0x0004, 0xBE5B, 0x3500, 0x800E, 0x200F,
+ 0xBE1D, 0x0F00, 0x8001, 0x5011, 0x800A, 0xA2F4, 0x800B, 0x17A3,
+ 0xBE4B, 0x17A3, 0xBE41, 0x5011, 0xBE17, 0x2100, 0x8000, 0x8304,
+ 0xBE40, 0x8304, 0xBE4A, 0xA2F4, 0x800C, 0xA8D5, 0x8014, 0x5500,
+ 0x8015, 0x0004, 0xBE4C, 0xA8D5, 0xBE59, 0x0008, 0xBE09, 0x0E00,
+ 0xBE36, 0x1036, 0xBE37, 0x1036, 0x800D, 0x00FF, 0xBE4D, 0x00FF,
+};
+
+/* DGN3500, "netgear,dgn3500", "netgear,dgn3500b" */
+static const u16 rtl8366rb_init_jam_dgn3500[] = {
+ 0x0000, 0x0830, 0x0400, 0x8130, 0x000A, 0x83ED, 0x0F51, 0x0017,
+ 0x02F5, 0x0048, 0x02FA, 0xFFDF, 0x02FB, 0xFFE0, 0x0450, 0x0000,
+ 0x0401, 0x0000, 0x0431, 0x0960,
+};
+
+/* This jam table activates "green ethernet", which means low power mode
+ * and is claimed to detect the cable length and not use more power than
+ * necessary, and the ports should enter power saving mode 10 seconds after
+ * a cable is disconnected. Seems to always be the same.
+ */
+static const u16 rtl8366rb_green_jam[][2] = {
+ {0xBE78, 0x323C}, {0xBE77, 0x5000}, {0xBE2E, 0x7BA7},
+ {0xBE59, 0x3459}, {0xBE5A, 0x745A}, {0xBE5B, 0x785C},
+ {0xBE5C, 0x785C}, {0xBE6E, 0xE120}, {0xBE79, 0x323C},
+};
+
+static int rtl8366rb_setup(struct dsa_switch *ds)
+{
+ struct realtek_smi *smi = ds->priv;
+ const u16 *jam_table;
+ u32 chip_ver = 0;
+ u32 chip_id = 0;
+ int jam_size;
+ u32 val;
+ int ret;
+ int i;
+
+ ret = regmap_read(smi->map, RTL8366RB_CHIP_ID_REG, &chip_id);
+ if (ret) {
+ dev_err(smi->dev, "unable to read chip id\n");
+ return ret;
+ }
+
+ switch (chip_id) {
+ case RTL8366RB_CHIP_ID_8366:
+ break;
+ default:
+ dev_err(smi->dev, "unknown chip id (%04x)\n", chip_id);
+ return -ENODEV;
+ }
+
+ ret = regmap_read(smi->map, RTL8366RB_CHIP_VERSION_CTRL_REG,
+ &chip_ver);
+ if (ret) {
+ dev_err(smi->dev, "unable to read chip version\n");
+ return ret;
+ }
+
+ dev_info(smi->dev, "RTL%04x ver %u chip found\n",
+ chip_id, chip_ver & RTL8366RB_CHIP_VERSION_MASK);
+
+ /* Do the init dance using the right jam table */
+ switch (chip_ver) {
+ case 0:
+ jam_table = rtl8366rb_init_jam_ver_0;
+ jam_size = ARRAY_SIZE(rtl8366rb_init_jam_ver_0);
+ break;
+ case 1:
+ jam_table = rtl8366rb_init_jam_ver_1;
+ jam_size = ARRAY_SIZE(rtl8366rb_init_jam_ver_1);
+ break;
+ case 2:
+ jam_table = rtl8366rb_init_jam_ver_2;
+ jam_size = ARRAY_SIZE(rtl8366rb_init_jam_ver_2);
+ break;
+ default:
+ jam_table = rtl8366rb_init_jam_ver_3;
+ jam_size = ARRAY_SIZE(rtl8366rb_init_jam_ver_3);
+ break;
+ }
+
+ /* Special jam tables for special routers
+ * TODO: are these necessary? Maintainers, please test
+ * without them, using just the off-the-shelf tables.
+ */
+ if (of_machine_is_compatible("belkin,f5d8235-v1")) {
+ jam_table = rtl8366rb_init_jam_f5d8235;
+ jam_size = ARRAY_SIZE(rtl8366rb_init_jam_f5d8235);
+ }
+ if (of_machine_is_compatible("netgear,dgn3500") ||
+ of_machine_is_compatible("netgear,dgn3500b")) {
+ jam_table = rtl8366rb_init_jam_dgn3500;
+ jam_size = ARRAY_SIZE(rtl8366rb_init_jam_dgn3500);
+ }
+
+ i = 0;
+ while (i < jam_size) {
+ if ((jam_table[i] & 0xBE00) == 0xBE00) {
+ ret = regmap_read(smi->map,
+ RTL8366RB_PHY_ACCESS_BUSY_REG,
+ &val);
+ if (ret)
+ return ret;
+ if (!(val & RTL8366RB_PHY_INT_BUSY)) {
+ ret = regmap_write(smi->map,
+ RTL8366RB_PHY_ACCESS_CTRL_REG,
+ RTL8366RB_PHY_CTRL_WRITE);
+ if (ret)
+ return ret;
+ }
+ }
+ dev_dbg(smi->dev, "jam %04x into register %04x\n",
+ jam_table[i + 1],
+ jam_table[i]);
+ ret = regmap_write(smi->map,
+ jam_table[i],
+ jam_table[i + 1]);
+ if (ret)
+ return ret;
+ i += 2;
+ }
+
+ /* Set up the "green ethernet" feature */
+ i = 0;
+ while (i < ARRAY_SIZE(rtl8366rb_green_jam)) {
+ ret = regmap_read(smi->map, RTL8366RB_PHY_ACCESS_BUSY_REG,
+ &val);
+ if (ret)
+ return ret;
+ if (!(val & RTL8366RB_PHY_INT_BUSY)) {
+ ret = regmap_write(smi->map,
+ RTL8366RB_PHY_ACCESS_CTRL_REG,
+ RTL8366RB_PHY_CTRL_WRITE);
+ if (ret)
+ return ret;
+ ret = regmap_write(smi->map,
+ rtl8366rb_green_jam[i][0],
+ rtl8366rb_green_jam[i][1]);
+ if (ret)
+ return ret;
+ i++;
+ }
+ }
+ ret = regmap_write(smi->map,
+ RTL8366RB_GREEN_FEATURE_REG,
+ (chip_ver == 1) ? 0x0007 : 0x0003);
+ if (ret)
+ return ret;
+
+ /* Vendor driver sets 0x240 in registers 0xc and 0xd (undocumented) */
+ ret = regmap_write(smi->map, 0x0c, 0x240);
+ if (ret)
+ return ret;
+ ret = regmap_write(smi->map, 0x0d, 0x240);
+ if (ret)
+ return ret;
+
+ /* Set some random MAC address */
+ ret = rtl8366rb_set_addr(smi);
+ if (ret)
+ return ret;
+
+ /* Enable CPU port and enable inserting CPU tag
+ *
+ * Disabling RTL8368RB_CPU_INSTAG here will change the behaviour
+ * of the switch totally and it will start talking Realtek RRCP
+ * internally. It is probably possible to experiment with this,
+ * but then the kernel needs to understand and handle RRCP first.
+ */
+ ret = regmap_update_bits(smi->map, RTL8368RB_CPU_CTRL_REG,
+ 0xFFFF,
+ RTL8368RB_CPU_INSTAG | BIT(smi->cpu_port));
+ if (ret)
+ return ret;
+
+ /* Make sure we default-enable the fixed CPU port */
+ ret = regmap_update_bits(smi->map, RTL8366RB_PECR,
+ BIT(smi->cpu_port),
+ 0);
+ if (ret)
+ return ret;
+
+ /* Set maximum packet length to 1536 bytes */
+ ret = regmap_update_bits(smi->map, RTL8366RB_SGCR,
+ RTL8366RB_SGCR_MAX_LENGTH_MASK,
+ RTL8366RB_SGCR_MAX_LENGTH_1536);
+ if (ret)
+ return ret;
+
+ /* Enable learning for all ports */
+ ret = regmap_write(smi->map, RTL8366RB_SSCR0, 0);
+ if (ret)
+ return ret;
+
+ /* Enable auto ageing for all ports */
+ ret = regmap_write(smi->map, RTL8366RB_SSCR1, 0);
+ if (ret)
+ return ret;
+
+ /* Discard VLAN tagged packets if the port is not a member of
+ * the VLAN with which the packets is associated.
+ */
+ ret = regmap_write(smi->map, RTL8366RB_VLAN_INGRESS_CTRL2_REG,
+ RTL8366RB_PORT_ALL);
+ if (ret)
+ return ret;
+
+ /* Don't drop packets whose DA has not been learned */
+ ret = regmap_update_bits(smi->map, RTL8366RB_SSCR2,
+ RTL8366RB_SSCR2_DROP_UNKNOWN_DA, 0);
+ if (ret)
+ return ret;
+
+ /* Set blinking, TODO: make this configurable */
+ ret = regmap_update_bits(smi->map, RTL8366RB_LED_BLINKRATE_REG,
+ RTL8366RB_LED_BLINKRATE_MASK,
+ RTL8366RB_LED_BLINKRATE_56MS);
+ if (ret)
+ return ret;
+
+ /* Set up LED activity:
+ * Each port has 4 LEDs, we configure all ports to the same
+ * behaviour (no individual config) but we can set up each
+ * LED separately.
+ */
+ if (smi->leds_disabled) {
+ /* Turn everything off */
+ regmap_update_bits(smi->map,
+ RTL8366RB_LED_0_1_CTRL_REG,
+ 0x0FFF, 0);
+ regmap_update_bits(smi->map,
+ RTL8366RB_LED_2_3_CTRL_REG,
+ 0x0FFF, 0);
+ regmap_update_bits(smi->map,
+ RTL8366RB_INTERRUPT_CONTROL_REG,
+ RTL8366RB_P4_RGMII_LED,
+ 0);
+ val = RTL8366RB_LED_OFF;
+ } else {
+ /* TODO: make this configurable per LED */
+ val = RTL8366RB_LED_FORCE;
+ }
+ for (i = 0; i < 4; i++) {
+ ret = regmap_update_bits(smi->map,
+ RTL8366RB_LED_CTRL_REG,
+ 0xf << (i * 4),
+ val << (i * 4));
+ if (ret)
+ return ret;
+ }
+
+ ret = rtl8366_init_vlan(smi);
+ if (ret)
+ return ret;
+
+ ret = rtl8366rb_setup_cascaded_irq(smi);
+ if (ret)
+ dev_info(smi->dev, "no interrupt support\n");
+
+ ret = realtek_smi_setup_mdio(smi);
+ if (ret) {
+ dev_info(smi->dev, "could not set up MDIO bus\n");
+ return -ENODEV;
+ }
+
+ return 0;
+}
+
+static enum dsa_tag_protocol rtl8366_get_tag_protocol(struct dsa_switch *ds,
+ int port)
+{
+ /* For now, the RTL switches are handled without any custom tags.
+ *
+ * It is possible to turn on "custom tags" by removing the
+ * RTL8368RB_CPU_INSTAG flag when enabling the port but what it
+ * does is unfamiliar to DSA: ethernet frames of type 8899, the Realtek
+ * Remote Control Protocol (RRCP) start to appear on the CPU port of
+ * the device. So this is not the ordinary few extra bytes in the
+ * frame. Instead it appears that the switch starts to talk Realtek
+ * RRCP internally which means a pretty complex RRCP implementation
+ * decoding and responding the RRCP protocol is needed to exploit this.
+ *
+ * The OpenRRCP project (dormant since 2009) have reverse-egineered
+ * parts of the protocol.
+ */
+ return DSA_TAG_PROTO_NONE;
+}
+
+static void rtl8366rb_adjust_link(struct dsa_switch *ds, int port,
+ struct phy_device *phydev)
+{
+ struct realtek_smi *smi = ds->priv;
+ int ret;
+
+ if (port != smi->cpu_port)
+ return;
+
+ dev_info(smi->dev, "adjust link on CPU port (%d)\n", port);
+
+ /* Force the fixed CPU port into 1Gbit mode, no autonegotiation */
+ ret = regmap_update_bits(smi->map, RTL8366RB_MAC_FORCE_CTRL_REG,
+ BIT(port), BIT(port));
+ if (ret)
+ return;
+
+ ret = regmap_update_bits(smi->map, RTL8366RB_PAACR2,
+ 0xFF00U,
+ RTL8366RB_PAACR_CPU_PORT << 8);
+ if (ret)
+ return;
+
+ /* Enable the CPU port */
+ ret = regmap_update_bits(smi->map, RTL8366RB_PECR, BIT(port),
+ 0);
+ if (ret)
+ return;
+}
+
+static void rb8366rb_set_port_led(struct realtek_smi *smi,
+ int port, bool enable)
+{
+ u16 val = enable ? 0x3f : 0;
+ int ret;
+
+ if (smi->leds_disabled)
+ return;
+
+ switch (port) {
+ case 0:
+ ret = regmap_update_bits(smi->map,
+ RTL8366RB_LED_0_1_CTRL_REG,
+ 0x3F, val);
+ break;
+ case 1:
+ ret = regmap_update_bits(smi->map,
+ RTL8366RB_LED_0_1_CTRL_REG,
+ 0x3F << RTL8366RB_LED_1_OFFSET,
+ val << RTL8366RB_LED_1_OFFSET);
+ break;
+ case 2:
+ ret = regmap_update_bits(smi->map,
+ RTL8366RB_LED_2_3_CTRL_REG,
+ 0x3F, val);
+ break;
+ case 3:
+ ret = regmap_update_bits(smi->map,
+ RTL8366RB_LED_2_3_CTRL_REG,
+ 0x3F << RTL8366RB_LED_3_OFFSET,
+ val << RTL8366RB_LED_3_OFFSET);
+ break;
+ case 4:
+ ret = regmap_update_bits(smi->map,
+ RTL8366RB_INTERRUPT_CONTROL_REG,
+ RTL8366RB_P4_RGMII_LED,
+ enable ? RTL8366RB_P4_RGMII_LED : 0);
+ break;
+ default:
+ dev_err(smi->dev, "no LED for port %d\n", port);
+ return;
+ }
+ if (ret)
+ dev_err(smi->dev, "error updating LED on port %d\n", port);
+}
+
+static int
+rtl8366rb_port_enable(struct dsa_switch *ds, int port,
+ struct phy_device *phy)
+{
+ struct realtek_smi *smi = ds->priv;
+ int ret;
+
+ dev_dbg(smi->dev, "enable port %d\n", port);
+ ret = regmap_update_bits(smi->map, RTL8366RB_PECR, BIT(port),
+ 0);
+ if (ret)
+ return ret;
+
+ rb8366rb_set_port_led(smi, port, true);
+ return 0;
+}
+
+static void
+rtl8366rb_port_disable(struct dsa_switch *ds, int port,
+ struct phy_device *phy)
+{
+ struct realtek_smi *smi = ds->priv;
+ int ret;
+
+ dev_dbg(smi->dev, "disable port %d\n", port);
+ ret = regmap_update_bits(smi->map, RTL8366RB_PECR, BIT(port),
+ BIT(port));
+ if (ret)
+ return;
+
+ rb8366rb_set_port_led(smi, port, false);
+}
+
+static int rtl8366rb_get_vlan_4k(struct realtek_smi *smi, u32 vid,
+ struct rtl8366_vlan_4k *vlan4k)
+{
+ u32 data[3];
+ int ret;
+ int i;
+
+ memset(vlan4k, '\0', sizeof(struct rtl8366_vlan_4k));
+
+ if (vid >= RTL8366RB_NUM_VIDS)
+ return -EINVAL;
+
+ /* write VID */
+ ret = regmap_write(smi->map, RTL8366RB_VLAN_TABLE_WRITE_BASE,
+ vid & RTL8366RB_VLAN_VID_MASK);
+ if (ret)
+ return ret;
+
+ /* write table access control word */
+ ret = regmap_write(smi->map, RTL8366RB_TABLE_ACCESS_CTRL_REG,
+ RTL8366RB_TABLE_VLAN_READ_CTRL);
+ if (ret)
+ return ret;
+
+ for (i = 0; i < 3; i++) {
+ ret = regmap_read(smi->map,
+ RTL8366RB_VLAN_TABLE_READ_BASE + i,
+ &data[i]);
+ if (ret)
+ return ret;
+ }
+
+ vlan4k->vid = vid;
+ vlan4k->untag = (data[1] >> RTL8366RB_VLAN_UNTAG_SHIFT) &
+ RTL8366RB_VLAN_UNTAG_MASK;
+ vlan4k->member = data[1] & RTL8366RB_VLAN_MEMBER_MASK;
+ vlan4k->fid = data[2] & RTL8366RB_VLAN_FID_MASK;
+
+ return 0;
+}
+
+static int rtl8366rb_set_vlan_4k(struct realtek_smi *smi,
+ const struct rtl8366_vlan_4k *vlan4k)
+{
+ u32 data[3];
+ int ret;
+ int i;
+
+ if (vlan4k->vid >= RTL8366RB_NUM_VIDS ||
+ vlan4k->member > RTL8366RB_VLAN_MEMBER_MASK ||
+ vlan4k->untag > RTL8366RB_VLAN_UNTAG_MASK ||
+ vlan4k->fid > RTL8366RB_FIDMAX)
+ return -EINVAL;
+
+ data[0] = vlan4k->vid & RTL8366RB_VLAN_VID_MASK;
+ data[1] = (vlan4k->member & RTL8366RB_VLAN_MEMBER_MASK) |
+ ((vlan4k->untag & RTL8366RB_VLAN_UNTAG_MASK) <<
+ RTL8366RB_VLAN_UNTAG_SHIFT);
+ data[2] = vlan4k->fid & RTL8366RB_VLAN_FID_MASK;
+
+ for (i = 0; i < 3; i++) {
+ ret = regmap_write(smi->map,
+ RTL8366RB_VLAN_TABLE_WRITE_BASE + i,
+ data[i]);
+ if (ret)
+ return ret;
+ }
+
+ /* write table access control word */
+ ret = regmap_write(smi->map, RTL8366RB_TABLE_ACCESS_CTRL_REG,
+ RTL8366RB_TABLE_VLAN_WRITE_CTRL);
+
+ return ret;
+}
+
+static int rtl8366rb_get_vlan_mc(struct realtek_smi *smi, u32 index,
+ struct rtl8366_vlan_mc *vlanmc)
+{
+ u32 data[3];
+ int ret;
+ int i;
+
+ memset(vlanmc, '\0', sizeof(struct rtl8366_vlan_mc));
+
+ if (index >= RTL8366RB_NUM_VLANS)
+ return -EINVAL;
+
+ for (i = 0; i < 3; i++) {
+ ret = regmap_read(smi->map,
+ RTL8366RB_VLAN_MC_BASE(index) + i,
+ &data[i]);
+ if (ret)
+ return ret;
+ }
+
+ vlanmc->vid = data[0] & RTL8366RB_VLAN_VID_MASK;
+ vlanmc->priority = (data[0] >> RTL8366RB_VLAN_PRIORITY_SHIFT) &
+ RTL8366RB_VLAN_PRIORITY_MASK;
+ vlanmc->untag = (data[1] >> RTL8366RB_VLAN_UNTAG_SHIFT) &
+ RTL8366RB_VLAN_UNTAG_MASK;
+ vlanmc->member = data[1] & RTL8366RB_VLAN_MEMBER_MASK;
+ vlanmc->fid = data[2] & RTL8366RB_VLAN_FID_MASK;
+
+ return 0;
+}
+
+static int rtl8366rb_set_vlan_mc(struct realtek_smi *smi, u32 index,
+ const struct rtl8366_vlan_mc *vlanmc)
+{
+ u32 data[3];
+ int ret;
+ int i;
+
+ if (index >= RTL8366RB_NUM_VLANS ||
+ vlanmc->vid >= RTL8366RB_NUM_VIDS ||
+ vlanmc->priority > RTL8366RB_PRIORITYMAX ||
+ vlanmc->member > RTL8366RB_VLAN_MEMBER_MASK ||
+ vlanmc->untag > RTL8366RB_VLAN_UNTAG_MASK ||
+ vlanmc->fid > RTL8366RB_FIDMAX)
+ return -EINVAL;
+
+ data[0] = (vlanmc->vid & RTL8366RB_VLAN_VID_MASK) |
+ ((vlanmc->priority & RTL8366RB_VLAN_PRIORITY_MASK) <<
+ RTL8366RB_VLAN_PRIORITY_SHIFT);
+ data[1] = (vlanmc->member & RTL8366RB_VLAN_MEMBER_MASK) |
+ ((vlanmc->untag & RTL8366RB_VLAN_UNTAG_MASK) <<
+ RTL8366RB_VLAN_UNTAG_SHIFT);
+ data[2] = vlanmc->fid & RTL8366RB_VLAN_FID_MASK;
+
+ for (i = 0; i < 3; i++) {
+ ret = regmap_write(smi->map,
+ RTL8366RB_VLAN_MC_BASE(index) + i,
+ data[i]);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
+static int rtl8366rb_get_mc_index(struct realtek_smi *smi, int port, int *val)
+{
+ u32 data;
+ int ret;
+
+ if (port >= smi->num_ports)
+ return -EINVAL;
+
+ ret = regmap_read(smi->map, RTL8366RB_PORT_VLAN_CTRL_REG(port),
+ &data);
+ if (ret)
+ return ret;
+
+ *val = (data >> RTL8366RB_PORT_VLAN_CTRL_SHIFT(port)) &
+ RTL8366RB_PORT_VLAN_CTRL_MASK;
+
+ return 0;
+}
+
+static int rtl8366rb_set_mc_index(struct realtek_smi *smi, int port, int index)
+{
+ if (port >= smi->num_ports || index >= RTL8366RB_NUM_VLANS)
+ return -EINVAL;
+
+ return regmap_update_bits(smi->map, RTL8366RB_PORT_VLAN_CTRL_REG(port),
+ RTL8366RB_PORT_VLAN_CTRL_MASK <<
+ RTL8366RB_PORT_VLAN_CTRL_SHIFT(port),
+ (index & RTL8366RB_PORT_VLAN_CTRL_MASK) <<
+ RTL8366RB_PORT_VLAN_CTRL_SHIFT(port));
+}
+
+static bool rtl8366rb_is_vlan_valid(struct realtek_smi *smi, unsigned int vlan)
+{
+ unsigned int max = RTL8366RB_NUM_VLANS;
+
+ if (smi->vlan4k_enabled)
+ max = RTL8366RB_NUM_VIDS - 1;
+
+ if (vlan == 0 || vlan >= max)
+ return false;
+
+ return true;
+}
+
+static int rtl8366rb_enable_vlan(struct realtek_smi *smi, bool enable)
+{
+ dev_dbg(smi->dev, "%s VLAN\n", enable ? "enable" : "disable");
+ return regmap_update_bits(smi->map,
+ RTL8366RB_SGCR, RTL8366RB_SGCR_EN_VLAN,
+ enable ? RTL8366RB_SGCR_EN_VLAN : 0);
+}
+
+static int rtl8366rb_enable_vlan4k(struct realtek_smi *smi, bool enable)
+{
+ dev_dbg(smi->dev, "%s VLAN 4k\n", enable ? "enable" : "disable");
+ return regmap_update_bits(smi->map, RTL8366RB_SGCR,
+ RTL8366RB_SGCR_EN_VLAN_4KTB,
+ enable ? RTL8366RB_SGCR_EN_VLAN_4KTB : 0);
+}
+
+static int rtl8366rb_phy_read(struct realtek_smi *smi, int phy, int regnum)
+{
+ u32 val;
+ u32 reg;
+ int ret;
+
+ if (phy > RTL8366RB_PHY_NO_MAX)
+ return -EINVAL;
+
+ ret = regmap_write(smi->map, RTL8366RB_PHY_ACCESS_CTRL_REG,
+ RTL8366RB_PHY_CTRL_READ);
+ if (ret)
+ return ret;
+
+ reg = 0x8000 | (1 << (phy + RTL8366RB_PHY_NO_OFFSET)) | regnum;
+
+ ret = regmap_write(smi->map, reg, 0);
+ if (ret) {
+ dev_err(smi->dev,
+ "failed to write PHY%d reg %04x @ %04x, ret %d\n",
+ phy, regnum, reg, ret);
+ return ret;
+ }
+
+ ret = regmap_read(smi->map, RTL8366RB_PHY_ACCESS_DATA_REG, &val);
+ if (ret)
+ return ret;
+
+ dev_dbg(smi->dev, "read PHY%d register 0x%04x @ %08x, val <- %04x\n",
+ phy, regnum, reg, val);
+
+ return val;
+}
+
+static int rtl8366rb_phy_write(struct realtek_smi *smi, int phy, int regnum,
+ u16 val)
+{
+ u32 reg;
+ int ret;
+
+ if (phy > RTL8366RB_PHY_NO_MAX)
+ return -EINVAL;
+
+ ret = regmap_write(smi->map, RTL8366RB_PHY_ACCESS_CTRL_REG,
+ RTL8366RB_PHY_CTRL_WRITE);
+ if (ret)
+ return ret;
+
+ reg = 0x8000 | (1 << (phy + RTL8366RB_PHY_NO_OFFSET)) | regnum;
+
+ dev_dbg(smi->dev, "write PHY%d register 0x%04x @ %04x, val -> %04x\n",
+ phy, regnum, reg, val);
+
+ ret = regmap_write(smi->map, reg, val);
+ if (ret)
+ return ret;
+
+ return 0;
+}
+
+static int rtl8366rb_reset_chip(struct realtek_smi *smi)
+{
+ int timeout = 10;
+ u32 val;
+ int ret;
+
+ realtek_smi_write_reg_noack(smi, RTL8366RB_RESET_CTRL_REG,
+ RTL8366RB_CHIP_CTRL_RESET_HW);
+ do {
+ usleep_range(20000, 25000);
+ ret = regmap_read(smi->map, RTL8366RB_RESET_CTRL_REG, &val);
+ if (ret)
+ return ret;
+
+ if (!(val & RTL8366RB_CHIP_CTRL_RESET_HW))
+ break;
+ } while (--timeout);
+
+ if (!timeout) {
+ dev_err(smi->dev, "timeout waiting for the switch to reset\n");
+ return -EIO;
+ }
+
+ return 0;
+}
+
+static int rtl8366rb_detect(struct realtek_smi *smi)
+{
+ struct device *dev = smi->dev;
+ int ret;
+ u32 val;
+
+ /* Detect device */
+ ret = regmap_read(smi->map, 0x5c, &val);
+ if (ret) {
+ dev_err(dev, "can't get chip ID (%d)\n", ret);
+ return ret;
+ }
+
+ switch (val) {
+ case 0x6027:
+ dev_info(dev, "found an RTL8366S switch\n");
+ dev_err(dev, "this switch is not yet supported, submit patches!\n");
+ return -ENODEV;
+ case 0x5937:
+ dev_info(dev, "found an RTL8366RB switch\n");
+ smi->cpu_port = RTL8366RB_PORT_NUM_CPU;
+ smi->num_ports = RTL8366RB_NUM_PORTS;
+ smi->num_vlan_mc = RTL8366RB_NUM_VLANS;
+ smi->mib_counters = rtl8366rb_mib_counters;
+ smi->num_mib_counters = ARRAY_SIZE(rtl8366rb_mib_counters);
+ break;
+ default:
+ dev_info(dev, "found an Unknown Realtek switch (id=0x%04x)\n",
+ val);
+ break;
+ }
+
+ ret = rtl8366rb_reset_chip(smi);
+ if (ret)
+ return ret;
+
+ return 0;
+}
+
+static const struct dsa_switch_ops rtl8366rb_switch_ops = {
+ .get_tag_protocol = rtl8366_get_tag_protocol,
+ .setup = rtl8366rb_setup,
+ .adjust_link = rtl8366rb_adjust_link,
+ .get_strings = rtl8366_get_strings,
+ .get_ethtool_stats = rtl8366_get_ethtool_stats,
+ .get_sset_count = rtl8366_get_sset_count,
+ .port_vlan_filtering = rtl8366_vlan_filtering,
+ .port_vlan_prepare = rtl8366_vlan_prepare,
+ .port_vlan_add = rtl8366_vlan_add,
+ .port_vlan_del = rtl8366_vlan_del,
+ .port_enable = rtl8366rb_port_enable,
+ .port_disable = rtl8366rb_port_disable,
+};
+
+static const struct realtek_smi_ops rtl8366rb_smi_ops = {
+ .detect = rtl8366rb_detect,
+ .get_vlan_mc = rtl8366rb_get_vlan_mc,
+ .set_vlan_mc = rtl8366rb_set_vlan_mc,
+ .get_vlan_4k = rtl8366rb_get_vlan_4k,
+ .set_vlan_4k = rtl8366rb_set_vlan_4k,
+ .get_mc_index = rtl8366rb_get_mc_index,
+ .set_mc_index = rtl8366rb_set_mc_index,
+ .get_mib_counter = rtl8366rb_get_mib_counter,
+ .is_vlan_valid = rtl8366rb_is_vlan_valid,
+ .enable_vlan = rtl8366rb_enable_vlan,
+ .enable_vlan4k = rtl8366rb_enable_vlan4k,
+ .phy_read = rtl8366rb_phy_read,
+ .phy_write = rtl8366rb_phy_write,
+};
+
+const struct realtek_smi_variant rtl8366rb_variant = {
+ .ds_ops = &rtl8366rb_switch_ops,
+ .ops = &rtl8366rb_smi_ops,
+ .clk_delay = 10,
+ .cmd_read = 0xa9,
+ .cmd_write = 0xa8,
+};
+EXPORT_SYMBOL_GPL(rtl8366rb_variant);
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* DSA driver for:
+ * Vitesse VSC7385 SparX-G5 5+1-port Integrated Gigabit Ethernet Switch
+ * Vitesse VSC7388 SparX-G8 8-port Integrated Gigabit Ethernet Switch
+ * Vitesse VSC7395 SparX-G5e 5+1-port Integrated Gigabit Ethernet Switch
+ * Vitesse VSC7398 SparX-G8e 8-port Integrated Gigabit Ethernet Switch
+ *
+ * These switches have a built-in 8051 CPU and can download and execute a
+ * firmware in this CPU. They can also be configured to use an external CPU
+ * handling the switch in a memory-mapped manner by connecting to that external
+ * CPU's memory bus.
+ *
+ * This driver (currently) only takes control of the switch chip over SPI and
+ * configures it to route packages around when connected to a CPU port. The
+ * chip has embedded PHYs and VLAN support so we model it using DSA.
+ *
+ * Copyright (C) 2018 Linus Wallej <linus.walleij@linaro.org>
+ * Includes portions of code from the firmware uploader by:
+ * Copyright (C) 2009 Gabor Juhos <juhosg@openwrt.org>
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_mdio.h>
+#include <linux/platform_device.h>
+#include <linux/spi/spi.h>
+#include <linux/bitops.h>
+#include <linux/if_bridge.h>
+#include <linux/etherdevice.h>
+#include <linux/gpio/consumer.h>
+#include <linux/gpio/driver.h>
+#include <linux/random.h>
+#include <net/dsa.h>
+
+#define VSC73XX_BLOCK_MAC 0x1 /* Subblocks 0-4, 6 (CPU port) */
+#define VSC73XX_BLOCK_ANALYZER 0x2 /* Only subblock 0 */
+#define VSC73XX_BLOCK_MII 0x3 /* Subblocks 0 and 1 */
+#define VSC73XX_BLOCK_MEMINIT 0x3 /* Only subblock 2 */
+#define VSC73XX_BLOCK_CAPTURE 0x4 /* Only subblock 2 */
+#define VSC73XX_BLOCK_ARBITER 0x5 /* Only subblock 0 */
+#define VSC73XX_BLOCK_SYSTEM 0x7 /* Only subblock 0 */
+
+#define CPU_PORT 6 /* CPU port */
+
+/* MAC Block registers */
+#define VSC73XX_MAC_CFG 0x00
+#define VSC73XX_MACHDXGAP 0x02
+#define VSC73XX_FCCONF 0x04
+#define VSC73XX_FCMACHI 0x08
+#define VSC73XX_FCMACLO 0x0c
+#define VSC73XX_MAXLEN 0x10
+#define VSC73XX_ADVPORTM 0x19
+#define VSC73XX_TXUPDCFG 0x24
+#define VSC73XX_TXQ_SELECT_CFG 0x28
+#define VSC73XX_RXOCT 0x50
+#define VSC73XX_TXOCT 0x51
+#define VSC73XX_C_RX0 0x52
+#define VSC73XX_C_RX1 0x53
+#define VSC73XX_C_RX2 0x54
+#define VSC73XX_C_TX0 0x55
+#define VSC73XX_C_TX1 0x56
+#define VSC73XX_C_TX2 0x57
+#define VSC73XX_C_CFG 0x58
+#define VSC73XX_CAT_DROP 0x6e
+#define VSC73XX_CAT_PR_MISC_L2 0x6f
+#define VSC73XX_CAT_PR_USR_PRIO 0x75
+#define VSC73XX_Q_MISC_CONF 0xdf
+
+/* MAC_CFG register bits */
+#define VSC73XX_MAC_CFG_WEXC_DIS BIT(31)
+#define VSC73XX_MAC_CFG_PORT_RST BIT(29)
+#define VSC73XX_MAC_CFG_TX_EN BIT(28)
+#define VSC73XX_MAC_CFG_SEED_LOAD BIT(27)
+#define VSC73XX_MAC_CFG_SEED_MASK GENMASK(26, 19)
+#define VSC73XX_MAC_CFG_SEED_OFFSET 19
+#define VSC73XX_MAC_CFG_FDX BIT(18)
+#define VSC73XX_MAC_CFG_GIGA_MODE BIT(17)
+#define VSC73XX_MAC_CFG_RX_EN BIT(16)
+#define VSC73XX_MAC_CFG_VLAN_DBLAWR BIT(15)
+#define VSC73XX_MAC_CFG_VLAN_AWR BIT(14)
+#define VSC73XX_MAC_CFG_100_BASE_T BIT(13) /* Not in manual */
+#define VSC73XX_MAC_CFG_TX_IPG_MASK GENMASK(10, 6)
+#define VSC73XX_MAC_CFG_TX_IPG_OFFSET 6
+#define VSC73XX_MAC_CFG_TX_IPG_1000M (6 << VSC73XX_MAC_CFG_TX_IPG_OFFSET)
+#define VSC73XX_MAC_CFG_TX_IPG_100_10M (17 << VSC73XX_MAC_CFG_TX_IPG_OFFSET)
+#define VSC73XX_MAC_CFG_MAC_RX_RST BIT(5)
+#define VSC73XX_MAC_CFG_MAC_TX_RST BIT(4)
+#define VSC73XX_MAC_CFG_CLK_SEL_MASK GENMASK(2, 0)
+#define VSC73XX_MAC_CFG_CLK_SEL_OFFSET 0
+#define VSC73XX_MAC_CFG_CLK_SEL_1000M 1
+#define VSC73XX_MAC_CFG_CLK_SEL_100M 2
+#define VSC73XX_MAC_CFG_CLK_SEL_10M 3
+#define VSC73XX_MAC_CFG_CLK_SEL_EXT 4
+
+#define VSC73XX_MAC_CFG_1000M_F_PHY (VSC73XX_MAC_CFG_FDX | \
+ VSC73XX_MAC_CFG_GIGA_MODE | \
+ VSC73XX_MAC_CFG_TX_IPG_1000M | \
+ VSC73XX_MAC_CFG_CLK_SEL_EXT)
+#define VSC73XX_MAC_CFG_100_10M_F_PHY (VSC73XX_MAC_CFG_FDX | \
+ VSC73XX_MAC_CFG_TX_IPG_100_10M | \
+ VSC73XX_MAC_CFG_CLK_SEL_EXT)
+#define VSC73XX_MAC_CFG_100_10M_H_PHY (VSC73XX_MAC_CFG_TX_IPG_100_10M | \
+ VSC73XX_MAC_CFG_CLK_SEL_EXT)
+#define VSC73XX_MAC_CFG_1000M_F_RGMII (VSC73XX_MAC_CFG_FDX | \
+ VSC73XX_MAC_CFG_GIGA_MODE | \
+ VSC73XX_MAC_CFG_TX_IPG_1000M | \
+ VSC73XX_MAC_CFG_CLK_SEL_1000M)
+#define VSC73XX_MAC_CFG_RESET (VSC73XX_MAC_CFG_PORT_RST | \
+ VSC73XX_MAC_CFG_MAC_RX_RST | \
+ VSC73XX_MAC_CFG_MAC_TX_RST)
+
+/* Flow control register bits */
+#define VSC73XX_FCCONF_ZERO_PAUSE_EN BIT(17)
+#define VSC73XX_FCCONF_FLOW_CTRL_OBEY BIT(16)
+#define VSC73XX_FCCONF_PAUSE_VAL_MASK GENMASK(15, 0)
+
+/* ADVPORTM advanced port setup register bits */
+#define VSC73XX_ADVPORTM_IFG_PPM BIT(7)
+#define VSC73XX_ADVPORTM_EXC_COL_CONT BIT(6)
+#define VSC73XX_ADVPORTM_EXT_PORT BIT(5)
+#define VSC73XX_ADVPORTM_INV_GTX BIT(4)
+#define VSC73XX_ADVPORTM_ENA_GTX BIT(3)
+#define VSC73XX_ADVPORTM_DDR_MODE BIT(2)
+#define VSC73XX_ADVPORTM_IO_LOOPBACK BIT(1)
+#define VSC73XX_ADVPORTM_HOST_LOOPBACK BIT(0)
+
+/* CAT_DROP categorizer frame dropping register bits */
+#define VSC73XX_CAT_DROP_DROP_MC_SMAC_ENA BIT(6)
+#define VSC73XX_CAT_DROP_FWD_CTRL_ENA BIT(4)
+#define VSC73XX_CAT_DROP_FWD_PAUSE_ENA BIT(3)
+#define VSC73XX_CAT_DROP_UNTAGGED_ENA BIT(2)
+#define VSC73XX_CAT_DROP_TAGGED_ENA BIT(1)
+#define VSC73XX_CAT_DROP_NULL_MAC_ENA BIT(0)
+
+#define VSC73XX_Q_MISC_CONF_EXTENT_MEM BIT(31)
+#define VSC73XX_Q_MISC_CONF_EARLY_TX_MASK GENMASK(4, 1)
+#define VSC73XX_Q_MISC_CONF_EARLY_TX_512 (1 << 1)
+#define VSC73XX_Q_MISC_CONF_MAC_PAUSE_MODE BIT(0)
+
+/* Frame analyzer block 2 registers */
+#define VSC73XX_STORMLIMIT 0x02
+#define VSC73XX_ADVLEARN 0x03
+#define VSC73XX_IFLODMSK 0x04
+#define VSC73XX_VLANMASK 0x05
+#define VSC73XX_MACHDATA 0x06
+#define VSC73XX_MACLDATA 0x07
+#define VSC73XX_ANMOVED 0x08
+#define VSC73XX_ANAGEFIL 0x09
+#define VSC73XX_ANEVENTS 0x0a
+#define VSC73XX_ANCNTMASK 0x0b
+#define VSC73XX_ANCNTVAL 0x0c
+#define VSC73XX_LEARNMASK 0x0d
+#define VSC73XX_UFLODMASK 0x0e
+#define VSC73XX_MFLODMASK 0x0f
+#define VSC73XX_RECVMASK 0x10
+#define VSC73XX_AGGRCTRL 0x20
+#define VSC73XX_AGGRMSKS 0x30 /* Until 0x3f */
+#define VSC73XX_DSTMASKS 0x40 /* Until 0x7f */
+#define VSC73XX_SRCMASKS 0x80 /* Until 0x87 */
+#define VSC73XX_CAPENAB 0xa0
+#define VSC73XX_MACACCESS 0xb0
+#define VSC73XX_IPMCACCESS 0xb1
+#define VSC73XX_MACTINDX 0xc0
+#define VSC73XX_VLANACCESS 0xd0
+#define VSC73XX_VLANTIDX 0xe0
+#define VSC73XX_AGENCTRL 0xf0
+#define VSC73XX_CAPRST 0xff
+
+#define VSC73XX_MACACCESS_CPU_COPY BIT(14)
+#define VSC73XX_MACACCESS_FWD_KILL BIT(13)
+#define VSC73XX_MACACCESS_IGNORE_VLAN BIT(12)
+#define VSC73XX_MACACCESS_AGED_FLAG BIT(11)
+#define VSC73XX_MACACCESS_VALID BIT(10)
+#define VSC73XX_MACACCESS_LOCKED BIT(9)
+#define VSC73XX_MACACCESS_DEST_IDX_MASK GENMASK(8, 3)
+#define VSC73XX_MACACCESS_CMD_MASK GENMASK(2, 0)
+#define VSC73XX_MACACCESS_CMD_IDLE 0
+#define VSC73XX_MACACCESS_CMD_LEARN 1
+#define VSC73XX_MACACCESS_CMD_FORGET 2
+#define VSC73XX_MACACCESS_CMD_AGE_TABLE 3
+#define VSC73XX_MACACCESS_CMD_FLUSH_TABLE 4
+#define VSC73XX_MACACCESS_CMD_CLEAR_TABLE 5
+#define VSC73XX_MACACCESS_CMD_READ_ENTRY 6
+#define VSC73XX_MACACCESS_CMD_WRITE_ENTRY 7
+
+#define VSC73XX_VLANACCESS_LEARN_DISABLED BIT(30)
+#define VSC73XX_VLANACCESS_VLAN_MIRROR BIT(29)
+#define VSC73XX_VLANACCESS_VLAN_SRC_CHECK BIT(28)
+#define VSC73XX_VLANACCESS_VLAN_PORT_MASK GENMASK(9, 2)
+#define VSC73XX_VLANACCESS_VLAN_TBL_CMD_MASK GENMASK(2, 0)
+#define VSC73XX_VLANACCESS_VLAN_TBL_CMD_IDLE 0
+#define VSC73XX_VLANACCESS_VLAN_TBL_CMD_READ_ENTRY 1
+#define VSC73XX_VLANACCESS_VLAN_TBL_CMD_WRITE_ENTRY 2
+#define VSC73XX_VLANACCESS_VLAN_TBL_CMD_CLEAR_TABLE 3
+
+/* MII block 3 registers */
+#define VSC73XX_MII_STAT 0x0
+#define VSC73XX_MII_CMD 0x1
+#define VSC73XX_MII_DATA 0x2
+
+/* Arbiter block 5 registers */
+#define VSC73XX_ARBEMPTY 0x0c
+#define VSC73XX_ARBDISC 0x0e
+#define VSC73XX_SBACKWDROP 0x12
+#define VSC73XX_DBACKWDROP 0x13
+#define VSC73XX_ARBBURSTPROB 0x15
+
+/* System block 7 registers */
+#define VSC73XX_ICPU_SIPAD 0x01
+#define VSC73XX_GMIIDELAY 0x05
+#define VSC73XX_ICPU_CTRL 0x10
+#define VSC73XX_ICPU_ADDR 0x11
+#define VSC73XX_ICPU_SRAM 0x12
+#define VSC73XX_HWSEM 0x13
+#define VSC73XX_GLORESET 0x14
+#define VSC73XX_ICPU_MBOX_VAL 0x15
+#define VSC73XX_ICPU_MBOX_SET 0x16
+#define VSC73XX_ICPU_MBOX_CLR 0x17
+#define VSC73XX_CHIPID 0x18
+#define VSC73XX_GPIO 0x34
+
+#define VSC73XX_GMIIDELAY_GMII0_GTXDELAY_NONE 0
+#define VSC73XX_GMIIDELAY_GMII0_GTXDELAY_1_4_NS 1
+#define VSC73XX_GMIIDELAY_GMII0_GTXDELAY_1_7_NS 2
+#define VSC73XX_GMIIDELAY_GMII0_GTXDELAY_2_0_NS 3
+
+#define VSC73XX_GMIIDELAY_GMII0_RXDELAY_NONE (0 << 4)
+#define VSC73XX_GMIIDELAY_GMII0_RXDELAY_1_4_NS (1 << 4)
+#define VSC73XX_GMIIDELAY_GMII0_RXDELAY_1_7_NS (2 << 4)
+#define VSC73XX_GMIIDELAY_GMII0_RXDELAY_2_0_NS (3 << 4)
+
+#define VSC73XX_ICPU_CTRL_WATCHDOG_RST BIT(31)
+#define VSC73XX_ICPU_CTRL_CLK_DIV_MASK GENMASK(12, 8)
+#define VSC73XX_ICPU_CTRL_SRST_HOLD BIT(7)
+#define VSC73XX_ICPU_CTRL_ICPU_PI_EN BIT(6)
+#define VSC73XX_ICPU_CTRL_BOOT_EN BIT(3)
+#define VSC73XX_ICPU_CTRL_EXT_ACC_EN BIT(2)
+#define VSC73XX_ICPU_CTRL_CLK_EN BIT(1)
+#define VSC73XX_ICPU_CTRL_SRST BIT(0)
+
+#define VSC73XX_CHIPID_ID_SHIFT 12
+#define VSC73XX_CHIPID_ID_MASK 0xffff
+#define VSC73XX_CHIPID_REV_SHIFT 28
+#define VSC73XX_CHIPID_REV_MASK 0xf
+#define VSC73XX_CHIPID_ID_7385 0x7385
+#define VSC73XX_CHIPID_ID_7388 0x7388
+#define VSC73XX_CHIPID_ID_7395 0x7395
+#define VSC73XX_CHIPID_ID_7398 0x7398
+
+#define VSC73XX_GLORESET_STROBE BIT(4)
+#define VSC73XX_GLORESET_ICPU_LOCK BIT(3)
+#define VSC73XX_GLORESET_MEM_LOCK BIT(2)
+#define VSC73XX_GLORESET_PHY_RESET BIT(1)
+#define VSC73XX_GLORESET_MASTER_RESET BIT(0)
+
+#define VSC73XX_CMD_MODE_READ 0
+#define VSC73XX_CMD_MODE_WRITE 1
+#define VSC73XX_CMD_MODE_SHIFT 4
+#define VSC73XX_CMD_BLOCK_SHIFT 5
+#define VSC73XX_CMD_BLOCK_MASK 0x7
+#define VSC73XX_CMD_SUBBLOCK_MASK 0xf
+
+#define VSC7385_CLOCK_DELAY ((3 << 4) | 3)
+#define VSC7385_CLOCK_DELAY_MASK ((3 << 4) | 3)
+
+#define VSC73XX_ICPU_CTRL_STOP (VSC73XX_ICPU_CTRL_SRST_HOLD | \
+ VSC73XX_ICPU_CTRL_BOOT_EN | \
+ VSC73XX_ICPU_CTRL_EXT_ACC_EN)
+
+#define VSC73XX_ICPU_CTRL_START (VSC73XX_ICPU_CTRL_CLK_DIV | \
+ VSC73XX_ICPU_CTRL_BOOT_EN | \
+ VSC73XX_ICPU_CTRL_CLK_EN | \
+ VSC73XX_ICPU_CTRL_SRST)
+
+/**
+ * struct vsc73xx - VSC73xx state container
+ */
+struct vsc73xx {
+ struct device *dev;
+ struct gpio_desc *reset;
+ struct spi_device *spi;
+ struct dsa_switch *ds;
+ struct gpio_chip gc;
+ u16 chipid;
+ u8 addr[ETH_ALEN];
+ struct mutex lock; /* Protects SPI traffic */
+};
+
+#define IS_7385(a) ((a)->chipid == VSC73XX_CHIPID_ID_7385)
+#define IS_7388(a) ((a)->chipid == VSC73XX_CHIPID_ID_7388)
+#define IS_7395(a) ((a)->chipid == VSC73XX_CHIPID_ID_7395)
+#define IS_7398(a) ((a)->chipid == VSC73XX_CHIPID_ID_7398)
+#define IS_739X(a) (IS_7395(a) || IS_7398(a))
+
+struct vsc73xx_counter {
+ u8 counter;
+ const char *name;
+};
+
+/* Counters are named according to the MIB standards where applicable.
+ * Some counters are custom, non-standard. The standard counters are
+ * named in accordance with RFC2819, RFC2021 and IEEE Std 802.3-2002 Annex
+ * 30A Counters.
+ */
+static const struct vsc73xx_counter vsc73xx_rx_counters[] = {
+ { 0, "RxEtherStatsPkts" },
+ { 1, "RxBroadcast+MulticastPkts" }, /* non-standard counter */
+ { 2, "RxTotalErrorPackets" }, /* non-standard counter */
+ { 3, "RxEtherStatsBroadcastPkts" },
+ { 4, "RxEtherStatsMulticastPkts" },
+ { 5, "RxEtherStatsPkts64Octets" },
+ { 6, "RxEtherStatsPkts65to127Octets" },
+ { 7, "RxEtherStatsPkts128to255Octets" },
+ { 8, "RxEtherStatsPkts256to511Octets" },
+ { 9, "RxEtherStatsPkts512to1023Octets" },
+ { 10, "RxEtherStatsPkts1024to1518Octets" },
+ { 11, "RxJumboFrames" }, /* non-standard counter */
+ { 12, "RxaPauseMACControlFramesTransmitted" },
+ { 13, "RxFIFODrops" }, /* non-standard counter */
+ { 14, "RxBackwardDrops" }, /* non-standard counter */
+ { 15, "RxClassifierDrops" }, /* non-standard counter */
+ { 16, "RxEtherStatsCRCAlignErrors" },
+ { 17, "RxEtherStatsUndersizePkts" },
+ { 18, "RxEtherStatsOversizePkts" },
+ { 19, "RxEtherStatsFragments" },
+ { 20, "RxEtherStatsJabbers" },
+ { 21, "RxaMACControlFramesReceived" },
+ /* 22-24 are undefined */
+ { 25, "RxaFramesReceivedOK" },
+ { 26, "RxQoSClass0" }, /* non-standard counter */
+ { 27, "RxQoSClass1" }, /* non-standard counter */
+ { 28, "RxQoSClass2" }, /* non-standard counter */
+ { 29, "RxQoSClass3" }, /* non-standard counter */
+};
+
+static const struct vsc73xx_counter vsc73xx_tx_counters[] = {
+ { 0, "TxEtherStatsPkts" },
+ { 1, "TxBroadcast+MulticastPkts" }, /* non-standard counter */
+ { 2, "TxTotalErrorPackets" }, /* non-standard counter */
+ { 3, "TxEtherStatsBroadcastPkts" },
+ { 4, "TxEtherStatsMulticastPkts" },
+ { 5, "TxEtherStatsPkts64Octets" },
+ { 6, "TxEtherStatsPkts65to127Octets" },
+ { 7, "TxEtherStatsPkts128to255Octets" },
+ { 8, "TxEtherStatsPkts256to511Octets" },
+ { 9, "TxEtherStatsPkts512to1023Octets" },
+ { 10, "TxEtherStatsPkts1024to1518Octets" },
+ { 11, "TxJumboFrames" }, /* non-standard counter */
+ { 12, "TxaPauseMACControlFramesTransmitted" },
+ { 13, "TxFIFODrops" }, /* non-standard counter */
+ { 14, "TxDrops" }, /* non-standard counter */
+ { 15, "TxEtherStatsCollisions" },
+ { 16, "TxEtherStatsCRCAlignErrors" },
+ { 17, "TxEtherStatsUndersizePkts" },
+ { 18, "TxEtherStatsOversizePkts" },
+ { 19, "TxEtherStatsFragments" },
+ { 20, "TxEtherStatsJabbers" },
+ /* 21-24 are undefined */
+ { 25, "TxaFramesReceivedOK" },
+ { 26, "TxQoSClass0" }, /* non-standard counter */
+ { 27, "TxQoSClass1" }, /* non-standard counter */
+ { 28, "TxQoSClass2" }, /* non-standard counter */
+ { 29, "TxQoSClass3" }, /* non-standard counter */
+};
+
+static int vsc73xx_is_addr_valid(u8 block, u8 subblock)
+{
+ switch (block) {
+ case VSC73XX_BLOCK_MAC:
+ switch (subblock) {
+ case 0 ... 4:
+ case 6:
+ return 1;
+ }
+ break;
+
+ case VSC73XX_BLOCK_ANALYZER:
+ case VSC73XX_BLOCK_SYSTEM:
+ switch (subblock) {
+ case 0:
+ return 1;
+ }
+ break;
+
+ case VSC73XX_BLOCK_MII:
+ case VSC73XX_BLOCK_CAPTURE:
+ case VSC73XX_BLOCK_ARBITER:
+ switch (subblock) {
+ case 0 ... 1:
+ return 1;
+ }
+ break;
+ }
+
+ return 0;
+}
+
+static u8 vsc73xx_make_addr(u8 mode, u8 block, u8 subblock)
+{
+ u8 ret;
+
+ ret = (block & VSC73XX_CMD_BLOCK_MASK) << VSC73XX_CMD_BLOCK_SHIFT;
+ ret |= (mode & 1) << VSC73XX_CMD_MODE_SHIFT;
+ ret |= subblock & VSC73XX_CMD_SUBBLOCK_MASK;
+
+ return ret;
+}
+
+static int vsc73xx_read(struct vsc73xx *vsc, u8 block, u8 subblock, u8 reg,
+ u32 *val)
+{
+ struct spi_transfer t[2];
+ struct spi_message m;
+ u8 cmd[4];
+ u8 buf[4];
+ int ret;
+
+ if (!vsc73xx_is_addr_valid(block, subblock))
+ return -EINVAL;
+
+ spi_message_init(&m);
+
+ memset(&t, 0, sizeof(t));
+
+ t[0].tx_buf = cmd;
+ t[0].len = sizeof(cmd);
+ spi_message_add_tail(&t[0], &m);
+
+ t[1].rx_buf = buf;
+ t[1].len = sizeof(buf);
+ spi_message_add_tail(&t[1], &m);
+
+ cmd[0] = vsc73xx_make_addr(VSC73XX_CMD_MODE_READ, block, subblock);
+ cmd[1] = reg;
+ cmd[2] = 0;
+ cmd[3] = 0;
+
+ mutex_lock(&vsc->lock);
+ ret = spi_sync(vsc->spi, &m);
+ mutex_unlock(&vsc->lock);
+
+ if (ret)
+ return ret;
+
+ *val = (buf[0] << 24) | (buf[1] << 16) | (buf[2] << 8) | buf[3];
+
+ return 0;
+}
+
+static int vsc73xx_write(struct vsc73xx *vsc, u8 block, u8 subblock, u8 reg,
+ u32 val)
+{
+ struct spi_transfer t[2];
+ struct spi_message m;
+ u8 cmd[2];
+ u8 buf[4];
+ int ret;
+
+ if (!vsc73xx_is_addr_valid(block, subblock))
+ return -EINVAL;
+
+ spi_message_init(&m);
+
+ memset(&t, 0, sizeof(t));
+
+ t[0].tx_buf = cmd;
+ t[0].len = sizeof(cmd);
+ spi_message_add_tail(&t[0], &m);
+
+ t[1].tx_buf = buf;
+ t[1].len = sizeof(buf);
+ spi_message_add_tail(&t[1], &m);
+
+ cmd[0] = vsc73xx_make_addr(VSC73XX_CMD_MODE_WRITE, block, subblock);
+ cmd[1] = reg;
+
+ buf[0] = (val >> 24) & 0xff;
+ buf[1] = (val >> 16) & 0xff;
+ buf[2] = (val >> 8) & 0xff;
+ buf[3] = val & 0xff;
+
+ mutex_lock(&vsc->lock);
+ ret = spi_sync(vsc->spi, &m);
+ mutex_unlock(&vsc->lock);
+
+ return ret;
+}
+
+static int vsc73xx_update_bits(struct vsc73xx *vsc, u8 block, u8 subblock,
+ u8 reg, u32 mask, u32 val)
+{
+ u32 tmp, orig;
+ int ret;
+
+ /* Same read-modify-write algorithm as e.g. regmap */
+ ret = vsc73xx_read(vsc, block, subblock, reg, &orig);
+ if (ret)
+ return ret;
+ tmp = orig & ~mask;
+ tmp |= val & mask;
+ return vsc73xx_write(vsc, block, subblock, reg, tmp);
+}
+
+static int vsc73xx_detect(struct vsc73xx *vsc)
+{
+ bool icpu_si_boot_en;
+ bool icpu_pi_en;
+ u32 val;
+ u32 rev;
+ int ret;
+ u32 id;
+
+ ret = vsc73xx_read(vsc, VSC73XX_BLOCK_SYSTEM, 0,
+ VSC73XX_ICPU_MBOX_VAL, &val);
+ if (ret) {
+ dev_err(vsc->dev, "unable to read mailbox (%d)\n", ret);
+ return ret;
+ }
+
+ if (val == 0xffffffff) {
+ dev_info(vsc->dev, "chip seems dead, assert reset\n");
+ gpiod_set_value_cansleep(vsc->reset, 1);
+ /* Reset pulse should be 20ns minimum, according to datasheet
+ * table 245, so 10us should be fine
+ */
+ usleep_range(10, 100);
+ gpiod_set_value_cansleep(vsc->reset, 0);
+ /* Wait 20ms according to datasheet table 245 */
+ msleep(20);
+
+ ret = vsc73xx_read(vsc, VSC73XX_BLOCK_SYSTEM, 0,
+ VSC73XX_ICPU_MBOX_VAL, &val);
+ if (val == 0xffffffff) {
+ dev_err(vsc->dev, "seems not to help, giving up\n");
+ return -ENODEV;
+ }
+ }
+
+ ret = vsc73xx_read(vsc, VSC73XX_BLOCK_SYSTEM, 0,
+ VSC73XX_CHIPID, &val);
+ if (ret) {
+ dev_err(vsc->dev, "unable to read chip id (%d)\n", ret);
+ return ret;
+ }
+
+ id = (val >> VSC73XX_CHIPID_ID_SHIFT) &
+ VSC73XX_CHIPID_ID_MASK;
+ switch (id) {
+ case VSC73XX_CHIPID_ID_7385:
+ case VSC73XX_CHIPID_ID_7388:
+ case VSC73XX_CHIPID_ID_7395:
+ case VSC73XX_CHIPID_ID_7398:
+ break;
+ default:
+ dev_err(vsc->dev, "unsupported chip, id=%04x\n", id);
+ return -ENODEV;
+ }
+
+ vsc->chipid = id;
+ rev = (val >> VSC73XX_CHIPID_REV_SHIFT) &
+ VSC73XX_CHIPID_REV_MASK;
+ dev_info(vsc->dev, "VSC%04X (rev: %d) switch found\n", id, rev);
+
+ ret = vsc73xx_read(vsc, VSC73XX_BLOCK_SYSTEM, 0,
+ VSC73XX_ICPU_CTRL, &val);
+ if (ret) {
+ dev_err(vsc->dev, "unable to read iCPU control\n");
+ return ret;
+ }
+
+ /* The iCPU can always be used but can boot in different ways.
+ * If it is initially disabled and has no external memory,
+ * we are in control and can do whatever we like, else we
+ * are probably in trouble (we need some way to communicate
+ * with the running firmware) so we bail out for now.
+ */
+ icpu_pi_en = !!(val & VSC73XX_ICPU_CTRL_ICPU_PI_EN);
+ icpu_si_boot_en = !!(val & VSC73XX_ICPU_CTRL_BOOT_EN);
+ if (icpu_si_boot_en && icpu_pi_en) {
+ dev_err(vsc->dev,
+ "iCPU enabled boots from SI, has external memory\n");
+ dev_err(vsc->dev, "no idea how to deal with this\n");
+ return -ENODEV;
+ }
+ if (icpu_si_boot_en && !icpu_pi_en) {
+ dev_err(vsc->dev,
+ "iCPU enabled boots from SI, no external memory\n");
+ dev_err(vsc->dev, "no idea how to deal with this\n");
+ return -ENODEV;
+ }
+ if (!icpu_si_boot_en && icpu_pi_en) {
+ dev_err(vsc->dev,
+ "iCPU enabled, boots from PI external memory\n");
+ dev_err(vsc->dev, "no idea how to deal with this\n");
+ return -ENODEV;
+ }
+ /* !icpu_si_boot_en && !cpu_pi_en */
+ dev_info(vsc->dev, "iCPU disabled, no external memory\n");
+
+ return 0;
+}
+
+static int vsc73xx_phy_read(struct dsa_switch *ds, int phy, int regnum)
+{
+ struct vsc73xx *vsc = ds->priv;
+ u32 cmd;
+ u32 val;
+ int ret;
+
+ /* Setting bit 26 means "read" */
+ cmd = BIT(26) | (phy << 21) | (regnum << 16);
+ ret = vsc73xx_write(vsc, VSC73XX_BLOCK_MII, 0, 1, cmd);
+ if (ret)
+ return ret;
+ msleep(2);
+ ret = vsc73xx_read(vsc, VSC73XX_BLOCK_MII, 0, 2, &val);
+ if (ret)
+ return ret;
+ if (val & BIT(16)) {
+ dev_err(vsc->dev, "reading reg %02x from phy%d failed\n",
+ regnum, phy);
+ return -EIO;
+ }
+ val &= 0xFFFFU;
+
+ dev_dbg(vsc->dev, "read reg %02x from phy%d = %04x\n",
+ regnum, phy, val);
+
+ return val;
+}
+
+static int vsc73xx_phy_write(struct dsa_switch *ds, int phy, int regnum,
+ u16 val)
+{
+ struct vsc73xx *vsc = ds->priv;
+ u32 cmd;
+ int ret;
+
+ /* It was found through tedious experiments that this router
+ * chip really hates to have it's PHYs reset. They
+ * never recover if that happens: autonegotiation stops
+ * working after a reset. Just filter out this command.
+ * (Resetting the whole chip is OK.)
+ */
+ if (regnum == 0 && (val & BIT(15))) {
+ dev_info(vsc->dev, "reset PHY - disallowed\n");
+ return 0;
+ }
+
+ cmd = (phy << 21) | (regnum << 16);
+ ret = vsc73xx_write(vsc, VSC73XX_BLOCK_MII, 0, 1, cmd);
+ if (ret)
+ return ret;
+
+ dev_dbg(vsc->dev, "write %04x to reg %02x in phy%d\n",
+ val, regnum, phy);
+ return 0;
+}
+
+static enum dsa_tag_protocol vsc73xx_get_tag_protocol(struct dsa_switch *ds,
+ int port)
+{
+ /* The switch internally uses a 8 byte header with length,
+ * source port, tag, LPA and priority. This is supposedly
+ * only accessible when operating the switch using the internal
+ * CPU or with an external CPU mapping the device in, but not
+ * when operating the switch over SPI and putting frames in/out
+ * on port 6 (the CPU port). So far we must assume that we
+ * cannot access the tag. (See "Internal frame header" section
+ * 3.9.1 in the manual.)
+ */
+ return DSA_TAG_PROTO_NONE;
+}
+
+static int vsc73xx_setup(struct dsa_switch *ds)
+{
+ struct vsc73xx *vsc = ds->priv;
+ int i;
+
+ dev_info(vsc->dev, "set up the switch\n");
+
+ /* Issue RESET */
+ vsc73xx_write(vsc, VSC73XX_BLOCK_SYSTEM, 0, VSC73XX_GLORESET,
+ VSC73XX_GLORESET_MASTER_RESET);
+ usleep_range(125, 200);
+
+ /* Initialize memory, initialize RAM bank 0..15 except 6 and 7
+ * This sequence appears in the
+ * VSC7385 SparX-G5 datasheet section 6.6.1
+ * VSC7395 SparX-G5e datasheet section 6.6.1
+ * "initialization sequence".
+ * No explanation is given to the 0x1010400 magic number.
+ */
+ for (i = 0; i <= 15; i++) {
+ if (i != 6 && i != 7) {
+ vsc73xx_write(vsc, VSC73XX_BLOCK_MEMINIT,
+ 2,
+ 0, 0x1010400 + i);
+ mdelay(1);
+ }
+ }
+ mdelay(30);
+
+ /* Clear MAC table */
+ vsc73xx_write(vsc, VSC73XX_BLOCK_ANALYZER, 0,
+ VSC73XX_MACACCESS,
+ VSC73XX_MACACCESS_CMD_CLEAR_TABLE);
+
+ /* Clear VLAN table */
+ vsc73xx_write(vsc, VSC73XX_BLOCK_ANALYZER, 0,
+ VSC73XX_VLANACCESS,
+ VSC73XX_VLANACCESS_VLAN_TBL_CMD_CLEAR_TABLE);
+
+ msleep(40);
+
+ /* Use 20KiB buffers on all ports on VSC7395
+ * The VSC7385 has 16KiB buffers and that is the
+ * default if we don't set this up explicitly.
+ * Port "31" is "all ports".
+ */
+ if (IS_739X(vsc))
+ vsc73xx_write(vsc, VSC73XX_BLOCK_MAC, 0x1f,
+ VSC73XX_Q_MISC_CONF,
+ VSC73XX_Q_MISC_CONF_EXTENT_MEM);
+
+ /* Put all ports into reset until enabled */
+ for (i = 0; i < 7; i++) {
+ if (i == 5)
+ continue;
+ vsc73xx_write(vsc, VSC73XX_BLOCK_MAC, 4,
+ VSC73XX_MAC_CFG, VSC73XX_MAC_CFG_RESET);
+ }
+
+ /* MII delay, set both GTX and RX delay to 2 ns */
+ vsc73xx_write(vsc, VSC73XX_BLOCK_SYSTEM, 0, VSC73XX_GMIIDELAY,
+ VSC73XX_GMIIDELAY_GMII0_GTXDELAY_2_0_NS |
+ VSC73XX_GMIIDELAY_GMII0_RXDELAY_2_0_NS);
+ /* Enable reception of frames on all ports */
+ vsc73xx_write(vsc, VSC73XX_BLOCK_ANALYZER, 0, VSC73XX_RECVMASK,
+ 0x5f);
+ /* IP multicast flood mask (table 144) */
+ vsc73xx_write(vsc, VSC73XX_BLOCK_ANALYZER, 0, VSC73XX_IFLODMSK,
+ 0xff);
+
+ mdelay(50);
+
+ /* Release reset from the internal PHYs */
+ vsc73xx_write(vsc, VSC73XX_BLOCK_SYSTEM, 0, VSC73XX_GLORESET,
+ VSC73XX_GLORESET_PHY_RESET);
+
+ udelay(4);
+
+ return 0;
+}
+
+static void vsc73xx_init_port(struct vsc73xx *vsc, int port)
+{
+ u32 val;
+
+ /* MAC configure, first reset the port and then write defaults */
+ vsc73xx_write(vsc, VSC73XX_BLOCK_MAC,
+ port,
+ VSC73XX_MAC_CFG,
+ VSC73XX_MAC_CFG_RESET);
+
+ /* Take up the port in 1Gbit mode by default, this will be
+ * augmented after auto-negotiation on the PHY-facing
+ * ports.
+ */
+ if (port == CPU_PORT)
+ val = VSC73XX_MAC_CFG_1000M_F_RGMII;
+ else
+ val = VSC73XX_MAC_CFG_1000M_F_PHY;
+
+ vsc73xx_write(vsc, VSC73XX_BLOCK_MAC,
+ port,
+ VSC73XX_MAC_CFG,
+ val |
+ VSC73XX_MAC_CFG_TX_EN |
+ VSC73XX_MAC_CFG_RX_EN);
+
+ /* Max length, we can do up to 9.6 KiB, so allow that.
+ * According to application not "VSC7398 Jumbo Frames" setting
+ * up the MTU to 9.6 KB does not affect the performance on standard
+ * frames, so just enable it. It is clear from the application note
+ * that "9.6 kilobytes" == 9600 bytes.
+ */
+ vsc73xx_write(vsc, VSC73XX_BLOCK_MAC,
+ port,
+ VSC73XX_MAXLEN, 9600);
+
+ /* Flow control for the CPU port:
+ * Use a zero delay pause frame when pause condition is left
+ * Obey pause control frames
+ */
+ vsc73xx_write(vsc, VSC73XX_BLOCK_MAC,
+ port,
+ VSC73XX_FCCONF,
+ VSC73XX_FCCONF_ZERO_PAUSE_EN |
+ VSC73XX_FCCONF_FLOW_CTRL_OBEY);
+
+ /* Issue pause control frames on PHY facing ports.
+ * Allow early initiation of MAC transmission if the amount
+ * of egress data is below 512 bytes on CPU port.
+ * FIXME: enable 20KiB buffers?
+ */
+ if (port == CPU_PORT)
+ val = VSC73XX_Q_MISC_CONF_EARLY_TX_512;
+ else
+ val = VSC73XX_Q_MISC_CONF_MAC_PAUSE_MODE;
+ val |= VSC73XX_Q_MISC_CONF_EXTENT_MEM;
+ vsc73xx_write(vsc, VSC73XX_BLOCK_MAC,
+ port,
+ VSC73XX_Q_MISC_CONF,
+ val);
+
+ /* Flow control MAC: a MAC address used in flow control frames */
+ val = (vsc->addr[5] << 16) | (vsc->addr[4] << 8) | (vsc->addr[3]);
+ vsc73xx_write(vsc, VSC73XX_BLOCK_MAC,
+ port,
+ VSC73XX_FCMACHI,
+ val);
+ val = (vsc->addr[2] << 16) | (vsc->addr[1] << 8) | (vsc->addr[0]);
+ vsc73xx_write(vsc, VSC73XX_BLOCK_MAC,
+ port,
+ VSC73XX_FCMACLO,
+ val);
+
+ /* Tell the categorizer to forward pause frames, not control
+ * frame. Do not drop anything.
+ */
+ vsc73xx_write(vsc, VSC73XX_BLOCK_MAC,
+ port,
+ VSC73XX_CAT_DROP,
+ VSC73XX_CAT_DROP_FWD_PAUSE_ENA);
+
+ /* Clear all counters */
+ vsc73xx_write(vsc, VSC73XX_BLOCK_MAC,
+ port, VSC73XX_C_RX0, 0);
+}
+
+static void vsc73xx_adjust_enable_port(struct vsc73xx *vsc,
+ int port, struct phy_device *phydev,
+ u32 initval)
+{
+ u32 val = initval;
+ u8 seed;
+
+ /* Reset this port FIXME: break out subroutine */
+ val |= VSC73XX_MAC_CFG_RESET;
+ vsc73xx_write(vsc, VSC73XX_BLOCK_MAC, port, VSC73XX_MAC_CFG, val);
+
+ /* Seed the port randomness with randomness */
+ get_random_bytes(&seed, 1);
+ val |= seed << VSC73XX_MAC_CFG_SEED_OFFSET;
+ val |= VSC73XX_MAC_CFG_SEED_LOAD;
+ val |= VSC73XX_MAC_CFG_WEXC_DIS;
+ vsc73xx_write(vsc, VSC73XX_BLOCK_MAC, port, VSC73XX_MAC_CFG, val);
+
+ /* Flow control for the PHY facing ports:
+ * Use a zero delay pause frame when pause condition is left
+ * Obey pause control frames
+ * When generating pause frames, use 0xff as pause value
+ */
+ vsc73xx_write(vsc, VSC73XX_BLOCK_MAC, port, VSC73XX_FCCONF,
+ VSC73XX_FCCONF_ZERO_PAUSE_EN |
+ VSC73XX_FCCONF_FLOW_CTRL_OBEY |
+ 0xff);
+
+ /* Disallow backward dropping of frames from this port */
+ vsc73xx_update_bits(vsc, VSC73XX_BLOCK_ARBITER, 0,
+ VSC73XX_SBACKWDROP, BIT(port), 0);
+
+ /* Enable TX, RX, deassert reset, stop loading seed */
+ vsc73xx_update_bits(vsc, VSC73XX_BLOCK_MAC, port,
+ VSC73XX_MAC_CFG,
+ VSC73XX_MAC_CFG_RESET | VSC73XX_MAC_CFG_SEED_LOAD |
+ VSC73XX_MAC_CFG_TX_EN | VSC73XX_MAC_CFG_RX_EN,
+ VSC73XX_MAC_CFG_TX_EN | VSC73XX_MAC_CFG_RX_EN);
+}
+
+static void vsc73xx_adjust_link(struct dsa_switch *ds, int port,
+ struct phy_device *phydev)
+{
+ struct vsc73xx *vsc = ds->priv;
+ u32 val;
+
+ /* Special handling of the CPU-facing port */
+ if (port == CPU_PORT) {
+ /* Other ports are already initialized but not this one */
+ vsc73xx_init_port(vsc, CPU_PORT);
+ /* Select the external port for this interface (EXT_PORT)
+ * Enable the GMII GTX external clock
+ * Use double data rate (DDR mode)
+ */
+ vsc73xx_write(vsc, VSC73XX_BLOCK_MAC,
+ CPU_PORT,
+ VSC73XX_ADVPORTM,
+ VSC73XX_ADVPORTM_EXT_PORT |
+ VSC73XX_ADVPORTM_ENA_GTX |
+ VSC73XX_ADVPORTM_DDR_MODE);
+ }
+
+ /* This is the MAC confiuration that always need to happen
+ * after a PHY or the CPU port comes up or down.
+ */
+ if (!phydev->link) {
+ int maxloop = 10;
+
+ dev_dbg(vsc->dev, "port %d: went down\n",
+ port);
+
+ /* Disable RX on this port */
+ vsc73xx_update_bits(vsc, VSC73XX_BLOCK_MAC, port,
+ VSC73XX_MAC_CFG,
+ VSC73XX_MAC_CFG_RX_EN, 0);
+
+ /* Discard packets */
+ vsc73xx_update_bits(vsc, VSC73XX_BLOCK_ARBITER, 0,
+ VSC73XX_ARBDISC, BIT(port), BIT(port));
+
+ /* Wait until queue is empty */
+ vsc73xx_read(vsc, VSC73XX_BLOCK_ARBITER, 0,
+ VSC73XX_ARBEMPTY, &val);
+ while (!(val & BIT(port))) {
+ msleep(1);
+ vsc73xx_read(vsc, VSC73XX_BLOCK_ARBITER, 0,
+ VSC73XX_ARBEMPTY, &val);
+ if (--maxloop == 0) {
+ dev_err(vsc->dev,
+ "timeout waiting for block arbiter\n");
+ /* Continue anyway */
+ break;
+ }
+ }
+
+ /* Put this port into reset */
+ vsc73xx_write(vsc, VSC73XX_BLOCK_MAC, port, VSC73XX_MAC_CFG,
+ VSC73XX_MAC_CFG_RESET);
+
+ /* Accept packets again */
+ vsc73xx_update_bits(vsc, VSC73XX_BLOCK_ARBITER, 0,
+ VSC73XX_ARBDISC, BIT(port), 0);
+
+ /* Allow backward dropping of frames from this port */
+ vsc73xx_update_bits(vsc, VSC73XX_BLOCK_ARBITER, 0,
+ VSC73XX_SBACKWDROP, BIT(port), BIT(port));
+
+ /* Receive mask (disable forwarding) */
+ vsc73xx_update_bits(vsc, VSC73XX_BLOCK_ANALYZER, 0,
+ VSC73XX_RECVMASK, BIT(port), 0);
+
+ return;
+ }
+
+ /* Figure out what speed was negotiated */
+ if (phydev->speed == SPEED_1000) {
+ dev_dbg(vsc->dev, "port %d: 1000 Mbit mode full duplex\n",
+ port);
+
+ /* Set up default for internal port or external RGMII */
+ if (phydev->interface == PHY_INTERFACE_MODE_RGMII)
+ val = VSC73XX_MAC_CFG_1000M_F_RGMII;
+ else
+ val = VSC73XX_MAC_CFG_1000M_F_PHY;
+ vsc73xx_adjust_enable_port(vsc, port, phydev, val);
+ } else if (phydev->speed == SPEED_100) {
+ if (phydev->duplex == DUPLEX_FULL) {
+ val = VSC73XX_MAC_CFG_100_10M_F_PHY;
+ dev_dbg(vsc->dev,
+ "port %d: 100 Mbit full duplex mode\n",
+ port);
+ } else {
+ val = VSC73XX_MAC_CFG_100_10M_H_PHY;
+ dev_dbg(vsc->dev,
+ "port %d: 100 Mbit half duplex mode\n",
+ port);
+ }
+ vsc73xx_adjust_enable_port(vsc, port, phydev, val);
+ } else if (phydev->speed == SPEED_10) {
+ if (phydev->duplex == DUPLEX_FULL) {
+ val = VSC73XX_MAC_CFG_100_10M_F_PHY;
+ dev_dbg(vsc->dev,
+ "port %d: 10 Mbit full duplex mode\n",
+ port);
+ } else {
+ val = VSC73XX_MAC_CFG_100_10M_H_PHY;
+ dev_dbg(vsc->dev,
+ "port %d: 10 Mbit half duplex mode\n",
+ port);
+ }
+ vsc73xx_adjust_enable_port(vsc, port, phydev, val);
+ } else {
+ dev_err(vsc->dev,
+ "could not adjust link: unknown speed\n");
+ }
+
+ /* Enable port (forwarding) in the receieve mask */
+ vsc73xx_update_bits(vsc, VSC73XX_BLOCK_ANALYZER, 0,
+ VSC73XX_RECVMASK, BIT(port), BIT(port));
+}
+
+static int vsc73xx_port_enable(struct dsa_switch *ds, int port,
+ struct phy_device *phy)
+{
+ struct vsc73xx *vsc = ds->priv;
+
+ dev_info(vsc->dev, "enable port %d\n", port);
+ vsc73xx_init_port(vsc, port);
+
+ return 0;
+}
+
+static void vsc73xx_port_disable(struct dsa_switch *ds, int port,
+ struct phy_device *phy)
+{
+ struct vsc73xx *vsc = ds->priv;
+
+ /* Just put the port into reset */
+ vsc73xx_write(vsc, VSC73XX_BLOCK_MAC, port,
+ VSC73XX_MAC_CFG, VSC73XX_MAC_CFG_RESET);
+}
+
+static const struct vsc73xx_counter *
+vsc73xx_find_counter(struct vsc73xx *vsc,
+ u8 counter,
+ bool tx)
+{
+ const struct vsc73xx_counter *cnts;
+ int num_cnts;
+ int i;
+
+ if (tx) {
+ cnts = vsc73xx_tx_counters;
+ num_cnts = ARRAY_SIZE(vsc73xx_tx_counters);
+ } else {
+ cnts = vsc73xx_rx_counters;
+ num_cnts = ARRAY_SIZE(vsc73xx_rx_counters);
+ }
+
+ for (i = 0; i < num_cnts; i++) {
+ const struct vsc73xx_counter *cnt;
+
+ cnt = &cnts[i];
+ if (cnt->counter == counter)
+ return cnt;
+ }
+
+ return NULL;
+}
+
+static void vsc73xx_get_strings(struct dsa_switch *ds, int port, u32 stringset,
+ uint8_t *data)
+{
+ const struct vsc73xx_counter *cnt;
+ struct vsc73xx *vsc = ds->priv;
+ u8 indices[6];
+ int i, j;
+ u32 val;
+ int ret;
+
+ if (stringset != ETH_SS_STATS)
+ return;
+
+ ret = vsc73xx_read(vsc, VSC73XX_BLOCK_MAC, port,
+ VSC73XX_C_CFG, &val);
+ if (ret)
+ return;
+
+ indices[0] = (val & 0x1f); /* RX counter 0 */
+ indices[1] = ((val >> 5) & 0x1f); /* RX counter 1 */
+ indices[2] = ((val >> 10) & 0x1f); /* RX counter 2 */
+ indices[3] = ((val >> 16) & 0x1f); /* TX counter 0 */
+ indices[4] = ((val >> 21) & 0x1f); /* TX counter 1 */
+ indices[5] = ((val >> 26) & 0x1f); /* TX counter 2 */
+
+ /* The first counters is the RX octets */
+ j = 0;
+ strncpy(data + j * ETH_GSTRING_LEN,
+ "RxEtherStatsOctets", ETH_GSTRING_LEN);
+ j++;
+
+ /* Each port supports recording 3 RX counters and 3 TX counters,
+ * figure out what counters we use in this set-up and return the
+ * names of them. The hardware default counters will be number of
+ * packets on RX/TX, combined broadcast+multicast packets RX/TX and
+ * total error packets RX/TX.
+ */
+ for (i = 0; i < 3; i++) {
+ cnt = vsc73xx_find_counter(vsc, indices[i], false);
+ if (cnt)
+ strncpy(data + j * ETH_GSTRING_LEN,
+ cnt->name, ETH_GSTRING_LEN);
+ j++;
+ }
+
+ /* TX stats begins with the number of TX octets */
+ strncpy(data + j * ETH_GSTRING_LEN,
+ "TxEtherStatsOctets", ETH_GSTRING_LEN);
+ j++;
+
+ for (i = 3; i < 6; i++) {
+ cnt = vsc73xx_find_counter(vsc, indices[i], true);
+ if (cnt)
+ strncpy(data + j * ETH_GSTRING_LEN,
+ cnt->name, ETH_GSTRING_LEN);
+ j++;
+ }
+}
+
+static int vsc73xx_get_sset_count(struct dsa_switch *ds, int port, int sset)
+{
+ /* We only support SS_STATS */
+ if (sset != ETH_SS_STATS)
+ return 0;
+ /* RX and TX packets, then 3 RX counters, 3 TX counters */
+ return 8;
+}
+
+static void vsc73xx_get_ethtool_stats(struct dsa_switch *ds, int port,
+ uint64_t *data)
+{
+ struct vsc73xx *vsc = ds->priv;
+ u8 regs[] = {
+ VSC73XX_RXOCT,
+ VSC73XX_C_RX0,
+ VSC73XX_C_RX1,
+ VSC73XX_C_RX2,
+ VSC73XX_TXOCT,
+ VSC73XX_C_TX0,
+ VSC73XX_C_TX1,
+ VSC73XX_C_TX2,
+ };
+ u32 val;
+ int ret;
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(regs); i++) {
+ ret = vsc73xx_read(vsc, VSC73XX_BLOCK_MAC, port,
+ regs[i], &val);
+ if (ret) {
+ dev_err(vsc->dev, "error reading counter %d\n", i);
+ return;
+ }
+ data[i] = val;
+ }
+}
+
+static const struct dsa_switch_ops vsc73xx_ds_ops = {
+ .get_tag_protocol = vsc73xx_get_tag_protocol,
+ .setup = vsc73xx_setup,
+ .phy_read = vsc73xx_phy_read,
+ .phy_write = vsc73xx_phy_write,
+ .adjust_link = vsc73xx_adjust_link,
+ .get_strings = vsc73xx_get_strings,
+ .get_ethtool_stats = vsc73xx_get_ethtool_stats,
+ .get_sset_count = vsc73xx_get_sset_count,
+ .port_enable = vsc73xx_port_enable,
+ .port_disable = vsc73xx_port_disable,
+};
+
+static int vsc73xx_gpio_get(struct gpio_chip *chip, unsigned int offset)
+{
+ struct vsc73xx *vsc = gpiochip_get_data(chip);
+ u32 val;
+ int ret;
+
+ ret = vsc73xx_read(vsc, VSC73XX_BLOCK_SYSTEM, 0,
+ VSC73XX_GPIO, &val);
+ if (ret)
+ return ret;
+
+ return !!(val & BIT(offset));
+}
+
+static void vsc73xx_gpio_set(struct gpio_chip *chip, unsigned int offset,
+ int val)
+{
+ struct vsc73xx *vsc = gpiochip_get_data(chip);
+ u32 tmp = val ? BIT(offset) : 0;
+
+ vsc73xx_update_bits(vsc, VSC73XX_BLOCK_SYSTEM, 0,
+ VSC73XX_GPIO, BIT(offset), tmp);
+}
+
+static int vsc73xx_gpio_direction_output(struct gpio_chip *chip,
+ unsigned int offset, int val)
+{
+ struct vsc73xx *vsc = gpiochip_get_data(chip);
+ u32 tmp = val ? BIT(offset) : 0;
+
+ return vsc73xx_update_bits(vsc, VSC73XX_BLOCK_SYSTEM, 0,
+ VSC73XX_GPIO, BIT(offset + 4) | BIT(offset),
+ BIT(offset + 4) | tmp);
+}
+
+static int vsc73xx_gpio_direction_input(struct gpio_chip *chip,
+ unsigned int offset)
+{
+ struct vsc73xx *vsc = gpiochip_get_data(chip);
+
+ return vsc73xx_update_bits(vsc, VSC73XX_BLOCK_SYSTEM, 0,
+ VSC73XX_GPIO, BIT(offset + 4),
+ 0);
+}
+
+static int vsc73xx_gpio_get_direction(struct gpio_chip *chip,
+ unsigned int offset)
+{
+ struct vsc73xx *vsc = gpiochip_get_data(chip);
+ u32 val;
+ int ret;
+
+ ret = vsc73xx_read(vsc, VSC73XX_BLOCK_SYSTEM, 0,
+ VSC73XX_GPIO, &val);
+ if (ret)
+ return ret;
+
+ return !(val & BIT(offset + 4));
+}
+
+static int vsc73xx_gpio_probe(struct vsc73xx *vsc)
+{
+ int ret;
+
+ vsc->gc.label = devm_kasprintf(vsc->dev, GFP_KERNEL, "VSC%04x",
+ vsc->chipid);
+ vsc->gc.ngpio = 4;
+ vsc->gc.owner = THIS_MODULE;
+ vsc->gc.parent = vsc->dev;
+ vsc->gc.of_node = vsc->dev->of_node;
+ vsc->gc.base = -1;
+ vsc->gc.get = vsc73xx_gpio_get;
+ vsc->gc.set = vsc73xx_gpio_set;
+ vsc->gc.direction_input = vsc73xx_gpio_direction_input;
+ vsc->gc.direction_output = vsc73xx_gpio_direction_output;
+ vsc->gc.get_direction = vsc73xx_gpio_get_direction;
+ vsc->gc.can_sleep = true;
+ ret = devm_gpiochip_add_data(vsc->dev, &vsc->gc, vsc);
+ if (ret) {
+ dev_err(vsc->dev, "unable to register GPIO chip\n");
+ return ret;
+ }
+ return 0;
+}
+
+static int vsc73xx_probe(struct spi_device *spi)
+{
+ struct device *dev = &spi->dev;
+ struct vsc73xx *vsc;
+ int ret;
+
+ vsc = devm_kzalloc(dev, sizeof(*vsc), GFP_KERNEL);
+ if (!vsc)
+ return -ENOMEM;
+
+ spi_set_drvdata(spi, vsc);
+ vsc->spi = spi_dev_get(spi);
+ vsc->dev = dev;
+ mutex_init(&vsc->lock);
+
+ /* Release reset, if any */
+ vsc->reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_LOW);
+ if (IS_ERR(vsc->reset)) {
+ dev_err(dev, "failed to get RESET GPIO\n");
+ return PTR_ERR(vsc->reset);
+ }
+ if (vsc->reset)
+ /* Wait 20ms according to datasheet table 245 */
+ msleep(20);
+
+ spi->mode = SPI_MODE_0;
+ spi->bits_per_word = 8;
+ ret = spi_setup(spi);
+ if (ret < 0) {
+ dev_err(dev, "spi setup failed.\n");
+ return ret;
+ }
+
+ ret = vsc73xx_detect(vsc);
+ if (ret) {
+ dev_err(dev, "no chip found (%d)\n", ret);
+ return -ENODEV;
+ }
+
+ eth_random_addr(vsc->addr);
+ dev_info(vsc->dev,
+ "MAC for control frames: %02X:%02X:%02X:%02X:%02X:%02X\n",
+ vsc->addr[0], vsc->addr[1], vsc->addr[2],
+ vsc->addr[3], vsc->addr[4], vsc->addr[5]);
+
+ /* The VSC7395 switch chips have 5+1 ports which means 5
+ * ordinary ports and a sixth CPU port facing the processor
+ * with an RGMII interface. These ports are numbered 0..4
+ * and 6, so they leave a "hole" in the port map for port 5,
+ * which is invalid.
+ *
+ * The VSC7398 has 8 ports, port 7 is again the CPU port.
+ *
+ * We allocate 8 ports and avoid access to the nonexistant
+ * ports.
+ */
+ vsc->ds = dsa_switch_alloc(dev, 8);
+ if (!vsc->ds)
+ return -ENOMEM;
+ vsc->ds->priv = vsc;
+
+ vsc->ds->ops = &vsc73xx_ds_ops;
+ ret = dsa_register_switch(vsc->ds);
+ if (ret) {
+ dev_err(dev, "unable to register switch (%d)\n", ret);
+ return ret;
+ }
+
+ ret = vsc73xx_gpio_probe(vsc);
+ if (ret) {
+ dsa_unregister_switch(vsc->ds);
+ return ret;
+ }
+
+ return 0;
+}
+
+static int vsc73xx_remove(struct spi_device *spi)
+{
+ struct vsc73xx *vsc = spi_get_drvdata(spi);
+
+ dsa_unregister_switch(vsc->ds);
+ gpiod_set_value(vsc->reset, 1);
+
+ return 0;
+}
+
+static const struct of_device_id vsc73xx_of_match[] = {
+ {
+ .compatible = "vitesse,vsc7385",
+ },
+ {
+ .compatible = "vitesse,vsc7388",
+ },
+ {
+ .compatible = "vitesse,vsc7395",
+ },
+ {
+ .compatible = "vitesse,vsc7398",
+ },
+ { },
+};
+MODULE_DEVICE_TABLE(of, vsc73xx_of_match);
+
+static struct spi_driver vsc73xx_driver = {
+ .probe = vsc73xx_probe,
+ .remove = vsc73xx_remove,
+ .driver = {
+ .name = "vsc73xx",
+ .of_match_table = vsc73xx_of_match,
+ },
+};
+module_spi_driver(vsc73xx_driver);
+
+MODULE_AUTHOR("Linus Walleij <linus.walleij@linaro.org>");
+MODULE_DESCRIPTION("Vitesse VSC7385/7388/7395/7398 driver");
+MODULE_LICENSE("GPL v2");
obj-$(CONFIG_NET_VENDOR_ARC) += arc/
obj-$(CONFIG_NET_VENDOR_ATHEROS) += atheros/
obj-$(CONFIG_NET_VENDOR_AURORA) += aurora/
-obj-$(CONFIG_NET_CADENCE) += cadence/
+obj-$(CONFIG_NET_VENDOR_CADENCE) += cadence/
obj-$(CONFIG_NET_VENDOR_BROADCOM) += broadcom/
obj-$(CONFIG_NET_VENDOR_BROCADE) += brocade/
obj-$(CONFIG_NET_CALXEDA_XGMAC) += calxeda/
obj-$(CONFIG_LPC_ENET) += nxp/
obj-$(CONFIG_NET_VENDOR_OKI) += oki-semi/
obj-$(CONFIG_ETHOC) += ethoc.o
-obj-$(CONFIG_NET_PACKET_ENGINE) += packetengines/
+obj-$(CONFIG_NET_VENDOR_PACKET_ENGINES) += packetengines/
obj-$(CONFIG_NET_VENDOR_PASEMI) += pasemi/
obj-$(CONFIG_NET_VENDOR_QLOGIC) += qlogic/
obj-$(CONFIG_NET_VENDOR_QUALCOMM) += qualcomm/
obj-$(CONFIG_NET_VENDOR_SEEQ) += seeq/
obj-$(CONFIG_NET_VENDOR_SILAN) += silan/
obj-$(CONFIG_NET_VENDOR_SIS) += sis/
-obj-$(CONFIG_SFC) += sfc/
-obj-$(CONFIG_SFC_FALCON) += sfc/falcon/
+obj-$(CONFIG_NET_VENDOR_SOLARFLARE) += sfc/
obj-$(CONFIG_NET_VENDOR_SGI) += sgi/
obj-$(CONFIG_NET_VENDOR_SMSC) += smsc/
obj-$(CONFIG_NET_VENDOR_SOCIONEXT) += socionext/
while (idx != rxretprd) {
struct ring_info *rip;
struct sk_buff *skb;
- struct rx_desc *rxdesc, *retdesc;
+ struct rx_desc *retdesc;
u32 skbidx;
int bd_flags, desc_type, mapsize;
u16 csum;
case 0:
rip = &ap->skb->rx_std_skbuff[skbidx];
mapsize = ACE_STD_BUFSIZE;
- rxdesc = &ap->rx_std_ring[skbidx];
std_count++;
break;
case BD_FLG_JUMBO:
rip = &ap->skb->rx_jumbo_skbuff[skbidx];
mapsize = ACE_JUMBO_BUFSIZE;
- rxdesc = &ap->rx_jumbo_ring[skbidx];
atomic_dec(&ap->cur_jumbo_bufs);
break;
case BD_FLG_MINI:
rip = &ap->skb->rx_mini_skbuff[skbidx];
mapsize = ACE_MINI_BUFSIZE;
- rxdesc = &ap->rx_mini_ring[skbidx];
mini_count++;
break;
default:
#endif /* CONFIG_NET_POLL_CONTROLLER */
static u16 ena_select_queue(struct net_device *dev, struct sk_buff *skb,
- void *accel_priv, select_queue_fallback_t fallback)
+ struct net_device *sb_dev,
+ select_queue_fallback_t fallback)
{
u16 qid;
/* we suspect that this is good for in--kernel network services that
if (skb_rx_queue_recorded(skb))
qid = skb_get_rx_queue(skb);
else
- qid = fallback(dev, skb);
+ qid = fallback(dev, skb, NULL);
return qid;
}
config AMD_XGBE
tristate "AMD 10GbE Ethernet driver"
- depends on ((OF_NET && OF_ADDRESS) || ACPI || PCI) && HAS_IOMEM && HAS_DMA
+ depends on ((OF_NET && OF_ADDRESS) || ACPI || PCI) && HAS_IOMEM
depends on X86 || ARM64 || COMPILE_TEST
select BITREVERSE
select CRC32
config NET_XGENE_V2
tristate "APM X-Gene SoC Ethernet-v2 Driver"
- depends on HAS_DMA
depends on ARCH_XGENE || COMPILE_TEST
help
This is the Ethernet driver for the on-chip ethernet interface
config NET_XGENE
tristate "APM X-Gene SoC Ethernet Driver"
- depends on HAS_DMA
depends on ARCH_XGENE || COMPILE_TEST
select PHYLIB
select MDIO_XGENE
#include "aq_ethtool.h"
#include "aq_nic.h"
+#include "aq_vec.h"
static void aq_ethtool_get_regs(struct net_device *ndev,
struct ethtool_regs *regs, void *p)
return aq_nic_update_interrupt_moderation_settings(aq_nic);
}
+static int aq_ethtool_nway_reset(struct net_device *ndev)
+{
+ struct aq_nic_s *aq_nic = netdev_priv(ndev);
+
+ if (unlikely(!aq_nic->aq_fw_ops->renegotiate))
+ return -EOPNOTSUPP;
+
+ if (netif_running(ndev))
+ return aq_nic->aq_fw_ops->renegotiate(aq_nic->aq_hw);
+
+ return 0;
+}
+
+static void aq_ethtool_get_pauseparam(struct net_device *ndev,
+ struct ethtool_pauseparam *pause)
+{
+ struct aq_nic_s *aq_nic = netdev_priv(ndev);
+
+ pause->autoneg = 0;
+
+ if (aq_nic->aq_hw->aq_nic_cfg->flow_control & AQ_NIC_FC_RX)
+ pause->rx_pause = 1;
+ if (aq_nic->aq_hw->aq_nic_cfg->flow_control & AQ_NIC_FC_TX)
+ pause->tx_pause = 1;
+}
+
+static int aq_ethtool_set_pauseparam(struct net_device *ndev,
+ struct ethtool_pauseparam *pause)
+{
+ struct aq_nic_s *aq_nic = netdev_priv(ndev);
+ int err = 0;
+
+ if (!aq_nic->aq_fw_ops->set_flow_control)
+ return -EOPNOTSUPP;
+
+ if (pause->autoneg == AUTONEG_ENABLE)
+ return -EOPNOTSUPP;
+
+ if (pause->rx_pause)
+ aq_nic->aq_hw->aq_nic_cfg->flow_control |= AQ_NIC_FC_RX;
+ else
+ aq_nic->aq_hw->aq_nic_cfg->flow_control &= ~AQ_NIC_FC_RX;
+
+ if (pause->tx_pause)
+ aq_nic->aq_hw->aq_nic_cfg->flow_control |= AQ_NIC_FC_TX;
+ else
+ aq_nic->aq_hw->aq_nic_cfg->flow_control &= ~AQ_NIC_FC_TX;
+
+ err = aq_nic->aq_fw_ops->set_flow_control(aq_nic->aq_hw);
+
+ return err;
+}
+
+static void aq_get_ringparam(struct net_device *ndev,
+ struct ethtool_ringparam *ring)
+{
+ struct aq_nic_s *aq_nic = netdev_priv(ndev);
+ struct aq_nic_cfg_s *aq_nic_cfg = aq_nic_get_cfg(aq_nic);
+
+ ring->rx_pending = aq_nic_cfg->rxds;
+ ring->tx_pending = aq_nic_cfg->txds;
+
+ ring->rx_max_pending = aq_nic_cfg->aq_hw_caps->rxds_max;
+ ring->tx_max_pending = aq_nic_cfg->aq_hw_caps->txds_max;
+}
+
+static int aq_set_ringparam(struct net_device *ndev,
+ struct ethtool_ringparam *ring)
+{
+ int err = 0;
+ bool ndev_running = false;
+ struct aq_nic_s *aq_nic = netdev_priv(ndev);
+ struct aq_nic_cfg_s *aq_nic_cfg = aq_nic_get_cfg(aq_nic);
+ const struct aq_hw_caps_s *hw_caps = aq_nic_cfg->aq_hw_caps;
+
+ if (ring->rx_mini_pending || ring->rx_jumbo_pending) {
+ err = -EOPNOTSUPP;
+ goto err_exit;
+ }
+
+ if (netif_running(ndev)) {
+ ndev_running = true;
+ dev_close(ndev);
+ }
+
+ aq_nic_free_vectors(aq_nic);
+
+ aq_nic_cfg->rxds = max(ring->rx_pending, hw_caps->rxds_min);
+ aq_nic_cfg->rxds = min(aq_nic_cfg->rxds, hw_caps->rxds_max);
+ aq_nic_cfg->rxds = ALIGN(aq_nic_cfg->rxds, AQ_HW_RXD_MULTIPLE);
+
+ aq_nic_cfg->txds = max(ring->tx_pending, hw_caps->txds_min);
+ aq_nic_cfg->txds = min(aq_nic_cfg->txds, hw_caps->txds_max);
+ aq_nic_cfg->txds = ALIGN(aq_nic_cfg->txds, AQ_HW_TXD_MULTIPLE);
+
+ for (aq_nic->aq_vecs = 0; aq_nic->aq_vecs < aq_nic_cfg->vecs;
+ aq_nic->aq_vecs++) {
+ aq_nic->aq_vec[aq_nic->aq_vecs] =
+ aq_vec_alloc(aq_nic, aq_nic->aq_vecs, aq_nic_cfg);
+ if (unlikely(!aq_nic->aq_vec[aq_nic->aq_vecs])) {
+ err = -ENOMEM;
+ goto err_exit;
+ }
+ }
+ if (ndev_running)
+ err = dev_open(ndev);
+
+err_exit:
+ return err;
+}
+
const struct ethtool_ops aq_ethtool_ops = {
.get_link = aq_ethtool_get_link,
.get_regs_len = aq_ethtool_get_regs_len,
.get_drvinfo = aq_ethtool_get_drvinfo,
.get_strings = aq_ethtool_get_strings,
.get_rxfh_indir_size = aq_ethtool_get_rss_indir_size,
+ .nway_reset = aq_ethtool_nway_reset,
+ .get_ringparam = aq_get_ringparam,
+ .set_ringparam = aq_set_ringparam,
+ .get_pauseparam = aq_ethtool_get_pauseparam,
+ .set_pauseparam = aq_ethtool_set_pauseparam,
.get_rxfh_key_size = aq_ethtool_get_rss_key_size,
.get_rxfh = aq_ethtool_get_rss,
.get_rxnfc = aq_ethtool_get_rxnfc,
u64 link_speed_msk;
unsigned int hw_priv_flags;
u32 media_type;
- u32 rxds;
- u32 txds;
+ u32 rxds_max;
+ u32 txds_max;
+ u32 rxds_min;
+ u32 txds_min;
u32 txhwb_alignment;
u32 irq_mask;
u32 vecs;
#define AQ_HW_MEDIA_TYPE_TP 1U
#define AQ_HW_MEDIA_TYPE_FIBRE 2U
+#define AQ_HW_TXD_MULTIPLE 8U
+#define AQ_HW_RXD_MULTIPLE 8U
+
struct aq_hw_s {
atomic_t flags;
u8 rbl_enabled:1;
int (*hw_get_fw_version)(struct aq_hw_s *self, u32 *fw_version);
- int (*hw_deinit)(struct aq_hw_s *self);
-
int (*hw_set_power)(struct aq_hw_s *self, unsigned int power_state);
};
struct aq_fw_ops {
int (*init)(struct aq_hw_s *self);
+ int (*deinit)(struct aq_hw_s *self);
+
int (*reset)(struct aq_hw_s *self);
+ int (*renegotiate)(struct aq_hw_s *self);
+
int (*get_mac_permanent)(struct aq_hw_s *self, u8 *mac);
int (*set_link_speed)(struct aq_hw_s *self, u32 speed);
- int (*set_state)(struct aq_hw_s *self, enum hal_atl_utils_fw_state_e state);
+ int (*set_state)(struct aq_hw_s *self,
+ enum hal_atl_utils_fw_state_e state);
int (*update_link_status)(struct aq_hw_s *self);
int (*update_stats)(struct aq_hw_s *self);
+
+ int (*set_flow_control)(struct aq_hw_s *self);
};
#endif /* AQ_HW_H */
aq_nic_rss_init(self, cfg->num_rss_queues);
/*descriptors */
- cfg->rxds = min(cfg->aq_hw_caps->rxds, AQ_CFG_RXDS_DEF);
- cfg->txds = min(cfg->aq_hw_caps->txds, AQ_CFG_TXDS_DEF);
+ cfg->rxds = min(cfg->aq_hw_caps->rxds_max, AQ_CFG_RXDS_DEF);
+ cfg->txds = min(cfg->aq_hw_caps->txds_max, AQ_CFG_TXDS_DEF);
/*rss rings */
cfg->vecs = min(cfg->aq_hw_caps->vecs, AQ_CFG_VECS_DEF);
ethtool_link_ksettings_add_link_mode(cmd, advertising,
100baseT_Full);
- if (self->aq_nic_cfg.flow_control)
+ if (self->aq_nic_cfg.flow_control & AQ_NIC_FC_RX)
ethtool_link_ksettings_add_link_mode(cmd, advertising,
Pause);
+ if (self->aq_nic_cfg.flow_control & AQ_NIC_FC_TX)
+ ethtool_link_ksettings_add_link_mode(cmd, advertising,
+ Asym_Pause);
+
if (self->aq_nic_cfg.aq_hw_caps->media_type == AQ_HW_MEDIA_TYPE_FIBRE)
ethtool_link_ksettings_add_link_mode(cmd, advertising, FIBRE);
else
aq_vec_deinit(aq_vec);
if (self->power_state == AQ_HW_POWER_STATE_D0) {
- (void)self->aq_hw_ops->hw_deinit(self->aq_hw);
+ (void)self->aq_fw_ops->deinit(self->aq_hw);
} else {
(void)self->aq_hw_ops->hw_set_power(self->aq_hw,
self->power_state);
#include "hw_atl_a0_internal.h"
#define DEFAULT_A0_BOARD_BASIC_CAPABILITIES \
- .is_64_dma = true, \
- .msix_irqs = 4U, \
- .irq_mask = ~0U, \
- .vecs = HW_ATL_A0_RSS_MAX, \
- .tcs = HW_ATL_A0_TC_MAX, \
- .rxd_alignment = 1U, \
- .rxd_size = HW_ATL_A0_RXD_SIZE, \
- .rxds = 248U, \
- .txd_alignment = 1U, \
- .txd_size = HW_ATL_A0_TXD_SIZE, \
- .txds = 8U * 1024U, \
- .txhwb_alignment = 4096U, \
- .tx_rings = HW_ATL_A0_TX_RINGS, \
- .rx_rings = HW_ATL_A0_RX_RINGS, \
- .hw_features = NETIF_F_HW_CSUM | \
- NETIF_F_RXHASH | \
- NETIF_F_RXCSUM | \
- NETIF_F_SG | \
- NETIF_F_TSO, \
+ .is_64_dma = true, \
+ .msix_irqs = 4U, \
+ .irq_mask = ~0U, \
+ .vecs = HW_ATL_A0_RSS_MAX, \
+ .tcs = HW_ATL_A0_TC_MAX, \
+ .rxd_alignment = 1U, \
+ .rxd_size = HW_ATL_A0_RXD_SIZE, \
+ .rxds_max = HW_ATL_A0_MAX_RXD, \
+ .rxds_min = HW_ATL_A0_MIN_RXD, \
+ .txd_alignment = 1U, \
+ .txd_size = HW_ATL_A0_TXD_SIZE, \
+ .txds_max = HW_ATL_A0_MAX_TXD, \
+ .txds_min = HW_ATL_A0_MIN_RXD, \
+ .txhwb_alignment = 4096U, \
+ .tx_rings = HW_ATL_A0_TX_RINGS, \
+ .rx_rings = HW_ATL_A0_RX_RINGS, \
+ .hw_features = NETIF_F_HW_CSUM | \
+ NETIF_F_RXHASH | \
+ NETIF_F_RXCSUM | \
+ NETIF_F_SG | \
+ NETIF_F_TSO, \
.hw_priv_flags = IFF_UNICAST_FLT, \
- .flow_control = true, \
- .mtu = HW_ATL_A0_MTU_JUMBO, \
- .mac_regs_count = 88, \
+ .flow_control = true, \
+ .mtu = HW_ATL_A0_MTU_JUMBO, \
+ .mac_regs_count = 88, \
.hw_alive_check_addr = 0x10U
const struct aq_hw_caps_s hw_atl_a0_caps_aqc100 = {
const struct aq_hw_ops hw_atl_ops_a0 = {
.hw_set_mac_address = hw_atl_a0_hw_mac_addr_set,
.hw_init = hw_atl_a0_hw_init,
- .hw_deinit = hw_atl_utils_hw_deinit,
.hw_set_power = hw_atl_utils_hw_set_power,
.hw_reset = hw_atl_a0_hw_reset,
.hw_start = hw_atl_a0_hw_start,
#define HW_ATL_A0_FW_VER_EXPECTED 0x01050006U
+#define HW_ATL_A0_MIN_RXD \
+ (ALIGN(AQ_CFG_SKB_FRAGS_MAX + 1U, AQ_HW_RXD_MULTIPLE))
+#define HW_ATL_A0_MIN_TXD \
+ (ALIGN(AQ_CFG_SKB_FRAGS_MAX + 1U, AQ_HW_TXD_MULTIPLE))
+
+#define HW_ATL_A0_MAX_RXD 8184U
+#define HW_ATL_A0_MAX_TXD 8184U
+
#endif /* HW_ATL_A0_INTERNAL_H */
#include "hw_atl_llh_internal.h"
#define DEFAULT_B0_BOARD_BASIC_CAPABILITIES \
- .is_64_dma = true, \
- .msix_irqs = 4U, \
- .irq_mask = ~0U, \
- .vecs = HW_ATL_B0_RSS_MAX, \
- .tcs = HW_ATL_B0_TC_MAX, \
- .rxd_alignment = 1U, \
- .rxd_size = HW_ATL_B0_RXD_SIZE, \
- .rxds = 4U * 1024U, \
- .txd_alignment = 1U, \
- .txd_size = HW_ATL_B0_TXD_SIZE, \
- .txds = 8U * 1024U, \
- .txhwb_alignment = 4096U, \
- .tx_rings = HW_ATL_B0_TX_RINGS, \
- .rx_rings = HW_ATL_B0_RX_RINGS, \
- .hw_features = NETIF_F_HW_CSUM | \
- NETIF_F_RXCSUM | \
- NETIF_F_RXHASH | \
- NETIF_F_SG | \
- NETIF_F_TSO | \
- NETIF_F_LRO, \
- .hw_priv_flags = IFF_UNICAST_FLT, \
- .flow_control = true, \
- .mtu = HW_ATL_B0_MTU_JUMBO, \
- .mac_regs_count = 88, \
+ .is_64_dma = true, \
+ .msix_irqs = 4U, \
+ .irq_mask = ~0U, \
+ .vecs = HW_ATL_B0_RSS_MAX, \
+ .tcs = HW_ATL_B0_TC_MAX, \
+ .rxd_alignment = 1U, \
+ .rxd_size = HW_ATL_B0_RXD_SIZE, \
+ .rxds_max = HW_ATL_B0_MAX_RXD, \
+ .rxds_min = HW_ATL_B0_MIN_RXD, \
+ .txd_alignment = 1U, \
+ .txd_size = HW_ATL_B0_TXD_SIZE, \
+ .txds_max = HW_ATL_B0_MAX_TXD, \
+ .txds_min = HW_ATL_B0_MIN_TXD, \
+ .txhwb_alignment = 4096U, \
+ .tx_rings = HW_ATL_B0_TX_RINGS, \
+ .rx_rings = HW_ATL_B0_RX_RINGS, \
+ .hw_features = NETIF_F_HW_CSUM | \
+ NETIF_F_RXCSUM | \
+ NETIF_F_RXHASH | \
+ NETIF_F_SG | \
+ NETIF_F_TSO | \
+ NETIF_F_LRO, \
+ .hw_priv_flags = IFF_UNICAST_FLT, \
+ .flow_control = true, \
+ .mtu = HW_ATL_B0_MTU_JUMBO, \
+ .mac_regs_count = 88, \
.hw_alive_check_addr = 0x10U
const struct aq_hw_caps_s hw_atl_b0_caps_aqc100 = {
const struct aq_hw_ops hw_atl_ops_b0 = {
.hw_set_mac_address = hw_atl_b0_hw_mac_addr_set,
.hw_init = hw_atl_b0_hw_init,
- .hw_deinit = hw_atl_utils_hw_deinit,
.hw_set_power = hw_atl_utils_hw_set_power,
.hw_reset = hw_atl_b0_hw_reset,
.hw_start = hw_atl_b0_hw_start,
#define HW_ATL_INTR_MODER_MAX 0x1FF
#define HW_ATL_INTR_MODER_MIN 0xFF
+#define HW_ATL_B0_MIN_RXD \
+ (ALIGN(AQ_CFG_SKB_FRAGS_MAX + 1U, AQ_HW_RXD_MULTIPLE))
+#define HW_ATL_B0_MIN_TXD \
+ (ALIGN(AQ_CFG_SKB_FRAGS_MAX + 1U, AQ_HW_TXD_MULTIPLE))
+
+#define HW_ATL_B0_MAX_RXD 8184U
+#define HW_ATL_B0_MAX_TXD 8184U
+
/* HW layer capabilities */
#endif /* HW_ATL_B0_INTERNAL_H */
#define HW_ATL_MPI_CONTROL_ADR 0x0368U
#define HW_ATL_MPI_STATE_ADR 0x036CU
-#define HW_ATL_MPI_STATE_MSK 0x00FFU
-#define HW_ATL_MPI_STATE_SHIFT 0U
-#define HW_ATL_MPI_SPEED_MSK 0xFFFF0000U
-#define HW_ATL_MPI_SPEED_SHIFT 16U
+#define HW_ATL_MPI_STATE_MSK 0x00FFU
+#define HW_ATL_MPI_STATE_SHIFT 0U
+#define HW_ATL_MPI_SPEED_MSK 0x00FF0000U
+#define HW_ATL_MPI_SPEED_SHIFT 16U
+#define HW_ATL_MPI_DIRTY_WAKE_MSK 0x02000000U
#define HW_ATL_MPI_DAISY_CHAIN_STATUS 0x704
#define HW_ATL_MPI_BOOT_EXIT_CODE 0x388
{
u32 val = aq_hw_read_reg(self, HW_ATL_MPI_CONTROL_ADR);
- val = (val & HW_ATL_MPI_STATE_MSK) | (speed << HW_ATL_MPI_SPEED_SHIFT);
+ val = val & ~HW_ATL_MPI_SPEED_MSK;
+ val |= speed << HW_ATL_MPI_SPEED_SHIFT;
aq_hw_write_reg(self, HW_ATL_MPI_CONTROL_ADR, val);
return 0;
}
-void hw_atl_utils_mpi_set(struct aq_hw_s *self,
- enum hal_atl_utils_fw_state_e state,
- u32 speed)
+static int hw_atl_utils_mpi_set_state(struct aq_hw_s *self,
+ enum hal_atl_utils_fw_state_e state)
{
int err = 0;
u32 transaction_id = 0;
struct hw_aq_atl_utils_mbox_header mbox;
+ u32 val = aq_hw_read_reg(self, HW_ATL_MPI_CONTROL_ADR);
if (state == MPI_RESET) {
hw_atl_utils_mpi_read_mbox(self, &mbox);
if (err < 0)
goto err_exit;
}
+ /* On interface DEINIT we disable DW (raise bit)
+ * Otherwise enable DW (clear bit)
+ */
+ if (state == MPI_DEINIT || state == MPI_POWER)
+ val |= HW_ATL_MPI_DIRTY_WAKE_MSK;
+ else
+ val &= ~HW_ATL_MPI_DIRTY_WAKE_MSK;
- aq_hw_write_reg(self, HW_ATL_MPI_CONTROL_ADR,
- (speed << HW_ATL_MPI_SPEED_SHIFT) | state);
-
-err_exit:;
-}
-
-static int hw_atl_utils_mpi_set_state(struct aq_hw_s *self,
- enum hal_atl_utils_fw_state_e state)
-{
- u32 val = aq_hw_read_reg(self, HW_ATL_MPI_CONTROL_ADR);
+ /* Set new state bits */
+ val = val & ~HW_ATL_MPI_STATE_MSK;
+ val |= state & HW_ATL_MPI_STATE_MSK;
- val = state | (val & HW_ATL_MPI_SPEED_MSK);
aq_hw_write_reg(self, HW_ATL_MPI_CONTROL_ADR, val);
- return 0;
+err_exit:
+ return err;
}
int hw_atl_utils_mpi_get_link_status(struct aq_hw_s *self)
*p = chip_features;
}
-int hw_atl_utils_hw_deinit(struct aq_hw_s *self)
+static int hw_atl_fw1x_deinit(struct aq_hw_s *self)
{
- hw_atl_utils_mpi_set(self, MPI_DEINIT, 0x0U);
+ hw_atl_utils_mpi_set_speed(self, 0);
+ hw_atl_utils_mpi_set_state(self, MPI_DEINIT);
return 0;
}
int hw_atl_utils_hw_set_power(struct aq_hw_s *self,
unsigned int power_state)
{
- hw_atl_utils_mpi_set(self, MPI_POWER, 0x0U);
+ hw_atl_utils_mpi_set_speed(self, 0);
+ hw_atl_utils_mpi_set_state(self, MPI_POWER);
return 0;
}
const struct aq_fw_ops aq_fw_1x_ops = {
.init = hw_atl_utils_mpi_create,
+ .deinit = hw_atl_fw1x_deinit,
.reset = NULL,
.get_mac_permanent = hw_atl_utils_get_mac_permanent,
.set_link_speed = hw_atl_utils_mpi_set_speed,
.set_state = hw_atl_utils_mpi_set_state,
.update_link_status = hw_atl_utils_mpi_get_link_status,
.update_stats = hw_atl_utils_update_stats,
+ .set_flow_control = NULL,
};
CAPS_HI_TRANSACTION_ID,
};
+enum hw_atl_fw2x_ctrl {
+ CTRL_RESERVED1 = 0x00,
+ CTRL_RESERVED2,
+ CTRL_RESERVED3,
+ CTRL_PAUSE,
+ CTRL_ASYMMETRIC_PAUSE,
+ CTRL_RESERVED4,
+ CTRL_RESERVED5,
+ CTRL_RESERVED6,
+ CTRL_1GBASET_FD_EEE,
+ CTRL_2P5GBASET_FD_EEE,
+ CTRL_5GBASET_FD_EEE,
+ CTRL_10GBASET_FD_EEE,
+ CTRL_THERMAL_SHUTDOWN,
+ CTRL_PHY_LOGS,
+ CTRL_EEE_AUTO_DISABLE,
+ CTRL_PFC,
+ CTRL_WAKE_ON_LINK,
+ CTRL_CABLE_DIAG,
+ CTRL_TEMPERATURE,
+ CTRL_DOWNSHIFT,
+ CTRL_PTP_AVB,
+ CTRL_RESERVED7,
+ CTRL_LINK_DROP,
+ CTRL_SLEEP_PROXY,
+ CTRL_WOL,
+ CTRL_MAC_STOP,
+ CTRL_EXT_LOOPBACK,
+ CTRL_INT_LOOPBACK,
+ CTRL_RESERVED8,
+ CTRL_WOL_TIMER,
+ CTRL_STATISTICS,
+ CTRL_FORCE_RECONNECT,
+};
+
struct aq_hw_s;
struct aq_fw_ops;
struct aq_hw_caps_s;
#define HW_ATL_FW2X_MPI_STATE_ADDR 0x370
#define HW_ATL_FW2X_MPI_STATE2_ADDR 0x374
+static int aq_fw2x_set_link_speed(struct aq_hw_s *self, u32 speed);
+static int aq_fw2x_set_state(struct aq_hw_s *self,
+ enum hal_atl_utils_fw_state_e state);
+
static int aq_fw2x_init(struct aq_hw_s *self)
{
int err = 0;
return err;
}
+static int aq_fw2x_deinit(struct aq_hw_s *self)
+{
+ int err = aq_fw2x_set_link_speed(self, 0);
+
+ if (!err)
+ err = aq_fw2x_set_state(self, MPI_DEINIT);
+
+ return err;
+}
+
static enum hw_atl_fw2x_rate link_speed_mask_2fw2x_ratemask(u32 speed)
{
enum hw_atl_fw2x_rate rate = 0;
return 0;
}
+static void aq_fw2x_set_mpi_flow_control(struct aq_hw_s *self, u32 *mpi_state)
+{
+ if (self->aq_nic_cfg->flow_control & AQ_NIC_FC_RX)
+ *mpi_state |= BIT(CAPS_HI_PAUSE);
+ else
+ *mpi_state &= ~BIT(CAPS_HI_PAUSE);
+
+ if (self->aq_nic_cfg->flow_control & AQ_NIC_FC_TX)
+ *mpi_state |= BIT(CAPS_HI_ASYMMETRIC_PAUSE);
+ else
+ *mpi_state &= ~BIT(CAPS_HI_ASYMMETRIC_PAUSE);
+}
+
static int aq_fw2x_set_state(struct aq_hw_s *self,
enum hal_atl_utils_fw_state_e state)
{
- /* No explicit state in 2x fw */
+ u32 mpi_state = aq_hw_read_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR);
+
+ switch (state) {
+ case MPI_INIT:
+ mpi_state &= ~BIT(CAPS_HI_LINK_DROP);
+ aq_fw2x_set_mpi_flow_control(self, &mpi_state);
+ break;
+ case MPI_DEINIT:
+ mpi_state |= BIT(CAPS_HI_LINK_DROP);
+ break;
+ case MPI_RESET:
+ case MPI_POWER:
+ /* No actions */
+ break;
+ }
+ aq_hw_write_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR, mpi_state);
return 0;
}
return hw_atl_utils_update_stats(self);
}
+static int aq_fw2x_renegotiate(struct aq_hw_s *self)
+{
+ u32 mpi_opts = aq_hw_read_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR);
+
+ mpi_opts |= BIT(CTRL_FORCE_RECONNECT);
+
+ aq_hw_write_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR, mpi_opts);
+
+ return 0;
+}
+
+static int aq_fw2x_set_flow_control(struct aq_hw_s *self)
+{
+ u32 mpi_state = aq_hw_read_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR);
+
+ aq_fw2x_set_mpi_flow_control(self, &mpi_state);
+
+ aq_hw_write_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR, mpi_state);
+
+ return 0;
+}
+
const struct aq_fw_ops aq_fw_2x_ops = {
.init = aq_fw2x_init,
+ .deinit = aq_fw2x_deinit,
.reset = NULL,
+ .renegotiate = aq_fw2x_renegotiate,
.get_mac_permanent = aq_fw2x_get_mac_permanent,
.set_link_speed = aq_fw2x_set_link_speed,
.set_state = aq_fw2x_set_state,
.update_link_status = aq_fw2x_update_link_status,
.update_stats = aq_fw2x_update_stats,
+ .set_flow_control = aq_fw2x_set_flow_control,
};
#define NIC_MAJOR_DRIVER_VERSION 2
#define NIC_MINOR_DRIVER_VERSION 0
-#define NIC_BUILD_DRIVER_VERSION 2
-#define NIC_REVISION_DRIVER_VERSION 1
+#define NIC_BUILD_DRIVER_VERSION 3
+#define NIC_REVISION_DRIVER_VERSION 0
#define AQ_CFG_DRV_VERSION_SUFFIX "-kern"
config ARC_EMAC
tristate "ARC EMAC support"
select ARC_EMAC_CORE
- depends on OF_IRQ && OF_NET && HAS_DMA && (ARC || COMPILE_TEST)
+ depends on OF_IRQ && OF_NET
+ depends on ARC || COMPILE_TEST
---help---
On some legacy ARC (Synopsys) FPGA boards such as ARCAngel4/ML50x
non-standard on-chip ethernet device ARC EMAC 10/100 is used.
config EMAC_ROCKCHIP
tristate "Rockchip EMAC support"
select ARC_EMAC_CORE
- depends on OF_IRQ && OF_NET && REGULATOR && HAS_DMA && (ARCH_ROCKCHIP || COMPILE_TEST)
+ depends on OF_IRQ && OF_NET && REGULATOR
+ depends on ARCH_ROCKCHIP || COMPILE_TEST
---help---
Support for Rockchip RK3036/RK3066/RK3188 EMAC ethernet controllers.
This selects Rockchip SoC glue layer support for the
struct alx_hw *hw = &alx->hw;
unsigned long flags;
int old_speed;
- u8 old_duplex;
int err;
/* clear PHY internal interrupt status, otherwise the main
alx_clear_phy_intr(hw);
old_speed = hw->link_speed;
- old_duplex = hw->duplex;
err = alx_read_phy_link(hw);
if (err < 0)
goto reset;
struct pci_dev *pdev = to_pci_dev(dev);
struct alx_priv *alx = pci_get_drvdata(pdev);
struct alx_hw *hw = &alx->hw;
+ int err;
alx_reset_phy(hw);
if (!netif_running(alx->dev))
return 0;
netif_device_attach(alx->dev);
- return __alx_open(alx, true);
+
+ rtnl_lock();
+ err = __alx_open(alx, true);
+ rtnl_unlock();
+
+ return err;
}
static SIMPLE_DEV_PM_OPS(alx_pm_ops, alx_suspend, alx_resume);
config NET_VENDOR_AURORA
bool "Aurora VLSI devices"
+ default y
help
If you have a network (Ethernet) device belonging to this class,
say Y.
again:
do {
- struct nb8800_rx_buf *rxb;
unsigned int len;
next = (last + 1) % RX_DESC_COUNT;
- rxb = &priv->rx_bufs[next];
rxd = &priv->rx_descs[next];
if (!rxd->report)
config BGMAC_BCMA
tristate "Broadcom iProc GBit BCMA support"
depends on BCMA && BCMA_HOST_SOC
- depends on HAS_DMA
depends on BCM47XX || ARCH_BCM_5301X || COMPILE_TEST
select BGMAC
select PHYLIB
config BGMAC_PLATFORM
tristate "Broadcom iProc GBit platform support"
- depends on HAS_DMA
depends on ARCH_BCM_IPROC || COMPILE_TEST
depends on OF
select BGMAC
};
static u16 bcm_sysport_select_queue(struct net_device *dev, struct sk_buff *skb,
- void *accel_priv,
+ struct net_device *sb_dev,
select_queue_fallback_t fallback)
{
struct bcm_sysport_priv *priv = netdev_priv(dev);
unsigned int q, port;
if (!netdev_uses_dsa(dev))
- return fallback(dev, skb);
+ return fallback(dev, skb, NULL);
/* DSA tagging layer will have configured the correct queue */
q = BRCM_TAG_GET_QUEUE(queue);
tx_ring = priv->ring_map[q + port * priv->per_port_num_tx_queues];
if (unlikely(!tx_ring))
- return fallback(dev, skb);
+ return fallback(dev, skb, NULL);
return tx_ring->index;
}
{
struct device *dma_dev = bgmac->dma_dev;
int empty_slot;
- bool freed = false;
unsigned bytes_compl = 0, pkts_compl = 0;
/* The last slot that hardware didn't consume yet */
slot->dma_addr = 0;
ring->start++;
- freed = true;
}
if (!pkts_compl)
struct link_vars link_vars;
u32 link_cnt;
struct bnx2x_link_report_data last_reported_link;
+ bool force_link_down;
struct mdio_if_info mdio;
{
struct bnx2x_link_report_data cur_data;
+ if (bp->force_link_down) {
+ bp->link_vars.link_up = 0;
+ return;
+ }
+
/* reread mf_cfg */
if (IS_PF(bp) && !CHIP_IS_E1(bp))
bnx2x_read_mf_cfg(bp);
}
u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb,
- void *accel_priv, select_queue_fallback_t fallback)
+ struct net_device *sb_dev,
+ select_queue_fallback_t fallback)
{
struct bnx2x *bp = netdev_priv(dev);
}
/* select a non-FCoE queue */
- return fallback(dev, skb) % (BNX2X_NUM_ETH_QUEUES(bp) * bp->max_cos);
+ return fallback(dev, skb, NULL) %
+ (BNX2X_NUM_ETH_QUEUES(bp) * bp->max_cos);
}
void bnx2x_set_num_queues(struct bnx2x *bp)
bp->pending_max = 0;
}
+ bp->force_link_down = false;
if (bp->port.pmf) {
rc = bnx2x_initial_phy_init(bp, load_mode);
if (rc)
/* select_queue callback */
u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb,
- void *accel_priv, select_queue_fallback_t fallback);
+ struct net_device *sb_dev,
+ select_queue_fallback_t fallback);
static inline void bnx2x_update_rx_prod(struct bnx2x *bp,
struct bnx2x_fastpath *fp,
*/
if (!vars->link_up)
break;
+ /* else: fall through */
case LED_MODE_ON:
if (((params->phy[EXT_PHY1].type ==
PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM8727) ||
switch (link_config & PORT_FEATURE_LINK_SPEED_MASK) {
case PORT_FEATURE_LINK_SPEED_10M_HALF:
phy->req_duplex = DUPLEX_HALF;
+ /* fall through */
case PORT_FEATURE_LINK_SPEED_10M_FULL:
phy->req_line_speed = SPEED_10;
break;
case PORT_FEATURE_LINK_SPEED_100M_HALF:
phy->req_duplex = DUPLEX_HALF;
+ /* fall through */
case PORT_FEATURE_LINK_SPEED_100M_FULL:
phy->req_line_speed = SPEED_100;
break;
bp->num_queues,
1 + bp->num_cnic_queues);
- /* falling through... */
+ /* fall through */
case BNX2X_INT_MODE_MSI:
bnx2x_enable_msi(bp);
- /* falling through... */
+ /* fall through */
case BNX2X_INT_MODE_INTX:
bp->num_ethernet_queues = 1;
bp->num_queues = bp->num_ethernet_queues + bp->num_cnic_queues;
bp->sp_rtnl_state = 0;
smp_mb();
+ /* Immediately indicate link as down */
+ bp->link_vars.link_up = 0;
+ bp->force_link_down = true;
+ netif_carrier_off(bp->dev);
+ BNX2X_ERR("Indicating link is down due to Tx-timeout\n");
+
bnx2x_nic_unload(bp, UNLOAD_NORMAL, true);
/* When ret value shows failure of allocation failure,
* the nic is rebooted again. If open still fails, a error
/* DEL command deletes all currently configured MACs */
case BNX2X_MCAST_CMD_DEL:
o->set_registry_size(o, 0);
- /* Don't break */
+ /* fall through */
/* RESTORE command will restore the entire multicast configuration */
case BNX2X_MCAST_CMD_RESTORE:
/* DEL command deletes all currently configured MACs */
case BNX2X_MCAST_CMD_DEL:
o->set_registry_size(o, 0);
- /* Don't break */
+ /* fall through */
/* RESTORE command will restore the entire multicast configuration */
case BNX2X_MCAST_CMD_RESTORE:
DP(BNX2X_MSG_IOV, "got VF [%d:%d] RSS update ramrod\n",
vf->abs_vfid, qidx);
bnx2x_vf_handle_rss_update_eqe(bp, vf);
+ /* fall through */
case EVENT_RING_OPCODE_VF_FLR:
/* Do nothing for now */
return 0;
speed);
}
set_bit(BNXT_LINK_SPEED_CHNG_SP_EVENT, &bp->sp_event);
- /* fall thru */
+ /* fall through */
}
case ASYNC_EVENT_CMPL_EVENT_ID_LINK_STATUS_CHANGE:
set_bit(BNXT_LINK_CHNG_SP_EVENT, &bp->sp_event);
bp->hwrm_cmd_resp_dma_addr);
bp->hwrm_cmd_resp_addr = NULL;
- if (bp->hwrm_dbg_resp_addr) {
- dma_free_coherent(&pdev->dev, HWRM_DBG_REG_BUF_SIZE,
- bp->hwrm_dbg_resp_addr,
- bp->hwrm_dbg_resp_dma_addr);
-
- bp->hwrm_dbg_resp_addr = NULL;
- }
}
static int bnxt_alloc_hwrm_resources(struct bnxt *bp)
GFP_KERNEL);
if (!bp->hwrm_cmd_resp_addr)
return -ENOMEM;
- bp->hwrm_dbg_resp_addr = dma_alloc_coherent(&pdev->dev,
- HWRM_DBG_REG_BUF_SIZE,
- &bp->hwrm_dbg_resp_dma_addr,
- GFP_KERNEL);
- if (!bp->hwrm_dbg_resp_addr)
- netdev_warn(bp->dev, "fail to alloc debug register dma mem\n");
return 0;
}
switch (f->command) {
case TC_BLOCK_BIND:
return tcf_block_cb_register(f->block, bnxt_setup_tc_block_cb,
- bp, bp);
+ bp, bp, f->extack);
case TC_BLOCK_UNBIND:
tcf_block_cb_unregister(f->block, bnxt_setup_tc_block_cb, bp);
return 0;
dma_addr_t hwrm_short_cmd_req_dma_addr;
void *hwrm_cmd_resp_addr;
dma_addr_t hwrm_cmd_resp_dma_addr;
- void *hwrm_dbg_resp_addr;
- dma_addr_t hwrm_dbg_resp_dma_addr;
-#define HWRM_DBG_REG_BUF_SIZE 128
struct rx_port_stats *hw_rx_port_stats;
struct tx_port_stats *hw_tx_port_stats;
#endif /* CONFIG_BNXT_SRIOV */
};
+static const struct bnxt_dl_nvm_param nvm_params[] = {
+ {DEVLINK_PARAM_GENERIC_ID_ENABLE_SRIOV, NVM_OFF_ENABLE_SRIOV,
+ BNXT_NVM_SHARED_CFG, 1},
+};
+
+static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg,
+ int msg_len, union devlink_param_value *val)
+{
+ struct hwrm_nvm_variable_input *req = msg;
+ void *data_addr = NULL, *buf = NULL;
+ struct bnxt_dl_nvm_param nvm_param;
+ int bytesize, idx = 0, rc, i;
+ dma_addr_t data_dma_addr;
+
+ /* Get/Set NVM CFG parameter is supported only on PFs */
+ if (BNXT_VF(bp))
+ return -EPERM;
+
+ for (i = 0; i < ARRAY_SIZE(nvm_params); i++) {
+ if (nvm_params[i].id == param_id) {
+ nvm_param = nvm_params[i];
+ break;
+ }
+ }
+
+ if (nvm_param.dir_type == BNXT_NVM_PORT_CFG)
+ idx = bp->pf.port_id;
+ else if (nvm_param.dir_type == BNXT_NVM_FUNC_CFG)
+ idx = bp->pf.fw_fid - BNXT_FIRST_PF_FID;
+
+ bytesize = roundup(nvm_param.num_bits, BITS_PER_BYTE) / BITS_PER_BYTE;
+ if (nvm_param.num_bits == 1)
+ buf = &val->vbool;
+
+ data_addr = dma_zalloc_coherent(&bp->pdev->dev, bytesize,
+ &data_dma_addr, GFP_KERNEL);
+ if (!data_addr)
+ return -ENOMEM;
+
+ req->data_addr = cpu_to_le64(data_dma_addr);
+ req->data_len = cpu_to_le16(nvm_param.num_bits);
+ req->option_num = cpu_to_le16(nvm_param.offset);
+ req->index_0 = cpu_to_le16(idx);
+ if (idx)
+ req->dimensions = cpu_to_le16(1);
+
+ if (req->req_type == HWRM_NVM_SET_VARIABLE)
+ memcpy(data_addr, buf, bytesize);
+
+ rc = hwrm_send_message(bp, msg, msg_len, HWRM_CMD_TIMEOUT);
+ if (!rc && req->req_type == HWRM_NVM_GET_VARIABLE)
+ memcpy(buf, data_addr, bytesize);
+
+ dma_free_coherent(&bp->pdev->dev, bytesize, data_addr, data_dma_addr);
+ if (rc)
+ return -EIO;
+ return 0;
+}
+
+static int bnxt_dl_nvm_param_get(struct devlink *dl, u32 id,
+ struct devlink_param_gset_ctx *ctx)
+{
+ struct hwrm_nvm_get_variable_input req = {0};
+ struct bnxt *bp = bnxt_get_bp_from_dl(dl);
+
+ bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_NVM_GET_VARIABLE, -1, -1);
+ return bnxt_hwrm_nvm_req(bp, id, &req, sizeof(req), &ctx->val);
+}
+
+static int bnxt_dl_nvm_param_set(struct devlink *dl, u32 id,
+ struct devlink_param_gset_ctx *ctx)
+{
+ struct hwrm_nvm_set_variable_input req = {0};
+ struct bnxt *bp = bnxt_get_bp_from_dl(dl);
+
+ bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_NVM_SET_VARIABLE, -1, -1);
+ return bnxt_hwrm_nvm_req(bp, id, &req, sizeof(req), &ctx->val);
+}
+
+static const struct devlink_param bnxt_dl_params[] = {
+ DEVLINK_PARAM_GENERIC(ENABLE_SRIOV,
+ BIT(DEVLINK_PARAM_CMODE_PERMANENT),
+ bnxt_dl_nvm_param_get, bnxt_dl_nvm_param_set,
+ NULL),
+};
+
int bnxt_dl_register(struct bnxt *bp)
{
struct devlink *dl;
int rc;
- if (!pci_find_ext_capability(bp->pdev, PCI_EXT_CAP_ID_SRIOV))
- return 0;
-
- if (bp->hwrm_spec_code < 0x10803) {
- netdev_warn(bp->dev, "Firmware does not support SR-IOV E-Switch SWITCHDEV mode.\n");
+ if (bp->hwrm_spec_code < 0x10600) {
+ netdev_warn(bp->dev, "Firmware does not support NVM params");
return -ENOTSUPP;
}
}
bnxt_link_bp_to_dl(bp, dl);
- bp->eswitch_mode = DEVLINK_ESWITCH_MODE_LEGACY;
+
+ /* Add switchdev eswitch mode setting, if SRIOV supported */
+ if (pci_find_ext_capability(bp->pdev, PCI_EXT_CAP_ID_SRIOV) &&
+ bp->hwrm_spec_code > 0x10803)
+ bp->eswitch_mode = DEVLINK_ESWITCH_MODE_LEGACY;
+
rc = devlink_register(dl, &bp->pdev->dev);
if (rc) {
- bnxt_link_bp_to_dl(bp, NULL);
- devlink_free(dl);
netdev_warn(bp->dev, "devlink_register failed. rc=%d", rc);
- return rc;
+ goto err_dl_free;
+ }
+
+ rc = devlink_params_register(dl, bnxt_dl_params,
+ ARRAY_SIZE(bnxt_dl_params));
+ if (rc) {
+ netdev_warn(bp->dev, "devlink_params_register failed. rc=%d",
+ rc);
+ goto err_dl_unreg;
}
return 0;
+
+err_dl_unreg:
+ devlink_unregister(dl);
+err_dl_free:
+ bnxt_link_bp_to_dl(bp, NULL);
+ devlink_free(dl);
+ return rc;
}
void bnxt_dl_unregister(struct bnxt *bp)
if (!dl)
return;
+ devlink_params_unregister(dl, bnxt_dl_params,
+ ARRAY_SIZE(bnxt_dl_params));
devlink_unregister(dl);
devlink_free(dl);
}
}
}
+#define NVM_OFF_ENABLE_SRIOV 401
+
+enum bnxt_nvm_dir_type {
+ BNXT_NVM_SHARED_CFG = 40,
+ BNXT_NVM_PORT_CFG,
+ BNXT_NVM_FUNC_CFG,
+};
+
+struct bnxt_dl_nvm_param {
+ u16 id;
+ u16 offset;
+ u16 dir_type;
+ u16 num_bits;
+};
+
int bnxt_dl_register(struct bnxt *bp);
void bnxt_dl_unregister(struct bnxt *bp);
u8 unused_0[7];
};
+struct hwrm_nvm_variable_input {
+ __le16 req_type;
+ __le16 cmpl_ring;
+ __le16 seq_id;
+ __le16 target_id;
+ __le64 resp_addr;
+ __le64 data_addr;
+ __le16 data_len;
+ __le16 option_num;
+ __le16 dimensions;
+ __le16 index_0;
+};
+
/* hwrm_nvm_get_variable_input (size:320b/40B) */
struct hwrm_nvm_get_variable_input {
__le16 req_type;
int bnxt_tc_setup_flower(struct bnxt *bp, u16 src_fid,
struct tc_cls_flower_offload *cls_flower)
{
- int rc = 0;
-
switch (cls_flower->command) {
case TC_CLSFLOWER_REPLACE:
- rc = bnxt_tc_add_flow(bp, src_fid, cls_flower);
- break;
-
+ return bnxt_tc_add_flow(bp, src_fid, cls_flower);
case TC_CLSFLOWER_DESTROY:
- rc = bnxt_tc_del_flow(bp, cls_flower);
- break;
-
+ return bnxt_tc_del_flow(bp, cls_flower);
case TC_CLSFLOWER_STATS:
- rc = bnxt_tc_get_flow_stats(bp, cls_flower);
- break;
+ return bnxt_tc_get_flow_stats(bp, cls_flower);
+ default:
+ return -EOPNOTSUPP;
}
- return rc;
}
static const struct rhashtable_params bnxt_tc_flow_ht_params = {
case TC_BLOCK_BIND:
return tcf_block_cb_register(f->block,
bnxt_vf_rep_setup_tc_block_cb,
- vf_rep, vf_rep);
+ vf_rep, vf_rep, f->extack);
case TC_BLOCK_UNBIND:
tcf_block_cb_unregister(f->block,
bnxt_vf_rep_setup_tc_block_cb, vf_rep);
break;
case DEVLINK_ESWITCH_MODE_SWITCHDEV:
+ if (bp->hwrm_spec_code < 0x10803) {
+ netdev_warn(bp->dev, "FW does not support SRIOV E-Switch SWITCHDEV mode\n");
+ rc = -ENOTSUPP;
+ goto done;
+ }
+
if (pci_num_vf(bp->pdev) == 0) {
- netdev_info(bp->dev,
- "Enable VFs before setting switchdev mode");
+ netdev_info(bp->dev, "Enable VFs before setting switchdev mode");
rc = -EPERM;
goto done;
}
rc = bnxt_xdp_set(bp, xdp->prog);
break;
case XDP_QUERY_PROG:
- xdp->prog_attached = !!bp->xdp_prog;
xdp->prog_id = bp->xdp_prog ? bp->xdp_prog->aux->id : 0;
rc = 0;
break;
id_tbl->max = size;
id_tbl->next = next;
spin_lock_init(&id_tbl->lock);
- id_tbl->table = kcalloc(DIV_ROUND_UP(size, 32), 4, GFP_KERNEL);
+ id_tbl->table = kcalloc(BITS_TO_LONGS(size), sizeof(long), GFP_KERNEL);
if (!id_tbl->table)
return -ENOMEM;
static int cnic_bnx2x_fcoe_fw_destroy(struct cnic_dev *dev, struct kwqe *kwqe)
{
- struct fcoe_kwqe_destroy *req;
union l5cm_specific_data l5_data;
struct cnic_local *cp = dev->cnic_priv;
struct bnx2x *bp = netdev_priv(dev->netdev);
cnic_bnx2x_delete_wait(dev, MAX_ISCSI_TBL_SZ);
- req = (struct fcoe_kwqe_destroy *) kwqe;
cid = BNX2X_HW_CID(bp, cp->fcoe_init_cid);
memset(&l5_data, 0, sizeof(l5_data));
{
struct cnic_local *cp = dev->cnic_priv;
- kfree(cp->csk_tbl);
+ kvfree(cp->csk_tbl);
cp->csk_tbl = NULL;
cnic_free_id_tbl(&cp->csk_port_tbl);
}
struct cnic_local *cp = dev->cnic_priv;
u32 port_id;
- cp->csk_tbl = kcalloc(MAX_CM_SK_TBL_SZ, sizeof(struct cnic_sock),
- GFP_KERNEL);
+ cp->csk_tbl = kvcalloc(MAX_CM_SK_TBL_SZ, sizeof(struct cnic_sock),
+ GFP_KERNEL);
if (!cp->csk_tbl)
return -ENOMEM;
struct cnic_local *cp = dev->cnic_priv;
struct bnx2x *bp = netdev_priv(dev->netdev);
struct cnic_eth_dev *ethdev = cp->ethdev;
- int func, ret;
+ int ret;
u32 pfid;
dev->stats_addr = ethdev->addr_drv_info_to_mcp;
cp->func = bp->pf_num;
- func = CNIC_FUNC(cp);
pfid = bp->pfid;
ret = cnic_init_id_tbl(&cp->cid_tbl, MAX_ISCSI_TBL_SZ,
case TG3_APE_LOCK_GPIO:
if (tg3_asic_rev(tp) == ASIC_REV_5761)
return 0;
+ /* else: fall through */
case TG3_APE_LOCK_GRC:
case TG3_APE_LOCK_MEM:
if (!tp->pci_fn)
case TG3_APE_LOCK_GPIO:
if (tg3_asic_rev(tp) == ASIC_REV_5761)
return;
+ /* else: fall through */
case TG3_APE_LOCK_GRC:
case TG3_APE_LOCK_MEM:
if (!tp->pci_fn)
switch (limit) {
case 16:
tw32(MAC_RCV_RULE_15, 0); tw32(MAC_RCV_VALUE_15, 0);
+ /* fall through */
case 15:
tw32(MAC_RCV_RULE_14, 0); tw32(MAC_RCV_VALUE_14, 0);
+ /* fall through */
case 14:
tw32(MAC_RCV_RULE_13, 0); tw32(MAC_RCV_VALUE_13, 0);
+ /* fall through */
case 13:
tw32(MAC_RCV_RULE_12, 0); tw32(MAC_RCV_VALUE_12, 0);
+ /* fall through */
case 12:
tw32(MAC_RCV_RULE_11, 0); tw32(MAC_RCV_VALUE_11, 0);
+ /* fall through */
case 11:
tw32(MAC_RCV_RULE_10, 0); tw32(MAC_RCV_VALUE_10, 0);
+ /* fall through */
case 10:
tw32(MAC_RCV_RULE_9, 0); tw32(MAC_RCV_VALUE_9, 0);
+ /* fall through */
case 9:
tw32(MAC_RCV_RULE_8, 0); tw32(MAC_RCV_VALUE_8, 0);
+ /* fall through */
case 8:
tw32(MAC_RCV_RULE_7, 0); tw32(MAC_RCV_VALUE_7, 0);
+ /* fall through */
case 7:
tw32(MAC_RCV_RULE_6, 0); tw32(MAC_RCV_VALUE_6, 0);
+ /* fall through */
case 6:
tw32(MAC_RCV_RULE_5, 0); tw32(MAC_RCV_VALUE_5, 0);
+ /* fall through */
case 5:
tw32(MAC_RCV_RULE_4, 0); tw32(MAC_RCV_VALUE_4, 0);
+ /* fall through */
case 4:
/* tw32(MAC_RCV_RULE_3, 0); tw32(MAC_RCV_VALUE_3, 0); */
case 3:
# Atmel device configuration
#
-config NET_CADENCE
+config NET_VENDOR_CADENCE
bool "Cadence devices"
depends on HAS_IOMEM
default y
the remaining Atmel network card questions. If you say Y, you will be
asked for your specific card in the following questions.
-if NET_CADENCE
+if NET_VENDOR_CADENCE
config MACB
tristate "Cadence MACB/GEM support"
To compile this driver as a module, choose M here: the module
will be called macb_pci.
-endif # NET_CADENCE
+endif # NET_VENDOR_CADENCE
int err;
u32 reg;
+ bp->queues[0].bp = bp;
+
dev->netdev_ops = &at91ether_netdev_ops;
dev->ethtool_ops = &macb_ethtool_ops;
if (delta > TSU_NSEC_MAX_VAL) {
gem_tsu_get_time(&bp->ptp_clock_info, &now);
- if (sign)
- now = timespec64_sub(now, then);
- else
- now = timespec64_add(now, then);
+ now = timespec64_add(now, then);
gem_tsu_set_time(&bp->ptp_clock_info,
(const struct timespec64 *)&now);
config NET_CALXEDA_XGMAC
tristate "Calxeda 1G/10G XGMAC Ethernet driver"
- depends on HAS_IOMEM && HAS_DMA
+ depends on HAS_IOMEM
depends on ARCH_HIGHBANK || COMPILE_TEST
select CRC32
help
config NET_VENDOR_CAVIUM
bool "Cavium ethernet drivers"
- depends on PCI
default y
---help---
Select this option if you want enable Cavium network support.
for (q_no = srn; q_no < ern; q_no++) {
reg_val = octeon_read_csr(oct, CN23XX_SLI_OQ_PKT_CONTROL(q_no));
+ /* clear IPTR */
+ reg_val &= ~CN23XX_PKT_OUTPUT_CTL_IPTR;
+
/* set DPTR */
reg_val |= CN23XX_PKT_OUTPUT_CTL_DPTR;
reg_val =
octeon_read_csr(oct, CN23XX_VF_SLI_OQ_PKT_CONTROL(q_no));
+ /* clear IPTR */
+ reg_val &= ~CN23XX_PKT_OUTPUT_CTL_IPTR;
+
/* set DPTR */
reg_val |= CN23XX_PKT_OUTPUT_CTL_DPTR;
lt = (struct lio_time *)sc->virtdptr;
/* Get time of the day */
- getnstimeofday64(&ts);
+ ktime_get_real_ts64(&ts);
lt->sec = ts.tv_sec;
lt->nsec = ts.tv_nsec;
octeon_swap_8B_data((u64 *)lt, (sizeof(struct lio_time)) / 8);
ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl);
if (ret < 0) {
- dev_err(&oct->pci_dev->dev, "Add VLAN filter failed in core (ret: 0x%x)\n",
+ dev_err(&oct->pci_dev->dev, "Del VLAN filter failed in core (ret: 0x%x)\n",
ret);
}
return ret;
{
struct lio *lio = NULL;
struct net_device *netdev;
- u8 mac[6], i, j, *fw_ver;
+ u8 mac[6], i, j, *fw_ver, *micro_ver;
+ unsigned long micro;
+ u32 cur_ver;
struct octeon_soft_command *sc;
struct liquidio_if_cfg_context *ctx;
struct liquidio_if_cfg_resp *resp;
fw_ver);
}
+ /* extract micro version field; point past '<maj>.<min>.' */
+ micro_ver = fw_ver + strlen(LIQUIDIO_BASE_VERSION) + 1;
+ if (kstrtoul(micro_ver, 10, µ) != 0)
+ micro = 0;
+ octeon_dev->fw_info.ver.maj = LIQUIDIO_BASE_MAJOR_VERSION;
+ octeon_dev->fw_info.ver.min = LIQUIDIO_BASE_MINOR_VERSION;
+ octeon_dev->fw_info.ver.rev = micro;
+
octeon_swap_8B_data((u64 *)(&resp->cfg_info),
(sizeof(struct liquidio_if_cfg_info)) >> 3);
for (j = 0; j < octeon_dev->sriov_info.max_vfs; j++) {
u8 vfmac[ETH_ALEN];
- random_ether_addr(&vfmac[0]);
- if (__liquidio_set_vf_mac(netdev, j,
- &vfmac[0], false)) {
+ eth_random_addr(vfmac);
+ if (__liquidio_set_vf_mac(netdev, j, vfmac, false)) {
dev_err(&octeon_dev->pci_dev->dev,
"Error setting VF%d MAC address\n",
j);
OCTEON_CN2350_25GB_SUBSYS_ID ||
octeon_dev->subsystem_id ==
OCTEON_CN2360_25GB_SUBSYS_ID) {
- liquidio_get_speed(lio);
+ cur_ver = OCT_FW_VER(octeon_dev->fw_info.ver.maj,
+ octeon_dev->fw_info.ver.min,
+ octeon_dev->fw_info.ver.rev);
+
+ /* speed control unsupported in f/w older than 1.7.2 */
+ if (cur_ver < OCT_FW_VER(1, 7, 2)) {
+ dev_info(&octeon_dev->pci_dev->dev,
+ "speed setting not supported by f/w.");
+ octeon_dev->speed_setting = 25;
+ octeon_dev->no_speed_setting = 1;
+ } else {
+ liquidio_get_speed(lio);
+ }
if (octeon_dev->speed_setting == 0) {
octeon_dev->speed_setting = 25;
ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl);
if (ret < 0) {
- dev_err(&oct->pci_dev->dev, "Add VLAN filter failed in core (ret: 0x%x)\n",
+ dev_err(&oct->pci_dev->dev, "Del VLAN filter failed in core (ret: 0x%x)\n",
ret);
}
return ret;
*
* Octeon always uses UTC time. so timezone information is not sent.
*/
- getnstimeofday64(&ts);
+ ktime_get_real_ts64(&ts);
ret = snprintf(boottime, MAX_BOOTTIME_SIZE,
" time_sec=%lld time_nsec=%ld",
(s64)ts.tv_sec, ts.tv_nsec);
*/
u32 app_mode;
char liquidio_firmware_version[32];
+ /* Fields extracted from legacy string 'liquidio_firmware_version' */
+ struct {
+ u8 maj;
+ u8 min;
+ u8 rev;
+ } ver;
};
+#define OCT_FW_VER(maj, min, rev) \
+ (((u32)(maj) << 16) | ((u32)(min) << 8) | ((u32)(rev)))
+
/* wrappers around work structs */
struct cavium_wk {
struct delayed_work work;
memset(iq->request_list, 0, sizeof(*iq->request_list) * num_descs);
- dev_dbg(&oct->pci_dev->dev, "IQ[%d]: base: %p basedma: %llx count: %d\n",
- iq_no, iq->base_addr, iq->base_addr_dma, iq->max_count);
+ dev_dbg(&oct->pci_dev->dev, "IQ[%d]: base: %p basedma: %pad count: %d\n",
+ iq_no, iq->base_addr, &iq->base_addr_dma, iq->max_count);
iq->txpciq.u64 = txpciq.u64;
iq->fill_threshold = (u32)conf->db_min;
case XDP_SETUP_PROG:
return nicvf_xdp_setup(nic, xdp->prog);
case XDP_QUERY_PROG:
- xdp->prog_attached = !!nic->xdp_prog;
xdp->prog_id = nic->xdp_prog ? nic->xdp_prog->aux->id : 0;
return 0;
default:
#define CUDBG_NUM_ULPTX 11
#define CUDBG_NUM_ULPTX_READ 512
+#define CUDBG_NUM_ULPTX_ASIC 6
+#define CUDBG_NUM_ULPTX_ASIC_READ 128
+
+#define CUDBG_ULPTX_LA_REV 1
struct cudbg_ulptx_la {
u32 rdptr[CUDBG_NUM_ULPTX];
u32 wrptr[CUDBG_NUM_ULPTX];
u32 rddata[CUDBG_NUM_ULPTX];
u32 rd_data[CUDBG_NUM_ULPTX][CUDBG_NUM_ULPTX_READ];
+ u32 rdptr_asic[CUDBG_NUM_ULPTX_ASIC_READ];
+ u32 rddata_asic[CUDBG_NUM_ULPTX_ASIC_READ][CUDBG_NUM_ULPTX_ASIC];
};
#define CUDBG_CHAC_PBT_ADDR 0x2800
struct adapter *padap = pdbg_init->adap;
struct cudbg_buffer temp_buff = { 0 };
struct cudbg_ulptx_la *ulptx_la_buff;
+ struct cudbg_ver_hdr *ver_hdr;
u32 i, j;
int rc;
- rc = cudbg_get_buff(pdbg_init, dbg_buff, sizeof(struct cudbg_ulptx_la),
+ rc = cudbg_get_buff(pdbg_init, dbg_buff,
+ sizeof(struct cudbg_ver_hdr) +
+ sizeof(struct cudbg_ulptx_la),
&temp_buff);
if (rc)
return rc;
- ulptx_la_buff = (struct cudbg_ulptx_la *)temp_buff.data;
+ ver_hdr = (struct cudbg_ver_hdr *)temp_buff.data;
+ ver_hdr->signature = CUDBG_ENTITY_SIGNATURE;
+ ver_hdr->revision = CUDBG_ULPTX_LA_REV;
+ ver_hdr->size = sizeof(struct cudbg_ulptx_la);
+
+ ulptx_la_buff = (struct cudbg_ulptx_la *)(temp_buff.data +
+ sizeof(*ver_hdr));
for (i = 0; i < CUDBG_NUM_ULPTX; i++) {
ulptx_la_buff->rdptr[i] = t4_read_reg(padap,
ULP_TX_LA_RDPTR_0_A +
t4_read_reg(padap,
ULP_TX_LA_RDDATA_0_A + 0x10 * i);
}
+
+ for (i = 0; i < CUDBG_NUM_ULPTX_ASIC_READ; i++) {
+ t4_write_reg(padap, ULP_TX_ASIC_DEBUG_CTRL_A, 0x1);
+ ulptx_la_buff->rdptr_asic[i] =
+ t4_read_reg(padap, ULP_TX_ASIC_DEBUG_CTRL_A);
+ ulptx_la_buff->rddata_asic[i][0] =
+ t4_read_reg(padap, ULP_TX_ASIC_DEBUG_0_A);
+ ulptx_la_buff->rddata_asic[i][1] =
+ t4_read_reg(padap, ULP_TX_ASIC_DEBUG_1_A);
+ ulptx_la_buff->rddata_asic[i][2] =
+ t4_read_reg(padap, ULP_TX_ASIC_DEBUG_2_A);
+ ulptx_la_buff->rddata_asic[i][3] =
+ t4_read_reg(padap, ULP_TX_ASIC_DEBUG_3_A);
+ ulptx_la_buff->rddata_asic[i][4] =
+ t4_read_reg(padap, ULP_TX_ASIC_DEBUG_4_A);
+ ulptx_la_buff->rddata_asic[i][5] =
+ t4_read_reg(padap, PM_RX_BASE_ADDR);
+ }
+
return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff);
}
#include <linux/spinlock.h>
#include <linux/timer.h>
#include <linux/vmalloc.h>
+#include <linux/rhashtable.h>
#include <linux/etherdevice.h>
#include <linux/net_tstamp.h>
#include <linux/ptp_clock_kernel.h>
u8 na[MACADDR_LEN + 1];
};
+/* Maximum resources provisioned for a PCI PF.
+ */
+struct pf_resources {
+ unsigned int nvi; /* N virtual interfaces */
+ unsigned int neq; /* N egress Qs */
+ unsigned int nethctrl; /* N egress ETH or CTRL Qs */
+ unsigned int niqflint; /* N ingress Qs/w free list(s) & intr */
+ unsigned int niq; /* N ingress Qs */
+ unsigned int tc; /* PCI-E traffic class */
+ unsigned int pmask; /* port access rights mask */
+ unsigned int nexactf; /* N exact MPS filters */
+ unsigned int r_caps; /* read capabilities */
+ unsigned int wx_caps; /* write/execute capabilities */
+};
+
struct pci_params {
unsigned int vpd_cap_addr;
unsigned char speed;
struct sge_params sge;
struct tp_params tp;
struct vpd_params vpd;
+ struct pf_resources pfres;
struct pci_params pci;
struct devlog_params devlog;
enum pcie_memwin drv_memwin;
MAX_INGQ = MAX_ETH_QSETS + INGQ_EXTRAS,
};
+enum {
+ PRIV_FLAG_PORT_TX_VM_BIT,
+};
+
+#define PRIV_FLAG_PORT_TX_VM BIT(PRIV_FLAG_PORT_TX_VM_BIT)
+
+#define PRIV_FLAGS_ADAP 0
+#define PRIV_FLAGS_PORT PRIV_FLAG_PORT_TX_VM
+
struct adapter;
struct sge_rspq;
struct hwtstamp_config tstamp_config;
bool ptp_enable;
struct sched_table *sched_tbl;
+ u32 eth_flags;
};
struct dentry;
unsigned int flags;
unsigned int adap_idx;
enum chip_type chip;
+ u32 eth_flags;
int msg_enable;
__be16 vxlan_port;
struct chcr_stats_debug chcr_stats;
/* TC flower offload */
+ bool tc_flower_initialized;
struct rhashtable flower_tbl;
struct rhashtable_params flower_ht_params;
struct timer_list flower_stats_timer;
void t4_free_sge_resources(struct adapter *adap);
void t4_free_ofld_rxqs(struct adapter *adap, int n, struct sge_ofld_rxq *q);
irq_handler_t t4_intr_handler(struct adapter *adap);
-netdev_tx_t t4_eth_xmit(struct sk_buff *skb, struct net_device *dev);
+netdev_tx_t t4_start_xmit(struct sk_buff *skb, struct net_device *dev);
int t4_ethrx_handler(struct sge_rspq *q, const __be64 *rsp,
const struct pkt_gl *gl);
int t4_mgmt_tx(struct adapter *adap, struct sk_buff *skb);
int t4_seeprom_wp(struct adapter *adapter, bool enable);
int t4_get_raw_vpd_params(struct adapter *adapter, struct vpd_params *p);
int t4_get_vpd_params(struct adapter *adapter, struct vpd_params *p);
+int t4_get_pfres(struct adapter *adapter);
int t4_read_flash(struct adapter *adapter, unsigned int addr,
unsigned int nwords, u32 *data, int byte_oriented);
int t4_load_fw(struct adapter *adapter, const u8 *fw_data, unsigned int size);
}
break;
case CUDBG_ULPTX_LA:
- len = sizeof(struct cudbg_ulptx_la);
+ len = sizeof(struct cudbg_ver_hdr) +
+ sizeof(struct cudbg_ulptx_la);
break;
case CUDBG_UP_CIM_INDIRECT:
n = 0;
.release = seq_release_private
};
+static int resources_show(struct seq_file *seq, void *v)
+{
+ struct adapter *adapter = seq->private;
+ struct pf_resources *pfres = &adapter->params.pfres;
+
+ #define S(desc, fmt, var) \
+ seq_printf(seq, "%-60s " fmt "\n", \
+ desc " (" #var "):", pfres->var)
+
+ S("Virtual Interfaces", "%d", nvi);
+ S("Egress Queues", "%d", neq);
+ S("Ethernet Control", "%d", nethctrl);
+ S("Ingress Queues/w Free Lists/Interrupts", "%d", niqflint);
+ S("Ingress Queues", "%d", niq);
+ S("Traffic Class", "%d", tc);
+ S("Port Access Rights Mask", "%#x", pmask);
+ S("MAC Address Filters", "%d", nexactf);
+ S("Firmware Command Read Capabilities", "%#x", r_caps);
+ S("Firmware Command Write/Execute Capabilities", "%#x", wx_caps);
+
+ #undef S
+
+ return 0;
+}
+
+static int resources_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, resources_show, inode->i_private);
+}
+
+static const struct file_operations resources_debugfs_fops = {
+ .owner = THIS_MODULE,
+ .open = resources_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
+};
+
/**
* ethqset2pinfo - return port_info of an Ethernet Queue Set
* @adap: the adapter
.llseek = seq_lseek,
.release = single_release,
};
+
+#define PRINT_ADAP_STATS(string, value) \
+ seq_printf(seq, "%-25s %-20llu\n", (string), \
+ (unsigned long long)(value))
+
+#define PRINT_CH_STATS(string, value) \
+do { \
+ seq_printf(seq, "%-25s ", (string)); \
+ for (i = 0; i < adap->params.arch.nchan; i++) \
+ seq_printf(seq, "%-20llu ", \
+ (unsigned long long)stats.value[i]); \
+ seq_printf(seq, "\n"); \
+} while (0)
+
+#define PRINT_CH_STATS2(string, value) \
+do { \
+ seq_printf(seq, "%-25s ", (string)); \
+ for (i = 0; i < adap->params.arch.nchan; i++) \
+ seq_printf(seq, "%-20llu ", \
+ (unsigned long long)stats[i].value); \
+ seq_printf(seq, "\n"); \
+} while (0)
+
+static void show_tcp_stats(struct seq_file *seq)
+{
+ struct adapter *adap = seq->private;
+ struct tp_tcp_stats v4, v6;
+
+ spin_lock(&adap->stats_lock);
+ t4_tp_get_tcp_stats(adap, &v4, &v6, false);
+ spin_unlock(&adap->stats_lock);
+
+ PRINT_ADAP_STATS("tcp_ipv4_out_rsts:", v4.tcp_out_rsts);
+ PRINT_ADAP_STATS("tcp_ipv4_in_segs:", v4.tcp_in_segs);
+ PRINT_ADAP_STATS("tcp_ipv4_out_segs:", v4.tcp_out_segs);
+ PRINT_ADAP_STATS("tcp_ipv4_retrans_segs:", v4.tcp_retrans_segs);
+ PRINT_ADAP_STATS("tcp_ipv6_out_rsts:", v6.tcp_out_rsts);
+ PRINT_ADAP_STATS("tcp_ipv6_in_segs:", v6.tcp_in_segs);
+ PRINT_ADAP_STATS("tcp_ipv6_out_segs:", v6.tcp_out_segs);
+ PRINT_ADAP_STATS("tcp_ipv6_retrans_segs:", v6.tcp_retrans_segs);
+}
+
+static void show_ddp_stats(struct seq_file *seq)
+{
+ struct adapter *adap = seq->private;
+ struct tp_usm_stats stats;
+
+ spin_lock(&adap->stats_lock);
+ t4_get_usm_stats(adap, &stats, false);
+ spin_unlock(&adap->stats_lock);
+
+ PRINT_ADAP_STATS("usm_ddp_frames:", stats.frames);
+ PRINT_ADAP_STATS("usm_ddp_octets:", stats.octets);
+ PRINT_ADAP_STATS("usm_ddp_drops:", stats.drops);
+}
+
+static void show_rdma_stats(struct seq_file *seq)
+{
+ struct adapter *adap = seq->private;
+ struct tp_rdma_stats stats;
+
+ spin_lock(&adap->stats_lock);
+ t4_tp_get_rdma_stats(adap, &stats, false);
+ spin_unlock(&adap->stats_lock);
+
+ PRINT_ADAP_STATS("rdma_no_rqe_mod_defer:", stats.rqe_dfr_mod);
+ PRINT_ADAP_STATS("rdma_no_rqe_pkt_defer:", stats.rqe_dfr_pkt);
+}
+
+static void show_tp_err_adapter_stats(struct seq_file *seq)
+{
+ struct adapter *adap = seq->private;
+ struct tp_err_stats stats;
+
+ spin_lock(&adap->stats_lock);
+ t4_tp_get_err_stats(adap, &stats, false);
+ spin_unlock(&adap->stats_lock);
+
+ PRINT_ADAP_STATS("tp_err_ofld_no_neigh:", stats.ofld_no_neigh);
+ PRINT_ADAP_STATS("tp_err_ofld_cong_defer:", stats.ofld_cong_defer);
+}
+
+static void show_cpl_stats(struct seq_file *seq)
+{
+ struct adapter *adap = seq->private;
+ struct tp_cpl_stats stats;
+ u8 i;
+
+ spin_lock(&adap->stats_lock);
+ t4_tp_get_cpl_stats(adap, &stats, false);
+ spin_unlock(&adap->stats_lock);
+
+ PRINT_CH_STATS("tp_cpl_requests:", req);
+ PRINT_CH_STATS("tp_cpl_responses:", rsp);
+}
+
+static void show_tp_err_channel_stats(struct seq_file *seq)
+{
+ struct adapter *adap = seq->private;
+ struct tp_err_stats stats;
+ u8 i;
+
+ spin_lock(&adap->stats_lock);
+ t4_tp_get_err_stats(adap, &stats, false);
+ spin_unlock(&adap->stats_lock);
+
+ PRINT_CH_STATS("tp_mac_in_errs:", mac_in_errs);
+ PRINT_CH_STATS("tp_hdr_in_errs:", hdr_in_errs);
+ PRINT_CH_STATS("tp_tcp_in_errs:", tcp_in_errs);
+ PRINT_CH_STATS("tp_tcp6_in_errs:", tcp6_in_errs);
+ PRINT_CH_STATS("tp_tnl_cong_drops:", tnl_cong_drops);
+ PRINT_CH_STATS("tp_tnl_tx_drops:", tnl_tx_drops);
+ PRINT_CH_STATS("tp_ofld_vlan_drops:", ofld_vlan_drops);
+ PRINT_CH_STATS("tp_ofld_chan_drops:", ofld_chan_drops);
+}
+
+static void show_fcoe_stats(struct seq_file *seq)
+{
+ struct adapter *adap = seq->private;
+ struct tp_fcoe_stats stats[NCHAN];
+ u8 i;
+
+ spin_lock(&adap->stats_lock);
+ for (i = 0; i < adap->params.arch.nchan; i++)
+ t4_get_fcoe_stats(adap, i, &stats[i], false);
+ spin_unlock(&adap->stats_lock);
+
+ PRINT_CH_STATS2("fcoe_octets_ddp", octets_ddp);
+ PRINT_CH_STATS2("fcoe_frames_ddp", frames_ddp);
+ PRINT_CH_STATS2("fcoe_frames_drop", frames_drop);
+}
+
+#undef PRINT_CH_STATS2
+#undef PRINT_CH_STATS
+#undef PRINT_ADAP_STATS
+
+static int tp_stats_show(struct seq_file *seq, void *v)
+{
+ struct adapter *adap = seq->private;
+
+ seq_puts(seq, "\n--------Adapter Stats--------\n");
+ show_tcp_stats(seq);
+ show_ddp_stats(seq);
+ show_rdma_stats(seq);
+ show_tp_err_adapter_stats(seq);
+
+ seq_puts(seq, "\n-------- Channel Stats --------\n");
+ if (adap->params.arch.nchan == NCHAN)
+ seq_printf(seq, "%-25s %-20s %-20s %-20s %-20s\n",
+ " ", "channel 0", "channel 1",
+ "channel 2", "channel 3");
+ else
+ seq_printf(seq, "%-25s %-20s %-20s\n",
+ " ", "channel 0", "channel 1");
+ show_cpl_stats(seq);
+ show_tp_err_channel_stats(seq);
+ show_fcoe_stats(seq);
+
+ return 0;
+}
+
+DEFINE_SIMPLE_DEBUGFS_FILE(tp_stats);
+
/* Add an array of Debug FS files.
*/
void add_debugfs_files(struct adapter *adap,
{ "rss_key", &rss_key_debugfs_fops, 0400, 0 },
{ "rss_pf_config", &rss_pf_config_debugfs_fops, 0400, 0 },
{ "rss_vf_config", &rss_vf_config_debugfs_fops, 0400, 0 },
+ { "resources", &resources_debugfs_fops, 0400, 0 },
{ "sge_qinfo", &sge_qinfo_debugfs_fops, 0400, 0 },
{ "ibq_tp0", &cim_ibq_fops, 0400, 0 },
{ "ibq_tp1", &cim_ibq_fops, 0400, 1 },
{ "blocked_fl", &blocked_fl_fops, 0600, 0 },
{ "meminfo", &meminfo_fops, 0400, 0 },
{ "crypto", &chcr_stats_debugfs_fops, 0400, 0 },
+ { "tp_stats", &tp_stats_debugfs_fops, 0400, 0 },
};
/* Debug FS nodes common to all T5 and later adapters.
"db_drop ",
"db_full ",
"db_empty ",
- "tcp_ipv4_out_rsts ",
- "tcp_ipv4_in_segs ",
- "tcp_ipv4_out_segs ",
- "tcp_ipv4_retrans_segs ",
- "tcp_ipv6_out_rsts ",
- "tcp_ipv6_in_segs ",
- "tcp_ipv6_out_segs ",
- "tcp_ipv6_retrans_segs ",
- "usm_ddp_frames ",
- "usm_ddp_octets ",
- "usm_ddp_drops ",
- "rdma_no_rqe_mod_defer ",
- "rdma_no_rqe_pkt_defer ",
- "tp_err_ofld_no_neigh ",
- "tp_err_ofld_cong_defer ",
"write_coal_success ",
"write_coal_fail ",
};
-static char channel_stats_strings[][ETH_GSTRING_LEN] = {
- "--------Channel--------- ",
- "tp_cpl_requests ",
- "tp_cpl_responses ",
- "tp_mac_in_errs ",
- "tp_hdr_in_errs ",
- "tp_tcp_in_errs ",
- "tp_tcp6_in_errs ",
- "tp_tnl_cong_drops ",
- "tp_tnl_tx_drops ",
- "tp_ofld_vlan_drops ",
- "tp_ofld_chan_drops ",
- "fcoe_octets_ddp ",
- "fcoe_frames_ddp ",
- "fcoe_frames_drop ",
-};
-
static char loopback_stats_strings[][ETH_GSTRING_LEN] = {
"-------Loopback----------- ",
"octets_ok ",
"bg3_frames_trunc ",
};
+static const char cxgb4_priv_flags_strings[][ETH_GSTRING_LEN] = {
+ [PRIV_FLAG_PORT_TX_VM_BIT] = "port_tx_vm_wr",
+};
+
static int get_sset_count(struct net_device *dev, int sset)
{
switch (sset) {
case ETH_SS_STATS:
return ARRAY_SIZE(stats_strings) +
ARRAY_SIZE(adapter_stats_strings) +
- ARRAY_SIZE(channel_stats_strings) +
ARRAY_SIZE(loopback_stats_strings);
+ case ETH_SS_PRIV_FLAGS:
+ return ARRAY_SIZE(cxgb4_priv_flags_strings);
default:
return -EOPNOTSUPP;
}
FW_HDR_FW_VER_MINOR_G(exprom_vers),
FW_HDR_FW_VER_MICRO_G(exprom_vers),
FW_HDR_FW_VER_BUILD_G(exprom_vers));
+ info->n_priv_flags = ARRAY_SIZE(cxgb4_priv_flags_strings);
}
static void get_strings(struct net_device *dev, u32 stringset, u8 *data)
memcpy(data, adapter_stats_strings,
sizeof(adapter_stats_strings));
data += sizeof(adapter_stats_strings);
- memcpy(data, channel_stats_strings,
- sizeof(channel_stats_strings));
- data += sizeof(channel_stats_strings);
memcpy(data, loopback_stats_strings,
sizeof(loopback_stats_strings));
+ } else if (stringset == ETH_SS_PRIV_FLAGS) {
+ memcpy(data, cxgb4_priv_flags_strings,
+ sizeof(cxgb4_priv_flags_strings));
}
}
u64 db_drop;
u64 db_full;
u64 db_empty;
- u64 tcp_v4_out_rsts;
- u64 tcp_v4_in_segs;
- u64 tcp_v4_out_segs;
- u64 tcp_v4_retrans_segs;
- u64 tcp_v6_out_rsts;
- u64 tcp_v6_in_segs;
- u64 tcp_v6_out_segs;
- u64 tcp_v6_retrans_segs;
- u64 frames;
- u64 octets;
- u64 drops;
- u64 rqe_dfr_mod;
- u64 rqe_dfr_pkt;
- u64 ofld_no_neigh;
- u64 ofld_cong_defer;
u64 wc_success;
u64 wc_fail;
};
-struct channel_stats {
- u64 cpl_req;
- u64 cpl_rsp;
- u64 mac_in_errs;
- u64 hdr_in_errs;
- u64 tcp_in_errs;
- u64 tcp6_in_errs;
- u64 tnl_cong_drops;
- u64 tnl_tx_drops;
- u64 ofld_vlan_drops;
- u64 ofld_chan_drops;
- u64 octets_ddp;
- u64 frames_ddp;
- u64 frames_drop;
-};
-
static void collect_sge_port_stats(const struct adapter *adap,
const struct port_info *p,
struct queue_port_stats *s)
static void collect_adapter_stats(struct adapter *adap, struct adapter_stats *s)
{
- struct tp_tcp_stats v4, v6;
- struct tp_rdma_stats rdma_stats;
- struct tp_err_stats err_stats;
- struct tp_usm_stats usm_stats;
u64 val1, val2;
memset(s, 0, sizeof(*s));
- spin_lock(&adap->stats_lock);
- t4_tp_get_tcp_stats(adap, &v4, &v6, false);
- t4_tp_get_rdma_stats(adap, &rdma_stats, false);
- t4_get_usm_stats(adap, &usm_stats, false);
- t4_tp_get_err_stats(adap, &err_stats, false);
- spin_unlock(&adap->stats_lock);
-
s->db_drop = adap->db_stats.db_drop;
s->db_full = adap->db_stats.db_full;
s->db_empty = adap->db_stats.db_empty;
- s->tcp_v4_out_rsts = v4.tcp_out_rsts;
- s->tcp_v4_in_segs = v4.tcp_in_segs;
- s->tcp_v4_out_segs = v4.tcp_out_segs;
- s->tcp_v4_retrans_segs = v4.tcp_retrans_segs;
- s->tcp_v6_out_rsts = v6.tcp_out_rsts;
- s->tcp_v6_in_segs = v6.tcp_in_segs;
- s->tcp_v6_out_segs = v6.tcp_out_segs;
- s->tcp_v6_retrans_segs = v6.tcp_retrans_segs;
-
- if (is_offload(adap)) {
- s->frames = usm_stats.frames;
- s->octets = usm_stats.octets;
- s->drops = usm_stats.drops;
- s->rqe_dfr_mod = rdma_stats.rqe_dfr_mod;
- s->rqe_dfr_pkt = rdma_stats.rqe_dfr_pkt;
- }
-
- s->ofld_no_neigh = err_stats.ofld_no_neigh;
- s->ofld_cong_defer = err_stats.ofld_cong_defer;
-
if (!is_t4(adap->params.chip)) {
int v;
}
}
-static void collect_channel_stats(struct adapter *adap, struct channel_stats *s,
- u8 i)
-{
- struct tp_cpl_stats cpl_stats;
- struct tp_err_stats err_stats;
- struct tp_fcoe_stats fcoe_stats;
-
- memset(s, 0, sizeof(*s));
-
- spin_lock(&adap->stats_lock);
- t4_tp_get_cpl_stats(adap, &cpl_stats, false);
- t4_tp_get_err_stats(adap, &err_stats, false);
- t4_get_fcoe_stats(adap, i, &fcoe_stats, false);
- spin_unlock(&adap->stats_lock);
-
- s->cpl_req = cpl_stats.req[i];
- s->cpl_rsp = cpl_stats.rsp[i];
- s->mac_in_errs = err_stats.mac_in_errs[i];
- s->hdr_in_errs = err_stats.hdr_in_errs[i];
- s->tcp_in_errs = err_stats.tcp_in_errs[i];
- s->tcp6_in_errs = err_stats.tcp6_in_errs[i];
- s->tnl_cong_drops = err_stats.tnl_cong_drops[i];
- s->tnl_tx_drops = err_stats.tnl_tx_drops[i];
- s->ofld_vlan_drops = err_stats.ofld_vlan_drops[i];
- s->ofld_chan_drops = err_stats.ofld_chan_drops[i];
- s->octets_ddp = fcoe_stats.octets_ddp;
- s->frames_ddp = fcoe_stats.frames_ddp;
- s->frames_drop = fcoe_stats.frames_drop;
-}
-
static void get_stats(struct net_device *dev, struct ethtool_stats *stats,
u64 *data)
{
collect_adapter_stats(adapter, (struct adapter_stats *)data);
data += sizeof(struct adapter_stats) / sizeof(u64);
- *data++ = (u64)pi->port_id;
- collect_channel_stats(adapter, (struct channel_stats *)data,
- pi->port_id);
- data += sizeof(struct channel_stats) / sizeof(u64);
-
*data++ = (u64)pi->port_id;
memset(&s, 0, sizeof(s));
t4_get_lb_stats(adapter, pi->port_id, &s);
fw_caps_to_lmm(pi->port_type, pi->link_cfg.lpacaps,
link_ksettings->link_modes.lp_advertising);
- if (netif_carrier_ok(dev)) {
- base->speed = pi->link_cfg.speed;
- base->duplex = DUPLEX_FULL;
- } else {
- base->speed = SPEED_UNKNOWN;
- base->duplex = DUPLEX_UNKNOWN;
- }
+ base->speed = (netif_carrier_ok(dev)
+ ? pi->link_cfg.speed
+ : SPEED_UNKNOWN);
+ base->duplex = DUPLEX_FULL;
if (pi->link_cfg.fc & PAUSE_RX) {
if (pi->link_cfg.fc & PAUSE_TX) {
offset, len, &data[eprom->len - len]);
}
+static u32 cxgb4_get_priv_flags(struct net_device *netdev)
+{
+ struct port_info *pi = netdev_priv(netdev);
+ struct adapter *adapter = pi->adapter;
+
+ return (adapter->eth_flags | pi->eth_flags);
+}
+
+/**
+ * set_flags - set/unset specified flags if passed in new_flags
+ * @cur_flags: pointer to current flags
+ * @new_flags: new incoming flags
+ * @flags: set of flags to set/unset
+ */
+static inline void set_flags(u32 *cur_flags, u32 new_flags, u32 flags)
+{
+ *cur_flags = (*cur_flags & ~flags) | (new_flags & flags);
+}
+
+static int cxgb4_set_priv_flags(struct net_device *netdev, u32 flags)
+{
+ struct port_info *pi = netdev_priv(netdev);
+ struct adapter *adapter = pi->adapter;
+
+ set_flags(&adapter->eth_flags, flags, PRIV_FLAGS_ADAP);
+ set_flags(&pi->eth_flags, flags, PRIV_FLAGS_PORT);
+
+ return 0;
+}
+
static const struct ethtool_ops cxgb_ethtool_ops = {
.get_link_ksettings = get_link_ksettings,
.set_link_ksettings = set_link_ksettings,
.get_dump_data = get_dump_data,
.get_module_info = cxgb4_get_module_info,
.get_module_eeprom = cxgb4_get_module_eeprom,
+ .get_priv_flags = cxgb4_get_priv_flags,
+ .set_priv_flags = cxgb4_set_priv_flags,
};
void cxgb4_set_ethtool_ops(struct net_device *netdev)
"Can't %s DCB Priority on port %d, TX Queue %d: err=%d\n",
enable ? "set" : "unset", pi->port_id, i, -err);
else
- txq->dcb_prio = value;
+ txq->dcb_prio = enable ? value : 0;
}
}
QUEUENUMBER_V(s->ethrxq[0].rspq.abs_id));
return 0;
freeout:
+ dev_err(adap->pdev_dev, "Can't allocate queues, err=%d\n", -err);
t4_free_sge_resources(adap);
return err;
}
static u16 cxgb_select_queue(struct net_device *dev, struct sk_buff *skb,
- void *accel_priv, select_queue_fallback_t fallback)
+ struct net_device *sb_dev,
+ select_queue_fallback_t fallback)
{
int txq;
return txq;
}
- return fallback(dev, skb) % dev->real_num_tx_queues;
+ return fallback(dev, skb, NULL) % dev->real_num_tx_queues;
}
static int closest_timer(const struct sge *s, int time)
switch (f->command) {
case TC_BLOCK_BIND:
return tcf_block_cb_register(f->block, cxgb_setup_tc_block_cb,
- pi, dev);
+ pi, dev, f->extack);
case TC_BLOCK_UNBIND:
tcf_block_cb_unregister(f->block, cxgb_setup_tc_block_cb, pi);
return 0;
static const struct net_device_ops cxgb4_netdev_ops = {
.ndo_open = cxgb_open,
.ndo_stop = cxgb_close,
- .ndo_start_xmit = t4_eth_xmit,
+ .ndo_start_xmit = t4_start_xmit,
.ndo_select_queue = cxgb_select_queue,
.ndo_get_stats64 = cxgb_get_stats,
.ndo_set_rx_mode = cxgb_set_rxmode,
u32 v;
int ret;
+ /* Now that we've successfully configured and initialized the adapter
+ * can ask the Firmware what resources it has provisioned for us.
+ */
+ ret = t4_get_pfres(adap);
+ if (ret) {
+ dev_err(adap->pdev_dev,
+ "Unable to retrieve resource provisioning information\n");
+ return ret;
+ }
+
/* get device capabilities */
memset(c, 0, sizeof(*c));
c->op_to_write = htonl(FW_CMD_OP_V(FW_CAPS_CONFIG_CMD) |
goto bye;
}
- /*
- * Grab VPD parameters. This should be done after we establish a
- * connection to the firmware since some of the VPD parameters
- * (notably the Core Clock frequency) are retrieved via requests to
- * the firmware. On the other hand, we need these fairly early on
- * so we do this right after getting ahold of the firmware.
- */
- ret = t4_get_vpd_params(adap, &adap->params.vpd);
- if (ret < 0)
- goto bye;
-
- /*
- * Find out what ports are available to us. Note that we need to do
- * this before calling adap_init0_no_config() since it needs nports
- * and portvec ...
- */
- v =
- FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) |
- FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_PORTVEC);
- ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 1, &v, &port_vec);
- if (ret < 0)
- goto bye;
-
- adap->params.nports = hweight32(port_vec);
- adap->params.portvec = port_vec;
-
/* If the firmware is initialized already, emit a simply note to that
* effect. Otherwise, it's time to try initializing the adapter.
*/
}
}
+ /* Now that we've successfully configured and initialized the adapter
+ * (or found it already initialized), we can ask the Firmware what
+ * resources it has provisioned for us.
+ */
+ ret = t4_get_pfres(adap);
+ if (ret) {
+ dev_err(adap->pdev_dev,
+ "Unable to retrieve resource provisioning information\n");
+ goto bye;
+ }
+
+ /* Grab VPD parameters. This should be done after we establish a
+ * connection to the firmware since some of the VPD parameters
+ * (notably the Core Clock frequency) are retrieved via requests to
+ * the firmware. On the other hand, we need these fairly early on
+ * so we do this right after getting ahold of the firmware.
+ *
+ * We need to do this after initializing the adapter because someone
+ * could have FLASHed a new VPD which won't be read by the firmware
+ * until we do the RESET ...
+ */
+ ret = t4_get_vpd_params(adap, &adap->params.vpd);
+ if (ret < 0)
+ goto bye;
+
+ /* Find out what ports are available to us. Note that we need to do
+ * this before calling adap_init0_no_config() since it needs nports
+ * and portvec ...
+ */
+ v =
+ FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) |
+ FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_PORTVEC);
+ ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 1, &v, &port_vec);
+ if (ret < 0)
+ goto bye;
+
+ adap->params.nports = hweight32(port_vec);
+ adap->params.portvec = port_vec;
+
/* Give the SGE code a chance to pull in anything that it needs ...
* Note that this must be called after we retrieve our VPD parameters
* in order to know how to convert core ticks to seconds, etc.
* of ports we found and the number of available CPUs. Most settings can be
* modified by the admin prior to actual use.
*/
-static void cfg_queues(struct adapter *adap)
+static int cfg_queues(struct adapter *adap)
{
struct sge *s = &adap->sge;
- int i = 0, n10g = 0, qidx = 0;
+ int i, n10g = 0, qidx = 0;
+ int niqflint, neq, avail_eth_qsets;
+ int max_eth_qsets = 32;
#ifndef CONFIG_CHELSIO_T4_DCB
int q10g = 0;
#endif
adap->params.crypto = 0;
}
- n10g += is_x_10g_port(&adap2pinfo(adap, i)->link_cfg);
+ /* Calculate the number of Ethernet Queue Sets available based on
+ * resources provisioned for us. We always have an Asynchronous
+ * Firmware Event Ingress Queue. If we're operating in MSI or Legacy
+ * IRQ Pin Interrupt mode, then we'll also have a Forwarded Interrupt
+ * Ingress Queue. Meanwhile, we need two Egress Queues for each
+ * Queue Set: one for the Free List and one for the Ethernet TX Queue.
+ *
+ * Note that we should also take into account all of the various
+ * Offload Queues. But, in any situation where we're operating in
+ * a Resource Constrained Provisioning environment, doing any Offload
+ * at all is problematic ...
+ */
+ niqflint = adap->params.pfres.niqflint - 1;
+ if (!(adap->flags & USING_MSIX))
+ niqflint--;
+ neq = adap->params.pfres.neq / 2;
+ avail_eth_qsets = min(niqflint, neq);
+
+ if (avail_eth_qsets > max_eth_qsets)
+ avail_eth_qsets = max_eth_qsets;
+
+ if (avail_eth_qsets < adap->params.nports) {
+ dev_err(adap->pdev_dev, "avail_eth_qsets=%d < nports=%d\n",
+ avail_eth_qsets, adap->params.nports);
+ return -ENOMEM;
+ }
+
+ /* Count the number of 10Gb/s or better ports */
+ for_each_port(adap, i)
+ n10g += is_x_10g_port(&adap2pinfo(adap, i)->link_cfg);
+
#ifdef CONFIG_CHELSIO_T4_DCB
/* For Data Center Bridging support we need to be able to support up
* to 8 Traffic Priorities; each of which will be assigned to its
* own TX Queue in order to prevent Head-Of-Line Blocking.
*/
- if (adap->params.nports * 8 > MAX_ETH_QSETS) {
- dev_err(adap->pdev_dev, "MAX_ETH_QSETS=%d < %d!\n",
- MAX_ETH_QSETS, adap->params.nports * 8);
- BUG_ON(1);
+ if (adap->params.nports * 8 > avail_eth_qsets) {
+ dev_err(adap->pdev_dev, "DCB avail_eth_qsets=%d < %d!\n",
+ avail_eth_qsets, adap->params.nports * 8);
+ return -ENOMEM;
}
for_each_port(adap, i) {
* per 10G port.
*/
if (n10g)
- q10g = (MAX_ETH_QSETS - (adap->params.nports - n10g)) / n10g;
+ q10g = (avail_eth_qsets - (adap->params.nports - n10g)) / n10g;
if (q10g > netif_get_num_default_rss_queues())
q10g = netif_get_num_default_rss_queues();
init_rspq(adap, &s->fw_evtq, 0, 1, 1024, 64);
init_rspq(adap, &s->intrq, 0, 1, 512, 64);
+
+ return 0;
}
/*
}
}
+ if (!(adapter->flags & FW_OK))
+ goto fw_attach_fail;
+
/* Configure queues and allocate tables now, they can be needed as
* soon as the first register_netdev completes.
*/
- cfg_queues(adapter);
+ err = cfg_queues(adapter);
+ if (err)
+ goto out_free_dev;
adapter->smt = t4_init_smt();
if (!adapter->smt) {
if (t4_read_reg(adapter, LE_DB_CONFIG_A) & HASHEN_F) {
u32 hash_base, hash_reg;
- if (chip <= CHELSIO_T5) {
+ if (chip_ver <= CHELSIO_T5) {
hash_reg = LE_DB_TID_HASHBASE_A;
hash_base = t4_read_reg(adapter, hash_reg);
adapter->tids.hash_base = hash_base / 4;
goto out_free_dev;
}
+fw_attach_fail:
/*
* The card is now ready to go. If any errors occur during device
* registration we do not fail the whole card but rather proceed only
{
int ret;
+ if (adap->tc_flower_initialized)
+ return -EEXIST;
+
adap->flower_ht_params = cxgb4_tc_flower_ht_params;
ret = rhashtable_init(&adap->flower_tbl, &adap->flower_ht_params);
if (ret)
INIT_WORK(&adap->flower_stats_work, ch_flower_stats_handler);
timer_setup(&adap->flower_stats_timer, ch_flower_stats_cb, 0);
mod_timer(&adap->flower_stats_timer, jiffies + STATS_CHECK_PERIOD);
+ adap->tc_flower_initialized = true;
return 0;
}
void cxgb4_cleanup_tc_flower(struct adapter *adap)
{
+ if (!adap->tc_flower_initialized)
+ return;
+
if (adap->flower_stats_timer.function)
del_timer_sync(&adap->flower_stats_timer);
cancel_work_sync(&adap->flower_stats_work);
rhashtable_destroy(&adap->flower_tbl);
+ adap->tc_flower_initialized = false;
}
struct port_info *pi = netdev2pinfo(adap->port[j]);
s = pi->sched_tbl;
+ if (!s)
+ continue;
+
for (i = 0; i < s->sched_size; i++) {
struct sched_class *e;
}
/**
- * t4_eth_xmit - add a packet to an Ethernet Tx queue
+ * cxgb4_eth_xmit - add a packet to an Ethernet Tx queue
* @skb: the packet
* @dev: the egress net device
*
* Add a packet to an SGE Ethernet Tx queue. Runs with softirqs disabled.
*/
-netdev_tx_t t4_eth_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t cxgb4_eth_xmit(struct sk_buff *skb, struct net_device *dev)
{
u32 wr_mid, ctrl0, op;
u64 cntrl, *end, *sgl;
return NETDEV_TX_OK;
}
+/* Constants ... */
+enum {
+ /* Egress Queue sizes, producer and consumer indices are all in units
+ * of Egress Context Units bytes. Note that as far as the hardware is
+ * concerned, the free list is an Egress Queue (the host produces free
+ * buffers which the hardware consumes) and free list entries are
+ * 64-bit PCI DMA addresses.
+ */
+ EQ_UNIT = SGE_EQ_IDXSIZE,
+ FL_PER_EQ_UNIT = EQ_UNIT / sizeof(__be64),
+ TXD_PER_EQ_UNIT = EQ_UNIT / sizeof(__be64),
+
+ T4VF_ETHTXQ_MAX_HDR = (sizeof(struct fw_eth_tx_pkt_vm_wr) +
+ sizeof(struct cpl_tx_pkt_lso_core) +
+ sizeof(struct cpl_tx_pkt_core)) / sizeof(__be64),
+};
+
+/**
+ * t4vf_is_eth_imm - can an Ethernet packet be sent as immediate data?
+ * @skb: the packet
+ *
+ * Returns whether an Ethernet packet is small enough to fit completely as
+ * immediate data.
+ */
+static inline int t4vf_is_eth_imm(const struct sk_buff *skb)
+{
+ /* The VF Driver uses the FW_ETH_TX_PKT_VM_WR firmware Work Request
+ * which does not accommodate immediate data. We could dike out all
+ * of the support code for immediate data but that would tie our hands
+ * too much if we ever want to enhace the firmware. It would also
+ * create more differences between the PF and VF Drivers.
+ */
+ return false;
+}
+
+/**
+ * t4vf_calc_tx_flits - calculate the number of flits for a packet TX WR
+ * @skb: the packet
+ *
+ * Returns the number of flits needed for a TX Work Request for the
+ * given Ethernet packet, including the needed WR and CPL headers.
+ */
+static inline unsigned int t4vf_calc_tx_flits(const struct sk_buff *skb)
+{
+ unsigned int flits;
+
+ /* If the skb is small enough, we can pump it out as a work request
+ * with only immediate data. In that case we just have to have the
+ * TX Packet header plus the skb data in the Work Request.
+ */
+ if (t4vf_is_eth_imm(skb))
+ return DIV_ROUND_UP(skb->len + sizeof(struct cpl_tx_pkt),
+ sizeof(__be64));
+
+ /* Otherwise, we're going to have to construct a Scatter gather list
+ * of the skb body and fragments. We also include the flits necessary
+ * for the TX Packet Work Request and CPL. We always have a firmware
+ * Write Header (incorporated as part of the cpl_tx_pkt_lso and
+ * cpl_tx_pkt structures), followed by either a TX Packet Write CPL
+ * message or, if we're doing a Large Send Offload, an LSO CPL message
+ * with an embedded TX Packet Write CPL message.
+ */
+ flits = sgl_len(skb_shinfo(skb)->nr_frags + 1);
+ if (skb_shinfo(skb)->gso_size)
+ flits += (sizeof(struct fw_eth_tx_pkt_vm_wr) +
+ sizeof(struct cpl_tx_pkt_lso_core) +
+ sizeof(struct cpl_tx_pkt_core)) / sizeof(__be64);
+ else
+ flits += (sizeof(struct fw_eth_tx_pkt_vm_wr) +
+ sizeof(struct cpl_tx_pkt_core)) / sizeof(__be64);
+ return flits;
+}
+
+/**
+ * cxgb4_vf_eth_xmit - add a packet to an Ethernet TX queue
+ * @skb: the packet
+ * @dev: the egress net device
+ *
+ * Add a packet to an SGE Ethernet TX queue. Runs with softirqs disabled.
+ */
+static netdev_tx_t cxgb4_vf_eth_xmit(struct sk_buff *skb,
+ struct net_device *dev)
+{
+ dma_addr_t addr[MAX_SKB_FRAGS + 1];
+ const struct skb_shared_info *ssi;
+ struct fw_eth_tx_pkt_vm_wr *wr;
+ int qidx, credits, max_pkt_len;
+ struct cpl_tx_pkt_core *cpl;
+ const struct port_info *pi;
+ unsigned int flits, ndesc;
+ struct sge_eth_txq *txq;
+ struct adapter *adapter;
+ u64 cntrl, *end;
+ u32 wr_mid;
+ const size_t fw_hdr_copy_len = sizeof(wr->ethmacdst) +
+ sizeof(wr->ethmacsrc) +
+ sizeof(wr->ethtype) +
+ sizeof(wr->vlantci);
+
+ /* The chip minimum packet length is 10 octets but the firmware
+ * command that we are using requires that we copy the Ethernet header
+ * (including the VLAN tag) into the header so we reject anything
+ * smaller than that ...
+ */
+ if (unlikely(skb->len < fw_hdr_copy_len))
+ goto out_free;
+
+ /* Discard the packet if the length is greater than mtu */
+ max_pkt_len = ETH_HLEN + dev->mtu;
+ if (skb_vlan_tag_present(skb))
+ max_pkt_len += VLAN_HLEN;
+ if (!skb_shinfo(skb)->gso_size && (unlikely(skb->len > max_pkt_len)))
+ goto out_free;
+
+ /* Figure out which TX Queue we're going to use. */
+ pi = netdev_priv(dev);
+ adapter = pi->adapter;
+ qidx = skb_get_queue_mapping(skb);
+ WARN_ON(qidx >= pi->nqsets);
+ txq = &adapter->sge.ethtxq[pi->first_qset + qidx];
+
+ /* Take this opportunity to reclaim any TX Descriptors whose DMA
+ * transfers have completed.
+ */
+ cxgb4_reclaim_completed_tx(adapter, &txq->q, true);
+
+ /* Calculate the number of flits and TX Descriptors we're going to
+ * need along with how many TX Descriptors will be left over after
+ * we inject our Work Request.
+ */
+ flits = t4vf_calc_tx_flits(skb);
+ ndesc = flits_to_desc(flits);
+ credits = txq_avail(&txq->q) - ndesc;
+
+ if (unlikely(credits < 0)) {
+ /* Not enough room for this packet's Work Request. Stop the
+ * TX Queue and return a "busy" condition. The queue will get
+ * started later on when the firmware informs us that space
+ * has opened up.
+ */
+ eth_txq_stop(txq);
+ dev_err(adapter->pdev_dev,
+ "%s: TX ring %u full while queue awake!\n",
+ dev->name, qidx);
+ return NETDEV_TX_BUSY;
+ }
+
+ if (!t4vf_is_eth_imm(skb) &&
+ unlikely(cxgb4_map_skb(adapter->pdev_dev, skb, addr) < 0)) {
+ /* We need to map the skb into PCI DMA space (because it can't
+ * be in-lined directly into the Work Request) and the mapping
+ * operation failed. Record the error and drop the packet.
+ */
+ txq->mapping_err++;
+ goto out_free;
+ }
+
+ wr_mid = FW_WR_LEN16_V(DIV_ROUND_UP(flits, 2));
+ if (unlikely(credits < ETHTXQ_STOP_THRES)) {
+ /* After we're done injecting the Work Request for this
+ * packet, we'll be below our "stop threshold" so stop the TX
+ * Queue now and schedule a request for an SGE Egress Queue
+ * Update message. The queue will get started later on when
+ * the firmware processes this Work Request and sends us an
+ * Egress Queue Status Update message indicating that space
+ * has opened up.
+ */
+ eth_txq_stop(txq);
+ wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F;
+ }
+
+ /* Start filling in our Work Request. Note that we do _not_ handle
+ * the WR Header wrapping around the TX Descriptor Ring. If our
+ * maximum header size ever exceeds one TX Descriptor, we'll need to
+ * do something else here.
+ */
+ WARN_ON(DIV_ROUND_UP(T4VF_ETHTXQ_MAX_HDR, TXD_PER_EQ_UNIT) > 1);
+ wr = (void *)&txq->q.desc[txq->q.pidx];
+ wr->equiq_to_len16 = cpu_to_be32(wr_mid);
+ wr->r3[0] = cpu_to_be32(0);
+ wr->r3[1] = cpu_to_be32(0);
+ skb_copy_from_linear_data(skb, (void *)wr->ethmacdst, fw_hdr_copy_len);
+ end = (u64 *)wr + flits;
+
+ /* If this is a Large Send Offload packet we'll put in an LSO CPL
+ * message with an encapsulated TX Packet CPL message. Otherwise we
+ * just use a TX Packet CPL message.
+ */
+ ssi = skb_shinfo(skb);
+ if (ssi->gso_size) {
+ struct cpl_tx_pkt_lso_core *lso = (void *)(wr + 1);
+ bool v6 = (ssi->gso_type & SKB_GSO_TCPV6) != 0;
+ int l3hdr_len = skb_network_header_len(skb);
+ int eth_xtra_len = skb_network_offset(skb) - ETH_HLEN;
+
+ wr->op_immdlen =
+ cpu_to_be32(FW_WR_OP_V(FW_ETH_TX_PKT_VM_WR) |
+ FW_WR_IMMDLEN_V(sizeof(*lso) +
+ sizeof(*cpl)));
+ /* Fill in the LSO CPL message. */
+ lso->lso_ctrl =
+ cpu_to_be32(LSO_OPCODE_V(CPL_TX_PKT_LSO) |
+ LSO_FIRST_SLICE_F |
+ LSO_LAST_SLICE_F |
+ LSO_IPV6_V(v6) |
+ LSO_ETHHDR_LEN_V(eth_xtra_len / 4) |
+ LSO_IPHDR_LEN_V(l3hdr_len / 4) |
+ LSO_TCPHDR_LEN_V(tcp_hdr(skb)->doff));
+ lso->ipid_ofst = cpu_to_be16(0);
+ lso->mss = cpu_to_be16(ssi->gso_size);
+ lso->seqno_offset = cpu_to_be32(0);
+ if (is_t4(adapter->params.chip))
+ lso->len = cpu_to_be32(skb->len);
+ else
+ lso->len = cpu_to_be32(LSO_T5_XFER_SIZE_V(skb->len));
+
+ /* Set up TX Packet CPL pointer, control word and perform
+ * accounting.
+ */
+ cpl = (void *)(lso + 1);
+
+ if (CHELSIO_CHIP_VERSION(adapter->params.chip) <= CHELSIO_T5)
+ cntrl = TXPKT_ETHHDR_LEN_V(eth_xtra_len);
+ else
+ cntrl = T6_TXPKT_ETHHDR_LEN_V(eth_xtra_len);
+
+ cntrl |= TXPKT_CSUM_TYPE_V(v6 ?
+ TX_CSUM_TCPIP6 : TX_CSUM_TCPIP) |
+ TXPKT_IPHDR_LEN_V(l3hdr_len);
+ txq->tso++;
+ txq->tx_cso += ssi->gso_segs;
+ } else {
+ int len;
+
+ len = (t4vf_is_eth_imm(skb)
+ ? skb->len + sizeof(*cpl)
+ : sizeof(*cpl));
+ wr->op_immdlen =
+ cpu_to_be32(FW_WR_OP_V(FW_ETH_TX_PKT_VM_WR) |
+ FW_WR_IMMDLEN_V(len));
+
+ /* Set up TX Packet CPL pointer, control word and perform
+ * accounting.
+ */
+ cpl = (void *)(wr + 1);
+ if (skb->ip_summed == CHECKSUM_PARTIAL) {
+ cntrl = hwcsum(adapter->params.chip, skb) |
+ TXPKT_IPCSUM_DIS_F;
+ txq->tx_cso++;
+ } else {
+ cntrl = TXPKT_L4CSUM_DIS_F | TXPKT_IPCSUM_DIS_F;
+ }
+ }
+
+ /* If there's a VLAN tag present, add that to the list of things to
+ * do in this Work Request.
+ */
+ if (skb_vlan_tag_present(skb)) {
+ txq->vlan_ins++;
+ cntrl |= TXPKT_VLAN_VLD_F | TXPKT_VLAN_V(skb_vlan_tag_get(skb));
+ }
+
+ /* Fill in the TX Packet CPL message header. */
+ cpl->ctrl0 = cpu_to_be32(TXPKT_OPCODE_V(CPL_TX_PKT_XT) |
+ TXPKT_INTF_V(pi->port_id) |
+ TXPKT_PF_V(0));
+ cpl->pack = cpu_to_be16(0);
+ cpl->len = cpu_to_be16(skb->len);
+ cpl->ctrl1 = cpu_to_be64(cntrl);
+
+ /* Fill in the body of the TX Packet CPL message with either in-lined
+ * data or a Scatter/Gather List.
+ */
+ if (t4vf_is_eth_imm(skb)) {
+ /* In-line the packet's data and free the skb since we don't
+ * need it any longer.
+ */
+ cxgb4_inline_tx_skb(skb, &txq->q, cpl + 1);
+ dev_consume_skb_any(skb);
+ } else {
+ /* Write the skb's Scatter/Gather list into the TX Packet CPL
+ * message and retain a pointer to the skb so we can free it
+ * later when its DMA completes. (We store the skb pointer
+ * in the Software Descriptor corresponding to the last TX
+ * Descriptor used by the Work Request.)
+ *
+ * The retained skb will be freed when the corresponding TX
+ * Descriptors are reclaimed after their DMAs complete.
+ * However, this could take quite a while since, in general,
+ * the hardware is set up to be lazy about sending DMA
+ * completion notifications to us and we mostly perform TX
+ * reclaims in the transmit routine.
+ *
+ * This is good for performamce but means that we rely on new
+ * TX packets arriving to run the destructors of completed
+ * packets, which open up space in their sockets' send queues.
+ * Sometimes we do not get such new packets causing TX to
+ * stall. A single UDP transmitter is a good example of this
+ * situation. We have a clean up timer that periodically
+ * reclaims completed packets but it doesn't run often enough
+ * (nor do we want it to) to prevent lengthy stalls. A
+ * solution to this problem is to run the destructor early,
+ * after the packet is queued but before it's DMAd. A con is
+ * that we lie to socket memory accounting, but the amount of
+ * extra memory is reasonable (limited by the number of TX
+ * descriptors), the packets do actually get freed quickly by
+ * new packets almost always, and for protocols like TCP that
+ * wait for acks to really free up the data the extra memory
+ * is even less. On the positive side we run the destructors
+ * on the sending CPU rather than on a potentially different
+ * completing CPU, usually a good thing.
+ *
+ * Run the destructor before telling the DMA engine about the
+ * packet to make sure it doesn't complete and get freed
+ * prematurely.
+ */
+ struct ulptx_sgl *sgl = (struct ulptx_sgl *)(cpl + 1);
+ struct sge_txq *tq = &txq->q;
+ int last_desc;
+
+ /* If the Work Request header was an exact multiple of our TX
+ * Descriptor length, then it's possible that the starting SGL
+ * pointer lines up exactly with the end of our TX Descriptor
+ * ring. If that's the case, wrap around to the beginning
+ * here ...
+ */
+ if (unlikely((void *)sgl == (void *)tq->stat)) {
+ sgl = (void *)tq->desc;
+ end = (void *)((void *)tq->desc +
+ ((void *)end - (void *)tq->stat));
+ }
+
+ cxgb4_write_sgl(skb, tq, sgl, end, 0, addr);
+ skb_orphan(skb);
+
+ last_desc = tq->pidx + ndesc - 1;
+ if (last_desc >= tq->size)
+ last_desc -= tq->size;
+ tq->sdesc[last_desc].skb = skb;
+ tq->sdesc[last_desc].sgl = sgl;
+ }
+
+ /* Advance our internal TX Queue state, tell the hardware about
+ * the new TX descriptors and return success.
+ */
+ txq_advance(&txq->q, ndesc);
+
+ cxgb4_ring_tx_db(adapter, &txq->q, ndesc);
+ return NETDEV_TX_OK;
+
+out_free:
+ /* An error of some sort happened. Free the TX skb and tell the
+ * OS that we've "dealt" with the packet ...
+ */
+ dev_kfree_skb_any(skb);
+ return NETDEV_TX_OK;
+}
+
+netdev_tx_t t4_start_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+ struct port_info *pi = netdev_priv(dev);
+
+ if (unlikely(pi->eth_flags & PRIV_FLAG_PORT_TX_VM))
+ return cxgb4_vf_eth_xmit(skb, dev);
+
+ return cxgb4_eth_xmit(skb, dev);
+}
+
/**
* reclaim_completed_tx_imm - reclaim completed control-queue Tx descs
* @q: the SGE control Tx queue
c.iqsize = htons(iq->size);
c.iqaddr = cpu_to_be64(iq->phys_addr);
if (cong >= 0)
- c.iqns_to_fl0congen = htonl(FW_IQ_CMD_IQFLINTCONGEN_F);
+ c.iqns_to_fl0congen = htonl(FW_IQ_CMD_IQFLINTCONGEN_F |
+ FW_IQ_CMD_IQTYPE_V(cong ? FW_IQ_IQTYPE_NIC
+ : FW_IQ_IQTYPE_OFLD));
if (fl) {
enum chip_type chip = CHELSIO_CHIP_VERSION(adap->params.chip);
return 0;
}
+/**
+ * t4_get_pfres - retrieve VF resource limits
+ * @adapter: the adapter
+ *
+ * Retrieves configured resource limits and capabilities for a physical
+ * function. The results are stored in @adapter->pfres.
+ */
+int t4_get_pfres(struct adapter *adapter)
+{
+ struct pf_resources *pfres = &adapter->params.pfres;
+ struct fw_pfvf_cmd cmd, rpl;
+ int v;
+ u32 word;
+
+ /* Execute PFVF Read command to get VF resource limits; bail out early
+ * with error on command failure.
+ */
+ memset(&cmd, 0, sizeof(cmd));
+ cmd.op_to_vfn = cpu_to_be32(FW_CMD_OP_V(FW_PFVF_CMD) |
+ FW_CMD_REQUEST_F |
+ FW_CMD_READ_F |
+ FW_PFVF_CMD_PFN_V(adapter->pf) |
+ FW_PFVF_CMD_VFN_V(0));
+ cmd.retval_len16 = cpu_to_be32(FW_LEN16(cmd));
+ v = t4_wr_mbox(adapter, adapter->mbox, &cmd, sizeof(cmd), &rpl);
+ if (v != FW_SUCCESS)
+ return v;
+
+ /* Extract PF resource limits and return success.
+ */
+ word = be32_to_cpu(rpl.niqflint_niq);
+ pfres->niqflint = FW_PFVF_CMD_NIQFLINT_G(word);
+ pfres->niq = FW_PFVF_CMD_NIQ_G(word);
+
+ word = be32_to_cpu(rpl.type_to_neq);
+ pfres->neq = FW_PFVF_CMD_NEQ_G(word);
+ pfres->pmask = FW_PFVF_CMD_PMASK_G(word);
+
+ word = be32_to_cpu(rpl.tc_to_nexactf);
+ pfres->tc = FW_PFVF_CMD_TC_G(word);
+ pfres->nvi = FW_PFVF_CMD_NVI_G(word);
+ pfres->nexactf = FW_PFVF_CMD_NEXACTF_G(word);
+
+ word = be32_to_cpu(rpl.r_caps_to_nethctrl);
+ pfres->r_caps = FW_PFVF_CMD_R_CAPS_G(word);
+ pfres->wx_caps = FW_PFVF_CMD_WX_CAPS_G(word);
+ pfres->nethctrl = FW_PFVF_CMD_NETHCTRL_G(word);
+
+ return 0;
+}
+
/* serial flash and firmware constants */
enum {
SF_ATTEMPTS = 10, /* max retries for SF operations */
CH_PCI_ID_TABLE_FENTRY(0x50ab), /* Custom T520-CR */
CH_PCI_ID_TABLE_FENTRY(0x50ac), /* Custom T540-BT */
CH_PCI_ID_TABLE_FENTRY(0x50ad), /* Custom T520-CR */
+ CH_PCI_ID_TABLE_FENTRY(0x50ae), /* Custom T540-XL-SO */
/* T6 adapters:
*/
#define ULP_TX_LA_RDPTR_0_A 0x8ec0
#define ULP_TX_LA_RDDATA_0_A 0x8ec4
#define ULP_TX_LA_WRPTR_0_A 0x8ec8
+#define ULP_TX_ASIC_DEBUG_CTRL_A 0x8f70
+
+#define ULP_TX_ASIC_DEBUG_0_A 0x8f74
+#define ULP_TX_ASIC_DEBUG_1_A 0x8f78
+#define ULP_TX_ASIC_DEBUG_2_A 0x8f7c
+#define ULP_TX_ASIC_DEBUG_3_A 0x8f80
+#define ULP_TX_ASIC_DEBUG_4_A 0x8f84
+
+/* registers for module PM_RX */
+#define PM_RX_BASE_ADDR 0x8fc0
#define PMRX_E_PCMD_PAR_ERROR_S 0
#define PMRX_E_PCMD_PAR_ERROR_V(x) ((x) << PMRX_E_PCMD_PAR_ERROR_S)
FW_IQ_TYPE_NO_FL_INT_CAP
};
+enum fw_iq_iqtype {
+ FW_IQ_IQTYPE_OTHER,
+ FW_IQ_IQTYPE_NIC,
+ FW_IQ_IQTYPE_OFLD,
+};
+
struct fw_iq_cmd {
__be32 op_to_vfn;
__be32 alloc_to_len16;
#define FW_IQ_CMD_IQFLINTISCSIC_S 26
#define FW_IQ_CMD_IQFLINTISCSIC_V(x) ((x) << FW_IQ_CMD_IQFLINTISCSIC_S)
+#define FW_IQ_CMD_IQTYPE_S 24
+#define FW_IQ_CMD_IQTYPE_M 0x3
+#define FW_IQ_CMD_IQTYPE_V(x) ((x) << FW_IQ_CMD_IQTYPE_S)
+#define FW_IQ_CMD_IQTYPE_G(x) \
+ (((x) >> FW_IQ_CMD_IQTYPE_S) & FW_IQ_CMD_IQTYPE_M)
+
#define FW_IQ_CMD_FL0CNGCHMAP_S 20
#define FW_IQ_CMD_FL0CNGCHMAP_V(x) ((x) << FW_IQ_CMD_FL0CNGCHMAP_S)
enic->rfs_h.max = enic->config.num_arfs;
enic->rfs_h.free = enic->rfs_h.max;
enic->rfs_h.toclean = 0;
- enic_rfs_timer_start(enic);
}
void enic_rfs_flw_tbl_free(struct enic *enic)
enic_rfs_timer_stop(enic);
spin_lock_bh(&enic->rfs_h.lock);
- enic->rfs_h.free = 0;
for (i = 0; i < (1 << ENIC_RFS_FLW_BITSHIFT); i++) {
struct hlist_head *hhead;
struct hlist_node *tmp;
enic_delfltr(enic, n->fltr_id);
hlist_del(&n->node);
kfree(n);
+ enic->rfs_h.free++;
}
}
spin_unlock_bh(&enic->rfs_h.lock);
{
struct enic *enic = netdev_priv(netdev);
unsigned int i;
- int err;
+ int err, ret;
err = enic_request_intr(enic);
if (err) {
vnic_intr_unmask(&enic->intr[i]);
enic_notify_timer_start(enic);
- enic_rfs_flw_tbl_init(enic);
+ enic_rfs_timer_start(enic);
return 0;
err_out_free_rq:
for (i = 0; i < enic->rq_count; i++) {
- err = vnic_rq_disable(&enic->rq[i]);
- if (err)
- return err;
- vnic_rq_clean(&enic->rq[i], enic_free_rq_buf);
+ ret = vnic_rq_disable(&enic->rq[i]);
+ if (!ret)
+ vnic_rq_clean(&enic->rq[i], enic_free_rq_buf);
}
enic_dev_notify_unset(enic);
err_out_free_intr:
timer_setup(&enic->notify_timer, enic_notify_timer, 0);
+ enic_rfs_flw_tbl_init(enic);
enic_set_rx_coal_setting(enic);
INIT_WORK(&enic->reset, enic_reset);
INIT_WORK(&enic->tx_hang_reset, enic_tx_hang_reset);
#define DRV_NAME "gmac-gemini"
#define DRV_VERSION "1.0"
+#define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK)
+static int debug = -1;
+module_param(debug, int, 0);
+MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)");
+
#define HSIZE_8 0x00
#define HSIZE_16 0x01
#define HSIZE_32 0x02
void __iomem *base;
struct gemini_ethernet_port *port0;
struct gemini_ethernet_port *port1;
+ bool initialized;
spinlock_t irq_lock; /* Locks IRQ-related registers */
unsigned int freeq_order;
status.bits.speed = GMAC_SPEED_1000;
if (phydev->interface == PHY_INTERFACE_MODE_RGMII)
status.bits.mii_rmii = GMAC_PHY_RGMII_1000;
- netdev_info(netdev, "connect to RGMII @ 1Gbit\n");
+ netdev_dbg(netdev, "connect %s to RGMII @ 1Gbit\n",
+ phydev_name(phydev));
break;
case 100:
status.bits.speed = GMAC_SPEED_100;
if (phydev->interface == PHY_INTERFACE_MODE_RGMII)
status.bits.mii_rmii = GMAC_PHY_RGMII_100_10;
- netdev_info(netdev, "connect to RGMII @ 100 Mbit\n");
+ netdev_dbg(netdev, "connect %s to RGMII @ 100 Mbit\n",
+ phydev_name(phydev));
break;
case 10:
status.bits.speed = GMAC_SPEED_10;
if (phydev->interface == PHY_INTERFACE_MODE_RGMII)
status.bits.mii_rmii = GMAC_PHY_RGMII_100_10;
- netdev_info(netdev, "connect to RGMII @ 10 Mbit\n");
+ netdev_dbg(netdev, "connect %s to RGMII @ 10 Mbit\n",
+ phydev_name(phydev));
break;
default:
- netdev_warn(netdev, "Not supported PHY speed (%d)\n",
- phydev->speed);
+ netdev_warn(netdev, "Unsupported PHY speed (%d) on %s\n",
+ phydev->speed, phydev_name(phydev));
}
if (phydev->duplex == DUPLEX_FULL) {
return -ENODEV;
netdev->phydev = phy;
- netdev_info(netdev, "connected to PHY \"%s\"\n",
- phydev_name(phy));
- phy_attached_print(phy, "phy_id=0x%.8lx, phy_mode=%s\n",
- (unsigned long)phy->phy_id,
- phy_modes(phy->interface));
-
phy->supported &= PHY_GBIT_FEATURES;
phy->supported |= SUPPORTED_Asym_Pause | SUPPORTED_Pause;
phy->advertising = phy->supported;
/* set PHY interface type */
switch (phy->interface) {
case PHY_INTERFACE_MODE_MII:
- netdev_info(netdev, "set GMAC0 to GMII mode, GMAC1 disabled\n");
+ netdev_dbg(netdev,
+ "MII: set GMAC0 to GMII mode, GMAC1 disabled\n");
status.bits.mii_rmii = GMAC_PHY_MII;
- netdev_info(netdev, "connect to MII\n");
break;
case PHY_INTERFACE_MODE_GMII:
- netdev_info(netdev, "set GMAC0 to GMII mode, GMAC1 disabled\n");
+ netdev_dbg(netdev,
+ "GMII: set GMAC0 to GMII mode, GMAC1 disabled\n");
status.bits.mii_rmii = GMAC_PHY_GMII;
- netdev_info(netdev, "connect to GMII\n");
break;
case PHY_INTERFACE_MODE_RGMII:
- dev_info(dev, "set GMAC0 and GMAC1 to MII/RGMII mode\n");
+ netdev_dbg(netdev,
+ "RGMII: set GMAC0 and GMAC1 to MII/RGMII mode\n");
status.bits.mii_rmii = GMAC_PHY_RGMII_100_10;
- netdev_info(netdev, "connect to RGMII\n");
break;
default:
netdev_err(netdev, "Unsupported MII interface\n");
}
writel(status.bits32, port->gmac_base + GMAC_STATUS);
+ if (netif_msg_link(port))
+ phy_attached_info(phy);
+
return 0;
}
-static int gmac_pick_rx_max_len(int max_l3_len)
-{
- /* index = CONFIG_MAXLEN_XXX values */
- static const int max_len[8] = {
- 1536, 1518, 1522, 1542,
- 9212, 10236, 1518, 1518
- };
- int i, n = 5;
+/* The maximum frame length is not logically enumerated in the
+ * hardware, so we do a table lookup to find the applicable max
+ * frame length.
+ */
+struct gmac_max_framelen {
+ unsigned int max_l3_len;
+ u8 val;
+};
+
+static const struct gmac_max_framelen gmac_maxlens[] = {
+ {
+ .max_l3_len = 1518,
+ .val = CONFIG0_MAXLEN_1518,
+ },
+ {
+ .max_l3_len = 1522,
+ .val = CONFIG0_MAXLEN_1522,
+ },
+ {
+ .max_l3_len = 1536,
+ .val = CONFIG0_MAXLEN_1536,
+ },
+ {
+ .max_l3_len = 1542,
+ .val = CONFIG0_MAXLEN_1542,
+ },
+ {
+ .max_l3_len = 9212,
+ .val = CONFIG0_MAXLEN_9k,
+ },
+ {
+ .max_l3_len = 10236,
+ .val = CONFIG0_MAXLEN_10k,
+ },
+};
- max_l3_len += ETH_HLEN + VLAN_HLEN;
+static int gmac_pick_rx_max_len(unsigned int max_l3_len)
+{
+ const struct gmac_max_framelen *maxlen;
+ int maxtot;
+ int i;
- if (max_l3_len > max_len[n])
- return -1;
+ maxtot = max_l3_len + ETH_HLEN + VLAN_HLEN;
- for (i = 0; i < 5; i++) {
- if (max_len[i] >= max_l3_len && max_len[i] < max_len[n])
- n = i;
+ for (i = 0; i < ARRAY_SIZE(gmac_maxlens); i++) {
+ maxlen = &gmac_maxlens[i];
+ if (maxtot <= maxlen->max_l3_len)
+ return maxlen->val;
}
- return n;
+ return -1;
}
static int gmac_init(struct net_device *netdev)
unsigned long flags;
u32 val, mask;
- netdev_info(netdev, "%s device %d %s\n", __func__,
- netdev->dev_id, enable ? "enable" : "disable");
+ netdev_dbg(netdev, "%s device %d %s\n", __func__,
+ netdev->dev_id, enable ? "enable" : "disable");
spin_lock_irqsave(&geth->irq_lock, flags);
mask = GMAC0_IRQ0_2 << (netdev->dev_id * 2);
phy_start(netdev->phydev);
err = geth_resize_freeq(port);
- if (err) {
+ /* It's fine if it's just busy, the other port has set up
+ * the freeq in that case.
+ */
+ if (err && (err != -EBUSY)) {
netdev_err(netdev, "could not resize freeq\n");
goto err_stop_phy;
}
HRTIMER_MODE_REL);
port->rx_coalesce_timer.function = &gmac_coalesce_delay_expired;
- netdev_info(netdev, "opened\n");
+ netdev_dbg(netdev, "opened\n");
return 0;
static void gemini_ethernet_init(struct gemini_ethernet *geth)
{
+ /* Only do this once both ports are online */
+ if (geth->initialized)
+ return;
+ if (geth->port0 && geth->port1)
+ geth->initialized = true;
+ else
+ return;
+
writel(0, geth->base + GLOBAL_INTERRUPT_ENABLE_0_REG);
writel(0, geth->base + GLOBAL_INTERRUPT_ENABLE_1_REG);
writel(0, geth->base + GLOBAL_INTERRUPT_ENABLE_2_REG);
port->id = id;
port->geth = geth;
port->dev = dev;
+ port->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE);
/* DMA memory */
dmares = platform_get_resource(pdev, IORESOURCE_MEM, 0);
geth->port0 = port;
else
geth->port1 = port;
+
+ /* This will just be done once both ports are up and reset */
+ gemini_ethernet_init(geth);
+
platform_set_drvdata(pdev, port);
/* Set up and register the netdev */
netdev->hw_features = GMAC_OFFLOAD_FEATURES;
netdev->features |= GMAC_OFFLOAD_FEATURES | NETIF_F_GRO;
+ /* We can handle jumbo frames up to 10236 bytes so, let's accept
+ * payloads of 10236 bytes minus VLAN and ethernet header
+ */
+ netdev->min_mtu = ETH_MIN_MTU;
+ netdev->max_mtu = 10236 - VLAN_ETH_HLEN;
port->freeq_refill = 0;
netif_napi_add(netdev, &port->napi, gmac_napi_poll,
port->mac_addr[0], port->mac_addr[1],
port->mac_addr[2]);
dev_info(dev, "using a random ethernet address\n");
- random_ether_addr(netdev->dev_addr);
+ eth_random_addr(netdev->dev_addr);
}
gmac_write_mac_address(netdev);
spin_lock_init(&geth->irq_lock);
spin_lock_init(&geth->freeq_lock);
- gemini_ethernet_init(geth);
/* The children will use this */
platform_set_drvdata(pdev, geth);
{
struct gemini_ethernet *geth = platform_get_drvdata(pdev);
- gemini_ethernet_init(geth);
geth_cleanup_freeq(geth);
+ geth->initialized = false;
return 0;
}
struct be_eq_obj {
struct be_queue_info q;
- char desc[32];
-
- /* Adaptive interrupt coalescing (AIC) info */
- bool enable_aic;
- u32 min_eqd; /* in usecs */
- u32 max_eqd; /* in usecs */
- u32 eqd; /* configured val when aic is off */
- u32 cur_eqd; /* in usecs */
+ struct be_adapter *adapter;
+ struct napi_struct napi;
u8 idx; /* array index */
u8 msix_idx;
u16 spurious_intr;
- struct napi_struct napi;
- struct be_adapter *adapter;
cpumask_var_t affinity_mask;
-
-#ifdef CONFIG_NET_RX_BUSY_POLL
-#define BE_EQ_IDLE 0
-#define BE_EQ_NAPI 1 /* napi owns this EQ */
-#define BE_EQ_POLL 2 /* poll owns this EQ */
-#define BE_EQ_LOCKED (BE_EQ_NAPI | BE_EQ_POLL)
-#define BE_EQ_NAPI_YIELD 4 /* napi yielded this EQ */
-#define BE_EQ_POLL_YIELD 8 /* poll yielded this EQ */
-#define BE_EQ_YIELD (BE_EQ_NAPI_YIELD | BE_EQ_POLL_YIELD)
-#define BE_EQ_USER_PEND (BE_EQ_POLL | BE_EQ_POLL_YIELD)
- unsigned int state;
- spinlock_t lock; /* lock to serialize napi and busy-poll */
-#endif /* CONFIG_NET_RX_BUSY_POLL */
} ____cacheline_aligned_in_smp;
struct be_aic_obj { /* Adaptive interrupt coalescing (AIC) info */
u64 tx_vxlan_offload_pkts;
u64 tx_reqs;
u64 tx_compl;
- ulong tx_jiffies;
u32 tx_stops;
u32 tx_drv_drops; /* pkts dropped by driver */
/* the error counters are described in be_ethtool.c */
struct be_tx_obj {
u32 db_offset;
+ struct be_tx_compl_info txcp;
struct be_queue_info q;
struct be_queue_info cq;
- struct be_tx_compl_info txcp;
/* Remember the skbs that were transmitted */
struct sk_buff *sent_skb_list[TX_Q_LEN];
struct be_tx_stats stats;
#define be_is_os2bmc_enabled(adapter) (adapter->flags & BE_FLAGS_OS2BMC)
struct rss_info {
- u64 rss_flags;
u8 rsstable[RSS_INDIR_TABLE_LEN];
u8 rss_queue[RSS_INDIR_TABLE_LEN];
u8 rss_hkey[RSS_HASH_KEY_LEN];
+ u64 rss_flags;
};
#define BE_INVALID_DIE_TEMP 0xFF
};
struct be_error_recovery {
- /* Lancer error recovery variables */
- u8 recovery_retries;
+ union {
+ u8 recovery_retries; /* used for Lancer */
+ u8 recovery_state; /* used for BEx and Skyhawk */
+ };
/* BEx/Skyhawk error recovery variables */
- u8 recovery_state;
+ bool recovery_supported;
u16 ue_to_reset_time; /* Time after UE, to soft reset
* the chip - PF0 only
*/
* of SLIPORT_SEMAPHORE reg
*/
u16 last_err_code;
- bool recovery_supported;
unsigned long probe_time;
unsigned long last_recovery_time;
int status, i, vec;
for_all_evt_queues(adapter, eqo, i) {
- sprintf(eqo->desc, "%s-q%d", netdev->name, i);
+ char irq_name[IFNAMSIZ+4];
+
+ snprintf(irq_name, sizeof(irq_name), "%s-q%d", netdev->name, i);
vec = be_msix_vec_get(adapter, eqo);
- status = request_irq(vec, be_msix, 0, eqo->desc, eqo);
+ status = request_irq(vec, be_msix, 0, irq_name, eqo);
if (status)
goto err_msix;
if (unlikely(nd->state != ncsi_dev_state_functional))
return;
- netdev_info(nd->dev, "NCSI interface %s\n",
- nd->link_up ? "up" : "down");
+ netdev_dbg(nd->dev, "NCSI interface %s\n",
+ nd->link_up ? "up" : "down");
}
static void ftgmac100_setup_clk(struct ftgmac100 *priv)
/* Default alignment for start of data in an Rx FD */
#define DPAA_FD_DATA_ALIGNMENT 16
+/* The DPAA requires 256 bytes reserved and mapped for the SGT */
+#define DPAA_SGT_SIZE 256
+
/* Values for the L3R field of the FM Parse Results
*/
/* L3 Type field: First IP Present IPv4 */
buf_prefix_content.priv_data_size = buf_layout->priv_data_size;
buf_prefix_content.pass_prs_result = true;
buf_prefix_content.pass_hash_result = true;
- buf_prefix_content.pass_time_stamp = false;
+ buf_prefix_content.pass_time_stamp = true;
buf_prefix_content.data_align = DPAA_FD_DATA_ALIGNMENT;
params.specific_params.non_rx_params.err_fqid = errq->fqid;
buf_prefix_content.priv_data_size = buf_layout->priv_data_size;
buf_prefix_content.pass_prs_result = true;
buf_prefix_content.pass_hash_result = true;
- buf_prefix_content.pass_time_stamp = false;
+ buf_prefix_content.pass_time_stamp = true;
buf_prefix_content.data_align = DPAA_FD_DATA_ALIGNMENT;
rx_p = ¶ms.specific_params.rx_params;
{
const enum dma_data_direction dma_dir = DMA_TO_DEVICE;
struct device *dev = priv->net_dev->dev.parent;
+ struct skb_shared_hwtstamps shhwtstamps;
dma_addr_t addr = qm_fd_addr(fd);
const struct qm_sg_entry *sgt;
struct sk_buff **skbh, *skb;
int nr_frags, i;
+ u64 ns;
skbh = (struct sk_buff **)phys_to_virt(addr);
skb = *skbh;
+ if (priv->tx_tstamp && skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) {
+ memset(&shhwtstamps, 0, sizeof(shhwtstamps));
+
+ if (!fman_port_get_tstamp(priv->mac_dev->port[TX], (void *)skbh,
+ &ns)) {
+ shhwtstamps.hwtstamp = ns_to_ktime(ns);
+ skb_tstamp_tx(skb, &shhwtstamps);
+ } else {
+ dev_warn(dev, "fman_port_get_tstamp failed!\n");
+ }
+ }
+
if (unlikely(qm_fd_get_format(fd) == qm_fd_sg)) {
nr_frags = skb_shinfo(skb)->nr_frags;
- dma_unmap_single(dev, addr, qm_fd_get_offset(fd) +
- sizeof(struct qm_sg_entry) * (1 + nr_frags),
+ dma_unmap_single(dev, addr,
+ qm_fd_get_offset(fd) + DPAA_SGT_SIZE,
dma_dir);
/* The sgt buffer has been allocated with netdev_alloc_frag(),
void *sgt_buf;
/* get a page frag to store the SGTable */
- sz = SKB_DATA_ALIGN(priv->tx_headroom +
- sizeof(struct qm_sg_entry) * (1 + nr_frags));
+ sz = SKB_DATA_ALIGN(priv->tx_headroom + DPAA_SGT_SIZE);
sgt_buf = netdev_alloc_frag(sz);
if (unlikely(!sgt_buf)) {
netdev_err(net_dev, "netdev_alloc_frag() failed for size %d\n",
skbh = (struct sk_buff **)buffer_start;
*skbh = skb;
- addr = dma_map_single(dev, buffer_start, priv->tx_headroom +
- sizeof(struct qm_sg_entry) * (1 + nr_frags),
- dma_dir);
+ addr = dma_map_single(dev, buffer_start,
+ priv->tx_headroom + DPAA_SGT_SIZE, dma_dir);
if (unlikely(dma_mapping_error(dev, addr))) {
dev_err(dev, "DMA mapping failed");
err = -EINVAL;
if (unlikely(err < 0))
goto skb_to_fd_failed;
+ if (priv->tx_tstamp && skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) {
+ fd.cmd |= cpu_to_be32(FM_FD_CMD_UPD);
+ skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+ }
+
if (likely(dpaa_xmit(priv, percpu_stats, queue_mapping, &fd) == 0))
return NETDEV_TX_OK;
struct qman_fq *fq,
const struct qm_dqrr_entry *dq)
{
+ struct skb_shared_hwtstamps *shhwtstamps;
struct rtnl_link_stats64 *percpu_stats;
struct dpaa_percpu_priv *percpu_priv;
const struct qm_fd *fd = &dq->fd;
struct sk_buff *skb;
int *count_ptr;
void *vaddr;
+ u64 ns;
fd_status = be32_to_cpu(fd->status);
fd_format = qm_fd_get_format(fd);
if (!skb)
return qman_cb_dqrr_consume;
+ if (priv->rx_tstamp) {
+ shhwtstamps = skb_hwtstamps(skb);
+ memset(shhwtstamps, 0, sizeof(*shhwtstamps));
+
+ if (!fman_port_get_tstamp(priv->mac_dev->port[RX], vaddr, &ns))
+ shhwtstamps->hwtstamp = ns_to_ktime(ns);
+ else
+ dev_warn(net_dev->dev.parent, "fman_port_get_tstamp failed!\n");
+ }
+
skb->protocol = eth_type_trans(skb, net_dev);
if (net_dev->features & NETIF_F_RXHASH && priv->keygen_in_use &&
return err;
}
+static int dpaa_ts_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
+{
+ struct dpaa_priv *priv = netdev_priv(dev);
+ struct hwtstamp_config config;
+
+ if (copy_from_user(&config, rq->ifr_data, sizeof(config)))
+ return -EFAULT;
+
+ switch (config.tx_type) {
+ case HWTSTAMP_TX_OFF:
+ /* Couldn't disable rx/tx timestamping separately.
+ * Do nothing here.
+ */
+ priv->tx_tstamp = false;
+ break;
+ case HWTSTAMP_TX_ON:
+ priv->mac_dev->set_tstamp(priv->mac_dev->fman_mac, true);
+ priv->tx_tstamp = true;
+ break;
+ default:
+ return -ERANGE;
+ }
+
+ if (config.rx_filter == HWTSTAMP_FILTER_NONE) {
+ /* Couldn't disable rx/tx timestamping separately.
+ * Do nothing here.
+ */
+ priv->rx_tstamp = false;
+ } else {
+ priv->mac_dev->set_tstamp(priv->mac_dev->fman_mac, true);
+ priv->rx_tstamp = true;
+ /* TS is set for all frame types, not only those requested */
+ config.rx_filter = HWTSTAMP_FILTER_ALL;
+ }
+
+ return copy_to_user(rq->ifr_data, &config, sizeof(config)) ?
+ -EFAULT : 0;
+}
+
static int dpaa_ioctl(struct net_device *net_dev, struct ifreq *rq, int cmd)
{
- if (!net_dev->phydev)
- return -EINVAL;
- return phy_mii_ioctl(net_dev->phydev, rq, cmd);
+ int ret = -EINVAL;
+
+ if (cmd == SIOCGMIIREG) {
+ if (net_dev->phydev)
+ return phy_mii_ioctl(net_dev->phydev, rq, cmd);
+ }
+
+ if (cmd == SIOCSHWTSTAMP)
+ return dpaa_ts_ioctl(net_dev, rq, cmd);
+
+ return ret;
}
static const struct net_device_ops dpaa_ops = {
struct dpaa_buffer_layout buf_layout[2];
u16 rx_headroom;
+
+ bool tx_tstamp; /* Tx timestamping enabled */
+ bool rx_tstamp; /* Rx timestamping enabled */
};
/* from dpaa_ethtool.c */
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/string.h>
+#include <linux/of_platform.h>
+#include <linux/net_tstamp.h>
+#include <linux/fsl/ptp_qoriq.h>
#include "dpaa_eth.h"
#include "mac.h"
return ret;
}
+static int dpaa_get_ts_info(struct net_device *net_dev,
+ struct ethtool_ts_info *info)
+{
+ struct device *dev = net_dev->dev.parent;
+ struct device_node *mac_node = dev->of_node;
+ struct device_node *fman_node = NULL, *ptp_node = NULL;
+ struct platform_device *ptp_dev = NULL;
+ struct qoriq_ptp *ptp = NULL;
+
+ info->phc_index = -1;
+
+ fman_node = of_get_parent(mac_node);
+ if (fman_node)
+ ptp_node = of_parse_phandle(fman_node, "ptimer-handle", 0);
+
+ if (ptp_node)
+ ptp_dev = of_find_device_by_node(ptp_node);
+
+ if (ptp_dev)
+ ptp = platform_get_drvdata(ptp_dev);
+
+ if (ptp)
+ info->phc_index = ptp->phc_index;
+
+ info->so_timestamping = SOF_TIMESTAMPING_TX_HARDWARE |
+ SOF_TIMESTAMPING_RX_HARDWARE |
+ SOF_TIMESTAMPING_RAW_HARDWARE;
+ info->tx_types = (1 << HWTSTAMP_TX_OFF) |
+ (1 << HWTSTAMP_TX_ON);
+ info->rx_filters = (1 << HWTSTAMP_FILTER_NONE) |
+ (1 << HWTSTAMP_FILTER_ALL);
+
+ return 0;
+}
+
const struct ethtool_ops dpaa_ethtool_ops = {
.get_drvinfo = dpaa_get_drvinfo,
.get_msglevel = dpaa_get_msglevel,
.set_link_ksettings = dpaa_set_link_ksettings,
.get_rxnfc = dpaa_get_rxnfc,
.set_rxnfc = dpaa_set_rxnfc,
+ .get_ts_info = dpaa_get_ts_info,
};
{
unsigned long flags;
u32 val, tempval;
- int inc;
struct timespec64 ts;
u64 ns;
val = 0;
fep->pps_channel = DEFAULT_PPS_CHANNEL;
fep->reload_period = PPS_OUPUT_RELOAD_PERIOD;
- inc = fep->ptp_inc;
spin_lock_irqsave(&fep->tmreg_lock, flags);
of_node_put(muram_node);
of_node_put(fm_node);
- err = devm_request_irq(&of_dev->dev, irq, fman_irq, 0, "fman", fman);
+ err = devm_request_irq(&of_dev->dev, irq, fman_irq, IRQF_SHARED,
+ "fman", fman);
if (err < 0) {
dev_err(&of_dev->dev, "%s: irq %d allocation failed (error = %d)\n",
__func__, irq, err);
/* Frame queue Context Override */
#define FM_FD_CMD_FCO 0x80000000
#define FM_FD_CMD_RPD 0x40000000 /* Read Prepended Data */
+#define FM_FD_CMD_UPD 0x20000000 /* Update Prepended Data */
#define FM_FD_CMD_DTC 0x10000000 /* Do L4 Checksum */
/* TX-Port: Unsupported Format */
#define DTSEC_ECNTRL_R100M 0x00000008
#define DTSEC_ECNTRL_QSGMIIM 0x00000001
+#define TCTRL_TTSE 0x00000040
#define TCTRL_GTS 0x00000020
#define RCTRL_PAL_MASK 0x001f0000
#define RCTRL_PAL_SHIFT 16
#define RCTRL_GHTX 0x00000400
+#define RCTRL_RTSE 0x00000040
#define RCTRL_GRS 0x00000020
#define RCTRL_MPROM 0x00000008
#define RCTRL_RSF 0x00000004
return 0;
}
+int dtsec_set_tstamp(struct fman_mac *dtsec, bool enable)
+{
+ struct dtsec_regs __iomem *regs = dtsec->regs;
+ u32 rctrl, tctrl;
+
+ if (!is_init_done(dtsec->dtsec_drv_param))
+ return -EINVAL;
+
+ rctrl = ioread32be(®s->rctrl);
+ tctrl = ioread32be(®s->tctrl);
+
+ if (enable) {
+ rctrl |= RCTRL_RTSE;
+ tctrl |= TCTRL_TTSE;
+ } else {
+ rctrl &= ~RCTRL_RTSE;
+ tctrl &= ~TCTRL_TTSE;
+ }
+
+ iowrite32be(rctrl, ®s->rctrl);
+ iowrite32be(tctrl, ®s->tctrl);
+
+ return 0;
+}
+
int dtsec_del_hash_mac_address(struct fman_mac *dtsec, enet_addr_t *eth_addr)
{
struct dtsec_regs __iomem *regs = dtsec->regs;
int dtsec_del_hash_mac_address(struct fman_mac *dtsec, enet_addr_t *eth_addr);
int dtsec_get_version(struct fman_mac *dtsec, u32 *mac_version);
int dtsec_set_allmulti(struct fman_mac *dtsec, bool enable);
+int dtsec_set_tstamp(struct fman_mac *dtsec, bool enable);
#endif /* __DTSEC_H */
return 0;
}
+int memac_set_tstamp(struct fman_mac *memac, bool enable)
+{
+ return 0; /* Always enabled. */
+}
+
int memac_del_hash_mac_address(struct fman_mac *memac, enet_addr_t *eth_addr)
{
struct memac_regs __iomem *regs = memac->regs;
int memac_add_hash_mac_address(struct fman_mac *memac, enet_addr_t *eth_addr);
int memac_del_hash_mac_address(struct fman_mac *memac, enet_addr_t *eth_addr);
int memac_set_allmulti(struct fman_mac *memac, bool enable);
+int memac_set_tstamp(struct fman_mac *memac, bool enable);
#endif /* __MEMAC_H */
#define HWP_HXS_PHE_REPORT 0x00000800
#define HWP_HXS_PCAC_PSTAT 0x00000100
#define HWP_HXS_PCAC_PSTOP 0x00000001
+#define HWP_HXS_TCP_OFFSET 0xA
+#define HWP_HXS_UDP_OFFSET 0xB
+#define HWP_HXS_SH_PAD_REM 0x80000000
+
struct fman_port_hwp_regs {
struct {
u32 ssa; /* Soft Sequence Attachment */
iowrite32be(0xffffffff, ®s->pmda[i].lcv);
}
+ /* Short packet padding removal from checksum calculation */
+ iowrite32be(HWP_HXS_SH_PAD_REM, ®s->pmda[HWP_HXS_TCP_OFFSET].ssa);
+ iowrite32be(HWP_HXS_SH_PAD_REM, ®s->pmda[HWP_HXS_UDP_OFFSET].ssa);
+
start_port_hwp(port);
}
}
EXPORT_SYMBOL(fman_port_get_hash_result_offset);
+int fman_port_get_tstamp(struct fman_port *port, const void *data, u64 *tstamp)
+{
+ if (port->buffer_offsets.time_stamp_offset == ILLEGAL_BASE)
+ return -EINVAL;
+
+ *tstamp = be64_to_cpu(*(__be64 *)(data +
+ port->buffer_offsets.time_stamp_offset));
+
+ return 0;
+}
+EXPORT_SYMBOL(fman_port_get_tstamp);
+
static int fman_port_probe(struct platform_device *of_dev)
{
struct fman_port *port;
int fman_port_get_hash_result_offset(struct fman_port *port, u32 *offset);
+int fman_port_get_tstamp(struct fman_port *port, const void *data, u64 *tstamp);
+
struct fman_port *fman_port_bind(struct device *dev);
#endif /* __FMAN_PORT_H */
#define TGEC_TX_IPG_LENGTH_MASK 0x000003ff
/* Command and Configuration Register (COMMAND_CONFIG) */
+#define CMD_CFG_EN_TIMESTAMP 0x00100000
#define CMD_CFG_NO_LEN_CHK 0x00020000
#define CMD_CFG_PAUSE_IGNORE 0x00000100
#define CMF_CFG_CRC_FWD 0x00000040
return 0;
}
+int tgec_set_tstamp(struct fman_mac *tgec, bool enable)
+{
+ struct tgec_regs __iomem *regs = tgec->regs;
+ u32 tmp;
+
+ if (!is_init_done(tgec->cfg))
+ return -EINVAL;
+
+ tmp = ioread32be(®s->command_config);
+
+ if (enable)
+ tmp |= CMD_CFG_EN_TIMESTAMP;
+ else
+ tmp &= ~CMD_CFG_EN_TIMESTAMP;
+
+ iowrite32be(tmp, ®s->command_config);
+
+ return 0;
+}
+
int tgec_del_hash_mac_address(struct fman_mac *tgec, enet_addr_t *eth_addr)
{
struct tgec_regs __iomem *regs = tgec->regs;
int tgec_del_hash_mac_address(struct fman_mac *tgec, enet_addr_t *eth_addr);
int tgec_get_version(struct fman_mac *tgec, u32 *mac_version);
int tgec_set_allmulti(struct fman_mac *tgec, bool enable);
+int tgec_set_tstamp(struct fman_mac *tgec, bool enable);
#endif /* __TGEC_H */
mac_dev->set_rx_pause = dtsec_accept_rx_pause_frames;
mac_dev->set_exception = dtsec_set_exception;
mac_dev->set_allmulti = dtsec_set_allmulti;
+ mac_dev->set_tstamp = dtsec_set_tstamp;
mac_dev->set_multi = set_multi;
mac_dev->start = start;
mac_dev->stop = stop;
mac_dev->set_rx_pause = tgec_accept_rx_pause_frames;
mac_dev->set_exception = tgec_set_exception;
mac_dev->set_allmulti = tgec_set_allmulti;
+ mac_dev->set_tstamp = tgec_set_tstamp;
mac_dev->set_multi = set_multi;
mac_dev->start = start;
mac_dev->stop = stop;
mac_dev->set_rx_pause = memac_accept_rx_pause_frames;
mac_dev->set_exception = memac_set_exception;
mac_dev->set_allmulti = memac_set_allmulti;
+ mac_dev->set_tstamp = memac_set_tstamp;
mac_dev->set_multi = set_multi;
mac_dev->start = start;
mac_dev->stop = stop;
int (*set_promisc)(struct fman_mac *mac_dev, bool enable);
int (*change_addr)(struct fman_mac *mac_dev, enet_addr_t *enet_addr);
int (*set_allmulti)(struct fman_mac *mac_dev, bool enable);
+ int (*set_tstamp)(struct fman_mac *mac_dev, bool enable);
int (*set_multi)(struct net_device *net_dev,
struct mac_device *mac_dev);
int (*set_rx_pause)(struct fman_mac *mac_dev, bool en);
static int gfar_ethflow_to_filer_table(struct gfar_private *priv, u64 ethflow,
u64 class)
{
- unsigned int last_rule_idx = priv->cur_filer_idx;
unsigned int cmp_rqfpr;
unsigned int *local_rqfpr;
unsigned int *local_rqfcr;
}
priv->cur_filer_idx = l - 1;
- last_rule_idx = l;
/* hash rules */
ethflow_to_filer_rules(priv, ethflow);
ugeth_vdbg("%s: IN", __func__);
+ netdev_sent_queue(dev, skb->len);
spin_lock_irqsave(&ugeth->lock, flags);
dev->stats.tx_bytes += skb->len;
{
/* Start from the next BD that should be filled */
struct ucc_geth_private *ugeth = netdev_priv(dev);
+ unsigned int bytes_sent = 0;
+ int howmany = 0;
u8 __iomem *bd; /* BD pointer */
u32 bd_status;
skb = ugeth->tx_skbuff[txQ][ugeth->skb_dirtytx[txQ]];
if (!skb)
break;
-
+ howmany++;
+ bytes_sent += skb->len;
dev->stats.tx_packets++;
dev_consume_skb_any(skb);
bd_status = in_be32((u32 __iomem *)bd);
}
ugeth->confBd[txQ] = bd;
+ netdev_completed_queue(dev, howmany, bytes_sent);
return 0;
}
phy_start(ugeth->phydev);
napi_enable(&ugeth->napi);
+ netdev_reset_queue(dev);
netif_start_queue(dev);
device_set_wakeup_capable(&dev->dev,
free_irq(ugeth->ug_info->uf_info.irq, ugeth->ndev);
netif_stop_queue(dev);
+ netdev_reset_queue(dev);
return 0;
}
config NET_VENDOR_HISILICON
bool "Hisilicon devices"
default y
- depends on (OF || ACPI) && HAS_DMA
+ depends on OF || ACPI
depends on ARM || ARM64 || COMPILE_TEST
---help---
If you have a network (Ethernet) card belonging to this class, say Y.
drivers(like ODP)to register with HNAE devices and their associated
operations.
+if HNS3
+
config HNS3_HCLGE
tristate "Hisilicon HNS3 HCLGE Acceleration Engine & Compatibility Layer Support"
+ default m
depends on PCI_MSI
- depends on HNS3
---help---
This selects the HNS3_HCLGE network acceleration engine & its hardware
compatibility layer. The engine would be used in Hisilicon hip08 family of
config HNS3_DCB
bool "Hisilicon HNS3 Data Center Bridge Support"
default n
- depends on HNS3 && HNS3_HCLGE && DCB
+ depends on HNS3_HCLGE && DCB
---help---
Say Y here if you want to use Data Center Bridging (DCB) in the HNS3 driver.
If unsure, say N.
config HNS3_HCLGEVF
- tristate "Hisilicon HNS3VF Acceleration Engine & Compatibility Layer Support"
- depends on PCI_MSI
- depends on HNS3
+ tristate "Hisilicon HNS3VF Acceleration Engine & Compatibility Layer Support"
+ depends on PCI_MSI
depends on HNS3_HCLGE
---help---
This selects the HNS3 VF drivers network acceleration engine & its hardware
config HNS3_ENET
tristate "Hisilicon HNS3 Ethernet Device Support"
+ default m
depends on 64BIT && PCI
- depends on HNS3
---help---
This selects the Ethernet Driver for Hisilicon Network Subsystem 3 for hip08
family of SoCs. This module depends upon HNAE3 driver to access the HNAE3
devices and their associated operations.
+endif #HNS3
+
endif # NET_VENDOR_HISILICON
hip04_config_port(ndev, SPEED_100, DUPLEX_FULL);
hip04_config_fifo(priv);
- random_ether_addr(ndev->dev_addr);
+ eth_random_addr(ndev->dev_addr);
hip04_update_mac_address(ndev);
ret = hip04_alloc_ring(ndev, d);
static u16
hns_nic_select_queue(struct net_device *ndev, struct sk_buff *skb,
- void *accel_priv, select_queue_fallback_t fallback)
+ struct net_device *sb_dev,
+ select_queue_fallback_t fallback)
{
struct ethhdr *eth_hdr = (struct ethhdr *)skb->data;
struct hns_nic_priv *priv = netdev_priv(ndev);
is_multicast_ether_addr(eth_hdr->h_dest))
return 0;
else
- return fallback(ndev, skb);
+ return fallback(ndev, skb, NULL);
}
static const struct net_device_ops hns_nic_netdev_ops = {
*/
#include <linux/list.h>
-#include <linux/slab.h>
#include <linux/spinlock.h>
#include "hnae3.h"
{
switch (client->type) {
case HNAE3_CLIENT_KNIC:
- hnae_set_bit(ae_dev->flag, HNAE3_KNIC_CLIENT_INITED_B, inited);
+ hnae3_set_bit(ae_dev->flag, HNAE3_KNIC_CLIENT_INITED_B, inited);
break;
case HNAE3_CLIENT_UNIC:
- hnae_set_bit(ae_dev->flag, HNAE3_UNIC_CLIENT_INITED_B, inited);
+ hnae3_set_bit(ae_dev->flag, HNAE3_UNIC_CLIENT_INITED_B, inited);
break;
case HNAE3_CLIENT_ROCE:
- hnae_set_bit(ae_dev->flag, HNAE3_ROCE_CLIENT_INITED_B, inited);
+ hnae3_set_bit(ae_dev->flag, HNAE3_ROCE_CLIENT_INITED_B, inited);
break;
default:
break;
switch (client->type) {
case HNAE3_CLIENT_KNIC:
- inited = hnae_get_bit(ae_dev->flag,
+ inited = hnae3_get_bit(ae_dev->flag,
HNAE3_KNIC_CLIENT_INITED_B);
break;
case HNAE3_CLIENT_UNIC:
- inited = hnae_get_bit(ae_dev->flag,
+ inited = hnae3_get_bit(ae_dev->flag,
HNAE3_UNIC_CLIENT_INITED_B);
break;
case HNAE3_CLIENT_ROCE:
- inited = hnae_get_bit(ae_dev->flag,
- HNAE3_ROCE_CLIENT_INITED_B);
+ inited = hnae3_get_bit(ae_dev->flag,
+ HNAE3_ROCE_CLIENT_INITED_B);
break;
default:
break;
/* check if this client matches the type of ae_dev */
if (!(hnae3_client_match(client->type, ae_dev->dev_type) &&
- hnae_get_bit(ae_dev->flag, HNAE3_DEV_INITED_B))) {
+ hnae3_get_bit(ae_dev->flag, HNAE3_DEV_INITED_B))) {
return 0;
}
ret = ae_dev->ops->init_client_instance(client, ae_dev);
if (ret) {
dev_err(&ae_dev->pdev->dev,
- "fail to instantiate client\n");
+ "fail to instantiate client, ret = %d\n", ret);
return ret;
}
ret = hnae3_match_n_instantiate(client, ae_dev, true);
if (ret)
dev_err(&ae_dev->pdev->dev,
- "match and instantiation failed for port\n");
+ "match and instantiation failed for port, ret = %d\n",
+ ret);
}
exit:
ae_dev->ops = ae_algo->ops;
ret = ae_algo->ops->init_ae_dev(ae_dev);
if (ret) {
- dev_err(&ae_dev->pdev->dev, "init ae_dev error.\n");
+ dev_err(&ae_dev->pdev->dev,
+ "init ae_dev error, ret = %d\n", ret);
continue;
}
- hnae_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 1);
+ hnae3_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 1);
/* check the client list for the match with this ae_dev type and
* initialize the figure out client instance
ret = hnae3_match_n_instantiate(client, ae_dev, true);
if (ret)
dev_err(&ae_dev->pdev->dev,
- "match and instantiation failed\n");
+ "match and instantiation failed, ret = %d\n",
+ ret);
}
}
mutex_lock(&hnae3_common_lock);
/* Check if there are matched ae_dev */
list_for_each_entry(ae_dev, &hnae3_ae_dev_list, node) {
- if (!hnae_get_bit(ae_dev->flag, HNAE3_DEV_INITED_B))
+ if (!hnae3_get_bit(ae_dev->flag, HNAE3_DEV_INITED_B))
continue;
id = pci_match_id(ae_algo->pdev_id_table, ae_dev->pdev);
hnae3_match_n_instantiate(client, ae_dev, false);
ae_algo->ops->uninit_ae_dev(ae_dev);
- hnae_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 0);
+ hnae3_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 0);
}
list_del(&ae_algo->node);
/* ae_dev init should set flag */
ret = ae_dev->ops->init_ae_dev(ae_dev);
if (ret) {
- dev_err(&ae_dev->pdev->dev, "init ae_dev error\n");
+ dev_err(&ae_dev->pdev->dev,
+ "init ae_dev error, ret = %d\n", ret);
goto out_err;
}
- hnae_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 1);
+ hnae3_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 1);
break;
}
ret = hnae3_match_n_instantiate(client, ae_dev, true);
if (ret)
dev_err(&ae_dev->pdev->dev,
- "match and instantiation failed\n");
+ "match and instantiation failed, ret = %d\n",
+ ret);
}
out_err:
mutex_lock(&hnae3_common_lock);
/* Check if there are matched ae_algo */
list_for_each_entry(ae_algo, &hnae3_ae_algo_list, node) {
- if (!hnae_get_bit(ae_dev->flag, HNAE3_DEV_INITED_B))
+ if (!hnae3_get_bit(ae_dev->flag, HNAE3_DEV_INITED_B))
continue;
id = pci_match_id(ae_algo->pdev_id_table, ae_dev->pdev);
hnae3_match_n_instantiate(client, ae_dev, false);
ae_algo->ops->uninit_ae_dev(ae_dev);
- hnae_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 0);
+ hnae3_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 0);
}
list_del(&ae_dev->node);
BIT(HNAE3_DEV_SUPPORT_ROCE_B))
#define hnae3_dev_roce_supported(hdev) \
- hnae_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_ROCE_B)
+ hnae3_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_ROCE_B)
#define hnae3_dev_dcb_supported(hdev) \
- hnae_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_DCB_B)
+ hnae3_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_DCB_B)
#define ring_ptr_move_fw(ring, p) \
((ring)->p = ((ring)->p + 1) % (ring)->desc_num)
#define HNAE3_CLIENT_NAME_LENGTH 16
struct hnae3_client {
char name[HNAE3_CLIENT_NAME_LENGTH];
- u16 version;
unsigned long state;
enum hnae3_client_type type;
const struct hnae3_client_ops *ops;
struct hnae3_ae_algo {
const struct hnae3_ae_ops *ops;
struct list_head node;
- char name[HNAE3_CLASS_NAME_SIZE];
const struct pci_device_id *pdev_id_table;
};
u32 numa_node_mask; /* for multi-chip support */
};
-#define hnae_set_field(origin, mask, shift, val) \
+#define hnae3_set_field(origin, mask, shift, val) \
do { \
(origin) &= (~(mask)); \
(origin) |= ((val) << (shift)) & (mask); \
} while (0)
-#define hnae_get_field(origin, mask, shift) (((origin) & (mask)) >> (shift))
+#define hnae3_get_field(origin, mask, shift) (((origin) & (mask)) >> (shift))
-#define hnae_set_bit(origin, shift, val) \
- hnae_set_field((origin), (0x1 << (shift)), (shift), (val))
-#define hnae_get_bit(origin, shift) \
- hnae_get_field((origin), (0x1 << (shift)), (shift))
+#define hnae3_set_bit(origin, shift, val) \
+ hnae3_set_field((origin), (0x1 << (shift)), (shift), (val))
+#define hnae3_get_bit(origin, shift) \
+ hnae3_get_field((origin), (0x1 << (shift)), (shift))
void hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev);
void hnae3_unregister_ae_dev(struct hnae3_ae_dev *ae_dev);
struct hnae3_handle *h = hns3_get_handle(netdev);
struct hnae3_knic_private_info *kinfo = &h->kinfo;
unsigned int queue_size = kinfo->rss_size * kinfo->num_tc;
- int ret;
+ int i, ret;
+
+ if (kinfo->num_tc <= 1) {
+ netdev_reset_tc(netdev);
+ } else {
+ ret = netdev_set_num_tc(netdev, kinfo->num_tc);
+ if (ret) {
+ netdev_err(netdev,
+ "netdev_set_num_tc fail, ret=%d!\n", ret);
+ return ret;
+ }
+
+ for (i = 0; i < HNAE3_MAX_TC; i++) {
+ if (!kinfo->tc_info[i].enable)
+ continue;
+
+ netdev_set_tc_queue(netdev,
+ kinfo->tc_info[i].tc,
+ kinfo->tc_info[i].tqp_count,
+ kinfo->tc_info[i].tqp_offset);
+ }
+ }
ret = netif_set_real_num_tx_queues(netdev, queue_size);
if (ret) {
static int hns3_nic_net_open(struct net_device *netdev)
{
struct hns3_nic_priv *priv = netdev_priv(netdev);
- int ret;
+ struct hnae3_handle *h = hns3_get_handle(netdev);
+ struct hnae3_knic_private_info *kinfo;
+ int i, ret;
netif_carrier_off(netdev);
return ret;
}
+ kinfo = &h->kinfo;
+ for (i = 0; i < HNAE3_MAX_USER_PRIO; i++) {
+ netdev_set_prio_tc_map(netdev, i,
+ kinfo->prio_tc[i]);
+ }
+
priv->ae_handle->last_reset_time = jiffies;
return 0;
}
/* find the txbd field values */
*paylen = skb->len - hdr_len;
- hnae_set_bit(*type_cs_vlan_tso,
- HNS3_TXD_TSO_B, 1);
+ hnae3_set_bit(*type_cs_vlan_tso,
+ HNS3_TXD_TSO_B, 1);
/* get MSS for TSO */
*mss = skb_shinfo(skb)->gso_size;
/* compute L2 header size for normal packet, defined in 2 Bytes */
l2_len = l3.hdr - skb->data;
- hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L2LEN_M,
- HNS3_TXD_L2LEN_S, l2_len >> 1);
+ hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L2LEN_M,
+ HNS3_TXD_L2LEN_S, l2_len >> 1);
/* tunnel packet*/
if (skb->encapsulation) {
/* compute OL2 header size, defined in 2 Bytes */
ol2_len = l2_len;
- hnae_set_field(*ol_type_vlan_len_msec,
- HNS3_TXD_L2LEN_M,
- HNS3_TXD_L2LEN_S, ol2_len >> 1);
+ hnae3_set_field(*ol_type_vlan_len_msec,
+ HNS3_TXD_L2LEN_M,
+ HNS3_TXD_L2LEN_S, ol2_len >> 1);
/* compute OL3 header size, defined in 4 Bytes */
ol3_len = l4.hdr - l3.hdr;
- hnae_set_field(*ol_type_vlan_len_msec, HNS3_TXD_L3LEN_M,
- HNS3_TXD_L3LEN_S, ol3_len >> 2);
+ hnae3_set_field(*ol_type_vlan_len_msec, HNS3_TXD_L3LEN_M,
+ HNS3_TXD_L3LEN_S, ol3_len >> 2);
/* MAC in UDP, MAC in GRE (0x6558)*/
if ((ol4_proto == IPPROTO_UDP) || (ol4_proto == IPPROTO_GRE)) {
/* compute OL4 header size, defined in 4 Bytes. */
ol4_len = l2_hdr - l4.hdr;
- hnae_set_field(*ol_type_vlan_len_msec, HNS3_TXD_L4LEN_M,
- HNS3_TXD_L4LEN_S, ol4_len >> 2);
+ hnae3_set_field(*ol_type_vlan_len_msec,
+ HNS3_TXD_L4LEN_M, HNS3_TXD_L4LEN_S,
+ ol4_len >> 2);
/* switch IP header ptr from outer to inner header */
l3.hdr = skb_inner_network_header(skb);
/* compute inner l2 header size, defined in 2 Bytes. */
l2_len = l3.hdr - l2_hdr;
- hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L2LEN_M,
- HNS3_TXD_L2LEN_S, l2_len >> 1);
+ hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L2LEN_M,
+ HNS3_TXD_L2LEN_S, l2_len >> 1);
} else {
/* skb packet types not supported by hardware,
* txbd len fild doesn't be filled.
/* compute inner(/normal) L3 header size, defined in 4 Bytes */
l3_len = l4.hdr - l3.hdr;
- hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L3LEN_M,
- HNS3_TXD_L3LEN_S, l3_len >> 2);
+ hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L3LEN_M,
+ HNS3_TXD_L3LEN_S, l3_len >> 2);
/* compute inner(/normal) L4 header size, defined in 4 Bytes */
switch (l4_proto) {
case IPPROTO_TCP:
- hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_M,
- HNS3_TXD_L4LEN_S, l4.tcp->doff);
+ hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_M,
+ HNS3_TXD_L4LEN_S, l4.tcp->doff);
break;
case IPPROTO_SCTP:
- hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_M,
- HNS3_TXD_L4LEN_S, (sizeof(struct sctphdr) >> 2));
+ hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_M,
+ HNS3_TXD_L4LEN_S,
+ (sizeof(struct sctphdr) >> 2));
break;
case IPPROTO_UDP:
- hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_M,
- HNS3_TXD_L4LEN_S, (sizeof(struct udphdr) >> 2));
+ hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_M,
+ HNS3_TXD_L4LEN_S,
+ (sizeof(struct udphdr) >> 2));
break;
default:
/* skb packet types not supported by hardware,
/* define outer network header type.*/
if (skb->protocol == htons(ETH_P_IP)) {
if (skb_is_gso(skb))
- hnae_set_field(*ol_type_vlan_len_msec,
- HNS3_TXD_OL3T_M, HNS3_TXD_OL3T_S,
- HNS3_OL3T_IPV4_CSUM);
+ hnae3_set_field(*ol_type_vlan_len_msec,
+ HNS3_TXD_OL3T_M,
+ HNS3_TXD_OL3T_S,
+ HNS3_OL3T_IPV4_CSUM);
else
- hnae_set_field(*ol_type_vlan_len_msec,
- HNS3_TXD_OL3T_M, HNS3_TXD_OL3T_S,
- HNS3_OL3T_IPV4_NO_CSUM);
+ hnae3_set_field(*ol_type_vlan_len_msec,
+ HNS3_TXD_OL3T_M,
+ HNS3_TXD_OL3T_S,
+ HNS3_OL3T_IPV4_NO_CSUM);
} else if (skb->protocol == htons(ETH_P_IPV6)) {
- hnae_set_field(*ol_type_vlan_len_msec, HNS3_TXD_OL3T_M,
- HNS3_TXD_OL3T_S, HNS3_OL3T_IPV6);
+ hnae3_set_field(*ol_type_vlan_len_msec, HNS3_TXD_OL3T_M,
+ HNS3_TXD_OL3T_S, HNS3_OL3T_IPV6);
}
/* define tunnel type(OL4).*/
switch (l4_proto) {
case IPPROTO_UDP:
- hnae_set_field(*ol_type_vlan_len_msec,
- HNS3_TXD_TUNTYPE_M,
- HNS3_TXD_TUNTYPE_S,
- HNS3_TUN_MAC_IN_UDP);
+ hnae3_set_field(*ol_type_vlan_len_msec,
+ HNS3_TXD_TUNTYPE_M,
+ HNS3_TXD_TUNTYPE_S,
+ HNS3_TUN_MAC_IN_UDP);
break;
case IPPROTO_GRE:
- hnae_set_field(*ol_type_vlan_len_msec,
- HNS3_TXD_TUNTYPE_M,
- HNS3_TXD_TUNTYPE_S,
- HNS3_TUN_NVGRE);
+ hnae3_set_field(*ol_type_vlan_len_msec,
+ HNS3_TXD_TUNTYPE_M,
+ HNS3_TXD_TUNTYPE_S,
+ HNS3_TUN_NVGRE);
break;
default:
/* drop the skb tunnel packet if hardware don't support,
}
if (l3.v4->version == 4) {
- hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L3T_M,
- HNS3_TXD_L3T_S, HNS3_L3T_IPV4);
+ hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L3T_M,
+ HNS3_TXD_L3T_S, HNS3_L3T_IPV4);
/* the stack computes the IP header already, the only time we
* need the hardware to recompute it is in the case of TSO.
*/
if (skb_is_gso(skb))
- hnae_set_bit(*type_cs_vlan_tso, HNS3_TXD_L3CS_B, 1);
-
- hnae_set_bit(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1);
+ hnae3_set_bit(*type_cs_vlan_tso, HNS3_TXD_L3CS_B, 1);
} else if (l3.v6->version == 6) {
- hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L3T_M,
- HNS3_TXD_L3T_S, HNS3_L3T_IPV6);
- hnae_set_bit(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1);
+ hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L3T_M,
+ HNS3_TXD_L3T_S, HNS3_L3T_IPV6);
}
switch (l4_proto) {
case IPPROTO_TCP:
- hnae_set_field(*type_cs_vlan_tso,
- HNS3_TXD_L4T_M,
- HNS3_TXD_L4T_S,
- HNS3_L4T_TCP);
+ hnae3_set_bit(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1);
+ hnae3_set_field(*type_cs_vlan_tso,
+ HNS3_TXD_L4T_M,
+ HNS3_TXD_L4T_S,
+ HNS3_L4T_TCP);
break;
case IPPROTO_UDP:
if (hns3_tunnel_csum_bug(skb))
break;
- hnae_set_field(*type_cs_vlan_tso,
- HNS3_TXD_L4T_M,
- HNS3_TXD_L4T_S,
- HNS3_L4T_UDP);
+ hnae3_set_bit(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1);
+ hnae3_set_field(*type_cs_vlan_tso,
+ HNS3_TXD_L4T_M,
+ HNS3_TXD_L4T_S,
+ HNS3_L4T_UDP);
break;
case IPPROTO_SCTP:
- hnae_set_field(*type_cs_vlan_tso,
- HNS3_TXD_L4T_M,
- HNS3_TXD_L4T_S,
- HNS3_L4T_SCTP);
+ hnae3_set_bit(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1);
+ hnae3_set_field(*type_cs_vlan_tso,
+ HNS3_TXD_L4T_M,
+ HNS3_TXD_L4T_S,
+ HNS3_L4T_SCTP);
break;
default:
/* drop the skb tunnel packet if hardware don't support,
static void hns3_set_txbd_baseinfo(u16 *bdtp_fe_sc_vld_ra_ri, int frag_end)
{
/* Config bd buffer end */
- hnae_set_field(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_BDTYPE_M,
- HNS3_TXD_BDTYPE_S, 0);
- hnae_set_bit(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_FE_B, !!frag_end);
- hnae_set_bit(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_VLD_B, 1);
- hnae_set_field(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_SC_M, HNS3_TXD_SC_S, 0);
+ hnae3_set_field(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_BDTYPE_M,
+ HNS3_TXD_BDTYPE_S, 0);
+ hnae3_set_bit(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_FE_B, !!frag_end);
+ hnae3_set_bit(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_VLD_B, 1);
+ hnae3_set_field(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_SC_M, HNS3_TXD_SC_S, 0);
}
static int hns3_fill_desc_vtags(struct sk_buff *skb,
* and use inner_vtag in one tag case.
*/
if (skb->protocol == htons(ETH_P_8021Q)) {
- hnae_set_bit(*out_vlan_flag, HNS3_TXD_OVLAN_B, 1);
+ hnae3_set_bit(*out_vlan_flag, HNS3_TXD_OVLAN_B, 1);
*out_vtag = vlan_tag;
} else {
- hnae_set_bit(*inner_vlan_flag, HNS3_TXD_VLAN_B, 1);
+ hnae3_set_bit(*inner_vlan_flag, HNS3_TXD_VLAN_B, 1);
*inner_vtag = vlan_tag;
}
} else if (skb->protocol == htons(ETH_P_8021Q)) {
u16 out_vtag = 0;
u32 paylen = 0;
u16 mss = 0;
- __be16 protocol;
u8 ol4_proto;
u8 il4_proto;
int ret;
if (skb->ip_summed == CHECKSUM_PARTIAL) {
skb_reset_mac_len(skb);
- protocol = skb->protocol;
ret = hns3_get_l4_protocol(skb, &ol4_proto, &il4_proto);
if (ret)
wmb(); /* Commit all data before submit */
- hnae_queue_xmit(ring->tqp, buf_num);
+ hnae3_queue_xmit(ring->tqp, buf_num);
return NETDEV_TX_OK;
u16 mode = mqprio_qopt->mode;
u8 hw = mqprio_qopt->qopt.hw;
bool if_running;
- unsigned int i;
int ret;
if (!((hw == TC_MQPRIO_HW_OFFLOAD_TCS &&
if (ret)
goto out;
- if (tc <= 1) {
- netdev_reset_tc(netdev);
- } else {
- ret = netdev_set_num_tc(netdev, tc);
- if (ret)
- goto out;
-
- for (i = 0; i < HNAE3_MAX_TC; i++) {
- if (!kinfo->tc_info[i].enable)
- continue;
-
- netdev_set_tc_queue(netdev,
- kinfo->tc_info[i].tc,
- kinfo->tc_info[i].tqp_count,
- kinfo->tc_info[i].tqp_offset);
- }
- }
-
ret = hns3_nic_set_real_num_queue(netdev);
out:
static int hns3_alloc_buffer(struct hns3_enet_ring *ring,
struct hns3_desc_cb *cb)
{
- unsigned int order = hnae_page_order(ring);
+ unsigned int order = hnae3_page_order(ring);
struct page *p;
p = dev_alloc_pages(order);
cb->page_offset = 0;
cb->reuse_flag = 0;
cb->buf = page_address(p);
- cb->length = hnae_page_size(ring);
+ cb->length = hnae3_page_size(ring);
cb->type = DESC_TYPE_PAGE;
return 0;
/* free desc along with its attached buffer */
static void hns3_free_desc(struct hns3_enet_ring *ring)
{
+ int size = ring->desc_num * sizeof(ring->desc[0]);
+
hns3_free_buffers(ring);
- dma_unmap_single(ring_to_dev(ring), ring->desc_dma_addr,
- ring->desc_num * sizeof(ring->desc[0]),
- DMA_BIDIRECTIONAL);
- ring->desc_dma_addr = 0;
- kfree(ring->desc);
- ring->desc = NULL;
+ if (ring->desc) {
+ dma_free_coherent(ring_to_dev(ring), size,
+ ring->desc, ring->desc_dma_addr);
+ ring->desc = NULL;
+ }
}
static int hns3_alloc_desc(struct hns3_enet_ring *ring)
{
int size = ring->desc_num * sizeof(ring->desc[0]);
- ring->desc = kzalloc(size, GFP_KERNEL);
+ ring->desc = dma_zalloc_coherent(ring_to_dev(ring), size,
+ &ring->desc_dma_addr,
+ GFP_KERNEL);
if (!ring->desc)
return -ENOMEM;
- ring->desc_dma_addr = dma_map_single(ring_to_dev(ring), ring->desc,
- size, DMA_BIDIRECTIONAL);
- if (dma_mapping_error(ring_to_dev(ring), ring->desc_dma_addr)) {
- ring->desc_dma_addr = 0;
- kfree(ring->desc);
- ring->desc = NULL;
- return -ENOMEM;
- }
-
return 0;
}
(*pkts) += (desc_cb->type == DESC_TYPE_SKB);
(*bytes) += desc_cb->length;
- /* desc_cb will be cleaned, after hnae_free_buffer_detach*/
+ /* desc_cb will be cleaned, after hnae3_free_buffer_detach*/
hns3_free_buffer_detach(ring, ring->next_to_clean);
ring_ptr_move_fw(ring, next_to_clean);
if (is_ring_empty(ring) || head == ring->next_to_clean)
return true; /* no data to poll */
- if (!is_valid_clean_head(ring, head)) {
+ if (unlikely(!is_valid_clean_head(ring, head))) {
netdev_err(netdev, "wrong head (%d, %d-%d)\n", head,
ring->next_to_use, ring->next_to_clean);
bool twobufs;
twobufs = ((PAGE_SIZE < 8192) &&
- hnae_buf_size(ring) == HNS3_BUFFER_SIZE_2048);
+ hnae3_buf_size(ring) == HNS3_BUFFER_SIZE_2048);
desc = &ring->desc[ring->next_to_clean];
size = le16_to_cpu(desc->rx.size);
- truesize = hnae_buf_size(ring);
+ truesize = hnae3_buf_size(ring);
if (!twobufs)
- last_offset = hnae_page_size(ring) - hnae_buf_size(ring);
+ last_offset = hnae3_page_size(ring) - hnae3_buf_size(ring);
skb_add_rx_frag(skb, i, desc_cb->priv, desc_cb->page_offset + pull_len,
size - pull_len, truesize);
return;
/* check if hardware has done checksum */
- if (!hnae_get_bit(bd_base_info, HNS3_RXD_L3L4P_B))
+ if (!hnae3_get_bit(bd_base_info, HNS3_RXD_L3L4P_B))
return;
- if (unlikely(hnae_get_bit(l234info, HNS3_RXD_L3E_B) ||
- hnae_get_bit(l234info, HNS3_RXD_L4E_B) ||
- hnae_get_bit(l234info, HNS3_RXD_OL3E_B) ||
- hnae_get_bit(l234info, HNS3_RXD_OL4E_B))) {
+ if (unlikely(hnae3_get_bit(l234info, HNS3_RXD_L3E_B) ||
+ hnae3_get_bit(l234info, HNS3_RXD_L4E_B) ||
+ hnae3_get_bit(l234info, HNS3_RXD_OL3E_B) ||
+ hnae3_get_bit(l234info, HNS3_RXD_OL4E_B))) {
netdev_err(netdev, "L3/L4 error pkt\n");
u64_stats_update_begin(&ring->syncp);
ring->stats.l3l4_csum_err++;
return;
}
- l3_type = hnae_get_field(l234info, HNS3_RXD_L3ID_M,
- HNS3_RXD_L3ID_S);
- l4_type = hnae_get_field(l234info, HNS3_RXD_L4ID_M,
- HNS3_RXD_L4ID_S);
+ l3_type = hnae3_get_field(l234info, HNS3_RXD_L3ID_M,
+ HNS3_RXD_L3ID_S);
+ l4_type = hnae3_get_field(l234info, HNS3_RXD_L4ID_M,
+ HNS3_RXD_L4ID_S);
- ol4_type = hnae_get_field(l234info, HNS3_RXD_OL4ID_M, HNS3_RXD_OL4ID_S);
+ ol4_type = hnae3_get_field(l234info, HNS3_RXD_OL4ID_M,
+ HNS3_RXD_OL4ID_S);
switch (ol4_type) {
case HNS3_OL4_TYPE_MAC_IN_UDP:
case HNS3_OL4_TYPE_NVGRE:
skb->csum_level = 1;
case HNS3_OL4_TYPE_NO_TUN:
/* Can checksum ipv4 or ipv6 + UDP/TCP/SCTP packets */
- if (l3_type == HNS3_L3_TYPE_IPV4 ||
- (l3_type == HNS3_L3_TYPE_IPV6 &&
- (l4_type == HNS3_L4_TYPE_UDP ||
- l4_type == HNS3_L4_TYPE_TCP ||
- l4_type == HNS3_L4_TYPE_SCTP)))
+ if ((l3_type == HNS3_L3_TYPE_IPV4 ||
+ l3_type == HNS3_L3_TYPE_IPV6) &&
+ (l4_type == HNS3_L4_TYPE_UDP ||
+ l4_type == HNS3_L4_TYPE_TCP ||
+ l4_type == HNS3_L4_TYPE_SCTP))
skb->ip_summed = CHECKSUM_UNNECESSARY;
break;
}
#define HNS3_STRP_OUTER_VLAN 0x1
#define HNS3_STRP_INNER_VLAN 0x2
- switch (hnae_get_field(l234info, HNS3_RXD_STRP_TAGP_M,
- HNS3_RXD_STRP_TAGP_S)) {
+ switch (hnae3_get_field(l234info, HNS3_RXD_STRP_TAGP_M,
+ HNS3_RXD_STRP_TAGP_S)) {
case HNS3_STRP_OUTER_VLAN:
vlan_tag = le16_to_cpu(desc->rx.ot_vlan_tag);
break;
bd_base_info = le32_to_cpu(desc->rx.bd_base_info);
/* Check valid BD */
- if (!hnae_get_bit(bd_base_info, HNS3_RXD_VLD_B))
+ if (unlikely(!hnae3_get_bit(bd_base_info, HNS3_RXD_VLD_B)))
return -EFAULT;
va = (unsigned char *)desc_cb->buf + desc_cb->page_offset;
hns3_nic_reuse_page(skb, 0, ring, pull_len, desc_cb);
ring_ptr_move_fw(ring, next_to_clean);
- while (!hnae_get_bit(bd_base_info, HNS3_RXD_FE_B)) {
+ while (!hnae3_get_bit(bd_base_info, HNS3_RXD_FE_B)) {
desc = &ring->desc[ring->next_to_clean];
desc_cb = &ring->desc_cb[ring->next_to_clean];
bd_base_info = le32_to_cpu(desc->rx.bd_base_info);
vlan_tag);
}
- if (unlikely(!hnae_get_bit(bd_base_info, HNS3_RXD_VLD_B))) {
+ if (unlikely(!hnae3_get_bit(bd_base_info, HNS3_RXD_VLD_B))) {
netdev_err(netdev, "no valid bd,%016llx,%016llx\n",
((u64 *)desc)[0], ((u64 *)desc)[1]);
u64_stats_update_begin(&ring->syncp);
}
if (unlikely((!desc->rx.pkt_len) ||
- hnae_get_bit(l234info, HNS3_RXD_TRUNCAT_B))) {
+ hnae3_get_bit(l234info, HNS3_RXD_TRUNCAT_B))) {
netdev_err(netdev, "truncated pkt\n");
u64_stats_update_begin(&ring->syncp);
ring->stats.err_pkt_len++;
return -EFAULT;
}
- if (unlikely(hnae_get_bit(l234info, HNS3_RXD_L2E_B))) {
+ if (unlikely(hnae3_get_bit(l234info, HNS3_RXD_L2E_B))) {
netdev_err(netdev, "L2 error pkt\n");
u64_stats_update_begin(&ring->syncp);
ring->stats.l2_err++;
tx_ring = tqp_vector->tx_group.ring;
if (tx_ring) {
cur_chain->tqp_index = tx_ring->tqp->tqp_index;
- hnae_set_bit(cur_chain->flag, HNAE3_RING_TYPE_B,
- HNAE3_RING_TYPE_TX);
- hnae_set_field(cur_chain->int_gl_idx, HNAE3_RING_GL_IDX_M,
- HNAE3_RING_GL_IDX_S, HNAE3_RING_GL_TX);
+ hnae3_set_bit(cur_chain->flag, HNAE3_RING_TYPE_B,
+ HNAE3_RING_TYPE_TX);
+ hnae3_set_field(cur_chain->int_gl_idx, HNAE3_RING_GL_IDX_M,
+ HNAE3_RING_GL_IDX_S, HNAE3_RING_GL_TX);
cur_chain->next = NULL;
cur_chain->next = chain;
chain->tqp_index = tx_ring->tqp->tqp_index;
- hnae_set_bit(chain->flag, HNAE3_RING_TYPE_B,
- HNAE3_RING_TYPE_TX);
- hnae_set_field(chain->int_gl_idx,
- HNAE3_RING_GL_IDX_M,
- HNAE3_RING_GL_IDX_S,
- HNAE3_RING_GL_TX);
+ hnae3_set_bit(chain->flag, HNAE3_RING_TYPE_B,
+ HNAE3_RING_TYPE_TX);
+ hnae3_set_field(chain->int_gl_idx,
+ HNAE3_RING_GL_IDX_M,
+ HNAE3_RING_GL_IDX_S,
+ HNAE3_RING_GL_TX);
cur_chain = chain;
}
if (!tx_ring && rx_ring) {
cur_chain->next = NULL;
cur_chain->tqp_index = rx_ring->tqp->tqp_index;
- hnae_set_bit(cur_chain->flag, HNAE3_RING_TYPE_B,
- HNAE3_RING_TYPE_RX);
- hnae_set_field(cur_chain->int_gl_idx, HNAE3_RING_GL_IDX_M,
- HNAE3_RING_GL_IDX_S, HNAE3_RING_GL_RX);
+ hnae3_set_bit(cur_chain->flag, HNAE3_RING_TYPE_B,
+ HNAE3_RING_TYPE_RX);
+ hnae3_set_field(cur_chain->int_gl_idx, HNAE3_RING_GL_IDX_M,
+ HNAE3_RING_GL_IDX_S, HNAE3_RING_GL_RX);
rx_ring = rx_ring->next;
}
cur_chain->next = chain;
chain->tqp_index = rx_ring->tqp->tqp_index;
- hnae_set_bit(chain->flag, HNAE3_RING_TYPE_B,
- HNAE3_RING_TYPE_RX);
- hnae_set_field(chain->int_gl_idx, HNAE3_RING_GL_IDX_M,
- HNAE3_RING_GL_IDX_S, HNAE3_RING_GL_RX);
+ hnae3_set_bit(chain->flag, HNAE3_RING_TYPE_B,
+ HNAE3_RING_TYPE_RX);
+ hnae3_set_field(chain->int_gl_idx, HNAE3_RING_GL_IDX_M,
+ HNAE3_RING_GL_IDX_S, HNAE3_RING_GL_RX);
cur_chain = chain;
if (ret)
return ret;
- ret = h->ae_algo->ops->put_vector(h, tqp_vector->vector_irq);
- if (ret)
- return ret;
-
hns3_free_vector_ring_chain(tqp_vector, &vector_ring_chain);
if (priv->tqp_vector[i].irq_init_flag == HNS3_VECTOR_INITED) {
ring->io_base = q->io_base;
}
- hnae_set_bit(ring->flag, HNAE3_RING_TYPE_B, ring_type);
+ hnae3_set_bit(ring->flag, HNAE3_RING_TYPE_B, ring_type);
ring->tqp = q;
ring->desc = NULL;
priv->dev = &pdev->dev;
priv->netdev = netdev;
priv->ae_handle = handle;
- priv->ae_handle->reset_level = HNAE3_NONE_RESET;
priv->ae_handle->last_reset_time = jiffies;
priv->tx_timeout_count = 0;
/* Carrier off reporting is important to ethtool even BEFORE open */
netif_carrier_off(netdev);
+ if (handle->flags & HNAE3_SUPPORT_VF)
+ handle->reset_level = HNAE3_VF_RESET;
+ else
+ handle->reset_level = HNAE3_FUNC_RESET;
+
ret = hns3_get_ring_config(priv);
if (ret) {
ret = -ENOMEM;
struct net_device *ndev = kinfo->netdev;
bool if_running;
int ret;
- u8 i;
if (tc > HNAE3_MAX_TC)
return -EINVAL;
if_running = netif_running(ndev);
- ret = netdev_set_num_tc(ndev, tc);
- if (ret)
- return ret;
-
if (if_running) {
(void)hns3_nic_net_stop(ndev);
msleep(100);
if (ret)
goto err_out;
- if (tc <= 1) {
- netdev_reset_tc(ndev);
- goto out;
- }
-
- for (i = 0; i < HNAE3_MAX_TC; i++) {
- struct hnae3_tc_info *tc_info = &kinfo->tc_info[i];
-
- if (tc_info->enable)
- netdev_set_tc_queue(ndev,
- tc_info->tc,
- tc_info->tqp_count,
- tc_info->tqp_offset);
- }
-
- for (i = 0; i < HNAE3_MAX_USER_PRIO; i++) {
- netdev_set_prio_tc_map(ndev, i,
- kinfo->prio_tc[i]);
- }
-
-out:
ret = hns3_nic_set_real_num_queue(ndev);
err_out:
struct net_device *ndev = kinfo->netdev;
if (!netif_running(ndev))
- return -EIO;
+ return 0;
return hns3_nic_net_stop(ndev);
}
/* Carrier off reporting is important to ethtool even BEFORE open */
netif_carrier_off(netdev);
- ret = hns3_get_ring_config(priv);
- if (ret)
- return ret;
-
ret = hns3_nic_init_vector_data(priv);
if (ret)
return ret;
if (ret)
netdev_err(netdev, "uninit ring error\n");
- hns3_put_ring_config(priv);
-
- priv->ring_data = NULL;
-
hns3_uninit_mac_addr(netdev);
return ret;
u16 num_tqps; /* total number of tqps in TQP vector */
- cpumask_t affinity_mask;
char name[HNAE3_INT_NAME_LEN];
/* when 0 should adjust interrupt coalesce parameter */
#define hns3_write_dev(a, reg, value) \
hns3_write_reg((a)->io_base, (reg), (value))
-#define hnae_queue_xmit(tqp, buf_num) writel_relaxed(buf_num, \
+#define hnae3_queue_xmit(tqp, buf_num) writel_relaxed(buf_num, \
(tqp)->io_base + HNS3_RING_TX_RING_TAIL_REG)
#define ring_to_dev(ring) (&(ring)->tqp->handle->pdev->dev)
#define tx_ring_data(priv, idx) ((priv)->ring_data[idx])
-#define hnae_buf_size(_ring) ((_ring)->buf_size)
-#define hnae_page_order(_ring) (get_order(hnae_buf_size(_ring)))
-#define hnae_page_size(_ring) (PAGE_SIZE << hnae_page_order(_ring))
+#define hnae3_buf_size(_ring) ((_ring)->buf_size)
+#define hnae3_page_order(_ring) (get_order(hnae3_buf_size(_ring)))
+#define hnae3_page_size(_ring) (PAGE_SIZE << hnae3_page_order(_ring))
/* iterator for handling rings in ring group */
#define hns3_for_each_ring(pos, head) \
rx_group = &ring->tqp_vector->rx_group;
pre_rx_pkt = rx_group->total_packets;
+ preempt_disable();
hns3_clean_rx_ring(ring, budget, hns3_lb_check_skb_data);
+ preempt_enable();
rcv_good_pkt_total += (rx_group->total_packets - pre_rx_pkt);
rx_group->total_packets = pre_rx_pkt;
#include "hclge_main.h"
#define hclge_is_csq(ring) ((ring)->flag & HCLGE_TYPE_CSQ)
-#define hclge_ring_to_dma_dir(ring) (hclge_is_csq(ring) ? \
- DMA_TO_DEVICE : DMA_FROM_DEVICE)
+
#define cmq_ring_to_dev(ring) (&(ring)->dev->pdev->dev)
static int hclge_ring_space(struct hclge_cmq_ring *ring)
{
int size = ring->desc_num * sizeof(struct hclge_desc);
- ring->desc = kzalloc(size, GFP_KERNEL);
+ ring->desc = dma_zalloc_coherent(cmq_ring_to_dev(ring),
+ size, &ring->desc_dma_addr,
+ GFP_KERNEL);
if (!ring->desc)
return -ENOMEM;
- ring->desc_dma_addr = dma_map_single(cmq_ring_to_dev(ring), ring->desc,
- size, DMA_BIDIRECTIONAL);
- if (dma_mapping_error(cmq_ring_to_dev(ring), ring->desc_dma_addr)) {
- ring->desc_dma_addr = 0;
- kfree(ring->desc);
- ring->desc = NULL;
- return -ENOMEM;
- }
-
return 0;
}
static void hclge_free_cmd_desc(struct hclge_cmq_ring *ring)
{
- dma_unmap_single(cmq_ring_to_dev(ring), ring->desc_dma_addr,
- ring->desc_num * sizeof(ring->desc[0]),
- DMA_BIDIRECTIONAL);
+ int size = ring->desc_num * sizeof(struct hclge_desc);
- ring->desc_dma_addr = 0;
- kfree(ring->desc);
- ring->desc = NULL;
+ if (ring->desc) {
+ dma_free_coherent(cmq_ring_to_dev(ring), size,
+ ring->desc, ring->desc_dma_addr);
+ ring->desc = NULL;
+ }
}
static int hclge_alloc_cmd_queue(struct hclge_dev *hdev, int ring_type)
if (is_read)
desc->flag |= cpu_to_le16(HCLGE_CMD_FLAG_WR);
- else
- desc->flag &= cpu_to_le16(~HCLGE_CMD_FLAG_WR);
}
static void hclge_cmd_config_regs(struct hclge_cmq_ring *ring)
if (ring->flag == HCLGE_TYPE_CSQ) {
hclge_write_dev(hw, HCLGE_NIC_CSQ_BASEADDR_L_REG,
- (u32)dma);
+ lower_32_bits(dma));
hclge_write_dev(hw, HCLGE_NIC_CSQ_BASEADDR_H_REG,
- (u32)((dma >> 31) >> 1));
+ upper_32_bits(dma));
hclge_write_dev(hw, HCLGE_NIC_CSQ_DEPTH_REG,
(ring->desc_num >> HCLGE_NIC_CMQ_DESC_NUM_S) |
HCLGE_NIC_CMQ_ENABLE);
- hclge_write_dev(hw, HCLGE_NIC_CSQ_TAIL_REG, 0);
hclge_write_dev(hw, HCLGE_NIC_CSQ_HEAD_REG, 0);
+ hclge_write_dev(hw, HCLGE_NIC_CSQ_TAIL_REG, 0);
} else {
hclge_write_dev(hw, HCLGE_NIC_CRQ_BASEADDR_L_REG,
- (u32)dma);
+ lower_32_bits(dma));
hclge_write_dev(hw, HCLGE_NIC_CRQ_BASEADDR_H_REG,
- (u32)((dma >> 31) >> 1));
+ upper_32_bits(dma));
hclge_write_dev(hw, HCLGE_NIC_CRQ_DEPTH_REG,
(ring->desc_num >> HCLGE_NIC_CMQ_DESC_NUM_S) |
HCLGE_NIC_CMQ_ENABLE);
- hclge_write_dev(hw, HCLGE_NIC_CRQ_TAIL_REG, 0);
hclge_write_dev(hw, HCLGE_NIC_CRQ_HEAD_REG, 0);
+ hclge_write_dev(hw, HCLGE_NIC_CRQ_TAIL_REG, 0);
}
}
static int hclge_cmd_csq_clean(struct hclge_hw *hw)
{
- struct hclge_dev *hdev = (struct hclge_dev *)hw->back;
+ struct hclge_dev *hdev = container_of(hw, struct hclge_dev, hw);
struct hclge_cmq_ring *csq = &hw->cmq.csq;
- u16 ntc = csq->next_to_clean;
- struct hclge_desc *desc;
- int clean = 0;
u32 head;
+ int clean;
- desc = &csq->desc[ntc];
head = hclge_read_dev(hw, HCLGE_NIC_CSQ_HEAD_REG);
rmb(); /* Make sure head is ready before touch any data */
if (!is_valid_csq_clean_head(csq, head)) {
- dev_warn(&hdev->pdev->dev, "wrong head (%d, %d-%d)\n", head,
- csq->next_to_use, csq->next_to_clean);
+ dev_warn(&hdev->pdev->dev, "wrong cmd head (%d, %d-%d)\n", head,
+ csq->next_to_use, csq->next_to_clean);
return 0;
}
- while (head != ntc) {
- memset(desc, 0, sizeof(*desc));
- ntc++;
- if (ntc == csq->desc_num)
- ntc = 0;
- desc = &csq->desc[ntc];
- clean++;
- }
- csq->next_to_clean = ntc;
-
+ clean = (head - csq->next_to_clean + csq->desc_num) % csq->desc_num;
+ csq->next_to_clean = head;
return clean;
}
**/
int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num)
{
- struct hclge_dev *hdev = (struct hclge_dev *)hw->back;
+ struct hclge_dev *hdev = container_of(hw, struct hclge_dev, hw);
struct hclge_desc *desc_to_use;
bool complete = false;
u32 timeout = 0;
spin_lock_bh(&hw->cmq.csq.lock);
- if (num > hclge_ring_space(&hw->cmq.csq)) {
+ if (num > hclge_ring_space(&hw->cmq.csq) ||
+ test_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state)) {
spin_unlock_bh(&hw->cmq.csq.lock);
return -EBUSY;
}
*/
if (HCLGE_SEND_SYNC(le16_to_cpu(desc->flag))) {
do {
- if (hclge_cmd_csq_done(hw))
+ if (hclge_cmd_csq_done(hw)) {
+ complete = true;
break;
+ }
udelay(1);
timeout++;
} while (timeout < hw->cmq.tx_timeout);
}
- if (hclge_cmd_csq_done(hw)) {
- complete = true;
+ if (!complete) {
+ retval = -EAGAIN;
+ } else {
handle = 0;
while (handle < num) {
/* Get the result of hardware write back */
desc_to_use = &hw->cmq.csq.desc[ntc];
desc[handle] = *desc_to_use;
- pr_debug("Get cmd desc:\n");
if (likely(!hclge_is_special_opcode(opcode)))
desc_ret = le16_to_cpu(desc[handle].retval);
else
desc_ret = le16_to_cpu(desc[0].retval);
- if ((enum hclge_cmd_return_status)desc_ret ==
- HCLGE_CMD_EXEC_SUCCESS)
+ if (desc_ret == HCLGE_CMD_EXEC_SUCCESS)
retval = 0;
else
retval = -EIO;
- hw->cmq.last_status = (enum hclge_cmd_status)desc_ret;
+ hw->cmq.last_status = desc_ret;
ntc++;
handle++;
if (ntc == hw->cmq.csq.desc_num)
}
}
- if (!complete)
- retval = -EAGAIN;
-
/* Clean the command send queue */
handle = hclge_cmd_csq_clean(hw);
if (handle != num) {
spin_lock_init(&hdev->hw.cmq.crq.lock);
hclge_cmd_init_regs(&hdev->hw);
+ clear_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
ret = hclge_cmd_query_firmware_version(&hdev->hw, &version);
if (ret) {
struct hclge_config_max_frm_size_cmd {
__le16 max_frm_size;
- u8 rsv[22];
+ u8 min_frm_size;
+ u8 rsv[21];
};
enum hclge_mac_vlan_tbl_opcode {
if (hnae3_dev_roce_supported(hdev)) {
hdev->num_roce_msi =
- hnae_get_field(__le16_to_cpu(req->pf_intr_vector_number),
- HCLGE_PF_VEC_NUM_M, HCLGE_PF_VEC_NUM_S);
+ hnae3_get_field(__le16_to_cpu(req->pf_intr_vector_number),
+ HCLGE_PF_VEC_NUM_M, HCLGE_PF_VEC_NUM_S);
/* PF should have NIC vectors and Roce vectors,
* NIC vectors are queued before Roce vectors.
hdev->num_msi = hdev->num_roce_msi + HCLGE_ROCE_VECTOR_OFFSET;
} else {
hdev->num_msi =
- hnae_get_field(__le16_to_cpu(req->pf_intr_vector_number),
- HCLGE_PF_VEC_NUM_M, HCLGE_PF_VEC_NUM_S);
+ hnae3_get_field(__le16_to_cpu(req->pf_intr_vector_number),
+ HCLGE_PF_VEC_NUM_M, HCLGE_PF_VEC_NUM_S);
}
return 0;
req = (struct hclge_cfg_param_cmd *)desc[0].data;
/* get the configuration */
- cfg->vmdq_vport_num = hnae_get_field(__le32_to_cpu(req->param[0]),
- HCLGE_CFG_VMDQ_M,
- HCLGE_CFG_VMDQ_S);
- cfg->tc_num = hnae_get_field(__le32_to_cpu(req->param[0]),
- HCLGE_CFG_TC_NUM_M, HCLGE_CFG_TC_NUM_S);
- cfg->tqp_desc_num = hnae_get_field(__le32_to_cpu(req->param[0]),
- HCLGE_CFG_TQP_DESC_N_M,
- HCLGE_CFG_TQP_DESC_N_S);
-
- cfg->phy_addr = hnae_get_field(__le32_to_cpu(req->param[1]),
- HCLGE_CFG_PHY_ADDR_M,
- HCLGE_CFG_PHY_ADDR_S);
- cfg->media_type = hnae_get_field(__le32_to_cpu(req->param[1]),
- HCLGE_CFG_MEDIA_TP_M,
- HCLGE_CFG_MEDIA_TP_S);
- cfg->rx_buf_len = hnae_get_field(__le32_to_cpu(req->param[1]),
- HCLGE_CFG_RX_BUF_LEN_M,
- HCLGE_CFG_RX_BUF_LEN_S);
+ cfg->vmdq_vport_num = hnae3_get_field(__le32_to_cpu(req->param[0]),
+ HCLGE_CFG_VMDQ_M,
+ HCLGE_CFG_VMDQ_S);
+ cfg->tc_num = hnae3_get_field(__le32_to_cpu(req->param[0]),
+ HCLGE_CFG_TC_NUM_M, HCLGE_CFG_TC_NUM_S);
+ cfg->tqp_desc_num = hnae3_get_field(__le32_to_cpu(req->param[0]),
+ HCLGE_CFG_TQP_DESC_N_M,
+ HCLGE_CFG_TQP_DESC_N_S);
+
+ cfg->phy_addr = hnae3_get_field(__le32_to_cpu(req->param[1]),
+ HCLGE_CFG_PHY_ADDR_M,
+ HCLGE_CFG_PHY_ADDR_S);
+ cfg->media_type = hnae3_get_field(__le32_to_cpu(req->param[1]),
+ HCLGE_CFG_MEDIA_TP_M,
+ HCLGE_CFG_MEDIA_TP_S);
+ cfg->rx_buf_len = hnae3_get_field(__le32_to_cpu(req->param[1]),
+ HCLGE_CFG_RX_BUF_LEN_M,
+ HCLGE_CFG_RX_BUF_LEN_S);
/* get mac_address */
mac_addr_tmp = __le32_to_cpu(req->param[2]);
- mac_addr_tmp_high = hnae_get_field(__le32_to_cpu(req->param[3]),
- HCLGE_CFG_MAC_ADDR_H_M,
- HCLGE_CFG_MAC_ADDR_H_S);
+ mac_addr_tmp_high = hnae3_get_field(__le32_to_cpu(req->param[3]),
+ HCLGE_CFG_MAC_ADDR_H_M,
+ HCLGE_CFG_MAC_ADDR_H_S);
mac_addr_tmp |= (mac_addr_tmp_high << 31) << 1;
- cfg->default_speed = hnae_get_field(__le32_to_cpu(req->param[3]),
- HCLGE_CFG_DEFAULT_SPEED_M,
- HCLGE_CFG_DEFAULT_SPEED_S);
- cfg->rss_size_max = hnae_get_field(__le32_to_cpu(req->param[3]),
- HCLGE_CFG_RSS_SIZE_M,
- HCLGE_CFG_RSS_SIZE_S);
+ cfg->default_speed = hnae3_get_field(__le32_to_cpu(req->param[3]),
+ HCLGE_CFG_DEFAULT_SPEED_M,
+ HCLGE_CFG_DEFAULT_SPEED_S);
+ cfg->rss_size_max = hnae3_get_field(__le32_to_cpu(req->param[3]),
+ HCLGE_CFG_RSS_SIZE_M,
+ HCLGE_CFG_RSS_SIZE_S);
for (i = 0; i < ETH_ALEN; i++)
cfg->mac_addr[i] = (mac_addr_tmp >> (8 * i)) & 0xff;
req = (struct hclge_cfg_param_cmd *)desc[1].data;
cfg->numa_node_map = __le32_to_cpu(req->param[0]);
- cfg->speed_ability = hnae_get_field(__le32_to_cpu(req->param[1]),
- HCLGE_CFG_SPEED_ABILITY_M,
- HCLGE_CFG_SPEED_ABILITY_S);
+ cfg->speed_ability = hnae3_get_field(__le32_to_cpu(req->param[1]),
+ HCLGE_CFG_SPEED_ABILITY_M,
+ HCLGE_CFG_SPEED_ABILITY_S);
}
/* hclge_get_cfg: query the static parameter from flash
req = (struct hclge_cfg_param_cmd *)desc[i].data;
hclge_cmd_setup_basic_desc(&desc[i], HCLGE_OPC_GET_CFG_PARAM,
true);
- hnae_set_field(offset, HCLGE_CFG_OFFSET_M,
- HCLGE_CFG_OFFSET_S, i * HCLGE_CFG_RD_LEN_BYTES);
+ hnae3_set_field(offset, HCLGE_CFG_OFFSET_M,
+ HCLGE_CFG_OFFSET_S, i * HCLGE_CFG_RD_LEN_BYTES);
/* Len should be united by 4 bytes when send to hardware */
- hnae_set_field(offset, HCLGE_CFG_RD_LEN_M, HCLGE_CFG_RD_LEN_S,
- HCLGE_CFG_RD_LEN_BYTES / HCLGE_CFG_RD_LEN_UNIT);
+ hnae3_set_field(offset, HCLGE_CFG_RD_LEN_M, HCLGE_CFG_RD_LEN_S,
+ HCLGE_CFG_RD_LEN_BYTES / HCLGE_CFG_RD_LEN_UNIT);
req->offset = cpu_to_le32(offset);
}
/* Currently not support uncontiuous tc */
for (i = 0; i < hdev->tm_info.num_tc; i++)
- hnae_set_bit(hdev->hw_tc_map, i, 1);
+ hnae3_set_bit(hdev->hw_tc_map, i, 1);
hdev->tx_sch_mode = HCLGE_FLAG_TC_BASE_SCH_MODE;
req = (struct hclge_cfg_tso_status_cmd *)desc.data;
tso_mss = 0;
- hnae_set_field(tso_mss, HCLGE_TSO_MSS_MIN_M,
- HCLGE_TSO_MSS_MIN_S, tso_mss_min);
+ hnae3_set_field(tso_mss, HCLGE_TSO_MSS_MIN_M,
+ HCLGE_TSO_MSS_MIN_S, tso_mss_min);
req->tso_mss_min = cpu_to_le16(tso_mss);
tso_mss = 0;
- hnae_set_field(tso_mss, HCLGE_TSO_MSS_MIN_M,
- HCLGE_TSO_MSS_MIN_S, tso_mss_max);
+ hnae3_set_field(tso_mss, HCLGE_TSO_MSS_MIN_M,
+ HCLGE_TSO_MSS_MIN_S, tso_mss_max);
req->tso_mss_max = cpu_to_le16(tso_mss);
return hclge_cmd_send(&hdev->hw, &desc, 1);
return 0;
}
-#define HCLGE_PRIV_ENABLE(a) ((a) > 0 ? 1 : 0)
-
static int hclge_rx_priv_wl_config(struct hclge_dev *hdev,
struct hclge_pkt_buf_alloc *buf_alloc)
{
req->tc_wl[j].high =
cpu_to_le16(priv->wl.high >> HCLGE_BUF_UNIT_S);
req->tc_wl[j].high |=
- cpu_to_le16(HCLGE_PRIV_ENABLE(priv->wl.high) <<
- HCLGE_RX_PRIV_EN_B);
+ cpu_to_le16(BIT(HCLGE_RX_PRIV_EN_B));
req->tc_wl[j].low =
cpu_to_le16(priv->wl.low >> HCLGE_BUF_UNIT_S);
req->tc_wl[j].low |=
- cpu_to_le16(HCLGE_PRIV_ENABLE(priv->wl.low) <<
- HCLGE_RX_PRIV_EN_B);
+ cpu_to_le16(BIT(HCLGE_RX_PRIV_EN_B));
}
}
req->com_thrd[j].high =
cpu_to_le16(tc->high >> HCLGE_BUF_UNIT_S);
req->com_thrd[j].high |=
- cpu_to_le16(HCLGE_PRIV_ENABLE(tc->high) <<
- HCLGE_RX_PRIV_EN_B);
+ cpu_to_le16(BIT(HCLGE_RX_PRIV_EN_B));
req->com_thrd[j].low =
cpu_to_le16(tc->low >> HCLGE_BUF_UNIT_S);
req->com_thrd[j].low |=
- cpu_to_le16(HCLGE_PRIV_ENABLE(tc->low) <<
- HCLGE_RX_PRIV_EN_B);
+ cpu_to_le16(BIT(HCLGE_RX_PRIV_EN_B));
}
}
req = (struct hclge_rx_com_wl *)desc.data;
req->com_wl.high = cpu_to_le16(buf->self.high >> HCLGE_BUF_UNIT_S);
- req->com_wl.high |=
- cpu_to_le16(HCLGE_PRIV_ENABLE(buf->self.high) <<
- HCLGE_RX_PRIV_EN_B);
+ req->com_wl.high |= cpu_to_le16(BIT(HCLGE_RX_PRIV_EN_B));
req->com_wl.low = cpu_to_le16(buf->self.low >> HCLGE_BUF_UNIT_S);
- req->com_wl.low |=
- cpu_to_le16(HCLGE_PRIV_ENABLE(buf->self.low) <<
- HCLGE_RX_PRIV_EN_B);
+ req->com_wl.low |= cpu_to_le16(BIT(HCLGE_RX_PRIV_EN_B));
ret = hclge_cmd_send(&hdev->hw, &desc, 1);
if (ret) {
hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_SPEED_DUP, false);
- hnae_set_bit(req->speed_dup, HCLGE_CFG_DUPLEX_B, !!duplex);
+ hnae3_set_bit(req->speed_dup, HCLGE_CFG_DUPLEX_B, !!duplex);
switch (speed) {
case HCLGE_MAC_SPEED_10M:
- hnae_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
- HCLGE_CFG_SPEED_S, 6);
+ hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
+ HCLGE_CFG_SPEED_S, 6);
break;
case HCLGE_MAC_SPEED_100M:
- hnae_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
- HCLGE_CFG_SPEED_S, 7);
+ hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
+ HCLGE_CFG_SPEED_S, 7);
break;
case HCLGE_MAC_SPEED_1G:
- hnae_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
- HCLGE_CFG_SPEED_S, 0);
+ hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
+ HCLGE_CFG_SPEED_S, 0);
break;
case HCLGE_MAC_SPEED_10G:
- hnae_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
- HCLGE_CFG_SPEED_S, 1);
+ hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
+ HCLGE_CFG_SPEED_S, 1);
break;
case HCLGE_MAC_SPEED_25G:
- hnae_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
- HCLGE_CFG_SPEED_S, 2);
+ hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
+ HCLGE_CFG_SPEED_S, 2);
break;
case HCLGE_MAC_SPEED_40G:
- hnae_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
- HCLGE_CFG_SPEED_S, 3);
+ hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
+ HCLGE_CFG_SPEED_S, 3);
break;
case HCLGE_MAC_SPEED_50G:
- hnae_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
- HCLGE_CFG_SPEED_S, 4);
+ hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
+ HCLGE_CFG_SPEED_S, 4);
break;
case HCLGE_MAC_SPEED_100G:
- hnae_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
- HCLGE_CFG_SPEED_S, 5);
+ hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
+ HCLGE_CFG_SPEED_S, 5);
break;
default:
dev_err(&hdev->pdev->dev, "invalid speed (%d)\n", speed);
return -EINVAL;
}
- hnae_set_bit(req->mac_change_fec_en, HCLGE_CFG_MAC_SPEED_CHANGE_EN_B,
- 1);
+ hnae3_set_bit(req->mac_change_fec_en, HCLGE_CFG_MAC_SPEED_CHANGE_EN_B,
+ 1);
ret = hclge_cmd_send(&hdev->hw, &desc, 1);
if (ret) {
return ret;
}
- *duplex = hnae_get_bit(req->an_syn_dup_speed, HCLGE_QUERY_DUPLEX_B);
- speed_tmp = hnae_get_field(req->an_syn_dup_speed, HCLGE_QUERY_SPEED_M,
- HCLGE_QUERY_SPEED_S);
+ *duplex = hnae3_get_bit(req->an_syn_dup_speed, HCLGE_QUERY_DUPLEX_B);
+ speed_tmp = hnae3_get_field(req->an_syn_dup_speed, HCLGE_QUERY_SPEED_M,
+ HCLGE_QUERY_SPEED_S);
ret = hclge_parse_speed(speed_tmp, speed);
if (ret) {
hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_AN_MODE, false);
req = (struct hclge_config_auto_neg_cmd *)desc.data;
- hnae_set_bit(flag, HCLGE_MAC_CFG_AN_EN_B, !!enable);
+ hnae3_set_bit(flag, HCLGE_MAC_CFG_AN_EN_B, !!enable);
req->cfg_an_cmd_flag = cpu_to_le32(flag);
ret = hclge_cmd_send(&hdev->hw, &desc, 1);
req = (struct hclge_mac_vlan_mask_entry_cmd *)desc.data;
hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MAC_VLAN_MASK_SET, false);
- hnae_set_bit(req->vlan_mask, HCLGE_VLAN_MASK_EN_B,
- mask_vlan ? 1 : 0);
+ hnae3_set_bit(req->vlan_mask, HCLGE_VLAN_MASK_EN_B,
+ mask_vlan ? 1 : 0);
ether_addr_copy(req->mac_mask, mac_mask);
status = hclge_cmd_send(&hdev->hw, &desc, 1);
u32 cmdq_src_reg;
/* fetch the events from their corresponding regs */
- rst_src_reg = hclge_read_dev(&hdev->hw, HCLGE_MISC_RESET_STS_REG);
+ rst_src_reg = hclge_read_dev(&hdev->hw, HCLGE_MISC_VECTOR_INT_STS);
cmdq_src_reg = hclge_read_dev(&hdev->hw, HCLGE_VECTOR0_CMDQ_SRC_REG);
/* Assumption: If by any chance reset and mailbox events are reported
/* check for vector0 reset event sources */
if (BIT(HCLGE_VECTOR0_GLOBALRESET_INT_B) & rst_src_reg) {
+ set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
set_bit(HNAE3_GLOBAL_RESET, &hdev->reset_pending);
*clearval = BIT(HCLGE_VECTOR0_GLOBALRESET_INT_B);
return HCLGE_VECTOR0_EVENT_RST;
}
if (BIT(HCLGE_VECTOR0_CORERESET_INT_B) & rst_src_reg) {
+ set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
set_bit(HNAE3_CORE_RESET, &hdev->reset_pending);
*clearval = BIT(HCLGE_VECTOR0_CORERESET_INT_B);
return HCLGE_VECTOR0_EVENT_RST;
static void hclge_free_vector(struct hclge_dev *hdev, int vector_id)
{
+ if (hdev->vector_status[vector_id] == HCLGE_INVALID_VPORT) {
+ dev_warn(&hdev->pdev->dev,
+ "vector(vector_id %d) has been freed.\n", vector_id);
+ return;
+ }
+
hdev->vector_status[vector_id] = HCLGE_INVALID_VPORT;
hdev->num_msi_left += 1;
hdev->num_msi_used -= 1;
}
val = hclge_read_dev(&hdev->hw, reg);
- while (hnae_get_bit(val, reg_bit) && cnt < HCLGE_RESET_WAIT_CNT) {
+ while (hnae3_get_bit(val, reg_bit) && cnt < HCLGE_RESET_WAIT_CNT) {
msleep(HCLGE_RESET_WATI_MS);
val = hclge_read_dev(&hdev->hw, reg);
cnt++;
int ret;
hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CFG_RST_TRIGGER, false);
- hnae_set_bit(req->mac_func_reset, HCLGE_CFG_RESET_MAC_B, 0);
- hnae_set_bit(req->mac_func_reset, HCLGE_CFG_RESET_FUNC_B, 1);
+ hnae3_set_bit(req->mac_func_reset, HCLGE_CFG_RESET_FUNC_B, 1);
req->fun_reset_vfid = func_id;
ret = hclge_cmd_send(&hdev->hw, &desc, 1);
switch (hdev->reset_type) {
case HNAE3_GLOBAL_RESET:
val = hclge_read_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG);
- hnae_set_bit(val, HCLGE_GLOBAL_RESET_BIT, 1);
+ hnae3_set_bit(val, HCLGE_GLOBAL_RESET_BIT, 1);
hclge_write_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG, val);
dev_info(&pdev->dev, "Global Reset requested\n");
break;
case HNAE3_CORE_RESET:
val = hclge_read_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG);
- hnae_set_bit(val, HCLGE_CORE_RESET_BIT, 1);
+ hnae3_set_bit(val, HCLGE_CORE_RESET_BIT, 1);
hclge_write_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG, val);
dev_info(&pdev->dev, "Core Reset requested\n");
break;
clearval = BIT(HCLGE_VECTOR0_CORERESET_INT_B);
break;
default:
- dev_warn(&hdev->pdev->dev, "Unsupported reset event to clear:%d",
- hdev->reset_type);
break;
}
static void hclge_reset(struct hclge_dev *hdev)
{
- /* perform reset of the stack & ae device for a client */
+ struct hnae3_handle *handle;
+ /* perform reset of the stack & ae device for a client */
+ handle = &hdev->vport[0].nic;
+ rtnl_lock();
hclge_notify_client(hdev, HNAE3_DOWN_CLIENT);
if (!hclge_reset_wait(hdev)) {
- rtnl_lock();
hclge_notify_client(hdev, HNAE3_UNINIT_CLIENT);
hclge_reset_ae_dev(hdev->ae_dev);
hclge_notify_client(hdev, HNAE3_INIT_CLIENT);
- rtnl_unlock();
hclge_clear_reset_cause(hdev);
} else {
}
hclge_notify_client(hdev, HNAE3_UP_CLIENT);
+ handle->last_reset_time = jiffies;
+ rtnl_unlock();
}
static void hclge_reset_event(struct hnae3_handle *handle)
* know this if last reset request did not occur very recently (watchdog
* timer = 5*HZ, let us check after sufficiently large time, say 4*5*Hz)
* In case of new request we reset the "reset level" to PF reset.
+ * And if it is a repeat reset request of the most recent one then we
+ * want to make sure we throttle the reset request. Therefore, we will
+ * not allow it again before 3*HZ times.
*/
- if (time_after(jiffies, (handle->last_reset_time + 4 * 5 * HZ)))
+ if (time_before(jiffies, (handle->last_reset_time + 3 * HZ)))
+ return;
+ else if (time_after(jiffies, (handle->last_reset_time + 4 * 5 * HZ)))
handle->reset_level = HNAE3_FUNC_RESET;
dev_info(&hdev->pdev->dev, "received reset event , reset type is %d",
if (handle->reset_level < HNAE3_GLOBAL_RESET)
handle->reset_level++;
-
- handle->last_reset_time = jiffies;
}
static void hclge_reset_subtask(struct hclge_dev *hdev)
for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
u16 mode = 0;
- hnae_set_bit(mode, HCLGE_RSS_TC_VALID_B, (tc_valid[i] & 0x1));
- hnae_set_field(mode, HCLGE_RSS_TC_SIZE_M,
- HCLGE_RSS_TC_SIZE_S, tc_size[i]);
- hnae_set_field(mode, HCLGE_RSS_TC_OFFSET_M,
- HCLGE_RSS_TC_OFFSET_S, tc_offset[i]);
+ hnae3_set_bit(mode, HCLGE_RSS_TC_VALID_B, (tc_valid[i] & 0x1));
+ hnae3_set_field(mode, HCLGE_RSS_TC_SIZE_M,
+ HCLGE_RSS_TC_SIZE_S, tc_size[i]);
+ hnae3_set_field(mode, HCLGE_RSS_TC_OFFSET_M,
+ HCLGE_RSS_TC_OFFSET_S, tc_offset[i]);
req->rss_tc_mode[i] = cpu_to_le16(mode);
}
i = 0;
for (node = ring_chain; node; node = node->next) {
tqp_type_and_id = le16_to_cpu(req->tqp_type_and_id[i]);
- hnae_set_field(tqp_type_and_id, HCLGE_INT_TYPE_M,
- HCLGE_INT_TYPE_S,
- hnae_get_bit(node->flag, HNAE3_RING_TYPE_B));
- hnae_set_field(tqp_type_and_id, HCLGE_TQP_ID_M,
- HCLGE_TQP_ID_S, node->tqp_index);
- hnae_set_field(tqp_type_and_id, HCLGE_INT_GL_IDX_M,
- HCLGE_INT_GL_IDX_S,
- hnae_get_field(node->int_gl_idx,
- HNAE3_RING_GL_IDX_M,
- HNAE3_RING_GL_IDX_S));
+ hnae3_set_field(tqp_type_and_id, HCLGE_INT_TYPE_M,
+ HCLGE_INT_TYPE_S,
+ hnae3_get_bit(node->flag, HNAE3_RING_TYPE_B));
+ hnae3_set_field(tqp_type_and_id, HCLGE_TQP_ID_M,
+ HCLGE_TQP_ID_S, node->tqp_index);
+ hnae3_set_field(tqp_type_and_id, HCLGE_INT_GL_IDX_M,
+ HCLGE_INT_GL_IDX_S,
+ hnae3_get_field(node->int_gl_idx,
+ HNAE3_RING_GL_IDX_M,
+ HNAE3_RING_GL_IDX_S));
req->tqp_type_and_id[i] = cpu_to_le16(tqp_type_and_id);
if (++i >= HCLGE_VECTOR_ELEMENTS_PER_CMD) {
req->int_cause_num = HCLGE_VECTOR_ELEMENTS_PER_CMD;
int ret;
hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_MAC_MODE, false);
- hnae_set_bit(loop_en, HCLGE_MAC_TX_EN_B, enable);
- hnae_set_bit(loop_en, HCLGE_MAC_RX_EN_B, enable);
- hnae_set_bit(loop_en, HCLGE_MAC_PAD_TX_B, enable);
- hnae_set_bit(loop_en, HCLGE_MAC_PAD_RX_B, enable);
- hnae_set_bit(loop_en, HCLGE_MAC_1588_TX_B, 0);
- hnae_set_bit(loop_en, HCLGE_MAC_1588_RX_B, 0);
- hnae_set_bit(loop_en, HCLGE_MAC_APP_LP_B, 0);
- hnae_set_bit(loop_en, HCLGE_MAC_LINE_LP_B, 0);
- hnae_set_bit(loop_en, HCLGE_MAC_FCS_TX_B, enable);
- hnae_set_bit(loop_en, HCLGE_MAC_RX_FCS_B, enable);
- hnae_set_bit(loop_en, HCLGE_MAC_RX_FCS_STRIP_B, enable);
- hnae_set_bit(loop_en, HCLGE_MAC_TX_OVERSIZE_TRUNCATE_B, enable);
- hnae_set_bit(loop_en, HCLGE_MAC_RX_OVERSIZE_TRUNCATE_B, enable);
- hnae_set_bit(loop_en, HCLGE_MAC_TX_UNDER_MIN_ERR_B, enable);
+ hnae3_set_bit(loop_en, HCLGE_MAC_TX_EN_B, enable);
+ hnae3_set_bit(loop_en, HCLGE_MAC_RX_EN_B, enable);
+ hnae3_set_bit(loop_en, HCLGE_MAC_PAD_TX_B, enable);
+ hnae3_set_bit(loop_en, HCLGE_MAC_PAD_RX_B, enable);
+ hnae3_set_bit(loop_en, HCLGE_MAC_1588_TX_B, 0);
+ hnae3_set_bit(loop_en, HCLGE_MAC_1588_RX_B, 0);
+ hnae3_set_bit(loop_en, HCLGE_MAC_APP_LP_B, 0);
+ hnae3_set_bit(loop_en, HCLGE_MAC_LINE_LP_B, 0);
+ hnae3_set_bit(loop_en, HCLGE_MAC_FCS_TX_B, enable);
+ hnae3_set_bit(loop_en, HCLGE_MAC_RX_FCS_B, enable);
+ hnae3_set_bit(loop_en, HCLGE_MAC_RX_FCS_STRIP_B, enable);
+ hnae3_set_bit(loop_en, HCLGE_MAC_TX_OVERSIZE_TRUNCATE_B, enable);
+ hnae3_set_bit(loop_en, HCLGE_MAC_RX_OVERSIZE_TRUNCATE_B, enable);
+ hnae3_set_bit(loop_en, HCLGE_MAC_TX_UNDER_MIN_ERR_B, enable);
req->txrx_pad_fcs_loop_en = cpu_to_le32(loop_en);
ret = hclge_cmd_send(&hdev->hw, &desc, 1);
/* 2 Then setup the loopback flag */
loop_en = le32_to_cpu(req->txrx_pad_fcs_loop_en);
- hnae_set_bit(loop_en, HCLGE_MAC_APP_LP_B, en ? 1 : 0);
+ hnae3_set_bit(loop_en, HCLGE_MAC_APP_LP_B, en ? 1 : 0);
req->txrx_pad_fcs_loop_en = cpu_to_le32(loop_en);
req = (struct hclge_mta_filter_mode_cmd *)desc.data;
hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MTA_MAC_MODE_CFG, false);
- hnae_set_bit(req->dmac_sel_en, HCLGE_CFG_MTA_MAC_EN_B,
- enable);
- hnae_set_field(req->dmac_sel_en, HCLGE_CFG_MTA_MAC_SEL_M,
- HCLGE_CFG_MTA_MAC_SEL_S, mta_mac_sel);
+ hnae3_set_bit(req->dmac_sel_en, HCLGE_CFG_MTA_MAC_EN_B,
+ enable);
+ hnae3_set_field(req->dmac_sel_en, HCLGE_CFG_MTA_MAC_SEL_M,
+ HCLGE_CFG_MTA_MAC_SEL_S, mta_mac_sel);
ret = hclge_cmd_send(&hdev->hw, &desc, 1);
if (ret) {
req = (struct hclge_cfg_func_mta_filter_cmd *)desc.data;
hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MTA_MAC_FUNC_CFG, false);
- hnae_set_bit(req->accept, HCLGE_CFG_FUNC_MTA_ACCEPT_B,
- enable);
+ hnae3_set_bit(req->accept, HCLGE_CFG_FUNC_MTA_ACCEPT_B,
+ enable);
req->function_id = func_id;
ret = hclge_cmd_send(&hdev->hw, &desc, 1);
req = (struct hclge_cfg_func_mta_item_cmd *)desc.data;
hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MTA_TBL_ITEM_CFG, false);
- hnae_set_bit(req->accept, HCLGE_CFG_MTA_ITEM_ACCEPT_B, enable);
+ hnae3_set_bit(req->accept, HCLGE_CFG_MTA_ITEM_ACCEPT_B, enable);
- hnae_set_field(item_idx, HCLGE_CFG_MTA_ITEM_IDX_M,
- HCLGE_CFG_MTA_ITEM_IDX_S, idx);
+ hnae3_set_field(item_idx, HCLGE_CFG_MTA_ITEM_IDX_M,
+ HCLGE_CFG_MTA_ITEM_IDX_S, idx);
req->item_idx = cpu_to_le16(item_idx);
ret = hclge_cmd_send(&hdev->hw, &desc, 1);
}
memset(&req, 0, sizeof(req));
- hnae_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1);
- hnae_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
- hnae_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT1_EN_B, 0);
- hnae_set_bit(req.mc_mac_en, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
-
- hnae_set_bit(egress_port, HCLGE_MAC_EPORT_SW_EN_B, 0);
- hnae_set_bit(egress_port, HCLGE_MAC_EPORT_TYPE_B, 0);
- hnae_set_field(egress_port, HCLGE_MAC_EPORT_VFID_M,
- HCLGE_MAC_EPORT_VFID_S, vport->vport_id);
- hnae_set_field(egress_port, HCLGE_MAC_EPORT_PFID_M,
- HCLGE_MAC_EPORT_PFID_S, 0);
+ hnae3_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1);
+
+ hnae3_set_field(egress_port, HCLGE_MAC_EPORT_VFID_M,
+ HCLGE_MAC_EPORT_VFID_S, vport->vport_id);
req.egress_port = cpu_to_le16(egress_port);
}
memset(&req, 0, sizeof(req));
- hnae_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1);
- hnae_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
+ hnae3_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1);
+ hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
hclge_prepare_mac_addr(&req, addr);
ret = hclge_remove_mac_vlan_tbl(vport, &req);
return -EINVAL;
}
memset(&req, 0, sizeof(req));
- hnae_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1);
- hnae_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
- hnae_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT1_EN_B, 1);
- hnae_set_bit(req.mc_mac_en, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
+ hnae3_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1);
+ hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
+ hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT1_EN_B, 1);
+ hnae3_set_bit(req.mc_mac_en, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
hclge_prepare_mac_addr(&req, addr);
status = hclge_lookup_mac_vlan_tbl(vport, &req, desc, true);
if (!status) {
}
memset(&req, 0, sizeof(req));
- hnae_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1);
- hnae_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
- hnae_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT1_EN_B, 1);
- hnae_set_bit(req.mc_mac_en, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
+ hnae3_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1);
+ hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
+ hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT1_EN_B, 1);
+ hnae3_set_bit(req.mc_mac_en, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
hclge_prepare_mac_addr(&req, addr);
status = hclge_lookup_mac_vlan_tbl(vport, &req, desc, true);
if (!status) {
req = (struct hclge_vport_vtag_tx_cfg_cmd *)desc.data;
req->def_vlan_tag1 = cpu_to_le16(vcfg->default_tag1);
req->def_vlan_tag2 = cpu_to_le16(vcfg->default_tag2);
- hnae_set_bit(req->vport_vlan_cfg, HCLGE_ACCEPT_TAG1_B,
- vcfg->accept_tag1 ? 1 : 0);
- hnae_set_bit(req->vport_vlan_cfg, HCLGE_ACCEPT_UNTAG1_B,
- vcfg->accept_untag1 ? 1 : 0);
- hnae_set_bit(req->vport_vlan_cfg, HCLGE_ACCEPT_TAG2_B,
- vcfg->accept_tag2 ? 1 : 0);
- hnae_set_bit(req->vport_vlan_cfg, HCLGE_ACCEPT_UNTAG2_B,
- vcfg->accept_untag2 ? 1 : 0);
- hnae_set_bit(req->vport_vlan_cfg, HCLGE_PORT_INS_TAG1_EN_B,
- vcfg->insert_tag1_en ? 1 : 0);
- hnae_set_bit(req->vport_vlan_cfg, HCLGE_PORT_INS_TAG2_EN_B,
- vcfg->insert_tag2_en ? 1 : 0);
- hnae_set_bit(req->vport_vlan_cfg, HCLGE_CFG_NIC_ROCE_SEL_B, 0);
+ hnae3_set_bit(req->vport_vlan_cfg, HCLGE_ACCEPT_TAG1_B,
+ vcfg->accept_tag1 ? 1 : 0);
+ hnae3_set_bit(req->vport_vlan_cfg, HCLGE_ACCEPT_UNTAG1_B,
+ vcfg->accept_untag1 ? 1 : 0);
+ hnae3_set_bit(req->vport_vlan_cfg, HCLGE_ACCEPT_TAG2_B,
+ vcfg->accept_tag2 ? 1 : 0);
+ hnae3_set_bit(req->vport_vlan_cfg, HCLGE_ACCEPT_UNTAG2_B,
+ vcfg->accept_untag2 ? 1 : 0);
+ hnae3_set_bit(req->vport_vlan_cfg, HCLGE_PORT_INS_TAG1_EN_B,
+ vcfg->insert_tag1_en ? 1 : 0);
+ hnae3_set_bit(req->vport_vlan_cfg, HCLGE_PORT_INS_TAG2_EN_B,
+ vcfg->insert_tag2_en ? 1 : 0);
+ hnae3_set_bit(req->vport_vlan_cfg, HCLGE_CFG_NIC_ROCE_SEL_B, 0);
req->vf_offset = vport->vport_id / HCLGE_VF_NUM_PER_CMD;
req->vf_bitmap[req->vf_offset] =
hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_VLAN_PORT_RX_CFG, false);
req = (struct hclge_vport_vtag_rx_cfg_cmd *)desc.data;
- hnae_set_bit(req->vport_vlan_cfg, HCLGE_REM_TAG1_EN_B,
- vcfg->strip_tag1_en ? 1 : 0);
- hnae_set_bit(req->vport_vlan_cfg, HCLGE_REM_TAG2_EN_B,
- vcfg->strip_tag2_en ? 1 : 0);
- hnae_set_bit(req->vport_vlan_cfg, HCLGE_SHOW_TAG1_EN_B,
- vcfg->vlan1_vlan_prionly ? 1 : 0);
- hnae_set_bit(req->vport_vlan_cfg, HCLGE_SHOW_TAG2_EN_B,
- vcfg->vlan2_vlan_prionly ? 1 : 0);
+ hnae3_set_bit(req->vport_vlan_cfg, HCLGE_REM_TAG1_EN_B,
+ vcfg->strip_tag1_en ? 1 : 0);
+ hnae3_set_bit(req->vport_vlan_cfg, HCLGE_REM_TAG2_EN_B,
+ vcfg->strip_tag2_en ? 1 : 0);
+ hnae3_set_bit(req->vport_vlan_cfg, HCLGE_SHOW_TAG1_EN_B,
+ vcfg->vlan1_vlan_prionly ? 1 : 0);
+ hnae3_set_bit(req->vport_vlan_cfg, HCLGE_SHOW_TAG2_EN_B,
+ vcfg->vlan2_vlan_prionly ? 1 : 0);
req->vf_offset = vport->vport_id / HCLGE_VF_NUM_PER_CMD;
req->vf_bitmap[req->vf_offset] =
req = (struct hclge_config_max_frm_size_cmd *)desc.data;
req->max_frm_size = cpu_to_le16(max_frm_size);
+ req->min_frm_size = HCLGE_MAC_MIN_FRAME;
ret = hclge_cmd_send(&hdev->hw, &desc, 1);
if (ret) {
req = (struct hclge_reset_tqp_queue_cmd *)desc.data;
req->tqp_id = cpu_to_le16(queue_id & HCLGE_RING_ID_MASK);
- hnae_set_bit(req->reset_req, HCLGE_TQP_RESET_B, enable);
+ hnae3_set_bit(req->reset_req, HCLGE_TQP_RESET_B, enable);
ret = hclge_cmd_send(&hdev->hw, &desc, 1);
if (ret) {
return ret;
}
- return hnae_get_bit(req->ready_to_reset, HCLGE_TQP_RESET_B);
+ return hnae3_get_bit(req->ready_to_reset, HCLGE_TQP_RESET_B);
}
static u16 hclge_covert_handle_qid_global(struct hnae3_handle *handle,
phy_write(phydev, HCLGE_PHY_PAGE_REG, HCLGE_PHY_PAGE_MDIX);
retval = phy_read(phydev, HCLGE_PHY_CSC_REG);
- mdix_ctrl = hnae_get_field(retval, HCLGE_PHY_MDIX_CTRL_M,
- HCLGE_PHY_MDIX_CTRL_S);
+ mdix_ctrl = hnae3_get_field(retval, HCLGE_PHY_MDIX_CTRL_M,
+ HCLGE_PHY_MDIX_CTRL_S);
retval = phy_read(phydev, HCLGE_PHY_CSS_REG);
- mdix = hnae_get_bit(retval, HCLGE_PHY_MDIX_STATUS_B);
- is_resolved = hnae_get_bit(retval, HCLGE_PHY_SPEED_DUP_RESOLVE_B);
+ mdix = hnae3_get_bit(retval, HCLGE_PHY_MDIX_STATUS_B);
+ is_resolved = hnae3_get_bit(retval, HCLGE_PHY_SPEED_DUP_RESOLVE_B);
phy_write(phydev, HCLGE_PHY_PAGE_REG, HCLGE_PHY_PAGE_COPPER);
pci_set_master(pdev);
hw = &hdev->hw;
- hw->back = hdev;
hw->io_base = pcim_iomap(pdev, 2, 0);
if (!hw->io_base) {
dev_err(&pdev->dev, "Can't map configuration register space\n");
pci_disable_device(pdev);
}
+static void hclge_state_init(struct hclge_dev *hdev)
+{
+ set_bit(HCLGE_STATE_SERVICE_INITED, &hdev->state);
+ set_bit(HCLGE_STATE_DOWN, &hdev->state);
+ clear_bit(HCLGE_STATE_RST_SERVICE_SCHED, &hdev->state);
+ clear_bit(HCLGE_STATE_RST_HANDLING, &hdev->state);
+ clear_bit(HCLGE_STATE_MBX_SERVICE_SCHED, &hdev->state);
+ clear_bit(HCLGE_STATE_MBX_HANDLING, &hdev->state);
+}
+
+static void hclge_state_uninit(struct hclge_dev *hdev)
+{
+ set_bit(HCLGE_STATE_DOWN, &hdev->state);
+
+ if (hdev->service_timer.function)
+ del_timer_sync(&hdev->service_timer);
+ if (hdev->service_task.func)
+ cancel_work_sync(&hdev->service_task);
+ if (hdev->rst_service_task.func)
+ cancel_work_sync(&hdev->rst_service_task);
+ if (hdev->mbx_service_task.func)
+ cancel_work_sync(&hdev->mbx_service_task);
+}
+
static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
{
struct pci_dev *pdev = ae_dev->pdev;
/* Enable MISC vector(vector0) */
hclge_enable_vector(&hdev->misc_vector, true);
- set_bit(HCLGE_STATE_SERVICE_INITED, &hdev->state);
- set_bit(HCLGE_STATE_DOWN, &hdev->state);
- clear_bit(HCLGE_STATE_RST_SERVICE_SCHED, &hdev->state);
- clear_bit(HCLGE_STATE_RST_HANDLING, &hdev->state);
- clear_bit(HCLGE_STATE_MBX_SERVICE_SCHED, &hdev->state);
- clear_bit(HCLGE_STATE_MBX_HANDLING, &hdev->state);
+ hclge_state_init(hdev);
pr_info("%s driver initialization finished.\n", HCLGE_DRIVER_NAME);
return 0;
struct hclge_dev *hdev = ae_dev->priv;
struct hclge_mac *mac = &hdev->hw.mac;
- set_bit(HCLGE_STATE_DOWN, &hdev->state);
-
- if (hdev->service_timer.function)
- del_timer_sync(&hdev->service_timer);
- if (hdev->service_task.func)
- cancel_work_sync(&hdev->service_task);
- if (hdev->rst_service_task.func)
- cancel_work_sync(&hdev->rst_service_task);
- if (hdev->mbx_service_task.func)
- cancel_work_sync(&hdev->mbx_service_task);
+ hclge_state_uninit(hdev);
if (mac->phydev)
mdiobus_unregister(mac->mdio_bus);
hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_LED_STATUS_CFG, false);
req = (struct hclge_set_led_state_cmd *)desc.data;
- hnae_set_field(req->locate_led_config, HCLGE_LED_LOCATE_STATE_M,
- HCLGE_LED_LOCATE_STATE_S, locate_led_status);
+ hnae3_set_field(req->locate_led_config, HCLGE_LED_LOCATE_STATE_M,
+ HCLGE_LED_LOCATE_STATE_S, locate_led_status);
ret = hclge_cmd_send(&hdev->hw, &desc, 1);
if (ret)
static struct hnae3_ae_algo ae_algo = {
.ops = &hclge_ops,
- .name = HCLGE_NAME,
.pdev_id_table = ae_algo_pci_tbl,
};
/* Reset related Registers */
#define HCLGE_MISC_RESET_STS_REG 0x20700
+#define HCLGE_MISC_VECTOR_INT_STS 0x20800
#define HCLGE_GLOBAL_RESET_REG 0x20A00
#define HCLGE_GLOBAL_RESET_BIT 0x0
#define HCLGE_CORE_RESET_BIT 0x1
HCLGE_STATE_MBX_SERVICE_SCHED,
HCLGE_STATE_MBX_HANDLING,
HCLGE_STATE_STATISTICS_UPDATING,
+ HCLGE_STATE_CMD_DISABLE,
HCLGE_STATE_MAX
};
int num_vec;
struct hclge_cmq cmq;
struct hclge_caps caps;
- void *back;
};
/* TQP stats */
}
}
-/* hclge_get_ring_chain_from_mbx: get ring type & tqpid from mailbox message
+/* hclge_get_ring_chain_from_mbx: get ring type & tqp id & int_gl idx
+ * from mailbox message
* msg[0]: opcode
* msg[1]: <not relevant to this function>
* msg[2]: ring_num
* msg[3]: first ring type (TX|RX)
* msg[4]: first tqp id
- * msg[5] ~ msg[14]: other ring type and tqp id
+ * msg[5]: first int_gl idx
+ * msg[6] ~ msg[14]: other ring type, tqp id and int_gl idx
*/
static int hclge_get_ring_chain_from_mbx(
struct hclge_mbx_vf_to_pf_cmd *req,
HCLGE_MBX_RING_NODE_VARIABLE_NUM))
return -ENOMEM;
- hnae_set_bit(ring_chain->flag, HNAE3_RING_TYPE_B, req->msg[3]);
+ hnae3_set_bit(ring_chain->flag, HNAE3_RING_TYPE_B, req->msg[3]);
ring_chain->tqp_index =
hclge_get_queue_id(vport->nic.kinfo.tqp[req->msg[4]]);
- hnae_set_field(ring_chain->int_gl_idx, HCLGE_INT_GL_IDX_M,
- HCLGE_INT_GL_IDX_S,
- req->msg[5]);
+ hnae3_set_field(ring_chain->int_gl_idx, HNAE3_RING_GL_IDX_M,
+ HNAE3_RING_GL_IDX_S,
+ req->msg[5]);
cur_chain = ring_chain;
if (!new_chain)
goto err;
- hnae_set_bit(new_chain->flag, HNAE3_RING_TYPE_B,
- req->msg[HCLGE_MBX_RING_NODE_VARIABLE_NUM * i +
- HCLGE_MBX_RING_MAP_BASIC_MSG_NUM]);
+ hnae3_set_bit(new_chain->flag, HNAE3_RING_TYPE_B,
+ req->msg[HCLGE_MBX_RING_NODE_VARIABLE_NUM * i +
+ HCLGE_MBX_RING_MAP_BASIC_MSG_NUM]);
new_chain->tqp_index =
hclge_get_queue_id(vport->nic.kinfo.tqp
[req->msg[HCLGE_MBX_RING_NODE_VARIABLE_NUM * i +
HCLGE_MBX_RING_MAP_BASIC_MSG_NUM + 1]]);
- hnae_set_field(new_chain->int_gl_idx, HCLGE_INT_GL_IDX_M,
- HCLGE_INT_GL_IDX_S,
- req->msg[HCLGE_MBX_RING_NODE_VARIABLE_NUM * i +
- HCLGE_MBX_RING_MAP_BASIC_MSG_NUM + 2]);
+ hnae3_set_field(new_chain->int_gl_idx, HNAE3_RING_GL_IDX_M,
+ HNAE3_RING_GL_IDX_S,
+ req->msg[HCLGE_MBX_RING_NODE_VARIABLE_NUM * i +
+ HCLGE_MBX_RING_MAP_BASIC_MSG_NUM + 2]);
cur_chain->next = new_chain;
cur_chain = new_chain;
req = (struct hclge_mbx_vf_to_pf_cmd *)desc->data;
flag = le16_to_cpu(crq->desc[crq->next_to_use].flag);
- if (unlikely(!hnae_get_bit(flag, HCLGE_CMDQ_RX_OUTVLD_B))) {
+ if (unlikely(!hnae3_get_bit(flag, HCLGE_CMDQ_RX_OUTVLD_B))) {
dev_warn(&hdev->pdev->dev,
"dropped invalid mailbox message, code = %d\n",
req->msg[0]);
mdio_cmd = (struct hclge_mdio_cfg_cmd *)desc.data;
- hnae_set_field(mdio_cmd->phyid, HCLGE_MDIO_PHYID_M,
- HCLGE_MDIO_PHYID_S, phyid);
- hnae_set_field(mdio_cmd->phyad, HCLGE_MDIO_PHYREG_M,
- HCLGE_MDIO_PHYREG_S, regnum);
+ hnae3_set_field(mdio_cmd->phyid, HCLGE_MDIO_PHYID_M,
+ HCLGE_MDIO_PHYID_S, phyid);
+ hnae3_set_field(mdio_cmd->phyad, HCLGE_MDIO_PHYREG_M,
+ HCLGE_MDIO_PHYREG_S, regnum);
- hnae_set_bit(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_START_B, 1);
- hnae_set_field(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_ST_M,
- HCLGE_MDIO_CTRL_ST_S, 1);
- hnae_set_field(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_OP_M,
- HCLGE_MDIO_CTRL_OP_S, HCLGE_MDIO_C22_WRITE);
+ hnae3_set_bit(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_START_B, 1);
+ hnae3_set_field(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_ST_M,
+ HCLGE_MDIO_CTRL_ST_S, 1);
+ hnae3_set_field(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_OP_M,
+ HCLGE_MDIO_CTRL_OP_S, HCLGE_MDIO_C22_WRITE);
mdio_cmd->data_wr = cpu_to_le16(data);
mdio_cmd = (struct hclge_mdio_cfg_cmd *)desc.data;
- hnae_set_field(mdio_cmd->phyid, HCLGE_MDIO_PHYID_M,
- HCLGE_MDIO_PHYID_S, phyid);
- hnae_set_field(mdio_cmd->phyad, HCLGE_MDIO_PHYREG_M,
- HCLGE_MDIO_PHYREG_S, regnum);
+ hnae3_set_field(mdio_cmd->phyid, HCLGE_MDIO_PHYID_M,
+ HCLGE_MDIO_PHYID_S, phyid);
+ hnae3_set_field(mdio_cmd->phyad, HCLGE_MDIO_PHYREG_M,
+ HCLGE_MDIO_PHYREG_S, regnum);
- hnae_set_bit(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_START_B, 1);
- hnae_set_field(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_ST_M,
- HCLGE_MDIO_CTRL_ST_S, 1);
- hnae_set_field(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_OP_M,
- HCLGE_MDIO_CTRL_OP_S, HCLGE_MDIO_C22_READ);
+ hnae3_set_bit(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_START_B, 1);
+ hnae3_set_field(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_ST_M,
+ HCLGE_MDIO_CTRL_ST_S, 1);
+ hnae3_set_field(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_OP_M,
+ HCLGE_MDIO_CTRL_OP_S, HCLGE_MDIO_C22_READ);
/* Read out phy data */
ret = hclge_cmd_send(&hdev->hw, &desc, 1);
return ret;
}
- if (hnae_get_bit(le16_to_cpu(mdio_cmd->sta), HCLGE_MDIO_STA_B)) {
+ if (hnae3_get_bit(le16_to_cpu(mdio_cmd->sta), HCLGE_MDIO_STA_B)) {
dev_err(&hdev->pdev->dev, "mdio read data error\n");
return -EIO;
}
u16 qs_id = vport->qs_offset + tc;
u8 grp, sub_grp;
- grp = hnae_get_field(qs_id, HCLGE_BP_GRP_ID_M,
- HCLGE_BP_GRP_ID_S);
- sub_grp = hnae_get_field(qs_id, HCLGE_BP_SUB_GRP_ID_M,
- HCLGE_BP_SUB_GRP_ID_S);
+ grp = hnae3_get_field(qs_id, HCLGE_BP_GRP_ID_M,
+ HCLGE_BP_GRP_ID_S);
+ sub_grp = hnae3_get_field(qs_id, HCLGE_BP_SUB_GRP_ID_M,
+ HCLGE_BP_SUB_GRP_ID_S);
if (i == grp)
qs_bitmap |= (1 << sub_grp);
tx_en = true;
rx_en = true;
break;
+ case HCLGE_FC_PFC:
+ tx_en = false;
+ rx_en = false;
+ break;
default:
tx_en = true;
rx_en = true;
if (ret)
return ret;
- if (hdev->tm_info.fc_mode != HCLGE_FC_PFC)
- return hclge_mac_pause_setup_hw(hdev);
+ ret = hclge_mac_pause_setup_hw(hdev);
+ if (ret)
+ return ret;
/* Only DCB-supported dev supports qset back pressure and pfc cmd */
if (!hnae3_dev_dcb_supported(hdev))
};
#define hclge_tm_set_field(dest, string, val) \
- hnae_set_field((dest), (HCLGE_TM_SHAP_##string##_MSK), \
- (HCLGE_TM_SHAP_##string##_LSH), val)
+ hnae3_set_field((dest), \
+ (HCLGE_TM_SHAP_##string##_MSK), \
+ (HCLGE_TM_SHAP_##string##_LSH), val)
#define hclge_tm_get_field(src, string) \
- hnae_get_field((src), (HCLGE_TM_SHAP_##string##_MSK), \
+ hnae3_get_field((src), (HCLGE_TM_SHAP_##string##_MSK), \
(HCLGE_TM_SHAP_##string##_LSH))
int hclge_tm_schd_init(struct hclge_dev *hdev);
{
int size = ring->desc_num * sizeof(struct hclgevf_desc);
- ring->desc = kzalloc(size, GFP_KERNEL);
+ ring->desc = dma_zalloc_coherent(cmq_ring_to_dev(ring),
+ size, &ring->desc_dma_addr,
+ GFP_KERNEL);
if (!ring->desc)
return -ENOMEM;
- ring->desc_dma_addr = dma_map_single(cmq_ring_to_dev(ring), ring->desc,
- size, DMA_BIDIRECTIONAL);
-
- if (dma_mapping_error(cmq_ring_to_dev(ring), ring->desc_dma_addr)) {
- ring->desc_dma_addr = 0;
- kfree(ring->desc);
- ring->desc = NULL;
- return -ENOMEM;
- }
-
return 0;
}
static void hclgevf_free_cmd_desc(struct hclgevf_cmq_ring *ring)
{
- dma_unmap_single(cmq_ring_to_dev(ring), ring->desc_dma_addr,
- ring->desc_num * sizeof(ring->desc[0]),
- hclgevf_ring_to_dma_dir(ring));
+ int size = ring->desc_num * sizeof(struct hclgevf_desc);
- ring->desc_dma_addr = 0;
- kfree(ring->desc);
- ring->desc = NULL;
+ if (ring->desc) {
+ dma_free_coherent(cmq_ring_to_dev(ring), size,
+ ring->desc, ring->desc_dma_addr);
+ ring->desc = NULL;
+ }
}
static int hclgevf_init_cmd_queue(struct hclgevf_dev *hdev,
static void hclgevf_free_vector(struct hclgevf_dev *hdev, int vector_id)
{
+ if (hdev->vector_status[vector_id] == HCLGEVF_INVALID_VPORT) {
+ dev_warn(&hdev->pdev->dev,
+ "vector(vector_id %d) has been freed.\n", vector_id);
+ return;
+ }
+
hdev->vector_status[vector_id] = HCLGEVF_INVALID_VPORT;
hdev->num_msi_left += 1;
hdev->num_msi_used -= 1;
hclgevf_cmd_setup_basic_desc(&desc, HCLGEVF_OPC_RSS_TC_MODE, false);
for (i = 0; i < HCLGEVF_MAX_TC_NUM; i++) {
- hnae_set_bit(req->rss_tc_mode[i], HCLGEVF_RSS_TC_VALID_B,
- (tc_valid[i] & 0x1));
- hnae_set_field(req->rss_tc_mode[i], HCLGEVF_RSS_TC_SIZE_M,
- HCLGEVF_RSS_TC_SIZE_S, tc_size[i]);
- hnae_set_field(req->rss_tc_mode[i], HCLGEVF_RSS_TC_OFFSET_M,
- HCLGEVF_RSS_TC_OFFSET_S, tc_offset[i]);
+ hnae3_set_bit(req->rss_tc_mode[i], HCLGEVF_RSS_TC_VALID_B,
+ (tc_valid[i] & 0x1));
+ hnae3_set_field(req->rss_tc_mode[i], HCLGEVF_RSS_TC_SIZE_M,
+ HCLGEVF_RSS_TC_SIZE_S, tc_size[i]);
+ hnae3_set_field(req->rss_tc_mode[i], HCLGEVF_RSS_TC_OFFSET_M,
+ HCLGEVF_RSS_TC_OFFSET_S, tc_offset[i]);
}
status = hclgevf_cmd_send(&hdev->hw, &desc, 1);
if (status)
}
static int hclgevf_bind_ring_to_vector(struct hnae3_handle *handle, bool en,
- int vector,
+ int vector_id,
struct hnae3_ring_chain_node *ring_chain)
{
struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
struct hnae3_ring_chain_node *node;
struct hclge_mbx_vf_to_pf_cmd *req;
struct hclgevf_desc desc;
- int i = 0, vector_id;
+ int i = 0;
int status;
u8 type;
req = (struct hclge_mbx_vf_to_pf_cmd *)desc.data;
- vector_id = hclgevf_get_vector_index(hdev, vector);
- if (vector_id < 0) {
- dev_err(&handle->pdev->dev,
- "Get vector index fail. ret =%d\n", vector_id);
- return vector_id;
- }
for (node = ring_chain; node; node = node->next) {
int idx_offset = HCLGE_MBX_RING_MAP_BASIC_MSG_NUM +
}
req->msg[idx_offset] =
- hnae_get_bit(node->flag, HNAE3_RING_TYPE_B);
+ hnae3_get_bit(node->flag, HNAE3_RING_TYPE_B);
req->msg[idx_offset + 1] = node->tqp_index;
- req->msg[idx_offset + 2] = hnae_get_field(node->int_gl_idx,
- HNAE3_RING_GL_IDX_M,
- HNAE3_RING_GL_IDX_S);
+ req->msg[idx_offset + 2] = hnae3_get_field(node->int_gl_idx,
+ HNAE3_RING_GL_IDX_M,
+ HNAE3_RING_GL_IDX_S);
i++;
if ((i == (HCLGE_MBX_VF_MSG_DATA_NUM -
static int hclgevf_map_ring_to_vector(struct hnae3_handle *handle, int vector,
struct hnae3_ring_chain_node *ring_chain)
{
- return hclgevf_bind_ring_to_vector(handle, true, vector, ring_chain);
+ struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+ int vector_id;
+
+ vector_id = hclgevf_get_vector_index(hdev, vector);
+ if (vector_id < 0) {
+ dev_err(&handle->pdev->dev,
+ "Get vector index fail. ret =%d\n", vector_id);
+ return vector_id;
+ }
+
+ return hclgevf_bind_ring_to_vector(handle, true, vector_id, ring_chain);
}
static int hclgevf_unmap_ring_from_vector(
return vector_id;
}
- ret = hclgevf_bind_ring_to_vector(handle, false, vector, ring_chain);
+ ret = hclgevf_bind_ring_to_vector(handle, false, vector_id, ring_chain);
if (ret)
dev_err(&handle->pdev->dev,
"Unmap ring from vector fail. vector=%d, ret =%d\n",
static int hclgevf_put_vector(struct hnae3_handle *handle, int vector)
{
struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+ int vector_id;
- hclgevf_free_vector(hdev, vector);
+ vector_id = hclgevf_get_vector_index(hdev, vector);
+ if (vector_id < 0) {
+ dev_err(&handle->pdev->dev,
+ "hclgevf_put_vector get vector index fail. ret =%d\n",
+ vector_id);
+ return vector_id;
+ }
+
+ hclgevf_free_vector(hdev, vector_id);
return 0;
}
/* wait to check the hardware reset completion status */
val = hclgevf_read_dev(&hdev->hw, HCLGEVF_FUN_RST_ING);
- while (hnae_get_bit(val, HCLGEVF_FUN_RST_ING_B) &&
- (cnt < HCLGEVF_RESET_WAIT_CNT)) {
+ while (hnae3_get_bit(val, HCLGEVF_FUN_RST_ING_B) &&
+ (cnt < HCLGEVF_RESET_WAIT_CNT)) {
msleep(HCLGEVF_RESET_WAIT_MS);
val = hclgevf_read_dev(&hdev->hw, HCLGEVF_FUN_RST_ING);
cnt++;
hclgevf_free_vector(hdev, 0);
}
-static int hclgevf_init_instance(struct hclgevf_dev *hdev,
- struct hnae3_client *client)
+static int hclgevf_init_client_instance(struct hnae3_client *client,
+ struct hnae3_ae_dev *ae_dev)
{
+ struct hclgevf_dev *hdev = ae_dev->priv;
int ret;
switch (client->type) {
return 0;
}
-static void hclgevf_uninit_instance(struct hclgevf_dev *hdev,
- struct hnae3_client *client)
+static void hclgevf_uninit_client_instance(struct hnae3_client *client,
+ struct hnae3_ae_dev *ae_dev)
{
+ struct hclgevf_dev *hdev = ae_dev->priv;
+
/* un-init roce, if it exists */
if (hdev->roce_client)
hdev->roce_client->ops->uninit_instance(&hdev->roce, 0);
client->ops->uninit_instance(&hdev->nic, 0);
}
-static int hclgevf_register_client(struct hnae3_client *client,
- struct hnae3_ae_dev *ae_dev)
-{
- struct hclgevf_dev *hdev = ae_dev->priv;
-
- return hclgevf_init_instance(hdev, client);
-}
-
-static void hclgevf_unregister_client(struct hnae3_client *client,
- struct hnae3_ae_dev *ae_dev)
-{
- struct hclgevf_dev *hdev = ae_dev->priv;
-
- hclgevf_uninit_instance(hdev, client);
-}
-
static int hclgevf_pci_init(struct hclgevf_dev *hdev)
{
struct pci_dev *pdev = hdev->pdev;
static const struct hnae3_ae_ops hclgevf_ops = {
.init_ae_dev = hclgevf_init_ae_dev,
.uninit_ae_dev = hclgevf_uninit_ae_dev,
- .init_client_instance = hclgevf_register_client,
- .uninit_client_instance = hclgevf_unregister_client,
+ .init_client_instance = hclgevf_init_client_instance,
+ .uninit_client_instance = hclgevf_uninit_client_instance,
.start = hclgevf_ae_start,
.stop = hclgevf_ae_stop,
.map_ring_to_vector = hclgevf_map_ring_to_vector,
static struct hnae3_ae_algo ae_algovf = {
.ops = &hclgevf_ops,
- .name = HCLGEVF_NAME,
.pdev_id_table = ae_algovf_pci_tbl,
};
req = (struct hclge_mbx_pf_to_vf_cmd *)desc->data;
flag = le16_to_cpu(crq->desc[crq->next_to_use].flag);
- if (unlikely(!hnae_get_bit(flag, HCLGEVF_CMDQ_RX_OUTVLD_B))) {
+ if (unlikely(!hnae3_get_bit(flag, HCLGEVF_CMDQ_RX_OUTVLD_B))) {
dev_warn(&hdev->pdev->dev,
"dropped invalid mailbox message, code = %d\n",
req->msg[0]);
/* tail the async message in arq */
msg_q = hdev->arq.msg_q[hdev->arq.tail];
- memcpy(&msg_q[0], req->msg, HCLGE_MBX_MAX_ARQ_MSG_SIZE);
+ memcpy(&msg_q[0], req->msg,
+ HCLGE_MBX_MAX_ARQ_MSG_SIZE * sizeof(u16));
hclge_mbx_tail_ptr_move_arq(hdev->arq);
hdev->arq.count++;
struct hinic_hwif *hwif = hwdev->hwif;
struct pci_dev *pdev = hwif->pdev;
struct hinic_cmd_fw_ctxt fw_ctxt;
- struct hinic_pfhwdev *pfhwdev;
u16 out_size;
int err;
fw_ctxt.func_idx = HINIC_HWIF_FUNC_IDX(hwif);
fw_ctxt.rx_buf_sz = HINIC_RX_BUF_SZ;
- pfhwdev = container_of(hwdev, struct hinic_pfhwdev, hwdev);
-
err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_FWCTXT_INIT,
&fw_ctxt, sizeof(fw_ctxt),
&fw_ctxt, &out_size);
{
struct hinic_rq *rq = rxq->rq;
+ irq_set_affinity_hint(rq->irq, NULL);
free_irq(rq->irq, rxq);
rx_del_napi(rxq);
}
case TC_CLSFLOWER_STATS:
return -EOPNOTSUPP;
default:
- return -EINVAL;
+ return -EOPNOTSUPP;
}
}
switch (f->command) {
case TC_BLOCK_BIND:
return tcf_block_cb_register(f->block, i40e_setup_tc_block_cb,
- np, np);
+ np, np, f->extack);
case TC_BLOCK_UNBIND:
tcf_block_cb_unregister(f->block, i40e_setup_tc_block_cb, np);
return 0;
case XDP_SETUP_PROG:
return i40e_xdp_setup(vsi, xdp->prog);
case XDP_QUERY_PROG:
- xdp->prog_attached = i40e_enabled_xdp_vsi(vsi);
xdp->prog_id = vsi->xdp_prog ? vsi->xdp_prog->aux->id : 0;
return 0;
default:
snprintf(netdev->name, IFNAMSIZ, "%.*sv%%d",
IFNAMSIZ - 4,
pf->vsi[pf->lan_vsi]->netdev->name);
- random_ether_addr(mac_addr);
+ eth_random_addr(mac_addr);
spin_lock_bh(&vsi->mac_filter_hash_lock);
i40e_add_mac_filter(vsi, mac_addr);
unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2;
#else
unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) +
- SKB_DATA_ALIGN(I40E_SKB_PAD +
- (xdp->data_end -
- xdp->data_hard_start));
+ SKB_DATA_ALIGN(xdp->data_end -
+ xdp->data_hard_start);
#endif
struct sk_buff *skb;
return NULL;
/* update pointers within the skb to store the data */
- skb_reserve(skb, I40E_SKB_PAD + (xdp->data - xdp->data_hard_start));
+ skb_reserve(skb, xdp->data - xdp->data_hard_start);
__skb_put(skb, xdp->data_end - xdp->data);
if (metasize)
skb_metadata_set(skb, metasize);
return true;
}
-#define I40E_XDP_PASS 0
-#define I40E_XDP_CONSUMED 1
-#define I40E_XDP_TX 2
+#define I40E_XDP_PASS 0
+#define I40E_XDP_CONSUMED BIT(0)
+#define I40E_XDP_TX BIT(1)
+#define I40E_XDP_REDIR BIT(2)
static int i40e_xmit_xdp_ring(struct xdp_frame *xdpf,
struct i40e_ring *xdp_ring);
break;
case XDP_REDIRECT:
err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
- result = !err ? I40E_XDP_TX : I40E_XDP_CONSUMED;
+ result = !err ? I40E_XDP_REDIR : I40E_XDP_CONSUMED;
break;
default:
bpf_warn_invalid_xdp_action(act);
unsigned int total_rx_bytes = 0, total_rx_packets = 0;
struct sk_buff *skb = rx_ring->skb;
u16 cleaned_count = I40E_DESC_UNUSED(rx_ring);
- bool failure = false, xdp_xmit = false;
+ unsigned int xdp_xmit = 0;
+ bool failure = false;
struct xdp_buff xdp;
xdp.rxq = &rx_ring->xdp_rxq;
}
if (IS_ERR(skb)) {
- if (PTR_ERR(skb) == -I40E_XDP_TX) {
- xdp_xmit = true;
+ unsigned int xdp_res = -PTR_ERR(skb);
+
+ if (xdp_res & (I40E_XDP_TX | I40E_XDP_REDIR)) {
+ xdp_xmit |= xdp_res;
i40e_rx_buffer_flip(rx_ring, rx_buffer, size);
} else {
rx_buffer->pagecnt_bias++;
total_rx_packets++;
}
- if (xdp_xmit) {
+ if (xdp_xmit & I40E_XDP_REDIR)
+ xdp_do_flush_map();
+
+ if (xdp_xmit & I40E_XDP_TX) {
struct i40e_ring *xdp_ring =
rx_ring->vsi->xdp_rings[rx_ring->queue_index];
i40e_xdp_ring_update_tail(xdp_ring);
- xdp_do_flush_map();
}
rx_ring->skb = skb;
case TC_CLSFLOWER_STATS:
return -EOPNOTSUPP;
default:
- return -EINVAL;
+ return -EOPNOTSUPP;
}
}
switch (f->command) {
case TC_BLOCK_BIND:
return tcf_block_cb_register(f->block, i40evf_setup_tc_block_cb,
- adapter, adapter);
+ adapter, adapter, f->extack);
case TC_BLOCK_UNBIND:
tcf_block_cb_unregister(f->block, i40evf_setup_tc_block_cb,
adapter);
#define E1000_TQAVCTRL_XMIT_MODE BIT(0)
#define E1000_TQAVCTRL_DATAFETCHARB BIT(4)
#define E1000_TQAVCTRL_DATATRANARB BIT(8)
+#define E1000_TQAVCTRL_DATATRANTIM BIT(9)
+#define E1000_TQAVCTRL_SP_WAIT_SR BIT(10)
+/* Fetch Time Delta - bits 31:16
+ *
+ * This field holds the value to be reduced from the launch time for
+ * fetch time decision. The FetchTimeDelta value is defined in 32 ns
+ * granularity.
+ *
+ * This field is 16 bits wide, and so the maximum value is:
+ *
+ * 65535 * 32 = 2097120 ~= 2.1 msec
+ *
+ * XXX: We are configuring the max value here since we couldn't come up
+ * with a reason for not doing so.
+ */
+#define E1000_TQAVCTRL_FETCHTIME_DELTA (0xFFFF << 16)
/* TX Qav Credit Control fields */
#define E1000_TQAVCC_IDLESLOPE_MASK 0xFFFF
u16 count; /* number of desc. in the ring */
u8 queue_index; /* logical index of the ring*/
u8 reg_idx; /* physical index of the ring */
+ bool launchtime_enable; /* true if LaunchTime is enabled */
bool cbs_enable; /* indicates if CBS is enabled */
s32 idleslope; /* idleSlope in kbps */
s32 sendslope; /* sendSlope in kbps */
wr32(E1000_I210_TQAVCC(queue), val);
}
+static bool is_any_cbs_enabled(struct igb_adapter *adapter)
+{
+ int i;
+
+ for (i = 0; i < adapter->num_tx_queues; i++) {
+ if (adapter->tx_ring[i]->cbs_enable)
+ return true;
+ }
+
+ return false;
+}
+
+static bool is_any_txtime_enabled(struct igb_adapter *adapter)
+{
+ int i;
+
+ for (i = 0; i < adapter->num_tx_queues; i++) {
+ if (adapter->tx_ring[i]->launchtime_enable)
+ return true;
+ }
+
+ return false;
+}
+
/**
- * igb_configure_cbs - Configure Credit-Based Shaper (CBS)
+ * igb_config_tx_modes - Configure "Qav Tx mode" features on igb
* @adapter: pointer to adapter struct
* @queue: queue number
- * @enable: true = enable CBS, false = disable CBS
- * @idleslope: idleSlope in kbps
- * @sendslope: sendSlope in kbps
- * @hicredit: hiCredit in bytes
- * @locredit: loCredit in bytes
*
- * Configure CBS for a given hardware queue. When disabling, idleslope,
- * sendslope, hicredit, locredit arguments are ignored. Returns 0 if
- * success. Negative otherwise.
+ * Configure CBS and Launchtime for a given hardware queue.
+ * Parameters are retrieved from the correct Tx ring, so
+ * igb_save_cbs_params() and igb_save_txtime_params() should be used
+ * for setting those correctly prior to this function being called.
**/
-static void igb_configure_cbs(struct igb_adapter *adapter, int queue,
- bool enable, int idleslope, int sendslope,
- int hicredit, int locredit)
+static void igb_config_tx_modes(struct igb_adapter *adapter, int queue)
{
+ struct igb_ring *ring = adapter->tx_ring[queue];
struct net_device *netdev = adapter->netdev;
struct e1000_hw *hw = &adapter->hw;
- u32 tqavcc;
+ u32 tqavcc, tqavctrl;
u16 value;
WARN_ON(hw->mac.type != e1000_i210);
WARN_ON(queue < 0 || queue > 1);
- if (enable || queue == 0) {
+ /* If any of the Qav features is enabled, configure queues as SR and
+ * with HIGH PRIO. If none is, then configure them with LOW PRIO and
+ * as SP.
+ */
+ if (ring->cbs_enable || ring->launchtime_enable) {
+ set_tx_desc_fetch_prio(hw, queue, TX_QUEUE_PRIO_HIGH);
+ set_queue_mode(hw, queue, QUEUE_MODE_STREAM_RESERVATION);
+ } else {
+ set_tx_desc_fetch_prio(hw, queue, TX_QUEUE_PRIO_LOW);
+ set_queue_mode(hw, queue, QUEUE_MODE_STRICT_PRIORITY);
+ }
+
+ /* If CBS is enabled, set DataTranARB and config its parameters. */
+ if (ring->cbs_enable || queue == 0) {
/* i210 does not allow the queue 0 to be in the Strict
* Priority mode while the Qav mode is enabled, so,
* instead of disabling strict priority mode, we give
* Queue0 QueueMode must be set to 1b when
* TransmitMode is set to Qav."
*/
- if (queue == 0 && !enable) {
+ if (queue == 0 && !ring->cbs_enable) {
/* max "linkspeed" idleslope in kbps */
- idleslope = 1000000;
- hicredit = ETH_FRAME_LEN;
+ ring->idleslope = 1000000;
+ ring->hicredit = ETH_FRAME_LEN;
}
- set_tx_desc_fetch_prio(hw, queue, TX_QUEUE_PRIO_HIGH);
- set_queue_mode(hw, queue, QUEUE_MODE_STREAM_RESERVATION);
+ /* Always set data transfer arbitration to credit-based
+ * shaper algorithm on TQAVCTRL if CBS is enabled for any of
+ * the queues.
+ */
+ tqavctrl = rd32(E1000_I210_TQAVCTRL);
+ tqavctrl |= E1000_TQAVCTRL_DATATRANARB;
+ wr32(E1000_I210_TQAVCTRL, tqavctrl);
/* According to i210 datasheet section 7.2.7.7, we should set
* the 'idleSlope' field from TQAVCC register following the
* calculated value, so the resulting bandwidth might
* be slightly higher for some configurations.
*/
- value = DIV_ROUND_UP_ULL(idleslope * 61034ULL, 1000000);
+ value = DIV_ROUND_UP_ULL(ring->idleslope * 61034ULL, 1000000);
tqavcc = rd32(E1000_I210_TQAVCC(queue));
tqavcc &= ~E1000_TQAVCC_IDLESLOPE_MASK;
tqavcc |= value;
wr32(E1000_I210_TQAVCC(queue), tqavcc);
- wr32(E1000_I210_TQAVHC(queue), 0x80000000 + hicredit * 0x7735);
+ wr32(E1000_I210_TQAVHC(queue),
+ 0x80000000 + ring->hicredit * 0x7735);
} else {
- set_tx_desc_fetch_prio(hw, queue, TX_QUEUE_PRIO_LOW);
- set_queue_mode(hw, queue, QUEUE_MODE_STRICT_PRIORITY);
/* Set idleSlope to zero. */
tqavcc = rd32(E1000_I210_TQAVCC(queue));
/* Set hiCredit to zero. */
wr32(E1000_I210_TQAVHC(queue), 0);
+
+ /* If CBS is not enabled for any queues anymore, then return to
+ * the default state of Data Transmission Arbitration on
+ * TQAVCTRL.
+ */
+ if (!is_any_cbs_enabled(adapter)) {
+ tqavctrl = rd32(E1000_I210_TQAVCTRL);
+ tqavctrl &= ~E1000_TQAVCTRL_DATATRANARB;
+ wr32(E1000_I210_TQAVCTRL, tqavctrl);
+ }
+ }
+
+ /* If LaunchTime is enabled, set DataTranTIM. */
+ if (ring->launchtime_enable) {
+ /* Always set DataTranTIM on TQAVCTRL if LaunchTime is enabled
+ * for any of the SR queues, and configure fetchtime delta.
+ * XXX NOTE:
+ * - LaunchTime will be enabled for all SR queues.
+ * - A fixed offset can be added relative to the launch
+ * time of all packets if configured at reg LAUNCH_OS0.
+ * We are keeping it as 0 for now (default value).
+ */
+ tqavctrl = rd32(E1000_I210_TQAVCTRL);
+ tqavctrl |= E1000_TQAVCTRL_DATATRANTIM |
+ E1000_TQAVCTRL_FETCHTIME_DELTA;
+ wr32(E1000_I210_TQAVCTRL, tqavctrl);
+ } else {
+ /* If Launchtime is not enabled for any SR queues anymore,
+ * then clear DataTranTIM on TQAVCTRL and clear fetchtime delta,
+ * effectively disabling Launchtime.
+ */
+ if (!is_any_txtime_enabled(adapter)) {
+ tqavctrl = rd32(E1000_I210_TQAVCTRL);
+ tqavctrl &= ~E1000_TQAVCTRL_DATATRANTIM;
+ tqavctrl &= ~E1000_TQAVCTRL_FETCHTIME_DELTA;
+ wr32(E1000_I210_TQAVCTRL, tqavctrl);
+ }
}
/* XXX: In i210 controller the sendSlope and loCredit parameters from
* configuration' in respect to these parameters.
*/
- netdev_dbg(netdev, "CBS %s: queue %d idleslope %d sendslope %d hiCredit %d locredit %d\n",
- (enable) ? "enabled" : "disabled", queue,
- idleslope, sendslope, hicredit, locredit);
+ netdev_dbg(netdev, "Qav Tx mode: cbs %s, launchtime %s, queue %d \
+ idleslope %d sendslope %d hiCredit %d \
+ locredit %d\n",
+ (ring->cbs_enable) ? "enabled" : "disabled",
+ (ring->launchtime_enable) ? "enabled" : "disabled", queue,
+ ring->idleslope, ring->sendslope, ring->hicredit,
+ ring->locredit);
+}
+
+static int igb_save_txtime_params(struct igb_adapter *adapter, int queue,
+ bool enable)
+{
+ struct igb_ring *ring;
+
+ if (queue < 0 || queue > adapter->num_tx_queues)
+ return -EINVAL;
+
+ ring = adapter->tx_ring[queue];
+ ring->launchtime_enable = enable;
+
+ return 0;
}
static int igb_save_cbs_params(struct igb_adapter *adapter, int queue,
return 0;
}
-static bool is_any_cbs_enabled(struct igb_adapter *adapter)
-{
- struct igb_ring *ring;
- int i;
-
- for (i = 0; i < adapter->num_tx_queues; i++) {
- ring = adapter->tx_ring[i];
-
- if (ring->cbs_enable)
- return true;
- }
-
- return false;
-}
-
+/**
+ * igb_setup_tx_mode - Switch to/from Qav Tx mode when applicable
+ * @adapter: pointer to adapter struct
+ *
+ * Configure TQAVCTRL register switching the controller's Tx mode
+ * if FQTSS mode is enabled or disabled. Additionally, will issue
+ * a call to igb_config_tx_modes() per queue so any previously saved
+ * Tx parameters are applied.
+ **/
static void igb_setup_tx_mode(struct igb_adapter *adapter)
{
struct net_device *netdev = adapter->netdev;
int i, max_queue;
/* Configure TQAVCTRL register: set transmit mode to 'Qav',
- * set data fetch arbitration to 'round robin' and set data
- * transfer arbitration to 'credit shaper algorithm.
+ * set data fetch arbitration to 'round robin', set SP_WAIT_SR
+ * so SP queues wait for SR ones.
*/
val = rd32(E1000_I210_TQAVCTRL);
- val |= E1000_TQAVCTRL_XMIT_MODE | E1000_TQAVCTRL_DATATRANARB;
+ val |= E1000_TQAVCTRL_XMIT_MODE | E1000_TQAVCTRL_SP_WAIT_SR;
val &= ~E1000_TQAVCTRL_DATAFETCHARB;
wr32(E1000_I210_TQAVCTRL, val);
adapter->num_tx_queues : I210_SR_QUEUES_NUM;
for (i = 0; i < max_queue; i++) {
- struct igb_ring *ring = adapter->tx_ring[i];
-
- igb_configure_cbs(adapter, i, ring->cbs_enable,
- ring->idleslope, ring->sendslope,
- ring->hicredit, ring->locredit);
+ igb_config_tx_modes(adapter, i);
}
} else {
wr32(E1000_RXPBS, I210_RXPBSIZE_DEFAULT);
return features;
}
+static void igb_offload_apply(struct igb_adapter *adapter, s32 queue)
+{
+ if (!is_fqtss_enabled(adapter)) {
+ enable_fqtss(adapter, true);
+ return;
+ }
+
+ igb_config_tx_modes(adapter, queue);
+
+ if (!is_any_cbs_enabled(adapter) && !is_any_txtime_enabled(adapter))
+ enable_fqtss(adapter, false);
+}
+
static int igb_offload_cbs(struct igb_adapter *adapter,
struct tc_cbs_qopt_offload *qopt)
{
if (err)
return err;
- if (is_fqtss_enabled(adapter)) {
- igb_configure_cbs(adapter, qopt->queue, qopt->enable,
- qopt->idleslope, qopt->sendslope,
- qopt->hicredit, qopt->locredit);
-
- if (!is_any_cbs_enabled(adapter))
- enable_fqtss(adapter, false);
-
- } else {
- enable_fqtss(adapter, true);
- }
+ igb_offload_apply(adapter, qopt->queue);
return 0;
}
case TC_CLSFLOWER_STATS:
return -EOPNOTSUPP;
default:
- return -EINVAL;
+ return -EOPNOTSUPP;
}
}
switch (f->command) {
case TC_BLOCK_BIND:
return tcf_block_cb_register(f->block, igb_setup_tc_block_cb,
- adapter, adapter);
+ adapter, adapter, f->extack);
case TC_BLOCK_UNBIND:
tcf_block_cb_unregister(f->block, igb_setup_tc_block_cb,
adapter);
}
}
+static int igb_offload_txtime(struct igb_adapter *adapter,
+ struct tc_etf_qopt_offload *qopt)
+{
+ struct e1000_hw *hw = &adapter->hw;
+ int err;
+
+ /* Launchtime offloading is only supported by i210 controller. */
+ if (hw->mac.type != e1000_i210)
+ return -EOPNOTSUPP;
+
+ /* Launchtime offloading is only supported by queues 0 and 1. */
+ if (qopt->queue < 0 || qopt->queue > 1)
+ return -EINVAL;
+
+ err = igb_save_txtime_params(adapter, qopt->queue, qopt->enable);
+ if (err)
+ return err;
+
+ igb_offload_apply(adapter, qopt->queue);
+
+ return 0;
+}
+
static int igb_setup_tc(struct net_device *dev, enum tc_setup_type type,
void *type_data)
{
return igb_offload_cbs(adapter, type_data);
case TC_SETUP_BLOCK:
return igb_setup_tc_block(adapter, type_data);
+ case TC_SETUP_QDISC_ETF:
+ return igb_offload_txtime(adapter, type_data);
default:
return -EOPNOTSUPP;
}
}
-static void igb_tx_ctxtdesc(struct igb_ring *tx_ring, u32 vlan_macip_lens,
- u32 type_tucmd, u32 mss_l4len_idx)
+static void igb_tx_ctxtdesc(struct igb_ring *tx_ring,
+ struct igb_tx_buffer *first,
+ u32 vlan_macip_lens, u32 type_tucmd,
+ u32 mss_l4len_idx)
{
struct e1000_adv_tx_context_desc *context_desc;
u16 i = tx_ring->next_to_use;
+ struct timespec64 ts;
context_desc = IGB_TX_CTXTDESC(tx_ring, i);
mss_l4len_idx |= tx_ring->reg_idx << 4;
context_desc->vlan_macip_lens = cpu_to_le32(vlan_macip_lens);
- context_desc->seqnum_seed = 0;
context_desc->type_tucmd_mlhl = cpu_to_le32(type_tucmd);
context_desc->mss_l4len_idx = cpu_to_le32(mss_l4len_idx);
+
+ /* We assume there is always a valid tx time available. Invalid times
+ * should have been handled by the upper layers.
+ */
+ if (tx_ring->launchtime_enable) {
+ ts = ns_to_timespec64(first->skb->tstamp);
+ context_desc->seqnum_seed = cpu_to_le32(ts.tv_nsec / 32);
+ } else {
+ context_desc->seqnum_seed = 0;
+ }
}
static int igb_tso(struct igb_ring *tx_ring,
vlan_macip_lens |= (ip.hdr - skb->data) << E1000_ADVTXD_MACLEN_SHIFT;
vlan_macip_lens |= first->tx_flags & IGB_TX_FLAGS_VLAN_MASK;
- igb_tx_ctxtdesc(tx_ring, vlan_macip_lens, type_tucmd, mss_l4len_idx);
+ igb_tx_ctxtdesc(tx_ring, first, vlan_macip_lens,
+ type_tucmd, mss_l4len_idx);
return 1;
}
vlan_macip_lens |= skb_network_offset(skb) << E1000_ADVTXD_MACLEN_SHIFT;
vlan_macip_lens |= first->tx_flags & IGB_TX_FLAGS_VLAN_MASK;
- igb_tx_ctxtdesc(tx_ring, vlan_macip_lens, type_tucmd, 0);
+ igb_tx_ctxtdesc(tx_ring, first, vlan_macip_lens, type_tucmd, 0);
}
#define IGB_SET_FLAG(_input, _flag, _result) \
}
}
- skb_tx_timestamp(skb);
-
if (skb_vlan_tag_present(skb)) {
tx_flags |= IGB_TX_FLAGS_VLAN;
tx_flags |= (skb_vlan_tag_get(skb) << IGB_TX_FLAGS_VLAN_SHIFT);
else if (!tso)
igb_tx_csum(tx_ring, first);
+ skb_tx_timestamp(skb);
+
if (igb_tx_map(tx_ring, first, hdr_len))
goto cleanup_tx_tstamp;
return skb;
}
-#define IXGBE_XDP_PASS 0
-#define IXGBE_XDP_CONSUMED 1
-#define IXGBE_XDP_TX 2
+#define IXGBE_XDP_PASS 0
+#define IXGBE_XDP_CONSUMED BIT(0)
+#define IXGBE_XDP_TX BIT(1)
+#define IXGBE_XDP_REDIR BIT(2)
static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter,
struct xdp_frame *xdpf);
case XDP_REDIRECT:
err = xdp_do_redirect(adapter->netdev, xdp, xdp_prog);
if (!err)
- result = IXGBE_XDP_TX;
+ result = IXGBE_XDP_REDIR;
else
result = IXGBE_XDP_CONSUMED;
break;
unsigned int mss = 0;
#endif /* IXGBE_FCOE */
u16 cleaned_count = ixgbe_desc_unused(rx_ring);
- bool xdp_xmit = false;
+ unsigned int xdp_xmit = 0;
struct xdp_buff xdp;
xdp.rxq = &rx_ring->xdp_rxq;
}
if (IS_ERR(skb)) {
- if (PTR_ERR(skb) == -IXGBE_XDP_TX) {
- xdp_xmit = true;
+ unsigned int xdp_res = -PTR_ERR(skb);
+
+ if (xdp_res & (IXGBE_XDP_TX | IXGBE_XDP_REDIR)) {
+ xdp_xmit |= xdp_res;
ixgbe_rx_buffer_flip(rx_ring, rx_buffer, size);
} else {
rx_buffer->pagecnt_bias++;
total_rx_packets++;
}
- if (xdp_xmit) {
+ if (xdp_xmit & IXGBE_XDP_REDIR)
+ xdp_do_flush_map();
+
+ if (xdp_xmit & IXGBE_XDP_TX) {
struct ixgbe_ring *ring = adapter->xdp_ring[smp_processor_id()];
/* Force memory writes to complete before letting h/w
*/
wmb();
writel(ring->next_to_use, ring->tail);
-
- xdp_do_flush_map();
}
u64_stats_update_begin(&rx_ring->syncp);
static int ixgbe_fwd_ring_up(struct ixgbe_adapter *adapter,
struct ixgbe_fwd_adapter *accel)
{
+ u16 rss_i = adapter->ring_feature[RING_F_RSS].indices;
+ int num_tc = netdev_get_num_tc(adapter->netdev);
struct net_device *vdev = accel->netdev;
int i, baseq, err;
accel->rx_base_queue = baseq;
accel->tx_base_queue = baseq;
+ /* record configuration for macvlan interface in vdev */
+ for (i = 0; i < num_tc; i++)
+ netdev_bind_sb_channel_queue(adapter->netdev, vdev,
+ i, rss_i, baseq + (rss_i * i));
+
for (i = 0; i < adapter->num_rx_queues_per_pool; i++)
adapter->rx_ring[baseq + i]->netdev = vdev;
netdev_err(vdev, "L2FW offload disabled due to L2 filter error\n");
+ /* unbind the queues and drop the subordinate channel config */
+ netdev_unbind_sb_channel(adapter->netdev, vdev);
+ netdev_set_sb_channel(vdev, 0);
+
clear_bit(accel->pool, adapter->fwd_bitmask);
kfree(accel);
input, common, ring->queue_index);
}
+#ifdef IXGBE_FCOE
static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
- void *accel_priv, select_queue_fallback_t fallback)
+ struct net_device *sb_dev,
+ select_queue_fallback_t fallback)
{
- struct ixgbe_fwd_adapter *fwd_adapter = accel_priv;
struct ixgbe_adapter *adapter;
- int txq;
-#ifdef IXGBE_FCOE
struct ixgbe_ring_feature *f;
-#endif
+ int txq;
- if (fwd_adapter) {
- adapter = netdev_priv(dev);
- txq = reciprocal_scale(skb_get_hash(skb),
- adapter->num_rx_queues_per_pool);
+ if (sb_dev) {
+ u8 tc = netdev_get_prio_tc_map(dev, skb->priority);
+ struct net_device *vdev = sb_dev;
- return txq + fwd_adapter->tx_base_queue;
- }
+ txq = vdev->tc_to_txq[tc].offset;
+ txq += reciprocal_scale(skb_get_hash(skb),
+ vdev->tc_to_txq[tc].count);
-#ifdef IXGBE_FCOE
+ return txq;
+ }
/*
* only execute the code below if protocol is FCoE
case htons(ETH_P_FIP):
adapter = netdev_priv(dev);
- if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED)
+ if (!sb_dev && (adapter->flags & IXGBE_FLAG_FCOE_ENABLED))
break;
/* fall through */
default:
- return fallback(dev, skb);
+ return fallback(dev, skb, sb_dev);
}
f = &adapter->ring_feature[RING_F_FCOE];
txq -= f->indices;
return txq + f->offset;
-#else
- return fallback(dev, skb);
-#endif
}
+#endif
static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter,
struct xdp_frame *xdpf)
{
/* if we cannot find a free pool then disable the offload */
netdev_err(vdev, "L2FW offload disabled due to lack of queue resources\n");
macvlan_release_l2fw_offload(vdev);
+
+ /* unbind the queues and drop the subordinate channel config */
+ netdev_unbind_sb_channel(adapter->netdev, vdev);
+ netdev_set_sb_channel(vdev, 0);
+
kfree(accel);
return 0;
switch (f->command) {
case TC_BLOCK_BIND:
return tcf_block_cb_register(f->block, ixgbe_setup_tc_block_cb,
- adapter, adapter);
+ adapter, adapter, f->extack);
case TC_BLOCK_UNBIND:
tcf_block_cb_unregister(f->block, ixgbe_setup_tc_block_cb,
adapter);
if (!macvlan_supports_dest_filter(vdev))
return ERR_PTR(-EMEDIUMTYPE);
+ /* We need to lock down the macvlan to be a single queue device so that
+ * we can reuse the tc_to_txq field in the macvlan netdev to represent
+ * the queue mapping to our netdev.
+ */
+ if (netif_is_multiqueue(vdev))
+ return ERR_PTR(-ERANGE);
+
pool = find_first_zero_bit(adapter->fwd_bitmask, adapter->num_rx_pools);
if (pool == adapter->num_rx_pools) {
u16 used_pools = adapter->num_vfs + adapter->num_rx_pools;
return ERR_PTR(-ENOMEM);
set_bit(pool, adapter->fwd_bitmask);
+ netdev_set_sb_channel(vdev, pool);
accel->pool = pool;
accel->netdev = vdev;
ring->netdev = NULL;
}
+ /* unbind the queues and drop the subordinate channel config */
+ netdev_unbind_sb_channel(pdev, accel->netdev);
+ netdev_set_sb_channel(accel->netdev, 0);
+
clear_bit(accel->pool, adapter->fwd_bitmask);
kfree(accel);
}
case XDP_SETUP_PROG:
return ixgbe_xdp_setup(dev, xdp->prog);
case XDP_QUERY_PROG:
- xdp->prog_attached = !!(adapter->xdp_prog);
xdp->prog_id = adapter->xdp_prog ?
adapter->xdp_prog->aux->id : 0;
return 0;
.ndo_open = ixgbe_open,
.ndo_stop = ixgbe_close,
.ndo_start_xmit = ixgbe_xmit_frame,
- .ndo_select_queue = ixgbe_select_queue,
.ndo_set_rx_mode = ixgbe_set_rx_mode,
.ndo_validate_addr = eth_validate_addr,
.ndo_set_mac_address = ixgbe_set_mac,
.ndo_poll_controller = ixgbe_netpoll,
#endif
#ifdef IXGBE_FCOE
+ .ndo_select_queue = ixgbe_select_queue,
.ndo_fcoe_ddp_setup = ixgbe_fcoe_ddp_get,
.ndo_fcoe_ddp_target = ixgbe_fcoe_ddp_target,
.ndo_fcoe_ddp_done = ixgbe_fcoe_ddp_put,
case XDP_SETUP_PROG:
return ixgbevf_xdp_setup(dev, xdp->prog);
case XDP_QUERY_PROG:
- xdp->prog_attached = !!(adapter->xdp_prog);
xdp->prog_id = adapter->xdp_prog ?
adapter->xdp_prog->aux->id : 0;
return 0;
spin_unlock_irqrestore(&priv->lock, flags);
}
-static u16
-ltq_etop_select_queue(struct net_device *dev, struct sk_buff *skb,
- void *accel_priv, select_queue_fallback_t fallback)
-{
- /* we are currently only using the first queue */
- return 0;
-}
-
static int
ltq_etop_init(struct net_device *dev)
{
.ndo_set_mac_address = ltq_etop_set_mac_address,
.ndo_validate_addr = eth_validate_addr,
.ndo_set_rx_mode = ltq_etop_set_multicast_list,
- .ndo_select_queue = ltq_etop_select_queue,
+ .ndo_select_queue = dev_pick_tx_zero,
.ndo_init = ltq_etop_init,
.ndo_tx_timeout = ltq_etop_tx_timeout,
};
config MV643XX_ETH
tristate "Marvell Discovery (643XX) and Orion ethernet support"
- depends on (MV64X60 || PPC32 || PLAT_ORION || COMPILE_TEST) && INET
- depends on HAS_DMA
+ depends on MV64X60 || PPC32 || PLAT_ORION || COMPILE_TEST
+ depends on INET
select PHYLIB
select MVMDIO
---help---
config MVNETA
tristate "Marvell Armada 370/38x/XP/37xx network interface support"
depends on ARCH_MVEBU || COMPILE_TEST
- depends on HAS_DMA
select MVMDIO
select PHYLINK
---help---
config MVPP2
tristate "Marvell Armada 375/7K/8K network interface support"
depends on ARCH_MVEBU || COMPILE_TEST
- depends on HAS_DMA
select MVMDIO
select PHYLINK
---help---
config PXA168_ETH
tristate "Marvell pxa168 ethernet support"
- depends on HAS_IOMEM && HAS_DMA
+ depends on HAS_IOMEM
depends on CPU_PXA168 || ARCH_BERLIN || COMPILE_TEST
select PHYLIB
---help---
rx_bytes = rx_desc->data_size - (ETH_FCS_LEN + MVNETA_MH_SIZE);
index = rx_desc - rxq->descs;
data = rxq->buf_virt_addr[index];
- phys_addr = rx_desc->buf_phys_addr;
+ phys_addr = rx_desc->buf_phys_addr - pp->rx_offset_correction;
if (!mvneta_rxq_desc_is_first_last(rx_status) ||
(rx_status & MVNETA_RXD_ERR_SUMMARY)) {
#
obj-$(CONFIG_MVPP2) := mvpp2.o
-mvpp2-objs := mvpp2_main.o mvpp2_prs.o mvpp2_cls.o
+mvpp2-objs := mvpp2_main.o mvpp2_prs.o mvpp2_cls.o mvpp2_debugfs.o
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Definitions for Marvell PPv2 network controller for Armada 375 SoC.
*
* Copyright (C) 2014 Marvell
*
* Marcin Wojtas <mw@semihalf.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
*/
#ifndef _MVPP2_H_
#define _MVPP2_H_
+#include <linux/interrupt.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <linux/phy.h>
#define MVPP2_PRS_SRAM_DATA_REG(idx) (0x1204 + (idx) * 4)
#define MVPP2_PRS_TCAM_CTRL_REG 0x1230
#define MVPP2_PRS_TCAM_EN_MASK BIT(0)
+#define MVPP2_PRS_TCAM_HIT_IDX_REG 0x1240
+#define MVPP2_PRS_TCAM_HIT_CNT_REG 0x1244
+#define MVPP2_PRS_TCAM_HIT_CNT_MASK GENMASK(15, 0)
/* RSS Registers */
#define MVPP22_RSS_INDEX 0x1500
#define MVPP22_RSS_INDEX_TABLE_ENTRY(idx) (idx)
#define MVPP22_RSS_INDEX_TABLE(idx) ((idx) << 8)
#define MVPP22_RSS_INDEX_QUEUE(idx) ((idx) << 16)
-#define MVPP22_RSS_TABLE_ENTRY 0x1508
-#define MVPP22_RSS_TABLE 0x1510
+#define MVPP22_RXQ2RSS_TABLE 0x1504
#define MVPP22_RSS_TABLE_POINTER(p) (p)
+#define MVPP22_RSS_TABLE_ENTRY 0x1508
#define MVPP22_RSS_WIDTH 0x150c
/* Classifier Registers */
#define MVPP2_CLS_LKP_INDEX_WAY_OFFS 6
#define MVPP2_CLS_LKP_TBL_REG 0x1818
#define MVPP2_CLS_LKP_TBL_RXQ_MASK 0xff
+#define MVPP2_CLS_LKP_FLOW_PTR(flow) ((flow) << 16)
#define MVPP2_CLS_LKP_TBL_LOOKUP_EN_MASK BIT(25)
#define MVPP2_CLS_FLOW_INDEX_REG 0x1820
#define MVPP2_CLS_FLOW_TBL0_REG 0x1824
+#define MVPP2_CLS_FLOW_TBL0_LAST BIT(0)
+#define MVPP2_CLS_FLOW_TBL0_ENG_MASK 0x7
+#define MVPP2_CLS_FLOW_TBL0_OFFS 1
+#define MVPP2_CLS_FLOW_TBL0_ENG(x) ((x) << 1)
+#define MVPP2_CLS_FLOW_TBL0_PORT_ID_MASK 0xff
+#define MVPP2_CLS_FLOW_TBL0_PORT_ID(port) ((port) << 4)
+#define MVPP2_CLS_FLOW_TBL0_PORT_ID_SEL BIT(23)
#define MVPP2_CLS_FLOW_TBL1_REG 0x1828
+#define MVPP2_CLS_FLOW_TBL1_N_FIELDS_MASK 0x7
+#define MVPP2_CLS_FLOW_TBL1_N_FIELDS(x) (x)
+#define MVPP2_CLS_FLOW_TBL1_PRIO_MASK 0x3f
+#define MVPP2_CLS_FLOW_TBL1_PRIO(x) ((x) << 9)
+#define MVPP2_CLS_FLOW_TBL1_SEQ_MASK 0x7
+#define MVPP2_CLS_FLOW_TBL1_SEQ(x) ((x) << 15)
#define MVPP2_CLS_FLOW_TBL2_REG 0x182c
+#define MVPP2_CLS_FLOW_TBL2_FLD_MASK 0x3f
+#define MVPP2_CLS_FLOW_TBL2_FLD_OFFS(n) ((n) * 6)
+#define MVPP2_CLS_FLOW_TBL2_FLD(n, x) ((x) << ((n) * 6))
#define MVPP2_CLS_OVERSIZE_RXQ_LOW_REG(port) (0x1980 + ((port) * 4))
#define MVPP2_CLS_OVERSIZE_RXQ_LOW_BITS 3
#define MVPP2_CLS_OVERSIZE_RXQ_LOW_MASK 0x7
#define MVPP2_CLS_SWFWD_PCTRL_REG 0x19d0
#define MVPP2_CLS_SWFWD_PCTRL_MASK(port) (1 << (port))
+/* Classifier C2 engine Registers */
+#define MVPP22_CLS_C2_TCAM_IDX 0x1b00
+#define MVPP22_CLS_C2_TCAM_DATA0 0x1b10
+#define MVPP22_CLS_C2_TCAM_DATA1 0x1b14
+#define MVPP22_CLS_C2_TCAM_DATA2 0x1b18
+#define MVPP22_CLS_C2_TCAM_DATA3 0x1b1c
+#define MVPP22_CLS_C2_TCAM_DATA4 0x1b20
+#define MVPP22_CLS_C2_PORT_ID(port) ((port) << 8)
+#define MVPP22_CLS_C2_HIT_CTR 0x1b50
+#define MVPP22_CLS_C2_ACT 0x1b60
+#define MVPP22_CLS_C2_ACT_RSS_EN(act) (((act) & 0x3) << 19)
+#define MVPP22_CLS_C2_ACT_FWD(act) (((act) & 0x7) << 13)
+#define MVPP22_CLS_C2_ACT_QHIGH(act) (((act) & 0x3) << 11)
+#define MVPP22_CLS_C2_ACT_QLOW(act) (((act) & 0x3) << 9)
+#define MVPP22_CLS_C2_ATTR0 0x1b64
+#define MVPP22_CLS_C2_ATTR0_QHIGH(qh) (((qh) & 0x1f) << 24)
+#define MVPP22_CLS_C2_ATTR0_QHIGH_MASK 0x1f
+#define MVPP22_CLS_C2_ATTR0_QHIGH_OFFS 24
+#define MVPP22_CLS_C2_ATTR0_QLOW(ql) (((ql) & 0x7) << 21)
+#define MVPP22_CLS_C2_ATTR0_QLOW_MASK 0x7
+#define MVPP22_CLS_C2_ATTR0_QLOW_OFFS 21
+#define MVPP22_CLS_C2_ATTR1 0x1b68
+#define MVPP22_CLS_C2_ATTR2 0x1b6c
+#define MVPP22_CLS_C2_ATTR2_RSS_EN BIT(30)
+#define MVPP22_CLS_C2_ATTR3 0x1b70
+
/* Descriptor Manager Top Registers */
#define MVPP2_RXQ_NUM_REG 0x2040
#define MVPP2_RXQ_DESC_ADDR_REG 0x2044
#define MVPP22_BM_ADDR_HIGH_VIRT_RLS_MASK 0xff00
#define MVPP22_BM_ADDR_HIGH_VIRT_RLS_SHIFT 8
+/* Hit counters registers */
+#define MVPP2_CTRS_IDX 0x7040
+#define MVPP2_CLS_DEC_TBL_HIT_CTR 0x7700
+#define MVPP2_CLS_FLOW_TBL_HIT_CTR 0x7704
+
/* TX Scheduler registers */
#define MVPP2_TXP_SCHED_PORT_INDEX_REG 0x8000
#define MVPP2_TXP_SCHED_Q_CMD_REG 0x8004
#define MVPP2_MAX_SKB_DESCS (MVPP2_MAX_TSO_SEGS * 2 + MAX_SKB_FRAGS)
/* Dfault number of RXQs in use */
-#define MVPP2_DEFAULT_RXQ 4
+#define MVPP2_DEFAULT_RXQ 1
/* Max number of Rx descriptors */
#define MVPP2_MAX_RXD_MAX 1024
((total_size) - NET_SKB_PAD - MVPP2_SKB_SHINFO_SIZE)
#define MVPP2_BIT_TO_BYTE(bit) ((bit) / 8)
+#define MVPP2_BIT_TO_WORD(bit) ((bit) / 32)
+#define MVPP2_BIT_IN_WORD(bit) ((bit) % 32)
+
+/* RSS constants */
+#define MVPP22_RSS_TABLE_ENTRIES 32
/* IPv6 max L3 address size */
#define MVPP2_MAX_L3_ADDR_SIZE 16
/* Workqueue to gather hardware statistics */
char queue_name[30];
struct workqueue_struct *stats_queue;
+
+ /* Debugfs root entry */
+ struct dentry *dbgfs_dir;
};
struct mvpp2_pcpu_stats {
bool has_tx_irqs;
u32 tx_time_coal;
+
+ /* RSS indirection table */
+ u32 indir[MVPP22_RSS_TABLE_ENTRIES];
};
/* The mvpp2_tx_desc and mvpp2_rx_desc structures describe the
/* HW TX descriptor for PPv2.1 */
struct mvpp21_tx_desc {
- u32 command; /* Options used by HW for packet transmitting.*/
+ __le32 command; /* Options used by HW for packet transmitting.*/
u8 packet_offset; /* the offset from the buffer beginning */
u8 phys_txq; /* destination queue ID */
- u16 data_size; /* data size of transmitted packet in bytes */
- u32 buf_dma_addr; /* physical addr of transmitted buffer */
- u32 buf_cookie; /* cookie for access to TX buffer in tx path */
- u32 reserved1[3]; /* hw_cmd (for future use, BM, PON, PNC) */
- u32 reserved2; /* reserved (for future use) */
+ __le16 data_size; /* data size of transmitted packet in bytes */
+ __le32 buf_dma_addr; /* physical addr of transmitted buffer */
+ __le32 buf_cookie; /* cookie for access to TX buffer in tx path */
+ __le32 reserved1[3]; /* hw_cmd (for future use, BM, PON, PNC) */
+ __le32 reserved2; /* reserved (for future use) */
};
/* HW RX descriptor for PPv2.1 */
struct mvpp21_rx_desc {
- u32 status; /* info about received packet */
- u16 reserved1; /* parser_info (for future use, PnC) */
- u16 data_size; /* size of received packet in bytes */
- u32 buf_dma_addr; /* physical address of the buffer */
- u32 buf_cookie; /* cookie for access to RX buffer in rx path */
- u16 reserved2; /* gem_port_id (for future use, PON) */
- u16 reserved3; /* csum_l4 (for future use, PnC) */
+ __le32 status; /* info about received packet */
+ __le16 reserved1; /* parser_info (for future use, PnC) */
+ __le16 data_size; /* size of received packet in bytes */
+ __le32 buf_dma_addr; /* physical address of the buffer */
+ __le32 buf_cookie; /* cookie for access to RX buffer in rx path */
+ __le16 reserved2; /* gem_port_id (for future use, PON) */
+ __le16 reserved3; /* csum_l4 (for future use, PnC) */
u8 reserved4; /* bm_qset (for future use, BM) */
u8 reserved5;
- u16 reserved6; /* classify_info (for future use, PnC) */
- u32 reserved7; /* flow_id (for future use, PnC) */
- u32 reserved8;
+ __le16 reserved6; /* classify_info (for future use, PnC) */
+ __le32 reserved7; /* flow_id (for future use, PnC) */
+ __le32 reserved8;
};
/* HW TX descriptor for PPv2.2 */
struct mvpp22_tx_desc {
- u32 command;
+ __le32 command;
u8 packet_offset;
u8 phys_txq;
- u16 data_size;
- u64 reserved1;
- u64 buf_dma_addr_ptp;
- u64 buf_cookie_misc;
+ __le16 data_size;
+ __le64 reserved1;
+ __le64 buf_dma_addr_ptp;
+ __le64 buf_cookie_misc;
};
/* HW RX descriptor for PPv2.2 */
struct mvpp22_rx_desc {
- u32 status;
- u16 reserved1;
- u16 data_size;
- u32 reserved2;
- u32 reserved3;
- u64 buf_dma_addr_key_hash;
- u64 buf_cookie_misc;
+ __le32 status;
+ __le16 reserved1;
+ __le16 data_size;
+ __le32 reserved2;
+ __le32 reserved3;
+ __le64 buf_dma_addr_key_hash;
+ __le64 buf_cookie_misc;
};
/* Opaque type used by the driver to manipulate the HW TX and RX
void mvpp2_percpu_write_relaxed(struct mvpp2 *priv, int cpu, u32 offset,
u32 data);
+void mvpp2_dbgfs_init(struct mvpp2 *priv, const char *name);
+
+void mvpp2_dbgfs_cleanup(struct mvpp2 *priv);
+
#endif
+// SPDX-License-Identifier: GPL-2.0
/*
* RSS and Classifier helpers for Marvell PPv2 Network Controller
*
* Copyright (C) 2014 Marvell
*
* Marcin Wojtas <mw@semihalf.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
*/
#include "mvpp2.h"
#include "mvpp2_cls.h"
+#include "mvpp2_prs.h"
+
+#define MVPP2_DEF_FLOW(_type, _id, _opts, _ri, _ri_mask) \
+{ \
+ .flow_type = _type, \
+ .flow_id = _id, \
+ .supported_hash_opts = _opts, \
+ .prs_ri = { \
+ .ri = _ri, \
+ .ri_mask = _ri_mask \
+ } \
+}
+
+static struct mvpp2_cls_flow cls_flows[MVPP2_N_FLOWS] = {
+ /* TCP over IPv4 flows, Not fragmented, no vlan tag */
+ MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_NF_UNTAG,
+ MVPP22_CLS_HEK_IP4_5T,
+ MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4 |
+ MVPP2_PRS_RI_L4_TCP,
+ MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+ MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_NF_UNTAG,
+ MVPP22_CLS_HEK_IP4_5T,
+ MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OPT |
+ MVPP2_PRS_RI_L4_TCP,
+ MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+ MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_NF_UNTAG,
+ MVPP22_CLS_HEK_IP4_5T,
+ MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OTHER |
+ MVPP2_PRS_RI_L4_TCP,
+ MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+ /* TCP over IPv4 flows, Not fragmented, with vlan tag */
+ MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_NF_TAG,
+ MVPP22_CLS_HEK_IP4_5T | MVPP22_CLS_HEK_OPT_VLAN,
+ MVPP2_PRS_RI_L3_IP4 | MVPP2_PRS_RI_L4_TCP,
+ MVPP2_PRS_IP_MASK),
+
+ MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_NF_TAG,
+ MVPP22_CLS_HEK_IP4_5T | MVPP22_CLS_HEK_OPT_VLAN,
+ MVPP2_PRS_RI_L3_IP4_OPT | MVPP2_PRS_RI_L4_TCP,
+ MVPP2_PRS_IP_MASK),
+
+ MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_NF_TAG,
+ MVPP22_CLS_HEK_IP4_5T | MVPP22_CLS_HEK_OPT_VLAN,
+ MVPP2_PRS_RI_L3_IP4_OTHER | MVPP2_PRS_RI_L4_TCP,
+ MVPP2_PRS_IP_MASK),
+
+ /* TCP over IPv4 flows, fragmented, no vlan tag */
+ MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_FRAG_UNTAG,
+ MVPP22_CLS_HEK_IP4_2T,
+ MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4 |
+ MVPP2_PRS_RI_L4_TCP,
+ MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+ MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_FRAG_UNTAG,
+ MVPP22_CLS_HEK_IP4_2T,
+ MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OPT |
+ MVPP2_PRS_RI_L4_TCP,
+ MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+ MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_FRAG_UNTAG,
+ MVPP22_CLS_HEK_IP4_2T,
+ MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OTHER |
+ MVPP2_PRS_RI_L4_TCP,
+ MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+ /* TCP over IPv4 flows, fragmented, with vlan tag */
+ MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_FRAG_TAG,
+ MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_OPT_VLAN,
+ MVPP2_PRS_RI_L3_IP4 | MVPP2_PRS_RI_L4_TCP,
+ MVPP2_PRS_IP_MASK),
+
+ MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_FRAG_TAG,
+ MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_OPT_VLAN,
+ MVPP2_PRS_RI_L3_IP4_OPT | MVPP2_PRS_RI_L4_TCP,
+ MVPP2_PRS_IP_MASK),
+
+ MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_FRAG_TAG,
+ MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_OPT_VLAN,
+ MVPP2_PRS_RI_L3_IP4_OTHER | MVPP2_PRS_RI_L4_TCP,
+ MVPP2_PRS_IP_MASK),
+
+ /* UDP over IPv4 flows, Not fragmented, no vlan tag */
+ MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_NF_UNTAG,
+ MVPP22_CLS_HEK_IP4_5T,
+ MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4 |
+ MVPP2_PRS_RI_L4_UDP,
+ MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+ MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_NF_UNTAG,
+ MVPP22_CLS_HEK_IP4_5T,
+ MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OPT |
+ MVPP2_PRS_RI_L4_UDP,
+ MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+ MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_NF_UNTAG,
+ MVPP22_CLS_HEK_IP4_5T,
+ MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OTHER |
+ MVPP2_PRS_RI_L4_UDP,
+ MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+ /* UDP over IPv4 flows, Not fragmented, with vlan tag */
+ MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_NF_TAG,
+ MVPP22_CLS_HEK_IP4_5T | MVPP22_CLS_HEK_OPT_VLAN,
+ MVPP2_PRS_RI_L3_IP4 | MVPP2_PRS_RI_L4_UDP,
+ MVPP2_PRS_IP_MASK),
+
+ MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_NF_TAG,
+ MVPP22_CLS_HEK_IP4_5T | MVPP22_CLS_HEK_OPT_VLAN,
+ MVPP2_PRS_RI_L3_IP4_OPT | MVPP2_PRS_RI_L4_UDP,
+ MVPP2_PRS_IP_MASK),
+
+ MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_NF_TAG,
+ MVPP22_CLS_HEK_IP4_5T | MVPP22_CLS_HEK_OPT_VLAN,
+ MVPP2_PRS_RI_L3_IP4_OTHER | MVPP2_PRS_RI_L4_UDP,
+ MVPP2_PRS_IP_MASK),
+
+ /* UDP over IPv4 flows, fragmented, no vlan tag */
+ MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_FRAG_UNTAG,
+ MVPP22_CLS_HEK_IP4_2T,
+ MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4 |
+ MVPP2_PRS_RI_L4_UDP,
+ MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+ MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_FRAG_UNTAG,
+ MVPP22_CLS_HEK_IP4_2T,
+ MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OPT |
+ MVPP2_PRS_RI_L4_UDP,
+ MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+ MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_FRAG_UNTAG,
+ MVPP22_CLS_HEK_IP4_2T,
+ MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OTHER |
+ MVPP2_PRS_RI_L4_UDP,
+ MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+ /* UDP over IPv4 flows, fragmented, with vlan tag */
+ MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_FRAG_TAG,
+ MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_OPT_VLAN,
+ MVPP2_PRS_RI_L3_IP4 | MVPP2_PRS_RI_L4_UDP,
+ MVPP2_PRS_IP_MASK),
+
+ MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_FRAG_TAG,
+ MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_OPT_VLAN,
+ MVPP2_PRS_RI_L3_IP4_OPT | MVPP2_PRS_RI_L4_UDP,
+ MVPP2_PRS_IP_MASK),
+
+ MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_FRAG_TAG,
+ MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_OPT_VLAN,
+ MVPP2_PRS_RI_L3_IP4_OTHER | MVPP2_PRS_RI_L4_UDP,
+ MVPP2_PRS_IP_MASK),
+
+ /* TCP over IPv6 flows, not fragmented, no vlan tag */
+ MVPP2_DEF_FLOW(TCP_V6_FLOW, MVPP2_FL_IP6_TCP_NF_UNTAG,
+ MVPP22_CLS_HEK_IP6_5T,
+ MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6 |
+ MVPP2_PRS_RI_L4_TCP,
+ MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+ MVPP2_DEF_FLOW(TCP_V6_FLOW, MVPP2_FL_IP6_TCP_NF_UNTAG,
+ MVPP22_CLS_HEK_IP6_5T,
+ MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6_EXT |
+ MVPP2_PRS_RI_L4_TCP,
+ MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+ /* TCP over IPv6 flows, not fragmented, with vlan tag */
+ MVPP2_DEF_FLOW(TCP_V6_FLOW, MVPP2_FL_IP6_TCP_NF_TAG,
+ MVPP22_CLS_HEK_IP6_5T | MVPP22_CLS_HEK_OPT_VLAN,
+ MVPP2_PRS_RI_L3_IP6 | MVPP2_PRS_RI_L4_TCP,
+ MVPP2_PRS_IP_MASK),
+
+ MVPP2_DEF_FLOW(TCP_V6_FLOW, MVPP2_FL_IP6_TCP_NF_TAG,
+ MVPP22_CLS_HEK_IP6_5T | MVPP22_CLS_HEK_OPT_VLAN,
+ MVPP2_PRS_RI_L3_IP6_EXT | MVPP2_PRS_RI_L4_TCP,
+ MVPP2_PRS_IP_MASK),
+
+ /* TCP over IPv6 flows, fragmented, no vlan tag */
+ MVPP2_DEF_FLOW(TCP_V6_FLOW, MVPP2_FL_IP6_TCP_FRAG_UNTAG,
+ MVPP22_CLS_HEK_IP6_2T,
+ MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6 |
+ MVPP2_PRS_RI_IP_FRAG_TRUE | MVPP2_PRS_RI_L4_TCP,
+ MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+ MVPP2_DEF_FLOW(TCP_V6_FLOW, MVPP2_FL_IP6_TCP_FRAG_UNTAG,
+ MVPP22_CLS_HEK_IP6_2T,
+ MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6_EXT |
+ MVPP2_PRS_RI_IP_FRAG_TRUE | MVPP2_PRS_RI_L4_TCP,
+ MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+ /* TCP over IPv6 flows, fragmented, with vlan tag */
+ MVPP2_DEF_FLOW(TCP_V6_FLOW, MVPP2_FL_IP6_TCP_FRAG_TAG,
+ MVPP22_CLS_HEK_IP6_2T | MVPP22_CLS_HEK_OPT_VLAN,
+ MVPP2_PRS_RI_L3_IP6 | MVPP2_PRS_RI_IP_FRAG_TRUE |
+ MVPP2_PRS_RI_L4_TCP,
+ MVPP2_PRS_IP_MASK),
+
+ MVPP2_DEF_FLOW(TCP_V6_FLOW, MVPP2_FL_IP6_TCP_FRAG_TAG,
+ MVPP22_CLS_HEK_IP6_2T | MVPP22_CLS_HEK_OPT_VLAN,
+ MVPP2_PRS_RI_L3_IP6_EXT | MVPP2_PRS_RI_IP_FRAG_TRUE |
+ MVPP2_PRS_RI_L4_TCP,
+ MVPP2_PRS_IP_MASK),
+
+ /* UDP over IPv6 flows, not fragmented, no vlan tag */
+ MVPP2_DEF_FLOW(UDP_V6_FLOW, MVPP2_FL_IP6_UDP_NF_UNTAG,
+ MVPP22_CLS_HEK_IP6_5T,
+ MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6 |
+ MVPP2_PRS_RI_L4_UDP,
+ MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+ MVPP2_DEF_FLOW(UDP_V6_FLOW, MVPP2_FL_IP6_UDP_NF_UNTAG,
+ MVPP22_CLS_HEK_IP6_5T,
+ MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6_EXT |
+ MVPP2_PRS_RI_L4_UDP,
+ MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+ /* UDP over IPv6 flows, not fragmented, with vlan tag */
+ MVPP2_DEF_FLOW(UDP_V6_FLOW, MVPP2_FL_IP6_UDP_NF_TAG,
+ MVPP22_CLS_HEK_IP6_5T | MVPP22_CLS_HEK_OPT_VLAN,
+ MVPP2_PRS_RI_L3_IP6 | MVPP2_PRS_RI_L4_UDP,
+ MVPP2_PRS_IP_MASK),
+
+ MVPP2_DEF_FLOW(UDP_V6_FLOW, MVPP2_FL_IP6_UDP_NF_TAG,
+ MVPP22_CLS_HEK_IP6_5T | MVPP22_CLS_HEK_OPT_VLAN,
+ MVPP2_PRS_RI_L3_IP6_EXT | MVPP2_PRS_RI_L4_UDP,
+ MVPP2_PRS_IP_MASK),
+
+ /* UDP over IPv6 flows, fragmented, no vlan tag */
+ MVPP2_DEF_FLOW(UDP_V6_FLOW, MVPP2_FL_IP6_UDP_FRAG_UNTAG,
+ MVPP22_CLS_HEK_IP6_2T,
+ MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6 |
+ MVPP2_PRS_RI_IP_FRAG_TRUE | MVPP2_PRS_RI_L4_UDP,
+ MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+ MVPP2_DEF_FLOW(UDP_V6_FLOW, MVPP2_FL_IP6_UDP_FRAG_UNTAG,
+ MVPP22_CLS_HEK_IP6_2T,
+ MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6_EXT |
+ MVPP2_PRS_RI_IP_FRAG_TRUE | MVPP2_PRS_RI_L4_UDP,
+ MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+ /* UDP over IPv6 flows, fragmented, with vlan tag */
+ MVPP2_DEF_FLOW(UDP_V6_FLOW, MVPP2_FL_IP6_UDP_FRAG_TAG,
+ MVPP22_CLS_HEK_IP6_2T | MVPP22_CLS_HEK_OPT_VLAN,
+ MVPP2_PRS_RI_L3_IP6 | MVPP2_PRS_RI_IP_FRAG_TRUE |
+ MVPP2_PRS_RI_L4_UDP,
+ MVPP2_PRS_IP_MASK),
+
+ MVPP2_DEF_FLOW(UDP_V6_FLOW, MVPP2_FL_IP6_UDP_FRAG_TAG,
+ MVPP22_CLS_HEK_IP6_2T | MVPP22_CLS_HEK_OPT_VLAN,
+ MVPP2_PRS_RI_L3_IP6_EXT | MVPP2_PRS_RI_IP_FRAG_TRUE |
+ MVPP2_PRS_RI_L4_UDP,
+ MVPP2_PRS_IP_MASK),
+
+ /* IPv4 flows, no vlan tag */
+ MVPP2_DEF_FLOW(IPV4_FLOW, MVPP2_FL_IP4_UNTAG,
+ MVPP22_CLS_HEK_IP4_2T,
+ MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4,
+ MVPP2_PRS_RI_VLAN_MASK | MVPP2_PRS_RI_L3_PROTO_MASK),
+ MVPP2_DEF_FLOW(IPV4_FLOW, MVPP2_FL_IP4_UNTAG,
+ MVPP22_CLS_HEK_IP4_2T,
+ MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OPT,
+ MVPP2_PRS_RI_VLAN_MASK | MVPP2_PRS_RI_L3_PROTO_MASK),
+ MVPP2_DEF_FLOW(IPV4_FLOW, MVPP2_FL_IP4_UNTAG,
+ MVPP22_CLS_HEK_IP4_2T,
+ MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OTHER,
+ MVPP2_PRS_RI_VLAN_MASK | MVPP2_PRS_RI_L3_PROTO_MASK),
+
+ /* IPv4 flows, with vlan tag */
+ MVPP2_DEF_FLOW(IPV4_FLOW, MVPP2_FL_IP4_TAG,
+ MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_OPT_VLAN,
+ MVPP2_PRS_RI_L3_IP4,
+ MVPP2_PRS_RI_L3_PROTO_MASK),
+ MVPP2_DEF_FLOW(IPV4_FLOW, MVPP2_FL_IP4_TAG,
+ MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_OPT_VLAN,
+ MVPP2_PRS_RI_L3_IP4_OPT,
+ MVPP2_PRS_RI_L3_PROTO_MASK),
+ MVPP2_DEF_FLOW(IPV4_FLOW, MVPP2_FL_IP4_TAG,
+ MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_OPT_VLAN,
+ MVPP2_PRS_RI_L3_IP4_OTHER,
+ MVPP2_PRS_RI_L3_PROTO_MASK),
+
+ /* IPv6 flows, no vlan tag */
+ MVPP2_DEF_FLOW(IPV6_FLOW, MVPP2_FL_IP6_UNTAG,
+ MVPP22_CLS_HEK_IP6_2T,
+ MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6,
+ MVPP2_PRS_RI_VLAN_MASK | MVPP2_PRS_RI_L3_PROTO_MASK),
+ MVPP2_DEF_FLOW(IPV6_FLOW, MVPP2_FL_IP6_UNTAG,
+ MVPP22_CLS_HEK_IP6_2T,
+ MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6,
+ MVPP2_PRS_RI_VLAN_MASK | MVPP2_PRS_RI_L3_PROTO_MASK),
+
+ /* IPv6 flows, with vlan tag */
+ MVPP2_DEF_FLOW(IPV6_FLOW, MVPP2_FL_IP6_TAG,
+ MVPP22_CLS_HEK_IP6_2T | MVPP22_CLS_HEK_OPT_VLAN,
+ MVPP2_PRS_RI_L3_IP6,
+ MVPP2_PRS_RI_L3_PROTO_MASK),
+ MVPP2_DEF_FLOW(IPV6_FLOW, MVPP2_FL_IP6_TAG,
+ MVPP22_CLS_HEK_IP6_2T | MVPP22_CLS_HEK_OPT_VLAN,
+ MVPP2_PRS_RI_L3_IP6,
+ MVPP2_PRS_RI_L3_PROTO_MASK),
+
+ /* Non IP flow, no vlan tag */
+ MVPP2_DEF_FLOW(ETHER_FLOW, MVPP2_FL_NON_IP_UNTAG,
+ 0,
+ MVPP2_PRS_RI_VLAN_NONE,
+ MVPP2_PRS_RI_VLAN_MASK),
+ /* Non IP flow, with vlan tag */
+ MVPP2_DEF_FLOW(ETHER_FLOW, MVPP2_FL_NON_IP_TAG,
+ MVPP22_CLS_HEK_OPT_VLAN,
+ 0, 0),
+};
+
+u32 mvpp2_cls_flow_hits(struct mvpp2 *priv, int index)
+{
+ mvpp2_write(priv, MVPP2_CTRS_IDX, index);
+
+ return mvpp2_read(priv, MVPP2_CLS_FLOW_TBL_HIT_CTR);
+}
+
+void mvpp2_cls_flow_read(struct mvpp2 *priv, int index,
+ struct mvpp2_cls_flow_entry *fe)
+{
+ fe->index = index;
+ mvpp2_write(priv, MVPP2_CLS_FLOW_INDEX_REG, index);
+ fe->data[0] = mvpp2_read(priv, MVPP2_CLS_FLOW_TBL0_REG);
+ fe->data[1] = mvpp2_read(priv, MVPP2_CLS_FLOW_TBL1_REG);
+ fe->data[2] = mvpp2_read(priv, MVPP2_CLS_FLOW_TBL2_REG);
+}
/* Update classification flow table registers */
static void mvpp2_cls_flow_write(struct mvpp2 *priv,
mvpp2_write(priv, MVPP2_CLS_FLOW_TBL2_REG, fe->data[2]);
}
+u32 mvpp2_cls_lookup_hits(struct mvpp2 *priv, int index)
+{
+ mvpp2_write(priv, MVPP2_CTRS_IDX, index);
+
+ return mvpp2_read(priv, MVPP2_CLS_DEC_TBL_HIT_CTR);
+}
+
+void mvpp2_cls_lookup_read(struct mvpp2 *priv, int lkpid, int way,
+ struct mvpp2_cls_lookup_entry *le)
+{
+ u32 val;
+
+ val = (way << MVPP2_CLS_LKP_INDEX_WAY_OFFS) | lkpid;
+ mvpp2_write(priv, MVPP2_CLS_LKP_INDEX_REG, val);
+ le->way = way;
+ le->lkpid = lkpid;
+ le->data = mvpp2_read(priv, MVPP2_CLS_LKP_TBL_REG);
+}
+
/* Update classification lookup table register */
static void mvpp2_cls_lookup_write(struct mvpp2 *priv,
struct mvpp2_cls_lookup_entry *le)
mvpp2_write(priv, MVPP2_CLS_LKP_TBL_REG, le->data);
}
+/* Operations on flow entry */
+static int mvpp2_cls_flow_hek_num_get(struct mvpp2_cls_flow_entry *fe)
+{
+ return fe->data[1] & MVPP2_CLS_FLOW_TBL1_N_FIELDS_MASK;
+}
+
+static void mvpp2_cls_flow_hek_num_set(struct mvpp2_cls_flow_entry *fe,
+ int num_of_fields)
+{
+ fe->data[1] &= ~MVPP2_CLS_FLOW_TBL1_N_FIELDS_MASK;
+ fe->data[1] |= MVPP2_CLS_FLOW_TBL1_N_FIELDS(num_of_fields);
+}
+
+static int mvpp2_cls_flow_hek_get(struct mvpp2_cls_flow_entry *fe,
+ int field_index)
+{
+ return (fe->data[2] >> MVPP2_CLS_FLOW_TBL2_FLD_OFFS(field_index)) &
+ MVPP2_CLS_FLOW_TBL2_FLD_MASK;
+}
+
+static void mvpp2_cls_flow_hek_set(struct mvpp2_cls_flow_entry *fe,
+ int field_index, int field_id)
+{
+ fe->data[2] &= ~MVPP2_CLS_FLOW_TBL2_FLD(field_index,
+ MVPP2_CLS_FLOW_TBL2_FLD_MASK);
+ fe->data[2] |= MVPP2_CLS_FLOW_TBL2_FLD(field_index, field_id);
+}
+
+static void mvpp2_cls_flow_eng_set(struct mvpp2_cls_flow_entry *fe,
+ int engine)
+{
+ fe->data[0] &= ~MVPP2_CLS_FLOW_TBL0_ENG(MVPP2_CLS_FLOW_TBL0_ENG_MASK);
+ fe->data[0] |= MVPP2_CLS_FLOW_TBL0_ENG(engine);
+}
+
+int mvpp2_cls_flow_eng_get(struct mvpp2_cls_flow_entry *fe)
+{
+ return (fe->data[0] >> MVPP2_CLS_FLOW_TBL0_OFFS) &
+ MVPP2_CLS_FLOW_TBL0_ENG_MASK;
+}
+
+static void mvpp2_cls_flow_port_id_sel(struct mvpp2_cls_flow_entry *fe,
+ bool from_packet)
+{
+ if (from_packet)
+ fe->data[0] |= MVPP2_CLS_FLOW_TBL0_PORT_ID_SEL;
+ else
+ fe->data[0] &= ~MVPP2_CLS_FLOW_TBL0_PORT_ID_SEL;
+}
+
+static void mvpp2_cls_flow_seq_set(struct mvpp2_cls_flow_entry *fe, u32 seq)
+{
+ fe->data[1] &= ~MVPP2_CLS_FLOW_TBL1_SEQ(MVPP2_CLS_FLOW_TBL1_SEQ_MASK);
+ fe->data[1] |= MVPP2_CLS_FLOW_TBL1_SEQ(seq);
+}
+
+static void mvpp2_cls_flow_last_set(struct mvpp2_cls_flow_entry *fe,
+ bool is_last)
+{
+ fe->data[0] &= ~MVPP2_CLS_FLOW_TBL0_LAST;
+ fe->data[0] |= !!is_last;
+}
+
+static void mvpp2_cls_flow_pri_set(struct mvpp2_cls_flow_entry *fe, int prio)
+{
+ fe->data[1] &= ~MVPP2_CLS_FLOW_TBL1_PRIO(MVPP2_CLS_FLOW_TBL1_PRIO_MASK);
+ fe->data[1] |= MVPP2_CLS_FLOW_TBL1_PRIO(prio);
+}
+
+static void mvpp2_cls_flow_port_add(struct mvpp2_cls_flow_entry *fe,
+ u32 port)
+{
+ fe->data[0] |= MVPP2_CLS_FLOW_TBL0_PORT_ID(port);
+}
+
+/* Initialize the parser entry for the given flow */
+static void mvpp2_cls_flow_prs_init(struct mvpp2 *priv,
+ struct mvpp2_cls_flow *flow)
+{
+ mvpp2_prs_add_flow(priv, flow->flow_id, flow->prs_ri.ri,
+ flow->prs_ri.ri_mask);
+}
+
+/* Initialize the Lookup Id table entry for the given flow */
+static void mvpp2_cls_flow_lkp_init(struct mvpp2 *priv,
+ struct mvpp2_cls_flow *flow)
+{
+ struct mvpp2_cls_lookup_entry le;
+
+ le.way = 0;
+ le.lkpid = flow->flow_id;
+
+ /* The default RxQ for this port is set in the C2 lookup */
+ le.data = 0;
+
+ /* We point on the first lookup in the sequence for the flow, that is
+ * the C2 lookup.
+ */
+ le.data |= MVPP2_CLS_LKP_FLOW_PTR(MVPP2_FLOW_C2_ENTRY(flow->flow_id));
+
+ /* CLS is always enabled, RSS is enabled/disabled in C2 lookup */
+ le.data |= MVPP2_CLS_LKP_TBL_LOOKUP_EN_MASK;
+
+ mvpp2_cls_lookup_write(priv, &le);
+}
+
+/* Initialize the flow table entries for the given flow */
+static void mvpp2_cls_flow_init(struct mvpp2 *priv, struct mvpp2_cls_flow *flow)
+{
+ struct mvpp2_cls_flow_entry fe;
+ int i;
+
+ /* C2 lookup */
+ memset(&fe, 0, sizeof(fe));
+ fe.index = MVPP2_FLOW_C2_ENTRY(flow->flow_id);
+
+ mvpp2_cls_flow_eng_set(&fe, MVPP22_CLS_ENGINE_C2);
+ mvpp2_cls_flow_port_id_sel(&fe, true);
+ mvpp2_cls_flow_last_set(&fe, 0);
+ mvpp2_cls_flow_pri_set(&fe, 0);
+ mvpp2_cls_flow_seq_set(&fe, MVPP2_CLS_FLOW_SEQ_FIRST1);
+
+ /* Add all ports */
+ for (i = 0; i < MVPP2_MAX_PORTS; i++)
+ mvpp2_cls_flow_port_add(&fe, BIT(i));
+
+ mvpp2_cls_flow_write(priv, &fe);
+
+ /* C3Hx lookups */
+ for (i = 0; i < MVPP2_MAX_PORTS; i++) {
+ memset(&fe, 0, sizeof(fe));
+ fe.index = MVPP2_PORT_FLOW_HASH_ENTRY(i, flow->flow_id);
+
+ mvpp2_cls_flow_port_id_sel(&fe, true);
+ mvpp2_cls_flow_pri_set(&fe, i + 1);
+ mvpp2_cls_flow_seq_set(&fe, MVPP2_CLS_FLOW_SEQ_MIDDLE);
+ mvpp2_cls_flow_port_add(&fe, BIT(i));
+
+ mvpp2_cls_flow_write(priv, &fe);
+ }
+
+ /* Update the last entry */
+ mvpp2_cls_flow_last_set(&fe, 1);
+ mvpp2_cls_flow_seq_set(&fe, MVPP2_CLS_FLOW_SEQ_LAST);
+
+ mvpp2_cls_flow_write(priv, &fe);
+}
+
+/* Adds a field to the Header Extracted Key generation parameters*/
+static int mvpp2_flow_add_hek_field(struct mvpp2_cls_flow_entry *fe,
+ u32 field_id)
+{
+ int nb_fields = mvpp2_cls_flow_hek_num_get(fe);
+
+ if (nb_fields == MVPP2_FLOW_N_FIELDS)
+ return -EINVAL;
+
+ mvpp2_cls_flow_hek_set(fe, nb_fields, field_id);
+
+ mvpp2_cls_flow_hek_num_set(fe, nb_fields + 1);
+
+ return 0;
+}
+
+static int mvpp2_flow_set_hek_fields(struct mvpp2_cls_flow_entry *fe,
+ unsigned long hash_opts)
+{
+ u32 field_id;
+ int i;
+
+ /* Clear old fields */
+ mvpp2_cls_flow_hek_num_set(fe, 0);
+ fe->data[2] = 0;
+
+ for_each_set_bit(i, &hash_opts, MVPP22_CLS_HEK_N_FIELDS) {
+ switch (BIT(i)) {
+ case MVPP22_CLS_HEK_OPT_VLAN:
+ field_id = MVPP22_CLS_FIELD_VLAN;
+ break;
+ case MVPP22_CLS_HEK_OPT_IP4SA:
+ field_id = MVPP22_CLS_FIELD_IP4SA;
+ break;
+ case MVPP22_CLS_HEK_OPT_IP4DA:
+ field_id = MVPP22_CLS_FIELD_IP4DA;
+ break;
+ case MVPP22_CLS_HEK_OPT_IP6SA:
+ field_id = MVPP22_CLS_FIELD_IP6SA;
+ break;
+ case MVPP22_CLS_HEK_OPT_IP6DA:
+ field_id = MVPP22_CLS_FIELD_IP6DA;
+ break;
+ case MVPP22_CLS_HEK_OPT_L4SIP:
+ field_id = MVPP22_CLS_FIELD_L4SIP;
+ break;
+ case MVPP22_CLS_HEK_OPT_L4DIP:
+ field_id = MVPP22_CLS_FIELD_L4DIP;
+ break;
+ default:
+ return -EINVAL;
+ }
+ if (mvpp2_flow_add_hek_field(fe, field_id))
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+struct mvpp2_cls_flow *mvpp2_cls_flow_get(int flow)
+{
+ if (flow >= MVPP2_N_FLOWS)
+ return NULL;
+
+ return &cls_flows[flow];
+}
+
+/* Set the hash generation options for the given traffic flow.
+ * One traffic flow (in the ethtool sense) has multiple classification flows,
+ * to handle specific cases such as fragmentation, or the presence of a
+ * VLAN / DSA Tag.
+ *
+ * Each of these individual flows has different constraints, for example we
+ * can't hash fragmented packets on L4 data (else we would risk having packet
+ * re-ordering), so each classification flows masks the options with their
+ * supported ones.
+ *
+ */
+static int mvpp2_port_rss_hash_opts_set(struct mvpp2_port *port, int flow_type,
+ u16 requested_opts)
+{
+ struct mvpp2_cls_flow_entry fe;
+ struct mvpp2_cls_flow *flow;
+ int i, engine, flow_index;
+ u16 hash_opts;
+
+ for (i = 0; i < MVPP2_N_FLOWS; i++) {
+ flow = mvpp2_cls_flow_get(i);
+ if (!flow)
+ return -EINVAL;
+
+ if (flow->flow_type != flow_type)
+ continue;
+
+ flow_index = MVPP2_PORT_FLOW_HASH_ENTRY(port->id,
+ flow->flow_id);
+
+ mvpp2_cls_flow_read(port->priv, flow_index, &fe);
+
+ hash_opts = flow->supported_hash_opts & requested_opts;
+
+ /* Use C3HB engine to access L4 infos. This adds L4 infos to the
+ * hash parameters
+ */
+ if (hash_opts & MVPP22_CLS_HEK_L4_OPTS)
+ engine = MVPP22_CLS_ENGINE_C3HB;
+ else
+ engine = MVPP22_CLS_ENGINE_C3HA;
+
+ if (mvpp2_flow_set_hek_fields(&fe, hash_opts))
+ return -EINVAL;
+
+ mvpp2_cls_flow_eng_set(&fe, engine);
+
+ mvpp2_cls_flow_write(port->priv, &fe);
+ }
+
+ return 0;
+}
+
+u16 mvpp2_flow_get_hek_fields(struct mvpp2_cls_flow_entry *fe)
+{
+ u16 hash_opts = 0;
+ int n_fields, i, field;
+
+ n_fields = mvpp2_cls_flow_hek_num_get(fe);
+
+ for (i = 0; i < n_fields; i++) {
+ field = mvpp2_cls_flow_hek_get(fe, i);
+
+ switch (field) {
+ case MVPP22_CLS_FIELD_MAC_DA:
+ hash_opts |= MVPP22_CLS_HEK_OPT_MAC_DA;
+ break;
+ case MVPP22_CLS_FIELD_VLAN:
+ hash_opts |= MVPP22_CLS_HEK_OPT_VLAN;
+ break;
+ case MVPP22_CLS_FIELD_L3_PROTO:
+ hash_opts |= MVPP22_CLS_HEK_OPT_L3_PROTO;
+ break;
+ case MVPP22_CLS_FIELD_IP4SA:
+ hash_opts |= MVPP22_CLS_HEK_OPT_IP4SA;
+ break;
+ case MVPP22_CLS_FIELD_IP4DA:
+ hash_opts |= MVPP22_CLS_HEK_OPT_IP4DA;
+ break;
+ case MVPP22_CLS_FIELD_IP6SA:
+ hash_opts |= MVPP22_CLS_HEK_OPT_IP6SA;
+ break;
+ case MVPP22_CLS_FIELD_IP6DA:
+ hash_opts |= MVPP22_CLS_HEK_OPT_IP6DA;
+ break;
+ case MVPP22_CLS_FIELD_L4SIP:
+ hash_opts |= MVPP22_CLS_HEK_OPT_L4SIP;
+ break;
+ case MVPP22_CLS_FIELD_L4DIP:
+ hash_opts |= MVPP22_CLS_HEK_OPT_L4DIP;
+ break;
+ default:
+ break;
+ }
+ }
+ return hash_opts;
+}
+
+/* Returns the hash opts for this flow. There are several classifier flows
+ * for one traffic flow, this returns an aggregation of all configurations.
+ */
+static u16 mvpp2_port_rss_hash_opts_get(struct mvpp2_port *port, int flow_type)
+{
+ struct mvpp2_cls_flow_entry fe;
+ struct mvpp2_cls_flow *flow;
+ int i, flow_index;
+ u16 hash_opts = 0;
+
+ for (i = 0; i < MVPP2_N_FLOWS; i++) {
+ flow = mvpp2_cls_flow_get(i);
+ if (!flow)
+ return 0;
+
+ if (flow->flow_type != flow_type)
+ continue;
+
+ flow_index = MVPP2_PORT_FLOW_HASH_ENTRY(port->id,
+ flow->flow_id);
+
+ mvpp2_cls_flow_read(port->priv, flow_index, &fe);
+
+ hash_opts |= mvpp2_flow_get_hek_fields(&fe);
+ }
+
+ return hash_opts;
+}
+
+static void mvpp2_cls_port_init_flows(struct mvpp2 *priv)
+{
+ struct mvpp2_cls_flow *flow;
+ int i;
+
+ for (i = 0; i < MVPP2_N_FLOWS; i++) {
+ flow = mvpp2_cls_flow_get(i);
+ if (!flow)
+ break;
+
+ mvpp2_cls_flow_prs_init(priv, flow);
+ mvpp2_cls_flow_lkp_init(priv, flow);
+ mvpp2_cls_flow_init(priv, flow);
+ }
+}
+
+static void mvpp2_cls_c2_write(struct mvpp2 *priv,
+ struct mvpp2_cls_c2_entry *c2)
+{
+ mvpp2_write(priv, MVPP22_CLS_C2_TCAM_IDX, c2->index);
+
+ /* Write TCAM */
+ mvpp2_write(priv, MVPP22_CLS_C2_TCAM_DATA0, c2->tcam[0]);
+ mvpp2_write(priv, MVPP22_CLS_C2_TCAM_DATA1, c2->tcam[1]);
+ mvpp2_write(priv, MVPP22_CLS_C2_TCAM_DATA2, c2->tcam[2]);
+ mvpp2_write(priv, MVPP22_CLS_C2_TCAM_DATA3, c2->tcam[3]);
+ mvpp2_write(priv, MVPP22_CLS_C2_TCAM_DATA4, c2->tcam[4]);
+
+ mvpp2_write(priv, MVPP22_CLS_C2_ACT, c2->act);
+
+ mvpp2_write(priv, MVPP22_CLS_C2_ATTR0, c2->attr[0]);
+ mvpp2_write(priv, MVPP22_CLS_C2_ATTR1, c2->attr[1]);
+ mvpp2_write(priv, MVPP22_CLS_C2_ATTR2, c2->attr[2]);
+ mvpp2_write(priv, MVPP22_CLS_C2_ATTR3, c2->attr[3]);
+}
+
+void mvpp2_cls_c2_read(struct mvpp2 *priv, int index,
+ struct mvpp2_cls_c2_entry *c2)
+{
+ mvpp2_write(priv, MVPP22_CLS_C2_TCAM_IDX, index);
+
+ c2->index = index;
+
+ c2->tcam[0] = mvpp2_read(priv, MVPP22_CLS_C2_TCAM_DATA0);
+ c2->tcam[1] = mvpp2_read(priv, MVPP22_CLS_C2_TCAM_DATA1);
+ c2->tcam[2] = mvpp2_read(priv, MVPP22_CLS_C2_TCAM_DATA2);
+ c2->tcam[3] = mvpp2_read(priv, MVPP22_CLS_C2_TCAM_DATA3);
+ c2->tcam[4] = mvpp2_read(priv, MVPP22_CLS_C2_TCAM_DATA4);
+
+ c2->act = mvpp2_read(priv, MVPP22_CLS_C2_ACT);
+
+ c2->attr[0] = mvpp2_read(priv, MVPP22_CLS_C2_ATTR0);
+ c2->attr[1] = mvpp2_read(priv, MVPP22_CLS_C2_ATTR1);
+ c2->attr[2] = mvpp2_read(priv, MVPP22_CLS_C2_ATTR2);
+ c2->attr[3] = mvpp2_read(priv, MVPP22_CLS_C2_ATTR3);
+}
+
+static void mvpp2_port_c2_cls_init(struct mvpp2_port *port)
+{
+ struct mvpp2_cls_c2_entry c2;
+ u8 qh, ql, pmap;
+
+ memset(&c2, 0, sizeof(c2));
+
+ c2.index = MVPP22_CLS_C2_RSS_ENTRY(port->id);
+
+ pmap = BIT(port->id);
+ c2.tcam[4] = MVPP22_CLS_C2_PORT_ID(pmap);
+ c2.tcam[4] |= MVPP22_CLS_C2_TCAM_EN(MVPP22_CLS_C2_PORT_ID(pmap));
+
+ /* Update RSS status after matching this entry */
+ c2.act = MVPP22_CLS_C2_ACT_RSS_EN(MVPP22_C2_UPD_LOCK);
+
+ /* Mark packet as "forwarded to software", needed for RSS */
+ c2.act |= MVPP22_CLS_C2_ACT_FWD(MVPP22_C2_FWD_SW_LOCK);
+
+ /* Configure the default rx queue : Update Queue Low and Queue High, but
+ * don't lock, since the rx queue selection might be overridden by RSS
+ */
+ c2.act |= MVPP22_CLS_C2_ACT_QHIGH(MVPP22_C2_UPD) |
+ MVPP22_CLS_C2_ACT_QLOW(MVPP22_C2_UPD);
+
+ qh = (port->first_rxq >> 3) & MVPP22_CLS_C2_ATTR0_QHIGH_MASK;
+ ql = port->first_rxq & MVPP22_CLS_C2_ATTR0_QLOW_MASK;
+
+ c2.attr[0] = MVPP22_CLS_C2_ATTR0_QHIGH(qh) |
+ MVPP22_CLS_C2_ATTR0_QLOW(ql);
+
+ mvpp2_cls_c2_write(port->priv, &c2);
+}
+
/* Classifier default initialization */
void mvpp2_cls_init(struct mvpp2 *priv)
{
le.way = 1;
mvpp2_cls_lookup_write(priv, &le);
}
+
+ mvpp2_cls_port_init_flows(priv);
}
void mvpp2_cls_port_config(struct mvpp2_port *port)
/* Update lookup ID table entry */
mvpp2_cls_lookup_write(port->priv, &le);
+
+ mvpp2_port_c2_cls_init(port);
+}
+
+u32 mvpp2_cls_c2_hit_count(struct mvpp2 *priv, int c2_index)
+{
+ mvpp2_write(priv, MVPP22_CLS_C2_TCAM_IDX, c2_index);
+
+ return mvpp2_read(priv, MVPP22_CLS_C2_HIT_CTR);
+}
+
+static void mvpp2_rss_port_c2_enable(struct mvpp2_port *port)
+{
+ struct mvpp2_cls_c2_entry c2;
+
+ mvpp2_cls_c2_read(port->priv, MVPP22_CLS_C2_RSS_ENTRY(port->id), &c2);
+
+ c2.attr[2] |= MVPP22_CLS_C2_ATTR2_RSS_EN;
+
+ mvpp2_cls_c2_write(port->priv, &c2);
+}
+
+static void mvpp2_rss_port_c2_disable(struct mvpp2_port *port)
+{
+ struct mvpp2_cls_c2_entry c2;
+
+ mvpp2_cls_c2_read(port->priv, MVPP22_CLS_C2_RSS_ENTRY(port->id), &c2);
+
+ c2.attr[2] &= ~MVPP22_CLS_C2_ATTR2_RSS_EN;
+
+ mvpp2_cls_c2_write(port->priv, &c2);
+}
+
+void mvpp22_rss_enable(struct mvpp2_port *port)
+{
+ mvpp2_rss_port_c2_enable(port);
+}
+
+void mvpp22_rss_disable(struct mvpp2_port *port)
+{
+ mvpp2_rss_port_c2_disable(port);
}
/* Set CPU queue number for oversize packets */
mvpp2_write(port->priv, MVPP2_CLS_SWFWD_PCTRL_REG, val);
}
-void mvpp22_init_rss(struct mvpp2_port *port)
+static inline u32 mvpp22_rxfh_indir(struct mvpp2_port *port, u32 rxq)
+{
+ int nrxqs, cpu, cpus = num_possible_cpus();
+
+ /* Number of RXQs per CPU */
+ nrxqs = port->nrxqs / cpus;
+
+ /* CPU that will handle this rx queue */
+ cpu = rxq / nrxqs;
+
+ if (!cpu_online(cpu))
+ return port->first_rxq;
+
+ /* Indirection to better distribute the paquets on the CPUs when
+ * configuring the RSS queues.
+ */
+ return port->first_rxq + ((rxq * nrxqs + rxq / cpus) % port->nrxqs);
+}
+
+void mvpp22_rss_fill_table(struct mvpp2_port *port, u32 table)
+{
+ struct mvpp2 *priv = port->priv;
+ int i;
+
+ for (i = 0; i < MVPP22_RSS_TABLE_ENTRIES; i++) {
+ u32 sel = MVPP22_RSS_INDEX_TABLE(table) |
+ MVPP22_RSS_INDEX_TABLE_ENTRY(i);
+ mvpp2_write(priv, MVPP22_RSS_INDEX, sel);
+
+ mvpp2_write(priv, MVPP22_RSS_TABLE_ENTRY,
+ mvpp22_rxfh_indir(port, port->indir[i]));
+ }
+}
+
+int mvpp2_ethtool_rxfh_set(struct mvpp2_port *port, struct ethtool_rxnfc *info)
+{
+ u16 hash_opts = 0;
+
+ switch (info->flow_type) {
+ case TCP_V4_FLOW:
+ case UDP_V4_FLOW:
+ case TCP_V6_FLOW:
+ case UDP_V6_FLOW:
+ if (info->data & RXH_L4_B_0_1)
+ hash_opts |= MVPP22_CLS_HEK_OPT_L4SIP;
+ if (info->data & RXH_L4_B_2_3)
+ hash_opts |= MVPP22_CLS_HEK_OPT_L4DIP;
+ /* Fallthrough */
+ case IPV4_FLOW:
+ case IPV6_FLOW:
+ if (info->data & RXH_L2DA)
+ hash_opts |= MVPP22_CLS_HEK_OPT_MAC_DA;
+ if (info->data & RXH_VLAN)
+ hash_opts |= MVPP22_CLS_HEK_OPT_VLAN;
+ if (info->data & RXH_L3_PROTO)
+ hash_opts |= MVPP22_CLS_HEK_OPT_L3_PROTO;
+ if (info->data & RXH_IP_SRC)
+ hash_opts |= (MVPP22_CLS_HEK_OPT_IP4SA |
+ MVPP22_CLS_HEK_OPT_IP6SA);
+ if (info->data & RXH_IP_DST)
+ hash_opts |= (MVPP22_CLS_HEK_OPT_IP4DA |
+ MVPP22_CLS_HEK_OPT_IP6DA);
+ break;
+ default: return -EOPNOTSUPP;
+ }
+
+ return mvpp2_port_rss_hash_opts_set(port, info->flow_type, hash_opts);
+}
+
+int mvpp2_ethtool_rxfh_get(struct mvpp2_port *port, struct ethtool_rxnfc *info)
+{
+ unsigned long hash_opts;
+ int i;
+
+ hash_opts = mvpp2_port_rss_hash_opts_get(port, info->flow_type);
+ info->data = 0;
+
+ for_each_set_bit(i, &hash_opts, MVPP22_CLS_HEK_N_FIELDS) {
+ switch (BIT(i)) {
+ case MVPP22_CLS_HEK_OPT_MAC_DA:
+ info->data |= RXH_L2DA;
+ break;
+ case MVPP22_CLS_HEK_OPT_VLAN:
+ info->data |= RXH_VLAN;
+ break;
+ case MVPP22_CLS_HEK_OPT_L3_PROTO:
+ info->data |= RXH_L3_PROTO;
+ break;
+ case MVPP22_CLS_HEK_OPT_IP4SA:
+ case MVPP22_CLS_HEK_OPT_IP6SA:
+ info->data |= RXH_IP_SRC;
+ break;
+ case MVPP22_CLS_HEK_OPT_IP4DA:
+ case MVPP22_CLS_HEK_OPT_IP6DA:
+ info->data |= RXH_IP_DST;
+ break;
+ case MVPP22_CLS_HEK_OPT_L4SIP:
+ info->data |= RXH_L4_B_0_1;
+ break;
+ case MVPP22_CLS_HEK_OPT_L4DIP:
+ info->data |= RXH_L4_B_2_3;
+ break;
+ default:
+ return -EINVAL;
+ }
+ }
+ return 0;
+}
+
+void mvpp22_rss_port_init(struct mvpp2_port *port)
{
struct mvpp2 *priv = port->priv;
int i;
/* Set the table width: replace the whole classifier Rx queue number
* with the ones configured in RSS table entries.
*/
- mvpp2_write(priv, MVPP22_RSS_INDEX, MVPP22_RSS_INDEX_TABLE(0));
+ mvpp2_write(priv, MVPP22_RSS_INDEX, MVPP22_RSS_INDEX_TABLE(port->id));
mvpp2_write(priv, MVPP22_RSS_WIDTH, 8);
- /* Loop through the classifier Rx Queues and map them to a RSS table.
- * Map them all to the first table (0) by default.
+ /* The default RxQ is used as a key to select the RSS table to use.
+ * We use one RSS table per port.
*/
- for (i = 0; i < MVPP2_CLS_RX_QUEUES; i++) {
- mvpp2_write(priv, MVPP22_RSS_INDEX, MVPP22_RSS_INDEX_QUEUE(i));
- mvpp2_write(priv, MVPP22_RSS_TABLE,
- MVPP22_RSS_TABLE_POINTER(0));
- }
+ mvpp2_write(priv, MVPP22_RSS_INDEX,
+ MVPP22_RSS_INDEX_QUEUE(port->first_rxq));
+ mvpp2_write(priv, MVPP22_RXQ2RSS_TABLE,
+ MVPP22_RSS_TABLE_POINTER(port->id));
/* Configure the first table to evenly distribute the packets across
- * real Rx Queues. The table entries map a hash to an port Rx Queue.
+ * real Rx Queues. The table entries map a hash to a port Rx Queue.
*/
- for (i = 0; i < MVPP22_RSS_TABLE_ENTRIES; i++) {
- u32 sel = MVPP22_RSS_INDEX_TABLE(0) |
- MVPP22_RSS_INDEX_TABLE_ENTRY(i);
- mvpp2_write(priv, MVPP22_RSS_INDEX, sel);
+ for (i = 0; i < MVPP22_RSS_TABLE_ENTRIES; i++)
+ port->indir[i] = ethtool_rxfh_indir_default(i, port->nrxqs);
- mvpp2_write(priv, MVPP22_RSS_TABLE_ENTRY, i % port->nrxqs);
- }
+ mvpp22_rss_fill_table(port, port->id);
+ /* Configure default flows */
+ mvpp2_port_rss_hash_opts_set(port, IPV4_FLOW, MVPP22_CLS_HEK_IP4_2T);
+ mvpp2_port_rss_hash_opts_set(port, IPV6_FLOW, MVPP22_CLS_HEK_IP6_2T);
+ mvpp2_port_rss_hash_opts_set(port, TCP_V4_FLOW, MVPP22_CLS_HEK_IP4_5T);
+ mvpp2_port_rss_hash_opts_set(port, TCP_V6_FLOW, MVPP22_CLS_HEK_IP6_5T);
+ mvpp2_port_rss_hash_opts_set(port, UDP_V4_FLOW, MVPP22_CLS_HEK_IP4_5T);
+ mvpp2_port_rss_hash_opts_set(port, UDP_V6_FLOW, MVPP22_CLS_HEK_IP6_5T);
}
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* RSS and Classifier definitions for Marvell PPv2 Network Controller
*
* Copyright (C) 2014 Marvell
*
* Marcin Wojtas <mw@semihalf.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
*/
#ifndef _MVPP2_CLS_H_
#define _MVPP2_CLS_H_
+#include "mvpp2.h"
+#include "mvpp2_prs.h"
+
/* Classifier constants */
#define MVPP2_CLS_FLOWS_TBL_SIZE 512
#define MVPP2_CLS_FLOWS_TBL_DATA_WORDS 3
#define MVPP2_CLS_LKP_TBL_SIZE 64
#define MVPP2_CLS_RX_QUEUES 256
-/* RSS constants */
-#define MVPP22_RSS_TABLE_ENTRIES 32
+/* Classifier flow constants */
+
+#define MVPP2_FLOW_N_FIELDS 4
+
+enum mvpp2_cls_engine {
+ MVPP22_CLS_ENGINE_C2 = 1,
+ MVPP22_CLS_ENGINE_C3A,
+ MVPP22_CLS_ENGINE_C3B,
+ MVPP22_CLS_ENGINE_C4,
+ MVPP22_CLS_ENGINE_C3HA = 6,
+ MVPP22_CLS_ENGINE_C3HB = 7,
+};
+
+#define MVPP22_CLS_HEK_OPT_MAC_DA BIT(0)
+#define MVPP22_CLS_HEK_OPT_VLAN BIT(1)
+#define MVPP22_CLS_HEK_OPT_L3_PROTO BIT(2)
+#define MVPP22_CLS_HEK_OPT_IP4SA BIT(3)
+#define MVPP22_CLS_HEK_OPT_IP4DA BIT(4)
+#define MVPP22_CLS_HEK_OPT_IP6SA BIT(5)
+#define MVPP22_CLS_HEK_OPT_IP6DA BIT(6)
+#define MVPP22_CLS_HEK_OPT_L4SIP BIT(7)
+#define MVPP22_CLS_HEK_OPT_L4DIP BIT(8)
+#define MVPP22_CLS_HEK_N_FIELDS 9
+
+#define MVPP22_CLS_HEK_L4_OPTS (MVPP22_CLS_HEK_OPT_L4SIP | \
+ MVPP22_CLS_HEK_OPT_L4DIP)
+
+#define MVPP22_CLS_HEK_IP4_2T (MVPP22_CLS_HEK_OPT_IP4SA | \
+ MVPP22_CLS_HEK_OPT_IP4DA)
+
+#define MVPP22_CLS_HEK_IP6_2T (MVPP22_CLS_HEK_OPT_IP6SA | \
+ MVPP22_CLS_HEK_OPT_IP6DA)
+
+/* The fifth tuple in "5T" is the L4_Info field */
+#define MVPP22_CLS_HEK_IP4_5T (MVPP22_CLS_HEK_IP4_2T | \
+ MVPP22_CLS_HEK_L4_OPTS)
+
+#define MVPP22_CLS_HEK_IP6_5T (MVPP22_CLS_HEK_IP6_2T | \
+ MVPP22_CLS_HEK_L4_OPTS)
+
+enum mvpp2_cls_field_id {
+ MVPP22_CLS_FIELD_MAC_DA = 0x03,
+ MVPP22_CLS_FIELD_VLAN = 0x06,
+ MVPP22_CLS_FIELD_L3_PROTO = 0x0f,
+ MVPP22_CLS_FIELD_IP4SA = 0x10,
+ MVPP22_CLS_FIELD_IP4DA = 0x11,
+ MVPP22_CLS_FIELD_IP6SA = 0x17,
+ MVPP22_CLS_FIELD_IP6DA = 0x1a,
+ MVPP22_CLS_FIELD_L4SIP = 0x1d,
+ MVPP22_CLS_FIELD_L4DIP = 0x1e,
+};
+
+enum mvpp2_cls_flow_seq {
+ MVPP2_CLS_FLOW_SEQ_NORMAL = 0,
+ MVPP2_CLS_FLOW_SEQ_FIRST1,
+ MVPP2_CLS_FLOW_SEQ_FIRST2,
+ MVPP2_CLS_FLOW_SEQ_LAST,
+ MVPP2_CLS_FLOW_SEQ_MIDDLE
+};
+
+/* Classifier C2 engine constants */
+#define MVPP22_CLS_C2_TCAM_EN(data) ((data) << 16)
+
+enum mvpp22_cls_c2_action {
+ MVPP22_C2_NO_UPD = 0,
+ MVPP22_C2_NO_UPD_LOCK,
+ MVPP22_C2_UPD,
+ MVPP22_C2_UPD_LOCK,
+};
+
+enum mvpp22_cls_c2_fwd_action {
+ MVPP22_C2_FWD_NO_UPD = 0,
+ MVPP22_C2_FWD_NO_UPD_LOCK,
+ MVPP22_C2_FWD_SW,
+ MVPP22_C2_FWD_SW_LOCK,
+ MVPP22_C2_FWD_HW,
+ MVPP22_C2_FWD_HW_LOCK,
+ MVPP22_C2_FWD_HW_LOW_LAT,
+ MVPP22_C2_FWD_HW_LOW_LAT_LOCK,
+};
+
+#define MVPP2_CLS_C2_TCAM_WORDS 5
+#define MVPP2_CLS_C2_ATTR_WORDS 5
+
+struct mvpp2_cls_c2_entry {
+ u32 index;
+ u32 tcam[MVPP2_CLS_C2_TCAM_WORDS];
+ u32 act;
+ u32 attr[MVPP2_CLS_C2_ATTR_WORDS];
+};
+
+/* Classifier C2 engine entries */
+#define MVPP22_CLS_C2_RSS_ENTRY(port) (port)
+#define MVPP22_CLS_C2_N_ENTRIES MVPP2_MAX_PORTS
+/* RSS flow entries in the flow table. We have 2 entries per port for RSS.
+ *
+ * The first performs a lookup using the C2 TCAM engine, to tag the
+ * packet for software forwarding (needed for RSS), enable or disable RSS, and
+ * assign the default rx queue.
+ *
+ * The second configures the hash generation, by specifying which fields of the
+ * packet header are used to generate the hash, and specifies the relevant hash
+ * engine to use.
+ */
+#define MVPP22_RSS_FLOW_C2_OFFS 0
+#define MVPP22_RSS_FLOW_HASH_OFFS 1
+#define MVPP22_RSS_FLOW_SIZE (MVPP22_RSS_FLOW_HASH_OFFS + 1)
+
+#define MVPP22_RSS_FLOW_C2(port) ((port) * MVPP22_RSS_FLOW_SIZE + \
+ MVPP22_RSS_FLOW_C2_OFFS)
+#define MVPP22_RSS_FLOW_HASH(port) ((port) * MVPP22_RSS_FLOW_SIZE + \
+ MVPP22_RSS_FLOW_HASH_OFFS)
+#define MVPP22_RSS_FLOW_FIRST(port) MVPP22_RSS_FLOW_C2(port)
+
+/* Packet flow ID */
+enum mvpp2_prs_flow {
+ MVPP2_FL_START = 8,
+ MVPP2_FL_IP4_TCP_NF_UNTAG = MVPP2_FL_START,
+ MVPP2_FL_IP4_UDP_NF_UNTAG,
+ MVPP2_FL_IP4_TCP_NF_TAG,
+ MVPP2_FL_IP4_UDP_NF_TAG,
+ MVPP2_FL_IP6_TCP_NF_UNTAG,
+ MVPP2_FL_IP6_UDP_NF_UNTAG,
+ MVPP2_FL_IP6_TCP_NF_TAG,
+ MVPP2_FL_IP6_UDP_NF_TAG,
+ MVPP2_FL_IP4_TCP_FRAG_UNTAG,
+ MVPP2_FL_IP4_UDP_FRAG_UNTAG,
+ MVPP2_FL_IP4_TCP_FRAG_TAG,
+ MVPP2_FL_IP4_UDP_FRAG_TAG,
+ MVPP2_FL_IP6_TCP_FRAG_UNTAG,
+ MVPP2_FL_IP6_UDP_FRAG_UNTAG,
+ MVPP2_FL_IP6_TCP_FRAG_TAG,
+ MVPP2_FL_IP6_UDP_FRAG_TAG,
+ MVPP2_FL_IP4_UNTAG, /* non-TCP, non-UDP, same for below */
+ MVPP2_FL_IP4_TAG,
+ MVPP2_FL_IP6_UNTAG,
+ MVPP2_FL_IP6_TAG,
+ MVPP2_FL_NON_IP_UNTAG,
+ MVPP2_FL_NON_IP_TAG,
+ MVPP2_FL_LAST,
+};
+
+struct mvpp2_cls_flow {
+ /* The L2-L4 traffic flow type */
+ int flow_type;
+
+ /* The first id in the flow table for this flow */
+ u16 flow_id;
+
+ /* The supported HEK fields for this flow */
+ u16 supported_hash_opts;
+
+ /* The Header Parser result_info that matches this flow */
+ struct mvpp2_prs_result_info prs_ri;
+};
+
+#define MVPP2_N_FLOWS 52
+
+#define MVPP2_ENTRIES_PER_FLOW (MVPP2_MAX_PORTS + 1)
+#define MVPP2_FLOW_C2_ENTRY(id) ((id) * MVPP2_ENTRIES_PER_FLOW)
+#define MVPP2_PORT_FLOW_HASH_ENTRY(port, id) ((id) * MVPP2_ENTRIES_PER_FLOW + \
+ (port) + 1)
struct mvpp2_cls_flow_entry {
u32 index;
u32 data[MVPP2_CLS_FLOWS_TBL_DATA_WORDS];
u32 data;
};
-void mvpp22_init_rss(struct mvpp2_port *port);
+void mvpp22_rss_fill_table(struct mvpp2_port *port, u32 table);
+
+void mvpp22_rss_port_init(struct mvpp2_port *port);
+
+void mvpp22_rss_enable(struct mvpp2_port *port);
+void mvpp22_rss_disable(struct mvpp2_port *port);
+
+int mvpp2_ethtool_rxfh_get(struct mvpp2_port *port, struct ethtool_rxnfc *info);
+int mvpp2_ethtool_rxfh_set(struct mvpp2_port *port, struct ethtool_rxnfc *info);
void mvpp2_cls_init(struct mvpp2 *priv);
void mvpp2_cls_oversize_rxq_set(struct mvpp2_port *port);
+int mvpp2_cls_flow_eng_get(struct mvpp2_cls_flow_entry *fe);
+
+u16 mvpp2_flow_get_hek_fields(struct mvpp2_cls_flow_entry *fe);
+
+struct mvpp2_cls_flow *mvpp2_cls_flow_get(int flow);
+
+u32 mvpp2_cls_flow_hits(struct mvpp2 *priv, int index);
+
+void mvpp2_cls_flow_read(struct mvpp2 *priv, int index,
+ struct mvpp2_cls_flow_entry *fe);
+
+u32 mvpp2_cls_lookup_hits(struct mvpp2 *priv, int index);
+
+void mvpp2_cls_lookup_read(struct mvpp2 *priv, int lkpid, int way,
+ struct mvpp2_cls_lookup_entry *le);
+
+u32 mvpp2_cls_c2_hit_count(struct mvpp2 *priv, int c2_index);
+
+void mvpp2_cls_c2_read(struct mvpp2 *priv, int index,
+ struct mvpp2_cls_c2_entry *c2);
+
#endif
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Driver for Marvell PPv2 network controller for Armada 375 SoC.
+ *
+ * Copyright (C) 2018 Marvell
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/debugfs.h>
+
+#include "mvpp2.h"
+#include "mvpp2_prs.h"
+#include "mvpp2_cls.h"
+
+struct mvpp2_dbgfs_prs_entry {
+ int tid;
+ struct mvpp2 *priv;
+};
+
+struct mvpp2_dbgfs_flow_entry {
+ int flow;
+ struct mvpp2 *priv;
+};
+
+struct mvpp2_dbgfs_port_flow_entry {
+ struct mvpp2_port *port;
+ struct mvpp2_dbgfs_flow_entry *dbg_fe;
+};
+
+static int mvpp2_dbgfs_flow_flt_hits_show(struct seq_file *s, void *unused)
+{
+ struct mvpp2_dbgfs_flow_entry *entry = s->private;
+ int id = MVPP2_FLOW_C2_ENTRY(entry->flow);
+
+ u32 hits = mvpp2_cls_flow_hits(entry->priv, id);
+
+ seq_printf(s, "%u\n", hits);
+
+ return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_flow_flt_hits);
+
+static int mvpp2_dbgfs_flow_dec_hits_show(struct seq_file *s, void *unused)
+{
+ struct mvpp2_dbgfs_flow_entry *entry = s->private;
+
+ u32 hits = mvpp2_cls_lookup_hits(entry->priv, entry->flow);
+
+ seq_printf(s, "%u\n", hits);
+
+ return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_flow_dec_hits);
+
+static int mvpp2_dbgfs_flow_type_show(struct seq_file *s, void *unused)
+{
+ struct mvpp2_dbgfs_flow_entry *entry = s->private;
+ struct mvpp2_cls_flow *f;
+ const char *flow_name;
+
+ f = mvpp2_cls_flow_get(entry->flow);
+ if (!f)
+ return -EINVAL;
+
+ switch (f->flow_type) {
+ case IPV4_FLOW:
+ flow_name = "ipv4";
+ break;
+ case IPV6_FLOW:
+ flow_name = "ipv6";
+ break;
+ case TCP_V4_FLOW:
+ flow_name = "tcp4";
+ break;
+ case TCP_V6_FLOW:
+ flow_name = "tcp6";
+ break;
+ case UDP_V4_FLOW:
+ flow_name = "udp4";
+ break;
+ case UDP_V6_FLOW:
+ flow_name = "udp6";
+ break;
+ default:
+ flow_name = "other";
+ }
+
+ seq_printf(s, "%s\n", flow_name);
+
+ return 0;
+}
+
+static int mvpp2_dbgfs_flow_type_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, mvpp2_dbgfs_flow_type_show, inode->i_private);
+}
+
+static int mvpp2_dbgfs_flow_type_release(struct inode *inode, struct file *file)
+{
+ struct seq_file *seq = file->private_data;
+ struct mvpp2_dbgfs_flow_entry *flow_entry = seq->private;
+
+ kfree(flow_entry);
+ return single_release(inode, file);
+}
+
+static const struct file_operations mvpp2_dbgfs_flow_type_fops = {
+ .open = mvpp2_dbgfs_flow_type_open,
+ .read = seq_read,
+ .release = mvpp2_dbgfs_flow_type_release,
+};
+
+static int mvpp2_dbgfs_flow_id_show(struct seq_file *s, void *unused)
+{
+ struct mvpp2_dbgfs_flow_entry *entry = s->private;
+ struct mvpp2_cls_flow *f;
+
+ f = mvpp2_cls_flow_get(entry->flow);
+ if (!f)
+ return -EINVAL;
+
+ seq_printf(s, "%d\n", f->flow_id);
+
+ return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_flow_id);
+
+static int mvpp2_dbgfs_port_flow_hash_opt_show(struct seq_file *s, void *unused)
+{
+ struct mvpp2_dbgfs_port_flow_entry *entry = s->private;
+ struct mvpp2_port *port = entry->port;
+ struct mvpp2_cls_flow_entry fe;
+ struct mvpp2_cls_flow *f;
+ int flow_index;
+ u16 hash_opts;
+
+ f = mvpp2_cls_flow_get(entry->dbg_fe->flow);
+ if (!f)
+ return -EINVAL;
+
+ flow_index = MVPP2_PORT_FLOW_HASH_ENTRY(entry->port->id, f->flow_id);
+
+ mvpp2_cls_flow_read(port->priv, flow_index, &fe);
+
+ hash_opts = mvpp2_flow_get_hek_fields(&fe);
+
+ seq_printf(s, "0x%04x\n", hash_opts);
+
+ return 0;
+}
+
+static int mvpp2_dbgfs_port_flow_hash_opt_open(struct inode *inode,
+ struct file *file)
+{
+ return single_open(file, mvpp2_dbgfs_port_flow_hash_opt_show,
+ inode->i_private);
+}
+
+static int mvpp2_dbgfs_port_flow_hash_opt_release(struct inode *inode,
+ struct file *file)
+{
+ struct seq_file *seq = file->private_data;
+ struct mvpp2_dbgfs_port_flow_entry *flow_entry = seq->private;
+
+ kfree(flow_entry);
+ return single_release(inode, file);
+}
+
+static const struct file_operations mvpp2_dbgfs_port_flow_hash_opt_fops = {
+ .open = mvpp2_dbgfs_port_flow_hash_opt_open,
+ .read = seq_read,
+ .release = mvpp2_dbgfs_port_flow_hash_opt_release,
+};
+
+static int mvpp2_dbgfs_port_flow_engine_show(struct seq_file *s, void *unused)
+{
+ struct mvpp2_dbgfs_port_flow_entry *entry = s->private;
+ struct mvpp2_port *port = entry->port;
+ struct mvpp2_cls_flow_entry fe;
+ struct mvpp2_cls_flow *f;
+ int flow_index, engine;
+
+ f = mvpp2_cls_flow_get(entry->dbg_fe->flow);
+ if (!f)
+ return -EINVAL;
+
+ flow_index = MVPP2_PORT_FLOW_HASH_ENTRY(entry->port->id, f->flow_id);
+
+ mvpp2_cls_flow_read(port->priv, flow_index, &fe);
+
+ engine = mvpp2_cls_flow_eng_get(&fe);
+
+ seq_printf(s, "%d\n", engine);
+
+ return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_port_flow_engine);
+
+static int mvpp2_dbgfs_flow_c2_hits_show(struct seq_file *s, void *unused)
+{
+ struct mvpp2_port *port = s->private;
+ u32 hits;
+
+ hits = mvpp2_cls_c2_hit_count(port->priv,
+ MVPP22_CLS_C2_RSS_ENTRY(port->id));
+
+ seq_printf(s, "%u\n", hits);
+
+ return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_flow_c2_hits);
+
+static int mvpp2_dbgfs_flow_c2_rxq_show(struct seq_file *s, void *unused)
+{
+ struct mvpp2_port *port = s->private;
+ struct mvpp2_cls_c2_entry c2;
+ u8 qh, ql;
+
+ mvpp2_cls_c2_read(port->priv, MVPP22_CLS_C2_RSS_ENTRY(port->id), &c2);
+
+ qh = (c2.attr[0] >> MVPP22_CLS_C2_ATTR0_QHIGH_OFFS) &
+ MVPP22_CLS_C2_ATTR0_QHIGH_MASK;
+
+ ql = (c2.attr[0] >> MVPP22_CLS_C2_ATTR0_QLOW_OFFS) &
+ MVPP22_CLS_C2_ATTR0_QLOW_MASK;
+
+ seq_printf(s, "%d\n", (qh << 3 | ql));
+
+ return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_flow_c2_rxq);
+
+static int mvpp2_dbgfs_flow_c2_enable_show(struct seq_file *s, void *unused)
+{
+ struct mvpp2_port *port = s->private;
+ struct mvpp2_cls_c2_entry c2;
+ int enabled;
+
+ mvpp2_cls_c2_read(port->priv, MVPP22_CLS_C2_RSS_ENTRY(port->id), &c2);
+
+ enabled = !!(c2.attr[2] | MVPP22_CLS_C2_ATTR2_RSS_EN);
+
+ seq_printf(s, "%d\n", enabled);
+
+ return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_flow_c2_enable);
+
+static int mvpp2_dbgfs_port_vid_show(struct seq_file *s, void *unused)
+{
+ struct mvpp2_port *port = s->private;
+ unsigned char byte[2], enable[2];
+ struct mvpp2 *priv = port->priv;
+ struct mvpp2_prs_entry pe;
+ unsigned long pmap;
+ u16 rvid;
+ int tid;
+
+ for (tid = MVPP2_PRS_VID_PORT_FIRST(port->id);
+ tid <= MVPP2_PRS_VID_PORT_LAST(port->id); tid++) {
+ mvpp2_prs_init_from_hw(priv, &pe, tid);
+
+ pmap = mvpp2_prs_tcam_port_map_get(&pe);
+
+ if (!priv->prs_shadow[tid].valid)
+ continue;
+
+ if (!test_bit(port->id, &pmap))
+ continue;
+
+ mvpp2_prs_tcam_data_byte_get(&pe, 2, &byte[0], &enable[0]);
+ mvpp2_prs_tcam_data_byte_get(&pe, 3, &byte[1], &enable[1]);
+
+ rvid = ((byte[0] & 0xf) << 8) + byte[1];
+
+ seq_printf(s, "%u\n", rvid);
+ }
+
+ return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_port_vid);
+
+static int mvpp2_dbgfs_port_parser_show(struct seq_file *s, void *unused)
+{
+ struct mvpp2_port *port = s->private;
+ struct mvpp2 *priv = port->priv;
+ struct mvpp2_prs_entry pe;
+ unsigned long pmap;
+ int i;
+
+ for (i = 0; i < MVPP2_PRS_TCAM_SRAM_SIZE; i++) {
+ mvpp2_prs_init_from_hw(port->priv, &pe, i);
+
+ pmap = mvpp2_prs_tcam_port_map_get(&pe);
+ if (priv->prs_shadow[i].valid && test_bit(port->id, &pmap))
+ seq_printf(s, "%03d\n", i);
+ }
+
+ return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_port_parser);
+
+static int mvpp2_dbgfs_filter_show(struct seq_file *s, void *unused)
+{
+ struct mvpp2_port *port = s->private;
+ struct mvpp2 *priv = port->priv;
+ struct mvpp2_prs_entry pe;
+ unsigned long pmap;
+ int index, tid;
+
+ for (tid = MVPP2_PE_MAC_RANGE_START;
+ tid <= MVPP2_PE_MAC_RANGE_END; tid++) {
+ unsigned char da[ETH_ALEN], da_mask[ETH_ALEN];
+
+ if (!priv->prs_shadow[tid].valid ||
+ priv->prs_shadow[tid].lu != MVPP2_PRS_LU_MAC ||
+ priv->prs_shadow[tid].udf != MVPP2_PRS_UDF_MAC_DEF)
+ continue;
+
+ mvpp2_prs_init_from_hw(priv, &pe, tid);
+
+ pmap = mvpp2_prs_tcam_port_map_get(&pe);
+
+ /* We only want entries active on this port */
+ if (!test_bit(port->id, &pmap))
+ continue;
+
+ /* Read mac addr from entry */
+ for (index = 0; index < ETH_ALEN; index++)
+ mvpp2_prs_tcam_data_byte_get(&pe, index, &da[index],
+ &da_mask[index]);
+
+ seq_printf(s, "%pM\n", da);
+ }
+
+ return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_filter);
+
+static int mvpp2_dbgfs_prs_lu_show(struct seq_file *s, void *unused)
+{
+ struct mvpp2_dbgfs_prs_entry *entry = s->private;
+ struct mvpp2 *priv = entry->priv;
+
+ seq_printf(s, "%x\n", priv->prs_shadow[entry->tid].lu);
+
+ return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_prs_lu);
+
+static int mvpp2_dbgfs_prs_pmap_show(struct seq_file *s, void *unused)
+{
+ struct mvpp2_dbgfs_prs_entry *entry = s->private;
+ struct mvpp2_prs_entry pe;
+ unsigned int pmap;
+
+ mvpp2_prs_init_from_hw(entry->priv, &pe, entry->tid);
+
+ pmap = mvpp2_prs_tcam_port_map_get(&pe);
+ pmap &= MVPP2_PRS_PORT_MASK;
+
+ seq_printf(s, "%02x\n", pmap);
+
+ return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_prs_pmap);
+
+static int mvpp2_dbgfs_prs_ai_show(struct seq_file *s, void *unused)
+{
+ struct mvpp2_dbgfs_prs_entry *entry = s->private;
+ struct mvpp2_prs_entry pe;
+ unsigned char ai, ai_mask;
+
+ mvpp2_prs_init_from_hw(entry->priv, &pe, entry->tid);
+
+ ai = pe.tcam[MVPP2_PRS_TCAM_AI_WORD] & MVPP2_PRS_AI_MASK;
+ ai_mask = (pe.tcam[MVPP2_PRS_TCAM_AI_WORD] >> 16) & MVPP2_PRS_AI_MASK;
+
+ seq_printf(s, "%02x %02x\n", ai, ai_mask);
+
+ return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_prs_ai);
+
+static int mvpp2_dbgfs_prs_hdata_show(struct seq_file *s, void *unused)
+{
+ struct mvpp2_dbgfs_prs_entry *entry = s->private;
+ struct mvpp2_prs_entry pe;
+ unsigned char data[8], mask[8];
+ int i;
+
+ mvpp2_prs_init_from_hw(entry->priv, &pe, entry->tid);
+
+ for (i = 0; i < 8; i++)
+ mvpp2_prs_tcam_data_byte_get(&pe, i, &data[i], &mask[i]);
+
+ seq_printf(s, "%*phN %*phN\n", 8, data, 8, mask);
+
+ return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_prs_hdata);
+
+static int mvpp2_dbgfs_prs_sram_show(struct seq_file *s, void *unused)
+{
+ struct mvpp2_dbgfs_prs_entry *entry = s->private;
+ struct mvpp2_prs_entry pe;
+
+ mvpp2_prs_init_from_hw(entry->priv, &pe, entry->tid);
+
+ seq_printf(s, "%*phN\n", 14, pe.sram);
+
+ return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_prs_sram);
+
+static int mvpp2_dbgfs_prs_hits_show(struct seq_file *s, void *unused)
+{
+ struct mvpp2_dbgfs_prs_entry *entry = s->private;
+ int val;
+
+ val = mvpp2_prs_hits(entry->priv, entry->tid);
+ if (val < 0)
+ return val;
+
+ seq_printf(s, "%d\n", val);
+
+ return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_prs_hits);
+
+static int mvpp2_dbgfs_prs_valid_show(struct seq_file *s, void *unused)
+{
+ struct mvpp2_dbgfs_prs_entry *entry = s->private;
+ struct mvpp2 *priv = entry->priv;
+ int tid = entry->tid;
+
+ seq_printf(s, "%d\n", priv->prs_shadow[tid].valid ? 1 : 0);
+
+ return 0;
+}
+
+static int mvpp2_dbgfs_prs_valid_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, mvpp2_dbgfs_prs_valid_show, inode->i_private);
+}
+
+static int mvpp2_dbgfs_prs_valid_release(struct inode *inode, struct file *file)
+{
+ struct seq_file *seq = file->private_data;
+ struct mvpp2_dbgfs_prs_entry *entry = seq->private;
+
+ kfree(entry);
+ return single_release(inode, file);
+}
+
+static const struct file_operations mvpp2_dbgfs_prs_valid_fops = {
+ .open = mvpp2_dbgfs_prs_valid_open,
+ .read = seq_read,
+ .release = mvpp2_dbgfs_prs_valid_release,
+};
+
+static int mvpp2_dbgfs_flow_port_init(struct dentry *parent,
+ struct mvpp2_port *port,
+ struct mvpp2_dbgfs_flow_entry *entry)
+{
+ struct mvpp2_dbgfs_port_flow_entry *port_entry;
+ struct dentry *port_dir;
+
+ port_dir = debugfs_create_dir(port->dev->name, parent);
+ if (IS_ERR(port_dir))
+ return PTR_ERR(port_dir);
+
+ /* This will be freed by 'hash_opts' release op */
+ port_entry = kmalloc(sizeof(*port_entry), GFP_KERNEL);
+ if (!port_entry)
+ return -ENOMEM;
+
+ port_entry->port = port;
+ port_entry->dbg_fe = entry;
+
+ debugfs_create_file("hash_opts", 0444, port_dir, port_entry,
+ &mvpp2_dbgfs_port_flow_hash_opt_fops);
+
+ debugfs_create_file("engine", 0444, port_dir, port_entry,
+ &mvpp2_dbgfs_port_flow_engine_fops);
+
+ return 0;
+}
+
+static int mvpp2_dbgfs_flow_entry_init(struct dentry *parent,
+ struct mvpp2 *priv, int flow)
+{
+ struct mvpp2_dbgfs_flow_entry *entry;
+ struct dentry *flow_entry_dir;
+ char flow_entry_name[10];
+ int i, ret;
+
+ sprintf(flow_entry_name, "%02d", flow);
+
+ flow_entry_dir = debugfs_create_dir(flow_entry_name, parent);
+ if (!flow_entry_dir)
+ return -ENOMEM;
+
+ /* This will be freed by 'type' release op */
+ entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+ if (!entry)
+ return -ENOMEM;
+
+ entry->flow = flow;
+ entry->priv = priv;
+
+ debugfs_create_file("flow_hits", 0444, flow_entry_dir, entry,
+ &mvpp2_dbgfs_flow_flt_hits_fops);
+
+ debugfs_create_file("dec_hits", 0444, flow_entry_dir, entry,
+ &mvpp2_dbgfs_flow_dec_hits_fops);
+
+ debugfs_create_file("type", 0444, flow_entry_dir, entry,
+ &mvpp2_dbgfs_flow_type_fops);
+
+ debugfs_create_file("id", 0444, flow_entry_dir, entry,
+ &mvpp2_dbgfs_flow_id_fops);
+
+ /* Create entry for each port */
+ for (i = 0; i < priv->port_count; i++) {
+ ret = mvpp2_dbgfs_flow_port_init(flow_entry_dir,
+ priv->port_list[i], entry);
+ if (ret)
+ return ret;
+ }
+ return 0;
+}
+
+static int mvpp2_dbgfs_flow_init(struct dentry *parent, struct mvpp2 *priv)
+{
+ struct dentry *flow_dir;
+ int i, ret;
+
+ flow_dir = debugfs_create_dir("flows", parent);
+ if (!flow_dir)
+ return -ENOMEM;
+
+ for (i = 0; i < MVPP2_N_FLOWS; i++) {
+ ret = mvpp2_dbgfs_flow_entry_init(flow_dir, priv, i);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
+static int mvpp2_dbgfs_prs_entry_init(struct dentry *parent,
+ struct mvpp2 *priv, int tid)
+{
+ struct mvpp2_dbgfs_prs_entry *entry;
+ struct dentry *prs_entry_dir;
+ char prs_entry_name[10];
+
+ if (tid >= MVPP2_PRS_TCAM_SRAM_SIZE)
+ return -EINVAL;
+
+ sprintf(prs_entry_name, "%03d", tid);
+
+ prs_entry_dir = debugfs_create_dir(prs_entry_name, parent);
+ if (!prs_entry_dir)
+ return -ENOMEM;
+
+ /* The 'valid' entry's ops will free that */
+ entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+ if (!entry)
+ return -ENOMEM;
+
+ entry->tid = tid;
+ entry->priv = priv;
+
+ /* Create each attr */
+ debugfs_create_file("sram", 0444, prs_entry_dir, entry,
+ &mvpp2_dbgfs_prs_sram_fops);
+
+ debugfs_create_file("valid", 0644, prs_entry_dir, entry,
+ &mvpp2_dbgfs_prs_valid_fops);
+
+ debugfs_create_file("lookup_id", 0644, prs_entry_dir, entry,
+ &mvpp2_dbgfs_prs_lu_fops);
+
+ debugfs_create_file("ai", 0644, prs_entry_dir, entry,
+ &mvpp2_dbgfs_prs_ai_fops);
+
+ debugfs_create_file("header_data", 0644, prs_entry_dir, entry,
+ &mvpp2_dbgfs_prs_hdata_fops);
+
+ debugfs_create_file("hits", 0444, prs_entry_dir, entry,
+ &mvpp2_dbgfs_prs_hits_fops);
+
+ return 0;
+}
+
+static int mvpp2_dbgfs_prs_init(struct dentry *parent, struct mvpp2 *priv)
+{
+ struct dentry *prs_dir;
+ int i, ret;
+
+ prs_dir = debugfs_create_dir("parser", parent);
+ if (!prs_dir)
+ return -ENOMEM;
+
+ for (i = 0; i < MVPP2_PRS_TCAM_SRAM_SIZE; i++) {
+ ret = mvpp2_dbgfs_prs_entry_init(prs_dir, priv, i);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
+static int mvpp2_dbgfs_port_init(struct dentry *parent,
+ struct mvpp2_port *port)
+{
+ struct dentry *port_dir;
+
+ port_dir = debugfs_create_dir(port->dev->name, parent);
+ if (IS_ERR(port_dir))
+ return PTR_ERR(port_dir);
+
+ debugfs_create_file("parser_entries", 0444, port_dir, port,
+ &mvpp2_dbgfs_port_parser_fops);
+
+ debugfs_create_file("mac_filter", 0444, port_dir, port,
+ &mvpp2_dbgfs_filter_fops);
+
+ debugfs_create_file("vid_filter", 0444, port_dir, port,
+ &mvpp2_dbgfs_port_vid_fops);
+
+ debugfs_create_file("c2_hits", 0444, port_dir, port,
+ &mvpp2_dbgfs_flow_c2_hits_fops);
+
+ debugfs_create_file("default_rxq", 0444, port_dir, port,
+ &mvpp2_dbgfs_flow_c2_rxq_fops);
+
+ debugfs_create_file("rss_enable", 0444, port_dir, port,
+ &mvpp2_dbgfs_flow_c2_enable_fops);
+
+ return 0;
+}
+
+void mvpp2_dbgfs_cleanup(struct mvpp2 *priv)
+{
+ debugfs_remove_recursive(priv->dbgfs_dir);
+}
+
+void mvpp2_dbgfs_init(struct mvpp2 *priv, const char *name)
+{
+ struct dentry *mvpp2_dir, *mvpp2_root;
+ int ret, i;
+
+ mvpp2_root = debugfs_lookup(MVPP2_DRIVER_NAME, NULL);
+ if (!mvpp2_root) {
+ mvpp2_root = debugfs_create_dir(MVPP2_DRIVER_NAME, NULL);
+ if (IS_ERR(mvpp2_root))
+ return;
+ }
+
+ mvpp2_dir = debugfs_create_dir(name, mvpp2_root);
+ if (IS_ERR(mvpp2_dir))
+ return;
+
+ priv->dbgfs_dir = mvpp2_dir;
+
+ ret = mvpp2_dbgfs_prs_init(mvpp2_dir, priv);
+ if (ret)
+ goto err;
+
+ for (i = 0; i < priv->port_count; i++) {
+ ret = mvpp2_dbgfs_port_init(mvpp2_dir, priv->port_list[i]);
+ if (ret)
+ goto err;
+ }
+
+ ret = mvpp2_dbgfs_flow_init(mvpp2_dir, priv);
+ if (ret)
+ goto err;
+
+ return;
+err:
+ mvpp2_dbgfs_cleanup(priv);
+}
+// SPDX-License-Identifier: GPL-2.0
/*
* Driver for Marvell PPv2 network controller for Armada 375 SoC.
*
* Copyright (C) 2014 Marvell
*
* Marcin Wojtas <mw@semihalf.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
*/
#include <linux/acpi.h>
#define MVPP2_QDIST_SINGLE_MODE 0
#define MVPP2_QDIST_MULTI_MODE 1
-static int queue_mode = MVPP2_QDIST_SINGLE_MODE;
+static int queue_mode = MVPP2_QDIST_MULTI_MODE;
module_param(queue_mode, int, 0444);
MODULE_PARM_DESC(queue_mode, "Set queue_mode (single=0, multi=1)");
struct mvpp2_tx_desc *tx_desc)
{
if (port->priv->hw_version == MVPP21)
- return tx_desc->pp21.buf_dma_addr;
+ return le32_to_cpu(tx_desc->pp21.buf_dma_addr);
else
- return tx_desc->pp22.buf_dma_addr_ptp & MVPP2_DESC_DMA_MASK;
+ return le64_to_cpu(tx_desc->pp22.buf_dma_addr_ptp) &
+ MVPP2_DESC_DMA_MASK;
}
static void mvpp2_txdesc_dma_addr_set(struct mvpp2_port *port,
offset = dma_addr & MVPP2_TX_DESC_ALIGN;
if (port->priv->hw_version == MVPP21) {
- tx_desc->pp21.buf_dma_addr = addr;
+ tx_desc->pp21.buf_dma_addr = cpu_to_le32(addr);
tx_desc->pp21.packet_offset = offset;
} else {
- u64 val = (u64)addr;
+ __le64 val = cpu_to_le64(addr);
- tx_desc->pp22.buf_dma_addr_ptp &= ~MVPP2_DESC_DMA_MASK;
+ tx_desc->pp22.buf_dma_addr_ptp &= ~cpu_to_le64(MVPP2_DESC_DMA_MASK);
tx_desc->pp22.buf_dma_addr_ptp |= val;
tx_desc->pp22.packet_offset = offset;
}
struct mvpp2_tx_desc *tx_desc)
{
if (port->priv->hw_version == MVPP21)
- return tx_desc->pp21.data_size;
+ return le16_to_cpu(tx_desc->pp21.data_size);
else
- return tx_desc->pp22.data_size;
+ return le16_to_cpu(tx_desc->pp22.data_size);
}
static void mvpp2_txdesc_size_set(struct mvpp2_port *port,
size_t size)
{
if (port->priv->hw_version == MVPP21)
- tx_desc->pp21.data_size = size;
+ tx_desc->pp21.data_size = cpu_to_le16(size);
else
- tx_desc->pp22.data_size = size;
+ tx_desc->pp22.data_size = cpu_to_le16(size);
}
static void mvpp2_txdesc_txq_set(struct mvpp2_port *port,
unsigned int command)
{
if (port->priv->hw_version == MVPP21)
- tx_desc->pp21.command = command;
+ tx_desc->pp21.command = cpu_to_le32(command);
else
- tx_desc->pp22.command = command;
+ tx_desc->pp22.command = cpu_to_le32(command);
}
static unsigned int mvpp2_txdesc_offset_get(struct mvpp2_port *port,
struct mvpp2_rx_desc *rx_desc)
{
if (port->priv->hw_version == MVPP21)
- return rx_desc->pp21.buf_dma_addr;
+ return le32_to_cpu(rx_desc->pp21.buf_dma_addr);
else
- return rx_desc->pp22.buf_dma_addr_key_hash & MVPP2_DESC_DMA_MASK;
+ return le64_to_cpu(rx_desc->pp22.buf_dma_addr_key_hash) &
+ MVPP2_DESC_DMA_MASK;
}
static unsigned long mvpp2_rxdesc_cookie_get(struct mvpp2_port *port,
struct mvpp2_rx_desc *rx_desc)
{
if (port->priv->hw_version == MVPP21)
- return rx_desc->pp21.buf_cookie;
+ return le32_to_cpu(rx_desc->pp21.buf_cookie);
else
- return rx_desc->pp22.buf_cookie_misc & MVPP2_DESC_DMA_MASK;
+ return le64_to_cpu(rx_desc->pp22.buf_cookie_misc) &
+ MVPP2_DESC_DMA_MASK;
}
static size_t mvpp2_rxdesc_size_get(struct mvpp2_port *port,
struct mvpp2_rx_desc *rx_desc)
{
if (port->priv->hw_version == MVPP21)
- return rx_desc->pp21.data_size;
+ return le16_to_cpu(rx_desc->pp21.data_size);
else
- return rx_desc->pp22.data_size;
+ return le16_to_cpu(rx_desc->pp22.data_size);
}
static u32 mvpp2_rxdesc_status_get(struct mvpp2_port *port,
struct mvpp2_rx_desc *rx_desc)
{
if (port->priv->hw_version == MVPP21)
- return rx_desc->pp21.status;
+ return le32_to_cpu(rx_desc->pp21.status);
else
- return rx_desc->pp22.status;
+ return le32_to_cpu(rx_desc->pp22.status);
}
static void mvpp2_txq_inc_get(struct mvpp2_txq_pcpu *txq_pcpu)
command |= (ip_hdr_len << MVPP2_TXD_IP_HLEN_SHIFT);
command |= MVPP2_TXD_IP_CSUM_DISABLE;
- if (l3_proto == swab16(ETH_P_IP)) {
+ if (l3_proto == htons(ETH_P_IP)) {
command &= ~MVPP2_TXD_IP_CSUM_DISABLE; /* enable IPv4 csum */
command &= ~MVPP2_TXD_L3_IP6; /* enable IPv4 */
} else {
}
}
+static bool mvpp22_rss_is_supported(void)
+{
+ return queue_mode == MVPP2_QDIST_MULTI_MODE;
+}
+
static int mvpp2_open(struct net_device *dev)
{
struct mvpp2_port *port = netdev_priv(dev);
mvpp2_start_dev(port);
- if (priv->hw_version == MVPP22)
- mvpp22_init_rss(port);
-
/* Start hardware statistics gathering */
queue_delayed_work(priv->stats_queue, &port->stats_work,
MVPP2_MIB_COUNTERS_STATS_DELAY);
}
}
+ if (changed & NETIF_F_RXHASH) {
+ if (features & NETIF_F_RXHASH)
+ mvpp22_rss_enable(port);
+ else
+ mvpp22_rss_disable(port);
+ }
+
return 0;
}
return phylink_ethtool_ksettings_set(port->phylink, cmd);
}
+static int mvpp2_ethtool_get_rxnfc(struct net_device *dev,
+ struct ethtool_rxnfc *info, u32 *rules)
+{
+ struct mvpp2_port *port = netdev_priv(dev);
+ int ret = 0;
+
+ if (!mvpp22_rss_is_supported())
+ return -EOPNOTSUPP;
+
+ switch (info->cmd) {
+ case ETHTOOL_GRXFH:
+ ret = mvpp2_ethtool_rxfh_get(port, info);
+ break;
+ case ETHTOOL_GRXRINGS:
+ info->data = port->nrxqs;
+ break;
+ default:
+ return -ENOTSUPP;
+ }
+
+ return ret;
+}
+
+static int mvpp2_ethtool_set_rxnfc(struct net_device *dev,
+ struct ethtool_rxnfc *info)
+{
+ struct mvpp2_port *port = netdev_priv(dev);
+ int ret = 0;
+
+ if (!mvpp22_rss_is_supported())
+ return -EOPNOTSUPP;
+
+ switch (info->cmd) {
+ case ETHTOOL_SRXFH:
+ ret = mvpp2_ethtool_rxfh_set(port, info);
+ break;
+ default:
+ return -EOPNOTSUPP;
+ }
+ return ret;
+}
+
+static u32 mvpp2_ethtool_get_rxfh_indir_size(struct net_device *dev)
+{
+ return mvpp22_rss_is_supported() ? MVPP22_RSS_TABLE_ENTRIES : 0;
+}
+
+static int mvpp2_ethtool_get_rxfh(struct net_device *dev, u32 *indir, u8 *key,
+ u8 *hfunc)
+{
+ struct mvpp2_port *port = netdev_priv(dev);
+
+ if (!mvpp22_rss_is_supported())
+ return -EOPNOTSUPP;
+
+ if (indir)
+ memcpy(indir, port->indir,
+ ARRAY_SIZE(port->indir) * sizeof(port->indir[0]));
+
+ if (hfunc)
+ *hfunc = ETH_RSS_HASH_CRC32;
+
+ return 0;
+}
+
+static int mvpp2_ethtool_set_rxfh(struct net_device *dev, const u32 *indir,
+ const u8 *key, const u8 hfunc)
+{
+ struct mvpp2_port *port = netdev_priv(dev);
+
+ if (!mvpp22_rss_is_supported())
+ return -EOPNOTSUPP;
+
+ if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_CRC32)
+ return -EOPNOTSUPP;
+
+ if (key)
+ return -EOPNOTSUPP;
+
+ if (indir) {
+ memcpy(port->indir, indir,
+ ARRAY_SIZE(port->indir) * sizeof(port->indir[0]));
+ mvpp22_rss_fill_table(port, port->id);
+ }
+
+ return 0;
+}
+
/* Device ops */
static const struct net_device_ops mvpp2_netdev_ops = {
.set_pauseparam = mvpp2_ethtool_set_pause_param,
.get_link_ksettings = mvpp2_ethtool_get_link_ksettings,
.set_link_ksettings = mvpp2_ethtool_set_link_ksettings,
+ .get_rxnfc = mvpp2_ethtool_get_rxnfc,
+ .set_rxnfc = mvpp2_ethtool_set_rxnfc,
+ .get_rxfh_indir_size = mvpp2_ethtool_get_rxfh_indir_size,
+ .get_rxfh = mvpp2_ethtool_get_rxfh,
+ .set_rxfh = mvpp2_ethtool_set_rxfh,
+
};
/* Used for PPv2.1, or PPv2.2 with the old Device Tree binding that
MVPP2_MAX_PORTS * priv->max_port_rxqs)
return -EINVAL;
- if (port->nrxqs % 4 || (port->nrxqs > priv->max_port_rxqs) ||
- (port->ntxqs > MVPP2_MAX_TXQ))
+ if (port->nrxqs % MVPP2_DEFAULT_RXQ ||
+ port->nrxqs > priv->max_port_rxqs || port->ntxqs > MVPP2_MAX_TXQ)
return -EINVAL;
/* Disable port */
mvpp2_cls_oversize_rxq_set(port);
mvpp2_cls_port_config(port);
+ if (mvpp22_rss_is_supported())
+ mvpp22_rss_port_init(port);
+
/* Provide an initial Rx packet size */
port->pkt_size = MVPP2_RX_PKT_SIZE(port->dev->mtu);
dev->hw_features |= features | NETIF_F_RXCSUM | NETIF_F_GRO |
NETIF_F_HW_VLAN_CTAG_FILTER;
+ if (mvpp22_rss_is_supported())
+ dev->hw_features |= NETIF_F_RXHASH;
+
if (port->pool_long->id == MVPP2_BM_JUMBO && port->id != 0) {
dev->features &= ~(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM);
dev->hw_features &= ~(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM);
(unsigned long)of_device_get_match_data(&pdev->dev);
}
+ /* multi queue mode isn't supported on PPV2.1, fallback to single
+ * mode
+ */
+ if (priv->hw_version == MVPP21)
+ queue_mode = MVPP2_QDIST_SINGLE_MODE;
+
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
base = devm_ioremap_resource(&pdev->dev, res);
if (IS_ERR(base))
goto err_port_probe;
}
+ mvpp2_dbgfs_init(priv, pdev->name);
+
platform_set_drvdata(pdev, priv);
return 0;
struct fwnode_handle *port_fwnode;
int i = 0;
+ mvpp2_dbgfs_cleanup(priv);
+
flush_workqueue(priv->stats_queue);
destroy_workqueue(priv->stats_queue);
+// SPDX-License-Identifier: GPL-2.0
/*
* Header Parser helpers for Marvell PPv2 Network Controller
*
* Copyright (C) 2014 Marvell
*
* Marcin Wojtas <mw@semihalf.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
*/
#include <linux/kernel.h>
return -EINVAL;
/* Clear entry invalidation bit */
- pe->tcam.word[MVPP2_PRS_TCAM_INV_WORD] &= ~MVPP2_PRS_TCAM_INV_MASK;
+ pe->tcam[MVPP2_PRS_TCAM_INV_WORD] &= ~MVPP2_PRS_TCAM_INV_MASK;
/* Write tcam index - indirect access */
mvpp2_write(priv, MVPP2_PRS_TCAM_IDX_REG, pe->index);
for (i = 0; i < MVPP2_PRS_TCAM_WORDS; i++)
- mvpp2_write(priv, MVPP2_PRS_TCAM_DATA_REG(i), pe->tcam.word[i]);
+ mvpp2_write(priv, MVPP2_PRS_TCAM_DATA_REG(i), pe->tcam[i]);
/* Write sram index - indirect access */
mvpp2_write(priv, MVPP2_PRS_SRAM_IDX_REG, pe->index);
for (i = 0; i < MVPP2_PRS_SRAM_WORDS; i++)
- mvpp2_write(priv, MVPP2_PRS_SRAM_DATA_REG(i), pe->sram.word[i]);
+ mvpp2_write(priv, MVPP2_PRS_SRAM_DATA_REG(i), pe->sram[i]);
return 0;
}
/* Initialize tcam entry from hw */
-static int mvpp2_prs_init_from_hw(struct mvpp2 *priv,
- struct mvpp2_prs_entry *pe, int tid)
+int mvpp2_prs_init_from_hw(struct mvpp2 *priv, struct mvpp2_prs_entry *pe,
+ int tid)
{
int i;
/* Write tcam index - indirect access */
mvpp2_write(priv, MVPP2_PRS_TCAM_IDX_REG, pe->index);
- pe->tcam.word[MVPP2_PRS_TCAM_INV_WORD] = mvpp2_read(priv,
+ pe->tcam[MVPP2_PRS_TCAM_INV_WORD] = mvpp2_read(priv,
MVPP2_PRS_TCAM_DATA_REG(MVPP2_PRS_TCAM_INV_WORD));
- if (pe->tcam.word[MVPP2_PRS_TCAM_INV_WORD] & MVPP2_PRS_TCAM_INV_MASK)
+ if (pe->tcam[MVPP2_PRS_TCAM_INV_WORD] & MVPP2_PRS_TCAM_INV_MASK)
return MVPP2_PRS_TCAM_ENTRY_INVALID;
for (i = 0; i < MVPP2_PRS_TCAM_WORDS; i++)
- pe->tcam.word[i] = mvpp2_read(priv, MVPP2_PRS_TCAM_DATA_REG(i));
+ pe->tcam[i] = mvpp2_read(priv, MVPP2_PRS_TCAM_DATA_REG(i));
/* Write sram index - indirect access */
mvpp2_write(priv, MVPP2_PRS_SRAM_IDX_REG, pe->index);
for (i = 0; i < MVPP2_PRS_SRAM_WORDS; i++)
- pe->sram.word[i] = mvpp2_read(priv, MVPP2_PRS_SRAM_DATA_REG(i));
+ pe->sram[i] = mvpp2_read(priv, MVPP2_PRS_SRAM_DATA_REG(i));
return 0;
}
/* Update lookup field in tcam sw entry */
static void mvpp2_prs_tcam_lu_set(struct mvpp2_prs_entry *pe, unsigned int lu)
{
- int enable_off = MVPP2_PRS_TCAM_EN_OFFS(MVPP2_PRS_TCAM_LU_BYTE);
-
- pe->tcam.byte[MVPP2_PRS_TCAM_LU_BYTE] = lu;
- pe->tcam.byte[enable_off] = MVPP2_PRS_LU_MASK;
+ pe->tcam[MVPP2_PRS_TCAM_LU_WORD] &= ~MVPP2_PRS_TCAM_LU(MVPP2_PRS_LU_MASK);
+ pe->tcam[MVPP2_PRS_TCAM_LU_WORD] &= ~MVPP2_PRS_TCAM_LU_EN(MVPP2_PRS_LU_MASK);
+ pe->tcam[MVPP2_PRS_TCAM_LU_WORD] |= MVPP2_PRS_TCAM_LU(lu & MVPP2_PRS_LU_MASK);
+ pe->tcam[MVPP2_PRS_TCAM_LU_WORD] |= MVPP2_PRS_TCAM_LU_EN(MVPP2_PRS_LU_MASK);
}
/* Update mask for single port in tcam sw entry */
static void mvpp2_prs_tcam_port_set(struct mvpp2_prs_entry *pe,
unsigned int port, bool add)
{
- int enable_off = MVPP2_PRS_TCAM_EN_OFFS(MVPP2_PRS_TCAM_PORT_BYTE);
-
if (add)
- pe->tcam.byte[enable_off] &= ~(1 << port);
+ pe->tcam[MVPP2_PRS_TCAM_PORT_WORD] &= ~MVPP2_PRS_TCAM_PORT_EN(BIT(port));
else
- pe->tcam.byte[enable_off] |= 1 << port;
+ pe->tcam[MVPP2_PRS_TCAM_PORT_WORD] |= MVPP2_PRS_TCAM_PORT_EN(BIT(port));
}
/* Update port map in tcam sw entry */
static void mvpp2_prs_tcam_port_map_set(struct mvpp2_prs_entry *pe,
unsigned int ports)
{
- unsigned char port_mask = MVPP2_PRS_PORT_MASK;
- int enable_off = MVPP2_PRS_TCAM_EN_OFFS(MVPP2_PRS_TCAM_PORT_BYTE);
-
- pe->tcam.byte[MVPP2_PRS_TCAM_PORT_BYTE] = 0;
- pe->tcam.byte[enable_off] &= ~port_mask;
- pe->tcam.byte[enable_off] |= ~ports & MVPP2_PRS_PORT_MASK;
+ pe->tcam[MVPP2_PRS_TCAM_PORT_WORD] &= ~MVPP2_PRS_TCAM_PORT(MVPP2_PRS_PORT_MASK);
+ pe->tcam[MVPP2_PRS_TCAM_PORT_WORD] &= ~MVPP2_PRS_TCAM_PORT_EN(MVPP2_PRS_PORT_MASK);
+ pe->tcam[MVPP2_PRS_TCAM_PORT_WORD] |= MVPP2_PRS_TCAM_PORT_EN(~ports & MVPP2_PRS_PORT_MASK);
}
/* Obtain port map from tcam sw entry */
-static unsigned int mvpp2_prs_tcam_port_map_get(struct mvpp2_prs_entry *pe)
+unsigned int mvpp2_prs_tcam_port_map_get(struct mvpp2_prs_entry *pe)
{
- int enable_off = MVPP2_PRS_TCAM_EN_OFFS(MVPP2_PRS_TCAM_PORT_BYTE);
-
- return ~(pe->tcam.byte[enable_off]) & MVPP2_PRS_PORT_MASK;
+ return (~pe->tcam[MVPP2_PRS_TCAM_PORT_WORD] >> 24) & MVPP2_PRS_PORT_MASK;
}
/* Set byte of data and its enable bits in tcam sw entry */
unsigned int offs, unsigned char byte,
unsigned char enable)
{
- pe->tcam.byte[MVPP2_PRS_TCAM_DATA_BYTE(offs)] = byte;
- pe->tcam.byte[MVPP2_PRS_TCAM_DATA_BYTE_EN(offs)] = enable;
+ int pos = MVPP2_PRS_BYTE_IN_WORD(offs) * BITS_PER_BYTE;
+
+ pe->tcam[MVPP2_PRS_BYTE_TO_WORD(offs)] &= ~(0xff << pos);
+ pe->tcam[MVPP2_PRS_BYTE_TO_WORD(offs)] &= ~(MVPP2_PRS_TCAM_EN(0xff) << pos);
+ pe->tcam[MVPP2_PRS_BYTE_TO_WORD(offs)] |= byte << pos;
+ pe->tcam[MVPP2_PRS_BYTE_TO_WORD(offs)] |= MVPP2_PRS_TCAM_EN(enable << pos);
}
/* Get byte of data and its enable bits from tcam sw entry */
-static void mvpp2_prs_tcam_data_byte_get(struct mvpp2_prs_entry *pe,
- unsigned int offs, unsigned char *byte,
- unsigned char *enable)
+void mvpp2_prs_tcam_data_byte_get(struct mvpp2_prs_entry *pe,
+ unsigned int offs, unsigned char *byte,
+ unsigned char *enable)
{
- *byte = pe->tcam.byte[MVPP2_PRS_TCAM_DATA_BYTE(offs)];
- *enable = pe->tcam.byte[MVPP2_PRS_TCAM_DATA_BYTE_EN(offs)];
+ int pos = MVPP2_PRS_BYTE_IN_WORD(offs) * BITS_PER_BYTE;
+
+ *byte = (pe->tcam[MVPP2_PRS_BYTE_TO_WORD(offs)] >> pos) & 0xff;
+ *enable = (pe->tcam[MVPP2_PRS_BYTE_TO_WORD(offs)] >> (pos + 16)) & 0xff;
}
/* Compare tcam data bytes with a pattern */
static bool mvpp2_prs_tcam_data_cmp(struct mvpp2_prs_entry *pe, int offs,
u16 data)
{
- int off = MVPP2_PRS_TCAM_DATA_BYTE(offs);
u16 tcam_data;
- tcam_data = (pe->tcam.byte[off + 1] << 8) | pe->tcam.byte[off];
- if (tcam_data != data)
- return false;
- return true;
+ tcam_data = pe->tcam[MVPP2_PRS_BYTE_TO_WORD(offs)] & 0xffff;
+ return tcam_data == data;
}
/* Update ai bits in tcam sw entry */
static void mvpp2_prs_tcam_ai_update(struct mvpp2_prs_entry *pe,
unsigned int bits, unsigned int enable)
{
- int i, ai_idx = MVPP2_PRS_TCAM_AI_BYTE;
+ int i;
for (i = 0; i < MVPP2_PRS_AI_BITS; i++) {
if (!(enable & BIT(i)))
continue;
if (bits & BIT(i))
- pe->tcam.byte[ai_idx] |= 1 << i;
+ pe->tcam[MVPP2_PRS_TCAM_AI_WORD] |= BIT(i);
else
- pe->tcam.byte[ai_idx] &= ~(1 << i);
+ pe->tcam[MVPP2_PRS_TCAM_AI_WORD] &= ~BIT(i);
}
- pe->tcam.byte[MVPP2_PRS_TCAM_EN_OFFS(ai_idx)] |= enable;
+ pe->tcam[MVPP2_PRS_TCAM_AI_WORD] |= MVPP2_PRS_TCAM_AI_EN(enable);
}
/* Get ai bits from tcam sw entry */
static int mvpp2_prs_tcam_ai_get(struct mvpp2_prs_entry *pe)
{
- return pe->tcam.byte[MVPP2_PRS_TCAM_AI_BYTE];
+ return pe->tcam[MVPP2_PRS_TCAM_AI_WORD] & MVPP2_PRS_AI_MASK;
}
/* Set ethertype in tcam sw entry */
/* Set bits in sram sw entry */
static void mvpp2_prs_sram_bits_set(struct mvpp2_prs_entry *pe, int bit_num,
- int val)
+ u32 val)
{
- pe->sram.byte[MVPP2_BIT_TO_BYTE(bit_num)] |= (val << (bit_num % 8));
+ pe->sram[MVPP2_BIT_TO_WORD(bit_num)] |= (val << (MVPP2_BIT_IN_WORD(bit_num)));
}
/* Clear bits in sram sw entry */
static void mvpp2_prs_sram_bits_clear(struct mvpp2_prs_entry *pe, int bit_num,
- int val)
+ u32 val)
{
- pe->sram.byte[MVPP2_BIT_TO_BYTE(bit_num)] &= ~(val << (bit_num % 8));
+ pe->sram[MVPP2_BIT_TO_WORD(bit_num)] &= ~(val << (MVPP2_BIT_IN_WORD(bit_num)));
}
/* Update ri bits in sram sw entry */
unsigned int i;
for (i = 0; i < MVPP2_PRS_SRAM_RI_CTRL_BITS; i++) {
- int ri_off = MVPP2_PRS_SRAM_RI_OFFS;
-
if (!(mask & BIT(i)))
continue;
if (bits & BIT(i))
- mvpp2_prs_sram_bits_set(pe, ri_off + i, 1);
+ mvpp2_prs_sram_bits_set(pe, MVPP2_PRS_SRAM_RI_OFFS + i,
+ 1);
else
- mvpp2_prs_sram_bits_clear(pe, ri_off + i, 1);
+ mvpp2_prs_sram_bits_clear(pe,
+ MVPP2_PRS_SRAM_RI_OFFS + i,
+ 1);
mvpp2_prs_sram_bits_set(pe, MVPP2_PRS_SRAM_RI_CTRL_OFFS + i, 1);
}
/* Obtain ri bits from sram sw entry */
static int mvpp2_prs_sram_ri_get(struct mvpp2_prs_entry *pe)
{
- return pe->sram.word[MVPP2_PRS_SRAM_RI_WORD];
+ return pe->sram[MVPP2_PRS_SRAM_RI_WORD];
}
/* Update ai bits in sram sw entry */
unsigned int bits, unsigned int mask)
{
unsigned int i;
- int ai_off = MVPP2_PRS_SRAM_AI_OFFS;
for (i = 0; i < MVPP2_PRS_SRAM_AI_CTRL_BITS; i++) {
if (!(mask & BIT(i)))
continue;
if (bits & BIT(i))
- mvpp2_prs_sram_bits_set(pe, ai_off + i, 1);
+ mvpp2_prs_sram_bits_set(pe, MVPP2_PRS_SRAM_AI_OFFS + i,
+ 1);
else
- mvpp2_prs_sram_bits_clear(pe, ai_off + i, 1);
+ mvpp2_prs_sram_bits_clear(pe,
+ MVPP2_PRS_SRAM_AI_OFFS + i,
+ 1);
mvpp2_prs_sram_bits_set(pe, MVPP2_PRS_SRAM_AI_CTRL_OFFS + i, 1);
}
static int mvpp2_prs_sram_ai_get(struct mvpp2_prs_entry *pe)
{
u8 bits;
- int ai_off = MVPP2_BIT_TO_BYTE(MVPP2_PRS_SRAM_AI_OFFS);
- int ai_en_off = ai_off + 1;
- int ai_shift = MVPP2_PRS_SRAM_AI_OFFS % 8;
+ /* ai is stored on bits 90->97; so it spreads across two u32 */
+ int ai_off = MVPP2_BIT_TO_WORD(MVPP2_PRS_SRAM_AI_OFFS);
+ int ai_shift = MVPP2_BIT_IN_WORD(MVPP2_PRS_SRAM_AI_OFFS);
- bits = (pe->sram.byte[ai_off] >> ai_shift) |
- (pe->sram.byte[ai_en_off] << (8 - ai_shift));
+ bits = (pe->sram[ai_off] >> ai_shift) |
+ (pe->sram[ai_off + 1] << (32 - ai_shift));
return bits;
}
}
/* Set value */
- pe->sram.byte[MVPP2_BIT_TO_BYTE(MVPP2_PRS_SRAM_SHIFT_OFFS)] =
- (unsigned char)shift;
+ pe->sram[MVPP2_BIT_TO_WORD(MVPP2_PRS_SRAM_SHIFT_OFFS)] = shift & MVPP2_PRS_SRAM_SHIFT_MASK;
/* Reset and set operation */
mvpp2_prs_sram_bits_clear(pe, MVPP2_PRS_SRAM_OP_SEL_SHIFT_OFFS,
/* Set value */
mvpp2_prs_sram_bits_clear(pe, MVPP2_PRS_SRAM_UDF_OFFS,
MVPP2_PRS_SRAM_UDF_MASK);
- mvpp2_prs_sram_bits_set(pe, MVPP2_PRS_SRAM_UDF_OFFS, offset);
- pe->sram.byte[MVPP2_BIT_TO_BYTE(MVPP2_PRS_SRAM_UDF_OFFS +
- MVPP2_PRS_SRAM_UDF_BITS)] &=
- ~(MVPP2_PRS_SRAM_UDF_MASK >> (8 - (MVPP2_PRS_SRAM_UDF_OFFS % 8)));
- pe->sram.byte[MVPP2_BIT_TO_BYTE(MVPP2_PRS_SRAM_UDF_OFFS +
- MVPP2_PRS_SRAM_UDF_BITS)] |=
- (offset >> (8 - (MVPP2_PRS_SRAM_UDF_OFFS % 8)));
+ mvpp2_prs_sram_bits_set(pe, MVPP2_PRS_SRAM_UDF_OFFS,
+ offset & MVPP2_PRS_SRAM_UDF_MASK);
/* Set offset type */
mvpp2_prs_sram_bits_clear(pe, MVPP2_PRS_SRAM_UDF_TYPE_OFFS,
/* Set offset operation */
mvpp2_prs_sram_bits_clear(pe, MVPP2_PRS_SRAM_OP_SEL_UDF_OFFS,
MVPP2_PRS_SRAM_OP_SEL_UDF_MASK);
- mvpp2_prs_sram_bits_set(pe, MVPP2_PRS_SRAM_OP_SEL_UDF_OFFS, op);
-
- pe->sram.byte[MVPP2_BIT_TO_BYTE(MVPP2_PRS_SRAM_OP_SEL_UDF_OFFS +
- MVPP2_PRS_SRAM_OP_SEL_UDF_BITS)] &=
- ~(MVPP2_PRS_SRAM_OP_SEL_UDF_MASK >>
- (8 - (MVPP2_PRS_SRAM_OP_SEL_UDF_OFFS % 8)));
-
- pe->sram.byte[MVPP2_BIT_TO_BYTE(MVPP2_PRS_SRAM_OP_SEL_UDF_OFFS +
- MVPP2_PRS_SRAM_OP_SEL_UDF_BITS)] |=
- (op >> (8 - (MVPP2_PRS_SRAM_OP_SEL_UDF_OFFS % 8)));
+ mvpp2_prs_sram_bits_set(pe, MVPP2_PRS_SRAM_OP_SEL_UDF_OFFS,
+ op & MVPP2_PRS_SRAM_OP_SEL_UDF_MASK);
/* Set base offset as current */
mvpp2_prs_sram_bits_clear(pe, MVPP2_PRS_SRAM_OP_SEL_BASE_OFFS, 1);
continue;
mvpp2_prs_init_from_hw(priv, &pe, tid);
- match = mvpp2_prs_tcam_data_cmp(&pe, 0, swab16(tpid));
+ match = mvpp2_prs_tcam_data_cmp(&pe, 0, tpid);
if (!match)
continue;
mvpp2_prs_init_from_hw(priv, &pe, tid);
- match = mvpp2_prs_tcam_data_cmp(&pe, 0, swab16(tpid1)) &&
- mvpp2_prs_tcam_data_cmp(&pe, 4, swab16(tpid2));
+ match = mvpp2_prs_tcam_data_cmp(&pe, 0, tpid1) &&
+ mvpp2_prs_tcam_data_cmp(&pe, 4, tpid2);
if (!match)
continue;
pe.index = tid;
/* Clear ri before updating */
- pe.sram.word[MVPP2_PRS_SRAM_RI_WORD] = 0x0;
- pe.sram.word[MVPP2_PRS_SRAM_RI_CTRL_WORD] = 0x0;
+ pe.sram[MVPP2_PRS_SRAM_RI_WORD] = 0x0;
+ pe.sram[MVPP2_PRS_SRAM_RI_CTRL_WORD] = 0x0;
mvpp2_prs_sram_ri_update(&pe, ri, ri_mask);
mvpp2_prs_sram_ri_update(&pe, ri | MVPP2_PRS_RI_IP_FRAG_TRUE,
pe.index = tid;
- /* Clear tcam data before updating */
- pe.tcam.byte[MVPP2_PRS_TCAM_DATA_BYTE(MVPP2_ETH_TYPE_LEN)] = 0x0;
- pe.tcam.byte[MVPP2_PRS_TCAM_DATA_BYTE_EN(MVPP2_ETH_TYPE_LEN)] = 0x0;
-
mvpp2_prs_tcam_data_byte_set(&pe, MVPP2_ETH_TYPE_LEN,
MVPP2_PRS_IPV4_HEAD,
MVPP2_PRS_IPV4_HEAD_MASK);
/* Clear ri before updating */
- pe.sram.word[MVPP2_PRS_SRAM_RI_WORD] = 0x0;
- pe.sram.word[MVPP2_PRS_SRAM_RI_CTRL_WORD] = 0x0;
+ pe.sram[MVPP2_PRS_SRAM_RI_WORD] = 0x0;
+ pe.sram[MVPP2_PRS_SRAM_RI_CTRL_WORD] = 0x0;
mvpp2_prs_sram_ri_update(&pe, MVPP2_PRS_RI_L3_IP4_OPT,
MVPP2_PRS_RI_L3_PROTO_MASK);
MVPP2_PRS_IPV4_IHL_MASK);
/* Clear ri before updating */
- pe.sram.word[MVPP2_PRS_SRAM_RI_WORD] = 0x0;
- pe.sram.word[MVPP2_PRS_SRAM_RI_CTRL_WORD] = 0x0;
+ pe.sram[MVPP2_PRS_SRAM_RI_WORD] = 0x0;
+ pe.sram[MVPP2_PRS_SRAM_RI_CTRL_WORD] = 0x0;
mvpp2_prs_sram_ri_update(&pe, MVPP2_PRS_RI_L3_IP4,
MVPP2_PRS_RI_L3_PROTO_MASK);
return 0;
}
+int mvpp2_prs_add_flow(struct mvpp2 *priv, int flow, u32 ri, u32 ri_mask)
+{
+ struct mvpp2_prs_entry pe;
+ u8 *ri_byte, *ri_byte_mask;
+ int tid, i;
+
+ memset(&pe, 0, sizeof(pe));
+
+ tid = mvpp2_prs_tcam_first_free(priv,
+ MVPP2_PE_LAST_FREE_TID,
+ MVPP2_PE_FIRST_FREE_TID);
+ if (tid < 0)
+ return tid;
+
+ pe.index = tid;
+
+ ri_byte = (u8 *)&ri;
+ ri_byte_mask = (u8 *)&ri_mask;
+
+ mvpp2_prs_sram_ai_update(&pe, flow, MVPP2_PRS_FLOW_ID_MASK);
+ mvpp2_prs_sram_bits_set(&pe, MVPP2_PRS_SRAM_LU_DONE_BIT, 1);
+
+ for (i = 0; i < 4; i++) {
+ mvpp2_prs_tcam_data_byte_set(&pe, i, ri_byte[i],
+ ri_byte_mask[i]);
+ }
+
+ mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_FLOWS);
+ mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_FLOWS);
+ mvpp2_prs_tcam_port_map_set(&pe, MVPP2_PRS_PORT_MASK);
+ mvpp2_prs_hw_write(priv, &pe);
+
+ return 0;
+}
+
/* Set prs flow for the port */
int mvpp2_prs_def_flow(struct mvpp2_port *port)
{
return 0;
}
+
+int mvpp2_prs_hits(struct mvpp2 *priv, int index)
+{
+ u32 val;
+
+ if (index > MVPP2_PRS_TCAM_SRAM_SIZE)
+ return -EINVAL;
+
+ mvpp2_write(priv, MVPP2_PRS_TCAM_HIT_IDX_REG, index);
+
+ val = mvpp2_read(priv, MVPP2_PRS_TCAM_HIT_CNT_REG);
+
+ val &= MVPP2_PRS_TCAM_HIT_CNT_MASK;
+
+ return val;
+}
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Header Parser definitions for Marvell PPv2 Network Controller
*
* Copyright (C) 2014 Marvell
*
* Marcin Wojtas <mw@semihalf.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
*/
+#ifndef _MVPP2_PRS_H_
+#define _MVPP2_PRS_H_
+
#include <linux/kernel.h>
#include <linux/netdevice.h>
+#include <linux/platform_device.h>
#include "mvpp2.h"
-#ifndef _MVPP2_PRS_H_
-#define _MVPP2_PRS_H_
-
/* Parser constants */
#define MVPP2_PRS_TCAM_SRAM_SIZE 256
#define MVPP2_PRS_TCAM_WORDS 6
* The fields are represented by MVPP2_PRS_TCAM_DATA_REG(5)->(0).
*/
#define MVPP2_PRS_AI_BITS 8
+#define MVPP2_PRS_AI_MASK 0xff
#define MVPP2_PRS_PORT_MASK 0xff
#define MVPP2_PRS_LU_MASK 0xf
-#define MVPP2_PRS_TCAM_DATA_BYTE(offs) \
- (((offs) - ((offs) % 2)) * 2 + ((offs) % 2))
-#define MVPP2_PRS_TCAM_DATA_BYTE_EN(offs) \
- (((offs) * 2) - ((offs) % 2) + 2)
-#define MVPP2_PRS_TCAM_AI_BYTE 16
-#define MVPP2_PRS_TCAM_PORT_BYTE 17
-#define MVPP2_PRS_TCAM_LU_BYTE 20
-#define MVPP2_PRS_TCAM_EN_OFFS(offs) ((offs) + 2)
-#define MVPP2_PRS_TCAM_INV_WORD 5
+
+/* TCAM entries in registers are accessed using 16 data bits + 16 enable bits */
+#define MVPP2_PRS_BYTE_TO_WORD(byte) ((byte) / 2)
+#define MVPP2_PRS_BYTE_IN_WORD(byte) ((byte) % 2)
+
+#define MVPP2_PRS_TCAM_EN(data) ((data) << 16)
+#define MVPP2_PRS_TCAM_AI_WORD 4
+#define MVPP2_PRS_TCAM_AI(ai) (ai)
+#define MVPP2_PRS_TCAM_AI_EN(ai) MVPP2_PRS_TCAM_EN(MVPP2_PRS_TCAM_AI(ai))
+#define MVPP2_PRS_TCAM_PORT_WORD 4
+#define MVPP2_PRS_TCAM_PORT(p) ((p) << 8)
+#define MVPP2_PRS_TCAM_PORT_EN(p) MVPP2_PRS_TCAM_EN(MVPP2_PRS_TCAM_PORT(p))
+#define MVPP2_PRS_TCAM_LU_WORD 5
+#define MVPP2_PRS_TCAM_LU(lu) (lu)
+#define MVPP2_PRS_TCAM_LU_EN(lu) MVPP2_PRS_TCAM_EN(MVPP2_PRS_TCAM_LU(lu))
+#define MVPP2_PRS_TCAM_INV_WORD 5
#define MVPP2_PRS_VID_TCAM_BYTE 2
#define MVPP2_PRS_SRAM_RI_CTRL_BITS 32
#define MVPP2_PRS_SRAM_SHIFT_OFFS 64
#define MVPP2_PRS_SRAM_SHIFT_SIGN_BIT 72
+#define MVPP2_PRS_SRAM_SHIFT_MASK 0xff
#define MVPP2_PRS_SRAM_UDF_OFFS 73
#define MVPP2_PRS_SRAM_UDF_BITS 8
#define MVPP2_PRS_SRAM_UDF_MASK 0xff
#define MVPP2_PRS_RI_UDF7_IP6_LITE BIT(29)
#define MVPP2_PRS_RI_DROP_MASK 0x80000000
+#define MVPP2_PRS_IP_MASK (MVPP2_PRS_RI_L3_PROTO_MASK | \
+ MVPP2_PRS_RI_IP_FRAG_MASK | \
+ MVPP2_PRS_RI_L4_PROTO_MASK)
+
/* Sram additional info bits assignment */
#define MVPP2_PRS_IPV4_DIP_AI_BIT BIT(0)
#define MVPP2_PRS_IPV6_NO_EXT_AI_BIT BIT(0)
MVPP2_PRS_LU_LAST,
};
-union mvpp2_prs_tcam_entry {
- u32 word[MVPP2_PRS_TCAM_WORDS];
- u8 byte[MVPP2_PRS_TCAM_WORDS * 4];
-};
-
-union mvpp2_prs_sram_entry {
- u32 word[MVPP2_PRS_SRAM_WORDS];
- u8 byte[MVPP2_PRS_SRAM_WORDS * 4];
-};
-
struct mvpp2_prs_entry {
u32 index;
- union mvpp2_prs_tcam_entry tcam;
- union mvpp2_prs_sram_entry sram;
+ u32 tcam[MVPP2_PRS_TCAM_WORDS];
+ u32 sram[MVPP2_PRS_SRAM_WORDS];
+};
+
+struct mvpp2_prs_result_info {
+ u32 ri;
+ u32 ri_mask;
};
struct mvpp2_prs_shadow {
int mvpp2_prs_default_init(struct platform_device *pdev, struct mvpp2 *priv);
+int mvpp2_prs_init_from_hw(struct mvpp2 *priv, struct mvpp2_prs_entry *pe,
+ int tid);
+
+unsigned int mvpp2_prs_tcam_port_map_get(struct mvpp2_prs_entry *pe);
+
+void mvpp2_prs_tcam_data_byte_get(struct mvpp2_prs_entry *pe,
+ unsigned int offs, unsigned char *byte,
+ unsigned char *enable);
+
int mvpp2_prs_mac_da_accept(struct mvpp2_port *port, const u8 *da, bool add);
int mvpp2_prs_tag_mode_set(struct mvpp2 *priv, int port, int type);
+int mvpp2_prs_add_flow(struct mvpp2 *priv, int flow, u32 ri, u32 ri_mask);
+
int mvpp2_prs_def_flow(struct mvpp2_port *port);
void mvpp2_prs_vid_enable_filtering(struct mvpp2_port *port);
int mvpp2_prs_update_mac_da(struct net_device *dev, const u8 *da);
+int mvpp2_prs_hits(struct mvpp2 *priv, int index);
+
#endif
mlx4_core-y := alloc.o catas.o cmd.o cq.o eq.o fw.o fw_qos.o icm.o intf.o \
main.o mcg.o mr.o pd.o port.o profile.o qp.o reset.o sense.o \
- srq.o resource_tracker.o
+ srq.o resource_tracker.o crdump.o
obj-$(CONFIG_MLX4_EN) += mlx4_en.o
dev = persist->dev;
mlx4_err(dev, "device is going to be reset\n");
- if (mlx4_is_slave(dev))
+ if (mlx4_is_slave(dev)) {
err = mlx4_reset_slave(dev);
- else
+ } else {
+ mlx4_crdump_collect(dev);
err = mlx4_reset_master(dev);
+ }
if (!err) {
mlx4_err(dev, "device was reset successfully\n");
mutex_lock(&persist->interface_state_mutex);
if (persist->interface_state & MLX4_INTERFACE_STATE_UP &&
!(persist->interface_state & MLX4_INTERFACE_STATE_DELETION)) {
- err = mlx4_restart_one(persist->pdev);
+ err = mlx4_restart_one(persist->pdev, false, NULL);
mlx4_info(persist->dev, "mlx4_restart_one was ended, ret=%d\n",
err);
}
--- /dev/null
+/*
+ * Copyright (c) 2018, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and/or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include "mlx4.h"
+
+#define BAD_ACCESS 0xBADACCE5
+#define HEALTH_BUFFER_SIZE 0x40
+#define CR_ENABLE_BIT swab32(BIT(6))
+#define CR_ENABLE_BIT_OFFSET 0xF3F04
+#define MAX_NUM_OF_DUMPS_TO_STORE (8)
+
+static const char *region_cr_space_str = "cr-space";
+static const char *region_fw_health_str = "fw-health";
+
+/* Set to true in case cr enable bit was set to true before crdump */
+static bool crdump_enbale_bit_set;
+
+static void crdump_enable_crspace_access(struct mlx4_dev *dev,
+ u8 __iomem *cr_space)
+{
+ /* Get current enable bit value */
+ crdump_enbale_bit_set =
+ readl(cr_space + CR_ENABLE_BIT_OFFSET) & CR_ENABLE_BIT;
+
+ /* Enable FW CR filter (set bit6 to 0) */
+ if (crdump_enbale_bit_set)
+ writel(readl(cr_space + CR_ENABLE_BIT_OFFSET) & ~CR_ENABLE_BIT,
+ cr_space + CR_ENABLE_BIT_OFFSET);
+
+ /* Enable block volatile crspace accesses */
+ writel(swab32(1), cr_space + dev->caps.health_buffer_addrs +
+ HEALTH_BUFFER_SIZE);
+}
+
+static void crdump_disable_crspace_access(struct mlx4_dev *dev,
+ u8 __iomem *cr_space)
+{
+ /* Disable block volatile crspace accesses */
+ writel(0, cr_space + dev->caps.health_buffer_addrs +
+ HEALTH_BUFFER_SIZE);
+
+ /* Restore FW CR filter value (set bit6 to original value) */
+ if (crdump_enbale_bit_set)
+ writel(readl(cr_space + CR_ENABLE_BIT_OFFSET) | CR_ENABLE_BIT,
+ cr_space + CR_ENABLE_BIT_OFFSET);
+}
+
+static void mlx4_crdump_collect_crspace(struct mlx4_dev *dev,
+ u8 __iomem *cr_space,
+ u32 id)
+{
+ struct mlx4_fw_crdump *crdump = &dev->persist->crdump;
+ struct pci_dev *pdev = dev->persist->pdev;
+ unsigned long cr_res_size;
+ u8 *crspace_data;
+ int offset;
+ int err;
+
+ if (!crdump->region_crspace) {
+ mlx4_err(dev, "crdump: cr-space region is NULL\n");
+ return;
+ }
+
+ /* Try to collect CR space */
+ cr_res_size = pci_resource_len(pdev, 0);
+ crspace_data = kvmalloc(cr_res_size, GFP_KERNEL);
+ if (crspace_data) {
+ for (offset = 0; offset < cr_res_size; offset += 4)
+ *(u32 *)(crspace_data + offset) =
+ readl(cr_space + offset);
+
+ err = devlink_region_snapshot_create(crdump->region_crspace,
+ cr_res_size, crspace_data,
+ id, &kvfree);
+ if (err) {
+ kvfree(crspace_data);
+ mlx4_warn(dev, "crdump: devlink create %s snapshot id %d err %d\n",
+ region_cr_space_str, id, err);
+ } else {
+ mlx4_info(dev, "crdump: added snapshot %d to devlink region %s\n",
+ id, region_cr_space_str);
+ }
+ } else {
+ mlx4_err(dev, "crdump: Failed to allocate crspace buffer\n");
+ }
+}
+
+static void mlx4_crdump_collect_fw_health(struct mlx4_dev *dev,
+ u8 __iomem *cr_space,
+ u32 id)
+{
+ struct mlx4_fw_crdump *crdump = &dev->persist->crdump;
+ u8 *health_data;
+ int offset;
+ int err;
+
+ if (!crdump->region_fw_health) {
+ mlx4_err(dev, "crdump: fw-health region is NULL\n");
+ return;
+ }
+
+ /* Try to collect health buffer */
+ health_data = kvmalloc(HEALTH_BUFFER_SIZE, GFP_KERNEL);
+ if (health_data) {
+ u8 __iomem *health_buf_start =
+ cr_space + dev->caps.health_buffer_addrs;
+
+ for (offset = 0; offset < HEALTH_BUFFER_SIZE; offset += 4)
+ *(u32 *)(health_data + offset) =
+ readl(health_buf_start + offset);
+
+ err = devlink_region_snapshot_create(crdump->region_fw_health,
+ HEALTH_BUFFER_SIZE,
+ health_data,
+ id, &kvfree);
+ if (err) {
+ kvfree(health_data);
+ mlx4_warn(dev, "crdump: devlink create %s snapshot id %d err %d\n",
+ region_fw_health_str, id, err);
+ } else {
+ mlx4_info(dev, "crdump: added snapshot %d to devlink region %s\n",
+ id, region_fw_health_str);
+ }
+ } else {
+ mlx4_err(dev, "crdump: Failed to allocate health buffer\n");
+ }
+}
+
+int mlx4_crdump_collect(struct mlx4_dev *dev)
+{
+ struct devlink *devlink = priv_to_devlink(mlx4_priv(dev));
+ struct mlx4_fw_crdump *crdump = &dev->persist->crdump;
+ struct pci_dev *pdev = dev->persist->pdev;
+ unsigned long cr_res_size;
+ u8 __iomem *cr_space;
+ u32 id;
+
+ if (!dev->caps.health_buffer_addrs) {
+ mlx4_info(dev, "crdump: FW doesn't support health buffer access, skipping\n");
+ return 0;
+ }
+
+ if (!crdump->snapshot_enable) {
+ mlx4_info(dev, "crdump: devlink snapshot disabled, skipping\n");
+ return 0;
+ }
+
+ cr_res_size = pci_resource_len(pdev, 0);
+
+ cr_space = ioremap(pci_resource_start(pdev, 0), cr_res_size);
+ if (!cr_space) {
+ mlx4_err(dev, "crdump: Failed to map pci cr region\n");
+ return -ENODEV;
+ }
+
+ crdump_enable_crspace_access(dev, cr_space);
+
+ /* Get the available snapshot ID for the dumps */
+ id = devlink_region_shapshot_id_get(devlink);
+
+ /* Try to capture dumps */
+ mlx4_crdump_collect_crspace(dev, cr_space, id);
+ mlx4_crdump_collect_fw_health(dev, cr_space, id);
+
+ crdump_disable_crspace_access(dev, cr_space);
+
+ iounmap(cr_space);
+ return 0;
+}
+
+int mlx4_crdump_init(struct mlx4_dev *dev)
+{
+ struct devlink *devlink = priv_to_devlink(mlx4_priv(dev));
+ struct mlx4_fw_crdump *crdump = &dev->persist->crdump;
+ struct pci_dev *pdev = dev->persist->pdev;
+
+ crdump->snapshot_enable = false;
+
+ /* Create cr-space region */
+ crdump->region_crspace =
+ devlink_region_create(devlink,
+ region_cr_space_str,
+ MAX_NUM_OF_DUMPS_TO_STORE,
+ pci_resource_len(pdev, 0));
+ if (IS_ERR(crdump->region_crspace))
+ mlx4_warn(dev, "crdump: create devlink region %s err %ld\n",
+ region_cr_space_str,
+ PTR_ERR(crdump->region_crspace));
+
+ /* Create fw-health region */
+ crdump->region_fw_health =
+ devlink_region_create(devlink,
+ region_fw_health_str,
+ MAX_NUM_OF_DUMPS_TO_STORE,
+ HEALTH_BUFFER_SIZE);
+ if (IS_ERR(crdump->region_fw_health))
+ mlx4_warn(dev, "crdump: create devlink region %s err %ld\n",
+ region_fw_health_str,
+ PTR_ERR(crdump->region_fw_health));
+
+ return 0;
+}
+
+void mlx4_crdump_end(struct mlx4_dev *dev)
+{
+ struct mlx4_fw_crdump *crdump = &dev->persist->crdump;
+
+ devlink_region_destroy(crdump->region_fw_health);
+ devlink_region_destroy(crdump->region_crspace);
+}
return mlx4_xdp_set(dev, xdp->prog);
case XDP_QUERY_PROG:
xdp->prog_id = mlx4_xdp_query(dev);
- xdp->prog_attached = !!xdp->prog_id;
return 0;
default:
return -EINVAL;
}
u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb,
- void *accel_priv, select_queue_fallback_t fallback)
+ struct net_device *sb_dev,
+ select_queue_fallback_t fallback)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
u16 rings_p_up = priv->num_tx_rings_p_up;
if (netdev_get_num_tc(dev))
- return fallback(dev, skb);
+ return fallback(dev, skb, NULL);
- return fallback(dev, skb) % rings_p_up;
+ return fallback(dev, skb, NULL) % rings_p_up;
}
static void mlx4_bf_copy(void __iomem *dst, const void *src,
#define QUERY_DEV_CAP_QP_RATE_LIMIT_NUM_OFFSET 0xcc
#define QUERY_DEV_CAP_QP_RATE_LIMIT_MAX_OFFSET 0xd0
#define QUERY_DEV_CAP_QP_RATE_LIMIT_MIN_OFFSET 0xd2
-
+#define QUERY_DEV_CAP_HEALTH_BUFFER_ADDRESS_OFFSET 0xe4
dev_cap->flags2 = 0;
mailbox = mlx4_alloc_cmd_mailbox(dev);
dev_cap->rl_caps.min_unit = size >> 14;
}
+ MLX4_GET(dev_cap->health_buffer_addrs, outbox,
+ QUERY_DEV_CAP_HEALTH_BUFFER_ADDRESS_OFFSET);
+
MLX4_GET(field32, outbox, QUERY_DEV_CAP_EXT_2_FLAGS_OFFSET);
if (field32 & (1 << 16))
dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_UPDATE_QP;
u32 dmfs_high_rate_qpn_base;
u32 dmfs_high_rate_qpn_range;
struct mlx4_rate_limit_caps rl_caps;
+ u32 health_buffer_addrs;
struct mlx4_port_cap port_cap[MLX4_MAX_PORTS + 1];
bool wol_port[MLX4_MAX_PORTS + 1];
};
static atomic_t pf_loading = ATOMIC_INIT(0);
+static int mlx4_devlink_ierr_reset_get(struct devlink *devlink, u32 id,
+ struct devlink_param_gset_ctx *ctx)
+{
+ ctx->val.vbool = !!mlx4_internal_err_reset;
+ return 0;
+}
+
+static int mlx4_devlink_ierr_reset_set(struct devlink *devlink, u32 id,
+ struct devlink_param_gset_ctx *ctx)
+{
+ mlx4_internal_err_reset = ctx->val.vbool;
+ return 0;
+}
+
+static int mlx4_devlink_crdump_snapshot_get(struct devlink *devlink, u32 id,
+ struct devlink_param_gset_ctx *ctx)
+{
+ struct mlx4_priv *priv = devlink_priv(devlink);
+ struct mlx4_dev *dev = &priv->dev;
+
+ ctx->val.vbool = dev->persist->crdump.snapshot_enable;
+ return 0;
+}
+
+static int mlx4_devlink_crdump_snapshot_set(struct devlink *devlink, u32 id,
+ struct devlink_param_gset_ctx *ctx)
+{
+ struct mlx4_priv *priv = devlink_priv(devlink);
+ struct mlx4_dev *dev = &priv->dev;
+
+ dev->persist->crdump.snapshot_enable = ctx->val.vbool;
+ return 0;
+}
+
+static int
+mlx4_devlink_max_macs_validate(struct devlink *devlink, u32 id,
+ union devlink_param_value val,
+ struct netlink_ext_ack *extack)
+{
+ u32 value = val.vu32;
+
+ if (value < 1 || value > 128)
+ return -ERANGE;
+
+ if (!is_power_of_2(value)) {
+ NL_SET_ERR_MSG_MOD(extack, "max_macs supported must be power of 2");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+enum mlx4_devlink_param_id {
+ MLX4_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX,
+ MLX4_DEVLINK_PARAM_ID_ENABLE_64B_CQE_EQE,
+ MLX4_DEVLINK_PARAM_ID_ENABLE_4K_UAR,
+};
+
+static const struct devlink_param mlx4_devlink_params[] = {
+ DEVLINK_PARAM_GENERIC(INT_ERR_RESET,
+ BIT(DEVLINK_PARAM_CMODE_RUNTIME) |
+ BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+ mlx4_devlink_ierr_reset_get,
+ mlx4_devlink_ierr_reset_set, NULL),
+ DEVLINK_PARAM_GENERIC(MAX_MACS,
+ BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+ NULL, NULL, mlx4_devlink_max_macs_validate),
+ DEVLINK_PARAM_GENERIC(REGION_SNAPSHOT,
+ BIT(DEVLINK_PARAM_CMODE_RUNTIME) |
+ BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+ mlx4_devlink_crdump_snapshot_get,
+ mlx4_devlink_crdump_snapshot_set, NULL),
+ DEVLINK_PARAM_DRIVER(MLX4_DEVLINK_PARAM_ID_ENABLE_64B_CQE_EQE,
+ "enable_64b_cqe_eqe", DEVLINK_PARAM_TYPE_BOOL,
+ BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+ NULL, NULL, NULL),
+ DEVLINK_PARAM_DRIVER(MLX4_DEVLINK_PARAM_ID_ENABLE_4K_UAR,
+ "enable_4k_uar", DEVLINK_PARAM_TYPE_BOOL,
+ BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+ NULL, NULL, NULL),
+};
+
+static void mlx4_devlink_set_init_value(struct devlink *devlink, u32 param_id,
+ union devlink_param_value init_val)
+{
+ struct mlx4_priv *priv = devlink_priv(devlink);
+ struct mlx4_dev *dev = &priv->dev;
+ int err;
+
+ err = devlink_param_driverinit_value_set(devlink, param_id, init_val);
+ if (err)
+ mlx4_warn(dev,
+ "devlink set parameter %u value failed (err = %d)",
+ param_id, err);
+}
+
+static void mlx4_devlink_set_params_init_values(struct devlink *devlink)
+{
+ union devlink_param_value value;
+
+ value.vbool = !!mlx4_internal_err_reset;
+ mlx4_devlink_set_init_value(devlink,
+ DEVLINK_PARAM_GENERIC_ID_INT_ERR_RESET,
+ value);
+
+ value.vu32 = 1UL << log_num_mac;
+ mlx4_devlink_set_init_value(devlink,
+ DEVLINK_PARAM_GENERIC_ID_MAX_MACS, value);
+
+ value.vbool = enable_64b_cqe_eqe;
+ mlx4_devlink_set_init_value(devlink,
+ MLX4_DEVLINK_PARAM_ID_ENABLE_64B_CQE_EQE,
+ value);
+
+ value.vbool = enable_4k_uar;
+ mlx4_devlink_set_init_value(devlink,
+ MLX4_DEVLINK_PARAM_ID_ENABLE_4K_UAR,
+ value);
+
+ value.vbool = false;
+ mlx4_devlink_set_init_value(devlink,
+ DEVLINK_PARAM_GENERIC_ID_REGION_SNAPSHOT,
+ value);
+}
+
static inline void mlx4_set_num_reserved_uars(struct mlx4_dev *dev,
struct mlx4_dev_cap *dev_cap)
{
dev->caps.max_rss_tbl_sz = dev_cap->max_rss_tbl_sz;
dev->caps.wol_port[1] = dev_cap->wol_port[1];
dev->caps.wol_port[2] = dev_cap->wol_port[2];
+ dev->caps.health_buffer_addrs = dev_cap->health_buffer_addrs;
/* Save uar page shift */
if (!mlx4_is_slave(dev)) {
}
}
- err = mlx4_catas_init(&priv->dev);
+ err = mlx4_crdump_init(&priv->dev);
if (err)
goto err_release_regions;
+ err = mlx4_catas_init(&priv->dev);
+ if (err)
+ goto err_crdump;
+
err = mlx4_load_one(pdev, pci_dev_data, total_vfs, nvfs, priv, 0);
if (err)
goto err_catas;
err_catas:
mlx4_catas_end(&priv->dev);
+err_crdump:
+ mlx4_crdump_end(&priv->dev);
+
err_release_regions:
pci_release_regions(pdev);
return __set_port_type(info, mlx4_port_type);
}
+static void mlx4_devlink_param_load_driverinit_values(struct devlink *devlink)
+{
+ struct mlx4_priv *priv = devlink_priv(devlink);
+ struct mlx4_dev *dev = &priv->dev;
+ struct mlx4_fw_crdump *crdump = &dev->persist->crdump;
+ union devlink_param_value saved_value;
+ int err;
+
+ err = devlink_param_driverinit_value_get(devlink,
+ DEVLINK_PARAM_GENERIC_ID_INT_ERR_RESET,
+ &saved_value);
+ if (!err && mlx4_internal_err_reset != saved_value.vbool) {
+ mlx4_internal_err_reset = saved_value.vbool;
+ /* Notify on value changed on runtime configuration mode */
+ devlink_param_value_changed(devlink,
+ DEVLINK_PARAM_GENERIC_ID_INT_ERR_RESET);
+ }
+ err = devlink_param_driverinit_value_get(devlink,
+ DEVLINK_PARAM_GENERIC_ID_MAX_MACS,
+ &saved_value);
+ if (!err)
+ log_num_mac = order_base_2(saved_value.vu32);
+ err = devlink_param_driverinit_value_get(devlink,
+ MLX4_DEVLINK_PARAM_ID_ENABLE_64B_CQE_EQE,
+ &saved_value);
+ if (!err)
+ enable_64b_cqe_eqe = saved_value.vbool;
+ err = devlink_param_driverinit_value_get(devlink,
+ MLX4_DEVLINK_PARAM_ID_ENABLE_4K_UAR,
+ &saved_value);
+ if (!err)
+ enable_4k_uar = saved_value.vbool;
+ err = devlink_param_driverinit_value_get(devlink,
+ DEVLINK_PARAM_GENERIC_ID_REGION_SNAPSHOT,
+ &saved_value);
+ if (!err && crdump->snapshot_enable != saved_value.vbool) {
+ crdump->snapshot_enable = saved_value.vbool;
+ devlink_param_value_changed(devlink,
+ DEVLINK_PARAM_GENERIC_ID_REGION_SNAPSHOT);
+ }
+}
+
+static int mlx4_devlink_reload(struct devlink *devlink,
+ struct netlink_ext_ack *extack)
+{
+ struct mlx4_priv *priv = devlink_priv(devlink);
+ struct mlx4_dev *dev = &priv->dev;
+ struct mlx4_dev_persistent *persist = dev->persist;
+ int err;
+
+ if (persist->num_vfs)
+ mlx4_warn(persist->dev, "Reload performed on PF, will cause reset on operating Virtual Functions\n");
+ err = mlx4_restart_one(persist->pdev, true, devlink);
+ if (err)
+ mlx4_err(persist->dev, "mlx4_restart_one failed, ret=%d\n", err);
+
+ return err;
+}
+
static const struct devlink_ops mlx4_devlink_ops = {
.port_type_set = mlx4_devlink_port_type_set,
+ .reload = mlx4_devlink_reload,
};
static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
ret = devlink_register(devlink, &pdev->dev);
if (ret)
goto err_persist_free;
-
- ret = __mlx4_init_one(pdev, id->driver_data, priv);
+ ret = devlink_params_register(devlink, mlx4_devlink_params,
+ ARRAY_SIZE(mlx4_devlink_params));
if (ret)
goto err_devlink_unregister;
+ mlx4_devlink_set_params_init_values(devlink);
+ ret = __mlx4_init_one(pdev, id->driver_data, priv);
+ if (ret)
+ goto err_params_unregister;
pci_save_state(pdev);
return 0;
+err_params_unregister:
+ devlink_params_unregister(devlink, mlx4_devlink_params,
+ ARRAY_SIZE(mlx4_devlink_params));
err_devlink_unregister:
devlink_unregister(devlink);
err_persist_free:
else
mlx4_info(dev, "%s: interface is down\n", __func__);
mlx4_catas_end(dev);
+ mlx4_crdump_end(dev);
if (dev->flags & MLX4_FLAG_SRIOV && !active_vfs) {
mlx4_warn(dev, "Disabling SR-IOV\n");
pci_disable_sriov(pdev);
pci_release_regions(pdev);
mlx4_pci_disable_device(dev);
+ devlink_params_unregister(devlink, mlx4_devlink_params,
+ ARRAY_SIZE(mlx4_devlink_params));
devlink_unregister(devlink);
kfree(dev->persist);
devlink_free(devlink);
return err;
}
-int mlx4_restart_one(struct pci_dev *pdev)
+int mlx4_restart_one(struct pci_dev *pdev, bool reload, struct devlink *devlink)
{
struct mlx4_dev_persistent *persist = pci_get_drvdata(pdev);
struct mlx4_dev *dev = persist->dev;
memcpy(nvfs, dev->persist->nvfs, sizeof(dev->persist->nvfs));
mlx4_unload_one(pdev);
+ if (reload)
+ mlx4_devlink_param_load_driverinit_values(devlink);
err = mlx4_load_one(pdev, pci_dev_data, total_vfs, nvfs, priv, 1);
if (err) {
mlx4_err(dev, "%s: ERROR: mlx4_load_one failed, pci_name=%s, err=%d\n",
void mlx4_stop_catas_poll(struct mlx4_dev *dev);
int mlx4_catas_init(struct mlx4_dev *dev);
void mlx4_catas_end(struct mlx4_dev *dev);
-int mlx4_restart_one(struct pci_dev *pdev);
+int mlx4_crdump_init(struct mlx4_dev *dev);
+void mlx4_crdump_end(struct mlx4_dev *dev);
+int mlx4_restart_one(struct pci_dev *pdev, bool reload,
+ struct devlink *devlink);
int mlx4_register_device(struct mlx4_dev *dev);
void mlx4_unregister_device(struct mlx4_dev *dev);
void mlx4_dispatch_event(struct mlx4_dev *dev, enum mlx4_dev_event type,
void mlx4_enter_error_state(struct mlx4_dev_persistent *persist);
int mlx4_comm_internal_err(u32 slave_read);
+int mlx4_crdump_collect(struct mlx4_dev *dev);
+
int mlx4_SENSE_PORT(struct mlx4_dev *dev, int port,
enum mlx4_port_type *type);
void mlx4_do_sense_ports(struct mlx4_dev *dev,
void mlx4_en_tx_irq(struct mlx4_cq *mcq);
u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb,
- void *accel_priv, select_queue_fallback_t fallback);
+ struct net_device *sb_dev,
+ select_queue_fallback_t fallback);
netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev);
netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring,
struct mlx4_en_rx_alloc *frame,
fpga/ipsec.o fpga/tls.o
mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
- en_tx.o en_rx.o en_dim.o en_txrx.o en_stats.o vxlan.o \
- en_arfs.o en_fs_ethtool.o en_selftest.o en/port.o
+ en_tx.o en_rx.o en_dim.o en_txrx.o en_accel/rxtx.o en_stats.o \
+ vxlan.o en_arfs.o en_fs_ethtool.o en_selftest.o en/port.o
mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o
--- /dev/null
+#ifndef __MLX5E_ACCEL_H__
+#define __MLX5E_ACCEL_H__
+
+#ifdef CONFIG_MLX5_ACCEL
+
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include "en.h"
+
+static inline bool is_metadata_hdr_valid(struct sk_buff *skb)
+{
+ __be16 *ethtype;
+
+ if (unlikely(skb->len < ETH_HLEN + MLX5E_METADATA_ETHER_LEN))
+ return false;
+ ethtype = (__be16 *)(skb->data + ETH_ALEN * 2);
+ if (*ethtype != cpu_to_be16(MLX5E_METADATA_ETHER_TYPE))
+ return false;
+ return true;
+}
+
+static inline void remove_metadata_hdr(struct sk_buff *skb)
+{
+ struct ethhdr *old_eth;
+ struct ethhdr *new_eth;
+
+ /* Remove the metadata from the buffer */
+ old_eth = (struct ethhdr *)skb->data;
+ new_eth = (struct ethhdr *)(skb->data + MLX5E_METADATA_ETHER_LEN);
+ memmove(new_eth, old_eth, 2 * ETH_ALEN);
+ /* Ethertype is already in its new place */
+ skb_pull_inline(skb, MLX5E_METADATA_ETHER_LEN);
+}
+
+#endif /* CONFIG_MLX5_ACCEL */
+
+#endif /* __MLX5E_EN_ACCEL_H__ */
#include "mlx5_core.h"
#include "fpga/tls.h"
-int mlx5_accel_tls_add_tx_flow(struct mlx5_core_dev *mdev, void *flow,
- struct tls_crypto_info *crypto_info,
- u32 start_offload_tcp_sn, u32 *p_swid)
+int mlx5_accel_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,
+ struct tls_crypto_info *crypto_info,
+ u32 start_offload_tcp_sn, u32 *p_swid,
+ bool direction_sx)
{
- return mlx5_fpga_tls_add_tx_flow(mdev, flow, crypto_info,
- start_offload_tcp_sn, p_swid);
+ return mlx5_fpga_tls_add_flow(mdev, flow, crypto_info,
+ start_offload_tcp_sn, p_swid,
+ direction_sx);
}
-void mlx5_accel_tls_del_tx_flow(struct mlx5_core_dev *mdev, u32 swid)
+void mlx5_accel_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid,
+ bool direction_sx)
{
- mlx5_fpga_tls_del_tx_flow(mdev, swid, GFP_KERNEL);
+ mlx5_fpga_tls_del_flow(mdev, swid, GFP_KERNEL, direction_sx);
+}
+
+int mlx5_accel_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq,
+ u64 rcd_sn)
+{
+ return mlx5_fpga_tls_resync_rx(mdev, handle, seq, rcd_sn);
}
bool mlx5_accel_is_tls_device(struct mlx5_core_dev *mdev)
u8 reserved_at_2[0x1e];
};
-int mlx5_accel_tls_add_tx_flow(struct mlx5_core_dev *mdev, void *flow,
- struct tls_crypto_info *crypto_info,
- u32 start_offload_tcp_sn, u32 *p_swid);
-void mlx5_accel_tls_del_tx_flow(struct mlx5_core_dev *mdev, u32 swid);
+int mlx5_accel_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,
+ struct tls_crypto_info *crypto_info,
+ u32 start_offload_tcp_sn, u32 *p_swid,
+ bool direction_sx);
+void mlx5_accel_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid,
+ bool direction_sx);
+int mlx5_accel_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq,
+ u64 rcd_sn);
bool mlx5_accel_is_tls_device(struct mlx5_core_dev *mdev);
u32 mlx5_accel_tls_device_caps(struct mlx5_core_dev *mdev);
int mlx5_accel_tls_init(struct mlx5_core_dev *mdev);
#else
-static inline int
-mlx5_accel_tls_add_tx_flow(struct mlx5_core_dev *mdev, void *flow,
- struct tls_crypto_info *crypto_info,
- u32 start_offload_tcp_sn, u32 *p_swid) { return 0; }
-static inline void mlx5_accel_tls_del_tx_flow(struct mlx5_core_dev *mdev, u32 swid) { }
+static int
+mlx5_accel_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,
+ struct tls_crypto_info *crypto_info,
+ u32 start_offload_tcp_sn, u32 *p_swid,
+ bool direction_sx) { return -ENOTSUPP; }
+static inline void mlx5_accel_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid,
+ bool direction_sx) { }
+static inline int mlx5_accel_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle,
+ u32 seq, u64 rcd_sn) { return 0; }
static inline bool mlx5_accel_is_tls_device(struct mlx5_core_dev *mdev) { return false; }
static inline u32 mlx5_accel_tls_device_caps(struct mlx5_core_dev *mdev) { return 0; }
static inline int mlx5_accel_tls_init(struct mlx5_core_dev *mdev) { return 0; }
unsigned long flags;
bool poll_cmd = ent->polling;
int alloc_ret;
+ int cmd_mode;
sem = ent->page_queue ? &cmd->pages_sem : &cmd->sem;
down(sem);
set_signature(ent, !cmd->checksum_disabled);
dump_command(dev, ent, 1);
ent->ts1 = ktime_get_ns();
+ cmd_mode = cmd->mode;
if (ent->callback)
schedule_delayed_work(&ent->cb_timeout_work, cb_timeout);
iowrite32be(1 << ent->idx, &dev->iseg->cmd_dbell);
mmiowb();
/* if not in polling don't use ent after this point */
- if (cmd->mode == CMD_MODE_POLLING || poll_cmd) {
+ if (cmd_mode == CMD_MODE_POLLING || poll_cmd) {
poll_timeout(ent);
/* make sure we read the descriptor after ownership is SW */
rmb();
{
struct mlx5_core_dev *dev = filp->private_data;
struct mlx5_cmd_debug *dbg = &dev->cmd.dbg;
- char outlen_str[8];
+ char outlen_str[8] = {0};
int outlen;
void *ptr;
int err;
if (copy_from_user(outlen_str, buf, count))
return -EFAULT;
- outlen_str[7] = 0;
-
err = sscanf(outlen_str, "%d", &outlen);
if (err < 0)
return err;
#define MLX5E_MAX_NUM_CHANNELS (MLX5E_INDIR_RQT_SIZE >> 1)
#define MLX5E_MAX_NUM_SQS (MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC)
#define MLX5E_TX_CQ_POLL_BUDGET 128
-#define MLX5E_UPDATE_STATS_INTERVAL 200 /* msecs */
#define MLX5E_SQ_RECOVER_MIN_INTERVAL 500 /* msecs */
#define MLX5E_UMR_WQE_INLINE_SZ \
void mlx5e_build_ptys2ethtool_map(void);
u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
- void *accel_priv, select_queue_fallback_t fallback);
+ struct net_device *sb_dev,
+ select_queue_fallback_t fallback);
netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev);
netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
struct mlx5e_tx_wqe *wqe, u16 pi);
#ifndef __MLX5E_EN_ACCEL_H__
#define __MLX5E_EN_ACCEL_H__
-#ifdef CONFIG_MLX5_ACCEL
-
#include <linux/skbuff.h>
#include <linux/netdevice.h>
#include "en_accel/ipsec_rxtx.h"
#include "en_accel/tls_rxtx.h"
+#include "en_accel/rxtx.h"
#include "en.h"
static inline struct sk_buff *mlx5e_accel_handle_tx(struct sk_buff *skb,
}
#endif
+ if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) {
+ skb = mlx5e_udp_gso_handle_tx_skb(dev, sq, skb, wqe, pi);
+ if (unlikely(!skb))
+ return NULL;
+ }
+
return skb;
}
-#endif /* CONFIG_MLX5_ACCEL */
-
#endif /* __MLX5E_EN_ACCEL_H__ */
#include "en_accel/ipsec_rxtx.h"
#include "en_accel/ipsec.h"
+#include "accel/accel.h"
#include "en.h"
enum {
}
struct sk_buff *mlx5e_ipsec_handle_rx_skb(struct net_device *netdev,
- struct sk_buff *skb)
+ struct sk_buff *skb, u32 *cqe_bcnt)
{
struct mlx5e_ipsec_metadata *mdata;
- struct ethhdr *old_eth;
- struct ethhdr *new_eth;
struct xfrm_state *xs;
- __be16 *ethtype;
- /* Detect inline metadata */
- if (skb->len < ETH_HLEN + MLX5E_METADATA_ETHER_LEN)
- return skb;
- ethtype = (__be16 *)(skb->data + ETH_ALEN * 2);
- if (*ethtype != cpu_to_be16(MLX5E_METADATA_ETHER_TYPE))
+ if (!is_metadata_hdr_valid(skb))
return skb;
/* Use the metadata */
return NULL;
}
- /* Remove the metadata from the buffer */
- old_eth = (struct ethhdr *)skb->data;
- new_eth = (struct ethhdr *)(skb->data + MLX5E_METADATA_ETHER_LEN);
- memmove(new_eth, old_eth, 2 * ETH_ALEN);
- /* Ethertype is already in its new place */
- skb_pull_inline(skb, MLX5E_METADATA_ETHER_LEN);
+ remove_metadata_hdr(skb);
+ *cqe_bcnt -= MLX5E_METADATA_ETHER_LEN;
return skb;
}
#include "en.h"
struct sk_buff *mlx5e_ipsec_handle_rx_skb(struct net_device *netdev,
- struct sk_buff *skb);
+ struct sk_buff *skb, u32 *cqe_bcnt);
void mlx5e_ipsec_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
void mlx5e_ipsec_inverse_table_init(void);
--- /dev/null
+#include "en_accel/rxtx.h"
+
+static void mlx5e_udp_gso_prepare_last_skb(struct sk_buff *skb,
+ struct sk_buff *nskb,
+ int remaining)
+{
+ int bytes_needed = remaining, remaining_headlen, remaining_page_offset;
+ int headlen = skb_transport_offset(skb) + sizeof(struct udphdr);
+ int payload_len = remaining + sizeof(struct udphdr);
+ int k = 0, i, j;
+
+ skb_copy_bits(skb, 0, nskb->data, headlen);
+ nskb->dev = skb->dev;
+ skb_reset_mac_header(nskb);
+ skb_set_network_header(nskb, skb_network_offset(skb));
+ skb_set_transport_header(nskb, skb_transport_offset(skb));
+ skb_set_tail_pointer(nskb, headlen);
+
+ /* How many frags do we need? */
+ for (i = skb_shinfo(skb)->nr_frags - 1; i >= 0; i--) {
+ bytes_needed -= skb_frag_size(&skb_shinfo(skb)->frags[i]);
+ k++;
+ if (bytes_needed <= 0)
+ break;
+ }
+
+ /* Fill the first frag and split it if necessary */
+ j = skb_shinfo(skb)->nr_frags - k;
+ remaining_page_offset = -bytes_needed;
+ skb_fill_page_desc(nskb, 0,
+ skb_shinfo(skb)->frags[j].page.p,
+ skb_shinfo(skb)->frags[j].page_offset + remaining_page_offset,
+ skb_shinfo(skb)->frags[j].size - remaining_page_offset);
+
+ skb_frag_ref(skb, j);
+
+ /* Fill the rest of the frags */
+ for (i = 1; i < k; i++) {
+ j = skb_shinfo(skb)->nr_frags - k + i;
+
+ skb_fill_page_desc(nskb, i,
+ skb_shinfo(skb)->frags[j].page.p,
+ skb_shinfo(skb)->frags[j].page_offset,
+ skb_shinfo(skb)->frags[j].size);
+ skb_frag_ref(skb, j);
+ }
+ skb_shinfo(nskb)->nr_frags = k;
+
+ remaining_headlen = remaining - skb->data_len;
+
+ /* headlen contains remaining data? */
+ if (remaining_headlen > 0)
+ skb_copy_bits(skb, skb->len - remaining, nskb->data + headlen,
+ remaining_headlen);
+ nskb->len = remaining + headlen;
+ nskb->data_len = payload_len - sizeof(struct udphdr) +
+ max_t(int, 0, remaining_headlen);
+ nskb->protocol = skb->protocol;
+ if (nskb->protocol == htons(ETH_P_IP)) {
+ ip_hdr(nskb)->id = htons(ntohs(ip_hdr(nskb)->id) +
+ skb_shinfo(skb)->gso_segs);
+ ip_hdr(nskb)->tot_len =
+ htons(payload_len + sizeof(struct iphdr));
+ } else {
+ ipv6_hdr(nskb)->payload_len = htons(payload_len);
+ }
+ udp_hdr(nskb)->len = htons(payload_len);
+ skb_shinfo(nskb)->gso_size = 0;
+ nskb->ip_summed = skb->ip_summed;
+ nskb->csum_start = skb->csum_start;
+ nskb->csum_offset = skb->csum_offset;
+ nskb->queue_mapping = skb->queue_mapping;
+}
+
+/* might send skbs and update wqe and pi */
+struct sk_buff *mlx5e_udp_gso_handle_tx_skb(struct net_device *netdev,
+ struct mlx5e_txqsq *sq,
+ struct sk_buff *skb,
+ struct mlx5e_tx_wqe **wqe,
+ u16 *pi)
+{
+ int payload_len = skb_shinfo(skb)->gso_size + sizeof(struct udphdr);
+ int headlen = skb_transport_offset(skb) + sizeof(struct udphdr);
+ int remaining = (skb->len - headlen) % skb_shinfo(skb)->gso_size;
+ struct sk_buff *nskb;
+
+ if (skb->protocol == htons(ETH_P_IP))
+ ip_hdr(skb)->tot_len = htons(payload_len + sizeof(struct iphdr));
+ else
+ ipv6_hdr(skb)->payload_len = htons(payload_len);
+ udp_hdr(skb)->len = htons(payload_len);
+ if (!remaining)
+ return skb;
+
+ sq->stats->udp_seg_rem++;
+ nskb = alloc_skb(max_t(int, headlen, headlen + remaining - skb->data_len), GFP_ATOMIC);
+ if (unlikely(!nskb)) {
+ sq->stats->dropped++;
+ return NULL;
+ }
+
+ mlx5e_udp_gso_prepare_last_skb(skb, nskb, remaining);
+
+ skb_shinfo(skb)->gso_segs--;
+ pskb_trim(skb, skb->len - remaining);
+ mlx5e_sq_xmit(sq, skb, *wqe, *pi);
+ mlx5e_sq_fetch_wqe(sq, wqe, pi);
+ return nskb;
+}
--- /dev/null
+
+#ifndef __MLX5E_EN_ACCEL_RX_TX_H__
+#define __MLX5E_EN_ACCEL_RX_TX_H__
+
+#include <linux/skbuff.h>
+#include "en.h"
+
+struct sk_buff *mlx5e_udp_gso_handle_tx_skb(struct net_device *netdev,
+ struct mlx5e_txqsq *sq,
+ struct sk_buff *skb,
+ struct mlx5e_tx_wqe **wqe,
+ u16 *pi);
+
+#endif
u32 caps = mlx5_accel_tls_device_caps(mdev);
int ret = -ENOMEM;
void *flow;
-
- if (direction != TLS_OFFLOAD_CTX_DIR_TX)
- return -EINVAL;
+ u32 swid;
flow = kzalloc(MLX5_ST_SZ_BYTES(tls_flow), GFP_KERNEL);
if (!flow)
if (ret)
goto free_flow;
+ ret = mlx5_accel_tls_add_flow(mdev, flow, crypto_info,
+ start_offload_tcp_sn, &swid,
+ direction == TLS_OFFLOAD_CTX_DIR_TX);
+ if (ret < 0)
+ goto free_flow;
+
if (direction == TLS_OFFLOAD_CTX_DIR_TX) {
- struct mlx5e_tls_offload_context *tx_ctx =
+ struct mlx5e_tls_offload_context_tx *tx_ctx =
mlx5e_get_tls_tx_context(tls_ctx);
- u32 swid;
-
- ret = mlx5_accel_tls_add_tx_flow(mdev, flow, crypto_info,
- start_offload_tcp_sn, &swid);
- if (ret < 0)
- goto free_flow;
tx_ctx->swid = htonl(swid);
tx_ctx->expected_seq = start_offload_tcp_sn;
+ } else {
+ struct mlx5e_tls_offload_context_rx *rx_ctx =
+ mlx5e_get_tls_rx_context(tls_ctx);
+
+ rx_ctx->handle = htonl(swid);
}
return 0;
enum tls_offload_ctx_dir direction)
{
struct mlx5e_priv *priv = netdev_priv(netdev);
+ unsigned int handle;
- if (direction == TLS_OFFLOAD_CTX_DIR_TX) {
- u32 swid = ntohl(mlx5e_get_tls_tx_context(tls_ctx)->swid);
+ handle = ntohl((direction == TLS_OFFLOAD_CTX_DIR_TX) ?
+ mlx5e_get_tls_tx_context(tls_ctx)->swid :
+ mlx5e_get_tls_rx_context(tls_ctx)->handle);
- mlx5_accel_tls_del_tx_flow(priv->mdev, swid);
- } else {
- netdev_err(netdev, "unsupported direction %d\n", direction);
- }
+ mlx5_accel_tls_del_flow(priv->mdev, handle,
+ direction == TLS_OFFLOAD_CTX_DIR_TX);
+}
+
+static void mlx5e_tls_resync_rx(struct net_device *netdev, struct sock *sk,
+ u32 seq, u64 rcd_sn)
+{
+ struct tls_context *tls_ctx = tls_get_ctx(sk);
+ struct mlx5e_priv *priv = netdev_priv(netdev);
+ struct mlx5e_tls_offload_context_rx *rx_ctx;
+
+ rx_ctx = mlx5e_get_tls_rx_context(tls_ctx);
+
+ netdev_info(netdev, "resyncing seq %d rcd %lld\n", seq,
+ be64_to_cpu(rcd_sn));
+ mlx5_accel_tls_resync_rx(priv->mdev, rx_ctx->handle, seq, rcd_sn);
+ atomic64_inc(&priv->tls->sw_stats.rx_tls_resync_reply);
}
static const struct tlsdev_ops mlx5e_tls_ops = {
.tls_dev_add = mlx5e_tls_add,
.tls_dev_del = mlx5e_tls_del,
+ .tls_dev_resync_rx = mlx5e_tls_resync_rx,
};
void mlx5e_tls_build_netdev(struct mlx5e_priv *priv)
{
+ u32 caps = mlx5_accel_tls_device_caps(priv->mdev);
struct net_device *netdev = priv->netdev;
if (!mlx5_accel_is_tls_device(priv->mdev))
return;
- netdev->features |= NETIF_F_HW_TLS_TX;
- netdev->hw_features |= NETIF_F_HW_TLS_TX;
+ if (caps & MLX5_ACCEL_TLS_TX) {
+ netdev->features |= NETIF_F_HW_TLS_TX;
+ netdev->hw_features |= NETIF_F_HW_TLS_TX;
+ }
+
+ if (caps & MLX5_ACCEL_TLS_RX) {
+ netdev->features |= NETIF_F_HW_TLS_RX;
+ netdev->hw_features |= NETIF_F_HW_TLS_RX;
+ }
+
+ if (!(caps & MLX5_ACCEL_TLS_LRO)) {
+ netdev->features &= ~NETIF_F_LRO;
+ netdev->hw_features &= ~NETIF_F_LRO;
+ }
+
netdev->tlsdev_ops = &mlx5e_tls_ops;
}
atomic64_t tx_tls_drop_resync_alloc;
atomic64_t tx_tls_drop_no_sync_data;
atomic64_t tx_tls_drop_bypass_required;
+ atomic64_t rx_tls_drop_resync_request;
+ atomic64_t rx_tls_resync_request;
+ atomic64_t rx_tls_resync_reply;
+ atomic64_t rx_tls_auth_fail;
};
struct mlx5e_tls {
struct mlx5e_tls_sw_stats sw_stats;
};
-struct mlx5e_tls_offload_context {
- struct tls_offload_context base;
+struct mlx5e_tls_offload_context_tx {
+ struct tls_offload_context_tx base;
u32 expected_seq;
__be32 swid;
};
-static inline struct mlx5e_tls_offload_context *
+static inline struct mlx5e_tls_offload_context_tx *
mlx5e_get_tls_tx_context(struct tls_context *tls_ctx)
{
- BUILD_BUG_ON(sizeof(struct mlx5e_tls_offload_context) >
- TLS_OFFLOAD_CONTEXT_SIZE);
- return container_of(tls_offload_ctx(tls_ctx),
- struct mlx5e_tls_offload_context,
+ BUILD_BUG_ON(sizeof(struct mlx5e_tls_offload_context_tx) >
+ TLS_OFFLOAD_CONTEXT_SIZE_TX);
+ return container_of(tls_offload_ctx_tx(tls_ctx),
+ struct mlx5e_tls_offload_context_tx,
+ base);
+}
+
+struct mlx5e_tls_offload_context_rx {
+ struct tls_offload_context_rx base;
+ __be32 handle;
+};
+
+static inline struct mlx5e_tls_offload_context_rx *
+mlx5e_get_tls_rx_context(struct tls_context *tls_ctx)
+{
+ BUILD_BUG_ON(sizeof(struct mlx5e_tls_offload_context_rx) >
+ TLS_OFFLOAD_CONTEXT_SIZE_RX);
+ return container_of(tls_offload_ctx_rx(tls_ctx),
+ struct mlx5e_tls_offload_context_rx,
base);
}
#include "en_accel/tls.h"
#include "en_accel/tls_rxtx.h"
+#include "accel/accel.h"
+
+#include <net/inet6_hashtables.h>
+#include <linux/ipv6.h>
+
+#define SYNDROM_DECRYPTED 0x30
+#define SYNDROM_RESYNC_REQUEST 0x31
+#define SYNDROM_AUTH_FAILED 0x32
#define SYNDROME_OFFLOAD_REQUIRED 32
#define SYNDROME_SYNC 33
skb_frag_t frags[MAX_SKB_FRAGS];
};
-struct mlx5e_tls_metadata {
+struct recv_metadata_content {
+ u8 syndrome;
+ u8 reserved;
+ __be32 sync_seq;
+} __packed;
+
+struct send_metadata_content {
/* One byte of syndrome followed by 3 bytes of swid */
__be32 syndrome_swid;
__be16 first_seq;
+} __packed;
+
+struct mlx5e_tls_metadata {
+ union {
+ /* from fpga to host */
+ struct recv_metadata_content recv;
+ /* from host to fpga */
+ struct send_metadata_content send;
+ unsigned char raw[6];
+ } __packed content;
/* packet type ID field */
__be16 ethertype;
} __packed;
2 * ETH_ALEN);
eth->h_proto = cpu_to_be16(MLX5E_METADATA_ETHER_TYPE);
- pet->syndrome_swid = htonl(SYNDROME_OFFLOAD_REQUIRED << 24) | swid;
+ pet->content.send.syndrome_swid =
+ htonl(SYNDROME_OFFLOAD_REQUIRED << 24) | swid;
return 0;
}
-static int mlx5e_tls_get_sync_data(struct mlx5e_tls_offload_context *context,
+static int mlx5e_tls_get_sync_data(struct mlx5e_tls_offload_context_tx *context,
u32 tcp_seq, struct sync_info *info)
{
int remaining, i = 0, ret = -EINVAL;
pet = (struct mlx5e_tls_metadata *)(nskb->data + sizeof(struct ethhdr));
memcpy(pet, &syndrome, sizeof(syndrome));
- pet->first_seq = htons(tcp_seq);
+ pet->content.send.first_seq = htons(tcp_seq);
/* MLX5 devices don't care about the checksum partial start, offset
* and pseudo header
}
static struct sk_buff *
-mlx5e_tls_handle_ooo(struct mlx5e_tls_offload_context *context,
+mlx5e_tls_handle_ooo(struct mlx5e_tls_offload_context_tx *context,
struct mlx5e_txqsq *sq, struct sk_buff *skb,
struct mlx5e_tx_wqe **wqe,
u16 *pi,
u16 *pi)
{
struct mlx5e_priv *priv = netdev_priv(netdev);
- struct mlx5e_tls_offload_context *context;
+ struct mlx5e_tls_offload_context_tx *context;
struct tls_context *tls_ctx;
u32 expected_seq;
int datalen;
out:
return skb;
}
+
+static int tls_update_resync_sn(struct net_device *netdev,
+ struct sk_buff *skb,
+ struct mlx5e_tls_metadata *mdata)
+{
+ struct sock *sk = NULL;
+ struct iphdr *iph;
+ struct tcphdr *th;
+ __be32 seq;
+
+ if (mdata->ethertype != htons(ETH_P_IP))
+ return -EINVAL;
+
+ iph = (struct iphdr *)(mdata + 1);
+
+ th = ((void *)iph) + iph->ihl * 4;
+
+ if (iph->version == 4) {
+ sk = inet_lookup_established(dev_net(netdev), &tcp_hashinfo,
+ iph->saddr, th->source, iph->daddr,
+ th->dest, netdev->ifindex);
+#if IS_ENABLED(CONFIG_IPV6)
+ } else {
+ struct ipv6hdr *ipv6h = (struct ipv6hdr *)iph;
+
+ sk = __inet6_lookup_established(dev_net(netdev), &tcp_hashinfo,
+ &ipv6h->saddr, th->source,
+ &ipv6h->daddr, th->dest,
+ netdev->ifindex, 0);
+#endif
+ }
+ if (!sk || sk->sk_state == TCP_TIME_WAIT) {
+ struct mlx5e_priv *priv = netdev_priv(netdev);
+
+ atomic64_inc(&priv->tls->sw_stats.rx_tls_drop_resync_request);
+ goto out;
+ }
+
+ skb->sk = sk;
+ skb->destructor = sock_edemux;
+
+ memcpy(&seq, &mdata->content.recv.sync_seq, sizeof(seq));
+ tls_offload_rx_resync_request(sk, seq);
+out:
+ return 0;
+}
+
+void mlx5e_tls_handle_rx_skb(struct net_device *netdev, struct sk_buff *skb,
+ u32 *cqe_bcnt)
+{
+ struct mlx5e_tls_metadata *mdata;
+ struct mlx5e_priv *priv;
+
+ if (!is_metadata_hdr_valid(skb))
+ return;
+
+ /* Use the metadata */
+ mdata = (struct mlx5e_tls_metadata *)(skb->data + ETH_HLEN);
+ switch (mdata->content.recv.syndrome) {
+ case SYNDROM_DECRYPTED:
+ skb->decrypted = 1;
+ break;
+ case SYNDROM_RESYNC_REQUEST:
+ tls_update_resync_sn(netdev, skb, mdata);
+ priv = netdev_priv(netdev);
+ atomic64_inc(&priv->tls->sw_stats.rx_tls_resync_request);
+ break;
+ case SYNDROM_AUTH_FAILED:
+ /* Authentication failure will be observed and verified by kTLS */
+ priv = netdev_priv(netdev);
+ atomic64_inc(&priv->tls->sw_stats.rx_tls_auth_fail);
+ break;
+ default:
+ /* Bypass the metadata header to others */
+ return;
+ }
+
+ remove_metadata_hdr(skb);
+ *cqe_bcnt -= MLX5E_METADATA_ETHER_LEN;
+}
struct mlx5e_tx_wqe **wqe,
u16 *pi);
+void mlx5e_tls_handle_rx_skb(struct net_device *netdev, struct sk_buff *skb,
+ u32 *cqe_bcnt);
+
#endif /* CONFIG_MLX5_EN_TLS */
#endif /* __MLX5E_TLS_RXTX_H__ */
struct delayed_work *dwork = to_delayed_work(work);
struct mlx5e_priv *priv = container_of(dwork, struct mlx5e_priv,
update_stats_work);
+
mutex_lock(&priv->state_lock);
- if (test_bit(MLX5E_STATE_OPENED, &priv->state)) {
- priv->profile->update_stats(priv);
- queue_delayed_work(priv->wq, dwork,
- msecs_to_jiffies(MLX5E_UPDATE_STATS_INTERVAL));
- }
+ priv->profile->update_stats(priv);
mutex_unlock(&priv->state_lock);
}
{
int wq_sz = mlx5_wq_ll_get_size(&rq->mpwqe.wq);
- rq->mpwqe.info = kcalloc_node(wq_sz, sizeof(*rq->mpwqe.info),
- GFP_KERNEL, cpu_to_node(c->cpu));
+ rq->mpwqe.info = kvzalloc_node(array_size(wq_sz,
+ sizeof(*rq->mpwqe.info)),
+ GFP_KERNEL, cpu_to_node(c->cpu));
if (!rq->mpwqe.info)
return -ENOMEM;
err_free:
switch (rq->wq_type) {
case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
- kfree(rq->mpwqe.info);
+ kvfree(rq->mpwqe.info);
mlx5_core_destroy_mkey(mdev, &rq->umr_mkey);
break;
default: /* MLX5_WQ_TYPE_CYCLIC */
switch (rq->wq_type) {
case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
- kfree(rq->mpwqe.info);
+ kvfree(rq->mpwqe.info);
mlx5_core_destroy_mkey(rq->mdev, &rq->umr_mkey);
break;
default: /* MLX5_WQ_TYPE_CYCLIC */
static void mlx5e_free_xdpsq_db(struct mlx5e_xdpsq *sq)
{
- kfree(sq->db.di);
+ kvfree(sq->db.di);
}
static int mlx5e_alloc_xdpsq_db(struct mlx5e_xdpsq *sq, int numa)
{
int wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
- sq->db.di = kcalloc_node(wq_sz, sizeof(*sq->db.di),
- GFP_KERNEL, numa);
+ sq->db.di = kvzalloc_node(array_size(wq_sz, sizeof(*sq->db.di)),
+ GFP_KERNEL, numa);
if (!sq->db.di) {
mlx5e_free_xdpsq_db(sq);
return -ENOMEM;
static void mlx5e_free_icosq_db(struct mlx5e_icosq *sq)
{
- kfree(sq->db.ico_wqe);
+ kvfree(sq->db.ico_wqe);
}
static int mlx5e_alloc_icosq_db(struct mlx5e_icosq *sq, int numa)
{
u8 wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
- sq->db.ico_wqe = kcalloc_node(wq_sz, sizeof(*sq->db.ico_wqe),
- GFP_KERNEL, numa);
+ sq->db.ico_wqe = kvzalloc_node(array_size(wq_sz,
+ sizeof(*sq->db.ico_wqe)),
+ GFP_KERNEL, numa);
if (!sq->db.ico_wqe)
return -ENOMEM;
static void mlx5e_free_txqsq_db(struct mlx5e_txqsq *sq)
{
- kfree(sq->db.wqe_info);
- kfree(sq->db.dma_fifo);
+ kvfree(sq->db.wqe_info);
+ kvfree(sq->db.dma_fifo);
}
static int mlx5e_alloc_txqsq_db(struct mlx5e_txqsq *sq, int numa)
int wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
int df_sz = wq_sz * MLX5_SEND_WQEBB_NUM_DS;
- sq->db.dma_fifo = kcalloc_node(df_sz, sizeof(*sq->db.dma_fifo),
- GFP_KERNEL, numa);
- sq->db.wqe_info = kcalloc_node(wq_sz, sizeof(*sq->db.wqe_info),
- GFP_KERNEL, numa);
+ sq->db.dma_fifo = kvzalloc_node(array_size(df_sz,
+ sizeof(*sq->db.dma_fifo)),
+ GFP_KERNEL, numa);
+ sq->db.wqe_info = kvzalloc_node(array_size(wq_sz,
+ sizeof(*sq->db.wqe_info)),
+ GFP_KERNEL, numa);
if (!sq->db.dma_fifo || !sq->db.wqe_info) {
mlx5e_free_txqsq_db(sq);
return -ENOMEM;
int err;
int eqn;
- c = kzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu));
+ c = kvzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu));
if (!c)
return -ENOMEM;
err_napi_del:
netif_napi_del(&c->napi);
- kfree(c);
+ kvfree(c);
return err;
}
mlx5e_close_cq(&c->icosq.cq);
netif_napi_del(&c->napi);
- kfree(c);
+ kvfree(c);
}
#define DEFAULT_FRAG_SIZE (2048)
chs->num = chs->params.num_channels;
chs->c = kcalloc(chs->num, sizeof(struct mlx5e_channel *), GFP_KERNEL);
- cparam = kzalloc(sizeof(struct mlx5e_channel_param), GFP_KERNEL);
+ cparam = kvzalloc(sizeof(struct mlx5e_channel_param), GFP_KERNEL);
if (!chs->c || !cparam)
goto err_free;
goto err_close_channels;
}
- kfree(cparam);
+ kvfree(cparam);
return 0;
err_close_channels:
err_free:
kfree(chs->c);
- kfree(cparam);
+ kvfree(cparam);
chs->num = 0;
return err;
}
mlx5e_activate_channels(&priv->channels);
netif_tx_start_all_queues(priv->netdev);
- if (MLX5_VPORT_MANAGER(priv->mdev))
+ if (MLX5_ESWITCH_MANAGER(priv->mdev))
mlx5e_add_sqs_fwd_rules(priv);
mlx5e_wait_channels_min_rx_wqes(&priv->channels);
{
mlx5e_redirect_rqts_to_drop(priv);
- if (MLX5_VPORT_MANAGER(priv->mdev))
+ if (MLX5_ESWITCH_MANAGER(priv->mdev))
mlx5e_remove_sqs_fwd_rules(priv);
/* FIXME: This is a W/A only for tx timeout watch dog false alarm when
switch (f->command) {
case TC_BLOCK_BIND:
return tcf_block_cb_register(f->block, mlx5e_setup_tc_block_cb,
- priv, priv);
+ priv, priv, f->extack);
case TC_BLOCK_UNBIND:
tcf_block_cb_unregister(f->block, mlx5e_setup_tc_block_cb,
priv);
struct mlx5e_vport_stats *vstats = &priv->stats.vport;
struct mlx5e_pport_stats *pstats = &priv->stats.pport;
+ /* update HW stats in background for next time */
+ queue_delayed_work(priv->wq, &priv->update_stats_work, 0);
+
if (mlx5e_is_uplink_rep(priv)) {
stats->rx_packets = PPORT_802_3_GET(pstats, a_frames_received_ok);
stats->rx_bytes = PPORT_802_3_GET(pstats, a_octets_received_ok);
return mlx5e_xdp_set(dev, xdp->prog);
case XDP_QUERY_PROG:
xdp->prog_id = mlx5e_xdp_query(dev);
- xdp->prog_attached = !!xdp->prog_id;
return 0;
default:
return -EINVAL;
netdev->features |= NETIF_F_HIGHDMA;
netdev->features |= NETIF_F_HW_VLAN_STAG_FILTER;
+ netdev->features |= NETIF_F_GSO_UDP_L4;
+ netdev->hw_features |= NETIF_F_GSO_UDP_L4;
+
netdev->priv_flags |= IFF_UNICAST_FLT;
mlx5e_set_netdev_dev_addr(netdev);
#if IS_ENABLED(CONFIG_MLX5_ESWITCH)
- if (MLX5_VPORT_MANAGER(mdev))
+ if (MLX5_ESWITCH_MANAGER(mdev))
netdev->switchdev_ops = &mlx5e_switchdev_ops;
#endif
mlx5e_enable_async_events(priv);
- if (MLX5_VPORT_MANAGER(priv->mdev))
+ if (MLX5_ESWITCH_MANAGER(priv->mdev))
mlx5e_register_vport_reps(priv);
if (netdev->reg_state != NETREG_REGISTERED)
queue_work(priv->wq, &priv->set_rx_mode_work);
- if (MLX5_VPORT_MANAGER(priv->mdev))
+ if (MLX5_ESWITCH_MANAGER(priv->mdev))
mlx5e_unregister_vport_reps(priv);
mlx5e_disable_async_events(priv);
return NULL;
#ifdef CONFIG_MLX5_ESWITCH
- if (MLX5_VPORT_MANAGER(mdev)) {
+ if (MLX5_ESWITCH_MANAGER(mdev)) {
rpriv = mlx5e_alloc_nic_rep_priv(mdev);
if (!rpriv) {
mlx5_core_warn(mdev, "Failed to alloc NIC rep priv data\n");
switch (f->command) {
case TC_BLOCK_BIND:
return tcf_block_cb_register(f->block, mlx5e_rep_setup_tc_cb,
- priv, priv);
+ priv, priv, f->extack);
case TC_BLOCK_UNBIND:
tcf_block_cb_unregister(f->block, mlx5e_rep_setup_tc_cb, priv);
return 0;
struct mlx5e_rep_priv *rpriv = priv->ppriv;
struct mlx5_eswitch_rep *rep;
- if (!MLX5_CAP_GEN(priv->mdev, vport_group_manager))
+ if (!MLX5_ESWITCH_MANAGER(priv->mdev))
return false;
rep = rpriv->rep;
static bool mlx5e_is_vf_vport_rep(struct mlx5e_priv *priv)
{
struct mlx5e_rep_priv *rpriv = priv->ppriv;
- struct mlx5_eswitch_rep *rep = rpriv->rep;
+ struct mlx5_eswitch_rep *rep;
+
+ if (!MLX5_ESWITCH_MANAGER(priv->mdev))
+ return false;
+ rep = rpriv->rep;
if (rep && rep->vport != FDB_UPLINK_VPORT)
return true;
{
struct mlx5e_priv *priv = netdev_priv(dev);
+ /* update HW stats in background for next time */
+ queue_delayed_work(priv->wq, &priv->update_stats_work, 0);
+
memcpy(stats, &priv->stats.vf_vport, sizeof(*stats));
}
#include "en_rep.h"
#include "ipoib/ipoib.h"
#include "en_accel/ipsec_rxtx.h"
+#include "en_accel/tls_rxtx.h"
#include "lib/clock.h"
static inline bool mlx5e_rx_hw_stamp(struct hwtstamp_config *config)
sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_UMR;
sq->pc += MLX5E_UMR_WQEBBS;
- mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, &umr_wqe->ctrl);
+ mlx5e_notify_hw(wq, sq->pc, sq->uar_map, &umr_wqe->ctrl);
return 0;
if (!rq->mpwqe.umr_in_progress)
mlx5e_alloc_rx_mpwqe(rq, wq->head);
+ else
+ rq->stats->congst_umr += mlx5_wq_ll_missing(wq) > 2;
return false;
}
struct net_device *netdev = rq->netdev;
skb->mac_len = ETH_HLEN;
+
+#ifdef CONFIG_MLX5_EN_TLS
+ mlx5e_tls_handle_rx_skb(netdev, skb, &cqe_bcnt);
+#endif
+
if (lro_num_seg > 1) {
mlx5e_lro_update_hdr(skb, cqe, cqe_bcnt);
skb_shinfo(skb)->gso_size = DIV_ROUND_UP(cqe_bcnt, lro_num_seg);
}
if (unlikely(mpwrq_is_filler_cqe(cqe))) {
- rq->stats->mpwqe_filler++;
+ struct mlx5e_rq_stats *stats = rq->stats;
+
+ stats->mpwqe_filler_cqes++;
+ stats->mpwqe_filler_strides += cstrides;
goto mpwrq_cqe_out;
}
} while (!last_wqe);
} while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
+ rq->stats->xdp_tx_cqe += i;
+
mlx5_cqwq_update_db_record(&cq->wq);
/* ensure cq space is freed before enabling more cqes */
mlx5e_free_rx_wqe(rq, wi);
goto wq_cyc_pop;
}
- skb = mlx5e_ipsec_handle_rx_skb(rq->netdev, skb);
+ skb = mlx5e_ipsec_handle_rx_skb(rq->netdev, skb, &cqe_bcnt);
if (unlikely(!skb)) {
mlx5e_free_rx_wqe(rq, wi);
goto wq_cyc_pop;
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_inner_packets) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_inner_bytes) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_added_vlan_packets) },
+ { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_nop) },
#ifdef CONFIG_MLX5_EN_TLS
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_ooo) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary_inner) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_drop) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx) },
+ { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_cqe) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_full) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_none) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_partial) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_dropped) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xmit_more) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_recover) },
+ { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_cqes) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_wake) },
+ { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_udp_seg_rem) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_cqe_err) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_wqe_err) },
- { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_filler) },
+ { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_filler_cqes) },
+ { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_filler_strides) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_buff_alloc_err) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cqe_compress_blks) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cqe_compress_pkts) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_empty) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_busy) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_waive) },
+ { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_congst_umr) },
+ { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_events) },
+ { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_poll) },
+ { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_arm) },
+ { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_aff_change) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_eq_rearm) },
};
s->rx_csum_unnecessary_inner += rq_stats->csum_unnecessary_inner;
s->rx_xdp_drop += rq_stats->xdp_drop;
s->rx_xdp_tx += rq_stats->xdp_tx;
+ s->rx_xdp_tx_cqe += rq_stats->xdp_tx_cqe;
s->rx_xdp_tx_full += rq_stats->xdp_tx_full;
s->rx_wqe_err += rq_stats->wqe_err;
- s->rx_mpwqe_filler += rq_stats->mpwqe_filler;
+ s->rx_mpwqe_filler_cqes += rq_stats->mpwqe_filler_cqes;
+ s->rx_mpwqe_filler_strides += rq_stats->mpwqe_filler_strides;
s->rx_buff_alloc_err += rq_stats->buff_alloc_err;
s->rx_cqe_compress_blks += rq_stats->cqe_compress_blks;
s->rx_cqe_compress_pkts += rq_stats->cqe_compress_pkts;
s->rx_cache_empty += rq_stats->cache_empty;
s->rx_cache_busy += rq_stats->cache_busy;
s->rx_cache_waive += rq_stats->cache_waive;
+ s->rx_congst_umr += rq_stats->congst_umr;
+ s->ch_events += ch_stats->events;
+ s->ch_poll += ch_stats->poll;
+ s->ch_arm += ch_stats->arm;
+ s->ch_aff_change += ch_stats->aff_change;
s->ch_eq_rearm += ch_stats->eq_rearm;
for (j = 0; j < priv->max_opened_tc; j++) {
s->tx_tso_inner_packets += sq_stats->tso_inner_packets;
s->tx_tso_inner_bytes += sq_stats->tso_inner_bytes;
s->tx_added_vlan_packets += sq_stats->added_vlan_packets;
+ s->tx_nop += sq_stats->nop;
s->tx_queue_stopped += sq_stats->stopped;
s->tx_queue_wake += sq_stats->wake;
+ s->tx_udp_seg_rem += sq_stats->udp_seg_rem;
s->tx_queue_dropped += sq_stats->dropped;
s->tx_cqe_err += sq_stats->cqe_err;
s->tx_recover += sq_stats->recover;
s->tx_tls_ooo += sq_stats->tls_ooo;
s->tx_tls_resync_bytes += sq_stats->tls_resync_bytes;
#endif
+ s->tx_cqes += sq_stats->cqes;
}
}
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_none) },
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_drop) },
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_tx) },
+ { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_tx_cqe) },
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_tx_full) },
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, lro_packets) },
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, lro_bytes) },
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, removed_vlan_packets) },
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, wqe_err) },
- { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, mpwqe_filler) },
+ { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, mpwqe_filler_cqes) },
+ { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, mpwqe_filler_strides) },
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, buff_alloc_err) },
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cqe_compress_blks) },
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cqe_compress_pkts) },
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_empty) },
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_busy) },
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_waive) },
+ { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, congst_umr) },
};
static const struct counter_desc sq_stats_desc[] = {
{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, dropped) },
{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, xmit_more) },
{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, recover) },
+ { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, cqes) },
{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, wake) },
{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, cqe_err) },
};
static const struct counter_desc ch_stats_desc[] = {
+ { MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, events) },
+ { MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, poll) },
+ { MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, arm) },
+ { MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, aff_change) },
{ MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, eq_rearm) },
};
u64 tx_tso_inner_packets;
u64 tx_tso_inner_bytes;
u64 tx_added_vlan_packets;
+ u64 tx_nop;
u64 rx_lro_packets;
u64 rx_lro_bytes;
u64 rx_removed_vlan_packets;
u64 rx_csum_unnecessary_inner;
u64 rx_xdp_drop;
u64 rx_xdp_tx;
+ u64 rx_xdp_tx_cqe;
u64 rx_xdp_tx_full;
u64 tx_csum_none;
u64 tx_csum_partial;
u64 tx_queue_dropped;
u64 tx_xmit_more;
u64 tx_recover;
+ u64 tx_cqes;
u64 tx_queue_wake;
+ u64 tx_udp_seg_rem;
u64 tx_cqe_err;
u64 rx_wqe_err;
- u64 rx_mpwqe_filler;
+ u64 rx_mpwqe_filler_cqes;
+ u64 rx_mpwqe_filler_strides;
u64 rx_buff_alloc_err;
u64 rx_cqe_compress_blks;
u64 rx_cqe_compress_pkts;
u64 rx_cache_empty;
u64 rx_cache_busy;
u64 rx_cache_waive;
+ u64 rx_congst_umr;
+ u64 ch_events;
+ u64 ch_poll;
+ u64 ch_arm;
+ u64 ch_aff_change;
u64 ch_eq_rearm;
#ifdef CONFIG_MLX5_EN_TLS
u64 removed_vlan_packets;
u64 xdp_drop;
u64 xdp_tx;
+ u64 xdp_tx_cqe;
u64 xdp_tx_full;
u64 wqe_err;
- u64 mpwqe_filler;
+ u64 mpwqe_filler_cqes;
+ u64 mpwqe_filler_strides;
u64 buff_alloc_err;
u64 cqe_compress_blks;
u64 cqe_compress_pkts;
u64 cache_empty;
u64 cache_busy;
u64 cache_waive;
+ u64 congst_umr;
};
struct mlx5e_sq_stats {
u64 csum_partial_inner;
u64 added_vlan_packets;
u64 nop;
+ u64 udp_seg_rem;
#ifdef CONFIG_MLX5_EN_TLS
u64 tls_ooo;
u64 tls_resync_bytes;
u64 dropped;
u64 recover;
/* dirtied @completion */
- u64 wake ____cacheline_aligned_in_smp;
+ u64 cqes ____cacheline_aligned_in_smp;
+ u64 wake;
u64 cqe_err;
};
struct mlx5e_ch_stats {
+ u64 events;
+ u64 poll;
+ u64 arm;
+ u64 aff_change;
u64 eq_rearm;
};
#endif
u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
- void *accel_priv, select_queue_fallback_t fallback)
+ struct net_device *sb_dev,
+ select_queue_fallback_t fallback)
{
struct mlx5e_priv *priv = netdev_priv(dev);
- int channel_ix = fallback(dev, skb);
+ int channel_ix = fallback(dev, skb, NULL);
u16 num_channels;
int up = 0;
stats->tso_inner_packets++;
stats->tso_inner_bytes += skb->len - ihs;
} else {
- ihs = skb_transport_offset(skb) + tcp_hdrlen(skb);
+ if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4)
+ ihs = skb_transport_offset(skb) + sizeof(struct udphdr);
+ else
+ ihs = skb_transport_offset(skb) + tcp_hdrlen(skb);
stats->tso_packets++;
stats->tso_bytes += skb->len - ihs;
}
sq = priv->txq2sq[skb_get_queue_mapping(skb)];
mlx5e_sq_fetch_wqe(sq, &wqe, &pi);
-#ifdef CONFIG_MLX5_ACCEL
/* might send skbs and update wqe and pi */
skb = mlx5e_accel_handle_tx(skb, sq, dev, &wqe, &pi);
if (unlikely(!skb))
return NETDEV_TX_OK;
-#endif
+
return mlx5e_sq_xmit(sq, skb, wqe, pi);
}
bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
{
+ struct mlx5e_sq_stats *stats;
struct mlx5e_txqsq *sq;
struct mlx5_cqe64 *cqe;
u32 dma_fifo_cc;
if (!cqe)
return false;
+ stats = sq->stats;
+
npkts = 0;
nbytes = 0;
queue_work(cq->channel->priv->wq,
&sq->recover.recover_work);
}
- sq->stats->cqe_err++;
+ stats->cqe_err++;
}
do {
} while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
+ stats->cqes += i;
+
mlx5_cqwq_update_db_record(&cq->wq);
/* ensure cq space is freed before enabling more cqes */
MLX5E_SQ_STOP_ROOM) &&
!test_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state)) {
netif_tx_wake_queue(sq->txq);
- sq->stats->wake++;
+ stats->wake++;
}
return (i == MLX5E_TX_CQ_POLL_BUDGET);
{
struct mlx5e_channel *c = container_of(napi, struct mlx5e_channel,
napi);
+ struct mlx5e_ch_stats *ch_stats = c->stats;
bool busy = false;
int work_done = 0;
int i;
+ ch_stats->poll++;
+
for (i = 0; i < c->num_tc; i++)
busy |= mlx5e_poll_tx_cq(&c->sq[i].cq, budget);
if (busy) {
if (likely(mlx5e_channel_no_affinity_change(c)))
return budget;
+ ch_stats->aff_change++;
if (budget && work_done == budget)
work_done--;
}
if (unlikely(!napi_complete_done(napi, work_done)))
return work_done;
+ ch_stats->arm++;
+
for (i = 0; i < c->num_tc; i++) {
mlx5e_handle_tx_dim(&c->sq[i]);
mlx5e_cq_arm(&c->sq[i].cq);
{
struct mlx5e_cq *cq = container_of(mcq, struct mlx5e_cq, mcq);
- cq->event_ctr++;
napi_schedule(cq->napi);
+ cq->event_ctr++;
+ cq->channel->stats->events++;
}
void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event)
}
/* Public E-Switch API */
-#define ESW_ALLOWED(esw) ((esw) && MLX5_VPORT_MANAGER((esw)->dev))
+#define ESW_ALLOWED(esw) ((esw) && MLX5_ESWITCH_MANAGER((esw)->dev))
+
int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
{
int err;
int i, enabled_events;
- if (!ESW_ALLOWED(esw))
- return 0;
-
- if (!MLX5_CAP_GEN(esw->dev, eswitch_flow_table) ||
+ if (!ESW_ALLOWED(esw) ||
!MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ft_support)) {
esw_warn(esw->dev, "E-Switch FDB is not supported, aborting ...\n");
return -EOPNOTSUPP;
u64 node_guid;
int err = 0;
- if (!ESW_ALLOWED(esw))
+ if (!MLX5_CAP_GEN(esw->dev, vport_group_manager))
return -EPERM;
if (!LEGAL_VPORT(esw, vport) || is_multicast_ether_addr(mac))
return -EINVAL;
{
struct mlx5_vport *evport;
- if (!ESW_ALLOWED(esw))
+ if (!MLX5_CAP_GEN(esw->dev, vport_group_manager))
return -EPERM;
if (!LEGAL_VPORT(esw, vport))
return -EINVAL;
if (MLX5_CAP_GEN(dev, port_type) != MLX5_CAP_PORT_TYPE_ETH)
return -EOPNOTSUPP;
- if (!MLX5_CAP_GEN(dev, vport_group_manager))
- return -EOPNOTSUPP;
+ if(!MLX5_ESWITCH_MANAGER(dev))
+ return -EPERM;
if (dev->priv.eswitch->mode == SRIOV_NONE)
return -EOPNOTSUPP;
static int mlx5_fpga_tls_alloc_swid(struct idr *idr, spinlock_t *idr_spinlock,
void *ptr)
{
+ unsigned long flags;
int ret;
/* TLS metadata format is 1 byte for syndrome followed
BUILD_BUG_ON((SWID_END - 1) & 0xFF000000);
idr_preload(GFP_KERNEL);
- spin_lock_irq(idr_spinlock);
+ spin_lock_irqsave(idr_spinlock, flags);
ret = idr_alloc(idr, ptr, SWID_START, SWID_END, GFP_ATOMIC);
- spin_unlock_irq(idr_spinlock);
+ spin_unlock_irqrestore(idr_spinlock, flags);
idr_preload_end();
return ret;
spin_unlock_irqrestore(idr_spinlock, flags);
}
+static void mlx_tls_kfree_complete(struct mlx5_fpga_conn *conn,
+ struct mlx5_fpga_device *fdev,
+ struct mlx5_fpga_dma_buf *buf, u8 status)
+{
+ kfree(buf);
+}
+
struct mlx5_teardown_stream_context {
struct mlx5_fpga_tls_command_context cmd;
u32 swid;
mlx5_fpga_err(fdev,
"Teardown stream failed with syndrome = %d",
syndrome);
- else
+ else if (MLX5_GET(tls_cmd, cmd->buf.sg[0].data, direction_sx))
mlx5_fpga_tls_release_swid(&fdev->tls->tx_idr,
- &fdev->tls->idr_spinlock,
+ &fdev->tls->tx_idr_spinlock,
+ ctx->swid);
+ else
+ mlx5_fpga_tls_release_swid(&fdev->tls->rx_idr,
+ &fdev->tls->rx_idr_spinlock,
ctx->swid);
}
mlx5_fpga_tls_put_command_ctx(cmd);
MLX5_GET(tls_flow, flow, direction_sx));
}
+int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq,
+ u64 rcd_sn)
+{
+ struct mlx5_fpga_dma_buf *buf;
+ int size = sizeof(*buf) + MLX5_TLS_COMMAND_SIZE;
+ void *flow;
+ void *cmd;
+ int ret;
+
+ buf = kzalloc(size, GFP_ATOMIC);
+ if (!buf)
+ return -ENOMEM;
+
+ cmd = (buf + 1);
+
+ rcu_read_lock();
+ flow = idr_find(&mdev->fpga->tls->rx_idr, ntohl(handle));
+ rcu_read_unlock();
+ mlx5_fpga_tls_flow_to_cmd(flow, cmd);
+
+ MLX5_SET(tls_cmd, cmd, swid, ntohl(handle));
+ MLX5_SET64(tls_cmd, cmd, tls_rcd_sn, be64_to_cpu(rcd_sn));
+ MLX5_SET(tls_cmd, cmd, tcp_sn, seq);
+ MLX5_SET(tls_cmd, cmd, command_type, CMD_RESYNC_RX);
+
+ buf->sg[0].data = cmd;
+ buf->sg[0].size = MLX5_TLS_COMMAND_SIZE;
+ buf->complete = mlx_tls_kfree_complete;
+
+ ret = mlx5_fpga_sbu_conn_sendmsg(mdev->fpga->tls->conn, buf);
+
+ return ret;
+}
+
static void mlx5_fpga_tls_send_teardown_cmd(struct mlx5_core_dev *mdev,
void *flow, u32 swid, gfp_t flags)
{
mlx5_fpga_tls_teardown_completion);
}
-void mlx5_fpga_tls_del_tx_flow(struct mlx5_core_dev *mdev, u32 swid,
- gfp_t flags)
+void mlx5_fpga_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid,
+ gfp_t flags, bool direction_sx)
{
struct mlx5_fpga_tls *tls = mdev->fpga->tls;
void *flow;
rcu_read_lock();
- flow = idr_find(&tls->tx_idr, swid);
+ if (direction_sx)
+ flow = idr_find(&tls->tx_idr, swid);
+ else
+ flow = idr_find(&tls->rx_idr, swid);
+
rcu_read_unlock();
if (!flow) {
* the command context because we might not have received
* the tx completion yet.
*/
- mlx5_fpga_tls_del_tx_flow(fdev->mdev,
- MLX5_GET(tls_cmd, tls_cmd, swid),
- GFP_ATOMIC);
+ mlx5_fpga_tls_del_flow(fdev->mdev,
+ MLX5_GET(tls_cmd, tls_cmd, swid),
+ GFP_ATOMIC,
+ MLX5_GET(tls_cmd, tls_cmd,
+ direction_sx));
}
mlx5_fpga_tls_put_command_ctx(cmd);
if (err)
goto error;
- if (!(tls->caps & (MLX5_ACCEL_TLS_TX | MLX5_ACCEL_TLS_V12 |
- MLX5_ACCEL_TLS_AES_GCM128))) {
+ if (!(tls->caps & (MLX5_ACCEL_TLS_V12 | MLX5_ACCEL_TLS_AES_GCM128))) {
err = -ENOTSUPP;
goto error;
}
INIT_LIST_HEAD(&tls->pending_cmds);
idr_init(&tls->tx_idr);
- spin_lock_init(&tls->idr_spinlock);
+ idr_init(&tls->rx_idr);
+ spin_lock_init(&tls->tx_idr_spinlock);
+ spin_lock_init(&tls->rx_idr_spinlock);
fdev->tls = tls;
return 0;
return 0;
}
-static int mlx5_fpga_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,
- struct tls_crypto_info *crypto_info, u32 swid,
- u32 tcp_sn)
+static int _mlx5_fpga_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,
+ struct tls_crypto_info *crypto_info,
+ u32 swid, u32 tcp_sn)
{
u32 caps = mlx5_fpga_tls_device_caps(mdev);
struct mlx5_setup_stream_context *ctx;
return ret;
}
-int mlx5_fpga_tls_add_tx_flow(struct mlx5_core_dev *mdev, void *flow,
- struct tls_crypto_info *crypto_info,
- u32 start_offload_tcp_sn, u32 *p_swid)
+int mlx5_fpga_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,
+ struct tls_crypto_info *crypto_info,
+ u32 start_offload_tcp_sn, u32 *p_swid,
+ bool direction_sx)
{
struct mlx5_fpga_tls *tls = mdev->fpga->tls;
int ret = -ENOMEM;
u32 swid;
- ret = mlx5_fpga_tls_alloc_swid(&tls->tx_idr, &tls->idr_spinlock, flow);
+ if (direction_sx)
+ ret = mlx5_fpga_tls_alloc_swid(&tls->tx_idr,
+ &tls->tx_idr_spinlock, flow);
+ else
+ ret = mlx5_fpga_tls_alloc_swid(&tls->rx_idr,
+ &tls->rx_idr_spinlock, flow);
+
if (ret < 0)
return ret;
swid = ret;
- MLX5_SET(tls_flow, flow, direction_sx, 1);
+ MLX5_SET(tls_flow, flow, direction_sx, direction_sx ? 1 : 0);
- ret = mlx5_fpga_tls_add_flow(mdev, flow, crypto_info, swid,
- start_offload_tcp_sn);
+ ret = _mlx5_fpga_tls_add_flow(mdev, flow, crypto_info, swid,
+ start_offload_tcp_sn);
if (ret && ret != -EINTR)
goto free_swid;
*p_swid = swid;
return 0;
free_swid:
- mlx5_fpga_tls_release_swid(&tls->tx_idr, &tls->idr_spinlock, swid);
+ if (direction_sx)
+ mlx5_fpga_tls_release_swid(&tls->tx_idr,
+ &tls->tx_idr_spinlock, swid);
+ else
+ mlx5_fpga_tls_release_swid(&tls->rx_idr,
+ &tls->rx_idr_spinlock, swid);
return ret;
}
struct mlx5_fpga_conn *conn;
struct idr tx_idr;
- spinlock_t idr_spinlock; /* protects the IDR */
+ struct idr rx_idr;
+ spinlock_t tx_idr_spinlock; /* protects the IDR */
+ spinlock_t rx_idr_spinlock; /* protects the IDR */
};
-int mlx5_fpga_tls_add_tx_flow(struct mlx5_core_dev *mdev, void *flow,
- struct tls_crypto_info *crypto_info,
- u32 start_offload_tcp_sn, u32 *p_swid);
+int mlx5_fpga_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,
+ struct tls_crypto_info *crypto_info,
+ u32 start_offload_tcp_sn, u32 *p_swid,
+ bool direction_sx);
-void mlx5_fpga_tls_del_tx_flow(struct mlx5_core_dev *mdev, u32 swid,
- gfp_t flags);
+void mlx5_fpga_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid,
+ gfp_t flags, bool direction_sx);
bool mlx5_fpga_is_tls_device(struct mlx5_core_dev *mdev);
int mlx5_fpga_tls_init(struct mlx5_core_dev *mdev);
return mdev->fpga->tls->caps;
}
+int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq,
+ u64 rcd_sn);
+
#endif /* __MLX5_FPGA_TLS_H__ */
#include <linux/mutex.h>
#include <linux/mlx5/driver.h>
+#include <linux/mlx5/eswitch.h>
#include "mlx5_core.h"
#include "fs_core.h"
goto err;
}
- if (MLX5_CAP_GEN(dev, eswitch_flow_table)) {
+ if (MLX5_ESWITCH_MANAGER(dev)) {
if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, ft_support)) {
err = init_fdb_root_ns(steering);
if (err)
#include <linux/mlx5/driver.h>
#include <linux/mlx5/cmd.h>
+#include <linux/mlx5/eswitch.h>
#include <linux/module.h>
#include "mlx5_core.h"
#include "../../mlxfw/mlxfw.h"
}
if (MLX5_CAP_GEN(dev, vport_group_manager) &&
- MLX5_CAP_GEN(dev, eswitch_flow_table)) {
+ MLX5_ESWITCH_MANAGER(dev)) {
err = mlx5_core_get_caps(dev, MLX5_CAP_ESWITCH_FLOW_TABLE);
if (err)
return err;
}
- if (MLX5_CAP_GEN(dev, eswitch_flow_table)) {
+ if (MLX5_ESWITCH_MANAGER(dev)) {
err = mlx5_core_get_caps(dev, MLX5_CAP_ESWITCH);
if (err)
return err;
#include <linux/etherdevice.h>
#include <linux/mlx5/driver.h>
#include <linux/mlx5/mlx5_ifc.h>
+#include <linux/mlx5/eswitch.h>
#include "mlx5_core.h"
#include "lib/mpfs.h"
int l2table_size = 1 << MLX5_CAP_GEN(dev, log_max_l2_table);
struct mlx5_mpfs *mpfs;
- if (!MLX5_VPORT_MANAGER(dev))
+ if (!MLX5_ESWITCH_MANAGER(dev))
return 0;
mpfs = kzalloc(sizeof(*mpfs), GFP_KERNEL);
{
struct mlx5_mpfs *mpfs = dev->priv.mpfs;
- if (!MLX5_VPORT_MANAGER(dev))
+ if (!MLX5_ESWITCH_MANAGER(dev))
return;
WARN_ON(!hlist_empty(mpfs->hash));
u32 index;
int err;
- if (!MLX5_VPORT_MANAGER(dev))
+ if (!MLX5_ESWITCH_MANAGER(dev))
return 0;
mutex_lock(&mpfs->lock);
int err = 0;
u32 index;
- if (!MLX5_VPORT_MANAGER(dev))
+ if (!MLX5_ESWITCH_MANAGER(dev))
return 0;
mutex_lock(&mpfs->lock);
static int mlx5_set_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *in,
int inlen)
{
- u32 out[MLX5_ST_SZ_DW(qtct_reg)];
+ u32 out[MLX5_ST_SZ_DW(qetc_reg)];
if (!MLX5_CAP_GEN(mdev, ets))
return -EOPNOTSUPP;
static int mlx5_query_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *out,
int outlen)
{
- u32 in[MLX5_ST_SZ_DW(qtct_reg)];
+ u32 in[MLX5_ST_SZ_DW(qetc_reg)];
if (!MLX5_CAP_GEN(mdev, ets))
return -EOPNOTSUPP;
return -EBUSY;
}
+ if (!MLX5_ESWITCH_MANAGER(dev))
+ goto enable_vfs_hca;
+
err = mlx5_eswitch_enable_sriov(dev->priv.eswitch, num_vfs, SRIOV_LEGACY);
if (err) {
mlx5_core_warn(dev,
return err;
}
+enable_vfs_hca:
for (vf = 0; vf < num_vfs; vf++) {
err = mlx5_core_enable_hca(dev, vf + 1);
if (err) {
}
out:
- mlx5_eswitch_disable_sriov(dev->priv.eswitch);
+ if (MLX5_ESWITCH_MANAGER(dev))
+ mlx5_eswitch_disable_sriov(dev->priv.eswitch);
if (mlx5_wait_for_vf_pages(dev))
mlx5_core_warn(dev, "timeout reclaiming VFs pages\n");
return -EINVAL;
if (!MLX5_CAP_GEN(mdev, vport_group_manager))
return -EACCES;
- if (!MLX5_CAP_ESW(mdev, nic_vport_node_guid_modify))
- return -EOPNOTSUPP;
in = kvzalloc(inlen, GFP_KERNEL);
if (!in)
return !wq->cur_sz;
}
+static inline int mlx5_wq_ll_missing(struct mlx5_wq_ll *wq)
+{
+ return wq->fbc.sz_m1 - wq->cur_sz;
+}
+
static inline void *mlx5_wq_ll_get_wqe(struct mlx5_wq_ll *wq, u16 ix)
{
return mlx5_frag_buf_get_wqe(&wq->fbc, ix);
config MLXSW_PCI
tristate "PCI bus implementation for Mellanox Technologies Switch ASICs"
- depends on PCI && HAS_DMA && HAS_IOMEM && MLXSW_CORE
+ depends on PCI && HAS_IOMEM && MLXSW_CORE
default m
---help---
This is PCI bus implementation for Mellanox Technologies Switch ASICs.
obj-$(CONFIG_MLXSW_SPECTRUM) += mlxsw_spectrum.o
mlxsw_spectrum-objs := spectrum.o spectrum_buffers.o \
spectrum_switchdev.o spectrum_router.o \
- spectrum_kvdl.o spectrum_acl_tcam.o \
- spectrum_acl.o spectrum_flower.o \
- spectrum_cnt.o spectrum_fid.o \
- spectrum_ipip.o spectrum_acl_flex_actions.o \
- spectrum_mr.o spectrum_mr_tcam.o \
+ spectrum1_kvdl.o spectrum_kvdl.o \
+ spectrum_acl_tcam.o spectrum_acl_ctcam.o \
+ spectrum1_acl_tcam.o \
+ spectrum_acl.o \
+ spectrum_flower.o spectrum_cnt.o \
+ spectrum_fid.o spectrum_ipip.o \
+ spectrum_acl_flex_actions.o \
+ spectrum_acl_flex_keys.o \
+ spectrum1_mr_tcam.o \
+ spectrum_mr_tcam.o spectrum_mr.o \
spectrum_qdisc.o spectrum_span.o
mlxsw_spectrum-$(CONFIG_MLXSW_SPECTRUM_DCB) += spectrum_dcb.o
mlxsw_spectrum-$(CONFIG_NET_DEVLINK) += spectrum_dpipe.o
block->first_set = mlxsw_afa_set_create(true);
if (!block->first_set)
goto err_first_set_create;
- block->cur_set = block->first_set;
+
+ /* In case user instructs to have dummy first set, we leave it
+ * empty here and create another, real, set right away.
+ */
+ if (mlxsw_afa->ops->dummy_first_set) {
+ block->cur_set = mlxsw_afa_set_create(false);
+ if (!block->cur_set)
+ goto err_second_set_create;
+ block->cur_set->prev = block->first_set;
+ block->first_set->next = block->cur_set;
+ } else {
+ block->cur_set = block->first_set;
+ }
+
return block;
+err_second_set_create:
+ mlxsw_afa_set_destroy(block->first_set);
err_first_set_create:
kfree(block);
return NULL;
}
EXPORT_SYMBOL(mlxsw_afa_block_first_set);
-u32 mlxsw_afa_block_first_set_kvdl_index(struct mlxsw_afa_block *block)
+u32 mlxsw_afa_block_first_kvdl_index(struct mlxsw_afa_block *block)
{
- return block->first_set->kvdl_index;
+ /* First set is never in KVD linear. So the first set
+ * with valid KVD linear index is always the second one.
+ */
+ if (WARN_ON(!block->first_set->next))
+ return 0;
+ return block->first_set->next->kvdl_index;
}
-EXPORT_SYMBOL(mlxsw_afa_block_first_set_kvdl_index);
+EXPORT_SYMBOL(mlxsw_afa_block_first_kvdl_index);
int mlxsw_afa_block_continue(struct mlxsw_afa_block *block)
{
bool ingress, int *p_span_id);
void (*mirror_del)(void *priv, u8 local_in_port, int span_id,
bool ingress);
+ bool dummy_first_set;
};
struct mlxsw_afa *mlxsw_afa_create(unsigned int max_acts_per_set,
void mlxsw_afa_block_destroy(struct mlxsw_afa_block *block);
int mlxsw_afa_block_commit(struct mlxsw_afa_block *block);
char *mlxsw_afa_block_first_set(struct mlxsw_afa_block *block);
-u32 mlxsw_afa_block_first_set_kvdl_index(struct mlxsw_afa_block *block);
+u32 mlxsw_afa_block_first_kvdl_index(struct mlxsw_afa_block *block);
int mlxsw_afa_block_continue(struct mlxsw_afa_block *block);
int mlxsw_afa_block_jump(struct mlxsw_afa_block *block, u16 group_id);
int mlxsw_afa_block_terminate(struct mlxsw_afa_block *block);
struct mlxsw_afk {
struct list_head key_info_list;
unsigned int max_blocks;
+ const struct mlxsw_afk_ops *ops;
const struct mlxsw_afk_block *blocks;
unsigned int blocks_count;
};
}
struct mlxsw_afk *mlxsw_afk_create(unsigned int max_blocks,
- const struct mlxsw_afk_block *blocks,
- unsigned int blocks_count)
+ const struct mlxsw_afk_ops *ops)
{
struct mlxsw_afk *mlxsw_afk;
return NULL;
INIT_LIST_HEAD(&mlxsw_afk->key_info_list);
mlxsw_afk->max_blocks = max_blocks;
- mlxsw_afk->blocks = blocks;
- mlxsw_afk->blocks_count = blocks_count;
+ mlxsw_afk->ops = ops;
+ mlxsw_afk->blocks = ops->blocks;
+ mlxsw_afk->blocks_count = ops->blocks_count;
WARN_ON(!mlxsw_afk_blocks_check(mlxsw_afk));
return mlxsw_afk;
}
}
EXPORT_SYMBOL(mlxsw_afk_values_add_buf);
-static void mlxsw_afk_encode_u32(const struct mlxsw_item *storage_item,
- const struct mlxsw_item *output_item,
- char *storage, char *output_indexed)
-{
- u32 value;
-
- value = __mlxsw_item_get32(storage, storage_item, 0);
- __mlxsw_item_set32(output_indexed, output_item, 0, value);
-}
-
-static void mlxsw_afk_encode_buf(const struct mlxsw_item *storage_item,
- const struct mlxsw_item *output_item,
- char *storage, char *output_indexed)
-{
- char *storage_data = __mlxsw_item_data(storage, storage_item, 0);
- char *output_data = __mlxsw_item_data(output_indexed, output_item, 0);
- size_t len = output_item->size.bytes;
-
- memcpy(output_data, storage_data, len);
-}
-
-#define MLXSW_AFK_KEY_BLOCK_SIZE 16
-
-static void mlxsw_afk_encode_one(const struct mlxsw_afk_element_inst *elinst,
- int block_index, char *storage, char *output)
-{
- char *output_indexed = output + block_index * MLXSW_AFK_KEY_BLOCK_SIZE;
- const struct mlxsw_item *storage_item = &elinst->info->item;
- const struct mlxsw_item *output_item = &elinst->item;
-
- if (elinst->type == MLXSW_AFK_ELEMENT_TYPE_U32)
- mlxsw_afk_encode_u32(storage_item, output_item,
- storage, output_indexed);
- else if (elinst->type == MLXSW_AFK_ELEMENT_TYPE_BUF)
- mlxsw_afk_encode_buf(storage_item, output_item,
- storage, output_indexed);
-}
-
-void mlxsw_afk_encode(struct mlxsw_afk_key_info *key_info,
+void mlxsw_afk_encode(struct mlxsw_afk *mlxsw_afk,
+ struct mlxsw_afk_key_info *key_info,
struct mlxsw_afk_element_values *values,
char *key, char *mask)
{
&block_index);
if (!elinst)
continue;
- mlxsw_afk_encode_one(elinst, block_index,
- values->storage.key, key);
- mlxsw_afk_encode_one(elinst, block_index,
- values->storage.mask, mask);
+ mlxsw_afk->ops->encode_one(elinst, block_index,
+ values->storage.key, key);
+ mlxsw_afk->ops->encode_one(elinst, block_index,
+ values->storage.mask, mask);
}
}
EXPORT_SYMBOL(mlxsw_afk_encode);
enum mlxsw_afk_element {
MLXSW_AFK_ELEMENT_SRC_SYS_PORT,
- MLXSW_AFK_ELEMENT_DMAC,
- MLXSW_AFK_ELEMENT_SMAC,
+ MLXSW_AFK_ELEMENT_DMAC_32_47,
+ MLXSW_AFK_ELEMENT_DMAC_0_31,
+ MLXSW_AFK_ELEMENT_SMAC_32_47,
+ MLXSW_AFK_ELEMENT_SMAC_0_31,
MLXSW_AFK_ELEMENT_ETHERTYPE,
MLXSW_AFK_ELEMENT_IP_PROTO,
- MLXSW_AFK_ELEMENT_SRC_IP4,
- MLXSW_AFK_ELEMENT_DST_IP4,
- MLXSW_AFK_ELEMENT_SRC_IP6_HI,
- MLXSW_AFK_ELEMENT_SRC_IP6_LO,
- MLXSW_AFK_ELEMENT_DST_IP6_HI,
- MLXSW_AFK_ELEMENT_DST_IP6_LO,
+ MLXSW_AFK_ELEMENT_SRC_IP_96_127,
+ MLXSW_AFK_ELEMENT_SRC_IP_64_95,
+ MLXSW_AFK_ELEMENT_SRC_IP_32_63,
+ MLXSW_AFK_ELEMENT_SRC_IP_0_31,
+ MLXSW_AFK_ELEMENT_DST_IP_96_127,
+ MLXSW_AFK_ELEMENT_DST_IP_64_95,
+ MLXSW_AFK_ELEMENT_DST_IP_32_63,
+ MLXSW_AFK_ELEMENT_DST_IP_0_31,
MLXSW_AFK_ELEMENT_DST_L4_PORT,
MLXSW_AFK_ELEMENT_SRC_L4_PORT,
MLXSW_AFK_ELEMENT_VID,
* define an internal storage geometry.
*/
static const struct mlxsw_afk_element_info mlxsw_afk_element_infos[] = {
- MLXSW_AFK_ELEMENT_INFO_U32(SRC_SYS_PORT, 0x00, 16, 16),
- MLXSW_AFK_ELEMENT_INFO_BUF(DMAC, 0x04, 6),
- MLXSW_AFK_ELEMENT_INFO_BUF(SMAC, 0x0A, 6),
+ MLXSW_AFK_ELEMENT_INFO_U32(SRC_SYS_PORT, 0x00, 16, 8),
+ MLXSW_AFK_ELEMENT_INFO_BUF(DMAC_32_47, 0x04, 2),
+ MLXSW_AFK_ELEMENT_INFO_BUF(DMAC_0_31, 0x06, 4),
+ MLXSW_AFK_ELEMENT_INFO_BUF(SMAC_32_47, 0x0A, 2),
+ MLXSW_AFK_ELEMENT_INFO_BUF(SMAC_0_31, 0x0C, 4),
MLXSW_AFK_ELEMENT_INFO_U32(ETHERTYPE, 0x00, 0, 16),
MLXSW_AFK_ELEMENT_INFO_U32(IP_PROTO, 0x10, 0, 8),
MLXSW_AFK_ELEMENT_INFO_U32(VID, 0x10, 8, 12),
MLXSW_AFK_ELEMENT_INFO_U32(IP_TTL_, 0x18, 0, 8),
MLXSW_AFK_ELEMENT_INFO_U32(IP_ECN, 0x18, 9, 2),
MLXSW_AFK_ELEMENT_INFO_U32(IP_DSCP, 0x18, 11, 6),
- MLXSW_AFK_ELEMENT_INFO_U32(SRC_IP4, 0x20, 0, 32),
- MLXSW_AFK_ELEMENT_INFO_U32(DST_IP4, 0x24, 0, 32),
- MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP6_HI, 0x20, 8),
- MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP6_LO, 0x28, 8),
- MLXSW_AFK_ELEMENT_INFO_BUF(DST_IP6_HI, 0x30, 8),
- MLXSW_AFK_ELEMENT_INFO_BUF(DST_IP6_LO, 0x38, 8),
+ MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP_96_127, 0x20, 4),
+ MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP_64_95, 0x24, 4),
+ MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP_32_63, 0x28, 4),
+ MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP_0_31, 0x2C, 4),
+ MLXSW_AFK_ELEMENT_INFO_BUF(DST_IP_96_127, 0x30, 4),
+ MLXSW_AFK_ELEMENT_INFO_BUF(DST_IP_64_95, 0x34, 4),
+ MLXSW_AFK_ELEMENT_INFO_BUF(DST_IP_32_63, 0x38, 4),
+ MLXSW_AFK_ELEMENT_INFO_BUF(DST_IP_0_31, 0x3C, 4),
};
#define MLXSW_AFK_ELEMENT_STORAGE_SIZE 0x40
struct mlxsw_afk;
+struct mlxsw_afk_ops {
+ const struct mlxsw_afk_block *blocks;
+ unsigned int blocks_count;
+ void (*encode_one)(const struct mlxsw_afk_element_inst *elinst,
+ int block_index, char *storage, char *output);
+};
+
struct mlxsw_afk *mlxsw_afk_create(unsigned int max_blocks,
- const struct mlxsw_afk_block *blocks,
- unsigned int blocks_count);
+ const struct mlxsw_afk_ops *ops);
void mlxsw_afk_destroy(struct mlxsw_afk *mlxsw_afk);
struct mlxsw_afk_key_info;
enum mlxsw_afk_element element,
const char *key_value, const char *mask_value,
unsigned int len);
-void mlxsw_afk_encode(struct mlxsw_afk_key_info *key_info,
+void mlxsw_afk_encode(struct mlxsw_afk *mlxsw_afk,
+ struct mlxsw_afk_key_info *key_info,
struct mlxsw_afk_element_values *values,
char *key, char *mask);
/* reg_ptar_action_set_type
* Type of action set to be used on this region.
- * For Spectrum, this is always type 2 - "flexible"
+ * For Spectrum and Spectrum-2, this is always type 2 - "flexible"
* Access: WO
*/
MLXSW_ITEM32(reg, ptar, action_set_type, 0x00, 16, 8);
+enum mlxsw_reg_ptar_key_type {
+ MLXSW_REG_PTAR_KEY_TYPE_FLEX = 0x50, /* Spetrum */
+ MLXSW_REG_PTAR_KEY_TYPE_FLEX2 = 0x51, /* Spectrum-2 */
+};
+
/* reg_ptar_key_type
* TCAM key type for the region.
- * For Spectrum, this is always type 0x50 - "FLEX_KEY"
* Access: WO
*/
MLXSW_ITEM32(reg, ptar, key_type, 0x00, 0, 8);
MLXSW_REG_PTAR_KEY_ID_LEN, 0x00, false);
static inline void mlxsw_reg_ptar_pack(char *payload, enum mlxsw_reg_ptar_op op,
+ enum mlxsw_reg_ptar_key_type key_type,
u16 region_size, u16 region_id,
const char *tcam_region_info)
{
MLXSW_REG_ZERO(ptar, payload);
mlxsw_reg_ptar_op_set(payload, op);
mlxsw_reg_ptar_action_set_type_set(payload, 2); /* "flexible" */
- mlxsw_reg_ptar_key_type_set(payload, 0x50); /* "FLEX_KEY" */
+ mlxsw_reg_ptar_key_type_set(payload, key_type);
mlxsw_reg_ptar_region_size_set(payload, region_size);
mlxsw_reg_ptar_region_id_set(payload, region_id);
mlxsw_reg_ptar_tcam_region_info_memcpy_to(payload, tcam_region_info);
*/
MLXSW_ITEM32(reg, ptce2, offset, 0x00, 0, 16);
+/* reg_ptce2_priority
+ * Priority of the rule, higher values win. The range is 1..cap_kvd_size-1.
+ * Note: priority does not have to be unique per rule.
+ * Within a region, higher priority should have lower offset (no limitation
+ * between regions in a multi-region).
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ptce2, priority, 0x04, 0, 24);
+
/* reg_ptce2_tcam_region_info
* Opaque object that represents the TCAM region.
* Access: Index
static inline void mlxsw_reg_ptce2_pack(char *payload, bool valid,
enum mlxsw_reg_ptce2_op op,
const char *tcam_region_info,
- u16 offset)
+ u16 offset, u32 priority)
{
MLXSW_REG_ZERO(ptce2, payload);
mlxsw_reg_ptce2_v_set(payload, valid);
mlxsw_reg_ptce2_op_set(payload, op);
mlxsw_reg_ptce2_offset_set(payload, offset);
+ mlxsw_reg_ptce2_priority_set(payload, priority);
mlxsw_reg_ptce2_tcam_region_info_memcpy_to(payload, tcam_region_info);
}
enum mlxsw_reg_ppcnt_grp {
MLXSW_REG_PPCNT_IEEE_8023_CNT = 0x0,
+ MLXSW_REG_PPCNT_RFC_2819_CNT = 0x2,
MLXSW_REG_PPCNT_EXT_CNT = 0x5,
MLXSW_REG_PPCNT_PRIO_CNT = 0x10,
MLXSW_REG_PPCNT_TC_CNT = 0x11,
MLXSW_ITEM64(reg, ppcnt, a_pause_mac_ctrl_frames_transmitted,
MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x90, 0, 64);
+/* Ethernet RFC 2819 Counter Group */
+
+/* reg_ppcnt_ether_stats_pkts64octets
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ether_stats_pkts64octets,
+ MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x58, 0, 64);
+
+/* reg_ppcnt_ether_stats_pkts65to127octets
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ether_stats_pkts65to127octets,
+ MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x60, 0, 64);
+
+/* reg_ppcnt_ether_stats_pkts128to255octets
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ether_stats_pkts128to255octets,
+ MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x68, 0, 64);
+
+/* reg_ppcnt_ether_stats_pkts256to511octets
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ether_stats_pkts256to511octets,
+ MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x70, 0, 64);
+
+/* reg_ppcnt_ether_stats_pkts512to1023octets
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ether_stats_pkts512to1023octets,
+ MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x78, 0, 64);
+
+/* reg_ppcnt_ether_stats_pkts1024to1518octets
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ether_stats_pkts1024to1518octets,
+ MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x80, 0, 64);
+
+/* reg_ppcnt_ether_stats_pkts1519to2047octets
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ether_stats_pkts1519to2047octets,
+ MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x88, 0, 64);
+
+/* reg_ppcnt_ether_stats_pkts2048to4095octets
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ether_stats_pkts2048to4095octets,
+ MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x90, 0, 64);
+
+/* reg_ppcnt_ether_stats_pkts4096to8191octets
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ether_stats_pkts4096to8191octets,
+ MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x98, 0, 64);
+
+/* reg_ppcnt_ether_stats_pkts8192to10239octets
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ether_stats_pkts8192to10239octets,
+ MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0xA0, 0, 64);
+
/* Ethernet Extended Counter Group Counters */
/* reg_ppcnt_ecn_marked
*/
MLXSW_ITEM_BUF(reg, ritr, if_mac, 0x12, 6);
+/* reg_ritr_if_vrrp_id_ipv6
+ * VRRP ID for IPv6
+ * Note: Reserved for RIF types other than VLAN, FID and Sub-port.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, if_vrrp_id_ipv6, 0x1C, 8, 8);
+
+/* reg_ritr_if_vrrp_id_ipv4
+ * VRRP ID for IPv4
+ * Note: Reserved for RIF types other than VLAN, FID and Sub-port.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, if_vrrp_id_ipv4, 0x1C, 0, 8);
+
/* VLAN Interface */
/* reg_ritr_vlan_if_vid
MLXSW_RES_ID_KVD_SIZE,
MLXSW_RES_ID_KVD_SINGLE_MIN_SIZE,
MLXSW_RES_ID_KVD_DOUBLE_MIN_SIZE,
+ MLXSW_RES_ID_MAX_KVD_LINEAR_RANGE,
+ MLXSW_RES_ID_MAX_KVD_ACTION_SETS,
MLXSW_RES_ID_MAX_TRAP_GROUPS,
MLXSW_RES_ID_CQE_V0,
MLXSW_RES_ID_CQE_V1,
[MLXSW_RES_ID_KVD_SIZE] = 0x1001,
[MLXSW_RES_ID_KVD_SINGLE_MIN_SIZE] = 0x1002,
[MLXSW_RES_ID_KVD_DOUBLE_MIN_SIZE] = 0x1003,
+ [MLXSW_RES_ID_MAX_KVD_LINEAR_RANGE] = 0x1005,
+ [MLXSW_RES_ID_MAX_KVD_ACTION_SETS] = 0x1007,
[MLXSW_RES_ID_MAX_TRAP_GROUPS] = 0x2201,
[MLXSW_RES_ID_CQE_V0] = 0x2210,
[MLXSW_RES_ID_CQE_V1] = 0x2211,
#include "spectrum_span.h"
#include "../mlxfw/mlxfw.h"
-#define MLXSW_FWREV_MAJOR 13
-#define MLXSW_FWREV_MINOR 1620
-#define MLXSW_FWREV_SUBMINOR 192
-#define MLXSW_FWREV_MINOR_TO_BRANCH(minor) ((minor) / 100)
+#define MLXSW_SP_FWREV_MINOR_TO_BRANCH(minor) ((minor) / 100)
-#define MLXSW_SP_FW_FILENAME \
- "mellanox/mlxsw_spectrum-" __stringify(MLXSW_FWREV_MAJOR) \
- "." __stringify(MLXSW_FWREV_MINOR) \
- "." __stringify(MLXSW_FWREV_SUBMINOR) ".mfa2"
+#define MLXSW_SP1_FWREV_MAJOR 13
+#define MLXSW_SP1_FWREV_MINOR 1620
+#define MLXSW_SP1_FWREV_SUBMINOR 192
+
+static const struct mlxsw_fw_rev mlxsw_sp1_fw_rev = {
+ .major = MLXSW_SP1_FWREV_MAJOR,
+ .minor = MLXSW_SP1_FWREV_MINOR,
+ .subminor = MLXSW_SP1_FWREV_SUBMINOR,
+};
+
+#define MLXSW_SP1_FW_FILENAME \
+ "mellanox/mlxsw_spectrum-" __stringify(MLXSW_SP1_FWREV_MAJOR) \
+ "." __stringify(MLXSW_SP1_FWREV_MINOR) \
+ "." __stringify(MLXSW_SP1_FWREV_SUBMINOR) ".mfa2"
static const char mlxsw_sp_driver_name[] = "mlxsw_spectrum";
static const char mlxsw_sp_driver_version[] = "1.0";
static int mlxsw_sp_fw_rev_validate(struct mlxsw_sp *mlxsw_sp)
{
const struct mlxsw_fw_rev *rev = &mlxsw_sp->bus_info->fw_rev;
+ const struct mlxsw_fw_rev *req_rev = mlxsw_sp->req_rev;
+ const char *fw_filename = mlxsw_sp->fw_filename;
const struct firmware *firmware;
int err;
+ /* Don't check if driver does not require it */
+ if (!req_rev || !fw_filename)
+ return 0;
+
/* Validate driver & FW are compatible */
- if (rev->major != MLXSW_FWREV_MAJOR) {
+ if (rev->major != req_rev->major) {
WARN(1, "Mismatch in major FW version [%d:%d] is never expected; Please contact support\n",
- rev->major, MLXSW_FWREV_MAJOR);
+ rev->major, req_rev->major);
return -EINVAL;
}
- if (MLXSW_FWREV_MINOR_TO_BRANCH(rev->minor) ==
- MLXSW_FWREV_MINOR_TO_BRANCH(MLXSW_FWREV_MINOR))
+ if (MLXSW_SP_FWREV_MINOR_TO_BRANCH(rev->minor) ==
+ MLXSW_SP_FWREV_MINOR_TO_BRANCH(req_rev->minor))
return 0;
dev_info(mlxsw_sp->bus_info->dev, "The firmware version %d.%d.%d is incompatible with the driver\n",
rev->major, rev->minor, rev->subminor);
dev_info(mlxsw_sp->bus_info->dev, "Flashing firmware using file %s\n",
- MLXSW_SP_FW_FILENAME);
+ fw_filename);
- err = request_firmware_direct(&firmware, MLXSW_SP_FW_FILENAME,
+ err = request_firmware_direct(&firmware, fw_filename,
mlxsw_sp->bus_info->dev);
if (err) {
dev_err(mlxsw_sp->bus_info->dev, "Could not request firmware file %s\n",
- MLXSW_SP_FW_FILENAME);
+ fw_filename);
return err;
}
static int
mlxsw_sp_setup_tc_block_flower_bind(struct mlxsw_sp_port *mlxsw_sp_port,
- struct tcf_block *block, bool ingress)
+ struct tcf_block *block, bool ingress,
+ struct netlink_ext_ack *extack)
{
struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
struct mlxsw_sp_acl_block *acl_block;
return -ENOMEM;
block_cb = __tcf_block_cb_register(block,
mlxsw_sp_setup_tc_block_cb_flower,
- mlxsw_sp, acl_block);
+ mlxsw_sp, acl_block, extack);
if (IS_ERR(block_cb)) {
err = PTR_ERR(block_cb);
goto err_cb_register;
err_block_bind:
if (!tcf_block_cb_decref(block_cb)) {
- __tcf_block_cb_unregister(block_cb);
+ __tcf_block_cb_unregister(block, block_cb);
err_cb_register:
mlxsw_sp_acl_block_destroy(acl_block);
}
err = mlxsw_sp_acl_block_unbind(mlxsw_sp, acl_block,
mlxsw_sp_port, ingress);
if (!err && !tcf_block_cb_decref(block_cb)) {
- __tcf_block_cb_unregister(block_cb);
+ __tcf_block_cb_unregister(block, block_cb);
mlxsw_sp_acl_block_destroy(acl_block);
}
}
switch (f->command) {
case TC_BLOCK_BIND:
err = tcf_block_cb_register(f->block, cb, mlxsw_sp_port,
- mlxsw_sp_port);
+ mlxsw_sp_port, f->extack);
if (err)
return err;
err = mlxsw_sp_setup_tc_block_flower_bind(mlxsw_sp_port,
- f->block, ingress);
+ f->block, ingress,
+ f->extack);
if (err) {
tcf_block_cb_unregister(f->block, cb, mlxsw_sp_port);
return err;
#define MLXSW_SP_PORT_HW_STATS_LEN ARRAY_SIZE(mlxsw_sp_port_hw_stats)
+static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_rfc_2819_stats[] = {
+ {
+ .str = "ether_pkts64octets",
+ .getter = mlxsw_reg_ppcnt_ether_stats_pkts64octets_get,
+ },
+ {
+ .str = "ether_pkts65to127octets",
+ .getter = mlxsw_reg_ppcnt_ether_stats_pkts65to127octets_get,
+ },
+ {
+ .str = "ether_pkts128to255octets",
+ .getter = mlxsw_reg_ppcnt_ether_stats_pkts128to255octets_get,
+ },
+ {
+ .str = "ether_pkts256to511octets",
+ .getter = mlxsw_reg_ppcnt_ether_stats_pkts256to511octets_get,
+ },
+ {
+ .str = "ether_pkts512to1023octets",
+ .getter = mlxsw_reg_ppcnt_ether_stats_pkts512to1023octets_get,
+ },
+ {
+ .str = "ether_pkts1024to1518octets",
+ .getter = mlxsw_reg_ppcnt_ether_stats_pkts1024to1518octets_get,
+ },
+ {
+ .str = "ether_pkts1519to2047octets",
+ .getter = mlxsw_reg_ppcnt_ether_stats_pkts1519to2047octets_get,
+ },
+ {
+ .str = "ether_pkts2048to4095octets",
+ .getter = mlxsw_reg_ppcnt_ether_stats_pkts2048to4095octets_get,
+ },
+ {
+ .str = "ether_pkts4096to8191octets",
+ .getter = mlxsw_reg_ppcnt_ether_stats_pkts4096to8191octets_get,
+ },
+ {
+ .str = "ether_pkts8192to10239octets",
+ .getter = mlxsw_reg_ppcnt_ether_stats_pkts8192to10239octets_get,
+ },
+};
+
+#define MLXSW_SP_PORT_HW_RFC_2819_STATS_LEN \
+ ARRAY_SIZE(mlxsw_sp_port_hw_rfc_2819_stats)
+
static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_prio_stats[] = {
{
.str = "rx_octets_prio",
ETH_GSTRING_LEN);
p += ETH_GSTRING_LEN;
}
+ for (i = 0; i < MLXSW_SP_PORT_HW_RFC_2819_STATS_LEN; i++) {
+ memcpy(p, mlxsw_sp_port_hw_rfc_2819_stats[i].str,
+ ETH_GSTRING_LEN);
+ p += ETH_GSTRING_LEN;
+ }
for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++)
mlxsw_sp_port_get_prio_strings(&p, i);
int *p_len, enum mlxsw_reg_ppcnt_grp grp)
{
switch (grp) {
- case MLXSW_REG_PPCNT_IEEE_8023_CNT:
+ case MLXSW_REG_PPCNT_IEEE_8023_CNT:
*p_hw_stats = mlxsw_sp_port_hw_stats;
*p_len = MLXSW_SP_PORT_HW_STATS_LEN;
break;
+ case MLXSW_REG_PPCNT_RFC_2819_CNT:
+ *p_hw_stats = mlxsw_sp_port_hw_rfc_2819_stats;
+ *p_len = MLXSW_SP_PORT_HW_RFC_2819_STATS_LEN;
+ break;
case MLXSW_REG_PPCNT_PRIO_CNT:
*p_hw_stats = mlxsw_sp_port_hw_prio_stats;
*p_len = MLXSW_SP_PORT_HW_PRIO_STATS_LEN;
data, data_index);
data_index = MLXSW_SP_PORT_HW_STATS_LEN;
+ /* RFC 2819 Counters */
+ __mlxsw_sp_port_get_stats(dev, MLXSW_REG_PPCNT_RFC_2819_CNT, 0,
+ data, data_index);
+ data_index += MLXSW_SP_PORT_HW_RFC_2819_STATS_LEN;
+
/* Per-Priority Counters */
for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
__mlxsw_sp_port_get_stats(dev, MLXSW_REG_PPCNT_PRIO_CNT, i,
MLXSW_SP_RXL_MARK(ROUTER_ALERT_IPV4, TRAP_TO_CPU, ROUTER_EXP, false),
MLXSW_SP_RXL_MARK(ROUTER_ALERT_IPV6, TRAP_TO_CPU, ROUTER_EXP, false),
MLXSW_SP_RXL_MARK(IPIP_DECAP_ERROR, TRAP_TO_CPU, ROUTER_EXP, false),
+ MLXSW_SP_RXL_MARK(IPV4_VRRP, TRAP_TO_CPU, ROUTER_EXP, false),
+ MLXSW_SP_RXL_MARK(IPV6_VRRP, TRAP_TO_CPU, ROUTER_EXP, false),
/* PKT Sample trap */
MLXSW_RXL(mlxsw_sp_rx_listener_sample_func, PKT_SAMPLE, MIRROR_TO_CPU,
false, SP_IP2ME, DISCARD),
struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
int err;
+ mlxsw_sp->req_rev = &mlxsw_sp1_fw_rev;
+ mlxsw_sp->fw_filename = MLXSW_SP1_FW_FILENAME;
+ mlxsw_sp->kvdl_ops = &mlxsw_sp1_kvdl_ops;
+ mlxsw_sp->afa_ops = &mlxsw_sp1_act_afa_ops;
+ mlxsw_sp->afk_ops = &mlxsw_sp1_afk_ops;
+ mlxsw_sp->mr_tcam_ops = &mlxsw_sp1_mr_tcam_ops;
+ mlxsw_sp->acl_tcam_ops = &mlxsw_sp1_acl_tcam_ops;
+
mlxsw_sp->core = mlxsw_core;
mlxsw_sp->bus_info = mlxsw_bus_info;
if (err)
return err;
- err = mlxsw_sp_kvdl_resources_register(mlxsw_core);
+ err = mlxsw_sp1_kvdl_resources_register(mlxsw_core);
if (err)
return err;
if (!is_vlan_dev(upper_dev) &&
!netif_is_lag_master(upper_dev) &&
!netif_is_bridge_master(upper_dev) &&
- !netif_is_ovs_master(upper_dev)) {
+ !netif_is_ovs_master(upper_dev) &&
+ !netif_is_macvlan(upper_dev)) {
NL_SET_ERR_MSG_MOD(extack, "Unknown upper device type");
return -EINVAL;
}
NL_SET_ERR_MSG_MOD(extack, "Can not put a VLAN on a LAG port");
return -EINVAL;
}
+ if (netif_is_macvlan(upper_dev) &&
+ !mlxsw_sp_rif_find_by_dev(mlxsw_sp, lower_dev)) {
+ NL_SET_ERR_MSG_MOD(extack, "macvlan is only supported on top of router interfaces");
+ return -EOPNOTSUPP;
+ }
if (netif_is_ovs_master(upper_dev) && vlan_uses_dev(dev)) {
NL_SET_ERR_MSG_MOD(extack, "Master device is an OVS master and this device has a VLAN");
return -EINVAL;
err = mlxsw_sp_port_ovs_join(mlxsw_sp_port);
else
mlxsw_sp_port_ovs_leave(mlxsw_sp_port);
+ } else if (netif_is_macvlan(upper_dev)) {
+ if (!info->linking)
+ mlxsw_sp_rif_macvlan_del(mlxsw_sp, upper_dev);
}
break;
}
switch (event) {
case NETDEV_PRECHANGEUPPER:
upper_dev = info->upper_dev;
- if (!netif_is_bridge_master(upper_dev)) {
- NL_SET_ERR_MSG_MOD(extack, "VLAN devices only support bridge and VRF uppers");
+ if (!netif_is_bridge_master(upper_dev) &&
+ !netif_is_macvlan(upper_dev)) {
+ NL_SET_ERR_MSG_MOD(extack, "Unknown upper device type");
return -EINVAL;
}
if (!info->linking)
NL_SET_ERR_MSG_MOD(extack, "Enslaving a port to a device that already has an upper device is not supported");
return -EINVAL;
}
+ if (netif_is_macvlan(upper_dev) &&
+ !mlxsw_sp_rif_find_by_dev(mlxsw_sp, vlan_dev)) {
+ NL_SET_ERR_MSG_MOD(extack, "macvlan is only supported on top of router interfaces");
+ return -EOPNOTSUPP;
+ }
break;
case NETDEV_CHANGEUPPER:
upper_dev = info->upper_dev;
mlxsw_sp_port_bridge_leave(mlxsw_sp_port,
vlan_dev,
upper_dev);
+ } else if (netif_is_macvlan(upper_dev)) {
+ if (!info->linking)
+ mlxsw_sp_rif_macvlan_del(mlxsw_sp, upper_dev);
} else {
err = -EINVAL;
WARN_ON(1);
return 0;
}
+static int mlxsw_sp_netdevice_bridge_event(struct net_device *br_dev,
+ unsigned long event, void *ptr)
+{
+ struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(br_dev);
+ struct netdev_notifier_changeupper_info *info = ptr;
+ struct netlink_ext_ack *extack;
+ struct net_device *upper_dev;
+
+ if (!mlxsw_sp)
+ return 0;
+
+ extack = netdev_notifier_info_to_extack(&info->info);
+
+ switch (event) {
+ case NETDEV_PRECHANGEUPPER:
+ upper_dev = info->upper_dev;
+ if (!is_vlan_dev(upper_dev) && !netif_is_macvlan(upper_dev)) {
+ NL_SET_ERR_MSG_MOD(extack, "Unknown upper device type");
+ return -EOPNOTSUPP;
+ }
+ if (!info->linking)
+ break;
+ if (netif_is_macvlan(upper_dev) &&
+ !mlxsw_sp_rif_find_by_dev(mlxsw_sp, br_dev)) {
+ NL_SET_ERR_MSG_MOD(extack, "macvlan is only supported on top of router interfaces");
+ return -EOPNOTSUPP;
+ }
+ break;
+ case NETDEV_CHANGEUPPER:
+ upper_dev = info->upper_dev;
+ if (info->linking)
+ break;
+ if (netif_is_macvlan(upper_dev))
+ mlxsw_sp_rif_macvlan_del(mlxsw_sp, upper_dev);
+ break;
+ }
+
+ return 0;
+}
+
+static int mlxsw_sp_netdevice_macvlan_event(struct net_device *macvlan_dev,
+ unsigned long event, void *ptr)
+{
+ struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(macvlan_dev);
+ struct netdev_notifier_changeupper_info *info = ptr;
+ struct netlink_ext_ack *extack;
+
+ if (!mlxsw_sp || event != NETDEV_PRECHANGEUPPER)
+ return 0;
+
+ extack = netdev_notifier_info_to_extack(&info->info);
+
+ /* VRF enslavement is handled in mlxsw_sp_netdevice_vrf_event() */
+ NL_SET_ERR_MSG_MOD(extack, "Unknown upper device type");
+
+ return -EOPNOTSUPP;
+}
+
static bool mlxsw_sp_is_vrf_event(unsigned long event, void *ptr)
{
struct netdev_notifier_changeupper_info *info = ptr;
err = mlxsw_sp_netdevice_lag_event(dev, event, ptr);
else if (is_vlan_dev(dev))
err = mlxsw_sp_netdevice_vlan_event(dev, event, ptr);
+ else if (netif_is_bridge_master(dev))
+ err = mlxsw_sp_netdevice_bridge_event(dev, event, ptr);
+ else if (netif_is_macvlan(dev))
+ err = mlxsw_sp_netdevice_macvlan_event(dev, event, ptr);
return notifier_from_errno(err);
}
MODULE_AUTHOR("Jiri Pirko <jiri@mellanox.com>");
MODULE_DESCRIPTION("Mellanox Spectrum driver");
MODULE_DEVICE_TABLE(pci, mlxsw_sp_pci_id_table);
-MODULE_FIRMWARE(MLXSW_SP_FW_FILENAME);
+MODULE_FIRMWARE(MLXSW_SP1_FW_FILENAME);
struct mlxsw_sp_counter_pool;
struct mlxsw_sp_fid_core;
struct mlxsw_sp_kvdl;
+struct mlxsw_sp_kvdl_ops;
+struct mlxsw_sp_mr_tcam_ops;
+struct mlxsw_sp_acl_tcam_ops;
struct mlxsw_sp {
struct mlxsw_sp_port **ports;
struct mlxsw_sp_span_entry *entries;
int entries_count;
} span;
+ const struct mlxsw_fw_rev *req_rev;
+ const char *fw_filename;
+ const struct mlxsw_sp_kvdl_ops *kvdl_ops;
+ const struct mlxsw_afa_ops *afa_ops;
+ const struct mlxsw_afk_ops *afk_ops;
+ const struct mlxsw_sp_mr_tcam_ops *mr_tcam_ops;
+ const struct mlxsw_sp_acl_tcam_ops *acl_tcam_ops;
};
static inline struct mlxsw_sp_upper *
int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp);
void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp);
int mlxsw_sp_netdevice_router_port_event(struct net_device *dev);
+void mlxsw_sp_rif_macvlan_del(struct mlxsw_sp *mlxsw_sp,
+ const struct net_device *macvlan_dev);
int mlxsw_sp_inetaddr_event(struct notifier_block *unused,
unsigned long event, void *ptr);
int mlxsw_sp_inetaddr_valid_event(struct notifier_block *unused,
void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif);
/* spectrum_kvdl.c */
+enum mlxsw_sp_kvdl_entry_type {
+ MLXSW_SP_KVDL_ENTRY_TYPE_ADJ,
+ MLXSW_SP_KVDL_ENTRY_TYPE_ACTSET,
+ MLXSW_SP_KVDL_ENTRY_TYPE_PBS,
+ MLXSW_SP_KVDL_ENTRY_TYPE_MCRIGR,
+};
+
+static inline unsigned int
+mlxsw_sp_kvdl_entry_size(enum mlxsw_sp_kvdl_entry_type type)
+{
+ switch (type) {
+ case MLXSW_SP_KVDL_ENTRY_TYPE_ADJ: /* fall through */
+ case MLXSW_SP_KVDL_ENTRY_TYPE_ACTSET: /* fall through */
+ case MLXSW_SP_KVDL_ENTRY_TYPE_PBS: /* fall through */
+ case MLXSW_SP_KVDL_ENTRY_TYPE_MCRIGR: /* fall through */
+ default:
+ return 1;
+ }
+}
+
+struct mlxsw_sp_kvdl_ops {
+ size_t priv_size;
+ int (*init)(struct mlxsw_sp *mlxsw_sp, void *priv);
+ void (*fini)(struct mlxsw_sp *mlxsw_sp, void *priv);
+ int (*alloc)(struct mlxsw_sp *mlxsw_sp, void *priv,
+ enum mlxsw_sp_kvdl_entry_type type,
+ unsigned int entry_count, u32 *p_entry_index);
+ void (*free)(struct mlxsw_sp *mlxsw_sp, void *priv,
+ enum mlxsw_sp_kvdl_entry_type type,
+ unsigned int entry_count, int entry_index);
+ int (*alloc_size_query)(struct mlxsw_sp *mlxsw_sp, void *priv,
+ enum mlxsw_sp_kvdl_entry_type type,
+ unsigned int entry_count,
+ unsigned int *p_alloc_count);
+ int (*resources_register)(struct mlxsw_sp *mlxsw_sp, void *priv);
+};
+
int mlxsw_sp_kvdl_init(struct mlxsw_sp *mlxsw_sp);
void mlxsw_sp_kvdl_fini(struct mlxsw_sp *mlxsw_sp);
-int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int entry_count,
- u32 *p_entry_index);
-void mlxsw_sp_kvdl_free(struct mlxsw_sp *mlxsw_sp, int entry_index);
-int mlxsw_sp_kvdl_alloc_size_query(struct mlxsw_sp *mlxsw_sp,
- unsigned int entry_count,
- unsigned int *p_alloc_size);
-int mlxsw_sp_kvdl_resources_register(struct mlxsw_core *mlxsw_core);
+int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp,
+ enum mlxsw_sp_kvdl_entry_type type,
+ unsigned int entry_count, u32 *p_entry_index);
+void mlxsw_sp_kvdl_free(struct mlxsw_sp *mlxsw_sp,
+ enum mlxsw_sp_kvdl_entry_type type,
+ unsigned int entry_count, int entry_index);
+int mlxsw_sp_kvdl_alloc_count_query(struct mlxsw_sp *mlxsw_sp,
+ enum mlxsw_sp_kvdl_entry_type type,
+ unsigned int entry_count,
+ unsigned int *p_alloc_count);
+
+/* spectrum1_kvdl.c */
+extern const struct mlxsw_sp_kvdl_ops mlxsw_sp1_kvdl_ops;
+int mlxsw_sp1_kvdl_resources_register(struct mlxsw_core *mlxsw_core);
struct mlxsw_sp_acl_rule_info {
unsigned int priority;
unsigned int counter_index;
};
-enum mlxsw_sp_acl_profile {
- MLXSW_SP_ACL_PROFILE_FLOWER,
-};
-
-struct mlxsw_sp_acl_profile_ops {
- size_t ruleset_priv_size;
- int (*ruleset_add)(struct mlxsw_sp *mlxsw_sp,
- void *priv, void *ruleset_priv);
- void (*ruleset_del)(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv);
- int (*ruleset_bind)(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv,
- struct mlxsw_sp_port *mlxsw_sp_port,
- bool ingress);
- void (*ruleset_unbind)(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv,
- struct mlxsw_sp_port *mlxsw_sp_port,
- bool ingress);
- u16 (*ruleset_group_id)(void *ruleset_priv);
- size_t rule_priv_size;
- int (*rule_add)(struct mlxsw_sp *mlxsw_sp,
- void *ruleset_priv, void *rule_priv,
- struct mlxsw_sp_acl_rule_info *rulei);
- void (*rule_del)(struct mlxsw_sp *mlxsw_sp, void *rule_priv);
- int (*rule_activity_get)(struct mlxsw_sp *mlxsw_sp, void *rule_priv,
- bool *activity);
-};
-
-struct mlxsw_sp_acl_ops {
- size_t priv_size;
- int (*init)(struct mlxsw_sp *mlxsw_sp, void *priv);
- void (*fini)(struct mlxsw_sp *mlxsw_sp, void *priv);
- const struct mlxsw_sp_acl_profile_ops *
- (*profile_ops)(struct mlxsw_sp *mlxsw_sp,
- enum mlxsw_sp_acl_profile profile);
-};
-
struct mlxsw_sp_acl_block;
struct mlxsw_sp_acl_ruleset;
/* spectrum_acl.c */
+enum mlxsw_sp_acl_profile {
+ MLXSW_SP_ACL_PROFILE_FLOWER,
+};
+
struct mlxsw_afk *mlxsw_sp_acl_afk(struct mlxsw_sp_acl *acl);
struct mlxsw_sp *mlxsw_sp_acl_block_mlxsw_sp(struct mlxsw_sp_acl_block *block);
unsigned int mlxsw_sp_acl_block_rule_count(struct mlxsw_sp_acl_block *block);
void mlxsw_sp_acl_fini(struct mlxsw_sp *mlxsw_sp);
/* spectrum_acl_tcam.c */
-extern const struct mlxsw_sp_acl_ops mlxsw_sp_acl_tcam_ops;
+struct mlxsw_sp_acl_tcam;
+struct mlxsw_sp_acl_tcam_region;
+
+struct mlxsw_sp_acl_tcam_ops {
+ enum mlxsw_reg_ptar_key_type key_type;
+ size_t priv_size;
+ int (*init)(struct mlxsw_sp *mlxsw_sp, void *priv,
+ struct mlxsw_sp_acl_tcam *tcam);
+ void (*fini)(struct mlxsw_sp *mlxsw_sp, void *priv);
+ size_t region_priv_size;
+ int (*region_init)(struct mlxsw_sp *mlxsw_sp, void *region_priv,
+ struct mlxsw_sp_acl_tcam_region *region);
+ void (*region_fini)(struct mlxsw_sp *mlxsw_sp, void *region_priv);
+ size_t chunk_priv_size;
+ void (*chunk_init)(void *region_priv, void *chunk_priv,
+ unsigned int priority);
+ void (*chunk_fini)(void *chunk_priv);
+ size_t entry_priv_size;
+ int (*entry_add)(struct mlxsw_sp *mlxsw_sp,
+ void *region_priv, void *chunk_priv,
+ void *entry_priv,
+ struct mlxsw_sp_acl_rule_info *rulei);
+ void (*entry_del)(struct mlxsw_sp *mlxsw_sp,
+ void *region_priv, void *chunk_priv,
+ void *entry_priv);
+ int (*entry_activity_get)(struct mlxsw_sp *mlxsw_sp,
+ void *region_priv, void *entry_priv,
+ bool *activity);
+};
+
+/* spectrum1_acl_tcam.c */
+extern const struct mlxsw_sp_acl_tcam_ops mlxsw_sp1_acl_tcam_ops;
+
+/* spectrum_acl_flex_actions.c */
+extern const struct mlxsw_afa_ops mlxsw_sp1_act_afa_ops;
+
+/* spectrum_acl_flex_keys.c */
+extern const struct mlxsw_afk_ops mlxsw_sp1_afk_ops;
/* spectrum_flower.c */
int mlxsw_sp_flower_replace(struct mlxsw_sp *mlxsw_sp,
int mlxsw_sp_fids_init(struct mlxsw_sp *mlxsw_sp);
void mlxsw_sp_fids_fini(struct mlxsw_sp *mlxsw_sp);
+/* spectrum_mr.c */
+enum mlxsw_sp_mr_route_prio {
+ MLXSW_SP_MR_ROUTE_PRIO_SG,
+ MLXSW_SP_MR_ROUTE_PRIO_STARG,
+ MLXSW_SP_MR_ROUTE_PRIO_CATCHALL,
+ __MLXSW_SP_MR_ROUTE_PRIO_MAX
+};
+
+#define MLXSW_SP_MR_ROUTE_PRIO_MAX (__MLXSW_SP_MR_ROUTE_PRIO_MAX - 1)
+
+struct mlxsw_sp_mr_route_key;
+
+struct mlxsw_sp_mr_tcam_ops {
+ size_t priv_size;
+ int (*init)(struct mlxsw_sp *mlxsw_sp, void *priv);
+ void (*fini)(void *priv);
+ size_t route_priv_size;
+ int (*route_create)(struct mlxsw_sp *mlxsw_sp, void *priv,
+ void *route_priv,
+ struct mlxsw_sp_mr_route_key *key,
+ struct mlxsw_afa_block *afa_block,
+ enum mlxsw_sp_mr_route_prio prio);
+ void (*route_destroy)(struct mlxsw_sp *mlxsw_sp, void *priv,
+ void *route_priv,
+ struct mlxsw_sp_mr_route_key *key);
+ int (*route_update)(struct mlxsw_sp *mlxsw_sp, void *route_priv,
+ struct mlxsw_sp_mr_route_key *key,
+ struct mlxsw_afa_block *afa_block);
+};
+
+/* spectrum1_mr_tcam.c */
+extern const struct mlxsw_sp_mr_tcam_ops mlxsw_sp1_mr_tcam_ops;
+
#endif
--- /dev/null
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
+ * Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017-2018 Jiri Pirko <jiri@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ * contributors may be used to endorse or promote products derived from
+ * this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+
+#include "reg.h"
+#include "core.h"
+#include "spectrum.h"
+#include "spectrum_acl_tcam.h"
+
+struct mlxsw_sp1_acl_tcam_region {
+ struct mlxsw_sp_acl_ctcam_region cregion;
+ struct mlxsw_sp_acl_tcam_region *region;
+ struct {
+ struct mlxsw_sp_acl_ctcam_chunk cchunk;
+ struct mlxsw_sp_acl_ctcam_entry centry;
+ struct mlxsw_sp_acl_rule_info *rulei;
+ } catchall;
+};
+
+struct mlxsw_sp1_acl_tcam_chunk {
+ struct mlxsw_sp_acl_ctcam_chunk cchunk;
+};
+
+struct mlxsw_sp1_acl_tcam_entry {
+ struct mlxsw_sp_acl_ctcam_entry centry;
+};
+
+static int mlxsw_sp1_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, void *priv,
+ struct mlxsw_sp_acl_tcam *tcam)
+{
+ return 0;
+}
+
+static void mlxsw_sp1_acl_tcam_fini(struct mlxsw_sp *mlxsw_sp, void *priv)
+{
+}
+
+static int
+mlxsw_sp1_acl_ctcam_region_catchall_add(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp1_acl_tcam_region *region)
+{
+ struct mlxsw_sp_acl_rule_info *rulei;
+ int err;
+
+ mlxsw_sp_acl_ctcam_chunk_init(®ion->cregion,
+ ®ion->catchall.cchunk,
+ MLXSW_SP_ACL_TCAM_CATCHALL_PRIO);
+ rulei = mlxsw_sp_acl_rulei_create(mlxsw_sp->acl);
+ if (IS_ERR(rulei)) {
+ err = PTR_ERR(rulei);
+ goto err_rulei_create;
+ }
+ err = mlxsw_sp_acl_rulei_act_continue(rulei);
+ if (WARN_ON(err))
+ goto err_rulei_act_continue;
+ err = mlxsw_sp_acl_rulei_commit(rulei);
+ if (err)
+ goto err_rulei_commit;
+ err = mlxsw_sp_acl_ctcam_entry_add(mlxsw_sp, ®ion->cregion,
+ ®ion->catchall.cchunk,
+ ®ion->catchall.centry,
+ rulei, false);
+ if (err)
+ goto err_entry_add;
+ region->catchall.rulei = rulei;
+ return 0;
+
+err_entry_add:
+err_rulei_commit:
+err_rulei_act_continue:
+ mlxsw_sp_acl_rulei_destroy(rulei);
+err_rulei_create:
+ mlxsw_sp_acl_ctcam_chunk_fini(®ion->catchall.cchunk);
+ return err;
+}
+
+static void
+mlxsw_sp1_acl_ctcam_region_catchall_del(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp1_acl_tcam_region *region)
+{
+ struct mlxsw_sp_acl_rule_info *rulei = region->catchall.rulei;
+
+ mlxsw_sp_acl_ctcam_entry_del(mlxsw_sp, ®ion->cregion,
+ ®ion->catchall.cchunk,
+ ®ion->catchall.centry);
+ mlxsw_sp_acl_rulei_destroy(rulei);
+ mlxsw_sp_acl_ctcam_chunk_fini(®ion->catchall.cchunk);
+}
+
+static int
+mlxsw_sp1_acl_tcam_region_init(struct mlxsw_sp *mlxsw_sp, void *region_priv,
+ struct mlxsw_sp_acl_tcam_region *_region)
+{
+ struct mlxsw_sp1_acl_tcam_region *region = region_priv;
+ int err;
+
+ err = mlxsw_sp_acl_ctcam_region_init(mlxsw_sp, ®ion->cregion,
+ _region);
+ if (err)
+ return err;
+ err = mlxsw_sp1_acl_ctcam_region_catchall_add(mlxsw_sp, region);
+ if (err)
+ goto err_catchall_add;
+ region->region = _region;
+ return 0;
+
+err_catchall_add:
+ mlxsw_sp_acl_ctcam_region_fini(®ion->cregion);
+ return err;
+}
+
+static void
+mlxsw_sp1_acl_tcam_region_fini(struct mlxsw_sp *mlxsw_sp, void *region_priv)
+{
+ struct mlxsw_sp1_acl_tcam_region *region = region_priv;
+
+ mlxsw_sp1_acl_ctcam_region_catchall_del(mlxsw_sp, region);
+ mlxsw_sp_acl_ctcam_region_fini(®ion->cregion);
+}
+
+static void mlxsw_sp1_acl_tcam_chunk_init(void *region_priv, void *chunk_priv,
+ unsigned int priority)
+{
+ struct mlxsw_sp1_acl_tcam_region *region = region_priv;
+ struct mlxsw_sp1_acl_tcam_chunk *chunk = chunk_priv;
+
+ mlxsw_sp_acl_ctcam_chunk_init(®ion->cregion, &chunk->cchunk,
+ priority);
+}
+
+static void mlxsw_sp1_acl_tcam_chunk_fini(void *chunk_priv)
+{
+ struct mlxsw_sp1_acl_tcam_chunk *chunk = chunk_priv;
+
+ mlxsw_sp_acl_ctcam_chunk_fini(&chunk->cchunk);
+}
+
+static int mlxsw_sp1_acl_tcam_entry_add(struct mlxsw_sp *mlxsw_sp,
+ void *region_priv, void *chunk_priv,
+ void *entry_priv,
+ struct mlxsw_sp_acl_rule_info *rulei)
+{
+ struct mlxsw_sp1_acl_tcam_region *region = region_priv;
+ struct mlxsw_sp1_acl_tcam_chunk *chunk = chunk_priv;
+ struct mlxsw_sp1_acl_tcam_entry *entry = entry_priv;
+
+ return mlxsw_sp_acl_ctcam_entry_add(mlxsw_sp, ®ion->cregion,
+ &chunk->cchunk, &entry->centry,
+ rulei, false);
+}
+
+static void mlxsw_sp1_acl_tcam_entry_del(struct mlxsw_sp *mlxsw_sp,
+ void *region_priv, void *chunk_priv,
+ void *entry_priv)
+{
+ struct mlxsw_sp1_acl_tcam_region *region = region_priv;
+ struct mlxsw_sp1_acl_tcam_chunk *chunk = chunk_priv;
+ struct mlxsw_sp1_acl_tcam_entry *entry = entry_priv;
+
+ mlxsw_sp_acl_ctcam_entry_del(mlxsw_sp, ®ion->cregion,
+ &chunk->cchunk, &entry->centry);
+}
+
+static int
+mlxsw_sp1_acl_tcam_region_entry_activity_get(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_acl_tcam_region *_region,
+ unsigned int offset,
+ bool *activity)
+{
+ char ptce2_pl[MLXSW_REG_PTCE2_LEN];
+ int err;
+
+ mlxsw_reg_ptce2_pack(ptce2_pl, true, MLXSW_REG_PTCE2_OP_QUERY_CLEAR_ON_READ,
+ _region->tcam_region_info, offset, 0);
+ err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ptce2), ptce2_pl);
+ if (err)
+ return err;
+ *activity = mlxsw_reg_ptce2_a_get(ptce2_pl);
+ return 0;
+}
+
+static int
+mlxsw_sp1_acl_tcam_entry_activity_get(struct mlxsw_sp *mlxsw_sp,
+ void *region_priv, void *entry_priv,
+ bool *activity)
+{
+ struct mlxsw_sp1_acl_tcam_region *region = region_priv;
+ struct mlxsw_sp1_acl_tcam_entry *entry = entry_priv;
+ unsigned int offset;
+
+ offset = mlxsw_sp_acl_ctcam_entry_offset(&entry->centry);
+ return mlxsw_sp1_acl_tcam_region_entry_activity_get(mlxsw_sp,
+ region->region,
+ offset, activity);
+}
+
+const struct mlxsw_sp_acl_tcam_ops mlxsw_sp1_acl_tcam_ops = {
+ .key_type = MLXSW_REG_PTAR_KEY_TYPE_FLEX,
+ .priv_size = 0,
+ .init = mlxsw_sp1_acl_tcam_init,
+ .fini = mlxsw_sp1_acl_tcam_fini,
+ .region_priv_size = sizeof(struct mlxsw_sp1_acl_tcam_region),
+ .region_init = mlxsw_sp1_acl_tcam_region_init,
+ .region_fini = mlxsw_sp1_acl_tcam_region_fini,
+ .chunk_priv_size = sizeof(struct mlxsw_sp1_acl_tcam_chunk),
+ .chunk_init = mlxsw_sp1_acl_tcam_chunk_init,
+ .chunk_fini = mlxsw_sp1_acl_tcam_chunk_fini,
+ .entry_priv_size = sizeof(struct mlxsw_sp1_acl_tcam_entry),
+ .entry_add = mlxsw_sp1_acl_tcam_entry_add,
+ .entry_del = mlxsw_sp1_acl_tcam_entry_del,
+ .entry_activity_get = mlxsw_sp1_acl_tcam_entry_activity_get,
+};
--- /dev/null
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum1_kvdl.c
+ * Copyright (c) 2018 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2018 Jiri Pirko <jiri@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ * contributors may be used to endorse or promote products derived from
+ * this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/bitops.h>
+
+#include "spectrum.h"
+
+#define MLXSW_SP1_KVDL_SINGLE_BASE 0
+#define MLXSW_SP1_KVDL_SINGLE_SIZE 16384
+#define MLXSW_SP1_KVDL_SINGLE_END \
+ (MLXSW_SP1_KVDL_SINGLE_SIZE + MLXSW_SP1_KVDL_SINGLE_BASE - 1)
+
+#define MLXSW_SP1_KVDL_CHUNKS_BASE \
+ (MLXSW_SP1_KVDL_SINGLE_BASE + MLXSW_SP1_KVDL_SINGLE_SIZE)
+#define MLXSW_SP1_KVDL_CHUNKS_SIZE 49152
+#define MLXSW_SP1_KVDL_CHUNKS_END \
+ (MLXSW_SP1_KVDL_CHUNKS_SIZE + MLXSW_SP1_KVDL_CHUNKS_BASE - 1)
+
+#define MLXSW_SP1_KVDL_LARGE_CHUNKS_BASE \
+ (MLXSW_SP1_KVDL_CHUNKS_BASE + MLXSW_SP1_KVDL_CHUNKS_SIZE)
+#define MLXSW_SP1_KVDL_LARGE_CHUNKS_SIZE \
+ (MLXSW_SP_KVD_LINEAR_SIZE - MLXSW_SP1_KVDL_LARGE_CHUNKS_BASE)
+#define MLXSW_SP1_KVDL_LARGE_CHUNKS_END \
+ (MLXSW_SP1_KVDL_LARGE_CHUNKS_SIZE + MLXSW_SP1_KVDL_LARGE_CHUNKS_BASE - 1)
+
+#define MLXSW_SP1_KVDL_SINGLE_ALLOC_SIZE 1
+#define MLXSW_SP1_KVDL_CHUNKS_ALLOC_SIZE 32
+#define MLXSW_SP1_KVDL_LARGE_CHUNKS_ALLOC_SIZE 512
+
+struct mlxsw_sp1_kvdl_part_info {
+ unsigned int part_index;
+ unsigned int start_index;
+ unsigned int end_index;
+ unsigned int alloc_size;
+ enum mlxsw_sp_resource_id resource_id;
+};
+
+enum mlxsw_sp1_kvdl_part_id {
+ MLXSW_SP1_KVDL_PART_ID_SINGLE,
+ MLXSW_SP1_KVDL_PART_ID_CHUNKS,
+ MLXSW_SP1_KVDL_PART_ID_LARGE_CHUNKS,
+};
+
+#define MLXSW_SP1_KVDL_PART_INFO(id) \
+[MLXSW_SP1_KVDL_PART_ID_##id] = { \
+ .start_index = MLXSW_SP1_KVDL_##id##_BASE, \
+ .end_index = MLXSW_SP1_KVDL_##id##_END, \
+ .alloc_size = MLXSW_SP1_KVDL_##id##_ALLOC_SIZE, \
+ .resource_id = MLXSW_SP_RESOURCE_KVD_LINEAR_##id, \
+}
+
+static const struct mlxsw_sp1_kvdl_part_info mlxsw_sp1_kvdl_parts_info[] = {
+ MLXSW_SP1_KVDL_PART_INFO(SINGLE),
+ MLXSW_SP1_KVDL_PART_INFO(CHUNKS),
+ MLXSW_SP1_KVDL_PART_INFO(LARGE_CHUNKS),
+};
+
+#define MLXSW_SP1_KVDL_PARTS_INFO_LEN ARRAY_SIZE(mlxsw_sp1_kvdl_parts_info)
+
+struct mlxsw_sp1_kvdl_part {
+ struct mlxsw_sp1_kvdl_part_info info;
+ unsigned long usage[0]; /* Entries */
+};
+
+struct mlxsw_sp1_kvdl {
+ struct mlxsw_sp1_kvdl_part *parts[MLXSW_SP1_KVDL_PARTS_INFO_LEN];
+};
+
+static struct mlxsw_sp1_kvdl_part *
+mlxsw_sp1_kvdl_alloc_size_part(struct mlxsw_sp1_kvdl *kvdl,
+ unsigned int alloc_size)
+{
+ struct mlxsw_sp1_kvdl_part *part, *min_part = NULL;
+ int i;
+
+ for (i = 0; i < MLXSW_SP1_KVDL_PARTS_INFO_LEN; i++) {
+ part = kvdl->parts[i];
+ if (alloc_size <= part->info.alloc_size &&
+ (!min_part ||
+ part->info.alloc_size <= min_part->info.alloc_size))
+ min_part = part;
+ }
+
+ return min_part ?: ERR_PTR(-ENOBUFS);
+}
+
+static struct mlxsw_sp1_kvdl_part *
+mlxsw_sp1_kvdl_index_part(struct mlxsw_sp1_kvdl *kvdl, u32 kvdl_index)
+{
+ struct mlxsw_sp1_kvdl_part *part;
+ int i;
+
+ for (i = 0; i < MLXSW_SP1_KVDL_PARTS_INFO_LEN; i++) {
+ part = kvdl->parts[i];
+ if (kvdl_index >= part->info.start_index &&
+ kvdl_index <= part->info.end_index)
+ return part;
+ }
+
+ return ERR_PTR(-EINVAL);
+}
+
+static u32
+mlxsw_sp1_kvdl_to_kvdl_index(const struct mlxsw_sp1_kvdl_part_info *info,
+ unsigned int entry_index)
+{
+ return info->start_index + entry_index * info->alloc_size;
+}
+
+static unsigned int
+mlxsw_sp1_kvdl_to_entry_index(const struct mlxsw_sp1_kvdl_part_info *info,
+ u32 kvdl_index)
+{
+ return (kvdl_index - info->start_index) / info->alloc_size;
+}
+
+static int mlxsw_sp1_kvdl_part_alloc(struct mlxsw_sp1_kvdl_part *part,
+ u32 *p_kvdl_index)
+{
+ const struct mlxsw_sp1_kvdl_part_info *info = &part->info;
+ unsigned int entry_index, nr_entries;
+
+ nr_entries = (info->end_index - info->start_index + 1) /
+ info->alloc_size;
+ entry_index = find_first_zero_bit(part->usage, nr_entries);
+ if (entry_index == nr_entries)
+ return -ENOBUFS;
+ __set_bit(entry_index, part->usage);
+
+ *p_kvdl_index = mlxsw_sp1_kvdl_to_kvdl_index(info, entry_index);
+
+ return 0;
+}
+
+static void mlxsw_sp1_kvdl_part_free(struct mlxsw_sp1_kvdl_part *part,
+ u32 kvdl_index)
+{
+ const struct mlxsw_sp1_kvdl_part_info *info = &part->info;
+ unsigned int entry_index;
+
+ entry_index = mlxsw_sp1_kvdl_to_entry_index(info, kvdl_index);
+ __clear_bit(entry_index, part->usage);
+}
+
+static int mlxsw_sp1_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, void *priv,
+ enum mlxsw_sp_kvdl_entry_type type,
+ unsigned int entry_count,
+ u32 *p_entry_index)
+{
+ struct mlxsw_sp1_kvdl *kvdl = priv;
+ struct mlxsw_sp1_kvdl_part *part;
+
+ /* Find partition with smallest allocation size satisfying the
+ * requested size.
+ */
+ part = mlxsw_sp1_kvdl_alloc_size_part(kvdl, entry_count);
+ if (IS_ERR(part))
+ return PTR_ERR(part);
+
+ return mlxsw_sp1_kvdl_part_alloc(part, p_entry_index);
+}
+
+static void mlxsw_sp1_kvdl_free(struct mlxsw_sp *mlxsw_sp, void *priv,
+ enum mlxsw_sp_kvdl_entry_type type,
+ unsigned int entry_count, int entry_index)
+{
+ struct mlxsw_sp1_kvdl *kvdl = priv;
+ struct mlxsw_sp1_kvdl_part *part;
+
+ part = mlxsw_sp1_kvdl_index_part(kvdl, entry_index);
+ if (IS_ERR(part))
+ return;
+ mlxsw_sp1_kvdl_part_free(part, entry_index);
+}
+
+static int mlxsw_sp1_kvdl_alloc_size_query(struct mlxsw_sp *mlxsw_sp,
+ void *priv,
+ enum mlxsw_sp_kvdl_entry_type type,
+ unsigned int entry_count,
+ unsigned int *p_alloc_size)
+{
+ struct mlxsw_sp1_kvdl *kvdl = priv;
+ struct mlxsw_sp1_kvdl_part *part;
+
+ part = mlxsw_sp1_kvdl_alloc_size_part(kvdl, entry_count);
+ if (IS_ERR(part))
+ return PTR_ERR(part);
+
+ *p_alloc_size = part->info.alloc_size;
+
+ return 0;
+}
+
+static void mlxsw_sp1_kvdl_part_update(struct mlxsw_sp1_kvdl_part *part,
+ struct mlxsw_sp1_kvdl_part *part_prev,
+ unsigned int size)
+{
+ if (!part_prev) {
+ part->info.end_index = size - 1;
+ } else {
+ part->info.start_index = part_prev->info.end_index + 1;
+ part->info.end_index = part->info.start_index + size - 1;
+ }
+}
+
+static struct mlxsw_sp1_kvdl_part *
+mlxsw_sp1_kvdl_part_init(struct mlxsw_sp *mlxsw_sp,
+ const struct mlxsw_sp1_kvdl_part_info *info,
+ struct mlxsw_sp1_kvdl_part *part_prev)
+{
+ struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
+ struct mlxsw_sp1_kvdl_part *part;
+ bool need_update = true;
+ unsigned int nr_entries;
+ size_t usage_size;
+ u64 resource_size;
+ int err;
+
+ err = devlink_resource_size_get(devlink, info->resource_id,
+ &resource_size);
+ if (err) {
+ need_update = false;
+ resource_size = info->end_index - info->start_index + 1;
+ }
+
+ nr_entries = div_u64(resource_size, info->alloc_size);
+ usage_size = BITS_TO_LONGS(nr_entries) * sizeof(unsigned long);
+ part = kzalloc(sizeof(*part) + usage_size, GFP_KERNEL);
+ if (!part)
+ return ERR_PTR(-ENOMEM);
+
+ memcpy(&part->info, info, sizeof(part->info));
+
+ if (need_update)
+ mlxsw_sp1_kvdl_part_update(part, part_prev, resource_size);
+ return part;
+}
+
+static void mlxsw_sp1_kvdl_part_fini(struct mlxsw_sp1_kvdl_part *part)
+{
+ kfree(part);
+}
+
+static int mlxsw_sp1_kvdl_parts_init(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp1_kvdl *kvdl)
+{
+ const struct mlxsw_sp1_kvdl_part_info *info;
+ struct mlxsw_sp1_kvdl_part *part_prev = NULL;
+ int err, i;
+
+ for (i = 0; i < MLXSW_SP1_KVDL_PARTS_INFO_LEN; i++) {
+ info = &mlxsw_sp1_kvdl_parts_info[i];
+ kvdl->parts[i] = mlxsw_sp1_kvdl_part_init(mlxsw_sp, info,
+ part_prev);
+ if (IS_ERR(kvdl->parts[i])) {
+ err = PTR_ERR(kvdl->parts[i]);
+ goto err_kvdl_part_init;
+ }
+ part_prev = kvdl->parts[i];
+ }
+ return 0;
+
+err_kvdl_part_init:
+ for (i--; i >= 0; i--)
+ mlxsw_sp1_kvdl_part_fini(kvdl->parts[i]);
+ return err;
+}
+
+static void mlxsw_sp1_kvdl_parts_fini(struct mlxsw_sp1_kvdl *kvdl)
+{
+ int i;
+
+ for (i = 0; i < MLXSW_SP1_KVDL_PARTS_INFO_LEN; i++)
+ mlxsw_sp1_kvdl_part_fini(kvdl->parts[i]);
+}
+
+static u64 mlxsw_sp1_kvdl_part_occ(struct mlxsw_sp1_kvdl_part *part)
+{
+ const struct mlxsw_sp1_kvdl_part_info *info = &part->info;
+ unsigned int nr_entries;
+ int bit = -1;
+ u64 occ = 0;
+
+ nr_entries = (info->end_index -
+ info->start_index + 1) /
+ info->alloc_size;
+ while ((bit = find_next_bit(part->usage, nr_entries, bit + 1))
+ < nr_entries)
+ occ += info->alloc_size;
+ return occ;
+}
+
+static u64 mlxsw_sp1_kvdl_occ_get(void *priv)
+{
+ const struct mlxsw_sp1_kvdl *kvdl = priv;
+ u64 occ = 0;
+ int i;
+
+ for (i = 0; i < MLXSW_SP1_KVDL_PARTS_INFO_LEN; i++)
+ occ += mlxsw_sp1_kvdl_part_occ(kvdl->parts[i]);
+
+ return occ;
+}
+
+static u64 mlxsw_sp1_kvdl_single_occ_get(void *priv)
+{
+ const struct mlxsw_sp1_kvdl *kvdl = priv;
+ struct mlxsw_sp1_kvdl_part *part;
+
+ part = kvdl->parts[MLXSW_SP1_KVDL_PART_ID_SINGLE];
+ return mlxsw_sp1_kvdl_part_occ(part);
+}
+
+static u64 mlxsw_sp1_kvdl_chunks_occ_get(void *priv)
+{
+ const struct mlxsw_sp1_kvdl *kvdl = priv;
+ struct mlxsw_sp1_kvdl_part *part;
+
+ part = kvdl->parts[MLXSW_SP1_KVDL_PART_ID_CHUNKS];
+ return mlxsw_sp1_kvdl_part_occ(part);
+}
+
+static u64 mlxsw_sp1_kvdl_large_chunks_occ_get(void *priv)
+{
+ const struct mlxsw_sp1_kvdl *kvdl = priv;
+ struct mlxsw_sp1_kvdl_part *part;
+
+ part = kvdl->parts[MLXSW_SP1_KVDL_PART_ID_LARGE_CHUNKS];
+ return mlxsw_sp1_kvdl_part_occ(part);
+}
+
+static int mlxsw_sp1_kvdl_init(struct mlxsw_sp *mlxsw_sp, void *priv)
+{
+ struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
+ struct mlxsw_sp1_kvdl *kvdl = priv;
+ int err;
+
+ err = mlxsw_sp1_kvdl_parts_init(mlxsw_sp, kvdl);
+ if (err)
+ return err;
+ devlink_resource_occ_get_register(devlink,
+ MLXSW_SP_RESOURCE_KVD_LINEAR,
+ mlxsw_sp1_kvdl_occ_get,
+ kvdl);
+ devlink_resource_occ_get_register(devlink,
+ MLXSW_SP_RESOURCE_KVD_LINEAR_SINGLE,
+ mlxsw_sp1_kvdl_single_occ_get,
+ kvdl);
+ devlink_resource_occ_get_register(devlink,
+ MLXSW_SP_RESOURCE_KVD_LINEAR_CHUNKS,
+ mlxsw_sp1_kvdl_chunks_occ_get,
+ kvdl);
+ devlink_resource_occ_get_register(devlink,
+ MLXSW_SP_RESOURCE_KVD_LINEAR_LARGE_CHUNKS,
+ mlxsw_sp1_kvdl_large_chunks_occ_get,
+ kvdl);
+ return 0;
+}
+
+static void mlxsw_sp1_kvdl_fini(struct mlxsw_sp *mlxsw_sp, void *priv)
+{
+ struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
+ struct mlxsw_sp1_kvdl *kvdl = priv;
+
+ devlink_resource_occ_get_unregister(devlink,
+ MLXSW_SP_RESOURCE_KVD_LINEAR_LARGE_CHUNKS);
+ devlink_resource_occ_get_unregister(devlink,
+ MLXSW_SP_RESOURCE_KVD_LINEAR_CHUNKS);
+ devlink_resource_occ_get_unregister(devlink,
+ MLXSW_SP_RESOURCE_KVD_LINEAR_SINGLE);
+ devlink_resource_occ_get_unregister(devlink,
+ MLXSW_SP_RESOURCE_KVD_LINEAR);
+ mlxsw_sp1_kvdl_parts_fini(kvdl);
+}
+
+const struct mlxsw_sp_kvdl_ops mlxsw_sp1_kvdl_ops = {
+ .priv_size = sizeof(struct mlxsw_sp1_kvdl),
+ .init = mlxsw_sp1_kvdl_init,
+ .fini = mlxsw_sp1_kvdl_fini,
+ .alloc = mlxsw_sp1_kvdl_alloc,
+ .free = mlxsw_sp1_kvdl_free,
+ .alloc_size_query = mlxsw_sp1_kvdl_alloc_size_query,
+};
+
+int mlxsw_sp1_kvdl_resources_register(struct mlxsw_core *mlxsw_core)
+{
+ struct devlink *devlink = priv_to_devlink(mlxsw_core);
+ static struct devlink_resource_size_params size_params;
+ u32 kvdl_max_size;
+ int err;
+
+ kvdl_max_size = MLXSW_CORE_RES_GET(mlxsw_core, KVD_SIZE) -
+ MLXSW_CORE_RES_GET(mlxsw_core, KVD_SINGLE_MIN_SIZE) -
+ MLXSW_CORE_RES_GET(mlxsw_core, KVD_DOUBLE_MIN_SIZE);
+
+ devlink_resource_size_params_init(&size_params, 0, kvdl_max_size,
+ MLXSW_SP1_KVDL_SINGLE_ALLOC_SIZE,
+ DEVLINK_RESOURCE_UNIT_ENTRY);
+ err = devlink_resource_register(devlink, MLXSW_SP_RESOURCE_NAME_KVD_LINEAR_SINGLES,
+ MLXSW_SP1_KVDL_SINGLE_SIZE,
+ MLXSW_SP_RESOURCE_KVD_LINEAR_SINGLE,
+ MLXSW_SP_RESOURCE_KVD_LINEAR,
+ &size_params);
+ if (err)
+ return err;
+
+ devlink_resource_size_params_init(&size_params, 0, kvdl_max_size,
+ MLXSW_SP1_KVDL_CHUNKS_ALLOC_SIZE,
+ DEVLINK_RESOURCE_UNIT_ENTRY);
+ err = devlink_resource_register(devlink, MLXSW_SP_RESOURCE_NAME_KVD_LINEAR_CHUNKS,
+ MLXSW_SP1_KVDL_CHUNKS_SIZE,
+ MLXSW_SP_RESOURCE_KVD_LINEAR_CHUNKS,
+ MLXSW_SP_RESOURCE_KVD_LINEAR,
+ &size_params);
+ if (err)
+ return err;
+
+ devlink_resource_size_params_init(&size_params, 0, kvdl_max_size,
+ MLXSW_SP1_KVDL_LARGE_CHUNKS_ALLOC_SIZE,
+ DEVLINK_RESOURCE_UNIT_ENTRY);
+ err = devlink_resource_register(devlink, MLXSW_SP_RESOURCE_NAME_KVD_LINEAR_LARGE_CHUNKS,
+ MLXSW_SP1_KVDL_LARGE_CHUNKS_SIZE,
+ MLXSW_SP_RESOURCE_KVD_LINEAR_LARGE_CHUNKS,
+ MLXSW_SP_RESOURCE_KVD_LINEAR,
+ &size_params);
+ return err;
+}
--- /dev/null
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum1_mr_tcam.c
+ * Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
+ * Copyright (c) 2018 Jiri Pirko <jiri@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ * contributors may be used to endorse or promote products derived from
+ * this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/parman.h>
+
+#include "reg.h"
+#include "spectrum.h"
+#include "core_acl_flex_actions.h"
+#include "spectrum_mr.h"
+
+struct mlxsw_sp1_mr_tcam_region {
+ struct mlxsw_sp *mlxsw_sp;
+ enum mlxsw_reg_rtar_key_type rtar_key_type;
+ struct parman *parman;
+ struct parman_prio *parman_prios;
+};
+
+struct mlxsw_sp1_mr_tcam {
+ struct mlxsw_sp1_mr_tcam_region tcam_regions[MLXSW_SP_L3_PROTO_MAX];
+};
+
+struct mlxsw_sp1_mr_tcam_route {
+ struct parman_item parman_item;
+ struct parman_prio *parman_prio;
+};
+
+static int mlxsw_sp1_mr_tcam_route_replace(struct mlxsw_sp *mlxsw_sp,
+ struct parman_item *parman_item,
+ struct mlxsw_sp_mr_route_key *key,
+ struct mlxsw_afa_block *afa_block)
+{
+ char rmft2_pl[MLXSW_REG_RMFT2_LEN];
+
+ switch (key->proto) {
+ case MLXSW_SP_L3_PROTO_IPV4:
+ mlxsw_reg_rmft2_ipv4_pack(rmft2_pl, true, parman_item->index,
+ key->vrid,
+ MLXSW_REG_RMFT2_IRIF_MASK_IGNORE, 0,
+ ntohl(key->group.addr4),
+ ntohl(key->group_mask.addr4),
+ ntohl(key->source.addr4),
+ ntohl(key->source_mask.addr4),
+ mlxsw_afa_block_first_set(afa_block));
+ break;
+ case MLXSW_SP_L3_PROTO_IPV6:
+ mlxsw_reg_rmft2_ipv6_pack(rmft2_pl, true, parman_item->index,
+ key->vrid,
+ MLXSW_REG_RMFT2_IRIF_MASK_IGNORE, 0,
+ key->group.addr6,
+ key->group_mask.addr6,
+ key->source.addr6,
+ key->source_mask.addr6,
+ mlxsw_afa_block_first_set(afa_block));
+ }
+
+ return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rmft2), rmft2_pl);
+}
+
+static int mlxsw_sp1_mr_tcam_route_remove(struct mlxsw_sp *mlxsw_sp,
+ struct parman_item *parman_item,
+ struct mlxsw_sp_mr_route_key *key)
+{
+ struct in6_addr zero_addr = IN6ADDR_ANY_INIT;
+ char rmft2_pl[MLXSW_REG_RMFT2_LEN];
+
+ switch (key->proto) {
+ case MLXSW_SP_L3_PROTO_IPV4:
+ mlxsw_reg_rmft2_ipv4_pack(rmft2_pl, false, parman_item->index,
+ key->vrid, 0, 0, 0, 0, 0, 0, NULL);
+ break;
+ case MLXSW_SP_L3_PROTO_IPV6:
+ mlxsw_reg_rmft2_ipv6_pack(rmft2_pl, false, parman_item->index,
+ key->vrid, 0, 0, zero_addr, zero_addr,
+ zero_addr, zero_addr, NULL);
+ break;
+ }
+
+ return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rmft2), rmft2_pl);
+}
+
+static struct mlxsw_sp1_mr_tcam_region *
+mlxsw_sp1_mr_tcam_protocol_region(struct mlxsw_sp1_mr_tcam *mr_tcam,
+ enum mlxsw_sp_l3proto proto)
+{
+ return &mr_tcam->tcam_regions[proto];
+}
+
+static int
+mlxsw_sp1_mr_tcam_route_parman_item_add(struct mlxsw_sp1_mr_tcam *mr_tcam,
+ struct mlxsw_sp1_mr_tcam_route *route,
+ struct mlxsw_sp_mr_route_key *key,
+ enum mlxsw_sp_mr_route_prio prio)
+{
+ struct mlxsw_sp1_mr_tcam_region *tcam_region;
+ int err;
+
+ tcam_region = mlxsw_sp1_mr_tcam_protocol_region(mr_tcam, key->proto);
+ err = parman_item_add(tcam_region->parman,
+ &tcam_region->parman_prios[prio],
+ &route->parman_item);
+ if (err)
+ return err;
+
+ route->parman_prio = &tcam_region->parman_prios[prio];
+ return 0;
+}
+
+static void
+mlxsw_sp1_mr_tcam_route_parman_item_remove(struct mlxsw_sp1_mr_tcam *mr_tcam,
+ struct mlxsw_sp1_mr_tcam_route *route,
+ struct mlxsw_sp_mr_route_key *key)
+{
+ struct mlxsw_sp1_mr_tcam_region *tcam_region;
+
+ tcam_region = mlxsw_sp1_mr_tcam_protocol_region(mr_tcam, key->proto);
+ parman_item_remove(tcam_region->parman,
+ route->parman_prio, &route->parman_item);
+}
+
+static int
+mlxsw_sp1_mr_tcam_route_create(struct mlxsw_sp *mlxsw_sp, void *priv,
+ void *route_priv,
+ struct mlxsw_sp_mr_route_key *key,
+ struct mlxsw_afa_block *afa_block,
+ enum mlxsw_sp_mr_route_prio prio)
+{
+ struct mlxsw_sp1_mr_tcam_route *route = route_priv;
+ struct mlxsw_sp1_mr_tcam *mr_tcam = priv;
+ int err;
+
+ err = mlxsw_sp1_mr_tcam_route_parman_item_add(mr_tcam, route,
+ key, prio);
+ if (err)
+ return err;
+
+ err = mlxsw_sp1_mr_tcam_route_replace(mlxsw_sp, &route->parman_item,
+ key, afa_block);
+ if (err)
+ goto err_route_replace;
+ return 0;
+
+err_route_replace:
+ mlxsw_sp1_mr_tcam_route_parman_item_remove(mr_tcam, route, key);
+ return err;
+}
+
+static void
+mlxsw_sp1_mr_tcam_route_destroy(struct mlxsw_sp *mlxsw_sp, void *priv,
+ void *route_priv,
+ struct mlxsw_sp_mr_route_key *key)
+{
+ struct mlxsw_sp1_mr_tcam_route *route = route_priv;
+ struct mlxsw_sp1_mr_tcam *mr_tcam = priv;
+
+ mlxsw_sp1_mr_tcam_route_remove(mlxsw_sp, &route->parman_item, key);
+ mlxsw_sp1_mr_tcam_route_parman_item_remove(mr_tcam, route, key);
+}
+
+static int
+mlxsw_sp1_mr_tcam_route_update(struct mlxsw_sp *mlxsw_sp,
+ void *route_priv,
+ struct mlxsw_sp_mr_route_key *key,
+ struct mlxsw_afa_block *afa_block)
+{
+ struct mlxsw_sp1_mr_tcam_route *route = route_priv;
+
+ return mlxsw_sp1_mr_tcam_route_replace(mlxsw_sp, &route->parman_item,
+ key, afa_block);
+}
+
+#define MLXSW_SP1_MR_TCAM_REGION_BASE_COUNT 16
+#define MLXSW_SP1_MR_TCAM_REGION_RESIZE_STEP 16
+
+static int
+mlxsw_sp1_mr_tcam_region_alloc(struct mlxsw_sp1_mr_tcam_region *mr_tcam_region)
+{
+ struct mlxsw_sp *mlxsw_sp = mr_tcam_region->mlxsw_sp;
+ char rtar_pl[MLXSW_REG_RTAR_LEN];
+
+ mlxsw_reg_rtar_pack(rtar_pl, MLXSW_REG_RTAR_OP_ALLOCATE,
+ mr_tcam_region->rtar_key_type,
+ MLXSW_SP1_MR_TCAM_REGION_BASE_COUNT);
+ return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rtar), rtar_pl);
+}
+
+static void
+mlxsw_sp1_mr_tcam_region_free(struct mlxsw_sp1_mr_tcam_region *mr_tcam_region)
+{
+ struct mlxsw_sp *mlxsw_sp = mr_tcam_region->mlxsw_sp;
+ char rtar_pl[MLXSW_REG_RTAR_LEN];
+
+ mlxsw_reg_rtar_pack(rtar_pl, MLXSW_REG_RTAR_OP_DEALLOCATE,
+ mr_tcam_region->rtar_key_type, 0);
+ mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rtar), rtar_pl);
+}
+
+static int mlxsw_sp1_mr_tcam_region_parman_resize(void *priv,
+ unsigned long new_count)
+{
+ struct mlxsw_sp1_mr_tcam_region *mr_tcam_region = priv;
+ struct mlxsw_sp *mlxsw_sp = mr_tcam_region->mlxsw_sp;
+ char rtar_pl[MLXSW_REG_RTAR_LEN];
+ u64 max_tcam_rules;
+
+ max_tcam_rules = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_TCAM_RULES);
+ if (new_count > max_tcam_rules)
+ return -EINVAL;
+ mlxsw_reg_rtar_pack(rtar_pl, MLXSW_REG_RTAR_OP_RESIZE,
+ mr_tcam_region->rtar_key_type, new_count);
+ return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rtar), rtar_pl);
+}
+
+static void mlxsw_sp1_mr_tcam_region_parman_move(void *priv,
+ unsigned long from_index,
+ unsigned long to_index,
+ unsigned long count)
+{
+ struct mlxsw_sp1_mr_tcam_region *mr_tcam_region = priv;
+ struct mlxsw_sp *mlxsw_sp = mr_tcam_region->mlxsw_sp;
+ char rrcr_pl[MLXSW_REG_RRCR_LEN];
+
+ mlxsw_reg_rrcr_pack(rrcr_pl, MLXSW_REG_RRCR_OP_MOVE,
+ from_index, count,
+ mr_tcam_region->rtar_key_type, to_index);
+ mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rrcr), rrcr_pl);
+}
+
+static const struct parman_ops mlxsw_sp1_mr_tcam_region_parman_ops = {
+ .base_count = MLXSW_SP1_MR_TCAM_REGION_BASE_COUNT,
+ .resize_step = MLXSW_SP1_MR_TCAM_REGION_RESIZE_STEP,
+ .resize = mlxsw_sp1_mr_tcam_region_parman_resize,
+ .move = mlxsw_sp1_mr_tcam_region_parman_move,
+ .algo = PARMAN_ALGO_TYPE_LSORT,
+};
+
+static int
+mlxsw_sp1_mr_tcam_region_init(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp1_mr_tcam_region *mr_tcam_region,
+ enum mlxsw_reg_rtar_key_type rtar_key_type)
+{
+ struct parman_prio *parman_prios;
+ struct parman *parman;
+ int err;
+ int i;
+
+ mr_tcam_region->rtar_key_type = rtar_key_type;
+ mr_tcam_region->mlxsw_sp = mlxsw_sp;
+
+ err = mlxsw_sp1_mr_tcam_region_alloc(mr_tcam_region);
+ if (err)
+ return err;
+
+ parman = parman_create(&mlxsw_sp1_mr_tcam_region_parman_ops,
+ mr_tcam_region);
+ if (!parman) {
+ err = -ENOMEM;
+ goto err_parman_create;
+ }
+ mr_tcam_region->parman = parman;
+
+ parman_prios = kmalloc_array(MLXSW_SP_MR_ROUTE_PRIO_MAX + 1,
+ sizeof(*parman_prios), GFP_KERNEL);
+ if (!parman_prios) {
+ err = -ENOMEM;
+ goto err_parman_prios_alloc;
+ }
+ mr_tcam_region->parman_prios = parman_prios;
+
+ for (i = 0; i < MLXSW_SP_MR_ROUTE_PRIO_MAX + 1; i++)
+ parman_prio_init(mr_tcam_region->parman,
+ &mr_tcam_region->parman_prios[i], i);
+ return 0;
+
+err_parman_prios_alloc:
+ parman_destroy(parman);
+err_parman_create:
+ mlxsw_sp1_mr_tcam_region_free(mr_tcam_region);
+ return err;
+}
+
+static void
+mlxsw_sp1_mr_tcam_region_fini(struct mlxsw_sp1_mr_tcam_region *mr_tcam_region)
+{
+ int i;
+
+ for (i = 0; i < MLXSW_SP_MR_ROUTE_PRIO_MAX + 1; i++)
+ parman_prio_fini(&mr_tcam_region->parman_prios[i]);
+ kfree(mr_tcam_region->parman_prios);
+ parman_destroy(mr_tcam_region->parman);
+ mlxsw_sp1_mr_tcam_region_free(mr_tcam_region);
+}
+
+static int mlxsw_sp1_mr_tcam_init(struct mlxsw_sp *mlxsw_sp, void *priv)
+{
+ struct mlxsw_sp1_mr_tcam *mr_tcam = priv;
+ struct mlxsw_sp1_mr_tcam_region *region = &mr_tcam->tcam_regions[0];
+ u32 rtar_key;
+ int err;
+
+ if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, ACL_MAX_TCAM_RULES))
+ return -EIO;
+
+ rtar_key = MLXSW_REG_RTAR_KEY_TYPE_IPV4_MULTICAST;
+ err = mlxsw_sp1_mr_tcam_region_init(mlxsw_sp,
+ ®ion[MLXSW_SP_L3_PROTO_IPV4],
+ rtar_key);
+ if (err)
+ return err;
+
+ rtar_key = MLXSW_REG_RTAR_KEY_TYPE_IPV6_MULTICAST;
+ err = mlxsw_sp1_mr_tcam_region_init(mlxsw_sp,
+ ®ion[MLXSW_SP_L3_PROTO_IPV6],
+ rtar_key);
+ if (err)
+ goto err_ipv6_region_init;
+
+ return 0;
+
+err_ipv6_region_init:
+ mlxsw_sp1_mr_tcam_region_fini(®ion[MLXSW_SP_L3_PROTO_IPV4]);
+ return err;
+}
+
+static void mlxsw_sp1_mr_tcam_fini(void *priv)
+{
+ struct mlxsw_sp1_mr_tcam *mr_tcam = priv;
+ struct mlxsw_sp1_mr_tcam_region *region = &mr_tcam->tcam_regions[0];
+
+ mlxsw_sp1_mr_tcam_region_fini(®ion[MLXSW_SP_L3_PROTO_IPV6]);
+ mlxsw_sp1_mr_tcam_region_fini(®ion[MLXSW_SP_L3_PROTO_IPV4]);
+}
+
+const struct mlxsw_sp_mr_tcam_ops mlxsw_sp1_mr_tcam_ops = {
+ .priv_size = sizeof(struct mlxsw_sp1_mr_tcam),
+ .init = mlxsw_sp1_mr_tcam_init,
+ .fini = mlxsw_sp1_mr_tcam_fini,
+ .route_priv_size = sizeof(struct mlxsw_sp1_mr_tcam_route),
+ .route_create = mlxsw_sp1_mr_tcam_route_create,
+ .route_destroy = mlxsw_sp1_mr_tcam_route_destroy,
+ .route_update = mlxsw_sp1_mr_tcam_route_update,
+};
#include "spectrum.h"
#include "core_acl_flex_keys.h"
#include "core_acl_flex_actions.h"
-#include "spectrum_acl_flex_keys.h"
+#include "spectrum_acl_tcam.h"
struct mlxsw_sp_acl {
struct mlxsw_sp *mlxsw_sp;
struct mlxsw_afk *afk;
struct mlxsw_sp_fid *dummy_fid;
- const struct mlxsw_sp_acl_ops *ops;
struct rhashtable ruleset_ht;
struct list_head rules;
struct {
unsigned long interval; /* ms */
#define MLXSW_SP_ACL_RULE_ACTIVITY_UPDATE_PERIOD_MS 1000
} rule_activity_update;
- unsigned long priv[0];
- /* priv has to be always the last item */
+ struct mlxsw_sp_acl_tcam tcam;
};
struct mlxsw_afk *mlxsw_sp_acl_afk(struct mlxsw_sp_acl *acl)
if (err)
goto err_rhashtable_init;
- err = ops->ruleset_add(mlxsw_sp, acl->priv, ruleset->priv);
+ err = ops->ruleset_add(mlxsw_sp, &acl->tcam, ruleset->priv);
if (err)
goto err_ops_ruleset_add;
struct mlxsw_sp_acl *acl = mlxsw_sp->acl;
struct mlxsw_sp_acl_ruleset *ruleset;
- ops = acl->ops->profile_ops(mlxsw_sp, profile);
+ ops = mlxsw_sp_acl_tcam_profile_ops(mlxsw_sp, profile);
if (!ops)
return ERR_PTR(-EINVAL);
ruleset = __mlxsw_sp_acl_ruleset_lookup(acl, block, chain_index, ops);
struct mlxsw_sp_acl *acl = mlxsw_sp->acl;
struct mlxsw_sp_acl_ruleset *ruleset;
- ops = acl->ops->profile_ops(mlxsw_sp, profile);
+ ops = mlxsw_sp_acl_tcam_profile_ops(mlxsw_sp, profile);
if (!ops)
return ERR_PTR(-EINVAL);
void mlxsw_sp_acl_rulei_priority(struct mlxsw_sp_acl_rule_info *rulei,
unsigned int priority)
{
- rulei->priority = priority;
+ rulei->priority = priority >> 16;
}
void mlxsw_sp_acl_rulei_keymask_u32(struct mlxsw_sp_acl_rule_info *rulei,
int err;
mlxsw_sp_acl_ruleset_ref_inc(ruleset);
- rule = kzalloc(sizeof(*rule) + ops->rule_priv_size, GFP_KERNEL);
+ rule = kzalloc(sizeof(*rule) + ops->rule_priv_size(mlxsw_sp),
+ GFP_KERNEL);
if (!rule) {
err = -ENOMEM;
goto err_alloc;
int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp)
{
- const struct mlxsw_sp_acl_ops *acl_ops = &mlxsw_sp_acl_tcam_ops;
struct mlxsw_sp_fid *fid;
struct mlxsw_sp_acl *acl;
+ size_t alloc_size;
int err;
- acl = kzalloc(sizeof(*acl) + acl_ops->priv_size, GFP_KERNEL);
+ alloc_size = sizeof(*acl) + mlxsw_sp_acl_tcam_priv_size(mlxsw_sp);
+ acl = kzalloc(alloc_size, GFP_KERNEL);
if (!acl)
return -ENOMEM;
mlxsw_sp->acl = acl;
acl->mlxsw_sp = mlxsw_sp;
acl->afk = mlxsw_afk_create(MLXSW_CORE_RES_GET(mlxsw_sp->core,
ACL_FLEX_KEYS),
- mlxsw_sp_afk_blocks,
- MLXSW_SP_AFK_BLOCKS_COUNT);
+ mlxsw_sp->afk_ops);
if (!acl->afk) {
err = -ENOMEM;
goto err_afk_create;
acl->dummy_fid = fid;
INIT_LIST_HEAD(&acl->rules);
- err = acl_ops->init(mlxsw_sp, acl->priv);
+ err = mlxsw_sp_acl_tcam_init(mlxsw_sp, &acl->tcam);
if (err)
goto err_acl_ops_init;
- acl->ops = acl_ops;
-
/* Create the delayed work for the rule activity_update */
INIT_DELAYED_WORK(&acl->rule_activity_update.dw,
mlxsw_sp_acl_rul_activity_update_work);
void mlxsw_sp_acl_fini(struct mlxsw_sp *mlxsw_sp)
{
struct mlxsw_sp_acl *acl = mlxsw_sp->acl;
- const struct mlxsw_sp_acl_ops *acl_ops = acl->ops;
cancel_delayed_work_sync(&mlxsw_sp->acl->rule_activity_update.dw);
- acl_ops->fini(mlxsw_sp, acl->priv);
+ mlxsw_sp_acl_tcam_fini(mlxsw_sp, &acl->tcam);
WARN_ON(!list_empty(&acl->rules));
mlxsw_sp_fid_put(acl->dummy_fid);
rhashtable_destroy(&acl->ruleset_ht);
--- /dev/null
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
+ * Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017-2018 Jiri Pirko <jiri@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ * contributors may be used to endorse or promote products derived from
+ * this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/parman.h>
+
+#include "reg.h"
+#include "core.h"
+#include "spectrum.h"
+#include "spectrum_acl_tcam.h"
+
+static int
+mlxsw_sp_acl_ctcam_region_resize(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_acl_tcam_region *region,
+ u16 new_size)
+{
+ char ptar_pl[MLXSW_REG_PTAR_LEN];
+
+ mlxsw_reg_ptar_pack(ptar_pl, MLXSW_REG_PTAR_OP_RESIZE,
+ region->key_type, new_size, region->id,
+ region->tcam_region_info);
+ return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptar), ptar_pl);
+}
+
+static void
+mlxsw_sp_acl_ctcam_region_move(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_acl_tcam_region *region,
+ u16 src_offset, u16 dst_offset, u16 size)
+{
+ char prcr_pl[MLXSW_REG_PRCR_LEN];
+
+ mlxsw_reg_prcr_pack(prcr_pl, MLXSW_REG_PRCR_OP_MOVE,
+ region->tcam_region_info, src_offset,
+ region->tcam_region_info, dst_offset, size);
+ mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(prcr), prcr_pl);
+}
+
+static int
+mlxsw_sp_acl_ctcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_acl_tcam_region *region,
+ unsigned int offset,
+ struct mlxsw_sp_acl_rule_info *rulei,
+ bool fillup_priority)
+{
+ struct mlxsw_afk *afk = mlxsw_sp_acl_afk(mlxsw_sp->acl);
+ char ptce2_pl[MLXSW_REG_PTCE2_LEN];
+ char *act_set;
+ u32 priority;
+ char *mask;
+ char *key;
+ int err;
+
+ err = mlxsw_sp_acl_tcam_priority_get(mlxsw_sp, rulei, &priority,
+ fillup_priority);
+ if (err)
+ return err;
+
+ mlxsw_reg_ptce2_pack(ptce2_pl, true, MLXSW_REG_PTCE2_OP_WRITE_WRITE,
+ region->tcam_region_info, offset, priority);
+ key = mlxsw_reg_ptce2_flex_key_blocks_data(ptce2_pl);
+ mask = mlxsw_reg_ptce2_mask_data(ptce2_pl);
+ mlxsw_afk_encode(afk, region->key_info, &rulei->values, key, mask);
+
+ /* Only the first action set belongs here, the rest is in KVD */
+ act_set = mlxsw_afa_block_first_set(rulei->act_block);
+ mlxsw_reg_ptce2_flex_action_set_memcpy_to(ptce2_pl, act_set);
+
+ return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptce2), ptce2_pl);
+}
+
+static void
+mlxsw_sp_acl_ctcam_region_entry_remove(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_acl_tcam_region *region,
+ unsigned int offset)
+{
+ char ptce2_pl[MLXSW_REG_PTCE2_LEN];
+
+ mlxsw_reg_ptce2_pack(ptce2_pl, false, MLXSW_REG_PTCE2_OP_WRITE_WRITE,
+ region->tcam_region_info, offset, 0);
+ mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptce2), ptce2_pl);
+}
+
+static int mlxsw_sp_acl_ctcam_region_parman_resize(void *priv,
+ unsigned long new_count)
+{
+ struct mlxsw_sp_acl_ctcam_region *cregion = priv;
+ struct mlxsw_sp_acl_tcam_region *region = cregion->region;
+ struct mlxsw_sp *mlxsw_sp = region->mlxsw_sp;
+ u64 max_tcam_rules;
+
+ max_tcam_rules = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_TCAM_RULES);
+ if (new_count > max_tcam_rules)
+ return -EINVAL;
+ return mlxsw_sp_acl_ctcam_region_resize(mlxsw_sp, region, new_count);
+}
+
+static void mlxsw_sp_acl_ctcam_region_parman_move(void *priv,
+ unsigned long from_index,
+ unsigned long to_index,
+ unsigned long count)
+{
+ struct mlxsw_sp_acl_ctcam_region *cregion = priv;
+ struct mlxsw_sp_acl_tcam_region *region = cregion->region;
+ struct mlxsw_sp *mlxsw_sp = region->mlxsw_sp;
+
+ mlxsw_sp_acl_ctcam_region_move(mlxsw_sp, region,
+ from_index, to_index, count);
+}
+
+static const struct parman_ops mlxsw_sp_acl_ctcam_region_parman_ops = {
+ .base_count = MLXSW_SP_ACL_TCAM_REGION_BASE_COUNT,
+ .resize_step = MLXSW_SP_ACL_TCAM_REGION_RESIZE_STEP,
+ .resize = mlxsw_sp_acl_ctcam_region_parman_resize,
+ .move = mlxsw_sp_acl_ctcam_region_parman_move,
+ .algo = PARMAN_ALGO_TYPE_LSORT,
+};
+
+int mlxsw_sp_acl_ctcam_region_init(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_acl_ctcam_region *cregion,
+ struct mlxsw_sp_acl_tcam_region *region)
+{
+ cregion->region = region;
+ cregion->parman = parman_create(&mlxsw_sp_acl_ctcam_region_parman_ops,
+ cregion);
+ if (!cregion->parman)
+ return -ENOMEM;
+ return 0;
+}
+
+void mlxsw_sp_acl_ctcam_region_fini(struct mlxsw_sp_acl_ctcam_region *cregion)
+{
+ parman_destroy(cregion->parman);
+}
+
+void mlxsw_sp_acl_ctcam_chunk_init(struct mlxsw_sp_acl_ctcam_region *cregion,
+ struct mlxsw_sp_acl_ctcam_chunk *cchunk,
+ unsigned int priority)
+{
+ parman_prio_init(cregion->parman, &cchunk->parman_prio, priority);
+}
+
+void mlxsw_sp_acl_ctcam_chunk_fini(struct mlxsw_sp_acl_ctcam_chunk *cchunk)
+{
+ parman_prio_fini(&cchunk->parman_prio);
+}
+
+int mlxsw_sp_acl_ctcam_entry_add(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_acl_ctcam_region *cregion,
+ struct mlxsw_sp_acl_ctcam_chunk *cchunk,
+ struct mlxsw_sp_acl_ctcam_entry *centry,
+ struct mlxsw_sp_acl_rule_info *rulei,
+ bool fillup_priority)
+{
+ int err;
+
+ err = parman_item_add(cregion->parman, &cchunk->parman_prio,
+ ¢ry->parman_item);
+ if (err)
+ return err;
+
+ err = mlxsw_sp_acl_ctcam_region_entry_insert(mlxsw_sp, cregion->region,
+ centry->parman_item.index,
+ rulei, fillup_priority);
+ if (err)
+ goto err_rule_insert;
+ return 0;
+
+err_rule_insert:
+ parman_item_remove(cregion->parman, &cchunk->parman_prio,
+ ¢ry->parman_item);
+ return err;
+}
+
+void mlxsw_sp_acl_ctcam_entry_del(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_acl_ctcam_region *cregion,
+ struct mlxsw_sp_acl_ctcam_chunk *cchunk,
+ struct mlxsw_sp_acl_ctcam_entry *centry)
+{
+ mlxsw_sp_acl_ctcam_region_entry_remove(mlxsw_sp, cregion->region,
+ centry->parman_item.index);
+ parman_item_remove(cregion->parman, &cchunk->parman_prio,
+ ¢ry->parman_item);
+}
#include "core_acl_flex_actions.h"
#include "spectrum_span.h"
-#define MLXSW_SP_KVDL_ACT_EXT_SIZE 1
-
static int mlxsw_sp_act_kvdl_set_add(void *priv, u32 *p_kvdl_index,
char *enc_actions, bool is_first)
{
if (is_first)
return 0;
- err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KVDL_ACT_EXT_SIZE,
- &kvdl_index);
+ err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ACTSET,
+ 1, &kvdl_index);
if (err)
return err;
mlxsw_reg_pefa_pack(pefa_pl, kvdl_index, enc_actions);
return 0;
err_pefa_write:
- mlxsw_sp_kvdl_free(mlxsw_sp, kvdl_index);
+ mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ACTSET,
+ 1, kvdl_index);
return err;
}
if (is_first)
return;
- mlxsw_sp_kvdl_free(mlxsw_sp, kvdl_index);
+ mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ACTSET,
+ 1, kvdl_index);
}
static int mlxsw_sp_act_kvdl_fwd_entry_add(void *priv, u32 *p_kvdl_index,
u32 kvdl_index;
int err;
- err = mlxsw_sp_kvdl_alloc(mlxsw_sp, 1, &kvdl_index);
+ err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_PBS,
+ 1, &kvdl_index);
if (err)
return err;
mlxsw_reg_ppbs_pack(ppbs_pl, kvdl_index, local_port);
return 0;
err_ppbs_write:
- mlxsw_sp_kvdl_free(mlxsw_sp, kvdl_index);
+ mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_PBS,
+ 1, kvdl_index);
return err;
}
{
struct mlxsw_sp *mlxsw_sp = priv;
- mlxsw_sp_kvdl_free(mlxsw_sp, kvdl_index);
+ mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_PBS,
+ 1, kvdl_index);
}
static int
mlxsw_sp_span_mirror_del(in_port, span_id, type, false);
}
-static const struct mlxsw_afa_ops mlxsw_sp_act_afa_ops = {
+const struct mlxsw_afa_ops mlxsw_sp1_act_afa_ops = {
.kvdl_set_add = mlxsw_sp_act_kvdl_set_add,
.kvdl_set_del = mlxsw_sp_act_kvdl_set_del,
.kvdl_fwd_entry_add = mlxsw_sp_act_kvdl_fwd_entry_add,
{
mlxsw_sp->afa = mlxsw_afa_create(MLXSW_CORE_RES_GET(mlxsw_sp->core,
ACL_ACTIONS_PER_SET),
- &mlxsw_sp_act_afa_ops, mlxsw_sp);
+ mlxsw_sp->afa_ops, mlxsw_sp);
return PTR_ERR_OR_ZERO(mlxsw_sp->afa);
}
/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Jiri Pirko <jiri@mellanox.com>
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
+ * Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017-2018 Jiri Pirko <jiri@mellanox.com>
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
* POSSIBILITY OF SUCH DAMAGE.
*/
-#ifndef _MLXSW_SPECTRUM_ACL_FLEX_KEYS_H
-#define _MLXSW_SPECTRUM_ACL_FLEX_KEYS_H
-
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include "spectrum.h"
+#include "item.h"
#include "core_acl_flex_keys.h"
static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l2_dmac[] = {
- MLXSW_AFK_ELEMENT_INST_BUF(DMAC, 0x00, 6),
+ MLXSW_AFK_ELEMENT_INST_BUF(DMAC_32_47, 0x00, 2),
+ MLXSW_AFK_ELEMENT_INST_BUF(DMAC_0_31, 0x02, 4),
MLXSW_AFK_ELEMENT_INST_U32(PCP, 0x08, 13, 3),
MLXSW_AFK_ELEMENT_INST_U32(VID, 0x08, 0, 12),
- MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 16),
+ MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 8),
};
static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l2_smac[] = {
- MLXSW_AFK_ELEMENT_INST_BUF(SMAC, 0x00, 6),
+ MLXSW_AFK_ELEMENT_INST_BUF(SMAC_32_47, 0x00, 2),
+ MLXSW_AFK_ELEMENT_INST_BUF(SMAC_0_31, 0x02, 4),
MLXSW_AFK_ELEMENT_INST_U32(PCP, 0x08, 13, 3),
MLXSW_AFK_ELEMENT_INST_U32(VID, 0x08, 0, 12),
- MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 16),
+ MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 8),
};
static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l2_smac_ex[] = {
- MLXSW_AFK_ELEMENT_INST_BUF(SMAC, 0x02, 6),
+ MLXSW_AFK_ELEMENT_INST_BUF(SMAC_32_47, 0x02, 2),
+ MLXSW_AFK_ELEMENT_INST_BUF(SMAC_0_31, 0x04, 4),
MLXSW_AFK_ELEMENT_INST_U32(ETHERTYPE, 0x0C, 0, 16),
};
static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_sip[] = {
- MLXSW_AFK_ELEMENT_INST_U32(SRC_IP4, 0x00, 0, 32),
+ MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_0_31, 0x00, 4),
MLXSW_AFK_ELEMENT_INST_U32(IP_PROTO, 0x08, 0, 8),
- MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 16),
+ MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 8),
};
static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_dip[] = {
- MLXSW_AFK_ELEMENT_INST_U32(DST_IP4, 0x00, 0, 32),
+ MLXSW_AFK_ELEMENT_INST_BUF(DST_IP_0_31, 0x00, 4),
MLXSW_AFK_ELEMENT_INST_U32(IP_PROTO, 0x08, 0, 8),
- MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 16),
+ MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 8),
};
static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4[] = {
- MLXSW_AFK_ELEMENT_INST_U32(SRC_IP4, 0x00, 0, 32),
+ MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_0_31, 0x00, 4),
MLXSW_AFK_ELEMENT_INST_U32(IP_ECN, 0x04, 4, 2),
MLXSW_AFK_ELEMENT_INST_U32(IP_TTL_, 0x04, 24, 8),
MLXSW_AFK_ELEMENT_INST_U32(IP_DSCP, 0x08, 0, 6),
};
static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_dip[] = {
- MLXSW_AFK_ELEMENT_INST_BUF(DST_IP6_LO, 0x00, 8),
+ MLXSW_AFK_ELEMENT_INST_BUF(DST_IP_32_63, 0x00, 4),
+ MLXSW_AFK_ELEMENT_INST_BUF(DST_IP_0_31, 0x04, 4),
};
static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_ex1[] = {
- MLXSW_AFK_ELEMENT_INST_BUF(DST_IP6_HI, 0x00, 8),
+ MLXSW_AFK_ELEMENT_INST_BUF(DST_IP_96_127, 0x00, 4),
+ MLXSW_AFK_ELEMENT_INST_BUF(DST_IP_64_95, 0x04, 4),
MLXSW_AFK_ELEMENT_INST_U32(IP_PROTO, 0x08, 0, 8),
};
static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_sip[] = {
- MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP6_LO, 0x00, 8),
+ MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_32_63, 0x00, 4),
+ MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_0_31, 0x04, 4),
};
static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_sip_ex[] = {
- MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP6_HI, 0x00, 8),
+ MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_96_127, 0x00, 4),
+ MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_64_95, 0x04, 4),
};
static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_packet_type[] = {
MLXSW_AFK_ELEMENT_INST_U32(ETHERTYPE, 0x00, 0, 16),
};
-static const struct mlxsw_afk_block mlxsw_sp_afk_blocks[] = {
+static const struct mlxsw_afk_block mlxsw_sp1_afk_blocks[] = {
MLXSW_AFK_BLOCK(0x10, mlxsw_sp_afk_element_info_l2_dmac),
MLXSW_AFK_BLOCK(0x11, mlxsw_sp_afk_element_info_l2_smac),
MLXSW_AFK_BLOCK(0x12, mlxsw_sp_afk_element_info_l2_smac_ex),
MLXSW_AFK_BLOCK(0xB0, mlxsw_sp_afk_element_info_packet_type),
};
-#define MLXSW_SP_AFK_BLOCKS_COUNT ARRAY_SIZE(mlxsw_sp_afk_blocks)
-
-#endif
+static void mlxsw_sp1_afk_encode_u32(const struct mlxsw_item *storage_item,
+ const struct mlxsw_item *output_item,
+ char *storage, char *output_indexed)
+{
+ u32 value;
+
+ value = __mlxsw_item_get32(storage, storage_item, 0);
+ __mlxsw_item_set32(output_indexed, output_item, 0, value);
+}
+
+static void mlxsw_sp1_afk_encode_buf(const struct mlxsw_item *storage_item,
+ const struct mlxsw_item *output_item,
+ char *storage, char *output_indexed)
+{
+ char *storage_data = __mlxsw_item_data(storage, storage_item, 0);
+ char *output_data = __mlxsw_item_data(output_indexed, output_item, 0);
+ size_t len = output_item->size.bytes;
+
+ memcpy(output_data, storage_data, len);
+}
+
+#define MLXSW_SP1_AFK_KEY_BLOCK_SIZE 16
+
+static void
+mlxsw_sp1_afk_encode_one(const struct mlxsw_afk_element_inst *elinst,
+ int block_index, char *storage, char *output)
+{
+ unsigned int offset = block_index * MLXSW_SP1_AFK_KEY_BLOCK_SIZE;
+ char *output_indexed = output + offset;
+ const struct mlxsw_item *storage_item = &elinst->info->item;
+ const struct mlxsw_item *output_item = &elinst->item;
+
+ if (elinst->type == MLXSW_AFK_ELEMENT_TYPE_U32)
+ mlxsw_sp1_afk_encode_u32(storage_item, output_item,
+ storage, output_indexed);
+ else if (elinst->type == MLXSW_AFK_ELEMENT_TYPE_BUF)
+ mlxsw_sp1_afk_encode_buf(storage_item, output_item,
+ storage, output_indexed);
+}
+
+const struct mlxsw_afk_ops mlxsw_sp1_afk_ops = {
+ .blocks = mlxsw_sp1_afk_blocks,
+ .blocks_count = ARRAY_SIZE(mlxsw_sp1_afk_blocks),
+ .encode_one = mlxsw_sp1_afk_encode_one,
+};
/*
* drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Jiri Pirko <jiri@mellanox.com>
+ * Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017-2018 Jiri Pirko <jiri@mellanox.com>
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
#include <linux/list.h>
#include <linux/rhashtable.h>
#include <linux/netdevice.h>
-#include <linux/parman.h>
#include "reg.h"
#include "core.h"
#include "resources.h"
#include "spectrum.h"
+#include "spectrum_acl_tcam.h"
#include "core_acl_flex_keys.h"
-struct mlxsw_sp_acl_tcam {
- unsigned long *used_regions; /* bit array */
- unsigned int max_regions;
- unsigned long *used_groups; /* bit array */
- unsigned int max_groups;
- unsigned int max_group_size;
-};
+size_t mlxsw_sp_acl_tcam_priv_size(struct mlxsw_sp *mlxsw_sp)
+{
+ const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
+
+ return ops->priv_size;
+}
-static int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, void *priv)
+int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_acl_tcam *tcam)
{
- struct mlxsw_sp_acl_tcam *tcam = priv;
+ const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
u64 max_tcam_regions;
u64 max_regions;
u64 max_groups;
tcam->max_groups = max_groups;
tcam->max_group_size = MLXSW_CORE_RES_GET(mlxsw_sp->core,
ACL_MAX_GROUP_SIZE);
+
+ err = ops->init(mlxsw_sp, tcam->priv, tcam);
+ if (err)
+ goto err_tcam_init;
+
return 0;
+err_tcam_init:
+ kfree(tcam->used_groups);
err_alloc_used_groups:
kfree(tcam->used_regions);
return err;
}
-static void mlxsw_sp_acl_tcam_fini(struct mlxsw_sp *mlxsw_sp, void *priv)
+void mlxsw_sp_acl_tcam_fini(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_acl_tcam *tcam)
{
- struct mlxsw_sp_acl_tcam *tcam = priv;
+ const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
+ ops->fini(mlxsw_sp, tcam->priv);
kfree(tcam->used_groups);
kfree(tcam->used_regions);
}
+int mlxsw_sp_acl_tcam_priority_get(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_acl_rule_info *rulei,
+ u32 *priority, bool fillup_priority)
+{
+ u64 max_priority;
+
+ if (!fillup_priority) {
+ *priority = 0;
+ return 0;
+ }
+
+ if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, KVD_SIZE))
+ return -EIO;
+
+ max_priority = MLXSW_CORE_RES_GET(mlxsw_sp->core, KVD_SIZE);
+ if (rulei->priority > max_priority)
+ return -EINVAL;
+
+ /* Unlike in TC, in HW, higher number means higher priority. */
+ *priority = max_priority - rulei->priority;
+ return 0;
+}
+
static int mlxsw_sp_acl_tcam_region_id_get(struct mlxsw_sp_acl_tcam *tcam,
u16 *p_id)
{
unsigned int patterns_count;
};
-struct mlxsw_sp_acl_tcam_region {
- struct list_head list; /* Member of a TCAM group */
- struct list_head chunk_list; /* List of chunks under this region */
- struct parman *parman;
- struct mlxsw_sp *mlxsw_sp;
- struct mlxsw_sp_acl_tcam_group *group;
- u16 id; /* ACL ID and region ID - they are same */
- char tcam_region_info[MLXSW_REG_PXXX_TCAM_REGION_INFO_LEN];
- struct mlxsw_afk_key_info *key_info;
- struct {
- struct parman_prio parman_prio;
- struct parman_item parman_item;
- struct mlxsw_sp_acl_rule_info *rulei;
- } catchall;
-};
-
struct mlxsw_sp_acl_tcam_chunk {
struct list_head list; /* Member of a TCAM region */
struct rhash_head ht_node; /* Member of a chunk HT */
unsigned int priority; /* Priority within the region and group */
- struct parman_prio parman_prio;
struct mlxsw_sp_acl_tcam_group *group;
struct mlxsw_sp_acl_tcam_region *region;
unsigned int ref_count;
+ unsigned long priv[0];
+ /* priv has to be always the last item */
};
struct mlxsw_sp_acl_tcam_entry {
- struct parman_item parman_item;
struct mlxsw_sp_acl_tcam_chunk *chunk;
+ unsigned long priv[0];
+ /* priv has to be always the last item */
};
static const struct rhashtable_params mlxsw_sp_acl_tcam_chunk_ht_params = {
memcpy(out, elusage, sizeof(*out));
}
-#define MLXSW_SP_ACL_TCAM_REGION_BASE_COUNT 16
-#define MLXSW_SP_ACL_TCAM_REGION_RESIZE_STEP 16
-
static int
mlxsw_sp_acl_tcam_region_alloc(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_acl_tcam_region *region)
int err;
mlxsw_reg_ptar_pack(ptar_pl, MLXSW_REG_PTAR_OP_ALLOC,
+ region->key_type,
MLXSW_SP_ACL_TCAM_REGION_BASE_COUNT,
region->id, region->tcam_region_info);
encodings_count = mlxsw_afk_key_info_blocks_count_get(key_info);
{
char ptar_pl[MLXSW_REG_PTAR_LEN];
- mlxsw_reg_ptar_pack(ptar_pl, MLXSW_REG_PTAR_OP_FREE, 0, region->id,
+ mlxsw_reg_ptar_pack(ptar_pl, MLXSW_REG_PTAR_OP_FREE,
+ region->key_type, 0, region->id,
region->tcam_region_info);
mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptar), ptar_pl);
}
-static int
-mlxsw_sp_acl_tcam_region_resize(struct mlxsw_sp *mlxsw_sp,
- struct mlxsw_sp_acl_tcam_region *region,
- u16 new_size)
-{
- char ptar_pl[MLXSW_REG_PTAR_LEN];
-
- mlxsw_reg_ptar_pack(ptar_pl, MLXSW_REG_PTAR_OP_RESIZE,
- new_size, region->id, region->tcam_region_info);
- return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptar), ptar_pl);
-}
-
static int
mlxsw_sp_acl_tcam_region_enable(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_acl_tcam_region *region)
mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pacl), pacl_pl);
}
-static int
-mlxsw_sp_acl_tcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp,
- struct mlxsw_sp_acl_tcam_region *region,
- unsigned int offset,
- struct mlxsw_sp_acl_rule_info *rulei)
-{
- char ptce2_pl[MLXSW_REG_PTCE2_LEN];
- char *act_set;
- char *mask;
- char *key;
-
- mlxsw_reg_ptce2_pack(ptce2_pl, true, MLXSW_REG_PTCE2_OP_WRITE_WRITE,
- region->tcam_region_info, offset);
- key = mlxsw_reg_ptce2_flex_key_blocks_data(ptce2_pl);
- mask = mlxsw_reg_ptce2_mask_data(ptce2_pl);
- mlxsw_afk_encode(region->key_info, &rulei->values, key, mask);
-
- /* Only the first action set belongs here, the rest is in KVD */
- act_set = mlxsw_afa_block_first_set(rulei->act_block);
- mlxsw_reg_ptce2_flex_action_set_memcpy_to(ptce2_pl, act_set);
-
- return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptce2), ptce2_pl);
-}
-
-static void
-mlxsw_sp_acl_tcam_region_entry_remove(struct mlxsw_sp *mlxsw_sp,
- struct mlxsw_sp_acl_tcam_region *region,
- unsigned int offset)
-{
- char ptce2_pl[MLXSW_REG_PTCE2_LEN];
-
- mlxsw_reg_ptce2_pack(ptce2_pl, false, MLXSW_REG_PTCE2_OP_WRITE_WRITE,
- region->tcam_region_info, offset);
- mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptce2), ptce2_pl);
-}
-
-static int
-mlxsw_sp_acl_tcam_region_entry_activity_get(struct mlxsw_sp *mlxsw_sp,
- struct mlxsw_sp_acl_tcam_region *region,
- unsigned int offset,
- bool *activity)
-{
- char ptce2_pl[MLXSW_REG_PTCE2_LEN];
- int err;
-
- mlxsw_reg_ptce2_pack(ptce2_pl, true, MLXSW_REG_PTCE2_OP_QUERY_CLEAR_ON_READ,
- region->tcam_region_info, offset);
- err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ptce2), ptce2_pl);
- if (err)
- return err;
- *activity = mlxsw_reg_ptce2_a_get(ptce2_pl);
- return 0;
-}
-
-#define MLXSW_SP_ACL_TCAM_CATCHALL_PRIO (~0U)
-
-static int
-mlxsw_sp_acl_tcam_region_catchall_add(struct mlxsw_sp *mlxsw_sp,
- struct mlxsw_sp_acl_tcam_region *region)
-{
- struct parman_prio *parman_prio = ®ion->catchall.parman_prio;
- struct parman_item *parman_item = ®ion->catchall.parman_item;
- struct mlxsw_sp_acl_rule_info *rulei;
- int err;
-
- parman_prio_init(region->parman, parman_prio,
- MLXSW_SP_ACL_TCAM_CATCHALL_PRIO);
- err = parman_item_add(region->parman, parman_prio, parman_item);
- if (err)
- goto err_parman_item_add;
-
- rulei = mlxsw_sp_acl_rulei_create(mlxsw_sp->acl);
- if (IS_ERR(rulei)) {
- err = PTR_ERR(rulei);
- goto err_rulei_create;
- }
-
- err = mlxsw_sp_acl_rulei_act_continue(rulei);
- if (WARN_ON(err))
- goto err_rulei_act_continue;
-
- err = mlxsw_sp_acl_rulei_commit(rulei);
- if (err)
- goto err_rulei_commit;
-
- err = mlxsw_sp_acl_tcam_region_entry_insert(mlxsw_sp, region,
- parman_item->index, rulei);
- region->catchall.rulei = rulei;
- if (err)
- goto err_rule_insert;
-
- return 0;
-
-err_rule_insert:
-err_rulei_commit:
-err_rulei_act_continue:
- mlxsw_sp_acl_rulei_destroy(rulei);
-err_rulei_create:
- parman_item_remove(region->parman, parman_prio, parman_item);
-err_parman_item_add:
- parman_prio_fini(parman_prio);
- return err;
-}
-
-static void
-mlxsw_sp_acl_tcam_region_catchall_del(struct mlxsw_sp *mlxsw_sp,
- struct mlxsw_sp_acl_tcam_region *region)
-{
- struct parman_prio *parman_prio = ®ion->catchall.parman_prio;
- struct parman_item *parman_item = ®ion->catchall.parman_item;
- struct mlxsw_sp_acl_rule_info *rulei = region->catchall.rulei;
-
- mlxsw_sp_acl_tcam_region_entry_remove(mlxsw_sp, region,
- parman_item->index);
- mlxsw_sp_acl_rulei_destroy(rulei);
- parman_item_remove(region->parman, parman_prio, parman_item);
- parman_prio_fini(parman_prio);
-}
-
-static void
-mlxsw_sp_acl_tcam_region_move(struct mlxsw_sp *mlxsw_sp,
- struct mlxsw_sp_acl_tcam_region *region,
- u16 src_offset, u16 dst_offset, u16 size)
-{
- char prcr_pl[MLXSW_REG_PRCR_LEN];
-
- mlxsw_reg_prcr_pack(prcr_pl, MLXSW_REG_PRCR_OP_MOVE,
- region->tcam_region_info, src_offset,
- region->tcam_region_info, dst_offset, size);
- mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(prcr), prcr_pl);
-}
-
-static int mlxsw_sp_acl_tcam_region_parman_resize(void *priv,
- unsigned long new_count)
-{
- struct mlxsw_sp_acl_tcam_region *region = priv;
- struct mlxsw_sp *mlxsw_sp = region->mlxsw_sp;
- u64 max_tcam_rules;
-
- max_tcam_rules = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_TCAM_RULES);
- if (new_count > max_tcam_rules)
- return -EINVAL;
- return mlxsw_sp_acl_tcam_region_resize(mlxsw_sp, region, new_count);
-}
-
-static void mlxsw_sp_acl_tcam_region_parman_move(void *priv,
- unsigned long from_index,
- unsigned long to_index,
- unsigned long count)
-{
- struct mlxsw_sp_acl_tcam_region *region = priv;
- struct mlxsw_sp *mlxsw_sp = region->mlxsw_sp;
-
- mlxsw_sp_acl_tcam_region_move(mlxsw_sp, region,
- from_index, to_index, count);
-}
-
-static const struct parman_ops mlxsw_sp_acl_tcam_region_parman_ops = {
- .base_count = MLXSW_SP_ACL_TCAM_REGION_BASE_COUNT,
- .resize_step = MLXSW_SP_ACL_TCAM_REGION_RESIZE_STEP,
- .resize = mlxsw_sp_acl_tcam_region_parman_resize,
- .move = mlxsw_sp_acl_tcam_region_parman_move,
- .algo = PARMAN_ALGO_TYPE_LSORT,
-};
-
static struct mlxsw_sp_acl_tcam_region *
mlxsw_sp_acl_tcam_region_create(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_acl_tcam *tcam,
struct mlxsw_afk_element_usage *elusage)
{
+ const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
struct mlxsw_afk *afk = mlxsw_sp_acl_afk(mlxsw_sp->acl);
struct mlxsw_sp_acl_tcam_region *region;
int err;
- region = kzalloc(sizeof(*region), GFP_KERNEL);
+ region = kzalloc(sizeof(*region) + ops->region_priv_size, GFP_KERNEL);
if (!region)
return ERR_PTR(-ENOMEM);
INIT_LIST_HEAD(®ion->chunk_list);
region->mlxsw_sp = mlxsw_sp;
- region->parman = parman_create(&mlxsw_sp_acl_tcam_region_parman_ops,
- region);
- if (!region->parman) {
- err = -ENOMEM;
- goto err_parman_create;
- }
-
region->key_info = mlxsw_afk_key_info_get(afk, elusage);
if (IS_ERR(region->key_info)) {
err = PTR_ERR(region->key_info);
if (err)
goto err_region_id_get;
+ region->key_type = ops->key_type;
err = mlxsw_sp_acl_tcam_region_alloc(mlxsw_sp, region);
if (err)
goto err_tcam_region_alloc;
if (err)
goto err_tcam_region_enable;
- err = mlxsw_sp_acl_tcam_region_catchall_add(mlxsw_sp, region);
+ err = ops->region_init(mlxsw_sp, region->priv, region);
if (err)
- goto err_tcam_region_catchall_add;
+ goto err_tcam_region_init;
return region;
-err_tcam_region_catchall_add:
+err_tcam_region_init:
mlxsw_sp_acl_tcam_region_disable(mlxsw_sp, region);
err_tcam_region_enable:
mlxsw_sp_acl_tcam_region_free(mlxsw_sp, region);
err_region_id_get:
mlxsw_afk_key_info_put(region->key_info);
err_key_info_get:
- parman_destroy(region->parman);
-err_parman_create:
kfree(region);
return ERR_PTR(err);
}
mlxsw_sp_acl_tcam_region_destroy(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_acl_tcam_region *region)
{
- mlxsw_sp_acl_tcam_region_catchall_del(mlxsw_sp, region);
+ const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
+
+ ops->region_fini(mlxsw_sp, region->priv);
mlxsw_sp_acl_tcam_region_disable(mlxsw_sp, region);
mlxsw_sp_acl_tcam_region_free(mlxsw_sp, region);
mlxsw_sp_acl_tcam_region_id_put(region->group->tcam, region->id);
mlxsw_afk_key_info_put(region->key_info);
- parman_destroy(region->parman);
kfree(region);
}
unsigned int priority,
struct mlxsw_afk_element_usage *elusage)
{
+ const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
struct mlxsw_sp_acl_tcam_chunk *chunk;
int err;
if (priority == MLXSW_SP_ACL_TCAM_CATCHALL_PRIO)
return ERR_PTR(-EINVAL);
- chunk = kzalloc(sizeof(*chunk), GFP_KERNEL);
+ chunk = kzalloc(sizeof(*chunk) + ops->chunk_priv_size, GFP_KERNEL);
if (!chunk)
return ERR_PTR(-ENOMEM);
chunk->priority = priority;
if (err)
goto err_chunk_assoc;
- parman_prio_init(chunk->region->parman, &chunk->parman_prio, priority);
+ ops->chunk_init(chunk->region->priv, chunk->priv, priority);
err = rhashtable_insert_fast(&group->chunk_ht, &chunk->ht_node,
mlxsw_sp_acl_tcam_chunk_ht_params);
return chunk;
err_rhashtable_insert:
- parman_prio_fini(&chunk->parman_prio);
+ ops->chunk_fini(chunk->priv);
mlxsw_sp_acl_tcam_chunk_deassoc(mlxsw_sp, chunk);
err_chunk_assoc:
kfree(chunk);
mlxsw_sp_acl_tcam_chunk_destroy(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_acl_tcam_chunk *chunk)
{
+ const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
struct mlxsw_sp_acl_tcam_group *group = chunk->group;
rhashtable_remove_fast(&group->chunk_ht, &chunk->ht_node,
mlxsw_sp_acl_tcam_chunk_ht_params);
- parman_prio_fini(&chunk->parman_prio);
+ ops->chunk_fini(chunk->priv);
mlxsw_sp_acl_tcam_chunk_deassoc(mlxsw_sp, chunk);
kfree(chunk);
}
mlxsw_sp_acl_tcam_chunk_destroy(mlxsw_sp, chunk);
}
+static size_t mlxsw_sp_acl_tcam_entry_priv_size(struct mlxsw_sp *mlxsw_sp)
+{
+ const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
+
+ return ops->entry_priv_size;
+}
+
static int mlxsw_sp_acl_tcam_entry_add(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_acl_tcam_group *group,
struct mlxsw_sp_acl_tcam_entry *entry,
struct mlxsw_sp_acl_rule_info *rulei)
{
+ const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
struct mlxsw_sp_acl_tcam_chunk *chunk;
struct mlxsw_sp_acl_tcam_region *region;
int err;
return PTR_ERR(chunk);
region = chunk->region;
- err = parman_item_add(region->parman, &chunk->parman_prio,
- &entry->parman_item);
- if (err)
- goto err_parman_item_add;
- err = mlxsw_sp_acl_tcam_region_entry_insert(mlxsw_sp, region,
- entry->parman_item.index,
- rulei);
+ err = ops->entry_add(mlxsw_sp, region->priv, chunk->priv,
+ entry->priv, rulei);
if (err)
- goto err_rule_insert;
+ goto err_entry_add;
entry->chunk = chunk;
return 0;
-err_rule_insert:
- parman_item_remove(region->parman, &chunk->parman_prio,
- &entry->parman_item);
-err_parman_item_add:
+err_entry_add:
mlxsw_sp_acl_tcam_chunk_put(mlxsw_sp, chunk);
return err;
}
static void mlxsw_sp_acl_tcam_entry_del(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_acl_tcam_entry *entry)
{
+ const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
struct mlxsw_sp_acl_tcam_chunk *chunk = entry->chunk;
struct mlxsw_sp_acl_tcam_region *region = chunk->region;
- mlxsw_sp_acl_tcam_region_entry_remove(mlxsw_sp, region,
- entry->parman_item.index);
- parman_item_remove(region->parman, &chunk->parman_prio,
- &entry->parman_item);
+ ops->entry_del(mlxsw_sp, region->priv, chunk->priv, entry->priv);
mlxsw_sp_acl_tcam_chunk_put(mlxsw_sp, chunk);
}
struct mlxsw_sp_acl_tcam_entry *entry,
bool *activity)
{
+ const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
struct mlxsw_sp_acl_tcam_chunk *chunk = entry->chunk;
struct mlxsw_sp_acl_tcam_region *region = chunk->region;
- return mlxsw_sp_acl_tcam_region_entry_activity_get(mlxsw_sp, region,
- entry->parman_item.index,
- activity);
+ return ops->entry_activity_get(mlxsw_sp, region->priv,
+ entry->priv, activity);
}
static const enum mlxsw_afk_element mlxsw_sp_acl_tcam_pattern_ipv4[] = {
MLXSW_AFK_ELEMENT_SRC_SYS_PORT,
- MLXSW_AFK_ELEMENT_DMAC,
- MLXSW_AFK_ELEMENT_SMAC,
+ MLXSW_AFK_ELEMENT_DMAC_32_47,
+ MLXSW_AFK_ELEMENT_DMAC_0_31,
+ MLXSW_AFK_ELEMENT_SMAC_32_47,
+ MLXSW_AFK_ELEMENT_SMAC_0_31,
MLXSW_AFK_ELEMENT_ETHERTYPE,
MLXSW_AFK_ELEMENT_IP_PROTO,
- MLXSW_AFK_ELEMENT_SRC_IP4,
- MLXSW_AFK_ELEMENT_DST_IP4,
+ MLXSW_AFK_ELEMENT_SRC_IP_0_31,
+ MLXSW_AFK_ELEMENT_DST_IP_0_31,
MLXSW_AFK_ELEMENT_DST_L4_PORT,
MLXSW_AFK_ELEMENT_SRC_L4_PORT,
MLXSW_AFK_ELEMENT_VID,
static const enum mlxsw_afk_element mlxsw_sp_acl_tcam_pattern_ipv6[] = {
MLXSW_AFK_ELEMENT_ETHERTYPE,
MLXSW_AFK_ELEMENT_IP_PROTO,
- MLXSW_AFK_ELEMENT_SRC_IP6_HI,
- MLXSW_AFK_ELEMENT_SRC_IP6_LO,
- MLXSW_AFK_ELEMENT_DST_IP6_HI,
- MLXSW_AFK_ELEMENT_DST_IP6_LO,
+ MLXSW_AFK_ELEMENT_SRC_IP_96_127,
+ MLXSW_AFK_ELEMENT_SRC_IP_64_95,
+ MLXSW_AFK_ELEMENT_SRC_IP_32_63,
+ MLXSW_AFK_ELEMENT_SRC_IP_0_31,
+ MLXSW_AFK_ELEMENT_DST_IP_96_127,
+ MLXSW_AFK_ELEMENT_DST_IP_64_95,
+ MLXSW_AFK_ELEMENT_DST_IP_32_63,
+ MLXSW_AFK_ELEMENT_DST_IP_0_31,
MLXSW_AFK_ELEMENT_DST_L4_PORT,
MLXSW_AFK_ELEMENT_SRC_L4_PORT,
};
static int
mlxsw_sp_acl_tcam_flower_ruleset_add(struct mlxsw_sp *mlxsw_sp,
- void *priv, void *ruleset_priv)
+ struct mlxsw_sp_acl_tcam *tcam,
+ void *ruleset_priv)
{
struct mlxsw_sp_acl_tcam_flower_ruleset *ruleset = ruleset_priv;
- struct mlxsw_sp_acl_tcam *tcam = priv;
return mlxsw_sp_acl_tcam_group_add(mlxsw_sp, tcam, &ruleset->group,
mlxsw_sp_acl_tcam_patterns,
return mlxsw_sp_acl_tcam_group_id(&ruleset->group);
}
+static size_t mlxsw_sp_acl_tcam_flower_rule_priv_size(struct mlxsw_sp *mlxsw_sp)
+{
+ return sizeof(struct mlxsw_sp_acl_tcam_flower_rule) +
+ mlxsw_sp_acl_tcam_entry_priv_size(mlxsw_sp);
+}
+
static int
mlxsw_sp_acl_tcam_flower_rule_add(struct mlxsw_sp *mlxsw_sp,
void *ruleset_priv, void *rule_priv,
.ruleset_bind = mlxsw_sp_acl_tcam_flower_ruleset_bind,
.ruleset_unbind = mlxsw_sp_acl_tcam_flower_ruleset_unbind,
.ruleset_group_id = mlxsw_sp_acl_tcam_flower_ruleset_group_id,
- .rule_priv_size = sizeof(struct mlxsw_sp_acl_tcam_flower_rule),
+ .rule_priv_size = mlxsw_sp_acl_tcam_flower_rule_priv_size,
.rule_add = mlxsw_sp_acl_tcam_flower_rule_add,
.rule_del = mlxsw_sp_acl_tcam_flower_rule_del,
.rule_activity_get = mlxsw_sp_acl_tcam_flower_rule_activity_get,
[MLXSW_SP_ACL_PROFILE_FLOWER] = &mlxsw_sp_acl_tcam_flower_ops,
};
-static const struct mlxsw_sp_acl_profile_ops *
+const struct mlxsw_sp_acl_profile_ops *
mlxsw_sp_acl_tcam_profile_ops(struct mlxsw_sp *mlxsw_sp,
enum mlxsw_sp_acl_profile profile)
{
return NULL;
return ops;
}
-
-const struct mlxsw_sp_acl_ops mlxsw_sp_acl_tcam_ops = {
- .priv_size = sizeof(struct mlxsw_sp_acl_tcam),
- .init = mlxsw_sp_acl_tcam_init,
- .fini = mlxsw_sp_acl_tcam_fini,
- .profile_ops = mlxsw_sp_acl_tcam_profile_ops,
-};
--- /dev/null
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
+ * Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017-2018 Jiri Pirko <jiri@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ * contributors may be used to endorse or promote products derived from
+ * this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _MLXSW_SPECTRUM_ACL_TCAM_H
+#define _MLXSW_SPECTRUM_ACL_TCAM_H
+
+#include <linux/list.h>
+#include <linux/parman.h>
+
+#include "reg.h"
+#include "spectrum.h"
+#include "core_acl_flex_keys.h"
+
+struct mlxsw_sp_acl_tcam {
+ unsigned long *used_regions; /* bit array */
+ unsigned int max_regions;
+ unsigned long *used_groups; /* bit array */
+ unsigned int max_groups;
+ unsigned int max_group_size;
+ unsigned long priv[0];
+ /* priv has to be always the last item */
+};
+
+size_t mlxsw_sp_acl_tcam_priv_size(struct mlxsw_sp *mlxsw_sp);
+int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_acl_tcam *tcam);
+void mlxsw_sp_acl_tcam_fini(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_acl_tcam *tcam);
+int mlxsw_sp_acl_tcam_priority_get(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_acl_rule_info *rulei,
+ u32 *priority, bool fillup_priority);
+
+struct mlxsw_sp_acl_profile_ops {
+ size_t ruleset_priv_size;
+ int (*ruleset_add)(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_acl_tcam *tcam, void *ruleset_priv);
+ void (*ruleset_del)(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv);
+ int (*ruleset_bind)(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv,
+ struct mlxsw_sp_port *mlxsw_sp_port,
+ bool ingress);
+ void (*ruleset_unbind)(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv,
+ struct mlxsw_sp_port *mlxsw_sp_port,
+ bool ingress);
+ u16 (*ruleset_group_id)(void *ruleset_priv);
+ size_t (*rule_priv_size)(struct mlxsw_sp *mlxsw_sp);
+ int (*rule_add)(struct mlxsw_sp *mlxsw_sp,
+ void *ruleset_priv, void *rule_priv,
+ struct mlxsw_sp_acl_rule_info *rulei);
+ void (*rule_del)(struct mlxsw_sp *mlxsw_sp, void *rule_priv);
+ int (*rule_activity_get)(struct mlxsw_sp *mlxsw_sp, void *rule_priv,
+ bool *activity);
+};
+
+const struct mlxsw_sp_acl_profile_ops *
+mlxsw_sp_acl_tcam_profile_ops(struct mlxsw_sp *mlxsw_sp,
+ enum mlxsw_sp_acl_profile profile);
+
+#define MLXSW_SP_ACL_TCAM_REGION_BASE_COUNT 16
+#define MLXSW_SP_ACL_TCAM_REGION_RESIZE_STEP 16
+
+#define MLXSW_SP_ACL_TCAM_CATCHALL_PRIO (~0U)
+
+struct mlxsw_sp_acl_tcam_group;
+
+struct mlxsw_sp_acl_tcam_region {
+ struct list_head list; /* Member of a TCAM group */
+ struct list_head chunk_list; /* List of chunks under this region */
+ struct mlxsw_sp_acl_tcam_group *group;
+ enum mlxsw_reg_ptar_key_type key_type;
+ u16 id; /* ACL ID and region ID - they are same */
+ char tcam_region_info[MLXSW_REG_PXXX_TCAM_REGION_INFO_LEN];
+ struct mlxsw_afk_key_info *key_info;
+ struct mlxsw_sp *mlxsw_sp;
+ unsigned long priv[0];
+ /* priv has to be always the last item */
+};
+
+struct mlxsw_sp_acl_ctcam_region {
+ struct parman *parman;
+ struct mlxsw_sp_acl_tcam_region *region;
+};
+
+struct mlxsw_sp_acl_ctcam_chunk {
+ struct parman_prio parman_prio;
+};
+
+struct mlxsw_sp_acl_ctcam_entry {
+ struct parman_item parman_item;
+};
+
+int mlxsw_sp_acl_ctcam_region_init(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_acl_ctcam_region *cregion,
+ struct mlxsw_sp_acl_tcam_region *region);
+void mlxsw_sp_acl_ctcam_region_fini(struct mlxsw_sp_acl_ctcam_region *cregion);
+void mlxsw_sp_acl_ctcam_chunk_init(struct mlxsw_sp_acl_ctcam_region *cregion,
+ struct mlxsw_sp_acl_ctcam_chunk *cchunk,
+ unsigned int priority);
+void mlxsw_sp_acl_ctcam_chunk_fini(struct mlxsw_sp_acl_ctcam_chunk *cchunk);
+int mlxsw_sp_acl_ctcam_entry_add(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_acl_ctcam_region *cregion,
+ struct mlxsw_sp_acl_ctcam_chunk *cchunk,
+ struct mlxsw_sp_acl_ctcam_entry *centry,
+ struct mlxsw_sp_acl_rule_info *rulei,
+ bool fillup_priority);
+void mlxsw_sp_acl_ctcam_entry_del(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_acl_ctcam_region *cregion,
+ struct mlxsw_sp_acl_ctcam_chunk *cchunk,
+ struct mlxsw_sp_acl_ctcam_entry *centry);
+static inline unsigned int
+mlxsw_sp_acl_ctcam_entry_offset(struct mlxsw_sp_acl_ctcam_entry *centry)
+{
+ return centry->parman_item.index;
+}
+
+#endif
FLOW_DISSECTOR_KEY_IPV4_ADDRS,
f->mask);
- mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_SRC_IP4,
- ntohl(key->src), ntohl(mask->src));
- mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_DST_IP4,
- ntohl(key->dst), ntohl(mask->dst));
+ mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_0_31,
+ (char *) &key->src,
+ (char *) &mask->src, 4);
+ mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_0_31,
+ (char *) &key->dst,
+ (char *) &mask->dst, 4);
}
static void mlxsw_sp_flower_parse_ipv6(struct mlxsw_sp_acl_rule_info *rulei,
skb_flow_dissector_target(f->dissector,
FLOW_DISSECTOR_KEY_IPV6_ADDRS,
f->mask);
- size_t addr_half_size = sizeof(key->src) / 2;
-
- mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP6_HI,
- &key->src.s6_addr[0],
- &mask->src.s6_addr[0],
- addr_half_size);
- mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP6_LO,
- &key->src.s6_addr[addr_half_size],
- &mask->src.s6_addr[addr_half_size],
- addr_half_size);
- mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP6_HI,
- &key->dst.s6_addr[0],
- &mask->dst.s6_addr[0],
- addr_half_size);
- mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP6_LO,
- &key->dst.s6_addr[addr_half_size],
- &mask->dst.s6_addr[addr_half_size],
- addr_half_size);
+
+ mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_96_127,
+ &key->src.s6_addr[0x0],
+ &mask->src.s6_addr[0x0], 4);
+ mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_64_95,
+ &key->src.s6_addr[0x4],
+ &mask->src.s6_addr[0x4], 4);
+ mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_32_63,
+ &key->src.s6_addr[0x8],
+ &mask->src.s6_addr[0x8], 4);
+ mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_0_31,
+ &key->src.s6_addr[0xC],
+ &mask->src.s6_addr[0xC], 4);
+ mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_96_127,
+ &key->dst.s6_addr[0x0],
+ &mask->dst.s6_addr[0x0], 4);
+ mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_64_95,
+ &key->dst.s6_addr[0x4],
+ &mask->dst.s6_addr[0x4], 4);
+ mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_32_63,
+ &key->dst.s6_addr[0x8],
+ &mask->dst.s6_addr[0x8], 4);
+ mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_0_31,
+ &key->dst.s6_addr[0xC],
+ &mask->dst.s6_addr[0xC], 4);
}
static int mlxsw_sp_flower_parse_ports(struct mlxsw_sp *mlxsw_sp,
f->mask);
mlxsw_sp_acl_rulei_keymask_buf(rulei,
- MLXSW_AFK_ELEMENT_DMAC,
- key->dst, mask->dst,
- sizeof(key->dst));
+ MLXSW_AFK_ELEMENT_DMAC_32_47,
+ key->dst, mask->dst, 2);
+ mlxsw_sp_acl_rulei_keymask_buf(rulei,
+ MLXSW_AFK_ELEMENT_DMAC_0_31,
+ key->dst + 2, mask->dst + 2, 4);
+ mlxsw_sp_acl_rulei_keymask_buf(rulei,
+ MLXSW_AFK_ELEMENT_SMAC_32_47,
+ key->src, mask->src, 2);
mlxsw_sp_acl_rulei_keymask_buf(rulei,
- MLXSW_AFK_ELEMENT_SMAC,
- key->src, mask->src,
- sizeof(key->src));
+ MLXSW_AFK_ELEMENT_SMAC_0_31,
+ key->src + 2, mask->src + 2, 4);
}
if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) {
/*
* drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
- * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com>
+ * Copyright (c) 2016-2018 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2016-2018 Jiri Pirko <jiri@mellanox.com>
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
*/
#include <linux/kernel.h>
-#include <linux/bitops.h>
+#include <linux/slab.h>
#include "spectrum.h"
-#define MLXSW_SP_KVDL_SINGLE_BASE 0
-#define MLXSW_SP_KVDL_SINGLE_SIZE 16384
-#define MLXSW_SP_KVDL_SINGLE_END \
- (MLXSW_SP_KVDL_SINGLE_SIZE + MLXSW_SP_KVDL_SINGLE_BASE - 1)
-
-#define MLXSW_SP_KVDL_CHUNKS_BASE \
- (MLXSW_SP_KVDL_SINGLE_BASE + MLXSW_SP_KVDL_SINGLE_SIZE)
-#define MLXSW_SP_KVDL_CHUNKS_SIZE 49152
-#define MLXSW_SP_KVDL_CHUNKS_END \
- (MLXSW_SP_KVDL_CHUNKS_SIZE + MLXSW_SP_KVDL_CHUNKS_BASE - 1)
-
-#define MLXSW_SP_KVDL_LARGE_CHUNKS_BASE \
- (MLXSW_SP_KVDL_CHUNKS_BASE + MLXSW_SP_KVDL_CHUNKS_SIZE)
-#define MLXSW_SP_KVDL_LARGE_CHUNKS_SIZE \
- (MLXSW_SP_KVD_LINEAR_SIZE - MLXSW_SP_KVDL_LARGE_CHUNKS_BASE)
-#define MLXSW_SP_KVDL_LARGE_CHUNKS_END \
- (MLXSW_SP_KVDL_LARGE_CHUNKS_SIZE + MLXSW_SP_KVDL_LARGE_CHUNKS_BASE - 1)
-
-#define MLXSW_SP_KVDL_SINGLE_ALLOC_SIZE 1
-#define MLXSW_SP_KVDL_CHUNKS_ALLOC_SIZE 32
-#define MLXSW_SP_KVDL_LARGE_CHUNKS_ALLOC_SIZE 512
-
-struct mlxsw_sp_kvdl_part_info {
- unsigned int part_index;
- unsigned int start_index;
- unsigned int end_index;
- unsigned int alloc_size;
- enum mlxsw_sp_resource_id resource_id;
-};
-
-enum mlxsw_sp_kvdl_part_id {
- MLXSW_SP_KVDL_PART_ID_SINGLE,
- MLXSW_SP_KVDL_PART_ID_CHUNKS,
- MLXSW_SP_KVDL_PART_ID_LARGE_CHUNKS,
-};
-
-#define MLXSW_SP_KVDL_PART_INFO(id) \
-[MLXSW_SP_KVDL_PART_ID_##id] = { \
- .start_index = MLXSW_SP_KVDL_##id##_BASE, \
- .end_index = MLXSW_SP_KVDL_##id##_END, \
- .alloc_size = MLXSW_SP_KVDL_##id##_ALLOC_SIZE, \
- .resource_id = MLXSW_SP_RESOURCE_KVD_LINEAR_##id, \
-}
-
-static const struct mlxsw_sp_kvdl_part_info mlxsw_sp_kvdl_parts_info[] = {
- MLXSW_SP_KVDL_PART_INFO(SINGLE),
- MLXSW_SP_KVDL_PART_INFO(CHUNKS),
- MLXSW_SP_KVDL_PART_INFO(LARGE_CHUNKS),
-};
-
-#define MLXSW_SP_KVDL_PARTS_INFO_LEN ARRAY_SIZE(mlxsw_sp_kvdl_parts_info)
-
-struct mlxsw_sp_kvdl_part {
- struct mlxsw_sp_kvdl_part_info info;
- unsigned long usage[0]; /* Entries */
-};
-
struct mlxsw_sp_kvdl {
- struct mlxsw_sp_kvdl_part *parts[MLXSW_SP_KVDL_PARTS_INFO_LEN];
+ const struct mlxsw_sp_kvdl_ops *kvdl_ops;
+ unsigned long priv[0];
+ /* priv has to be always the last item */
};
-static struct mlxsw_sp_kvdl_part *
-mlxsw_sp_kvdl_alloc_size_part(struct mlxsw_sp_kvdl *kvdl,
- unsigned int alloc_size)
-{
- struct mlxsw_sp_kvdl_part *part, *min_part = NULL;
- int i;
-
- for (i = 0; i < MLXSW_SP_KVDL_PARTS_INFO_LEN; i++) {
- part = kvdl->parts[i];
- if (alloc_size <= part->info.alloc_size &&
- (!min_part ||
- part->info.alloc_size <= min_part->info.alloc_size))
- min_part = part;
- }
-
- return min_part ?: ERR_PTR(-ENOBUFS);
-}
-
-static struct mlxsw_sp_kvdl_part *
-mlxsw_sp_kvdl_index_part(struct mlxsw_sp_kvdl *kvdl, u32 kvdl_index)
-{
- struct mlxsw_sp_kvdl_part *part;
- int i;
-
- for (i = 0; i < MLXSW_SP_KVDL_PARTS_INFO_LEN; i++) {
- part = kvdl->parts[i];
- if (kvdl_index >= part->info.start_index &&
- kvdl_index <= part->info.end_index)
- return part;
- }
-
- return ERR_PTR(-EINVAL);
-}
-
-static u32
-mlxsw_sp_entry_index_kvdl_index(const struct mlxsw_sp_kvdl_part_info *info,
- unsigned int entry_index)
-{
- return info->start_index + entry_index * info->alloc_size;
-}
-
-static unsigned int
-mlxsw_sp_kvdl_index_entry_index(const struct mlxsw_sp_kvdl_part_info *info,
- u32 kvdl_index)
-{
- return (kvdl_index - info->start_index) / info->alloc_size;
-}
-
-static int mlxsw_sp_kvdl_part_alloc(struct mlxsw_sp_kvdl_part *part,
- u32 *p_kvdl_index)
-{
- const struct mlxsw_sp_kvdl_part_info *info = &part->info;
- unsigned int entry_index, nr_entries;
-
- nr_entries = (info->end_index - info->start_index + 1) /
- info->alloc_size;
- entry_index = find_first_zero_bit(part->usage, nr_entries);
- if (entry_index == nr_entries)
- return -ENOBUFS;
- __set_bit(entry_index, part->usage);
-
- *p_kvdl_index = mlxsw_sp_entry_index_kvdl_index(info, entry_index);
-
- return 0;
-}
-
-static void mlxsw_sp_kvdl_part_free(struct mlxsw_sp_kvdl_part *part,
- u32 kvdl_index)
-{
- const struct mlxsw_sp_kvdl_part_info *info = &part->info;
- unsigned int entry_index;
-
- entry_index = mlxsw_sp_kvdl_index_entry_index(info, kvdl_index);
- __clear_bit(entry_index, part->usage);
-}
-
-int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int entry_count,
- u32 *p_entry_index)
-{
- struct mlxsw_sp_kvdl_part *part;
-
- /* Find partition with smallest allocation size satisfying the
- * requested size.
- */
- part = mlxsw_sp_kvdl_alloc_size_part(mlxsw_sp->kvdl, entry_count);
- if (IS_ERR(part))
- return PTR_ERR(part);
-
- return mlxsw_sp_kvdl_part_alloc(part, p_entry_index);
-}
-
-void mlxsw_sp_kvdl_free(struct mlxsw_sp *mlxsw_sp, int entry_index)
-{
- struct mlxsw_sp_kvdl_part *part;
-
- part = mlxsw_sp_kvdl_index_part(mlxsw_sp->kvdl, entry_index);
- if (IS_ERR(part))
- return;
- mlxsw_sp_kvdl_part_free(part, entry_index);
-}
-
-int mlxsw_sp_kvdl_alloc_size_query(struct mlxsw_sp *mlxsw_sp,
- unsigned int entry_count,
- unsigned int *p_alloc_size)
-{
- struct mlxsw_sp_kvdl_part *part;
-
- part = mlxsw_sp_kvdl_alloc_size_part(mlxsw_sp->kvdl, entry_count);
- if (IS_ERR(part))
- return PTR_ERR(part);
-
- *p_alloc_size = part->info.alloc_size;
-
- return 0;
-}
-
-static void mlxsw_sp_kvdl_part_update(struct mlxsw_sp_kvdl_part *part,
- struct mlxsw_sp_kvdl_part *part_prev,
- unsigned int size)
-{
-
- if (!part_prev) {
- part->info.end_index = size - 1;
- } else {
- part->info.start_index = part_prev->info.end_index + 1;
- part->info.end_index = part->info.start_index + size - 1;
- }
-}
-
-static struct mlxsw_sp_kvdl_part *
-mlxsw_sp_kvdl_part_init(struct mlxsw_sp *mlxsw_sp,
- const struct mlxsw_sp_kvdl_part_info *info,
- struct mlxsw_sp_kvdl_part *part_prev)
+int mlxsw_sp_kvdl_init(struct mlxsw_sp *mlxsw_sp)
{
- struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
- struct mlxsw_sp_kvdl_part *part;
- bool need_update = true;
- unsigned int nr_entries;
- size_t usage_size;
- u64 resource_size;
+ const struct mlxsw_sp_kvdl_ops *kvdl_ops = mlxsw_sp->kvdl_ops;
+ struct mlxsw_sp_kvdl *kvdl;
int err;
- err = devlink_resource_size_get(devlink, info->resource_id,
- &resource_size);
- if (err) {
- need_update = false;
- resource_size = info->end_index - info->start_index + 1;
- }
-
- nr_entries = div_u64(resource_size, info->alloc_size);
- usage_size = BITS_TO_LONGS(nr_entries) * sizeof(unsigned long);
- part = kzalloc(sizeof(*part) + usage_size, GFP_KERNEL);
- if (!part)
- return ERR_PTR(-ENOMEM);
-
- memcpy(&part->info, info, sizeof(part->info));
-
- if (need_update)
- mlxsw_sp_kvdl_part_update(part, part_prev, resource_size);
- return part;
-}
-
-static void mlxsw_sp_kvdl_part_fini(struct mlxsw_sp_kvdl_part *part)
-{
- kfree(part);
-}
-
-static int mlxsw_sp_kvdl_parts_init(struct mlxsw_sp *mlxsw_sp)
-{
- struct mlxsw_sp_kvdl *kvdl = mlxsw_sp->kvdl;
- const struct mlxsw_sp_kvdl_part_info *info;
- struct mlxsw_sp_kvdl_part *part_prev = NULL;
- int err, i;
+ kvdl = kzalloc(sizeof(*mlxsw_sp->kvdl) + kvdl_ops->priv_size,
+ GFP_KERNEL);
+ if (!kvdl)
+ return -ENOMEM;
+ kvdl->kvdl_ops = kvdl_ops;
+ mlxsw_sp->kvdl = kvdl;
- for (i = 0; i < MLXSW_SP_KVDL_PARTS_INFO_LEN; i++) {
- info = &mlxsw_sp_kvdl_parts_info[i];
- kvdl->parts[i] = mlxsw_sp_kvdl_part_init(mlxsw_sp, info,
- part_prev);
- if (IS_ERR(kvdl->parts[i])) {
- err = PTR_ERR(kvdl->parts[i]);
- goto err_kvdl_part_init;
- }
- part_prev = kvdl->parts[i];
- }
+ err = kvdl_ops->init(mlxsw_sp, kvdl->priv);
+ if (err)
+ goto err_init;
return 0;
-err_kvdl_part_init:
- for (i--; i >= 0; i--)
- mlxsw_sp_kvdl_part_fini(kvdl->parts[i]);
+err_init:
+ kfree(kvdl);
return err;
}
-static void mlxsw_sp_kvdl_parts_fini(struct mlxsw_sp *mlxsw_sp)
+void mlxsw_sp_kvdl_fini(struct mlxsw_sp *mlxsw_sp)
{
struct mlxsw_sp_kvdl *kvdl = mlxsw_sp->kvdl;
- int i;
-
- for (i = 0; i < MLXSW_SP_KVDL_PARTS_INFO_LEN; i++)
- mlxsw_sp_kvdl_part_fini(kvdl->parts[i]);
-}
-
-static u64 mlxsw_sp_kvdl_part_occ(struct mlxsw_sp_kvdl_part *part)
-{
- const struct mlxsw_sp_kvdl_part_info *info = &part->info;
- unsigned int nr_entries;
- int bit = -1;
- u64 occ = 0;
-
- nr_entries = (info->end_index -
- info->start_index + 1) /
- info->alloc_size;
- while ((bit = find_next_bit(part->usage, nr_entries, bit + 1))
- < nr_entries)
- occ += info->alloc_size;
- return occ;
-}
-
-static u64 mlxsw_sp_kvdl_occ_get(void *priv)
-{
- const struct mlxsw_sp *mlxsw_sp = priv;
- u64 occ = 0;
- int i;
-
- for (i = 0; i < MLXSW_SP_KVDL_PARTS_INFO_LEN; i++)
- occ += mlxsw_sp_kvdl_part_occ(mlxsw_sp->kvdl->parts[i]);
-
- return occ;
-}
-
-static u64 mlxsw_sp_kvdl_single_occ_get(void *priv)
-{
- const struct mlxsw_sp *mlxsw_sp = priv;
- struct mlxsw_sp_kvdl_part *part;
-
- part = mlxsw_sp->kvdl->parts[MLXSW_SP_KVDL_PART_ID_SINGLE];
- return mlxsw_sp_kvdl_part_occ(part);
-}
-
-static u64 mlxsw_sp_kvdl_chunks_occ_get(void *priv)
-{
- const struct mlxsw_sp *mlxsw_sp = priv;
- struct mlxsw_sp_kvdl_part *part;
-
- part = mlxsw_sp->kvdl->parts[MLXSW_SP_KVDL_PART_ID_CHUNKS];
- return mlxsw_sp_kvdl_part_occ(part);
-}
-
-static u64 mlxsw_sp_kvdl_large_chunks_occ_get(void *priv)
-{
- const struct mlxsw_sp *mlxsw_sp = priv;
- struct mlxsw_sp_kvdl_part *part;
- part = mlxsw_sp->kvdl->parts[MLXSW_SP_KVDL_PART_ID_LARGE_CHUNKS];
- return mlxsw_sp_kvdl_part_occ(part);
+ kvdl->kvdl_ops->fini(mlxsw_sp, kvdl->priv);
+ kfree(kvdl);
}
-int mlxsw_sp_kvdl_resources_register(struct mlxsw_core *mlxsw_core)
+int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp,
+ enum mlxsw_sp_kvdl_entry_type type,
+ unsigned int entry_count, u32 *p_entry_index)
{
- struct devlink *devlink = priv_to_devlink(mlxsw_core);
- static struct devlink_resource_size_params size_params;
- u32 kvdl_max_size;
- int err;
-
- kvdl_max_size = MLXSW_CORE_RES_GET(mlxsw_core, KVD_SIZE) -
- MLXSW_CORE_RES_GET(mlxsw_core, KVD_SINGLE_MIN_SIZE) -
- MLXSW_CORE_RES_GET(mlxsw_core, KVD_DOUBLE_MIN_SIZE);
-
- devlink_resource_size_params_init(&size_params, 0, kvdl_max_size,
- MLXSW_SP_KVDL_SINGLE_ALLOC_SIZE,
- DEVLINK_RESOURCE_UNIT_ENTRY);
- err = devlink_resource_register(devlink, MLXSW_SP_RESOURCE_NAME_KVD_LINEAR_SINGLES,
- MLXSW_SP_KVDL_SINGLE_SIZE,
- MLXSW_SP_RESOURCE_KVD_LINEAR_SINGLE,
- MLXSW_SP_RESOURCE_KVD_LINEAR,
- &size_params);
- if (err)
- return err;
-
- devlink_resource_size_params_init(&size_params, 0, kvdl_max_size,
- MLXSW_SP_KVDL_CHUNKS_ALLOC_SIZE,
- DEVLINK_RESOURCE_UNIT_ENTRY);
- err = devlink_resource_register(devlink, MLXSW_SP_RESOURCE_NAME_KVD_LINEAR_CHUNKS,
- MLXSW_SP_KVDL_CHUNKS_SIZE,
- MLXSW_SP_RESOURCE_KVD_LINEAR_CHUNKS,
- MLXSW_SP_RESOURCE_KVD_LINEAR,
- &size_params);
- if (err)
- return err;
+ struct mlxsw_sp_kvdl *kvdl = mlxsw_sp->kvdl;
- devlink_resource_size_params_init(&size_params, 0, kvdl_max_size,
- MLXSW_SP_KVDL_LARGE_CHUNKS_ALLOC_SIZE,
- DEVLINK_RESOURCE_UNIT_ENTRY);
- err = devlink_resource_register(devlink, MLXSW_SP_RESOURCE_NAME_KVD_LINEAR_LARGE_CHUNKS,
- MLXSW_SP_KVDL_LARGE_CHUNKS_SIZE,
- MLXSW_SP_RESOURCE_KVD_LINEAR_LARGE_CHUNKS,
- MLXSW_SP_RESOURCE_KVD_LINEAR,
- &size_params);
- return err;
+ return kvdl->kvdl_ops->alloc(mlxsw_sp, kvdl->priv, type,
+ entry_count, p_entry_index);
}
-int mlxsw_sp_kvdl_init(struct mlxsw_sp *mlxsw_sp)
+void mlxsw_sp_kvdl_free(struct mlxsw_sp *mlxsw_sp,
+ enum mlxsw_sp_kvdl_entry_type type,
+ unsigned int entry_count, int entry_index)
{
- struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
- struct mlxsw_sp_kvdl *kvdl;
- int err;
-
- kvdl = kzalloc(sizeof(*mlxsw_sp->kvdl), GFP_KERNEL);
- if (!kvdl)
- return -ENOMEM;
- mlxsw_sp->kvdl = kvdl;
-
- err = mlxsw_sp_kvdl_parts_init(mlxsw_sp);
- if (err)
- goto err_kvdl_parts_init;
-
- devlink_resource_occ_get_register(devlink,
- MLXSW_SP_RESOURCE_KVD_LINEAR,
- mlxsw_sp_kvdl_occ_get,
- mlxsw_sp);
- devlink_resource_occ_get_register(devlink,
- MLXSW_SP_RESOURCE_KVD_LINEAR_SINGLE,
- mlxsw_sp_kvdl_single_occ_get,
- mlxsw_sp);
- devlink_resource_occ_get_register(devlink,
- MLXSW_SP_RESOURCE_KVD_LINEAR_CHUNKS,
- mlxsw_sp_kvdl_chunks_occ_get,
- mlxsw_sp);
- devlink_resource_occ_get_register(devlink,
- MLXSW_SP_RESOURCE_KVD_LINEAR_LARGE_CHUNKS,
- mlxsw_sp_kvdl_large_chunks_occ_get,
- mlxsw_sp);
-
- return 0;
+ struct mlxsw_sp_kvdl *kvdl = mlxsw_sp->kvdl;
-err_kvdl_parts_init:
- kfree(mlxsw_sp->kvdl);
- return err;
+ kvdl->kvdl_ops->free(mlxsw_sp, kvdl->priv, type,
+ entry_count, entry_index);
}
-void mlxsw_sp_kvdl_fini(struct mlxsw_sp *mlxsw_sp)
+int mlxsw_sp_kvdl_alloc_count_query(struct mlxsw_sp *mlxsw_sp,
+ enum mlxsw_sp_kvdl_entry_type type,
+ unsigned int entry_count,
+ unsigned int *p_alloc_count)
{
- struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
+ struct mlxsw_sp_kvdl *kvdl = mlxsw_sp->kvdl;
- devlink_resource_occ_get_unregister(devlink,
- MLXSW_SP_RESOURCE_KVD_LINEAR_LARGE_CHUNKS);
- devlink_resource_occ_get_unregister(devlink,
- MLXSW_SP_RESOURCE_KVD_LINEAR_CHUNKS);
- devlink_resource_occ_get_unregister(devlink,
- MLXSW_SP_RESOURCE_KVD_LINEAR_SINGLE);
- devlink_resource_occ_get_unregister(devlink,
- MLXSW_SP_RESOURCE_KVD_LINEAR);
- mlxsw_sp_kvdl_parts_fini(mlxsw_sp);
- kfree(mlxsw_sp->kvdl);
+ return kvdl->kvdl_ops->alloc_size_query(mlxsw_sp, kvdl->priv, type,
+ entry_count, p_alloc_count);
}
struct mlxsw_sp_mr *mr = mlxsw_sp->mr;
cancel_delayed_work_sync(&mr->stats_update_dw);
- mr->mr_ops->fini(mr->priv);
+ mr->mr_ops->fini(mlxsw_sp, mr->priv);
kfree(mr);
}
MLXSW_SP_MR_ROUTE_ACTION_TRAP_AND_FORWARD,
};
-enum mlxsw_sp_mr_route_prio {
- MLXSW_SP_MR_ROUTE_PRIO_SG,
- MLXSW_SP_MR_ROUTE_PRIO_STARG,
- MLXSW_SP_MR_ROUTE_PRIO_CATCHALL,
- __MLXSW_SP_MR_ROUTE_PRIO_MAX
-};
-
-#define MLXSW_SP_MR_ROUTE_PRIO_MAX (__MLXSW_SP_MR_ROUTE_PRIO_MAX - 1)
-
struct mlxsw_sp_mr_route_key {
int vrid;
enum mlxsw_sp_l3proto proto;
u16 erif_index);
void (*route_destroy)(struct mlxsw_sp *mlxsw_sp, void *priv,
void *route_priv);
- void (*fini)(void *priv);
+ void (*fini)(struct mlxsw_sp *mlxsw_sp, void *priv);
};
struct mlxsw_sp_mr;
/*
* drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved.
* Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
+ * Copyright (c) 2018 Jiri Pirko <jiri@mellanox.com>
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/netdevice.h>
-#include <linux/parman.h>
#include "spectrum_mr_tcam.h"
#include "reg.h"
#include "core_acl_flex_actions.h"
#include "spectrum_mr.h"
-struct mlxsw_sp_mr_tcam_region {
- struct mlxsw_sp *mlxsw_sp;
- enum mlxsw_reg_rtar_key_type rtar_key_type;
- struct parman *parman;
- struct parman_prio *parman_prios;
-};
-
struct mlxsw_sp_mr_tcam {
- struct mlxsw_sp_mr_tcam_region tcam_regions[MLXSW_SP_L3_PROTO_MAX];
+ void *priv;
};
/* This struct maps to one RIGR2 register entry */
INIT_LIST_HEAD(&erif_list->erif_sublists);
}
-#define MLXSW_SP_KVDL_RIGR2_SIZE 1
-
static struct mlxsw_sp_mr_erif_sublist *
mlxsw_sp_mr_erif_sublist_create(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_mr_tcam_erif_list *erif_list)
erif_sublist = kzalloc(sizeof(*erif_sublist), GFP_KERNEL);
if (!erif_sublist)
return ERR_PTR(-ENOMEM);
- err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KVDL_RIGR2_SIZE,
- &erif_sublist->rigr2_kvdl_index);
+ err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_MCRIGR,
+ 1, &erif_sublist->rigr2_kvdl_index);
if (err) {
kfree(erif_sublist);
return ERR_PTR(err);
struct mlxsw_sp_mr_erif_sublist *erif_sublist)
{
list_del(&erif_sublist->list);
- mlxsw_sp_kvdl_free(mlxsw_sp, erif_sublist->rigr2_kvdl_index);
+ mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_MCRIGR,
+ 1, erif_sublist->rigr2_kvdl_index);
kfree(erif_sublist);
}
struct mlxsw_sp_mr_tcam_erif_list erif_list;
struct mlxsw_afa_block *afa_block;
u32 counter_index;
- struct parman_item parman_item;
- struct parman_prio *parman_prio;
enum mlxsw_sp_mr_route_action action;
struct mlxsw_sp_mr_route_key key;
u16 irif_index;
u16 min_mtu;
+ void *priv;
};
static struct mlxsw_afa_block *
mlxsw_afa_block_destroy(afa_block);
}
-static int mlxsw_sp_mr_tcam_route_replace(struct mlxsw_sp *mlxsw_sp,
- struct parman_item *parman_item,
- struct mlxsw_sp_mr_route_key *key,
- struct mlxsw_afa_block *afa_block)
-{
- char rmft2_pl[MLXSW_REG_RMFT2_LEN];
-
- switch (key->proto) {
- case MLXSW_SP_L3_PROTO_IPV4:
- mlxsw_reg_rmft2_ipv4_pack(rmft2_pl, true, parman_item->index,
- key->vrid,
- MLXSW_REG_RMFT2_IRIF_MASK_IGNORE, 0,
- ntohl(key->group.addr4),
- ntohl(key->group_mask.addr4),
- ntohl(key->source.addr4),
- ntohl(key->source_mask.addr4),
- mlxsw_afa_block_first_set(afa_block));
- break;
- case MLXSW_SP_L3_PROTO_IPV6:
- mlxsw_reg_rmft2_ipv6_pack(rmft2_pl, true, parman_item->index,
- key->vrid,
- MLXSW_REG_RMFT2_IRIF_MASK_IGNORE, 0,
- key->group.addr6,
- key->group_mask.addr6,
- key->source.addr6,
- key->source_mask.addr6,
- mlxsw_afa_block_first_set(afa_block));
- }
-
- return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rmft2), rmft2_pl);
-}
-
-static int mlxsw_sp_mr_tcam_route_remove(struct mlxsw_sp *mlxsw_sp, int vrid,
- struct mlxsw_sp_mr_route_key *key,
- struct parman_item *parman_item)
-{
- struct in6_addr zero_addr = IN6ADDR_ANY_INIT;
- char rmft2_pl[MLXSW_REG_RMFT2_LEN];
-
- switch (key->proto) {
- case MLXSW_SP_L3_PROTO_IPV4:
- mlxsw_reg_rmft2_ipv4_pack(rmft2_pl, false, parman_item->index,
- vrid, 0, 0, 0, 0, 0, 0, NULL);
- break;
- case MLXSW_SP_L3_PROTO_IPV6:
- mlxsw_reg_rmft2_ipv6_pack(rmft2_pl, false, parman_item->index,
- vrid, 0, 0, zero_addr, zero_addr,
- zero_addr, zero_addr, NULL);
- break;
- }
-
- return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rmft2), rmft2_pl);
-}
-
static int
mlxsw_sp_mr_tcam_erif_populate(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_mr_tcam_erif_list *erif_list,
return 0;
}
-static struct mlxsw_sp_mr_tcam_region *
-mlxsw_sp_mr_tcam_protocol_region(struct mlxsw_sp_mr_tcam *mr_tcam,
- enum mlxsw_sp_l3proto proto)
-{
- return &mr_tcam->tcam_regions[proto];
-}
-
-static int
-mlxsw_sp_mr_tcam_route_parman_item_add(struct mlxsw_sp_mr_tcam *mr_tcam,
- struct mlxsw_sp_mr_tcam_route *route,
- enum mlxsw_sp_mr_route_prio prio)
-{
- struct mlxsw_sp_mr_tcam_region *tcam_region;
- int err;
-
- tcam_region = mlxsw_sp_mr_tcam_protocol_region(mr_tcam,
- route->key.proto);
- err = parman_item_add(tcam_region->parman,
- &tcam_region->parman_prios[prio],
- &route->parman_item);
- if (err)
- return err;
-
- route->parman_prio = &tcam_region->parman_prios[prio];
- return 0;
-}
-
-static void
-mlxsw_sp_mr_tcam_route_parman_item_remove(struct mlxsw_sp_mr_tcam *mr_tcam,
- struct mlxsw_sp_mr_tcam_route *route)
-{
- struct mlxsw_sp_mr_tcam_region *tcam_region;
-
- tcam_region = mlxsw_sp_mr_tcam_protocol_region(mr_tcam,
- route->key.proto);
-
- parman_item_remove(tcam_region->parman,
- route->parman_prio, &route->parman_item);
-}
-
static int
mlxsw_sp_mr_tcam_route_create(struct mlxsw_sp *mlxsw_sp, void *priv,
void *route_priv,
struct mlxsw_sp_mr_route_params *route_params)
{
+ const struct mlxsw_sp_mr_tcam_ops *ops = mlxsw_sp->mr_tcam_ops;
struct mlxsw_sp_mr_tcam_route *route = route_priv;
struct mlxsw_sp_mr_tcam *mr_tcam = priv;
int err;
goto err_afa_block_create;
}
- /* Allocate place in the TCAM */
- err = mlxsw_sp_mr_tcam_route_parman_item_add(mr_tcam, route,
- route_params->prio);
- if (err)
- goto err_parman_item_add;
+ route->priv = kzalloc(ops->route_priv_size, GFP_KERNEL);
+ if (!route->priv) {
+ err = -ENOMEM;
+ goto err_route_priv_alloc;
+ }
/* Write the route to the TCAM */
- err = mlxsw_sp_mr_tcam_route_replace(mlxsw_sp, &route->parman_item,
- &route->key, route->afa_block);
+ err = ops->route_create(mlxsw_sp, mr_tcam->priv, route->priv,
+ &route->key, route->afa_block,
+ route_params->prio);
if (err)
- goto err_route_replace;
+ goto err_route_create;
return 0;
-err_route_replace:
- mlxsw_sp_mr_tcam_route_parman_item_remove(mr_tcam, route);
-err_parman_item_add:
+err_route_create:
+ kfree(route->priv);
+err_route_priv_alloc:
mlxsw_sp_mr_tcam_afa_block_destroy(route->afa_block);
err_afa_block_create:
mlxsw_sp_flow_counter_free(mlxsw_sp, route->counter_index);
static void mlxsw_sp_mr_tcam_route_destroy(struct mlxsw_sp *mlxsw_sp,
void *priv, void *route_priv)
{
+ const struct mlxsw_sp_mr_tcam_ops *ops = mlxsw_sp->mr_tcam_ops;
struct mlxsw_sp_mr_tcam_route *route = route_priv;
struct mlxsw_sp_mr_tcam *mr_tcam = priv;
- mlxsw_sp_mr_tcam_route_remove(mlxsw_sp, route->key.vrid,
- &route->key, &route->parman_item);
- mlxsw_sp_mr_tcam_route_parman_item_remove(mr_tcam, route);
+ ops->route_destroy(mlxsw_sp, mr_tcam->priv, route->priv, &route->key);
+ kfree(route->priv);
mlxsw_sp_mr_tcam_afa_block_destroy(route->afa_block);
mlxsw_sp_flow_counter_free(mlxsw_sp, route->counter_index);
mlxsw_sp_mr_erif_list_flush(mlxsw_sp, &route->erif_list);
void *route_priv,
enum mlxsw_sp_mr_route_action route_action)
{
+ const struct mlxsw_sp_mr_tcam_ops *ops = mlxsw_sp->mr_tcam_ops;
struct mlxsw_sp_mr_tcam_route *route = route_priv;
struct mlxsw_afa_block *afa_block;
int err;
return PTR_ERR(afa_block);
/* Update the TCAM route entry */
- err = mlxsw_sp_mr_tcam_route_replace(mlxsw_sp, &route->parman_item,
- &route->key, afa_block);
+ err = ops->route_update(mlxsw_sp, route->priv, &route->key, afa_block);
if (err)
goto err;
static int mlxsw_sp_mr_tcam_route_min_mtu_update(struct mlxsw_sp *mlxsw_sp,
void *route_priv, u16 min_mtu)
{
+ const struct mlxsw_sp_mr_tcam_ops *ops = mlxsw_sp->mr_tcam_ops;
struct mlxsw_sp_mr_tcam_route *route = route_priv;
struct mlxsw_afa_block *afa_block;
int err;
return PTR_ERR(afa_block);
/* Update the TCAM route entry */
- err = mlxsw_sp_mr_tcam_route_replace(mlxsw_sp, &route->parman_item,
- &route->key, afa_block);
+ err = ops->route_update(mlxsw_sp, route->priv, &route->key, afa_block);
if (err)
goto err;
static int mlxsw_sp_mr_tcam_route_erif_del(struct mlxsw_sp *mlxsw_sp,
void *route_priv, u16 erif_index)
{
+ const struct mlxsw_sp_mr_tcam_ops *ops = mlxsw_sp->mr_tcam_ops;
struct mlxsw_sp_mr_tcam_route *route = route_priv;
struct mlxsw_sp_mr_erif_sublist *erif_sublist;
struct mlxsw_sp_mr_tcam_erif_list erif_list;
}
/* Update the TCAM route entry */
- err = mlxsw_sp_mr_tcam_route_replace(mlxsw_sp, &route->parman_item,
- &route->key, afa_block);
+ err = ops->route_update(mlxsw_sp, route->priv, &route->key, afa_block);
if (err)
goto err_route_write;
mlxsw_sp_mr_tcam_route_update(struct mlxsw_sp *mlxsw_sp, void *route_priv,
struct mlxsw_sp_mr_route_info *route_info)
{
+ const struct mlxsw_sp_mr_tcam_ops *ops = mlxsw_sp->mr_tcam_ops;
struct mlxsw_sp_mr_tcam_route *route = route_priv;
struct mlxsw_sp_mr_tcam_erif_list erif_list;
struct mlxsw_afa_block *afa_block;
}
/* Update the TCAM route entry */
- err = mlxsw_sp_mr_tcam_route_replace(mlxsw_sp, &route->parman_item,
- &route->key, afa_block);
+ err = ops->route_update(mlxsw_sp, route->priv, &route->key, afa_block);
if (err)
goto err_route_write;
return err;
}
-#define MLXSW_SP_MR_TCAM_REGION_BASE_COUNT 16
-#define MLXSW_SP_MR_TCAM_REGION_RESIZE_STEP 16
-
-static int
-mlxsw_sp_mr_tcam_region_alloc(struct mlxsw_sp_mr_tcam_region *mr_tcam_region)
-{
- struct mlxsw_sp *mlxsw_sp = mr_tcam_region->mlxsw_sp;
- char rtar_pl[MLXSW_REG_RTAR_LEN];
-
- mlxsw_reg_rtar_pack(rtar_pl, MLXSW_REG_RTAR_OP_ALLOCATE,
- mr_tcam_region->rtar_key_type,
- MLXSW_SP_MR_TCAM_REGION_BASE_COUNT);
- return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rtar), rtar_pl);
-}
-
-static void
-mlxsw_sp_mr_tcam_region_free(struct mlxsw_sp_mr_tcam_region *mr_tcam_region)
-{
- struct mlxsw_sp *mlxsw_sp = mr_tcam_region->mlxsw_sp;
- char rtar_pl[MLXSW_REG_RTAR_LEN];
-
- mlxsw_reg_rtar_pack(rtar_pl, MLXSW_REG_RTAR_OP_DEALLOCATE,
- mr_tcam_region->rtar_key_type, 0);
- mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rtar), rtar_pl);
-}
-
-static int mlxsw_sp_mr_tcam_region_parman_resize(void *priv,
- unsigned long new_count)
-{
- struct mlxsw_sp_mr_tcam_region *mr_tcam_region = priv;
- struct mlxsw_sp *mlxsw_sp = mr_tcam_region->mlxsw_sp;
- char rtar_pl[MLXSW_REG_RTAR_LEN];
- u64 max_tcam_rules;
-
- max_tcam_rules = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_TCAM_RULES);
- if (new_count > max_tcam_rules)
- return -EINVAL;
- mlxsw_reg_rtar_pack(rtar_pl, MLXSW_REG_RTAR_OP_RESIZE,
- mr_tcam_region->rtar_key_type, new_count);
- return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rtar), rtar_pl);
-}
-
-static void mlxsw_sp_mr_tcam_region_parman_move(void *priv,
- unsigned long from_index,
- unsigned long to_index,
- unsigned long count)
-{
- struct mlxsw_sp_mr_tcam_region *mr_tcam_region = priv;
- struct mlxsw_sp *mlxsw_sp = mr_tcam_region->mlxsw_sp;
- char rrcr_pl[MLXSW_REG_RRCR_LEN];
-
- mlxsw_reg_rrcr_pack(rrcr_pl, MLXSW_REG_RRCR_OP_MOVE,
- from_index, count,
- mr_tcam_region->rtar_key_type, to_index);
- mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rrcr), rrcr_pl);
-}
-
-static const struct parman_ops mlxsw_sp_mr_tcam_region_parman_ops = {
- .base_count = MLXSW_SP_MR_TCAM_REGION_BASE_COUNT,
- .resize_step = MLXSW_SP_MR_TCAM_REGION_RESIZE_STEP,
- .resize = mlxsw_sp_mr_tcam_region_parman_resize,
- .move = mlxsw_sp_mr_tcam_region_parman_move,
- .algo = PARMAN_ALGO_TYPE_LSORT,
-};
-
-static int
-mlxsw_sp_mr_tcam_region_init(struct mlxsw_sp *mlxsw_sp,
- struct mlxsw_sp_mr_tcam_region *mr_tcam_region,
- enum mlxsw_reg_rtar_key_type rtar_key_type)
-{
- struct parman_prio *parman_prios;
- struct parman *parman;
- int err;
- int i;
-
- mr_tcam_region->rtar_key_type = rtar_key_type;
- mr_tcam_region->mlxsw_sp = mlxsw_sp;
-
- err = mlxsw_sp_mr_tcam_region_alloc(mr_tcam_region);
- if (err)
- return err;
-
- parman = parman_create(&mlxsw_sp_mr_tcam_region_parman_ops,
- mr_tcam_region);
- if (!parman) {
- err = -ENOMEM;
- goto err_parman_create;
- }
- mr_tcam_region->parman = parman;
-
- parman_prios = kmalloc_array(MLXSW_SP_MR_ROUTE_PRIO_MAX + 1,
- sizeof(*parman_prios), GFP_KERNEL);
- if (!parman_prios) {
- err = -ENOMEM;
- goto err_parman_prios_alloc;
- }
- mr_tcam_region->parman_prios = parman_prios;
-
- for (i = 0; i < MLXSW_SP_MR_ROUTE_PRIO_MAX + 1; i++)
- parman_prio_init(mr_tcam_region->parman,
- &mr_tcam_region->parman_prios[i], i);
- return 0;
-
-err_parman_prios_alloc:
- parman_destroy(parman);
-err_parman_create:
- mlxsw_sp_mr_tcam_region_free(mr_tcam_region);
- return err;
-}
-
-static void
-mlxsw_sp_mr_tcam_region_fini(struct mlxsw_sp_mr_tcam_region *mr_tcam_region)
-{
- int i;
-
- for (i = 0; i < MLXSW_SP_MR_ROUTE_PRIO_MAX + 1; i++)
- parman_prio_fini(&mr_tcam_region->parman_prios[i]);
- kfree(mr_tcam_region->parman_prios);
- parman_destroy(mr_tcam_region->parman);
- mlxsw_sp_mr_tcam_region_free(mr_tcam_region);
-}
-
static int mlxsw_sp_mr_tcam_init(struct mlxsw_sp *mlxsw_sp, void *priv)
{
+ const struct mlxsw_sp_mr_tcam_ops *ops = mlxsw_sp->mr_tcam_ops;
struct mlxsw_sp_mr_tcam *mr_tcam = priv;
- struct mlxsw_sp_mr_tcam_region *region = &mr_tcam->tcam_regions[0];
- u32 rtar_key;
int err;
- if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MC_ERIF_LIST_ENTRIES) ||
- !MLXSW_CORE_RES_VALID(mlxsw_sp->core, ACL_MAX_TCAM_RULES))
+ if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MC_ERIF_LIST_ENTRIES))
return -EIO;
- rtar_key = MLXSW_REG_RTAR_KEY_TYPE_IPV4_MULTICAST;
- err = mlxsw_sp_mr_tcam_region_init(mlxsw_sp,
- ®ion[MLXSW_SP_L3_PROTO_IPV4],
- rtar_key);
- if (err)
- return err;
+ mr_tcam->priv = kzalloc(ops->priv_size, GFP_KERNEL);
+ if (!mr_tcam->priv)
+ return -ENOMEM;
- rtar_key = MLXSW_REG_RTAR_KEY_TYPE_IPV6_MULTICAST;
- err = mlxsw_sp_mr_tcam_region_init(mlxsw_sp,
- ®ion[MLXSW_SP_L3_PROTO_IPV6],
- rtar_key);
+ err = ops->init(mlxsw_sp, mr_tcam->priv);
if (err)
- goto err_ipv6_region_init;
-
+ goto err_init;
return 0;
-err_ipv6_region_init:
- mlxsw_sp_mr_tcam_region_fini(®ion[MLXSW_SP_L3_PROTO_IPV4]);
+err_init:
+ kfree(mr_tcam->priv);
return err;
}
-static void mlxsw_sp_mr_tcam_fini(void *priv)
+static void mlxsw_sp_mr_tcam_fini(struct mlxsw_sp *mlxsw_sp, void *priv)
{
+ const struct mlxsw_sp_mr_tcam_ops *ops = mlxsw_sp->mr_tcam_ops;
struct mlxsw_sp_mr_tcam *mr_tcam = priv;
- struct mlxsw_sp_mr_tcam_region *region = &mr_tcam->tcam_regions[0];
- mlxsw_sp_mr_tcam_region_fini(®ion[MLXSW_SP_L3_PROTO_IPV6]);
- mlxsw_sp_mr_tcam_region_fini(®ion[MLXSW_SP_L3_PROTO_IPV4]);
+ ops->fini(mr_tcam->priv);
+ kfree(mr_tcam->priv);
}
const struct mlxsw_sp_mr_ops mlxsw_sp_mr_tcam_ops = {
#include <linux/route.h>
#include <linux/gcd.h>
#include <linux/random.h>
+#include <linux/if_macvlan.h>
#include <net/netevent.h>
#include <net/neighbour.h>
#include <net/arp.h>
#include <net/ndisc.h>
#include <net/ipv6.h>
#include <net/fib_notifier.h>
+#include <net/switchdev.h>
#include "spectrum.h"
#include "core.h"
const struct mlxsw_sp_rif_params *params);
int (*configure)(struct mlxsw_sp_rif *rif);
void (*deconfigure)(struct mlxsw_sp_rif *rif);
- struct mlxsw_sp_fid * (*fid_get)(struct mlxsw_sp_rif *rif);
+ struct mlxsw_sp_fid * (*fid_get)(struct mlxsw_sp_rif *rif,
+ struct netlink_ext_ack *extack);
+ void (*fdb_del)(struct mlxsw_sp_rif *rif, const char *mac);
};
static void mlxsw_sp_lpm_tree_hold(struct mlxsw_sp_lpm_tree *lpm_tree);
mlxsw_sp_rif_counter_free(mlxsw_sp, rif, MLXSW_SP_RIF_COUNTER_EGRESS);
}
-static struct mlxsw_sp_rif *
-mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp,
- const struct net_device *dev);
-
#define MLXSW_SP_PREFIX_COUNT (sizeof(struct in6_addr) * BITS_PER_BYTE + 1)
struct mlxsw_sp_prefix_usage {
u32 tunnel_index;
int err;
- err = mlxsw_sp_kvdl_alloc(mlxsw_sp, 1, &tunnel_index);
+ err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ,
+ 1, &tunnel_index);
if (err)
return err;
/* Unlink this node from the IPIP entry that it's the decap entry of. */
fib_entry->decap.ipip_entry->decap_fib_entry = NULL;
fib_entry->decap.ipip_entry = NULL;
- mlxsw_sp_kvdl_free(mlxsw_sp, fib_entry->decap.tunnel_index);
+ mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ,
+ 1, fib_entry->decap.tunnel_index);
}
static struct mlxsw_sp_fib_node *
* by the device and make sure the request can be satisfied.
*/
mlxsw_sp_adj_grp_size_round_up(p_adj_grp_size);
- err = mlxsw_sp_kvdl_alloc_size_query(mlxsw_sp, *p_adj_grp_size,
- &alloc_size);
+ err = mlxsw_sp_kvdl_alloc_count_query(mlxsw_sp,
+ MLXSW_SP_KVDL_ENTRY_TYPE_ADJ,
+ *p_adj_grp_size, &alloc_size);
if (err)
return err;
/* It is possible the allocation results in more allocated
/* No valid allocation size available. */
goto set_trap;
- err = mlxsw_sp_kvdl_alloc(mlxsw_sp, ecmp_size, &adj_index);
+ err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ,
+ ecmp_size, &adj_index);
if (err) {
/* We ran out of KVD linear space, just set the
* trap and let everything flow through kernel.
err = mlxsw_sp_adj_index_mass_update(mlxsw_sp, nh_grp,
old_adj_index, old_ecmp_size);
- mlxsw_sp_kvdl_free(mlxsw_sp, old_adj_index);
+ mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ,
+ old_ecmp_size, old_adj_index);
if (err) {
dev_warn(mlxsw_sp->bus_info->dev, "Failed to mass-update adjacency index for nexthop group.\n");
goto set_trap;
if (err)
dev_warn(mlxsw_sp->bus_info->dev, "Failed to set traps for fib entries.\n");
if (old_adj_index_valid)
- mlxsw_sp_kvdl_free(mlxsw_sp, nh_grp->adj_index);
+ mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ,
+ nh_grp->ecmp_size, nh_grp->adj_index);
}
static void __mlxsw_sp_nexthop_neigh_update(struct mlxsw_sp_nexthop *nh,
return NOTIFY_DONE;
}
-static struct mlxsw_sp_rif *
+struct mlxsw_sp_rif *
mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp,
const struct net_device *dev)
{
!list_empty(&inet6_dev->addr_list))
addr_list_empty = false;
+ /* macvlans do not have a RIF, but rather piggy back on the
+ * RIF of their lower device.
+ */
+ if (netif_is_macvlan(dev) && addr_list_empty)
+ return true;
+
if (rif && addr_list_empty &&
!netif_is_l3_slave(rif->dev))
return true;
return rif->dev;
}
+struct mlxsw_sp_fid *mlxsw_sp_rif_fid(const struct mlxsw_sp_rif *rif)
+{
+ return rif->fid;
+}
+
static struct mlxsw_sp_rif *
mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp,
const struct mlxsw_sp_rif_params *params,
rif->ops = ops;
if (ops->fid_get) {
- fid = ops->fid_get(rif);
+ fid = ops->fid_get(rif, extack);
if (IS_ERR(fid)) {
err = PTR_ERR(fid);
goto err_fid_get;
}
/* FID was already created, just take a reference */
- fid = rif->ops->fid_get(rif);
+ fid = rif->ops->fid_get(rif, extack);
err = mlxsw_sp_fid_port_vid_map(fid, mlxsw_sp_port, vid);
if (err)
goto err_fid_port_vid_map;
return 0;
}
+static bool mlxsw_sp_rif_macvlan_is_vrrp4(const u8 *mac)
+{
+ u8 vrrp4[ETH_ALEN] = { 0x00, 0x00, 0x5e, 0x00, 0x01, 0x00 };
+ u8 mask[ETH_ALEN] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0x00 };
+
+ return ether_addr_equal_masked(mac, vrrp4, mask);
+}
+
+static bool mlxsw_sp_rif_macvlan_is_vrrp6(const u8 *mac)
+{
+ u8 vrrp6[ETH_ALEN] = { 0x00, 0x00, 0x5e, 0x00, 0x02, 0x00 };
+ u8 mask[ETH_ALEN] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0x00 };
+
+ return ether_addr_equal_masked(mac, vrrp6, mask);
+}
+
+static int mlxsw_sp_rif_vrrp_op(struct mlxsw_sp *mlxsw_sp, u16 rif_index,
+ const u8 *mac, bool adding)
+{
+ char ritr_pl[MLXSW_REG_RITR_LEN];
+ u8 vrrp_id = adding ? mac[5] : 0;
+ int err;
+
+ if (!mlxsw_sp_rif_macvlan_is_vrrp4(mac) &&
+ !mlxsw_sp_rif_macvlan_is_vrrp6(mac))
+ return 0;
+
+ mlxsw_reg_ritr_rif_pack(ritr_pl, rif_index);
+ err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
+ if (err)
+ return err;
+
+ if (mlxsw_sp_rif_macvlan_is_vrrp4(mac))
+ mlxsw_reg_ritr_if_vrrp_id_ipv4_set(ritr_pl, vrrp_id);
+ else
+ mlxsw_reg_ritr_if_vrrp_id_ipv6_set(ritr_pl, vrrp_id);
+
+ return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
+}
+
+static int mlxsw_sp_rif_macvlan_add(struct mlxsw_sp *mlxsw_sp,
+ const struct net_device *macvlan_dev,
+ struct netlink_ext_ack *extack)
+{
+ struct macvlan_dev *vlan = netdev_priv(macvlan_dev);
+ struct mlxsw_sp_rif *rif;
+ int err;
+
+ rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, vlan->lowerdev);
+ if (!rif) {
+ NL_SET_ERR_MSG_MOD(extack, "macvlan is only supported on top of router interfaces");
+ return -EOPNOTSUPP;
+ }
+
+ err = mlxsw_sp_rif_fdb_op(mlxsw_sp, macvlan_dev->dev_addr,
+ mlxsw_sp_fid_index(rif->fid), true);
+ if (err)
+ return err;
+
+ err = mlxsw_sp_rif_vrrp_op(mlxsw_sp, rif->rif_index,
+ macvlan_dev->dev_addr, true);
+ if (err)
+ goto err_rif_vrrp_add;
+
+ /* Make sure the bridge driver does not have this MAC pointing at
+ * some other port.
+ */
+ if (rif->ops->fdb_del)
+ rif->ops->fdb_del(rif, macvlan_dev->dev_addr);
+
+ return 0;
+
+err_rif_vrrp_add:
+ mlxsw_sp_rif_fdb_op(mlxsw_sp, macvlan_dev->dev_addr,
+ mlxsw_sp_fid_index(rif->fid), false);
+ return err;
+}
+
+void mlxsw_sp_rif_macvlan_del(struct mlxsw_sp *mlxsw_sp,
+ const struct net_device *macvlan_dev)
+{
+ struct macvlan_dev *vlan = netdev_priv(macvlan_dev);
+ struct mlxsw_sp_rif *rif;
+
+ rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, vlan->lowerdev);
+ /* If we do not have a RIF, then we already took care of
+ * removing the macvlan's MAC during RIF deletion.
+ */
+ if (!rif)
+ return;
+ mlxsw_sp_rif_vrrp_op(mlxsw_sp, rif->rif_index, macvlan_dev->dev_addr,
+ false);
+ mlxsw_sp_rif_fdb_op(mlxsw_sp, macvlan_dev->dev_addr,
+ mlxsw_sp_fid_index(rif->fid), false);
+}
+
+static int mlxsw_sp_inetaddr_macvlan_event(struct net_device *macvlan_dev,
+ unsigned long event,
+ struct netlink_ext_ack *extack)
+{
+ struct mlxsw_sp *mlxsw_sp;
+
+ mlxsw_sp = mlxsw_sp_lower_get(macvlan_dev);
+ if (!mlxsw_sp)
+ return 0;
+
+ switch (event) {
+ case NETDEV_UP:
+ return mlxsw_sp_rif_macvlan_add(mlxsw_sp, macvlan_dev, extack);
+ case NETDEV_DOWN:
+ mlxsw_sp_rif_macvlan_del(mlxsw_sp, macvlan_dev);
+ break;
+ }
+
+ return 0;
+}
+
static int __mlxsw_sp_inetaddr_event(struct net_device *dev,
unsigned long event,
struct netlink_ext_ack *extack)
return mlxsw_sp_inetaddr_bridge_event(dev, event, extack);
else if (is_vlan_dev(dev))
return mlxsw_sp_inetaddr_vlan_event(dev, event, extack);
+ else if (netif_is_macvlan(dev))
+ return mlxsw_sp_inetaddr_macvlan_event(dev, event, extack);
else
return 0;
}
struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(l3_dev);
int err = 0;
- if (!mlxsw_sp)
+ /* We do not create a RIF for a macvlan, but only use it to
+ * direct more MAC addresses to the router.
+ */
+ if (!mlxsw_sp || netif_is_macvlan(l3_dev))
return 0;
switch (event) {
return err;
}
+static int __mlxsw_sp_rif_macvlan_flush(struct net_device *dev, void *data)
+{
+ struct mlxsw_sp_rif *rif = data;
+
+ if (!netif_is_macvlan(dev))
+ return 0;
+
+ return mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, dev->dev_addr,
+ mlxsw_sp_fid_index(rif->fid), false);
+}
+
+static int mlxsw_sp_rif_macvlan_flush(struct mlxsw_sp_rif *rif)
+{
+ if (!netif_is_macvlan_port(rif->dev))
+ return 0;
+
+ netdev_warn(rif->dev, "Router interface is deleted. Upper macvlans will not work\n");
+ return netdev_walk_all_upper_dev_rcu(rif->dev,
+ __mlxsw_sp_rif_macvlan_flush, rif);
+}
+
static struct mlxsw_sp_rif_subport *
mlxsw_sp_rif_subport_rif(const struct mlxsw_sp_rif *rif)
{
mlxsw_sp_fid_rif_set(fid, NULL);
mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, rif->dev->dev_addr,
mlxsw_sp_fid_index(fid), false);
+ mlxsw_sp_rif_macvlan_flush(rif);
mlxsw_sp_rif_subport_op(rif, false);
}
static struct mlxsw_sp_fid *
-mlxsw_sp_rif_subport_fid_get(struct mlxsw_sp_rif *rif)
+mlxsw_sp_rif_subport_fid_get(struct mlxsw_sp_rif *rif,
+ struct netlink_ext_ack *extack)
{
return mlxsw_sp_fid_rfid_get(rif->mlxsw_sp, rif->rif_index);
}
mlxsw_sp_fid_rif_set(fid, NULL);
mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, rif->dev->dev_addr,
mlxsw_sp_fid_index(fid), false);
+ mlxsw_sp_rif_macvlan_flush(rif);
mlxsw_sp_fid_flood_set(rif->fid, MLXSW_SP_FLOOD_TYPE_BC,
mlxsw_sp_router_port(mlxsw_sp), false);
mlxsw_sp_fid_flood_set(rif->fid, MLXSW_SP_FLOOD_TYPE_MC,
}
static struct mlxsw_sp_fid *
-mlxsw_sp_rif_vlan_fid_get(struct mlxsw_sp_rif *rif)
+mlxsw_sp_rif_vlan_fid_get(struct mlxsw_sp_rif *rif,
+ struct netlink_ext_ack *extack)
{
- u16 vid = is_vlan_dev(rif->dev) ? vlan_dev_vlan_id(rif->dev) : 1;
+ u16 vid;
+ int err;
+
+ if (is_vlan_dev(rif->dev)) {
+ vid = vlan_dev_vlan_id(rif->dev);
+ } else {
+ err = br_vlan_get_pvid(rif->dev, &vid);
+ if (err < 0 || !vid) {
+ NL_SET_ERR_MSG_MOD(extack, "Couldn't determine bridge PVID");
+ return ERR_PTR(-EINVAL);
+ }
+ }
return mlxsw_sp_fid_8021q_get(rif->mlxsw_sp, vid);
}
+static void mlxsw_sp_rif_vlan_fdb_del(struct mlxsw_sp_rif *rif, const char *mac)
+{
+ u16 vid = mlxsw_sp_fid_8021q_vid(rif->fid);
+ struct switchdev_notifier_fdb_info info;
+ struct net_device *br_dev;
+ struct net_device *dev;
+
+ br_dev = is_vlan_dev(rif->dev) ? vlan_dev_real_dev(rif->dev) : rif->dev;
+ dev = br_fdb_find_port(br_dev, mac, vid);
+ if (!dev)
+ return;
+
+ info.addr = mac;
+ info.vid = vid;
+ call_switchdev_notifiers(SWITCHDEV_FDB_DEL_TO_BRIDGE, dev, &info.info);
+}
+
static const struct mlxsw_sp_rif_ops mlxsw_sp_rif_vlan_ops = {
.type = MLXSW_SP_RIF_TYPE_VLAN,
.rif_size = sizeof(struct mlxsw_sp_rif),
.configure = mlxsw_sp_rif_vlan_configure,
.deconfigure = mlxsw_sp_rif_vlan_deconfigure,
.fid_get = mlxsw_sp_rif_vlan_fid_get,
+ .fdb_del = mlxsw_sp_rif_vlan_fdb_del,
};
static int mlxsw_sp_rif_fid_configure(struct mlxsw_sp_rif *rif)
mlxsw_sp_fid_rif_set(fid, NULL);
mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, rif->dev->dev_addr,
mlxsw_sp_fid_index(fid), false);
+ mlxsw_sp_rif_macvlan_flush(rif);
mlxsw_sp_fid_flood_set(rif->fid, MLXSW_SP_FLOOD_TYPE_BC,
mlxsw_sp_router_port(mlxsw_sp), false);
mlxsw_sp_fid_flood_set(rif->fid, MLXSW_SP_FLOOD_TYPE_MC,
}
static struct mlxsw_sp_fid *
-mlxsw_sp_rif_fid_fid_get(struct mlxsw_sp_rif *rif)
+mlxsw_sp_rif_fid_fid_get(struct mlxsw_sp_rif *rif,
+ struct netlink_ext_ack *extack)
{
return mlxsw_sp_fid_8021d_get(rif->mlxsw_sp, rif->dev->ifindex);
}
+static void mlxsw_sp_rif_fid_fdb_del(struct mlxsw_sp_rif *rif, const char *mac)
+{
+ struct switchdev_notifier_fdb_info info;
+ struct net_device *dev;
+
+ dev = br_fdb_find_port(rif->dev, mac, 0);
+ if (!dev)
+ return;
+
+ info.addr = mac;
+ info.vid = 0;
+ call_switchdev_notifiers(SWITCHDEV_FDB_DEL_TO_BRIDGE, dev, &info.info);
+}
+
static const struct mlxsw_sp_rif_ops mlxsw_sp_rif_fid_ops = {
.type = MLXSW_SP_RIF_TYPE_FID,
.rif_size = sizeof(struct mlxsw_sp_rif),
.configure = mlxsw_sp_rif_fid_configure,
.deconfigure = mlxsw_sp_rif_fid_deconfigure,
.fid_get = mlxsw_sp_rif_fid_fid_get,
+ .fdb_del = mlxsw_sp_rif_fid_fdb_del,
};
static struct mlxsw_sp_rif_ipip_lb *
struct mlxsw_sp_nexthop;
struct mlxsw_sp_ipip_entry;
+struct mlxsw_sp_rif *mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp,
+ const struct net_device *dev);
struct mlxsw_sp_rif *mlxsw_sp_rif_by_index(const struct mlxsw_sp *mlxsw_sp,
u16 rif_index);
u16 mlxsw_sp_rif_index(const struct mlxsw_sp_rif *rif);
int mlxsw_sp_rif_dev_ifindex(const struct mlxsw_sp_rif *rif);
u8 mlxsw_sp_router_port(const struct mlxsw_sp *mlxsw_sp);
const struct net_device *mlxsw_sp_rif_dev(const struct mlxsw_sp_rif *rif);
+struct mlxsw_sp_fid *mlxsw_sp_rif_fid(const struct mlxsw_sp_rif *rif);
int mlxsw_sp_rif_counter_value_get(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_rif *rif,
enum mlxsw_sp_rif_counter_dir dir,
#include <linux/list.h>
#include <net/arp.h>
#include <net/gre.h>
+#include <net/lag.h>
#include <net/ndisc.h>
#include <net/ip6_tunnel.h>
struct list_head *iter;
netdev_for_each_lower_dev(lag_dev, dev, iter)
- if ((dev->flags & IFF_UP) && mlxsw_sp_port_dev_check(dev))
+ if (netif_carrier_ok(dev) &&
+ net_lag_port_dev_txable(dev) &&
+ mlxsw_sp_port_dev_check(dev))
return dev;
return NULL;
return err;
}
+static int
+mlxsw_sp_br_ban_rif_pvid_change(struct mlxsw_sp *mlxsw_sp,
+ const struct net_device *br_dev,
+ const struct switchdev_obj_port_vlan *vlan)
+{
+ struct mlxsw_sp_rif *rif;
+ struct mlxsw_sp_fid *fid;
+ u16 pvid;
+ u16 vid;
+
+ rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, br_dev);
+ if (!rif)
+ return 0;
+ fid = mlxsw_sp_rif_fid(rif);
+ pvid = mlxsw_sp_fid_8021q_vid(fid);
+
+ for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) {
+ if (vlan->flags & BRIDGE_VLAN_INFO_PVID) {
+ if (vid != pvid) {
+ netdev_err(br_dev, "Can't change PVID, it's used by router interface\n");
+ return -EBUSY;
+ }
+ } else {
+ if (vid == pvid) {
+ netdev_err(br_dev, "Can't remove PVID, it's used by router interface\n");
+ return -EBUSY;
+ }
+ }
+ }
+
+ return 0;
+}
+
static int mlxsw_sp_port_vlans_add(struct mlxsw_sp_port *mlxsw_sp_port,
const struct switchdev_obj_port_vlan *vlan,
struct switchdev_trans *trans)
struct mlxsw_sp_bridge_port *bridge_port;
u16 vid;
- if (netif_is_bridge_master(orig_dev))
- return -EOPNOTSUPP;
+ if (netif_is_bridge_master(orig_dev)) {
+ int err = 0;
+
+ if ((vlan->flags & BRIDGE_VLAN_INFO_BRENTRY) &&
+ br_vlan_enabled(orig_dev) &&
+ switchdev_trans_ph_prepare(trans))
+ err = mlxsw_sp_br_ban_rif_pvid_change(mlxsw_sp,
+ orig_dev, vlan);
+ if (!err)
+ err = -EOPNOTSUPP;
+ return err;
+ }
if (switchdev_trans_ph_prepare(trans))
return 0;
MLXSW_TRAP_ID_LBERROR = 0x54,
MLXSW_TRAP_ID_IPV4_OSPF = 0x55,
MLXSW_TRAP_ID_IPV4_PIM = 0x58,
+ MLXSW_TRAP_ID_IPV4_VRRP = 0x59,
MLXSW_TRAP_ID_RPF = 0x5C,
MLXSW_TRAP_ID_IP2ME = 0x5F,
MLXSW_TRAP_ID_IPV6_UNSPECIFIED_ADDRESS = 0x60,
MLXSW_TRAP_ID_IPV6_ALL_ROUTERS_LINK = 0x6F,
MLXSW_TRAP_ID_RTR_INGRESS0 = 0x70,
MLXSW_TRAP_ID_IPV6_PIM = 0x79,
+ MLXSW_TRAP_ID_IPV6_VRRP = 0x7A,
MLXSW_TRAP_ID_IPV4_BGP = 0x88,
MLXSW_TRAP_ID_IPV6_BGP = 0x89,
MLXSW_TRAP_ID_L3_IPV6_ROUTER_SOLICITATION = 0x8A,
*/
static void port_set_link_speed(struct ksz_port *port)
{
- struct ksz_port_info *info;
struct ksz_hw *hw = port->hw;
u16 data;
u16 cfg;
int p;
for (i = 0, p = port->first_port; i < port->port_cnt; i++, p++) {
- info = &hw->port_info[p];
-
port_r16(hw, p, KS884X_PORT_CTRL_4_OFFSET, &data);
port_r8(hw, p, KS884X_PORT_STATUS_OFFSET, &status);
}
if (!mac_address_valid)
- random_ether_addr(adapter->mac_address);
+ eth_random_addr(adapter->mac_address);
lan743x_mac_set_address(adapter, adapter->mac_address);
ether_addr_copy(netdev->dev_addr, adapter->mac_address);
return 0;
return 0;
}
+static int ocelot_vlant_set_mask(struct ocelot *ocelot, u16 vid, u32 mask)
+{
+ /* Select the VID to configure */
+ ocelot_write(ocelot, ANA_TABLES_VLANTIDX_V_INDEX(vid),
+ ANA_TABLES_VLANTIDX);
+ /* Set the vlan port members mask and issue a write command */
+ ocelot_write(ocelot, ANA_TABLES_VLANACCESS_VLAN_PORT_MASK(mask) |
+ ANA_TABLES_VLANACCESS_CMD_WRITE,
+ ANA_TABLES_VLANACCESS);
+
+ return ocelot_vlant_wait_for_completion(ocelot);
+}
+
+static void ocelot_vlan_mode(struct ocelot_port *port,
+ netdev_features_t features)
+{
+ struct ocelot *ocelot = port->ocelot;
+ u8 p = port->chip_port;
+ u32 val;
+
+ /* Filtering */
+ val = ocelot_read(ocelot, ANA_VLANMASK);
+ if (features & NETIF_F_HW_VLAN_CTAG_FILTER)
+ val |= BIT(p);
+ else
+ val &= ~BIT(p);
+ ocelot_write(ocelot, val, ANA_VLANMASK);
+}
+
+static void ocelot_vlan_port_apply(struct ocelot *ocelot,
+ struct ocelot_port *port)
+{
+ u32 val;
+
+ /* Ingress clasification (ANA_PORT_VLAN_CFG) */
+ /* Default vlan to clasify for untagged frames (may be zero) */
+ val = ANA_PORT_VLAN_CFG_VLAN_VID(port->pvid);
+ if (port->vlan_aware)
+ val |= ANA_PORT_VLAN_CFG_VLAN_AWARE_ENA |
+ ANA_PORT_VLAN_CFG_VLAN_POP_CNT(1);
+
+ ocelot_rmw_gix(ocelot, val,
+ ANA_PORT_VLAN_CFG_VLAN_VID_M |
+ ANA_PORT_VLAN_CFG_VLAN_AWARE_ENA |
+ ANA_PORT_VLAN_CFG_VLAN_POP_CNT_M,
+ ANA_PORT_VLAN_CFG, port->chip_port);
+
+ /* Drop frames with multicast source address */
+ val = ANA_PORT_DROP_CFG_DROP_MC_SMAC_ENA;
+ if (port->vlan_aware && !port->vid)
+ /* If port is vlan-aware and tagged, drop untagged and priority
+ * tagged frames.
+ */
+ val |= ANA_PORT_DROP_CFG_DROP_UNTAGGED_ENA |
+ ANA_PORT_DROP_CFG_DROP_PRIO_S_TAGGED_ENA |
+ ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA;
+ ocelot_write_gix(ocelot, val, ANA_PORT_DROP_CFG, port->chip_port);
+
+ /* Egress configuration (REW_TAG_CFG): VLAN tag type to 8021Q. */
+ val = REW_TAG_CFG_TAG_TPID_CFG(0);
+
+ if (port->vlan_aware) {
+ if (port->vid)
+ /* Tag all frames except when VID == DEFAULT_VLAN */
+ val |= REW_TAG_CFG_TAG_CFG(1);
+ else
+ /* Tag all frames */
+ val |= REW_TAG_CFG_TAG_CFG(3);
+ }
+ ocelot_rmw_gix(ocelot, val,
+ REW_TAG_CFG_TAG_TPID_CFG_M |
+ REW_TAG_CFG_TAG_CFG_M,
+ REW_TAG_CFG, port->chip_port);
+
+ /* Set default VLAN and tag type to 8021Q. */
+ val = REW_PORT_VLAN_CFG_PORT_TPID(ETH_P_8021Q) |
+ REW_PORT_VLAN_CFG_PORT_VID(port->vid);
+ ocelot_rmw_gix(ocelot, val,
+ REW_PORT_VLAN_CFG_PORT_TPID_M |
+ REW_PORT_VLAN_CFG_PORT_VID_M,
+ REW_PORT_VLAN_CFG, port->chip_port);
+}
+
+static int ocelot_vlan_vid_add(struct net_device *dev, u16 vid, bool pvid,
+ bool untagged)
+{
+ struct ocelot_port *port = netdev_priv(dev);
+ struct ocelot *ocelot = port->ocelot;
+ int ret;
+
+ /* Add the port MAC address to with the right VLAN information */
+ ocelot_mact_learn(ocelot, PGID_CPU, dev->dev_addr, vid,
+ ENTRYTYPE_LOCKED);
+
+ /* Make the port a member of the VLAN */
+ ocelot->vlan_mask[vid] |= BIT(port->chip_port);
+ ret = ocelot_vlant_set_mask(ocelot, vid, ocelot->vlan_mask[vid]);
+ if (ret)
+ return ret;
+
+ /* Default ingress vlan classification */
+ if (pvid)
+ port->pvid = vid;
+
+ /* Untagged egress vlan clasification */
+ if (untagged)
+ port->vid = vid;
+
+ ocelot_vlan_port_apply(ocelot, port);
+
+ return 0;
+}
+
+static int ocelot_vlan_vid_del(struct net_device *dev, u16 vid)
+{
+ struct ocelot_port *port = netdev_priv(dev);
+ struct ocelot *ocelot = port->ocelot;
+ int ret;
+
+ /* 8021q removes VID 0 on module unload for all interfaces
+ * with VLAN filtering feature. We need to keep it to receive
+ * untagged traffic.
+ */
+ if (vid == 0)
+ return 0;
+
+ /* Del the port MAC address to with the right VLAN information */
+ ocelot_mact_forget(ocelot, dev->dev_addr, vid);
+
+ /* Stop the port from being a member of the vlan */
+ ocelot->vlan_mask[vid] &= ~BIT(port->chip_port);
+ ret = ocelot_vlant_set_mask(ocelot, vid, ocelot->vlan_mask[vid]);
+ if (ret)
+ return ret;
+
+ /* Ingress */
+ if (port->pvid == vid)
+ port->pvid = 0;
+
+ /* Egress */
+ if (port->vid == vid)
+ port->vid = 0;
+
+ ocelot_vlan_port_apply(ocelot, port);
+
+ return 0;
+}
+
static void ocelot_vlan_init(struct ocelot *ocelot)
{
+ u16 port, vid;
+
/* Clear VLAN table, by default all ports are members of all VLANs */
ocelot_write(ocelot, ANA_TABLES_VLANACCESS_CMD_INIT,
ANA_TABLES_VLANACCESS);
ocelot_vlant_wait_for_completion(ocelot);
+
+ /* Configure the port VLAN memberships */
+ for (vid = 1; vid < VLAN_N_VID; vid++) {
+ ocelot->vlan_mask[vid] = 0;
+ ocelot_vlant_set_mask(ocelot, vid, ocelot->vlan_mask[vid]);
+ }
+
+ /* Because VLAN filtering is enabled, we need VID 0 to get untagged
+ * traffic. It is added automatically if 8021q module is loaded, but
+ * we can't rely on it since module may be not loaded.
+ */
+ ocelot->vlan_mask[0] = GENMASK(ocelot->num_phys_ports - 1, 0);
+ ocelot_vlant_set_mask(ocelot, 0, ocelot->vlan_mask[0]);
+
+ /* Configure the CPU port to be VLAN aware */
+ ocelot_write_gix(ocelot, ANA_PORT_VLAN_CFG_VLAN_VID(0) |
+ ANA_PORT_VLAN_CFG_VLAN_AWARE_ENA |
+ ANA_PORT_VLAN_CFG_VLAN_POP_CNT(1),
+ ANA_PORT_VLAN_CFG, ocelot->num_phys_ports);
+
+ /* Set vlan ingress filter mask to all ports but the CPU port by
+ * default.
+ */
+ ocelot_write(ocelot, GENMASK(9, 0), ANA_VLANMASK);
+
+ for (port = 0; port < ocelot->num_phys_ports; port++) {
+ ocelot_write_gix(ocelot, 0, REW_PORT_VLAN_CFG, port);
+ ocelot_write_gix(ocelot, 0, REW_TAG_CFG, port);
+ }
}
/* Watermark encode
static int ocelot_gen_ifh(u32 *ifh, struct frame_info *info)
{
ifh[0] = IFH_INJ_BYPASS;
- ifh[1] = (0xff00 & info->port) >> 8;
+ ifh[1] = (0xf00 & info->port) >> 8;
ifh[2] = (0xff & info->port) << 24;
- ifh[3] = IFH_INJ_POP_CNT_DISABLE | (info->cpuq << 20) |
- (info->tag_type << 16) | info->vid;
+ ifh[3] = (info->tag_type << 16) | info->vid;
return 0;
}
QS_INJ_CTRL_SOF, QS_INJ_CTRL, grp);
info.port = BIT(port->chip_port);
- info.cpuq = 0xff;
+ info.tag_type = IFH_TAG_TYPE_C;
+ info.vid = skb_vlan_tag_get(skb);
ocelot_gen_ifh(ifh, &info);
for (i = 0; i < IFH_LEN; i++)
- ocelot_write_rix(ocelot, ifh[i], QS_INJ_WR, grp);
+ ocelot_write_rix(ocelot, (__force u32)cpu_to_be32(ifh[i]),
+ QS_INJ_WR, grp);
count = (skb->len + 3) / 4;
last = skb->len % 4;
struct ocelot_port *port = netdev_priv(dev);
struct ocelot *ocelot = port->ocelot;
+ if (!vid) {
+ if (!port->vlan_aware)
+ /* If the bridge is not VLAN aware and no VID was
+ * provided, set it to pvid to ensure the MAC entry
+ * matches incoming untagged packets
+ */
+ vid = port->pvid;
+ else
+ /* If the bridge is VLAN aware a VID must be provided as
+ * otherwise the learnt entry wouldn't match any frame.
+ */
+ return -EINVAL;
+ }
+
return ocelot_mact_learn(ocelot, port->chip_port, addr, vid,
ENTRYTYPE_NORMAL);
}
return ret;
}
+static int ocelot_vlan_rx_add_vid(struct net_device *dev, __be16 proto,
+ u16 vid)
+{
+ return ocelot_vlan_vid_add(dev, vid, false, true);
+}
+
+static int ocelot_vlan_rx_kill_vid(struct net_device *dev, __be16 proto,
+ u16 vid)
+{
+ return ocelot_vlan_vid_del(dev, vid);
+}
+
+static int ocelot_set_features(struct net_device *dev,
+ netdev_features_t features)
+{
+ struct ocelot_port *port = netdev_priv(dev);
+ netdev_features_t changed = dev->features ^ features;
+
+ if (changed & NETIF_F_HW_VLAN_CTAG_FILTER)
+ ocelot_vlan_mode(port, features);
+
+ return 0;
+}
+
static const struct net_device_ops ocelot_port_netdev_ops = {
.ndo_open = ocelot_port_open,
.ndo_stop = ocelot_port_stop,
.ndo_fdb_add = ocelot_fdb_add,
.ndo_fdb_del = ocelot_fdb_del,
.ndo_fdb_dump = ocelot_fdb_dump,
+ .ndo_vlan_rx_add_vid = ocelot_vlan_rx_add_vid,
+ .ndo_vlan_rx_kill_vid = ocelot_vlan_rx_kill_vid,
+ .ndo_set_features = ocelot_set_features,
};
static void ocelot_get_strings(struct net_device *netdev, u32 sset, u8 *data)
.get_strings = ocelot_get_strings,
.get_ethtool_stats = ocelot_get_ethtool_stats,
.get_sset_count = ocelot_get_sset_count,
+ .get_link_ksettings = phy_ethtool_get_link_ksettings,
+ .set_link_ksettings = phy_ethtool_set_link_ksettings,
};
static int ocelot_port_attr_get(struct net_device *dev,
case SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME:
ocelot_port_attr_ageing_set(ocelot_port, attr->u.ageing_time);
break;
+ case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING:
+ ocelot_port->vlan_aware = attr->u.vlan_filtering;
+ ocelot_vlan_port_apply(ocelot_port->ocelot, ocelot_port);
+ break;
case SWITCHDEV_ATTR_ID_BRIDGE_MC_DISABLED:
ocelot_port_attr_mc_set(ocelot_port, !attr->u.mc_disabled);
break;
return err;
}
+static int ocelot_port_obj_add_vlan(struct net_device *dev,
+ const struct switchdev_obj_port_vlan *vlan,
+ struct switchdev_trans *trans)
+{
+ int ret;
+ u16 vid;
+
+ for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) {
+ ret = ocelot_vlan_vid_add(dev, vid,
+ vlan->flags & BRIDGE_VLAN_INFO_PVID,
+ vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
+static int ocelot_port_vlan_del_vlan(struct net_device *dev,
+ const struct switchdev_obj_port_vlan *vlan)
+{
+ int ret;
+ u16 vid;
+
+ for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) {
+ ret = ocelot_vlan_vid_del(dev, vid);
+
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
static struct ocelot_multicast *ocelot_multicast_get(struct ocelot *ocelot,
const unsigned char *addr,
u16 vid)
bool new = false;
if (!vid)
- vid = 1;
+ vid = port->pvid;
mc = ocelot_multicast_get(ocelot, mdb->addr, vid);
if (!mc) {
u16 vid = mdb->vid;
if (!vid)
- vid = 1;
+ vid = port->pvid;
mc = ocelot_multicast_get(ocelot, mdb->addr, vid);
if (!mc)
int ret = 0;
switch (obj->id) {
+ case SWITCHDEV_OBJ_ID_PORT_VLAN:
+ ret = ocelot_port_obj_add_vlan(dev,
+ SWITCHDEV_OBJ_PORT_VLAN(obj),
+ trans);
+ break;
case SWITCHDEV_OBJ_ID_PORT_MDB:
ret = ocelot_port_obj_add_mdb(dev, SWITCHDEV_OBJ_PORT_MDB(obj),
trans);
int ret = 0;
switch (obj->id) {
+ case SWITCHDEV_OBJ_ID_PORT_VLAN:
+ ret = ocelot_port_vlan_del_vlan(dev,
+ SWITCHDEV_OBJ_PORT_VLAN(obj));
+ break;
case SWITCHDEV_OBJ_ID_PORT_MDB:
ret = ocelot_port_obj_del_mdb(dev, SWITCHDEV_OBJ_PORT_MDB(obj));
break;
if (!ocelot->bridge_mask)
ocelot->hw_bridge_dev = NULL;
+
+ /* Clear bridge vlan settings before calling ocelot_vlan_port_apply */
+ ocelot_port->vlan_aware = 0;
+ ocelot_port->pvid = 0;
+ ocelot_port->vid = 0;
+}
+
+static void ocelot_set_aggr_pgids(struct ocelot *ocelot)
+{
+ int i, port, lag;
+
+ /* Reset destination and aggregation PGIDS */
+ for (port = 0; port < ocelot->num_phys_ports; port++)
+ ocelot_write_rix(ocelot, BIT(port), ANA_PGID_PGID, port);
+
+ for (i = PGID_AGGR; i < PGID_SRC; i++)
+ ocelot_write_rix(ocelot, GENMASK(ocelot->num_phys_ports - 1, 0),
+ ANA_PGID_PGID, i);
+
+ /* Now, set PGIDs for each LAG */
+ for (lag = 0; lag < ocelot->num_phys_ports; lag++) {
+ unsigned long bond_mask;
+ int aggr_count = 0;
+ u8 aggr_idx[16];
+
+ bond_mask = ocelot->lags[lag];
+ if (!bond_mask)
+ continue;
+
+ for_each_set_bit(port, &bond_mask, ocelot->num_phys_ports) {
+ // Destination mask
+ ocelot_write_rix(ocelot, bond_mask,
+ ANA_PGID_PGID, port);
+ aggr_idx[aggr_count] = port;
+ aggr_count++;
+ }
+
+ for (i = PGID_AGGR; i < PGID_SRC; i++) {
+ u32 ac;
+
+ ac = ocelot_read_rix(ocelot, ANA_PGID_PGID, i);
+ ac &= ~bond_mask;
+ ac |= BIT(aggr_idx[i % aggr_count]);
+ ocelot_write_rix(ocelot, ac, ANA_PGID_PGID, i);
+ }
+ }
+}
+
+static void ocelot_setup_lag(struct ocelot *ocelot, int lag)
+{
+ unsigned long bond_mask = ocelot->lags[lag];
+ unsigned int p;
+
+ for_each_set_bit(p, &bond_mask, ocelot->num_phys_ports) {
+ u32 port_cfg = ocelot_read_gix(ocelot, ANA_PORT_PORT_CFG, p);
+
+ port_cfg &= ~ANA_PORT_PORT_CFG_PORTID_VAL_M;
+
+ /* Use lag port as logical port for port i */
+ ocelot_write_gix(ocelot, port_cfg |
+ ANA_PORT_PORT_CFG_PORTID_VAL(lag),
+ ANA_PORT_PORT_CFG, p);
+ }
+}
+
+static int ocelot_port_lag_join(struct ocelot_port *ocelot_port,
+ struct net_device *bond)
+{
+ struct ocelot *ocelot = ocelot_port->ocelot;
+ int p = ocelot_port->chip_port;
+ int lag, lp;
+ struct net_device *ndev;
+ u32 bond_mask = 0;
+
+ rcu_read_lock();
+ for_each_netdev_in_bond_rcu(bond, ndev) {
+ struct ocelot_port *port = netdev_priv(ndev);
+
+ bond_mask |= BIT(port->chip_port);
+ }
+ rcu_read_unlock();
+
+ lp = __ffs(bond_mask);
+
+ /* If the new port is the lowest one, use it as the logical port from
+ * now on
+ */
+ if (p == lp) {
+ lag = p;
+ ocelot->lags[p] = bond_mask;
+ bond_mask &= ~BIT(p);
+ if (bond_mask) {
+ lp = __ffs(bond_mask);
+ ocelot->lags[lp] = 0;
+ }
+ } else {
+ lag = lp;
+ ocelot->lags[lp] |= BIT(p);
+ }
+
+ ocelot_setup_lag(ocelot, lag);
+ ocelot_set_aggr_pgids(ocelot);
+
+ return 0;
+}
+
+static void ocelot_port_lag_leave(struct ocelot_port *ocelot_port,
+ struct net_device *bond)
+{
+ struct ocelot *ocelot = ocelot_port->ocelot;
+ int p = ocelot_port->chip_port;
+ u32 port_cfg;
+ int i;
+
+ /* Remove port from any lag */
+ for (i = 0; i < ocelot->num_phys_ports; i++)
+ ocelot->lags[i] &= ~BIT(ocelot_port->chip_port);
+
+ /* if it was the logical port of the lag, move the lag config to the
+ * next port
+ */
+ if (ocelot->lags[p]) {
+ int n = __ffs(ocelot->lags[p]);
+
+ ocelot->lags[n] = ocelot->lags[p];
+ ocelot->lags[p] = 0;
+
+ ocelot_setup_lag(ocelot, n);
+ }
+
+ port_cfg = ocelot_read_gix(ocelot, ANA_PORT_PORT_CFG, p);
+ port_cfg &= ~ANA_PORT_PORT_CFG_PORTID_VAL_M;
+ ocelot_write_gix(ocelot, port_cfg | ANA_PORT_PORT_CFG_PORTID_VAL(p),
+ ANA_PORT_PORT_CFG, p);
+
+ ocelot_set_aggr_pgids(ocelot);
}
/* Checks if the net_device instance given to us originate from our driver. */
else
ocelot_port_bridge_leave(ocelot_port,
info->upper_dev);
+
+ ocelot_vlan_port_apply(ocelot_port->ocelot,
+ ocelot_port);
+ }
+ if (netif_is_lag_master(info->upper_dev)) {
+ if (info->linking)
+ err = ocelot_port_lag_join(ocelot_port,
+ info->upper_dev);
+ else
+ ocelot_port_lag_leave(ocelot_port,
+ info->upper_dev);
}
break;
default:
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
int ret = 0;
+ if (event == NETDEV_PRECHANGEUPPER &&
+ netif_is_lag_master(info->upper_dev)) {
+ struct netdev_lag_upper_info *lag_upper_info = info->upper_info;
+ struct netlink_ext_ack *extack;
+
+ if (lag_upper_info->tx_type != NETDEV_LAG_TX_TYPE_HASH) {
+ extack = netdev_notifier_info_to_extack(&info->info);
+ NL_SET_ERR_MSG_MOD(extack, "LAG device using unsupported Tx type");
+
+ ret = -EINVAL;
+ goto notify;
+ }
+ }
+
if (netif_is_lag_master(dev)) {
struct net_device *slave;
struct list_head *iter;
dev->ethtool_ops = &ocelot_ethtool_ops;
dev->switchdev_ops = &ocelot_port_switchdev_ops;
+ dev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER;
+ dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
+
memcpy(dev->dev_addr, ocelot->base_mac, ETH_ALEN);
dev->dev_addr[ETH_ALEN - 1] += port;
ocelot_mact_learn(ocelot, PGID_CPU, dev->dev_addr, ocelot_port->pvid,
goto err_register_netdev;
}
+ /* Basic L2 initialization */
+ ocelot_vlan_port_apply(ocelot, ocelot_port);
+
return 0;
err_register_netdev:
int i, cpu = ocelot->num_phys_ports;
char queue_name[32];
+ ocelot->lags = devm_kcalloc(ocelot->dev, ocelot->num_phys_ports,
+ sizeof(u32), GFP_KERNEL);
+ if (!ocelot->lags)
+ return -ENOMEM;
+
ocelot->stats = devm_kcalloc(ocelot->dev,
ocelot->num_phys_ports * ocelot->num_stats,
sizeof(u64), GFP_KERNEL);
u8 num_cpu_ports;
struct ocelot_port **ports;
- u16 lags[16];
+ u32 *lags;
/* Keep track of the vlan port masks */
u32 vlan_mask[VLAN_N_VID];
info->port = (ifh[2] & GENMASK(14, 11)) >> 11;
info->cpuq = (ifh[3] & GENMASK(27, 20)) >> 20;
- info->tag_type = (ifh[3] & GENMASK(16, 16)) >> 16;
+ info->tag_type = (ifh[3] & BIT(16)) >> 16;
info->vid = ifh[3] & GENMASK(11, 0);
return 0;
#define pr_fmt(fmt) "NFP net bpf: " fmt
#include <linux/bug.h>
-#include <linux/kernel.h>
#include <linux/bpf.h>
#include <linux/filter.h>
+#include <linux/kernel.h>
#include <linux/pkt_cls.h>
+#include <linux/reciprocal_div.h>
#include <linux/unistd.h>
#include "main.h"
reg.dst_lmextn, reg.src_lmextn);
}
+static void
+__emit_mul(struct nfp_prog *nfp_prog, enum alu_dst_ab dst_ab, u16 areg,
+ enum mul_type type, enum mul_step step, u16 breg, bool swap,
+ bool wr_both, bool dst_lmextn, bool src_lmextn)
+{
+ u64 insn;
+
+ insn = OP_MUL_BASE |
+ FIELD_PREP(OP_MUL_A_SRC, areg) |
+ FIELD_PREP(OP_MUL_B_SRC, breg) |
+ FIELD_PREP(OP_MUL_STEP, step) |
+ FIELD_PREP(OP_MUL_DST_AB, dst_ab) |
+ FIELD_PREP(OP_MUL_SW, swap) |
+ FIELD_PREP(OP_MUL_TYPE, type) |
+ FIELD_PREP(OP_MUL_WR_AB, wr_both) |
+ FIELD_PREP(OP_MUL_SRC_LMEXTN, src_lmextn) |
+ FIELD_PREP(OP_MUL_DST_LMEXTN, dst_lmextn);
+
+ nfp_prog_push(nfp_prog, insn);
+}
+
+static void
+emit_mul(struct nfp_prog *nfp_prog, swreg lreg, enum mul_type type,
+ enum mul_step step, swreg rreg)
+{
+ struct nfp_insn_ur_regs reg;
+ u16 areg;
+ int err;
+
+ if (type == MUL_TYPE_START && step != MUL_STEP_NONE) {
+ nfp_prog->error = -EINVAL;
+ return;
+ }
+
+ if (step == MUL_LAST || step == MUL_LAST_2) {
+ /* When type is step and step Number is LAST or LAST2, left
+ * source is used as destination.
+ */
+ err = swreg_to_unrestricted(lreg, reg_none(), rreg, ®);
+ areg = reg.dst;
+ } else {
+ err = swreg_to_unrestricted(reg_none(), lreg, rreg, ®);
+ areg = reg.areg;
+ }
+
+ if (err) {
+ nfp_prog->error = err;
+ return;
+ }
+
+ __emit_mul(nfp_prog, reg.dst_ab, areg, type, step, reg.breg, reg.swap,
+ reg.wr_both, reg.dst_lmextn, reg.src_lmextn);
+}
+
static void
__emit_ld_field(struct nfp_prog *nfp_prog, enum shf_sc sc,
u8 areg, u8 bmask, u8 breg, u8 shift, bool imm8,
xfer_num = round_up(len, 4) / 4;
if (src_40bit_addr)
- addr40_offset(nfp_prog, meta->insn.src_reg, off, &src_base,
+ addr40_offset(nfp_prog, meta->insn.src_reg * 2, off, &src_base,
&off);
/* Setup PREV_ALU fields to override memory read length. */
SHF_SC_R_ROT, 16);
}
+static void
+wrp_mul_u32(struct nfp_prog *nfp_prog, swreg dst_hi, swreg dst_lo, swreg lreg,
+ swreg rreg, bool gen_high_half)
+{
+ emit_mul(nfp_prog, lreg, MUL_TYPE_START, MUL_STEP_NONE, rreg);
+ emit_mul(nfp_prog, lreg, MUL_TYPE_STEP_32x32, MUL_STEP_1, rreg);
+ emit_mul(nfp_prog, lreg, MUL_TYPE_STEP_32x32, MUL_STEP_2, rreg);
+ emit_mul(nfp_prog, lreg, MUL_TYPE_STEP_32x32, MUL_STEP_3, rreg);
+ emit_mul(nfp_prog, lreg, MUL_TYPE_STEP_32x32, MUL_STEP_4, rreg);
+ emit_mul(nfp_prog, dst_lo, MUL_TYPE_STEP_32x32, MUL_LAST, reg_none());
+ if (gen_high_half)
+ emit_mul(nfp_prog, dst_hi, MUL_TYPE_STEP_32x32, MUL_LAST_2,
+ reg_none());
+ else
+ wrp_immed(nfp_prog, dst_hi, 0);
+}
+
+static void
+wrp_mul_u16(struct nfp_prog *nfp_prog, swreg dst_hi, swreg dst_lo, swreg lreg,
+ swreg rreg)
+{
+ emit_mul(nfp_prog, lreg, MUL_TYPE_START, MUL_STEP_NONE, rreg);
+ emit_mul(nfp_prog, lreg, MUL_TYPE_STEP_16x16, MUL_STEP_1, rreg);
+ emit_mul(nfp_prog, lreg, MUL_TYPE_STEP_16x16, MUL_STEP_2, rreg);
+ emit_mul(nfp_prog, dst_lo, MUL_TYPE_STEP_16x16, MUL_LAST, reg_none());
+}
+
+static int
+wrp_mul(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
+ bool gen_high_half, bool ropnd_from_reg)
+{
+ swreg multiplier, multiplicand, dst_hi, dst_lo;
+ const struct bpf_insn *insn = &meta->insn;
+ u32 lopnd_max, ropnd_max;
+ u8 dst_reg;
+
+ dst_reg = insn->dst_reg;
+ multiplicand = reg_a(dst_reg * 2);
+ dst_hi = reg_both(dst_reg * 2 + 1);
+ dst_lo = reg_both(dst_reg * 2);
+ lopnd_max = meta->umax_dst;
+ if (ropnd_from_reg) {
+ multiplier = reg_b(insn->src_reg * 2);
+ ropnd_max = meta->umax_src;
+ } else {
+ u32 imm = insn->imm;
+
+ multiplier = ur_load_imm_any(nfp_prog, imm, imm_b(nfp_prog));
+ ropnd_max = imm;
+ }
+ if (lopnd_max > U16_MAX || ropnd_max > U16_MAX)
+ wrp_mul_u32(nfp_prog, dst_hi, dst_lo, multiplicand, multiplier,
+ gen_high_half);
+ else
+ wrp_mul_u16(nfp_prog, dst_hi, dst_lo, multiplicand, multiplier);
+
+ return 0;
+}
+
+static int wrp_div_imm(struct nfp_prog *nfp_prog, u8 dst, u64 imm)
+{
+ swreg dst_both = reg_both(dst), dst_a = reg_a(dst), dst_b = reg_a(dst);
+ struct reciprocal_value_adv rvalue;
+ u8 pre_shift, exp;
+ swreg magic;
+
+ if (imm > U32_MAX) {
+ wrp_immed(nfp_prog, dst_both, 0);
+ return 0;
+ }
+
+ /* NOTE: because we are using "reciprocal_value_adv" which doesn't
+ * support "divisor > (1u << 31)", we need to JIT separate NFP sequence
+ * to handle such case which actually equals to the result of unsigned
+ * comparison "dst >= imm" which could be calculated using the following
+ * NFP sequence:
+ *
+ * alu[--, dst, -, imm]
+ * immed[imm, 0]
+ * alu[dst, imm, +carry, 0]
+ *
+ */
+ if (imm > 1U << 31) {
+ swreg tmp_b = ur_load_imm_any(nfp_prog, imm, imm_b(nfp_prog));
+
+ emit_alu(nfp_prog, reg_none(), dst_a, ALU_OP_SUB, tmp_b);
+ wrp_immed(nfp_prog, imm_a(nfp_prog), 0);
+ emit_alu(nfp_prog, dst_both, imm_a(nfp_prog), ALU_OP_ADD_C,
+ reg_imm(0));
+ return 0;
+ }
+
+ rvalue = reciprocal_value_adv(imm, 32);
+ exp = rvalue.exp;
+ if (rvalue.is_wide_m && !(imm & 1)) {
+ pre_shift = fls(imm & -imm) - 1;
+ rvalue = reciprocal_value_adv(imm >> pre_shift, 32 - pre_shift);
+ } else {
+ pre_shift = 0;
+ }
+ magic = ur_load_imm_any(nfp_prog, rvalue.m, imm_b(nfp_prog));
+ if (imm == 1U << exp) {
+ emit_shf(nfp_prog, dst_both, reg_none(), SHF_OP_NONE, dst_b,
+ SHF_SC_R_SHF, exp);
+ } else if (rvalue.is_wide_m) {
+ wrp_mul_u32(nfp_prog, imm_both(nfp_prog), reg_none(), dst_a,
+ magic, true);
+ emit_alu(nfp_prog, dst_both, dst_a, ALU_OP_SUB,
+ imm_b(nfp_prog));
+ emit_shf(nfp_prog, dst_both, reg_none(), SHF_OP_NONE, dst_b,
+ SHF_SC_R_SHF, 1);
+ emit_alu(nfp_prog, dst_both, dst_a, ALU_OP_ADD,
+ imm_b(nfp_prog));
+ emit_shf(nfp_prog, dst_both, reg_none(), SHF_OP_NONE, dst_b,
+ SHF_SC_R_SHF, rvalue.sh - 1);
+ } else {
+ if (pre_shift)
+ emit_shf(nfp_prog, dst_both, reg_none(), SHF_OP_NONE,
+ dst_b, SHF_SC_R_SHF, pre_shift);
+ wrp_mul_u32(nfp_prog, dst_both, reg_none(), dst_a, magic, true);
+ emit_shf(nfp_prog, dst_both, reg_none(), SHF_OP_NONE,
+ dst_b, SHF_SC_R_SHF, rvalue.sh);
+ }
+
+ return 0;
+}
+
static int adjust_head(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
{
swreg tmp = imm_a(nfp_prog), tmp_len = imm_b(nfp_prog);
return 0;
}
+static int mul_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+ return wrp_mul(nfp_prog, meta, true, true);
+}
+
+static int mul_imm64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+ return wrp_mul(nfp_prog, meta, true, false);
+}
+
+static int div_imm64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+ const struct bpf_insn *insn = &meta->insn;
+
+ return wrp_div_imm(nfp_prog, insn->dst_reg * 2, insn->imm);
+}
+
+static int div_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+ /* NOTE: verifier hook has rejected cases for which verifier doesn't
+ * know whether the source operand is constant or not.
+ */
+ return wrp_div_imm(nfp_prog, meta->insn.dst_reg * 2, meta->umin_src);
+}
+
static int neg_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
{
const struct bpf_insn *insn = &meta->insn;
u8 dst, src;
dst = insn->dst_reg * 2;
- umin = meta->umin;
- umax = meta->umax;
+ umin = meta->umin_src;
+ umax = meta->umax_src;
if (umin == umax)
return __shl_imm64(nfp_prog, dst, umin);
u8 dst, src;
dst = insn->dst_reg * 2;
- umin = meta->umin;
- umax = meta->umax;
+ umin = meta->umin_src;
+ umax = meta->umax_src;
if (umin == umax)
return __shr_imm64(nfp_prog, dst, umin);
u8 dst, src;
dst = insn->dst_reg * 2;
- umin = meta->umin;
- umax = meta->umax;
+ umin = meta->umin_src;
+ umax = meta->umax_src;
if (umin == umax)
return __ashr_imm64(nfp_prog, dst, umin);
return wrp_alu32_imm(nfp_prog, meta, ALU_OP_SUB, !meta->insn.imm);
}
+static int mul_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+ return wrp_mul(nfp_prog, meta, false, true);
+}
+
+static int mul_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+ return wrp_mul(nfp_prog, meta, false, false);
+}
+
+static int div_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+ return div_reg64(nfp_prog, meta);
+}
+
+static int div_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+ return div_imm64(nfp_prog, meta);
+}
+
static int neg_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
{
u8 dst = meta->insn.dst_reg * 2;
[BPF_ALU64 | BPF_ADD | BPF_K] = add_imm64,
[BPF_ALU64 | BPF_SUB | BPF_X] = sub_reg64,
[BPF_ALU64 | BPF_SUB | BPF_K] = sub_imm64,
+ [BPF_ALU64 | BPF_MUL | BPF_X] = mul_reg64,
+ [BPF_ALU64 | BPF_MUL | BPF_K] = mul_imm64,
+ [BPF_ALU64 | BPF_DIV | BPF_X] = div_reg64,
+ [BPF_ALU64 | BPF_DIV | BPF_K] = div_imm64,
[BPF_ALU64 | BPF_NEG] = neg_reg64,
[BPF_ALU64 | BPF_LSH | BPF_X] = shl_reg64,
[BPF_ALU64 | BPF_LSH | BPF_K] = shl_imm64,
[BPF_ALU | BPF_ADD | BPF_K] = add_imm,
[BPF_ALU | BPF_SUB | BPF_X] = sub_reg,
[BPF_ALU | BPF_SUB | BPF_K] = sub_imm,
+ [BPF_ALU | BPF_MUL | BPF_X] = mul_reg,
+ [BPF_ALU | BPF_MUL | BPF_K] = mul_imm,
+ [BPF_ALU | BPF_DIV | BPF_X] = div_reg,
+ [BPF_ALU | BPF_DIV | BPF_K] = div_imm,
[BPF_ALU | BPF_NEG] = neg_reg,
[BPF_ALU | BPF_LSH | BPF_K] = shl_imm,
[BPF_ALU | BPF_END | BPF_X] = end_reg32,
if (!is_mbpf_load(ld_meta) || !is_mbpf_store(st_meta))
return false;
- if (ld_meta->ptr.type != PTR_TO_PACKET)
+ if (ld_meta->ptr.type != PTR_TO_PACKET &&
+ ld_meta->ptr.type != PTR_TO_MAP_VALUE)
return false;
if (st_meta->ptr.type != PTR_TO_PACKET)
struct bpf_prog *prog, struct netlink_ext_ack *extack)
{
bool running, xdp_running;
- int ret;
if (!nfp_net_ebpf_capable(nn))
return -EINVAL;
running = nn->dp.ctrl & NFP_NET_CFG_CTRL_BPF;
- xdp_running = running && nn->dp.bpf_offload_xdp;
+ xdp_running = running && nn->xdp_hw.prog;
if (!prog && !xdp_running)
return 0;
if (prog && running && !xdp_running)
return -EBUSY;
- ret = nfp_net_bpf_offload(nn, prog, running, extack);
- /* Stop offload if replace not possible */
- if (ret && prog)
- nfp_bpf_xdp_offload(app, nn, NULL, extack);
-
- nn->dp.bpf_offload_xdp = prog && !ret;
- return ret;
+ return nfp_net_bpf_offload(nn, prog, running, extack);
}
static const char *nfp_bpf_extra_cap(struct nfp_app *app, struct nfp_net *nn)
if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
return -EOPNOTSUPP;
+ if (tcf_block_shared(f->block))
+ return -EOPNOTSUPP;
+
switch (f->command) {
case TC_BLOCK_BIND:
return tcf_block_cb_register(f->block,
nfp_bpf_setup_tc_block_cb,
- nn, nn);
+ nn, nn, f->extack);
case TC_BLOCK_UNBIND:
tcf_block_cb_unregister(f->block,
nfp_bpf_setup_tc_block_cb,
* @func_id: function id for call instructions
* @arg1: arg1 for call instructions
* @arg2: arg2 for call instructions
- * @umin: copy of core verifier umin_value.
- * @umax: copy of core verifier umax_value.
+ * @umin_src: copy of core verifier umin_value for src opearnd.
+ * @umax_src: copy of core verifier umax_value for src operand.
+ * @umin_dst: copy of core verifier umin_value for dst opearnd.
+ * @umax_dst: copy of core verifier umax_value for dst operand.
* @off: index of first generated machine instruction (in nfp_prog.prog)
* @n: eBPF instruction number
* @flags: eBPF instruction extra optimization flags
struct bpf_reg_state arg1;
struct nfp_bpf_reg_state arg2;
};
- /* We are interested in range info for some operands,
- * for example, the shift amount.
+ /* We are interested in range info for operands of ALU
+ * operations. For example, shift amount, multiplicand and
+ * multiplier etc.
*/
struct {
- u64 umin;
- u64 umax;
+ u64 umin_src;
+ u64 umax_src;
+ u64 umin_dst;
+ u64 umax_dst;
};
};
unsigned int off;
return BPF_MODE(meta->insn.code);
}
+static inline bool is_mbpf_alu(const struct nfp_insn_meta *meta)
+{
+ return mbpf_class(meta) == BPF_ALU64 || mbpf_class(meta) == BPF_ALU;
+}
+
static inline bool is_mbpf_load(const struct nfp_insn_meta *meta)
{
return (meta->insn.code & ~BPF_SIZE_MASK) == (BPF_LDX | BPF_MEM);
return (meta->insn.code & ~BPF_SIZE_MASK) == (BPF_STX | BPF_XADD);
}
-static inline bool is_mbpf_indir_shift(const struct nfp_insn_meta *meta)
+static inline bool is_mbpf_mul(const struct nfp_insn_meta *meta)
{
- u8 code = meta->insn.code;
- bool is_alu, is_shift;
- u8 opclass, opcode;
-
- opclass = BPF_CLASS(code);
- is_alu = opclass == BPF_ALU64 || opclass == BPF_ALU;
- if (!is_alu)
- return false;
-
- opcode = BPF_OP(code);
- is_shift = opcode == BPF_LSH || opcode == BPF_RSH || opcode == BPF_ARSH;
- if (!is_shift)
- return false;
+ return is_mbpf_alu(meta) && mbpf_op(meta) == BPF_MUL;
+}
- return BPF_SRC(code) == BPF_X;
+static inline bool is_mbpf_div(const struct nfp_insn_meta *meta)
+{
+ return is_mbpf_alu(meta) && mbpf_op(meta) == BPF_DIV;
}
/**
meta->insn = prog[i];
meta->n = i;
- if (is_mbpf_indir_shift(meta))
- meta->umin = U64_MAX;
+ if (is_mbpf_alu(meta)) {
+ meta->umin_src = U64_MAX;
+ meta->umin_dst = U64_MAX;
+ }
list_add_tail(&meta->l, &nfp_prog->insns);
}
return nfp_bpf_check_ptr(nfp_prog, meta, env, meta->insn.dst_reg);
}
+static int
+nfp_bpf_check_alu(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
+ struct bpf_verifier_env *env)
+{
+ const struct bpf_reg_state *sreg =
+ cur_regs(env) + meta->insn.src_reg;
+ const struct bpf_reg_state *dreg =
+ cur_regs(env) + meta->insn.dst_reg;
+
+ meta->umin_src = min(meta->umin_src, sreg->umin_value);
+ meta->umax_src = max(meta->umax_src, sreg->umax_value);
+ meta->umin_dst = min(meta->umin_dst, dreg->umin_value);
+ meta->umax_dst = max(meta->umax_dst, dreg->umax_value);
+
+ /* NFP supports u16 and u32 multiplication.
+ *
+ * For ALU64, if either operand is beyond u32's value range, we reject
+ * it. One thing to note, if the source operand is BPF_K, then we need
+ * to check "imm" field directly, and we'd reject it if it is negative.
+ * Because for ALU64, "imm" (with s32 type) is expected to be sign
+ * extended to s64 which NFP mul doesn't support.
+ *
+ * For ALU32, it is fine for "imm" be negative though, because the
+ * result is 32-bits and there is no difference on the low halve of
+ * the result for signed/unsigned mul, so we will get correct result.
+ */
+ if (is_mbpf_mul(meta)) {
+ if (meta->umax_dst > U32_MAX) {
+ pr_vlog(env, "multiplier is not within u32 value range\n");
+ return -EINVAL;
+ }
+ if (mbpf_src(meta) == BPF_X && meta->umax_src > U32_MAX) {
+ pr_vlog(env, "multiplicand is not within u32 value range\n");
+ return -EINVAL;
+ }
+ if (mbpf_class(meta) == BPF_ALU64 &&
+ mbpf_src(meta) == BPF_K && meta->insn.imm < 0) {
+ pr_vlog(env, "sign extended multiplicand won't be within u32 value range\n");
+ return -EINVAL;
+ }
+ }
+
+ /* NFP doesn't have divide instructions, we support divide by constant
+ * through reciprocal multiplication. Given NFP support multiplication
+ * no bigger than u32, we'd require divisor and dividend no bigger than
+ * that as well.
+ *
+ * Also eBPF doesn't support signed divide and has enforced this on C
+ * language level by failing compilation. However LLVM assembler hasn't
+ * enforced this, so it is possible for negative constant to leak in as
+ * a BPF_K operand through assembly code, we reject such cases as well.
+ */
+ if (is_mbpf_div(meta)) {
+ if (meta->umax_dst > U32_MAX) {
+ pr_vlog(env, "dividend is not within u32 value range\n");
+ return -EINVAL;
+ }
+ if (mbpf_src(meta) == BPF_X) {
+ if (meta->umin_src != meta->umax_src) {
+ pr_vlog(env, "divisor is not constant\n");
+ return -EINVAL;
+ }
+ if (meta->umax_src > U32_MAX) {
+ pr_vlog(env, "divisor is not within u32 value range\n");
+ return -EINVAL;
+ }
+ }
+ if (mbpf_src(meta) == BPF_K && meta->insn.imm < 0) {
+ pr_vlog(env, "divide by negative constant is not supported\n");
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
+
static int
nfp_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx)
{
if (is_mbpf_xadd(meta))
return nfp_bpf_check_xadd(nfp_prog, meta, env);
- if (is_mbpf_indir_shift(meta)) {
- const struct bpf_reg_state *sreg =
- cur_regs(env) + meta->insn.src_reg;
-
- meta->umin = min(meta->umin, sreg->umin_value);
- meta->umax = max(meta->umax, sreg->umax_value);
- }
+ if (is_mbpf_alu(meta))
+ return nfp_bpf_check_alu(nfp_prog, meta, env);
return 0;
}
#include <linux/bitfield.h>
#include <net/pkt_cls.h>
#include <net/switchdev.h>
+#include <net/tc_act/tc_csum.h>
#include <net/tc_act/tc_gact.h>
#include <net/tc_act/tc_mirred.h>
#include <net/tc_act/tc_pedit.h>
#include "main.h"
#include "../nfp_net_repr.h"
+#define NFP_FL_SUPPORTED_IPV4_UDP_TUN_FLAGS (TUNNEL_CSUM | TUNNEL_KEY)
+
static void nfp_fl_pop_vlan(struct nfp_fl_pop_vlan *pop_vlan)
{
size_t act_size = sizeof(struct nfp_fl_pop_vlan);
size_t act_size = sizeof(struct nfp_fl_set_ipv4_udp_tun);
struct ip_tunnel_info *ip_tun = tcf_tunnel_info(action);
u32 tmp_set_ip_tun_type_index = 0;
+ struct flowi4 flow = {};
/* Currently support one pre-tunnel so index is always 0. */
int pretun_idx = 0;
+ struct rtable *rt;
struct net *net;
+ int err;
if (ip_tun->options_len)
return -EOPNOTSUPP;
set_tun->tun_type_index = cpu_to_be32(tmp_set_ip_tun_type_index);
set_tun->tun_id = ip_tun->key.tun_id;
- set_tun->ttl = net->ipv4.sysctl_ip_default_ttl;
+
+ /* Do a route lookup to determine ttl - if fails then use default.
+ * Note that CONFIG_INET is a requirement of CONFIG_NET_SWITCHDEV so
+ * must be defined here.
+ */
+ flow.daddr = ip_tun->key.u.ipv4.dst;
+ flow.flowi4_proto = IPPROTO_UDP;
+ rt = ip_route_output_key(net, &flow);
+ err = PTR_ERR_OR_ZERO(rt);
+ if (!err) {
+ set_tun->ttl = ip4_dst_hoplimit(&rt->dst);
+ ip_rt_put(rt);
+ } else {
+ set_tun->ttl = net->ipv4.sysctl_ip_default_ttl;
+ }
+
+ set_tun->tos = ip_tun->key.tos;
+
+ if (!(ip_tun->key.tun_flags & TUNNEL_KEY) ||
+ ip_tun->key.tun_flags & ~NFP_FL_SUPPORTED_IPV4_UDP_TUN_FLAGS)
+ return -EOPNOTSUPP;
+ set_tun->tun_flags = ip_tun->key.tun_flags;
/* Complete pre_tunnel action. */
pre_tun->ipv4_dst = ip_tun->key.u.ipv4.dst;
return 0;
}
+static u32 nfp_fl_csum_l4_to_flag(u8 ip_proto)
+{
+ switch (ip_proto) {
+ case 0:
+ /* Filter doesn't force proto match,
+ * both TCP and UDP will be updated if encountered
+ */
+ return TCA_CSUM_UPDATE_FLAG_TCP | TCA_CSUM_UPDATE_FLAG_UDP;
+ case IPPROTO_TCP:
+ return TCA_CSUM_UPDATE_FLAG_TCP;
+ case IPPROTO_UDP:
+ return TCA_CSUM_UPDATE_FLAG_UDP;
+ default:
+ /* All other protocols will be ignored by FW */
+ return 0;
+ }
+}
+
static int
-nfp_fl_pedit(const struct tc_action *action, char *nfp_action, int *a_len)
+nfp_fl_pedit(const struct tc_action *action, struct tc_cls_flower_offload *flow,
+ char *nfp_action, int *a_len, u32 *csum_updated)
{
struct nfp_fl_set_ipv6_addr set_ip6_dst, set_ip6_src;
struct nfp_fl_set_ip4_addrs set_ip_addr;
int idx, nkeys, err;
size_t act_size;
u32 offset, cmd;
+ u8 ip_proto = 0;
memset(&set_ip6_dst, 0, sizeof(set_ip6_dst));
memset(&set_ip6_src, 0, sizeof(set_ip6_src));
return err;
}
+ if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
+ struct flow_dissector_key_basic *basic;
+
+ basic = skb_flow_dissector_target(flow->dissector,
+ FLOW_DISSECTOR_KEY_BASIC,
+ flow->key);
+ ip_proto = basic->ip_proto;
+ }
+
if (set_eth.head.len_lw) {
act_size = sizeof(set_eth);
memcpy(nfp_action, &set_eth, act_size);
act_size = sizeof(set_ip_addr);
memcpy(nfp_action, &set_ip_addr, act_size);
*a_len += act_size;
+
+ /* Hardware will automatically fix IPv4 and TCP/UDP checksum. */
+ *csum_updated |= TCA_CSUM_UPDATE_FLAG_IPV4HDR |
+ nfp_fl_csum_l4_to_flag(ip_proto);
} else if (set_ip6_dst.head.len_lw && set_ip6_src.head.len_lw) {
/* TC compiles set src and dst IPv6 address as a single action,
* the hardware requires this to be 2 separate actions.
memcpy(&nfp_action[sizeof(set_ip6_src)], &set_ip6_dst,
act_size);
*a_len += act_size;
+
+ /* Hardware will automatically fix TCP/UDP checksum. */
+ *csum_updated |= nfp_fl_csum_l4_to_flag(ip_proto);
} else if (set_ip6_dst.head.len_lw) {
act_size = sizeof(set_ip6_dst);
memcpy(nfp_action, &set_ip6_dst, act_size);
*a_len += act_size;
+
+ /* Hardware will automatically fix TCP/UDP checksum. */
+ *csum_updated |= nfp_fl_csum_l4_to_flag(ip_proto);
} else if (set_ip6_src.head.len_lw) {
act_size = sizeof(set_ip6_src);
memcpy(nfp_action, &set_ip6_src, act_size);
*a_len += act_size;
+
+ /* Hardware will automatically fix TCP/UDP checksum. */
+ *csum_updated |= nfp_fl_csum_l4_to_flag(ip_proto);
} else if (set_tport.head.len_lw) {
act_size = sizeof(set_tport);
memcpy(nfp_action, &set_tport, act_size);
*a_len += act_size;
+
+ /* Hardware will automatically fix TCP/UDP checksum. */
+ *csum_updated |= nfp_fl_csum_l4_to_flag(ip_proto);
}
return 0;
struct nfp_fl_payload *nfp_fl, int *a_len,
struct net_device *netdev, bool last,
enum nfp_flower_tun_type *tun_type, int *tun_out_cnt,
- int *out_cnt)
+ int *out_cnt, u32 *csum_updated)
{
struct nfp_flower_priv *priv = app->priv;
struct nfp_fl_output *output;
int err, prelag_size;
+ /* If csum_updated has not been reset by now, it means HW will
+ * incorrectly update csums when they are not requested.
+ */
+ if (*csum_updated)
+ return -EOPNOTSUPP;
+
if (*a_len + sizeof(struct nfp_fl_output) > NFP_FL_MAX_A_SIZ)
return -EOPNOTSUPP;
static int
nfp_flower_loop_action(struct nfp_app *app, const struct tc_action *a,
+ struct tc_cls_flower_offload *flow,
struct nfp_fl_payload *nfp_fl, int *a_len,
struct net_device *netdev,
enum nfp_flower_tun_type *tun_type, int *tun_out_cnt,
- int *out_cnt)
+ int *out_cnt, u32 *csum_updated)
{
struct nfp_fl_set_ipv4_udp_tun *set_tun;
struct nfp_fl_pre_tunnel *pre_tun;
} else if (is_tcf_mirred_egress_redirect(a)) {
err = nfp_flower_output_action(app, a, nfp_fl, a_len, netdev,
true, tun_type, tun_out_cnt,
- out_cnt);
+ out_cnt, csum_updated);
if (err)
return err;
} else if (is_tcf_mirred_egress_mirror(a)) {
err = nfp_flower_output_action(app, a, nfp_fl, a_len, netdev,
false, tun_type, tun_out_cnt,
- out_cnt);
+ out_cnt, csum_updated);
if (err)
return err;
/* Tunnel decap is handled by default so accept action. */
return 0;
} else if (is_tcf_pedit(a)) {
- if (nfp_fl_pedit(a, &nfp_fl->action_data[*a_len], a_len))
+ if (nfp_fl_pedit(a, flow, &nfp_fl->action_data[*a_len],
+ a_len, csum_updated))
+ return -EOPNOTSUPP;
+ } else if (is_tcf_csum(a)) {
+ /* csum action requests recalc of something we have not fixed */
+ if (tcf_csum_update_flags(a) & ~*csum_updated)
return -EOPNOTSUPP;
+ /* If we will correctly fix the csum we can remove it from the
+ * csum update list. Which will later be used to check support.
+ */
+ *csum_updated &= ~tcf_csum_update_flags(a);
} else {
/* Currently we do not handle any other actions. */
return -EOPNOTSUPP;
int act_len, act_cnt, err, tun_out_cnt, out_cnt;
enum nfp_flower_tun_type tun_type;
const struct tc_action *a;
+ u32 csum_updated = 0;
LIST_HEAD(actions);
memset(nfp_flow->action_data, 0, NFP_FL_MAX_A_SIZ);
tcf_exts_to_list(flow->exts, &actions);
list_for_each_entry(a, &actions, list) {
- err = nfp_flower_loop_action(app, a, nfp_flow, &act_len, netdev,
- &tun_type, &tun_out_cnt, &out_cnt);
+ err = nfp_flower_loop_action(app, a, flow, nfp_flow, &act_len,
+ netdev, &tun_type, &tun_out_cnt,
+ &out_cnt, &csum_updated);
if (err)
return err;
act_cnt++;
__be16 reserved;
__be64 tun_id __packed;
__be32 tun_type_index;
- __be16 reserved2;
+ __be16 tun_flags;
u8 ttl;
- u8 reserved3;
+ u8 tos;
__be32 extra[2];
};
if (lag_upper_info &&
lag_upper_info->tx_type != NETDEV_LAG_TX_TYPE_ACTIVEBACKUP &&
(lag_upper_info->tx_type != NETDEV_LAG_TX_TYPE_HASH ||
- (lag_upper_info->hash_type != NETDEV_LAG_HASH_L34 &&
- lag_upper_info->hash_type != NETDEV_LAG_HASH_E34))) {
+ (lag_upper_info->hash_type != NETDEV_LAG_HASH_L34 &&
+ lag_upper_info->hash_type != NETDEV_LAG_HASH_E34 &&
+ lag_upper_info->hash_type != NETDEV_LAG_HASH_UNKNOWN))) {
can_offload = false;
nfp_flower_cmsg_warn(priv->app,
"Unable to offload tx_type %u hash %u\n",
struct nfp_fl_mask_id {
struct circ_buf mask_id_free_list;
- struct timespec64 *last_used;
+ ktime_t *last_used;
u8 init_unallocated;
};
NFP_FLOWER_MASK_MPLS_Q;
frame->mpls_lse = cpu_to_be32(t_mpls);
+ } else if (dissector_uses_key(flow->dissector,
+ FLOW_DISSECTOR_KEY_BASIC)) {
+ /* Check for mpls ether type and set NFP_FLOWER_MASK_MPLS_Q
+ * bit, which indicates an mpls ether type but without any
+ * mpls fields.
+ */
+ struct flow_dissector_key_basic *key_basic;
+
+ key_basic = skb_flow_dissector_target(flow->dissector,
+ FLOW_DISSECTOR_KEY_BASIC,
+ flow->key);
+ if (key_basic->n_proto == cpu_to_be16(ETH_P_MPLS_UC) ||
+ key_basic->n_proto == cpu_to_be16(ETH_P_MPLS_MC))
+ frame->mpls_lse = cpu_to_be32(NFP_FLOWER_MASK_MPLS_Q);
}
}
{
struct nfp_flower_priv *priv = app->priv;
struct circ_buf *ring;
- struct timespec64 now;
ring = &priv->mask_ids.mask_id_free_list;
/* Checking if buffer is full. */
ring->head = (ring->head + NFP_FLOWER_MASK_ELEMENT_RS) %
(NFP_FLOWER_MASK_ENTRY_RS * NFP_FLOWER_MASK_ELEMENT_RS);
- getnstimeofday64(&now);
- priv->mask_ids.last_used[mask_id] = now;
+ priv->mask_ids.last_used[mask_id] = ktime_get();
return 0;
}
static int nfp_mask_alloc(struct nfp_app *app, u8 *mask_id)
{
struct nfp_flower_priv *priv = app->priv;
- struct timespec64 delta, now;
+ ktime_t reuse_timeout;
struct circ_buf *ring;
u8 temp_id, freed_id;
memcpy(&temp_id, &ring->buf[ring->tail], NFP_FLOWER_MASK_ELEMENT_RS);
*mask_id = temp_id;
- getnstimeofday64(&now);
- delta = timespec64_sub(now, priv->mask_ids.last_used[*mask_id]);
+ reuse_timeout = ktime_add_ns(priv->mask_ids.last_used[*mask_id],
+ NFP_FL_MASK_REUSE_TIME_NS);
- if (timespec64_to_ns(&delta) < NFP_FL_MASK_REUSE_TIME_NS)
+ if (ktime_before(ktime_get(), reuse_timeout))
goto err_not_found;
memcpy(&ring->buf[ring->tail], &freed_id, NFP_FLOWER_MASK_ELEMENT_RS);
case cpu_to_be16(ETH_P_ARP):
return -EOPNOTSUPP;
+ case cpu_to_be16(ETH_P_MPLS_UC):
+ case cpu_to_be16(ETH_P_MPLS_MC):
+ if (!(key_layer & NFP_FLOWER_LAYER_MAC)) {
+ key_layer |= NFP_FLOWER_LAYER_MAC;
+ key_size += sizeof(struct nfp_flower_mac_mpls);
+ }
+ break;
+
/* Will be included in layer 2. */
case cpu_to_be16(ETH_P_8021Q):
break;
return nfp_flower_del_offload(app, netdev, flower, egress);
case TC_CLSFLOWER_STATS:
return nfp_flower_get_stats(app, netdev, flower, egress);
+ default:
+ return -EOPNOTSUPP;
}
-
- return -EOPNOTSUPP;
}
int nfp_flower_setup_tc_egress_cb(enum tc_setup_type type, void *type_data,
if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
return -EOPNOTSUPP;
+ if (tcf_block_shared(f->block))
+ return -EOPNOTSUPP;
+
switch (f->command) {
case TC_BLOCK_BIND:
return tcf_block_cb_register(f->block,
nfp_flower_setup_tc_block_cb,
- repr, repr);
+ repr, repr, f->extack);
case TC_BLOCK_UNBIND:
tcf_block_cb_unregister(f->block,
nfp_flower_setup_tc_block_cb,
return (read_offset & ~NFP_IND_ME_CTX_PTR_BASE_MASK) | NFP_CSR_CTX_PTR;
}
+enum mul_type {
+ MUL_TYPE_START = 0x00,
+ MUL_TYPE_STEP_24x8 = 0x01,
+ MUL_TYPE_STEP_16x16 = 0x02,
+ MUL_TYPE_STEP_32x32 = 0x03,
+};
+
+enum mul_step {
+ MUL_STEP_1 = 0x00,
+ MUL_STEP_NONE = MUL_STEP_1,
+ MUL_STEP_2 = 0x01,
+ MUL_STEP_3 = 0x02,
+ MUL_STEP_4 = 0x03,
+ MUL_LAST = 0x04,
+ MUL_LAST_2 = 0x05,
+};
+
+#define OP_MUL_BASE 0x0f800000000ULL
+#define OP_MUL_A_SRC 0x000000003ffULL
+#define OP_MUL_B_SRC 0x000000ffc00ULL
+#define OP_MUL_STEP 0x00000700000ULL
+#define OP_MUL_DST_AB 0x00000800000ULL
+#define OP_MUL_SW 0x00040000000ULL
+#define OP_MUL_TYPE 0x00180000000ULL
+#define OP_MUL_WR_AB 0x20000000000ULL
+#define OP_MUL_SRC_LMEXTN 0x40000000000ULL
+#define OP_MUL_DST_LMEXTN 0x80000000000ULL
+
#endif
* @dev: Backpointer to struct device
* @netdev: Backpointer to net_device structure
* @is_vf: Is the driver attached to a VF?
- * @bpf_offload_xdp: Offloaded BPF program is XDP
* @chained_metadata_format: Firemware will use new metadata format
* @rx_dma_dir: Mapping direction for RX buffers
* @rx_dma_off: Offset at which DMA packets (for XDP headroom)
struct net_device *netdev;
u8 is_vf:1;
- u8 bpf_offload_xdp:1;
u8 chained_metadata_format:1;
u8 rx_dma_dir;
* @rss_cfg: RSS configuration
* @rss_key: RSS secret key
* @rss_itbl: RSS indirection table
- * @xdp_flags: Flags with which XDP prog was loaded
- * @xdp_prog: XDP prog (for ctrl path, both DRV and HW modes)
+ * @xdp: Information about the driver XDP program
+ * @xdp_hw: Information about the HW XDP program
* @max_r_vecs: Number of allocated interrupt vectors for RX/TX
* @max_tx_rings: Maximum number of TX rings supported by the Firmware
* @max_rx_rings: Maximum number of RX rings supported by the Firmware
u8 rss_key[NFP_NET_CFG_RSS_KEY_SZ];
u8 rss_itbl[NFP_NET_CFG_RSS_ITBL_SZ];
- u32 xdp_flags;
- struct bpf_prog *xdp_prog;
+ struct xdp_attachment_info xdp;
+ struct xdp_attachment_info xdp_hw;
unsigned int max_tx_rings;
unsigned int max_rx_rings;
/**
* nfp_net_tx_complete() - Handled completed TX packets
- * @tx_ring: TX ring structure
+ * @tx_ring: TX ring structure
+ * @budget: NAPI budget (only used as bool to determine if in NAPI context)
*
* Return: Number of completed TX descriptors
*/
-static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring)
+static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring, int budget)
{
struct nfp_net_r_vector *r_vec = tx_ring->r_vec;
struct nfp_net_dp *dp = &r_vec->nfp_net->dp;
/* check for last gather fragment */
if (fidx == nr_frags - 1)
- dev_consume_skb_any(skb);
+ napi_consume_skb(skb, budget);
tx_ring->txbufs[idx].dma_addr = 0;
tx_ring->txbufs[idx].skb = NULL;
}
}
- if (xdp_prog && !(rxd->rxd.flags & PCIE_DESC_RX_BPF &&
- dp->bpf_offload_xdp) && !meta.portid) {
+ if (xdp_prog && !meta.portid) {
void *orig_data = rxbuf->frag + pkt_off;
unsigned int dma_off;
int act;
unsigned int pkts_polled = 0;
if (r_vec->tx_ring)
- nfp_net_tx_complete(r_vec->tx_ring);
+ nfp_net_tx_complete(r_vec->tx_ring, budget);
if (r_vec->rx_ring)
pkts_polled = nfp_net_rx(r_vec->rx_ring, budget);
struct nfp_net_r_vector *r_vec = (void *)arg;
spin_lock_bh(&r_vec->lock);
- nfp_net_tx_complete(r_vec->tx_ring);
+ nfp_net_tx_complete(r_vec->tx_ring, 0);
__nfp_ctrl_tx_queued(r_vec);
spin_unlock_bh(&r_vec->lock);
return nfp_net_reconfig_mbox(nn, NFP_NET_CFG_MBOX_CMD_CTAG_FILTER_KILL);
}
+#ifdef CONFIG_NET_POLL_CONTROLLER
+static void nfp_net_netpoll(struct net_device *netdev)
+{
+ struct nfp_net *nn = netdev_priv(netdev);
+ int i;
+
+ /* nfp_net's NAPIs are statically allocated so even if there is a race
+ * with reconfig path this will simply try to schedule some disabled
+ * NAPI instances.
+ */
+ for (i = 0; i < nn->dp.num_stack_tx_rings; i++)
+ napi_schedule_irqoff(&nn->r_vecs[i].napi);
+}
+#endif
+
static void nfp_net_stat64(struct net_device *netdev,
struct rtnl_link_stats64 *stats)
{
nfp_net_set_vxlan_port(nn, idx, 0);
}
-static int
-nfp_net_xdp_setup_drv(struct nfp_net *nn, struct bpf_prog *prog,
- struct netlink_ext_ack *extack)
+static int nfp_net_xdp_setup_drv(struct nfp_net *nn, struct netdev_bpf *bpf)
{
+ struct bpf_prog *prog = bpf->prog;
struct nfp_net_dp *dp;
+ int err;
+
+ if (!xdp_attachment_flags_ok(&nn->xdp, bpf))
+ return -EBUSY;
if (!prog == !nn->dp.xdp_prog) {
WRITE_ONCE(nn->dp.xdp_prog, prog);
+ xdp_attachment_setup(&nn->xdp, bpf);
return 0;
}
dp->rx_dma_off = prog ? XDP_PACKET_HEADROOM - nn->dp.rx_offset : 0;
/* We need RX reconfig to remap the buffers (BIDIR vs FROM_DEV) */
- return nfp_net_ring_reconfig(nn, dp, extack);
+ err = nfp_net_ring_reconfig(nn, dp, bpf->extack);
+ if (err)
+ return err;
+
+ xdp_attachment_setup(&nn->xdp, bpf);
+ return 0;
}
-static int
-nfp_net_xdp_setup(struct nfp_net *nn, struct bpf_prog *prog, u32 flags,
- struct netlink_ext_ack *extack)
+static int nfp_net_xdp_setup_hw(struct nfp_net *nn, struct netdev_bpf *bpf)
{
- struct bpf_prog *drv_prog, *offload_prog;
int err;
- if (nn->xdp_prog && (flags ^ nn->xdp_flags) & XDP_FLAGS_MODES)
+ if (!xdp_attachment_flags_ok(&nn->xdp_hw, bpf))
return -EBUSY;
- /* Load both when no flags set to allow easy activation of driver path
- * when program is replaced by one which can't be offloaded.
- */
- drv_prog = flags & XDP_FLAGS_HW_MODE ? NULL : prog;
- offload_prog = flags & XDP_FLAGS_DRV_MODE ? NULL : prog;
-
- err = nfp_net_xdp_setup_drv(nn, drv_prog, extack);
+ err = nfp_app_xdp_offload(nn->app, nn, bpf->prog, bpf->extack);
if (err)
return err;
- err = nfp_app_xdp_offload(nn->app, nn, offload_prog, extack);
- if (err && flags & XDP_FLAGS_HW_MODE)
- return err;
-
- if (nn->xdp_prog)
- bpf_prog_put(nn->xdp_prog);
- nn->xdp_prog = prog;
- nn->xdp_flags = flags;
-
+ xdp_attachment_setup(&nn->xdp_hw, bpf);
return 0;
}
switch (xdp->command) {
case XDP_SETUP_PROG:
+ return nfp_net_xdp_setup_drv(nn, xdp);
case XDP_SETUP_PROG_HW:
- return nfp_net_xdp_setup(nn, xdp->prog, xdp->flags,
- xdp->extack);
+ return nfp_net_xdp_setup_hw(nn, xdp);
case XDP_QUERY_PROG:
- xdp->prog_attached = !!nn->xdp_prog;
- if (nn->dp.bpf_offload_xdp)
- xdp->prog_attached = XDP_ATTACHED_HW;
- xdp->prog_id = nn->xdp_prog ? nn->xdp_prog->aux->id : 0;
- xdp->prog_flags = nn->xdp_prog ? nn->xdp_flags : 0;
- return 0;
+ return xdp_attachment_query(&nn->xdp, xdp);
+ case XDP_QUERY_PROG_HW:
+ return xdp_attachment_query(&nn->xdp_hw, xdp);
default:
return nfp_app_bpf(nn->app, nn, xdp);
}
.ndo_get_stats64 = nfp_net_stat64,
.ndo_vlan_rx_add_vid = nfp_net_vlan_rx_add_vid,
.ndo_vlan_rx_kill_vid = nfp_net_vlan_rx_kill_vid,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+ .ndo_poll_controller = nfp_net_netpoll,
+#endif
.ndo_set_vf_mac = nfp_app_set_vf_mac,
.ndo_set_vf_vlan = nfp_app_set_vf_vlan,
.ndo_set_vf_spoofchk = nfp_app_set_vf_spoofchk,
static void
nfp_app_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo)
{
- struct nfp_app *app;
-
- app = nfp_app_from_netdev(netdev);
- if (!app)
- return;
+ struct nfp_app *app = nfp_app_from_netdev(netdev);
+ strlcpy(drvinfo->bus_info, pci_name(app->pdev),
+ sizeof(drvinfo->bus_info));
nfp_get_drvinfo(app, app->pdev, "*", drvinfo);
}
{
struct nfp_net *nn = netdev_priv(netdev);
- return NN_RVEC_GATHER_STATS + nn->dp.num_r_vecs * NN_RVEC_PER_Q_STATS;
+ return NN_RVEC_GATHER_STATS + nn->max_r_vecs * NN_RVEC_PER_Q_STATS;
}
static u8 *nfp_vnic_get_sw_stats_strings(struct net_device *netdev, u8 *data)
struct nfp_net *nn = netdev_priv(netdev);
int i;
- for (i = 0; i < nn->dp.num_r_vecs; i++) {
+ for (i = 0; i < nn->max_r_vecs; i++) {
data = nfp_pr_et(data, "rvec_%u_rx_pkts", i);
data = nfp_pr_et(data, "rvec_%u_tx_pkts", i);
data = nfp_pr_et(data, "rvec_%u_tx_busy", i);
u64 tmp[NN_RVEC_GATHER_STATS];
unsigned int i, j;
- for (i = 0; i < nn->dp.num_r_vecs; i++) {
+ for (i = 0; i < nn->max_r_vecs; i++) {
unsigned int start;
do {
return data;
}
-static unsigned int
-nfp_vnic_get_hw_stats_count(unsigned int rx_rings, unsigned int tx_rings)
+static unsigned int nfp_vnic_get_hw_stats_count(unsigned int num_vecs)
{
- return NN_ET_GLOBAL_STATS_LEN + (rx_rings + tx_rings) * 2;
+ return NN_ET_GLOBAL_STATS_LEN + num_vecs * 4;
}
static u8 *
-nfp_vnic_get_hw_stats_strings(u8 *data, unsigned int rx_rings,
- unsigned int tx_rings, bool repr)
+nfp_vnic_get_hw_stats_strings(u8 *data, unsigned int num_vecs, bool repr)
{
int swap_off, i;
for (i = NN_ET_SWITCH_STATS_LEN * 2; i < NN_ET_GLOBAL_STATS_LEN; i++)
data = nfp_pr_et(data, nfp_net_et_stats[i].name);
- for (i = 0; i < tx_rings; i++) {
- data = nfp_pr_et(data, "txq_%u_pkts", i);
- data = nfp_pr_et(data, "txq_%u_bytes", i);
- }
-
- for (i = 0; i < rx_rings; i++) {
+ for (i = 0; i < num_vecs; i++) {
data = nfp_pr_et(data, "rxq_%u_pkts", i);
data = nfp_pr_et(data, "rxq_%u_bytes", i);
+ data = nfp_pr_et(data, "txq_%u_pkts", i);
+ data = nfp_pr_et(data, "txq_%u_bytes", i);
}
return data;
}
static u64 *
-nfp_vnic_get_hw_stats(u64 *data, u8 __iomem *mem,
- unsigned int rx_rings, unsigned int tx_rings)
+nfp_vnic_get_hw_stats(u64 *data, u8 __iomem *mem, unsigned int num_vecs)
{
unsigned int i;
for (i = 0; i < NN_ET_GLOBAL_STATS_LEN; i++)
*data++ = readq(mem + nfp_net_et_stats[i].off);
- for (i = 0; i < tx_rings; i++) {
- *data++ = readq(mem + NFP_NET_CFG_TXR_STATS(i));
- *data++ = readq(mem + NFP_NET_CFG_TXR_STATS(i) + 8);
- }
-
- for (i = 0; i < rx_rings; i++) {
+ for (i = 0; i < num_vecs; i++) {
*data++ = readq(mem + NFP_NET_CFG_RXR_STATS(i));
*data++ = readq(mem + NFP_NET_CFG_RXR_STATS(i) + 8);
+ *data++ = readq(mem + NFP_NET_CFG_TXR_STATS(i));
+ *data++ = readq(mem + NFP_NET_CFG_TXR_STATS(i) + 8);
}
return data;
switch (stringset) {
case ETH_SS_STATS:
data = nfp_vnic_get_sw_stats_strings(netdev, data);
- data = nfp_vnic_get_hw_stats_strings(data, nn->dp.num_rx_rings,
- nn->dp.num_tx_rings,
+ data = nfp_vnic_get_hw_stats_strings(data, nn->max_r_vecs,
false);
data = nfp_mac_get_stats_strings(netdev, data);
data = nfp_app_port_get_stats_strings(nn->port, data);
struct nfp_net *nn = netdev_priv(netdev);
data = nfp_vnic_get_sw_stats(netdev, data);
- data = nfp_vnic_get_hw_stats(data, nn->dp.ctrl_bar,
- nn->dp.num_rx_rings, nn->dp.num_tx_rings);
+ data = nfp_vnic_get_hw_stats(data, nn->dp.ctrl_bar, nn->max_r_vecs);
data = nfp_mac_get_stats(netdev, data);
data = nfp_app_port_get_stats(nn->port, data);
}
switch (sset) {
case ETH_SS_STATS:
return nfp_vnic_get_sw_stats_count(netdev) +
- nfp_vnic_get_hw_stats_count(nn->dp.num_rx_rings,
- nn->dp.num_tx_rings) +
+ nfp_vnic_get_hw_stats_count(nn->max_r_vecs) +
nfp_mac_get_stats_count(netdev) +
nfp_app_port_get_stats_count(nn->port);
default:
switch (stringset) {
case ETH_SS_STATS:
if (nfp_port_is_vnic(port))
- data = nfp_vnic_get_hw_stats_strings(data, 0, 0, true);
+ data = nfp_vnic_get_hw_stats_strings(data, 0, true);
else
data = nfp_mac_get_stats_strings(netdev, data);
data = nfp_app_port_get_stats_strings(port, data);
struct nfp_port *port = nfp_port_from_netdev(netdev);
if (nfp_port_is_vnic(port))
- data = nfp_vnic_get_hw_stats(data, port->vnic, 0, 0);
+ data = nfp_vnic_get_hw_stats(data, port->vnic, 0);
else
data = nfp_mac_get_stats(netdev, data);
data = nfp_app_port_get_stats(port, data);
switch (sset) {
case ETH_SS_STATS:
if (nfp_port_is_vnic(port))
- count = nfp_vnic_get_hw_stats_count(0, 0);
+ count = nfp_vnic_get_hw_stats_count(0);
else
count = nfp_mac_get_stats_count(netdev);
count += nfp_app_port_get_stats_count(port);
kfree(nfp);
}
-static void nfp6000_read_serial(struct device *dev, u8 *serial)
+static int nfp6000_read_serial(struct device *dev, u8 *serial)
{
struct pci_dev *pdev = to_pci_dev(dev);
int pos;
pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_DSN);
if (!pos) {
- memset(serial, 0, NFP_SERIAL_LEN);
- return;
+ dev_err(dev, "can't find PCIe Serial Number Capability\n");
+ return -EINVAL;
}
pci_read_config_dword(pdev, pos + 4, ®);
put_unaligned_be16(reg >> 16, serial + 4);
pci_read_config_dword(pdev, pos + 8, ®);
put_unaligned_be32(reg, serial);
+
+ return 0;
}
-static u16 nfp6000_get_interface(struct device *dev)
+static int nfp6000_get_interface(struct device *dev)
{
struct pci_dev *pdev = to_pci_dev(dev);
int pos;
u32 reg;
pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_DSN);
- if (!pos)
- return NFP_CPP_INTERFACE(NFP_CPP_INTERFACE_TYPE_PCI, 0, 0xff);
+ if (!pos) {
+ dev_err(dev, "can't find PCIe Serial Number Capability\n");
+ return -EINVAL;
+ }
pci_read_config_dword(pdev, pos + 4, ®);
int (*init)(struct nfp_cpp *cpp);
void (*free)(struct nfp_cpp *cpp);
- void (*read_serial)(struct device *dev, u8 *serial);
- u16 (*get_interface)(struct device *dev);
+ int (*read_serial)(struct device *dev, u8 *serial);
+ int (*get_interface)(struct device *dev);
int (*area_init)(struct nfp_cpp_area *area,
u32 dest, unsigned long long address,
{
const u32 arm = NFP_CPP_ID(NFP_CPP_TARGET_ARM, NFP_CPP_ACTION_RW, 0);
struct nfp_cpp *cpp;
+ int ifc, err;
u32 mask[2];
u32 xpbaddr;
size_t tgt;
- int err;
cpp = kzalloc(sizeof(*cpp), GFP_KERNEL);
if (!cpp) {
cpp->op = ops;
cpp->priv = priv;
- cpp->interface = ops->get_interface(parent);
- if (ops->read_serial)
- ops->read_serial(parent, cpp->serial);
+
+ ifc = ops->get_interface(parent);
+ if (ifc < 0) {
+ err = ifc;
+ goto err_free_cpp;
+ }
+ cpp->interface = ifc;
+ if (ops->read_serial) {
+ err = ops->read_serial(parent, cpp->serial);
+ if (err)
+ goto err_free_cpp;
+ }
+
rwlock_init(&cpp->resource_lock);
init_waitqueue_head(&cpp->waitq);
lockdep_set_class(&cpp->resource_lock, &nfp_cpp_resource_lock_key);
err = device_register(&cpp->dev);
if (err < 0) {
put_device(&cpp->dev);
- goto err_dev;
+ goto err_free_cpp;
}
dev_set_drvdata(&cpp->dev, cpp);
err_out:
device_unregister(&cpp->dev);
-err_dev:
+err_free_cpp:
kfree(cpp);
err_malloc:
return ERR_PTR(err);
err = nfp_cpp_read(cpp, nfp_resource_cpp_id(state->res),
nfp_resource_address(state->res),
fwinf, sizeof(*fwinf));
- if (err < sizeof(*fwinf))
+ if (err < (int)sizeof(*fwinf))
goto err_release;
if (!nffw_res_flg_init_get(fwinf))
obj-$(CONFIG_PCH_GBE) += pch_gbe.o
pch_gbe-y := pch_gbe_phy.o pch_gbe_ethtool.o pch_gbe_param.o
-pch_gbe-y += pch_gbe_api.o pch_gbe_main.o
+pch_gbe-y += pch_gbe_main.o
#define PCH_GBE_FC_FULL 3
#define PCH_GBE_FC_DEFAULT PCH_GBE_FC_FULL
-
-struct pch_gbe_hw;
-/**
- * struct pch_gbe_functions - HAL APi function pointer
- * @get_bus_info: for pch_gbe_hal_get_bus_info
- * @init_hw: for pch_gbe_hal_init_hw
- * @read_phy_reg: for pch_gbe_hal_read_phy_reg
- * @write_phy_reg: for pch_gbe_hal_write_phy_reg
- * @reset_phy: for pch_gbe_hal_phy_hw_reset
- * @sw_reset_phy: for pch_gbe_hal_phy_sw_reset
- * @power_up_phy: for pch_gbe_hal_power_up_phy
- * @power_down_phy: for pch_gbe_hal_power_down_phy
- * @read_mac_addr: for pch_gbe_hal_read_mac_addr
- */
-struct pch_gbe_functions {
- void (*get_bus_info) (struct pch_gbe_hw *);
- s32 (*init_hw) (struct pch_gbe_hw *);
- s32 (*read_phy_reg) (struct pch_gbe_hw *, u32, u16 *);
- s32 (*write_phy_reg) (struct pch_gbe_hw *, u32, u16);
- void (*reset_phy) (struct pch_gbe_hw *);
- void (*sw_reset_phy) (struct pch_gbe_hw *);
- void (*power_up_phy) (struct pch_gbe_hw *hw);
- void (*power_down_phy) (struct pch_gbe_hw *hw);
- s32 (*read_mac_addr) (struct pch_gbe_hw *);
-};
-
/**
* struct pch_gbe_mac_info - MAC information
* @addr[6]: Store the MAC address
u16 autoneg_advertised;
};
-/*!
- * @ingroup Gigabit Ether driver Layer
- * @struct pch_gbe_bus_info
- * @brief Bus information
- */
-struct pch_gbe_bus_info {
- u8 type;
- u8 speed;
- u8 width;
-};
-
/*!
* @ingroup Gigabit Ether driver Layer
* @struct pch_gbe_hw
struct pch_gbe_regs __iomem *reg;
spinlock_t miim_lock;
- const struct pch_gbe_functions *func;
struct pch_gbe_mac_info mac;
struct pch_gbe_phy_info phy;
- struct pch_gbe_bus_info bus;
};
/**
/* pch_gbe_mac.c */
s32 pch_gbe_mac_force_mac_fc(struct pch_gbe_hw *hw);
-s32 pch_gbe_mac_read_mac_addr(struct pch_gbe_hw *hw);
u16 pch_gbe_mac_ctrl_miim(struct pch_gbe_hw *hw, u32 addr, u32 dir, u32 reg,
u16 data);
#endif /* _PCH_GBE_H_ */
+++ /dev/null
-/*
- * Copyright (C) 1999 - 2010 Intel Corporation.
- * Copyright (C) 2010 OKI SEMICONDUCTOR Co., LTD.
- *
- * This code was derived from the Intel e1000e Linux driver.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
- */
-#include "pch_gbe.h"
-#include "pch_gbe_phy.h"
-#include "pch_gbe_api.h"
-
-/* bus type values */
-#define pch_gbe_bus_type_unknown 0
-#define pch_gbe_bus_type_pci 1
-#define pch_gbe_bus_type_pcix 2
-#define pch_gbe_bus_type_pci_express 3
-#define pch_gbe_bus_type_reserved 4
-
-/* bus speed values */
-#define pch_gbe_bus_speed_unknown 0
-#define pch_gbe_bus_speed_33 1
-#define pch_gbe_bus_speed_66 2
-#define pch_gbe_bus_speed_100 3
-#define pch_gbe_bus_speed_120 4
-#define pch_gbe_bus_speed_133 5
-#define pch_gbe_bus_speed_2500 6
-#define pch_gbe_bus_speed_reserved 7
-
-/* bus width values */
-#define pch_gbe_bus_width_unknown 0
-#define pch_gbe_bus_width_pcie_x1 1
-#define pch_gbe_bus_width_pcie_x2 2
-#define pch_gbe_bus_width_pcie_x4 4
-#define pch_gbe_bus_width_32 5
-#define pch_gbe_bus_width_64 6
-#define pch_gbe_bus_width_reserved 7
-
-/**
- * pch_gbe_plat_get_bus_info - Obtain bus information for adapter
- * @hw: Pointer to the HW structure
- */
-static void pch_gbe_plat_get_bus_info(struct pch_gbe_hw *hw)
-{
- hw->bus.type = pch_gbe_bus_type_pci_express;
- hw->bus.speed = pch_gbe_bus_speed_2500;
- hw->bus.width = pch_gbe_bus_width_pcie_x1;
-}
-
-/**
- * pch_gbe_plat_init_hw - Initialize hardware
- * @hw: Pointer to the HW structure
- * Returns:
- * 0: Successfully
- * Negative value: Failed-EBUSY
- */
-static s32 pch_gbe_plat_init_hw(struct pch_gbe_hw *hw)
-{
- s32 ret_val;
-
- ret_val = pch_gbe_phy_get_id(hw);
- if (ret_val) {
- struct pch_gbe_adapter *adapter = pch_gbe_hw_to_adapter(hw);
-
- netdev_err(adapter->netdev, "pch_gbe_phy_get_id error\n");
- return ret_val;
- }
- pch_gbe_phy_init_setting(hw);
- /* Setup Mac interface option RGMII */
-#ifdef PCH_GBE_MAC_IFOP_RGMII
- pch_gbe_phy_set_rgmii(hw);
-#endif
- return ret_val;
-}
-
-static const struct pch_gbe_functions pch_gbe_ops = {
- .get_bus_info = pch_gbe_plat_get_bus_info,
- .init_hw = pch_gbe_plat_init_hw,
- .read_phy_reg = pch_gbe_phy_read_reg_miic,
- .write_phy_reg = pch_gbe_phy_write_reg_miic,
- .reset_phy = pch_gbe_phy_hw_reset,
- .sw_reset_phy = pch_gbe_phy_sw_reset,
- .power_up_phy = pch_gbe_phy_power_up,
- .power_down_phy = pch_gbe_phy_power_down,
- .read_mac_addr = pch_gbe_mac_read_mac_addr
-};
-
-/**
- * pch_gbe_plat_init_function_pointers - Init func ptrs
- * @hw: Pointer to the HW structure
- */
-static void pch_gbe_plat_init_function_pointers(struct pch_gbe_hw *hw)
-{
- /* Set PHY parameter */
- hw->phy.reset_delay_us = PCH_GBE_PHY_RESET_DELAY_US;
- /* Set function pointers */
- hw->func = &pch_gbe_ops;
-}
-
-/**
- * pch_gbe_hal_setup_init_funcs - Initializes function pointers
- * @hw: Pointer to the HW structure
- * Returns:
- * 0: Successfully
- * ENOSYS: Function is not registered
- */
-s32 pch_gbe_hal_setup_init_funcs(struct pch_gbe_hw *hw)
-{
- if (!hw->reg) {
- struct pch_gbe_adapter *adapter = pch_gbe_hw_to_adapter(hw);
-
- netdev_err(adapter->netdev, "ERROR: Registers not mapped\n");
- return -ENOSYS;
- }
- pch_gbe_plat_init_function_pointers(hw);
- return 0;
-}
-
-/**
- * pch_gbe_hal_get_bus_info - Obtain bus information for adapter
- * @hw: Pointer to the HW structure
- */
-void pch_gbe_hal_get_bus_info(struct pch_gbe_hw *hw)
-{
- if (!hw->func->get_bus_info) {
- struct pch_gbe_adapter *adapter = pch_gbe_hw_to_adapter(hw);
-
- netdev_err(adapter->netdev, "ERROR: configuration\n");
- return;
- }
- hw->func->get_bus_info(hw);
-}
-
-/**
- * pch_gbe_hal_init_hw - Initialize hardware
- * @hw: Pointer to the HW structure
- * Returns:
- * 0: Successfully
- * ENOSYS: Function is not registered
- */
-s32 pch_gbe_hal_init_hw(struct pch_gbe_hw *hw)
-{
- if (!hw->func->init_hw) {
- struct pch_gbe_adapter *adapter = pch_gbe_hw_to_adapter(hw);
-
- netdev_err(adapter->netdev, "ERROR: configuration\n");
- return -ENOSYS;
- }
- return hw->func->init_hw(hw);
-}
-
-/**
- * pch_gbe_hal_read_phy_reg - Reads PHY register
- * @hw: Pointer to the HW structure
- * @offset: The register to read
- * @data: The buffer to store the 16-bit read.
- * Returns:
- * 0: Successfully
- * Negative value: Failed
- */
-s32 pch_gbe_hal_read_phy_reg(struct pch_gbe_hw *hw, u32 offset,
- u16 *data)
-{
- if (!hw->func->read_phy_reg)
- return 0;
- return hw->func->read_phy_reg(hw, offset, data);
-}
-
-/**
- * pch_gbe_hal_write_phy_reg - Writes PHY register
- * @hw: Pointer to the HW structure
- * @offset: The register to read
- * @data: The value to write.
- * Returns:
- * 0: Successfully
- * Negative value: Failed
- */
-s32 pch_gbe_hal_write_phy_reg(struct pch_gbe_hw *hw, u32 offset,
- u16 data)
-{
- if (!hw->func->write_phy_reg)
- return 0;
- return hw->func->write_phy_reg(hw, offset, data);
-}
-
-/**
- * pch_gbe_hal_phy_hw_reset - Hard PHY reset
- * @hw: Pointer to the HW structure
- */
-void pch_gbe_hal_phy_hw_reset(struct pch_gbe_hw *hw)
-{
- if (!hw->func->reset_phy) {
- struct pch_gbe_adapter *adapter = pch_gbe_hw_to_adapter(hw);
-
- netdev_err(adapter->netdev, "ERROR: configuration\n");
- return;
- }
- hw->func->reset_phy(hw);
-}
-
-/**
- * pch_gbe_hal_phy_sw_reset - Soft PHY reset
- * @hw: Pointer to the HW structure
- */
-void pch_gbe_hal_phy_sw_reset(struct pch_gbe_hw *hw)
-{
- if (!hw->func->sw_reset_phy) {
- struct pch_gbe_adapter *adapter = pch_gbe_hw_to_adapter(hw);
-
- netdev_err(adapter->netdev, "ERROR: configuration\n");
- return;
- }
- hw->func->sw_reset_phy(hw);
-}
-
-/**
- * pch_gbe_hal_read_mac_addr - Reads MAC address
- * @hw: Pointer to the HW structure
- * Returns:
- * 0: Successfully
- * ENOSYS: Function is not registered
- */
-s32 pch_gbe_hal_read_mac_addr(struct pch_gbe_hw *hw)
-{
- if (!hw->func->read_mac_addr) {
- struct pch_gbe_adapter *adapter = pch_gbe_hw_to_adapter(hw);
-
- netdev_err(adapter->netdev, "ERROR: configuration\n");
- return -ENOSYS;
- }
- return hw->func->read_mac_addr(hw);
-}
-
-/**
- * pch_gbe_hal_power_up_phy - Power up PHY
- * @hw: Pointer to the HW structure
- */
-void pch_gbe_hal_power_up_phy(struct pch_gbe_hw *hw)
-{
- if (hw->func->power_up_phy)
- hw->func->power_up_phy(hw);
-}
-
-/**
- * pch_gbe_hal_power_down_phy - Power down PHY
- * @hw: Pointer to the HW structure
- */
-void pch_gbe_hal_power_down_phy(struct pch_gbe_hw *hw)
-{
- if (hw->func->power_down_phy)
- hw->func->power_down_phy(hw);
-}
+++ /dev/null
-/*
- * Copyright (C) 1999 - 2010 Intel Corporation.
- * Copyright (C) 2010 OKI SEMICONDUCTOR Co., LTD.
- *
- * This code was derived from the Intel e1000e Linux driver.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
- */
-#ifndef _PCH_GBE_API_H_
-#define _PCH_GBE_API_H_
-
-#include "pch_gbe_phy.h"
-
-s32 pch_gbe_hal_setup_init_funcs(struct pch_gbe_hw *hw);
-void pch_gbe_hal_get_bus_info(struct pch_gbe_hw *hw);
-s32 pch_gbe_hal_init_hw(struct pch_gbe_hw *hw);
-s32 pch_gbe_hal_read_phy_reg(struct pch_gbe_hw *hw, u32 offset, u16 *data);
-s32 pch_gbe_hal_write_phy_reg(struct pch_gbe_hw *hw, u32 offset, u16 data);
-void pch_gbe_hal_phy_hw_reset(struct pch_gbe_hw *hw);
-void pch_gbe_hal_phy_sw_reset(struct pch_gbe_hw *hw);
-s32 pch_gbe_hal_read_mac_addr(struct pch_gbe_hw *hw);
-void pch_gbe_hal_power_up_phy(struct pch_gbe_hw *hw);
-void pch_gbe_hal_power_down_phy(struct pch_gbe_hw *hw);
-
-#endif
* along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
#include "pch_gbe.h"
-#include "pch_gbe_api.h"
+#include "pch_gbe_phy.h"
/**
* pch_gbe_stats - Stats item information
u32 advertising;
int ret;
- pch_gbe_hal_write_phy_reg(hw, MII_BMCR, BMCR_RESET);
+ pch_gbe_phy_write_reg_miic(hw, MII_BMCR, BMCR_RESET);
memcpy(©_ecmd, ecmd, sizeof(*ecmd));
*regs_buff++ = ioread32(&hw->reg->INT_ST + i);
/* PHY register */
for (i = 0; i < PCH_GBE_PHY_REGS_LEN; i++) {
- pch_gbe_hal_read_phy_reg(&adapter->hw, i, &tmp);
+ pch_gbe_phy_read_reg_miic(&adapter->hw, i, &tmp);
*regs_buff++ = tmp;
}
}
err = pch_gbe_setup_tx_resources(adapter, adapter->tx_ring);
if (err)
goto err_setup_tx;
- /* save the new, restore the old in order to free it,
- * then restore the new back again */
-#ifdef RINGFREE
- adapter->rx_ring = rx_old;
- adapter->tx_ring = tx_old;
- pch_gbe_free_rx_resources(adapter, adapter->rx_ring);
- pch_gbe_free_tx_resources(adapter, adapter->tx_ring);
- kfree(tx_old);
- kfree(rx_old);
- adapter->rx_ring = rxdr;
- adapter->tx_ring = txdr;
-#else
pch_gbe_free_rx_resources(adapter, rx_old);
pch_gbe_free_tx_resources(adapter, tx_old);
kfree(tx_old);
kfree(rx_old);
adapter->rx_ring = rxdr;
adapter->tx_ring = txdr;
-#endif
err = pch_gbe_up(adapter);
}
return err;
*/
#include "pch_gbe.h"
-#include "pch_gbe_api.h"
+#include "pch_gbe_phy.h"
#include <linux/module.h>
#include <linux/net_tstamp.h>
#include <linux/ptp_classify.h>
#define PCH_GBE_DMA_ALIGN 0
#define PCH_GBE_DMA_PADDING 2
#define PCH_GBE_WATCHDOG_PERIOD (5 * HZ) /* watchdog time */
-#define PCH_GBE_COPYBREAK_DEFAULT 256
#define PCH_GBE_PCI_BAR 1
#define PCH_GBE_RESERVE_MEMORY 0x200000 /* 2MB */
#define MINNOW_PHY_RESET_GPIO 13
-static unsigned int copybreak __read_mostly = PCH_GBE_COPYBREAK_DEFAULT;
-
static int pch_gbe_mdio_read(struct net_device *netdev, int addr, int reg);
static void pch_gbe_mdio_write(struct net_device *netdev, int addr, int reg,
int data);
* Returns:
* 0: Successful.
*/
-s32 pch_gbe_mac_read_mac_addr(struct pch_gbe_hw *hw)
+static s32 pch_gbe_mac_read_mac_addr(struct pch_gbe_hw *hw)
{
struct pch_gbe_adapter *adapter = pch_gbe_hw_to_adapter(hw);
u32 adr1a, adr1b;
/* Read the MAC address. and store to the private data */
pch_gbe_mac_read_mac_addr(hw);
iowrite32(PCH_GBE_ALL_RST, &hw->reg->RESET);
-#ifdef PCH_GBE_MAC_IFOP_RGMII
iowrite32(PCH_GBE_MODE_GMII_ETHER, &hw->reg->MODE);
-#endif
pch_gbe_wait_clr_bit(&hw->reg->RESET, PCH_GBE_ALL_RST);
/* Setup the receive addresses */
pch_gbe_mac_mar_set(hw, hw->mac.addr, 0);
pch_gbe_wait_clr_bit(&hw->reg->ADDR_MASK, PCH_GBE_BUSY);
}
-
-/**
- * pch_gbe_mac_mc_addr_list_update - Update Multicast addresses
- * @hw: Pointer to the HW structure
- * @mc_addr_list: Array of multicast addresses to program
- * @mc_addr_count: Number of multicast addresses to program
- * @mar_used_count: The first MAC Address register free to program
- * @mar_total_num: Total number of supported MAC Address Registers
- */
-static void pch_gbe_mac_mc_addr_list_update(struct pch_gbe_hw *hw,
- u8 *mc_addr_list, u32 mc_addr_count,
- u32 mar_used_count, u32 mar_total_num)
-{
- u32 i, adrmask;
-
- /* Load the first set of multicast addresses into the exact
- * filters (RAR). If there are not enough to fill the RAR
- * array, clear the filters.
- */
- for (i = mar_used_count; i < mar_total_num; i++) {
- if (mc_addr_count) {
- pch_gbe_mac_mar_set(hw, mc_addr_list, i);
- mc_addr_count--;
- mc_addr_list += ETH_ALEN;
- } else {
- /* Clear MAC address mask */
- adrmask = ioread32(&hw->reg->ADDR_MASK);
- iowrite32((adrmask | (0x0001 << i)),
- &hw->reg->ADDR_MASK);
- /* wait busy */
- pch_gbe_wait_clr_bit(&hw->reg->ADDR_MASK, PCH_GBE_BUSY);
- /* Clear MAC address */
- iowrite32(0, &hw->reg->mac_adr[i].high);
- iowrite32(0, &hw->reg->mac_adr[i].low);
- }
- }
-}
-
/**
* pch_gbe_mac_force_mac_fc - Force the MAC's flow control settings
* @hw: Pointer to the HW structure
void pch_gbe_reset(struct pch_gbe_adapter *adapter)
{
struct net_device *netdev = adapter->netdev;
+ struct pch_gbe_hw *hw = &adapter->hw;
+ s32 ret_val;
- pch_gbe_mac_reset_hw(&adapter->hw);
+ pch_gbe_mac_reset_hw(hw);
/* reprogram multicast address register after reset */
pch_gbe_set_multi(netdev);
/* Setup the receive address. */
- pch_gbe_mac_init_rx_addrs(&adapter->hw, PCH_GBE_MAR_ENTRIES);
- if (pch_gbe_hal_init_hw(&adapter->hw))
- netdev_err(netdev, "Hardware Error\n");
+ pch_gbe_mac_init_rx_addrs(hw, PCH_GBE_MAR_ENTRIES);
+
+ ret_val = pch_gbe_phy_get_id(hw);
+ if (ret_val) {
+ netdev_err(adapter->netdev, "pch_gbe_phy_get_id error\n");
+ return;
+ }
+ pch_gbe_phy_init_setting(hw);
+ /* Setup Mac interface option RGMII */
+ pch_gbe_phy_set_rgmii(hw);
}
/**
unsigned long rgmii = 0;
/* Set the RGMII control. */
-#ifdef PCH_GBE_MAC_IFOP_RGMII
switch (speed) {
case SPEED_10:
rgmii = (PCH_GBE_RGMII_RATE_2_5M |
break;
}
iowrite32(rgmii, &hw->reg->RGMII_CTRL);
-#else /* GMII */
- rgmii = 0;
- iowrite32(rgmii, &hw->reg->RGMII_CTRL);
-#endif
}
static void pch_gbe_set_mode(struct pch_gbe_adapter *adapter, u16 speed,
u16 duplex)
adapter->rx_buffer_len = PCH_GBE_FRAME_SIZE_2048;
hw->mac.max_frame_size = netdev->mtu + ETH_HLEN + ETH_FCS_LEN;
hw->mac.min_frame_size = ETH_ZLEN + ETH_FCS_LEN;
+ hw->phy.reset_delay_us = PCH_GBE_PHY_RESET_DELAY_US;
- /* Initialize the hardware-specific values */
- if (pch_gbe_hal_setup_init_funcs(hw)) {
- netdev_err(netdev, "Hardware Initialization Failure\n");
- return -EIO;
- }
if (pch_gbe_alloc_queues(adapter)) {
netdev_err(netdev, "Unable to allocate memory for queues\n");
return -ENOMEM;
err = pch_gbe_setup_rx_resources(adapter, adapter->rx_ring);
if (err)
goto err_setup_rx;
- pch_gbe_hal_power_up_phy(hw);
+ pch_gbe_phy_power_up(hw);
err = pch_gbe_up(adapter);
if (err)
goto err_up;
err_up:
if (!adapter->wake_up_evt)
- pch_gbe_hal_power_down_phy(hw);
+ pch_gbe_phy_power_down(hw);
pch_gbe_free_rx_resources(adapter, adapter->rx_ring);
err_setup_rx:
pch_gbe_free_tx_resources(adapter, adapter->tx_ring);
pch_gbe_down(adapter);
if (!adapter->wake_up_evt)
- pch_gbe_hal_power_down_phy(hw);
+ pch_gbe_phy_power_down(hw);
pch_gbe_free_tx_resources(adapter, adapter->tx_ring);
pch_gbe_free_rx_resources(adapter, adapter->rx_ring);
return 0;
struct pch_gbe_adapter *adapter = netdev_priv(netdev);
struct pch_gbe_hw *hw = &adapter->hw;
struct netdev_hw_addr *ha;
- u8 *mta_list;
- u32 rctl;
- int i;
- int mc_count;
+ u32 rctl, adrmask;
+ int mc_count, i;
netdev_dbg(netdev, "netdev->flags : 0x%08x\n", netdev->flags);
- /* Check for Promiscuous and All Multicast modes */
+ /* By default enable address & multicast filtering */
rctl = ioread32(&hw->reg->RX_MODE);
+ rctl |= PCH_GBE_ADD_FIL_EN | PCH_GBE_MLT_FIL_EN;
+
+ /* Promiscuous mode disables all hardware address filtering */
+ if (netdev->flags & IFF_PROMISC)
+ rctl &= ~(PCH_GBE_ADD_FIL_EN | PCH_GBE_MLT_FIL_EN);
+
+ /* If we want to monitor more multicast addresses than the hardware can
+ * support then disable hardware multicast filtering.
+ */
mc_count = netdev_mc_count(netdev);
- if ((netdev->flags & IFF_PROMISC)) {
- rctl &= ~PCH_GBE_ADD_FIL_EN;
- rctl &= ~PCH_GBE_MLT_FIL_EN;
- } else if ((netdev->flags & IFF_ALLMULTI)) {
- /* all the multicasting receive permissions */
- rctl |= PCH_GBE_ADD_FIL_EN;
+ if ((netdev->flags & IFF_ALLMULTI) || mc_count >= PCH_GBE_MAR_ENTRIES)
rctl &= ~PCH_GBE_MLT_FIL_EN;
- } else {
- if (mc_count >= PCH_GBE_MAR_ENTRIES) {
- /* all the multicasting receive permissions */
- rctl |= PCH_GBE_ADD_FIL_EN;
- rctl &= ~PCH_GBE_MLT_FIL_EN;
- } else {
- rctl |= (PCH_GBE_ADD_FIL_EN | PCH_GBE_MLT_FIL_EN);
- }
- }
+
iowrite32(rctl, &hw->reg->RX_MODE);
- if (mc_count >= PCH_GBE_MAR_ENTRIES)
- return;
- mta_list = kmalloc_array(ETH_ALEN, mc_count, GFP_ATOMIC);
- if (!mta_list)
+ /* If we're not using multicast filtering then there's no point
+ * configuring the unused MAC address registers.
+ */
+ if (!(rctl & PCH_GBE_MLT_FIL_EN))
return;
- /* The shared function expects a packed array of only addresses. */
- i = 0;
- netdev_for_each_mc_addr(ha, netdev) {
- if (i == mc_count)
- break;
- memcpy(mta_list + (i++ * ETH_ALEN), &ha->addr, ETH_ALEN);
+ /* Load the first set of multicast addresses into MAC address registers
+ * for use by hardware filtering.
+ */
+ i = 1;
+ netdev_for_each_mc_addr(ha, netdev)
+ pch_gbe_mac_mar_set(hw, ha->addr, i++);
+
+ /* If there are spare MAC registers, mask & clear them */
+ for (; i < PCH_GBE_MAR_ENTRIES; i++) {
+ /* Clear MAC address mask */
+ adrmask = ioread32(&hw->reg->ADDR_MASK);
+ iowrite32(adrmask | BIT(i), &hw->reg->ADDR_MASK);
+ /* wait busy */
+ pch_gbe_wait_clr_bit(&hw->reg->ADDR_MASK, PCH_GBE_BUSY);
+ /* Clear MAC address */
+ iowrite32(0, &hw->reg->mac_adr[i].high);
+ iowrite32(0, &hw->reg->mac_adr[i].low);
}
- pch_gbe_mac_mc_addr_list_update(hw, mta_list, i, 1,
- PCH_GBE_MAR_ENTRIES);
- kfree(mta_list);
netdev_dbg(netdev,
"RX_MODE reg(check bit31,30 ADD,MLT) : 0x%08x netdev->mc_count : 0x%08x\n",
}
pci_set_master(pdev);
pci_enable_wake(pdev, PCI_D0, 0);
- pch_gbe_hal_power_up_phy(hw);
+ pch_gbe_phy_power_up(hw);
pch_gbe_reset(adapter);
/* Clear wake up status */
pch_gbe_mac_set_wol_event(hw, 0);
pch_gbe_mac_set_wol_event(hw, wufc);
pci_disable_device(pdev);
} else {
- pch_gbe_hal_power_down_phy(hw);
+ pch_gbe_phy_power_down(hw);
pch_gbe_mac_set_wol_event(hw, wufc);
pci_disable_device(pdev);
}
return err;
}
pci_set_master(pdev);
- pch_gbe_hal_power_up_phy(hw);
+ pch_gbe_phy_power_up(hw);
pch_gbe_reset(adapter);
/* Clear wake on lan control and status */
pch_gbe_mac_set_wol_event(hw, 0);
cancel_work_sync(&adapter->reset_task);
unregister_netdev(netdev);
- pch_gbe_hal_phy_hw_reset(&adapter->hw);
+ pch_gbe_phy_hw_reset(&adapter->hw);
free_netdev(netdev);
}
dev_err(&pdev->dev, "PHY initialize error\n");
goto err_free_adapter;
}
- pch_gbe_hal_get_bus_info(&adapter->hw);
/* Read the MAC address. and store to the private data */
- ret = pch_gbe_hal_read_mac_addr(&adapter->hw);
+ ret = pch_gbe_mac_read_mac_addr(&adapter->hw);
if (ret) {
dev_err(&pdev->dev, "MAC address Read Error\n");
goto err_free_adapter;
return 0;
err_free_adapter:
- pch_gbe_hal_phy_hw_reset(&adapter->hw);
+ pch_gbe_phy_hw_reset(&adapter->hw);
err_free_netdev:
free_netdev(netdev);
return ret;
.shutdown = pch_gbe_shutdown,
.err_handler = &pch_gbe_err_handler
};
-
-
-static int __init pch_gbe_init_module(void)
-{
- int ret;
-
- pr_info("EG20T PCH Gigabit Ethernet Driver - version %s\n",DRV_VERSION);
- ret = pci_register_driver(&pch_gbe_driver);
- if (copybreak != PCH_GBE_COPYBREAK_DEFAULT) {
- if (copybreak == 0) {
- pr_info("copybreak disabled\n");
- } else {
- pr_info("copybreak enabled for packets <= %u bytes\n",
- copybreak);
- }
- }
- return ret;
-}
-
-static void __exit pch_gbe_exit_module(void)
-{
- pci_unregister_driver(&pch_gbe_driver);
-}
-
-module_init(pch_gbe_init_module);
-module_exit(pch_gbe_exit_module);
+module_pci_driver(pch_gbe_driver);
MODULE_DESCRIPTION("EG20T PCH Gigabit ethernet Driver");
MODULE_AUTHOR("LAPIS SEMICONDUCTOR, <tshimizu818@gmail.com>");
MODULE_VERSION(DRV_VERSION);
MODULE_DEVICE_TABLE(pci, pch_gbe_pcidev_id);
-module_param(copybreak, uint, 0644);
-MODULE_PARM_DESC(copybreak,
- "Maximum size of packet that is copied to a new buffer on receive");
-
/* pch_gbe_main.c */
* pch_gbe_phy_sw_reset - PHY software reset
* @hw: Pointer to the HW structure
*/
-void pch_gbe_phy_sw_reset(struct pch_gbe_hw *hw)
+static void pch_gbe_phy_sw_reset(struct pch_gbe_hw *hw)
{
u16 phy_ctrl;
#define PCH_GBE_PHY_REGS_LEN 32
#define PCH_GBE_PHY_RESET_DELAY_US 10
-#define PCH_GBE_MAC_IFOP_RGMII
s32 pch_gbe_phy_get_id(struct pch_gbe_hw *hw);
s32 pch_gbe_phy_read_reg_miic(struct pch_gbe_hw *hw, u32 offset, u16 *data);
s32 pch_gbe_phy_write_reg_miic(struct pch_gbe_hw *hw, u32 offset, u16 data);
-void pch_gbe_phy_sw_reset(struct pch_gbe_hw *hw);
void pch_gbe_phy_hw_reset(struct pch_gbe_hw *hw);
void pch_gbe_phy_power_up(struct pch_gbe_hw *hw);
void pch_gbe_phy_power_down(struct pch_gbe_hw *hw);
# Packet engine device configuration
#
-config NET_PACKET_ENGINE
+config NET_VENDOR_PACKET_ENGINES
bool "Packet Engine devices"
default y
depends on PCI
the questions about packet engine devices. If you say Y, you will
be asked for your specific card in the following questions.
-if NET_PACKET_ENGINE
+if NET_VENDOR_PACKET_ENGINES
config HAMACHI
tristate "Packet Engines Hamachi GNIC-II support"
To compile this driver as a module, choose M here: the module
will be called yellowfin. This is recommended.
-endif # NET_PACKET_ENGINE
+endif # NET_VENDOR_PACKET_ENGINES
netxen_send_cmd_descs(struct netxen_adapter *adapter,
struct cmd_desc_type0 *cmd_desc_arr, int nr_desc)
{
- u32 i, producer, consumer;
+ u32 i, producer;
struct netxen_cmd_buffer *pbuf;
- struct cmd_desc_type0 *cmd_desc;
struct nx_host_tx_ring *tx_ring;
i = 0;
__netif_tx_lock_bh(tx_ring->txq);
producer = tx_ring->producer;
- consumer = tx_ring->sw_consumer;
if (nr_desc >= netxen_tx_avail(tx_ring)) {
netif_tx_stop_queue(tx_ring->txq);
}
do {
- cmd_desc = &cmd_desc_arr[i];
-
pbuf = &tx_ring->cmd_buf_arr[producer];
pbuf->skb = NULL;
pbuf->frag_count = 0;
static int netxen_parse_md_template(struct netxen_adapter *adapter)
{
int num_of_entries, buff_level, e_cnt, esize;
- int end_cnt = 0, rv = 0, sane_start = 0, sane_end = 0;
+ int rv = 0, sane_start = 0, sane_end = 0;
char *dbuff;
void *template_buff = adapter->mdump.md_template;
char *dump_buff = adapter->mdump.md_capture_buff;
break;
case RDEND:
entry->hdr.driver_flags |= NX_DUMP_SKIP;
- if (!sane_end)
- end_cnt = e_cnt;
sane_end += 1;
break;
case CNTRL:
struct skb_frag_struct *frag;
u32 producer;
- int frag_count, no_of_desc;
+ int frag_count;
u32 num_txd = tx_ring->num_desc;
frag_count = skb_shinfo(skb)->nr_frags + 1;
frag_count = 1 + skb_shinfo(skb)->nr_frags;
}
- /* 4 fragments per cmd des */
- no_of_desc = (frag_count + 3) >> 2;
if (unlikely(netxen_tx_avail(tx_ring) <= TX_STOP_THRESH)) {
netif_stop_queue(netdev);
struct qed_hw_info *p_info = &p_hwfn->hw_info;
enum qed_pci_personality personality;
enum dcbx_protocol_type id;
- char *name;
int i;
for (i = 0; i < ARRAY_SIZE(qed_dcbx_app_update); i++) {
continue;
personality = qed_dcbx_app_update[i].personality;
- name = qed_dcbx_app_update[i].name;
qed_dcbx_set_params(p_data, p_info, enable,
prio, tc, type, personality);
*type = DCBX_PROTOCOL_ROCE_V2;
} else {
*type = DCBX_MAX_PROTOCOL_TYPE;
- DP_ERR(p_hwfn,
- "No action required, App TLV id = 0x%x app_prio_bitmap = 0x%x\n",
- id, app_prio_bitmap);
+ DP_ERR(p_hwfn, "No action required, App TLV entry = 0x%x\n",
+ app_prio_bitmap);
return false;
}
p_local = &p_hwfn->p_dcbx_info->lldp_local[LLDP_NEAREST_BRIDGE];
memcpy(params->lldp_local.local_chassis_id, p_local->local_chassis_id,
- ARRAY_SIZE(p_local->local_chassis_id));
+ sizeof(p_local->local_chassis_id));
memcpy(params->lldp_local.local_port_id, p_local->local_port_id,
- ARRAY_SIZE(p_local->local_port_id));
+ sizeof(p_local->local_port_id));
}
static void
p_remote = &p_hwfn->p_dcbx_info->lldp_remote[LLDP_NEAREST_BRIDGE];
memcpy(params->lldp_remote.peer_chassis_id, p_remote->peer_chassis_id,
- ARRAY_SIZE(p_remote->peer_chassis_id));
+ sizeof(p_remote->peer_chassis_id));
memcpy(params->lldp_remote.peer_port_id, p_remote->peer_port_id,
- ARRAY_SIZE(p_remote->peer_port_id));
+ sizeof(p_remote->peer_port_id));
}
static int
*cap = 0x80;
break;
case DCB_CAP_ATTR_DCBX:
- *cap = (DCB_CAP_DCBX_LLD_MANAGED | DCB_CAP_DCBX_VER_CEE |
- DCB_CAP_DCBX_VER_IEEE | DCB_CAP_DCBX_STATIC);
+ *cap = (DCB_CAP_DCBX_VER_CEE | DCB_CAP_DCBX_VER_IEEE |
+ DCB_CAP_DCBX_STATIC);
break;
default:
*cap = false;
if (!dcbx_info)
return 0;
- if (dcbx_info->operational.enabled)
- mode |= DCB_CAP_DCBX_LLD_MANAGED;
if (dcbx_info->operational.ieee)
mode |= DCB_CAP_DCBX_VER_IEEE;
if (dcbx_info->operational.cee)
DP_INFO(p_hwfn, "Failed to update driver state\n");
rc = qed_mcp_ov_update_eswitch(p_hwfn, p_hwfn->p_main_ptt,
- QED_OV_ESWITCH_VEB);
+ QED_OV_ESWITCH_NONE);
if (rc)
DP_INFO(p_hwfn, "Failed to update eswitch mode\n");
}
skb = build_skb(buffer->data, 0);
if (!skb) {
- rc = -ENOMEM;
- goto out_post;
+ DP_INFO(cdev, "Failed to build SKB\n");
+ kfree(buffer->data);
+ goto out_post1;
}
data->u.placement_offset += NET_SKB_PAD;
cdev->ll2->cbs->rx_cb(cdev->ll2->cb_cookie, skb,
data->opaque_data_0,
data->opaque_data_1);
+ } else {
+ DP_VERBOSE(p_hwfn, (NETIF_MSG_RX_STATUS | NETIF_MSG_PKTDATA |
+ QED_MSG_LL2 | QED_MSG_STORAGE),
+ "Dropping the packet\n");
+ kfree(buffer->data);
}
+out_post1:
/* Update Buffer information and update FW producer */
buffer->data = new_data;
buffer->phys_addr = new_phys_addr;
/* Fastpath interrupts */
for (j = 0; j < 64; j++) {
if ((0x2ULL << j) & status) {
- hwfn->simd_proto_handler[j].func(
- hwfn->simd_proto_handler[j].token);
+ struct qed_simd_fp_handler *p_handler =
+ &hwfn->simd_proto_handler[j];
+
+ if (p_handler->func)
+ p_handler->func(p_handler->token);
+ else
+ DP_NOTICE(hwfn,
+ "Not calling fastpath handler as it is NULL [handler #%d, status 0x%llx]\n",
+ j, status);
+
status &= ~(0x2ULL << j);
rc = IRQ_HANDLED;
}
/* We want a minimum of one slowpath and one fastpath vector per hwfn */
cdev->int_params.in.min_msix_cnt = cdev->num_hwfns * 2;
+ if (is_kdump_kernel()) {
+ DP_INFO(cdev,
+ "Kdump kernel: Limit the max number of requested MSI-X vectors to %hd\n",
+ cdev->int_params.in.min_msix_cnt);
+ cdev->int_params.in.num_vectors =
+ cdev->int_params.in.min_msix_cnt;
+ }
+
rc = qed_set_int_mode(cdev, false);
if (rc) {
DP_ERR(cdev, "qed_slowpath_setup_int ERR\n");
static int qed_sriov_enable(struct qed_dev *cdev, int num)
{
struct qed_iov_vf_init_params params;
+ struct qed_hwfn *hwfn;
+ struct qed_ptt *ptt;
int i, j, rc;
if (num >= RESC_NUM(&cdev->hwfns[0], QED_VPORT)) {
/* Initialize HW for VF access */
for_each_hwfn(cdev, j) {
- struct qed_hwfn *hwfn = &cdev->hwfns[j];
- struct qed_ptt *ptt = qed_ptt_acquire(hwfn);
+ hwfn = &cdev->hwfns[j];
+ ptt = qed_ptt_acquire(hwfn);
/* Make sure not to use more than 16 queues per VF */
params.num_queues = min_t(int,
goto err;
}
+ hwfn = QED_LEADING_HWFN(cdev);
+ ptt = qed_ptt_acquire(hwfn);
+ if (!ptt) {
+ DP_ERR(hwfn, "Failed to acquire ptt\n");
+ rc = -EBUSY;
+ goto err;
+ }
+
+ rc = qed_mcp_ov_update_eswitch(hwfn, ptt, QED_OV_ESWITCH_VEB);
+ if (rc)
+ DP_INFO(cdev, "Failed to update eswitch mode\n");
+ qed_ptt_release(hwfn, ptt);
+
return num;
err:
case XDP_SETUP_PROG:
return qede_xdp_set(edev, xdp->prog);
case XDP_QUERY_PROG:
- xdp->prog_attached = !!edev->xdp_prog;
xdp->prog_id = edev->xdp_prog ? edev->xdp_prog->aux->id : 0;
return 0;
default:
{
struct qede_ptp *ptp = edev->ptp;
- if (!ptp)
- return -EIO;
+ if (!ptp) {
+ info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
+ SOF_TIMESTAMPING_RX_SOFTWARE |
+ SOF_TIMESTAMPING_SOFTWARE;
+ info->phc_index = -1;
+
+ return 0;
+ }
info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
SOF_TIMESTAMPING_RX_SOFTWARE |
vp->max_tx_bw = MAX_BW;
vp->min_tx_bw = MIN_BW;
vp->spoofchk = false;
- random_ether_addr(vp->mac);
+ eth_random_addr(vp->mac);
dev_info(&adapter->pdev->dev,
"MAC Address %pM is configured for VF %d\n",
vp->mac, i);
rmnet_dev->netdev_ops = &rmnet_vnd_ops;
rmnet_dev->mtu = RMNET_DFLT_PACKET_SIZE;
rmnet_dev->needed_headroom = RMNET_NEEDED_HEADROOM;
- random_ether_addr(rmnet_dev->dev_addr);
+ eth_random_addr(rmnet_dev->dev_addr);
rmnet_dev->tx_queue_len = RMNET_TX_QUEUE_LEN;
/* Raw IP mode */
depends on PCI
select FW_LOADER
select CRC32
- select MII
+ select PHYLIB
---help---
Say Y here if you have a Realtek 8169 PCI Gigabit Ethernet adapter.
#include <linux/etherdevice.h>
#include <linux/delay.h>
#include <linux/ethtool.h>
-#include <linux/mii.h>
+#include <linux/phy.h>
#include <linux/if_vlan.h>
#include <linux/crc32.h>
#include <linux/in.h>
#include <linux/dma-mapping.h>
#include <linux/pm_runtime.h>
#include <linux/firmware.h>
-#include <linux/pci-aspm.h>
#include <linux/prefetch.h>
#include <linux/ipv6.h>
#include <net/ip6_checksum.h>
#define RTL8169_VERSION "2.3LK-NAPI"
#define MODULENAME "r8169"
-#define PFX MODULENAME ": "
#define FIRMWARE_8168D_1 "rtl_nic/rtl8168d-1.fw"
#define FIRMWARE_8168D_2 "rtl_nic/rtl8168d-2.fw"
#define FIRMWARE_8107E_1 "rtl_nic/rtl8107e-1.fw"
#define FIRMWARE_8107E_2 "rtl_nic/rtl8107e-2.fw"
-#ifdef RTL8169_DEBUG
-#define assert(expr) \
- if (!(expr)) { \
- printk( "Assertion failed! %s,%s,%s,line=%d\n", \
- #expr,__FILE__,__func__,__LINE__); \
- }
-#define dprintk(fmt, args...) \
- do { printk(KERN_DEBUG PFX fmt, ## args); } while (0)
-#else
-#define assert(expr) do {} while (0)
-#define dprintk(fmt, args...) do {} while (0)
-#endif /* RTL8169_DEBUG */
-
#define R8169_MSG_DEFAULT \
(NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_IFUP | NETIF_MSG_IFDOWN)
#define R8169_RX_RING_BYTES (NUM_RX_DESC * sizeof(struct RxDesc))
#define RTL8169_TX_TIMEOUT (6*HZ)
-#define RTL8169_PHY_TIMEOUT (10*HZ)
/* write/read MMIO register */
#define RTL_W8(tp, reg, val8) writeb((val8), tp->mmio_addr + (reg))
FuncForceEvent = 0xfc,
};
-enum rtl8110_registers {
- TBICSR = 0x64,
- TBI_ANAR = 0x68,
- TBI_LPAR = 0x6a,
-};
-
enum rtl8168_8101_registers {
CSIDR = 0x64,
CSIAR = 0x68,
PMEStatus = (1 << 0), /* PME status can be reset by PCI RST# */
ASPM_en = (1 << 0), /* ASPM enable */
- /* TBICSR p.28 */
- TBIReset = 0x80000000,
- TBILoopback = 0x40000000,
- TBINwEnable = 0x20000000,
- TBINwRestart = 0x10000000,
- TBILinkOk = 0x02000000,
- TBINwComplete = 0x01000000,
-
/* CPlusCmd p.31 */
EnableBist = (1 << 15), // 8168 8101
Mac_dbgo_oe = (1 << 14), // 8168 8101
RTL_FLAG_TASK_ENABLED,
RTL_FLAG_TASK_SLOW_PENDING,
RTL_FLAG_TASK_RESET_PENDING,
- RTL_FLAG_TASK_PHY_PENDING,
RTL_FLAG_MAX
};
dma_addr_t RxPhyAddr;
void *Rx_databuff[NUM_RX_DESC]; /* Rx data buffers */
struct ring_info tx_skb[NUM_TX_DESC]; /* Tx data buffers */
- struct timer_list timer;
u16 cp_cmd;
u16 event_slow;
void (*disable)(struct rtl8169_private *);
} jumbo_ops;
- int (*set_speed)(struct net_device *, u8 aneg, u16 sp, u8 dpx, u32 adv);
- int (*get_link_ksettings)(struct net_device *,
- struct ethtool_link_ksettings *);
- void (*phy_reset_enable)(struct rtl8169_private *tp);
void (*hw_start)(struct rtl8169_private *tp);
- unsigned int (*phy_reset_pending)(struct rtl8169_private *tp);
- unsigned int (*link_ok)(struct rtl8169_private *tp);
- int (*do_ioctl)(struct rtl8169_private *tp, struct mii_ioctl_data *data, int cmd);
bool (*tso_csum)(struct rtl8169_private *, struct sk_buff *, u32 *);
struct {
struct work_struct work;
} wk;
- struct mii_if_info mii;
+ unsigned supports_gmii:1;
+ struct mii_bus *mii_bus;
dma_addr_t counters_phys_addr;
struct rtl8169_counters *counters;
struct rtl8169_tc_offsets tc_offset;
rtl_writephy(tp, reg_addr, (val & ~m) | p);
}
-static void rtl_mdio_write(struct net_device *dev, int phy_id, int location,
- int val)
-{
- struct rtl8169_private *tp = netdev_priv(dev);
-
- rtl_writephy(tp, location, val);
-}
-
-static int rtl_mdio_read(struct net_device *dev, int phy_id, int location)
-{
- struct rtl8169_private *tp = netdev_priv(dev);
-
- return rtl_readphy(tp, location);
-}
-
DECLARE_RTL_COND(rtl_ephyar_cond)
{
return RTL_R32(tp, EPHYAR) & EPHYAR_FLAG;
RTL_R8(tp, ChipCmd);
}
-static unsigned int rtl8169_tbi_reset_pending(struct rtl8169_private *tp)
-{
- return RTL_R32(tp, TBICSR) & TBIReset;
-}
-
-static unsigned int rtl8169_xmii_reset_pending(struct rtl8169_private *tp)
-{
- return rtl_readphy(tp, MII_BMCR) & BMCR_RESET;
-}
-
-static unsigned int rtl8169_tbi_link_ok(struct rtl8169_private *tp)
-{
- return RTL_R32(tp, TBICSR) & TBILinkOk;
-}
-
-static unsigned int rtl8169_xmii_link_ok(struct rtl8169_private *tp)
-{
- return RTL_R8(tp, PHYstatus) & LinkStatus;
-}
-
-static void rtl8169_tbi_reset_enable(struct rtl8169_private *tp)
-{
- RTL_W32(tp, TBICSR, RTL_R32(tp, TBICSR) | TBIReset);
-}
-
-static void rtl8169_xmii_reset_enable(struct rtl8169_private *tp)
-{
- unsigned int val;
-
- val = rtl_readphy(tp, MII_BMCR) | BMCR_RESET;
- rtl_writephy(tp, MII_BMCR, val & 0xffff);
-}
-
static void rtl_link_chg_patch(struct rtl8169_private *tp)
{
struct net_device *dev = tp->dev;
+ struct phy_device *phydev = dev->phydev;
if (!netif_running(dev))
return;
if (tp->mac_version == RTL_GIGA_MAC_VER_34 ||
tp->mac_version == RTL_GIGA_MAC_VER_38) {
- if (RTL_R8(tp, PHYstatus) & _1000bpsF) {
+ if (phydev->speed == SPEED_1000) {
rtl_eri_write(tp, 0x1bc, ERIAR_MASK_1111, 0x00000011,
ERIAR_EXGMAC);
rtl_eri_write(tp, 0x1dc, ERIAR_MASK_1111, 0x00000005,
ERIAR_EXGMAC);
- } else if (RTL_R8(tp, PHYstatus) & _100bps) {
+ } else if (phydev->speed == SPEED_100) {
rtl_eri_write(tp, 0x1bc, ERIAR_MASK_1111, 0x0000001f,
ERIAR_EXGMAC);
rtl_eri_write(tp, 0x1dc, ERIAR_MASK_1111, 0x00000005,
ERIAR_EXGMAC);
} else if (tp->mac_version == RTL_GIGA_MAC_VER_35 ||
tp->mac_version == RTL_GIGA_MAC_VER_36) {
- if (RTL_R8(tp, PHYstatus) & _1000bpsF) {
+ if (phydev->speed == SPEED_1000) {
rtl_eri_write(tp, 0x1bc, ERIAR_MASK_1111, 0x00000011,
ERIAR_EXGMAC);
rtl_eri_write(tp, 0x1dc, ERIAR_MASK_1111, 0x00000005,
ERIAR_EXGMAC);
}
} else if (tp->mac_version == RTL_GIGA_MAC_VER_37) {
- if (RTL_R8(tp, PHYstatus) & _10bps) {
+ if (phydev->speed == SPEED_10) {
rtl_eri_write(tp, 0x1d0, ERIAR_MASK_0011, 0x4d02,
ERIAR_EXGMAC);
rtl_eri_write(tp, 0x1dc, ERIAR_MASK_0011, 0x0060,
}
}
-static void rtl8169_check_link_status(struct net_device *dev,
- struct rtl8169_private *tp)
-{
- struct device *d = tp_to_dev(tp);
-
- if (tp->link_ok(tp)) {
- rtl_link_chg_patch(tp);
- /* This is to cancel a scheduled suspend if there's one. */
- pm_request_resume(d);
- netif_carrier_on(dev);
- if (net_ratelimit())
- netif_info(tp, ifup, dev, "link up\n");
- } else {
- netif_carrier_off(dev);
- netif_info(tp, ifdown, dev, "link down\n");
- pm_runtime_idle(d);
- }
-}
-
#define WAKE_ANY (WAKE_PHY | WAKE_MAGIC | WAKE_UCAST | WAKE_BCAST | WAKE_MCAST)
static u32 __rtl8169_get_wol(struct rtl8169_private *tp)
static void rtl8169_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
{
struct rtl8169_private *tp = netdev_priv(dev);
- struct device *d = tp_to_dev(tp);
-
- pm_runtime_get_noresume(d);
rtl_lock_work(tp);
-
wol->supported = WAKE_ANY;
- if (pm_runtime_active(d))
- wol->wolopts = __rtl8169_get_wol(tp);
- else
- wol->wolopts = tp->saved_wolopts;
-
+ wol->wolopts = tp->saved_wolopts;
rtl_unlock_work(tp);
-
- pm_runtime_put_noidle(d);
}
static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts)
struct rtl8169_private *tp = netdev_priv(dev);
struct device *d = tp_to_dev(tp);
+ if (wol->wolopts & ~WAKE_ANY)
+ return -EINVAL;
+
pm_runtime_get_noresume(d);
rtl_lock_work(tp);
+ tp->saved_wolopts = wol->wolopts;
+
if (pm_runtime_active(d))
- __rtl8169_set_wol(tp, wol->wolopts);
- else
- tp->saved_wolopts = wol->wolopts;
+ __rtl8169_set_wol(tp, tp->saved_wolopts);
rtl_unlock_work(tp);
- device_set_wakeup_enable(d, wol->wolopts);
+ device_set_wakeup_enable(d, tp->saved_wolopts);
pm_runtime_put_noidle(d);
return R8169_REGS_SIZE;
}
-static int rtl8169_set_speed_tbi(struct net_device *dev,
- u8 autoneg, u16 speed, u8 duplex, u32 ignored)
-{
- struct rtl8169_private *tp = netdev_priv(dev);
- int ret = 0;
- u32 reg;
-
- reg = RTL_R32(tp, TBICSR);
- if ((autoneg == AUTONEG_DISABLE) && (speed == SPEED_1000) &&
- (duplex == DUPLEX_FULL)) {
- RTL_W32(tp, TBICSR, reg & ~(TBINwEnable | TBINwRestart));
- } else if (autoneg == AUTONEG_ENABLE)
- RTL_W32(tp, TBICSR, reg | TBINwEnable | TBINwRestart);
- else {
- netif_warn(tp, link, dev,
- "incorrect speed setting refused in TBI mode\n");
- ret = -EOPNOTSUPP;
- }
-
- return ret;
-}
-
-static int rtl8169_set_speed_xmii(struct net_device *dev,
- u8 autoneg, u16 speed, u8 duplex, u32 adv)
-{
- struct rtl8169_private *tp = netdev_priv(dev);
- int giga_ctrl, bmcr;
- int rc = -EINVAL;
-
- rtl_writephy(tp, 0x1f, 0x0000);
-
- if (autoneg == AUTONEG_ENABLE) {
- int auto_nego;
-
- auto_nego = rtl_readphy(tp, MII_ADVERTISE);
- auto_nego &= ~(ADVERTISE_10HALF | ADVERTISE_10FULL |
- ADVERTISE_100HALF | ADVERTISE_100FULL);
-
- if (adv & ADVERTISED_10baseT_Half)
- auto_nego |= ADVERTISE_10HALF;
- if (adv & ADVERTISED_10baseT_Full)
- auto_nego |= ADVERTISE_10FULL;
- if (adv & ADVERTISED_100baseT_Half)
- auto_nego |= ADVERTISE_100HALF;
- if (adv & ADVERTISED_100baseT_Full)
- auto_nego |= ADVERTISE_100FULL;
-
- auto_nego |= ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM;
-
- giga_ctrl = rtl_readphy(tp, MII_CTRL1000);
- giga_ctrl &= ~(ADVERTISE_1000FULL | ADVERTISE_1000HALF);
-
- /* The 8100e/8101e/8102e do Fast Ethernet only. */
- if (tp->mii.supports_gmii) {
- if (adv & ADVERTISED_1000baseT_Half)
- giga_ctrl |= ADVERTISE_1000HALF;
- if (adv & ADVERTISED_1000baseT_Full)
- giga_ctrl |= ADVERTISE_1000FULL;
- } else if (adv & (ADVERTISED_1000baseT_Half |
- ADVERTISED_1000baseT_Full)) {
- netif_info(tp, link, dev,
- "PHY does not support 1000Mbps\n");
- goto out;
- }
-
- bmcr = BMCR_ANENABLE | BMCR_ANRESTART;
-
- rtl_writephy(tp, MII_ADVERTISE, auto_nego);
- rtl_writephy(tp, MII_CTRL1000, giga_ctrl);
- } else {
- if (speed == SPEED_10)
- bmcr = 0;
- else if (speed == SPEED_100)
- bmcr = BMCR_SPEED100;
- else
- goto out;
-
- if (duplex == DUPLEX_FULL)
- bmcr |= BMCR_FULLDPLX;
- }
-
- rtl_writephy(tp, MII_BMCR, bmcr);
-
- if (tp->mac_version == RTL_GIGA_MAC_VER_02 ||
- tp->mac_version == RTL_GIGA_MAC_VER_03) {
- if ((speed == SPEED_100) && (autoneg != AUTONEG_ENABLE)) {
- rtl_writephy(tp, 0x17, 0x2138);
- rtl_writephy(tp, 0x0e, 0x0260);
- } else {
- rtl_writephy(tp, 0x17, 0x2108);
- rtl_writephy(tp, 0x0e, 0x0000);
- }
- }
-
- rc = 0;
-out:
- return rc;
-}
-
-static int rtl8169_set_speed(struct net_device *dev,
- u8 autoneg, u16 speed, u8 duplex, u32 advertising)
-{
- struct rtl8169_private *tp = netdev_priv(dev);
- int ret;
-
- ret = tp->set_speed(dev, autoneg, speed, duplex, advertising);
- if (ret < 0)
- goto out;
-
- if (netif_running(dev) && (autoneg == AUTONEG_ENABLE) &&
- (advertising & ADVERTISED_1000baseT_Full) &&
- !pci_is_pcie(tp->pci_dev)) {
- mod_timer(&tp->timer, jiffies + RTL8169_PHY_TIMEOUT);
- }
-out:
- return ret;
-}
-
static netdev_features_t rtl8169_fix_features(struct net_device *dev,
netdev_features_t features)
{
__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), swab16(opts2 & 0xffff));
}
-static int rtl8169_get_link_ksettings_tbi(struct net_device *dev,
- struct ethtool_link_ksettings *cmd)
-{
- struct rtl8169_private *tp = netdev_priv(dev);
- u32 status;
- u32 supported, advertising;
-
- supported =
- SUPPORTED_1000baseT_Full | SUPPORTED_Autoneg | SUPPORTED_FIBRE;
- cmd->base.port = PORT_FIBRE;
-
- status = RTL_R32(tp, TBICSR);
- advertising = (status & TBINwEnable) ? ADVERTISED_Autoneg : 0;
- cmd->base.autoneg = !!(status & TBINwEnable);
-
- cmd->base.speed = SPEED_1000;
- cmd->base.duplex = DUPLEX_FULL; /* Always set */
-
- ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
- supported);
- ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
- advertising);
-
- return 0;
-}
-
-static int rtl8169_get_link_ksettings_xmii(struct net_device *dev,
- struct ethtool_link_ksettings *cmd)
-{
- struct rtl8169_private *tp = netdev_priv(dev);
-
- mii_ethtool_get_link_ksettings(&tp->mii, cmd);
-
- return 0;
-}
-
-static int rtl8169_get_link_ksettings(struct net_device *dev,
- struct ethtool_link_ksettings *cmd)
-{
- struct rtl8169_private *tp = netdev_priv(dev);
- int rc;
-
- rtl_lock_work(tp);
- rc = tp->get_link_ksettings(dev, cmd);
- rtl_unlock_work(tp);
-
- return rc;
-}
-
-static int rtl8169_set_link_ksettings(struct net_device *dev,
- const struct ethtool_link_ksettings *cmd)
-{
- struct rtl8169_private *tp = netdev_priv(dev);
- int rc;
- u32 advertising;
-
- if (!ethtool_convert_link_mode_to_legacy_u32(&advertising,
- cmd->link_modes.advertising))
- return -EINVAL;
-
- del_timer_sync(&tp->timer);
-
- rtl_lock_work(tp);
- rc = rtl8169_set_speed(dev, cmd->base.autoneg, cmd->base.speed,
- cmd->base.duplex, advertising);
- rtl_unlock_work(tp);
-
- return rc;
-}
-
static void rtl8169_get_regs(struct net_device *dev, struct ethtool_regs *regs,
void *p)
{
}
}
-static int rtl8169_nway_reset(struct net_device *dev)
-{
- struct rtl8169_private *tp = netdev_priv(dev);
-
- return mii_nway_restart(&tp->mii);
-}
-
/*
* Interrupt coalescing
*
const struct rtl_coalesce_info *ci;
int rc;
- rc = rtl8169_get_link_ksettings(dev, &ecmd);
+ rc = phy_ethtool_get_link_ksettings(dev, &ecmd);
if (rc < 0)
return ERR_PTR(rc);
.get_sset_count = rtl8169_get_sset_count,
.get_ethtool_stats = rtl8169_get_ethtool_stats,
.get_ts_info = ethtool_op_get_ts_info,
- .nway_reset = rtl8169_nway_reset,
- .get_link_ksettings = rtl8169_get_link_ksettings,
- .set_link_ksettings = rtl8169_set_link_ksettings,
+ .nway_reset = phy_ethtool_nway_reset,
+ .get_link_ksettings = phy_ethtool_get_link_ksettings,
+ .set_link_ksettings = phy_ethtool_set_link_ksettings,
};
static void rtl8169_get_mac_version(struct rtl8169_private *tp,
"unknown MAC, using family default\n");
tp->mac_version = default_version;
} else if (tp->mac_version == RTL_GIGA_MAC_VER_42) {
- tp->mac_version = tp->mii.supports_gmii ?
+ tp->mac_version = tp->supports_gmii ?
RTL_GIGA_MAC_VER_42 :
RTL_GIGA_MAC_VER_43;
} else if (tp->mac_version == RTL_GIGA_MAC_VER_45) {
- tp->mac_version = tp->mii.supports_gmii ?
+ tp->mac_version = tp->supports_gmii ?
RTL_GIGA_MAC_VER_45 :
RTL_GIGA_MAC_VER_47;
} else if (tp->mac_version == RTL_GIGA_MAC_VER_46) {
- tp->mac_version = tp->mii.supports_gmii ?
+ tp->mac_version = tp->supports_gmii ?
RTL_GIGA_MAC_VER_46 :
RTL_GIGA_MAC_VER_48;
}
static void rtl8169_print_mac_version(struct rtl8169_private *tp)
{
- dprintk("mac_version = 0x%02x\n", tp->mac_version);
+ netif_dbg(tp, drv, tp->dev, "mac_version = 0x%02x\n", tp->mac_version);
}
struct phy_reg {
}
}
-static void rtl_phy_work(struct rtl8169_private *tp)
-{
- struct timer_list *timer = &tp->timer;
- unsigned long timeout = RTL8169_PHY_TIMEOUT;
-
- assert(tp->mac_version > RTL_GIGA_MAC_VER_01);
-
- if (tp->phy_reset_pending(tp)) {
- /*
- * A busy loop could burn quite a few cycles on nowadays CPU.
- * Let's delay the execution of the timer for a few ticks.
- */
- timeout = HZ/10;
- goto out_mod_timer;
- }
-
- if (tp->link_ok(tp))
- return;
-
- netif_dbg(tp, link, tp->dev, "PHY reset until link up\n");
-
- tp->phy_reset_enable(tp);
-
-out_mod_timer:
- mod_timer(timer, jiffies + timeout);
-}
-
static void rtl_schedule_task(struct rtl8169_private *tp, enum rtl_flag flag)
{
if (!test_and_set_bit(flag, tp->wk.flags))
schedule_work(&tp->wk.work);
}
-static void rtl8169_phy_timer(struct timer_list *t)
-{
- struct rtl8169_private *tp = from_timer(tp, t, timer);
-
- rtl_schedule_task(tp, RTL_FLAG_TASK_PHY_PENDING);
-}
-
-DECLARE_RTL_COND(rtl_phy_reset_cond)
-{
- return tp->phy_reset_pending(tp);
-}
-
-static void rtl8169_phy_reset(struct net_device *dev,
- struct rtl8169_private *tp)
-{
- tp->phy_reset_enable(tp);
- rtl_msleep_loop_wait_low(tp, &rtl_phy_reset_cond, 1, 100);
-}
-
static bool rtl_tbi_enabled(struct rtl8169_private *tp)
{
return (tp->mac_version == RTL_GIGA_MAC_VER_01) &&
- (RTL_R8(tp, PHYstatus) & TBI_Enable);
+ (RTL_R8(tp, PHYstatus) & TBI_Enable);
}
static void rtl8169_init_phy(struct net_device *dev, struct rtl8169_private *tp)
rtl_hw_phy_config(dev);
if (tp->mac_version <= RTL_GIGA_MAC_VER_06) {
- dprintk("Set MAC Reg C+CR Offset 0x82h = 0x01h\n");
+ netif_dbg(tp, drv, dev,
+ "Set MAC Reg C+CR Offset 0x82h = 0x01h\n");
RTL_W8(tp, 0x82, 0x01);
}
pci_write_config_byte(tp->pci_dev, PCI_CACHE_LINE_SIZE, 0x08);
if (tp->mac_version == RTL_GIGA_MAC_VER_02) {
- dprintk("Set MAC Reg C+CR Offset 0x82h = 0x01h\n");
+ netif_dbg(tp, drv, dev,
+ "Set MAC Reg C+CR Offset 0x82h = 0x01h\n");
RTL_W8(tp, 0x82, 0x01);
- dprintk("Set PHY Reg 0x0bh = 0x00h\n");
+ netif_dbg(tp, drv, dev,
+ "Set PHY Reg 0x0bh = 0x00h\n");
rtl_writephy(tp, 0x0b, 0x0000); //w 0x0b 15 0 0
}
- rtl8169_phy_reset(dev, tp);
+ /* We may have called phy_speed_down before */
+ phy_speed_up(dev->phydev);
- rtl8169_set_speed(dev, AUTONEG_ENABLE, SPEED_1000, DUPLEX_FULL,
- ADVERTISED_10baseT_Half | ADVERTISED_10baseT_Full |
- ADVERTISED_100baseT_Half | ADVERTISED_100baseT_Full |
- (tp->mii.supports_gmii ?
- ADVERTISED_1000baseT_Half |
- ADVERTISED_1000baseT_Full : 0));
-
- if (rtl_tbi_enabled(tp))
- netif_info(tp, link, dev, "TBI auto-negotiating\n");
+ genphy_soft_reset(dev->phydev);
}
static void rtl_rar_set(struct rtl8169_private *tp, u8 *addr)
static int rtl8169_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
{
- struct rtl8169_private *tp = netdev_priv(dev);
- struct mii_ioctl_data *data = if_mii(ifr);
-
- return netif_running(dev) ? tp->do_ioctl(tp, data, cmd) : -ENODEV;
-}
-
-static int rtl_xmii_ioctl(struct rtl8169_private *tp,
- struct mii_ioctl_data *data, int cmd)
-{
- switch (cmd) {
- case SIOCGMIIPHY:
- data->phy_id = 32; /* Internal PHY */
- return 0;
-
- case SIOCGMIIREG:
- data->val_out = rtl_readphy(tp, data->reg_num & 0x1f);
- return 0;
-
- case SIOCSMIIREG:
- rtl_writephy(tp, data->reg_num & 0x1f, data->val_in);
- return 0;
- }
- return -EOPNOTSUPP;
-}
+ if (!netif_running(dev))
+ return -ENODEV;
-static int rtl_tbi_ioctl(struct rtl8169_private *tp, struct mii_ioctl_data *data, int cmd)
-{
- return -EOPNOTSUPP;
+ return phy_mii_ioctl(dev->phydev, ifr, cmd);
}
static void rtl_init_mdio_ops(struct rtl8169_private *tp)
}
}
-static void rtl_speed_down(struct rtl8169_private *tp)
-{
- u32 adv;
- int lpa;
-
- rtl_writephy(tp, 0x1f, 0x0000);
- lpa = rtl_readphy(tp, MII_LPA);
-
- if (lpa & (LPA_10HALF | LPA_10FULL))
- adv = ADVERTISED_10baseT_Half | ADVERTISED_10baseT_Full;
- else if (lpa & (LPA_100HALF | LPA_100FULL))
- adv = ADVERTISED_10baseT_Half | ADVERTISED_10baseT_Full |
- ADVERTISED_100baseT_Half | ADVERTISED_100baseT_Full;
- else
- adv = ADVERTISED_10baseT_Half | ADVERTISED_10baseT_Full |
- ADVERTISED_100baseT_Half | ADVERTISED_100baseT_Full |
- (tp->mii.supports_gmii ?
- ADVERTISED_1000baseT_Half |
- ADVERTISED_1000baseT_Full : 0);
-
- rtl8169_set_speed(tp->dev, AUTONEG_ENABLE, SPEED_1000, DUPLEX_FULL,
- adv);
-}
-
static void rtl_wol_suspend_quirk(struct rtl8169_private *tp)
{
switch (tp->mac_version) {
static bool rtl_wol_pll_power_down(struct rtl8169_private *tp)
{
- if (!(__rtl8169_get_wol(tp) & WAKE_ANY))
+ if (!netif_running(tp->dev) || !__rtl8169_get_wol(tp))
return false;
- rtl_speed_down(tp);
+ phy_speed_down(tp->dev->phydev, false);
rtl_wol_suspend_quirk(tp);
return true;
}
-static void r8168_phy_power_up(struct rtl8169_private *tp)
-{
- rtl_writephy(tp, 0x1f, 0x0000);
- switch (tp->mac_version) {
- case RTL_GIGA_MAC_VER_11:
- case RTL_GIGA_MAC_VER_12:
- case RTL_GIGA_MAC_VER_17 ... RTL_GIGA_MAC_VER_28:
- case RTL_GIGA_MAC_VER_31:
- rtl_writephy(tp, 0x0e, 0x0000);
- break;
- default:
- break;
- }
- rtl_writephy(tp, MII_BMCR, BMCR_ANENABLE);
-
- /* give MAC/PHY some time to resume */
- msleep(20);
-}
-
-static void r8168_phy_power_down(struct rtl8169_private *tp)
-{
- rtl_writephy(tp, 0x1f, 0x0000);
- switch (tp->mac_version) {
- case RTL_GIGA_MAC_VER_32:
- case RTL_GIGA_MAC_VER_33:
- case RTL_GIGA_MAC_VER_40:
- case RTL_GIGA_MAC_VER_41:
- rtl_writephy(tp, MII_BMCR, BMCR_ANENABLE | BMCR_PDOWN);
- break;
-
- case RTL_GIGA_MAC_VER_11:
- case RTL_GIGA_MAC_VER_12:
- case RTL_GIGA_MAC_VER_17 ... RTL_GIGA_MAC_VER_28:
- case RTL_GIGA_MAC_VER_31:
- rtl_writephy(tp, 0x0e, 0x0200);
- default:
- rtl_writephy(tp, MII_BMCR, BMCR_PDOWN);
- break;
- }
-}
-
static void r8168_pll_power_down(struct rtl8169_private *tp)
{
if (r8168_check_dash(tp))
if (rtl_wol_pll_power_down(tp))
return;
- r8168_phy_power_down(tp);
-
switch (tp->mac_version) {
case RTL_GIGA_MAC_VER_25 ... RTL_GIGA_MAC_VER_33:
case RTL_GIGA_MAC_VER_37:
break;
}
- r8168_phy_power_up(tp);
+ phy_resume(tp->dev->phydev);
+ /* give MAC/PHY some time to resume */
+ msleep(20);
}
static void rtl_pll_power_down(struct rtl8169_private *tp)
if (tp->mac_version == RTL_GIGA_MAC_VER_02 ||
tp->mac_version == RTL_GIGA_MAC_VER_03) {
- dprintk("Set MAC Reg C+CR Offset 0xe0. "
- "Bit-3 and bit-14 MUST be 1\n");
+ netif_dbg(tp, drv, tp->dev,
+ "Set MAC Reg C+CR Offset 0xe0. Bit 3 and Bit 14 MUST be 1\n");
tp->cp_cmd |= (1 << 14);
}
rtl_csi_write(tp, 0x070c, csi | val << 24);
}
-static void rtl_csi_access_enable_1(struct rtl8169_private *tp)
-{
- rtl_csi_access_enable(tp, 0x17);
-}
-
-static void rtl_csi_access_enable_2(struct rtl8169_private *tp)
+static void rtl_set_def_aspm_entry_latency(struct rtl8169_private *tp)
{
rtl_csi_access_enable(tp, 0x27);
}
RTL_W8(tp, Config3, data);
}
+static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable)
+{
+ if (enable) {
+ RTL_W8(tp, Config2, RTL_R8(tp, Config2) | ClkReqEn);
+ RTL_W8(tp, Config5, RTL_R8(tp, Config5) | ASPM_en);
+ } else {
+ RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn);
+ RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en);
+ }
+}
+
static void rtl_hw_start_8168bb(struct rtl8169_private *tp)
{
RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Beacon_en);
{ 0x07, 0, 0x2000 }
};
- rtl_csi_access_enable_2(tp);
+ rtl_set_def_aspm_entry_latency(tp);
rtl_ephy_init(tp, e_info_8168cp, ARRAY_SIZE(e_info_8168cp));
static void rtl_hw_start_8168cp_2(struct rtl8169_private *tp)
{
- rtl_csi_access_enable_2(tp);
+ rtl_set_def_aspm_entry_latency(tp);
RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Beacon_en);
static void rtl_hw_start_8168cp_3(struct rtl8169_private *tp)
{
- rtl_csi_access_enable_2(tp);
+ rtl_set_def_aspm_entry_latency(tp);
RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Beacon_en);
{ 0x06, 0x0080, 0x0000 }
};
- rtl_csi_access_enable_2(tp);
+ rtl_set_def_aspm_entry_latency(tp);
RTL_W8(tp, DBG_REG, 0x06 | FIX_NAK_1 | FIX_NAK_2);
{ 0x03, 0x0400, 0x0220 }
};
- rtl_csi_access_enable_2(tp);
+ rtl_set_def_aspm_entry_latency(tp);
rtl_ephy_init(tp, e_info_8168c_2, ARRAY_SIZE(e_info_8168c_2));
static void rtl_hw_start_8168c_4(struct rtl8169_private *tp)
{
- rtl_csi_access_enable_2(tp);
+ rtl_set_def_aspm_entry_latency(tp);
__rtl_hw_start_8168cp(tp);
}
static void rtl_hw_start_8168d(struct rtl8169_private *tp)
{
- rtl_csi_access_enable_2(tp);
+ rtl_set_def_aspm_entry_latency(tp);
rtl_disable_clock_request(tp);
static void rtl_hw_start_8168dp(struct rtl8169_private *tp)
{
- rtl_csi_access_enable_1(tp);
+ rtl_set_def_aspm_entry_latency(tp);
if (tp->dev->mtu <= ETH_DATA_LEN)
rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
{ 0x0c, 0x0100, 0x0020 }
};
- rtl_csi_access_enable_1(tp);
+ rtl_set_def_aspm_entry_latency(tp);
rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
{ 0x0a, 0x0000, 0x0040 }
};
- rtl_csi_access_enable_2(tp);
+ rtl_set_def_aspm_entry_latency(tp);
rtl_ephy_init(tp, e_info_8168e_1, ARRAY_SIZE(e_info_8168e_1));
{ 0x19, 0x0000, 0x0224 }
};
- rtl_csi_access_enable_1(tp);
+ rtl_set_def_aspm_entry_latency(tp);
rtl_ephy_init(tp, e_info_8168e_2, ARRAY_SIZE(e_info_8168e_2));
RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) | PFM_EN);
RTL_W32(tp, MISC, RTL_R32(tp, MISC) | PWM_EN);
RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~Spi_en);
+
+ rtl_hw_aspm_clkreq_enable(tp, true);
}
static void rtl_hw_start_8168f(struct rtl8169_private *tp)
{
- rtl_csi_access_enable_2(tp);
+ rtl_set_def_aspm_entry_latency(tp);
rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
rtl_eri_write(tp, 0xd0, ERIAR_MASK_0001, 0x48, ERIAR_EXGMAC);
rtl_eri_write(tp, 0xe8, ERIAR_MASK_1111, 0x00100006, ERIAR_EXGMAC);
- rtl_csi_access_enable_1(tp);
+ rtl_set_def_aspm_entry_latency(tp);
rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
rtl_hw_start_8168g(tp);
/* disable aspm and clock request before access ephy */
- RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn);
- RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en);
+ rtl_hw_aspm_clkreq_enable(tp, false);
rtl_ephy_init(tp, e_info_8168g_1, ARRAY_SIZE(e_info_8168g_1));
+ rtl_hw_aspm_clkreq_enable(tp, true);
}
static void rtl_hw_start_8168g_2(struct rtl8169_private *tp)
rtl_hw_start_8168g(tp);
/* disable aspm and clock request before access ephy */
- RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn);
- RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en);
+ rtl_hw_aspm_clkreq_enable(tp, false);
rtl_ephy_init(tp, e_info_8411_2, ARRAY_SIZE(e_info_8411_2));
+ rtl_hw_aspm_clkreq_enable(tp, true);
}
static void rtl_hw_start_8168h_1(struct rtl8169_private *tp)
};
/* disable aspm and clock request before access ephy */
- RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn);
- RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en);
+ rtl_hw_aspm_clkreq_enable(tp, false);
rtl_ephy_init(tp, e_info_8168h_1, ARRAY_SIZE(e_info_8168h_1));
RTL_W32(tp, TxConfig, RTL_R32(tp, TxConfig) | TXCFG_AUTO_FIFO);
rtl_eri_write(tp, 0xd0, ERIAR_MASK_0001, 0x48, ERIAR_EXGMAC);
rtl_eri_write(tp, 0xe8, ERIAR_MASK_1111, 0x00100006, ERIAR_EXGMAC);
- rtl_csi_access_enable_1(tp);
+ rtl_set_def_aspm_entry_latency(tp);
rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
r8168_mac_ocp_write(tp, 0xe63e, 0x0000);
r8168_mac_ocp_write(tp, 0xc094, 0x0000);
r8168_mac_ocp_write(tp, 0xc09e, 0x0000);
+
+ rtl_hw_aspm_clkreq_enable(tp, true);
}
static void rtl_hw_start_8168ep(struct rtl8169_private *tp)
rtl_eri_write(tp, 0xd0, ERIAR_MASK_0001, 0x5f, ERIAR_EXGMAC);
rtl_eri_write(tp, 0xe8, ERIAR_MASK_1111, 0x00100006, ERIAR_EXGMAC);
- rtl_csi_access_enable_1(tp);
+ rtl_set_def_aspm_entry_latency(tp);
rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
};
/* disable aspm and clock request before access ephy */
- RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn);
- RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en);
+ rtl_hw_aspm_clkreq_enable(tp, false);
rtl_ephy_init(tp, e_info_8168ep_1, ARRAY_SIZE(e_info_8168ep_1));
rtl_hw_start_8168ep(tp);
+
+ rtl_hw_aspm_clkreq_enable(tp, true);
}
static void rtl_hw_start_8168ep_2(struct rtl8169_private *tp)
};
/* disable aspm and clock request before access ephy */
- RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn);
- RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en);
+ rtl_hw_aspm_clkreq_enable(tp, false);
rtl_ephy_init(tp, e_info_8168ep_2, ARRAY_SIZE(e_info_8168ep_2));
rtl_hw_start_8168ep(tp);
RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) & ~PFM_EN);
RTL_W8(tp, MISC_1, RTL_R8(tp, MISC_1) & ~PFM_D3COLD_EN);
+
+ rtl_hw_aspm_clkreq_enable(tp, true);
}
static void rtl_hw_start_8168ep_3(struct rtl8169_private *tp)
};
/* disable aspm and clock request before access ephy */
- RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn);
- RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en);
+ rtl_hw_aspm_clkreq_enable(tp, false);
rtl_ephy_init(tp, e_info_8168ep_3, ARRAY_SIZE(e_info_8168ep_3));
rtl_hw_start_8168ep(tp);
data = r8168_mac_ocp_read(tp, 0xe860);
data |= 0x0080;
r8168_mac_ocp_write(tp, 0xe860, data);
+
+ rtl_hw_aspm_clkreq_enable(tp, true);
}
static void rtl_hw_start_8168(struct rtl8169_private *tp)
break;
default:
- printk(KERN_ERR PFX "%s: unknown chipset (mac_version = %d).\n",
- tp->dev->name, tp->mac_version);
+ netif_err(tp, drv, tp->dev,
+ "unknown chipset (mac_version = %d)\n",
+ tp->mac_version);
break;
}
}
};
u8 cfg1;
- rtl_csi_access_enable_2(tp);
+ rtl_set_def_aspm_entry_latency(tp);
RTL_W8(tp, DBG_REG, FIX_NAK_1);
static void rtl_hw_start_8102e_2(struct rtl8169_private *tp)
{
- rtl_csi_access_enable_2(tp);
+ rtl_set_def_aspm_entry_latency(tp);
rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
{ 0x1e, 0, 0x4000 }
};
- rtl_csi_access_enable_2(tp);
+ rtl_set_def_aspm_entry_latency(tp);
/* Force LAN exit from ASPM if Rx/Tx are not idle */
RTL_W32(tp, FuncEvent, RTL_R32(tp, FuncEvent) | 0x002800);
napi_enable(&tp->napi);
rtl_hw_start(tp);
netif_wake_queue(dev);
- rtl8169_check_link_status(dev, tp);
}
static void rtl8169_tx_timeout(struct net_device *dev)
rtl8169_pcierr_interrupt(dev);
if (status & LinkChg)
- rtl8169_check_link_status(dev, tp);
+ phy_mac_interrupt(dev->phydev);
rtl_irq_enable_all(tp);
}
/* XXX - keep rtl_slow_event_work() as first element. */
{ RTL_FLAG_TASK_SLOW_PENDING, rtl_slow_event_work },
{ RTL_FLAG_TASK_RESET_PENDING, rtl_reset_work },
- { RTL_FLAG_TASK_PHY_PENDING, rtl_phy_work }
};
struct rtl8169_private *tp =
container_of(work, struct rtl8169_private, wk.work);
RTL_W32(tp, RxMissed, 0);
}
+static void r8169_phylink_handler(struct net_device *ndev)
+{
+ struct rtl8169_private *tp = netdev_priv(ndev);
+
+ if (netif_carrier_ok(ndev)) {
+ rtl_link_chg_patch(tp);
+ pm_request_resume(&tp->pci_dev->dev);
+ } else {
+ pm_runtime_idle(&tp->pci_dev->dev);
+ }
+
+ if (net_ratelimit())
+ phy_print_status(ndev->phydev);
+}
+
+static int r8169_phy_connect(struct rtl8169_private *tp)
+{
+ struct phy_device *phydev = mdiobus_get_phy(tp->mii_bus, 0);
+ phy_interface_t phy_mode;
+ int ret;
+
+ phy_mode = tp->supports_gmii ? PHY_INTERFACE_MODE_GMII :
+ PHY_INTERFACE_MODE_MII;
+
+ ret = phy_connect_direct(tp->dev, phydev, r8169_phylink_handler,
+ phy_mode);
+ if (ret)
+ return ret;
+
+ if (!tp->supports_gmii)
+ phy_set_max_speed(phydev, SPEED_100);
+
+ /* Ensure to advertise everything, incl. pause */
+ phydev->advertising = phydev->supported;
+
+ phy_attached_info(phydev);
+
+ return 0;
+}
+
static void rtl8169_down(struct net_device *dev)
{
struct rtl8169_private *tp = netdev_priv(dev);
- del_timer_sync(&tp->timer);
+ phy_stop(dev->phydev);
napi_disable(&tp->napi);
netif_stop_queue(dev);
cancel_work_sync(&tp->wk.work);
+ phy_disconnect(dev->phydev);
+
pci_free_irq(pdev, 0, tp);
dma_free_coherent(&pdev->dev, R8169_RX_RING_BYTES, tp->RxDescArray,
{
struct rtl8169_private *tp = netdev_priv(dev);
- rtl8169_interrupt(pci_irq_vector(tp->pci_dev, 0), dev);
+ rtl8169_interrupt(pci_irq_vector(tp->pci_dev, 0), tp);
}
#endif
if (retval < 0)
goto err_release_fw_2;
+ retval = r8169_phy_connect(tp);
+ if (retval)
+ goto err_free_irq;
+
rtl_lock_work(tp);
set_bit(RTL_FLAG_TASK_ENABLED, tp->wk.flags);
if (!rtl8169_init_counter_offsets(tp))
netif_warn(tp, hw, dev, "counter reset/update failed\n");
+ phy_start(dev->phydev);
netif_start_queue(dev);
rtl_unlock_work(tp);
- tp->saved_wolopts = 0;
pm_runtime_put_sync(&pdev->dev);
-
- rtl8169_check_link_status(dev, tp);
out:
return retval;
+err_free_irq:
+ pci_free_irq(pdev, 0, tp);
err_release_fw_2:
rtl_release_firmware(tp);
rtl8169_rx_clear(tp);
if (!netif_running(dev))
return;
+ phy_stop(dev->phydev);
netif_device_detach(dev);
netif_stop_queue(dev);
netif_device_attach(dev);
rtl_pll_power_up(tp);
+ rtl8169_init_phy(dev, tp);
+
+ phy_start(tp->dev->phydev);
rtl_lock_work(tp);
napi_enable(&tp->napi);
{
struct pci_dev *pdev = to_pci_dev(device);
struct net_device *dev = pci_get_drvdata(pdev);
- struct rtl8169_private *tp = netdev_priv(dev);
-
- rtl8169_init_phy(dev, tp);
if (netif_running(dev))
__rtl8169_resume(dev);
struct net_device *dev = pci_get_drvdata(pdev);
struct rtl8169_private *tp = netdev_priv(dev);
- if (!tp->TxDescArray) {
- rtl_pll_power_down(tp);
+ if (!tp->TxDescArray)
return 0;
- }
rtl_lock_work(tp);
- tp->saved_wolopts = __rtl8169_get_wol(tp);
__rtl8169_set_wol(tp, WAKE_ANY);
rtl_unlock_work(tp);
rtl_lock_work(tp);
__rtl8169_set_wol(tp, tp->saved_wolopts);
- tp->saved_wolopts = 0;
rtl_unlock_work(tp);
- rtl8169_init_phy(dev, tp);
-
__rtl8169_resume(dev);
return 0;
rtl8169_hw_reset(tp);
if (system_state == SYSTEM_POWER_OFF) {
- if (__rtl8169_get_wol(tp) & WAKE_ANY) {
+ if (tp->saved_wolopts) {
rtl_wol_suspend_quirk(tp);
rtl_wol_shutdown_quirk(tp);
}
netif_napi_del(&tp->napi);
unregister_netdev(dev);
+ mdiobus_unregister(tp->mii_bus);
rtl_release_firmware(tp);
return (RTL_R8(tp, MCU) & RXTX_EMPTY) == RXTX_EMPTY;
}
+static int r8169_mdio_read_reg(struct mii_bus *mii_bus, int phyaddr, int phyreg)
+{
+ struct rtl8169_private *tp = mii_bus->priv;
+
+ if (phyaddr > 0)
+ return -ENODEV;
+
+ return rtl_readphy(tp, phyreg);
+}
+
+static int r8169_mdio_write_reg(struct mii_bus *mii_bus, int phyaddr,
+ int phyreg, u16 val)
+{
+ struct rtl8169_private *tp = mii_bus->priv;
+
+ if (phyaddr > 0)
+ return -ENODEV;
+
+ rtl_writephy(tp, phyreg, val);
+
+ return 0;
+}
+
+static int r8169_mdio_register(struct rtl8169_private *tp)
+{
+ struct pci_dev *pdev = tp->pci_dev;
+ struct phy_device *phydev;
+ struct mii_bus *new_bus;
+ int ret;
+
+ new_bus = devm_mdiobus_alloc(&pdev->dev);
+ if (!new_bus)
+ return -ENOMEM;
+
+ new_bus->name = "r8169";
+ new_bus->priv = tp;
+ new_bus->parent = &pdev->dev;
+ new_bus->irq[0] = PHY_IGNORE_INTERRUPT;
+ snprintf(new_bus->id, MII_BUS_ID_SIZE, "r8169-%x",
+ PCI_DEVID(pdev->bus->number, pdev->devfn));
+
+ new_bus->read = r8169_mdio_read_reg;
+ new_bus->write = r8169_mdio_write_reg;
+
+ ret = mdiobus_register(new_bus);
+ if (ret)
+ return ret;
+
+ phydev = mdiobus_get_phy(new_bus, 0);
+ if (!phydev) {
+ mdiobus_unregister(new_bus);
+ return -ENODEV;
+ }
+
+ /* PHY will be woken up in rtl_open() */
+ phy_suspend(phydev);
+
+ tp->mii_bus = new_bus;
+
+ return 0;
+}
+
static void rtl_hw_init_8168g(struct rtl8169_private *tp)
{
u32 data;
{
const struct rtl_cfg_info *cfg = rtl_cfg_infos + ent->driver_data;
struct rtl8169_private *tp;
- struct mii_if_info *mii;
struct net_device *dev;
int chipset, region, i;
int rc;
tp->dev = dev;
tp->pci_dev = pdev;
tp->msg_enable = netif_msg_init(debug.msg_enable, R8169_MSG_DEFAULT);
-
- mii = &tp->mii;
- mii->dev = dev;
- mii->mdio_read = rtl_mdio_read;
- mii->mdio_write = rtl_mdio_write;
- mii->phy_id_mask = 0x1f;
- mii->reg_num_mask = 0x1f;
- mii->supports_gmii = cfg->has_gmii;
-
- /* disable ASPM completely as that cause random device stop working
- * problems as well as full system hangs for some PCIe devices users */
- pci_disable_link_state(pdev, PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1 |
- PCIE_LINK_STATE_CLKPM);
+ tp->supports_gmii = cfg->has_gmii;
/* enable device (incl. PCI PM wakeup and hotplug setup) */
rc = pcim_enable_device(pdev);
/* Identify chip attached to board */
rtl8169_get_mac_version(tp, cfg->default_ver);
+ if (rtl_tbi_enabled(tp)) {
+ dev_err(&pdev->dev, "TBI fiber mode not supported\n");
+ return -ENODEV;
+ }
+
tp->cp_cmd = RTL_R16(tp, CPlusCmd);
if ((sizeof(dma_addr_t) > 4) &&
/* override BIOS settings, use userspace tools to enable WOL */
__rtl8169_set_wol(tp, 0);
- if (rtl_tbi_enabled(tp)) {
- tp->set_speed = rtl8169_set_speed_tbi;
- tp->get_link_ksettings = rtl8169_get_link_ksettings_tbi;
- tp->phy_reset_enable = rtl8169_tbi_reset_enable;
- tp->phy_reset_pending = rtl8169_tbi_reset_pending;
- tp->link_ok = rtl8169_tbi_link_ok;
- tp->do_ioctl = rtl_tbi_ioctl;
- } else {
- tp->set_speed = rtl8169_set_speed_xmii;
- tp->get_link_ksettings = rtl8169_get_link_ksettings_xmii;
- tp->phy_reset_enable = rtl8169_xmii_reset_enable;
- tp->phy_reset_pending = rtl8169_xmii_reset_pending;
- tp->link_ok = rtl8169_xmii_link_ok;
- tp->do_ioctl = rtl_xmii_ioctl;
- }
-
mutex_init(&tp->wk.mutex);
u64_stats_init(&tp->rx_stats.syncp);
u64_stats_init(&tp->tx_stats.syncp);
tp->event_slow = cfg->event_slow;
tp->coalesce_info = cfg->coalesce_info;
- timer_setup(&tp->timer, rtl8169_phy_timer, 0);
-
tp->rtl_fw = RTL_FIRMWARE_UNKNOWN;
tp->counters = dmam_alloc_coherent (&pdev->dev, sizeof(*tp->counters),
pci_set_drvdata(pdev, dev);
- rc = register_netdev(dev);
- if (rc < 0)
+ rc = r8169_mdio_register(tp);
+ if (rc)
return rc;
+ /* chip gets powered up in rtl_open() */
+ rtl_pll_power_down(tp);
+
+ rc = register_netdev(dev);
+ if (rc)
+ goto err_mdio_unregister;
+
netif_info(tp, probe, dev, "%s, %pM, XID %08x, IRQ %d\n",
rtl_chip_infos[chipset].name, dev->dev_addr,
(u32)(RTL_R32(tp, TxConfig) & 0xfcf0f8ff),
if (r8168_check_dash(tp))
rtl8168_driver_start(tp);
- netif_carrier_off(dev);
-
if (pci_dev_run_wake(pdev))
pm_runtime_put_sync(&pdev->dev);
return 0;
+
+err_mdio_unregister:
+ mdiobus_unregister(tp->mii_bus);
+ return rc;
}
static struct pci_driver rtl8169_pci_driver = {
config SH_ETH
tristate "Renesas SuperH Ethernet support"
- depends on HAS_DMA
depends on ARCH_RENESAS || SUPERH || COMPILE_TEST
select CRC32
select MII
config RAVB
tristate "Renesas Ethernet AVB support"
- depends on HAS_DMA
depends on ARCH_RENESAS || COMPILE_TEST
select CRC32
select MII
}
static void ravb_get_ethtool_stats(struct net_device *ndev,
- struct ethtool_stats *stats, u64 *data)
+ struct ethtool_stats *estats, u64 *data)
{
struct ravb_private *priv = netdev_priv(ndev);
int i = 0;
{
switch (stringset) {
case ETH_SS_STATS:
- memcpy(data, *ravb_gstrings_stats, sizeof(ravb_gstrings_stats));
+ memcpy(data, ravb_gstrings_stats, sizeof(ravb_gstrings_stats));
break;
}
}
/* TAG and timestamp required flag */
skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
desc->tagh_tsr = (ts_skb->tag >> 4) | TX_TSR;
- desc->ds_tagl |= le16_to_cpu(ts_skb->tag << 12);
+ desc->ds_tagl |= cpu_to_le16(ts_skb->tag << 12);
}
skb_tx_timestamp(skb);
}
static u16 ravb_select_queue(struct net_device *ndev, struct sk_buff *skb,
- void *accel_priv, select_queue_fallback_t fallback)
+ struct net_device *sb_dev,
+ select_queue_fallback_t fallback)
{
/* If skb needs TX timestamp, it is handled in network control queue */
return (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) ? RAVB_NC :
.tpauser = 1,
.hw_swap = 1,
.rpadir = 1,
- .rpadir_value = 2 << 16,
.no_trimd = 1,
.no_ade = 1,
.xdfar_rw = 1,
.bculr = 1,
.hw_swap = 1,
.rpadir = 1,
- .rpadir_value = 2 << 16,
.no_trimd = 1,
.no_ade = 1,
.xdfar_rw = 1,
.hw_swap = 1,
.nbst = 1,
.rpadir = 1,
- .rpadir_value = 2 << 16,
.no_trimd = 1,
.no_ade = 1,
.xdfar_rw = 1,
.tpauser = 1,
.hw_swap = 1,
.rpadir = 1,
- .rpadir_value = 0x00020000, /* NET_IP_ALIGN assumed to be 2 */
};
static void sh_eth_set_rate_sh7757(struct net_device *ndev)
.hw_swap = 1,
.no_ade = 1,
.rpadir = 1,
- .rpadir_value = 2 << 16,
.rtrate = 1,
.dual_port = 1,
};
.bculr = 1,
.hw_swap = 1,
.rpadir = 1,
- .rpadir_value = 2 << 16,
.no_trimd = 1,
.no_ade = 1,
.xdfar_rw = 1,
/* Descriptor format */
sh_eth_ring_format(ndev);
if (mdp->cd->rpadir)
- sh_eth_write(ndev, mdp->cd->rpadir_value, RPADIR);
+ sh_eth_write(ndev, NET_IP_ALIGN << 16, RPADIR);
/* all sh_eth int mask */
sh_eth_write(ndev, 0, EESIPR);
/* mask reset */
if (mdp->cd->apr)
- sh_eth_write(ndev, APR_AP, APR);
+ sh_eth_write(ndev, 1, APR);
if (mdp->cd->mpr)
- sh_eth_write(ndev, MPR_MP, MPR);
+ sh_eth_write(ndev, 1, MPR);
if (mdp->cd->tpauser)
sh_eth_write(ndev, TPAUSER_UNLIMITED, TPAUSER);
/* APR */
enum APR_BIT {
- APR_AP = 0x00000001,
+ APR_AP = 0x0000ffff,
};
/* MPR */
enum MPR_BIT {
- MPR_MP = 0x00000001,
+ MPR_MP = 0x0000ffff,
};
/* TRSCER */
/* RPADIR */
enum RPADIR_BIT {
- RPADIR_PADS1 = 0x20000, RPADIR_PADS0 = 0x10000,
- RPADIR_PADR = 0x0003f,
+ RPADIR_PADS = 0x1f0000, RPADIR_PADR = 0xffff,
};
/* FDR */
u32 ecsipr_value;
u32 fdr_value;
u32 fcftr_value;
- u32 rpadir_value;
/* interrupt checking mask */
u32 tx_check;
sfc-$(CONFIG_SFC_SRIOV) += sriov.o siena_sriov.o ef10_sriov.o
obj-$(CONFIG_SFC) += sfc.o
+
+obj-$(CONFIG_SFC_FALCON) += falcon/
return -ENOMEM;
for (i = 0; i < efx->vf_count; i++) {
- random_ether_addr(nic_data->vf[i].mac);
+ eth_random_addr(nic_data->vf[i].mac);
nic_data->vf[i].efx = NULL;
nic_data->vf[i].vlan = EFX_EF10_NO_VLAN;
{
struct efx_ef10_nic_data *nic_data = efx->nic_data;
struct ef10_vf *vf;
- u16 old_vlan, new_vlan;
+ u16 new_vlan;
int rc = 0, rc2 = 0;
if (vf_i >= efx->vf_count)
}
/* Do the actual vlan change */
- old_vlan = vf->vlan;
vf->vlan = new_vlan;
/* Restore everything in reverse order */
static int efx_process_channel(struct efx_channel *channel, int budget)
{
struct efx_tx_queue *tx_queue;
+ struct list_head rx_list;
int spent;
if (unlikely(!channel->enabled))
return 0;
+ /* Prepare the batch receive list */
+ EFX_WARN_ON_PARANOID(channel->rx_list != NULL);
+ INIT_LIST_HEAD(&rx_list);
+ channel->rx_list = &rx_list;
+
efx_for_each_channel_tx_queue(tx_queue, channel) {
tx_queue->pkts_compl = 0;
tx_queue->bytes_compl = 0;
}
}
+ /* Receive any packets we queued up */
+ netif_receive_skb_list(channel->rx_list);
+ channel->rx_list = NULL;
+
return spent;
}
goto fail;
}
+ channel->rx_list = NULL;
+
return 0;
fail:
return true;
}
+static
struct hlist_head *efx_rps_hash_bucket(struct efx_nic *efx,
const struct efx_filter_spec *spec)
{
if (!state)
return -ENOMEM;
efx->filter_state = state;
+ init_rwsem(&state->lock);
table = &state->table[EFX_FARCH_FILTER_TABLE_RX_IP];
table->id = EFX_FARCH_FILTER_TABLE_RX_IP;
* __efx_rx_packet(), or zero if there is none
* @rx_pkt_index: Ring index of first buffer for next packet to be delivered
* by __efx_rx_packet(), if @rx_pkt_n_frags != 0
+ * @rx_list: list of SKBs from current RX, awaiting processing
* @rx_queue: RX queue for this channel
* @tx_queue: TX queues for this channel
* @sync_events_state: Current state of sync events on this channel
unsigned int rx_pkt_n_frags;
unsigned int rx_pkt_index;
+ struct list_head *rx_list;
+
struct efx_rx_queue rx_queue;
struct efx_tx_queue tx_queue[EFX_TXQ_TYPES];
return;
/* Pass the packet up */
- netif_receive_skb(skb);
+ if (channel->rx_list != NULL)
+ /* Add to list, will pass up later */
+ list_add_tail(&skb->list, channel->rx_list);
+ else
+ /* No list, so pass it up now */
+ netif_receive_skb(skb);
}
/* Handle a received packet. Second half: Touches packet payload. */
static int card_idx = -1;
void __iomem *ioaddr;
int chip_idx = (int) ent->driver_data;
- int irq;
struct net_device *dev;
struct epic_private *ep;
int i, ret, option = 0, duplex = 0;
ret = pci_enable_device(pdev);
if (ret)
goto out;
- irq = pdev->irq;
if (pci_resource_len(pdev, 0) < EPIC_TOTAL_SIZE) {
dev_err(&pdev->dev, "no PCI region space\n");
static int netsec_napi_poll(struct napi_struct *napi, int budget)
{
struct netsec_priv *priv;
- struct net_device *ndev;
int tx, rx, done, todo;
priv = container_of(napi, struct netsec_priv, napi);
- ndev = priv->ndev;
todo = budget;
do {
config DWMAC_SOCFPGA
tristate "SOCFPGA dwmac support"
default ARCH_SOCFPGA
- depends on OF && (ARCH_SOCFPGA || COMPILE_TEST)
+ depends on OF && (ARCH_SOCFPGA || ARCH_STRATIX10 || COMPILE_TEST)
select MFD_SYSCON
help
Support for ethernet controller on Altera SOCFPGA
struct clk *mac_clk_tx;
struct clk *clk_mac_ref;
struct clk *clk_mac_refout;
+ struct clk *clk_mac_speed;
struct clk *aclk_mac;
struct clk *pclk_mac;
struct clk *clk_phy;
(((tx) ? soc##_GMAC_TXCLK_DLY_ENABLE : soc##_GMAC_TXCLK_DLY_DISABLE) | \
((rx) ? soc##_GMAC_RXCLK_DLY_ENABLE : soc##_GMAC_RXCLK_DLY_DISABLE))
+#define PX30_GRF_GMAC_CON1 0x0904
+
+/* PX30_GRF_GMAC_CON1 */
+#define PX30_GMAC_PHY_INTF_SEL_RMII (GRF_CLR_BIT(4) | GRF_CLR_BIT(5) | \
+ GRF_BIT(6))
+#define PX30_GMAC_SPEED_10M GRF_CLR_BIT(2)
+#define PX30_GMAC_SPEED_100M GRF_BIT(2)
+
+static void px30_set_to_rmii(struct rk_priv_data *bsp_priv)
+{
+ struct device *dev = &bsp_priv->pdev->dev;
+
+ if (IS_ERR(bsp_priv->grf)) {
+ dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
+ return;
+ }
+
+ regmap_write(bsp_priv->grf, PX30_GRF_GMAC_CON1,
+ PX30_GMAC_PHY_INTF_SEL_RMII);
+}
+
+static void px30_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed)
+{
+ struct device *dev = &bsp_priv->pdev->dev;
+ int ret;
+
+ if (IS_ERR(bsp_priv->clk_mac_speed)) {
+ dev_err(dev, "%s: Missing clk_mac_speed clock\n", __func__);
+ return;
+ }
+
+ if (speed == 10) {
+ regmap_write(bsp_priv->grf, PX30_GRF_GMAC_CON1,
+ PX30_GMAC_SPEED_10M);
+
+ ret = clk_set_rate(bsp_priv->clk_mac_speed, 2500000);
+ if (ret)
+ dev_err(dev, "%s: set clk_mac_speed rate 2500000 failed: %d\n",
+ __func__, ret);
+ } else if (speed == 100) {
+ regmap_write(bsp_priv->grf, PX30_GRF_GMAC_CON1,
+ PX30_GMAC_SPEED_100M);
+
+ ret = clk_set_rate(bsp_priv->clk_mac_speed, 25000000);
+ if (ret)
+ dev_err(dev, "%s: set clk_mac_speed rate 25000000 failed: %d\n",
+ __func__, ret);
+
+ } else {
+ dev_err(dev, "unknown speed value for RMII! speed=%d", speed);
+ }
+}
+
+static const struct rk_gmac_ops px30_ops = {
+ .set_to_rmii = px30_set_to_rmii,
+ .set_rmii_speed = px30_set_rmii_speed,
+};
+
#define RK3128_GRF_MAC_CON0 0x0168
#define RK3128_GRF_MAC_CON1 0x016c
}
}
+ bsp_priv->clk_mac_speed = devm_clk_get(dev, "clk_mac_speed");
+ if (IS_ERR(bsp_priv->clk_mac_speed))
+ dev_err(dev, "cannot get clock %s\n", "clk_mac_speed");
+
if (bsp_priv->clock_input) {
dev_info(dev, "clock input from PHY\n");
} else {
if (!IS_ERR(bsp_priv->mac_clk_tx))
clk_prepare_enable(bsp_priv->mac_clk_tx);
+ if (!IS_ERR(bsp_priv->clk_mac_speed))
+ clk_prepare_enable(bsp_priv->clk_mac_speed);
+
/**
* if (!IS_ERR(bsp_priv->clk_mac))
* clk_prepare_enable(bsp_priv->clk_mac);
clk_disable_unprepare(bsp_priv->pclk_mac);
clk_disable_unprepare(bsp_priv->mac_clk_tx);
+
+ clk_disable_unprepare(bsp_priv->clk_mac_speed);
/**
* if (!IS_ERR(bsp_priv->clk_mac))
* clk_disable_unprepare(bsp_priv->clk_mac);
static SIMPLE_DEV_PM_OPS(rk_gmac_pm_ops, rk_gmac_suspend, rk_gmac_resume);
static const struct of_device_id rk_gmac_dwmac_match[] = {
+ { .compatible = "rockchip,px30-gmac", .data = &px30_ops },
{ .compatible = "rockchip,rk3128-gmac", .data = &rk3128_ops },
{ .compatible = "rockchip,rk3228-gmac", .data = &rk3228_ops },
{ .compatible = "rockchip,rk3288-gmac", .data = &rk3288_ops },
struct device *dev;
struct regmap *sys_mgr_base_addr;
struct reset_control *stmmac_rst;
+ struct reset_control *stmmac_ocp_rst;
void __iomem *splitter_base;
bool f2h_ptp_ref_clk;
struct tse_pcs pcs;
val = SYSMGR_EMACGRP_CTRL_PHYSEL_ENUM_GMII_MII;
/* Assert reset to the enet controller before changing the phy mode */
- if (dwmac->stmmac_rst)
- reset_control_assert(dwmac->stmmac_rst);
+ reset_control_assert(dwmac->stmmac_ocp_rst);
+ reset_control_assert(dwmac->stmmac_rst);
regmap_read(sys_mgr_base_addr, reg_offset, &ctrl);
ctrl &= ~(SYSMGR_EMACGRP_CTRL_PHYSEL_MASK << reg_shift);
/* Deassert reset for the phy configuration to be sampled by
* the enet controller, and operation to start in requested mode
*/
- if (dwmac->stmmac_rst)
- reset_control_deassert(dwmac->stmmac_rst);
+ reset_control_deassert(dwmac->stmmac_ocp_rst);
+ reset_control_deassert(dwmac->stmmac_rst);
if (phymode == PHY_INTERFACE_MODE_SGMII) {
if (tse_pcs_init(dwmac->pcs.tse_pcs_base, &dwmac->pcs) != 0) {
dev_err(dwmac->dev, "Unable to initialize TSE PCS");
goto err_remove_config_dt;
}
+ dwmac->stmmac_ocp_rst = devm_reset_control_get_optional(dev, "stmmaceth-ocp");
+ if (IS_ERR(dwmac->stmmac_ocp_rst)) {
+ ret = PTR_ERR(dwmac->stmmac_ocp_rst);
+ dev_err(dev, "error getting reset control of ocp %d\n", ret);
+ goto err_remove_config_dt;
+ }
+
+ reset_control_deassert(dwmac->stmmac_ocp_rst);
+
ret = socfpga_dwmac_parse_data(dwmac, dev);
if (ret) {
dev_err(dev, "Unable to parse OF data\n");
}
}
+static void dwmac4_qmode(void __iomem *ioaddr, u32 channel, u8 qmode)
+{
+ u32 mtl_tx_op = readl(ioaddr + MTL_CHAN_TX_OP_MODE(channel));
+
+ mtl_tx_op &= ~MTL_OP_MODE_TXQEN_MASK;
+ if (qmode != MTL_QUEUE_AVB)
+ mtl_tx_op |= MTL_OP_MODE_TXQEN;
+ else
+ mtl_tx_op |= MTL_OP_MODE_TXQEN_AV;
+
+ writel(mtl_tx_op, ioaddr + MTL_CHAN_TX_OP_MODE(channel));
+}
+
+static void dwmac4_set_bfsize(void __iomem *ioaddr, int bfsize, u32 chan)
+{
+ u32 value = readl(ioaddr + DMA_CHAN_RX_CONTROL(chan));
+
+ value &= ~DMA_RBSZ_MASK;
+ value |= (bfsize << DMA_RBSZ_SHIFT) & DMA_RBSZ_MASK;
+
+ writel(value, ioaddr + DMA_CHAN_RX_CONTROL(chan));
+}
+
const struct stmmac_dma_ops dwmac4_dma_ops = {
.reset = dwmac4_dma_reset,
.init = dwmac4_dma_init,
.set_rx_tail_ptr = dwmac4_set_rx_tail_ptr,
.set_tx_tail_ptr = dwmac4_set_tx_tail_ptr,
.enable_tso = dwmac4_enable_tso,
+ .qmode = dwmac4_qmode,
+ .set_bfsize = dwmac4_set_bfsize,
};
const struct stmmac_dma_ops dwmac410_dma_ops = {
.set_rx_tail_ptr = dwmac4_set_rx_tail_ptr,
.set_tx_tail_ptr = dwmac4_set_tx_tail_ptr,
.enable_tso = dwmac4_enable_tso,
+ .qmode = dwmac4_qmode,
+ .set_bfsize = dwmac4_set_bfsize,
};
/* DMA Rx Channel X Control register defines */
#define DMA_CONTROL_SR BIT(0)
+#define DMA_RBSZ_MASK GENMASK(14, 1)
+#define DMA_RBSZ_SHIFT 1
/* Interrupt status per channel */
#define DMA_CHAN_STATUS_REB GENMASK(21, 19)
void (*set_rx_tail_ptr)(void __iomem *ioaddr, u32 tail_ptr, u32 chan);
void (*set_tx_tail_ptr)(void __iomem *ioaddr, u32 tail_ptr, u32 chan);
void (*enable_tso)(void __iomem *ioaddr, bool en, u32 chan);
+ void (*qmode)(void __iomem *ioaddr, u32 channel, u8 qmode);
+ void (*set_bfsize)(void __iomem *ioaddr, int bfsize, u32 chan);
};
#define stmmac_reset(__priv, __args...) \
stmmac_do_void_callback(__priv, dma, set_tx_tail_ptr, __args)
#define stmmac_enable_tso(__priv, __args...) \
stmmac_do_void_callback(__priv, dma, enable_tso, __args)
+#define stmmac_dma_qmode(__priv, __args...) \
+ stmmac_do_void_callback(__priv, dma, qmode, __args)
+#define stmmac_set_dma_bfsize(__priv, __args...) \
+ stmmac_do_void_callback(__priv, dma, set_bfsize, __args)
struct mac_device_info;
struct net_device;
struct stmmac_priv;
struct tc_cls_u32_offload;
+struct tc_cbs_qopt_offload;
struct stmmac_tc_ops {
int (*init)(struct stmmac_priv *priv);
int (*setup_cls_u32)(struct stmmac_priv *priv,
struct tc_cls_u32_offload *cls);
+ int (*setup_cbs)(struct stmmac_priv *priv,
+ struct tc_cbs_qopt_offload *qopt);
};
#define stmmac_tc_init(__priv, __args...) \
stmmac_do_callback(__priv, tc, init, __args)
#define stmmac_tc_setup_cls_u32(__priv, __args...) \
stmmac_do_callback(__priv, tc, setup_cls_u32, __args)
+#define stmmac_tc_setup_cbs(__priv, __args...) \
+ stmmac_do_callback(__priv, tc, setup_cbs, __args)
struct stmmac_regs_off {
u32 ptp_off;
static int stmmac_init_phy(struct net_device *dev)
{
struct stmmac_priv *priv = netdev_priv(dev);
+ u32 tx_cnt = priv->plat->tx_queues_to_use;
struct phy_device *phydev;
char phy_id_fmt[MII_BUS_ID_SIZE + 3];
char bus_id[MII_BUS_ID_SIZE];
phydev->advertising &= ~(SUPPORTED_1000baseT_Half |
SUPPORTED_1000baseT_Full);
+ /*
+ * Half-duplex mode not supported with multiqueue
+ * half-duplex can only works with single queue
+ */
+ if (tx_cnt > 1)
+ phydev->supported &= ~(SUPPORTED_1000baseT_Half |
+ SUPPORTED_100baseT_Half |
+ SUPPORTED_10baseT_Half);
+
/*
* Broken HW is sometimes missing the pull-up resistor on the
* MDIO line, which results in reads to non-existent devices returning
stmmac_dma_rx_mode(priv, priv->ioaddr, rxmode, chan,
rxfifosz, qmode);
+ stmmac_set_dma_bfsize(priv, priv->ioaddr, priv->dma_buf_sz,
+ chan);
}
for (chan = 0; chan < tx_channels_count; chan++) {
switch (f->command) {
case TC_BLOCK_BIND:
return tcf_block_cb_register(f->block, stmmac_setup_tc_block_cb,
- priv, priv);
+ priv, priv, f->extack);
case TC_BLOCK_UNBIND:
tcf_block_cb_unregister(f->block, stmmac_setup_tc_block_cb, priv);
return 0;
switch (type) {
case TC_SETUP_BLOCK:
return stmmac_setup_tc_block(priv, type_data);
+ case TC_SETUP_QDISC_CBS:
+ return stmmac_tc_setup_cbs(priv, priv, type_data);
default:
return -EOPNOTSUPP;
}
return 0;
}
+static int tc_setup_cbs(struct stmmac_priv *priv,
+ struct tc_cbs_qopt_offload *qopt)
+{
+ u32 tx_queues_count = priv->plat->tx_queues_to_use;
+ u32 queue = qopt->queue;
+ u32 ptr, speed_div;
+ u32 mode_to_use;
+ u64 value;
+ int ret;
+
+ /* Queue 0 is not AVB capable */
+ if (queue <= 0 || queue >= tx_queues_count)
+ return -EINVAL;
+ if (priv->speed != SPEED_100 && priv->speed != SPEED_1000)
+ return -EOPNOTSUPP;
+
+ mode_to_use = priv->plat->tx_queues_cfg[queue].mode_to_use;
+ if (mode_to_use == MTL_QUEUE_DCB && qopt->enable) {
+ ret = stmmac_dma_qmode(priv, priv->ioaddr, queue, MTL_QUEUE_AVB);
+ if (ret)
+ return ret;
+
+ priv->plat->tx_queues_cfg[queue].mode_to_use = MTL_QUEUE_AVB;
+ } else if (!qopt->enable) {
+ return stmmac_dma_qmode(priv, priv->ioaddr, queue, MTL_QUEUE_DCB);
+ }
+
+ /* Port Transmit Rate and Speed Divider */
+ ptr = (priv->speed == SPEED_100) ? 4 : 8;
+ speed_div = (priv->speed == SPEED_100) ? 100000 : 1000000;
+
+ /* Final adjustments for HW */
+ value = div_s64(qopt->idleslope * 1024ll * ptr, speed_div);
+ priv->plat->tx_queues_cfg[queue].idle_slope = value & GENMASK(31, 0);
+
+ value = div_s64(-qopt->sendslope * 1024ll * ptr, speed_div);
+ priv->plat->tx_queues_cfg[queue].send_slope = value & GENMASK(31, 0);
+
+ value = qopt->hicredit * 1024ll * 8;
+ priv->plat->tx_queues_cfg[queue].high_credit = value & GENMASK(31, 0);
+
+ value = qopt->locredit * 1024ll * 8;
+ priv->plat->tx_queues_cfg[queue].low_credit = value & GENMASK(31, 0);
+
+ ret = stmmac_config_cbs(priv, priv->hw,
+ priv->plat->tx_queues_cfg[queue].send_slope,
+ priv->plat->tx_queues_cfg[queue].idle_slope,
+ priv->plat->tx_queues_cfg[queue].high_credit,
+ priv->plat->tx_queues_cfg[queue].low_credit,
+ queue);
+ if (ret)
+ return ret;
+
+ dev_info(priv->device, "CBS queue %d: send %d, idle %d, hi %d, lo %d\n",
+ queue, qopt->sendslope, qopt->idleslope,
+ qopt->hicredit, qopt->locredit);
+ return 0;
+}
+
const struct stmmac_tc_ops dwmac510_tc_ops = {
.init = tc_init,
.setup_cls_u32 = tc_setup_cls_u32,
+ .setup_cbs = tc_setup_cbs,
};
}
static u16 vsw_select_queue(struct net_device *dev, struct sk_buff *skb,
- void *accel_priv, select_queue_fallback_t fallback)
+ struct net_device *sb_dev,
+ select_queue_fallback_t fallback)
{
struct vnet_port *port = netdev_priv(dev);
bmsr = err;
if (bmsr & BMSR_LSTATUS) {
- u16 adv, lpa;
-
- err = mii_read(np, np->phy_addr, MII_ADVERTISE);
- if (err < 0)
- goto out;
- adv = err;
-
- err = mii_read(np, np->phy_addr, MII_LPA);
- if (err < 0)
- goto out;
- lpa = err;
-
- err = mii_read(np, np->phy_addr, MII_ESTATUS);
- if (err < 0)
- goto out;
link_up = 1;
current_speed = SPEED_1000;
current_duplex = DUPLEX_FULL;
-
}
lp->active_speed = current_speed;
lp->active_duplex = current_duplex;
#include <linux/sungem_phy.h>
#include "sungem.h"
-/* Stripping FCS is causing problems, disabled for now */
-#undef STRIP_FCS
+#define STRIP_FCS
#define DEFAULT_MSG (NETIF_MSG_DRV | \
NETIF_MSG_PROBE | \
writel(desc_dma & 0xffffffff, gp->regs + RXDMA_DBLOW);
writel(RX_RING_SIZE - 4, gp->regs + RXDMA_KICK);
val = (RXDMA_CFG_BASE | (RX_OFFSET << 10) |
- ((14 / 2) << 13) | RXDMA_CFG_FTHRESH_128);
+ (ETH_HLEN << 13) | RXDMA_CFG_FTHRESH_128);
writel(val, gp->regs + RXDMA_CFG);
if (readl(gp->regs + GREG_BIFCFG) & GREG_BIFCFG_M66EN)
writel(((5 & RXDMA_BLANK_IPKTS) |
struct net_device *dev = gp->dev;
int entry, drops, work_done = 0;
u32 done;
- __sum16 csum;
if (netif_msg_rx_status(gp))
printk(KERN_DEBUG "%s: rx interrupt, done: %d, rx_new: %d\n",
skb = copy_skb;
}
- csum = (__force __sum16)htons((status & RXDCTRL_TCPCSUM) ^ 0xffff);
- skb->csum = csum_unfold(csum);
- skb->ip_summed = CHECKSUM_COMPLETE;
+ if (likely(dev->features & NETIF_F_RXCSUM)) {
+ __sum16 csum;
+
+ csum = (__force __sum16)htons((status & RXDCTRL_TCPCSUM) ^ 0xffff);
+ skb->csum = csum_unfold(csum);
+ skb->ip_summed = CHECKSUM_COMPLETE;
+ }
skb->protocol = eth_type_trans(skb, gp->dev);
napi_gro_receive(&gp->napi, skb);
writel(0, gp->regs + TXDMA_KICK);
val = (RXDMA_CFG_BASE | (RX_OFFSET << 10) |
- ((14 / 2) << 13) | RXDMA_CFG_FTHRESH_128);
+ (ETH_HLEN << 13) | RXDMA_CFG_FTHRESH_128);
writel(val, gp->regs + RXDMA_CFG);
writel(desc_dma >> 32, gp->regs + RXDMA_DBHI);
pci_set_drvdata(pdev, dev);
/* We can do scatter/gather and HW checksum */
- dev->hw_features = NETIF_F_SG | NETIF_F_HW_CSUM;
- dev->features |= dev->hw_features | NETIF_F_RXCSUM;
+ dev->hw_features = NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_RXCSUM;
+ dev->features = dev->hw_features;
if (pci_using_dac)
dev->features |= NETIF_F_HIGHDMA;
}
static u16 vnet_select_queue(struct net_device *dev, struct sk_buff *skb,
- void *accel_priv, select_queue_fallback_t fallback)
+ struct net_device *sb_dev,
+ select_queue_fallback_t fallback)
{
struct vnet *vp = netdev_priv(dev);
struct vnet_port *port = __tx_port_find(vp, skb);
struct rx_map *dm;
struct rxf_fifo *f;
struct rxdb *db;
- struct sk_buff *skb;
int delta;
ENTER;
DBG("db=%p f=%p\n", db, f);
dm = bdx_rxdb_addr_elem(db, rxdd->va_lo);
DBG("dm=%p\n", dm);
- skb = dm->skb;
rxfd = (struct rxf_desc *)(f->m.va + f->m.wptr);
rxfd->info = CPU_CHIP_SWAP32(0x10003); /* INFO=1 BC=3 */
rxfd->va_lo = rxdd->va_lo;
#define RX_DSCP_PRI_MAP7 0x4c /* Rx DSCP Priority to Rx Packet Mapping */
/* Bit definitions for the CPSW2_CONTROL register */
-#define PASS_PRI_TAGGED (1<<24) /* Pass Priority Tagged */
-#define VLAN_LTYPE2_EN (1<<21) /* VLAN LTYPE 2 enable */
-#define VLAN_LTYPE1_EN (1<<20) /* VLAN LTYPE 1 enable */
-#define DSCP_PRI_EN (1<<16) /* DSCP Priority Enable */
-#define TS_320 (1<<14) /* Time Sync Dest Port 320 enable */
-#define TS_319 (1<<13) /* Time Sync Dest Port 319 enable */
-#define TS_132 (1<<12) /* Time Sync Dest IP Addr 132 enable */
-#define TS_131 (1<<11) /* Time Sync Dest IP Addr 131 enable */
-#define TS_130 (1<<10) /* Time Sync Dest IP Addr 130 enable */
-#define TS_129 (1<<9) /* Time Sync Dest IP Addr 129 enable */
-#define TS_TTL_NONZERO (1<<8) /* Time Sync Time To Live Non-zero enable */
-#define TS_ANNEX_F_EN (1<<6) /* Time Sync Annex F enable */
-#define TS_ANNEX_D_EN (1<<4) /* Time Sync Annex D enable */
-#define TS_LTYPE2_EN (1<<3) /* Time Sync LTYPE 2 enable */
-#define TS_LTYPE1_EN (1<<2) /* Time Sync LTYPE 1 enable */
-#define TS_TX_EN (1<<1) /* Time Sync Transmit Enable */
-#define TS_RX_EN (1<<0) /* Time Sync Receive Enable */
+#define PASS_PRI_TAGGED BIT(24) /* Pass Priority Tagged */
+#define VLAN_LTYPE2_EN BIT(21) /* VLAN LTYPE 2 enable */
+#define VLAN_LTYPE1_EN BIT(20) /* VLAN LTYPE 1 enable */
+#define DSCP_PRI_EN BIT(16) /* DSCP Priority Enable */
+#define TS_107 BIT(15) /* Tyme Sync Dest IP Address 107 */
+#define TS_320 BIT(14) /* Time Sync Dest Port 320 enable */
+#define TS_319 BIT(13) /* Time Sync Dest Port 319 enable */
+#define TS_132 BIT(12) /* Time Sync Dest IP Addr 132 enable */
+#define TS_131 BIT(11) /* Time Sync Dest IP Addr 131 enable */
+#define TS_130 BIT(10) /* Time Sync Dest IP Addr 130 enable */
+#define TS_129 BIT(9) /* Time Sync Dest IP Addr 129 enable */
+#define TS_TTL_NONZERO BIT(8) /* Time Sync Time To Live Non-zero enable */
+#define TS_ANNEX_F_EN BIT(6) /* Time Sync Annex F enable */
+#define TS_ANNEX_D_EN BIT(4) /* Time Sync Annex D enable */
+#define TS_LTYPE2_EN BIT(3) /* Time Sync LTYPE 2 enable */
+#define TS_LTYPE1_EN BIT(2) /* Time Sync LTYPE 1 enable */
+#define TS_TX_EN BIT(1) /* Time Sync Transmit Enable */
+#define TS_RX_EN BIT(0) /* Time Sync Receive Enable */
#define CTRL_V2_TS_BITS \
(TS_320 | TS_319 | TS_132 | TS_131 | TS_130 | TS_129 |\
#define CTRL_V3_TS_BITS \
- (TS_320 | TS_319 | TS_132 | TS_131 | TS_130 | TS_129 |\
+ (TS_107 | TS_320 | TS_319 | TS_132 | TS_131 | TS_130 | TS_129 |\
TS_TTL_NONZERO | TS_ANNEX_F_EN | TS_ANNEX_D_EN |\
TS_LTYPE1_EN)
dev_info(cpsw->dev, "cpsw: Detected MACID = %pM\n",
priv_sl2->mac_addr);
} else {
- random_ether_addr(priv_sl2->mac_addr);
+ eth_random_addr(priv_sl2->mac_addr);
dev_info(cpsw->dev, "cpsw: Random MACID = %pM\n",
priv_sl2->mac_addr);
}
dev_consume_skb_any(skb);
dev_dbg(cpts->dev, "match tx timestamp mtype %u seqid %04x\n",
mtype, seqid);
- } else if (time_after(jiffies, skb_cb->tmo)) {
+ break;
+ }
+
+ if (time_after(jiffies, skb_cb->tmo)) {
/* timeout any expired skbs over 1s */
dev_dbg(cpts->dev,
"expiring tx timestamp mtype %u seqid %04x\n",
* devices (e.g. cpsw switches) use plain old memory. Descriptor pools
* abstract out these details
*/
-int cpdma_desc_pool_create(struct cpdma_ctlr *ctlr)
+static int cpdma_desc_pool_create(struct cpdma_ctlr *ctlr)
{
struct cpdma_params *cpdma_params = &ctlr->params;
struct cpdma_desc_pool *pool;
return -EOPNOTSUPP;
}
+static int match_first_device(struct device *dev, void *data)
+{
+ if (dev->parent && dev->parent->of_node)
+ return of_device_is_compatible(dev->parent->of_node,
+ "ti,davinci_mdio");
+
+ return !strncmp(dev_name(dev), "davinci_mdio", 12);
+}
+
/**
* emac_dev_open - EMAC device open
* @ndev: The DaVinci EMAC network adapter
/* use the first phy on the bus if pdata did not give us a phy id */
if (!phydev && !priv->phy_id) {
- phy = bus_find_device_by_name(&mdio_bus_type, NULL,
- "davinci_mdio");
+ /* NOTE: we can't use bus_find_device_by_name() here because
+ * the device name is not guaranteed to be 'davinci_mdio'. On
+ * some systems it can be 'davinci_mdio.0' so we need to use
+ * strncmp() against the first part of the string to correctly
+ * match it.
+ */
+ phy = bus_find_device(&mdio_bus_type, NULL, NULL,
+ match_first_device);
if (phy) {
priv->phy_id = dev_name(phy);
if (!priv->phy_id || !*priv->phy_id)
return err;
}
-static u16 netcp_select_queue(struct net_device *dev, struct sk_buff *skb,
- void *accel_priv,
- select_queue_fallback_t fallback)
-{
- return 0;
-}
-
static int netcp_setup_tc(struct net_device *dev, enum tc_setup_type type,
void *type_data)
{
.ndo_vlan_rx_add_vid = netcp_rx_add_vid,
.ndo_vlan_rx_kill_vid = netcp_rx_kill_vid,
.ndo_tx_timeout = netcp_ndo_tx_timeout,
- .ndo_select_queue = netcp_select_queue,
+ .ndo_select_queue = dev_pick_tx_zero,
.ndo_setup_tc = netcp_setup_tc,
};
if (is_valid_ether_addr(efuse_mac_addr))
ether_addr_copy(ndev->dev_addr, efuse_mac_addr);
else
- random_ether_addr(ndev->dev_addr);
+ eth_random_addr(ndev->dev_addr);
devm_iounmap(dev, efuse);
devm_release_mem_region(dev, res.start, size);
if (mac_addr)
ether_addr_copy(ndev->dev_addr, mac_addr);
else
- random_ether_addr(ndev->dev_addr);
+ eth_random_addr(ndev->dev_addr);
}
ret = of_property_read_string(node_interface, "rx-channel",
#define XEL_TSR_XMIT_IE_MASK 0x00000008 /* Tx interrupt enable bit */
#define XEL_TSR_XMIT_ACTIVE_MASK 0x80000000 /* Buffer is active, SW bit
* only. This is not documented
- * in the HW spec */
+ * in the HW spec
+ */
/* Define for programming the MAC address into the EmacLite */
#define XEL_TSR_PROG_MAC_ADDR (XEL_TSR_XMIT_BUSY_MASK | XEL_TSR_PROGRAM_MASK)
-#define TX_TIMEOUT (60*HZ) /* Tx timeout is 60 seconds. */
+#define TX_TIMEOUT (60 * HZ) /* Tx timeout is 60 seconds. */
#define ALIGNMENT 4
/* BUFFER_ALIGN(adr) calculates the number of bytes to the next alignment. */
-#define BUFFER_ALIGN(adr) ((ALIGNMENT - ((u32) adr)) % ALIGNMENT)
+#define BUFFER_ALIGN(adr) ((ALIGNMENT - ((u32)adr)) % ALIGNMENT)
#ifdef __BIG_ENDIAN
#define xemaclite_readl ioread32be
/* Set up to output the remaining data */
align_buffer = 0;
- to_u8_ptr = (u8 *) &align_buffer;
- from_u8_ptr = (u8 *) from_u16_ptr;
+ to_u8_ptr = (u8 *)&align_buffer;
+ from_u8_ptr = (u8 *)from_u16_ptr;
/* Output the remaining data */
for (; length > 0; length--)
u32 align_buffer;
from_u32_ptr = src_ptr;
- to_u16_ptr = (u16 *) dest_ptr;
+ to_u16_ptr = (u16 *)dest_ptr;
for (; length > 3; length -= 4) {
/* Copy each word into the temporary buffer */
u8 *to_u8_ptr, *from_u8_ptr;
/* Set up to read the remaining data */
- to_u8_ptr = (u8 *) to_u16_ptr;
+ to_u8_ptr = (u8 *)to_u16_ptr;
align_buffer = *from_u32_ptr++;
- from_u8_ptr = (u8 *) &align_buffer;
+ from_u8_ptr = (u8 *)&align_buffer;
/* Read the remaining data */
for (; length > 0; length--)
drvdata->next_tx_buf_to_use ^= XEL_BUFFER_OFFSET;
} else if (drvdata->tx_ping_pong != 0) {
/* If the expected buffer is full, try the other buffer,
- * if it is configured in HW */
+ * if it is configured in HW
+ */
addr = (void __iomem __force *)((u32 __force)addr ^
XEL_BUFFER_OFFSET);
return -1; /* Buffer was full, return failure */
/* Write the frame to the buffer */
- xemaclite_aligned_write(data, (u32 __force *) addr, byte_count);
+ xemaclite_aligned_write(data, (u32 __force *)addr, byte_count);
xemaclite_writel((byte_count & XEL_TPLR_LENGTH_MASK),
addr + XEL_TPLR_OFFSET);
/* Update the Tx Status Register to indicate that there is a
* frame to send. Set the XEL_TSR_XMIT_ACTIVE_MASK flag which
* is used by the interrupt handler to check whether a frame
- * has been transmitted */
+ * has been transmitted
+ */
reg_data = xemaclite_readl(addr + XEL_TSR_OFFSET);
reg_data |= (XEL_TSR_XMIT_BUSY_MASK | XEL_TSR_XMIT_ACTIVE_MASK);
xemaclite_writel(reg_data, addr + XEL_TSR_OFFSET);
* xemaclite_recv_data - Receive a frame
* @drvdata: Pointer to the Emaclite device private data
* @data: Address where the data is to be received
+ * @maxlen: Maximum supported ethernet packet length
*
* This function is intended to be called from the interrupt context or
* with a wrapper which waits for the receive frame to be available.
/* The instance is out of sync, try other buffer if other
* buffer is configured, return 0 otherwise. If the instance is
* out of sync, do not update the 'next_rx_buf_to_use' since it
- * will correct on subsequent calls */
+ * will correct on subsequent calls
+ */
if (drvdata->rx_ping_pong != 0)
addr = (void __iomem __force *)((u32 __force)addr ^
XEL_BUFFER_OFFSET);
return 0; /* No data was available */
}
- /* Get the protocol type of the ethernet frame that arrived */
+ /* Get the protocol type of the ethernet frame that arrived
+ */
proto_type = ((ntohl(xemaclite_readl(addr + XEL_HEADER_OFFSET +
XEL_RXBUFF_OFFSET)) >> XEL_HEADER_SHIFT) &
XEL_RPLR_LENGTH_MASK);
/* Check if received ethernet frame is a raw ethernet frame
- * or an IP packet or an ARP packet */
+ * or an IP packet or an ARP packet
+ */
if (proto_type > ETH_DATA_LEN) {
if (proto_type == ETH_P_IP) {
length = XEL_ARP_PACKET_SIZE + ETH_HLEN + ETH_FCS_LEN;
else
/* Field contains type other than IP or ARP, use max
- * frame size and let user parse it */
+ * frame size and let user parse it
+ */
length = ETH_FRAME_LEN + ETH_FCS_LEN;
} else
/* Use the length in the frame, plus the header and trailer */
length = maxlen;
/* Read from the EmacLite device */
- xemaclite_aligned_read((u32 __force *) (addr + XEL_RXBUFF_OFFSET),
+ xemaclite_aligned_read((u32 __force *)(addr + XEL_RXBUFF_OFFSET),
data, length);
/* Acknowledge the frame */
/* Determine the expected Tx buffer address */
addr = drvdata->base_addr + drvdata->next_tx_buf_to_use;
- xemaclite_aligned_write(address_ptr, (u32 __force *) addr, ETH_ALEN);
+ xemaclite_aligned_write(address_ptr, (u32 __force *)addr, ETH_ALEN);
xemaclite_writel(ETH_ALEN, addr + XEL_TPLR_OFFSET);
/**
* xemaclite_set_mac_address - Set the MAC address for this device
* @dev: Pointer to the network device instance
- * @addr: Void pointer to the sockaddr structure
+ * @address: Void pointer to the sockaddr structure
*
* This function copies the HW address from the sockaddr strucutre to the
* net_device structure and updates the address in HW.
struct net_local *lp = netdev_priv(dev);
dev->stats.tx_packets++;
- if (lp->deferred_skb) {
- if (xemaclite_send_data(lp,
- (u8 *) lp->deferred_skb->data,
- lp->deferred_skb->len) != 0)
- return;
- else {
- dev->stats.tx_bytes += lp->deferred_skb->len;
- dev_kfree_skb_irq(lp->deferred_skb);
- lp->deferred_skb = NULL;
- netif_trans_update(dev); /* prevent tx timeout */
- netif_wake_queue(dev);
- }
- }
+
+ if (!lp->deferred_skb)
+ return;
+
+ if (xemaclite_send_data(lp, (u8 *)lp->deferred_skb->data,
+ lp->deferred_skb->len))
+ return;
+
+ dev->stats.tx_bytes += lp->deferred_skb->len;
+ dev_kfree_skb_irq(lp->deferred_skb);
+ lp->deferred_skb = NULL;
+ netif_trans_update(dev); /* prevent tx timeout */
+ netif_wake_queue(dev);
}
/**
return;
}
- /*
- * A new skb should have the data halfword aligned, but this code is
+ /* A new skb should have the data halfword aligned, but this code is
* here just in case that isn't true. Calculate how many
* bytes we should reserve to get the data to start on a word
- * boundary */
+ * boundary
+ */
align = BUFFER_ALIGN(skb->data);
if (align)
skb_reserve(skb, align);
skb_reserve(skb, 2);
- len = xemaclite_recv_data(lp, (u8 *) skb->data, len);
+ len = xemaclite_recv_data(lp, (u8 *)skb->data, len);
if (!len) {
dev->stats.rx_errors++;
* @dev_id: Void pointer to the network device instance used as callback
* reference
*
+ * Return: IRQ_HANDLED
+ *
* This function handles the Tx and Rx interrupts of the EmacLite device.
*/
static irqreturn_t xemaclite_interrupt(int irq, void *dev_id)
unsigned long end = jiffies + 2;
/* wait for the MDIO interface to not be busy or timeout
- after some time.
- */
+ * after some time.
+ */
while (xemaclite_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET) &
XEL_MDIOCTRL_MDIOSTS_MASK) {
if (time_before_eq(end, jiffies)) {
rc = xemaclite_readl(lp->base_addr + XEL_MDIORD_OFFSET);
dev_dbg(&lp->ndev->dev,
- "xemaclite_mdio_read(phy_id=%i, reg=%x) == %x\n",
+ "%s(phy_id=%i, reg=%x) == %x\n", __func__,
phy_id, reg, rc);
return rc;
*
* This function waits till the device is ready to accept a new MDIO
* request and then writes the val to the MDIO Write Data register.
+ *
+ * Return: 0 upon success or a negative error upon failure
*/
static int xemaclite_mdio_write(struct mii_bus *bus, int phy_id, int reg,
u16 val)
u32 ctrl_reg;
dev_dbg(&lp->ndev->dev,
- "xemaclite_mdio_write(phy_id=%i, reg=%x, val=%x)\n",
+ "%s(phy_id=%i, reg=%x, val=%x)\n", __func__,
phy_id, reg, val);
if (xemaclite_mdio_wait(lp))
/**
* xemaclite_mdio_setup - Register mii_bus for the Emaclite device
* @lp: Pointer to the Emaclite device private data
- * @ofdev: Pointer to OF device structure
+ * @dev: Pointer to OF device structure
*
* This function enables MDIO bus in the Emaclite device and registers a
* mii_bus.
* This function sets the MAC address, requests an IRQ and enables interrupts
* for the Emaclite device and starts the Tx queue.
* It also connects to the phy device, if MDIO is included in Emaclite device.
+ *
+ * Return: 0 on success. -ENODEV, if PHY cannot be connected.
+ * Non-zero error value on failure.
*/
static int xemaclite_open(struct net_device *dev)
{
* This function stops the Tx queue, disables interrupts and frees the IRQ for
* the Emaclite device.
* It also disconnects the phy device associated with the Emaclite device.
+ *
+ * Return: 0, always.
*/
static int xemaclite_close(struct net_device *dev)
{
new_skb = orig_skb;
spin_lock_irqsave(&lp->reset_lock, flags);
- if (xemaclite_send_data(lp, (u8 *) new_skb->data, len) != 0) {
+ if (xemaclite_send_data(lp, (u8 *)new_skb->data, len) != 0) {
/* If the Emaclite Tx buffer is busy, stop the Tx queue and
* defer the skb for transmission during the ISR, after the
- * current transmission is complete */
+ * current transmission is complete
+ */
netif_stop_queue(dev);
lp->deferred_skb = new_skb;
/* Take the time stamp now, since we can't do this in an ISR. */
{
u32 *p = (u32 *)of_get_property(ofdev->dev.of_node, s, NULL);
- if (p) {
- return (bool)*p;
- } else {
- dev_warn(&ofdev->dev, "Parameter %s not found,"
- "defaulting to false\n", s);
+ if (!p) {
+ dev_warn(&ofdev->dev, "Parameter %s not found, defaulting to false\n", s);
return false;
}
+
+ return (bool)*p;
}
static const struct net_device_ops xemaclite_netdev_ops;
/**
* xemaclite_of_probe - Probe method for the Emaclite device.
* @ofdev: Pointer to OF device structure
- * @match: Pointer to the structure used for matching a device
*
* This function probes for the Emaclite device in the device tree.
* It initializes the driver data structure and the hardware, sets the MAC
while ((unshare_watch_bitmask || hw->txrx_stop_req_bit) &&
(wait_time < 3000)) {
- for (epidx = 0; epidx < hw->max_epid; epidx++) {
- if (epidx == hw->my_epid)
+ for (epidx = 0; epidx < max_epid; epidx++) {
+ if (epidx == my_epid)
continue;
is_shared = fjes_hw_epid_is_shared(hw->hw_info.share,
}
if (hw->hw_info.buffer_unshare_reserve_bit) {
- for (epidx = 0; epidx < hw->max_epid; epidx++) {
- if (epidx == hw->my_epid)
+ for (epidx = 0; epidx < max_epid; epidx++) {
+ if (epidx == my_epid)
continue;
if (test_bit(epidx,
}
/* Update tunnel dst according to Geneve options. */
ip_tunnel_info_opts_set(&tun_dst->u.tun_info,
- gnvh->options, gnvh->opt_len * 4);
+ gnvh->options, gnvh->opt_len * 4,
+ TUNNEL_GENEVE_OPT);
} else {
/* Drop packets w/ critical options,
* since we don't support any...
return sizeof(*gh) + gh->opt_len * 4;
}
-static struct sk_buff **geneve_gro_receive(struct sock *sk,
- struct sk_buff **head,
- struct sk_buff *skb)
+static struct sk_buff *geneve_gro_receive(struct sock *sk,
+ struct list_head *head,
+ struct sk_buff *skb)
{
- struct sk_buff *p, **pp = NULL;
+ struct sk_buff *pp = NULL;
+ struct sk_buff *p;
struct genevehdr *gh, *gh2;
unsigned int hlen, gh_len, off_gnv;
const struct packet_offload *ptype;
goto out;
}
- for (p = *head; p; p = p->next) {
+ list_for_each_entry(p, head, list) {
if (!NAPI_GRO_CB(p)->same_flow)
continue;
out_unlock:
rcu_read_unlock();
out:
- NAPI_GRO_CB(skb)->flush |= flush;
+ skb_gro_flush_final(skb, pp, flush);
return pp;
}
geneveh->proto_type = htons(ETH_P_TEB);
geneveh->rsvd2 = 0;
- ip_tunnel_info_opts_get(geneveh->options, info);
+ if (info->key.tun_flags & TUNNEL_GENEVE_OPT)
+ ip_tunnel_info_opts_get(geneveh->options, info);
}
static int geneve_build_skb(struct dst_entry *dst, struct sk_buff *skb,
static void decode_prio_command(struct sixpack *sp, unsigned char cmd)
{
- unsigned char channel;
int actual;
- channel = cmd & SIXP_CHN_MASK;
if ((cmd & SIXP_PRIO_DATA_MASK) != 0) { /* idle ? */
/* RX and DCD flags can only be set in the same prio command,
static void decode_std_command(struct sixpack *sp, unsigned char cmd)
{
- unsigned char checksum = 0, rest = 0, channel;
+ unsigned char checksum = 0, rest = 0;
short i;
- channel = cmd & SIXP_CHN_MASK;
switch (cmd & SIXP_CMD_MASK) { /* normal command */
case SIXP_SEOF:
if ((sp->rx_count == 0) && (sp->rx_count_cooked == 0)) {
static const char banner[] __initconst = KERN_INFO \
"AX.25: bpqether driver version 004\n";
-static char bcast_addr[6]={0xFF,0xFF,0xFF,0xFF,0xFF,0xFF};
-
-static char bpq_eth_addr[6];
-
static int bpq_rcv(struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *);
static int bpq_device_event(struct notifier_block *, unsigned long, void *);
bpq->ethdev = edev;
bpq->axdev = ndev;
- memcpy(bpq->dest_addr, bcast_addr, sizeof(bpq_eth_addr));
- memcpy(bpq->acpt_addr, bcast_addr, sizeof(bpq_eth_addr));
+ eth_broadcast_addr(bpq->dest_addr);
+ eth_broadcast_addr(bpq->acpt_addr);
err = register_netdevice(ndev);
if (err)
void netvsc_channel_cb(void *context);
int netvsc_poll(struct napi_struct *napi, int budget);
-void rndis_set_subchannel(struct work_struct *w);
+int rndis_set_subchannel(struct net_device *ndev, struct netvsc_device *nvdev);
int rndis_filter_open(struct netvsc_device *nvdev);
int rndis_filter_close(struct netvsc_device *nvdev);
struct netvsc_device *rndis_filter_device_add(struct hv_device *dev,
VM_PKT_DATA_INBAND, 0);
}
+/* Worker to setup sub channels on initial setup
+ * Initial hotplug event occurs in softirq context
+ * and can't wait for channels.
+ */
+static void netvsc_subchan_work(struct work_struct *w)
+{
+ struct netvsc_device *nvdev =
+ container_of(w, struct netvsc_device, subchan_work);
+ struct rndis_device *rdev;
+ int i, ret;
+
+ /* Avoid deadlock with device removal already under RTNL */
+ if (!rtnl_trylock()) {
+ schedule_work(w);
+ return;
+ }
+
+ rdev = nvdev->extension;
+ if (rdev) {
+ ret = rndis_set_subchannel(rdev->ndev, nvdev);
+ if (ret == 0) {
+ netif_device_attach(rdev->ndev);
+ } else {
+ /* fallback to only primary channel */
+ for (i = 1; i < nvdev->num_chn; i++)
+ netif_napi_del(&nvdev->chan_table[i].napi);
+
+ nvdev->max_chn = 1;
+ nvdev->num_chn = 1;
+ }
+ }
+
+ rtnl_unlock();
+}
+
static struct netvsc_device *alloc_net_device(void)
{
struct netvsc_device *net_device;
init_completion(&net_device->channel_init_wait);
init_waitqueue_head(&net_device->subchan_open);
- INIT_WORK(&net_device->subchan_work, rndis_set_subchannel);
+ INIT_WORK(&net_device->subchan_work, netvsc_subchan_work);
return net_device;
}
}
static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
- void *accel_priv,
+ struct net_device *sb_dev,
select_queue_fallback_t fallback)
{
struct net_device_context *ndc = netdev_priv(ndev);
if (vf_ops->ndo_select_queue)
txq = vf_ops->ndo_select_queue(vf_netdev, skb,
- accel_priv, fallback);
+ sb_dev, fallback);
else
- txq = fallback(vf_netdev, skb);
+ txq = fallback(vf_netdev, skb, NULL);
/* Record the queue selected by VF so that it can be
* used for common case where VF has more queues than
if (IS_ERR(nvdev))
return PTR_ERR(nvdev);
- /* Note: enable and attach happen when sub-channels setup */
+ if (nvdev->num_chn > 1) {
+ ret = rndis_set_subchannel(ndev, nvdev);
+
+ /* if unavailable, just proceed with one queue */
+ if (ret) {
+ nvdev->max_chn = 1;
+ nvdev->num_chn = 1;
+ }
+ }
+
+ /* In any case device is now ready */
+ netif_device_attach(ndev);
+ /* Note: enable and attach happen when sub-channels setup */
netif_carrier_off(ndev);
if (netif_running(ndev)) {
memcpy(net->dev_addr, device_info.mac_adr, ETH_ALEN);
+ if (nvdev->num_chn > 1)
+ schedule_work(&nvdev->subchan_work);
+
/* hw_features computed in rndis_netdev_set_hwcaps() */
net->features = net->hw_features |
NETIF_F_HIGHDMA | NETIF_F_SG |
* This breaks overlap of processing the host message for the
* new primary channel with the initialization of sub-channels.
*/
-void rndis_set_subchannel(struct work_struct *w)
+int rndis_set_subchannel(struct net_device *ndev, struct netvsc_device *nvdev)
{
- struct netvsc_device *nvdev
- = container_of(w, struct netvsc_device, subchan_work);
struct nvsp_message *init_packet = &nvdev->channel_init_pkt;
- struct net_device_context *ndev_ctx;
- struct rndis_device *rdev;
- struct net_device *ndev;
- struct hv_device *hv_dev;
+ struct net_device_context *ndev_ctx = netdev_priv(ndev);
+ struct hv_device *hv_dev = ndev_ctx->device_ctx;
+ struct rndis_device *rdev = nvdev->extension;
int i, ret;
- if (!rtnl_trylock()) {
- schedule_work(w);
- return;
- }
-
- rdev = nvdev->extension;
- if (!rdev)
- goto unlock; /* device was removed */
-
- ndev = rdev->ndev;
- ndev_ctx = netdev_priv(ndev);
- hv_dev = ndev_ctx->device_ctx;
+ ASSERT_RTNL();
memset(init_packet, 0, sizeof(struct nvsp_message));
init_packet->hdr.msg_type = NVSP_MSG5_TYPE_SUBCHANNEL;
VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
if (ret) {
netdev_err(ndev, "sub channel allocate send failed: %d\n", ret);
- goto failed;
+ return ret;
}
wait_for_completion(&nvdev->channel_init_wait);
if (init_packet->msg.v5_msg.subchn_comp.status != NVSP_STAT_SUCCESS) {
netdev_err(ndev, "sub channel request failed\n");
- goto failed;
+ return -EIO;
}
nvdev->num_chn = 1 +
for (i = 0; i < VRSS_SEND_TAB_SIZE; i++)
ndev_ctx->tx_table[i] = i % nvdev->num_chn;
- netif_device_attach(ndev);
- rtnl_unlock();
- return;
-
-failed:
- /* fallback to only primary channel */
- for (i = 1; i < nvdev->num_chn; i++)
- netif_napi_del(&nvdev->chan_table[i].napi);
-
- nvdev->max_chn = 1;
- nvdev->num_chn = 1;
-
- netif_device_attach(ndev);
-unlock:
- rtnl_unlock();
+ return 0;
}
static int rndis_netdev_set_hwcaps(struct rndis_device *rndis_device,
netif_napi_add(net, &net_device->chan_table[i].napi,
netvsc_poll, NAPI_POLL_WEIGHT);
- if (net_device->num_chn > 1)
- schedule_work(&net_device->subchan_work);
+ return net_device;
out:
- /* if unavailable, just proceed with one queue */
- if (ret) {
- net_device->max_chn = 1;
- net_device->num_chn = 1;
- }
-
- /* No sub channels, device is ready */
- if (net_device->num_chn == 1)
- netif_device_attach(net);
-
- return net_device;
+ /* setting up multiple channels failed */
+ net_device->max_chn = 1;
+ net_device->num_chn = 1;
err_dev_remv:
rndis_filter_device_remove(dev, net_device);
{
struct ipvl_dev *ipvlan;
struct net_device *mdev = port->dev;
- int err = 0;
+ unsigned int flags;
+ int err;
ASSERT_RTNL();
if (port->mode != nval) {
+ list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
+ flags = ipvlan->dev->flags;
+ if (nval == IPVLAN_MODE_L3 || nval == IPVLAN_MODE_L3S) {
+ err = dev_change_flags(ipvlan->dev,
+ flags | IFF_NOARP);
+ } else {
+ err = dev_change_flags(ipvlan->dev,
+ flags & ~IFF_NOARP);
+ }
+ if (unlikely(err))
+ goto fail;
+ }
if (nval == IPVLAN_MODE_L3S) {
/* New mode is L3S */
err = ipvlan_register_nf_hook(read_pnet(&port->pnet));
mdev->l3mdev_ops = &ipvl_l3mdev_ops;
mdev->priv_flags |= IFF_L3MDEV_MASTER;
} else
- return err;
+ goto fail;
} else if (port->mode == IPVLAN_MODE_L3S) {
/* Old mode was L3S */
mdev->priv_flags &= ~IFF_L3MDEV_MASTER;
ipvlan_unregister_nf_hook(read_pnet(&port->pnet));
mdev->l3mdev_ops = NULL;
}
- list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
- if (nval == IPVLAN_MODE_L3 || nval == IPVLAN_MODE_L3S)
- ipvlan->dev->flags |= IFF_NOARP;
- else
- ipvlan->dev->flags &= ~IFF_NOARP;
- }
port->mode = nval;
}
+ return 0;
+
+fail:
+ /* Undo the flags changes that have been done so far. */
+ list_for_each_entry_continue_reverse(ipvlan, &port->ipvlans, pnode) {
+ flags = ipvlan->dev->flags;
+ if (port->mode == IPVLAN_MODE_L3 ||
+ port->mode == IPVLAN_MODE_L3S)
+ dev_change_flags(ipvlan->dev, flags | IFF_NOARP);
+ else
+ dev_change_flags(ipvlan->dev, flags & ~IFF_NOARP);
+ }
+
return err;
}
ipvlan->phy_dev = phy_dev;
ipvlan->dev = dev;
ipvlan->sfeatures = IPVLAN_FEATURES;
- ipvlan_adjust_mtu(ipvlan, phy_dev);
+ if (!tb[IFLA_MTU])
+ ipvlan_adjust_mtu(ipvlan, phy_dev);
INIT_LIST_HEAD(&ipvlan->addrs);
spin_lock_init(&ipvlan->addrs_lock);
{
ether_setup(dev);
+ dev->max_mtu = ETH_MAX_MTU;
dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING);
dev->priv_flags |= IFF_UNICAST_FLT | IFF_NO_QUEUE;
dev->netdev_ops = &ipvlan_netdev_ops;
const struct macvlan_dev *vlan = netdev_priv(dev);
const struct macvlan_port *port = vlan->port;
const struct macvlan_dev *dest;
- void *accel_priv = NULL;
if (vlan->mode == MACVLAN_MODE_BRIDGE) {
const struct ethhdr *eth = (void *)skb->data;
return NET_XMIT_SUCCESS;
}
}
-
- /* For packets that are non-multicast and not bridged we will pass
- * the necessary information so that the lowerdev can distinguish
- * the source of the packets via the accel_priv value.
- */
- accel_priv = vlan->accel_priv;
xmit_world:
skb->dev = vlan->lowerdev;
- return dev_queue_xmit_accel(skb, accel_priv);
+ return dev_queue_xmit_accel(skb,
+ netdev_get_sb_channel(dev) ? dev : NULL);
}
static inline netdev_tx_t macvlan_netpoll_send_skb(struct macvlan_dev *vlan, struct sk_buff *skb)
switch (event) {
case NETDEV_UP:
+ case NETDEV_DOWN:
case NETDEV_CHANGE:
list_for_each_entry(vlan, &port->vlans, list)
netif_stacked_transfer_operstate(vlan->lowerdev,
}
static u16 net_failover_select_queue(struct net_device *dev,
- struct sk_buff *skb, void *accel_priv,
+ struct sk_buff *skb,
+ struct net_device *sb_dev,
select_queue_fallback_t fallback)
{
struct net_failover_info *nfo_info = netdev_priv(dev);
if (ops->ndo_select_queue)
txq = ops->ndo_select_queue(primary_dev, skb,
- accel_priv, fallback);
+ sb_dev, fallback);
else
- txq = fallback(primary_dev, skb);
+ txq = fallback(primary_dev, skb, NULL);
qdisc_skb_cb(skb)->slave_dev_queue_mapping = skb->queue_mapping;
netif_addr_lock_bh(failover_dev);
dev_uc_sync_multiple(slave_dev, failover_dev);
- dev_uc_sync_multiple(slave_dev, failover_dev);
+ dev_mc_sync_multiple(slave_dev, failover_dev);
netif_addr_unlock_bh(failover_dev);
err = vlan_vids_add_by_dev(slave_dev, failover_dev);
ifneq ($(CONFIG_NET_DEVLINK),)
netdevsim-objs += devlink.o fib.o
endif
+
+ifneq ($(CONFIG_XFRM_OFFLOAD),)
+netdevsim-objs += ipsec.o
+endif
static bool nsim_xdp_offload_active(struct netdevsim *ns)
{
- return ns->xdp_prog_mode == XDP_ATTACHED_HW;
+ return ns->xdp_hw.prog;
}
static void nsim_prog_set_loaded(struct bpf_prog *prog, bool loaded)
return nsim_bpf_offload(ns, bpf->prog, nsim_xdp_offload_active(ns));
}
-static int nsim_xdp_set_prog(struct netdevsim *ns, struct netdev_bpf *bpf)
+static int
+nsim_xdp_set_prog(struct netdevsim *ns, struct netdev_bpf *bpf,
+ struct xdp_attachment_info *xdp)
{
int err;
- if (ns->xdp_prog && (bpf->flags ^ ns->xdp_flags) & XDP_FLAGS_MODES) {
- NSIM_EA(bpf->extack, "program loaded with different flags");
+ if (!xdp_attachment_flags_ok(xdp, bpf))
return -EBUSY;
- }
if (bpf->command == XDP_SETUP_PROG && !ns->bpf_xdpdrv_accept) {
NSIM_EA(bpf->extack, "driver XDP disabled in DebugFS");
return err;
}
- if (ns->xdp_prog)
- bpf_prog_put(ns->xdp_prog);
-
- ns->xdp_prog = bpf->prog;
- ns->xdp_flags = bpf->flags;
-
- if (!bpf->prog)
- ns->xdp_prog_mode = XDP_ATTACHED_NONE;
- else if (bpf->command == XDP_SETUP_PROG)
- ns->xdp_prog_mode = XDP_ATTACHED_DRV;
- else
- ns->xdp_prog_mode = XDP_ATTACHED_HW;
+ xdp_attachment_setup(xdp, bpf);
return 0;
}
NSIM_EA(bpf->extack, "MTU too large w/ XDP enabled");
return -EINVAL;
}
- if (nsim_xdp_offload_active(ns)) {
- NSIM_EA(bpf->extack, "xdp offload active, can't load drv prog");
- return -EBUSY;
- }
return 0;
}
nsim_bpf_destroy_prog(bpf->offload.prog);
return 0;
case XDP_QUERY_PROG:
- bpf->prog_attached = ns->xdp_prog_mode;
- bpf->prog_id = ns->xdp_prog ? ns->xdp_prog->aux->id : 0;
- bpf->prog_flags = ns->xdp_prog ? ns->xdp_flags : 0;
- return 0;
+ return xdp_attachment_query(&ns->xdp, bpf);
+ case XDP_QUERY_PROG_HW:
+ return xdp_attachment_query(&ns->xdp_hw, bpf);
case XDP_SETUP_PROG:
err = nsim_setup_prog_checks(ns, bpf);
if (err)
return err;
- return nsim_xdp_set_prog(ns, bpf);
+ return nsim_xdp_set_prog(ns, bpf, &ns->xdp);
case XDP_SETUP_PROG_HW:
err = nsim_setup_prog_hw_checks(ns, bpf);
if (err)
return err;
- return nsim_xdp_set_prog(ns, bpf);
+ return nsim_xdp_set_prog(ns, bpf, &ns->xdp_hw);
case BPF_OFFLOAD_MAP_ALLOC:
if (!ns->bpf_map_accept)
return -EOPNOTSUPP;
{
WARN_ON(!list_empty(&ns->bpf_bound_progs));
WARN_ON(!list_empty(&ns->bpf_bound_maps));
- WARN_ON(ns->xdp_prog);
+ WARN_ON(ns->xdp.prog);
+ WARN_ON(ns->xdp_hw.prog);
WARN_ON(ns->bpf_offloaded);
}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2018 Oracle and/or its affiliates. All rights reserved. */
+
+#include <crypto/aead.h>
+#include <linux/debugfs.h>
+#include <net/xfrm.h>
+
+#include "netdevsim.h"
+
+#define NSIM_IPSEC_AUTH_BITS 128
+
+static ssize_t nsim_dbg_netdev_ops_read(struct file *filp,
+ char __user *buffer,
+ size_t count, loff_t *ppos)
+{
+ struct netdevsim *ns = filp->private_data;
+ struct nsim_ipsec *ipsec = &ns->ipsec;
+ size_t bufsize;
+ char *buf, *p;
+ int len;
+ int i;
+
+ /* the buffer needed is
+ * (num SAs * 3 lines each * ~60 bytes per line) + one more line
+ */
+ bufsize = (ipsec->count * 4 * 60) + 60;
+ buf = kzalloc(bufsize, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
+ p = buf;
+ p += snprintf(p, bufsize - (p - buf),
+ "SA count=%u tx=%u\n",
+ ipsec->count, ipsec->tx);
+
+ for (i = 0; i < NSIM_IPSEC_MAX_SA_COUNT; i++) {
+ struct nsim_sa *sap = &ipsec->sa[i];
+
+ if (!sap->used)
+ continue;
+
+ p += snprintf(p, bufsize - (p - buf),
+ "sa[%i] %cx ipaddr=0x%08x %08x %08x %08x\n",
+ i, (sap->rx ? 'r' : 't'), sap->ipaddr[0],
+ sap->ipaddr[1], sap->ipaddr[2], sap->ipaddr[3]);
+ p += snprintf(p, bufsize - (p - buf),
+ "sa[%i] spi=0x%08x proto=0x%x salt=0x%08x crypt=%d\n",
+ i, be32_to_cpu(sap->xs->id.spi),
+ sap->xs->id.proto, sap->salt, sap->crypt);
+ p += snprintf(p, bufsize - (p - buf),
+ "sa[%i] key=0x%08x %08x %08x %08x\n",
+ i, sap->key[0], sap->key[1],
+ sap->key[2], sap->key[3]);
+ }
+
+ len = simple_read_from_buffer(buffer, count, ppos, buf, p - buf);
+
+ kfree(buf);
+ return len;
+}
+
+static const struct file_operations ipsec_dbg_fops = {
+ .owner = THIS_MODULE,
+ .open = simple_open,
+ .read = nsim_dbg_netdev_ops_read,
+};
+
+static int nsim_ipsec_find_empty_idx(struct nsim_ipsec *ipsec)
+{
+ u32 i;
+
+ if (ipsec->count == NSIM_IPSEC_MAX_SA_COUNT)
+ return -ENOSPC;
+
+ /* search sa table */
+ for (i = 0; i < NSIM_IPSEC_MAX_SA_COUNT; i++) {
+ if (!ipsec->sa[i].used)
+ return i;
+ }
+
+ return -ENOSPC;
+}
+
+static int nsim_ipsec_parse_proto_keys(struct xfrm_state *xs,
+ u32 *mykey, u32 *mysalt)
+{
+ const char aes_gcm_name[] = "rfc4106(gcm(aes))";
+ struct net_device *dev = xs->xso.dev;
+ unsigned char *key_data;
+ char *alg_name = NULL;
+ int key_len;
+
+ if (!xs->aead) {
+ netdev_err(dev, "Unsupported IPsec algorithm\n");
+ return -EINVAL;
+ }
+
+ if (xs->aead->alg_icv_len != NSIM_IPSEC_AUTH_BITS) {
+ netdev_err(dev, "IPsec offload requires %d bit authentication\n",
+ NSIM_IPSEC_AUTH_BITS);
+ return -EINVAL;
+ }
+
+ key_data = &xs->aead->alg_key[0];
+ key_len = xs->aead->alg_key_len;
+ alg_name = xs->aead->alg_name;
+
+ if (strcmp(alg_name, aes_gcm_name)) {
+ netdev_err(dev, "Unsupported IPsec algorithm - please use %s\n",
+ aes_gcm_name);
+ return -EINVAL;
+ }
+
+ /* 160 accounts for 16 byte key and 4 byte salt */
+ if (key_len > NSIM_IPSEC_AUTH_BITS) {
+ *mysalt = ((u32 *)key_data)[4];
+ } else if (key_len == NSIM_IPSEC_AUTH_BITS) {
+ *mysalt = 0;
+ } else {
+ netdev_err(dev, "IPsec hw offload only supports 128 bit keys with optional 32 bit salt\n");
+ return -EINVAL;
+ }
+ memcpy(mykey, key_data, 16);
+
+ return 0;
+}
+
+static int nsim_ipsec_add_sa(struct xfrm_state *xs)
+{
+ struct nsim_ipsec *ipsec;
+ struct net_device *dev;
+ struct netdevsim *ns;
+ struct nsim_sa sa;
+ u16 sa_idx;
+ int ret;
+
+ dev = xs->xso.dev;
+ ns = netdev_priv(dev);
+ ipsec = &ns->ipsec;
+
+ if (xs->id.proto != IPPROTO_ESP && xs->id.proto != IPPROTO_AH) {
+ netdev_err(dev, "Unsupported protocol 0x%04x for ipsec offload\n",
+ xs->id.proto);
+ return -EINVAL;
+ }
+
+ if (xs->calg) {
+ netdev_err(dev, "Compression offload not supported\n");
+ return -EINVAL;
+ }
+
+ /* find the first unused index */
+ ret = nsim_ipsec_find_empty_idx(ipsec);
+ if (ret < 0) {
+ netdev_err(dev, "No space for SA in Rx table!\n");
+ return ret;
+ }
+ sa_idx = (u16)ret;
+
+ memset(&sa, 0, sizeof(sa));
+ sa.used = true;
+ sa.xs = xs;
+
+ if (sa.xs->id.proto & IPPROTO_ESP)
+ sa.crypt = xs->ealg || xs->aead;
+
+ /* get the key and salt */
+ ret = nsim_ipsec_parse_proto_keys(xs, sa.key, &sa.salt);
+ if (ret) {
+ netdev_err(dev, "Failed to get key data for SA table\n");
+ return ret;
+ }
+
+ if (xs->xso.flags & XFRM_OFFLOAD_INBOUND) {
+ sa.rx = true;
+
+ if (xs->props.family == AF_INET6)
+ memcpy(sa.ipaddr, &xs->id.daddr.a6, 16);
+ else
+ memcpy(&sa.ipaddr[3], &xs->id.daddr.a4, 4);
+ }
+
+ /* the preparations worked, so save the info */
+ memcpy(&ipsec->sa[sa_idx], &sa, sizeof(sa));
+
+ /* the XFRM stack doesn't like offload_handle == 0,
+ * so add a bitflag in case our array index is 0
+ */
+ xs->xso.offload_handle = sa_idx | NSIM_IPSEC_VALID;
+ ipsec->count++;
+
+ return 0;
+}
+
+static void nsim_ipsec_del_sa(struct xfrm_state *xs)
+{
+ struct netdevsim *ns = netdev_priv(xs->xso.dev);
+ struct nsim_ipsec *ipsec = &ns->ipsec;
+ u16 sa_idx;
+
+ sa_idx = xs->xso.offload_handle & ~NSIM_IPSEC_VALID;
+ if (!ipsec->sa[sa_idx].used) {
+ netdev_err(ns->netdev, "Invalid SA for delete sa_idx=%d\n",
+ sa_idx);
+ return;
+ }
+
+ memset(&ipsec->sa[sa_idx], 0, sizeof(struct nsim_sa));
+ ipsec->count--;
+}
+
+static bool nsim_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs)
+{
+ struct netdevsim *ns = netdev_priv(xs->xso.dev);
+ struct nsim_ipsec *ipsec = &ns->ipsec;
+
+ ipsec->ok++;
+
+ return true;
+}
+
+static const struct xfrmdev_ops nsim_xfrmdev_ops = {
+ .xdo_dev_state_add = nsim_ipsec_add_sa,
+ .xdo_dev_state_delete = nsim_ipsec_del_sa,
+ .xdo_dev_offload_ok = nsim_ipsec_offload_ok,
+};
+
+bool nsim_ipsec_tx(struct netdevsim *ns, struct sk_buff *skb)
+{
+ struct nsim_ipsec *ipsec = &ns->ipsec;
+ struct xfrm_state *xs;
+ struct nsim_sa *tsa;
+ u32 sa_idx;
+
+ /* do we even need to check this packet? */
+ if (!skb->sp)
+ return true;
+
+ if (unlikely(!skb->sp->len)) {
+ netdev_err(ns->netdev, "no xfrm state len = %d\n",
+ skb->sp->len);
+ return false;
+ }
+
+ xs = xfrm_input_state(skb);
+ if (unlikely(!xs)) {
+ netdev_err(ns->netdev, "no xfrm_input_state() xs = %p\n", xs);
+ return false;
+ }
+
+ sa_idx = xs->xso.offload_handle & ~NSIM_IPSEC_VALID;
+ if (unlikely(sa_idx >= NSIM_IPSEC_MAX_SA_COUNT)) {
+ netdev_err(ns->netdev, "bad sa_idx=%d max=%d\n",
+ sa_idx, NSIM_IPSEC_MAX_SA_COUNT);
+ return false;
+ }
+
+ tsa = &ipsec->sa[sa_idx];
+ if (unlikely(!tsa->used)) {
+ netdev_err(ns->netdev, "unused sa_idx=%d\n", sa_idx);
+ return false;
+ }
+
+ if (xs->id.proto != IPPROTO_ESP && xs->id.proto != IPPROTO_AH) {
+ netdev_err(ns->netdev, "unexpected proto=%d\n", xs->id.proto);
+ return false;
+ }
+
+ ipsec->tx++;
+
+ return true;
+}
+
+void nsim_ipsec_init(struct netdevsim *ns)
+{
+ ns->netdev->xfrmdev_ops = &nsim_xfrmdev_ops;
+
+#define NSIM_ESP_FEATURES (NETIF_F_HW_ESP | \
+ NETIF_F_HW_ESP_TX_CSUM | \
+ NETIF_F_GSO_ESP)
+
+ ns->netdev->features |= NSIM_ESP_FEATURES;
+ ns->netdev->hw_enc_features |= NSIM_ESP_FEATURES;
+
+ ns->ipsec.pfile = debugfs_create_file("ipsec", 0400, ns->ddir, ns,
+ &ipsec_dbg_fops);
+}
+
+void nsim_ipsec_teardown(struct netdevsim *ns)
+{
+ struct nsim_ipsec *ipsec = &ns->ipsec;
+
+ if (ipsec->count)
+ netdev_err(ns->netdev, "tearing down IPsec offload with %d SAs left\n",
+ ipsec->count);
+ debugfs_remove_recursive(ipsec->pfile);
+}
if (err)
goto err_unreg_dev;
+ nsim_ipsec_init(ns);
+
return 0;
err_unreg_dev:
{
struct netdevsim *ns = netdev_priv(dev);
+ nsim_ipsec_teardown(ns);
nsim_devlink_teardown(ns);
debugfs_remove_recursive(ns->ddir);
nsim_bpf_uninit(ns);
{
struct netdevsim *ns = netdev_priv(dev);
+ if (!nsim_ipsec_tx(ns, skb))
+ goto out;
+
u64_stats_update_begin(&ns->syncp);
ns->tx_packets++;
ns->tx_bytes += skb->len;
u64_stats_update_end(&ns->syncp);
+out:
dev_kfree_skb(skb);
return NETDEV_TX_OK;
{
struct netdevsim *ns = netdev_priv(dev);
- if (ns->xdp_prog_mode == XDP_ATTACHED_DRV &&
- new_mtu > NSIM_XDP_MAX_MTU)
+ if (ns->xdp.prog && new_mtu > NSIM_XDP_MAX_MTU)
return -EBUSY;
dev->mtu = new_mtu;
switch (f->command) {
case TC_BLOCK_BIND:
return tcf_block_cb_register(f->block, nsim_setup_tc_block_cb,
- ns, ns);
+ ns, ns, f->extack);
case TC_BLOCK_UNBIND:
tcf_block_cb_unregister(f->block, nsim_setup_tc_block_cb, ns);
return 0;
#include <linux/list.h>
#include <linux/netdevice.h>
#include <linux/u64_stats_sync.h>
+#include <net/xdp.h>
#define DRV_NAME "netdevsim"
struct dentry;
struct nsim_vf_config;
+#define NSIM_IPSEC_MAX_SA_COUNT 33
+#define NSIM_IPSEC_VALID BIT(31)
+
+struct nsim_sa {
+ struct xfrm_state *xs;
+ __be32 ipaddr[4];
+ u32 key[4];
+ u32 salt;
+ bool used;
+ bool crypt;
+ bool rx;
+};
+
+struct nsim_ipsec {
+ struct nsim_sa sa[NSIM_IPSEC_MAX_SA_COUNT];
+ struct dentry *pfile;
+ u32 count;
+ u32 tx;
+ u32 ok;
+};
+
struct netdevsim {
struct net_device *netdev;
struct bpf_prog *bpf_offloaded;
u32 bpf_offloaded_id;
- u32 xdp_flags;
- int xdp_prog_mode;
- struct bpf_prog *xdp_prog;
+ struct xdp_attachment_info xdp;
+ struct xdp_attachment_info xdp_hw;
u32 prog_id_gen;
#if IS_ENABLED(CONFIG_NET_DEVLINK)
struct devlink *devlink;
#endif
+ struct nsim_ipsec ipsec;
};
extern struct dentry *nsim_ddir;
}
#endif
+#if IS_ENABLED(CONFIG_XFRM_OFFLOAD)
+void nsim_ipsec_init(struct netdevsim *ns);
+void nsim_ipsec_teardown(struct netdevsim *ns);
+bool nsim_ipsec_tx(struct netdevsim *ns, struct sk_buff *skb);
+#else
+static inline void nsim_ipsec_init(struct netdevsim *ns)
+{
+}
+
+static inline void nsim_ipsec_teardown(struct netdevsim *ns)
+{
+}
+
+static inline bool nsim_ipsec_tx(struct netdevsim *ns, struct sk_buff *skb)
+{
+ return true;
+}
+#endif
+
static inline struct netdevsim *to_nsim(struct device *ptr)
{
return container_of(ptr, struct netdevsim, dev);
ndev->hw_features = ndev->features;
ndev->watchdog_timeo = msecs_to_jiffies(NTB_TX_TIMEOUT_MS);
- random_ether_addr(ndev->perm_addr);
+ eth_random_addr(ndev->perm_addr);
memcpy(ndev->dev_addr, ndev->perm_addr, ndev->addr_len);
ndev->netdev_ops = &ntb_netdev_ops;
config MDIO_GPIO
tristate "GPIO lib-based bitbanged MDIO buses"
- depends on MDIO_BITBANG && GPIOLIB
+ depends on MDIO_BITBANG
+ depends on GPIOLIB || COMPILE_TEST
---help---
Supports GPIO lib-based MDIO busses.
tristate "SFP cage support"
depends on I2C && PHYLINK
select MDIO_I2C
+ imply HWMON
config AMD_PHY
tristate "AMD PHYs"
#define MII_DP83811_SGMII_CTRL 0x09
#define MII_DP83811_INT_STAT1 0x12
#define MII_DP83811_INT_STAT2 0x13
+#define MII_DP83811_INT_STAT3 0x18
#define MII_DP83811_RESET_CTRL 0x1f
#define DP83811_HW_RESET BIT(15)
#define DP83811_OVERVOLTAGE_INT_EN BIT(6)
#define DP83811_UNDERVOLTAGE_INT_EN BIT(7)
+/* INT_STAT3 bits */
+#define DP83811_LPS_INT_EN BIT(0)
+#define DP83811_NO_FRAME_INT_EN BIT(3)
+#define DP83811_POR_DONE_INT_EN BIT(4)
+
#define MII_DP83811_RXSOP1 0x04a5
#define MII_DP83811_RXSOP2 0x04a6
#define MII_DP83811_RXSOP3 0x04a7
if (err < 0)
return err;
+ err = phy_read(phydev, MII_DP83811_INT_STAT3);
+ if (err < 0)
+ return err;
+
return 0;
}
DP83811_UNDERVOLTAGE_INT_EN);
err = phy_write(phydev, MII_DP83811_INT_STAT2, misr_status);
+ if (err < 0)
+ return err;
+
+ misr_status = phy_read(phydev, MII_DP83811_INT_STAT3);
+ if (misr_status < 0)
+ return misr_status;
+
+ misr_status |= (DP83811_LPS_INT_EN |
+ DP83811_NO_FRAME_INT_EN |
+ DP83811_POR_DONE_INT_EN);
+
+ err = phy_write(phydev, MII_DP83811_INT_STAT3, misr_status);
} else {
err = phy_write(phydev, MII_DP83811_INT_STAT1, 0);
if (err < 0)
return err;
- err = phy_write(phydev, MII_DP83811_INT_STAT1, 0);
+ err = phy_write(phydev, MII_DP83811_INT_STAT2, 0);
+ if (err < 0)
+ return err;
+
+ err = phy_write(phydev, MII_DP83811_INT_STAT3, 0);
}
return err;
if (err < 0)
return err;
+ value = phy_read(phydev, MII_DP83811_SGMII_CTRL);
if (phydev->interface == PHY_INTERFACE_MODE_SGMII) {
- value = phy_read(phydev, MII_DP83811_SGMII_CTRL);
- if (!(value & DP83811_SGMII_EN)) {
- err = phy_write(phydev, MII_DP83811_SGMII_CTRL,
+ err = phy_write(phydev, MII_DP83811_SGMII_CTRL,
(DP83811_SGMII_EN | value));
- if (err < 0)
- return err;
- } else {
- err = phy_write(phydev, MII_DP83811_SGMII_CTRL,
- (~DP83811_SGMII_EN & value));
- if (err < 0)
- return err;
- }
+ } else {
+ err = phy_write(phydev, MII_DP83811_SGMII_CTRL,
+ (~DP83811_SGMII_EN & value));
}
+ if (err < 0)
+
+ return err;
+
value = DP83811_WOL_MAGIC_EN | DP83811_WOL_SECURE_ON | DP83811_WOL_EN;
return phy_write_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_CFG,
int ret;
pdev = platform_device_register_simple("Fixed MDIO bus", 0, NULL, 0);
- if (IS_ERR(pdev)) {
- ret = PTR_ERR(pdev);
- goto err_pdev;
- }
+ if (IS_ERR(pdev))
+ return PTR_ERR(pdev);
fmb->mii_bus = mdiobus_alloc();
if (fmb->mii_bus == NULL) {
mdiobus_free(fmb->mii_bus);
err_mdiobus_reg:
platform_device_unregister(pdev);
-err_pdev:
return ret;
}
module_init(fixed_mdio_bus_init);
struct mdio_mux_gpio_state {
struct gpio_descs *gpios;
void *mux_handle;
+ int values[];
};
static int mdio_mux_gpio_switch_fn(int current_child, int desired_child,
void *data)
{
struct mdio_mux_gpio_state *s = data;
- int values[s->gpios->ndescs];
unsigned int n;
if (current_child == desired_child)
return 0;
for (n = 0; n < s->gpios->ndescs; n++)
- values[n] = (desired_child >> n) & 1;
+ s->values[n] = (desired_child >> n) & 1;
gpiod_set_array_value_cansleep(s->gpios->ndescs, s->gpios->desc,
- values);
+ s->values);
return 0;
}
static int mdio_mux_gpio_probe(struct platform_device *pdev)
{
struct mdio_mux_gpio_state *s;
+ struct gpio_descs *gpios;
int r;
- s = devm_kzalloc(&pdev->dev, sizeof(*s), GFP_KERNEL);
- if (!s)
+ gpios = gpiod_get_array(&pdev->dev, NULL, GPIOD_OUT_LOW);
+ if (IS_ERR(gpios))
+ return PTR_ERR(gpios);
+
+ s = devm_kzalloc(&pdev->dev, struct_size(s, values, gpios->ndescs),
+ GFP_KERNEL);
+ if (!s) {
+ gpiod_put_array(gpios);
return -ENOMEM;
+ }
- s->gpios = gpiod_get_array(&pdev->dev, NULL, GPIOD_OUT_LOW);
- if (IS_ERR(s->gpios))
- return PTR_ERR(s->gpios);
+ s->gpios = gpios;
r = mdio_mux_init(&pdev->dev, pdev->dev.of_node,
mdio_mux_gpio_switch_fn, &s->mux_handle, s, NULL);
}
EXPORT_SYMBOL(phy_mii_ioctl);
+static int phy_config_aneg(struct phy_device *phydev)
+{
+ if (phydev->drv->config_aneg)
+ return phydev->drv->config_aneg(phydev);
+ else
+ return genphy_config_aneg(phydev);
+}
+
/**
* phy_start_aneg_priv - start auto-negotiation for this PHY device
* @phydev: the phy_device struct
/* Invalidate LP advertising flags */
phydev->lp_advertising = 0;
- if (phydev->drv->config_aneg)
- err = phydev->drv->config_aneg(phydev);
- else
- err = genphy_config_aneg(phydev);
+ err = phy_config_aneg(phydev);
if (err < 0)
goto out_unlock;
}
EXPORT_SYMBOL(phy_start_aneg);
+static int phy_poll_aneg_done(struct phy_device *phydev)
+{
+ unsigned int retries = 100;
+ int ret;
+
+ do {
+ msleep(100);
+ ret = phy_aneg_done(phydev);
+ } while (!ret && --retries);
+
+ if (!ret)
+ return -ETIMEDOUT;
+
+ return ret < 0 ? ret : 0;
+}
+
+/**
+ * phy_speed_down - set speed to lowest speed supported by both link partners
+ * @phydev: the phy_device struct
+ * @sync: perform action synchronously
+ *
+ * Description: Typically used to save energy when waiting for a WoL packet
+ *
+ * WARNING: Setting sync to false may cause the system being unable to suspend
+ * in case the PHY generates an interrupt when finishing the autonegotiation.
+ * This interrupt may wake up the system immediately after suspend.
+ * Therefore use sync = false only if you're sure it's safe with the respective
+ * network chip.
+ */
+int phy_speed_down(struct phy_device *phydev, bool sync)
+{
+ u32 adv = phydev->lp_advertising & phydev->supported;
+ u32 adv_old = phydev->advertising;
+ int ret;
+
+ if (phydev->autoneg != AUTONEG_ENABLE)
+ return 0;
+
+ if (adv & PHY_10BT_FEATURES)
+ phydev->advertising &= ~(PHY_100BT_FEATURES |
+ PHY_1000BT_FEATURES);
+ else if (adv & PHY_100BT_FEATURES)
+ phydev->advertising &= ~PHY_1000BT_FEATURES;
+
+ if (phydev->advertising == adv_old)
+ return 0;
+
+ ret = phy_config_aneg(phydev);
+ if (ret)
+ return ret;
+
+ return sync ? phy_poll_aneg_done(phydev) : 0;
+}
+EXPORT_SYMBOL_GPL(phy_speed_down);
+
+/**
+ * phy_speed_up - (re)set advertised speeds to all supported speeds
+ * @phydev: the phy_device struct
+ *
+ * Description: Used to revert the effect of phy_speed_down
+ */
+int phy_speed_up(struct phy_device *phydev)
+{
+ u32 mask = PHY_10BT_FEATURES | PHY_100BT_FEATURES | PHY_1000BT_FEATURES;
+ u32 adv_old = phydev->advertising;
+
+ if (phydev->autoneg != AUTONEG_ENABLE)
+ return 0;
+
+ phydev->advertising = (adv_old & ~mask) | (phydev->supported & mask);
+
+ if (phydev->advertising == adv_old)
+ return 0;
+
+ return phy_config_aneg(phydev);
+}
+EXPORT_SYMBOL_GPL(phy_speed_up);
+
/**
* phy_start_machine - start PHY state machine tracking
* @phydev: the phy_device struct
#define RTL8201F_ISR 0x1e
#define RTL8201F_IER 0x13
+#define RTL8366RB_POWER_SAVE 0x15
+#define RTL8366RB_POWER_SAVE_ON BIT(12)
+
MODULE_DESCRIPTION("Realtek PHY driver");
MODULE_AUTHOR("Johnson Leung");
MODULE_LICENSE("GPL");
return phy_write_paged(phydev, 0xa42, RTL821x_INER, val);
}
+static int rtl8211_config_aneg(struct phy_device *phydev)
+{
+ int ret;
+
+ ret = genphy_config_aneg(phydev);
+ if (ret < 0)
+ return ret;
+
+ /* Quirk was copied from vendor driver. Unfortunately it includes no
+ * description of the magic numbers.
+ */
+ if (phydev->speed == SPEED_100 && phydev->autoneg == AUTONEG_DISABLE) {
+ phy_write(phydev, 0x17, 0x2138);
+ phy_write(phydev, 0x0e, 0x0260);
+ } else {
+ phy_write(phydev, 0x17, 0x2108);
+ phy_write(phydev, 0x0e, 0x0000);
+ }
+
+ return 0;
+}
+
+static int rtl8211c_config_init(struct phy_device *phydev)
+{
+ /* RTL8211C has an issue when operating in Gigabit slave mode */
+ phy_set_bits(phydev, MII_CTRL1000,
+ CTL1000_ENABLE_MASTER | CTL1000_AS_MASTER);
+
+ return genphy_config_init(phydev);
+}
+
static int rtl8211f_config_init(struct phy_device *phydev)
{
int ret;
return genphy_resume(phydev);
}
+static int rtl8366rb_config_init(struct phy_device *phydev)
+{
+ int ret;
+
+ ret = genphy_config_init(phydev);
+ if (ret < 0)
+ return ret;
+
+ ret = phy_set_bits(phydev, RTL8366RB_POWER_SAVE,
+ RTL8366RB_POWER_SAVE_ON);
+ if (ret) {
+ dev_err(&phydev->mdio.dev,
+ "error enabling power management\n");
+ }
+
+ return ret;
+}
+
static struct phy_driver realtek_drvs[] = {
{
.phy_id = 0x00008201,
.resume = genphy_resume,
.read_page = rtl821x_read_page,
.write_page = rtl821x_write_page,
+ }, {
+ .phy_id = 0x001cc910,
+ .name = "RTL8211 Gigabit Ethernet",
+ .phy_id_mask = 0x001fffff,
+ .features = PHY_GBIT_FEATURES,
+ .config_aneg = rtl8211_config_aneg,
+ .read_mmd = &genphy_read_mmd_unsupported,
+ .write_mmd = &genphy_write_mmd_unsupported,
}, {
.phy_id = 0x001cc912,
.name = "RTL8211B Gigabit Ethernet",
.write_mmd = &genphy_write_mmd_unsupported,
.suspend = rtl8211b_suspend,
.resume = rtl8211b_resume,
+ }, {
+ .phy_id = 0x001cc913,
+ .name = "RTL8211C Gigabit Ethernet",
+ .phy_id_mask = 0x001fffff,
+ .features = PHY_GBIT_FEATURES,
+ .config_init = rtl8211c_config_init,
+ .read_mmd = &genphy_read_mmd_unsupported,
+ .write_mmd = &genphy_write_mmd_unsupported,
}, {
.phy_id = 0x001cc914,
.name = "RTL8211DN Gigabit Ethernet",
.resume = genphy_resume,
.read_page = rtl821x_read_page,
.write_page = rtl821x_write_page,
+ }, {
+ .phy_id = 0x001cc961,
+ .name = "RTL8366RB Gigabit Ethernet",
+ .phy_id_mask = 0x001fffff,
+ .features = PHY_GBIT_FEATURES,
+ .flags = PHY_HAS_INTERRUPT,
+ .config_init = &rtl8366rb_config_init,
+ .suspend = genphy_suspend,
+ .resume = genphy_resume,
},
};
static struct mdio_device_id __maybe_unused realtek_tbl[] = {
{ 0x001cc816, 0x001fffff },
+ { 0x001cc910, 0x001fffff },
{ 0x001cc912, 0x001fffff },
+ { 0x001cc913, 0x001fffff },
{ 0x001cc914, 0x001fffff },
{ 0x001cc915, 0x001fffff },
{ 0x001cc916, 0x001fffff },
+ { 0x001cc961, 0x001fffff },
{ }
};
+#include <linux/ctype.h>
#include <linux/delay.h>
#include <linux/gpio/consumer.h>
+#include <linux/hwmon.h>
#include <linux/i2c.h>
#include <linux/interrupt.h>
#include <linux/jiffies.h>
unsigned int sm_retries;
struct sfp_eeprom_id id;
+#if IS_ENABLED(CONFIG_HWMON)
+ struct sfp_diag diag;
+ struct device *hwmon_dev;
+ char *hwmon_name;
+#endif
+
};
static bool sff_module_supported(const struct sfp_eeprom_id *id)
return check;
}
+/* hwmon */
+#if IS_ENABLED(CONFIG_HWMON)
+static umode_t sfp_hwmon_is_visible(const void *data,
+ enum hwmon_sensor_types type,
+ u32 attr, int channel)
+{
+ const struct sfp *sfp = data;
+
+ switch (type) {
+ case hwmon_temp:
+ switch (attr) {
+ case hwmon_temp_input:
+ case hwmon_temp_min_alarm:
+ case hwmon_temp_max_alarm:
+ case hwmon_temp_lcrit_alarm:
+ case hwmon_temp_crit_alarm:
+ case hwmon_temp_min:
+ case hwmon_temp_max:
+ case hwmon_temp_lcrit:
+ case hwmon_temp_crit:
+ return 0444;
+ default:
+ return 0;
+ }
+ case hwmon_in:
+ switch (attr) {
+ case hwmon_in_input:
+ case hwmon_in_min_alarm:
+ case hwmon_in_max_alarm:
+ case hwmon_in_lcrit_alarm:
+ case hwmon_in_crit_alarm:
+ case hwmon_in_min:
+ case hwmon_in_max:
+ case hwmon_in_lcrit:
+ case hwmon_in_crit:
+ return 0444;
+ default:
+ return 0;
+ }
+ case hwmon_curr:
+ switch (attr) {
+ case hwmon_curr_input:
+ case hwmon_curr_min_alarm:
+ case hwmon_curr_max_alarm:
+ case hwmon_curr_lcrit_alarm:
+ case hwmon_curr_crit_alarm:
+ case hwmon_curr_min:
+ case hwmon_curr_max:
+ case hwmon_curr_lcrit:
+ case hwmon_curr_crit:
+ return 0444;
+ default:
+ return 0;
+ }
+ case hwmon_power:
+ /* External calibration of receive power requires
+ * floating point arithmetic. Doing that in the kernel
+ * is not easy, so just skip it. If the module does
+ * not require external calibration, we can however
+ * show receiver power, since FP is then not needed.
+ */
+ if (sfp->id.ext.diagmon & SFP_DIAGMON_EXT_CAL &&
+ channel == 1)
+ return 0;
+ switch (attr) {
+ case hwmon_power_input:
+ case hwmon_power_min_alarm:
+ case hwmon_power_max_alarm:
+ case hwmon_power_lcrit_alarm:
+ case hwmon_power_crit_alarm:
+ case hwmon_power_min:
+ case hwmon_power_max:
+ case hwmon_power_lcrit:
+ case hwmon_power_crit:
+ return 0444;
+ default:
+ return 0;
+ }
+ default:
+ return 0;
+ }
+}
+
+static int sfp_hwmon_read_sensor(struct sfp *sfp, int reg, long *value)
+{
+ __be16 val;
+ int err;
+
+ err = sfp_read(sfp, true, reg, &val, sizeof(val));
+ if (err < 0)
+ return err;
+
+ *value = be16_to_cpu(val);
+
+ return 0;
+}
+
+static void sfp_hwmon_to_rx_power(long *value)
+{
+ *value = DIV_ROUND_CLOSEST(*value, 100);
+}
+
+static void sfp_hwmon_calibrate(struct sfp *sfp, unsigned int slope, int offset,
+ long *value)
+{
+ if (sfp->id.ext.diagmon & SFP_DIAGMON_EXT_CAL)
+ *value = DIV_ROUND_CLOSEST(*value * slope, 256) + offset;
+}
+
+static void sfp_hwmon_calibrate_temp(struct sfp *sfp, long *value)
+{
+ sfp_hwmon_calibrate(sfp, be16_to_cpu(sfp->diag.cal_t_slope),
+ be16_to_cpu(sfp->diag.cal_t_offset), value);
+
+ if (*value >= 0x8000)
+ *value -= 0x10000;
+
+ *value = DIV_ROUND_CLOSEST(*value * 1000, 256);
+}
+
+static void sfp_hwmon_calibrate_vcc(struct sfp *sfp, long *value)
+{
+ sfp_hwmon_calibrate(sfp, be16_to_cpu(sfp->diag.cal_v_slope),
+ be16_to_cpu(sfp->diag.cal_v_offset), value);
+
+ *value = DIV_ROUND_CLOSEST(*value, 10);
+}
+
+static void sfp_hwmon_calibrate_bias(struct sfp *sfp, long *value)
+{
+ sfp_hwmon_calibrate(sfp, be16_to_cpu(sfp->diag.cal_txi_slope),
+ be16_to_cpu(sfp->diag.cal_txi_offset), value);
+
+ *value = DIV_ROUND_CLOSEST(*value, 500);
+}
+
+static void sfp_hwmon_calibrate_tx_power(struct sfp *sfp, long *value)
+{
+ sfp_hwmon_calibrate(sfp, be16_to_cpu(sfp->diag.cal_txpwr_slope),
+ be16_to_cpu(sfp->diag.cal_txpwr_offset), value);
+
+ *value = DIV_ROUND_CLOSEST(*value, 10);
+}
+
+static int sfp_hwmon_read_temp(struct sfp *sfp, int reg, long *value)
+{
+ int err;
+
+ err = sfp_hwmon_read_sensor(sfp, reg, value);
+ if (err < 0)
+ return err;
+
+ sfp_hwmon_calibrate_temp(sfp, value);
+
+ return 0;
+}
+
+static int sfp_hwmon_read_vcc(struct sfp *sfp, int reg, long *value)
+{
+ int err;
+
+ err = sfp_hwmon_read_sensor(sfp, reg, value);
+ if (err < 0)
+ return err;
+
+ sfp_hwmon_calibrate_vcc(sfp, value);
+
+ return 0;
+}
+
+static int sfp_hwmon_read_bias(struct sfp *sfp, int reg, long *value)
+{
+ int err;
+
+ err = sfp_hwmon_read_sensor(sfp, reg, value);
+ if (err < 0)
+ return err;
+
+ sfp_hwmon_calibrate_bias(sfp, value);
+
+ return 0;
+}
+
+static int sfp_hwmon_read_tx_power(struct sfp *sfp, int reg, long *value)
+{
+ int err;
+
+ err = sfp_hwmon_read_sensor(sfp, reg, value);
+ if (err < 0)
+ return err;
+
+ sfp_hwmon_calibrate_tx_power(sfp, value);
+
+ return 0;
+}
+
+static int sfp_hwmon_read_rx_power(struct sfp *sfp, int reg, long *value)
+{
+ int err;
+
+ err = sfp_hwmon_read_sensor(sfp, reg, value);
+ if (err < 0)
+ return err;
+
+ sfp_hwmon_to_rx_power(value);
+
+ return 0;
+}
+
+static int sfp_hwmon_temp(struct sfp *sfp, u32 attr, long *value)
+{
+ u8 status;
+ int err;
+
+ switch (attr) {
+ case hwmon_temp_input:
+ return sfp_hwmon_read_temp(sfp, SFP_TEMP, value);
+
+ case hwmon_temp_lcrit:
+ *value = be16_to_cpu(sfp->diag.temp_low_alarm);
+ sfp_hwmon_calibrate_temp(sfp, value);
+ return 0;
+
+ case hwmon_temp_min:
+ *value = be16_to_cpu(sfp->diag.temp_low_warn);
+ sfp_hwmon_calibrate_temp(sfp, value);
+ return 0;
+ case hwmon_temp_max:
+ *value = be16_to_cpu(sfp->diag.temp_high_warn);
+ sfp_hwmon_calibrate_temp(sfp, value);
+ return 0;
+
+ case hwmon_temp_crit:
+ *value = be16_to_cpu(sfp->diag.temp_high_alarm);
+ sfp_hwmon_calibrate_temp(sfp, value);
+ return 0;
+
+ case hwmon_temp_lcrit_alarm:
+ err = sfp_read(sfp, true, SFP_ALARM0, &status, sizeof(status));
+ if (err < 0)
+ return err;
+
+ *value = !!(status & SFP_ALARM0_TEMP_LOW);
+ return 0;
+
+ case hwmon_temp_min_alarm:
+ err = sfp_read(sfp, true, SFP_WARN0, &status, sizeof(status));
+ if (err < 0)
+ return err;
+
+ *value = !!(status & SFP_WARN0_TEMP_LOW);
+ return 0;
+
+ case hwmon_temp_max_alarm:
+ err = sfp_read(sfp, true, SFP_WARN0, &status, sizeof(status));
+ if (err < 0)
+ return err;
+
+ *value = !!(status & SFP_WARN0_TEMP_HIGH);
+ return 0;
+
+ case hwmon_temp_crit_alarm:
+ err = sfp_read(sfp, true, SFP_ALARM0, &status, sizeof(status));
+ if (err < 0)
+ return err;
+
+ *value = !!(status & SFP_ALARM0_TEMP_HIGH);
+ return 0;
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ return -EOPNOTSUPP;
+}
+
+static int sfp_hwmon_vcc(struct sfp *sfp, u32 attr, long *value)
+{
+ u8 status;
+ int err;
+
+ switch (attr) {
+ case hwmon_in_input:
+ return sfp_hwmon_read_vcc(sfp, SFP_VCC, value);
+
+ case hwmon_in_lcrit:
+ *value = be16_to_cpu(sfp->diag.volt_low_alarm);
+ sfp_hwmon_calibrate_vcc(sfp, value);
+ return 0;
+
+ case hwmon_in_min:
+ *value = be16_to_cpu(sfp->diag.volt_low_warn);
+ sfp_hwmon_calibrate_vcc(sfp, value);
+ return 0;
+
+ case hwmon_in_max:
+ *value = be16_to_cpu(sfp->diag.volt_high_warn);
+ sfp_hwmon_calibrate_vcc(sfp, value);
+ return 0;
+
+ case hwmon_in_crit:
+ *value = be16_to_cpu(sfp->diag.volt_high_alarm);
+ sfp_hwmon_calibrate_vcc(sfp, value);
+ return 0;
+
+ case hwmon_in_lcrit_alarm:
+ err = sfp_read(sfp, true, SFP_ALARM0, &status, sizeof(status));
+ if (err < 0)
+ return err;
+
+ *value = !!(status & SFP_ALARM0_VCC_LOW);
+ return 0;
+
+ case hwmon_in_min_alarm:
+ err = sfp_read(sfp, true, SFP_WARN0, &status, sizeof(status));
+ if (err < 0)
+ return err;
+
+ *value = !!(status & SFP_WARN0_VCC_LOW);
+ return 0;
+
+ case hwmon_in_max_alarm:
+ err = sfp_read(sfp, true, SFP_WARN0, &status, sizeof(status));
+ if (err < 0)
+ return err;
+
+ *value = !!(status & SFP_WARN0_VCC_HIGH);
+ return 0;
+
+ case hwmon_in_crit_alarm:
+ err = sfp_read(sfp, true, SFP_ALARM0, &status, sizeof(status));
+ if (err < 0)
+ return err;
+
+ *value = !!(status & SFP_ALARM0_VCC_HIGH);
+ return 0;
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ return -EOPNOTSUPP;
+}
+
+static int sfp_hwmon_bias(struct sfp *sfp, u32 attr, long *value)
+{
+ u8 status;
+ int err;
+
+ switch (attr) {
+ case hwmon_curr_input:
+ return sfp_hwmon_read_bias(sfp, SFP_TX_BIAS, value);
+
+ case hwmon_curr_lcrit:
+ *value = be16_to_cpu(sfp->diag.bias_low_alarm);
+ sfp_hwmon_calibrate_bias(sfp, value);
+ return 0;
+
+ case hwmon_curr_min:
+ *value = be16_to_cpu(sfp->diag.bias_low_warn);
+ sfp_hwmon_calibrate_bias(sfp, value);
+ return 0;
+
+ case hwmon_curr_max:
+ *value = be16_to_cpu(sfp->diag.bias_high_warn);
+ sfp_hwmon_calibrate_bias(sfp, value);
+ return 0;
+
+ case hwmon_curr_crit:
+ *value = be16_to_cpu(sfp->diag.bias_high_alarm);
+ sfp_hwmon_calibrate_bias(sfp, value);
+ return 0;
+
+ case hwmon_curr_lcrit_alarm:
+ err = sfp_read(sfp, true, SFP_ALARM0, &status, sizeof(status));
+ if (err < 0)
+ return err;
+
+ *value = !!(status & SFP_ALARM0_TX_BIAS_LOW);
+ return 0;
+
+ case hwmon_curr_min_alarm:
+ err = sfp_read(sfp, true, SFP_WARN0, &status, sizeof(status));
+ if (err < 0)
+ return err;
+
+ *value = !!(status & SFP_WARN0_TX_BIAS_LOW);
+ return 0;
+
+ case hwmon_curr_max_alarm:
+ err = sfp_read(sfp, true, SFP_WARN0, &status, sizeof(status));
+ if (err < 0)
+ return err;
+
+ *value = !!(status & SFP_WARN0_TX_BIAS_HIGH);
+ return 0;
+
+ case hwmon_curr_crit_alarm:
+ err = sfp_read(sfp, true, SFP_ALARM0, &status, sizeof(status));
+ if (err < 0)
+ return err;
+
+ *value = !!(status & SFP_ALARM0_TX_BIAS_HIGH);
+ return 0;
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ return -EOPNOTSUPP;
+}
+
+static int sfp_hwmon_tx_power(struct sfp *sfp, u32 attr, long *value)
+{
+ u8 status;
+ int err;
+
+ switch (attr) {
+ case hwmon_power_input:
+ return sfp_hwmon_read_tx_power(sfp, SFP_TX_POWER, value);
+
+ case hwmon_power_lcrit:
+ *value = be16_to_cpu(sfp->diag.txpwr_low_alarm);
+ sfp_hwmon_calibrate_tx_power(sfp, value);
+ return 0;
+
+ case hwmon_power_min:
+ *value = be16_to_cpu(sfp->diag.txpwr_low_warn);
+ sfp_hwmon_calibrate_tx_power(sfp, value);
+ return 0;
+
+ case hwmon_power_max:
+ *value = be16_to_cpu(sfp->diag.txpwr_high_warn);
+ sfp_hwmon_calibrate_tx_power(sfp, value);
+ return 0;
+
+ case hwmon_power_crit:
+ *value = be16_to_cpu(sfp->diag.txpwr_high_alarm);
+ sfp_hwmon_calibrate_tx_power(sfp, value);
+ return 0;
+
+ case hwmon_power_lcrit_alarm:
+ err = sfp_read(sfp, true, SFP_ALARM0, &status, sizeof(status));
+ if (err < 0)
+ return err;
+
+ *value = !!(status & SFP_ALARM0_TXPWR_LOW);
+ return 0;
+
+ case hwmon_power_min_alarm:
+ err = sfp_read(sfp, true, SFP_WARN0, &status, sizeof(status));
+ if (err < 0)
+ return err;
+
+ *value = !!(status & SFP_WARN0_TXPWR_LOW);
+ return 0;
+
+ case hwmon_power_max_alarm:
+ err = sfp_read(sfp, true, SFP_WARN0, &status, sizeof(status));
+ if (err < 0)
+ return err;
+
+ *value = !!(status & SFP_WARN0_TXPWR_HIGH);
+ return 0;
+
+ case hwmon_power_crit_alarm:
+ err = sfp_read(sfp, true, SFP_ALARM0, &status, sizeof(status));
+ if (err < 0)
+ return err;
+
+ *value = !!(status & SFP_ALARM0_TXPWR_HIGH);
+ return 0;
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ return -EOPNOTSUPP;
+}
+
+static int sfp_hwmon_rx_power(struct sfp *sfp, u32 attr, long *value)
+{
+ u8 status;
+ int err;
+
+ switch (attr) {
+ case hwmon_power_input:
+ return sfp_hwmon_read_rx_power(sfp, SFP_RX_POWER, value);
+
+ case hwmon_power_lcrit:
+ *value = be16_to_cpu(sfp->diag.rxpwr_low_alarm);
+ sfp_hwmon_to_rx_power(value);
+ return 0;
+
+ case hwmon_power_min:
+ *value = be16_to_cpu(sfp->diag.rxpwr_low_warn);
+ sfp_hwmon_to_rx_power(value);
+ return 0;
+
+ case hwmon_power_max:
+ *value = be16_to_cpu(sfp->diag.rxpwr_high_warn);
+ sfp_hwmon_to_rx_power(value);
+ return 0;
+
+ case hwmon_power_crit:
+ *value = be16_to_cpu(sfp->diag.rxpwr_high_alarm);
+ sfp_hwmon_to_rx_power(value);
+ return 0;
+
+ case hwmon_power_lcrit_alarm:
+ err = sfp_read(sfp, true, SFP_ALARM1, &status, sizeof(status));
+ if (err < 0)
+ return err;
+
+ *value = !!(status & SFP_ALARM1_RXPWR_LOW);
+ return 0;
+
+ case hwmon_power_min_alarm:
+ err = sfp_read(sfp, true, SFP_WARN1, &status, sizeof(status));
+ if (err < 0)
+ return err;
+
+ *value = !!(status & SFP_WARN1_RXPWR_LOW);
+ return 0;
+
+ case hwmon_power_max_alarm:
+ err = sfp_read(sfp, true, SFP_WARN1, &status, sizeof(status));
+ if (err < 0)
+ return err;
+
+ *value = !!(status & SFP_WARN1_RXPWR_HIGH);
+ return 0;
+
+ case hwmon_power_crit_alarm:
+ err = sfp_read(sfp, true, SFP_ALARM1, &status, sizeof(status));
+ if (err < 0)
+ return err;
+
+ *value = !!(status & SFP_ALARM1_RXPWR_HIGH);
+ return 0;
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ return -EOPNOTSUPP;
+}
+
+static int sfp_hwmon_read(struct device *dev, enum hwmon_sensor_types type,
+ u32 attr, int channel, long *value)
+{
+ struct sfp *sfp = dev_get_drvdata(dev);
+
+ switch (type) {
+ case hwmon_temp:
+ return sfp_hwmon_temp(sfp, attr, value);
+ case hwmon_in:
+ return sfp_hwmon_vcc(sfp, attr, value);
+ case hwmon_curr:
+ return sfp_hwmon_bias(sfp, attr, value);
+ case hwmon_power:
+ switch (channel) {
+ case 0:
+ return sfp_hwmon_tx_power(sfp, attr, value);
+ case 1:
+ return sfp_hwmon_rx_power(sfp, attr, value);
+ default:
+ return -EOPNOTSUPP;
+ }
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
+static const struct hwmon_ops sfp_hwmon_ops = {
+ .is_visible = sfp_hwmon_is_visible,
+ .read = sfp_hwmon_read,
+};
+
+static u32 sfp_hwmon_chip_config[] = {
+ HWMON_C_REGISTER_TZ,
+ 0,
+};
+
+static const struct hwmon_channel_info sfp_hwmon_chip = {
+ .type = hwmon_chip,
+ .config = sfp_hwmon_chip_config,
+};
+
+static u32 sfp_hwmon_temp_config[] = {
+ HWMON_T_INPUT |
+ HWMON_T_MAX | HWMON_T_MIN |
+ HWMON_T_MAX_ALARM | HWMON_T_MIN_ALARM |
+ HWMON_T_CRIT | HWMON_T_LCRIT |
+ HWMON_T_CRIT_ALARM | HWMON_T_LCRIT_ALARM,
+ 0,
+};
+
+static const struct hwmon_channel_info sfp_hwmon_temp_channel_info = {
+ .type = hwmon_temp,
+ .config = sfp_hwmon_temp_config,
+};
+
+static u32 sfp_hwmon_vcc_config[] = {
+ HWMON_I_INPUT |
+ HWMON_I_MAX | HWMON_I_MIN |
+ HWMON_I_MAX_ALARM | HWMON_I_MIN_ALARM |
+ HWMON_I_CRIT | HWMON_I_LCRIT |
+ HWMON_I_CRIT_ALARM | HWMON_I_LCRIT_ALARM,
+ 0,
+};
+
+static const struct hwmon_channel_info sfp_hwmon_vcc_channel_info = {
+ .type = hwmon_in,
+ .config = sfp_hwmon_vcc_config,
+};
+
+static u32 sfp_hwmon_bias_config[] = {
+ HWMON_C_INPUT |
+ HWMON_C_MAX | HWMON_C_MIN |
+ HWMON_C_MAX_ALARM | HWMON_C_MIN_ALARM |
+ HWMON_C_CRIT | HWMON_C_LCRIT |
+ HWMON_C_CRIT_ALARM | HWMON_C_LCRIT_ALARM,
+ 0,
+};
+
+static const struct hwmon_channel_info sfp_hwmon_bias_channel_info = {
+ .type = hwmon_curr,
+ .config = sfp_hwmon_bias_config,
+};
+
+static u32 sfp_hwmon_power_config[] = {
+ /* Transmit power */
+ HWMON_P_INPUT |
+ HWMON_P_MAX | HWMON_P_MIN |
+ HWMON_P_MAX_ALARM | HWMON_P_MIN_ALARM |
+ HWMON_P_CRIT | HWMON_P_LCRIT |
+ HWMON_P_CRIT_ALARM | HWMON_P_LCRIT_ALARM,
+ /* Receive power */
+ HWMON_P_INPUT |
+ HWMON_P_MAX | HWMON_P_MIN |
+ HWMON_P_MAX_ALARM | HWMON_P_MIN_ALARM |
+ HWMON_P_CRIT | HWMON_P_LCRIT |
+ HWMON_P_CRIT_ALARM | HWMON_P_LCRIT_ALARM,
+ 0,
+};
+
+static const struct hwmon_channel_info sfp_hwmon_power_channel_info = {
+ .type = hwmon_power,
+ .config = sfp_hwmon_power_config,
+};
+
+static const struct hwmon_channel_info *sfp_hwmon_info[] = {
+ &sfp_hwmon_chip,
+ &sfp_hwmon_vcc_channel_info,
+ &sfp_hwmon_temp_channel_info,
+ &sfp_hwmon_bias_channel_info,
+ &sfp_hwmon_power_channel_info,
+ NULL,
+};
+
+static const struct hwmon_chip_info sfp_hwmon_chip_info = {
+ .ops = &sfp_hwmon_ops,
+ .info = sfp_hwmon_info,
+};
+
+static int sfp_hwmon_insert(struct sfp *sfp)
+{
+ int err, i;
+
+ if (sfp->id.ext.sff8472_compliance == SFP_SFF8472_COMPLIANCE_NONE)
+ return 0;
+
+ if (!(sfp->id.ext.diagmon & SFP_DIAGMON_DDM))
+ return 0;
+
+ if (sfp->id.ext.diagmon & SFP_DIAGMON_ADDRMODE)
+ /* This driver in general does not support address
+ * change.
+ */
+ return 0;
+
+ err = sfp_read(sfp, true, 0, &sfp->diag, sizeof(sfp->diag));
+ if (err < 0)
+ return err;
+
+ sfp->hwmon_name = kstrdup(dev_name(sfp->dev), GFP_KERNEL);
+ if (!sfp->hwmon_name)
+ return -ENODEV;
+
+ for (i = 0; sfp->hwmon_name[i]; i++)
+ if (hwmon_is_bad_char(sfp->hwmon_name[i]))
+ sfp->hwmon_name[i] = '_';
+
+ sfp->hwmon_dev = hwmon_device_register_with_info(sfp->dev,
+ sfp->hwmon_name, sfp,
+ &sfp_hwmon_chip_info,
+ NULL);
+
+ return PTR_ERR_OR_ZERO(sfp->hwmon_dev);
+}
+
+static void sfp_hwmon_remove(struct sfp *sfp)
+{
+ hwmon_device_unregister(sfp->hwmon_dev);
+ kfree(sfp->hwmon_name);
+}
+#else
+static int sfp_hwmon_insert(struct sfp *sfp)
+{
+ return 0;
+}
+
+static void sfp_hwmon_remove(struct sfp *sfp)
+{
+}
+#endif
+
/* Helpers */
static void sfp_module_tx_disable(struct sfp *sfp)
{
dev_warn(sfp->dev,
"module address swap to access page 0xA2 is not supported.\n");
+ ret = sfp_hwmon_insert(sfp);
+ if (ret < 0)
+ return ret;
+
ret = sfp_module_insert(sfp->sfp_bus, &sfp->id);
if (ret < 0)
return ret;
{
sfp_module_remove(sfp->sfp_bus);
+ sfp_hwmon_remove(sfp);
+
if (sfp->mod_phy)
sfp_sm_phy_detach(sfp);
#define PHY_ID_VSC8572 0x000704d0
#define PHY_ID_VSC8574 0x000704a0
#define PHY_ID_VSC8601 0x00070420
+#define PHY_ID_VSC7385 0x00070450
+#define PHY_ID_VSC7388 0x00070480
+#define PHY_ID_VSC7395 0x00070550
+#define PHY_ID_VSC7398 0x00070580
#define PHY_ID_VSC8662 0x00070660
#define PHY_ID_VSC8221 0x000fc550
#define PHY_ID_VSC8211 0x000fc4b0
return err;
}
+#define VSC73XX_EXT_PAGE_ACCESS 0x1f
+
+static int vsc73xx_read_page(struct phy_device *phydev)
+{
+ return __phy_read(phydev, VSC73XX_EXT_PAGE_ACCESS);
+}
+
+static int vsc73xx_write_page(struct phy_device *phydev, int page)
+{
+ return __phy_write(phydev, VSC73XX_EXT_PAGE_ACCESS, page);
+}
+
+static void vsc73xx_config_init(struct phy_device *phydev)
+{
+ /* Receiver init */
+ phy_write(phydev, 0x1f, 0x2a30);
+ phy_modify(phydev, 0x0c, 0x0300, 0x0200);
+ phy_write(phydev, 0x1f, 0x0000);
+
+ /* Config LEDs 0x61 */
+ phy_modify(phydev, MII_TPISTATUS, 0xff00, 0x0061);
+}
+
+static int vsc738x_config_init(struct phy_device *phydev)
+{
+ u16 rev;
+ /* This magic sequence appear in the application note
+ * "VSC7385/7388 PHY Configuration".
+ *
+ * Maybe one day we will get to know what it all means.
+ */
+ phy_write(phydev, 0x1f, 0x2a30);
+ phy_modify(phydev, 0x08, 0x0200, 0x0200);
+ phy_write(phydev, 0x1f, 0x52b5);
+ phy_write(phydev, 0x10, 0xb68a);
+ phy_modify(phydev, 0x12, 0xff07, 0x0003);
+ phy_modify(phydev, 0x11, 0x00ff, 0x00a2);
+ phy_write(phydev, 0x10, 0x968a);
+ phy_write(phydev, 0x1f, 0x2a30);
+ phy_modify(phydev, 0x08, 0x0200, 0x0000);
+ phy_write(phydev, 0x1f, 0x0000);
+
+ /* Read revision */
+ rev = phy_read(phydev, MII_PHYSID2);
+ rev &= 0x0f;
+
+ /* Special quirk for revision 0 */
+ if (rev == 0) {
+ phy_write(phydev, 0x1f, 0x2a30);
+ phy_modify(phydev, 0x08, 0x0200, 0x0200);
+ phy_write(phydev, 0x1f, 0x52b5);
+ phy_write(phydev, 0x12, 0x0000);
+ phy_write(phydev, 0x11, 0x0689);
+ phy_write(phydev, 0x10, 0x8f92);
+ phy_write(phydev, 0x1f, 0x52b5);
+ phy_write(phydev, 0x12, 0x0000);
+ phy_write(phydev, 0x11, 0x0e35);
+ phy_write(phydev, 0x10, 0x9786);
+ phy_write(phydev, 0x1f, 0x2a30);
+ phy_modify(phydev, 0x08, 0x0200, 0x0000);
+ phy_write(phydev, 0x17, 0xff80);
+ phy_write(phydev, 0x17, 0x0000);
+ }
+
+ phy_write(phydev, 0x1f, 0x0000);
+ phy_write(phydev, 0x12, 0x0048);
+
+ if (rev == 0) {
+ phy_write(phydev, 0x1f, 0x2a30);
+ phy_write(phydev, 0x14, 0x6600);
+ phy_write(phydev, 0x1f, 0x0000);
+ phy_write(phydev, 0x18, 0xa24e);
+ } else {
+ phy_write(phydev, 0x1f, 0x2a30);
+ phy_modify(phydev, 0x16, 0x0fc0, 0x0240);
+ phy_modify(phydev, 0x14, 0x6000, 0x4000);
+ /* bits 14-15 in extended register 0x14 controls DACG amplitude
+ * 6 = -8%, 2 is hardware default
+ */
+ phy_write(phydev, 0x1f, 0x0001);
+ phy_modify(phydev, 0x14, 0xe000, 0x6000);
+ phy_write(phydev, 0x1f, 0x0000);
+ }
+
+ vsc73xx_config_init(phydev);
+
+ return genphy_config_init(phydev);
+}
+
+static int vsc739x_config_init(struct phy_device *phydev)
+{
+ /* This magic sequence appears in the VSC7395 SparX-G5e application
+ * note "VSC7395/VSC7398 PHY Configuration"
+ *
+ * Maybe one day we will get to know what it all means.
+ */
+ phy_write(phydev, 0x1f, 0x2a30);
+ phy_modify(phydev, 0x08, 0x0200, 0x0200);
+ phy_write(phydev, 0x1f, 0x52b5);
+ phy_write(phydev, 0x10, 0xb68a);
+ phy_modify(phydev, 0x12, 0xff07, 0x0003);
+ phy_modify(phydev, 0x11, 0x00ff, 0x00a2);
+ phy_write(phydev, 0x10, 0x968a);
+ phy_write(phydev, 0x1f, 0x2a30);
+ phy_modify(phydev, 0x08, 0x0200, 0x0000);
+ phy_write(phydev, 0x1f, 0x0000);
+
+ phy_write(phydev, 0x1f, 0x0000);
+ phy_write(phydev, 0x12, 0x0048);
+ phy_write(phydev, 0x1f, 0x2a30);
+ phy_modify(phydev, 0x16, 0x0fc0, 0x0240);
+ phy_modify(phydev, 0x14, 0x6000, 0x4000);
+ phy_write(phydev, 0x1f, 0x0001);
+ phy_modify(phydev, 0x14, 0xe000, 0x6000);
+ phy_write(phydev, 0x1f, 0x0000);
+
+ vsc73xx_config_init(phydev);
+
+ return genphy_config_init(phydev);
+}
+
+static int vsc73xx_config_aneg(struct phy_device *phydev)
+{
+ /* The VSC73xx switches does not like to be instructed to
+ * do autonegotiation in any way, it prefers that you just go
+ * with the power-on/reset defaults. Writing some registers will
+ * just make autonegotiation permanently fail.
+ */
+ return 0;
+}
+
/* This adds a skew for both TX and RX clocks, so the skew should only be
* applied to "rgmii-id" interfaces. It may not work as expected
* on "rgmii-txid", "rgmii-rxid" or "rgmii" interfaces. */
.config_init = &vsc8601_config_init,
.ack_interrupt = &vsc824x_ack_interrupt,
.config_intr = &vsc82xx_config_intr,
+}, {
+ .phy_id = PHY_ID_VSC7385,
+ .name = "Vitesse VSC7385",
+ .phy_id_mask = 0x000ffff0,
+ .features = PHY_GBIT_FEATURES,
+ .config_init = vsc738x_config_init,
+ .config_aneg = vsc73xx_config_aneg,
+ .read_page = vsc73xx_read_page,
+ .write_page = vsc73xx_write_page,
+}, {
+ .phy_id = PHY_ID_VSC7388,
+ .name = "Vitesse VSC7388",
+ .phy_id_mask = 0x000ffff0,
+ .features = PHY_GBIT_FEATURES,
+ .config_init = vsc738x_config_init,
+ .config_aneg = vsc73xx_config_aneg,
+ .read_page = vsc73xx_read_page,
+ .write_page = vsc73xx_write_page,
+}, {
+ .phy_id = PHY_ID_VSC7395,
+ .name = "Vitesse VSC7395",
+ .phy_id_mask = 0x000ffff0,
+ .features = PHY_GBIT_FEATURES,
+ .config_init = vsc739x_config_init,
+ .config_aneg = vsc73xx_config_aneg,
+ .read_page = vsc73xx_read_page,
+ .write_page = vsc73xx_write_page,
+}, {
+ .phy_id = PHY_ID_VSC7398,
+ .name = "Vitesse VSC7398",
+ .phy_id_mask = 0x000ffff0,
+ .features = PHY_GBIT_FEATURES,
+ .config_init = vsc739x_config_init,
+ .config_aneg = vsc73xx_config_aneg,
+ .read_page = vsc73xx_read_page,
+ .write_page = vsc73xx_write_page,
}, {
.phy_id = PHY_ID_VSC8662,
.name = "Vitesse VSC8662",
{ PHY_ID_VSC8514, 0x000ffff0 },
{ PHY_ID_VSC8572, 0x000ffff0 },
{ PHY_ID_VSC8574, 0x000ffff0 },
+ { PHY_ID_VSC7385, 0x000ffff0 },
+ { PHY_ID_VSC7388, 0x000ffff0 },
+ { PHY_ID_VSC7395, 0x000ffff0 },
+ { PHY_ID_VSC7398, 0x000ffff0 },
{ PHY_ID_VSC8662, 0x000ffff0 },
{ PHY_ID_VSC8221, 0x000ffff0 },
{ PHY_ID_VSC8211, 0x000ffff0 },
struct phy_device *phy_dev;
struct phy_driver *phy_drv;
struct phy_driver conv_phy_drv;
- int addr;
+ struct mdio_device *mdio;
};
static int xgmiitorgmii_read_status(struct phy_device *phydev)
{
struct gmii2rgmii *priv = phydev->priv;
+ struct mii_bus *bus = priv->mdio->bus;
+ int addr = priv->mdio->addr;
u16 val = 0;
+ int err;
- priv->phy_drv->read_status(phydev);
+ err = priv->phy_drv->read_status(phydev);
+ if (err < 0)
+ return err;
- val = mdiobus_read(phydev->mdio.bus, priv->addr, XILINX_GMII2RGMII_REG);
+ val = mdiobus_read(bus, addr, XILINX_GMII2RGMII_REG);
val &= ~XILINX_GMII2RGMII_SPEED_MASK;
if (phydev->speed == SPEED_1000)
else
val |= BMCR_SPEED10;
- mdiobus_write(phydev->mdio.bus, priv->addr, XILINX_GMII2RGMII_REG, val);
+ mdiobus_write(bus, addr, XILINX_GMII2RGMII_REG, val);
return 0;
}
return -EPROBE_DEFER;
}
- priv->addr = mdiodev->addr;
+ if (!priv->phy_dev->drv) {
+ dev_info(dev, "Attached phy not ready\n");
+ return -EPROBE_DEFER;
+ }
+
+ priv->mdio = mdiodev;
priv->phy_drv = priv->phy_dev->drv;
memcpy(&priv->conv_phy_drv, priv->phy_dev->drv,
sizeof(struct phy_driver));
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = pppoe_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.setsockopt = sock_no_setsockopt,
#define team_port_exists(dev) (dev->priv_flags & IFF_TEAM_PORT)
-static struct team_port *team_port_get_rcu(const struct net_device *dev)
-{
- return rcu_dereference(dev->rx_handler_data);
-}
-
static struct team_port *team_port_get_rtnl(const struct net_device *dev)
{
struct team_port *port = rtnl_dereference(dev->rx_handler_data);
}
static u16 team_select_queue(struct net_device *dev, struct sk_buff *skb,
- void *accel_priv, select_queue_fallback_t fallback)
+ struct net_device *sb_dev,
+ select_queue_fallback_t fallback)
{
/*
* This helper function exists to help dev_pick_tx get the correct
}
static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb,
- void *accel_priv, select_queue_fallback_t fallback)
+ struct net_device *sb_dev,
+ select_queue_fallback_t fallback)
{
struct tun_struct *tun = netdev_priv(dev);
u16 ret;
return tun_xdp_set(dev, xdp->prog, xdp->extack);
case XDP_QUERY_PROG:
xdp->prog_id = tun_xdp_query(dev);
- xdp->prog_attached = !!xdp->prog_id;
return 0;
default:
return -EINVAL;
u32 phyid;
struct asix_common_private *priv;
- usbnet_get_endpoints(dev,intf);
+ usbnet_get_endpoints(dev, intf);
- /* Get the MAC address */
- if (dev->driver_info->data & FLAG_EEPROM_MAC) {
- for (i = 0; i < (ETH_ALEN >> 1); i++) {
- ret = asix_read_cmd(dev, AX_CMD_READ_EEPROM, 0x04 + i,
- 0, 2, buf + i * 2, 0);
- if (ret < 0)
- break;
- }
+ /* Maybe the boot loader passed the MAC address via device tree */
+ if (!eth_platform_get_mac_address(&dev->udev->dev, buf)) {
+ netif_dbg(dev, ifup, dev->net,
+ "MAC address read from device tree");
} else {
- ret = asix_read_cmd(dev, AX_CMD_READ_NODE_ID,
- 0, 0, ETH_ALEN, buf, 0);
- }
+ /* Try getting the MAC address from EEPROM */
+ if (dev->driver_info->data & FLAG_EEPROM_MAC) {
+ for (i = 0; i < (ETH_ALEN >> 1); i++) {
+ ret = asix_read_cmd(dev, AX_CMD_READ_EEPROM,
+ 0x04 + i, 0, 2, buf + i * 2,
+ 0);
+ if (ret < 0)
+ break;
+ }
+ } else {
+ ret = asix_read_cmd(dev, AX_CMD_READ_NODE_ID,
+ 0, 0, ETH_ALEN, buf, 0);
+ }
- if (ret < 0) {
- netdev_dbg(dev->net, "Failed to read MAC address: %d\n", ret);
- return ret;
+ if (ret < 0) {
+ netdev_dbg(dev->net, "Failed to read MAC address: %d\n",
+ ret);
+ return ret;
+ }
}
asix_set_netdev_dev_addr(dev, buf);
default:
dev_warn(&intf->dev,
"Couldn't detect memory size, assuming 32k\n");
+ /* fall through */
case 0x87654321:
catc_set_reg(catc, TxBufCount, 4);
catc_set_reg(catc, RxBufCount, 16);
struct net_device *dev = skb->dev;
struct usbpn_dev *pnd = netdev_priv(dev);
int status = req->status;
+ unsigned long flags;
switch (status) {
case 0:
case -ECONNRESET:
case -ESHUTDOWN:
dev->stats.tx_aborted_errors++;
+ /* fall through */
default:
dev->stats.tx_errors++;
dev_dbg(&dev->dev, "TX error (%d)\n", status);
}
dev->stats.tx_packets++;
- spin_lock(&pnd->tx_lock);
+ spin_lock_irqsave(&pnd->tx_lock, flags);
pnd->tx_queue--;
netif_wake_queue(dev);
- spin_unlock(&pnd->tx_lock);
+ spin_unlock_irqrestore(&pnd->tx_lock, flags);
dev_kfree_skb_any(skb);
usb_free_urb(req);
atomic_set(&ctx->stop, 1);
- if (hrtimer_active(&ctx->tx_timer))
- hrtimer_cancel(&ctx->tx_timer);
+ hrtimer_cancel(&ctx->tx_timer);
tasklet_kill(&ctx->bh);
struct hso_net *odev = urb->context;
struct net_device *net;
int result;
+ unsigned long flags;
int status = urb->status;
/* is al ok? (Filip: Who's Al ?) */
if (urb->actual_length) {
/* Handle the IP stream, add header and push it onto network
* stack if the packet is complete. */
- spin_lock(&odev->net_lock);
+ spin_lock_irqsave(&odev->net_lock, flags);
packetizeRx(odev, urb->transfer_buffer, urb->actual_length,
(urb->transfer_buffer_length >
urb->actual_length) ? 1 : 0);
- spin_unlock(&odev->net_lock);
+ spin_unlock_irqrestore(&odev->net_lock, flags);
}
/* We are done with this URB, resubmit it. Prep the USB to wait for
{
struct hso_serial *serial = urb->context;
int status = urb->status;
+ unsigned long flags;
hso_dbg(0x8, "--- Got serial_read_bulk callback %02x ---\n", status);
if (serial->parent->port_spec & HSO_INFO_CRC_BUG)
fix_crc_bug(urb, serial->in_endp->wMaxPacketSize);
/* Valid data, handle RX data */
- spin_lock(&serial->serial_lock);
+ spin_lock_irqsave(&serial->serial_lock, flags);
serial->rx_urb_filled[hso_urb_to_index(serial, urb)] = 1;
put_rxbuf_data_and_resubmit_bulk_urb(serial);
- spin_unlock(&serial->serial_lock);
+ spin_unlock_irqrestore(&serial->serial_lock, flags);
}
/*
DUMP(serial_state_notification,
sizeof(struct hso_serial_state_notification));
} else {
+ unsigned long flags;
UART_state_bitmap = le16_to_cpu(serial_state_notification->
UART_state_bitmap);
prev_UART_state_bitmap = tiocmget->prev_UART_state_bitmap;
icount = &tiocmget->icount;
- spin_lock(&serial->serial_lock);
+ spin_lock_irqsave(&serial->serial_lock, flags);
if ((UART_state_bitmap & B_OVERRUN) !=
(prev_UART_state_bitmap & B_OVERRUN))
icount->parity++;
(prev_UART_state_bitmap & B_RX_CARRIER))
icount->dcd++;
tiocmget->prev_UART_state_bitmap = UART_state_bitmap;
- spin_unlock(&serial->serial_lock);
+ spin_unlock_irqrestore(&serial->serial_lock, flags);
tiocmget->intr_completed = 1;
wake_up_interruptible(&tiocmget->waitq);
}
/* starts a transmit */
static void hso_kick_transmit(struct hso_serial *serial)
{
- u8 *temp;
unsigned long flags;
int res;
goto out;
/* Switch pointers around to avoid memcpy */
- temp = serial->tx_buffer;
- serial->tx_buffer = serial->tx_data;
- serial->tx_data = temp;
+ swap(serial->tx_buffer, serial->tx_data);
serial->tx_data_count = serial->tx_buffer_count;
serial->tx_buffer_count = 0;
- /* If temp is set, it means we switched buffers */
- if (temp && serial->write_data) {
+ /* If serial->tx_data is set, it means we switched buffers */
+ if (serial->tx_data && serial->write_data) {
res = serial->write_data(serial);
if (res >= 0)
serial->tx_urb_used = 1;
struct hso_serial *serial;
unsigned char *port_req;
int status = urb->status;
+ unsigned long flags;
int i;
usb_mark_last_busy(urb->dev);
if (serial != NULL) {
hso_dbg(0x1, "Pending read interrupt on port %d\n",
i);
- spin_lock(&serial->serial_lock);
+ spin_lock_irqsave(&serial->serial_lock, flags);
if (serial->rx_state == RX_IDLE &&
serial->port.count > 0) {
/* Setup and send a ctrl req read on
hso_dbg(0x1, "Already a read pending on port %d or port not open\n",
i);
}
- spin_unlock(&serial->serial_lock);
+ spin_unlock_irqrestore(&serial->serial_lock,
+ flags);
}
}
}
{
struct hso_serial *serial = urb->context;
int status = urb->status;
+ unsigned long flags;
/* sanity check */
if (!serial) {
return;
}
- spin_lock(&serial->serial_lock);
+ spin_lock_irqsave(&serial->serial_lock, flags);
serial->tx_urb_used = 0;
- spin_unlock(&serial->serial_lock);
+ spin_unlock_irqrestore(&serial->serial_lock, flags);
if (status) {
handle_usb_error(status, __func__, serial->parent);
return;
struct hso_serial *serial = urb->context;
struct usb_ctrlrequest *req;
int status = urb->status;
+ unsigned long flags;
/* sanity check */
if (!serial)
return;
- spin_lock(&serial->serial_lock);
+ spin_lock_irqsave(&serial->serial_lock, flags);
serial->tx_urb_used = 0;
- spin_unlock(&serial->serial_lock);
+ spin_unlock_irqrestore(&serial->serial_lock, flags);
if (status) {
handle_usb_error(status, __func__, serial->parent);
return;
(USB_DIR_IN | USB_TYPE_OPTION_VENDOR | USB_RECIP_INTERFACE)) {
/* response to a read command */
serial->rx_urb_filled[0] = 1;
- spin_lock(&serial->serial_lock);
+ spin_lock_irqsave(&serial->serial_lock, flags);
put_rxbuf_data_and_resubmit_ctrl_urb(serial);
- spin_unlock(&serial->serial_lock);
+ spin_unlock_irqrestore(&serial->serial_lock, flags);
} else {
hso_put_activity(serial->parent);
tty_port_tty_wakeup(&serial->port);
struct kaweth_device *kaweth = urb->context;
struct net_device *net = kaweth->net;
int status = urb->status;
-
+ unsigned long flags;
int count = urb->actual_length;
int count2 = urb->transfer_buffer_length;
net->stats.rx_errors++;
dev_dbg(dev, "Status was -EOVERFLOW.\n");
}
- spin_lock(&kaweth->device_lock);
+ spin_lock_irqsave(&kaweth->device_lock, flags);
if (IS_BLOCKED(kaweth->status)) {
- spin_unlock(&kaweth->device_lock);
+ spin_unlock_irqrestore(&kaweth->device_lock, flags);
return;
}
- spin_unlock(&kaweth->device_lock);
+ spin_unlock_irqrestore(&kaweth->device_lock, flags);
if(status && status != -EREMOTEIO && count != 1) {
dev_err(&kaweth->intf->dev,
#define DEFAULT_RX_CSUM_ENABLE (true)
#define DEFAULT_TSO_CSUM_ENABLE (true)
#define DEFAULT_VLAN_FILTER_ENABLE (true)
+#define DEFAULT_VLAN_RX_OFFLOAD (true)
#define TX_OVERHEAD (8)
#define RXW_PADDING 2
"MAC address read from EEPROM");
} else {
/* generate random MAC */
- random_ether_addr(addr);
+ eth_random_addr(addr);
netif_dbg(dev, ifup, dev->net,
"MAC address set to random addr");
}
if ((ll_mtu % dev->maxpacket) == 0)
return -EDOM;
- ret = lan78xx_set_rx_max_frame_length(dev, new_mtu + ETH_HLEN);
+ ret = lan78xx_set_rx_max_frame_length(dev, new_mtu + VLAN_ETH_HLEN);
netdev->mtu = new_mtu;
}
if (features & NETIF_F_HW_VLAN_CTAG_RX)
+ pdata->rfe_ctl |= RFE_CTL_VLAN_STRIP_;
+ else
+ pdata->rfe_ctl &= ~RFE_CTL_VLAN_STRIP_;
+
+ if (features & NETIF_F_HW_VLAN_CTAG_FILTER)
pdata->rfe_ctl |= RFE_CTL_VLAN_FILTER_;
else
pdata->rfe_ctl &= ~RFE_CTL_VLAN_FILTER_;
buf |= FCT_TX_CTL_EN_;
ret = lan78xx_write_reg(dev, FCT_TX_CTL, buf);
- ret = lan78xx_set_rx_max_frame_length(dev, dev->net->mtu + ETH_HLEN);
+ ret = lan78xx_set_rx_max_frame_length(dev,
+ dev->net->mtu + VLAN_ETH_HLEN);
ret = lan78xx_read_reg(dev, MAC_RX, &buf);
buf |= MAC_RX_RXEN_;
if (DEFAULT_TSO_CSUM_ENABLE)
dev->net->features |= NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_SG;
+ if (DEFAULT_VLAN_RX_OFFLOAD)
+ dev->net->features |= NETIF_F_HW_VLAN_CTAG_RX;
+
+ if (DEFAULT_VLAN_FILTER_ENABLE)
+ dev->net->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
+
dev->net->hw_features = dev->net->features;
ret = lan78xx_setup_irq_domain(dev);
struct sk_buff *skb,
u32 rx_cmd_a, u32 rx_cmd_b)
{
+ /* HW Checksum offload appears to be flawed if used when not stripping
+ * VLAN headers. Drop back to S/W checksums under these conditions.
+ */
if (!(dev->net->features & NETIF_F_RXCSUM) ||
- unlikely(rx_cmd_a & RX_CMD_A_ICSM_)) {
+ unlikely(rx_cmd_a & RX_CMD_A_ICSM_) ||
+ ((rx_cmd_a & RX_CMD_A_FVTG_) &&
+ !(dev->net->features & NETIF_F_HW_VLAN_CTAG_RX))) {
skb->ip_summed = CHECKSUM_NONE;
} else {
skb->csum = ntohs((u16)(rx_cmd_b >> RX_CMD_B_CSUM_SHIFT_));
}
}
+static void lan78xx_rx_vlan_offload(struct lan78xx_net *dev,
+ struct sk_buff *skb,
+ u32 rx_cmd_a, u32 rx_cmd_b)
+{
+ if ((dev->net->features & NETIF_F_HW_VLAN_CTAG_RX) &&
+ (rx_cmd_a & RX_CMD_A_FVTG_))
+ __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
+ (rx_cmd_b & 0xffff));
+}
+
static void lan78xx_skb_return(struct lan78xx_net *dev, struct sk_buff *skb)
{
int status;
if (skb->len == size) {
lan78xx_rx_csum_offload(dev, skb,
rx_cmd_a, rx_cmd_b);
+ lan78xx_rx_vlan_offload(dev, skb,
+ rx_cmd_a, rx_cmd_b);
skb_trim(skb, skb->len - 4); /* remove fcs */
skb->truesize = size + sizeof(struct sk_buff);
skb_set_tail_pointer(skb2, size);
lan78xx_rx_csum_offload(dev, skb2, rx_cmd_a, rx_cmd_b);
+ lan78xx_rx_vlan_offload(dev, skb2, rx_cmd_a, rx_cmd_b);
skb_trim(skb2, skb2->len - 4); /* remove fcs */
skb2->truesize = size + sizeof(struct sk_buff);
{QMI_FIXED_INTF(0x413c, 0x81b3, 8)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */
{QMI_FIXED_INTF(0x413c, 0x81b6, 8)}, /* Dell Wireless 5811e */
{QMI_FIXED_INTF(0x413c, 0x81b6, 10)}, /* Dell Wireless 5811e */
+ {QMI_FIXED_INTF(0x413c, 0x81d7, 1)}, /* Dell Wireless 5821e */
{QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)}, /* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */
{QMI_FIXED_INTF(0x03f0, 0x9d1d, 1)}, /* HP lt4120 Snapdragon X5 LTE */
{QMI_FIXED_INTF(0x22de, 0x9061, 3)}, /* WeTelecom WPD-600N */
int status = urb->status;
struct rx_agg *agg;
struct r8152 *tp;
+ unsigned long flags;
agg = urb->context;
if (!agg)
if (urb->actual_length < ETH_ZLEN)
break;
- spin_lock(&tp->rx_lock);
+ spin_lock_irqsave(&tp->rx_lock, flags);
list_add_tail(&agg->list, &tp->rx_done);
- spin_unlock(&tp->rx_lock);
+ spin_unlock_irqrestore(&tp->rx_lock, flags);
napi_schedule(&tp->napi);
return;
case -ESHUTDOWN:
struct net_device *netdev;
struct tx_agg *agg;
struct r8152 *tp;
+ unsigned long flags;
int status = urb->status;
agg = urb->context;
stats->tx_bytes += agg->skb_len;
}
- spin_lock(&tp->tx_lock);
+ spin_lock_irqsave(&tp->tx_lock, flags);
list_add_tail(&agg->list, &tp->tx_free);
- spin_unlock(&tp->tx_lock);
+ spin_unlock_irqrestore(&tp->tx_lock, flags);
usb_autopm_put_interface_async(tp->intf);
case -ECONNRESET: /* unlink */
case -ESHUTDOWN:
netif_device_detach(tp->netdev);
+ /* fall through */
case -ENOENT:
case -EPROTO:
netif_info(tp, intr, tp->netdev,
r8152_mdio_write(tp, MII_BMCR, data);
data = r8153_phy_status(tp, PHY_STAT_LAN_ON);
+ /* fall through */
default:
if (data != PHY_STAT_LAN_ON)
#ifdef CONFIG_PM_SLEEP
unregister_pm_notifier(&tp->pm_notifier);
#endif
- napi_disable(&tp->napi);
+ if (!test_bit(RTL8152_UNPLUG, &tp->flags))
+ napi_disable(&tp->napi);
clear_bit(WORK_ENABLE, &tp->flags);
usb_kill_urb(tp->intr_urb);
cancel_delayed_work_sync(&tp->schedule);
u16 rx_stat;
int status = urb->status;
int result;
+ unsigned long flags;
dev = urb->context;
if (!dev)
netdev->stats.rx_packets++;
netdev->stats.rx_bytes += pkt_len;
- spin_lock(&dev->rx_pool_lock);
+ spin_lock_irqsave(&dev->rx_pool_lock, flags);
skb = pull_skb(dev);
- spin_unlock(&dev->rx_pool_lock);
+ spin_unlock_irqrestore(&dev->rx_pool_lock, flags);
if (!skb)
goto resched;
/* Amount of XDP headroom to prepend to packets for use by xdp_adjust_head */
#define VIRTIO_XDP_HEADROOM 256
+/* Separating two types of XDP xmit */
+#define VIRTIO_XDP_TX BIT(0)
+#define VIRTIO_XDP_REDIR BIT(1)
+
/* RX packet size EWMA. The average packet size is used to determine the packet
* buffer size when refilling RX rings. As the entire RX ring may be refilled
* at once, the weight is chosen so that the EWMA will be insensitive to short-
struct receive_queue *rq,
void *buf, void *ctx,
unsigned int len,
- bool *xdp_xmit)
+ unsigned int *xdp_xmit)
{
struct sk_buff *skb;
struct bpf_prog *xdp_prog;
trace_xdp_exception(vi->dev, xdp_prog, act);
goto err_xdp;
}
- *xdp_xmit = true;
+ *xdp_xmit |= VIRTIO_XDP_TX;
rcu_read_unlock();
goto xdp_xmit;
case XDP_REDIRECT:
err = xdp_do_redirect(dev, &xdp, xdp_prog);
if (err)
goto err_xdp;
- *xdp_xmit = true;
+ *xdp_xmit |= VIRTIO_XDP_REDIR;
rcu_read_unlock();
goto xdp_xmit;
default:
void *buf,
void *ctx,
unsigned int len,
- bool *xdp_xmit)
+ unsigned int *xdp_xmit)
{
struct virtio_net_hdr_mrg_rxbuf *hdr = buf;
u16 num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers);
put_page(xdp_page);
goto err_xdp;
}
- *xdp_xmit = true;
+ *xdp_xmit |= VIRTIO_XDP_TX;
if (unlikely(xdp_page != page))
put_page(page);
rcu_read_unlock();
put_page(xdp_page);
goto err_xdp;
}
- *xdp_xmit = true;
+ *xdp_xmit |= VIRTIO_XDP_REDIR;
if (unlikely(xdp_page != page))
put_page(page);
rcu_read_unlock();
}
static int receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
- void *buf, unsigned int len, void **ctx, bool *xdp_xmit)
+ void *buf, unsigned int len, void **ctx,
+ unsigned int *xdp_xmit)
{
struct net_device *dev = vi->dev;
struct sk_buff *skb;
}
}
-static int virtnet_receive(struct receive_queue *rq, int budget, bool *xdp_xmit)
+static int virtnet_receive(struct receive_queue *rq, int budget,
+ unsigned int *xdp_xmit)
{
struct virtnet_info *vi = rq->vq->vdev->priv;
unsigned int len, received = 0, bytes = 0;
struct virtnet_info *vi = rq->vq->vdev->priv;
struct send_queue *sq;
unsigned int received, qp;
- bool xdp_xmit = false;
+ unsigned int xdp_xmit = 0;
virtnet_poll_cleantx(rq);
if (received < budget)
virtqueue_napi_complete(napi, rq->vq, received);
- if (xdp_xmit) {
+ if (xdp_xmit & VIRTIO_XDP_REDIR)
+ xdp_do_flush_map();
+
+ if (xdp_xmit & VIRTIO_XDP_TX) {
qp = vi->curr_queue_pairs - vi->xdp_queue_pairs +
smp_processor_id();
sq = &vi->sq[qp];
virtqueue_kick(sq->vq);
- xdp_do_flush_map();
}
return received;
return virtnet_xdp_set(dev, xdp->prog, xdp->extack);
case XDP_QUERY_PROG:
xdp->prog_id = virtnet_xdp_query(dev);
- xdp->prog_attached = !!xdp->prog_id;
return 0;
default:
return -EINVAL;
return vh;
}
-static struct sk_buff **vxlan_gro_receive(struct sock *sk,
- struct sk_buff **head,
- struct sk_buff *skb)
+static struct sk_buff *vxlan_gro_receive(struct sock *sk,
+ struct list_head *head,
+ struct sk_buff *skb)
{
- struct sk_buff *p, **pp = NULL;
+ struct sk_buff *pp = NULL;
+ struct sk_buff *p;
struct vxlanhdr *vh, *vh2;
unsigned int hlen, off_vx;
int flush = 1;
skb_gro_pull(skb, sizeof(struct vxlanhdr)); /* pull vxlan header */
- for (p = *head; p; p = p->next) {
+ list_for_each_entry(p, head, list) {
if (!NAPI_GRO_CB(p)->same_flow)
continue;
flush = 0;
out:
- skb_gro_remcsum_cleanup(skb, &grc);
- skb->remcsum_offload = 0;
- NAPI_GRO_CB(skb)->flush |= flush;
+ skb_gro_flush_final_remcsum(skb, pp, flush, &grc);
return pp;
}
return eth_gro_complete(skb, nhoff + sizeof(struct vxlanhdr));
}
-/* Add new entry to forwarding table -- assumes lock held */
+static struct vxlan_fdb *vxlan_fdb_alloc(struct vxlan_dev *vxlan,
+ const u8 *mac, __u16 state,
+ __be32 src_vni, __u8 ndm_flags)
+{
+ struct vxlan_fdb *f;
+
+ f = kmalloc(sizeof(*f), GFP_ATOMIC);
+ if (!f)
+ return NULL;
+ f->state = state;
+ f->flags = ndm_flags;
+ f->updated = f->used = jiffies;
+ f->vni = src_vni;
+ INIT_LIST_HEAD(&f->remotes);
+ memcpy(f->eth_addr, mac, ETH_ALEN);
+
+ return f;
+}
+
static int vxlan_fdb_create(struct vxlan_dev *vxlan,
+ const u8 *mac, union vxlan_addr *ip,
+ __u16 state, __be16 port, __be32 src_vni,
+ __be32 vni, __u32 ifindex, __u8 ndm_flags,
+ struct vxlan_fdb **fdb)
+{
+ struct vxlan_rdst *rd = NULL;
+ struct vxlan_fdb *f;
+ int rc;
+
+ if (vxlan->cfg.addrmax &&
+ vxlan->addrcnt >= vxlan->cfg.addrmax)
+ return -ENOSPC;
+
+ netdev_dbg(vxlan->dev, "add %pM -> %pIS\n", mac, ip);
+ f = vxlan_fdb_alloc(vxlan, mac, state, src_vni, ndm_flags);
+ if (!f)
+ return -ENOMEM;
+
+ rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd);
+ if (rc < 0) {
+ kfree(f);
+ return rc;
+ }
+
+ ++vxlan->addrcnt;
+ hlist_add_head_rcu(&f->hlist,
+ vxlan_fdb_head(vxlan, mac, src_vni));
+
+ *fdb = f;
+
+ return 0;
+}
+
+/* Add new entry to forwarding table -- assumes lock held */
+static int vxlan_fdb_update(struct vxlan_dev *vxlan,
const u8 *mac, union vxlan_addr *ip,
__u16 state, __u16 flags,
__be16 port, __be32 src_vni, __be32 vni,
if (!(flags & NLM_F_CREATE))
return -ENOENT;
- if (vxlan->cfg.addrmax &&
- vxlan->addrcnt >= vxlan->cfg.addrmax)
- return -ENOSPC;
-
/* Disallow replace to add a multicast entry */
if ((flags & NLM_F_REPLACE) &&
(is_multicast_ether_addr(mac) || is_zero_ether_addr(mac)))
return -EOPNOTSUPP;
netdev_dbg(vxlan->dev, "add %pM -> %pIS\n", mac, ip);
- f = kmalloc(sizeof(*f), GFP_ATOMIC);
- if (!f)
- return -ENOMEM;
-
- notify = 1;
- f->state = state;
- f->flags = ndm_flags;
- f->updated = f->used = jiffies;
- f->vni = src_vni;
- INIT_LIST_HEAD(&f->remotes);
- memcpy(f->eth_addr, mac, ETH_ALEN);
-
- rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd);
- if (rc < 0) {
- kfree(f);
+ rc = vxlan_fdb_create(vxlan, mac, ip, state, port, src_vni,
+ vni, ifindex, ndm_flags, &f);
+ if (rc < 0)
return rc;
- }
-
- ++vxlan->addrcnt;
- hlist_add_head_rcu(&f->hlist,
- vxlan_fdb_head(vxlan, mac, src_vni));
+ notify = 1;
}
if (notify) {
kfree(f);
}
-static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f)
+static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f,
+ bool do_notify)
{
netdev_dbg(vxlan->dev,
"delete %pM\n", f->eth_addr);
--vxlan->addrcnt;
- vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_DELNEIGH);
+ if (do_notify)
+ vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_DELNEIGH);
hlist_del_rcu(&f->hlist);
call_rcu(&f->rcu, vxlan_fdb_free);
return -EAFNOSUPPORT;
spin_lock_bh(&vxlan->hash_lock);
- err = vxlan_fdb_create(vxlan, addr, &ip, ndm->ndm_state, flags,
+ err = vxlan_fdb_update(vxlan, addr, &ip, ndm->ndm_state, flags,
port, src_vni, vni, ifindex, ndm->ndm_flags);
spin_unlock_bh(&vxlan->hash_lock);
goto out;
}
- vxlan_fdb_destroy(vxlan, f);
+ vxlan_fdb_destroy(vxlan, f, true);
out:
return 0;
/* close off race between vxlan_flush and incoming packets */
if (netif_running(dev))
- vxlan_fdb_create(vxlan, src_mac, src_ip,
+ vxlan_fdb_update(vxlan, src_mac, src_ip,
NUD_REACHABLE,
NLM_F_EXCL|NLM_F_CREATE,
vxlan->cfg.dst_port,
vni = tunnel_id_to_key32(info->key.tun_id);
ifindex = 0;
dst_cache = &info->dst_cache;
- if (info->options_len)
+ if (info->options_len &&
+ info->key.tun_flags & TUNNEL_VXLAN_OPT)
md = ip_tunnel_info_opts(info);
ttl = info->key.ttl;
tos = info->key.tos;
"garbage collect %pM\n",
f->eth_addr);
f->state = NUD_STALE;
- vxlan_fdb_destroy(vxlan, f);
+ vxlan_fdb_destroy(vxlan, f, true);
} else if (time_before(timeout, next_timer))
next_timer = timeout;
}
spin_lock_bh(&vxlan->hash_lock);
f = __vxlan_find_mac(vxlan, all_zeros_mac, vni);
if (f)
- vxlan_fdb_destroy(vxlan, f);
+ vxlan_fdb_destroy(vxlan, f, true);
spin_unlock_bh(&vxlan->hash_lock);
}
continue;
/* the all_zeros_mac entry is deleted at vxlan_uninit */
if (!is_zero_ether_addr(f->eth_addr))
- vxlan_fdb_destroy(vxlan, f);
+ vxlan_fdb_destroy(vxlan, f, true);
}
}
spin_unlock_bh(&vxlan->hash_lock);
{
struct vxlan_net *vn = net_generic(net, vxlan_net_id);
struct vxlan_dev *vxlan = netdev_priv(dev);
+ struct vxlan_fdb *f = NULL;
int err;
err = vxlan_dev_configure(net, dev, conf, false, extack);
err = vxlan_fdb_create(vxlan, all_zeros_mac,
&vxlan->default_dst.remote_ip,
NUD_REACHABLE | NUD_PERMANENT,
- NLM_F_EXCL | NLM_F_CREATE,
vxlan->cfg.dst_port,
vxlan->default_dst.remote_vni,
vxlan->default_dst.remote_vni,
vxlan->default_dst.remote_ifindex,
- NTF_SELF);
+ NTF_SELF, &f);
if (err)
return err;
}
err = register_netdevice(dev);
+ if (err)
+ goto errout;
+
+ err = rtnl_configure_link(dev, NULL);
if (err) {
- vxlan_fdb_delete_default(vxlan, vxlan->default_dst.remote_vni);
- return err;
+ unregister_netdevice(dev);
+ goto errout;
}
+ /* notify default fdb entry */
+ if (f)
+ vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH);
+
list_add(&vxlan->next, &vn->vxlan_list);
return 0;
+errout:
+ if (f)
+ vxlan_fdb_destroy(vxlan, f, false);
+ return err;
}
static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[],
struct vxlan_rdst *dst = &vxlan->default_dst;
struct vxlan_rdst old_dst;
struct vxlan_config conf;
+ struct vxlan_fdb *f = NULL;
int err;
err = vxlan_nl2conf(tb, data,
err = vxlan_fdb_create(vxlan, all_zeros_mac,
&dst->remote_ip,
NUD_REACHABLE | NUD_PERMANENT,
- NLM_F_CREATE | NLM_F_APPEND,
vxlan->cfg.dst_port,
dst->remote_vni,
dst->remote_vni,
dst->remote_ifindex,
- NTF_SELF);
+ NTF_SELF, &f);
if (err) {
spin_unlock_bh(&vxlan->hash_lock);
return err;
}
+ vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH);
}
spin_unlock_bh(&vxlan->hash_lock);
}
fst_openport(struct fst_port_info *port)
{
int signals;
- int txq_length;
/* Only init things if card is actually running. This allows open to
* succeed for downloads etc.
else
netif_carrier_off(port_to_dev(port));
- txq_length = port->txqe - port->txqs;
port->txqe = 0;
port->txqs = 0;
}
lmc_softc_t *sc = dev_to_sc(dev);
int i;
int rx_work_limit = LMC_RXDESCS;
- unsigned int next_rx;
int rxIntLoopCnt; /* debug -baz */
int localLengthErrCnt = 0;
long stat;
rxIntLoopCnt = 0; /* debug -baz */
i = sc->lmc_next_rx % LMC_RXDESCS;
- next_rx = sc->lmc_next_rx;
while (((stat = sc->lmc_rxring[i].status) & LMC_RDES_OWN_BIT) != DESC_OWNED_BY_DC21X4)
{
{
int result;
struct device *dev = i2400m_dev(i2400m);
- unsigned ack_type, ack_status;
+ unsigned int ack_type;
char strerr[32];
/* Chew on the message, we might need some information from
* here */
ack_type = le16_to_cpu(l3l4_hdr->type);
- ack_status = le16_to_cpu(l3l4_hdr->status);
switch (ack_type) {
case I2400M_MT_CMD_ENTER_POWERSAVE:
/* This is just left here for the sake of example, as
int ret, itr;
struct device *dev = i2400m_dev(i2400m);
struct i2400m_fw *i2400m_fw;
- const struct i2400m_bcf_hdr *bcf; /* Firmware data */
const struct firmware *fw;
const char *fw_name;
}
/* Load firmware files to memory. */
- for (itr = 0, bcf = NULL, ret = -ENOENT; ; itr++) {
+ for (itr = 0, ret = -ENOENT; ; itr++) {
fw_name = i2400m->bus_fw_names[itr];
if (fw_name == NULL) {
dev_err(dev, "Could not find a usable firmware image\n");
{
struct net_device *net_dev = i2400m->wimax_dev.net_dev;
struct device *dev = i2400m_dev(i2400m);
- int protocol;
d_fnstart(2, dev, "(i2400m %p skb %p [%u] cs %d)\n",
i2400m, skb, skb->len, cs);
switch(cs) {
case I2400M_CS_IPV4_0:
case I2400M_CS_IPV4:
- protocol = ETH_P_IP;
i2400m_rx_fake_eth_header(i2400m->wimax_dev.net_dev,
skb->data - ETH_HLEN,
cpu_to_be16(ETH_P_IP));
ath_err(common, "eeprom contains invalid mac address: %pM\n",
common->macaddr);
- random_ether_addr(common->macaddr);
+ eth_random_addr(common->macaddr);
ath_err(common, "random mac address will be used: %pM\n",
common->macaddr);
bool "PCIE bus interface support for FullMAC driver"
depends on BRCMFMAC
depends on PCI
- depends on HAS_DMA
select BRCMFMAC_PROTO_MSGBUF
select FW_LOADER
---help---
static u16
mwifiex_netdev_select_wmm_queue(struct net_device *dev, struct sk_buff *skb,
- void *accel_priv, select_queue_fallback_t fallback)
+ struct net_device *sb_dev,
+ select_queue_fallback_t fallback)
{
skb->priority = cfg80211_classify8021d(skb, NULL);
return mwifiex_1d_to_wmm_queue[skb->priority];
config QTNFMAC_PEARL_PCIE
tristate "Quantenna QSR10g PCIe support"
default n
- depends on HAS_DMA && PCI && CFG80211
+ depends on PCI && CFG80211
select QTNFMAC
select FW_LOADER
select CRC32
reject_agg, ctrl_agg_size, agg_size);
rtlpriv->hw->max_rx_aggregation_subframes =
- (ctrl_agg_size ? agg_size : IEEE80211_MAX_AMPDU_BUF);
+ (ctrl_agg_size ? agg_size : IEEE80211_MAX_AMPDU_BUF_HT);
}
EXPORT_SYMBOL(rtl_rx_ampdu_apply);
}
static u16 xenvif_select_queue(struct net_device *dev, struct sk_buff *skb,
- void *accel_priv,
+ struct net_device *sb_dev,
select_queue_fallback_t fallback)
{
struct xenvif *vif = netdev_priv(dev);
unsigned int size = vif->hash.size;
if (vif->hash.alg == XEN_NETIF_CTRL_HASH_ALGORITHM_NONE)
- return fallback(dev, skb) % dev->real_num_tx_queues;
+ return fallback(dev, skb, NULL) % dev->real_num_tx_queues;
xenvif_set_skb_hash(vif, skb);
}
static u16 xennet_select_queue(struct net_device *dev, struct sk_buff *skb,
- void *accel_priv, select_queue_fallback_t fallback)
+ struct net_device *sb_dev,
+ select_queue_fallback_t fallback)
{
unsigned int num_queues = dev->real_num_tx_queues;
u32 hash;
err = xen_net_read_mac(dev, info->netdev->dev_addr);
if (err) {
xenbus_dev_fatal(dev, err, "parsing %s/mac", dev->nodename);
- goto out;
+ goto out_unlocked;
}
rtnl_lock();
xennet_destroy_queues(info);
out:
rtnl_unlock();
+out_unlocked:
device_unregister(&dev->dev);
return err;
}
/* talk_to_netback() sets the correct number of queues */
num_queues = dev->real_num_tx_queues;
- rtnl_lock();
- netdev_update_features(dev);
- rtnl_unlock();
-
if (dev->reg_state == NETREG_UNINITIALIZED) {
err = register_netdev(dev);
if (err) {
}
}
+ rtnl_lock();
+ netdev_update_features(dev);
+ rtnl_unlock();
+
/*
* All public and private state should now be sane. Get
* ready to start sending and receiving packets and give the driver
struct sk_buff *skb = NULL;
if (!urb->status) {
- skb = alloc_skb(urb->actual_length, GFP_KERNEL);
+ skb = alloc_skb(urb->actual_length, GFP_ATOMIC);
if (!skb) {
nfc_err(&phy->udev->dev, "failed to alloc memory\n");
} else {
if (dev->protocol_type == PN533_PROTO_REQ_RESP) {
/* request for response for sent packet directly */
- rc = pn533_submit_urb_for_response(phy, GFP_ATOMIC);
+ rc = pn533_submit_urb_for_response(phy, GFP_KERNEL);
if (rc)
goto error;
} else if (dev->protocol_type == PN533_PROTO_REQ_ACK_RESP) {
blk_queue_logical_block_size(q, pmem_sector_size(ndns));
blk_queue_max_hw_sectors(q, UINT_MAX);
blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
- blk_queue_flag_set(QUEUE_FLAG_DAX, q);
+ if (pmem->pfn_flags & PFN_MAP)
+ blk_queue_flag_set(QUEUE_FLAG_DAX, q);
q->queuedata = pmem;
disk = alloc_disk_node(0, nid);
u32 max_segments =
(ctrl->max_hw_sectors / (ctrl->page_size >> 9)) + 1;
+ max_segments = min_not_zero(max_segments, ctrl->max_segments);
blk_queue_max_hw_sectors(q, ctrl->max_hw_sectors);
blk_queue_max_segments(q, min_t(u32, max_segments, USHRT_MAX));
}
/* re-enable the admin_q so anything new can fast fail */
blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
+ /* resume the io queues so that things will fast fail */
+ nvme_start_queues(&ctrl->ctrl);
+
nvme_fc_ctlr_inactive_on_rport(ctrl);
}
* waiting for io to terminate
*/
nvme_fc_delete_association(ctrl);
-
- /* resume the io queues so that things will fast fail */
- nvme_start_queues(nctrl);
}
static void
u64 cap;
u32 page_size;
u32 max_hw_sectors;
+ u32 max_segments;
u16 oncs;
u16 oacs;
u16 nssa;
#define SGES_PER_PAGE (PAGE_SIZE / sizeof(struct nvme_sgl_desc))
+/*
+ * These can be higher, but we need to ensure that any command doesn't
+ * require an sg allocation that needs more than a page of data.
+ */
+#define NVME_MAX_KB_SZ 4096
+#define NVME_MAX_SEGS 127
+
static int use_threaded_interrupts;
module_param(use_threaded_interrupts, int, 0);
struct nvme_ctrl ctrl;
struct completion ioq_wait;
+ mempool_t *iod_mempool;
+
/* shadow doorbell buffer support: */
u32 *dbbuf_dbs;
dma_addr_t dbbuf_dbs_dma_addr;
iod->use_sgl = nvme_pci_use_sgls(dev, rq);
if (nseg > NVME_INT_PAGES || size > NVME_INT_BYTES(dev)) {
- size_t alloc_size = nvme_pci_iod_alloc_size(dev, size, nseg,
- iod->use_sgl);
-
- iod->sg = kmalloc(alloc_size, GFP_ATOMIC);
+ iod->sg = mempool_alloc(dev->iod_mempool, GFP_ATOMIC);
if (!iod->sg)
return BLK_STS_RESOURCE;
} else {
}
if (iod->sg != iod->inline_sg)
- kfree(iod->sg);
+ mempool_free(iod->sg, dev->iod_mempool);
}
#ifdef CONFIG_BLK_DEV_INTEGRITY
blk_put_queue(dev->ctrl.admin_q);
kfree(dev->queues);
free_opal_dev(dev->ctrl.opal_dev);
+ mempool_destroy(dev->iod_mempool);
kfree(dev);
}
nvme_get_ctrl(&dev->ctrl);
nvme_dev_disable(dev, false);
+ nvme_kill_queues(&dev->ctrl);
if (!queue_work(nvme_wq, &dev->remove_work))
nvme_put_ctrl(&dev->ctrl);
}
if (result)
goto out;
+ /*
+ * Limit the max command size to prevent iod->sg allocations going
+ * over a single page.
+ */
+ dev->ctrl.max_hw_sectors = NVME_MAX_KB_SZ << 1;
+ dev->ctrl.max_segments = NVME_MAX_SEGS;
+
result = nvme_init_identify(&dev->ctrl);
if (result)
goto out;
struct nvme_dev *dev = container_of(work, struct nvme_dev, remove_work);
struct pci_dev *pdev = to_pci_dev(dev->dev);
- nvme_kill_queues(&dev->ctrl);
if (pci_get_drvdata(pdev))
device_release_driver(&pdev->dev);
nvme_put_ctrl(&dev->ctrl);
int node, result = -ENOMEM;
struct nvme_dev *dev;
unsigned long quirks = id->driver_data;
+ size_t alloc_size;
node = dev_to_node(&pdev->dev);
if (node == NUMA_NO_NODE)
if (result)
goto release_pools;
+ /*
+ * Double check that our mempool alloc size will cover the biggest
+ * command we support.
+ */
+ alloc_size = nvme_pci_iod_alloc_size(dev, NVME_MAX_KB_SZ,
+ NVME_MAX_SEGS, true);
+ WARN_ON_ONCE(alloc_size > PAGE_SIZE);
+
+ dev->iod_mempool = mempool_create_node(1, mempool_kmalloc,
+ mempool_kfree,
+ (void *) alloc_size,
+ GFP_KERNEL, node);
+ if (!dev->iod_mempool) {
+ result = -ENOMEM;
+ goto release_pools;
+ }
+
dev_info(dev->ctrl.device, "pci function %s\n", dev_name(&pdev->dev));
nvme_get_ctrl(&dev->ctrl);
if (!test_and_clear_bit(NVME_RDMA_Q_ALLOCATED, &queue->flags))
return;
- if (nvme_rdma_queue_idx(queue) == 0) {
- nvme_rdma_free_qe(queue->device->dev,
- &queue->ctrl->async_event_sqe,
- sizeof(struct nvme_command), DMA_TO_DEVICE);
- }
-
nvme_rdma_destroy_queue_ib(queue);
rdma_destroy_id(queue->cm_id);
}
set = &ctrl->tag_set;
memset(set, 0, sizeof(*set));
set->ops = &nvme_rdma_mq_ops;
- set->queue_depth = nctrl->opts->queue_size;
+ set->queue_depth = nctrl->sqsize + 1;
set->reserved_tags = 1; /* fabric connect */
set->numa_node = NUMA_NO_NODE;
set->flags = BLK_MQ_F_SHOULD_MERGE;
static void nvme_rdma_destroy_admin_queue(struct nvme_rdma_ctrl *ctrl,
bool remove)
{
- nvme_rdma_stop_queue(&ctrl->queues[0]);
if (remove) {
blk_cleanup_queue(ctrl->ctrl.admin_q);
nvme_rdma_free_tagset(&ctrl->ctrl, ctrl->ctrl.admin_tagset);
}
+ if (ctrl->async_event_sqe.data) {
+ nvme_rdma_free_qe(ctrl->device->dev, &ctrl->async_event_sqe,
+ sizeof(struct nvme_command), DMA_TO_DEVICE);
+ ctrl->async_event_sqe.data = NULL;
+ }
nvme_rdma_free_queue(&ctrl->queues[0]);
}
ctrl->max_fr_pages = nvme_rdma_get_max_fr_pages(ctrl->device->dev);
+ error = nvme_rdma_alloc_qe(ctrl->device->dev, &ctrl->async_event_sqe,
+ sizeof(struct nvme_command), DMA_TO_DEVICE);
+ if (error)
+ goto out_free_queue;
+
if (new) {
ctrl->ctrl.admin_tagset = nvme_rdma_alloc_tagset(&ctrl->ctrl, true);
if (IS_ERR(ctrl->ctrl.admin_tagset)) {
error = PTR_ERR(ctrl->ctrl.admin_tagset);
- goto out_free_queue;
+ goto out_free_async_qe;
}
ctrl->ctrl.admin_q = blk_mq_init_queue(&ctrl->admin_tag_set);
if (error)
goto out_stop_queue;
- error = nvme_rdma_alloc_qe(ctrl->queues[0].device->dev,
- &ctrl->async_event_sqe, sizeof(struct nvme_command),
- DMA_TO_DEVICE);
- if (error)
- goto out_stop_queue;
-
return 0;
out_stop_queue:
out_free_tagset:
if (new)
nvme_rdma_free_tagset(&ctrl->ctrl, ctrl->ctrl.admin_tagset);
+out_free_async_qe:
+ nvme_rdma_free_qe(ctrl->device->dev, &ctrl->async_event_sqe,
+ sizeof(struct nvme_command), DMA_TO_DEVICE);
out_free_queue:
nvme_rdma_free_queue(&ctrl->queues[0]);
return error;
static void nvme_rdma_destroy_io_queues(struct nvme_rdma_ctrl *ctrl,
bool remove)
{
- nvme_rdma_stop_io_queues(ctrl);
if (remove) {
blk_cleanup_queue(ctrl->ctrl.connect_q);
nvme_rdma_free_tagset(&ctrl->ctrl, ctrl->ctrl.tagset);
list_del(&ctrl->list);
mutex_unlock(&nvme_rdma_ctrl_mutex);
- kfree(ctrl->queues);
nvmf_free_options(nctrl->opts);
free_ctrl:
+ kfree(ctrl->queues);
kfree(ctrl);
}
return;
destroy_admin:
+ nvme_rdma_stop_queue(&ctrl->queues[0]);
nvme_rdma_destroy_admin_queue(ctrl, false);
requeue:
dev_info(ctrl->ctrl.device, "Failed reconnect attempt %d\n",
if (ctrl->ctrl.queue_count > 1) {
nvme_stop_queues(&ctrl->ctrl);
+ nvme_rdma_stop_io_queues(ctrl);
blk_mq_tagset_busy_iter(&ctrl->tag_set,
nvme_cancel_request, &ctrl->ctrl);
nvme_rdma_destroy_io_queues(ctrl, false);
}
blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
+ nvme_rdma_stop_queue(&ctrl->queues[0]);
blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
nvme_cancel_request, &ctrl->ctrl);
nvme_rdma_destroy_admin_queue(ctrl, false);
{
if (ctrl->ctrl.queue_count > 1) {
nvme_stop_queues(&ctrl->ctrl);
+ nvme_rdma_stop_io_queues(ctrl);
blk_mq_tagset_busy_iter(&ctrl->tag_set,
nvme_cancel_request, &ctrl->ctrl);
nvme_rdma_destroy_io_queues(ctrl, shutdown);
nvme_disable_ctrl(&ctrl->ctrl, ctrl->ctrl.cap);
blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
+ nvme_rdma_stop_queue(&ctrl->queues[0]);
blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
nvme_cancel_request, &ctrl->ctrl);
blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
goto out_free_ctrl;
}
- ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_rdma_ctrl_ops,
- 0 /* no quirks, we're perfect! */);
- if (ret)
- goto out_free_ctrl;
-
INIT_DELAYED_WORK(&ctrl->reconnect_work,
nvme_rdma_reconnect_ctrl_work);
INIT_WORK(&ctrl->err_work, nvme_rdma_error_recovery_work);
ctrl->queues = kcalloc(ctrl->ctrl.queue_count, sizeof(*ctrl->queues),
GFP_KERNEL);
if (!ctrl->queues)
- goto out_uninit_ctrl;
+ goto out_free_ctrl;
+
+ ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_rdma_ctrl_ops,
+ 0 /* no quirks, we're perfect! */);
+ if (ret)
+ goto out_kfree_queues;
changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING);
WARN_ON_ONCE(!changed);
ret = nvme_rdma_configure_admin_queue(ctrl, true);
if (ret)
- goto out_kfree_queues;
+ goto out_uninit_ctrl;
/* sanity check icdoff */
if (ctrl->ctrl.icdoff) {
goto out_remove_admin_queue;
}
- if (opts->queue_size > ctrl->ctrl.maxcmd) {
- /* warn if maxcmd is lower than queue_size */
- dev_warn(ctrl->ctrl.device,
- "queue_size %zu > ctrl maxcmd %u, clamping down\n",
- opts->queue_size, ctrl->ctrl.maxcmd);
- opts->queue_size = ctrl->ctrl.maxcmd;
- }
-
+ /* only warn if argument is too large here, will clamp later */
if (opts->queue_size > ctrl->ctrl.sqsize + 1) {
- /* warn if sqsize is lower than queue_size */
dev_warn(ctrl->ctrl.device,
"queue_size %zu > ctrl sqsize %u, clamping down\n",
opts->queue_size, ctrl->ctrl.sqsize + 1);
- opts->queue_size = ctrl->ctrl.sqsize + 1;
+ }
+
+ /* warn if maxcmd is lower than sqsize+1 */
+ if (ctrl->ctrl.sqsize + 1 > ctrl->ctrl.maxcmd) {
+ dev_warn(ctrl->ctrl.device,
+ "sqsize %u > ctrl maxcmd %u, clamping down\n",
+ ctrl->ctrl.sqsize + 1, ctrl->ctrl.maxcmd);
+ ctrl->ctrl.sqsize = ctrl->ctrl.maxcmd - 1;
}
if (opts->nr_io_queues) {
return &ctrl->ctrl;
out_remove_admin_queue:
+ nvme_rdma_stop_queue(&ctrl->queues[0]);
nvme_rdma_destroy_admin_queue(ctrl, true);
-out_kfree_queues:
- kfree(ctrl->queues);
out_uninit_ctrl:
nvme_uninit_ctrl(&ctrl->ctrl);
nvme_put_ctrl(&ctrl->ctrl);
if (ret > 0)
ret = -EIO;
return ERR_PTR(ret);
+out_kfree_queues:
+ kfree(ctrl->queues);
out_free_ctrl:
kfree(ctrl);
return ERR_PTR(ret);
}
ctrl->csts = NVME_CSTS_RDY;
+
+ /*
+ * Controllers that are not yet enabled should not really enforce the
+ * keep alive timeout, but we still want to track a timeout and cleanup
+ * in case a host died before it enabled the controller. Hence, simply
+ * reset the keep alive timer when the controller is enabled.
+ */
+ mod_delayed_work(system_wq, &ctrl->ka_work, ctrl->kato * HZ);
}
static void nvmet_clear_ctrl(struct nvmet_ctrl *ctrl)
phy_interface_t iface;
struct device_node *phy_np;
struct phy_device *phy;
+ int ret;
iface = of_get_phy_mode(np);
if (iface < 0)
return NULL;
-
- phy_np = of_parse_phandle(np, "phy-handle", 0);
- if (!phy_np)
- return NULL;
+ if (of_phy_is_fixed_link(np)) {
+ ret = of_phy_register_fixed_link(np);
+ if (ret < 0) {
+ netdev_err(dev, "broken fixed-link specification\n");
+ return NULL;
+ }
+ phy_np = of_node_get(np);
+ } else {
+ phy_np = of_parse_phandle(np, "phy-handle", 0);
+ if (!phy_np)
+ return NULL;
+ }
phy = of_phy_connect(dev, phy_np, hndlr, 0, iface);
}
/* Scaling up? Scale voltage before frequency */
- if (freq > old_freq) {
+ if (freq >= old_freq) {
ret = _set_opp_voltage(dev, reg, new_supply);
if (ret)
goto restore_voltage;
obj-$(CONFIG_PCI_ECAM) += ecam.o
obj-$(CONFIG_XEN_PCIDEV_FRONTEND) += xen-pcifront.o
-obj-y += controller/
-obj-y += switch/
-
# Endpoint library must be initialized before its users
obj-$(CONFIG_PCI_ENDPOINT) += endpoint/
+obj-y += controller/
+obj-y += switch/
+
ccflags-$(CONFIG_PCI_DEBUG) := -DDEBUG
depends on OF
select PCI_HOST_COMMON
select IRQ_DOMAIN
- select PCI_DOMAINS
help
Say Y here if you want to support a simple generic PCI host
controller, such as the one emulated by kvmtool.
config PCIE_IPROC
tristate
- select PCI_DOMAINS
help
This enables the iProc PCIe core controller support for Broadcom's
iProc family of SoCs. An appropriate bus interface driver needs
config PCIE_ALTERA
bool "Altera PCIe controller"
depends on ARM || NIOS2 || COMPILE_TEST
- select PCI_DOMAINS
help
Say Y here if you want to enable PCIe controller support on Altera
FPGA.
* All rights reserved.
*
* Send feedback to <kristen.c.accardi@intel.com>
- *
*/
#include <linux/module.h>
return 0;
/* If _OSC exists, we should not evaluate OSHP */
+
+ /*
+ * If there's no ACPI host bridge (i.e., ACPI support is compiled
+ * into the kernel but the hardware platform doesn't support ACPI),
+ * there's nothing to do here.
+ */
host = pci_find_host_bridge(pdev->bus);
root = acpi_pci_find_root(ACPI_HANDLE(&host->dev));
+ if (!root)
+ return 0;
+
if (root->osc_support_set)
goto no_control;
case PMU_TYPE_IOB:
return devm_kasprintf(dev, GFP_KERNEL, "iob%d", id);
case PMU_TYPE_IOB_SLOW:
- return devm_kasprintf(dev, GFP_KERNEL, "iob-slow%d", id);
+ return devm_kasprintf(dev, GFP_KERNEL, "iob_slow%d", id);
case PMU_TYPE_MCB:
return devm_kasprintf(dev, GFP_KERNEL, "mcb%d", id);
case PMU_TYPE_MC:
unsigned long flags;
unsigned int param;
u32 reg, bit, width, arg;
- int ret, i;
+ int ret = 0, i;
info = &pctrl->soc->padinfo[pin];
}
static int dt_to_map_one_config(struct pinctrl *p,
- struct pinctrl_dev *pctldev,
+ struct pinctrl_dev *hog_pctldev,
const char *statename,
struct device_node *np_config)
{
+ struct pinctrl_dev *pctldev = NULL;
struct device_node *np_pctldev;
const struct pinctrl_ops *ops;
int ret;
return -EPROBE_DEFER;
}
/* If we're creating a hog we can use the passed pctldev */
- if (pctldev && (np_pctldev == p->dev->of_node))
+ if (hog_pctldev && (np_pctldev == p->dev->of_node)) {
+ pctldev = hog_pctldev;
break;
+ }
pctldev = get_pinctrl_dev_from_of_node(np_pctldev);
if (pctldev)
break;
struct mtk_pinctrl *hw = gpiochip_get_data(chip);
unsigned long eint_n;
+ if (!hw->eint)
+ return -ENOTSUPP;
+
eint_n = offset;
return mtk_eint_find_irq(hw->eint, eint_n);
unsigned long eint_n;
u32 debounce;
- if (pinconf_to_config_param(config) != PIN_CONFIG_INPUT_DEBOUNCE)
+ if (!hw->eint ||
+ pinconf_to_config_param(config) != PIN_CONFIG_INPUT_DEBOUNCE)
return -ENOTSUPP;
debounce = pinconf_to_config_argument(config);
return -ENOMEM;
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- if (!res) {
- dev_err(&pdev->dev, "Unable to get eint resource\n");
- return -ENODEV;
- }
-
pctl->eint->base = devm_ioremap_resource(&pdev->dev, res);
if (IS_ERR(pctl->eint->base))
return PTR_ERR(pctl->eint->base);
mux_bytes = pcs->width / BITS_PER_BYTE;
- if (!pcs->saved_vals)
+ if (!pcs->saved_vals) {
pcs->saved_vals = devm_kzalloc(pcs->dev, pcs->size, GFP_ATOMIC);
+ if (!pcs->saved_vals)
+ return -ENOMEM;
+ }
switch (pcs->width) {
case 64:
if (!pcs)
return -EINVAL;
- if (pcs->flags & PCS_CONTEXT_LOSS_OFF)
- pcs_save_context(pcs);
+ if (pcs->flags & PCS_CONTEXT_LOSS_OFF) {
+ int ret;
+
+ ret = pcs_save_context(pcs);
+ if (ret < 0)
+ return ret;
+ }
return pinctrl_force_sleep(pcs->pctl);
}
config PTP_1588_CLOCK_QORIQ
tristate "Freescale QorIQ 1588 timer as PTP clock"
- depends on GIANFAR
+ depends on GIANFAR || FSL_DPAA_ETH
depends on PTP_1588_CLOCK
default y
help
}
pct = &sysoff->ts[0];
for (i = 0; i < sysoff->n_samples; i++) {
- getnstimeofday64(&ts);
+ ktime_get_real_ts64(&ts);
pct->sec = ts.tv_sec;
pct->nsec = ts.tv_nsec;
pct++;
pct->nsec = ts.tv_nsec;
pct++;
}
- getnstimeofday64(&ts);
+ ktime_get_real_ts64(&ts);
pct->sec = ts.tv_sec;
pct->nsec = ts.tv_nsec;
if (copy_to_user((void __user *)arg, sysoff, sizeof(*sysoff)))
/* Caller must hold qoriq_ptp->lock. */
static u64 tmr_cnt_read(struct qoriq_ptp *qoriq_ptp)
{
+ struct qoriq_ptp_registers *regs = &qoriq_ptp->regs;
u64 ns;
u32 lo, hi;
- lo = qoriq_read(&qoriq_ptp->regs->tmr_cnt_l);
- hi = qoriq_read(&qoriq_ptp->regs->tmr_cnt_h);
+ lo = qoriq_read(®s->ctrl_regs->tmr_cnt_l);
+ hi = qoriq_read(®s->ctrl_regs->tmr_cnt_h);
ns = ((u64) hi) << 32;
ns |= lo;
return ns;
/* Caller must hold qoriq_ptp->lock. */
static void tmr_cnt_write(struct qoriq_ptp *qoriq_ptp, u64 ns)
{
+ struct qoriq_ptp_registers *regs = &qoriq_ptp->regs;
u32 hi = ns >> 32;
u32 lo = ns & 0xffffffff;
- qoriq_write(&qoriq_ptp->regs->tmr_cnt_l, lo);
- qoriq_write(&qoriq_ptp->regs->tmr_cnt_h, hi);
+ qoriq_write(®s->ctrl_regs->tmr_cnt_l, lo);
+ qoriq_write(®s->ctrl_regs->tmr_cnt_h, hi);
}
/* Caller must hold qoriq_ptp->lock. */
static void set_alarm(struct qoriq_ptp *qoriq_ptp)
{
+ struct qoriq_ptp_registers *regs = &qoriq_ptp->regs;
u64 ns;
u32 lo, hi;
ns -= qoriq_ptp->tclk_period;
hi = ns >> 32;
lo = ns & 0xffffffff;
- qoriq_write(&qoriq_ptp->regs->tmr_alarm1_l, lo);
- qoriq_write(&qoriq_ptp->regs->tmr_alarm1_h, hi);
+ qoriq_write(®s->alarm_regs->tmr_alarm1_l, lo);
+ qoriq_write(®s->alarm_regs->tmr_alarm1_h, hi);
}
/* Caller must hold qoriq_ptp->lock. */
static void set_fipers(struct qoriq_ptp *qoriq_ptp)
{
+ struct qoriq_ptp_registers *regs = &qoriq_ptp->regs;
+
set_alarm(qoriq_ptp);
- qoriq_write(&qoriq_ptp->regs->tmr_fiper1, qoriq_ptp->tmr_fiper1);
- qoriq_write(&qoriq_ptp->regs->tmr_fiper2, qoriq_ptp->tmr_fiper2);
+ qoriq_write(®s->fiper_regs->tmr_fiper1, qoriq_ptp->tmr_fiper1);
+ qoriq_write(®s->fiper_regs->tmr_fiper2, qoriq_ptp->tmr_fiper2);
}
/*
static irqreturn_t isr(int irq, void *priv)
{
struct qoriq_ptp *qoriq_ptp = priv;
+ struct qoriq_ptp_registers *regs = &qoriq_ptp->regs;
struct ptp_clock_event event;
u64 ns;
u32 ack = 0, lo, hi, mask, val;
- val = qoriq_read(&qoriq_ptp->regs->tmr_tevent);
+ val = qoriq_read(®s->ctrl_regs->tmr_tevent);
if (val & ETS1) {
ack |= ETS1;
- hi = qoriq_read(&qoriq_ptp->regs->tmr_etts1_h);
- lo = qoriq_read(&qoriq_ptp->regs->tmr_etts1_l);
+ hi = qoriq_read(®s->etts_regs->tmr_etts1_h);
+ lo = qoriq_read(®s->etts_regs->tmr_etts1_l);
event.type = PTP_CLOCK_EXTTS;
event.index = 0;
event.timestamp = ((u64) hi) << 32;
if (val & ETS2) {
ack |= ETS2;
- hi = qoriq_read(&qoriq_ptp->regs->tmr_etts2_h);
- lo = qoriq_read(&qoriq_ptp->regs->tmr_etts2_l);
+ hi = qoriq_read(®s->etts_regs->tmr_etts2_h);
+ lo = qoriq_read(®s->etts_regs->tmr_etts2_l);
event.type = PTP_CLOCK_EXTTS;
event.index = 1;
event.timestamp = ((u64) hi) << 32;
hi = ns >> 32;
lo = ns & 0xffffffff;
spin_lock(&qoriq_ptp->lock);
- qoriq_write(&qoriq_ptp->regs->tmr_alarm2_l, lo);
- qoriq_write(&qoriq_ptp->regs->tmr_alarm2_h, hi);
+ qoriq_write(®s->alarm_regs->tmr_alarm2_l, lo);
+ qoriq_write(®s->alarm_regs->tmr_alarm2_h, hi);
spin_unlock(&qoriq_ptp->lock);
qoriq_ptp->alarm_value = ns;
} else {
- qoriq_write(&qoriq_ptp->regs->tmr_tevent, ALM2);
+ qoriq_write(®s->ctrl_regs->tmr_tevent, ALM2);
spin_lock(&qoriq_ptp->lock);
- mask = qoriq_read(&qoriq_ptp->regs->tmr_temask);
+ mask = qoriq_read(®s->ctrl_regs->tmr_temask);
mask &= ~ALM2EN;
- qoriq_write(&qoriq_ptp->regs->tmr_temask, mask);
+ qoriq_write(®s->ctrl_regs->tmr_temask, mask);
spin_unlock(&qoriq_ptp->lock);
qoriq_ptp->alarm_value = 0;
qoriq_ptp->alarm_interval = 0;
}
if (ack) {
- qoriq_write(&qoriq_ptp->regs->tmr_tevent, ack);
+ qoriq_write(®s->ctrl_regs->tmr_tevent, ack);
return IRQ_HANDLED;
} else
return IRQ_NONE;
u32 tmr_add;
int neg_adj = 0;
struct qoriq_ptp *qoriq_ptp = container_of(ptp, struct qoriq_ptp, caps);
+ struct qoriq_ptp_registers *regs = &qoriq_ptp->regs;
if (scaled_ppm < 0) {
neg_adj = 1;
tmr_add = neg_adj ? tmr_add - diff : tmr_add + diff;
- qoriq_write(&qoriq_ptp->regs->tmr_add, tmr_add);
+ qoriq_write(®s->ctrl_regs->tmr_add, tmr_add);
return 0;
}
struct ptp_clock_request *rq, int on)
{
struct qoriq_ptp *qoriq_ptp = container_of(ptp, struct qoriq_ptp, caps);
+ struct qoriq_ptp_registers *regs = &qoriq_ptp->regs;
unsigned long flags;
u32 bit, mask;
return -EINVAL;
}
spin_lock_irqsave(&qoriq_ptp->lock, flags);
- mask = qoriq_read(&qoriq_ptp->regs->tmr_temask);
+ mask = qoriq_read(®s->ctrl_regs->tmr_temask);
if (on)
mask |= bit;
else
mask &= ~bit;
- qoriq_write(&qoriq_ptp->regs->tmr_temask, mask);
+ qoriq_write(®s->ctrl_regs->tmr_temask, mask);
spin_unlock_irqrestore(&qoriq_ptp->lock, flags);
return 0;
case PTP_CLK_REQ_PPS:
spin_lock_irqsave(&qoriq_ptp->lock, flags);
- mask = qoriq_read(&qoriq_ptp->regs->tmr_temask);
+ mask = qoriq_read(®s->ctrl_regs->tmr_temask);
if (on)
mask |= PP1EN;
else
mask &= ~PP1EN;
- qoriq_write(&qoriq_ptp->regs->tmr_temask, mask);
+ qoriq_write(®s->ctrl_regs->tmr_temask, mask);
spin_unlock_irqrestore(&qoriq_ptp->lock, flags);
return 0;
{
struct device_node *node = dev->dev.of_node;
struct qoriq_ptp *qoriq_ptp;
+ struct qoriq_ptp_registers *regs;
struct timespec64 now;
int err = -ENOMEM;
u32 tmr_ctrl;
unsigned long flags;
+ void __iomem *base;
qoriq_ptp = kzalloc(sizeof(*qoriq_ptp), GFP_KERNEL);
if (!qoriq_ptp)
pr_err("irq not in device tree\n");
goto no_node;
}
- if (request_irq(qoriq_ptp->irq, isr, 0, DRIVER, qoriq_ptp)) {
+ if (request_irq(qoriq_ptp->irq, isr, IRQF_SHARED, DRIVER, qoriq_ptp)) {
pr_err("request_irq failed\n");
goto no_node;
}
spin_lock_init(&qoriq_ptp->lock);
- qoriq_ptp->regs = ioremap(qoriq_ptp->rsrc->start,
- resource_size(qoriq_ptp->rsrc));
- if (!qoriq_ptp->regs) {
+ base = ioremap(qoriq_ptp->rsrc->start,
+ resource_size(qoriq_ptp->rsrc));
+ if (!base) {
pr_err("ioremap ptp registers failed\n");
goto no_ioremap;
}
- getnstimeofday64(&now);
+
+ qoriq_ptp->base = base;
+
+ if (of_device_is_compatible(node, "fsl,fman-ptp-timer")) {
+ qoriq_ptp->regs.ctrl_regs = base + FMAN_CTRL_REGS_OFFSET;
+ qoriq_ptp->regs.alarm_regs = base + FMAN_ALARM_REGS_OFFSET;
+ qoriq_ptp->regs.fiper_regs = base + FMAN_FIPER_REGS_OFFSET;
+ qoriq_ptp->regs.etts_regs = base + FMAN_ETTS_REGS_OFFSET;
+ } else {
+ qoriq_ptp->regs.ctrl_regs = base + CTRL_REGS_OFFSET;
+ qoriq_ptp->regs.alarm_regs = base + ALARM_REGS_OFFSET;
+ qoriq_ptp->regs.fiper_regs = base + FIPER_REGS_OFFSET;
+ qoriq_ptp->regs.etts_regs = base + ETTS_REGS_OFFSET;
+ }
+
+ ktime_get_real_ts64(&now);
ptp_qoriq_settime(&qoriq_ptp->caps, &now);
tmr_ctrl =
spin_lock_irqsave(&qoriq_ptp->lock, flags);
- qoriq_write(&qoriq_ptp->regs->tmr_ctrl, tmr_ctrl);
- qoriq_write(&qoriq_ptp->regs->tmr_add, qoriq_ptp->tmr_add);
- qoriq_write(&qoriq_ptp->regs->tmr_prsc, qoriq_ptp->tmr_prsc);
- qoriq_write(&qoriq_ptp->regs->tmr_fiper1, qoriq_ptp->tmr_fiper1);
- qoriq_write(&qoriq_ptp->regs->tmr_fiper2, qoriq_ptp->tmr_fiper2);
+ regs = &qoriq_ptp->regs;
+ qoriq_write(®s->ctrl_regs->tmr_ctrl, tmr_ctrl);
+ qoriq_write(®s->ctrl_regs->tmr_add, qoriq_ptp->tmr_add);
+ qoriq_write(®s->ctrl_regs->tmr_prsc, qoriq_ptp->tmr_prsc);
+ qoriq_write(®s->fiper_regs->tmr_fiper1, qoriq_ptp->tmr_fiper1);
+ qoriq_write(®s->fiper_regs->tmr_fiper2, qoriq_ptp->tmr_fiper2);
set_alarm(qoriq_ptp);
- qoriq_write(&qoriq_ptp->regs->tmr_ctrl, tmr_ctrl|FIPERST|RTPE|TE|FRD);
+ qoriq_write(®s->ctrl_regs->tmr_ctrl, tmr_ctrl|FIPERST|RTPE|TE|FRD);
spin_unlock_irqrestore(&qoriq_ptp->lock, flags);
return 0;
no_clock:
- iounmap(qoriq_ptp->regs);
+ iounmap(qoriq_ptp->base);
no_ioremap:
release_resource(qoriq_ptp->rsrc);
no_resource:
static int qoriq_ptp_remove(struct platform_device *dev)
{
struct qoriq_ptp *qoriq_ptp = platform_get_drvdata(dev);
+ struct qoriq_ptp_registers *regs = &qoriq_ptp->regs;
- qoriq_write(&qoriq_ptp->regs->tmr_temask, 0);
- qoriq_write(&qoriq_ptp->regs->tmr_ctrl, 0);
+ qoriq_write(®s->ctrl_regs->tmr_temask, 0);
+ qoriq_write(®s->ctrl_regs->tmr_ctrl, 0);
ptp_clock_unregister(qoriq_ptp->clock);
- iounmap(qoriq_ptp->regs);
+ iounmap(qoriq_ptp->base);
release_resource(qoriq_ptp->rsrc);
free_irq(qoriq_ptp->irq, qoriq_ptp);
kfree(qoriq_ptp);
static const struct of_device_id match_table[] = {
{ .compatible = "fsl,etsec-ptp" },
+ { .compatible = "fsl,fman-ptp-timer" },
{},
};
MODULE_DEVICE_TABLE(of, match_table);
device->hosts_dentry = pde;
}
-/*
- * Allocate memory for a channel program with 'cplength' channel
- * command words and 'datasize' additional space. There are two
- * variantes: 1) dasd_kmalloc_request uses kmalloc to get the needed
- * memory and 2) dasd_smalloc_request uses the static ccw memory
- * that gets allocated for each device.
- */
-struct dasd_ccw_req *dasd_kmalloc_request(int magic, int cplength,
- int datasize,
- struct dasd_device *device)
-{
- struct dasd_ccw_req *cqr;
-
- /* Sanity checks */
- BUG_ON(datasize > PAGE_SIZE ||
- (cplength*sizeof(struct ccw1)) > PAGE_SIZE);
-
- cqr = kzalloc(sizeof(struct dasd_ccw_req), GFP_ATOMIC);
- if (cqr == NULL)
- return ERR_PTR(-ENOMEM);
- cqr->cpaddr = NULL;
- if (cplength > 0) {
- cqr->cpaddr = kcalloc(cplength, sizeof(struct ccw1),
- GFP_ATOMIC | GFP_DMA);
- if (cqr->cpaddr == NULL) {
- kfree(cqr);
- return ERR_PTR(-ENOMEM);
- }
- }
- cqr->data = NULL;
- if (datasize > 0) {
- cqr->data = kzalloc(datasize, GFP_ATOMIC | GFP_DMA);
- if (cqr->data == NULL) {
- kfree(cqr->cpaddr);
- kfree(cqr);
- return ERR_PTR(-ENOMEM);
- }
- }
- cqr->magic = magic;
- set_bit(DASD_CQR_FLAGS_USE_ERP, &cqr->flags);
- dasd_get_device(device);
- return cqr;
-}
-EXPORT_SYMBOL(dasd_kmalloc_request);
-
-struct dasd_ccw_req *dasd_smalloc_request(int magic, int cplength,
- int datasize,
- struct dasd_device *device)
+struct dasd_ccw_req *dasd_smalloc_request(int magic, int cplength, int datasize,
+ struct dasd_device *device,
+ struct dasd_ccw_req *cqr)
{
unsigned long flags;
- struct dasd_ccw_req *cqr;
- char *data;
- int size;
+ char *data, *chunk;
+ int size = 0;
- size = (sizeof(struct dasd_ccw_req) + 7L) & -8L;
if (cplength > 0)
size += cplength * sizeof(struct ccw1);
if (datasize > 0)
size += datasize;
+ if (!cqr)
+ size += (sizeof(*cqr) + 7L) & -8L;
+
spin_lock_irqsave(&device->mem_lock, flags);
- cqr = (struct dasd_ccw_req *)
- dasd_alloc_chunk(&device->ccw_chunks, size);
+ data = chunk = dasd_alloc_chunk(&device->ccw_chunks, size);
spin_unlock_irqrestore(&device->mem_lock, flags);
- if (cqr == NULL)
+ if (!chunk)
return ERR_PTR(-ENOMEM);
- memset(cqr, 0, sizeof(struct dasd_ccw_req));
- data = (char *) cqr + ((sizeof(struct dasd_ccw_req) + 7L) & -8L);
- cqr->cpaddr = NULL;
+ if (!cqr) {
+ cqr = (void *) data;
+ data += (sizeof(*cqr) + 7L) & -8L;
+ }
+ memset(cqr, 0, sizeof(*cqr));
+ cqr->mem_chunk = chunk;
if (cplength > 0) {
- cqr->cpaddr = (struct ccw1 *) data;
- data += cplength*sizeof(struct ccw1);
- memset(cqr->cpaddr, 0, cplength*sizeof(struct ccw1));
+ cqr->cpaddr = data;
+ data += cplength * sizeof(struct ccw1);
+ memset(cqr->cpaddr, 0, cplength * sizeof(struct ccw1));
}
- cqr->data = NULL;
if (datasize > 0) {
cqr->data = data;
memset(cqr->data, 0, datasize);
}
EXPORT_SYMBOL(dasd_smalloc_request);
-/*
- * Free memory of a channel program. This function needs to free all the
- * idal lists that might have been created by dasd_set_cda and the
- * struct dasd_ccw_req itself.
- */
-void dasd_kfree_request(struct dasd_ccw_req *cqr, struct dasd_device *device)
-{
- struct ccw1 *ccw;
-
- /* Clear any idals used for the request. */
- ccw = cqr->cpaddr;
- do {
- clear_normalized_cda(ccw);
- } while (ccw++->flags & (CCW_FLAG_CC | CCW_FLAG_DC));
- kfree(cqr->cpaddr);
- kfree(cqr->data);
- kfree(cqr);
- dasd_put_device(device);
-}
-EXPORT_SYMBOL(dasd_kfree_request);
-
void dasd_sfree_request(struct dasd_ccw_req *cqr, struct dasd_device *device)
{
unsigned long flags;
spin_lock_irqsave(&device->mem_lock, flags);
- dasd_free_chunk(&device->ccw_chunks, cqr);
+ dasd_free_chunk(&device->ccw_chunks, cqr->mem_chunk);
spin_unlock_irqrestore(&device->mem_lock, flags);
dasd_put_device(device);
}
}
}
+static void __dasd_process_cqr(struct dasd_device *device,
+ struct dasd_ccw_req *cqr)
+{
+ char errorstring[ERRORLENGTH];
+
+ switch (cqr->status) {
+ case DASD_CQR_SUCCESS:
+ cqr->status = DASD_CQR_DONE;
+ break;
+ case DASD_CQR_ERROR:
+ cqr->status = DASD_CQR_NEED_ERP;
+ break;
+ case DASD_CQR_CLEARED:
+ cqr->status = DASD_CQR_TERMINATED;
+ break;
+ default:
+ /* internal error 12 - wrong cqr status*/
+ snprintf(errorstring, ERRORLENGTH, "12 %p %x02", cqr, cqr->status);
+ dev_err(&device->cdev->dev,
+ "An error occurred in the DASD device driver, "
+ "reason=%s\n", errorstring);
+ BUG();
+ }
+ if (cqr->callback)
+ cqr->callback(cqr, cqr->callback_data);
+}
+
/*
* the cqrs from the final queue are returned to the upper layer
* by setting a dasd_block state and calling the callback function
struct list_head *l, *n;
struct dasd_ccw_req *cqr;
struct dasd_block *block;
- void (*callback)(struct dasd_ccw_req *, void *data);
- void *callback_data;
- char errorstring[ERRORLENGTH];
list_for_each_safe(l, n, final_queue) {
cqr = list_entry(l, struct dasd_ccw_req, devlist);
list_del_init(&cqr->devlist);
block = cqr->block;
- callback = cqr->callback;
- callback_data = cqr->callback_data;
- if (block)
+ if (!block) {
+ __dasd_process_cqr(device, cqr);
+ } else {
spin_lock_bh(&block->queue_lock);
- switch (cqr->status) {
- case DASD_CQR_SUCCESS:
- cqr->status = DASD_CQR_DONE;
- break;
- case DASD_CQR_ERROR:
- cqr->status = DASD_CQR_NEED_ERP;
- break;
- case DASD_CQR_CLEARED:
- cqr->status = DASD_CQR_TERMINATED;
- break;
- default:
- /* internal error 12 - wrong cqr status*/
- snprintf(errorstring, ERRORLENGTH, "12 %p %x02", cqr, cqr->status);
- dev_err(&device->cdev->dev,
- "An error occurred in the DASD device driver, "
- "reason=%s\n", errorstring);
- BUG();
- }
- if (cqr->callback != NULL)
- (callback)(cqr, callback_data);
- if (block)
+ __dasd_process_cqr(device, cqr);
spin_unlock_bh(&block->queue_lock);
+ }
}
}
cqr->callback_data = req;
cqr->status = DASD_CQR_FILLED;
cqr->dq = dq;
- *((struct dasd_ccw_req **) blk_mq_rq_to_pdu(req)) = cqr;
blk_mq_start_request(req);
spin_lock(&block->queue_lock);
unsigned long flags;
int rc = 0;
- cqr = *((struct dasd_ccw_req **) blk_mq_rq_to_pdu(req));
+ cqr = blk_mq_rq_to_pdu(req);
if (!cqr)
return BLK_EH_DONE;
int rc;
block->tag_set.ops = &dasd_mq_ops;
- block->tag_set.cmd_size = sizeof(struct dasd_ccw_req *);
+ block->tag_set.cmd_size = sizeof(struct dasd_ccw_req);
block->tag_set.nr_hw_queues = DASD_NR_HW_QUEUES;
block->tag_set.queue_depth = DASD_MAX_LCU_DEV * DASD_REQ_PER_DEV;
block->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
struct ccw1 *ccw;
unsigned long *idaw;
- cqr = dasd_smalloc_request(magic, 1 /* RDC */, rdc_buffer_size, device);
+ cqr = dasd_smalloc_request(magic, 1 /* RDC */, rdc_buffer_size, device,
+ NULL);
if (IS_ERR(cqr)) {
/* internal error 13 - Allocating the RDC request failed*/
int rc;
unsigned long flags;
- cqr = dasd_kmalloc_request(DASD_ECKD_MAGIC, 1 /* PSF */ + 1 /* RSSD */,
+ cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1 /* PSF */ + 1 /* RSSD */,
(sizeof(struct dasd_psf_prssd_data)),
- device);
+ device, NULL);
if (IS_ERR(cqr))
return PTR_ERR(cqr);
cqr->startdev = device;
lcu->flags |= NEED_UAC_UPDATE;
spin_unlock_irqrestore(&lcu->lock, flags);
}
- dasd_kfree_request(cqr, cqr->memdev);
+ dasd_sfree_request(cqr, cqr->memdev);
return rc;
}
/* Build the request */
datasize = sizeof(struct dasd_diag_req) +
count*sizeof(struct dasd_diag_bio);
- cqr = dasd_smalloc_request(DASD_DIAG_MAGIC, 0, datasize, memdev);
+ cqr = dasd_smalloc_request(DASD_DIAG_MAGIC, 0, datasize, memdev,
+ blk_mq_rq_to_pdu(req));
if (IS_ERR(cqr))
return cqr;
}
cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1 /* RCD */,
0, /* use rcd_buf as data ara */
- device);
+ device, NULL);
if (IS_ERR(cqr)) {
DBF_DEV_EVENT(DBF_WARNING, device, "%s",
"Could not allocate RCD request");
cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1 /* PSF */ + 1 /* RSSD */,
(sizeof(struct dasd_psf_prssd_data) +
sizeof(struct dasd_rssd_features)),
- device);
+ device, NULL);
if (IS_ERR(cqr)) {
DBF_EVENT_DEVID(DBF_WARNING, device->cdev, "%s", "Could not "
"allocate initialization request");
cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1 /* PSF */ ,
sizeof(struct dasd_psf_ssc_data),
- device);
+ device, NULL);
if (IS_ERR(cqr)) {
DBF_DEV_EVENT(DBF_WARNING, device, "%s",
cplength = 8;
datasize = sizeof(struct DE_eckd_data) + 2*sizeof(struct LO_eckd_data);
- cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, cplength, datasize, device);
+ cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, cplength, datasize, device,
+ NULL);
if (IS_ERR(cqr))
return cqr;
ccw = cqr->cpaddr;
*/
itcw_size = itcw_calc_size(0, count, 0);
- cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 0, itcw_size, startdev);
+ cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 0, itcw_size, startdev,
+ NULL);
if (IS_ERR(cqr))
return cqr;
cplength += count;
cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, cplength, datasize,
- startdev);
+ startdev, NULL);
if (IS_ERR(cqr))
return cqr;
}
/* Allocate the format ccw request. */
fcp = dasd_smalloc_request(DASD_ECKD_MAGIC, cplength,
- datasize, startdev);
+ datasize, startdev, NULL);
if (IS_ERR(fcp))
return fcp;
}
/* Allocate the ccw request. */
cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, cplength, datasize,
- startdev);
+ startdev, blk_mq_rq_to_pdu(req));
if (IS_ERR(cqr))
return cqr;
ccw = cqr->cpaddr;
/* Allocate the ccw request. */
cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, cplength, datasize,
- startdev);
+ startdev, blk_mq_rq_to_pdu(req));
if (IS_ERR(cqr))
return cqr;
ccw = cqr->cpaddr;
/* Allocate the ccw request. */
itcw_size = itcw_calc_size(0, ctidaw, 0);
- cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 0, itcw_size, startdev);
+ cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 0, itcw_size, startdev,
+ blk_mq_rq_to_pdu(req));
if (IS_ERR(cqr))
return cqr;
/* Allocate the ccw request. */
cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, cplength,
- datasize, startdev);
+ datasize, startdev, blk_mq_rq_to_pdu(req));
if (IS_ERR(cqr))
return cqr;
return -EACCES;
useglobal = 0;
- cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1, 32, device);
+ cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1, 32, device, NULL);
if (IS_ERR(cqr)) {
mutex_lock(&dasd_reserve_mutex);
useglobal = 1;
return -EACCES;
useglobal = 0;
- cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1, 32, device);
+ cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1, 32, device, NULL);
if (IS_ERR(cqr)) {
mutex_lock(&dasd_reserve_mutex);
useglobal = 1;
return -EACCES;
useglobal = 0;
- cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1, 32, device);
+ cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1, 32, device, NULL);
if (IS_ERR(cqr)) {
mutex_lock(&dasd_reserve_mutex);
useglobal = 1;
useglobal = 0;
cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1,
- sizeof(struct dasd_snid_data), device);
+ sizeof(struct dasd_snid_data), device,
+ NULL);
if (IS_ERR(cqr)) {
mutex_lock(&dasd_reserve_mutex);
useglobal = 1;
cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1 /* PSF */ + 1 /* RSSD */,
(sizeof(struct dasd_psf_prssd_data) +
sizeof(struct dasd_rssd_perf_stats_t)),
- device);
+ device, NULL);
if (IS_ERR(cqr)) {
DBF_DEV_EVENT(DBF_WARNING, device, "%s",
"Could not allocate initialization request");
psf1 = psf_data[1];
/* setup CCWs for PSF + RSSD */
- cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 2 , 0, device);
+ cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 2, 0, device, NULL);
if (IS_ERR(cqr)) {
DBF_DEV_EVENT(DBF_WARNING, device, "%s",
"Could not allocate initialization request");
cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1 /* PSF */ + 1 /* RSSD */,
(sizeof(struct dasd_psf_prssd_data) +
sizeof(struct dasd_rssd_messages)),
- device);
+ device, NULL);
if (IS_ERR(cqr)) {
DBF_EVENT_DEVID(DBF_WARNING, device->cdev, "%s",
"Could not allocate read message buffer request");
cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1 /* PSF */ + 1 /* RSSD */,
sizeof(struct dasd_psf_prssd_data) + 1,
- device);
+ device, NULL);
if (IS_ERR(cqr)) {
DBF_EVENT_DEVID(DBF_WARNING, device->cdev, "%s",
"Could not allocate read message buffer request");
int rc;
cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1 /* PSF */ ,
- sizeof(struct dasd_psf_cuir_response),
- device);
+ sizeof(struct dasd_psf_cuir_response),
+ device, NULL);
if (IS_ERR(cqr)) {
DBF_DEV_EVENT(DBF_WARNING, device, "%s",
* is a new ccw in device->eer_cqr. Free the "old"
* snss request now.
*/
- dasd_kfree_request(cqr, device);
+ dasd_sfree_request(cqr, device);
}
/*
if (rc)
goto out;
- cqr = dasd_kmalloc_request(DASD_ECKD_MAGIC, 1 /* SNSS */,
- SNSS_DATA_SIZE, device);
+ cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1 /* SNSS */,
+ SNSS_DATA_SIZE, device, NULL);
if (IS_ERR(cqr)) {
rc = -ENOMEM;
cqr = NULL;
spin_unlock_irqrestore(get_ccwdev_lock(device->cdev), flags);
if (cqr)
- dasd_kfree_request(cqr, device);
+ dasd_sfree_request(cqr, device);
return rc;
}
in_use = test_and_clear_bit(DASD_FLAG_EER_IN_USE, &device->flags);
spin_unlock_irqrestore(get_ccwdev_lock(device->cdev), flags);
if (cqr && !in_use)
- dasd_kfree_request(cqr, device);
+ dasd_sfree_request(cqr, device);
}
/*
datasize = sizeof(struct DE_fba_data) +
nr_ccws * (sizeof(struct LO_fba_data) + sizeof(struct ccw1));
- cqr = dasd_smalloc_request(DASD_FBA_MAGIC, cplength, datasize, memdev);
+ cqr = dasd_smalloc_request(DASD_FBA_MAGIC, cplength, datasize, memdev,
+ blk_mq_rq_to_pdu(req));
if (IS_ERR(cqr))
return cqr;
datasize += (count - 1)*sizeof(struct LO_fba_data);
}
/* Allocate the ccw request. */
- cqr = dasd_smalloc_request(DASD_FBA_MAGIC, cplength, datasize, memdev);
+ cqr = dasd_smalloc_request(DASD_FBA_MAGIC, cplength, datasize, memdev,
+ blk_mq_rq_to_pdu(req));
if (IS_ERR(cqr))
return cqr;
ccw = cqr->cpaddr;
struct dasd_ccw_req {
unsigned int magic; /* Eye catcher */
+ int intrc; /* internal error, e.g. from start_IO */
struct list_head devlist; /* for dasd_device request queue */
struct list_head blocklist; /* for dasd_block request queue */
-
- /* Where to execute what... */
struct dasd_block *block; /* the originating block device */
struct dasd_device *memdev; /* the device used to allocate this */
struct dasd_device *startdev; /* device the request is started on */
struct dasd_device *basedev; /* base device if no block->base */
void *cpaddr; /* address of ccw or tcw */
+ short retries; /* A retry counter */
unsigned char cpmode; /* 0 = cmd mode, 1 = itcw */
char status; /* status of this request */
- short retries; /* A retry counter */
+ char lpm; /* logical path mask */
unsigned long flags; /* flags of this request */
struct dasd_queue *dq;
-
- /* ... and how */
unsigned long starttime; /* jiffies time of request start */
unsigned long expires; /* expiration period in jiffies */
- char lpm; /* logical path mask */
void *data; /* pointer to data area */
-
- /* these are important for recovering erroneous requests */
- int intrc; /* internal error, e.g. from start_IO */
struct irb irb; /* device status in case of an error */
struct dasd_ccw_req *refers; /* ERP-chain queueing. */
void *function; /* originating ERP action */
+ void *mem_chunk;
- /* these are for statistics only */
unsigned long buildclk; /* TOD-clock of request generation */
unsigned long startclk; /* TOD-clock of request start */
unsigned long stopclk; /* TOD-clock of request interrupt */
unsigned long endclk; /* TOD-clock of request termination */
- /* Callback that is called after reaching final status. */
void (*callback)(struct dasd_ccw_req *, void *data);
void *callback_data;
};
extern struct kmem_cache *dasd_page_cache;
struct dasd_ccw_req *
-dasd_kmalloc_request(int , int, int, struct dasd_device *);
-struct dasd_ccw_req *
-dasd_smalloc_request(int , int, int, struct dasd_device *);
-void dasd_kfree_request(struct dasd_ccw_req *, struct dasd_device *);
+dasd_smalloc_request(int, int, int, struct dasd_device *, struct dasd_ccw_req *);
void dasd_sfree_request(struct dasd_ccw_req *, struct dasd_device *);
void dasd_wakeup_cb(struct dasd_ccw_req *, void *);
-static inline int
-dasd_kmalloc_set_cda(struct ccw1 *ccw, void *cda, struct dasd_device *device)
-{
- return set_normalized_cda(ccw, cda);
-}
-
struct dasd_device *dasd_alloc_device(void);
void dasd_free_device(struct dasd_device *);
# The following is required for define_trace.h to find ./trace.h
CFLAGS_trace.o := -I$(src)
+CFLAGS_vfio_ccw_fsm.o := -I$(src)
obj-y += airq.o blacklist.o chsc.o cio.o css.o chp.o idset.o isc.o \
fcx.o itcw.o crw.o ccwreq.o trace.o ioasm.o
#define CCWCHAIN_LEN_MAX 256
struct pfn_array {
+ /* Starting guest physical I/O address. */
unsigned long pa_iova;
+ /* Array that stores PFNs of the pages need to pin. */
unsigned long *pa_iova_pfn;
+ /* Array that receives PFNs of the pages pinned. */
unsigned long *pa_pfn;
+ /* Number of pages pinned from @pa_iova. */
int pa_nr;
};
};
/*
- * pfn_array_pin() - pin user pages in memory
+ * pfn_array_alloc_pin() - alloc memory for PFNs, then pin user pages in memory
* @pa: pfn_array on which to perform the operation
* @mdev: the mediated device to perform pin/unpin operations
+ * @iova: target guest physical address
+ * @len: number of bytes that should be pinned from @iova
*
- * Attempt to pin user pages in memory.
+ * Attempt to allocate memory for PFNs, and pin user pages in memory.
*
* Usage of pfn_array:
- * @pa->pa_iova starting guest physical I/O address. Assigned by caller.
- * @pa->pa_iova_pfn array that stores PFNs of the pages need to pin. Allocated
- * by caller.
- * @pa->pa_pfn array that receives PFNs of the pages pinned. Allocated by
- * caller.
- * @pa->pa_nr number of pages from @pa->pa_iova to pin. Assigned by
- * caller.
- * number of pages pinned. Assigned by callee.
+ * We expect (pa_nr == 0) and (pa_iova_pfn == NULL), any field in
+ * this structure will be filled in by this function.
*
* Returns:
* Number of pages pinned on success.
- * If @pa->pa_nr is 0 or negative, returns 0.
+ * If @pa->pa_nr is not 0, or @pa->pa_iova_pfn is not NULL initially,
+ * returns -EINVAL.
* If no pages were pinned, returns -errno.
*/
-static int pfn_array_pin(struct pfn_array *pa, struct device *mdev)
-{
- int i, ret;
-
- if (pa->pa_nr <= 0) {
- pa->pa_nr = 0;
- return 0;
- }
-
- pa->pa_iova_pfn[0] = pa->pa_iova >> PAGE_SHIFT;
- for (i = 1; i < pa->pa_nr; i++)
- pa->pa_iova_pfn[i] = pa->pa_iova_pfn[i - 1] + 1;
-
- ret = vfio_pin_pages(mdev, pa->pa_iova_pfn, pa->pa_nr,
- IOMMU_READ | IOMMU_WRITE, pa->pa_pfn);
-
- if (ret > 0 && ret != pa->pa_nr) {
- vfio_unpin_pages(mdev, pa->pa_iova_pfn, ret);
- pa->pa_nr = 0;
- return 0;
- }
-
- return ret;
-}
-
-/* Unpin the pages before releasing the memory. */
-static void pfn_array_unpin_free(struct pfn_array *pa, struct device *mdev)
-{
- vfio_unpin_pages(mdev, pa->pa_iova_pfn, pa->pa_nr);
- pa->pa_nr = 0;
- kfree(pa->pa_iova_pfn);
-}
-
-/* Alloc memory for PFNs, then pin pages with them. */
static int pfn_array_alloc_pin(struct pfn_array *pa, struct device *mdev,
u64 iova, unsigned int len)
{
- int ret = 0;
+ int i, ret = 0;
if (!len)
return 0;
- if (pa->pa_nr)
+ if (pa->pa_nr || pa->pa_iova_pfn)
return -EINVAL;
pa->pa_iova = iova;
return -ENOMEM;
pa->pa_pfn = pa->pa_iova_pfn + pa->pa_nr;
- ret = pfn_array_pin(pa, mdev);
+ pa->pa_iova_pfn[0] = pa->pa_iova >> PAGE_SHIFT;
+ for (i = 1; i < pa->pa_nr; i++)
+ pa->pa_iova_pfn[i] = pa->pa_iova_pfn[i - 1] + 1;
- if (ret > 0)
- return ret;
- else if (!ret)
+ ret = vfio_pin_pages(mdev, pa->pa_iova_pfn, pa->pa_nr,
+ IOMMU_READ | IOMMU_WRITE, pa->pa_pfn);
+
+ if (ret < 0) {
+ goto err_out;
+ } else if (ret > 0 && ret != pa->pa_nr) {
+ vfio_unpin_pages(mdev, pa->pa_iova_pfn, ret);
ret = -EINVAL;
+ goto err_out;
+ }
+ return ret;
+
+err_out:
+ pa->pa_nr = 0;
kfree(pa->pa_iova_pfn);
+ pa->pa_iova_pfn = NULL;
return ret;
}
+/* Unpin the pages before releasing the memory. */
+static void pfn_array_unpin_free(struct pfn_array *pa, struct device *mdev)
+{
+ vfio_unpin_pages(mdev, pa->pa_iova_pfn, pa->pa_nr);
+ pa->pa_nr = 0;
+ kfree(pa->pa_iova_pfn);
+}
+
static int pfn_array_table_init(struct pfn_array_table *pat, int nr)
{
pat->pat_pa = kcalloc(nr, sizeof(*pat->pat_pa), GFP_KERNEL);
* This is the chain length not considering any TICs.
* You need to do a new round for each TIC target.
*
+ * The program is also validated for absence of not yet supported
+ * indirect data addressing scenarios.
+ *
* Returns: the length of the ccw chain or -errno.
*/
static int ccwchain_calc_length(u64 iova, struct channel_program *cp)
do {
cnt++;
+ /*
+ * As we don't want to fail direct addressing even if the
+ * orb specified one of the unsupported formats, we defer
+ * checking for IDAWs in unsupported formats to here.
+ */
+ if ((!cp->orb.cmd.c64 || cp->orb.cmd.i2k) && ccw_is_idal(ccw))
+ return -EOPNOTSUPP;
+
if ((!ccw_is_chain(ccw)) && (!ccw_is_tic(ccw)))
break;
struct ccw1 *ccw;
struct pfn_array_table *pat;
unsigned long *idaws;
- int idaw_nr;
+ int ret;
ccw = chain->ch_ccw + idx;
* needed when translating a direct ccw to a idal ccw.
*/
pat = chain->ch_pat + idx;
- if (pfn_array_table_init(pat, 1))
- return -ENOMEM;
- idaw_nr = pfn_array_alloc_pin(pat->pat_pa, cp->mdev,
- ccw->cda, ccw->count);
- if (idaw_nr < 0)
- return idaw_nr;
+ ret = pfn_array_table_init(pat, 1);
+ if (ret)
+ goto out_init;
+
+ ret = pfn_array_alloc_pin(pat->pat_pa, cp->mdev, ccw->cda, ccw->count);
+ if (ret < 0)
+ goto out_init;
/* Translate this direct ccw to a idal ccw. */
- idaws = kcalloc(idaw_nr, sizeof(*idaws), GFP_DMA | GFP_KERNEL);
+ idaws = kcalloc(ret, sizeof(*idaws), GFP_DMA | GFP_KERNEL);
if (!idaws) {
- pfn_array_table_unpin_free(pat, cp->mdev);
- return -ENOMEM;
+ ret = -ENOMEM;
+ goto out_unpin;
}
ccw->cda = (__u32) virt_to_phys(idaws);
ccw->flags |= CCW_FLAG_IDA;
pfn_array_table_idal_create_words(pat, idaws);
return 0;
+
+out_unpin:
+ pfn_array_table_unpin_free(pat, cp->mdev);
+out_init:
+ ccw->cda = 0;
+ return ret;
}
static int ccwchain_fetch_idal(struct ccwchain *chain,
pat = chain->ch_pat + idx;
ret = pfn_array_table_init(pat, idaw_nr);
if (ret)
- return ret;
+ goto out_init;
/* Translate idal ccw to use new allocated idaws. */
idaws = kzalloc(idaw_len, GFP_DMA | GFP_KERNEL);
kfree(idaws);
out_unpin:
pfn_array_table_unpin_free(pat, cp->mdev);
+out_init:
+ ccw->cda = 0;
return ret;
}
/*
* XXX:
* Only support prefetch enable mode now.
- * Only support 64bit addressing idal.
- * Only support 4k IDAW.
*/
- if (!orb->cmd.pfch || !orb->cmd.c64 || orb->cmd.i2k)
+ if (!orb->cmd.pfch)
return -EOPNOTSUPP;
INIT_LIST_HEAD(&cp->ccwchain_list);
ret = ccwchain_loop_tic(chain, cp);
if (ret)
cp_unpin_free(cp);
+ /* It is safe to force: if not set but idals used
+ * ccwchain_calc_length returns an error.
+ */
+ cp->orb.cmd.c64 = 1;
return ret;
}
{
struct vfio_ccw_private *private = dev_get_drvdata(&sch->dev);
unsigned long flags;
+ int rc = -EAGAIN;
spin_lock_irqsave(sch->lock, flags);
if (!device_is_registered(&sch->dev))
if (cio_update_schib(sch)) {
vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_NOT_OPER);
+ rc = 0;
goto out_unlock;
}
private->state = private->mdev ? VFIO_CCW_STATE_IDLE :
VFIO_CCW_STATE_STANDBY;
}
+ rc = 0;
out_unlock:
spin_unlock_irqrestore(sch->lock, flags);
- return 0;
+ return rc;
}
static struct css_device_id vfio_ccw_sch_ids[] = {
#include "ioasm.h"
#include "vfio_ccw_private.h"
+#define CREATE_TRACE_POINTS
+#include "vfio_ccw_trace.h"
+
static int fsm_io_helper(struct vfio_ccw_private *private)
{
struct subchannel *sch;
*/
cio_disable_subchannel(sch);
}
+inline struct subchannel_id get_schid(struct vfio_ccw_private *p)
+{
+ return p->sch->schid;
+}
/*
* Deal with the ccw command request from the userspace.
union scsw *scsw = &private->scsw;
struct ccw_io_region *io_region = &private->io_region;
struct mdev_device *mdev = private->mdev;
+ char *errstr = "request";
private->state = VFIO_CCW_STATE_BOXED;
/* Don't try to build a cp if transport mode is specified. */
if (orb->tm.b) {
io_region->ret_code = -EOPNOTSUPP;
+ errstr = "transport mode";
goto err_out;
}
io_region->ret_code = cp_init(&private->cp, mdev_dev(mdev),
orb);
- if (io_region->ret_code)
+ if (io_region->ret_code) {
+ errstr = "cp init";
goto err_out;
+ }
io_region->ret_code = cp_prefetch(&private->cp);
if (io_region->ret_code) {
+ errstr = "cp prefetch";
cp_free(&private->cp);
goto err_out;
}
/* Start channel program and wait for I/O interrupt. */
io_region->ret_code = fsm_io_helper(private);
if (io_region->ret_code) {
+ errstr = "cp fsm_io_helper";
cp_free(&private->cp);
goto err_out;
}
err_out:
private->state = VFIO_CCW_STATE_IDLE;
+ trace_vfio_ccw_io_fctl(scsw->cmd.fctl, get_schid(private),
+ io_region->ret_code, errstr);
}
/*
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0
+ * Tracepoints for vfio_ccw driver
+ *
+ * Copyright IBM Corp. 2018
+ *
+ * Author(s): Dong Jia Shi <bjsdjshi@linux.vnet.ibm.com>
+ * Halil Pasic <pasic@linux.vnet.ibm.com>
+ */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM vfio_ccw
+
+#if !defined(_VFIO_CCW_TRACE_) || defined(TRACE_HEADER_MULTI_READ)
+#define _VFIO_CCW_TRACE_
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(vfio_ccw_io_fctl,
+ TP_PROTO(int fctl, struct subchannel_id schid, int errno, char *errstr),
+ TP_ARGS(fctl, schid, errno, errstr),
+
+ TP_STRUCT__entry(
+ __field(int, fctl)
+ __field_struct(struct subchannel_id, schid)
+ __field(int, errno)
+ __field(char*, errstr)
+ ),
+
+ TP_fast_assign(
+ __entry->fctl = fctl;
+ __entry->schid = schid;
+ __entry->errno = errno;
+ __entry->errstr = errstr;
+ ),
+
+ TP_printk("schid=%x.%x.%04x fctl=%x errno=%d info=%s",
+ __entry->schid.cssid,
+ __entry->schid.ssid,
+ __entry->schid.sch_no,
+ __entry->fctl,
+ __entry->errno,
+ __entry->errstr)
+);
+
+#endif /* _VFIO_CCW_TRACE_ */
+
+/* This part must be outside protection */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE vfio_ccw_trace
+
+#include <trace/define_trace.h>
tristate
default (LCS || CTCM || QETH)
+config ISM
+ tristate "Support for ISM vPCI Adapter"
+ depends on PCI && SMC
+ default n
+ help
+ Select this option if you want to use the Internal Shared Memory
+ vPCI Adapter.
+
+ To compile as a module choose M. The module name is ism.
+ If unsure, choose N.
endmenu
obj-$(CONFIG_QETH_L2) += qeth_l2.o
qeth_l3-y += qeth_l3_main.o qeth_l3_sys.o
obj-$(CONFIG_QETH_L3) += qeth_l3.o
+
+ism-y := ism_drv.o
+obj-$(CONFIG_ISM) += ism.o
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef S390_ISM_H
+#define S390_ISM_H
+
+#include <linux/spinlock.h>
+#include <linux/types.h>
+#include <linux/pci.h>
+#include <net/smc.h>
+
+#define UTIL_STR_LEN 16
+
+/*
+ * Do not use the first word of the DMB bits to ensure 8 byte aligned access.
+ */
+#define ISM_DMB_WORD_OFFSET 1
+#define ISM_DMB_BIT_OFFSET (ISM_DMB_WORD_OFFSET * 32)
+#define ISM_NR_DMBS 1920
+
+#define ISM_REG_SBA 0x1
+#define ISM_REG_IEQ 0x2
+#define ISM_READ_GID 0x3
+#define ISM_ADD_VLAN_ID 0x4
+#define ISM_DEL_VLAN_ID 0x5
+#define ISM_SET_VLAN 0x6
+#define ISM_RESET_VLAN 0x7
+#define ISM_QUERY_INFO 0x8
+#define ISM_QUERY_RGID 0x9
+#define ISM_REG_DMB 0xA
+#define ISM_UNREG_DMB 0xB
+#define ISM_SIGNAL_IEQ 0xE
+#define ISM_UNREG_SBA 0x11
+#define ISM_UNREG_IEQ 0x12
+
+#define ISM_ERROR 0xFFFF
+
+struct ism_req_hdr {
+ u32 cmd;
+ u16 : 16;
+ u16 len;
+};
+
+struct ism_resp_hdr {
+ u32 cmd;
+ u16 ret;
+ u16 len;
+};
+
+union ism_reg_sba {
+ struct {
+ struct ism_req_hdr hdr;
+ u64 sba;
+ } request;
+ struct {
+ struct ism_resp_hdr hdr;
+ } response;
+} __aligned(16);
+
+union ism_reg_ieq {
+ struct {
+ struct ism_req_hdr hdr;
+ u64 ieq;
+ u64 len;
+ } request;
+ struct {
+ struct ism_resp_hdr hdr;
+ } response;
+} __aligned(16);
+
+union ism_read_gid {
+ struct {
+ struct ism_req_hdr hdr;
+ } request;
+ struct {
+ struct ism_resp_hdr hdr;
+ u64 gid;
+ } response;
+} __aligned(16);
+
+union ism_qi {
+ struct {
+ struct ism_req_hdr hdr;
+ } request;
+ struct {
+ struct ism_resp_hdr hdr;
+ u32 version;
+ u32 max_len;
+ u64 ism_state;
+ u64 my_gid;
+ u64 sba;
+ u64 ieq;
+ u32 ieq_len;
+ u32 : 32;
+ u32 dmbs_owned;
+ u32 dmbs_used;
+ u32 vlan_required;
+ u32 vlan_nr_ids;
+ u16 vlan_id[64];
+ } response;
+} __aligned(64);
+
+union ism_query_rgid {
+ struct {
+ struct ism_req_hdr hdr;
+ u64 rgid;
+ u32 vlan_valid;
+ u32 vlan_id;
+ } request;
+ struct {
+ struct ism_resp_hdr hdr;
+ } response;
+} __aligned(16);
+
+union ism_reg_dmb {
+ struct {
+ struct ism_req_hdr hdr;
+ u64 dmb;
+ u32 dmb_len;
+ u32 sba_idx;
+ u32 vlan_valid;
+ u32 vlan_id;
+ u64 rgid;
+ } request;
+ struct {
+ struct ism_resp_hdr hdr;
+ u64 dmb_tok;
+ } response;
+} __aligned(32);
+
+union ism_sig_ieq {
+ struct {
+ struct ism_req_hdr hdr;
+ u64 rgid;
+ u32 trigger_irq;
+ u32 event_code;
+ u64 info;
+ } request;
+ struct {
+ struct ism_resp_hdr hdr;
+ } response;
+} __aligned(32);
+
+union ism_unreg_dmb {
+ struct {
+ struct ism_req_hdr hdr;
+ u64 dmb_tok;
+ } request;
+ struct {
+ struct ism_resp_hdr hdr;
+ } response;
+} __aligned(16);
+
+union ism_cmd_simple {
+ struct {
+ struct ism_req_hdr hdr;
+ } request;
+ struct {
+ struct ism_resp_hdr hdr;
+ } response;
+} __aligned(8);
+
+union ism_set_vlan_id {
+ struct {
+ struct ism_req_hdr hdr;
+ u64 vlan_id;
+ } request;
+ struct {
+ struct ism_resp_hdr hdr;
+ } response;
+} __aligned(16);
+
+struct ism_eq_header {
+ u64 idx;
+ u64 ieq_len;
+ u64 entry_len;
+ u64 : 64;
+};
+
+struct ism_eq {
+ struct ism_eq_header header;
+ struct smcd_event entry[15];
+};
+
+struct ism_sba {
+ u32 s : 1; /* summary bit */
+ u32 e : 1; /* event bit */
+ u32 : 30;
+ u32 dmb_bits[ISM_NR_DMBS / 32];
+ u32 reserved[3];
+ u16 dmbe_mask[ISM_NR_DMBS];
+};
+
+struct ism_dev {
+ spinlock_t lock;
+ struct pci_dev *pdev;
+ struct smcd_dev *smcd;
+
+ void __iomem *ctl;
+
+ struct ism_sba *sba;
+ dma_addr_t sba_dma_addr;
+ DECLARE_BITMAP(sba_bitmap, ISM_NR_DMBS);
+
+ struct ism_eq *ieq;
+ dma_addr_t ieq_dma_addr;
+
+ int ieq_idx;
+};
+
+#define ISM_CREATE_REQ(dmb, idx, sf, offset) \
+ ((dmb) | (idx) << 24 | (sf) << 23 | (offset))
+
+static inline int __ism_move(struct ism_dev *ism, u64 dmb_req, void *data,
+ unsigned int size)
+{
+ struct zpci_dev *zdev = to_zpci(ism->pdev);
+ u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, size);
+
+ return zpci_write_block(req, data, dmb_req);
+}
+
+#endif /* S390_ISM_H */
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ISM driver for s390.
+ *
+ * Copyright IBM Corp. 2018
+ */
+#define KMSG_COMPONENT "ism"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/interrupt.h>
+#include <linux/device.h>
+#include <linux/pci.h>
+#include <linux/err.h>
+#include <net/smc.h>
+
+#include <asm/debug.h>
+
+#include "ism.h"
+
+MODULE_DESCRIPTION("ISM driver for s390");
+MODULE_LICENSE("GPL");
+
+#define PCI_DEVICE_ID_IBM_ISM 0x04ED
+#define DRV_NAME "ism"
+
+static const struct pci_device_id ism_device_table[] = {
+ { PCI_VDEVICE(IBM, PCI_DEVICE_ID_IBM_ISM), 0 },
+ { 0, }
+};
+MODULE_DEVICE_TABLE(pci, ism_device_table);
+
+static debug_info_t *ism_debug_info;
+
+static int ism_cmd(struct ism_dev *ism, void *cmd)
+{
+ struct ism_req_hdr *req = cmd;
+ struct ism_resp_hdr *resp = cmd;
+
+ memcpy_toio(ism->ctl + sizeof(*req), req + 1, req->len - sizeof(*req));
+ memcpy_toio(ism->ctl, req, sizeof(*req));
+
+ WRITE_ONCE(resp->ret, ISM_ERROR);
+
+ memcpy_fromio(resp, ism->ctl, sizeof(*resp));
+ if (resp->ret) {
+ debug_text_event(ism_debug_info, 0, "cmd failure");
+ debug_event(ism_debug_info, 0, resp, sizeof(*resp));
+ goto out;
+ }
+ memcpy_fromio(resp + 1, ism->ctl + sizeof(*resp),
+ resp->len - sizeof(*resp));
+out:
+ return resp->ret;
+}
+
+static int ism_cmd_simple(struct ism_dev *ism, u32 cmd_code)
+{
+ union ism_cmd_simple cmd;
+
+ memset(&cmd, 0, sizeof(cmd));
+ cmd.request.hdr.cmd = cmd_code;
+ cmd.request.hdr.len = sizeof(cmd.request);
+
+ return ism_cmd(ism, &cmd);
+}
+
+static int query_info(struct ism_dev *ism)
+{
+ union ism_qi cmd;
+
+ memset(&cmd, 0, sizeof(cmd));
+ cmd.request.hdr.cmd = ISM_QUERY_INFO;
+ cmd.request.hdr.len = sizeof(cmd.request);
+
+ if (ism_cmd(ism, &cmd))
+ goto out;
+
+ debug_text_event(ism_debug_info, 3, "query info");
+ debug_event(ism_debug_info, 3, &cmd.response, sizeof(cmd.response));
+out:
+ return 0;
+}
+
+static int register_sba(struct ism_dev *ism)
+{
+ union ism_reg_sba cmd;
+ dma_addr_t dma_handle;
+ struct ism_sba *sba;
+
+ sba = dma_zalloc_coherent(&ism->pdev->dev, PAGE_SIZE,
+ &dma_handle, GFP_KERNEL);
+ if (!sba)
+ return -ENOMEM;
+
+ memset(&cmd, 0, sizeof(cmd));
+ cmd.request.hdr.cmd = ISM_REG_SBA;
+ cmd.request.hdr.len = sizeof(cmd.request);
+ cmd.request.sba = dma_handle;
+
+ if (ism_cmd(ism, &cmd)) {
+ dma_free_coherent(&ism->pdev->dev, PAGE_SIZE, sba, dma_handle);
+ return -EIO;
+ }
+
+ ism->sba = sba;
+ ism->sba_dma_addr = dma_handle;
+
+ return 0;
+}
+
+static int register_ieq(struct ism_dev *ism)
+{
+ union ism_reg_ieq cmd;
+ dma_addr_t dma_handle;
+ struct ism_eq *ieq;
+
+ ieq = dma_zalloc_coherent(&ism->pdev->dev, PAGE_SIZE,
+ &dma_handle, GFP_KERNEL);
+ if (!ieq)
+ return -ENOMEM;
+
+ memset(&cmd, 0, sizeof(cmd));
+ cmd.request.hdr.cmd = ISM_REG_IEQ;
+ cmd.request.hdr.len = sizeof(cmd.request);
+ cmd.request.ieq = dma_handle;
+ cmd.request.len = sizeof(*ieq);
+
+ if (ism_cmd(ism, &cmd)) {
+ dma_free_coherent(&ism->pdev->dev, PAGE_SIZE, ieq, dma_handle);
+ return -EIO;
+ }
+
+ ism->ieq = ieq;
+ ism->ieq_idx = -1;
+ ism->ieq_dma_addr = dma_handle;
+
+ return 0;
+}
+
+static int unregister_sba(struct ism_dev *ism)
+{
+ if (!ism->sba)
+ return 0;
+
+ if (ism_cmd_simple(ism, ISM_UNREG_SBA))
+ return -EIO;
+
+ dma_free_coherent(&ism->pdev->dev, PAGE_SIZE,
+ ism->sba, ism->sba_dma_addr);
+
+ ism->sba = NULL;
+ ism->sba_dma_addr = 0;
+
+ return 0;
+}
+
+static int unregister_ieq(struct ism_dev *ism)
+{
+ if (!ism->ieq)
+ return 0;
+
+ if (ism_cmd_simple(ism, ISM_UNREG_IEQ))
+ return -EIO;
+
+ dma_free_coherent(&ism->pdev->dev, PAGE_SIZE,
+ ism->ieq, ism->ieq_dma_addr);
+
+ ism->ieq = NULL;
+ ism->ieq_dma_addr = 0;
+
+ return 0;
+}
+
+static int ism_read_local_gid(struct ism_dev *ism)
+{
+ union ism_read_gid cmd;
+ int ret;
+
+ memset(&cmd, 0, sizeof(cmd));
+ cmd.request.hdr.cmd = ISM_READ_GID;
+ cmd.request.hdr.len = sizeof(cmd.request);
+
+ ret = ism_cmd(ism, &cmd);
+ if (ret)
+ goto out;
+
+ ism->smcd->local_gid = cmd.response.gid;
+out:
+ return ret;
+}
+
+static int ism_query_rgid(struct smcd_dev *smcd, u64 rgid, u32 vid_valid,
+ u32 vid)
+{
+ struct ism_dev *ism = smcd->priv;
+ union ism_query_rgid cmd;
+
+ memset(&cmd, 0, sizeof(cmd));
+ cmd.request.hdr.cmd = ISM_QUERY_RGID;
+ cmd.request.hdr.len = sizeof(cmd.request);
+
+ cmd.request.rgid = rgid;
+ cmd.request.vlan_valid = vid_valid;
+ cmd.request.vlan_id = vid;
+
+ return ism_cmd(ism, &cmd);
+}
+
+static void ism_free_dmb(struct ism_dev *ism, struct smcd_dmb *dmb)
+{
+ clear_bit(dmb->sba_idx, ism->sba_bitmap);
+ dma_free_coherent(&ism->pdev->dev, dmb->dmb_len,
+ dmb->cpu_addr, dmb->dma_addr);
+}
+
+static int ism_alloc_dmb(struct ism_dev *ism, struct smcd_dmb *dmb)
+{
+ unsigned long bit;
+
+ if (PAGE_ALIGN(dmb->dmb_len) > dma_get_max_seg_size(&ism->pdev->dev))
+ return -EINVAL;
+
+ if (!dmb->sba_idx) {
+ bit = find_next_zero_bit(ism->sba_bitmap, ISM_NR_DMBS,
+ ISM_DMB_BIT_OFFSET);
+ if (bit == ISM_NR_DMBS)
+ return -ENOMEM;
+
+ dmb->sba_idx = bit;
+ }
+ if (dmb->sba_idx < ISM_DMB_BIT_OFFSET ||
+ test_and_set_bit(dmb->sba_idx, ism->sba_bitmap))
+ return -EINVAL;
+
+ dmb->cpu_addr = dma_zalloc_coherent(&ism->pdev->dev, dmb->dmb_len,
+ &dmb->dma_addr, GFP_KERNEL |
+ __GFP_NOWARN | __GFP_NOMEMALLOC |
+ __GFP_COMP | __GFP_NORETRY);
+ if (!dmb->cpu_addr)
+ clear_bit(dmb->sba_idx, ism->sba_bitmap);
+
+ return dmb->cpu_addr ? 0 : -ENOMEM;
+}
+
+static int ism_register_dmb(struct smcd_dev *smcd, struct smcd_dmb *dmb)
+{
+ struct ism_dev *ism = smcd->priv;
+ union ism_reg_dmb cmd;
+ int ret;
+
+ ret = ism_alloc_dmb(ism, dmb);
+ if (ret)
+ goto out;
+
+ memset(&cmd, 0, sizeof(cmd));
+ cmd.request.hdr.cmd = ISM_REG_DMB;
+ cmd.request.hdr.len = sizeof(cmd.request);
+
+ cmd.request.dmb = dmb->dma_addr;
+ cmd.request.dmb_len = dmb->dmb_len;
+ cmd.request.sba_idx = dmb->sba_idx;
+ cmd.request.vlan_valid = dmb->vlan_valid;
+ cmd.request.vlan_id = dmb->vlan_id;
+ cmd.request.rgid = dmb->rgid;
+
+ ret = ism_cmd(ism, &cmd);
+ if (ret) {
+ ism_free_dmb(ism, dmb);
+ goto out;
+ }
+ dmb->dmb_tok = cmd.response.dmb_tok;
+out:
+ return ret;
+}
+
+static int ism_unregister_dmb(struct smcd_dev *smcd, struct smcd_dmb *dmb)
+{
+ struct ism_dev *ism = smcd->priv;
+ union ism_unreg_dmb cmd;
+ int ret;
+
+ memset(&cmd, 0, sizeof(cmd));
+ cmd.request.hdr.cmd = ISM_UNREG_DMB;
+ cmd.request.hdr.len = sizeof(cmd.request);
+
+ cmd.request.dmb_tok = dmb->dmb_tok;
+
+ ret = ism_cmd(ism, &cmd);
+ if (ret)
+ goto out;
+
+ ism_free_dmb(ism, dmb);
+out:
+ return ret;
+}
+
+static int ism_add_vlan_id(struct smcd_dev *smcd, u64 vlan_id)
+{
+ struct ism_dev *ism = smcd->priv;
+ union ism_set_vlan_id cmd;
+
+ memset(&cmd, 0, sizeof(cmd));
+ cmd.request.hdr.cmd = ISM_ADD_VLAN_ID;
+ cmd.request.hdr.len = sizeof(cmd.request);
+
+ cmd.request.vlan_id = vlan_id;
+
+ return ism_cmd(ism, &cmd);
+}
+
+static int ism_del_vlan_id(struct smcd_dev *smcd, u64 vlan_id)
+{
+ struct ism_dev *ism = smcd->priv;
+ union ism_set_vlan_id cmd;
+
+ memset(&cmd, 0, sizeof(cmd));
+ cmd.request.hdr.cmd = ISM_DEL_VLAN_ID;
+ cmd.request.hdr.len = sizeof(cmd.request);
+
+ cmd.request.vlan_id = vlan_id;
+
+ return ism_cmd(ism, &cmd);
+}
+
+static int ism_set_vlan_required(struct smcd_dev *smcd)
+{
+ return ism_cmd_simple(smcd->priv, ISM_SET_VLAN);
+}
+
+static int ism_reset_vlan_required(struct smcd_dev *smcd)
+{
+ return ism_cmd_simple(smcd->priv, ISM_RESET_VLAN);
+}
+
+static int ism_signal_ieq(struct smcd_dev *smcd, u64 rgid, u32 trigger_irq,
+ u32 event_code, u64 info)
+{
+ struct ism_dev *ism = smcd->priv;
+ union ism_sig_ieq cmd;
+
+ memset(&cmd, 0, sizeof(cmd));
+ cmd.request.hdr.cmd = ISM_SIGNAL_IEQ;
+ cmd.request.hdr.len = sizeof(cmd.request);
+
+ cmd.request.rgid = rgid;
+ cmd.request.trigger_irq = trigger_irq;
+ cmd.request.event_code = event_code;
+ cmd.request.info = info;
+
+ return ism_cmd(ism, &cmd);
+}
+
+static unsigned int max_bytes(unsigned int start, unsigned int len,
+ unsigned int boundary)
+{
+ return min(boundary - (start & (boundary - 1)), len);
+}
+
+static int ism_move(struct smcd_dev *smcd, u64 dmb_tok, unsigned int idx,
+ bool sf, unsigned int offset, void *data, unsigned int size)
+{
+ struct ism_dev *ism = smcd->priv;
+ unsigned int bytes;
+ u64 dmb_req;
+ int ret;
+
+ while (size) {
+ bytes = max_bytes(offset, size, PAGE_SIZE);
+ dmb_req = ISM_CREATE_REQ(dmb_tok, idx, size == bytes ? sf : 0,
+ offset);
+
+ ret = __ism_move(ism, dmb_req, data, bytes);
+ if (ret)
+ return ret;
+
+ size -= bytes;
+ data += bytes;
+ offset += bytes;
+ }
+
+ return 0;
+}
+
+static void ism_handle_event(struct ism_dev *ism)
+{
+ struct smcd_event *entry;
+
+ while ((ism->ieq_idx + 1) != READ_ONCE(ism->ieq->header.idx)) {
+ if (++(ism->ieq_idx) == ARRAY_SIZE(ism->ieq->entry))
+ ism->ieq_idx = 0;
+
+ entry = &ism->ieq->entry[ism->ieq_idx];
+ debug_event(ism_debug_info, 2, entry, sizeof(*entry));
+ smcd_handle_event(ism->smcd, entry);
+ }
+}
+
+static irqreturn_t ism_handle_irq(int irq, void *data)
+{
+ struct ism_dev *ism = data;
+ unsigned long bit, end;
+ unsigned long *bv;
+
+ bv = (void *) &ism->sba->dmb_bits[ISM_DMB_WORD_OFFSET];
+ end = sizeof(ism->sba->dmb_bits) * BITS_PER_BYTE - ISM_DMB_BIT_OFFSET;
+
+ spin_lock(&ism->lock);
+ ism->sba->s = 0;
+ barrier();
+ for (bit = 0;;) {
+ bit = find_next_bit_inv(bv, end, bit);
+ if (bit >= end)
+ break;
+
+ clear_bit_inv(bit, bv);
+ barrier();
+ smcd_handle_irq(ism->smcd, bit + ISM_DMB_BIT_OFFSET);
+ ism->sba->dmbe_mask[bit + ISM_DMB_BIT_OFFSET] = 0;
+ }
+
+ if (ism->sba->e) {
+ ism->sba->e = 0;
+ barrier();
+ ism_handle_event(ism);
+ }
+ spin_unlock(&ism->lock);
+ return IRQ_HANDLED;
+}
+
+static const struct smcd_ops ism_ops = {
+ .query_remote_gid = ism_query_rgid,
+ .register_dmb = ism_register_dmb,
+ .unregister_dmb = ism_unregister_dmb,
+ .add_vlan_id = ism_add_vlan_id,
+ .del_vlan_id = ism_del_vlan_id,
+ .set_vlan_required = ism_set_vlan_required,
+ .reset_vlan_required = ism_reset_vlan_required,
+ .signal_event = ism_signal_ieq,
+ .move_data = ism_move,
+};
+
+static int ism_dev_init(struct ism_dev *ism)
+{
+ struct pci_dev *pdev = ism->pdev;
+ int ret;
+
+ ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSI);
+ if (ret <= 0)
+ goto out;
+
+ ret = request_irq(pci_irq_vector(pdev, 0), ism_handle_irq, 0,
+ pci_name(pdev), ism);
+ if (ret)
+ goto free_vectors;
+
+ ret = register_sba(ism);
+ if (ret)
+ goto free_irq;
+
+ ret = register_ieq(ism);
+ if (ret)
+ goto unreg_sba;
+
+ ret = ism_read_local_gid(ism);
+ if (ret)
+ goto unreg_ieq;
+
+ ret = smcd_register_dev(ism->smcd);
+ if (ret)
+ goto unreg_ieq;
+
+ query_info(ism);
+ return 0;
+
+unreg_ieq:
+ unregister_ieq(ism);
+unreg_sba:
+ unregister_sba(ism);
+free_irq:
+ free_irq(pci_irq_vector(pdev, 0), ism);
+free_vectors:
+ pci_free_irq_vectors(pdev);
+out:
+ return ret;
+}
+
+static int ism_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+ struct ism_dev *ism;
+ int ret;
+
+ ism = kzalloc(sizeof(*ism), GFP_KERNEL);
+ if (!ism)
+ return -ENOMEM;
+
+ spin_lock_init(&ism->lock);
+ dev_set_drvdata(&pdev->dev, ism);
+ ism->pdev = pdev;
+
+ ret = pci_enable_device_mem(pdev);
+ if (ret)
+ goto err;
+
+ ret = pci_request_mem_regions(pdev, DRV_NAME);
+ if (ret)
+ goto err_disable;
+
+ ism->ctl = pci_iomap(pdev, 2, 0);
+ if (!ism->ctl)
+ goto err_resource;
+
+ ret = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
+ if (ret)
+ goto err_unmap;
+
+ pci_set_dma_seg_boundary(pdev, SZ_1M - 1);
+ pci_set_dma_max_seg_size(pdev, SZ_1M);
+ pci_set_master(pdev);
+
+ ism->smcd = smcd_alloc_dev(&pdev->dev, dev_name(&pdev->dev), &ism_ops,
+ ISM_NR_DMBS);
+ if (!ism->smcd)
+ goto err_unmap;
+
+ ism->smcd->priv = ism;
+ ret = ism_dev_init(ism);
+ if (ret)
+ goto err_free;
+
+ return 0;
+
+err_free:
+ smcd_free_dev(ism->smcd);
+err_unmap:
+ pci_iounmap(pdev, ism->ctl);
+err_resource:
+ pci_release_mem_regions(pdev);
+err_disable:
+ pci_disable_device(pdev);
+err:
+ kfree(ism);
+ dev_set_drvdata(&pdev->dev, NULL);
+ return ret;
+}
+
+static void ism_dev_exit(struct ism_dev *ism)
+{
+ struct pci_dev *pdev = ism->pdev;
+
+ smcd_unregister_dev(ism->smcd);
+ unregister_ieq(ism);
+ unregister_sba(ism);
+ free_irq(pci_irq_vector(pdev, 0), ism);
+ pci_free_irq_vectors(pdev);
+}
+
+static void ism_remove(struct pci_dev *pdev)
+{
+ struct ism_dev *ism = dev_get_drvdata(&pdev->dev);
+
+ ism_dev_exit(ism);
+
+ smcd_free_dev(ism->smcd);
+ pci_iounmap(pdev, ism->ctl);
+ pci_release_mem_regions(pdev);
+ pci_disable_device(pdev);
+ dev_set_drvdata(&pdev->dev, NULL);
+ kfree(ism);
+}
+
+static int ism_suspend(struct device *dev)
+{
+ struct ism_dev *ism = dev_get_drvdata(dev);
+
+ ism_dev_exit(ism);
+ return 0;
+}
+
+static int ism_resume(struct device *dev)
+{
+ struct ism_dev *ism = dev_get_drvdata(dev);
+
+ return ism_dev_init(ism);
+}
+
+static SIMPLE_DEV_PM_OPS(ism_pm_ops, ism_suspend, ism_resume);
+
+static struct pci_driver ism_driver = {
+ .name = DRV_NAME,
+ .id_table = ism_device_table,
+ .probe = ism_probe,
+ .remove = ism_remove,
+ .driver = {
+ .pm = &ism_pm_ops,
+ },
+};
+
+static int __init ism_init(void)
+{
+ int ret;
+
+ ism_debug_info = debug_register("ism", 2, 1, 16);
+ if (!ism_debug_info)
+ return -ENODEV;
+
+ debug_register_view(ism_debug_info, &debug_hex_ascii_view);
+ ret = pci_register_driver(&ism_driver);
+ if (ret)
+ debug_unregister(ism_debug_info);
+
+ return ret;
+}
+
+static void __exit ism_exit(void)
+{
+ pci_unregister_driver(&ism_driver);
+ debug_unregister(ism_debug_info);
+}
+
+module_init(ism_init);
+module_exit(ism_exit);
struct sk_buff_head skb_list;
int is_header[QDIO_MAX_ELEMENTS_PER_BUFFER];
- struct qaob *aob;
struct qeth_qdio_out_q *q;
struct qeth_qdio_out_buffer *next_pending;
};
int portno;
enum qeth_card_types type;
enum qeth_link_types link_type;
- int is_multicast_different;
int initial_mtu;
int max_mtu;
int broadcast_capable;
/*some helper functions*/
#define QETH_CARD_IFNAME(card) (((card)->dev)? (card)->dev->name : "")
+static inline void qeth_scrub_qdio_buffer(struct qdio_buffer *buf,
+ unsigned int elements)
+{
+ unsigned int i;
+
+ for (i = 0; i < elements; i++)
+ memset(&buf->element[i], 0, sizeof(struct qdio_buffer_element));
+ buf->element[14].sflags = 0;
+ buf->element[15].sflags = 0;
+}
+
/**
* qeth_get_elements_for_range() - find number of SBALEs to cover range.
* @start: Start of the address range.
data, QETH_PROT_IPV6);
}
+int qeth_get_priority_queue(struct qeth_card *card, struct sk_buff *skb,
+ int ipv);
+static inline struct qeth_qdio_out_q *qeth_get_tx_queue(struct qeth_card *card,
+ struct sk_buff *skb,
+ int ipv, int cast_type)
+{
+ if (IS_IQD(card) && cast_type != RTN_UNICAST)
+ return card->qdio.out_qs[card->qdio.no_out_queues - 1];
+ if (!card->qdio.do_prio_queueing)
+ return card->qdio.out_qs[card->qdio.default_out_queue];
+ return card->qdio.out_qs[qeth_get_priority_queue(card, skb, ipv)];
+}
+
extern struct qeth_discipline qeth_l2_discipline;
extern struct qeth_discipline qeth_l3_discipline;
extern const struct attribute_group *qeth_generic_attr_groups[];
void *);
struct qeth_cmd_buffer *qeth_get_ipacmd_buffer(struct qeth_card *,
enum qeth_ipa_cmds, enum qeth_prot_versions);
-int qeth_query_setadapterparms(struct qeth_card *);
struct sk_buff *qeth_core_get_next_skb(struct qeth_card *,
struct qeth_qdio_buffer *, struct qdio_buffer_element **, int *,
struct qeth_hdr **);
int qeth_send_control_data(struct qeth_card *, int, struct qeth_cmd_buffer *,
int (*reply_cb)(struct qeth_card *, struct qeth_reply*, unsigned long),
void *reply_param);
-int qeth_bridgeport_query_ports(struct qeth_card *card,
- enum qeth_sbp_roles *role, enum qeth_sbp_states *state);
-int qeth_bridgeport_setrole(struct qeth_card *card, enum qeth_sbp_roles role);
-int qeth_bridgeport_an_set(struct qeth_card *card, int enable);
-int qeth_get_priority_queue(struct qeth_card *, struct sk_buff *, int, int);
int qeth_get_elements_no(struct qeth_card *card, struct sk_buff *skb,
int extra_elems, int data_offset);
int qeth_get_elements_for_frags(struct sk_buff *);
int qeth_hdr_chk_and_bounce(struct sk_buff *, struct qeth_hdr **, int);
int qeth_configure_cq(struct qeth_card *, enum qeth_cq);
int qeth_hw_trap(struct qeth_card *, enum qeth_diags_trap_action);
-int qeth_query_ipassists(struct qeth_card *, enum qeth_prot_versions prot);
void qeth_trace_features(struct qeth_card *);
void qeth_close_dev(struct qeth_card *);
int qeth_send_setassparms(struct qeth_card *, struct qeth_cmd_buffer *, __u16,
__u16, __u16,
enum qeth_prot_versions);
int qeth_set_features(struct net_device *, netdev_features_t);
-void qeth_recover_features(struct net_device *dev);
+void qeth_enable_hw_features(struct net_device *dev);
netdev_features_t qeth_fix_features(struct net_device *, netdev_features_t);
netdev_features_t qeth_features_check(struct sk_buff *skb,
struct net_device *dev,
struct qeth_qdio_out_buffer *buf,
enum iucv_tx_notify notification);
static void qeth_release_skbs(struct qeth_qdio_out_buffer *buf);
-static void qeth_clear_output_buffer(struct qeth_qdio_out_q *queue,
- struct qeth_qdio_out_buffer *buf,
- enum qeth_qdio_buffer_states newbufstate);
static int qeth_init_qdio_out_buf(struct qeth_qdio_out_q *, int);
struct workqueue_struct *qeth_wq;
if (forced_cleanup && (atomic_read(&(q->bufs[bidx]->state)) ==
QETH_QDIO_BUF_HANDLED_DELAYED)) {
/* for recovery situations */
- q->bufs[bidx]->aob = q->bufstates[bidx].aob;
qeth_init_qdio_out_buf(q, bidx);
QETH_CARD_TEXT(q->card, 2, "clprecov");
}
struct qaob *aob;
struct qeth_qdio_out_buffer *buffer;
enum iucv_tx_notify notification;
+ unsigned int i;
aob = (struct qaob *) phys_to_virt(phys_aob_addr);
QETH_CARD_TEXT(card, 5, "haob");
}
qeth_notify_skbs(buffer->q, buffer, notification);
- buffer->aob = NULL;
- qeth_clear_output_buffer(buffer->q, buffer,
- QETH_QDIO_BUF_HANDLED_DELAYED);
+ /* Free dangling allocations. The attached skbs are handled by
+ * qeth_cleanup_handled_pending().
+ */
+ for (i = 0;
+ i < aob->sb_count && i < QETH_MAX_BUFFER_ELEMENTS(card);
+ i++) {
+ if (aob->sba[i] && buffer->is_header[i])
+ kmem_cache_free(qeth_core_header_cache,
+ (void *) aob->sba[i]);
+ }
+ atomic_set(&buffer->state, QETH_QDIO_BUF_HANDLED_DELAYED);
- /* from here on: do not touch buffer anymore */
qdio_release_aob(aob);
}
}
static void qeth_clear_output_buffer(struct qeth_qdio_out_q *queue,
- struct qeth_qdio_out_buffer *buf,
- enum qeth_qdio_buffer_states newbufstate)
+ struct qeth_qdio_out_buffer *buf)
{
int i;
if (buf->buffer->element[0].sflags & SBAL_SFLAGS0_PCI_REQ)
atomic_dec(&queue->set_pci_flags_count);
- if (newbufstate == QETH_QDIO_BUF_EMPTY) {
- qeth_release_skbs(buf);
- }
+ qeth_release_skbs(buf);
+
for (i = 0; i < QETH_MAX_BUFFER_ELEMENTS(queue->card); ++i) {
if (buf->buffer->element[i].addr && buf->is_header[i])
kmem_cache_free(qeth_core_header_cache,
buf->buffer->element[i].addr);
buf->is_header[i] = 0;
- buf->buffer->element[i].length = 0;
- buf->buffer->element[i].addr = NULL;
- buf->buffer->element[i].eflags = 0;
- buf->buffer->element[i].sflags = 0;
}
- buf->buffer->element[15].eflags = 0;
- buf->buffer->element[15].sflags = 0;
+
+ qeth_scrub_qdio_buffer(buf->buffer,
+ QETH_MAX_BUFFER_ELEMENTS(queue->card));
buf->next_element_to_fill = 0;
- atomic_set(&buf->state, newbufstate);
+ atomic_set(&buf->state, QETH_QDIO_BUF_EMPTY);
}
static void qeth_clear_outq_buffers(struct qeth_qdio_out_q *q, int free)
if (!q->bufs[j])
continue;
qeth_cleanup_handled_pending(q, j, 1);
- qeth_clear_output_buffer(q, q->bufs[j], QETH_QDIO_BUF_EMPTY);
+ qeth_clear_output_buffer(q, q->bufs[j]);
if (free) {
kmem_cache_free(qeth_qdio_outbuf_cache, q->bufs[j]);
q->bufs[j] = NULL;
card->qdio.default_out_queue = QETH_DEFAULT_QUEUE;
card->info.type = CARD_RDEV(card)->id.driver_info;
card->qdio.no_out_queues = QETH_MAX_QUEUES;
- if (card->info.type == QETH_CARD_TYPE_IQD)
- card->info.is_multicast_different = 0x0103;
qeth_update_from_chp_desc(card);
}
static int qeth_init_qdio_out_buf(struct qeth_qdio_out_q *q, int bidx)
{
- int rc;
struct qeth_qdio_out_buffer *newbuf;
- rc = 0;
newbuf = kmem_cache_zalloc(qeth_qdio_outbuf_cache, GFP_ATOMIC);
- if (!newbuf) {
- rc = -ENOMEM;
- goto out;
- }
+ if (!newbuf)
+ return -ENOMEM;
+
newbuf->buffer = q->qdio_bufs[bidx];
skb_queue_head_init(&newbuf->skb_list);
lockdep_set_class(&newbuf->skb_list.lock, &qdio_out_skb_queue_key);
newbuf->q = q;
- newbuf->aob = NULL;
newbuf->next_pending = q->bufs[bidx];
atomic_set(&newbuf->state, QETH_QDIO_BUF_EMPTY);
q->bufs[bidx] = newbuf;
- if (q->bufstates) {
- q->bufstates[bidx].user = newbuf;
- QETH_CARD_TEXT_(q->card, 2, "nbs%d", bidx);
- QETH_CARD_TEXT_(q->card, 2, "%lx", (long) newbuf);
- QETH_CARD_TEXT_(q->card, 2, "%lx",
- (long) newbuf->next_pending);
- }
-out:
- return rc;
+ return 0;
}
static void qeth_free_qdio_out_buf(struct qeth_qdio_out_q *q)
QDIO_MAX_BUFFERS_PER_Q);
for (j = 0; j < QDIO_MAX_BUFFERS_PER_Q; ++j) {
qeth_clear_output_buffer(card->qdio.out_qs[i],
- card->qdio.out_qs[i]->bufs[j],
- QETH_QDIO_BUF_EMPTY);
+ card->qdio.out_qs[i]->bufs[j]);
}
card->qdio.out_qs[i]->card = card;
card->qdio.out_qs[i]->next_buf_to_fill = 0;
return iob;
}
-int qeth_query_setadapterparms(struct qeth_card *card)
+static int qeth_query_setadapterparms(struct qeth_card *card)
{
int rc;
struct qeth_cmd_buffer *iob;
rc = qeth_send_ipa_cmd(card, iob, qeth_query_setadapterparms_cb, NULL);
return rc;
}
-EXPORT_SYMBOL_GPL(qeth_query_setadapterparms);
static int qeth_query_ipassists_cb(struct qeth_card *card,
struct qeth_reply *reply, unsigned long data)
return 0;
}
-int qeth_query_ipassists(struct qeth_card *card, enum qeth_prot_versions prot)
+static int qeth_query_ipassists(struct qeth_card *card,
+ enum qeth_prot_versions prot)
{
int rc;
struct qeth_cmd_buffer *iob;
rc = qeth_send_ipa_cmd(card, iob, qeth_query_ipassists_cb, NULL);
return rc;
}
-EXPORT_SYMBOL_GPL(qeth_query_ipassists);
static int qeth_query_switch_attributes_cb(struct qeth_card *card,
struct qeth_reply *reply, unsigned long data)
return qeth_send_ipa_cmd(card, iob,
qeth_query_switch_attributes_cb, sw_info);
}
-EXPORT_SYMBOL_GPL(qeth_query_switch_attributes);
static int qeth_query_setdiagass_cb(struct qeth_card *card,
struct qeth_reply *reply, unsigned long data)
}
EXPORT_SYMBOL_GPL(qeth_configure_cq);
-
-static void qeth_qdio_cq_handler(struct qeth_card *card,
- unsigned int qdio_err,
- unsigned int queue, int first_element, int count) {
+static void qeth_qdio_cq_handler(struct qeth_card *card, unsigned int qdio_err,
+ unsigned int queue, int first_element,
+ int count)
+{
struct qeth_qdio_q *cq = card->qdio.c_q;
int i;
int rc;
for (i = first_element; i < first_element + count; ++i) {
int bidx = i % QDIO_MAX_BUFFERS_PER_Q;
struct qdio_buffer *buffer = cq->qdio_bufs[bidx];
- int e;
+ int e = 0;
- e = 0;
while ((e < QDIO_MAX_ELEMENTS_PER_BUFFER) &&
buffer->element[e].addr) {
unsigned long phys_aob_addr;
phys_aob_addr = (unsigned long) buffer->element[e].addr;
qeth_qdio_handle_aob(card, phys_aob_addr);
- buffer->element[e].addr = NULL;
- buffer->element[e].eflags = 0;
- buffer->element[e].sflags = 0;
- buffer->element[e].length = 0;
-
++e;
}
-
- buffer->element[15].eflags = 0;
- buffer->element[15].sflags = 0;
+ qeth_scrub_qdio_buffer(buffer, QDIO_MAX_ELEMENTS_PER_BUFFER);
}
rc = do_QDIO(CARD_DDEV(card), QDIO_FLAG_SYNC_INPUT, queue,
card->qdio.c_q->next_buf_to_init,
qeth_notify_skbs(queue, buffer,
TX_NOTIFY_PENDING);
}
- buffer->aob = queue->bufstates[bidx].aob;
QETH_CARD_TEXT_(queue->card, 5, "pel%d", bidx);
- QETH_CARD_TEXT(queue->card, 5, "aob");
- QETH_CARD_TEXT_(queue->card, 5, "%lx",
- virt_to_phys(buffer->aob));
+
+ /* prepare the queue slot for re-use: */
+ qeth_scrub_qdio_buffer(buffer->buffer,
+ QETH_MAX_BUFFER_ELEMENTS(card));
if (qeth_init_qdio_out_buf(queue, bidx)) {
QETH_CARD_TEXT(card, 2, "outofbuf");
qeth_schedule_recovery(card);
qeth_notify_skbs(queue, buffer, n);
}
- qeth_clear_output_buffer(queue, buffer,
- QETH_QDIO_BUF_EMPTY);
+ qeth_clear_output_buffer(queue, buffer);
}
qeth_cleanup_handled_pending(queue, bidx, 0);
}
* Note: Function assumes that we have 4 outbound queues.
*/
int qeth_get_priority_queue(struct qeth_card *card, struct sk_buff *skb,
- int ipv, int cast_type)
+ int ipv)
{
__be16 *tci;
u8 tos;
- if (cast_type && card->info.is_multicast_different)
- return card->info.is_multicast_different &
- (card->qdio.no_out_queues - 1);
-
switch (card->qdio.do_prio_queueing) {
case QETH_PRIO_Q_ING_TOS:
case QETH_PRIO_Q_ING_PREC:
goto out;
}
- ccw_device_get_id(CARD_RDEV(card), &id);
+ ccw_device_get_id(CARD_DDEV(card), &id);
request->resp_buf_len = sizeof(*response);
request->resp_version = DIAG26C_VERSION2;
request->op_code = DIAG26C_GET_MAC;
return 0;
}
-static struct ccwgroup_driver qeth_core_ccwgroup_driver = {
- .driver = {
- .owner = THIS_MODULE,
- .name = "qeth",
- },
- .ccw_driver = &qeth_ccw_driver,
- .setup = qeth_core_probe_device,
- .remove = qeth_core_remove_device,
- .set_online = qeth_core_set_online,
- .set_offline = qeth_core_set_offline,
- .shutdown = qeth_core_shutdown,
- .prepare = NULL,
- .complete = NULL,
- .freeze = qeth_core_freeze,
- .thaw = qeth_core_thaw,
- .restore = qeth_core_restore,
-};
-
static ssize_t group_store(struct device_driver *ddrv, const char *buf,
size_t count)
{
int err;
- err = ccwgroup_create_dev(qeth_core_root_dev,
- &qeth_core_ccwgroup_driver, 3, buf);
+ err = ccwgroup_create_dev(qeth_core_root_dev, to_ccwgroupdrv(ddrv), 3,
+ buf);
return err ? err : count;
}
NULL,
};
+static struct ccwgroup_driver qeth_core_ccwgroup_driver = {
+ .driver = {
+ .groups = qeth_drv_attr_groups,
+ .owner = THIS_MODULE,
+ .name = "qeth",
+ },
+ .ccw_driver = &qeth_ccw_driver,
+ .setup = qeth_core_probe_device,
+ .remove = qeth_core_remove_device,
+ .set_online = qeth_core_set_online,
+ .set_offline = qeth_core_set_offline,
+ .shutdown = qeth_core_shutdown,
+ .prepare = NULL,
+ .complete = NULL,
+ .freeze = qeth_core_freeze,
+ .thaw = qeth_core_thaw,
+ .restore = qeth_core_restore,
+};
+
int qeth_do_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
{
struct qeth_card *card = dev->ml_priv;
#define QETH_HW_FEATURES (NETIF_F_RXCSUM | NETIF_F_IP_CSUM | NETIF_F_TSO | \
NETIF_F_IPV6_CSUM)
/**
- * qeth_recover_features() - Restore device features after recovery
- * @dev: the recovering net_device
- *
- * Caller must hold rtnl lock.
+ * qeth_enable_hw_features() - (Re-)Enable HW functions for device features
+ * @dev: a net_device
*/
-void qeth_recover_features(struct net_device *dev)
+void qeth_enable_hw_features(struct net_device *dev)
{
- netdev_features_t features = dev->features;
struct qeth_card *card = dev->ml_priv;
+ netdev_features_t features;
+ rtnl_lock();
+ features = dev->features;
/* force-off any feature that needs an IPA sequence.
* netdev_update_features() will restart them.
*/
dev->features &= ~QETH_HW_FEATURES;
netdev_update_features(dev);
-
- if (features == dev->features)
- return;
- dev_warn(&card->gdev->dev,
- "Device recovery failed to restore all offload features\n");
+ if (features != dev->features)
+ dev_warn(&card->gdev->dev,
+ "Device recovery failed to restore all offload features\n");
+ rtnl_unlock();
}
-EXPORT_SYMBOL_GPL(qeth_recover_features);
+EXPORT_SYMBOL_GPL(qeth_enable_hw_features);
int qeth_set_features(struct net_device *dev, netdev_features_t features)
{
rc = ccw_driver_register(&qeth_ccw_driver);
if (rc)
goto ccw_err;
- qeth_core_ccwgroup_driver.driver.groups = qeth_drv_attr_groups;
rc = ccwgroup_driver_register(&qeth_core_ccwgroup_driver);
if (rc)
goto ccwgroup_err;
QETH_CARD_TYPE_OSX = 2,
};
+#define IS_IQD(card) ((card)->info.type == QETH_CARD_TYPE_IQD)
+
#define QETH_MPC_DIFINFO_LEN_INDICATES_LINK_TYPE 0x18
/* only the first two bytes are looked at in qeth_get_cardname_short */
enum qeth_link_types {
int qeth_l2_create_device_attributes(struct device *);
void qeth_l2_remove_device_attributes(struct device *);
void qeth_l2_setup_bridgeport_attrs(struct qeth_card *card);
+int qeth_bridgeport_query_ports(struct qeth_card *card,
+ enum qeth_sbp_roles *role,
+ enum qeth_sbp_states *state);
+int qeth_bridgeport_setrole(struct qeth_card *card, enum qeth_sbp_roles role);
+int qeth_bridgeport_an_set(struct qeth_card *card, int enable);
int qeth_l2_vnicc_set_state(struct qeth_card *card, u32 vnicc, bool state);
int qeth_l2_vnicc_get_state(struct qeth_card *card, u32 vnicc, bool *state);
static int qeth_l2_set_offline(struct ccwgroup_device *);
static int qeth_l2_stop(struct net_device *);
-static void qeth_l2_set_rx_mode(struct net_device *);
static void qeth_bridgeport_query_support(struct qeth_card *card);
static void qeth_bridge_state_change(struct qeth_card *card,
struct qeth_ipa_cmd *cmd);
static int qeth_l2_write_mac(struct qeth_card *card, u8 *mac)
{
- enum qeth_ipa_cmds cmd = is_multicast_ether_addr_64bits(mac) ?
+ enum qeth_ipa_cmds cmd = is_multicast_ether_addr(mac) ?
IPA_CMD_SETGMAC : IPA_CMD_SETVMAC;
int rc;
static int qeth_l2_remove_mac(struct qeth_card *card, u8 *mac)
{
- enum qeth_ipa_cmds cmd = is_multicast_ether_addr_64bits(mac) ?
+ enum qeth_ipa_cmds cmd = is_multicast_ether_addr(mac) ?
IPA_CMD_DELGMAC : IPA_CMD_DELVMAC;
int rc;
static int qeth_l2_get_cast_type(struct qeth_card *card, struct sk_buff *skb)
{
if (card->info.type == QETH_CARD_TYPE_OSN)
- return RTN_UNSPEC;
+ return RTN_UNICAST;
if (is_broadcast_ether_addr(skb->data))
return RTN_BROADCAST;
if (is_multicast_ether_addr(skb->data))
return RTN_MULTICAST;
- return RTN_UNSPEC;
+ return RTN_UNICAST;
}
static void qeth_l2_fill_header(struct qeth_hdr *hdr, struct sk_buff *skb,
rc = qeth_l2_send_setdelvlan(card, vid, IPA_CMD_DELVLAN);
kfree(tmpid);
}
- qeth_l2_set_rx_mode(card->dev);
return rc;
}
return -ERESTARTSYS;
}
+ /* avoid racing against concurrent state change: */
+ if (!mutex_trylock(&card->conf_mutex))
+ return -EAGAIN;
+
if (!qeth_card_hw_is_reachable(card)) {
ether_addr_copy(dev->dev_addr, addr->sa_data);
- return 0;
+ goto out_unlock;
}
/* don't register the same address twice */
if (ether_addr_equal_64bits(dev->dev_addr, addr->sa_data) &&
(card->info.mac_bits & QETH_LAYER2_MAC_REGISTERED))
- return 0;
+ goto out_unlock;
/* add the new address, switch over, drop the old */
rc = qeth_l2_send_setmac(card, addr->sa_data);
if (rc)
- return rc;
+ goto out_unlock;
ether_addr_copy(old_addr, dev->dev_addr);
ether_addr_copy(dev->dev_addr, addr->sa_data);
if (card->info.mac_bits & QETH_LAYER2_MAC_REGISTERED)
qeth_l2_remove_mac(card, old_addr);
card->info.mac_bits |= QETH_LAYER2_MAC_REGISTERED;
- return 0;
+
+out_unlock:
+ mutex_unlock(&card->conf_mutex);
+ return rc;
}
static void qeth_promisc_to_bridge(struct qeth_card *card)
int tx_bytes = skb->len;
int rc;
- if (card->qdio.do_prio_queueing || (cast_type &&
- card->info.is_multicast_different))
- queue = card->qdio.out_qs[qeth_get_priority_queue(card, skb,
- ipv, cast_type)];
- else
- queue = card->qdio.out_qs[card->qdio.default_out_queue];
-
if ((card->state != CARD_STATE_UP) || !card->lan_online) {
card->stats.tx_carrier_errors++;
goto tx_drop;
}
+ queue = qeth_get_tx_queue(card, skb, ipv, cast_type);
+
if (card->options.performance_stats) {
card->perf_stats.outbound_cnt++;
card->perf_stats.outbound_start_time = qeth_get_micros();
netif_carrier_off(card->dev);
qeth_set_allowed_threads(card, 0xffffffff, 0);
+
+ qeth_enable_hw_features(card->dev);
if (recover_flag == CARD_STATE_RECOVER) {
if (recovery_mode &&
card->info.type != QETH_CARD_TYPE_OSN) {
__qeth_l2_open(card->dev);
+ qeth_l2_set_rx_mode(card->dev);
} else {
rtnl_lock();
dev_open(card->dev);
rtnl_unlock();
}
- /* this also sets saved unicast addresses */
- qeth_l2_set_rx_mode(card->dev);
- rtnl_lock();
- qeth_recover_features(card->dev);
- rtnl_unlock();
}
/* let user_space know that device is online */
kobject_uevent(&gdev->dev.kobj, KOBJ_CHANGE);
return rc;
return qeth_bridgeport_makerc(card, &cbctl, IPA_SBP_QUERY_BRIDGE_PORTS);
}
-EXPORT_SYMBOL_GPL(qeth_bridgeport_query_ports);
static int qeth_bridgeport_set_cb(struct qeth_card *card,
struct qeth_reply *reply, unsigned long data)
rc = qdio_pnso_brinfo(schid, 0, &response, NULL, NULL);
return qeth_anset_makerc(card, rc, response);
}
-EXPORT_SYMBOL_GPL(qeth_bridgeport_an_set);
static bool qeth_bridgeport_is_in_use(struct qeth_card *card)
{
(cast_type == RTN_MULTICAST) ||
(cast_type == RTN_ANYCAST))
return cast_type;
- return RTN_UNSPEC;
+ return RTN_UNICAST;
}
rcu_read_unlock();
/* no neighbour (eg AF_PACKET), fall back to target's IP address ... */
if (be16_to_cpu(skb->protocol) == ETH_P_IPV6)
return ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr) ?
- RTN_MULTICAST : RTN_UNSPEC;
+ RTN_MULTICAST : RTN_UNICAST;
else if (be16_to_cpu(skb->protocol) == ETH_P_IP)
return ipv4_is_multicast(ip_hdr(skb)->daddr) ?
- RTN_MULTICAST : RTN_UNSPEC;
+ RTN_MULTICAST : RTN_UNICAST;
/* ... and MAC address */
if (ether_addr_equal_64bits(eth_hdr(skb)->h_dest, skb->dev->broadcast))
return RTN_MULTICAST;
/* default to unicast */
- return RTN_UNSPEC;
+ return RTN_UNICAST;
}
-static void qeth_l3_fill_af_iucv_hdr(struct qeth_card *card,
- struct qeth_hdr *hdr, struct sk_buff *skb)
+static void qeth_l3_fill_af_iucv_hdr(struct qeth_hdr *hdr, struct sk_buff *skb,
+ unsigned int data_len)
{
char daddr[16];
struct af_iucv_trans_hdr *iucv_hdr;
memset(hdr, 0, sizeof(struct qeth_hdr));
hdr->hdr.l3.id = QETH_HEADER_TYPE_LAYER3;
- hdr->hdr.l3.ext_flags = 0;
- hdr->hdr.l3.length = skb->len - ETH_HLEN;
+ hdr->hdr.l3.length = data_len;
hdr->hdr.l3.flags = QETH_HDR_IPV6 | QETH_CAST_UNICAST;
- iucv_hdr = (struct af_iucv_trans_hdr *) (skb->data + ETH_HLEN);
+ iucv_hdr = (struct af_iucv_trans_hdr *)(skb_mac_header(skb) + ETH_HLEN);
memset(daddr, 0, sizeof(daddr));
daddr[0] = 0xfe;
daddr[1] = 0x80;
hdr->hdr.l3.vlan_id = skb_vlan_tag_get(skb);
}
+ if (!skb_is_gso(skb) && skb->ip_summed == CHECKSUM_PARTIAL) {
+ qeth_tx_csum(skb, &hdr->hdr.l3.ext_flags, ipv);
+ if (card->options.performance_stats)
+ card->perf_stats.tx_csum++;
+ }
+
/* OSA only: */
if (!ipv) {
hdr->hdr.l3.flags = QETH_HDR_PASSTHRU;
return elements;
}
-static netdev_tx_t qeth_l3_hard_start_xmit(struct sk_buff *skb,
- struct net_device *dev)
+static int qeth_l3_xmit_offload(struct qeth_card *card, struct sk_buff *skb,
+ struct qeth_qdio_out_q *queue, int ipv,
+ int cast_type)
{
- int rc;
- __be16 *tag;
+ const unsigned int hw_hdr_len = sizeof(struct qeth_hdr);
+ unsigned int frame_len, nr_frags;
+ unsigned char eth_hdr[ETH_HLEN];
+ unsigned int hdr_elements = 0;
struct qeth_hdr *hdr = NULL;
- int hdr_elements = 0;
- int elements;
- struct qeth_card *card = dev->ml_priv;
- struct sk_buff *new_skb = NULL;
- int ipv = qeth_get_ip_version(skb);
- int cast_type = qeth_l3_get_cast_type(skb);
- struct qeth_qdio_out_q *queue =
- card->qdio.out_qs[card->qdio.do_prio_queueing
- || (cast_type && card->info.is_multicast_different) ?
- qeth_get_priority_queue(card, skb, ipv, cast_type) :
- card->qdio.default_out_queue];
- int tx_bytes = skb->len;
+ int elements, push_len, rc;
unsigned int hd_len = 0;
- bool use_tso;
- int data_offset = -1;
- unsigned int nr_frags;
-
- if (((card->info.type == QETH_CARD_TYPE_IQD) &&
- (((card->options.cq != QETH_CQ_ENABLED) && !ipv) ||
- ((card->options.cq == QETH_CQ_ENABLED) &&
- (be16_to_cpu(skb->protocol) != ETH_P_AF_IUCV)))) ||
- card->options.sniffer)
- goto tx_drop;
- if ((card->state != CARD_STATE_UP) || !card->lan_online) {
- card->stats.tx_carrier_errors++;
- goto tx_drop;
+ /* compress skb to fit into one IO buffer: */
+ if (!qeth_get_elements_no(card, skb, 0, 0)) {
+ rc = skb_linearize(skb);
+
+ if (card->options.performance_stats) {
+ if (rc)
+ card->perf_stats.tx_linfail++;
+ else
+ card->perf_stats.tx_lin++;
+ }
+ if (rc)
+ return rc;
}
- if ((cast_type == RTN_BROADCAST) &&
- (card->info.broadcast_capable == 0))
- goto tx_drop;
+ /* re-use the L2 header area for the HW header: */
+ rc = skb_cow_head(skb, hw_hdr_len - ETH_HLEN);
+ if (rc)
+ return rc;
+ skb_copy_from_linear_data(skb, eth_hdr, ETH_HLEN);
+ skb_pull(skb, ETH_HLEN);
+ frame_len = skb->len;
+ nr_frags = skb_shinfo(skb)->nr_frags;
- if (card->options.performance_stats) {
- card->perf_stats.outbound_cnt++;
- card->perf_stats.outbound_start_time = qeth_get_micros();
+ push_len = qeth_push_hdr(skb, &hdr, hw_hdr_len);
+ if (push_len < 0)
+ return push_len;
+ if (!push_len) {
+ /* hdr was added discontiguous from skb->data */
+ hd_len = hw_hdr_len;
+ hdr_elements = 1;
}
- /* Ignore segment size from skb_is_gso(), 1 page is always used. */
- use_tso = skb_is_gso(skb) &&
- (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4);
+ elements = qeth_get_elements_no(card, skb, hdr_elements, 0);
+ if (!elements) {
+ rc = -E2BIG;
+ goto out;
+ }
+ elements += hdr_elements;
- if (card->info.type == QETH_CARD_TYPE_IQD) {
- new_skb = skb;
- data_offset = ETH_HLEN;
- hd_len = sizeof(*hdr);
- hdr = kmem_cache_alloc(qeth_core_header_cache, GFP_ATOMIC);
- if (!hdr)
- goto tx_drop;
- hdr_elements++;
- } else {
- /* create a clone with writeable headroom */
- new_skb = skb_realloc_headroom(skb, sizeof(struct qeth_hdr_tso)
- + VLAN_HLEN);
- if (!new_skb)
- goto tx_drop;
+ if (skb->protocol == htons(ETH_P_AF_IUCV))
+ qeth_l3_fill_af_iucv_hdr(hdr, skb, frame_len);
+ else
+ qeth_l3_fill_header(card, hdr, skb, ipv, cast_type, frame_len);
- if (ipv == 4) {
- skb_pull(new_skb, ETH_HLEN);
+ if (IS_IQD(card)) {
+ rc = qeth_do_send_packet_fast(queue, skb, hdr, 0, hd_len);
+ } else {
+ /* TODO: drop skb_orphan() once TX completion is fast enough */
+ skb_orphan(skb);
+ rc = qeth_do_send_packet(card, queue, skb, hdr, 0, hd_len,
+ elements);
+ }
+out:
+ if (!rc) {
+ if (card->options.performance_stats && nr_frags) {
+ card->perf_stats.sg_skbs_sent++;
+ /* nr_frags + skb->data */
+ card->perf_stats.sg_frags_sent += nr_frags + 1;
}
-
- if (ipv != 4 && skb_vlan_tag_present(new_skb)) {
- skb_push(new_skb, VLAN_HLEN);
- skb_copy_to_linear_data(new_skb, new_skb->data + 4, 4);
- skb_copy_to_linear_data_offset(new_skb, 4,
- new_skb->data + 8, 4);
- skb_copy_to_linear_data_offset(new_skb, 8,
- new_skb->data + 12, 4);
- tag = (__be16 *)(new_skb->data + 12);
- *tag = cpu_to_be16(ETH_P_8021Q);
- *(tag + 1) = cpu_to_be16(skb_vlan_tag_get(new_skb));
+ } else {
+ if (!push_len)
+ kmem_cache_free(qeth_core_header_cache, hdr);
+ if (rc == -EBUSY) {
+ /* roll back to ETH header */
+ skb_pull(skb, push_len);
+ skb_push(skb, ETH_HLEN);
+ skb_copy_to_linear_data(skb, eth_hdr, ETH_HLEN);
}
}
+ return rc;
+}
- netif_stop_queue(dev);
+static int qeth_l3_xmit(struct qeth_card *card, struct sk_buff *skb,
+ struct qeth_qdio_out_q *queue, int ipv, int cast_type)
+{
+ unsigned int hd_len, nr_frags;
+ int elements, len, rc;
+ __be16 *tag;
+ struct qeth_hdr *hdr = NULL;
+ int hdr_elements = 0;
+ struct sk_buff *new_skb = NULL;
+ int tx_bytes = skb->len;
+ bool use_tso;
+
+ /* Ignore segment size from skb_is_gso(), 1 page is always used. */
+ use_tso = skb_is_gso(skb) &&
+ (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4);
+
+ /* create a clone with writeable headroom */
+ new_skb = skb_realloc_headroom(skb, sizeof(struct qeth_hdr_tso) +
+ VLAN_HLEN);
+ if (!new_skb)
+ return -ENOMEM;
+
+ if (ipv == 4) {
+ skb_pull(new_skb, ETH_HLEN);
+ } else if (skb_vlan_tag_present(new_skb)) {
+ skb_push(new_skb, VLAN_HLEN);
+ skb_copy_to_linear_data(new_skb, new_skb->data + 4, 4);
+ skb_copy_to_linear_data_offset(new_skb, 4,
+ new_skb->data + 8, 4);
+ skb_copy_to_linear_data_offset(new_skb, 8,
+ new_skb->data + 12, 4);
+ tag = (__be16 *)(new_skb->data + 12);
+ *tag = cpu_to_be16(ETH_P_8021Q);
+ *(tag + 1) = cpu_to_be16(skb_vlan_tag_get(new_skb));
+ }
/* fix hardware limitation: as long as we do not have sbal
* chaining we can not send long frag lists
*/
- if ((card->info.type != QETH_CARD_TYPE_IQD) &&
- ((use_tso && !qeth_l3_get_elements_no_tso(card, new_skb, 1)) ||
- (!use_tso && !qeth_get_elements_no(card, new_skb, 0, 0)))) {
- int lin_rc = skb_linearize(new_skb);
+ if ((use_tso && !qeth_l3_get_elements_no_tso(card, new_skb, 1)) ||
+ (!use_tso && !qeth_get_elements_no(card, new_skb, 0, 0))) {
+ rc = skb_linearize(new_skb);
if (card->options.performance_stats) {
- if (lin_rc)
+ if (rc)
card->perf_stats.tx_linfail++;
else
card->perf_stats.tx_lin++;
}
- if (lin_rc)
- goto tx_drop;
+ if (rc)
+ goto out;
}
nr_frags = skb_shinfo(new_skb)->nr_frags;
qeth_tso_fill_header(card, hdr, new_skb);
hdr_elements++;
} else {
- if (data_offset < 0) {
- hdr = skb_push(new_skb, sizeof(struct qeth_hdr));
- qeth_l3_fill_header(card, hdr, new_skb, ipv, cast_type,
- new_skb->len -
- sizeof(struct qeth_hdr));
- } else {
- if (be16_to_cpu(new_skb->protocol) == ETH_P_AF_IUCV)
- qeth_l3_fill_af_iucv_hdr(card, hdr, new_skb);
- else {
- qeth_l3_fill_header(card, hdr, new_skb, ipv,
- cast_type,
- new_skb->len - data_offset);
- }
- }
-
- if (new_skb->ip_summed == CHECKSUM_PARTIAL) {
- qeth_tx_csum(new_skb, &hdr->hdr.l3.ext_flags, ipv);
- if (card->options.performance_stats)
- card->perf_stats.tx_csum++;
- }
+ hdr = skb_push(new_skb, sizeof(struct qeth_hdr));
+ qeth_l3_fill_header(card, hdr, new_skb, ipv, cast_type,
+ new_skb->len - sizeof(struct qeth_hdr));
}
elements = use_tso ?
qeth_l3_get_elements_no_tso(card, new_skb, hdr_elements) :
- qeth_get_elements_no(card, new_skb, hdr_elements,
- (data_offset > 0) ? data_offset : 0);
+ qeth_get_elements_no(card, new_skb, hdr_elements, 0);
if (!elements) {
- if (data_offset >= 0)
- kmem_cache_free(qeth_core_header_cache, hdr);
- goto tx_drop;
+ rc = -E2BIG;
+ goto out;
}
elements += hdr_elements;
- if (card->info.type != QETH_CARD_TYPE_IQD) {
- int len;
- if (use_tso) {
- hd_len = sizeof(struct qeth_hdr_tso) +
- ip_hdrlen(new_skb) + tcp_hdrlen(new_skb);
- len = hd_len;
- } else {
- len = sizeof(struct qeth_hdr_layer3);
- }
-
- if (qeth_hdr_chk_and_bounce(new_skb, &hdr, len))
- goto tx_drop;
- rc = qeth_do_send_packet(card, queue, new_skb, hdr, hd_len,
- hd_len, elements);
- } else
- rc = qeth_do_send_packet_fast(queue, new_skb, hdr, data_offset,
- hd_len);
+ if (use_tso) {
+ hd_len = sizeof(struct qeth_hdr_tso) +
+ ip_hdrlen(new_skb) + tcp_hdrlen(new_skb);
+ len = hd_len;
+ } else {
+ hd_len = 0;
+ len = sizeof(struct qeth_hdr_layer3);
+ }
+ if (qeth_hdr_chk_and_bounce(new_skb, &hdr, len)) {
+ rc = -EINVAL;
+ goto out;
+ }
+ rc = qeth_do_send_packet(card, queue, new_skb, hdr, hd_len, hd_len,
+ elements);
+out:
if (!rc) {
- card->stats.tx_packets++;
- card->stats.tx_bytes += tx_bytes;
if (new_skb != skb)
dev_kfree_skb_any(skb);
if (card->options.performance_stats) {
card->perf_stats.sg_frags_sent += nr_frags + 1;
}
}
- rc = NETDEV_TX_OK;
} else {
- if (data_offset >= 0)
- kmem_cache_free(qeth_core_header_cache, hdr);
+ if (new_skb != skb)
+ dev_kfree_skb_any(new_skb);
+ }
+ return rc;
+}
- if (rc == -EBUSY) {
- if (new_skb != skb)
- dev_kfree_skb_any(new_skb);
- return NETDEV_TX_BUSY;
- } else
+static netdev_tx_t qeth_l3_hard_start_xmit(struct sk_buff *skb,
+ struct net_device *dev)
+{
+ int cast_type = qeth_l3_get_cast_type(skb);
+ struct qeth_card *card = dev->ml_priv;
+ int ipv = qeth_get_ip_version(skb);
+ struct qeth_qdio_out_q *queue;
+ int tx_bytes = skb->len;
+ int rc;
+
+ if (IS_IQD(card)) {
+ if (card->options.sniffer)
+ goto tx_drop;
+ if ((card->options.cq != QETH_CQ_ENABLED && !ipv) ||
+ (card->options.cq == QETH_CQ_ENABLED &&
+ skb->protocol != htons(ETH_P_AF_IUCV)))
goto tx_drop;
}
- netif_wake_queue(dev);
- if (card->options.performance_stats)
- card->perf_stats.outbound_time += qeth_get_micros() -
- card->perf_stats.outbound_start_time;
- return rc;
+ if (card->state != CARD_STATE_UP || !card->lan_online) {
+ card->stats.tx_carrier_errors++;
+ goto tx_drop;
+ }
+
+ if (cast_type == RTN_BROADCAST && !card->info.broadcast_capable)
+ goto tx_drop;
+
+ queue = qeth_get_tx_queue(card, skb, ipv, cast_type);
+
+ if (card->options.performance_stats) {
+ card->perf_stats.outbound_cnt++;
+ card->perf_stats.outbound_start_time = qeth_get_micros();
+ }
+ netif_stop_queue(dev);
+
+ if (IS_IQD(card) || (!skb_is_gso(skb) && ipv == 4))
+ rc = qeth_l3_xmit_offload(card, skb, queue, ipv, cast_type);
+ else
+ rc = qeth_l3_xmit(card, skb, queue, ipv, cast_type);
+
+ if (!rc) {
+ card->stats.tx_packets++;
+ card->stats.tx_bytes += tx_bytes;
+ if (card->options.performance_stats)
+ card->perf_stats.outbound_time += qeth_get_micros() -
+ card->perf_stats.outbound_start_time;
+ netif_wake_queue(dev);
+ return NETDEV_TX_OK;
+ } else if (rc == -EBUSY) {
+ return NETDEV_TX_BUSY;
+ } /* else fall through */
tx_drop:
card->stats.tx_dropped++;
card->stats.tx_errors++;
- if ((new_skb != skb) && new_skb)
- dev_kfree_skb_any(new_skb);
dev_kfree_skb_any(skb);
netif_wake_queue(dev);
return NETDEV_TX_OK;
if (!(card->info.unique_id & UNIQUE_ID_NOT_BY_CARD))
card->dev->dev_id = card->info.unique_id & 0xffff;
- card->dev->hw_features |= NETIF_F_SG;
- card->dev->vlan_features |= NETIF_F_SG;
-
if (!card->info.guestlan) {
card->dev->features |= NETIF_F_SG;
card->dev->hw_features |= NETIF_F_TSO |
return -ENODEV;
card->dev->flags |= IFF_NOARP;
card->dev->netdev_ops = &qeth_l3_netdev_ops;
+
rc = qeth_l3_iqd_read_initial_mac(card);
if (rc)
return rc;
card->dev->max_mtu = ETH_MAX_MTU;
card->dev->dev_port = card->info.portno;
card->dev->ethtool_ops = &qeth_l3_ethtool_ops;
+ card->dev->priv_flags &= ~IFF_TX_SKB_SHARING;
+ card->dev->needed_headroom = sizeof(struct qeth_hdr) - ETH_HLEN;
card->dev->features |= NETIF_F_HW_VLAN_CTAG_TX |
NETIF_F_HW_VLAN_CTAG_RX |
NETIF_F_HW_VLAN_CTAG_FILTER;
+ card->dev->hw_features |= NETIF_F_SG;
+ card->dev->vlan_features |= NETIF_F_SG;
+
netif_keep_dst(card->dev);
- netif_set_gso_max_size(card->dev, (QETH_MAX_BUFFER_ELEMENTS(card) - 1) *
- PAGE_SIZE);
+ if (card->dev->hw_features & NETIF_F_TSO)
+ netif_set_gso_max_size(card->dev,
+ PAGE_SIZE * (QETH_MAX_BUFFER_ELEMENTS(card) - 1));
SET_NETDEV_DEV(card->dev, &card->gdev->dev);
netif_napi_add(card->dev, &card->napi, qeth_poll, QETH_NAPI_WEIGHT);
netif_carrier_on(card->dev);
else
netif_carrier_off(card->dev);
+
+ qeth_enable_hw_features(card->dev);
if (recover_flag == CARD_STATE_RECOVER) {
rtnl_lock();
- if (recovery_mode)
+ if (recovery_mode) {
__qeth_l3_open(card->dev);
- else
+ qeth_l3_set_rx_mode(card->dev);
+ } else {
dev_open(card->dev);
- qeth_l3_set_rx_mode(card->dev);
- qeth_recover_features(card->dev);
+ }
rtnl_unlock();
}
qeth_trace_features(card);
ioa_cfg->hrrq[i].allow_interrupts = 0;
spin_unlock(&ioa_cfg->hrrq[i]._lock);
}
- wmb();
/* Set interrupt mask to stop all new interrupts */
if (ioa_cfg->sis64)
ioa_cfg->hrrq[i].allow_interrupts = 1;
spin_unlock(&ioa_cfg->hrrq[i]._lock);
}
- wmb();
if (ioa_cfg->sis64) {
/* Set the adapter to the correct endian mode. */
writel(IPR_ENDIAN_SWAP_KEY, ioa_cfg->regs.endian_swap_reg);
void qlt_schedule_sess_for_deletion(struct fc_port *sess)
{
struct qla_tgt *tgt = sess->tgt;
- struct qla_hw_data *ha = sess->vha->hw;
unsigned long flags;
if (sess->disc_state == DSC_DELETE_PEND)
return;
}
- spin_lock_irqsave(&ha->tgt.sess_lock, flags);
if (sess->deleted == QLA_SESS_DELETED)
sess->logout_on_delete = 0;
+ spin_lock_irqsave(&sess->vha->work_lock, flags);
if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) {
- spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
+ spin_unlock_irqrestore(&sess->vha->work_lock, flags);
return;
}
sess->deleted = QLA_SESS_DELETION_IN_PROGRESS;
- spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
+ spin_unlock_irqrestore(&sess->vha->work_lock, flags);
sess->disc_state = DSC_DELETE_PEND;
int k = sdebug_add_host;
stop_all_queued();
- free_all_queued();
for (; k; k--)
sdebug_remove_adapter();
+ free_all_queued();
driver_unregister(&sdebug_driverfs_driver);
bus_unregister(&pseudo_lld_bus);
root_device_unregister(pseudo_primary);
/* the blk_end_sync_io() doesn't check the error */
if (inflight)
- blk_mq_complete_request(req);
+ __blk_complete_request(req);
return BLK_EH_DONE;
}
static int scsifront_sdev_configure(struct scsi_device *sdev)
{
struct vscsifrnt_info *info = shost_priv(sdev->host);
+ int err;
- if (info && current == info->curr)
- xenbus_printf(XBT_NIL, info->dev->nodename,
+ if (info && current == info->curr) {
+ err = xenbus_printf(XBT_NIL, info->dev->nodename,
info->dev_state_path, "%d", XenbusStateConnected);
+ if (err) {
+ xenbus_dev_error(info->dev, err,
+ "%s: writing dev_state_path", __func__);
+ return err;
+ }
+ }
return 0;
}
static void scsifront_sdev_destroy(struct scsi_device *sdev)
{
struct vscsifrnt_info *info = shost_priv(sdev->host);
+ int err;
- if (info && current == info->curr)
- xenbus_printf(XBT_NIL, info->dev->nodename,
+ if (info && current == info->curr) {
+ err = xenbus_printf(XBT_NIL, info->dev->nodename,
info->dev_state_path, "%d", XenbusStateClosed);
+ if (err)
+ xenbus_dev_error(info->dev, err,
+ "%s: writing dev_state_path", __func__);
+ }
}
static struct scsi_host_template scsifront_sht = {
if (scsi_add_device(info->host, chn, tgt, lun)) {
dev_err(&dev->dev, "scsi_add_device\n");
- xenbus_printf(XBT_NIL, dev->nodename,
+ err = xenbus_printf(XBT_NIL, dev->nodename,
info->dev_state_path,
"%d", XenbusStateClosed);
+ if (err)
+ xenbus_dev_error(dev, err,
+ "%s: writing dev_state_path", __func__);
}
break;
case VSCSIFRONT_OP_DEL_LUN:
}
break;
case VSCSIFRONT_OP_READD_LUN:
- if (device_state == XenbusStateConnected)
- xenbus_printf(XBT_NIL, dev->nodename,
+ if (device_state == XenbusStateConnected) {
+ err = xenbus_printf(XBT_NIL, dev->nodename,
info->dev_state_path,
"%d", XenbusStateConnected);
+ if (err)
+ xenbus_dev_error(dev, err,
+ "%s: writing dev_state_path", __func__);
+ }
break;
default:
break;
#define GPC_M4_PU_PDN_FLG 0x1bc
-
-#define PGC_MIPI 4
-#define PGC_PCIE 5
-#define PGC_USB_HSIC 8
+/*
+ * The PGC offset values in Reference Manual
+ * (Rev. 1, 01/2018 and the older ones) GPC chapter's
+ * GPC_PGC memory map are incorrect, below offset
+ * values are from design RTL.
+ */
+#define PGC_MIPI 16
+#define PGC_PCIE 17
+#define PGC_USB_HSIC 20
#define GPC_PGC_CTRL(n) (0x800 + (n) * 0x40)
#define GPC_PGC_SR(n) (GPC_PGC_CTRL(n) + 0xc)
config QCOM_COMMAND_DB
bool "Qualcomm Command DB"
- depends on (ARCH_QCOM && OF) || COMPILE_TEST
+ depends on ARCH_QCOM || COMPILE_TEST
+ depends on OF_RESERVED_MEM
help
Command DB queries shared memory by key string for shared system
resources. Platform drivers that require to set state of a shared
static bool has_cpg_mstp;
-static void __init rcar_sysc_pd_setup(struct rcar_sysc_pd *pd)
+static int __init rcar_sysc_pd_setup(struct rcar_sysc_pd *pd)
{
struct generic_pm_domain *genpd = &pd->genpd;
const char *name = pd->genpd.name;
struct dev_power_governor *gov = &simple_qos_governor;
+ int error;
if (pd->flags & PD_CPU) {
/*
rcar_sysc_power_up(&pd->ch);
finalize:
- pm_genpd_init(genpd, gov, false);
+ error = pm_genpd_init(genpd, gov, false);
+ if (error)
+ pr_err("Failed to init PM domain %s: %d\n", name, error);
+
+ return error;
}
static const struct of_device_id rcar_sysc_matches[] __initconst = {
pr_debug("%pOF: syscier = 0x%08x\n", np, syscier);
iowrite32(syscier, base + SYSCIER);
+ /*
+ * First, create all PM domains
+ */
for (i = 0; i < info->num_areas; i++) {
const struct rcar_sysc_area *area = &info->areas[i];
struct rcar_sysc_pd *pd;
pd->ch.isr_bit = area->isr_bit;
pd->flags = area->flags;
- rcar_sysc_pd_setup(pd);
- if (area->parent >= 0)
- pm_genpd_add_subdomain(domains->domains[area->parent],
- &pd->genpd);
+ error = rcar_sysc_pd_setup(pd);
+ if (error)
+ goto out_put;
domains->domains[area->isr_bit] = &pd->genpd;
}
+ /*
+ * Second, link all PM domains to their parents
+ */
+ for (i = 0; i < info->num_areas; i++) {
+ const struct rcar_sysc_area *area = &info->areas[i];
+
+ if (!area->name || area->parent < 0)
+ continue;
+
+ error = pm_genpd_add_subdomain(domains->domains[area->parent],
+ domains->domains[area->isr_bit]);
+ if (error)
+ pr_warn("Failed to add PM subdomain %s to parent %u\n",
+ area->name, area->parent);
+ }
+
error = of_genpd_add_provider_onecell(np, &domains->onecell_data);
out_put:
struct page **tmp = pages;
if (!pages)
- return NULL;
+ return ERR_PTR(-ENOMEM);
if (buffer->flags & ION_FLAG_CACHED)
pgprot = PAGE_KERNEL;
/* Make sure D/A update mode is direct update */
outb(0, dev->iobase + DAQP_AUX_REG);
- for (i = 0; i > insn->n; i++) {
+ for (i = 0; i < insn->n; i++) {
unsigned int val = data[i];
int ret;
return NETDEV_TX_OK;
}
-static u16 xlr_net_select_queue(struct net_device *ndev, struct sk_buff *skb,
- void *accel_priv,
- select_queue_fallback_t fallback)
-{
- return (u16)smp_processor_id();
-}
-
static void xlr_hw_set_mac_addr(struct net_device *ndev)
{
struct xlr_net_priv *priv = netdev_priv(ndev);
.ndo_open = xlr_net_open,
.ndo_stop = xlr_net_stop,
.ndo_start_xmit = xlr_net_start_xmit,
- .ndo_select_queue = xlr_net_select_queue,
+ .ndo_select_queue = dev_pick_tx_cpu_id,
.ndo_set_mac_address = xlr_net_set_mac_addr,
.ndo_set_rx_mode = xlr_set_rx_mode,
.ndo_get_stats64 = xlr_stats,
* According to IEEE802.11n spec size varies from 8K to 64K (in powers of 2)
*/
#define IEEE80211_MIN_AMPDU_BUF 0x8
-#define IEEE80211_MAX_AMPDU_BUF 0x40
#define OP_MODE_PURE 0
}
static u16 rtw_select_queue(struct net_device *dev, struct sk_buff *skb,
- void *accel_priv, select_queue_fallback_t fallback)
+ struct net_device *sb_dev,
+ select_queue_fallback_t fallback)
{
struct adapter *padapter = rtw_netdev_priv(dev);
struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
* According to IEEE802.11n spec size varies from 8K to 64K (in powers of 2)
*/
#define IEEE80211_MIN_AMPDU_BUF 0x8
-#define IEEE80211_MAX_AMPDU_BUF 0x40
/* Spatial Multiplexing Power Save Modes */
* According to IEEE802.11n spec size varies from 8K to 64K (in powers of 2)
*/
#define IEEE80211_MIN_AMPDU_BUF 0x8
-#define IEEE80211_MAX_AMPDU_BUF 0x40
/* Spatial Multiplexing Power Save Modes */
}
-static u16 rtw_select_queue(struct net_device *dev, struct sk_buff *skb
- , void *accel_priv
- , select_queue_fallback_t fallback
-)
+static u16 rtw_select_queue(struct net_device *dev, struct sk_buff *skb,
+ struct net_device *sb_dev,
+ select_queue_fallback_t fallback)
{
struct adapter *padapter = rtw_netdev_priv(dev);
struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
reject_agg, ctrl_agg_size, agg_size);
rtlpriv->hw->max_rx_aggregation_subframes =
- (ctrl_agg_size ? agg_size : IEEE80211_MAX_AMPDU_BUF);
+ (ctrl_agg_size ? agg_size : IEEE80211_MAX_AMPDU_BUF_HT);
}
/*********************************************************
config TYPEC_RT1711H
tristate "Richtek RT1711H Type-C chip driver"
+ depends on I2C
select TYPEC_TCPCI
help
Richtek RT1711H Type-C chip driver that works with
}
static void gather_data_area(struct tcmu_dev *udev, struct tcmu_cmd *cmd,
- bool bidi)
+ bool bidi, uint32_t read_len)
{
struct se_cmd *se_cmd = cmd->se_cmd;
int i, dbi;
for_each_sg(data_sg, sg, data_nents, i) {
int sg_remaining = sg->length;
to = kmap_atomic(sg_page(sg)) + sg->offset;
- while (sg_remaining > 0) {
+ while (sg_remaining > 0 && read_len > 0) {
if (block_remaining == 0) {
if (from)
kunmap_atomic(from);
}
copy_bytes = min_t(size_t, sg_remaining,
block_remaining);
+ if (read_len < copy_bytes)
+ copy_bytes = read_len;
offset = DATA_BLOCK_SIZE - block_remaining;
tcmu_flush_dcache_range(from, copy_bytes);
memcpy(to + sg->length - sg_remaining, from + offset,
sg_remaining -= copy_bytes;
block_remaining -= copy_bytes;
+ read_len -= copy_bytes;
}
kunmap_atomic(to - sg->offset);
+ if (read_len == 0)
+ break;
}
if (from)
kunmap_atomic(from);
{
struct se_cmd *se_cmd = cmd->se_cmd;
struct tcmu_dev *udev = cmd->tcmu_dev;
+ bool read_len_valid = false;
+ uint32_t read_len = se_cmd->data_length;
/*
* cmd has been completed already from timeout, just reclaim
pr_warn("TCMU: Userspace set UNKNOWN_OP flag on se_cmd %p\n",
cmd->se_cmd);
entry->rsp.scsi_status = SAM_STAT_CHECK_CONDITION;
- } else if (entry->rsp.scsi_status == SAM_STAT_CHECK_CONDITION) {
+ goto done;
+ }
+
+ if (se_cmd->data_direction == DMA_FROM_DEVICE &&
+ (entry->hdr.uflags & TCMU_UFLAG_READ_LEN) && entry->rsp.read_len) {
+ read_len_valid = true;
+ if (entry->rsp.read_len < read_len)
+ read_len = entry->rsp.read_len;
+ }
+
+ if (entry->rsp.scsi_status == SAM_STAT_CHECK_CONDITION) {
transport_copy_sense_to_cmd(se_cmd, entry->rsp.sense_buffer);
- } else if (se_cmd->se_cmd_flags & SCF_BIDI) {
+ if (!read_len_valid )
+ goto done;
+ else
+ se_cmd->se_cmd_flags |= SCF_TREAT_READ_AS_NORMAL;
+ }
+ if (se_cmd->se_cmd_flags & SCF_BIDI) {
/* Get Data-In buffer before clean up */
- gather_data_area(udev, cmd, true);
+ gather_data_area(udev, cmd, true, read_len);
} else if (se_cmd->data_direction == DMA_FROM_DEVICE) {
- gather_data_area(udev, cmd, false);
+ gather_data_area(udev, cmd, false, read_len);
} else if (se_cmd->data_direction == DMA_TO_DEVICE) {
/* TODO: */
} else if (se_cmd->data_direction != DMA_NONE) {
se_cmd->data_direction);
}
- target_complete_cmd(cmd->se_cmd, entry->rsp.scsi_status);
+done:
+ if (read_len_valid) {
+ pr_debug("read_len = %d\n", read_len);
+ target_complete_cmd_with_length(cmd->se_cmd,
+ entry->rsp.scsi_status, read_len);
+ } else
+ target_complete_cmd(cmd->se_cmd, entry->rsp.scsi_status);
out:
cmd->se_cmd = NULL;
/* Initialise the mailbox of the ring buffer */
mb = udev->mb_addr;
mb->version = TCMU_MAILBOX_VERSION;
- mb->flags = TCMU_MAILBOX_FLAG_CAP_OOOC;
+ mb->flags = TCMU_MAILBOX_FLAG_CAP_OOOC | TCMU_MAILBOX_FLAG_CAP_READ_LEN;
mb->cmdr_off = CMDR_OFF;
mb->cmdr_size = udev->cmdr_size;
struct mutex output_lock;
};
+#define MASK(x) ((x) & (N_TTY_BUF_SIZE - 1))
+
static inline size_t read_cnt(struct n_tty_data *ldata)
{
return ldata->read_head - ldata->read_tail;
static inline unsigned char echo_buf(struct n_tty_data *ldata, size_t i)
{
+ smp_rmb(); /* Matches smp_wmb() in add_echo_byte(). */
return ldata->echo_buf[i & (N_TTY_BUF_SIZE - 1)];
}
static void reset_buffer_flags(struct n_tty_data *ldata)
{
ldata->read_head = ldata->canon_head = ldata->read_tail = 0;
- ldata->echo_head = ldata->echo_tail = ldata->echo_commit = 0;
ldata->commit_head = 0;
- ldata->echo_mark = 0;
ldata->line_start = 0;
ldata->erasing = 0;
old_space = space = tty_write_room(tty);
tail = ldata->echo_tail;
- while (ldata->echo_commit != tail) {
+ while (MASK(ldata->echo_commit) != MASK(tail)) {
c = echo_buf(ldata, tail);
if (c == ECHO_OP_START) {
unsigned char op;
int no_space_left = 0;
+ /*
+ * Since add_echo_byte() is called without holding
+ * output_lock, we might see only portion of multi-byte
+ * operation.
+ */
+ if (MASK(ldata->echo_commit) == MASK(tail + 1))
+ goto not_yet_stored;
/*
* If the buffer byte is the start of a multi-byte
* operation, get the next byte, which is either the
unsigned int num_chars, num_bs;
case ECHO_OP_ERASE_TAB:
+ if (MASK(ldata->echo_commit) == MASK(tail + 2))
+ goto not_yet_stored;
num_chars = echo_buf(ldata, tail + 2);
/*
/* If the echo buffer is nearly full (so that the possibility exists
* of echo overrun before the next commit), then discard enough
* data at the tail to prevent a subsequent overrun */
- while (ldata->echo_commit - tail >= ECHO_DISCARD_WATERMARK) {
+ while (ldata->echo_commit > tail &&
+ ldata->echo_commit - tail >= ECHO_DISCARD_WATERMARK) {
if (echo_buf(ldata, tail) == ECHO_OP_START) {
if (echo_buf(ldata, tail + 1) == ECHO_OP_ERASE_TAB)
tail += 3;
tail++;
}
+ not_yet_stored:
ldata->echo_tail = tail;
return old_space - space;
}
size_t nr, old, echoed;
size_t head;
+ mutex_lock(&ldata->output_lock);
head = ldata->echo_head;
ldata->echo_mark = head;
old = ldata->echo_commit - ldata->echo_tail;
* is over the threshold (and try again each time another
* block is accumulated) */
nr = head - ldata->echo_tail;
- if (nr < ECHO_COMMIT_WATERMARK || (nr % ECHO_BLOCK > old % ECHO_BLOCK))
+ if (nr < ECHO_COMMIT_WATERMARK ||
+ (nr % ECHO_BLOCK > old % ECHO_BLOCK)) {
+ mutex_unlock(&ldata->output_lock);
return;
+ }
- mutex_lock(&ldata->output_lock);
ldata->echo_commit = head;
echoed = __process_echoes(tty);
mutex_unlock(&ldata->output_lock);
static inline void add_echo_byte(unsigned char c, struct n_tty_data *ldata)
{
- *echo_buf_addr(ldata, ldata->echo_head++) = c;
+ *echo_buf_addr(ldata, ldata->echo_head) = c;
+ smp_wmb(); /* Matches smp_rmb() in echo_buf(). */
+ ldata->echo_head++;
}
/**
}
seen_alnums = 0;
- while (ldata->read_head != ldata->canon_head) {
+ while (MASK(ldata->read_head) != MASK(ldata->canon_head)) {
head = ldata->read_head;
/* erase a single possibly multibyte character */
do {
head--;
c = read_buf(ldata, head);
- } while (is_continuation(c, tty) && head != ldata->canon_head);
+ } while (is_continuation(c, tty) &&
+ MASK(head) != MASK(ldata->canon_head));
/* do not partially erase */
if (is_continuation(c, tty))
* This info is used to go back the correct
* number of columns.
*/
- while (tail != ldata->canon_head) {
+ while (MASK(tail) != MASK(ldata->canon_head)) {
tail--;
c = read_buf(ldata, tail);
if (c == '\t') {
finish_erasing(ldata);
echo_char(c, tty);
echo_char_raw('\n', ldata);
- while (tail != ldata->read_head) {
+ while (MASK(tail) != MASK(ldata->read_head)) {
echo_char(read_buf(ldata, tail), tty);
tail++;
}
struct n_tty_data *ldata;
/* Currently a malloc failure here can panic */
- ldata = vmalloc(sizeof(*ldata));
+ ldata = vzalloc(sizeof(*ldata));
if (!ldata)
- goto err;
+ return -ENOMEM;
ldata->overrun_time = jiffies;
mutex_init(&ldata->atomic_read_lock);
mutex_init(&ldata->output_lock);
tty->disc_data = ldata;
- reset_buffer_flags(tty->disc_data);
- ldata->column = 0;
- ldata->canon_column = 0;
- ldata->num_overrun = 0;
- ldata->no_room = 0;
- ldata->lnext = 0;
tty->closing = 0;
/* indicate buffer work may resume */
clear_bit(TTY_LDISC_HALTED, &tty->flags);
n_tty_set_termios(tty, NULL);
tty_unthrottle(tty);
-
return 0;
-err:
- return -ENOMEM;
}
static inline int input_available_p(struct tty_struct *tty, int poll)
tail = ldata->read_tail;
nr = head - tail;
/* Skip EOF-chars.. */
- while (head != tail) {
+ while (MASK(head) != MASK(tail)) {
if (test_bit(tail & (N_TTY_BUF_SIZE - 1), ldata->read_flags) &&
read_buf(ldata, tail) == __DISABLED_CHAR)
nr--;
static void __exit serdev_exit(void)
{
bus_unregister(&serdev_bus_type);
+ ida_destroy(&ctrl_ida);
}
module_exit(serdev_exit);
/* multi-io cards handled by parport_serial */
{ PCI_DEVICE(0x4348, 0x7053), }, /* WCH CH353 2S1P */
{ PCI_DEVICE(0x4348, 0x5053), }, /* WCH CH353 1S1P */
- { PCI_DEVICE(0x4348, 0x7173), }, /* WCH CH355 4S */
{ PCI_DEVICE(0x1c00, 0x3250), }, /* WCH CH382 2S1P */
- { PCI_DEVICE(0x1c00, 0x3470), }, /* WCH CH384 4S */
/* Moxa Smartio MUE boards handled by 8250_moxa */
{ PCI_VDEVICE(MOXA, 0x1024), },
if (!*vc->vc_uni_pagedir_loc)
con_set_default_unimap(vc);
- vc->vc_screenbuf = kmalloc(vc->vc_screenbuf_size, GFP_KERNEL);
+ vc->vc_screenbuf = kzalloc(vc->vc_screenbuf_size, GFP_KERNEL);
if (!vc->vc_screenbuf)
goto err_free;
if (new_screen_size > (4 << 20))
return -EINVAL;
- newscreen = kmalloc(new_screen_size, GFP_USER);
+ newscreen = kzalloc(new_screen_size, GFP_USER);
if (!newscreen)
return -ENOMEM;
hcd->power_budget = ci->platdata->power_budget;
hcd->tpl_support = ci->platdata->tpl_support;
- if (ci->phy || ci->usb_phy)
+ if (ci->phy || ci->usb_phy) {
hcd->skip_phy_initialization = 1;
+ if (ci->usb_phy)
+ hcd->usb_phy = ci->usb_phy;
+ }
ehci = hcd_to_ehci(hcd);
ehci->caps = ci->hw_bank.cap;
{ USB_DEVICE(0x11ca, 0x0201), /* VeriFone Mx870 Gadget Serial */
.driver_info = SINGLE_RX_URB,
},
+ { USB_DEVICE(0x1965, 0x0018), /* Uniden UBC125XLT */
+ .driver_info = NO_UNION_NORMAL, /* has no union descriptor */
+ },
{ USB_DEVICE(0x22b8, 0x7000), /* Motorola Q Phone */
.driver_info = NO_UNION_NORMAL, /* has no union descriptor */
},
* @frame_list_sz: Frame list size
* @desc_gen_cache: Kmem cache for generic descriptors
* @desc_hsisoc_cache: Kmem cache for hs isochronous descriptors
+ * @unaligned_cache: Kmem cache for DMA mode to handle non-aligned buf
*
* These are for peripheral mode:
*
u32 frame_list_sz;
struct kmem_cache *desc_gen_cache;
struct kmem_cache *desc_hsisoc_cache;
+ struct kmem_cache *unaligned_cache;
+#define DWC2_KMEM_UNALIGNED_BUF_SIZE 1024
#endif /* CONFIG_USB_DWC2_HOST || CONFIG_USB_DWC2_DUAL_ROLE */
u32 index;
u32 maxsize = 0;
u32 mask = 0;
+ u8 pid = 0;
maxsize = dwc2_gadget_get_desc_params(hs_ep, &mask);
((len << DEV_DMA_NBYTES_SHIFT) & mask));
if (hs_ep->dir_in) {
- desc->status |= ((hs_ep->mc << DEV_DMA_ISOC_PID_SHIFT) &
+ if (len)
+ pid = DIV_ROUND_UP(len, hs_ep->ep.maxpacket);
+ else
+ pid = 1;
+ desc->status |= ((pid << DEV_DMA_ISOC_PID_SHIFT) &
DEV_DMA_ISOC_PID_MASK) |
((len % hs_ep->ep.maxpacket) ?
DEV_DMA_SHORT : 0) |
struct dwc2_dma_desc *desc;
if (list_empty(&hs_ep->queue)) {
+ hs_ep->target_frame = TARGET_FRAME_INITIAL;
dev_dbg(hsotg->dev, "%s: No requests in queue\n", __func__);
return;
}
*/
tmp = dwc2_hsotg_read_frameno(hsotg);
- dwc2_hsotg_complete_request(hsotg, ep, get_ep_head(ep), 0);
-
if (using_desc_dma(hsotg)) {
if (ep->target_frame == TARGET_FRAME_INITIAL) {
/* Start first ISO Out */
tmp = dwc2_hsotg_read_frameno(hsotg);
if (using_desc_dma(hsotg)) {
- dwc2_hsotg_complete_request(hsotg, hs_ep,
- get_ep_head(hs_ep), 0);
-
hs_ep->target_frame = tmp;
dwc2_gadget_incr_frame_num(hs_ep);
dwc2_gadget_start_isoc_ddma(hs_ep);
}
ret = usb_add_gadget_udc(dev, &hsotg->gadget);
- if (ret)
+ if (ret) {
+ dwc2_hsotg_ep_free_request(&hsotg->eps_out[0]->ep,
+ hsotg->ctrl_req);
return ret;
-
+ }
dwc2_hsotg_dump(hsotg);
return 0;
int dwc2_hsotg_remove(struct dwc2_hsotg *hsotg)
{
usb_del_gadget_udc(&hsotg->gadget);
+ dwc2_hsotg_ep_free_request(&hsotg->eps_out[0]->ep, hsotg->ctrl_req);
return 0;
}
}
if (hsotg->params.host_dma) {
- dwc2_writel((u32)chan->xfer_dma,
- hsotg->regs + HCDMA(chan->hc_num));
+ dma_addr_t dma_addr;
+
+ if (chan->align_buf) {
+ if (dbg_hc(chan))
+ dev_vdbg(hsotg->dev, "align_buf\n");
+ dma_addr = chan->align_buf;
+ } else {
+ dma_addr = chan->xfer_dma;
+ }
+ dwc2_writel((u32)dma_addr, hsotg->regs + HCDMA(chan->hc_num));
+
if (dbg_hc(chan))
dev_vdbg(hsotg->dev, "Wrote %08lx to HCDMA(%d)\n",
- (unsigned long)chan->xfer_dma, chan->hc_num);
+ (unsigned long)dma_addr, chan->hc_num);
}
/* Start the split */
}
}
+static int dwc2_alloc_split_dma_aligned_buf(struct dwc2_hsotg *hsotg,
+ struct dwc2_qh *qh,
+ struct dwc2_host_chan *chan)
+{
+ if (!hsotg->unaligned_cache ||
+ chan->max_packet > DWC2_KMEM_UNALIGNED_BUF_SIZE)
+ return -ENOMEM;
+
+ if (!qh->dw_align_buf) {
+ qh->dw_align_buf = kmem_cache_alloc(hsotg->unaligned_cache,
+ GFP_ATOMIC | GFP_DMA);
+ if (!qh->dw_align_buf)
+ return -ENOMEM;
+ }
+
+ qh->dw_align_buf_dma = dma_map_single(hsotg->dev, qh->dw_align_buf,
+ DWC2_KMEM_UNALIGNED_BUF_SIZE,
+ DMA_FROM_DEVICE);
+
+ if (dma_mapping_error(hsotg->dev, qh->dw_align_buf_dma)) {
+ dev_err(hsotg->dev, "can't map align_buf\n");
+ chan->align_buf = 0;
+ return -EINVAL;
+ }
+
+ chan->align_buf = qh->dw_align_buf_dma;
+ return 0;
+}
+
#define DWC2_USB_DMA_ALIGN 4
struct dma_aligned_buffer {
/* Set the transfer attributes */
dwc2_hc_init_xfer(hsotg, chan, qtd);
+ /* For non-dword aligned buffers */
+ if (hsotg->params.host_dma && qh->do_split &&
+ chan->ep_is_in && (chan->xfer_dma & 0x3)) {
+ dev_vdbg(hsotg->dev, "Non-aligned buffer\n");
+ if (dwc2_alloc_split_dma_aligned_buf(hsotg, qh, chan)) {
+ dev_err(hsotg->dev,
+ "Failed to allocate memory to handle non-aligned buffer\n");
+ /* Add channel back to free list */
+ chan->align_buf = 0;
+ chan->multi_count = 0;
+ list_add_tail(&chan->hc_list_entry,
+ &hsotg->free_hc_list);
+ qtd->in_process = 0;
+ qh->channel = NULL;
+ return -ENOMEM;
+ }
+ } else {
+ /*
+ * We assume that DMA is always aligned in non-split
+ * case or split out case. Warn if not.
+ */
+ WARN_ON_ONCE(hsotg->params.host_dma &&
+ (chan->xfer_dma & 0x3));
+ chan->align_buf = 0;
+ }
+
if (chan->ep_type == USB_ENDPOINT_XFER_INT ||
chan->ep_type == USB_ENDPOINT_XFER_ISOC)
/*
}
}
+ if (hsotg->params.host_dma) {
+ /*
+ * Create kmem caches to handle non-aligned buffer
+ * in Buffer DMA mode.
+ */
+ hsotg->unaligned_cache = kmem_cache_create("dwc2-unaligned-dma",
+ DWC2_KMEM_UNALIGNED_BUF_SIZE, 4,
+ SLAB_CACHE_DMA, NULL);
+ if (!hsotg->unaligned_cache)
+ dev_err(hsotg->dev,
+ "unable to create dwc2 unaligned cache\n");
+ }
+
hsotg->otg_port = 1;
hsotg->frame_list = NULL;
hsotg->frame_list_dma = 0;
return 0;
error4:
- kmem_cache_destroy(hsotg->desc_gen_cache);
+ kmem_cache_destroy(hsotg->unaligned_cache);
kmem_cache_destroy(hsotg->desc_hsisoc_cache);
+ kmem_cache_destroy(hsotg->desc_gen_cache);
error3:
dwc2_hcd_release(hsotg);
error2:
usb_remove_hcd(hcd);
hsotg->priv = NULL;
- kmem_cache_destroy(hsotg->desc_gen_cache);
+ kmem_cache_destroy(hsotg->unaligned_cache);
kmem_cache_destroy(hsotg->desc_hsisoc_cache);
+ kmem_cache_destroy(hsotg->desc_gen_cache);
dwc2_hcd_release(hsotg);
usb_put_hcd(hcd);
dwc2_writel(hprt0, hsotg->regs + HPRT0);
/* Wait for the HPRT0.PrtSusp register field to be set */
- if (dwc2_hsotg_wait_bit_set(hsotg, HPRT0, HPRT0_SUSP, 300))
+ if (dwc2_hsotg_wait_bit_set(hsotg, HPRT0, HPRT0_SUSP, 3000))
dev_warn(hsotg->dev, "Suspend wasn't generated\n");
/*
return ret;
}
+ dwc2_hcd_rem_wakeup(hsotg);
+
hsotg->hibernated = 0;
hsotg->bus_suspended = 0;
hsotg->lx_state = DWC2_L0;
* (micro)frame
* @xfer_buf: Pointer to current transfer buffer position
* @xfer_dma: DMA address of xfer_buf
+ * @align_buf: In Buffer DMA mode this will be used if xfer_buf is not
+ * DWORD aligned
* @xfer_len: Total number of bytes to transfer
* @xfer_count: Number of bytes transferred so far
* @start_pkt_count: Packet count at start of transfer
u8 *xfer_buf;
dma_addr_t xfer_dma;
+ dma_addr_t align_buf;
u32 xfer_len;
u32 xfer_count;
u16 start_pkt_count;
* speed. Note that this is in "schedule slice" which
* is tightly packed.
* @ntd: Actual number of transfer descriptors in a list
+ * @dw_align_buf: Used instead of original buffer if its physical address
+ * is not dword-aligned
+ * @dw_align_buf_dma: DMA address for dw_align_buf
* @qtd_list: List of QTDs for this QH
* @channel: Host channel currently processing transfers for this QH
* @qh_list_entry: Entry for QH in either the periodic or non-periodic
struct dwc2_hs_transfer_time hs_transfers[DWC2_HS_SCHEDULE_UFRAMES];
u32 ls_start_schedule_slice;
u16 ntd;
+ u8 *dw_align_buf;
+ dma_addr_t dw_align_buf_dma;
struct list_head qtd_list;
struct dwc2_host_chan *channel;
struct list_head qh_list_entry;
frame_desc = &qtd->urb->iso_descs[qtd->isoc_frame_index];
len = dwc2_get_actual_xfer_length(hsotg, chan, chnum, qtd,
DWC2_HC_XFER_COMPLETE, NULL);
- if (!len) {
+ if (!len && !qtd->isoc_split_offset) {
qtd->complete_split = 0;
- qtd->isoc_split_offset = 0;
return 0;
}
frame_desc->actual_length += len;
+ if (chan->align_buf) {
+ dev_vdbg(hsotg->dev, "non-aligned buffer\n");
+ dma_unmap_single(hsotg->dev, chan->qh->dw_align_buf_dma,
+ DWC2_KMEM_UNALIGNED_BUF_SIZE, DMA_FROM_DEVICE);
+ memcpy(qtd->urb->buf + (chan->xfer_dma - qtd->urb->dma),
+ chan->qh->dw_align_buf, len);
+ }
+
qtd->isoc_split_offset += len;
hctsiz = dwc2_readl(hsotg->regs + HCTSIZ(chnum));
/* Get the map and adjust if this is a multi_tt hub */
map = qh->dwc_tt->periodic_bitmaps;
if (qh->dwc_tt->usb_tt->multi)
- map += DWC2_ELEMENTS_PER_LS_BITMAP * qh->ttport;
+ map += DWC2_ELEMENTS_PER_LS_BITMAP * (qh->ttport - 1);
return map;
}
if (qh->desc_list)
dwc2_hcd_qh_free_ddma(hsotg, qh);
+ else if (hsotg->unaligned_cache && qh->dw_align_buf)
+ kmem_cache_free(hsotg->unaligned_cache, qh->dw_align_buf);
+
kfree(qh);
}
if (!dwc->clks)
return -ENOMEM;
- dwc->num_clks = ARRAY_SIZE(dwc3_core_clks);
dwc->dev = dev;
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
if (IS_ERR(dwc->reset))
return PTR_ERR(dwc->reset);
- ret = clk_bulk_get(dev, dwc->num_clks, dwc->clks);
- if (ret == -EPROBE_DEFER)
- return ret;
- /*
- * Clocks are optional, but new DT platforms should support all clocks
- * as required by the DT-binding.
- */
- if (ret)
- dwc->num_clks = 0;
+ if (dev->of_node) {
+ dwc->num_clks = ARRAY_SIZE(dwc3_core_clks);
+
+ ret = clk_bulk_get(dev, dwc->num_clks, dwc->clks);
+ if (ret == -EPROBE_DEFER)
+ return ret;
+ /*
+ * Clocks are optional, but new DT platforms should support all
+ * clocks as required by the DT-binding.
+ */
+ if (ret)
+ dwc->num_clks = 0;
+ }
ret = reset_control_deassert(dwc->reset);
if (ret)
reset_control_put(simple->resets);
- pm_runtime_put_sync(dev);
pm_runtime_disable(dev);
+ pm_runtime_put_noidle(dev);
+ pm_runtime_set_suspended(dev);
return 0;
}
#define PCI_DEVICE_ID_INTEL_GLK 0x31aa
#define PCI_DEVICE_ID_INTEL_CNPLP 0x9dee
#define PCI_DEVICE_ID_INTEL_CNPH 0xa36e
+#define PCI_DEVICE_ID_INTEL_ICLLP 0x34ee
#define PCI_INTEL_BXT_DSM_GUID "732b85d5-b7a7-4a1b-9ba0-4bbd00ffd511"
#define PCI_INTEL_BXT_FUNC_PMU_PWR 4
{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_GLK), },
{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CNPLP), },
{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CNPH), },
+ { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICLLP), },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_NL_USB), },
{ } /* Terminating Entry */
};
qcom->dwc3 = of_find_device_by_node(dwc3_np);
if (!qcom->dwc3) {
dev_err(&pdev->dev, "failed to get dwc3 platform device\n");
+ ret = -ENODEV;
goto depopulate;
}
return 0;
}
-#ifdef CONFIG_PM_SLEEP
-static int dwc3_qcom_pm_suspend(struct device *dev)
+static int __maybe_unused dwc3_qcom_pm_suspend(struct device *dev)
{
struct dwc3_qcom *qcom = dev_get_drvdata(dev);
int ret = 0;
return ret;
}
-static int dwc3_qcom_pm_resume(struct device *dev)
+static int __maybe_unused dwc3_qcom_pm_resume(struct device *dev)
{
struct dwc3_qcom *qcom = dev_get_drvdata(dev);
int ret;
return ret;
}
-#endif
-#ifdef CONFIG_PM
-static int dwc3_qcom_runtime_suspend(struct device *dev)
+static int __maybe_unused dwc3_qcom_runtime_suspend(struct device *dev)
{
struct dwc3_qcom *qcom = dev_get_drvdata(dev);
return dwc3_qcom_suspend(qcom);
}
-static int dwc3_qcom_runtime_resume(struct device *dev)
+static int __maybe_unused dwc3_qcom_runtime_resume(struct device *dev)
{
struct dwc3_qcom *qcom = dev_get_drvdata(dev);
return dwc3_qcom_resume(qcom);
}
-#endif
static const struct dev_pm_ops dwc3_qcom_dev_pm_ops = {
SET_SYSTEM_SLEEP_PM_OPS(dwc3_qcom_pm_suspend, dwc3_qcom_pm_resume)
*/
if (w_value && !f->get_alt)
break;
+
+ spin_lock(&cdev->lock);
value = f->set_alt(f, w_index, w_value);
if (value == USB_GADGET_DELAYED_STATUS) {
DBG(cdev,
DBG(cdev, "delayed_status count %d\n",
cdev->delayed_status);
}
+ spin_unlock(&cdev->lock);
break;
case USB_REQ_GET_INTERFACE:
if (ctrl->bRequestType != (USB_DIR_IN|USB_RECIP_INTERFACE))
struct mm_struct *mm;
struct work_struct work;
+ struct work_struct cancellation_work;
struct usb_ep *ep;
struct usb_request *req;
return 0;
}
+static void ffs_aio_cancel_worker(struct work_struct *work)
+{
+ struct ffs_io_data *io_data = container_of(work, struct ffs_io_data,
+ cancellation_work);
+
+ ENTER();
+
+ usb_ep_dequeue(io_data->ep, io_data->req);
+}
+
static int ffs_aio_cancel(struct kiocb *kiocb)
{
struct ffs_io_data *io_data = kiocb->private;
- struct ffs_epfile *epfile = kiocb->ki_filp->private_data;
+ struct ffs_data *ffs = io_data->ffs;
int value;
ENTER();
- spin_lock_irq(&epfile->ffs->eps_lock);
-
- if (likely(io_data && io_data->ep && io_data->req))
- value = usb_ep_dequeue(io_data->ep, io_data->req);
- else
+ if (likely(io_data && io_data->ep && io_data->req)) {
+ INIT_WORK(&io_data->cancellation_work, ffs_aio_cancel_worker);
+ queue_work(ffs->io_completion_wq, &io_data->cancellation_work);
+ value = -EINPROGRESS;
+ } else {
value = -EINVAL;
-
- spin_unlock_irq(&epfile->ffs->eps_lock);
+ }
return value;
}
dev = xhci->devs[slot_id];
- trace_xhci_free_virt_device(dev);
-
xhci->dcbaa->dev_context_ptrs[slot_id] = 0;
if (!dev)
return;
+ trace_xhci_free_virt_device(dev);
+
if (dev->tt_info)
old_active_eps = dev->tt_info->active_eps;
unsigned long mask;
unsigned int port;
bool idle, enable;
- int err;
+ int err = 0;
memset(&rsp, 0, sizeof(rsp));
pm_runtime_disable(&pdev->dev);
usb_put_hcd(tegra->hcd);
disable_xusbc:
- if (!&pdev->dev.pm_domain)
+ if (!pdev->dev.pm_domain)
tegra_powergate_power_off(TEGRA_POWERGATE_XUSBC);
disable_xusba:
- if (!&pdev->dev.pm_domain)
+ if (!pdev->dev.pm_domain)
tegra_powergate_power_off(TEGRA_POWERGATE_XUSBA);
put_padctl:
tegra_xusb_padctl_put(tegra->padctl);
TP_ARGS(ring, trb)
);
+DECLARE_EVENT_CLASS(xhci_log_free_virt_dev,
+ TP_PROTO(struct xhci_virt_device *vdev),
+ TP_ARGS(vdev),
+ TP_STRUCT__entry(
+ __field(void *, vdev)
+ __field(unsigned long long, out_ctx)
+ __field(unsigned long long, in_ctx)
+ __field(u8, fake_port)
+ __field(u8, real_port)
+ __field(u16, current_mel)
+
+ ),
+ TP_fast_assign(
+ __entry->vdev = vdev;
+ __entry->in_ctx = (unsigned long long) vdev->in_ctx->dma;
+ __entry->out_ctx = (unsigned long long) vdev->out_ctx->dma;
+ __entry->fake_port = (u8) vdev->fake_port;
+ __entry->real_port = (u8) vdev->real_port;
+ __entry->current_mel = (u16) vdev->current_mel;
+ ),
+ TP_printk("vdev %p ctx %llx | %llx fake_port %d real_port %d current_mel %d",
+ __entry->vdev, __entry->in_ctx, __entry->out_ctx,
+ __entry->fake_port, __entry->real_port, __entry->current_mel
+ )
+);
+
+DEFINE_EVENT(xhci_log_free_virt_dev, xhci_free_virt_device,
+ TP_PROTO(struct xhci_virt_device *vdev),
+ TP_ARGS(vdev)
+);
+
DECLARE_EVENT_CLASS(xhci_log_virt_dev,
TP_PROTO(struct xhci_virt_device *vdev),
TP_ARGS(vdev),
TP_ARGS(vdev)
);
-DEFINE_EVENT(xhci_log_virt_dev, xhci_free_virt_device,
- TP_PROTO(struct xhci_virt_device *vdev),
- TP_ARGS(vdev)
-);
-
DEFINE_EVENT(xhci_log_virt_dev, xhci_setup_device,
TP_PROTO(struct xhci_virt_device *vdev),
TP_ARGS(vdev)
spin_unlock_irqrestore(&xhci->lock, flags);
}
+static bool xhci_pending_portevent(struct xhci_hcd *xhci)
+{
+ struct xhci_port **ports;
+ int port_index;
+ u32 status;
+ u32 portsc;
+
+ status = readl(&xhci->op_regs->status);
+ if (status & STS_EINT)
+ return true;
+ /*
+ * Checking STS_EINT is not enough as there is a lag between a change
+ * bit being set and the Port Status Change Event that it generated
+ * being written to the Event Ring. See note in xhci 1.1 section 4.19.2.
+ */
+
+ port_index = xhci->usb2_rhub.num_ports;
+ ports = xhci->usb2_rhub.ports;
+ while (port_index--) {
+ portsc = readl(ports[port_index]->addr);
+ if (portsc & PORT_CHANGE_MASK ||
+ (portsc & PORT_PLS_MASK) == XDEV_RESUME)
+ return true;
+ }
+ port_index = xhci->usb3_rhub.num_ports;
+ ports = xhci->usb3_rhub.ports;
+ while (port_index--) {
+ portsc = readl(ports[port_index]->addr);
+ if (portsc & PORT_CHANGE_MASK ||
+ (portsc & PORT_PLS_MASK) == XDEV_RESUME)
+ return true;
+ }
+ return false;
+}
+
/*
* Stop HC (not bus-specific)
*
*/
int xhci_resume(struct xhci_hcd *xhci, bool hibernated)
{
- u32 command, temp = 0, status;
+ u32 command, temp = 0;
struct usb_hcd *hcd = xhci_to_hcd(xhci);
struct usb_hcd *secondary_hcd;
int retval = 0;
command = readl(&xhci->op_regs->command);
command |= CMD_CRS;
writel(command, &xhci->op_regs->command);
+ /*
+ * Some controllers take up to 55+ ms to complete the controller
+ * restore so setting the timeout to 100ms. Xhci specification
+ * doesn't mention any timeout value.
+ */
if (xhci_handshake(&xhci->op_regs->status,
- STS_RESTORE, 0, 10 * 1000)) {
+ STS_RESTORE, 0, 100 * 1000)) {
xhci_warn(xhci, "WARN: xHC restore state timeout\n");
spin_unlock_irq(&xhci->lock);
return -ETIMEDOUT;
done:
if (retval == 0) {
/* Resume root hubs only when have pending events. */
- status = readl(&xhci->op_regs->status);
- if (status & STS_EINT) {
+ if (xhci_pending_portevent(xhci)) {
usb_hcd_resume_root_hub(xhci->shared_hcd);
usb_hcd_resume_root_hub(hcd);
}
#define PORT_PLC (1 << 22)
/* port configure error change - port failed to configure its link partner */
#define PORT_CEC (1 << 23)
+#define PORT_CHANGE_MASK (PORT_CSC | PORT_PEC | PORT_WRC | PORT_OCC | \
+ PORT_RC | PORT_PLC | PORT_CEC)
+
+
/* Cold Attach Status - xHC can set this bit to report device attached during
* Sx state. Warm port reset should be perfomed to clear this bit and move port
* to connected state.
{ USB_DEVICE(0x10C4, 0x8156) }, /* B&G H3000 link cable */
{ USB_DEVICE(0x10C4, 0x815E) }, /* Helicomm IP-Link 1220-DVM */
{ USB_DEVICE(0x10C4, 0x815F) }, /* Timewave HamLinkUSB */
+ { USB_DEVICE(0x10C4, 0x817C) }, /* CESINEL MEDCAL N Power Quality Monitor */
+ { USB_DEVICE(0x10C4, 0x817D) }, /* CESINEL MEDCAL NT Power Quality Monitor */
+ { USB_DEVICE(0x10C4, 0x817E) }, /* CESINEL MEDCAL S Power Quality Monitor */
{ USB_DEVICE(0x10C4, 0x818B) }, /* AVIT Research USB to TTL */
{ USB_DEVICE(0x10C4, 0x819F) }, /* MJS USB Toslink Switcher */
{ USB_DEVICE(0x10C4, 0x81A6) }, /* ThinkOptics WavIt */
{ USB_DEVICE(0x10C4, 0x826B) }, /* Cygnal Integrated Products, Inc., Fasttrax GPS demonstration module */
{ USB_DEVICE(0x10C4, 0x8281) }, /* Nanotec Plug & Drive */
{ USB_DEVICE(0x10C4, 0x8293) }, /* Telegesis ETRX2USB */
+ { USB_DEVICE(0x10C4, 0x82EF) }, /* CESINEL FALCO 6105 AC Power Supply */
+ { USB_DEVICE(0x10C4, 0x82F1) }, /* CESINEL MEDCAL EFD Earth Fault Detector */
+ { USB_DEVICE(0x10C4, 0x82F2) }, /* CESINEL MEDCAL ST Network Analyzer */
{ USB_DEVICE(0x10C4, 0x82F4) }, /* Starizona MicroTouch */
{ USB_DEVICE(0x10C4, 0x82F9) }, /* Procyon AVS */
{ USB_DEVICE(0x10C4, 0x8341) }, /* Siemens MC35PU GPRS Modem */
{ USB_DEVICE(0x10C4, 0x8470) }, /* Juniper Networks BX Series System Console */
{ USB_DEVICE(0x10C4, 0x8477) }, /* Balluff RFID */
{ USB_DEVICE(0x10C4, 0x84B6) }, /* Starizona Hyperion */
+ { USB_DEVICE(0x10C4, 0x851E) }, /* CESINEL MEDCAL PT Network Analyzer */
{ USB_DEVICE(0x10C4, 0x85A7) }, /* LifeScan OneTouch Verio IQ */
+ { USB_DEVICE(0x10C4, 0x85B8) }, /* CESINEL ReCon T Energy Logger */
{ USB_DEVICE(0x10C4, 0x85EA) }, /* AC-Services IBUS-IF */
{ USB_DEVICE(0x10C4, 0x85EB) }, /* AC-Services CIS-IBUS */
{ USB_DEVICE(0x10C4, 0x85F8) }, /* Virtenio Preon32 */
{ USB_DEVICE(0x10C4, 0x8857) }, /* CEL EM357 ZigBee USB Stick */
{ USB_DEVICE(0x10C4, 0x88A4) }, /* MMB Networks ZigBee USB Device */
{ USB_DEVICE(0x10C4, 0x88A5) }, /* Planet Innovation Ingeni ZigBee USB Device */
+ { USB_DEVICE(0x10C4, 0x88FB) }, /* CESINEL MEDCAL STII Network Analyzer */
+ { USB_DEVICE(0x10C4, 0x8938) }, /* CESINEL MEDCAL S II Network Analyzer */
{ USB_DEVICE(0x10C4, 0x8946) }, /* Ketra N1 Wireless Interface */
{ USB_DEVICE(0x10C4, 0x8962) }, /* Brim Brothers charging dock */
{ USB_DEVICE(0x10C4, 0x8977) }, /* CEL MeshWorks DevKit Device */
{ USB_DEVICE(0x10C4, 0x8998) }, /* KCF Technologies PRN */
+ { USB_DEVICE(0x10C4, 0x89A4) }, /* CESINEL FTBC Flexible Thyristor Bridge Controller */
{ USB_DEVICE(0x10C4, 0x8A2A) }, /* HubZ dual ZigBee and Z-Wave dongle */
{ USB_DEVICE(0x10C4, 0x8A5E) }, /* CEL EM3588 ZigBee USB Stick Long Range */
{ USB_DEVICE(0x10C4, 0x8B34) }, /* Qivicon ZigBee USB Radio Stick */
{ USB_DEVICE(0x10C4, 0xEA60) }, /* Silicon Labs factory default */
{ USB_DEVICE(0x10C4, 0xEA61) }, /* Silicon Labs factory default */
+ { USB_DEVICE(0x10C4, 0xEA63) }, /* Silicon Labs Windows Update (CP2101-4/CP2102N) */
{ USB_DEVICE(0x10C4, 0xEA70) }, /* Silicon Labs factory default */
{ USB_DEVICE(0x10C4, 0xEA71) }, /* Infinity GPS-MIC-1 Radio Monophone */
+ { USB_DEVICE(0x10C4, 0xEA7A) }, /* Silicon Labs Windows Update (CP2105) */
+ { USB_DEVICE(0x10C4, 0xEA7B) }, /* Silicon Labs Windows Update (CP2108) */
{ USB_DEVICE(0x10C4, 0xF001) }, /* Elan Digital Systems USBscope50 */
{ USB_DEVICE(0x10C4, 0xF002) }, /* Elan Digital Systems USBwave12 */
{ USB_DEVICE(0x10C4, 0xF003) }, /* Elan Digital Systems USBpulse100 */
u64 ts_nsec = local_clock();
unsigned long rem_nsec;
+ mutex_lock(&port->logbuffer_lock);
if (!port->logbuffer[port->logbuffer_head]) {
port->logbuffer[port->logbuffer_head] =
kzalloc(LOG_BUFFER_ENTRY_SIZE, GFP_KERNEL);
- if (!port->logbuffer[port->logbuffer_head])
+ if (!port->logbuffer[port->logbuffer_head]) {
+ mutex_unlock(&port->logbuffer_lock);
return;
+ }
}
vsnprintf(tmpbuffer, sizeof(tmpbuffer), fmt, args);
- mutex_lock(&port->logbuffer_lock);
-
if (tcpm_log_full(port)) {
port->logbuffer_head = max(port->logbuffer_head - 1, 0);
strcpy(tmpbuffer, "overflow");
tcpm_port_is_sink(port) &&
time_is_after_jiffies(port->delayed_runtime)) {
tcpm_set_state(port, SNK_DISCOVERY,
- port->delayed_runtime - jiffies);
+ jiffies_to_msecs(port->delayed_runtime -
+ jiffies));
break;
}
tcpm_set_state(port, unattached_state(port), 0);
}
if (con->status.change & UCSI_CONSTAT_CONNECT_CHANGE) {
+ typec_set_pwr_role(con->port, con->status.pwr_dir);
+
+ switch (con->status.partner_type) {
+ case UCSI_CONSTAT_PARTNER_TYPE_UFP:
+ typec_set_data_role(con->port, TYPEC_HOST);
+ break;
+ case UCSI_CONSTAT_PARTNER_TYPE_DFP:
+ typec_set_data_role(con->port, TYPEC_DEVICE);
+ break;
+ default:
+ break;
+ }
+
if (con->status.connected)
ucsi_register_partner(con);
else
return -ENODEV;
}
+ /* This will make sure we can use ioremap_nocache() */
+ status = acpi_release_memory(ACPI_HANDLE(&pdev->dev), res, 1);
+ if (ACPI_FAILURE(status))
+ return -ENOMEM;
+
/*
* NOTE: The memory region for the data structures is used also in an
* operation region, which means ACPI has already reserved it. Therefore
return local_clock() >> 10;
}
-static bool vhost_can_busy_poll(struct vhost_dev *dev,
- unsigned long endtime)
+static bool vhost_can_busy_poll(unsigned long endtime)
{
- return likely(!need_resched()) &&
- likely(!time_after(busy_clock(), endtime)) &&
- likely(!signal_pending(current)) &&
- !vhost_has_work(dev);
+ return likely(!need_resched() && !time_after(busy_clock(), endtime) &&
+ !signal_pending(current));
}
static void vhost_net_disable_vq(struct vhost_net *n,
static int vhost_net_tx_get_vq_desc(struct vhost_net *net,
struct vhost_virtqueue *vq,
struct iovec iov[], unsigned int iov_size,
- unsigned int *out_num, unsigned int *in_num)
+ unsigned int *out_num, unsigned int *in_num,
+ bool *busyloop_intr)
{
unsigned long uninitialized_var(endtime);
int r = vhost_get_vq_desc(vq, vq->iov, ARRAY_SIZE(vq->iov),
if (r == vq->num && vq->busyloop_timeout) {
preempt_disable();
endtime = busy_clock() + vq->busyloop_timeout;
- while (vhost_can_busy_poll(vq->dev, endtime) &&
- vhost_vq_avail_empty(vq->dev, vq))
+ while (vhost_can_busy_poll(endtime)) {
+ if (vhost_has_work(vq->dev)) {
+ *busyloop_intr = true;
+ break;
+ }
+ if (!vhost_vq_avail_empty(vq->dev, vq))
+ break;
cpu_relax();
+ }
preempt_enable();
r = vhost_get_vq_desc(vq, vq->iov, ARRAY_SIZE(vq->iov),
out_num, in_num, NULL, NULL);
zcopy = nvq->ubufs;
for (;;) {
+ bool busyloop_intr;
+
/* Release DMAs done buffers first */
if (zcopy)
vhost_zerocopy_signal_used(net, vq);
-
+ busyloop_intr = false;
head = vhost_net_tx_get_vq_desc(net, vq, vq->iov,
ARRAY_SIZE(vq->iov),
- &out, &in);
+ &out, &in, &busyloop_intr);
/* On error, stop handling until the next kick. */
if (unlikely(head < 0))
break;
/* Nothing new? Wait for eventfd to tell us they refilled. */
if (head == vq->num) {
- if (unlikely(vhost_enable_notify(&net->dev, vq))) {
+ if (unlikely(busyloop_intr)) {
+ vhost_poll_queue(&vq->poll);
+ } else if (unlikely(vhost_enable_notify(&net->dev, vq))) {
vhost_disable_notify(&net->dev, vq);
continue;
}
nvq->done_idx = 0;
}
-static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk)
+static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk,
+ bool *busyloop_intr)
{
- struct vhost_net_virtqueue *rvq = &net->vqs[VHOST_NET_VQ_RX];
- struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX];
- struct vhost_virtqueue *vq = &nvq->vq;
+ struct vhost_net_virtqueue *rnvq = &net->vqs[VHOST_NET_VQ_RX];
+ struct vhost_net_virtqueue *tnvq = &net->vqs[VHOST_NET_VQ_TX];
+ struct vhost_virtqueue *rvq = &rnvq->vq;
+ struct vhost_virtqueue *tvq = &tnvq->vq;
unsigned long uninitialized_var(endtime);
- int len = peek_head_len(rvq, sk);
+ int len = peek_head_len(rnvq, sk);
- if (!len && vq->busyloop_timeout) {
+ if (!len && tvq->busyloop_timeout) {
/* Flush batched heads first */
- vhost_rx_signal_used(rvq);
+ vhost_rx_signal_used(rnvq);
/* Both tx vq and rx socket were polled here */
- mutex_lock_nested(&vq->mutex, 1);
- vhost_disable_notify(&net->dev, vq);
+ mutex_lock_nested(&tvq->mutex, 1);
+ vhost_disable_notify(&net->dev, tvq);
preempt_disable();
- endtime = busy_clock() + vq->busyloop_timeout;
+ endtime = busy_clock() + tvq->busyloop_timeout;
- while (vhost_can_busy_poll(&net->dev, endtime) &&
- !sk_has_rx_data(sk) &&
- vhost_vq_avail_empty(&net->dev, vq))
+ while (vhost_can_busy_poll(endtime)) {
+ if (vhost_has_work(&net->dev)) {
+ *busyloop_intr = true;
+ break;
+ }
+ if ((sk_has_rx_data(sk) &&
+ !vhost_vq_avail_empty(&net->dev, rvq)) ||
+ !vhost_vq_avail_empty(&net->dev, tvq))
+ break;
cpu_relax();
+ }
preempt_enable();
- if (!vhost_vq_avail_empty(&net->dev, vq))
- vhost_poll_queue(&vq->poll);
- else if (unlikely(vhost_enable_notify(&net->dev, vq))) {
- vhost_disable_notify(&net->dev, vq);
- vhost_poll_queue(&vq->poll);
+ if (!vhost_vq_avail_empty(&net->dev, tvq)) {
+ vhost_poll_queue(&tvq->poll);
+ } else if (unlikely(vhost_enable_notify(&net->dev, tvq))) {
+ vhost_disable_notify(&net->dev, tvq);
+ vhost_poll_queue(&tvq->poll);
}
- mutex_unlock(&vq->mutex);
+ mutex_unlock(&tvq->mutex);
- len = peek_head_len(rvq, sk);
+ len = peek_head_len(rnvq, sk);
}
return len;
s16 headcount;
size_t vhost_hlen, sock_hlen;
size_t vhost_len, sock_len;
+ bool busyloop_intr = false;
struct socket *sock;
struct iov_iter fixup;
__virtio16 num_buffers;
vq->log : NULL;
mergeable = vhost_has_feature(vq, VIRTIO_NET_F_MRG_RXBUF);
- while ((sock_len = vhost_net_rx_peek_head_len(net, sock->sk))) {
+ while ((sock_len = vhost_net_rx_peek_head_len(net, sock->sk,
+ &busyloop_intr))) {
sock_len += sock_hlen;
vhost_len = sock_len + vhost_hlen;
headcount = get_rx_bufs(vq, vq->heads + nvq->done_idx,
goto out;
/* OK, now we need to know about added descriptors. */
if (!headcount) {
- if (unlikely(vhost_enable_notify(&net->dev, vq))) {
+ if (unlikely(busyloop_intr)) {
+ vhost_poll_queue(&vq->poll);
+ } else if (unlikely(vhost_enable_notify(&net->dev, vq))) {
/* They have slipped one in as we were
* doing that: check again. */
vhost_disable_notify(&net->dev, vq);
* they refilled. */
goto out;
}
+ busyloop_intr = false;
if (nvq->rx_ring)
msg.msg_control = vhost_net_buf_consume(&nvq->rxq);
/* On overrun, truncate and discard */
goto out;
}
}
- vhost_net_enable_vq(net, vq);
+ if (unlikely(busyloop_intr))
+ vhost_poll_queue(&vq->poll);
+ else
+ vhost_net_enable_vq(net, vq);
out:
vhost_rx_signal_used(nvq);
mutex_unlock(&vq->mutex);
if (ubufs)
vhost_net_ubuf_put_wait_and_free(ubufs);
err_ubufs:
- sockfd_put(sock);
+ if (sock)
+ sockfd_put(sock);
err_vq:
mutex_unlock(&vq->mutex);
err:
xen-evtchn-y := evtchn.o
xen-gntdev-y := gntdev.o
xen-gntalloc-y := gntalloc.o
-xen-privcmd-y := privcmd.o
+xen-privcmd-y := privcmd.o privcmd-buf.o
xen_irq_info_cleanup(info);
}
- BUG_ON(info_for_irq(irq)->type == IRQT_UNBOUND);
-
xen_free_irq(irq);
}
return 0;
}
-EXPORT_SYMBOL(gnttab_alloc_pages);
+EXPORT_SYMBOL_GPL(gnttab_alloc_pages);
/**
* gnttab_free_pages - free pages allocated by gnttab_alloc_pages()
}
free_xenballooned_pages(nr_pages, pages);
}
-EXPORT_SYMBOL(gnttab_free_pages);
+EXPORT_SYMBOL_GPL(gnttab_free_pages);
/* Handling of paged out grant targets (GNTST_eagain) */
#define MAX_DELAY 256
return;
}
- if (sysrq_key != '\0')
- xenbus_printf(xbt, "control", "sysrq", "%c", '\0');
+ if (sysrq_key != '\0') {
+ err = xenbus_printf(xbt, "control", "sysrq", "%c", '\0');
+ if (err) {
+ pr_err("%s: Error %d writing sysrq in control/sysrq\n",
+ __func__, err);
+ xenbus_transaction_end(xbt, 1);
+ return;
+ }
+ }
err = xenbus_transaction_end(xbt, 0);
if (err == -EAGAIN)
continue;
snprintf(node, FEATURE_PATH_SIZE, "feature-%s",
shutdown_handlers[idx].command);
- xenbus_printf(XBT_NIL, "control", node, "%u", 1);
+ err = xenbus_printf(XBT_NIL, "control", node, "%u", 1);
+ if (err) {
+ pr_err("%s: Error %d writing %s\n", __func__,
+ err, node);
+ return err;
+ }
}
return 0;
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+
+/******************************************************************************
+ * privcmd-buf.c
+ *
+ * Mmap of hypercall buffers.
+ *
+ * Copyright (c) 2018 Juergen Gross
+ */
+
+#define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/miscdevice.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+
+#include "privcmd.h"
+
+MODULE_LICENSE("GPL");
+
+static unsigned int limit = 64;
+module_param(limit, uint, 0644);
+MODULE_PARM_DESC(limit, "Maximum number of pages that may be allocated by "
+ "the privcmd-buf device per open file");
+
+struct privcmd_buf_private {
+ struct mutex lock;
+ struct list_head list;
+ unsigned int allocated;
+};
+
+struct privcmd_buf_vma_private {
+ struct privcmd_buf_private *file_priv;
+ struct list_head list;
+ unsigned int users;
+ unsigned int n_pages;
+ struct page *pages[];
+};
+
+static int privcmd_buf_open(struct inode *ino, struct file *file)
+{
+ struct privcmd_buf_private *file_priv;
+
+ file_priv = kzalloc(sizeof(*file_priv), GFP_KERNEL);
+ if (!file_priv)
+ return -ENOMEM;
+
+ mutex_init(&file_priv->lock);
+ INIT_LIST_HEAD(&file_priv->list);
+
+ file->private_data = file_priv;
+
+ return 0;
+}
+
+static void privcmd_buf_vmapriv_free(struct privcmd_buf_vma_private *vma_priv)
+{
+ unsigned int i;
+
+ vma_priv->file_priv->allocated -= vma_priv->n_pages;
+
+ list_del(&vma_priv->list);
+
+ for (i = 0; i < vma_priv->n_pages; i++)
+ if (vma_priv->pages[i])
+ __free_page(vma_priv->pages[i]);
+
+ kfree(vma_priv);
+}
+
+static int privcmd_buf_release(struct inode *ino, struct file *file)
+{
+ struct privcmd_buf_private *file_priv = file->private_data;
+ struct privcmd_buf_vma_private *vma_priv;
+
+ mutex_lock(&file_priv->lock);
+
+ while (!list_empty(&file_priv->list)) {
+ vma_priv = list_first_entry(&file_priv->list,
+ struct privcmd_buf_vma_private,
+ list);
+ privcmd_buf_vmapriv_free(vma_priv);
+ }
+
+ mutex_unlock(&file_priv->lock);
+
+ kfree(file_priv);
+
+ return 0;
+}
+
+static void privcmd_buf_vma_open(struct vm_area_struct *vma)
+{
+ struct privcmd_buf_vma_private *vma_priv = vma->vm_private_data;
+
+ if (!vma_priv)
+ return;
+
+ mutex_lock(&vma_priv->file_priv->lock);
+ vma_priv->users++;
+ mutex_unlock(&vma_priv->file_priv->lock);
+}
+
+static void privcmd_buf_vma_close(struct vm_area_struct *vma)
+{
+ struct privcmd_buf_vma_private *vma_priv = vma->vm_private_data;
+ struct privcmd_buf_private *file_priv;
+
+ if (!vma_priv)
+ return;
+
+ file_priv = vma_priv->file_priv;
+
+ mutex_lock(&file_priv->lock);
+
+ vma_priv->users--;
+ if (!vma_priv->users)
+ privcmd_buf_vmapriv_free(vma_priv);
+
+ mutex_unlock(&file_priv->lock);
+}
+
+static vm_fault_t privcmd_buf_vma_fault(struct vm_fault *vmf)
+{
+ pr_debug("fault: vma=%p %lx-%lx, pgoff=%lx, uv=%p\n",
+ vmf->vma, vmf->vma->vm_start, vmf->vma->vm_end,
+ vmf->pgoff, (void *)vmf->address);
+
+ return VM_FAULT_SIGBUS;
+}
+
+static const struct vm_operations_struct privcmd_buf_vm_ops = {
+ .open = privcmd_buf_vma_open,
+ .close = privcmd_buf_vma_close,
+ .fault = privcmd_buf_vma_fault,
+};
+
+static int privcmd_buf_mmap(struct file *file, struct vm_area_struct *vma)
+{
+ struct privcmd_buf_private *file_priv = file->private_data;
+ struct privcmd_buf_vma_private *vma_priv;
+ unsigned long count = vma_pages(vma);
+ unsigned int i;
+ int ret = 0;
+
+ if (!(vma->vm_flags & VM_SHARED) || count > limit ||
+ file_priv->allocated + count > limit)
+ return -EINVAL;
+
+ vma_priv = kzalloc(sizeof(*vma_priv) + count * sizeof(void *),
+ GFP_KERNEL);
+ if (!vma_priv)
+ return -ENOMEM;
+
+ vma_priv->n_pages = count;
+ count = 0;
+ for (i = 0; i < vma_priv->n_pages; i++) {
+ vma_priv->pages[i] = alloc_page(GFP_KERNEL | __GFP_ZERO);
+ if (!vma_priv->pages[i])
+ break;
+ count++;
+ }
+
+ mutex_lock(&file_priv->lock);
+
+ file_priv->allocated += count;
+
+ vma_priv->file_priv = file_priv;
+ vma_priv->users = 1;
+
+ vma->vm_flags |= VM_IO | VM_DONTEXPAND;
+ vma->vm_ops = &privcmd_buf_vm_ops;
+ vma->vm_private_data = vma_priv;
+
+ list_add(&vma_priv->list, &file_priv->list);
+
+ if (vma_priv->n_pages != count)
+ ret = -ENOMEM;
+ else
+ for (i = 0; i < vma_priv->n_pages; i++) {
+ ret = vm_insert_page(vma, vma->vm_start + i * PAGE_SIZE,
+ vma_priv->pages[i]);
+ if (ret)
+ break;
+ }
+
+ if (ret)
+ privcmd_buf_vmapriv_free(vma_priv);
+
+ mutex_unlock(&file_priv->lock);
+
+ return ret;
+}
+
+const struct file_operations xen_privcmdbuf_fops = {
+ .owner = THIS_MODULE,
+ .open = privcmd_buf_open,
+ .release = privcmd_buf_release,
+ .mmap = privcmd_buf_mmap,
+};
+EXPORT_SYMBOL_GPL(xen_privcmdbuf_fops);
+
+struct miscdevice xen_privcmdbuf_dev = {
+ .minor = MISC_DYNAMIC_MINOR,
+ .name = "xen/hypercall",
+ .fops = &xen_privcmdbuf_fops,
+};
pr_err("Could not register Xen privcmd device\n");
return err;
}
+
+ err = misc_register(&xen_privcmdbuf_dev);
+ if (err != 0) {
+ pr_err("Could not register Xen hypercall-buf device\n");
+ misc_deregister(&privcmd_dev);
+ return err;
+ }
+
return 0;
}
static void __exit privcmd_exit(void)
{
misc_deregister(&privcmd_dev);
+ misc_deregister(&xen_privcmdbuf_dev);
}
module_init(privcmd_init);
#include <linux/fs.h>
extern const struct file_operations xen_privcmd_fops;
+extern const struct file_operations xen_privcmdbuf_fops;
+
+extern struct miscdevice xen_privcmdbuf_dev;
{
struct v2p_entry *entry;
unsigned long flags;
+ int err;
if (try) {
spin_lock_irqsave(&info->v2p_lock, flags);
scsiback_del_translation_entry(info, vir);
}
} else if (!try) {
- xenbus_printf(XBT_NIL, info->dev->nodename, state,
+ err = xenbus_printf(XBT_NIL, info->dev->nodename, state,
"%d", XenbusStateClosed);
+ if (err)
+ xenbus_dev_error(info->dev, err,
+ "%s: writing %s", __func__, state);
}
}
snprintf(str, sizeof(str), "vscsi-devs/%s/p-dev", ent);
val = xenbus_read(XBT_NIL, dev->nodename, str, NULL);
if (IS_ERR(val)) {
- xenbus_printf(XBT_NIL, dev->nodename, state,
+ err = xenbus_printf(XBT_NIL, dev->nodename, state,
"%d", XenbusStateClosed);
+ if (err)
+ xenbus_dev_error(info->dev, err,
+ "%s: writing %s", __func__, state);
return;
}
strlcpy(phy, val, VSCSI_NAMELEN);
err = xenbus_scanf(XBT_NIL, dev->nodename, str, "%u:%u:%u:%u",
&vir.hst, &vir.chn, &vir.tgt, &vir.lun);
if (XENBUS_EXIST_ERR(err)) {
- xenbus_printf(XBT_NIL, dev->nodename, state,
+ err = xenbus_printf(XBT_NIL, dev->nodename, state,
"%d", XenbusStateClosed);
+ if (err)
+ xenbus_dev_error(info->dev, err,
+ "%s: writing %s", __func__, state);
return;
}
* Implements an efficient asynchronous io interface.
*
* Copyright 2000, 2001, 2002 Red Hat, Inc. All Rights Reserved.
- * Copyright 2018 Christoph Hellwig.
*
* See ../COPYING for licensing terms.
*/
bool datasync;
};
-struct poll_iocb {
- struct file *file;
- __poll_t events;
- struct wait_queue_head *head;
-
- union {
- struct wait_queue_entry wait;
- struct work_struct work;
- };
-};
-
struct aio_kiocb {
union {
struct kiocb rw;
struct fsync_iocb fsync;
- struct poll_iocb poll;
};
struct kioctx *ki_ctx;
if (unlikely(iocb->aio_buf || iocb->aio_offset || iocb->aio_nbytes ||
iocb->aio_rw_flags))
return -EINVAL;
+
req->file = fget(iocb->aio_fildes);
if (unlikely(!req->file))
return -EBADF;
return 0;
}
-/* need to use list_del_init so we can check if item was present */
-static inline bool __aio_poll_remove(struct poll_iocb *req)
-{
- if (list_empty(&req->wait.entry))
- return false;
- list_del_init(&req->wait.entry);
- return true;
-}
-
-static inline void __aio_poll_complete(struct aio_kiocb *iocb, __poll_t mask)
-{
- fput(iocb->poll.file);
- aio_complete(iocb, mangle_poll(mask), 0);
-}
-
-static void aio_poll_work(struct work_struct *work)
-{
- struct aio_kiocb *iocb = container_of(work, struct aio_kiocb, poll.work);
-
- if (!list_empty_careful(&iocb->ki_list))
- aio_remove_iocb(iocb);
- __aio_poll_complete(iocb, iocb->poll.events);
-}
-
-static int aio_poll_cancel(struct kiocb *iocb)
-{
- struct aio_kiocb *aiocb = container_of(iocb, struct aio_kiocb, rw);
- struct poll_iocb *req = &aiocb->poll;
- struct wait_queue_head *head = req->head;
- bool found = false;
-
- spin_lock(&head->lock);
- found = __aio_poll_remove(req);
- spin_unlock(&head->lock);
-
- if (found) {
- req->events = 0;
- INIT_WORK(&req->work, aio_poll_work);
- schedule_work(&req->work);
- }
- return 0;
-}
-
-static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
- void *key)
-{
- struct poll_iocb *req = container_of(wait, struct poll_iocb, wait);
- struct aio_kiocb *iocb = container_of(req, struct aio_kiocb, poll);
- struct file *file = req->file;
- __poll_t mask = key_to_poll(key);
-
- assert_spin_locked(&req->head->lock);
-
- /* for instances that support it check for an event match first: */
- if (mask && !(mask & req->events))
- return 0;
-
- mask = file->f_op->poll_mask(file, req->events) & req->events;
- if (!mask)
- return 0;
-
- __aio_poll_remove(req);
-
- /*
- * Try completing without a context switch if we can acquire ctx_lock
- * without spinning. Otherwise we need to defer to a workqueue to
- * avoid a deadlock due to the lock order.
- */
- if (spin_trylock(&iocb->ki_ctx->ctx_lock)) {
- list_del_init(&iocb->ki_list);
- spin_unlock(&iocb->ki_ctx->ctx_lock);
-
- __aio_poll_complete(iocb, mask);
- } else {
- req->events = mask;
- INIT_WORK(&req->work, aio_poll_work);
- schedule_work(&req->work);
- }
-
- return 1;
-}
-
-static ssize_t aio_poll(struct aio_kiocb *aiocb, struct iocb *iocb)
-{
- struct kioctx *ctx = aiocb->ki_ctx;
- struct poll_iocb *req = &aiocb->poll;
- __poll_t mask;
-
- /* reject any unknown events outside the normal event mask. */
- if ((u16)iocb->aio_buf != iocb->aio_buf)
- return -EINVAL;
- /* reject fields that are not defined for poll */
- if (iocb->aio_offset || iocb->aio_nbytes || iocb->aio_rw_flags)
- return -EINVAL;
-
- req->events = demangle_poll(iocb->aio_buf) | EPOLLERR | EPOLLHUP;
- req->file = fget(iocb->aio_fildes);
- if (unlikely(!req->file))
- return -EBADF;
- if (!file_has_poll_mask(req->file))
- goto out_fail;
-
- req->head = req->file->f_op->get_poll_head(req->file, req->events);
- if (!req->head)
- goto out_fail;
- if (IS_ERR(req->head)) {
- mask = EPOLLERR;
- goto done;
- }
-
- init_waitqueue_func_entry(&req->wait, aio_poll_wake);
- aiocb->ki_cancel = aio_poll_cancel;
-
- spin_lock_irq(&ctx->ctx_lock);
- spin_lock(&req->head->lock);
- mask = req->file->f_op->poll_mask(req->file, req->events) & req->events;
- if (!mask) {
- __add_wait_queue(req->head, &req->wait);
- list_add_tail(&aiocb->ki_list, &ctx->active_reqs);
- }
- spin_unlock(&req->head->lock);
- spin_unlock_irq(&ctx->ctx_lock);
-done:
- if (mask)
- __aio_poll_complete(aiocb, mask);
- return 0;
-out_fail:
- fput(req->file);
- return -EINVAL; /* same as no support for IOCB_CMD_POLL */
-}
-
static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
bool compat)
{
case IOCB_CMD_FDSYNC:
ret = aio_fsync(&req->fsync, &iocb, true);
break;
- case IOCB_CMD_POLL:
- ret = aio_poll(req, &iocb);
- break;
default:
pr_debug("invalid aio operation %d\n", iocb.aio_lio_opcode);
ret = -EINVAL;
offset_in_extent = em_start - em->start;
em_end = extent_map_end(em);
em_len = em_end - em_start;
- disko = em->block_start + offset_in_extent;
flags = 0;
+ if (em->block_start < EXTENT_MAP_LAST_BYTE)
+ disko = em->block_start + offset_in_extent;
+ else
+ disko = 0;
/*
* bump off for our next call to get_extent
unlock_extent_cached(io_tree, page_start, page_end, &cached_state);
-out_unlock:
if (!ret2) {
btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE, true);
sb_end_pagefault(inode->i_sb);
extent_changeset_free(data_reserved);
return VM_FAULT_LOCKED;
}
+
+out_unlock:
unlock_page(page);
out:
btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE, (ret != 0));
u64 new_idx = 0;
u64 root_objectid;
int ret;
+ int ret2;
bool root_log_pinned = false;
bool dest_log_pinned = false;
dest_log_pinned = false;
}
}
- ret = btrfs_end_transaction(trans);
+ ret2 = btrfs_end_transaction(trans);
+ ret = ret ? ret : ret2;
out_notrans:
if (new_ino == BTRFS_FIRST_FREE_OBJECTID)
up_read(&fs_info->subvol_sem);
ret = btrfs_extent_same_range(src, loff, BTRFS_MAX_DEDUPE_LEN,
dst, dst_loff, &cmp);
if (ret)
- goto out_unlock;
+ goto out_free;
loff += BTRFS_MAX_DEDUPE_LEN;
dst_loff += BTRFS_MAX_DEDUPE_LEN;
ret = btrfs_extent_same_range(src, loff, tail_len, dst,
dst_loff, &cmp);
+out_free:
+ kvfree(cmp.src_pages);
+ kvfree(cmp.dst_pages);
+
out_unlock:
if (same_inode)
inode_unlock(src);
else
btrfs_double_inode_unlock(src, dst);
-out_free:
- kvfree(cmp.src_pages);
- kvfree(cmp.dst_pages);
-
return ret;
}
free_extent_buffer(scratch_leaf);
}
- if (done && !ret)
+ if (done && !ret) {
ret = 1;
+ fs_info->qgroup_rescan_progress.objectid = (u64)-1;
+ }
return ret;
}
if (!init_flags) {
/* we're resuming qgroup rescan at mount time */
- if (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN))
+ if (!(fs_info->qgroup_flags &
+ BTRFS_QGROUP_STATUS_FLAG_RESCAN)) {
btrfs_warn(fs_info,
"qgroup rescan init failed, qgroup is not enabled");
- else if (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_ON))
+ ret = -EINVAL;
+ } else if (!(fs_info->qgroup_flags &
+ BTRFS_QGROUP_STATUS_FLAG_ON)) {
btrfs_warn(fs_info,
"qgroup rescan init failed, qgroup rescan is not queued");
- return -EINVAL;
+ ret = -EINVAL;
+ }
+
+ if (ret)
+ return ret;
}
mutex_lock(&fs_info->qgroup_rescan_lock);
if (IS_ERR(realdn)) {
pr_err("splice_dentry error %ld %p inode %p ino %llx.%llx\n",
PTR_ERR(realdn), dn, in, ceph_vinop(in));
+ dput(dn);
dn = realdn; /* note realdn contains the error */
goto out;
} else if (realdn) {
seq_putc(m, '\n');
}
+static void
+cifs_dump_iface(struct seq_file *m, struct cifs_server_iface *iface)
+{
+ struct sockaddr_in *ipv4 = (struct sockaddr_in *)&iface->sockaddr;
+ struct sockaddr_in6 *ipv6 = (struct sockaddr_in6 *)&iface->sockaddr;
+
+ seq_printf(m, "\t\tSpeed: %zu bps\n", iface->speed);
+ seq_puts(m, "\t\tCapabilities: ");
+ if (iface->rdma_capable)
+ seq_puts(m, "rdma ");
+ if (iface->rss_capable)
+ seq_puts(m, "rss ");
+ seq_putc(m, '\n');
+ if (iface->sockaddr.ss_family == AF_INET)
+ seq_printf(m, "\t\tIPv4: %pI4\n", &ipv4->sin_addr);
+ else if (iface->sockaddr.ss_family == AF_INET6)
+ seq_printf(m, "\t\tIPv6: %pI6\n", &ipv6->sin6_addr);
+}
+
static int cifs_debug_data_proc_show(struct seq_file *m, void *v)
{
struct list_head *tmp1, *tmp2, *tmp3;
mid_entry->mid);
}
spin_unlock(&GlobalMid_Lock);
+
+ spin_lock(&ses->iface_lock);
+ if (ses->iface_count)
+ seq_printf(m, "\n\tServer interfaces: %zu\n",
+ ses->iface_count);
+ for (j = 0; j < ses->iface_count; j++) {
+ seq_printf(m, "\t%d)\n", j);
+ cifs_dump_iface(m, &ses->iface_list[j]);
+ }
+ spin_unlock(&ses->iface_lock);
}
}
spin_unlock(&cifs_tcp_ses_lock);
#include <crypto/aead.h>
int __cifs_calc_signature(struct smb_rqst *rqst,
- int start,
struct TCP_Server_Info *server, char *signature,
struct shash_desc *shash)
{
int rc;
struct kvec *iov = rqst->rq_iov;
int n_vec = rqst->rq_nvec;
+ int is_smb2 = server->vals->header_preamble_size == 0;
- for (i = start; i < n_vec; i++) {
+ /* iov[0] is actual data and not the rfc1002 length for SMB2+ */
+ if (is_smb2) {
+ if (iov[0].iov_len <= 4)
+ return -EIO;
+ i = 0;
+ } else {
+ if (n_vec < 2 || iov[0].iov_len != 4)
+ return -EIO;
+ i = 1; /* skip rfc1002 length */
+ }
+
+ for (; i < n_vec; i++) {
if (iov[i].iov_len == 0)
continue;
if (iov[i].iov_base == NULL) {
cifs_dbg(VFS, "null iovec entry\n");
return -EIO;
}
- if (i == 1 && iov[1].iov_len <= 4)
- break; /* nothing to sign or corrupt header */
+
rc = crypto_shash_update(shash,
iov[i].iov_base, iov[i].iov_len);
if (rc) {
return rc;
}
- return __cifs_calc_signature(rqst, 1, server, signature,
+ return __cifs_calc_signature(rqst, server, signature,
&server->secmech.sdescmd5->shash);
}
#define CIFS_MAGIC_NUMBER 0xFF534D42 /* the first four bytes of SMB PDUs */
+#define CIFS_PORT 445
+#define RFC1001_PORT 139
+
/*
* The sizes of various internal tables and strings
*/
/* send echo request */
int (*echo)(struct TCP_Server_Info *);
/* create directory */
+ int (*posix_mkdir)(const unsigned int xid, struct inode *inode,
+ umode_t mode, struct cifs_tcon *tcon,
+ const char *full_path,
+ struct cifs_sb_info *cifs_sb);
int (*mkdir)(const unsigned int, struct cifs_tcon *, const char *,
struct cifs_sb_info *);
/* set info on created directory */
#endif
+struct cifs_server_iface {
+ size_t speed;
+ unsigned int rdma_capable : 1;
+ unsigned int rss_capable : 1;
+ struct sockaddr_storage sockaddr;
+};
+
/*
* Session structure. One of these for each uid session with a particular host
*/
#ifdef CONFIG_CIFS_SMB311
__u8 preauth_sha_hash[SMB2_PREAUTH_HASH_SIZE];
#endif /* 3.1.1 */
+
+ /*
+ * Network interfaces available on the server this session is
+ * connected to.
+ *
+ * Other channels can be opened by connecting and binding this
+ * session to interfaces from this list.
+ *
+ * iface_lock should be taken when accessing any of these fields
+ */
+ spinlock_t iface_lock;
+ struct cifs_server_iface *iface_list;
+ size_t iface_count;
+ unsigned long iface_last_update; /* jiffies */
};
static inline bool
return ses->server->vals->cap_unix & ses->capabilities;
}
+struct cached_fid {
+ bool is_valid:1; /* Do we have a useable root fid */
+ struct cifs_fid *fid;
+ struct mutex fid_mutex;
+ struct cifs_tcon *tcon;
+ struct work_struct lease_break;
+};
+
/*
* there is one of these for each connection to a resource on a particular
* session
struct fscache_cookie *fscache; /* cookie for share */
#endif
struct list_head pending_opens; /* list of incomplete opens */
- bool valid_root_fid:1; /* Do we have a useable root fid */
- struct mutex prfid_mutex; /* prevents reopen race after dead ses*/
- struct cifs_fid *prfid; /* handle to the directory at top of share */
+ struct cached_fid crfid; /* Cached root fid */
/* BB add field for back pointer to sb struct(s)? */
};
struct kvec *, int /* nvec to send */,
int * /* type of buf returned */, const int flags,
struct kvec * /* resp vec */);
-extern int smb2_send_recv(const unsigned int xid, struct cifs_ses *pses,
- struct kvec *pkvec, int nvec_to_send,
- int *pbuftype, const int flags,
- struct kvec *presp);
extern int SendReceiveBlockingLock(const unsigned int xid,
struct cifs_tcon *ptcon,
struct smb_hdr *in_buf ,
struct cifs_sb_info *cifs_sb,
const unsigned char *path, char *pbuf,
unsigned int *pbytes_written);
-int __cifs_calc_signature(struct smb_rqst *rqst, int start,
+int __cifs_calc_signature(struct smb_rqst *rqst,
struct TCP_Server_Info *server, char *signature,
struct shash_desc *shash);
enum securityEnum cifs_select_sectype(struct TCP_Server_Info *,
struct cifs_aio_ctx *cifs_aio_ctx_alloc(void);
void cifs_aio_ctx_release(struct kref *refcount);
int setup_aio_ctx_iter(struct cifs_aio_ctx *ctx, struct iov_iter *iter, int rw);
+void smb2_cached_lease_break(struct work_struct *work);
int cifs_alloc_hash(const char *name, struct crypto_shash **shash,
struct sdesc **sdesc);
}
spin_unlock(&tcon->open_file_lock);
- mutex_lock(&tcon->prfid_mutex);
- tcon->valid_root_fid = false;
- memset(tcon->prfid, 0, sizeof(struct cifs_fid));
- mutex_unlock(&tcon->prfid_mutex);
+ mutex_lock(&tcon->crfid.fid_mutex);
+ tcon->crfid.is_valid = false;
+ memset(tcon->crfid.fid, 0, sizeof(struct cifs_fid));
+ mutex_unlock(&tcon->crfid.fid_mutex);
/*
* BB Add call to invalidate_inodes(sb) for all superblocks mounted
#include "smb2proto.h"
#include "smbdirect.h"
-#define CIFS_PORT 445
-#define RFC1001_PORT 139
-
extern mempool_t *cifs_req_poolp;
extern bool disable_legacy_dialects;
#ifdef CONFIG_CIFS_SMB311
if ((volume_info->linux_ext) && (ses->server->posix_ext_supported)) {
- if (ses->server->vals->protocol_id == SMB311_PROT_ID)
+ if (ses->server->vals->protocol_id == SMB311_PROT_ID) {
tcon->posix_extensions = true;
+ printk_once(KERN_WARNING
+ "SMB3.11 POSIX Extensions are experimental\n");
+ }
}
#endif /* 311 */
goto mkdir_out;
}
+ server = tcon->ses->server;
+
+#ifdef CONFIG_CIFS_SMB311
+ if ((server->ops->posix_mkdir) && (tcon->posix_extensions)) {
+ rc = server->ops->posix_mkdir(xid, inode, mode, tcon, full_path,
+ cifs_sb);
+ d_drop(direntry); /* for time being always refresh inode info */
+ goto mkdir_out;
+ }
+#endif /* SMB311 */
+
if (cap_unix(tcon->ses) && (CIFS_UNIX_POSIX_PATH_OPS_CAP &
le64_to_cpu(tcon->fsUnixInfo.Capability))) {
rc = cifs_posix_mkdir(inode, direntry, mode, full_path, cifs_sb,
goto mkdir_out;
}
- server = tcon->ses->server;
-
if (!server->ops->mkdir) {
rc = -ENOSYS;
goto mkdir_out;
INIT_LIST_HEAD(&ret_buf->smb_ses_list);
INIT_LIST_HEAD(&ret_buf->tcon_list);
mutex_init(&ret_buf->session_mutex);
+ spin_lock_init(&ret_buf->iface_lock);
}
return ret_buf;
}
kfree(buf_to_free->user_name);
kfree(buf_to_free->domainName);
kzfree(buf_to_free->auth_key.response);
+ kfree(buf_to_free->iface_list);
kzfree(buf_to_free);
}
INIT_LIST_HEAD(&ret_buf->openFileList);
INIT_LIST_HEAD(&ret_buf->tcon_list);
spin_lock_init(&ret_buf->open_file_lock);
- mutex_init(&ret_buf->prfid_mutex);
- ret_buf->prfid = kzalloc(sizeof(struct cifs_fid), GFP_KERNEL);
+ mutex_init(&ret_buf->crfid.fid_mutex);
+ ret_buf->crfid.fid = kzalloc(sizeof(struct cifs_fid),
+ GFP_KERNEL);
#ifdef CONFIG_CIFS_STATS
spin_lock_init(&ret_buf->stat_lock);
#endif
atomic_dec(&tconInfoAllocCount);
kfree(buf_to_free->nativeFileSystem);
kzfree(buf_to_free->password);
- kfree(buf_to_free->prfid);
+ kfree(buf_to_free->crfid.fid);
kfree(buf_to_free);
}
#ifdef CONFIG_CIFS_SMB311
/* SMB311 POSIX extensions paths do not include leading slash */
else if (cifs_sb_master_tlink(cifs_sb) &&
- cifs_sb_master_tcon(cifs_sb)->posix_extensions) {
+ cifs_sb_master_tcon(cifs_sb)->posix_extensions &&
+ (from[0] == '/')) {
start_of_path = from + 1;
}
#endif /* 311 */
{
struct smb2_lease_break_work *lw = container_of(work,
struct smb2_lease_break_work, lease_break);
- int rc;
+ int rc = 0;
rc = SMB2_lease_break(0, tlink_tcon(lw->tlink), lw->lease_key,
lw->lease_state);
+
cifs_dbg(FYI, "Lease release rc %d\n", rc);
cifs_put_tlink(lw->tlink);
kfree(lw);
open->oplock = lease_state;
}
+
return found;
}
return true;
}
spin_unlock(&tcon->open_file_lock);
+
+ if (tcon->crfid.is_valid &&
+ !memcmp(rsp->LeaseKey,
+ tcon->crfid.fid->lease_key,
+ SMB2_LEASE_KEY_SIZE)) {
+ INIT_WORK(&tcon->crfid.lease_break,
+ smb2_cached_lease_break);
+ queue_work(cifsiod_wq,
+ &tcon->crfid.lease_break);
+ spin_unlock(&cifs_tcp_ses_lock);
+ return true;
+ }
}
}
}
return rsize;
}
-#ifdef CONFIG_CIFS_STATS2
+
+static int
+parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf,
+ size_t buf_len,
+ struct cifs_server_iface **iface_list,
+ size_t *iface_count)
+{
+ struct network_interface_info_ioctl_rsp *p;
+ struct sockaddr_in *addr4;
+ struct sockaddr_in6 *addr6;
+ struct iface_info_ipv4 *p4;
+ struct iface_info_ipv6 *p6;
+ struct cifs_server_iface *info;
+ ssize_t bytes_left;
+ size_t next = 0;
+ int nb_iface = 0;
+ int rc = 0;
+
+ *iface_list = NULL;
+ *iface_count = 0;
+
+ /*
+ * Fist pass: count and sanity check
+ */
+
+ bytes_left = buf_len;
+ p = buf;
+ while (bytes_left >= sizeof(*p)) {
+ nb_iface++;
+ next = le32_to_cpu(p->Next);
+ if (!next) {
+ bytes_left -= sizeof(*p);
+ break;
+ }
+ p = (struct network_interface_info_ioctl_rsp *)((u8 *)p+next);
+ bytes_left -= next;
+ }
+
+ if (!nb_iface) {
+ cifs_dbg(VFS, "%s: malformed interface info\n", __func__);
+ rc = -EINVAL;
+ goto out;
+ }
+
+ if (bytes_left || p->Next)
+ cifs_dbg(VFS, "%s: incomplete interface info\n", __func__);
+
+
+ /*
+ * Second pass: extract info to internal structure
+ */
+
+ *iface_list = kcalloc(nb_iface, sizeof(**iface_list), GFP_KERNEL);
+ if (!*iface_list) {
+ rc = -ENOMEM;
+ goto out;
+ }
+
+ info = *iface_list;
+ bytes_left = buf_len;
+ p = buf;
+ while (bytes_left >= sizeof(*p)) {
+ info->speed = le64_to_cpu(p->LinkSpeed);
+ info->rdma_capable = le32_to_cpu(p->Capability & RDMA_CAPABLE);
+ info->rss_capable = le32_to_cpu(p->Capability & RSS_CAPABLE);
+
+ cifs_dbg(FYI, "%s: adding iface %zu\n", __func__, *iface_count);
+ cifs_dbg(FYI, "%s: speed %zu bps\n", __func__, info->speed);
+ cifs_dbg(FYI, "%s: capabilities 0x%08x\n", __func__,
+ le32_to_cpu(p->Capability));
+
+ switch (p->Family) {
+ /*
+ * The kernel and wire socket structures have the same
+ * layout and use network byte order but make the
+ * conversion explicit in case either one changes.
+ */
+ case INTERNETWORK:
+ addr4 = (struct sockaddr_in *)&info->sockaddr;
+ p4 = (struct iface_info_ipv4 *)p->Buffer;
+ addr4->sin_family = AF_INET;
+ memcpy(&addr4->sin_addr, &p4->IPv4Address, 4);
+
+ /* [MS-SMB2] 2.2.32.5.1.1 Clients MUST ignore these */
+ addr4->sin_port = cpu_to_be16(CIFS_PORT);
+
+ cifs_dbg(FYI, "%s: ipv4 %pI4\n", __func__,
+ &addr4->sin_addr);
+ break;
+ case INTERNETWORKV6:
+ addr6 = (struct sockaddr_in6 *)&info->sockaddr;
+ p6 = (struct iface_info_ipv6 *)p->Buffer;
+ addr6->sin6_family = AF_INET6;
+ memcpy(&addr6->sin6_addr, &p6->IPv6Address, 16);
+
+ /* [MS-SMB2] 2.2.32.5.1.2 Clients MUST ignore these */
+ addr6->sin6_flowinfo = 0;
+ addr6->sin6_scope_id = 0;
+ addr6->sin6_port = cpu_to_be16(CIFS_PORT);
+
+ cifs_dbg(FYI, "%s: ipv6 %pI6\n", __func__,
+ &addr6->sin6_addr);
+ break;
+ default:
+ cifs_dbg(VFS,
+ "%s: skipping unsupported socket family\n",
+ __func__);
+ goto next_iface;
+ }
+
+ (*iface_count)++;
+ info++;
+next_iface:
+ next = le32_to_cpu(p->Next);
+ if (!next)
+ break;
+ p = (struct network_interface_info_ioctl_rsp *)((u8 *)p+next);
+ bytes_left -= next;
+ }
+
+ if (!*iface_count) {
+ rc = -EINVAL;
+ goto out;
+ }
+
+out:
+ if (rc) {
+ kfree(*iface_list);
+ *iface_count = 0;
+ *iface_list = NULL;
+ }
+ return rc;
+}
+
+
static int
SMB3_request_interfaces(const unsigned int xid, struct cifs_tcon *tcon)
{
int rc;
unsigned int ret_data_len = 0;
- struct network_interface_info_ioctl_rsp *out_buf;
+ struct network_interface_info_ioctl_rsp *out_buf = NULL;
+ struct cifs_server_iface *iface_list;
+ size_t iface_count;
+ struct cifs_ses *ses = tcon->ses;
rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID,
FSCTL_QUERY_NETWORK_INTERFACE_INFO, true /* is_fsctl */,
NULL /* no data input */, 0 /* no data input */,
(char **)&out_buf, &ret_data_len);
- if (rc != 0)
+ if (rc != 0) {
cifs_dbg(VFS, "error %d on ioctl to get interface list\n", rc);
- else if (ret_data_len < sizeof(struct network_interface_info_ioctl_rsp)) {
- cifs_dbg(VFS, "server returned bad net interface info buf\n");
- rc = -EINVAL;
- } else {
- /* Dump info on first interface */
- cifs_dbg(FYI, "Adapter Capability 0x%x\t",
- le32_to_cpu(out_buf->Capability));
- cifs_dbg(FYI, "Link Speed %lld\n",
- le64_to_cpu(out_buf->LinkSpeed));
+ goto out;
}
+
+ rc = parse_server_interfaces(out_buf, ret_data_len,
+ &iface_list, &iface_count);
+ if (rc)
+ goto out;
+
+ spin_lock(&ses->iface_lock);
+ kfree(ses->iface_list);
+ ses->iface_list = iface_list;
+ ses->iface_count = iface_count;
+ ses->iface_last_update = jiffies;
+ spin_unlock(&ses->iface_lock);
+
+out:
kfree(out_buf);
return rc;
}
-#endif /* STATS2 */
+
+void
+smb2_cached_lease_break(struct work_struct *work)
+{
+ struct cached_fid *cfid = container_of(work,
+ struct cached_fid, lease_break);
+ mutex_lock(&cfid->fid_mutex);
+ if (cfid->is_valid) {
+ cifs_dbg(FYI, "clear cached root file handle\n");
+ SMB2_close(0, cfid->tcon, cfid->fid->persistent_fid,
+ cfid->fid->volatile_fid);
+ cfid->is_valid = false;
+ }
+ mutex_unlock(&cfid->fid_mutex);
+}
/*
* Open the directory at the root of a share
struct cifs_open_parms oparams;
int rc;
__le16 srch_path = 0; /* Null - since an open of top of share */
- u8 oplock = SMB2_OPLOCK_LEVEL_NONE;
+ u8 oplock = SMB2_OPLOCK_LEVEL_II;
- mutex_lock(&tcon->prfid_mutex);
- if (tcon->valid_root_fid) {
+ mutex_lock(&tcon->crfid.fid_mutex);
+ if (tcon->crfid.is_valid) {
cifs_dbg(FYI, "found a cached root file handle\n");
- memcpy(pfid, tcon->prfid, sizeof(struct cifs_fid));
- mutex_unlock(&tcon->prfid_mutex);
+ memcpy(pfid, tcon->crfid.fid, sizeof(struct cifs_fid));
+ mutex_unlock(&tcon->crfid.fid_mutex);
return 0;
}
rc = SMB2_open(xid, &oparams, &srch_path, &oplock, NULL, NULL, NULL);
if (rc == 0) {
- memcpy(tcon->prfid, pfid, sizeof(struct cifs_fid));
- tcon->valid_root_fid = true;
+ memcpy(tcon->crfid.fid, pfid, sizeof(struct cifs_fid));
+ tcon->crfid.tcon = tcon;
+ tcon->crfid.is_valid = true;
}
- mutex_unlock(&tcon->prfid_mutex);
+ mutex_unlock(&tcon->crfid.fid_mutex);
return rc;
}
if (rc)
return;
-#ifdef CONFIG_CIFS_STATS2
SMB3_request_interfaces(xid, tcon);
-#endif /* STATS2 */
SMB2_QFS_attr(xid, tcon, fid.persistent_fid, fid.volatile_fid,
FS_ATTRIBUTE_INFORMATION);
struct cifs_open_parms oparms;
struct cifs_fid fid;
- if ((*full_path == 0) && tcon->valid_root_fid)
+ if ((*full_path == 0) && tcon->crfid.is_valid)
return 0;
utf16_path = cifs_convert_path_to_utf16(full_path, cifs_sb);
struct smb_rqst *old_rq)
{
struct smb2_sync_hdr *shdr =
- (struct smb2_sync_hdr *)old_rq->rq_iov[1].iov_base;
+ (struct smb2_sync_hdr *)old_rq->rq_iov[0].iov_base;
memset(tr_hdr, 0, sizeof(struct smb2_transform_hdr));
tr_hdr->ProtocolId = SMB2_TRANSFORM_PROTO_NUM;
}
/* Assumes:
- * rqst->rq_iov[0] is rfc1002 length
- * rqst->rq_iov[1] is tranform header
- * rqst->rq_iov[2+] data to be encrypted/decrypted
+ * rqst->rq_iov[0] is transform header
+ * rqst->rq_iov[1+] data to be encrypted/decrypted
*/
static struct scatterlist *
init_sg(struct smb_rqst *rqst, u8 *sign)
{
- unsigned int sg_len = rqst->rq_nvec + rqst->rq_npages;
+ unsigned int sg_len = rqst->rq_nvec + rqst->rq_npages + 1;
unsigned int assoc_data_len = sizeof(struct smb2_transform_hdr) - 20;
struct scatterlist *sg;
unsigned int i;
return NULL;
sg_init_table(sg, sg_len);
- smb2_sg_set_buf(&sg[0], rqst->rq_iov[1].iov_base + 20, assoc_data_len);
- for (i = 1; i < rqst->rq_nvec - 1; i++)
- smb2_sg_set_buf(&sg[i], rqst->rq_iov[i+1].iov_base,
- rqst->rq_iov[i+1].iov_len);
+ smb2_sg_set_buf(&sg[0], rqst->rq_iov[0].iov_base + 20, assoc_data_len);
+ for (i = 1; i < rqst->rq_nvec; i++)
+ smb2_sg_set_buf(&sg[i], rqst->rq_iov[i].iov_base,
+ rqst->rq_iov[i].iov_len);
for (j = 0; i < sg_len - 1; i++, j++) {
unsigned int len, offset;
return 1;
}
/*
- * Encrypt or decrypt @rqst message. @rqst has the following format:
- * iov[0] - rfc1002 length
- * iov[1] - transform header (associate data),
- * iov[2-N] and pages - data to encrypt.
- * On success return encrypted data in iov[2-N] and pages, leave iov[0-1]
+ * Encrypt or decrypt @rqst message. @rqst[0] has the following format:
+ * iov[0] - transform header (associate data),
+ * iov[1-N] - SMB2 header and pages - data to encrypt.
+ * On success return encrypted data in iov[1-N] and pages, leave iov[0]
* untouched.
*/
static int
crypt_message(struct TCP_Server_Info *server, struct smb_rqst *rqst, int enc)
{
struct smb2_transform_hdr *tr_hdr =
- (struct smb2_transform_hdr *)rqst->rq_iov[1].iov_base;
+ (struct smb2_transform_hdr *)rqst->rq_iov[0].iov_base;
unsigned int assoc_data_len = sizeof(struct smb2_transform_hdr) - 20;
int rc = 0;
struct scatterlist *sg;
return rc;
}
-/*
- * This is called from smb_send_rqst. At this point we have the rfc1002
- * header as the first element in the vector.
- */
static int
smb3_init_transform_rq(struct TCP_Server_Info *server, struct smb_rqst *new_rq,
struct smb_rqst *old_rq)
struct page **pages;
struct smb2_transform_hdr *tr_hdr;
unsigned int npages = old_rq->rq_npages;
- unsigned int orig_len = get_rfc1002_length(old_rq->rq_iov[0].iov_base);
+ unsigned int orig_len;
int i;
int rc = -ENOMEM;
goto err_free_pages;
}
- /* Make space for one extra iov to hold the transform header */
iov = kmalloc_array(old_rq->rq_nvec + 1, sizeof(struct kvec),
GFP_KERNEL);
if (!iov)
goto err_free_pages;
- /* copy all iovs from the old except the 1st one (rfc1002 length) */
- memcpy(&iov[2], &old_rq->rq_iov[1],
- sizeof(struct kvec) * (old_rq->rq_nvec - 1));
- /* copy the rfc1002 iov */
- iov[0].iov_base = old_rq->rq_iov[0].iov_base;
- iov[0].iov_len = old_rq->rq_iov[0].iov_len;
+ /* copy all iovs from the old */
+ memcpy(&iov[1], &old_rq->rq_iov[0],
+ sizeof(struct kvec) * old_rq->rq_nvec);
new_rq->rq_iov = iov;
new_rq->rq_nvec = old_rq->rq_nvec + 1;
if (!tr_hdr)
goto err_free_iov;
+ orig_len = smb2_rqst_len(old_rq, false);
+
/* fill the 2nd iov with a transform header */
fill_transform_hdr(tr_hdr, orig_len, old_rq);
- new_rq->rq_iov[1].iov_base = tr_hdr;
- new_rq->rq_iov[1].iov_len = sizeof(struct smb2_transform_hdr);
-
- /* Update rfc1002 header */
- inc_rfc1001_len(new_rq->rq_iov[0].iov_base,
- sizeof(struct smb2_transform_hdr));
+ new_rq->rq_iov[0].iov_base = tr_hdr;
+ new_rq->rq_iov[0].iov_len = sizeof(struct smb2_transform_hdr);
/* copy pages form the old */
for (i = 0; i < npages; i++) {
put_page(rqst->rq_pages[i]);
kfree(rqst->rq_pages);
/* free transform header */
- kfree(rqst->rq_iov[1].iov_base);
+ kfree(rqst->rq_iov[0].iov_base);
kfree(rqst->rq_iov);
}
unsigned int buf_data_size, struct page **pages,
unsigned int npages, unsigned int page_data_size)
{
- struct kvec iov[3];
+ struct kvec iov[2];
struct smb_rqst rqst = {NULL};
int rc;
- iov[0].iov_base = NULL;
- iov[0].iov_len = 0;
- iov[1].iov_base = buf;
- iov[1].iov_len = sizeof(struct smb2_transform_hdr);
- iov[2].iov_base = buf + sizeof(struct smb2_transform_hdr);
- iov[2].iov_len = buf_data_size;
+ iov[0].iov_base = buf;
+ iov[0].iov_len = sizeof(struct smb2_transform_hdr);
+ iov[1].iov_base = buf + sizeof(struct smb2_transform_hdr);
+ iov[1].iov_len = buf_data_size;
rqst.rq_iov = iov;
- rqst.rq_nvec = 3;
+ rqst.rq_nvec = 2;
rqst.rq_pages = pages;
rqst.rq_npages = npages;
rqst.rq_pagesz = PAGE_SIZE;
if (rc)
return rc;
- memmove(buf, iov[2].iov_base, buf_data_size);
+ memmove(buf, iov[1].iov_base, buf_data_size);
server->total_read = buf_data_size + page_data_size;
.set_compression = smb2_set_compression,
.mkdir = smb2_mkdir,
.mkdir_setinfo = smb2_mkdir_setinfo,
+ .posix_mkdir = smb311_posix_mkdir,
.rmdir = smb2_rmdir,
.unlink = smb2_unlink,
.rename = smb2_rename_path,
int
SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
{
+ struct smb_rqst rqst;
struct smb2_negotiate_req *req;
struct smb2_negotiate_rsp *rsp;
struct kvec iov[1];
iov[0].iov_base = (char *)req;
iov[0].iov_len = total_len;
- rc = smb2_send_recv(xid, ses, iov, 1, &resp_buftype, flags, &rsp_iov);
+ memset(&rqst, 0, sizeof(struct smb_rqst));
+ rqst.rq_iov = iov;
+ rqst.rq_nvec = 1;
+
+ rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov);
cifs_small_buf_release(req);
rsp = (struct smb2_negotiate_rsp *)rsp_iov.iov_base;
/*
req->PreviousSessionId = sess_data->previous_session;
req->Flags = 0; /* MBZ */
- /* to enable echos and oplocks */
- req->sync_hdr.CreditRequest = cpu_to_le16(3);
+
+ /* enough to enable echos and oplocks and one max size write */
+ req->sync_hdr.CreditRequest = cpu_to_le16(130);
/* only one of SMB2 signing flags may be set in SMB2 request */
if (server->sign)
SMB2_sess_sendreceive(struct SMB2_sess_data *sess_data)
{
int rc;
+ struct smb_rqst rqst;
struct smb2_sess_setup_req *req = sess_data->iov[0].iov_base;
struct kvec rsp_iov = { NULL, 0 };
cpu_to_le16(sizeof(struct smb2_sess_setup_req) - 1 /* pad */);
req->SecurityBufferLength = cpu_to_le16(sess_data->iov[1].iov_len);
- /* BB add code to build os and lm fields */
+ memset(&rqst, 0, sizeof(struct smb_rqst));
+ rqst.rq_iov = sess_data->iov;
+ rqst.rq_nvec = 2;
- rc = smb2_send_recv(sess_data->xid, sess_data->ses,
- sess_data->iov, 2,
+ /* BB add code to build os and lm fields */
+ rc = cifs_send_recv(sess_data->xid, sess_data->ses,
+ &rqst,
&sess_data->buf0_type,
CIFS_LOG_ERROR | CIFS_NEG_OP, &rsp_iov);
cifs_small_buf_release(sess_data->iov[0].iov_base);
int
SMB2_logoff(const unsigned int xid, struct cifs_ses *ses)
{
+ struct smb_rqst rqst;
struct smb2_logoff_req *req; /* response is also trivial struct */
int rc = 0;
struct TCP_Server_Info *server;
iov[0].iov_base = (char *)req;
iov[0].iov_len = total_len;
- rc = smb2_send_recv(xid, ses, iov, 1, &resp_buf_type, flags, &rsp_iov);
+ memset(&rqst, 0, sizeof(struct smb_rqst));
+ rqst.rq_iov = iov;
+ rqst.rq_nvec = 1;
+
+ rc = cifs_send_recv(xid, ses, &rqst, &resp_buf_type, flags, &rsp_iov);
cifs_small_buf_release(req);
/*
* No tcon so can't do
SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
struct cifs_tcon *tcon, const struct nls_table *cp)
{
+ struct smb_rqst rqst;
struct smb2_tree_connect_req *req;
struct smb2_tree_connect_rsp *rsp = NULL;
struct kvec iov[2];
!smb3_encryption_required(tcon))
req->sync_hdr.Flags |= SMB2_FLAGS_SIGNED;
- rc = smb2_send_recv(xid, ses, iov, 2, &resp_buftype, flags, &rsp_iov);
+ memset(&rqst, 0, sizeof(struct smb_rqst));
+ rqst.rq_iov = iov;
+ rqst.rq_nvec = 2;
+
+ rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov);
cifs_small_buf_release(req);
rsp = (struct smb2_tree_connect_rsp *)rsp_iov.iov_base;
int
SMB2_tdis(const unsigned int xid, struct cifs_tcon *tcon)
{
+ struct smb_rqst rqst;
struct smb2_tree_disconnect_req *req; /* response is trivial */
int rc = 0;
struct cifs_ses *ses = tcon->ses;
iov[0].iov_base = (char *)req;
iov[0].iov_len = total_len;
- rc = smb2_send_recv(xid, ses, iov, 1, &resp_buf_type, flags, &rsp_iov);
+ memset(&rqst, 0, sizeof(struct smb_rqst));
+ rqst.rq_iov = iov;
+ rqst.rq_nvec = 1;
+
+ rc = cifs_send_recv(xid, ses, &rqst, &resp_buf_type, flags, &rsp_iov);
cifs_small_buf_release(req);
if (rc)
cifs_stats_fail_inc(tcon, SMB2_TREE_DISCONNECT_HE);
return 0;
}
+#ifdef CONFIG_CIFS_SMB311
+int smb311_posix_mkdir(const unsigned int xid, struct inode *inode,
+ umode_t mode, struct cifs_tcon *tcon,
+ const char *full_path,
+ struct cifs_sb_info *cifs_sb)
+{
+ struct smb_rqst rqst;
+ struct smb2_create_req *req;
+ struct smb2_create_rsp *rsp;
+ struct TCP_Server_Info *server;
+ struct cifs_ses *ses = tcon->ses;
+ struct kvec iov[3]; /* make sure at least one for each open context */
+ struct kvec rsp_iov = {NULL, 0};
+ int resp_buftype;
+ int uni_path_len;
+ __le16 *copy_path = NULL;
+ int copy_size;
+ int rc = 0;
+ unsigned int n_iov = 2;
+ __u32 file_attributes = 0;
+ char *pc_buf = NULL;
+ int flags = 0;
+ unsigned int total_len;
+ __le16 *path = cifs_convert_path_to_utf16(full_path, cifs_sb);
+
+ if (!path)
+ return -ENOMEM;
+
+ cifs_dbg(FYI, "mkdir\n");
+
+ if (ses && (ses->server))
+ server = ses->server;
+ else
+ return -EIO;
+
+ rc = smb2_plain_req_init(SMB2_CREATE, tcon, (void **) &req, &total_len);
+
+ if (rc)
+ return rc;
+
+ if (smb3_encryption_required(tcon))
+ flags |= CIFS_TRANSFORM_REQ;
+
+
+ req->ImpersonationLevel = IL_IMPERSONATION;
+ req->DesiredAccess = cpu_to_le32(FILE_WRITE_ATTRIBUTES);
+ /* File attributes ignored on open (used in create though) */
+ req->FileAttributes = cpu_to_le32(file_attributes);
+ req->ShareAccess = FILE_SHARE_ALL_LE;
+ req->CreateDisposition = cpu_to_le32(FILE_CREATE);
+ req->CreateOptions = cpu_to_le32(CREATE_NOT_FILE);
+
+ iov[0].iov_base = (char *)req;
+ /* -1 since last byte is buf[0] which is sent below (path) */
+ iov[0].iov_len = total_len - 1;
+
+ req->NameOffset = cpu_to_le16(sizeof(struct smb2_create_req));
+
+ /* [MS-SMB2] 2.2.13 NameOffset:
+ * If SMB2_FLAGS_DFS_OPERATIONS is set in the Flags field of
+ * the SMB2 header, the file name includes a prefix that will
+ * be processed during DFS name normalization as specified in
+ * section 3.3.5.9. Otherwise, the file name is relative to
+ * the share that is identified by the TreeId in the SMB2
+ * header.
+ */
+ if (tcon->share_flags & SHI1005_FLAGS_DFS) {
+ int name_len;
+
+ req->sync_hdr.Flags |= SMB2_FLAGS_DFS_OPERATIONS;
+ rc = alloc_path_with_tree_prefix(©_path, ©_size,
+ &name_len,
+ tcon->treeName, path);
+ if (rc) {
+ cifs_small_buf_release(req);
+ return rc;
+ }
+ req->NameLength = cpu_to_le16(name_len * 2);
+ uni_path_len = copy_size;
+ path = copy_path;
+ } else {
+ uni_path_len = (2 * UniStrnlen((wchar_t *)path, PATH_MAX)) + 2;
+ /* MUST set path len (NameLength) to 0 opening root of share */
+ req->NameLength = cpu_to_le16(uni_path_len - 2);
+ if (uni_path_len % 8 != 0) {
+ copy_size = roundup(uni_path_len, 8);
+ copy_path = kzalloc(copy_size, GFP_KERNEL);
+ if (!copy_path) {
+ cifs_small_buf_release(req);
+ return -ENOMEM;
+ }
+ memcpy((char *)copy_path, (const char *)path,
+ uni_path_len);
+ uni_path_len = copy_size;
+ path = copy_path;
+ }
+ }
+
+ iov[1].iov_len = uni_path_len;
+ iov[1].iov_base = path;
+ req->RequestedOplockLevel = SMB2_OPLOCK_LEVEL_NONE;
+
+ if (tcon->posix_extensions) {
+ if (n_iov > 2) {
+ struct create_context *ccontext =
+ (struct create_context *)iov[n_iov-1].iov_base;
+ ccontext->Next =
+ cpu_to_le32(iov[n_iov-1].iov_len);
+ }
+
+ rc = add_posix_context(iov, &n_iov, mode);
+ if (rc) {
+ cifs_small_buf_release(req);
+ kfree(copy_path);
+ return rc;
+ }
+ pc_buf = iov[n_iov-1].iov_base;
+ }
+
+
+ memset(&rqst, 0, sizeof(struct smb_rqst));
+ rqst.rq_iov = iov;
+ rqst.rq_nvec = n_iov;
+
+ rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags,
+ &rsp_iov);
+
+ cifs_small_buf_release(req);
+ rsp = (struct smb2_create_rsp *)rsp_iov.iov_base;
+
+ if (rc != 0) {
+ cifs_stats_fail_inc(tcon, SMB2_CREATE_HE);
+ trace_smb3_posix_mkdir_err(xid, tcon->tid, ses->Suid,
+ CREATE_NOT_FILE, FILE_WRITE_ATTRIBUTES, rc);
+ goto smb311_mkdir_exit;
+ } else
+ trace_smb3_posix_mkdir_done(xid, rsp->PersistentFileId, tcon->tid,
+ ses->Suid, CREATE_NOT_FILE,
+ FILE_WRITE_ATTRIBUTES);
+
+ SMB2_close(xid, tcon, rsp->PersistentFileId, rsp->VolatileFileId);
+
+ /* Eventually save off posix specific response info and timestaps */
+
+smb311_mkdir_exit:
+ kfree(copy_path);
+ kfree(pc_buf);
+ free_rsp_buf(resp_buftype, rsp);
+ return rc;
+
+}
+#endif /* SMB311 */
+
int
SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
__u8 *oplock, struct smb2_file_all_info *buf,
struct kvec *err_iov, int *buftype)
{
+ struct smb_rqst rqst;
struct smb2_create_req *req;
struct smb2_create_rsp *rsp;
struct TCP_Server_Info *server;
}
#endif /* SMB311 */
- rc = smb2_send_recv(xid, ses, iov, n_iov, &resp_buftype, flags,
+ memset(&rqst, 0, sizeof(struct smb_rqst));
+ rqst.rq_iov = iov;
+ rqst.rq_nvec = n_iov;
+
+ rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags,
&rsp_iov);
cifs_small_buf_release(req);
rsp = (struct smb2_create_rsp *)rsp_iov.iov_base;
char *in_data, u32 indatalen,
char **out_data, u32 *plen /* returned data len */)
{
+ struct smb_rqst rqst;
struct smb2_ioctl_req *req;
struct smb2_ioctl_rsp *rsp;
struct cifs_ses *ses;
if (opcode == FSCTL_VALIDATE_NEGOTIATE_INFO)
req->sync_hdr.Flags |= SMB2_FLAGS_SIGNED;
- rc = smb2_send_recv(xid, ses, iov, n_iov, &resp_buftype, flags,
+ memset(&rqst, 0, sizeof(struct smb_rqst));
+ rqst.rq_iov = iov;
+ rqst.rq_nvec = n_iov;
+
+ rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags,
&rsp_iov);
cifs_small_buf_release(req);
rsp = (struct smb2_ioctl_rsp *)rsp_iov.iov_base;
SMB2_close_flags(const unsigned int xid, struct cifs_tcon *tcon,
u64 persistent_fid, u64 volatile_fid, int flags)
{
+ struct smb_rqst rqst;
struct smb2_close_req *req;
struct smb2_close_rsp *rsp;
struct cifs_ses *ses = tcon->ses;
iov[0].iov_base = (char *)req;
iov[0].iov_len = total_len;
- rc = smb2_send_recv(xid, ses, iov, 1, &resp_buftype, flags, &rsp_iov);
+ memset(&rqst, 0, sizeof(struct smb_rqst));
+ rqst.rq_iov = iov;
+ rqst.rq_nvec = 1;
+
+ rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov);
cifs_small_buf_release(req);
rsp = (struct smb2_close_rsp *)rsp_iov.iov_base;
u32 additional_info, size_t output_len, size_t min_len, void **data,
u32 *dlen)
{
+ struct smb_rqst rqst;
struct smb2_query_info_req *req;
struct smb2_query_info_rsp *rsp = NULL;
struct kvec iov[2];
/* 1 for Buffer */
iov[0].iov_len = total_len - 1;
- rc = smb2_send_recv(xid, ses, iov, 1, &resp_buftype, flags, &rsp_iov);
+ memset(&rqst, 0, sizeof(struct smb_rqst));
+ rqst.rq_iov = iov;
+ rqst.rq_nvec = 1;
+
+ rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov);
cifs_small_buf_release(req);
rsp = (struct smb2_query_info_rsp *)rsp_iov.iov_base;
{
struct smb2_echo_req *req;
int rc = 0;
- struct kvec iov[2];
+ struct kvec iov[1];
struct smb_rqst rqst = { .rq_iov = iov,
- .rq_nvec = 2 };
+ .rq_nvec = 1 };
unsigned int total_len;
- __be32 rfc1002_marker;
cifs_dbg(FYI, "In echo request\n");
req->sync_hdr.CreditRequest = cpu_to_le16(1);
- iov[0].iov_len = 4;
- rfc1002_marker = cpu_to_be32(total_len);
- iov[0].iov_base = &rfc1002_marker;
- iov[1].iov_len = total_len;
- iov[1].iov_base = (char *)req;
+ iov[0].iov_len = total_len;
+ iov[0].iov_base = (char *)req;
rc = cifs_call_async(server, &rqst, NULL, smb2_echo_callback, NULL,
server, CIFS_ECHO_OP);
SMB2_flush(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
u64 volatile_fid)
{
+ struct smb_rqst rqst;
struct smb2_flush_req *req;
struct cifs_ses *ses = tcon->ses;
struct kvec iov[1];
iov[0].iov_base = (char *)req;
iov[0].iov_len = total_len;
- rc = smb2_send_recv(xid, ses, iov, 1, &resp_buftype, flags, &rsp_iov);
+ memset(&rqst, 0, sizeof(struct smb_rqst));
+ rqst.rq_iov = iov;
+ rqst.rq_nvec = 1;
+
+ rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov);
cifs_small_buf_release(req);
if (rc != 0) {
struct smb2_sync_hdr *shdr;
struct cifs_io_parms io_parms;
struct smb_rqst rqst = { .rq_iov = rdata->iov,
- .rq_nvec = 2 };
+ .rq_nvec = 1 };
struct TCP_Server_Info *server;
unsigned int total_len;
- __be32 req_len;
cifs_dbg(FYI, "%s: offset=%llu bytes=%u\n",
__func__, rdata->offset, rdata->bytes);
if (smb3_encryption_required(io_parms.tcon))
flags |= CIFS_TRANSFORM_REQ;
- req_len = cpu_to_be32(total_len);
-
- rdata->iov[0].iov_base = &req_len;
- rdata->iov[0].iov_len = sizeof(__be32);
- rdata->iov[1].iov_base = buf;
- rdata->iov[1].iov_len = total_len;
+ rdata->iov[0].iov_base = buf;
+ rdata->iov[0].iov_len = total_len;
shdr = (struct smb2_sync_hdr *)buf;
SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms,
unsigned int *nbytes, char **buf, int *buf_type)
{
+ struct smb_rqst rqst;
int resp_buftype, rc = -EACCES;
struct smb2_read_plain_req *req = NULL;
struct smb2_read_rsp *rsp = NULL;
iov[0].iov_base = (char *)req;
iov[0].iov_len = total_len;
- rc = smb2_send_recv(xid, ses, iov, 1, &resp_buftype, flags, &rsp_iov);
+ memset(&rqst, 0, sizeof(struct smb_rqst));
+ rqst.rq_iov = iov;
+ rqst.rq_nvec = 1;
+
+ rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov);
cifs_small_buf_release(req);
rsp = (struct smb2_read_rsp *)rsp_iov.iov_base;
struct smb2_sync_hdr *shdr;
struct cifs_tcon *tcon = tlink_tcon(wdata->cfile->tlink);
struct TCP_Server_Info *server = tcon->ses->server;
- struct kvec iov[2];
+ struct kvec iov[1];
struct smb_rqst rqst = { };
unsigned int total_len;
- __be32 rfc1002_marker;
rc = smb2_plain_req_init(SMB2_WRITE, tcon, (void **) &req, &total_len);
if (rc) {
v1->length = cpu_to_le32(wdata->mr->mr->length);
}
#endif
- /* 4 for rfc1002 length field and 1 for Buffer */
- iov[0].iov_len = 4;
- rfc1002_marker = cpu_to_be32(total_len - 1 + wdata->bytes);
- iov[0].iov_base = &rfc1002_marker;
- iov[1].iov_len = total_len - 1;
- iov[1].iov_base = (char *)req;
+ iov[0].iov_len = total_len - 1;
+ iov[0].iov_base = (char *)req;
rqst.rq_iov = iov;
- rqst.rq_nvec = 2;
+ rqst.rq_nvec = 1;
rqst.rq_pages = wdata->pages;
rqst.rq_offset = wdata->page_offset;
rqst.rq_npages = wdata->nr_pages;
rqst.rq_tailsz = wdata->tailsz;
#ifdef CONFIG_CIFS_SMB_DIRECT
if (wdata->mr) {
- iov[1].iov_len += sizeof(struct smbd_buffer_descriptor_v1);
+ iov[0].iov_len += sizeof(struct smbd_buffer_descriptor_v1);
rqst.rq_npages = 0;
}
#endif
SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms,
unsigned int *nbytes, struct kvec *iov, int n_vec)
{
+ struct smb_rqst rqst;
int rc = 0;
struct smb2_write_req *req = NULL;
struct smb2_write_rsp *rsp = NULL;
/* 1 for Buffer */
iov[0].iov_len = total_len - 1;
- rc = smb2_send_recv(xid, io_parms->tcon->ses, iov, n_vec + 1,
+ memset(&rqst, 0, sizeof(struct smb_rqst));
+ rqst.rq_iov = iov;
+ rqst.rq_nvec = n_vec + 1;
+
+ rc = cifs_send_recv(xid, io_parms->tcon->ses, &rqst,
&resp_buftype, flags, &rsp_iov);
cifs_small_buf_release(req);
rsp = (struct smb2_write_rsp *)rsp_iov.iov_base;
u64 persistent_fid, u64 volatile_fid, int index,
struct cifs_search_info *srch_inf)
{
+ struct smb_rqst rqst;
struct smb2_query_directory_req *req;
struct smb2_query_directory_rsp *rsp = NULL;
struct kvec iov[2];
iov[1].iov_base = (char *)(req->Buffer);
iov[1].iov_len = len;
- rc = smb2_send_recv(xid, ses, iov, 2, &resp_buftype, flags, &rsp_iov);
+ memset(&rqst, 0, sizeof(struct smb_rqst));
+ rqst.rq_iov = iov;
+ rqst.rq_nvec = 2;
+
+ rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov);
cifs_small_buf_release(req);
rsp = (struct smb2_query_directory_rsp *)rsp_iov.iov_base;
u8 info_type, u32 additional_info, unsigned int num,
void **data, unsigned int *size)
{
+ struct smb_rqst rqst;
struct smb2_set_info_req *req;
struct smb2_set_info_rsp *rsp = NULL;
struct kvec *iov;
iov[i].iov_len = size[i];
}
- rc = smb2_send_recv(xid, ses, iov, num, &resp_buftype, flags,
+ memset(&rqst, 0, sizeof(struct smb_rqst));
+ rqst.rq_iov = iov;
+ rqst.rq_nvec = num;
+
+ rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags,
&rsp_iov);
cifs_small_buf_release(req);
rsp = (struct smb2_set_info_rsp *)rsp_iov.iov_base;
const u64 persistent_fid, const u64 volatile_fid,
__u8 oplock_level)
{
+ struct smb_rqst rqst;
int rc;
struct smb2_oplock_break *req = NULL;
struct cifs_ses *ses = tcon->ses;
iov[0].iov_base = (char *)req;
iov[0].iov_len = total_len;
- rc = smb2_send_recv(xid, ses, iov, 1, &resp_buf_type, flags, &rsp_iov);
+ memset(&rqst, 0, sizeof(struct smb_rqst));
+ rqst.rq_iov = iov;
+ rqst.rq_nvec = 1;
+
+ rc = cifs_send_recv(xid, ses, &rqst, &resp_buf_type, flags, &rsp_iov);
cifs_small_buf_release(req);
if (rc) {
SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
u64 persistent_fid, u64 volatile_fid, struct kstatfs *fsdata)
{
+ struct smb_rqst rqst;
struct smb2_query_info_rsp *rsp = NULL;
struct kvec iov;
struct kvec rsp_iov;
if (smb3_encryption_required(tcon))
flags |= CIFS_TRANSFORM_REQ;
- rc = smb2_send_recv(xid, ses, &iov, 1, &resp_buftype, flags, &rsp_iov);
+ memset(&rqst, 0, sizeof(struct smb_rqst));
+ rqst.rq_iov = &iov;
+ rqst.rq_nvec = 1;
+
+ rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov);
cifs_small_buf_release(iov.iov_base);
if (rc) {
cifs_stats_fail_inc(tcon, SMB2_QUERY_INFO_HE);
SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon,
u64 persistent_fid, u64 volatile_fid, int level)
{
+ struct smb_rqst rqst;
struct smb2_query_info_rsp *rsp = NULL;
struct kvec iov;
struct kvec rsp_iov;
if (smb3_encryption_required(tcon))
flags |= CIFS_TRANSFORM_REQ;
- rc = smb2_send_recv(xid, ses, &iov, 1, &resp_buftype, flags, &rsp_iov);
+ memset(&rqst, 0, sizeof(struct smb_rqst));
+ rqst.rq_iov = &iov;
+ rqst.rq_nvec = 1;
+
+ rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov);
cifs_small_buf_release(iov.iov_base);
if (rc) {
cifs_stats_fail_inc(tcon, SMB2_QUERY_INFO_HE);
const __u64 persist_fid, const __u64 volatile_fid, const __u32 pid,
const __u32 num_lock, struct smb2_lock_element *buf)
{
+ struct smb_rqst rqst;
int rc = 0;
struct smb2_lock_req *req = NULL;
struct kvec iov[2];
iov[1].iov_len = count;
cifs_stats_inc(&tcon->stats.cifs_stats.num_locks);
- rc = smb2_send_recv(xid, tcon->ses, iov, 2, &resp_buf_type, flags,
+
+ memset(&rqst, 0, sizeof(struct smb_rqst));
+ rqst.rq_iov = iov;
+ rqst.rq_nvec = 2;
+
+ rc = cifs_send_recv(xid, tcon->ses, &rqst, &resp_buf_type, flags,
&rsp_iov);
cifs_small_buf_release(req);
if (rc) {
SMB2_lease_break(const unsigned int xid, struct cifs_tcon *tcon,
__u8 *lease_key, const __le32 lease_state)
{
+ struct smb_rqst rqst;
int rc;
struct smb2_lease_ack *req = NULL;
struct cifs_ses *ses = tcon->ses;
iov[0].iov_base = (char *)req;
iov[0].iov_len = total_len;
- rc = smb2_send_recv(xid, ses, iov, 1, &resp_buf_type, flags, &rsp_iov);
+ memset(&rqst, 0, sizeof(struct smb_rqst));
+ rqst.rq_iov = iov;
+ rqst.rq_nvec = 1;
+
+ rc = cifs_send_recv(xid, ses, &rqst, &resp_buf_type, flags, &rsp_iov);
cifs_small_buf_release(req);
if (rc) {
__le16 Dialect; /* Dialect in use for the connection */
} __packed;
-#define RSS_CAPABLE 0x00000001
-#define RDMA_CAPABLE 0x00000002
+#define RSS_CAPABLE cpu_to_le32(0x00000001)
+#define RDMA_CAPABLE cpu_to_le32(0x00000002)
+
+#define INTERNETWORK cpu_to_le16(0x0002)
+#define INTERNETWORKV6 cpu_to_le16(0x0017)
struct network_interface_info_ioctl_rsp {
__le32 Next; /* next interface. zero if this is last one */
__le32 Capability; /* RSS or RDMA Capable */
__le32 Reserved;
__le64 LinkSpeed;
- char SockAddr_Storage[128];
+ __le16 Family;
+ __u8 Buffer[126];
+} __packed;
+
+struct iface_info_ipv4 {
+ __be16 Port;
+ __be32 IPv4Address;
+ __be64 Reserved;
+} __packed;
+
+struct iface_info_ipv6 {
+ __be16 Port;
+ __be32 FlowInfo;
+ __u8 IPv6Address[16];
+ __be32 ScopeId;
} __packed;
#define NO_FILE_ID 0xFFFFFFFFFFFFFFFFULL /* general ioctls to srv not to file */
struct cifs_sb_info *cifs_sb, bool set_alloc);
extern int smb2_set_file_info(struct inode *inode, const char *full_path,
FILE_BASIC_INFO *buf, const unsigned int xid);
+extern int smb311_posix_mkdir(const unsigned int xid, struct inode *inode,
+ umode_t mode, struct cifs_tcon *tcon,
+ const char *full_path,
+ struct cifs_sb_info *cifs_sb);
extern int smb2_mkdir(const unsigned int xid, struct cifs_tcon *tcon,
const char *name, struct cifs_sb_info *cifs_sb);
extern void smb2_mkdir_setinfo(struct inode *inode, const char *full_path,
extern int smb2_push_mandatory_locks(struct cifsFileInfo *cfile);
extern void smb2_reconnect_server(struct work_struct *work);
extern int smb3_crypto_aead_allocate(struct TCP_Server_Info *server);
+extern unsigned long
+smb2_rqst_len(struct smb_rqst *rqst, bool skip_rfc1002_marker);
/*
* SMB2 Worker functions - most of protocol specific implementation details
unsigned char smb2_signature[SMB2_HMACSHA256_SIZE];
unsigned char *sigptr = smb2_signature;
struct kvec *iov = rqst->rq_iov;
- int iov_hdr_index = rqst->rq_nvec > 1 ? 1 : 0;
- struct smb2_sync_hdr *shdr =
- (struct smb2_sync_hdr *)iov[iov_hdr_index].iov_base;
+ struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)iov[0].iov_base;
struct cifs_ses *ses;
ses = smb2_find_smb_ses(server, shdr->SessionId);
return rc;
}
- rc = __cifs_calc_signature(rqst, iov_hdr_index, server, sigptr,
+ rc = __cifs_calc_signature(rqst, server, sigptr,
&server->secmech.sdeschmacsha256->shash);
if (!rc)
unsigned char smb3_signature[SMB2_CMACAES_SIZE];
unsigned char *sigptr = smb3_signature;
struct kvec *iov = rqst->rq_iov;
- int iov_hdr_index = rqst->rq_nvec > 1 ? 1 : 0;
- struct smb2_sync_hdr *shdr =
- (struct smb2_sync_hdr *)iov[iov_hdr_index].iov_base;
+ struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)iov[0].iov_base;
struct cifs_ses *ses;
ses = smb2_find_smb_ses(server, shdr->SessionId);
return rc;
}
- rc = __cifs_calc_signature(rqst, iov_hdr_index, server, sigptr,
+ rc = __cifs_calc_signature(rqst, server, sigptr,
&server->secmech.sdesccmacaes->shash);
if (!rc)
{
int rc = 0;
struct smb2_sync_hdr *shdr =
- (struct smb2_sync_hdr *)rqst->rq_iov[1].iov_base;
+ (struct smb2_sync_hdr *)rqst->rq_iov[0].iov_base;
if (!(shdr->Flags & SMB2_FLAGS_SIGNED) ||
server->tcpStatus == CifsNeedNegotiate)
{
int rc;
struct smb2_sync_hdr *shdr =
- (struct smb2_sync_hdr *)rqst->rq_iov[1].iov_base;
+ (struct smb2_sync_hdr *)rqst->rq_iov[0].iov_base;
struct mid_q_entry *mid;
smb2_seq_num_into_buf(ses->server, shdr);
{
int rc;
struct smb2_sync_hdr *shdr =
- (struct smb2_sync_hdr *)rqst->rq_iov[1].iov_base;
+ (struct smb2_sync_hdr *)rqst->rq_iov[0].iov_base;
struct mid_q_entry *mid;
smb2_seq_num_into_buf(server, shdr);
#include "smbdirect.h"
#include "cifs_debug.h"
#include "cifsproto.h"
+#include "smb2proto.h"
static struct smbd_response *get_empty_queue_buffer(
struct smbd_connection *info);
struct kvec vec;
int nvecs;
int size;
- unsigned int buflen = 0, remaining_data_length;
+ unsigned int buflen, remaining_data_length;
int start, i, j;
int max_iov_size =
info->max_send_size - sizeof(struct smbd_data_transfer);
log_write(ERR, "expected the pdu length in 1st iov, but got %zu\n", rqst->rq_iov[0].iov_len);
return -EINVAL;
}
- iov = &rqst->rq_iov[1];
-
- /* total up iov array first */
- for (i = 0; i < rqst->rq_nvec-1; i++) {
- buflen += iov[i].iov_len;
- }
/*
* Add in the page array if there is one. The caller needs to set
* rq_tailsz to PAGE_SIZE when the buffer has multiple pages and
* ends at page boundary
*/
- if (rqst->rq_npages) {
- if (rqst->rq_npages == 1)
- buflen += rqst->rq_tailsz;
- else
- buflen += rqst->rq_pagesz * (rqst->rq_npages - 1) -
- rqst->rq_offset + rqst->rq_tailsz;
- }
+ buflen = smb2_rqst_len(rqst, true);
if (buflen + sizeof(struct smbd_data_transfer) >
info->max_fragmented_send_size) {
goto done;
}
+ iov = &rqst->rq_iov[1];
+
cifs_dbg(FYI, "Sending smb (RDMA): smb_len=%u\n", buflen);
for (i = 0; i < rqst->rq_nvec-1; i++)
dump_smb(iov[i].iov_base, iov[i].iov_len);
TP_ARGS(xid, tid, sesid, create_options, desired_access, rc))
DEFINE_SMB3_OPEN_ERR_EVENT(open_err);
-
+DEFINE_SMB3_OPEN_ERR_EVENT(posix_mkdir_err);
DECLARE_EVENT_CLASS(smb3_open_done_class,
TP_PROTO(unsigned int xid,
TP_ARGS(xid, fid, tid, sesid, create_options, desired_access))
DEFINE_SMB3_OPEN_DONE_EVENT(open_done);
+DEFINE_SMB3_OPEN_DONE_EVENT(posix_mkdir_done);
#endif /* _CIFS_TRACE_H */
return 0;
}
-static unsigned long
-rqst_len(struct smb_rqst *rqst)
+unsigned long
+smb2_rqst_len(struct smb_rqst *rqst, bool skip_rfc1002_marker)
{
unsigned int i;
- struct kvec *iov = rqst->rq_iov;
+ struct kvec *iov;
+ int nvec;
unsigned long buflen = 0;
+ if (skip_rfc1002_marker && rqst->rq_iov[0].iov_len == 4) {
+ iov = &rqst->rq_iov[1];
+ nvec = rqst->rq_nvec - 1;
+ } else {
+ iov = rqst->rq_iov;
+ nvec = rqst->rq_nvec;
+ }
+
/* total up iov array first */
- for (i = 0; i < rqst->rq_nvec; i++)
+ for (i = 0; i < nvec; i++)
buflen += iov[i].iov_len;
/*
}
static int
-__smb_send_rqst(struct TCP_Server_Info *server, struct smb_rqst *rqst)
+__smb_send_rqst(struct TCP_Server_Info *server, int num_rqst,
+ struct smb_rqst *rqst)
{
- int rc;
- struct kvec *iov = rqst->rq_iov;
- int n_vec = rqst->rq_nvec;
- unsigned int smb_buf_length = get_rfc1002_length(iov[0].iov_base);
- unsigned long send_length;
- unsigned int i;
+ int rc = 0;
+ struct kvec *iov;
+ int n_vec;
+ unsigned int send_length = 0;
+ unsigned int i, j;
size_t total_len = 0, sent, size;
struct socket *ssocket = server->ssocket;
struct msghdr smb_msg;
int val = 1;
+ __be32 rfc1002_marker;
+
if (cifs_rdma_enabled(server) && server->smbd_conn) {
rc = smbd_send(server->smbd_conn, rqst);
goto smbd_done;
if (ssocket == NULL)
return -ENOTSOCK;
- /* sanity check send length */
- send_length = rqst_len(rqst);
- if (send_length != smb_buf_length + 4) {
- WARN(1, "Send length mismatch(send_length=%lu smb_buf_length=%u)\n",
- send_length, smb_buf_length);
- return -EIO;
- }
-
- if (n_vec < 2)
- return -EIO;
-
- cifs_dbg(FYI, "Sending smb: smb_len=%u\n", smb_buf_length);
- dump_smb(iov[0].iov_base, iov[0].iov_len);
- dump_smb(iov[1].iov_base, iov[1].iov_len);
-
/* cork the socket */
kernel_setsockopt(ssocket, SOL_TCP, TCP_CORK,
(char *)&val, sizeof(val));
- size = 0;
- for (i = 0; i < n_vec; i++)
- size += iov[i].iov_len;
+ for (j = 0; j < num_rqst; j++)
+ send_length += smb2_rqst_len(&rqst[j], true);
+ rfc1002_marker = cpu_to_be32(send_length);
- iov_iter_kvec(&smb_msg.msg_iter, WRITE | ITER_KVEC, iov, n_vec, size);
+ /* Generate a rfc1002 marker for SMB2+ */
+ if (server->vals->header_preamble_size == 0) {
+ struct kvec hiov = {
+ .iov_base = &rfc1002_marker,
+ .iov_len = 4
+ };
+ iov_iter_kvec(&smb_msg.msg_iter, WRITE | ITER_KVEC, &hiov,
+ 1, 4);
+ rc = smb_send_kvec(server, &smb_msg, &sent);
+ if (rc < 0)
+ goto uncork;
- rc = smb_send_kvec(server, &smb_msg, &sent);
- if (rc < 0)
- goto uncork;
+ total_len += sent;
+ send_length += 4;
+ }
- total_len += sent;
+ cifs_dbg(FYI, "Sending smb: smb_len=%u\n", send_length);
- /* now walk the page array and send each page in it */
- for (i = 0; i < rqst->rq_npages; i++) {
- struct bio_vec bvec;
+ for (j = 0; j < num_rqst; j++) {
+ iov = rqst[j].rq_iov;
+ n_vec = rqst[j].rq_nvec;
- bvec.bv_page = rqst->rq_pages[i];
- rqst_page_get_length(rqst, i, &bvec.bv_len, &bvec.bv_offset);
+ size = 0;
+ for (i = 0; i < n_vec; i++) {
+ dump_smb(iov[i].iov_base, iov[i].iov_len);
+ size += iov[i].iov_len;
+ }
+
+ iov_iter_kvec(&smb_msg.msg_iter, WRITE | ITER_KVEC,
+ iov, n_vec, size);
- iov_iter_bvec(&smb_msg.msg_iter, WRITE | ITER_BVEC,
- &bvec, 1, bvec.bv_len);
rc = smb_send_kvec(server, &smb_msg, &sent);
if (rc < 0)
- break;
+ goto uncork;
total_len += sent;
+
+ /* now walk the page array and send each page in it */
+ for (i = 0; i < rqst[j].rq_npages; i++) {
+ struct bio_vec bvec;
+
+ bvec.bv_page = rqst[j].rq_pages[i];
+ rqst_page_get_length(&rqst[j], i, &bvec.bv_len,
+ &bvec.bv_offset);
+
+ iov_iter_bvec(&smb_msg.msg_iter, WRITE | ITER_BVEC,
+ &bvec, 1, bvec.bv_len);
+ rc = smb_send_kvec(server, &smb_msg, &sent);
+ if (rc < 0)
+ break;
+
+ total_len += sent;
+ }
}
uncork:
kernel_setsockopt(ssocket, SOL_TCP, TCP_CORK,
(char *)&val, sizeof(val));
- if ((total_len > 0) && (total_len != smb_buf_length + 4)) {
+ if ((total_len > 0) && (total_len != send_length)) {
cifs_dbg(FYI, "partial send (wanted=%u sent=%zu): terminating session\n",
- smb_buf_length + 4, total_len);
+ send_length, total_len);
/*
* If we have only sent part of an SMB then the next SMB could
* be taken as the remainder of this one. We need to kill the
int rc;
if (!(flags & CIFS_TRANSFORM_REQ))
- return __smb_send_rqst(server, rqst);
+ return __smb_send_rqst(server, 1, rqst);
if (!server->ops->init_transform_rq ||
!server->ops->free_transform_rq) {
if (rc)
return rc;
- rc = __smb_send_rqst(server, &cur_rqst);
+ rc = __smb_send_rqst(server, 1, &cur_rqst);
server->ops->free_transform_rq(&cur_rqst);
return rc;
}
iov[1].iov_base = (char *)smb_buffer + 4;
iov[1].iov_len = smb_buf_length;
- return __smb_send_rqst(server, &rqst);
+ return __smb_send_rqst(server, 1, &rqst);
}
static int
* to the same server. We may make this configurable later or
* use ses->maxReq.
*/
-
rc = wait_for_free_request(ses->server, timeout, optype);
if (rc)
return rc;
#ifdef CONFIG_CIFS_SMB311
if ((ses->status == CifsNew) || (optype & CIFS_NEG_OP))
- smb311_update_preauth_hash(ses, rqst->rq_iov+1,
- rqst->rq_nvec-1);
+ smb311_update_preauth_hash(ses, rqst->rq_iov,
+ rqst->rq_nvec);
#endif
if (timeout == CIFS_ASYNC_OP)
#ifdef CONFIG_CIFS_SMB311
if ((ses->status == CifsNew) || (optype & CIFS_NEG_OP)) {
struct kvec iov = {
- .iov_base = buf,
- .iov_len = midQ->resp_buf_size
+ .iov_base = resp_iov->iov_base,
+ .iov_len = resp_iov->iov_len
};
smb311_update_preauth_hash(ses, &iov, 1);
}
return rc;
}
-/* Like SendReceive2 but iov[0] does not contain an rfc1002 header */
-int
-smb2_send_recv(const unsigned int xid, struct cifs_ses *ses,
- struct kvec *iov, int n_vec, int *resp_buf_type /* ret */,
- const int flags, struct kvec *resp_iov)
-{
- struct smb_rqst rqst;
- struct kvec s_iov[CIFS_MAX_IOV_SIZE], *new_iov;
- int rc;
- int i;
- __u32 count;
- __be32 rfc1002_marker;
-
- if (n_vec + 1 > CIFS_MAX_IOV_SIZE) {
- new_iov = kmalloc_array(n_vec + 1, sizeof(struct kvec),
- GFP_KERNEL);
- if (!new_iov)
- return -ENOMEM;
- } else
- new_iov = s_iov;
-
- /* 1st iov is an RFC1002 Session Message length */
- memcpy(new_iov + 1, iov, (sizeof(struct kvec) * n_vec));
-
- count = 0;
- for (i = 1; i < n_vec + 1; i++)
- count += new_iov[i].iov_len;
-
- rfc1002_marker = cpu_to_be32(count);
-
- new_iov[0].iov_base = &rfc1002_marker;
- new_iov[0].iov_len = 4;
-
- memset(&rqst, 0, sizeof(struct smb_rqst));
- rqst.rq_iov = new_iov;
- rqst.rq_nvec = n_vec + 1;
-
- rc = cifs_send_recv(xid, ses, &rqst, resp_buf_type, flags, resp_iov);
- if (n_vec + 1 > CIFS_MAX_IOV_SIZE)
- kfree(new_iov);
- return rc;
-}
-
int
SendReceive(const unsigned int xid, struct cifs_ses *ses,
struct smb_hdr *in_buf, struct smb_hdr *out_buf,
return 0;
}
-static struct wait_queue_head *
-eventfd_get_poll_head(struct file *file, __poll_t events)
-{
- struct eventfd_ctx *ctx = file->private_data;
-
- return &ctx->wqh;
-}
-
-static __poll_t eventfd_poll_mask(struct file *file, __poll_t eventmask)
+static __poll_t eventfd_poll(struct file *file, poll_table *wait)
{
struct eventfd_ctx *ctx = file->private_data;
__poll_t events = 0;
u64 count;
+ poll_wait(file, &ctx->wqh, wait);
+
/*
* All writes to ctx->count occur within ctx->wqh.lock. This read
* can be done outside ctx->wqh.lock because we know that poll_wait
count = READ_ONCE(ctx->count);
if (count > 0)
- events |= (EPOLLIN & eventmask);
+ events |= EPOLLIN;
if (count == ULLONG_MAX)
events |= EPOLLERR;
if (ULLONG_MAX - 1 > count)
- events |= (EPOLLOUT & eventmask);
+ events |= EPOLLOUT;
return events;
}
.show_fdinfo = eventfd_show_fdinfo,
#endif
.release = eventfd_release,
- .get_poll_head = eventfd_get_poll_head,
- .poll_mask = eventfd_poll_mask,
+ .poll = eventfd_poll,
.read = eventfd_read,
.write = eventfd_write,
.llseek = noop_llseek,
return 0;
}
-static struct wait_queue_head *ep_eventpoll_get_poll_head(struct file *file,
- __poll_t eventmask)
-{
- struct eventpoll *ep = file->private_data;
- return &ep->poll_wait;
-}
-
-static __poll_t ep_eventpoll_poll_mask(struct file *file, __poll_t eventmask)
+static __poll_t ep_eventpoll_poll(struct file *file, poll_table *wait)
{
struct eventpoll *ep = file->private_data;
int depth = 0;
+ /* Insert inside our poll wait queue */
+ poll_wait(file, &ep->poll_wait, wait);
+
/*
* Proceed to find out if wanted events are really available inside
* the ready list.
.show_fdinfo = ep_show_fdinfo,
#endif
.release = ep_eventpoll_release,
- .get_poll_head = ep_eventpoll_get_poll_head,
- .poll_mask = ep_eventpoll_poll_mask,
+ .poll = ep_eventpoll_poll,
.llseek = noop_llseek,
};
unsigned long);
extern unsigned long ext2_count_free_blocks (struct super_block *);
extern unsigned long ext2_count_dirs (struct super_block *);
-extern void ext2_check_blocks_bitmap (struct super_block *);
extern struct ext2_group_desc * ext2_get_group_desc(struct super_block * sb,
unsigned int block_group,
struct buffer_head ** bh);
extern struct inode * ext2_new_inode (struct inode *, umode_t, const struct qstr *);
extern void ext2_free_inode (struct inode *);
extern unsigned long ext2_count_free_inodes (struct super_block *);
-extern void ext2_check_inodes_bitmap (struct super_block *);
extern unsigned long ext2_count_free (struct buffer_head *, unsigned);
/* inode.c */
set_opt (opts->s_mount_opt, NO_UID32);
break;
case Opt_nocheck:
+ ext2_msg(sb, KERN_WARNING,
+ "Option nocheck/check=none is deprecated and"
+ " will be removed in June 2020.");
clear_opt (opts->s_mount_opt, CHECK);
break;
case Opt_debug:
new_opts.s_resgid = sbi->s_resgid;
spin_unlock(&sbi->s_lock);
- /*
- * Allow the "check" option to be passed as a remount option.
- */
if (!parse_options(data, sb, &new_opts))
return -EINVAL;
if (size > PSIZE) {
/*
* To keep the rest of the code simple. Allocate a
- * contiguous buffer to work with
+ * contiguous buffer to work with. Make the buffer large
+ * enough to make use of the whole extent.
*/
- ea_buf->xattr = kmalloc(size, GFP_KERNEL);
+ ea_buf->max_size = (size + sb->s_blocksize - 1) &
+ ~(sb->s_blocksize - 1);
+
+ ea_buf->xattr = kmalloc(ea_buf->max_size, GFP_KERNEL);
if (ea_buf->xattr == NULL)
return -ENOMEM;
ea_buf->flag = EA_MALLOC;
- ea_buf->max_size = (size + sb->s_blocksize - 1) &
- ~(sb->s_blocksize - 1);
if (ea_size == 0)
return 0;
rcu_read_lock();
list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
res = nfs_delegation_find_inode_server(server, fhandle);
- if (res != ERR_PTR(-ENOENT))
+ if (res != ERR_PTR(-ENOENT)) {
+ rcu_read_unlock();
return res;
+ }
}
rcu_read_unlock();
return ERR_PTR(-ENOENT);
hdr->ds_clp, hdr->lseg,
hdr->pgio_mirror_idx);
+ clear_bit(NFS_IOHDR_RESEND_PNFS, &hdr->flags);
+ clear_bit(NFS_IOHDR_RESEND_MDS, &hdr->flags);
switch (err) {
case -NFS4ERR_RESET_TO_PNFS:
if (ff_layout_choose_best_ds_for_read(hdr->lseg,
hdr->pgio_mirror_idx + 1,
&hdr->pgio_mirror_idx))
goto out_eagain;
- ff_layout_read_record_layoutstats_done(task, hdr);
- pnfs_read_resend_pnfs(hdr);
+ set_bit(NFS_IOHDR_RESEND_PNFS, &hdr->flags);
return task->tk_status;
case -NFS4ERR_RESET_TO_MDS:
- ff_layout_reset_read(hdr);
+ set_bit(NFS_IOHDR_RESEND_MDS, &hdr->flags);
return task->tk_status;
case -EAGAIN:
goto out_eagain;
struct nfs_pgio_header *hdr = data;
ff_layout_read_record_layoutstats_done(&hdr->task, hdr);
+ if (test_bit(NFS_IOHDR_RESEND_PNFS, &hdr->flags))
+ pnfs_read_resend_pnfs(hdr);
+ else if (test_bit(NFS_IOHDR_RESEND_MDS, &hdr->flags))
+ ff_layout_reset_read(hdr);
pnfs_generic_rw_release(data);
}
hdr->ds_clp, hdr->lseg,
hdr->pgio_mirror_idx);
+ clear_bit(NFS_IOHDR_RESEND_PNFS, &hdr->flags);
+ clear_bit(NFS_IOHDR_RESEND_MDS, &hdr->flags);
switch (err) {
case -NFS4ERR_RESET_TO_PNFS:
- ff_layout_reset_write(hdr, true);
+ set_bit(NFS_IOHDR_RESEND_PNFS, &hdr->flags);
return task->tk_status;
case -NFS4ERR_RESET_TO_MDS:
- ff_layout_reset_write(hdr, false);
+ set_bit(NFS_IOHDR_RESEND_MDS, &hdr->flags);
return task->tk_status;
case -EAGAIN:
return -EAGAIN;
struct nfs_pgio_header *hdr = data;
ff_layout_write_record_layoutstats_done(&hdr->task, hdr);
+ if (test_bit(NFS_IOHDR_RESEND_PNFS, &hdr->flags))
+ ff_layout_reset_write(hdr, true);
+ else if (test_bit(NFS_IOHDR_RESEND_MDS, &hdr->flags))
+ ff_layout_reset_write(hdr, false);
pnfs_generic_rw_release(data);
}
struct nfs4_closedata *calldata = data;
struct nfs4_state *state = calldata->state;
struct inode *inode = calldata->inode;
+ struct pnfs_layout_hdr *lo;
bool is_rdonly, is_wronly, is_rdwr;
int call_close = 0;
goto out_wait;
}
+ lo = calldata->arg.lr_args ? calldata->arg.lr_args->layout : NULL;
+ if (lo && !pnfs_layout_is_valid(lo)) {
+ calldata->arg.lr_args = NULL;
+ calldata->res.lr_res = NULL;
+ }
+
if (calldata->arg.fmode == 0)
task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_CLOSE];
static void nfs4_delegreturn_prepare(struct rpc_task *task, void *data)
{
struct nfs4_delegreturndata *d_data;
+ struct pnfs_layout_hdr *lo;
d_data = (struct nfs4_delegreturndata *)data;
if (!d_data->lr.roc && nfs4_wait_on_layoutreturn(d_data->inode, task))
return;
+ lo = d_data->args.lr_args ? d_data->args.lr_args->layout : NULL;
+ if (lo && !pnfs_layout_is_valid(lo)) {
+ d_data->args.lr_args = NULL;
+ d_data->res.lr_res = NULL;
+ }
+
nfs4_setup_sequence(d_data->res.server->nfs_client,
&d_data->args.seq_args,
&d_data->res.seq_res,
dprintk("--> %s tk_status => %d\n", __func__, -task->tk_status);
+ nfs4_sequence_free_slot(&lgp->res.seq_res);
+
switch (nfs4err) {
case 0:
goto out;
goto out;
}
- nfs4_sequence_free_slot(&lgp->res.seq_res);
err = nfs4_handle_exception(server, nfs4err, exception);
if (!status) {
if (exception->retry)
if (IS_ERR(task))
return ERR_CAST(task);
status = rpc_wait_for_completion_task(task);
- if (status == 0) {
+ if (status != 0)
+ goto out;
+
+ /* if layoutp->len is 0, nfs4_layoutget_prepare called rpc_exit */
+ if (task->tk_status < 0 || lgp->res.layoutp->len == 0) {
status = nfs4_layoutget_handle_exception(task, lgp, &exception);
*timeout = exception.timeout;
- }
-
+ } else
+ lseg = pnfs_layout_process(lgp);
+out:
trace_nfs4_layoutget(lgp->args.ctx,
&lgp->args.range,
&lgp->res.range,
&lgp->res.stateid,
status);
- /* if layoutp->len is 0, nfs4_layoutget_prepare called rpc_exit */
- if (status == 0 && lgp->res.layoutp->len)
- lseg = pnfs_layout_process(lgp);
rpc_put_task(task);
dprintk("<-- %s status=%d\n", __func__, status);
if (status)
&lrp->args.seq_args,
&lrp->res.seq_res,
task);
+ if (!pnfs_layout_is_valid(lrp->args.layout))
+ rpc_exit(task, 0);
}
static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata)
{
}
+static inline bool pnfs_layout_is_valid(const struct pnfs_layout_hdr *lo)
+{
+ return false;
+}
+
#endif /* CONFIG_NFS_V4_1 */
#if IS_ENABLED(CONFIG_NFS_V4_2)
}
}
-static struct wait_queue_head *
-pipe_get_poll_head(struct file *filp, __poll_t events)
-{
- struct pipe_inode_info *pipe = filp->private_data;
-
- return &pipe->wait;
-}
-
/* No kernel lock held - fine */
-static __poll_t pipe_poll_mask(struct file *filp, __poll_t events)
+static __poll_t
+pipe_poll(struct file *filp, poll_table *wait)
{
+ __poll_t mask;
struct pipe_inode_info *pipe = filp->private_data;
- int nrbufs = pipe->nrbufs;
- __poll_t mask = 0;
+ int nrbufs;
+
+ poll_wait(filp, &pipe->wait, wait);
/* Reading only -- no need for acquiring the semaphore. */
+ nrbufs = pipe->nrbufs;
+ mask = 0;
if (filp->f_mode & FMODE_READ) {
mask = (nrbufs > 0) ? EPOLLIN | EPOLLRDNORM : 0;
if (!pipe->writers && filp->f_version != pipe->w_counter)
.llseek = no_llseek,
.read_iter = pipe_read,
.write_iter = pipe_write,
- .get_poll_head = pipe_get_poll_head,
- .poll_mask = pipe_poll_mask,
+ .poll = pipe_poll,
.unlocked_ioctl = pipe_ioctl,
.release = pipe_release,
.fasync = pipe_fasync,
if (env_start != arg_end || env_start >= env_end)
env_start = env_end = arg_end;
+ /* .. and limit it to a maximum of one page of slop */
+ if (env_end >= arg_end + PAGE_SIZE)
+ env_end = arg_end + PAGE_SIZE - 1;
+
/* We're not going to care if "*ppos" has high bits set */
pos = arg_start + *ppos;
while (count) {
int got;
size_t size = min_t(size_t, PAGE_SIZE, count);
+ long offset;
- got = access_remote_vm(mm, pos, page, size, FOLL_ANON);
- if (got <= 0)
+ /*
+ * Are we already starting past the official end?
+ * We always include the last byte that is *supposed*
+ * to be NUL
+ */
+ offset = (pos >= arg_end) ? pos - arg_end + 1 : 0;
+
+ got = access_remote_vm(mm, pos - offset, page, size + offset, FOLL_ANON);
+ if (got <= offset)
break;
+ got -= offset;
/* Don't walk past a NUL character once you hit arg_end */
if (pos + got >= arg_end) {
n = arg_end - pos - 1;
/* Cut off at first NUL after 'n' */
- got = n + strnlen(page+n, got-n);
- if (!got)
+ got = n + strnlen(page+n, offset+got-n);
+ if (got < offset)
break;
+ got -= offset;
+
+ /* Include the NUL if it existed */
+ if (got < size)
+ got++;
}
- got -= copy_to_user(buf, page, got);
+ got -= copy_to_user(buf, page+offset, got);
if (unlikely(!got)) {
if (!len)
len = -EFAULT;
return seq_open(file, de->seq_ops);
}
+static int proc_seq_release(struct inode *inode, struct file *file)
+{
+ struct proc_dir_entry *de = PDE(inode);
+
+ if (de->state_size)
+ return seq_release_private(inode, file);
+ return seq_release(inode, file);
+}
+
static const struct file_operations proc_seq_fops = {
.open = proc_seq_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = seq_release,
+ .release = proc_seq_release,
};
struct proc_dir_entry *proc_create_seq_private(const char *name, umode_t mode,
static unsigned long
dqcache_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
{
- struct list_head *head;
struct dquot *dquot;
unsigned long freed = 0;
spin_lock(&dq_list_lock);
- head = free_dquots.prev;
- while (head != &free_dquots && sc->nr_to_scan) {
- dquot = list_entry(head, struct dquot, dq_free);
+ while (!list_empty(&free_dquots) && sc->nr_to_scan) {
+ dquot = list_first_entry(&free_dquots, struct dquot, dq_free);
remove_dquot_hash(dquot);
remove_free_dquot(dquot);
remove_inuse(dquot);
do_destroy_dquot(dquot);
sc->nr_to_scan--;
freed++;
- head = free_dquots.prev;
}
spin_unlock(&dq_list_lock);
return freed;
#include <linux/uaccess.h>
-__poll_t vfs_poll(struct file *file, struct poll_table_struct *pt)
-{
- if (file->f_op->poll) {
- return file->f_op->poll(file, pt);
- } else if (file_has_poll_mask(file)) {
- unsigned int events = poll_requested_events(pt);
- struct wait_queue_head *head;
-
- if (pt && pt->_qproc) {
- head = file->f_op->get_poll_head(file, events);
- if (!head)
- return DEFAULT_POLLMASK;
- if (IS_ERR(head))
- return EPOLLERR;
- pt->_qproc(file, head, pt);
- }
-
- return file->f_op->poll_mask(file, events);
- } else {
- return DEFAULT_POLLMASK;
- }
-}
-EXPORT_SYMBOL_GPL(vfs_poll);
/*
* Estimate expected accuracy in ns from a timeval.
kfree_rcu(ctx, rcu);
return 0;
}
-
-static struct wait_queue_head *timerfd_get_poll_head(struct file *file,
- __poll_t eventmask)
+
+static __poll_t timerfd_poll(struct file *file, poll_table *wait)
{
struct timerfd_ctx *ctx = file->private_data;
+ __poll_t events = 0;
+ unsigned long flags;
- return &ctx->wqh;
-}
+ poll_wait(file, &ctx->wqh, wait);
-static __poll_t timerfd_poll_mask(struct file *file, __poll_t eventmask)
-{
- struct timerfd_ctx *ctx = file->private_data;
+ spin_lock_irqsave(&ctx->wqh.lock, flags);
+ if (ctx->ticks)
+ events |= EPOLLIN;
+ spin_unlock_irqrestore(&ctx->wqh.lock, flags);
- return ctx->ticks ? EPOLLIN : 0;
+ return events;
}
static ssize_t timerfd_read(struct file *file, char __user *buf, size_t count,
static const struct file_operations timerfd_fops = {
.release = timerfd_release,
- .get_poll_head = timerfd_get_poll_head,
- .poll_mask = timerfd_poll_mask,
+ .poll = timerfd_poll,
.read = timerfd_read,
.llseek = noop_llseek,
.show_fdinfo = timerfd_show,
udf_write_aext(table, &epos, &eloc,
(etype << 30) | elen, 1);
} else
- udf_delete_aext(table, epos, eloc,
- (etype << 30) | elen);
+ udf_delete_aext(table, epos);
} else {
alloc_count = 0;
}
if (goal_elen)
udf_write_aext(table, &goal_epos, &goal_eloc, goal_elen, 1);
else
- udf_delete_aext(table, goal_epos, goal_eloc, goal_elen);
+ udf_delete_aext(table, goal_epos);
brelse(goal_epos.bh);
udf_add_free_space(sb, partition, -1);
fibh->ebh->b_data,
sizeof(struct fileIdentDesc) + fibh->soffset);
- fi_len = (sizeof(struct fileIdentDesc) +
- cfi->lengthFileIdent +
- le16_to_cpu(cfi->lengthOfImpUse) + 3) & ~3;
-
+ fi_len = udf_dir_entry_len(cfi);
*nf_pos += fi_len - (fibh->eoffset - fibh->soffset);
fibh->eoffset = fibh->soffset + fi_len;
} else {
sizeof(struct fileIdentDesc));
}
}
+ /* Got last entry outside of dir size - fs is corrupted! */
+ if (*nf_pos > dir->i_size)
+ return NULL;
return fi;
}
if (startnum > endnum) {
for (i = 0; i < (startnum - endnum); i++)
- udf_delete_aext(inode, *epos, laarr[i].extLocation,
- laarr[i].extLength);
+ udf_delete_aext(inode, *epos);
} else if (startnum < endnum) {
for (i = 0; i < (endnum - startnum); i++) {
udf_insert_aext(inode, *epos, laarr[i].extLocation,
return (nelen >> 30);
}
-int8_t udf_delete_aext(struct inode *inode, struct extent_position epos,
- struct kernel_lb_addr eloc, uint32_t elen)
+int8_t udf_delete_aext(struct inode *inode, struct extent_position epos)
{
struct extent_position oepos;
int adsize;
int8_t etype;
struct allocExtDesc *aed;
struct udf_inode_info *iinfo;
+ struct kernel_lb_addr eloc;
+ uint32_t elen;
if (epos.bh) {
get_bh(epos.bh);
loff_t f_pos;
loff_t size = udf_ext0_offset(dir) + dir->i_size;
int nfidlen;
- uint8_t lfi;
- uint16_t liu;
udf_pblk_t block;
struct kernel_lb_addr eloc;
uint32_t elen = 0;
namelen = 0;
}
- nfidlen = (sizeof(struct fileIdentDesc) + namelen + 3) & ~3;
+ nfidlen = ALIGN(sizeof(struct fileIdentDesc) + namelen, UDF_NAME_PAD);
f_pos = udf_ext0_offset(dir);
goto out_err;
}
- liu = le16_to_cpu(cfi->lengthOfImpUse);
- lfi = cfi->lengthFileIdent;
-
if ((cfi->fileCharacteristics & FID_FILE_CHAR_DELETED) != 0) {
- if (((sizeof(struct fileIdentDesc) +
- liu + lfi + 3) & ~3) == nfidlen) {
+ if (udf_dir_entry_len(cfi) == nfidlen) {
cfi->descTag.tagSerialNum = cpu_to_le16(1);
cfi->fileVersionNum = cpu_to_le16(1);
cfi->fileCharacteristics = 0;
if (dir_fi) {
dir_fi->icb.extLocation = cpu_to_lelb(UDF_I(new_dir)->i_location);
- udf_update_tag((char *)dir_fi,
- (sizeof(struct fileIdentDesc) +
- le16_to_cpu(dir_fi->lengthOfImpUse) + 3) & ~3);
+ udf_update_tag((char *)dir_fi, udf_dir_entry_len(dir_fi));
if (old_iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB)
mark_inode_dirty(old_inode);
else
extern int udf_write_fi(struct inode *inode, struct fileIdentDesc *,
struct fileIdentDesc *, struct udf_fileident_bh *,
uint8_t *, uint8_t *);
+static inline unsigned int udf_dir_entry_len(struct fileIdentDesc *cfi)
+{
+ return ALIGN(sizeof(struct fileIdentDesc) +
+ le16_to_cpu(cfi->lengthOfImpUse) + cfi->lengthFileIdent,
+ UDF_NAME_PAD);
+}
/* file.c */
extern long udf_ioctl(struct file *, unsigned int, unsigned long);
struct kernel_lb_addr *, uint32_t, int);
extern void udf_write_aext(struct inode *, struct extent_position *,
struct kernel_lb_addr *, uint32_t, int);
-extern int8_t udf_delete_aext(struct inode *, struct extent_position,
- struct kernel_lb_addr, uint32_t);
+extern int8_t udf_delete_aext(struct inode *, struct extent_position);
extern int8_t udf_next_aext(struct inode *, struct extent_position *,
struct kernel_lb_addr *, uint32_t *, int);
extern int8_t udf_current_aext(struct inode *, struct extent_position *,
error = xfs_mod_fdblocks(pag->pag_mount, oldresv, true);
resv->ar_reserved = 0;
resv->ar_asked = 0;
+ resv->ar_orig_reserved = 0;
if (error)
trace_xfs_ag_resv_free_error(pag->pag_mount, pag->pag_agno,
struct xfs_mount *mp = pag->pag_mount;
struct xfs_ag_resv *resv;
int error;
- xfs_extlen_t reserved;
+ xfs_extlen_t hidden_space;
if (used > ask)
ask = used;
- reserved = ask - used;
- error = xfs_mod_fdblocks(mp, -(int64_t)reserved, true);
+ switch (type) {
+ case XFS_AG_RESV_RMAPBT:
+ /*
+ * Space taken by the rmapbt is not subtracted from fdblocks
+ * because the rmapbt lives in the free space. Here we must
+ * subtract the entire reservation from fdblocks so that we
+ * always have blocks available for rmapbt expansion.
+ */
+ hidden_space = ask;
+ break;
+ case XFS_AG_RESV_METADATA:
+ /*
+ * Space taken by all other metadata btrees are accounted
+ * on-disk as used space. We therefore only hide the space
+ * that is reserved but not used by the trees.
+ */
+ hidden_space = ask - used;
+ break;
+ default:
+ ASSERT(0);
+ return -EINVAL;
+ }
+ error = xfs_mod_fdblocks(mp, -(int64_t)hidden_space, true);
if (error) {
trace_xfs_ag_resv_init_error(pag->pag_mount, pag->pag_agno,
error, _RET_IP_);
resv = xfs_perag_resv(pag, type);
resv->ar_asked = ask;
- resv->ar_reserved = resv->ar_orig_reserved = reserved;
+ resv->ar_orig_reserved = hidden_space;
+ resv->ar_reserved = ask - used;
trace_xfs_ag_resv_init(pag, type, ask);
return 0;
return error;
}
+/* Make sure we won't be right-shifting an extent past the maximum bound. */
+int
+xfs_bmap_can_insert_extents(
+ struct xfs_inode *ip,
+ xfs_fileoff_t off,
+ xfs_fileoff_t shift)
+{
+ struct xfs_bmbt_irec got;
+ int is_empty;
+ int error = 0;
+
+ ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
+
+ if (XFS_FORCED_SHUTDOWN(ip->i_mount))
+ return -EIO;
+
+ xfs_ilock(ip, XFS_ILOCK_EXCL);
+ error = xfs_bmap_last_extent(NULL, ip, XFS_DATA_FORK, &got, &is_empty);
+ if (!error && !is_empty && got.br_startoff >= off &&
+ ((got.br_startoff + shift) & BMBT_STARTOFF_MASK) < got.br_startoff)
+ error = -EINVAL;
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+
+ return error;
+}
+
int
xfs_bmap_insert_extents(
struct xfs_trans *tp,
xfs_fileoff_t *next_fsb, xfs_fileoff_t offset_shift_fsb,
bool *done, xfs_fsblock_t *firstblock,
struct xfs_defer_ops *dfops);
+int xfs_bmap_can_insert_extents(struct xfs_inode *ip, xfs_fileoff_t off,
+ xfs_fileoff_t shift);
int xfs_bmap_insert_extents(struct xfs_trans *tp, struct xfs_inode *ip,
xfs_fileoff_t *next_fsb, xfs_fileoff_t offset_shift_fsb,
bool *done, xfs_fileoff_t stop_fsb, xfs_fsblock_t *firstblock,
XFS_DFORK_DSIZE(dip, mp) : \
XFS_DFORK_ASIZE(dip, mp))
+#define XFS_DFORK_MAXEXT(dip, mp, w) \
+ (XFS_DFORK_SIZE(dip, mp, w) / sizeof(struct xfs_bmbt_rec))
+
/*
* Return pointers to the data or attribute forks.
*/
#define BMBT_STARTBLOCK_BITLEN 52
#define BMBT_BLOCKCOUNT_BITLEN 21
+#define BMBT_STARTOFF_MASK ((1ULL << BMBT_STARTOFF_BITLEN) - 1)
+
typedef struct xfs_bmbt_rec {
__be64 l0, l1;
} xfs_bmbt_rec_t;
}
}
+static xfs_failaddr_t
+xfs_dinode_verify_fork(
+ struct xfs_dinode *dip,
+ struct xfs_mount *mp,
+ int whichfork)
+{
+ uint32_t di_nextents = XFS_DFORK_NEXTENTS(dip, whichfork);
+
+ switch (XFS_DFORK_FORMAT(dip, whichfork)) {
+ case XFS_DINODE_FMT_LOCAL:
+ /*
+ * no local regular files yet
+ */
+ if (whichfork == XFS_DATA_FORK) {
+ if (S_ISREG(be16_to_cpu(dip->di_mode)))
+ return __this_address;
+ if (be64_to_cpu(dip->di_size) >
+ XFS_DFORK_SIZE(dip, mp, whichfork))
+ return __this_address;
+ }
+ if (di_nextents)
+ return __this_address;
+ break;
+ case XFS_DINODE_FMT_EXTENTS:
+ if (di_nextents > XFS_DFORK_MAXEXT(dip, mp, whichfork))
+ return __this_address;
+ break;
+ case XFS_DINODE_FMT_BTREE:
+ if (whichfork == XFS_ATTR_FORK) {
+ if (di_nextents > MAXAEXTNUM)
+ return __this_address;
+ } else if (di_nextents > MAXEXTNUM) {
+ return __this_address;
+ }
+ break;
+ default:
+ return __this_address;
+ }
+ return NULL;
+}
+
xfs_failaddr_t
xfs_dinode_verify(
struct xfs_mount *mp,
case S_IFREG:
case S_IFLNK:
case S_IFDIR:
- switch (dip->di_format) {
- case XFS_DINODE_FMT_LOCAL:
- /*
- * no local regular files yet
- */
- if (S_ISREG(mode))
- return __this_address;
- if (di_size > XFS_DFORK_DSIZE(dip, mp))
- return __this_address;
- if (dip->di_nextents)
- return __this_address;
- /* fall through */
- case XFS_DINODE_FMT_EXTENTS:
- case XFS_DINODE_FMT_BTREE:
- break;
- default:
- return __this_address;
- }
+ fa = xfs_dinode_verify_fork(dip, mp, XFS_DATA_FORK);
+ if (fa)
+ return fa;
break;
case 0:
/* Uninitialized inode ok. */
}
if (XFS_DFORK_Q(dip)) {
- switch (dip->di_aformat) {
- case XFS_DINODE_FMT_LOCAL:
- if (dip->di_anextents)
- return __this_address;
- /* fall through */
- case XFS_DINODE_FMT_EXTENTS:
- case XFS_DINODE_FMT_BTREE:
- break;
- default:
- return __this_address;
- }
+ fa = xfs_dinode_verify_fork(dip, mp, XFS_ATTR_FORK);
+ if (fa)
+ return fa;
} else {
/*
* If there is no fork offset, this may be a freshly-made inode
if (low_rec->ar_startext >= mp->m_sb.sb_rextents ||
low_rec->ar_startext == high_rec->ar_startext)
return 0;
- if (high_rec->ar_startext >= mp->m_sb.sb_rextents)
- high_rec->ar_startext = mp->m_sb.sb_rextents - 1;
+ if (high_rec->ar_startext > mp->m_sb.sb_rextents)
+ high_rec->ar_startext = mp->m_sb.sb_rextents;
/* Iterate the bitmap, looking for discrepancies. */
rtstart = low_rec->ar_startext;
}
/*
- * dead simple method of punching delalyed allocation blocks from a range in
- * the inode. Walks a block at a time so will be slow, but is only executed in
- * rare error cases so the overhead is not critical. This will always punch out
- * both the start and end blocks, even if the ranges only partially overlap
- * them, so it is up to the caller to ensure that partial blocks are not
- * passed in.
+ * Dead simple method of punching delalyed allocation blocks from a range in
+ * the inode. This will always punch out both the start and end blocks, even
+ * if the ranges only partially overlap them, so it is up to the caller to
+ * ensure that partial blocks are not passed in.
*/
int
xfs_bmap_punch_delalloc_range(
xfs_fileoff_t start_fsb,
xfs_fileoff_t length)
{
- xfs_fileoff_t remaining = length;
+ struct xfs_ifork *ifp = &ip->i_df;
+ xfs_fileoff_t end_fsb = start_fsb + length;
+ struct xfs_bmbt_irec got, del;
+ struct xfs_iext_cursor icur;
int error = 0;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
- do {
- int done;
- xfs_bmbt_irec_t imap;
- int nimaps = 1;
- xfs_fsblock_t firstblock;
- struct xfs_defer_ops dfops;
+ if (!(ifp->if_flags & XFS_IFEXTENTS)) {
+ error = xfs_iread_extents(NULL, ip, XFS_DATA_FORK);
+ if (error)
+ return error;
+ }
- /*
- * Map the range first and check that it is a delalloc extent
- * before trying to unmap the range. Otherwise we will be
- * trying to remove a real extent (which requires a
- * transaction) or a hole, which is probably a bad idea...
- */
- error = xfs_bmapi_read(ip, start_fsb, 1, &imap, &nimaps,
- XFS_BMAPI_ENTIRE);
+ if (!xfs_iext_lookup_extent_before(ip, ifp, &end_fsb, &icur, &got))
+ return 0;
- if (error) {
- /* something screwed, just bail */
- if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) {
- xfs_alert(ip->i_mount,
- "Failed delalloc mapping lookup ino %lld fsb %lld.",
- ip->i_ino, start_fsb);
- }
- break;
- }
- if (!nimaps) {
- /* nothing there */
- goto next_block;
- }
- if (imap.br_startblock != DELAYSTARTBLOCK) {
- /* been converted, ignore */
- goto next_block;
- }
- WARN_ON(imap.br_blockcount == 0);
+ while (got.br_startoff + got.br_blockcount > start_fsb) {
+ del = got;
+ xfs_trim_extent(&del, start_fsb, length);
/*
- * Note: while we initialise the firstblock/dfops pair, they
- * should never be used because blocks should never be
- * allocated or freed for a delalloc extent and hence we need
- * don't cancel or finish them after the xfs_bunmapi() call.
+ * A delete can push the cursor forward. Step back to the
+ * previous extent on non-delalloc or extents outside the
+ * target range.
*/
- xfs_defer_init(&dfops, &firstblock);
- error = xfs_bunmapi(NULL, ip, start_fsb, 1, 0, 1, &firstblock,
- &dfops, &done);
- if (error)
- break;
+ if (!del.br_blockcount ||
+ !isnullstartblock(del.br_startblock)) {
+ if (!xfs_iext_prev_extent(ifp, &icur, &got))
+ break;
+ continue;
+ }
- ASSERT(!xfs_defer_has_unfinished_work(&dfops));
-next_block:
- start_fsb++;
- remaining--;
- } while(remaining > 0);
+ error = xfs_bmap_del_extent_delay(ip, XFS_DATA_FORK, &icur,
+ &got, &del);
+ if (error || !xfs_iext_get_extent(ifp, &icur, &got))
+ break;
+ }
return error;
}
return 0;
if (offset + len > XFS_ISIZE(ip))
len = XFS_ISIZE(ip) - offset;
- return iomap_zero_range(VFS_I(ip), offset, len, NULL, &xfs_iomap_ops);
+ error = iomap_zero_range(VFS_I(ip), offset, len, NULL, &xfs_iomap_ops);
+ if (error)
+ return error;
+
+ /*
+ * If we zeroed right up to EOF and EOF straddles a page boundary we
+ * must make sure that the post-EOF area is also zeroed because the
+ * page could be mmap'd and iomap_zero_range doesn't do that for us.
+ * Writeback of the eof page will do this, albeit clumsily.
+ */
+ if (offset + len >= XFS_ISIZE(ip) && ((offset + len) & PAGE_MASK)) {
+ error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
+ (offset + len) & ~PAGE_MASK, LLONG_MAX);
+ }
+
+ return error;
}
/*
trace_xfs_insert_file_space(ip);
+ error = xfs_bmap_can_insert_extents(ip, stop_fsb, shift_fsb);
+ if (error)
+ return error;
+
error = xfs_prepare_shift(ip, offset);
if (error)
return error;
struct xfs_trans *tp,
struct xfs_getfsmap_info *info)
{
- struct xfs_rtalloc_rec alow;
- struct xfs_rtalloc_rec ahigh;
+ struct xfs_rtalloc_rec alow = { 0 };
+ struct xfs_rtalloc_rec ahigh = { 0 };
int error;
xfs_ilock(tp->t_mountp->m_rbmip, XFS_ILOCK_SHARED);
do {
free = percpu_counter_sum(&mp->m_fdblocks) -
mp->m_alloc_set_aside;
- if (!free)
+ if (free <= 0)
break;
delta = request - mp->m_resblks;
struct xfs_inode *cip;
int nr_found;
int clcount = 0;
- int bufwasdelwri;
int i;
pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
* inode buffer and shut down the filesystem.
*/
rcu_read_unlock();
- /*
- * Clean up the buffer. If it was delwri, just release it --
- * brelse can handle it with no problems. If not, shut down the
- * filesystem before releasing the buffer.
- */
- bufwasdelwri = (bp->b_flags & _XBF_DELWRI_Q);
- if (bufwasdelwri)
- xfs_buf_relse(bp);
-
xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
- if (!bufwasdelwri) {
- /*
- * Just like incore_relse: if we have b_iodone functions,
- * mark the buffer as an error and call them. Otherwise
- * mark it as stale and brelse.
- */
- if (bp->b_iodone) {
- bp->b_flags &= ~XBF_DONE;
- xfs_buf_stale(bp);
- xfs_buf_ioerror(bp, -EIO);
- xfs_buf_ioend(bp);
- } else {
- xfs_buf_stale(bp);
- xfs_buf_relse(bp);
- }
- }
-
/*
- * Unlocks the flush lock
+ * We'll always have an inode attached to the buffer for completion
+ * process by the time we are called from xfs_iflush(). Hence we have
+ * always need to do IO completion processing to abort the inodes
+ * attached to the buffer. handle them just like the shutdown case in
+ * xfs_buf_submit().
*/
+ ASSERT(bp->b_iodone);
+ bp->b_flags &= ~XBF_DONE;
+ xfs_buf_stale(bp);
+ xfs_buf_ioerror(bp, -EIO);
+ xfs_buf_ioend(bp);
+
+ /* abort the corrupt inode, as it was not attached to the buffer */
xfs_iflush_abort(cip, false);
kmem_free(cilist);
xfs_perag_put(pag);
xfs_log_force(mp, 0);
/*
- * inode clustering:
- * see if other inodes can be gathered into this write
+ * inode clustering: try to gather other inodes into this write
+ *
+ * Note: Any error during clustering will result in the filesystem
+ * being shut down and completion callbacks run on the cluster buffer.
+ * As we have already flushed and attached this inode to the buffer,
+ * it has already been aborted and released by xfs_iflush_cluster() and
+ * so we have no further error handling to do here.
*/
error = xfs_iflush_cluster(ip, bp);
if (error)
- goto cluster_corrupt_out;
+ return error;
*bpp = bp;
return 0;
if (bp)
xfs_buf_relse(bp);
xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
-cluster_corrupt_out:
- error = -EFSCORRUPTED;
abort_out:
- /*
- * Unlocks the flush lock
- */
+ /* abort the corrupt inode, as it was not attached to the buffer */
xfs_iflush_abort(ip, false);
return error;
}
unsigned *lockmode)
{
unsigned mode = XFS_ILOCK_SHARED;
+ bool is_write = flags & (IOMAP_WRITE | IOMAP_ZERO);
/*
* COW writes may allocate delalloc space or convert unwritten COW
* extents, so we need to make sure to take the lock exclusively here.
*/
- if (xfs_is_reflink_inode(ip) && (flags & (IOMAP_WRITE | IOMAP_ZERO))) {
+ if (xfs_is_reflink_inode(ip) && is_write) {
/*
* FIXME: It could still overwrite on unshared extents and not
* need allocation.
mode = XFS_ILOCK_EXCL;
}
+relock:
if (flags & IOMAP_NOWAIT) {
if (!xfs_ilock_nowait(ip, mode))
return -EAGAIN;
xfs_ilock(ip, mode);
}
+ /*
+ * The reflink iflag could have changed since the earlier unlocked
+ * check, so if we got ILOCK_SHARED for a write and but we're now a
+ * reflink inode we have to switch to ILOCK_EXCL and relock.
+ */
+ if (mode == XFS_ILOCK_SHARED && is_write && xfs_is_reflink_inode(ip)) {
+ xfs_iunlock(ip, mode);
+ mode = XFS_ILOCK_EXCL;
+ goto relock;
+ }
+
*lockmode = mode;
return 0;
}
if (!(flags & XFS_TRANS_NO_WRITECOUNT))
sb_start_intwrite(mp->m_super);
- WARN_ON(mp->m_super->s_writers.frozen == SB_FREEZE_COMPLETE);
+ /*
+ * Zero-reservation ("empty") transactions can't modify anything, so
+ * they're allowed to run while we're frozen.
+ */
+ WARN_ON(resp->tr_logres > 0 &&
+ mp->m_super->s_writers.frozen == SB_FREEZE_COMPLETE);
atomic_inc(&mp->m_active_trans);
tp = kmem_zone_zalloc(xfs_trans_zone,
{
return;
}
-static inline int acpi_processor_ppc_has_changed(struct acpi_processor *pr,
+static inline void acpi_processor_ppc_has_changed(struct acpi_processor *pr,
int event_flag)
{
static unsigned int printout = 1;
"Consider compiling CPUfreq support into your kernel.\n");
printout = 0;
}
- return 0;
}
static inline int acpi_processor_get_bios_limit(int cpu, unsigned int *limit)
{
/*
* Initializier
*/
-#define __ARCH_SPIN_LOCK_UNLOCKED { .val = ATOMIC_INIT(0) }
+#define __ARCH_SPIN_LOCK_UNLOCKED { { .val = ATOMIC_INIT(0) } }
/*
* Bitfields in the atomic value:
int offset, size_t size, int flags);
void af_alg_free_resources(struct af_alg_async_req *areq);
void af_alg_async_cb(struct crypto_async_request *_req, int err);
-__poll_t af_alg_poll_mask(struct socket *sock, __poll_t events);
+__poll_t af_alg_poll(struct file *file, struct socket *sock,
+ poll_table *wait);
struct af_alg_async_req *af_alg_alloc_areq(struct sock *sk,
unsigned int areqlen);
int af_alg_get_rsgl(struct sock *sk, struct msghdr *msg, int flags,
int acpi_check_region(resource_size_t start, resource_size_t n,
const char *name);
+acpi_status acpi_release_memory(acpi_handle handle, struct resource *res,
+ u32 level);
+
int acpi_resources_are_enforced(void);
#ifdef CONFIG_HIBERNATION
struct atm_skb_data {
struct atm_vcc *vcc; /* ATM VCC */
unsigned long atm_options; /* ATM layer options */
+ unsigned int acct_truesize; /* truesize accounted to vcc */
};
#define VCC_HTABLE_SIZE 32
void atm_dev_release_vccs(struct atm_dev *dev);
+static inline void atm_account_tx(struct atm_vcc *vcc, struct sk_buff *skb)
+{
+ /*
+ * Because ATM skbs may not belong to a sock (and we don't
+ * necessarily want to), skb->truesize may be adjusted,
+ * escaping the hack in pskb_expand_head() which avoids
+ * doing so for some cases. So stash the value of truesize
+ * at the time we accounted it, and atm_pop_raw() can use
+ * that value later, in case it changes.
+ */
+ refcount_add(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc);
+ ATM_SKB(skb)->acct_truesize = skb->truesize;
+ ATM_SKB(skb)->atm_options = vcc->atm_options;
+}
static inline void atm_force_charge(struct atm_vcc *vcc,int truesize)
{
*/
enum wb_state {
WB_registered, /* bdi_register() was done */
- WB_shutting_down, /* wb_shutdown() in progress */
WB_writeback_running, /* Writeback is in progress */
WB_has_dirty_io, /* Dirty inodes on ->b_{dirty|io|more_io} */
WB_start_all, /* nr_pages == 0 (all) work pending */
#ifdef CONFIG_CGROUP_WRITEBACK
struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */
struct rb_root cgwb_congested_tree; /* their congested states */
+ struct mutex cgwb_release_mutex; /* protect shutdown of wb structs */
#else
struct bdi_writeback_congested *wb_congested;
#endif
if (!q->limits.chunk_sectors)
return q->limits.max_sectors;
- return q->limits.chunk_sectors -
- (offset & (q->limits.chunk_sectors - 1));
+ return min(q->limits.max_sectors, (unsigned int)(q->limits.chunk_sectors -
+ (offset & (q->limits.chunk_sectors - 1))));
}
static inline unsigned int blk_rq_get_max_sectors(struct request *rq,
\
__ret; \
})
+int cgroup_bpf_prog_attach(const union bpf_attr *attr,
+ enum bpf_prog_type ptype, struct bpf_prog *prog);
+int cgroup_bpf_prog_detach(const union bpf_attr *attr,
+ enum bpf_prog_type ptype);
+int cgroup_bpf_prog_query(const union bpf_attr *attr,
+ union bpf_attr __user *uattr);
#else
+struct bpf_prog;
struct cgroup_bpf {};
static inline void cgroup_bpf_put(struct cgroup *cgrp) {}
static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; }
+static inline int cgroup_bpf_prog_attach(const union bpf_attr *attr,
+ enum bpf_prog_type ptype,
+ struct bpf_prog *prog)
+{
+ return -EINVAL;
+}
+
+static inline int cgroup_bpf_prog_detach(const union bpf_attr *attr,
+ enum bpf_prog_type ptype)
+{
+ return -EINVAL;
+}
+
+static inline int cgroup_bpf_prog_query(const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ return -EINVAL;
+}
+
#define cgroup_bpf_enabled (0)
#define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0)
#define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; })
/* Map specifics */
struct xdp_buff;
+struct sk_buff;
struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key);
void __dev_map_insert_ctx(struct bpf_map *map, u32 index);
void __dev_map_flush(struct bpf_map *map);
int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
struct net_device *dev_rx);
+int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
+ struct bpf_prog *xdp_prog);
struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key);
void __cpu_map_insert_ctx(struct bpf_map *map, u32 index);
return 0;
}
+struct sk_buff;
+
+static inline int dev_map_generic_redirect(struct bpf_dtab_netdev *dst,
+ struct sk_buff *skb,
+ struct bpf_prog *xdp_prog)
+{
+ return 0;
+}
+
static inline
struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key)
{
struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key);
struct sock *__sock_hash_lookup_elem(struct bpf_map *map, void *key);
int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type);
+int sockmap_get_from_fd(const union bpf_attr *attr, int type,
+ struct bpf_prog *prog);
#else
static inline struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key)
{
{
return -EOPNOTSUPP;
}
+
+static inline int sockmap_get_from_fd(const union bpf_attr *attr, int type,
+ struct bpf_prog *prog)
+{
+ return -EINVAL;
+}
#endif
#if defined(CONFIG_XDP_SOCKETS)
#include <uapi/linux/bpf.h>
#ifdef CONFIG_BPF_LIRC_MODE2
-int lirc_prog_attach(const union bpf_attr *attr);
+int lirc_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog);
int lirc_prog_detach(const union bpf_attr *attr);
int lirc_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr);
#else
-static inline int lirc_prog_attach(const union bpf_attr *attr)
+static inline int lirc_prog_attach(const union bpf_attr *attr,
+ struct bpf_prog *prog)
{
return -EINVAL;
}
*/
#ifndef COMPAT_SYSCALL_DEFINEx
#define COMPAT_SYSCALL_DEFINEx(x, name, ...) \
+ __diag_push(); \
+ __diag_ignore(GCC, 8, "-Wattribute-alias", \
+ "Type aliasing is used to sanitize syscall arguments");\
asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \
asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) \
__attribute__((alias(__stringify(__se_compat_sys##name)))); \
asmlinkage long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \
asmlinkage long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \
{ \
- return __do_compat_sys##name(__MAP(x,__SC_DELOUSE,__VA_ARGS__));\
+ long ret = __do_compat_sys##name(__MAP(x,__SC_DELOUSE,__VA_ARGS__));\
+ __MAP(x,__SC_TEST,__VA_ARGS__); \
+ return ret; \
} \
+ __diag_pop(); \
static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))
#endif /* COMPAT_SYSCALL_DEFINEx */
#if GCC_VERSION >= 50100
#define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1
#endif
+
+/*
+ * Turn individual warnings and errors on and off locally, depending
+ * on version.
+ */
+#define __diag_GCC(version, severity, s) \
+ __diag_GCC_ ## version(__diag_GCC_ ## severity s)
+
+/* Severity used in pragma directives */
+#define __diag_GCC_ignore ignored
+#define __diag_GCC_warn warning
+#define __diag_GCC_error error
+
+/* Compilers before gcc-4.6 do not understand "#pragma GCC diagnostic push" */
+#if GCC_VERSION >= 40600
+#define __diag_str1(s) #s
+#define __diag_str(s) __diag_str1(s)
+#define __diag(s) _Pragma(__diag_str(GCC diagnostic s))
+#endif
+
+#if GCC_VERSION >= 80000
+#define __diag_GCC_8(s) __diag(s)
+#else
+#define __diag_GCC_8(s)
+#endif
# define __native_word(t) (sizeof(t) == sizeof(char) || sizeof(t) == sizeof(short) || sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long))
#endif
+#ifndef __diag
+#define __diag(string)
+#endif
+
+#ifndef __diag_GCC
+#define __diag_GCC(version, severity, string)
+#endif
+
+#define __diag_push() __diag(push)
+#define __diag_pop() __diag(pop)
+
+#define __diag_ignore(compiler, version, option, comment) \
+ __diag_ ## compiler(version, ignore, option)
+#define __diag_warn(compiler, version, option, comment) \
+ __diag_ ## compiler(version, warn, option)
+#define __diag_error(compiler, version, option, comment) \
+ __diag_ ## compiler(version, error, option)
+
#endif /* __LINUX_COMPILER_TYPES_H */
#define cpu_active(cpu) ((cpu) == 0)
#endif
-/* verify cpu argument to cpumask_* operators */
-static inline unsigned int cpumask_check(unsigned int cpu)
+static inline void cpu_max_bits_warn(unsigned int cpu, unsigned int bits)
{
#ifdef CONFIG_DEBUG_PER_CPU_MAPS
- WARN_ON_ONCE(cpu >= nr_cpumask_bits);
+ WARN_ON_ONCE(cpu >= bits);
#endif /* CONFIG_DEBUG_PER_CPU_MAPS */
+}
+
+/* verify cpu argument to cpumask_* operators */
+static inline unsigned int cpumask_check(unsigned int cpu)
+{
+ cpu_max_bits_warn(cpu, nr_cpumask_bits);
return cpu;
}
ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
const struct iomap_ops *ops);
-int dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size,
+vm_fault_t dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size,
pfn_t *pfnp, int *errp, const struct iomap_ops *ops);
vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf,
enum page_entry_size pe_size, pfn_t pfn);
* CMA should not be used by the device drivers directly. It is
* only a helper framework for dma-mapping subsystem.
*
- * For more information, see kernel-docs in drivers/base/dma-contiguous.c
+ * For more information, see kernel-docs in kernel/dma/contiguous.c
*/
#ifdef __KERNEL__
unsigned int rxqs);
#define devm_alloc_etherdev(dev, sizeof_priv) devm_alloc_etherdev_mqs(dev, sizeof_priv, 1, 1)
-struct sk_buff **eth_gro_receive(struct sk_buff **head,
- struct sk_buff *skb);
+struct sk_buff *eth_gro_receive(struct list_head *head, struct sk_buff *skb);
int eth_gro_complete(struct sk_buff *skb, int nhoff);
/* Reserved Ethernet Addresses per IEEE 802.1Q */
#include <linux/cryptohash.h>
#include <linux/set_memory.h>
#include <linux/kallsyms.h>
+#include <linux/if_vlan.h>
#include <net/sch_generic.h>
};
struct bpf_binary_header {
- unsigned int pages;
- u8 image[];
+ u32 pages;
+ /* Some arches need word alignment for their instructions */
+ u8 image[] __aligned(4);
};
struct bpf_prog {
u16 pages; /* Number of allocated pages */
u16 jited:1, /* Is our filter JIT'ed? */
jit_requested:1,/* archs need to JIT the prog */
- locked:1, /* Program image locked? */
+ undo_set_mem:1, /* Passed set_memory_ro() checkpoint */
gpl_compatible:1, /* Is filter GPL compatible? */
cb_access:1, /* Is control block accessed? */
dst_needed:1, /* Do we need dst entry? */
#define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0]))
-#ifdef CONFIG_ARCH_HAS_SET_MEMORY
-static inline void bpf_prog_lock_ro(struct bpf_prog *fp)
-{
- fp->locked = 1;
- WARN_ON_ONCE(set_memory_ro((unsigned long)fp, fp->pages));
-}
-
-static inline void bpf_prog_unlock_ro(struct bpf_prog *fp)
-{
- if (fp->locked) {
- WARN_ON_ONCE(set_memory_rw((unsigned long)fp, fp->pages));
- /* In case set_memory_rw() fails, we want to be the first
- * to crash here instead of some random place later on.
- */
- fp->locked = 0;
- }
-}
-
-static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr)
-{
- WARN_ON_ONCE(set_memory_ro((unsigned long)hdr, hdr->pages));
-}
-
-static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr)
-{
- WARN_ON_ONCE(set_memory_rw((unsigned long)hdr, hdr->pages));
-}
-#else
static inline void bpf_prog_lock_ro(struct bpf_prog *fp)
{
+ fp->undo_set_mem = 1;
+ set_memory_ro((unsigned long)fp, fp->pages);
}
static inline void bpf_prog_unlock_ro(struct bpf_prog *fp)
{
+ if (fp->undo_set_mem)
+ set_memory_rw((unsigned long)fp, fp->pages);
}
static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr)
{
+ set_memory_ro((unsigned long)hdr, hdr->pages);
}
static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr)
{
+ set_memory_rw((unsigned long)hdr, hdr->pages);
}
-#endif /* CONFIG_ARCH_HAS_SET_MEMORY */
static inline struct bpf_binary_header *
bpf_jit_binary_hdr(const struct bpf_prog *fp)
struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
const struct bpf_insn *patch, u32 len);
+static inline int __xdp_generic_ok_fwd_dev(struct sk_buff *skb,
+ struct net_device *fwd)
+{
+ unsigned int len;
+
+ if (unlikely(!(fwd->flags & IFF_UP)))
+ return -ENETDOWN;
+
+ len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN;
+ if (skb->len > len)
+ return -EMSGSIZE;
+
+ return 0;
+}
+
/* The pair of xdp_do_redirect and xdp_do_flush_map MUST be called in the
* same cpu context. Further for best results no more than a single map
* for the do_redirect/do_flush pair should be used. This limitation is
}
#endif /* CONFIG_BPF_JIT */
+void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp);
+void bpf_prog_kallsyms_del_all(struct bpf_prog *fp);
+
#define BPF_ANC BIT(15)
static inline bool bpf_needs_clear_a(const struct sock_filter *first)
int (*iterate) (struct file *, struct dir_context *);
int (*iterate_shared) (struct file *, struct dir_context *);
__poll_t (*poll) (struct file *, struct poll_table_struct *);
- struct wait_queue_head * (*get_poll_head)(struct file *, __poll_t);
- __poll_t (*poll_mask) (struct file *, __poll_t);
long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
int (*mmap) (struct file *, struct vm_area_struct *);
/*
* qoriq ptp registers
- * Generated by regen.tcl on Thu May 13 01:38:57 PM CEST 2010
*/
-struct qoriq_ptp_registers {
+struct ctrl_regs {
u32 tmr_ctrl; /* Timer control register */
u32 tmr_tevent; /* Timestamp event register */
u32 tmr_temask; /* Timer event mask register */
u8 res1[4];
u32 tmroff_h; /* Timer offset high */
u32 tmroff_l; /* Timer offset low */
- u8 res2[8];
+};
+
+struct alarm_regs {
u32 tmr_alarm1_h; /* Timer alarm 1 high register */
u32 tmr_alarm1_l; /* Timer alarm 1 high register */
u32 tmr_alarm2_h; /* Timer alarm 2 high register */
u32 tmr_alarm2_l; /* Timer alarm 2 high register */
- u8 res3[48];
+};
+
+struct fiper_regs {
u32 tmr_fiper1; /* Timer fixed period interval */
u32 tmr_fiper2; /* Timer fixed period interval */
u32 tmr_fiper3; /* Timer fixed period interval */
- u8 res4[20];
+};
+
+struct etts_regs {
u32 tmr_etts1_h; /* Timestamp of general purpose external trigger */
u32 tmr_etts1_l; /* Timestamp of general purpose external trigger */
u32 tmr_etts2_h; /* Timestamp of general purpose external trigger */
u32 tmr_etts2_l; /* Timestamp of general purpose external trigger */
};
+struct qoriq_ptp_registers {
+ struct ctrl_regs __iomem *ctrl_regs;
+ struct alarm_regs __iomem *alarm_regs;
+ struct fiper_regs __iomem *fiper_regs;
+ struct etts_regs __iomem *etts_regs;
+};
+
+/* Offset definitions for the four register groups */
+#define CTRL_REGS_OFFSET 0x0
+#define ALARM_REGS_OFFSET 0x40
+#define FIPER_REGS_OFFSET 0x80
+#define ETTS_REGS_OFFSET 0xa0
+
+#define FMAN_CTRL_REGS_OFFSET 0x80
+#define FMAN_ALARM_REGS_OFFSET 0xb8
+#define FMAN_FIPER_REGS_OFFSET 0xd0
+#define FMAN_ETTS_REGS_OFFSET 0xe0
+
+
/* Bit definitions for the TMR_CTRL register */
#define ALM1P (1<<31) /* Alarm1 output polarity */
#define ALM2P (1<<30) /* Alarm2 output polarity */
#define DRIVER "ptp_qoriq"
#define DEFAULT_CKSEL 1
#define N_EXT_TS 2
-#define REG_SIZE sizeof(struct qoriq_ptp_registers)
struct qoriq_ptp {
- struct qoriq_ptp_registers __iomem *regs;
+ void __iomem *base;
+ struct qoriq_ptp_registers regs;
spinlock_t lock; /* protects regs */
struct ptp_clock *clock;
struct ptp_clock_info caps;
#define HWMON_T_MIN_ALARM BIT(hwmon_temp_min_alarm)
#define HWMON_T_MAX_ALARM BIT(hwmon_temp_max_alarm)
#define HWMON_T_CRIT_ALARM BIT(hwmon_temp_crit_alarm)
+#define HWMON_T_LCRIT_ALARM BIT(hwmon_temp_lcrit_alarm)
#define HWMON_T_EMERGENCY_ALARM BIT(hwmon_temp_emergency_alarm)
#define HWMON_T_FAULT BIT(hwmon_temp_fault)
#define HWMON_T_OFFSET BIT(hwmon_temp_offset)
hwmon_power_cap_hyst,
hwmon_power_cap_max,
hwmon_power_cap_min,
+ hwmon_power_min,
hwmon_power_max,
hwmon_power_crit,
+ hwmon_power_lcrit,
hwmon_power_label,
hwmon_power_alarm,
hwmon_power_cap_alarm,
+ hwmon_power_min_alarm,
hwmon_power_max_alarm,
+ hwmon_power_lcrit_alarm,
hwmon_power_crit_alarm,
};
#define HWMON_P_CAP_HYST BIT(hwmon_power_cap_hyst)
#define HWMON_P_CAP_MAX BIT(hwmon_power_cap_max)
#define HWMON_P_CAP_MIN BIT(hwmon_power_cap_min)
+#define HWMON_P_MIN BIT(hwmon_power_min)
#define HWMON_P_MAX BIT(hwmon_power_max)
+#define HWMON_P_LCRIT BIT(hwmon_power_lcrit)
#define HWMON_P_CRIT BIT(hwmon_power_crit)
#define HWMON_P_LABEL BIT(hwmon_power_label)
#define HWMON_P_ALARM BIT(hwmon_power_alarm)
#define HWMON_P_CAP_ALARM BIT(hwmon_power_cap_alarm)
+#define HWMON_P_MIN_ALARM BIT(hwmon_power_max_alarm)
#define HWMON_P_MAX_ALARM BIT(hwmon_power_max_alarm)
+#define HWMON_P_LCRIT_ALARM BIT(hwmon_power_lcrit_alarm)
#define HWMON_P_CRIT_ALARM BIT(hwmon_power_crit_alarm)
enum hwmon_energy_attributes {
void hwmon_device_unregister(struct device *dev);
void devm_hwmon_device_unregister(struct device *dev);
+/**
+ * hwmon_is_bad_char - Is the char invalid in a hwmon name
+ * @ch: the char to be considered
+ *
+ * hwmon_is_bad_char() can be used to determine if the given character
+ * may not be used in a hwmon name.
+ *
+ * Returns true if the char is invalid, false otherwise.
+ */
+static inline bool hwmon_is_bad_char(const char ch)
+{
+ switch (ch) {
+ case '-':
+ case '*':
+ case ' ':
+ case '\t':
+ case '\n':
+ return true;
+ default:
+ return false;
+ }
+}
+
#endif
#define IEEE80211_DELBA_PARAM_INITIATOR_MASK 0x0800
/*
- * A-PMDU buffer sizes
- * According to IEEE802.11n spec size varies from 8K to 64K (in powers of 2)
+ * A-MPDU buffer sizes
+ * According to HT size varies from 8 to 64 frames
+ * HE adds the ability to have up to 256 frames.
*/
-#define IEEE80211_MIN_AMPDU_BUF 0x8
-#define IEEE80211_MAX_AMPDU_BUF 0x40
+#define IEEE80211_MIN_AMPDU_BUF 0x8
+#define IEEE80211_MAX_AMPDU_BUF_HT 0x40
+#define IEEE80211_MAX_AMPDU_BUF 0x100
/* Spatial Multiplexing Power Save Modes (for capability) */
__le16 basic_mcs_set;
} __packed;
+/**
+ * struct ieee80211_he_cap_elem - HE capabilities element
+ *
+ * This structure is the "HE capabilities element" fixed fields as
+ * described in P802.11ax_D2.0 section 9.4.2.237.2 and 9.4.2.237.3
+ */
+struct ieee80211_he_cap_elem {
+ u8 mac_cap_info[5];
+ u8 phy_cap_info[9];
+} __packed;
+
+#define IEEE80211_TX_RX_MCS_NSS_DESC_MAX_LEN 5
+
+/**
+ * enum ieee80211_he_mcs_support - HE MCS support definitions
+ * @IEEE80211_HE_MCS_SUPPORT_0_7: MCSes 0-7 are supported for the
+ * number of streams
+ * @IEEE80211_HE_MCS_SUPPORT_0_9: MCSes 0-9 are supported
+ * @IEEE80211_HE_MCS_SUPPORT_0_11: MCSes 0-11 are supported
+ * @IEEE80211_HE_MCS_NOT_SUPPORTED: This number of streams isn't supported
+ *
+ * These definitions are used in each 2-bit subfield of the rx_mcs_*
+ * and tx_mcs_* fields of &struct ieee80211_he_mcs_nss_supp, which are
+ * both split into 8 subfields by number of streams. These values indicate
+ * which MCSes are supported for the number of streams the value appears
+ * for.
+ */
+enum ieee80211_he_mcs_support {
+ IEEE80211_HE_MCS_SUPPORT_0_7 = 0,
+ IEEE80211_HE_MCS_SUPPORT_0_9 = 1,
+ IEEE80211_HE_MCS_SUPPORT_0_11 = 2,
+ IEEE80211_HE_MCS_NOT_SUPPORTED = 3,
+};
+
+/**
+ * struct ieee80211_he_mcs_nss_supp - HE Tx/Rx HE MCS NSS Support Field
+ *
+ * This structure holds the data required for the Tx/Rx HE MCS NSS Support Field
+ * described in P802.11ax_D2.0 section 9.4.2.237.4
+ *
+ * @rx_mcs_80: Rx MCS map 2 bits for each stream, total 8 streams, for channel
+ * widths less than 80MHz.
+ * @tx_mcs_80: Tx MCS map 2 bits for each stream, total 8 streams, for channel
+ * widths less than 80MHz.
+ * @rx_mcs_160: Rx MCS map 2 bits for each stream, total 8 streams, for channel
+ * width 160MHz.
+ * @tx_mcs_160: Tx MCS map 2 bits for each stream, total 8 streams, for channel
+ * width 160MHz.
+ * @rx_mcs_80p80: Rx MCS map 2 bits for each stream, total 8 streams, for
+ * channel width 80p80MHz.
+ * @tx_mcs_80p80: Tx MCS map 2 bits for each stream, total 8 streams, for
+ * channel width 80p80MHz.
+ */
+struct ieee80211_he_mcs_nss_supp {
+ __le16 rx_mcs_80;
+ __le16 tx_mcs_80;
+ __le16 rx_mcs_160;
+ __le16 tx_mcs_160;
+ __le16 rx_mcs_80p80;
+ __le16 tx_mcs_80p80;
+} __packed;
+
+/**
+ * struct ieee80211_he_operation - HE capabilities element
+ *
+ * This structure is the "HE operation element" fields as
+ * described in P802.11ax_D2.0 section 9.4.2.238
+ */
+struct ieee80211_he_operation {
+ __le32 he_oper_params;
+ __le16 he_mcs_nss_set;
+ /* Optional 0,1,3 or 4 bytes: depends on @he_oper_params */
+ u8 optional[0];
+} __packed;
+
+/**
+ * struct ieee80211_he_mu_edca_param_ac_rec - MU AC Parameter Record field
+ *
+ * This structure is the "MU AC Parameter Record" fields as
+ * described in P802.11ax_D2.0 section 9.4.2.240
+ */
+struct ieee80211_he_mu_edca_param_ac_rec {
+ u8 aifsn;
+ u8 ecw_min_max;
+ u8 mu_edca_timer;
+} __packed;
+
+/**
+ * struct ieee80211_mu_edca_param_set - MU EDCA Parameter Set element
+ *
+ * This structure is the "MU EDCA Parameter Set element" fields as
+ * described in P802.11ax_D2.0 section 9.4.2.240
+ */
+struct ieee80211_mu_edca_param_set {
+ u8 mu_qos_info;
+ struct ieee80211_he_mu_edca_param_ac_rec ac_be;
+ struct ieee80211_he_mu_edca_param_ac_rec ac_bk;
+ struct ieee80211_he_mu_edca_param_ac_rec ac_vi;
+ struct ieee80211_he_mu_edca_param_ac_rec ac_vo;
+} __packed;
/* 802.11ac VHT Capabilities */
#define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895 0x00000000
#define IEEE80211_VHT_CAP_RX_ANTENNA_PATTERN 0x10000000
#define IEEE80211_VHT_CAP_TX_ANTENNA_PATTERN 0x20000000
+/* 802.11ax HE MAC capabilities */
+#define IEEE80211_HE_MAC_CAP0_HTC_HE 0x01
+#define IEEE80211_HE_MAC_CAP0_TWT_REQ 0x02
+#define IEEE80211_HE_MAC_CAP0_TWT_RES 0x04
+#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_NOT_SUPP 0x00
+#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_LEVEL_1 0x08
+#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_LEVEL_2 0x10
+#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_LEVEL_3 0x18
+#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_MASK 0x18
+#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_1 0x00
+#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_2 0x20
+#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_4 0x40
+#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_8 0x60
+#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_16 0x80
+#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_32 0xa0
+#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_64 0xc0
+#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_UNLIMITED 0xe0
+#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_MASK 0xe0
+
+#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_UNLIMITED 0x00
+#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_128 0x01
+#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_256 0x02
+#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_512 0x03
+#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_MASK 0x03
+#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_0US 0x00
+#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_8US 0x04
+#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US 0x08
+#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_MASK 0x0c
+#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_1 0x00
+#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_2 0x10
+#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_3 0x20
+#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_4 0x30
+#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_5 0x40
+#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_6 0x50
+#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_7 0x60
+#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_8 0x70
+#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_MASK 0x70
+
+/* Link adaptation is split between byte HE_MAC_CAP1 and
+ * HE_MAC_CAP2. It should be set only if IEEE80211_HE_MAC_CAP0_HTC_HE
+ * in which case the following values apply:
+ * 0 = No feedback.
+ * 1 = reserved.
+ * 2 = Unsolicited feedback.
+ * 3 = both
+ */
+#define IEEE80211_HE_MAC_CAP1_LINK_ADAPTATION 0x80
+
+#define IEEE80211_HE_MAC_CAP2_LINK_ADAPTATION 0x01
+#define IEEE80211_HE_MAC_CAP2_ALL_ACK 0x02
+#define IEEE80211_HE_MAC_CAP2_UL_MU_RESP_SCHED 0x04
+#define IEEE80211_HE_MAC_CAP2_BSR 0x08
+#define IEEE80211_HE_MAC_CAP2_BCAST_TWT 0x10
+#define IEEE80211_HE_MAC_CAP2_32BIT_BA_BITMAP 0x20
+#define IEEE80211_HE_MAC_CAP2_MU_CASCADING 0x40
+#define IEEE80211_HE_MAC_CAP2_ACK_EN 0x80
+
+#define IEEE80211_HE_MAC_CAP3_GRP_ADDR_MULTI_STA_BA_DL_MU 0x01
+#define IEEE80211_HE_MAC_CAP3_OMI_CONTROL 0x02
+#define IEEE80211_HE_MAC_CAP3_OFDMA_RA 0x04
+
+/* The maximum length of an A-MDPU is defined by the combination of the Maximum
+ * A-MDPU Length Exponent field in the HT capabilities, VHT capabilities and the
+ * same field in the HE capabilities.
+ */
+#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_USE_VHT 0x00
+#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_VHT_1 0x08
+#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_VHT_2 0x10
+#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_RESERVED 0x18
+#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_MASK 0x18
+#define IEEE80211_HE_MAC_CAP3_A_AMSDU_FRAG 0x20
+#define IEEE80211_HE_MAC_CAP3_FLEX_TWT_SCHED 0x40
+#define IEEE80211_HE_MAC_CAP3_RX_CTRL_FRAME_TO_MULTIBSS 0x80
+
+#define IEEE80211_HE_MAC_CAP4_BSRP_BQRP_A_MPDU_AGG 0x01
+#define IEEE80211_HE_MAC_CAP4_QTP 0x02
+#define IEEE80211_HE_MAC_CAP4_BQR 0x04
+#define IEEE80211_HE_MAC_CAP4_SR_RESP 0x08
+#define IEEE80211_HE_MAC_CAP4_NDP_FB_REP 0x10
+#define IEEE80211_HE_MAC_CAP4_OPS 0x20
+#define IEEE80211_HE_MAC_CAP4_AMDSU_IN_AMPDU 0x40
+
+/* 802.11ax HE PHY capabilities */
+#define IEEE80211_HE_PHY_CAP0_DUAL_BAND 0x01
+#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G 0x02
+#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G 0x04
+#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G 0x08
+#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G 0x10
+#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_RU_MAPPING_IN_2G 0x20
+#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_RU_MAPPING_IN_5G 0x40
+#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_MASK 0xfe
+
+#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_80MHZ_ONLY_SECOND_20MHZ 0x01
+#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_80MHZ_ONLY_SECOND_40MHZ 0x02
+#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_160MHZ_ONLY_SECOND_20MHZ 0x04
+#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_160MHZ_ONLY_SECOND_40MHZ 0x08
+#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK 0x0f
+#define IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A 0x10
+#define IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD 0x20
+#define IEEE80211_HE_PHY_CAP1_HE_LTF_AND_GI_FOR_HE_PPDUS_0_8US 0x40
+/* Midamble RX Max NSTS is split between byte #2 and byte #3 */
+#define IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_MAX_NSTS 0x80
+
+#define IEEE80211_HE_PHY_CAP2_MIDAMBLE_RX_MAX_NSTS 0x01
+#define IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US 0x02
+#define IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ 0x04
+#define IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ 0x08
+#define IEEE80211_HE_PHY_CAP2_DOPPLER_TX 0x10
+#define IEEE80211_HE_PHY_CAP2_DOPPLER_RX 0x20
+
+/* Note that the meaning of UL MU below is different between an AP and a non-AP
+ * sta, where in the AP case it indicates support for Rx and in the non-AP sta
+ * case it indicates support for Tx.
+ */
+#define IEEE80211_HE_PHY_CAP2_UL_MU_FULL_MU_MIMO 0x40
+#define IEEE80211_HE_PHY_CAP2_UL_MU_PARTIAL_MU_MIMO 0x80
+
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_NO_DCM 0x00
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_BPSK 0x01
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_QPSK 0x02
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_16_QAM 0x03
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_MASK 0x03
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_TX_NSS_1 0x00
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_TX_NSS_2 0x04
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_NO_DCM 0x00
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_BPSK 0x08
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_QPSK 0x10
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_16_QAM 0x18
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_MASK 0x18
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_RX_NSS_1 0x00
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_RX_NSS_2 0x20
+#define IEEE80211_HE_PHY_CAP3_RX_HE_MU_PPDU_FROM_NON_AP_STA 0x40
+#define IEEE80211_HE_PHY_CAP3_SU_BEAMFORMER 0x80
+
+#define IEEE80211_HE_PHY_CAP4_SU_BEAMFORMEE 0x01
+#define IEEE80211_HE_PHY_CAP4_MU_BEAMFORMER 0x02
+
+/* Minimal allowed value of Max STS under 80MHz is 3 */
+#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_4 0x0c
+#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_5 0x10
+#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_6 0x14
+#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_7 0x18
+#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_8 0x1c
+#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_MASK 0x1c
+
+/* Minimal allowed value of Max STS above 80MHz is 3 */
+#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_4 0x60
+#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_5 0x80
+#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_6 0xa0
+#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_7 0xc0
+#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_8 0xe0
+#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_MASK 0xe0
+
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_1 0x00
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_2 0x01
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_3 0x02
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_4 0x03
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_5 0x04
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_6 0x05
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_7 0x06
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_8 0x07
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_MASK 0x07
+
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_1 0x00
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_2 0x08
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_3 0x10
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_4 0x18
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_5 0x20
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_6 0x28
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_7 0x30
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_8 0x38
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_MASK 0x38
+
+#define IEEE80211_HE_PHY_CAP5_NG16_SU_FEEDBACK 0x40
+#define IEEE80211_HE_PHY_CAP5_NG16_MU_FEEDBACK 0x80
+
+#define IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_42_SU 0x01
+#define IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_75_MU 0x02
+#define IEEE80211_HE_PHY_CAP6_TRIG_SU_BEAMFORMER_FB 0x04
+#define IEEE80211_HE_PHY_CAP6_TRIG_MU_BEAMFORMER_FB 0x08
+#define IEEE80211_HE_PHY_CAP6_TRIG_CQI_FB 0x10
+#define IEEE80211_HE_PHY_CAP6_PARTIAL_BW_EXT_RANGE 0x20
+#define IEEE80211_HE_PHY_CAP6_PARTIAL_BANDWIDTH_DL_MUMIMO 0x40
+#define IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT 0x80
+
+#define IEEE80211_HE_PHY_CAP7_SRP_BASED_SR 0x01
+#define IEEE80211_HE_PHY_CAP7_POWER_BOOST_FACTOR_AR 0x02
+#define IEEE80211_HE_PHY_CAP7_HE_SU_MU_PPDU_4XLTF_AND_08_US_GI 0x04
+#define IEEE80211_HE_PHY_CAP7_MAX_NC_1 0x08
+#define IEEE80211_HE_PHY_CAP7_MAX_NC_2 0x10
+#define IEEE80211_HE_PHY_CAP7_MAX_NC_3 0x18
+#define IEEE80211_HE_PHY_CAP7_MAX_NC_4 0x20
+#define IEEE80211_HE_PHY_CAP7_MAX_NC_5 0x28
+#define IEEE80211_HE_PHY_CAP7_MAX_NC_6 0x30
+#define IEEE80211_HE_PHY_CAP7_MAX_NC_7 0x38
+#define IEEE80211_HE_PHY_CAP7_MAX_NC_MASK 0x38
+#define IEEE80211_HE_PHY_CAP7_STBC_TX_ABOVE_80MHZ 0x40
+#define IEEE80211_HE_PHY_CAP7_STBC_RX_ABOVE_80MHZ 0x80
+
+#define IEEE80211_HE_PHY_CAP8_HE_ER_SU_PPDU_4XLTF_AND_08_US_GI 0x01
+#define IEEE80211_HE_PHY_CAP8_20MHZ_IN_40MHZ_HE_PPDU_IN_2G 0x02
+#define IEEE80211_HE_PHY_CAP8_20MHZ_IN_160MHZ_HE_PPDU 0x04
+#define IEEE80211_HE_PHY_CAP8_80MHZ_IN_160MHZ_HE_PPDU 0x08
+#define IEEE80211_HE_PHY_CAP8_HE_ER_SU_1XLTF_AND_08_US_GI 0x10
+#define IEEE80211_HE_PHY_CAP8_MIDAMBLE_RX_2X_AND_1XLTF 0x20
+
+/* 802.11ax HE TX/RX MCS NSS Support */
+#define IEEE80211_TX_RX_MCS_NSS_SUPP_HIGHEST_MCS_POS (3)
+#define IEEE80211_TX_RX_MCS_NSS_SUPP_TX_BITMAP_POS (6)
+#define IEEE80211_TX_RX_MCS_NSS_SUPP_RX_BITMAP_POS (11)
+#define IEEE80211_TX_RX_MCS_NSS_SUPP_TX_BITMAP_MASK 0x07c0
+#define IEEE80211_TX_RX_MCS_NSS_SUPP_RX_BITMAP_MASK 0xf800
+
+/* TX/RX HE MCS Support field Highest MCS subfield encoding */
+enum ieee80211_he_highest_mcs_supported_subfield_enc {
+ HIGHEST_MCS_SUPPORTED_MCS7 = 0,
+ HIGHEST_MCS_SUPPORTED_MCS8,
+ HIGHEST_MCS_SUPPORTED_MCS9,
+ HIGHEST_MCS_SUPPORTED_MCS10,
+ HIGHEST_MCS_SUPPORTED_MCS11,
+};
+
+/* Calculate 802.11ax HE capabilities IE Tx/Rx HE MCS NSS Support Field size */
+static inline u8
+ieee80211_he_mcs_nss_size(const struct ieee80211_he_cap_elem *he_cap)
+{
+ u8 count = 4;
+
+ if (he_cap->phy_cap_info[0] &
+ IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G)
+ count += 4;
+
+ if (he_cap->phy_cap_info[0] &
+ IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G)
+ count += 4;
+
+ return count;
+}
+
+/* 802.11ax HE PPE Thresholds */
+#define IEEE80211_PPE_THRES_NSS_SUPPORT_2NSS (1)
+#define IEEE80211_PPE_THRES_NSS_POS (0)
+#define IEEE80211_PPE_THRES_NSS_MASK (7)
+#define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_2x966_AND_966_RU \
+ (BIT(5) | BIT(6))
+#define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_MASK 0x78
+#define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_POS (3)
+#define IEEE80211_PPE_THRES_INFO_PPET_SIZE (3)
+
+/*
+ * Calculate 802.11ax HE capabilities IE PPE field size
+ * Input: Header byte of ppe_thres (first byte), and HE capa IE's PHY cap u8*
+ */
+static inline u8
+ieee80211_he_ppe_size(u8 ppe_thres_hdr, const u8 *phy_cap_info)
+{
+ u8 n;
+
+ if ((phy_cap_info[6] &
+ IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT) == 0)
+ return 0;
+
+ n = hweight8(ppe_thres_hdr &
+ IEEE80211_PPE_THRES_RU_INDEX_BITMASK_MASK);
+ n *= (1 + ((ppe_thres_hdr & IEEE80211_PPE_THRES_NSS_MASK) >>
+ IEEE80211_PPE_THRES_NSS_POS));
+
+ /*
+ * Each pair is 6 bits, and we need to add the 7 "header" bits to the
+ * total size.
+ */
+ n = (n * IEEE80211_PPE_THRES_INFO_PPET_SIZE * 2) + 7;
+ n = DIV_ROUND_UP(n, 8);
+
+ return n;
+}
+
+/* HE Operation defines */
+#define IEEE80211_HE_OPERATION_BSS_COLOR_MASK 0x0000003f
+#define IEEE80211_HE_OPERATION_DFLT_PE_DURATION_MASK 0x000001c0
+#define IEEE80211_HE_OPERATION_DFLT_PE_DURATION_OFFSET 6
+#define IEEE80211_HE_OPERATION_TWT_REQUIRED 0x00000200
+#define IEEE80211_HE_OPERATION_RTS_THRESHOLD_MASK 0x000ffc00
+#define IEEE80211_HE_OPERATION_RTS_THRESHOLD_OFFSET 10
+#define IEEE80211_HE_OPERATION_PARTIAL_BSS_COLOR 0x000100000
+#define IEEE80211_HE_OPERATION_VHT_OPER_INFO 0x000200000
+#define IEEE80211_HE_OPERATION_MULTI_BSSID_AP 0x10000000
+#define IEEE80211_HE_OPERATION_TX_BSSID_INDICATOR 0x20000000
+#define IEEE80211_HE_OPERATION_BSS_COLOR_DISABLED 0x40000000
+
+/*
+ * ieee80211_he_oper_size - calculate 802.11ax HE Operations IE size
+ * @he_oper_ie: byte data of the He Operations IE, stating from the the byte
+ * after the ext ID byte. It is assumed that he_oper_ie has at least
+ * sizeof(struct ieee80211_he_operation) bytes, checked already in
+ * ieee802_11_parse_elems_crc()
+ * @return the actual size of the IE data (not including header), or 0 on error
+ */
+static inline u8
+ieee80211_he_oper_size(const u8 *he_oper_ie)
+{
+ struct ieee80211_he_operation *he_oper = (void *)he_oper_ie;
+ u8 oper_len = sizeof(struct ieee80211_he_operation);
+ u32 he_oper_params;
+
+ /* Make sure the input is not NULL */
+ if (!he_oper_ie)
+ return 0;
+
+ /* Calc required length */
+ he_oper_params = le32_to_cpu(he_oper->he_oper_params);
+ if (he_oper_params & IEEE80211_HE_OPERATION_VHT_OPER_INFO)
+ oper_len += 3;
+ if (he_oper_params & IEEE80211_HE_OPERATION_MULTI_BSSID_AP)
+ oper_len++;
+
+ /* Add the first byte (extension ID) to the total length */
+ oper_len++;
+
+ return oper_len;
+}
+
/* Authentication algorithms */
#define WLAN_AUTH_OPEN 0
#define WLAN_AUTH_SHARED_KEY 1
WLAN_EID_EXT_FILS_WRAPPED_DATA = 8,
WLAN_EID_EXT_FILS_PUBLIC_KEY = 12,
WLAN_EID_EXT_FILS_NONCE = 13,
+ WLAN_EID_EXT_FUTURE_CHAN_GUIDANCE = 14,
+ WLAN_EID_EXT_HE_CAPABILITY = 35,
+ WLAN_EID_EXT_HE_OPERATION = 36,
+ WLAN_EID_EXT_UORA = 37,
+ WLAN_EID_EXT_HE_MU_EDCA = 38,
};
/* Action category code */
long mode_priv[0];
};
+static inline struct team_port *team_port_get_rcu(const struct net_device *dev)
+{
+ return rcu_dereference(dev->rx_handler_data);
+}
+
static inline bool team_port_enabled(struct team_port *port)
{
return port->index != -1;
return port->linkup && team_port_enabled(port);
}
+static inline bool team_port_dev_txable(const struct net_device *port_dev)
+{
+ struct team_port *port;
+ bool txable;
+
+ rcu_read_lock();
+ port = team_port_get_rcu(port_dev);
+ txable = port ? team_port_txable(port) : false;
+ rcu_read_unlock();
+
+ return txable;
+}
+
#ifdef CONFIG_NET_POLL_CONTROLLER
static inline void team_netpoll_send_skb(struct team_port *port,
struct sk_buff *skb)
char __user *user_buffer);
size_t iio_dma_buffer_data_available(struct iio_buffer *buffer);
int iio_dma_buffer_set_bytes_per_datum(struct iio_buffer *buffer, size_t bpd);
-int iio_dma_buffer_set_length(struct iio_buffer *buffer, int length);
+int iio_dma_buffer_set_length(struct iio_buffer *buffer, unsigned int length);
int iio_dma_buffer_request_update(struct iio_buffer *buffer);
int iio_dma_buffer_init(struct iio_dma_buffer_queue *queue,
return axis == ABS_MT_SLOT || input_is_mt_value(axis);
}
-void input_mt_report_slot_state(struct input_dev *dev,
+bool input_mt_report_slot_state(struct input_dev *dev,
unsigned int tool_type, bool active);
void input_mt_report_finger_count(struct input_dev *dev, int count);
#include <linux/spinlock.h>
#include <linux/uidgid.h>
-#include <linux/rhashtable.h>
+#include <linux/rhashtable-types.h>
#include <uapi/linux/ipc.h>
#include <linux/refcount.h>
#include <linux/nsproxy.h>
#include <linux/ns_common.h>
#include <linux/refcount.h>
-#include <linux/rhashtable.h>
+#include <linux/rhashtable-types.h>
struct user_namespace;
* IRQCHIP_SKIP_SET_WAKE: Skip chip.irq_set_wake(), for this irq chip
* IRQCHIP_ONESHOT_SAFE: One shot does not require mask/unmask
* IRQCHIP_EOI_THREADED: Chip requires eoi() on unmask in threaded mode
+ * IRQCHIP_SUPPORTS_LEVEL_MSI Chip can provide two doorbells for Level MSIs
*/
enum {
IRQCHIP_SET_TYPE_MASKED = (1 << 0),
return desc->irq_common_data.handler_data;
}
-static inline struct msi_desc *irq_desc_get_msi_desc(struct irq_desc *desc)
-{
- return desc->irq_common_data.msi_desc;
-}
-
/*
* Architectures call this to let the generic IRQ layer
* handle an interrupt.
* your code. (Extra memory is used for special buffers that are
* allocated when trace_printk() is used.)
*
- * A little optization trick is done here. If there's only one
+ * A little optimization trick is done here. If there's only one
* argument, there's no need to scan the string for printf formats.
* The trace_puts() will suffice. But how can we take advantage of
* using trace_puts() when trace_printk() has only one argument?
__list_cut_position(list, head, entry);
}
+/**
+ * list_cut_before - cut a list into two, before given entry
+ * @list: a new list to add all removed entries
+ * @head: a list with entries
+ * @entry: an entry within head, could be the head itself
+ *
+ * This helper moves the initial part of @head, up to but
+ * excluding @entry, from @head to @list. You should pass
+ * in @entry an element you know is on @head. @list should
+ * be an empty list or a list you do not care about losing
+ * its data.
+ * If @entry == @head, all entries on @head are moved to
+ * @list.
+ */
+static inline void list_cut_before(struct list_head *list,
+ struct list_head *head,
+ struct list_head *entry)
+{
+ if (head->next == entry) {
+ INIT_LIST_HEAD(list);
+ return;
+ }
+ list->next = head->next;
+ list->next->prev = list;
+ list->prev = entry->prev;
+ list->prev->next = list;
+ head->next = entry;
+ entry->prev = head;
+}
+
static inline void __list_splice(const struct list_head *list,
struct list_head *prev,
struct list_head *next)
int arch_get_memory_phys_device(unsigned long start_pfn);
unsigned long memory_block_size_bytes(void);
+int set_memory_block_size_order(unsigned int order);
/* These states are exposed to userspace as text strings in sysfs */
#define MEM_ONLINE (1<<0) /* exposed to userspace */
u32 vf_caps;
bool wol_port[MLX4_MAX_PORTS + 1];
struct mlx4_rate_limit_caps rl_caps;
+ u32 health_buffer_addrs;
};
struct mlx4_buf_list {
u8 n_ports;
};
+struct mlx4_fw_crdump {
+ bool snapshot_enable;
+ struct devlink_region *region_crspace;
+ struct devlink_region *region_fw_health;
+};
+
enum mlx4_pci_status {
MLX4_PCI_STATUS_DISABLED,
MLX4_PCI_STATUS_ENABLED,
u8 interface_state;
struct mutex pci_status_mutex; /* sync pci state */
enum mlx4_pci_status pci_status;
+ struct mlx4_fw_crdump crdump;
};
struct mlx4_dev {
#include <linux/mlx5/driver.h>
+#define MLX5_ESWITCH_MANAGER(mdev) MLX5_CAP_GEN(mdev, eswitch_manager)
+
enum {
SRIOV_NONE,
SRIOV_LEGACY,
u8 vnic_env_queue_counters[0x1];
u8 ets[0x1];
u8 nic_flow_table[0x1];
- u8 eswitch_flow_table[0x1];
+ u8 eswitch_manager[0x1];
u8 device_memory[0x1];
u8 mcam_reg[0x1];
u8 pcam_reg[0x1];
enum fpga_tls_cmds {
CMD_SETUP_STREAM = 0x1001,
CMD_TEARDOWN_STREAM = 0x1002,
+ CMD_RESYNC_RX = 0x1003,
};
#define MLX5_TLS_1_2 (0)
DMI_PRODUCT_VERSION,
DMI_PRODUCT_SERIAL,
DMI_PRODUCT_UUID,
+ DMI_PRODUCT_SKU,
DMI_PRODUCT_FAMILY,
DMI_BOARD_VENDOR,
DMI_BOARD_NAME,
#define __LINUX_MROUTE_BASE_H
#include <linux/netdevice.h>
-#include <linux/rhashtable.h>
+#include <linux/rhashtable-types.h>
#include <linux/spinlock.h>
#include <net/net_namespace.h>
#include <net/sock.h>
atomic_t cache_resolve_queue_len;
bool mroute_do_assert;
bool mroute_do_pim;
+ bool mroute_do_wrvifwhole;
int mroute_reg_vif_num;
};
int (*getname) (struct socket *sock,
struct sockaddr *addr,
int peer);
- __poll_t (*poll_mask) (struct socket *sock, __poll_t events);
__poll_t (*poll) (struct file *file, struct socket *sock,
struct poll_table_struct *wait);
int (*ioctl) (struct socket *sock, unsigned int cmd,
NETIF_F_HW_ESP_TX_CSUM_BIT, /* ESP with TX checksum offload */
NETIF_F_RX_UDP_TUNNEL_PORT_BIT, /* Offload of RX port for UDP tunnels */
NETIF_F_HW_TLS_TX_BIT, /* Hardware TLS TX offload */
+ NETIF_F_HW_TLS_RX_BIT, /* Hardware TLS RX offload */
NETIF_F_GRO_HW_BIT, /* Hardware Generic receive offload */
NETIF_F_HW_TLS_RECORD_BIT, /* Offload TLS record */
#define NETIF_F_HW_TLS_RECORD __NETIF_F(HW_TLS_RECORD)
#define NETIF_F_GSO_UDP_L4 __NETIF_F(GSO_UDP_L4)
#define NETIF_F_HW_TLS_TX __NETIF_F(HW_TLS_TX)
+#define NETIF_F_HW_TLS_RX __NETIF_F(HW_TLS_RX)
#define for_each_netdev_feature(mask_addr, bit) \
for_each_set_bit(bit, (unsigned long *)mask_addr, NETDEV_FEATURE_COUNT)
int __init netdev_boot_setup(char *str);
+struct gro_list {
+ struct list_head list;
+ int count;
+};
+
+/*
+ * size of gro hash buckets, must less than bit number of
+ * napi_struct::gro_bitmask
+ */
+#define GRO_HASH_BUCKETS 8
+
/*
* Structure for NAPI scheduling similar to tasklet but with weighting
*/
unsigned long state;
int weight;
- unsigned int gro_count;
+ unsigned long gro_bitmask;
int (*poll)(struct napi_struct *, int);
#ifdef CONFIG_NETPOLL
int poll_owner;
#endif
struct net_device *dev;
- struct sk_buff *gro_list;
+ struct gro_list gro_hash[GRO_HASH_BUCKETS];
struct sk_buff *skb;
struct hrtimer timer;
struct list_head dev_list;
* (/sys/class/net/DEV/Q/trans_timeout)
*/
unsigned long trans_timeout;
+
+ /* Subordinate device that the queue has been assigned to */
+ struct net_device *sb_dev;
/*
* write-mostly part
*/
*/
struct xps_dev_maps {
struct rcu_head rcu;
- struct xps_map __rcu *cpu_map[0];
+ struct xps_map __rcu *attr_map[0]; /* Either CPUs map or RXQs map */
};
-#define XPS_DEV_MAPS_SIZE(_tcs) (sizeof(struct xps_dev_maps) + \
+
+#define XPS_CPU_DEV_MAPS_SIZE(_tcs) (sizeof(struct xps_dev_maps) + \
(nr_cpu_ids * (_tcs) * sizeof(struct xps_map *)))
+
+#define XPS_RXQ_DEV_MAPS_SIZE(_tcs, _rxqs) (sizeof(struct xps_dev_maps) +\
+ (_rxqs * (_tcs) * sizeof(struct xps_map *)))
+
#endif /* CONFIG_XPS */
#define TC_MAX_QUEUE 16
}
typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
- struct sk_buff *skb);
+ struct sk_buff *skb,
+ struct net_device *sb_dev);
enum tc_setup_type {
TC_SETUP_QDISC_MQPRIO,
TC_SETUP_QDISC_RED,
TC_SETUP_QDISC_PRIO,
TC_SETUP_QDISC_MQ,
+ TC_SETUP_QDISC_ETF,
};
/* These structures hold the attributes of bpf state that are being passed
*/
XDP_SETUP_PROG,
XDP_SETUP_PROG_HW,
- /* Check if a bpf program is set on the device. The callee should
- * set @prog_attached to one of XDP_ATTACHED_* values, note that "true"
- * is equivalent to XDP_ATTACHED_DRV.
- */
XDP_QUERY_PROG,
+ XDP_QUERY_PROG_HW,
/* BPF program for offload callbacks, invoked at program load time. */
BPF_OFFLOAD_VERIFIER_PREP,
BPF_OFFLOAD_TRANSLATE,
struct bpf_prog *prog;
struct netlink_ext_ack *extack;
};
- /* XDP_QUERY_PROG */
+ /* XDP_QUERY_PROG, XDP_QUERY_PROG_HW */
struct {
- u8 prog_attached;
u32 prog_id;
/* flags with which program was installed */
u32 prog_flags;
void (*tls_dev_del)(struct net_device *netdev,
struct tls_context *ctx,
enum tls_offload_ctx_dir direction);
+ void (*tls_dev_resync_rx)(struct net_device *netdev,
+ struct sock *sk, u32 seq, u64 rcd_sn);
};
#endif
* those the driver believes to be appropriate.
*
* u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb,
- * void *accel_priv, select_queue_fallback_t fallback);
+ * struct net_device *sb_dev,
+ * select_queue_fallback_t fallback);
* Called to decide which queue to use when device supports multiple
* transmit queues.
*
netdev_features_t features);
u16 (*ndo_select_queue)(struct net_device *dev,
struct sk_buff *skb,
- void *accel_priv,
+ struct net_device *sb_dev,
select_queue_fallback_t fallback);
void (*ndo_change_rx_flags)(struct net_device *dev,
int flags);
int watchdog_timeo;
#ifdef CONFIG_XPS
- struct xps_dev_maps __rcu *xps_maps;
+ struct xps_dev_maps __rcu *xps_cpus_map;
+ struct xps_dev_maps __rcu *xps_rxqs_map;
#endif
#ifdef CONFIG_NET_CLS_ACT
struct mini_Qdisc __rcu *miniq_egress;
#ifdef CONFIG_DCB
const struct dcbnl_rtnl_ops *dcbnl_ops;
#endif
- u8 num_tc;
+ s16 num_tc;
struct netdev_tc_txq tc_to_txq[TC_MAX_QUEUE];
u8 prio_tc_map[TC_BITMASK + 1];
return dev->num_tc;
}
+void netdev_unbind_sb_channel(struct net_device *dev,
+ struct net_device *sb_dev);
+int netdev_bind_sb_channel_queue(struct net_device *dev,
+ struct net_device *sb_dev,
+ u8 tc, u16 count, u16 offset);
+int netdev_set_sb_channel(struct net_device *dev, u16 channel);
+static inline int netdev_get_sb_channel(struct net_device *dev)
+{
+ return max_t(int, -dev->num_tc, 0);
+}
+
static inline
struct netdev_queue *netdev_get_tx_queue(const struct net_device *dev,
unsigned int index)
struct netdev_queue *netdev_pick_tx(struct net_device *dev,
struct sk_buff *skb,
- void *accel_priv);
+ struct net_device *sb_dev);
/* returns the headroom that the master device needs to take in account
* when forwarding to this dev
return ++NAPI_GRO_CB(skb)->recursion_counter == GRO_RECURSION_LIMIT;
}
-typedef struct sk_buff **(*gro_receive_t)(struct sk_buff **, struct sk_buff *);
-static inline struct sk_buff **call_gro_receive(gro_receive_t cb,
- struct sk_buff **head,
- struct sk_buff *skb)
+typedef struct sk_buff *(*gro_receive_t)(struct list_head *, struct sk_buff *);
+static inline struct sk_buff *call_gro_receive(gro_receive_t cb,
+ struct list_head *head,
+ struct sk_buff *skb)
{
if (unlikely(gro_recursion_inc_test(skb))) {
NAPI_GRO_CB(skb)->flush |= 1;
return cb(head, skb);
}
-typedef struct sk_buff **(*gro_receive_sk_t)(struct sock *, struct sk_buff **,
- struct sk_buff *);
-static inline struct sk_buff **call_gro_receive_sk(gro_receive_sk_t cb,
- struct sock *sk,
- struct sk_buff **head,
- struct sk_buff *skb)
+typedef struct sk_buff *(*gro_receive_sk_t)(struct sock *, struct list_head *,
+ struct sk_buff *);
+static inline struct sk_buff *call_gro_receive_sk(gro_receive_sk_t cb,
+ struct sock *sk,
+ struct list_head *head,
+ struct sk_buff *skb)
{
if (unlikely(gro_recursion_inc_test(skb))) {
NAPI_GRO_CB(skb)->flush |= 1;
struct net_device *,
struct packet_type *,
struct net_device *);
+ void (*list_func) (struct list_head *,
+ struct packet_type *,
+ struct net_device *);
bool (*id_match)(struct packet_type *ptype,
struct sock *sk);
void *af_packet_priv;
struct offload_callbacks {
struct sk_buff *(*gso_segment)(struct sk_buff *skb,
netdev_features_t features);
- struct sk_buff **(*gro_receive)(struct sk_buff **head,
- struct sk_buff *skb);
+ struct sk_buff *(*gro_receive)(struct list_head *head,
+ struct sk_buff *skb);
int (*gro_complete)(struct sk_buff *skb, int nhoff);
};
void dev_close_many(struct list_head *head, bool unlink);
void dev_disable_lro(struct net_device *dev);
int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb);
+u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb,
+ struct net_device *sb_dev,
+ select_queue_fallback_t fallback);
+u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb,
+ struct net_device *sb_dev,
+ select_queue_fallback_t fallback);
int dev_queue_xmit(struct sk_buff *skb);
-int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv);
+int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev);
int dev_direct_xmit(struct sk_buff *skb, u16 queue_id);
int register_netdevice(struct net_device *dev);
void unregister_netdevice_queue(struct net_device *dev, struct list_head *head);
struct net_device *dev_get_by_napi_id(unsigned int napi_id);
int netdev_get_name(struct net *net, char *name, int ifindex);
int dev_restart(struct net_device *dev);
-int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb);
+int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb);
static inline unsigned int skb_gro_offset(const struct sk_buff *skb)
{
}
#ifdef CONFIG_XFRM_OFFLOAD
-static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp, int flush)
+static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff *pp, int flush)
{
if (PTR_ERR(pp) != -EINPROGRESS)
NAPI_GRO_CB(skb)->flush |= flush;
}
+static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb,
+ struct sk_buff *pp,
+ int flush,
+ struct gro_remcsum *grc)
+{
+ if (PTR_ERR(pp) != -EINPROGRESS) {
+ NAPI_GRO_CB(skb)->flush |= flush;
+ skb_gro_remcsum_cleanup(skb, grc);
+ skb->remcsum_offload = 0;
+ }
+}
#else
-static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp, int flush)
+static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff *pp, int flush)
{
NAPI_GRO_CB(skb)->flush |= flush;
}
+static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb,
+ struct sk_buff *pp,
+ int flush,
+ struct gro_remcsum *grc)
+{
+ NAPI_GRO_CB(skb)->flush |= flush;
+ skb_gro_remcsum_cleanup(skb, grc);
+ skb->remcsum_offload = 0;
+}
#endif
static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev,
#ifdef CONFIG_XPS
int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask,
u16 index);
+int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask,
+ u16 index, bool is_rxqs_map);
+
+/**
+ * netif_attr_test_mask - Test a CPU or Rx queue set in a mask
+ * @j: CPU/Rx queue index
+ * @mask: bitmask of all cpus/rx queues
+ * @nr_bits: number of bits in the bitmask
+ *
+ * Test if a CPU or Rx queue index is set in a mask of all CPU/Rx queues.
+ */
+static inline bool netif_attr_test_mask(unsigned long j,
+ const unsigned long *mask,
+ unsigned int nr_bits)
+{
+ cpu_max_bits_warn(j, nr_bits);
+ return test_bit(j, mask);
+}
+
+/**
+ * netif_attr_test_online - Test for online CPU/Rx queue
+ * @j: CPU/Rx queue index
+ * @online_mask: bitmask for CPUs/Rx queues that are online
+ * @nr_bits: number of bits in the bitmask
+ *
+ * Returns true if a CPU/Rx queue is online.
+ */
+static inline bool netif_attr_test_online(unsigned long j,
+ const unsigned long *online_mask,
+ unsigned int nr_bits)
+{
+ cpu_max_bits_warn(j, nr_bits);
+
+ if (online_mask)
+ return test_bit(j, online_mask);
+
+ return (j < nr_bits);
+}
+
+/**
+ * netif_attrmask_next - get the next CPU/Rx queue in a cpu/Rx queues mask
+ * @n: CPU/Rx queue index
+ * @srcp: the cpumask/Rx queue mask pointer
+ * @nr_bits: number of bits in the bitmask
+ *
+ * Returns >= nr_bits if no further CPUs/Rx queues set.
+ */
+static inline unsigned int netif_attrmask_next(int n, const unsigned long *srcp,
+ unsigned int nr_bits)
+{
+ /* -1 is a legal arg here. */
+ if (n != -1)
+ cpu_max_bits_warn(n, nr_bits);
+
+ if (srcp)
+ return find_next_bit(srcp, nr_bits, n + 1);
+
+ return n + 1;
+}
+
+/**
+ * netif_attrmask_next_and - get the next CPU/Rx queue in *src1p & *src2p
+ * @n: CPU/Rx queue index
+ * @src1p: the first CPUs/Rx queues mask pointer
+ * @src2p: the second CPUs/Rx queues mask pointer
+ * @nr_bits: number of bits in the bitmask
+ *
+ * Returns >= nr_bits if no further CPUs/Rx queues set in both.
+ */
+static inline int netif_attrmask_next_and(int n, const unsigned long *src1p,
+ const unsigned long *src2p,
+ unsigned int nr_bits)
+{
+ /* -1 is a legal arg here. */
+ if (n != -1)
+ cpu_max_bits_warn(n, nr_bits);
+
+ if (src1p && src2p)
+ return find_next_and_bit(src1p, src2p, nr_bits, n + 1);
+ else if (src1p)
+ return find_next_bit(src1p, nr_bits, n + 1);
+ else if (src2p)
+ return find_next_bit(src2p, nr_bits, n + 1);
+
+ return n + 1;
+}
#else
static inline int netif_set_xps_queue(struct net_device *dev,
const struct cpumask *mask,
int netif_rx_ni(struct sk_buff *skb);
int netif_receive_skb(struct sk_buff *skb);
int netif_receive_skb_core(struct sk_buff *skb);
+void netif_receive_skb_list(struct list_head *head);
gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb);
void napi_gro_flush(struct napi_struct *napi, bool flush_old);
struct sk_buff *napi_get_frags(struct napi_struct *napi);
typedef int (*bpf_op_t)(struct net_device *dev, struct netdev_bpf *bpf);
int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
int fd, u32 flags);
-void __dev_xdp_query(struct net_device *dev, bpf_op_t xdp_op,
- struct netdev_bpf *xdp);
+u32 __dev_xdp_query(struct net_device *dev, bpf_op_t xdp_op,
+ enum bpf_netdev_command cmd);
int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
int dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
return ret;
}
+static inline void
+NF_HOOK_LIST(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk,
+ struct list_head *head, struct net_device *in, struct net_device *out,
+ int (*okfn)(struct net *, struct sock *, struct sk_buff *))
+{
+ struct sk_buff *skb, *next;
+ struct list_head sublist;
+
+ INIT_LIST_HEAD(&sublist);
+ list_for_each_entry_safe(skb, next, head, list) {
+ list_del(&skb->list);
+ if (nf_hook(pf, hook, net, sk, skb, in, out, okfn) == 1)
+ list_add_tail(&skb->list, &sublist);
+ }
+ /* Put passed packets back on main list */
+ list_splice(&sublist, head);
+}
+
/* Call setsockopt() */
int nf_setsockopt(struct sock *sk, u_int8_t pf, int optval, char __user *opt,
unsigned int len);
return okfn(net, sk, skb);
}
+static inline void
+NF_HOOK_LIST(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk,
+ struct list_head *head, struct net_device *in, struct net_device *out,
+ int (*okfn)(struct net *, struct sock *, struct sk_buff *))
+{
+ /* nothing to do */
+}
+
static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net,
struct sock *sk, struct sk_buff *skb,
struct net_device *indev, struct net_device *outdev,
extern void (*ip_ct_attach)(struct sk_buff *, const struct sk_buff *) __rcu;
void nf_ct_attach(struct sk_buff *, const struct sk_buff *);
+struct nf_conntrack_tuple;
+bool nf_ct_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple,
+ const struct sk_buff *skb);
#else
static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {}
+struct nf_conntrack_tuple;
+static inline bool nf_ct_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple,
+ const struct sk_buff *skb)
+{
+ return false;
+}
#endif
struct nf_conn;
struct nf_ct_hook {
int (*update)(struct net *net, struct sk_buff *skb);
void (*destroy)(struct nf_conntrack *);
+ bool (*get_tuple_skb)(struct nf_conntrack_tuple *,
+ const struct sk_buff *);
};
extern struct nf_ct_hook __rcu *nf_ct_hook;
NFS_IOHDR_EOF,
NFS_IOHDR_REDO,
NFS_IOHDR_STAT,
+ NFS_IOHDR_RESEND_PNFS,
+ NFS_IOHDR_RESEND_MDS,
};
struct nfs_io_completion;
#include <uapi/linux/openvswitch.h>
+#define OVS_CLONE_ATTR_EXEC 0 /* Specify an u32 value. When nonzero,
+ * actions in clone will not change flow
+ * keys. False otherwise.
+ */
+
#endif /* _LINUX_OPENVSWITCH_H */
void phy_stop(struct phy_device *phydev);
int phy_start_aneg(struct phy_device *phydev);
int phy_aneg_done(struct phy_device *phydev);
+int phy_speed_down(struct phy_device *phydev, bool sync);
+int phy_speed_up(struct phy_device *phydev);
int phy_stop_interrupts(struct phy_device *phydev);
int phy_restart_aneg(struct phy_device *phydev);
int of_genpd_parse_idle_states(struct device_node *dn,
struct genpd_power_state **states, int *n);
unsigned int of_genpd_opp_to_performance_state(struct device *dev,
- struct device_node *opp_node);
+ struct device_node *np);
int genpd_dev_pm_attach(struct device *dev);
struct device *genpd_dev_pm_attach_by_id(struct device *dev,
static inline unsigned int
of_genpd_opp_to_performance_state(struct device *dev,
- struct device_node *opp_node)
+ struct device_node *np)
{
- return -ENODEV;
+ return 0;
}
static inline int genpd_dev_pm_attach(struct device *dev)
pt->_key = ~(__poll_t)0; /* all events enabled */
}
-static inline bool file_has_poll_mask(struct file *file)
+static inline bool file_can_poll(struct file *file)
{
- return file->f_op->get_poll_head && file->f_op->poll_mask;
+ return file->f_op->poll;
}
-static inline bool file_can_poll(struct file *file)
+static inline __poll_t vfs_poll(struct file *file, struct poll_table_struct *pt)
{
- return file->f_op->poll || file_has_poll_mask(file);
+ if (unlikely(!file->f_op->poll))
+ return DEFAULT_POLLMASK;
+ return file->f_op->poll(file, pt);
}
-__poll_t vfs_poll(struct file *file, struct poll_table_struct *pt);
-
struct poll_table_entry {
struct file *filp;
__poll_t key;
u8 sh1, sh2;
};
+/* "reciprocal_value" and "reciprocal_divide" together implement the basic
+ * version of the algorithm described in Figure 4.1 of the paper.
+ */
struct reciprocal_value reciprocal_value(u32 d);
static inline u32 reciprocal_divide(u32 a, struct reciprocal_value R)
return (t + ((a - t) >> R.sh1)) >> R.sh2;
}
+struct reciprocal_value_adv {
+ u32 m;
+ u8 sh, exp;
+ bool is_wide_m;
+};
+
+/* "reciprocal_value_adv" implements the advanced version of the algorithm
+ * described in Figure 4.2 of the paper except when "divisor > (1U << 31)" whose
+ * ceil(log2(d)) result will be 32 which then requires u128 divide on host. The
+ * exception case could be easily handled before calling "reciprocal_value_adv".
+ *
+ * The advanced version requires more complex calculation to get the reciprocal
+ * multiplier and other control variables, but then could reduce the required
+ * emulation operations.
+ *
+ * It makes no sense to use this advanced version for host divide emulation,
+ * those extra complexities for calculating multiplier etc could completely
+ * waive our saving on emulation operations.
+ *
+ * However, it makes sense to use it for JIT divide code generation for which
+ * we are willing to trade performance of JITed code with that of host. As shown
+ * by the following pseudo code, the required emulation operations could go down
+ * from 6 (the basic version) to 3 or 4.
+ *
+ * To use the result of "reciprocal_value_adv", suppose we want to calculate
+ * n/d, the pseudo C code will be:
+ *
+ * struct reciprocal_value_adv rvalue;
+ * u8 pre_shift, exp;
+ *
+ * // handle exception case.
+ * if (d >= (1U << 31)) {
+ * result = n >= d;
+ * return;
+ * }
+ *
+ * rvalue = reciprocal_value_adv(d, 32)
+ * exp = rvalue.exp;
+ * if (rvalue.is_wide_m && !(d & 1)) {
+ * // floor(log2(d & (2^32 -d)))
+ * pre_shift = fls(d & -d) - 1;
+ * rvalue = reciprocal_value_adv(d >> pre_shift, 32 - pre_shift);
+ * } else {
+ * pre_shift = 0;
+ * }
+ *
+ * // code generation starts.
+ * if (imm == 1U << exp) {
+ * result = n >> exp;
+ * } else if (rvalue.is_wide_m) {
+ * // pre_shift must be zero when reached here.
+ * t = (n * rvalue.m) >> 32;
+ * result = n - t;
+ * result >>= 1;
+ * result += t;
+ * result >>= rvalue.sh - 1;
+ * } else {
+ * if (pre_shift)
+ * result = n >> pre_shift;
+ * result = ((u64)result * rvalue.m) >> 32;
+ * result >>= rvalue.sh;
+ * }
+ */
+struct reciprocal_value_adv reciprocal_value_adv(u32 d, u8 prec);
+
#endif /* _LINUX_RECIPROCAL_DIV_H */
extern __must_check bool refcount_dec_not_one(refcount_t *r);
extern __must_check bool refcount_dec_and_mutex_lock(refcount_t *r, struct mutex *lock);
extern __must_check bool refcount_dec_and_lock(refcount_t *r, spinlock_t *lock);
-
+extern __must_check bool refcount_dec_and_lock_irqsave(refcount_t *r,
+ spinlock_t *lock,
+ unsigned long *flags);
#endif /* _LINUX_REFCOUNT_H */
#if defined(CONFIG_RFKILL) || defined(CONFIG_RFKILL_MODULE)
/**
- * rfkill_alloc - allocate rfkill structure
+ * rfkill_alloc - Allocate rfkill structure
* @name: name of the struct -- the string is not copied internally
* @parent: device that has rf switch on it
* @type: type of the switch (RFKILL_TYPE_*)
/**
* rfkill_resume_polling(struct rfkill *rfkill)
*
- * Pause polling -- say transmitter is off for other reasons.
+ * Resume polling
* NOTE: not necessary for suspend/resume -- in that case the
* core stops polling anyway
*/
void rfkill_unregister(struct rfkill *rfkill);
/**
- * rfkill_destroy - free rfkill structure
+ * rfkill_destroy - Free rfkill structure
* @rfkill: rfkill structure to be destroyed
*
* Destroys the rfkill structure.
/**
* rfkill_set_hw_state - Set the internal rfkill hardware block state
* @rfkill: pointer to the rfkill class to modify.
- * @state: the current hardware block state to set
+ * @blocked: the current hardware block state to set
*
* rfkill drivers that get events when the hard-blocked state changes
* use this function to notify the rfkill core (and through that also
/**
* rfkill_set_sw_state - Set the internal rfkill software block state
* @rfkill: pointer to the rfkill class to modify.
- * @state: the current software block state to set
+ * @blocked: the current software block state to set
*
* rfkill drivers that get events when the soft-blocked state changes
* (yes, some platforms directly act on input but allow changing again)
/**
* rfkill_init_sw_state - Initialize persistent software block state
* @rfkill: pointer to the rfkill class to modify.
- * @state: the current software block state to set
+ * @blocked: the current software block state to set
*
* rfkill drivers that preserve their software block state over power off
* use this function to notify the rfkill core (and through that also
void rfkill_set_states(struct rfkill *rfkill, bool sw, bool hw);
/**
- * rfkill_blocked - query rfkill block
+ * rfkill_blocked - Query rfkill block state
*
* @rfkill: rfkill struct to query
*/
bool rfkill_blocked(struct rfkill *rfkill);
/**
- * rfkill_find_type - Helpper for finding rfkill type by name
+ * rfkill_find_type - Helper for finding rfkill type by name
* @name: the name of the type
*
- * Returns enum rfkill_type that conrresponds the name.
+ * Returns enum rfkill_type that corresponds to the name.
*/
enum rfkill_type rfkill_find_type(const char *name);
const char *rfkill_get_led_trigger_name(struct rfkill *rfkill);
/**
- * rfkill_set_led_trigger_name -- set the LED trigger name
+ * rfkill_set_led_trigger_name - Set the LED trigger name
* @rfkill: rfkill struct
* @name: LED trigger name
*
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Resizable, Scalable, Concurrent Hash Table
+ *
+ * Simple structures that might be needed in include
+ * files.
+ */
+
+#ifndef _LINUX_RHASHTABLE_TYPES_H
+#define _LINUX_RHASHTABLE_TYPES_H
+
+#include <linux/atomic.h>
+#include <linux/compiler.h>
+#include <linux/mutex.h>
+#include <linux/workqueue.h>
+
+struct rhash_head {
+ struct rhash_head __rcu *next;
+};
+
+struct rhlist_head {
+ struct rhash_head rhead;
+ struct rhlist_head __rcu *next;
+};
+
+struct bucket_table;
+
+/**
+ * struct rhashtable_compare_arg - Key for the function rhashtable_compare
+ * @ht: Hash table
+ * @key: Key to compare against
+ */
+struct rhashtable_compare_arg {
+ struct rhashtable *ht;
+ const void *key;
+};
+
+typedef u32 (*rht_hashfn_t)(const void *data, u32 len, u32 seed);
+typedef u32 (*rht_obj_hashfn_t)(const void *data, u32 len, u32 seed);
+typedef int (*rht_obj_cmpfn_t)(struct rhashtable_compare_arg *arg,
+ const void *obj);
+
+/**
+ * struct rhashtable_params - Hash table construction parameters
+ * @nelem_hint: Hint on number of elements, should be 75% of desired size
+ * @key_len: Length of key
+ * @key_offset: Offset of key in struct to be hashed
+ * @head_offset: Offset of rhash_head in struct to be hashed
+ * @max_size: Maximum size while expanding
+ * @min_size: Minimum size while shrinking
+ * @locks_mul: Number of bucket locks to allocate per cpu (default: 32)
+ * @automatic_shrinking: Enable automatic shrinking of tables
+ * @hashfn: Hash function (default: jhash2 if !(key_len % 4), or jhash)
+ * @obj_hashfn: Function to hash object
+ * @obj_cmpfn: Function to compare key with object
+ */
+struct rhashtable_params {
+ u16 nelem_hint;
+ u16 key_len;
+ u16 key_offset;
+ u16 head_offset;
+ unsigned int max_size;
+ u16 min_size;
+ bool automatic_shrinking;
+ u8 locks_mul;
+ rht_hashfn_t hashfn;
+ rht_obj_hashfn_t obj_hashfn;
+ rht_obj_cmpfn_t obj_cmpfn;
+};
+
+/**
+ * struct rhashtable - Hash table handle
+ * @tbl: Bucket table
+ * @key_len: Key length for hashfn
+ * @max_elems: Maximum number of elements in table
+ * @p: Configuration parameters
+ * @rhlist: True if this is an rhltable
+ * @run_work: Deferred worker to expand/shrink asynchronously
+ * @mutex: Mutex to protect current/future table swapping
+ * @lock: Spin lock to protect walker list
+ * @nelems: Number of elements in table
+ */
+struct rhashtable {
+ struct bucket_table __rcu *tbl;
+ unsigned int key_len;
+ unsigned int max_elems;
+ struct rhashtable_params p;
+ bool rhlist;
+ struct work_struct run_work;
+ struct mutex mutex;
+ spinlock_t lock;
+ atomic_t nelems;
+};
+
+/**
+ * struct rhltable - Hash table with duplicate objects in a list
+ * @ht: Underlying rhtable
+ */
+struct rhltable {
+ struct rhashtable ht;
+};
+
+/**
+ * struct rhashtable_walker - Hash table walker
+ * @list: List entry on list of walkers
+ * @tbl: The table that we were walking over
+ */
+struct rhashtable_walker {
+ struct list_head list;
+ struct bucket_table *tbl;
+};
+
+/**
+ * struct rhashtable_iter - Hash table iterator
+ * @ht: Table to iterate through
+ * @p: Current pointer
+ * @list: Current hash list pointer
+ * @walker: Associated rhashtable walker
+ * @slot: Current slot
+ * @skip: Number of entries to skip in slot
+ */
+struct rhashtable_iter {
+ struct rhashtable *ht;
+ struct rhash_head *p;
+ struct rhlist_head *list;
+ struct rhashtable_walker walker;
+ unsigned int slot;
+ unsigned int skip;
+ bool end_of_table;
+};
+
+int rhashtable_init(struct rhashtable *ht,
+ const struct rhashtable_params *params);
+int rhltable_init(struct rhltable *hlt,
+ const struct rhashtable_params *params);
+
+#endif /* _LINUX_RHASHTABLE_TYPES_H */
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Resizable, Scalable, Concurrent Hash Table
*
#ifndef _LINUX_RHASHTABLE_H
#define _LINUX_RHASHTABLE_H
-#include <linux/atomic.h>
-#include <linux/compiler.h>
#include <linux/err.h>
#include <linux/errno.h>
#include <linux/jhash.h>
#include <linux/list_nulls.h>
#include <linux/workqueue.h>
-#include <linux/mutex.h>
#include <linux/rculist.h>
+#include <linux/rhashtable-types.h>
/*
* The end of the chain is marked with a special nulls marks which has
- * the following format:
- *
- * +-------+-----------------------------------------------------+-+
- * | Base | Hash |1|
- * +-------+-----------------------------------------------------+-+
- *
- * Base (4 bits) : Reserved to distinguish between multiple tables.
- * Specified via &struct rhashtable_params.nulls_base.
- * Hash (27 bits): Full hash (unmasked) of first element added to bucket
- * 1 (1 bit) : Nulls marker (always set)
- *
- * The remaining bits of the next pointer remain unused for now.
+ * the least significant bit set.
*/
-#define RHT_BASE_BITS 4
-#define RHT_HASH_BITS 27
-#define RHT_BASE_SHIFT RHT_HASH_BITS
-
-/* Base bits plus 1 bit for nulls marker */
-#define RHT_HASH_RESERVED_SPACE (RHT_BASE_BITS + 1)
/* Maximum chain length before rehash
*
*/
#define RHT_ELASTICITY 16u
-struct rhash_head {
- struct rhash_head __rcu *next;
-};
-
-struct rhlist_head {
- struct rhash_head rhead;
- struct rhlist_head __rcu *next;
-};
-
/**
* struct bucket_table - Table of hash buckets
* @size: Number of hash buckets
struct rhash_head __rcu *buckets[] ____cacheline_aligned_in_smp;
};
-/**
- * struct rhashtable_compare_arg - Key for the function rhashtable_compare
- * @ht: Hash table
- * @key: Key to compare against
- */
-struct rhashtable_compare_arg {
- struct rhashtable *ht;
- const void *key;
-};
-
-typedef u32 (*rht_hashfn_t)(const void *data, u32 len, u32 seed);
-typedef u32 (*rht_obj_hashfn_t)(const void *data, u32 len, u32 seed);
-typedef int (*rht_obj_cmpfn_t)(struct rhashtable_compare_arg *arg,
- const void *obj);
-
-struct rhashtable;
-
-/**
- * struct rhashtable_params - Hash table construction parameters
- * @nelem_hint: Hint on number of elements, should be 75% of desired size
- * @key_len: Length of key
- * @key_offset: Offset of key in struct to be hashed
- * @head_offset: Offset of rhash_head in struct to be hashed
- * @max_size: Maximum size while expanding
- * @min_size: Minimum size while shrinking
- * @locks_mul: Number of bucket locks to allocate per cpu (default: 32)
- * @automatic_shrinking: Enable automatic shrinking of tables
- * @nulls_base: Base value to generate nulls marker
- * @hashfn: Hash function (default: jhash2 if !(key_len % 4), or jhash)
- * @obj_hashfn: Function to hash object
- * @obj_cmpfn: Function to compare key with object
- */
-struct rhashtable_params {
- u16 nelem_hint;
- u16 key_len;
- u16 key_offset;
- u16 head_offset;
- unsigned int max_size;
- u16 min_size;
- bool automatic_shrinking;
- u8 locks_mul;
- u32 nulls_base;
- rht_hashfn_t hashfn;
- rht_obj_hashfn_t obj_hashfn;
- rht_obj_cmpfn_t obj_cmpfn;
-};
-
-/**
- * struct rhashtable - Hash table handle
- * @tbl: Bucket table
- * @key_len: Key length for hashfn
- * @max_elems: Maximum number of elements in table
- * @p: Configuration parameters
- * @rhlist: True if this is an rhltable
- * @run_work: Deferred worker to expand/shrink asynchronously
- * @mutex: Mutex to protect current/future table swapping
- * @lock: Spin lock to protect walker list
- * @nelems: Number of elements in table
- */
-struct rhashtable {
- struct bucket_table __rcu *tbl;
- unsigned int key_len;
- unsigned int max_elems;
- struct rhashtable_params p;
- bool rhlist;
- struct work_struct run_work;
- struct mutex mutex;
- spinlock_t lock;
- atomic_t nelems;
-};
-
-/**
- * struct rhltable - Hash table with duplicate objects in a list
- * @ht: Underlying rhtable
- */
-struct rhltable {
- struct rhashtable ht;
-};
-
-/**
- * struct rhashtable_walker - Hash table walker
- * @list: List entry on list of walkers
- * @tbl: The table that we were walking over
- */
-struct rhashtable_walker {
- struct list_head list;
- struct bucket_table *tbl;
-};
-
-/**
- * struct rhashtable_iter - Hash table iterator
- * @ht: Table to iterate through
- * @p: Current pointer
- * @list: Current hash list pointer
- * @walker: Associated rhashtable walker
- * @slot: Current slot
- * @skip: Number of entries to skip in slot
- */
-struct rhashtable_iter {
- struct rhashtable *ht;
- struct rhash_head *p;
- struct rhlist_head *list;
- struct rhashtable_walker walker;
- unsigned int slot;
- unsigned int skip;
- bool end_of_table;
-};
-
-static inline unsigned long rht_marker(const struct rhashtable *ht, u32 hash)
-{
- return NULLS_MARKER(ht->p.nulls_base + hash);
-}
-
-#define INIT_RHT_NULLS_HEAD(ptr, ht, hash) \
- ((ptr) = (typeof(ptr)) rht_marker(ht, hash))
+#define INIT_RHT_NULLS_HEAD(ptr) \
+ ((ptr) = (typeof(ptr)) NULLS_MARKER(0))
static inline bool rht_is_a_nulls(const struct rhash_head *ptr)
{
return ((unsigned long) ptr & 1);
}
-static inline unsigned long rht_get_nulls_value(const struct rhash_head *ptr)
-{
- return ((unsigned long) ptr) >> 1;
-}
-
static inline void *rht_obj(const struct rhashtable *ht,
const struct rhash_head *he)
{
static inline unsigned int rht_bucket_index(const struct bucket_table *tbl,
unsigned int hash)
{
- return (hash >> RHT_HASH_RESERVED_SPACE) & (tbl->size - 1);
+ return hash & (tbl->size - 1);
}
static inline unsigned int rht_key_get_hash(struct rhashtable *ht,
}
#endif /* CONFIG_PROVE_LOCKING */
-int rhashtable_init(struct rhashtable *ht,
- const struct rhashtable_params *params);
-int rhltable_init(struct rhltable *hlt,
- const struct rhashtable_params *params);
-
void *rhashtable_insert_slow(struct rhashtable *ht, const void *key,
struct rhash_head *obj);
lock = rht_bucket_lock(tbl, hash);
spin_lock_bh(lock);
- if (unlikely(rht_dereference_bucket(tbl->future_tbl, tbl, hash))) {
+ if (unlikely(rcu_access_pointer(tbl->future_tbl))) {
slow_path:
spin_unlock_bh(lock);
rcu_read_unlock();
struct mutex irq_mutex;
struct input_dev *input;
+ struct irq_domain *irqdomain;
+
u8 pdt_props;
u8 num_rx_electrodes;
#include <asm/io.h>
struct scatterlist {
-#ifdef CONFIG_DEBUG_SG
- unsigned long sg_magic;
-#endif
unsigned long page_link;
unsigned int offset;
unsigned int length;
*
*/
-#define SG_MAGIC 0x87654321
#define SG_CHAIN 0x01UL
#define SG_END 0x02UL
*/
BUG_ON((unsigned long) page & (SG_CHAIN | SG_END));
#ifdef CONFIG_DEBUG_SG
- BUG_ON(sg->sg_magic != SG_MAGIC);
BUG_ON(sg_is_chain(sg));
#endif
sg->page_link = page_link | (unsigned long) page;
static inline struct page *sg_page(struct scatterlist *sg)
{
#ifdef CONFIG_DEBUG_SG
- BUG_ON(sg->sg_magic != SG_MAGIC);
BUG_ON(sg_is_chain(sg));
#endif
return (struct page *)((sg)->page_link & ~(SG_CHAIN | SG_END));
**/
static inline void sg_mark_end(struct scatterlist *sg)
{
-#ifdef CONFIG_DEBUG_SG
- BUG_ON(sg->sg_magic != SG_MAGIC);
-#endif
/*
* Set termination bit, clear potential chain bit
*/
**/
static inline void sg_unmark_end(struct scatterlist *sg)
{
-#ifdef CONFIG_DEBUG_SG
- BUG_ON(sg->sg_magic != SG_MAGIC);
-#endif
sg->page_link &= ~SG_END;
}
static inline void sg_init_marker(struct scatterlist *sgl,
unsigned int nents)
{
-#ifdef CONFIG_DEBUG_SG
- unsigned int i;
-
- for (i = 0; i < nents; i++)
- sgl[i].sg_magic = SG_MAGIC;
-#endif
sg_mark_end(&sgl[nents - 1]);
}
set_tsk_thread_flag(t, TIF_NOTIFY_RESUME);
}
-void __rseq_handle_notify_resume(struct pt_regs *regs);
+void __rseq_handle_notify_resume(struct ksignal *sig, struct pt_regs *regs);
-static inline void rseq_handle_notify_resume(struct pt_regs *regs)
+static inline void rseq_handle_notify_resume(struct ksignal *ksig,
+ struct pt_regs *regs)
{
if (current->rseq)
- __rseq_handle_notify_resume(regs);
+ __rseq_handle_notify_resume(ksig, regs);
}
-static inline void rseq_signal_deliver(struct pt_regs *regs)
+static inline void rseq_signal_deliver(struct ksignal *ksig,
+ struct pt_regs *regs)
{
preempt_disable();
__set_bit(RSEQ_EVENT_SIGNAL_BIT, ¤t->rseq_event_mask);
preempt_enable();
- rseq_handle_notify_resume(regs);
+ rseq_handle_notify_resume(ksig, regs);
}
/* rseq_preempt() requires preemption to be disabled. */
/*
* If parent process has a registered restartable sequences area, the
- * child inherits. Only applies when forking a process, not a thread. In
- * case a parent fork() in the middle of a restartable sequence, set the
- * resume notifier to force the child to retry.
+ * child inherits. Only applies when forking a process, not a thread.
*/
static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags)
{
t->rseq_len = current->rseq_len;
t->rseq_sig = current->rseq_sig;
t->rseq_event_mask = current->rseq_event_mask;
- rseq_preempt(t);
}
}
static inline void rseq_set_notify_resume(struct task_struct *t)
{
}
-static inline void rseq_handle_notify_resume(struct pt_regs *regs)
+static inline void rseq_handle_notify_resume(struct ksignal *ksig,
+ struct pt_regs *regs)
{
}
-static inline void rseq_signal_deliver(struct pt_regs *regs)
+static inline void rseq_signal_deliver(struct ksignal *ksig,
+ struct pt_regs *regs)
{
}
static inline void rseq_preempt(struct task_struct *t)
__be32 receivers_next_tsn;
};
+enum {
+ SCTP_DSCP_SET_MASK = 0x1,
+ SCTP_DSCP_VAL_MASK = 0xfc,
+ SCTP_FLOWLABEL_SET_MASK = 0x100000,
+ SCTP_FLOWLABEL_VAL_MASK = 0xfffff
+};
+
#endif /* __LINUX_SCTP_H__ */
struct sfp_eeprom_ext ext;
} __packed;
+struct sfp_diag {
+ __be16 temp_high_alarm;
+ __be16 temp_low_alarm;
+ __be16 temp_high_warn;
+ __be16 temp_low_warn;
+ __be16 volt_high_alarm;
+ __be16 volt_low_alarm;
+ __be16 volt_high_warn;
+ __be16 volt_low_warn;
+ __be16 bias_high_alarm;
+ __be16 bias_low_alarm;
+ __be16 bias_high_warn;
+ __be16 bias_low_warn;
+ __be16 txpwr_high_alarm;
+ __be16 txpwr_low_alarm;
+ __be16 txpwr_high_warn;
+ __be16 txpwr_low_warn;
+ __be16 rxpwr_high_alarm;
+ __be16 rxpwr_low_alarm;
+ __be16 rxpwr_high_warn;
+ __be16 rxpwr_low_warn;
+ __be16 laser_temp_high_alarm;
+ __be16 laser_temp_low_alarm;
+ __be16 laser_temp_high_warn;
+ __be16 laser_temp_low_warn;
+ __be16 tec_cur_high_alarm;
+ __be16 tec_cur_low_alarm;
+ __be16 tec_cur_high_warn;
+ __be16 tec_cur_low_warn;
+ __be32 cal_rxpwr4;
+ __be32 cal_rxpwr3;
+ __be32 cal_rxpwr2;
+ __be32 cal_rxpwr1;
+ __be32 cal_rxpwr0;
+ __be16 cal_txi_slope;
+ __be16 cal_txi_offset;
+ __be16 cal_txpwr_slope;
+ __be16 cal_txpwr_offset;
+ __be16 cal_t_slope;
+ __be16 cal_t_offset;
+ __be16 cal_v_slope;
+ __be16 cal_v_offset;
+} __packed;
+
/* SFP EEPROM registers */
enum {
SFP_PHYS_ID = 0x00,
SFP_TEC_CUR = 0x6c,
SFP_STATUS = 0x6e,
- SFP_ALARM = 0x70,
+ SFP_ALARM0 = 0x70,
+ SFP_ALARM0_TEMP_HIGH = BIT(7),
+ SFP_ALARM0_TEMP_LOW = BIT(6),
+ SFP_ALARM0_VCC_HIGH = BIT(5),
+ SFP_ALARM0_VCC_LOW = BIT(4),
+ SFP_ALARM0_TX_BIAS_HIGH = BIT(3),
+ SFP_ALARM0_TX_BIAS_LOW = BIT(2),
+ SFP_ALARM0_TXPWR_HIGH = BIT(1),
+ SFP_ALARM0_TXPWR_LOW = BIT(0),
+
+ SFP_ALARM1 = 0x71,
+ SFP_ALARM1_RXPWR_HIGH = BIT(7),
+ SFP_ALARM1_RXPWR_LOW = BIT(6),
+
+ SFP_WARN0 = 0x74,
+ SFP_WARN0_TEMP_HIGH = BIT(7),
+ SFP_WARN0_TEMP_LOW = BIT(6),
+ SFP_WARN0_VCC_HIGH = BIT(5),
+ SFP_WARN0_VCC_LOW = BIT(4),
+ SFP_WARN0_TX_BIAS_HIGH = BIT(3),
+ SFP_WARN0_TX_BIAS_LOW = BIT(2),
+ SFP_WARN0_TXPWR_HIGH = BIT(1),
+ SFP_WARN0_TXPWR_LOW = BIT(0),
+
+ SFP_WARN1 = 0x75,
+ SFP_WARN1_RXPWR_HIGH = BIT(7),
+ SFP_WARN1_RXPWR_LOW = BIT(6),
SFP_EXT_STATUS = 0x76,
SFP_VSL = 0x78,
* @hash: the packet hash
* @queue_mapping: Queue mapping for multiqueue devices
* @xmit_more: More SKBs are pending for this queue
+ * @decrypted: Decrypted SKB
* @ndisc_nodetype: router type (from link layer)
* @ooo_okay: allow the mapping of a socket to a queue to be changed
* @l4_hash: indicate hash is a canonical 4-tuple hash over transport
int ip_defrag_offset;
};
};
- struct rb_node rbnode; /* used in netem & tcp stack */
+ struct rb_node rbnode; /* used in netem & tcp stack */
+ struct list_head list;
};
struct sock *sk;
peeked:1,
head_frag:1,
xmit_more:1,
- __unused:1; /* one bit hole */
+#ifdef CONFIG_TLS_DEVICE
+ decrypted:1;
+#else
+ __unused:1;
+#endif
/* fields enclosed in headers_start/headers_end are copied
* using a single memcpy() in __copy_skb_header()
int *peeked, int *off, int *err);
struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, int noblock,
int *err);
-__poll_t datagram_poll_mask(struct socket *sock, __poll_t events);
+__poll_t datagram_poll(struct file *file, struct socket *sock,
+ struct poll_table_struct *wait);
int skb_copy_datagram_iter(const struct sk_buff *from, int offset,
struct iov_iter *to, int size);
static inline int skb_copy_datagram_msg(const struct sk_buff *from, int offset,
#ifdef CONFIG_SYSFS
#define SLAB_SUPPORTS_SYSFS
+void sysfs_slab_unlink(struct kmem_cache *);
void sysfs_slab_release(struct kmem_cache *);
#else
+static inline void sysfs_slab_unlink(struct kmem_cache *s)
+{
+}
static inline void sysfs_slab_release(struct kmem_cache *s)
{
}
#define atomic_dec_and_lock(atomic, lock) \
__cond_lock(lock, _atomic_dec_and_lock(atomic, lock))
+extern int _atomic_dec_and_lock_irqsave(atomic_t *atomic, spinlock_t *lock,
+ unsigned long *flags);
+#define atomic_dec_and_lock_irqsave(atomic, lock, flags) \
+ __cond_lock(lock, _atomic_dec_and_lock_irqsave(atomic, lock, &(flags)))
+
int alloc_bucket_spinlocks(spinlock_t **locks, unsigned int *lock_mask,
size_t max_size, unsigned int cpu_mult,
gfp_t gfp);
*/
#ifndef __SYSCALL_DEFINEx
#define __SYSCALL_DEFINEx(x, name, ...) \
+ __diag_push(); \
+ __diag_ignore(GCC, 8, "-Wattribute-alias", \
+ "Type aliasing is used to sanitize syscall arguments");\
asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) \
__attribute__((alias(__stringify(__se_sys##name)))); \
ALLOW_ERROR_INJECTION(sys##name, ERRNO); \
__PROTECT(x, ret,__MAP(x,__SC_ARGS,__VA_ARGS__)); \
return ret; \
} \
+ __diag_pop(); \
static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))
#endif /* __SYSCALL_DEFINEx */
struct tcp_options_received {
/* PAWS/RTTM data */
- long ts_recent_stamp;/* Time we stored ts_recent (for aging) */
+ int ts_recent_stamp;/* Time we stored ts_recent (for aging) */
u32 ts_recent; /* Time stamp to echo next */
u32 rcv_tsval; /* Time stamp value */
u32 rcv_tsecr; /* Time stamp echo reply */
#endif
/* Receiver side RTT estimation */
+ u32 rcv_rtt_last_tsecr;
struct {
u32 rtt_us;
u32 seq;
/* The time we sent the last out-of-window ACK: */
u32 tw_last_oow_ack_time;
- long tw_ts_recent_stamp;
+ int tw_ts_recent_stamp;
#ifdef CONFIG_TCP_MD5SIG
struct tcp_md5sig_key *tw_md5_key;
#endif
void (*encap_destroy)(struct sock *sk);
/* GRO functions for UDP socket */
- struct sk_buff ** (*gro_receive)(struct sock *sk,
- struct sk_buff **head,
+ struct sk_buff * (*gro_receive)(struct sock *sk,
+ struct list_head *head,
struct sk_buff *skb);
int (*gro_complete)(struct sock *sk,
struct sk_buff *skb,
* Public action API for classifiers/qdiscs
*/
+#include <linux/refcount.h>
#include <net/sch_generic.h>
#include <net/pkt_sched.h>
#include <net/net_namespace.h>
struct tcf_idrinfo *idrinfo;
u32 tcfa_index;
- int tcfa_refcnt;
- int tcfa_bindcnt;
+ refcount_t tcfa_refcnt;
+ atomic_t tcfa_bindcnt;
u32 tcfa_capab;
int tcfa_action;
struct tcf_t tcfa_tm;
spinlock_t tcfa_lock;
struct gnet_stats_basic_cpu __percpu *cpu_bstats;
struct gnet_stats_queue __percpu *cpu_qstats;
- struct tc_cookie *act_cookie;
+ struct tc_cookie __rcu *act_cookie;
struct tcf_chain *goto_chain;
};
#define tcf_index common.tcfa_index
struct netlink_ext_ack *extack);
int (*init)(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **act, int ovr,
- int bind, struct netlink_ext_ack *extack);
+ int bind, bool rtnl_held,
+ struct netlink_ext_ack *extack);
int (*walk)(struct net *, struct sk_buff *,
struct netlink_callback *, int,
const struct tc_action_ops *,
void (*stats_update)(struct tc_action *, u64, u32, u64);
size_t (*get_fill_size)(const struct tc_action *act);
struct net_device *(*get_dev)(const struct tc_action *a);
+ int (*delete)(struct net *net, u32 index);
};
struct tc_action_net {
int bind, bool cpustats);
void tcf_idr_insert(struct tc_action_net *tn, struct tc_action *a);
+void tcf_idr_cleanup(struct tc_action_net *tn, u32 index);
+int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index,
+ struct tc_action **a, int bind);
+int tcf_idr_delete_index(struct tc_action_net *tn, u32 index);
int __tcf_idr_release(struct tc_action *a, bool bind, bool strict);
static inline int tcf_idr_release(struct tc_action *a, bool bind)
int tcf_register_action(struct tc_action_ops *a, struct pernet_operations *ops);
int tcf_unregister_action(struct tc_action_ops *a,
struct pernet_operations *ops);
-int tcf_action_destroy(struct list_head *actions, int bind);
+int tcf_action_destroy(struct tc_action *actions[], int bind);
int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions,
int nr_actions, struct tcf_result *res);
int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
struct nlattr *est, char *name, int ovr, int bind,
- struct list_head *actions, size_t *attr_size,
- struct netlink_ext_ack *extack);
+ struct tc_action *actions[], size_t *attr_size,
+ bool rtnl_held, struct netlink_ext_ack *extack);
struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
struct nlattr *nla, struct nlattr *est,
char *name, int ovr, int bind,
+ bool rtnl_held,
struct netlink_ext_ack *extack);
-int tcf_action_dump(struct sk_buff *skb, struct list_head *, int, int);
+int tcf_action_dump(struct sk_buff *skb, struct tc_action *actions[], int bind,
+ int ref);
int tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int, int);
int tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int, int);
int tcf_action_copy_stats(struct sk_buff *, struct tc_action *, int);
#endif
}
-typedef int tc_setup_cb_t(enum tc_setup_type type,
- void *type_data, void *cb_priv);
-
#ifdef CONFIG_NET_CLS_ACT
int tc_setup_cb_egdev_register(const struct net_device *dev,
tc_setup_cb_t *cb, void *cb_priv);
int flags);
int bt_sock_stream_recvmsg(struct socket *sock, struct msghdr *msg,
size_t len, int flags);
-__poll_t bt_sock_poll_mask(struct socket *sock, __poll_t events);
+__poll_t bt_sock_poll(struct file *file, struct socket *sock, poll_table *wait);
int bt_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
int bt_sock_wait_state(struct sock *sk, int state, unsigned long timeo);
int bt_sock_wait_ready(struct sock *sk, unsigned long flags);
bond_is_active_slave(slave);
}
+static inline bool bond_is_active_slave_dev(const struct net_device *slave_dev)
+{
+ struct slave *slave;
+ bool active;
+
+ rcu_read_lock();
+ slave = bond_slave_get_rcu(slave_dev);
+ active = bond_is_active_slave(slave);
+ rcu_read_unlock();
+
+ return active;
+}
+
static inline void bond_hw_addr_copy(u8 *dst, const u8 *src, unsigned int len)
{
if (len == ETH_ALEN) {
#ifdef CONFIG_NET_RX_BUSY_POLL
sk->sk_napi_id = skb->napi_id;
#endif
+ sk_rx_queue_set(sk, skb);
}
/* variant used for unconnected sockets */
struct ieee80211_vht_mcs_info vht_mcs;
};
+#define IEEE80211_HE_PPE_THRES_MAX_LEN 25
+
+/**
+ * struct ieee80211_sta_he_cap - STA's HE capabilities
+ *
+ * This structure describes most essential parameters needed
+ * to describe 802.11ax HE capabilities for a STA.
+ *
+ * @has_he: true iff HE data is valid.
+ * @he_cap_elem: Fixed portion of the HE capabilities element.
+ * @he_mcs_nss_supp: The supported NSS/MCS combinations.
+ * @ppe_thres: Holds the PPE Thresholds data.
+ */
+struct ieee80211_sta_he_cap {
+ bool has_he;
+ struct ieee80211_he_cap_elem he_cap_elem;
+ struct ieee80211_he_mcs_nss_supp he_mcs_nss_supp;
+ u8 ppe_thres[IEEE80211_HE_PPE_THRES_MAX_LEN];
+};
+
+/**
+ * struct ieee80211_sband_iftype_data
+ *
+ * This structure encapsulates sband data that is relevant for the
+ * interface types defined in @types_mask. Each type in the
+ * @types_mask must be unique across all instances of iftype_data.
+ *
+ * @types_mask: interface types mask
+ * @he_cap: holds the HE capabilities
+ */
+struct ieee80211_sband_iftype_data {
+ u16 types_mask;
+ struct ieee80211_sta_he_cap he_cap;
+};
+
/**
* struct ieee80211_supported_band - frequency band definition
*
* @n_bitrates: Number of bitrates in @bitrates
* @ht_cap: HT capabilities in this band
* @vht_cap: VHT capabilities in this band
+ * @n_iftype_data: number of iftype data entries
+ * @iftype_data: interface type data entries. Note that the bits in
+ * @types_mask inside this structure cannot overlap (i.e. only
+ * one occurrence of each type is allowed across all instances of
+ * iftype_data).
*/
struct ieee80211_supported_band {
struct ieee80211_channel *channels;
int n_bitrates;
struct ieee80211_sta_ht_cap ht_cap;
struct ieee80211_sta_vht_cap vht_cap;
+ u16 n_iftype_data;
+ const struct ieee80211_sband_iftype_data *iftype_data;
};
+/**
+ * ieee80211_get_sband_iftype_data - return sband data for a given iftype
+ * @sband: the sband to search for the STA on
+ * @iftype: enum nl80211_iftype
+ *
+ * Return: pointer to struct ieee80211_sband_iftype_data, or NULL is none found
+ */
+static inline const struct ieee80211_sband_iftype_data *
+ieee80211_get_sband_iftype_data(const struct ieee80211_supported_band *sband,
+ u8 iftype)
+{
+ int i;
+
+ if (WARN_ON(iftype >= NL80211_IFTYPE_MAX))
+ return NULL;
+
+ for (i = 0; i < sband->n_iftype_data; i++) {
+ const struct ieee80211_sband_iftype_data *data =
+ &sband->iftype_data[i];
+
+ if (data->types_mask & BIT(iftype))
+ return data;
+ }
+
+ return NULL;
+}
+
+/**
+ * ieee80211_get_he_sta_cap - return HE capabilities for an sband's STA
+ * @sband: the sband to search for the STA on
+ *
+ * Return: pointer to the struct ieee80211_sta_he_cap, or NULL is none found
+ */
+static inline const struct ieee80211_sta_he_cap *
+ieee80211_get_he_sta_cap(const struct ieee80211_supported_band *sband)
+{
+ const struct ieee80211_sband_iftype_data *data =
+ ieee80211_get_sband_iftype_data(sband, NL80211_IFTYPE_STATION);
+
+ if (data && data->he_cap.has_he)
+ return &data->he_cap;
+
+ return NULL;
+}
+
/**
* wiphy_read_of_freq_limits - read frequency limits from device tree
*
* @opmode_notif: operating mode field from Operating Mode Notification
* @opmode_notif_used: information if operating mode field is used
* @support_p2p_ps: information if station supports P2P PS mechanism
+ * @he_capa: HE capabilities of station
+ * @he_capa_len: the length of the HE capabilities
*/
struct station_parameters {
const u8 *supported_rates;
u8 opmode_notif;
bool opmode_notif_used;
int support_p2p_ps;
+ const struct ieee80211_he_cap_elem *he_capa;
+ u8 he_capa_len;
};
/**
* @RATE_INFO_FLAGS_VHT_MCS: mcs field filled with VHT MCS
* @RATE_INFO_FLAGS_SHORT_GI: 400ns guard interval
* @RATE_INFO_FLAGS_60G: 60GHz MCS
+ * @RATE_INFO_FLAGS_HE_MCS: HE MCS information
*/
enum rate_info_flags {
RATE_INFO_FLAGS_MCS = BIT(0),
RATE_INFO_FLAGS_VHT_MCS = BIT(1),
RATE_INFO_FLAGS_SHORT_GI = BIT(2),
RATE_INFO_FLAGS_60G = BIT(3),
+ RATE_INFO_FLAGS_HE_MCS = BIT(4),
};
/**
* @RATE_INFO_BW_40: 40 MHz bandwidth
* @RATE_INFO_BW_80: 80 MHz bandwidth
* @RATE_INFO_BW_160: 160 MHz bandwidth
+ * @RATE_INFO_BW_HE_RU: bandwidth determined by HE RU allocation
*/
enum rate_info_bw {
RATE_INFO_BW_20 = 0,
RATE_INFO_BW_40,
RATE_INFO_BW_80,
RATE_INFO_BW_160,
+ RATE_INFO_BW_HE_RU,
};
/**
* Information about a receiving or transmitting bitrate
*
* @flags: bitflag of flags from &enum rate_info_flags
- * @mcs: mcs index if struct describes a 802.11n bitrate
+ * @mcs: mcs index if struct describes an HT/VHT/HE rate
* @legacy: bitrate in 100kbit/s for 802.11abg
- * @nss: number of streams (VHT only)
+ * @nss: number of streams (VHT & HE only)
* @bw: bandwidth (from &enum rate_info_bw)
+ * @he_gi: HE guard interval (from &enum nl80211_he_gi)
+ * @he_dcm: HE DCM value
+ * @he_ru_alloc: HE RU allocation (from &enum nl80211_he_ru_alloc,
+ * only valid if bw is %RATE_INFO_BW_HE_RU)
*/
struct rate_info {
u8 flags;
u16 legacy;
u8 nss;
u8 bw;
+ u8 he_gi;
+ u8 he_dcm;
+ u8 he_ru_alloc;
};
/**
struct list_head sb_list;
struct list_head dpipe_table_list;
struct list_head resource_list;
+ struct list_head param_list;
+ struct list_head region_list;
+ u32 snapshot_id;
struct devlink_dpipe_headers *dpipe_headers;
const struct devlink_ops *ops;
struct device *dev;
#define DEVLINK_RESOURCE_ID_PARENT_TOP 0
+#define DEVLINK_PARAM_MAX_STRING_VALUE 32
+enum devlink_param_type {
+ DEVLINK_PARAM_TYPE_U8,
+ DEVLINK_PARAM_TYPE_U16,
+ DEVLINK_PARAM_TYPE_U32,
+ DEVLINK_PARAM_TYPE_STRING,
+ DEVLINK_PARAM_TYPE_BOOL,
+};
+
+union devlink_param_value {
+ u8 vu8;
+ u16 vu16;
+ u32 vu32;
+ const char *vstr;
+ bool vbool;
+};
+
+struct devlink_param_gset_ctx {
+ union devlink_param_value val;
+ enum devlink_param_cmode cmode;
+};
+
+/**
+ * struct devlink_param - devlink configuration parameter data
+ * @name: name of the parameter
+ * @generic: indicates if the parameter is generic or driver specific
+ * @type: parameter type
+ * @supported_cmodes: bitmap of supported configuration modes
+ * @get: get parameter value, used for runtime and permanent
+ * configuration modes
+ * @set: set parameter value, used for runtime and permanent
+ * configuration modes
+ * @validate: validate input value is applicable (within value range, etc.)
+ *
+ * This struct should be used by the driver to fill the data for
+ * a parameter it registers.
+ */
+struct devlink_param {
+ u32 id;
+ const char *name;
+ bool generic;
+ enum devlink_param_type type;
+ unsigned long supported_cmodes;
+ int (*get)(struct devlink *devlink, u32 id,
+ struct devlink_param_gset_ctx *ctx);
+ int (*set)(struct devlink *devlink, u32 id,
+ struct devlink_param_gset_ctx *ctx);
+ int (*validate)(struct devlink *devlink, u32 id,
+ union devlink_param_value val,
+ struct netlink_ext_ack *extack);
+};
+
+struct devlink_param_item {
+ struct list_head list;
+ const struct devlink_param *param;
+ union devlink_param_value driverinit_value;
+ bool driverinit_value_valid;
+};
+
+enum devlink_param_generic_id {
+ DEVLINK_PARAM_GENERIC_ID_INT_ERR_RESET,
+ DEVLINK_PARAM_GENERIC_ID_MAX_MACS,
+ DEVLINK_PARAM_GENERIC_ID_ENABLE_SRIOV,
+ DEVLINK_PARAM_GENERIC_ID_REGION_SNAPSHOT,
+
+ /* add new param generic ids above here*/
+ __DEVLINK_PARAM_GENERIC_ID_MAX,
+ DEVLINK_PARAM_GENERIC_ID_MAX = __DEVLINK_PARAM_GENERIC_ID_MAX - 1,
+};
+
+#define DEVLINK_PARAM_GENERIC_INT_ERR_RESET_NAME "internal_error_reset"
+#define DEVLINK_PARAM_GENERIC_INT_ERR_RESET_TYPE DEVLINK_PARAM_TYPE_BOOL
+
+#define DEVLINK_PARAM_GENERIC_MAX_MACS_NAME "max_macs"
+#define DEVLINK_PARAM_GENERIC_MAX_MACS_TYPE DEVLINK_PARAM_TYPE_U32
+
+#define DEVLINK_PARAM_GENERIC_ENABLE_SRIOV_NAME "enable_sriov"
+#define DEVLINK_PARAM_GENERIC_ENABLE_SRIOV_TYPE DEVLINK_PARAM_TYPE_BOOL
+
+#define DEVLINK_PARAM_GENERIC_REGION_SNAPSHOT_NAME "region_snapshot_enable"
+#define DEVLINK_PARAM_GENERIC_REGION_SNAPSHOT_TYPE DEVLINK_PARAM_TYPE_BOOL
+
+#define DEVLINK_PARAM_GENERIC(_id, _cmodes, _get, _set, _validate) \
+{ \
+ .id = DEVLINK_PARAM_GENERIC_ID_##_id, \
+ .name = DEVLINK_PARAM_GENERIC_##_id##_NAME, \
+ .type = DEVLINK_PARAM_GENERIC_##_id##_TYPE, \
+ .generic = true, \
+ .supported_cmodes = _cmodes, \
+ .get = _get, \
+ .set = _set, \
+ .validate = _validate, \
+}
+
+#define DEVLINK_PARAM_DRIVER(_id, _name, _type, _cmodes, _get, _set, _validate) \
+{ \
+ .id = _id, \
+ .name = _name, \
+ .type = _type, \
+ .supported_cmodes = _cmodes, \
+ .get = _get, \
+ .set = _set, \
+ .validate = _validate, \
+}
+
+struct devlink_region;
+
+typedef void devlink_snapshot_data_dest_t(const void *data);
+
struct devlink_ops {
int (*reload)(struct devlink *devlink, struct netlink_ext_ack *extack);
int (*port_type_set)(struct devlink_port *devlink_port,
void *occ_get_priv);
void devlink_resource_occ_get_unregister(struct devlink *devlink,
u64 resource_id);
+int devlink_params_register(struct devlink *devlink,
+ const struct devlink_param *params,
+ size_t params_count);
+void devlink_params_unregister(struct devlink *devlink,
+ const struct devlink_param *params,
+ size_t params_count);
+int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id,
+ union devlink_param_value *init_val);
+int devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id,
+ union devlink_param_value init_val);
+void devlink_param_value_changed(struct devlink *devlink, u32 param_id);
+struct devlink_region *devlink_region_create(struct devlink *devlink,
+ const char *region_name,
+ u32 region_max_snapshots,
+ u64 region_size);
+void devlink_region_destroy(struct devlink_region *region);
+u32 devlink_region_shapshot_id_get(struct devlink *devlink);
+int devlink_region_snapshot_create(struct devlink_region *region, u64 data_len,
+ u8 *data, u32 snapshot_id,
+ devlink_snapshot_data_dest_t *data_destructor);
#else
{
}
+static inline int
+devlink_params_register(struct devlink *devlink,
+ const struct devlink_param *params,
+ size_t params_count)
+{
+ return 0;
+}
+
+static inline void
+devlink_params_unregister(struct devlink *devlink,
+ const struct devlink_param *params,
+ size_t params_count)
+{
+
+}
+
+static inline int
+devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id,
+ union devlink_param_value *init_val)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline int
+devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id,
+ union devlink_param_value init_val)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline void
+devlink_param_value_changed(struct devlink *devlink, u32 param_id)
+{
+}
+
+static inline struct devlink_region *
+devlink_region_create(struct devlink *devlink,
+ const char *region_name,
+ u32 region_max_snapshots,
+ u64 region_size)
+{
+ return NULL;
+}
+
+static inline void
+devlink_region_destroy(struct devlink_region *region)
+{
+}
+
+static inline u32
+devlink_region_shapshot_id_get(struct devlink *devlink)
+{
+ return 0;
+}
+
+static inline int
+devlink_region_snapshot_create(struct devlink_region *region, u64 data_len,
+ u8 *data, u32 snapshot_id,
+ devlink_snapshot_data_dest_t *data_destructor)
+{
+ return 0;
+}
+
#endif
#endif /* _NET_DEVLINK_H_ */
struct flow_dissector_key_vlan {
u16 vlan_id:12,
vlan_priority:3;
- u16 padding;
+ __be16 vlan_tpid;
};
struct flow_dissector_key_mpls {
FLOW_DISSECTOR_KEY_MPLS, /* struct flow_dissector_key_mpls */
FLOW_DISSECTOR_KEY_TCP, /* struct flow_dissector_key_tcp */
FLOW_DISSECTOR_KEY_IP, /* struct flow_dissector_key_ip */
+ FLOW_DISSECTOR_KEY_CVLAN, /* struct flow_dissector_key_flow_vlan */
FLOW_DISSECTOR_KEY_MAX,
};
struct flow_dissector_key_basic basic;
struct flow_dissector_key_tags tags;
struct flow_dissector_key_vlan vlan;
+ struct flow_dissector_key_vlan cvlan;
struct flow_dissector_key_keyid keyid;
struct flow_dissector_key_ports ports;
struct flow_dissector_key_addrs addrs;
/*
* Copyright (c) 2017 Intel Deutschland GmbH
+ * Copyright (c) 2018 Intel Corporation
*
* Permission to use, copy, modify, and/or distribute this software for any
* purpose with or without fee is hereby granted, provided that the above
IEEE80211_RADIOTAP_AMPDU_STATUS = 20,
IEEE80211_RADIOTAP_VHT = 21,
IEEE80211_RADIOTAP_TIMESTAMP = 22,
+ IEEE80211_RADIOTAP_HE = 23,
+ IEEE80211_RADIOTAP_HE_MU = 24,
/* valid in every it_present bitmap, even vendor namespaces */
IEEE80211_RADIOTAP_RADIOTAP_NAMESPACE = 29,
IEEE80211_RADIOTAP_TIMESTAMP_FLAG_ACCURACY = 0x02,
};
+struct ieee80211_radiotap_he {
+ __le16 data1, data2, data3, data4, data5, data6;
+};
+
+enum ieee80211_radiotap_he_bits {
+ IEEE80211_RADIOTAP_HE_DATA1_FORMAT_MASK = 3,
+ IEEE80211_RADIOTAP_HE_DATA1_FORMAT_SU = 0,
+ IEEE80211_RADIOTAP_HE_DATA1_FORMAT_EXT_SU = 1,
+ IEEE80211_RADIOTAP_HE_DATA1_FORMAT_MU = 2,
+ IEEE80211_RADIOTAP_HE_DATA1_FORMAT_TRIG = 3,
+
+ IEEE80211_RADIOTAP_HE_DATA1_BSS_COLOR_KNOWN = 0x0004,
+ IEEE80211_RADIOTAP_HE_DATA1_BEAM_CHANGE_KNOWN = 0x0008,
+ IEEE80211_RADIOTAP_HE_DATA1_UL_DL_KNOWN = 0x0010,
+ IEEE80211_RADIOTAP_HE_DATA1_DATA_MCS_KNOWN = 0x0020,
+ IEEE80211_RADIOTAP_HE_DATA1_DATA_DCM_KNOWN = 0x0040,
+ IEEE80211_RADIOTAP_HE_DATA1_CODING_KNOWN = 0x0080,
+ IEEE80211_RADIOTAP_HE_DATA1_LDPC_XSYMSEG_KNOWN = 0x0100,
+ IEEE80211_RADIOTAP_HE_DATA1_STBC_KNOWN = 0x0200,
+ IEEE80211_RADIOTAP_HE_DATA1_SPTL_REUSE_KNOWN = 0x0400,
+ IEEE80211_RADIOTAP_HE_DATA1_SPTL_REUSE2_KNOWN = 0x0800,
+ IEEE80211_RADIOTAP_HE_DATA1_SPTL_REUSE3_KNOWN = 0x1000,
+ IEEE80211_RADIOTAP_HE_DATA1_SPTL_REUSE4_KNOWN = 0x2000,
+ IEEE80211_RADIOTAP_HE_DATA1_BW_RU_ALLOC_KNOWN = 0x4000,
+ IEEE80211_RADIOTAP_HE_DATA1_DOPPLER_KNOWN = 0x8000,
+
+ IEEE80211_RADIOTAP_HE_DATA2_PRISEC_80_KNOWN = 0x0001,
+ IEEE80211_RADIOTAP_HE_DATA2_GI_KNOWN = 0x0002,
+ IEEE80211_RADIOTAP_HE_DATA2_NUM_LTF_SYMS_KNOWN = 0x0004,
+ IEEE80211_RADIOTAP_HE_DATA2_PRE_FEC_PAD_KNOWN = 0x0008,
+ IEEE80211_RADIOTAP_HE_DATA2_TXBF_KNOWN = 0x0010,
+ IEEE80211_RADIOTAP_HE_DATA2_PE_DISAMBIG_KNOWN = 0x0020,
+ IEEE80211_RADIOTAP_HE_DATA2_TXOP_KNOWN = 0x0040,
+ IEEE80211_RADIOTAP_HE_DATA2_MIDAMBLE_KNOWN = 0x0080,
+ IEEE80211_RADIOTAP_HE_DATA2_RU_OFFSET = 0x3f00,
+ IEEE80211_RADIOTAP_HE_DATA2_RU_OFFSET_KNOWN = 0x4000,
+ IEEE80211_RADIOTAP_HE_DATA2_PRISEC_80_SEC = 0x8000,
+
+ IEEE80211_RADIOTAP_HE_DATA3_BSS_COLOR = 0x003f,
+ IEEE80211_RADIOTAP_HE_DATA3_BEAM_CHANGE = 0x0040,
+ IEEE80211_RADIOTAP_HE_DATA3_UL_DL = 0x0080,
+ IEEE80211_RADIOTAP_HE_DATA3_DATA_MCS = 0x0f00,
+ IEEE80211_RADIOTAP_HE_DATA3_DATA_DCM = 0x1000,
+ IEEE80211_RADIOTAP_HE_DATA3_CODING = 0x2000,
+ IEEE80211_RADIOTAP_HE_DATA3_LDPC_XSYMSEG = 0x4000,
+ IEEE80211_RADIOTAP_HE_DATA3_STBC = 0x8000,
+
+ IEEE80211_RADIOTAP_HE_DATA4_SU_MU_SPTL_REUSE = 0x000f,
+ IEEE80211_RADIOTAP_HE_DATA4_MU_STA_ID = 0x7ff0,
+ IEEE80211_RADIOTAP_HE_DATA4_TB_SPTL_REUSE1 = 0x000f,
+ IEEE80211_RADIOTAP_HE_DATA4_TB_SPTL_REUSE2 = 0x00f0,
+ IEEE80211_RADIOTAP_HE_DATA4_TB_SPTL_REUSE3 = 0x0f00,
+ IEEE80211_RADIOTAP_HE_DATA4_TB_SPTL_REUSE4 = 0xf000,
+
+ IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC = 0x000f,
+ IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_20MHZ = 0,
+ IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_40MHZ = 1,
+ IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_80MHZ = 2,
+ IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_160MHZ = 3,
+ IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_26T = 4,
+ IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_52T = 5,
+ IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_106T = 6,
+ IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_242T = 7,
+ IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_484T = 8,
+ IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_996T = 9,
+ IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_2x996T = 10,
+
+ IEEE80211_RADIOTAP_HE_DATA5_GI = 0x0030,
+ IEEE80211_RADIOTAP_HE_DATA5_GI_0_8 = 0,
+ IEEE80211_RADIOTAP_HE_DATA5_GI_1_6 = 1,
+ IEEE80211_RADIOTAP_HE_DATA5_GI_3_2 = 2,
+
+ IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE = 0x00c0,
+ IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE_UNKNOWN = 0,
+ IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE_1X = 1,
+ IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE_2X = 2,
+ IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE_4X = 3,
+ IEEE80211_RADIOTAP_HE_DATA5_NUM_LTF_SYMS = 0x0700,
+ IEEE80211_RADIOTAP_HE_DATA5_PRE_FEC_PAD = 0x3000,
+ IEEE80211_RADIOTAP_HE_DATA5_TXBF = 0x4000,
+ IEEE80211_RADIOTAP_HE_DATA5_PE_DISAMBIG = 0x8000,
+
+ IEEE80211_RADIOTAP_HE_DATA6_NSTS = 0x000f,
+ IEEE80211_RADIOTAP_HE_DATA6_DOPPLER = 0x0010,
+ IEEE80211_RADIOTAP_HE_DATA6_TXOP = 0x7f00,
+ IEEE80211_RADIOTAP_HE_DATA6_MIDAMBLE_PDCTY = 0x8000,
+};
+
+struct ieee80211_radiotap_he_mu {
+ __le16 flags1, flags2;
+ u8 ru_ch1[4];
+ u8 ru_ch2[4];
+};
+
+enum ieee80211_radiotap_he_mu_bits {
+ IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_MCS = 0x000f,
+ IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_MCS_KNOWN = 0x0010,
+ IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_DCM = 0x0020,
+ IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_DCM_KNOWN = 0x0040,
+ IEEE80211_RADIOTAP_HE_MU_FLAGS1_CH2_CTR_26T_RU_KNOWN = 0x0080,
+ IEEE80211_RADIOTAP_HE_MU_FLAGS1_CH1_RU_KNOWN = 0x0100,
+ IEEE80211_RADIOTAP_HE_MU_FLAGS1_CH2_RU_KNOWN = 0x0200,
+ IEEE80211_RADIOTAP_HE_MU_FLAGS1_CH1_CTR_26T_RU_KNOWN = 0x1000,
+ IEEE80211_RADIOTAP_HE_MU_FLAGS1_CH1_CTR_26T_RU = 0x2000,
+ IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_COMP_KNOWN = 0x4000,
+ IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_SYMS_USERS_KNOWN = 0x8000,
+
+ IEEE80211_RADIOTAP_HE_MU_FLAGS2_BW_FROM_SIG_A_BW = 0x0003,
+ IEEE80211_RADIOTAP_HE_MU_FLAGS2_BW_FROM_SIG_A_BW_20MHZ = 0x0000,
+ IEEE80211_RADIOTAP_HE_MU_FLAGS2_BW_FROM_SIG_A_BW_40MHZ = 0x0001,
+ IEEE80211_RADIOTAP_HE_MU_FLAGS2_BW_FROM_SIG_A_BW_80MHZ = 0x0002,
+ IEEE80211_RADIOTAP_HE_MU_FLAGS2_BW_FROM_SIG_A_BW_160MHZ = 0x0003,
+ IEEE80211_RADIOTAP_HE_MU_FLAGS2_BW_FROM_SIG_A_BW_KNOWN = 0x0004,
+ IEEE80211_RADIOTAP_HE_MU_FLAGS2_SIG_B_COMP = 0x0008,
+ IEEE80211_RADIOTAP_HE_MU_FLAGS2_SIG_B_SYMS_USERS = 0x00f0,
+ IEEE80211_RADIOTAP_HE_MU_FLAGS2_PUNC_FROM_SIG_A_BW = 0x0300,
+ IEEE80211_RADIOTAP_HE_MU_FLAGS2_PUNC_FROM_SIG_A_BW_KNOWN= 0x0400,
+ IEEE80211_RADIOTAP_HE_MU_FLAGS2_CH2_CTR_26T_RU = 0x0800,
+};
+
/**
* ieee80211_get_radiotap_len - get radiotap header length
*/
int inet_recv_error(struct sock *sk, struct msghdr *msg, int len,
int *addr_len);
-struct sk_buff **inet_gro_receive(struct sk_buff **head, struct sk_buff *skb);
+struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb);
int inet_gro_complete(struct sk_buff *skb, int nhoff);
struct sk_buff *inet_gso_segment(struct sk_buff *skb,
netdev_features_t features);
#ifndef __NET_FRAG_H__
#define __NET_FRAG_H__
-#include <linux/rhashtable.h>
+#include <linux/rhashtable-types.h>
struct netns_frags {
/* sysctls */
__s16 tos;
char priority;
__u16 gso_size;
+ u64 transmit_time;
};
struct inet_cork_full {
__be32 addr;
int oif;
struct ip_options_rcu *opt;
- __u8 tx_flags;
__u8 ttl;
__s16 tos;
char priority;
__u16 gso_size;
};
+static inline void ipcm_init(struct ipcm_cookie *ipcm)
+{
+ *ipcm = (struct ipcm_cookie) { .tos = -1 };
+}
+
+static inline void ipcm_init_sk(struct ipcm_cookie *ipcm,
+ const struct inet_sock *inet)
+{
+ ipcm_init(ipcm);
+
+ ipcm->sockc.tsflags = inet->sk.sk_tsflags;
+ ipcm->oif = inet->sk.sk_bound_dev_if;
+ ipcm->addr = inet->inet_saddr;
+}
+
#define IPCB(skb) ((struct inet_skb_parm*)((skb)->cb))
#define PKTINFO_SKB_CB(skb) ((struct in_pktinfo *)((skb)->cb))
struct ip_options_rcu *opt);
int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt,
struct net_device *orig_dev);
+void ip_list_rcv(struct list_head *head, struct packet_type *pt,
+ struct net_device *orig_dev);
int ip_local_deliver(struct sk_buff *skb);
int ip_mr_input(struct sk_buff *skb);
int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb);
int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb);
int ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb);
-int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl);
+int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
+ __u8 tos);
void ip_init(void);
int ip_append_data(struct sock *sk, struct flowi4 *fl4,
int getfrag(void *from, char *to, int offset, int len,
struct ipcm_cookie *ipc, struct rtable **rtp,
struct inet_cork *cork, unsigned int flags);
+static inline int ip_queue_xmit(struct sock *sk, struct sk_buff *skb,
+ struct flowi *fl)
+{
+ return __ip_queue_xmit(sk, skb, fl, inet_sk(sk)->tos);
+}
+
static inline struct sk_buff *ip_finish_skb(struct sock *sk, struct flowi4 *fl4)
{
return __ip_make_skb(sk, fl4, &sk->sk_write_queue, &inet_sk(sk)->cork.base);
unused:3;
struct fib6_nh fib6_nh;
+ struct rcu_head rcu;
};
struct rt6_info {
}
struct fib6_info *fib6_info_alloc(gfp_t gfp_flags);
-void fib6_info_destroy(struct fib6_info *f6i);
+void fib6_info_destroy_rcu(struct rcu_head *head);
static inline void fib6_info_hold(struct fib6_info *f6i)
{
static inline void fib6_info_release(struct fib6_info *f6i)
{
if (f6i && atomic_dec_and_test(&f6i->fib6_ref))
- fib6_info_destroy(f6i);
+ call_rcu(&f6i->rcu, fib6_info_destroy_rcu);
}
enum fib6_walk_state {
}
static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info,
- const void *from, int len)
+ const void *from, int len,
+ __be16 flags)
{
memcpy(ip_tunnel_info_opts(info), from, len);
info->options_len = len;
+ info->key.tun_flags |= flags;
}
static inline struct ip_tunnel_info *lwt_tun_info(struct lwtunnel_state *lwtstate)
}
static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info,
- const void *from, int len)
+ const void *from, int len,
+ __be16 flags)
{
info->options_len = 0;
+ info->key.tun_flags |= flags;
}
#endif /* CONFIG_INET */
};
struct ipcm6_cookie {
+ struct sockcm_cookie sockc;
__s16 hlimit;
__s16 tclass;
__s8 dontfrag;
__u16 gso_size;
};
+static inline void ipcm6_init(struct ipcm6_cookie *ipc6)
+{
+ *ipc6 = (struct ipcm6_cookie) {
+ .hlimit = -1,
+ .tclass = -1,
+ .dontfrag = -1,
+ };
+}
+
+static inline void ipcm6_init_sk(struct ipcm6_cookie *ipc6,
+ const struct ipv6_pinfo *np)
+{
+ *ipc6 = (struct ipcm6_cookie) {
+ .hlimit = -1,
+ .tclass = np->tclass,
+ .dontfrag = np->dontfrag,
+ };
+}
+
static inline struct ipv6_txoptions *txopt_get(const struct ipv6_pinfo *np)
{
struct ipv6_txoptions *opt;
int ipv6_rcv(struct sk_buff *skb, struct net_device *dev,
struct packet_type *pt, struct net_device *orig_dev);
+void ipv6_list_rcv(struct list_head *head, struct packet_type *pt,
+ struct net_device *orig_dev);
int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb);
int odd, struct sk_buff *skb),
void *from, int length, int transhdrlen,
struct ipcm6_cookie *ipc6, struct flowi6 *fl6,
- struct rt6_info *rt, unsigned int flags,
- const struct sockcm_cookie *sockc);
+ struct rt6_info *rt, unsigned int flags);
int ip6_push_pending_frames(struct sock *sk);
void *from, int length, int transhdrlen,
struct ipcm6_cookie *ipc6, struct flowi6 *fl6,
struct rt6_info *rt, unsigned int flags,
- struct inet_cork_full *cork,
- const struct sockcm_cookie *sockc);
+ struct inet_cork_full *cork);
static inline struct sk_buff *ip6_finish_skb(struct sock *sk)
{
atomic_t autobind_name;
};
+__poll_t iucv_sock_poll(struct file *file, struct socket *sock,
+ poll_table *wait);
void iucv_sock_link(struct iucv_sock_list *l, struct sock *s);
void iucv_sock_unlink(struct iucv_sock_list *l, struct sock *s);
void iucv_accept_enqueue(struct sock *parent, struct sock *sk);
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_IF_LAG_H
+#define _LINUX_IF_LAG_H
+
+#include <linux/netdevice.h>
+#include <linux/if_team.h>
+#include <net/bonding.h>
+
+static inline bool net_lag_port_dev_txable(const struct net_device *port_dev)
+{
+ if (netif_is_team_port(port_dev))
+ return team_port_dev_txable(port_dev);
+ else
+ return bond_is_active_slave_dev(port_dev);
+}
+
+#endif /* _LINUX_IF_LAG_H */
#include <linux/ieee80211.h>
#include <net/cfg80211.h>
#include <net/codel.h>
+#include <net/ieee80211_radiotap.h>
#include <asm/unaligned.h>
/**
* @txop: maximum burst time in units of 32 usecs, 0 meaning disabled
* @acm: is mandatory admission control required for the access category
* @uapsd: is U-APSD mode enabled for the queue
+ * @mu_edca: is the MU EDCA configured
+ * @mu_edca_param_rec: MU EDCA Parameter Record for HE
*/
struct ieee80211_tx_queue_params {
u16 txop;
u8 aifs;
bool acm;
bool uapsd;
+ bool mu_edca;
+ struct ieee80211_he_mu_edca_param_ac_rec mu_edca_param_rec;
};
struct ieee80211_low_level_stats {
* This structure keeps information about a BSS (and an association
* to that BSS) that can change during the lifetime of the BSS.
*
+ * @bss_color: 6-bit value to mark inter-BSS frame, if BSS supports HE
+ * @htc_trig_based_pkt_ext: default PE in 4us units, if BSS supports HE
+ * @multi_sta_back_32bit: supports BA bitmap of 32-bits in Multi-STA BACK
+ * @uora_exists: is the UORA element advertised by AP
+ * @ack_enabled: indicates support to receive a multi-TID that solicits either
+ * ACK, BACK or both
+ * @uora_ocw_range: UORA element's OCW Range field
+ * @frame_time_rts_th: HE duration RTS threshold, in units of 32us
+ * @he_support: does this BSS support HE
* @assoc: association status
* @ibss_joined: indicates whether this station is part of an IBSS
* or not
*/
struct ieee80211_bss_conf {
const u8 *bssid;
+ u8 bss_color;
+ u8 htc_trig_based_pkt_ext;
+ bool multi_sta_back_32bit;
+ bool uora_exists;
+ bool ack_enabled;
+ u8 uora_ocw_range;
+ u16 frame_time_rts_th;
+ bool he_support;
/* association related data */
bool assoc, ibss_joined;
bool ibss_creator;
* @RX_FLAG_AMPDU_EOF_BIT: Value of the EOF bit in the A-MPDU delimiter for this
* frame
* @RX_FLAG_AMPDU_EOF_BIT_KNOWN: The EOF value is known
+ * @RX_FLAG_RADIOTAP_HE: HE radiotap data is present
+ * (&struct ieee80211_radiotap_he, mac80211 will fill in
+ * - DATA3_DATA_MCS
+ * - DATA3_DATA_DCM
+ * - DATA3_CODING
+ * - DATA5_GI
+ * - DATA5_DATA_BW_RU_ALLOC
+ * - DATA6_NSTS
+ * - DATA3_STBC
+ * from the RX info data, so leave those zeroed when building this data)
+ * @RX_FLAG_RADIOTAP_HE_MU: HE MU radiotap data is present
+ * (&struct ieee80211_radiotap_he_mu)
*/
enum mac80211_rx_flags {
RX_FLAG_MMIC_ERROR = BIT(0),
RX_FLAG_ICV_STRIPPED = BIT(23),
RX_FLAG_AMPDU_EOF_BIT = BIT(24),
RX_FLAG_AMPDU_EOF_BIT_KNOWN = BIT(25),
+ RX_FLAG_RADIOTAP_HE = BIT(26),
+ RX_FLAG_RADIOTAP_HE_MU = BIT(27),
};
/**
RX_ENC_LEGACY = 0,
RX_ENC_HT,
RX_ENC_VHT,
+ RX_ENC_HE,
};
/**
* @encoding: &enum mac80211_rx_encoding
* @bw: &enum rate_info_bw
* @enc_flags: uses bits from &enum mac80211_rx_encoding_flags
+ * @he_ru: HE RU, from &enum nl80211_he_ru_alloc
+ * @he_gi: HE GI, from &enum nl80211_he_gi
+ * @he_dcm: HE DCM value
* @rx_flags: internal RX flags for mac80211
* @ampdu_reference: A-MPDU reference number, must be a different value for
* each A-MPDU but the same for each subframe within one A-MPDU
u32 flag;
u16 freq;
u8 enc_flags;
- u8 encoding:2, bw:3;
+ u8 encoding:2, bw:3, he_ru:3;
+ u8 he_gi:2, he_dcm:1;
u8 rate_idx;
u8 nss;
u8 rx_flags;
* @supp_rates: Bitmap of supported rates (per band)
* @ht_cap: HT capabilities of this STA; restricted to our own capabilities
* @vht_cap: VHT capabilities of this STA; restricted to our own capabilities
+ * @he_cap: HE capabilities of this STA
* @max_rx_aggregation_subframes: maximal amount of frames in a single AMPDU
* that this station is allowed to transmit to us.
* Can be modified by driver.
u16 aid;
struct ieee80211_sta_ht_cap ht_cap;
struct ieee80211_sta_vht_cap vht_cap;
- u8 max_rx_aggregation_subframes;
+ struct ieee80211_sta_he_cap he_cap;
+ u16 max_rx_aggregation_subframes;
bool wme;
u8 uapsd_queues;
u8 max_sp;
* it shouldn't be set.
*
* @max_tx_aggregation_subframes: maximum number of subframes in an
- * aggregate an HT driver will transmit. Though ADDBA will advertise
- * a constant value of 64 as some older APs can crash if the window
- * size is smaller (an example is LinkSys WRT120N with FW v1.0.07
- * build 002 Jun 18 2012).
+ * aggregate an HT/HE device will transmit. In HT AddBA we'll
+ * advertise a constant value of 64 as some older APs crash if
+ * the window size is smaller (an example is LinkSys WRT120N
+ * with FW v1.0.07 build 002 Jun 18 2012).
+ * For AddBA to HE capable peers this value will be used.
*
* @max_tx_fragments: maximum number of tx buffers per (A)-MSDU, sum
* of 1 + skb_shinfo(skb)->nr_frags for each skb in the frag_list.
* the default is _GI | _BANDWIDTH.
* Use the %IEEE80211_RADIOTAP_VHT_KNOWN_\* values.
*
+ * @radiotap_he: HE radiotap validity flags
+ *
* @radiotap_timestamp: Information for the radiotap timestamp field; if the
* 'units_pos' member is set to a non-negative value it must be set to
* a combination of a IEEE80211_RADIOTAP_TIMESTAMP_UNIT_* and a
u8 max_rates;
u8 max_report_rates;
u8 max_rate_tries;
- u8 max_rx_aggregation_subframes;
- u8 max_tx_aggregation_subframes;
+ u16 max_rx_aggregation_subframes;
+ u16 max_tx_aggregation_subframes;
u8 max_tx_fragments;
u8 offchannel_tx_hw_queue;
u8 radiotap_mcs_details;
struct ieee80211_sta *sta;
u16 tid;
u16 ssn;
- u8 buf_size;
+ u16 buf_size;
bool amsdu;
u16 timeout;
};
#endif
#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
struct netns_nf_frag nf_frag;
+ struct ctl_table_header *nf_frag_frags_hdr;
#endif
struct sock *nfnl;
struct sock *nfnl_stash;
#include <linux/in.h>
#include <linux/in6.h>
#include <linux/netdevice.h>
-#include <linux/rhashtable.h>
+#include <linux/rhashtable-types.h>
#include <linux/rcupdate.h>
#include <linux/netfilter/nf_conntrack_tuple_common.h>
#include <net/dst.h>
int nf_log_dump_tcp_header(struct nf_log_buf *m, const struct sk_buff *skb,
u8 proto, int fragment, unsigned int offset,
unsigned int logflags);
-void nf_log_dump_sk_uid_gid(struct nf_log_buf *m, struct sock *sk);
+void nf_log_dump_sk_uid_gid(struct net *net, struct nf_log_buf *m,
+ struct sock *sk);
void nf_log_dump_packet_common(struct nf_log_buf *m, u_int8_t pf,
unsigned int hooknum, const struct sk_buff *skb,
const struct net_device *in,
static inline u32 net_hash_mix(const struct net *net)
{
#ifdef CONFIG_NET_NS
- /*
- * shift this right to eliminate bits, that are
- * always zeroed
- */
-
- return (u32)(((unsigned long)net) >> L1_CACHE_SHIFT);
+ return (u32)(((unsigned long)net) >> ilog2(sizeof(*net)));
#else
return 0;
#endif
#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
struct netns_nf_frag {
- struct netns_sysctl_ipv6 sysctl;
struct netns_frags frags;
};
#endif
int stop;
int skip;
int count;
+ unsigned long cookie;
int (*fn)(struct tcf_proto *, void *node, struct tcf_walker *);
};
unsigned int tcf_block_cb_decref(struct tcf_block_cb *block_cb);
struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block,
tc_setup_cb_t *cb, void *cb_ident,
- void *cb_priv);
+ void *cb_priv,
+ struct netlink_ext_ack *extack);
int tcf_block_cb_register(struct tcf_block *block,
tc_setup_cb_t *cb, void *cb_ident,
- void *cb_priv);
-void __tcf_block_cb_unregister(struct tcf_block_cb *block_cb);
+ void *cb_priv, struct netlink_ext_ack *extack);
+void __tcf_block_cb_unregister(struct tcf_block *block,
+ struct tcf_block_cb *block_cb);
void tcf_block_cb_unregister(struct tcf_block *block,
tc_setup_cb_t *cb, void *cb_ident);
{
}
+static inline bool tcf_block_shared(struct tcf_block *block)
+{
+ return false;
+}
+
static inline struct Qdisc *tcf_block_q(struct tcf_block *block)
{
return NULL;
static inline
struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block,
tc_setup_cb_t *cb, void *cb_ident,
- void *cb_priv)
+ void *cb_priv,
+ struct netlink_ext_ack *extack)
{
return NULL;
}
static inline
int tcf_block_cb_register(struct tcf_block *block,
tc_setup_cb_t *cb, void *cb_ident,
- void *cb_priv)
+ void *cb_priv, struct netlink_ext_ack *extack)
{
return 0;
}
static inline
-void __tcf_block_cb_unregister(struct tcf_block_cb *block_cb)
+void __tcf_block_cb_unregister(struct tcf_block *block,
+ struct tcf_block_cb *block_cb)
{
}
enum tc_block_command command;
enum tcf_block_binder_type binder_type;
struct tcf_block *block;
+ struct netlink_ext_ack *extack;
};
struct tc_cls_common_offload {
struct tc_cookie {
u8 *data;
u32 len;
+ struct rcu_head rcu;
};
struct tc_qopt_offload_stats {
struct Qdisc *qdisc;
};
+void qdisc_watchdog_init_clockid(struct qdisc_watchdog *wd, struct Qdisc *qdisc,
+ clockid_t clockid);
void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc);
void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires);
s32 sendslope;
};
+struct tc_etf_qopt_offload {
+ u8 enable;
+ s32 queue;
+};
+
#endif
struct tcf_walker;
struct module;
+typedef int tc_setup_cb_t(enum tc_setup_type type,
+ void *type_data, void *cb_priv);
+
struct qdisc_rate_table {
struct tc_ratespec rate;
u32 data[256];
bool *last,
struct netlink_ext_ack *);
void (*walk)(struct tcf_proto*, struct tcf_walker *arg);
+ int (*reoffload)(struct tcf_proto *tp, bool add,
+ tc_setup_cb_t *cb, void *cb_priv,
+ struct netlink_ext_ack *extack);
void (*bind_class)(void *, u32, unsigned long);
/* rtnetlink specific */
block->offloadcnt--;
}
+static inline void
+tc_cls_offload_cnt_update(struct tcf_block *block, unsigned int *cnt,
+ u32 *flags, bool add)
+{
+ if (add) {
+ if (!*cnt)
+ tcf_block_offload_inc(block, flags);
+ (*cnt)++;
+ } else {
+ (*cnt)--;
+ if (!*cnt)
+ tcf_block_offload_dec(block, flags);
+ }
+}
+
static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz)
{
struct qdisc_skb_cb *qcb;
int sctp_inet_listen(struct socket *sock, int backlog);
void sctp_write_space(struct sock *sk);
void sctp_data_ready(struct sock *sk);
-__poll_t sctp_poll_mask(struct socket *sock, __poll_t events);
+__poll_t sctp_poll(struct file *file, struct socket *sock,
+ poll_table *wait);
void sctp_sock_rfree(struct sk_buff *skb);
void sctp_copy_sock(struct sock *newsk, struct sock *sk,
struct sctp_association *asoc);
#define __sctp_structs_h__
#include <linux/ktime.h>
-#include <linux/rhashtable.h>
+#include <linux/rhashtable-types.h>
#include <linux/socket.h> /* linux/in.h needs this!! */
#include <linux/in.h> /* We get struct sockaddr_in. */
#include <linux/in6.h> /* We get struct in6_addr */
/* This is the max_retrans value for new associations. */
__u16 pathmaxrxt;
+ __u32 flowlabel;
+ __u8 dscp;
+
/* The initial Path MTU to use for new associations. */
__u32 pathmtu;
__u32 adaptation_ind;
__u32 pd_point;
__u16 nodelay:1,
+ reuse:1,
disable_fragments:1,
v4mapped:1,
frag_interleave:1,
*/
__u16 pathmaxrxt;
+ __u32 flowlabel;
+ __u8 dscp;
+
/* This is the partially failed retrans value for the transport
* and will be initialized from the assocs value. This can be changed
* using the SCTP_PEER_ADDR_THLDS socket option
*/
__u16 pathmaxrxt;
+ __u32 flowlabel;
+ __u8 dscp;
+
/* Flag that path mtu update is pending */
__u8 pmtu_pending;
#include <linux/ipv6.h>
#include <net/lwtunnel.h>
#include <linux/seg6.h>
-#include <linux/rhashtable.h>
+#include <linux/rhashtable-types.h>
static inline void update_csum_diff4(struct sk_buff *skb, __be32 from,
__be32 to)
#include <linux/route.h>
#include <net/seg6.h>
#include <linux/seg6_hmac.h>
-#include <linux/rhashtable.h>
+#include <linux/rhashtable-types.h>
#define SEG6_HMAC_MAX_DIGESTSIZE 160
#define SEG6_HMAC_RING_SIZE 256
#ifndef _SMC_H
#define _SMC_H
+#define SMC_MAX_PNETID_LEN 16 /* Max. length of PNET id */
+
struct smc_hashinfo {
rwlock_t lock;
struct hlist_head ht;
int smc_hash_sk(struct sock *sk);
void smc_unhash_sk(struct sock *sk);
+
+/* SMCD/ISM device driver interface */
+struct smcd_dmb {
+ u64 dmb_tok;
+ u64 rgid;
+ u32 dmb_len;
+ u32 sba_idx;
+ u32 vlan_valid;
+ u32 vlan_id;
+ void *cpu_addr;
+ dma_addr_t dma_addr;
+};
+
+#define ISM_EVENT_DMB 0
+#define ISM_EVENT_GID 1
+#define ISM_EVENT_SWR 2
+
+struct smcd_event {
+ u32 type;
+ u32 code;
+ u64 tok;
+ u64 time;
+ u64 info;
+};
+
+struct smcd_dev;
+
+struct smcd_ops {
+ int (*query_remote_gid)(struct smcd_dev *dev, u64 rgid, u32 vid_valid,
+ u32 vid);
+ int (*register_dmb)(struct smcd_dev *dev, struct smcd_dmb *dmb);
+ int (*unregister_dmb)(struct smcd_dev *dev, struct smcd_dmb *dmb);
+ int (*add_vlan_id)(struct smcd_dev *dev, u64 vlan_id);
+ int (*del_vlan_id)(struct smcd_dev *dev, u64 vlan_id);
+ int (*set_vlan_required)(struct smcd_dev *dev);
+ int (*reset_vlan_required)(struct smcd_dev *dev);
+ int (*signal_event)(struct smcd_dev *dev, u64 rgid, u32 trigger_irq,
+ u32 event_code, u64 info);
+ int (*move_data)(struct smcd_dev *dev, u64 dmb_tok, unsigned int idx,
+ bool sf, unsigned int offset, void *data,
+ unsigned int size);
+};
+
+struct smcd_dev {
+ const struct smcd_ops *ops;
+ struct device dev;
+ void *priv;
+ u64 local_gid;
+ struct list_head list;
+ spinlock_t lock;
+ struct smc_connection **conn;
+ struct list_head vlan;
+ struct workqueue_struct *event_wq;
+ u8 pnetid[SMC_MAX_PNETID_LEN];
+};
+
+struct smcd_dev *smcd_alloc_dev(struct device *parent, const char *name,
+ const struct smcd_ops *ops, int max_dmbs);
+int smcd_register_dev(struct smcd_dev *smcd);
+void smcd_unregister_dev(struct smcd_dev *smcd);
+void smcd_free_dev(struct smcd_dev *smcd);
+void smcd_handle_event(struct smcd_dev *dev, struct smcd_event *event);
+void smcd_handle_irq(struct smcd_dev *dev, unsigned int bit);
#endif /* _SMC_H */
* @skc_node: main hash linkage for various protocol lookup tables
* @skc_nulls_node: main hash linkage for TCP/UDP/UDP-Lite protocol
* @skc_tx_queue_mapping: tx queue number for this connection
+ * @skc_rx_queue_mapping: rx queue number for this connection
* @skc_flags: place holder for sk_flags
* %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE,
* %SO_OOBINLINE settings, %SO_TIMESTAMPING settings
struct hlist_node skc_node;
struct hlist_nulls_node skc_nulls_node;
};
- int skc_tx_queue_mapping;
+ unsigned short skc_tx_queue_mapping;
+#ifdef CONFIG_XPS
+ unsigned short skc_rx_queue_mapping;
+#endif
union {
int skc_incoming_cpu;
u32 skc_rcv_wnd;
* @sk_destruct: called at sock freeing time, i.e. when all refcnt == 0
* @sk_reuseport_cb: reuseport group container
* @sk_rcu: used during RCU grace period
+ * @sk_clockid: clockid used by time-based scheduling (SO_TXTIME)
+ * @sk_txtime_deadline_mode: set deadline mode for SO_TXTIME
+ * @sk_txtime_unused: unused txtime flags
*/
struct sock {
/*
#define sk_nulls_node __sk_common.skc_nulls_node
#define sk_refcnt __sk_common.skc_refcnt
#define sk_tx_queue_mapping __sk_common.skc_tx_queue_mapping
+#ifdef CONFIG_XPS
+#define sk_rx_queue_mapping __sk_common.skc_rx_queue_mapping
+#endif
#define sk_dontcopy_begin __sk_common.skc_dontcopy_begin
#define sk_dontcopy_end __sk_common.skc_dontcopy_end
u8 sk_shutdown;
u32 sk_tskey;
atomic_t sk_zckey;
+
+ u8 sk_clockid;
+ u8 sk_txtime_deadline_mode : 1,
+ sk_txtime_report_errors : 1,
+ sk_txtime_unused : 6;
+
struct socket *sk_socket;
void *sk_user_data;
#ifdef CONFIG_SECURITY
SOCK_FILTER_LOCKED, /* Filter cannot be changed anymore */
SOCK_SELECT_ERR_QUEUE, /* Wake select on error queue */
SOCK_RCU_FREE, /* wait rcu grace period in sk_destruct() */
+ SOCK_TXTIME,
};
#define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE))
void sk_send_sigurg(struct sock *sk);
struct sockcm_cookie {
+ u64 transmit_time;
u32 mark;
u16 tsflags;
};
+static inline void sockcm_init(struct sockcm_cookie *sockc,
+ const struct sock *sk)
+{
+ *sockc = (struct sockcm_cookie) { .tsflags = sk->sk_tsflags };
+}
+
int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg,
struct sockcm_cookie *sockc);
int sock_cmsg_send(struct sock *sk, struct msghdr *msg,
static inline void sk_tx_queue_set(struct sock *sk, int tx_queue)
{
+ /* sk_tx_queue_mapping accept only upto a 16-bit value */
+ if (WARN_ON_ONCE((unsigned short)tx_queue >= USHRT_MAX))
+ return;
sk->sk_tx_queue_mapping = tx_queue;
}
+#define NO_QUEUE_MAPPING USHRT_MAX
+
static inline void sk_tx_queue_clear(struct sock *sk)
{
- sk->sk_tx_queue_mapping = -1;
+ sk->sk_tx_queue_mapping = NO_QUEUE_MAPPING;
}
static inline int sk_tx_queue_get(const struct sock *sk)
{
- return sk ? sk->sk_tx_queue_mapping : -1;
+ if (sk && sk->sk_tx_queue_mapping != NO_QUEUE_MAPPING)
+ return sk->sk_tx_queue_mapping;
+
+ return -1;
+}
+
+static inline void sk_rx_queue_set(struct sock *sk, const struct sk_buff *skb)
+{
+#ifdef CONFIG_XPS
+ if (skb_rx_queue_recorded(skb)) {
+ u16 rx_queue = skb_get_rx_queue(skb);
+
+ if (WARN_ON_ONCE(rx_queue == NO_QUEUE_MAPPING))
+ return;
+
+ sk->sk_rx_queue_mapping = rx_queue;
+ }
+#endif
}
+static inline void sk_rx_queue_clear(struct sock *sk)
+{
+#ifdef CONFIG_XPS
+ sk->sk_rx_queue_mapping = NO_QUEUE_MAPPING;
+#endif
+}
+
+#ifdef CONFIG_XPS
+static inline int sk_rx_queue_get(const struct sock *sk)
+{
+ if (sk && sk->sk_rx_queue_mapping != NO_QUEUE_MAPPING)
+ return sk->sk_rx_queue_mapping;
+
+ return -1;
+}
+#endif
+
static inline void sk_set_socket(struct sock *sk, struct socket *sock)
{
sk_tx_queue_clear(sk);
struct tc_pedit_key *tcfp_keys;
struct tcf_pedit_key_ex *tcfp_keys_ex;
};
+
#define to_pedit(a) ((struct tcf_pedit *)a)
static inline bool is_tcf_pedit(const struct tc_action *a)
#include <net/act_api.h>
#include <linux/tc_act/tc_skbedit.h>
+struct tcf_skbedit_params {
+ u32 flags;
+ u32 priority;
+ u32 mark;
+ u32 mask;
+ u16 queue_mapping;
+ u16 ptype;
+ struct rcu_head rcu;
+};
+
struct tcf_skbedit {
- struct tc_action common;
- u32 flags;
- u32 priority;
- u32 mark;
- u32 mask;
- u16 queue_mapping;
- u16 ptype;
+ struct tc_action common;
+ struct tcf_skbedit_params __rcu *params;
};
#define to_skbedit(a) ((struct tcf_skbedit *)a)
static inline bool is_tcf_skbedit_mark(const struct tc_action *a)
{
#ifdef CONFIG_NET_CLS_ACT
- if (a->ops && a->ops->type == TCA_ACT_SKBEDIT)
- return to_skbedit(a)->flags == SKBEDIT_F_MARK;
+ u32 flags;
+
+ if (a->ops && a->ops->type == TCA_ACT_SKBEDIT) {
+ rcu_read_lock();
+ flags = rcu_dereference(to_skbedit(a)->params)->flags;
+ rcu_read_unlock();
+ return flags == SKBEDIT_F_MARK;
+ }
#endif
return false;
}
static inline u32 tcf_skbedit_mark(const struct tc_action *a)
{
- return to_skbedit(a)->mark;
+ u32 mark;
+
+ rcu_read_lock();
+ mark = rcu_dereference(to_skbedit(a)->params)->mark;
+ rcu_read_unlock();
+
+ return mark;
}
#endif /* __NET_TC_SKBEDIT_H */
void tcp_close(struct sock *sk, long timeout);
void tcp_init_sock(struct sock *sk);
void tcp_init_transfer(struct sock *sk, int bpf_op);
-__poll_t tcp_poll_mask(struct socket *sock, __poll_t events);
+__poll_t tcp_poll(struct file *file, struct socket *sock,
+ struct poll_table_struct *wait);
int tcp_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen);
int tcp_setsockopt(struct sock *sk, int level, int optname,
*/
static inline void tcp_synq_overflow(const struct sock *sk)
{
- unsigned long last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
- unsigned long now = jiffies;
+ unsigned int last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
+ unsigned int now = jiffies;
- if (time_after(now, last_overflow + HZ))
+ if (time_after32(now, last_overflow + HZ))
tcp_sk(sk)->rx_opt.ts_recent_stamp = now;
}
/* syncookies: no recent synqueue overflow on this listening socket? */
static inline bool tcp_synq_no_recent_overflow(const struct sock *sk)
{
- unsigned long last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
+ unsigned int last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
+ unsigned int now = jiffies;
- return time_after(jiffies, last_overflow + TCP_SYNCOOKIE_VALID);
+ return time_after32(now, last_overflow + TCP_SYNCOOKIE_VALID);
}
static inline u32 tcp_cookie_time(void)
u32 prior_delivered; /* tp->delivered at "prior_mstamp" */
s32 delivered; /* number of packets delivered over interval */
long interval_us; /* time for tp->delivered to incr "delivered" */
+ u32 snd_interval_us; /* snd interval for delivered packets */
+ u32 rcv_interval_us; /* rcv interval for delivered packets */
long rtt_us; /* RTT of last (S)ACKed packet (or -1) */
int losses; /* number of packets marked lost upon ACK */
u32 acked_sacked; /* number of packets newly (S)ACKed upon ACK */
return tp->is_cwnd_limited;
}
+/* BBR congestion control needs pacing.
+ * Same remark for SO_MAX_PACING_RATE.
+ * sch_fq packet scheduler is efficiently handling pacing,
+ * but is not always installed/used.
+ * Return true if TCP stack should pace packets itself.
+ */
+static inline bool tcp_needs_internal_pacing(const struct sock *sk)
+{
+ return smp_load_acquire(&sk->sk_pacing_status) == SK_PACING_NEEDED;
+}
+
/* Something is really bad, we could not queue an additional packet,
* because qdisc is full or receiver sent a 0 window.
* We do not want to add fuel to the fire, or abort too early,
{
if ((s32)(rx_opt->ts_recent - rx_opt->rcv_tsval) <= paws_win)
return true;
- if (unlikely(get_seconds() >= rx_opt->ts_recent_stamp + TCP_PAWS_24DAYS))
+ if (unlikely(!time_before32(ktime_get_seconds(),
+ rx_opt->ts_recent_stamp + TCP_PAWS_24DAYS)))
return true;
/*
* Some OSes send SYN and SYNACK messages with tsval=0 tsecr=0,
However, we can relax time bounds for RST segments to MSL.
*/
- if (rst && get_seconds() >= rx_opt->ts_recent_stamp + TCP_PAWS_MSL)
+ if (rst && !time_before32(ktime_get_seconds(),
+ rx_opt->ts_recent_stamp + TCP_PAWS_MSL))
return false;
return true;
}
struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
netdev_features_t features);
-struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb);
+struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb);
int tcp_gro_complete(struct sk_buff *skb);
void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr);
void (*unhash)(struct tls_device *device, struct sock *sk);
};
+enum {
+ TLS_BASE,
+ TLS_SW,
+#ifdef CONFIG_TLS_DEVICE
+ TLS_HW,
+#endif
+ TLS_HW_RECORD,
+ TLS_NUM_CONFIG,
+};
+
struct tls_sw_context_tx {
struct crypto_aead *aead_send;
struct crypto_wait async_wait;
struct strparser strp;
void (*saved_data_ready)(struct sock *sk);
- __poll_t (*sk_poll_mask)(struct socket *sock, __poll_t events);
+ unsigned int (*sk_poll)(struct file *file, struct socket *sock,
+ struct poll_table_struct *wait);
struct sk_buff *recv_pkt;
u8 control;
bool decrypted;
skb_frag_t frags[MAX_SKB_FRAGS];
};
-struct tls_offload_context {
+struct tls_offload_context_tx {
struct crypto_aead *aead_send;
spinlock_t lock; /* protects records list */
struct list_head records_list;
#define TLS_DRIVER_STATE_SIZE (max_t(size_t, 8, sizeof(void *)))
};
-#define TLS_OFFLOAD_CONTEXT_SIZE \
- (ALIGN(sizeof(struct tls_offload_context), sizeof(void *)) + \
+#define TLS_OFFLOAD_CONTEXT_SIZE_TX \
+ (ALIGN(sizeof(struct tls_offload_context_tx), sizeof(void *)) + \
TLS_DRIVER_STATE_SIZE)
enum {
int (*push_pending_record)(struct sock *sk, int flags);
void (*sk_write_space)(struct sock *sk);
+ void (*sk_destruct)(struct sock *sk);
void (*sk_proto_close)(struct sock *sk, long timeout);
int (*setsockopt)(struct sock *sk, int level,
void (*unhash)(struct sock *sk);
};
+struct tls_offload_context_rx {
+ /* sw must be the first member of tls_offload_context_rx */
+ struct tls_sw_context_rx sw;
+ atomic64_t resync_req;
+ u8 driver_state[];
+ /* The TLS layer reserves room for driver specific state
+ * Currently the belief is that there is not enough
+ * driver specific state to justify another layer of indirection
+ */
+};
+
+#define TLS_OFFLOAD_CONTEXT_SIZE_RX \
+ (ALIGN(sizeof(struct tls_offload_context_rx), sizeof(void *)) + \
+ TLS_DRIVER_STATE_SIZE)
+
int wait_on_pending_writer(struct sock *sk, long *timeo);
int tls_sk_query(struct sock *sk, int optname, char __user *optval,
int __user *optlen);
int tls_sk_attach(struct sock *sk, int optname, char __user *optval,
unsigned int optlen);
-
int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx);
int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
int tls_sw_sendpage(struct sock *sk, struct page *page,
void tls_sw_close(struct sock *sk, long timeout);
void tls_sw_free_resources_tx(struct sock *sk);
void tls_sw_free_resources_rx(struct sock *sk);
+void tls_sw_release_resources_rx(struct sock *sk);
int tls_sw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
int nonblock, int flags, int *addr_len);
-__poll_t tls_sw_poll_mask(struct socket *sock, __poll_t events);
+unsigned int tls_sw_poll(struct file *file, struct socket *sock,
+ struct poll_table_struct *wait);
ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos,
struct pipe_inode_info *pipe,
size_t len, unsigned int flags);
void tls_device_init(void);
void tls_device_cleanup(void);
-struct tls_record_info *tls_get_record(struct tls_offload_context *context,
+struct tls_record_info *tls_get_record(struct tls_offload_context_tx *context,
u32 seq, u64 *p_record_sn);
static inline bool tls_record_is_start_marker(struct tls_record_info *rec)
return tls_ctx->pending_open_record_frags;
}
+struct sk_buff *
+tls_validate_xmit_skb(struct sock *sk, struct net_device *dev,
+ struct sk_buff *skb);
+
static inline bool tls_is_sk_tx_device_offloaded(struct sock *sk)
{
- return sk_fullsock(sk) &&
- /* matches smp_store_release in tls_set_device_offload */
- smp_load_acquire(&sk->sk_destruct) == &tls_device_sk_destruct;
+#ifdef CONFIG_SOCK_VALIDATE_XMIT
+ return sk_fullsock(sk) &
+ (smp_load_acquire(&sk->sk_validate_xmit_skb) ==
+ &tls_validate_xmit_skb);
+#else
+ return false;
+#endif
}
static inline void tls_err_abort(struct sock *sk, int err)
return (struct tls_sw_context_tx *)tls_ctx->priv_ctx_tx;
}
-static inline struct tls_offload_context *tls_offload_ctx(
- const struct tls_context *tls_ctx)
+static inline struct tls_offload_context_tx *
+tls_offload_ctx_tx(const struct tls_context *tls_ctx)
{
- return (struct tls_offload_context *)tls_ctx->priv_ctx_tx;
+ return (struct tls_offload_context_tx *)tls_ctx->priv_ctx_tx;
}
+static inline struct tls_offload_context_rx *
+tls_offload_ctx_rx(const struct tls_context *tls_ctx)
+{
+ return (struct tls_offload_context_rx *)tls_ctx->priv_ctx_rx;
+}
+
+/* The TLS context is valid until sk_destruct is called */
+static inline void tls_offload_rx_resync_request(struct sock *sk, __be32 seq)
+{
+ struct tls_context *tls_ctx = tls_get_ctx(sk);
+ struct tls_offload_context_rx *rx_ctx = tls_offload_ctx_rx(tls_ctx);
+
+ atomic64_set(&rx_ctx->resync_req, ((((uint64_t)seq) << 32) | 1));
+}
+
+
int tls_proccess_cmsg(struct sock *sk, struct msghdr *msg,
unsigned char *record_type);
void tls_register_device(struct tls_device *device);
void tls_unregister_device(struct tls_device *device);
+int tls_device_decrypted(struct sock *sk, struct sk_buff *skb);
+int decrypt_skb(struct sock *sk, struct sk_buff *skb,
+ struct scatterlist *sgout);
struct sk_buff *tls_validate_xmit_skb(struct sock *sk,
struct net_device *dev,
struct sk_buff *skb);
int tls_sw_fallback_init(struct sock *sk,
- struct tls_offload_context *offload_ctx,
+ struct tls_offload_context_tx *offload_ctx,
struct tls_crypto_info *crypto_info);
+int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx);
+
+void tls_device_offload_cleanup_rx(struct sock *sk);
+void handle_device_resync(struct sock *sk, u32 seq, u64 rcd_sn);
+
#endif /* _TLS_OFFLOAD_H */
struct sk_buff *skb);
int ip6_datagram_send_ctl(struct net *net, struct sock *sk, struct msghdr *msg,
- struct flowi6 *fl6, struct ipcm6_cookie *ipc6,
- struct sockcm_cookie *sockc);
+ struct flowi6 *fl6, struct ipcm6_cookie *ipc6);
void __ip6_dgram_sock_seq_show(struct seq_file *seq, struct sock *sp,
__u16 srcp, __u16 destp, int rqueue, int bucket);
typedef struct sock *(*udp_lookup_t)(struct sk_buff *skb, __be16 sport,
__be16 dport);
-struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb,
- struct udphdr *uh, udp_lookup_t lookup);
+struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
+ struct udphdr *uh, udp_lookup_t lookup);
int udp_gro_complete(struct sk_buff *skb, int nhoff, udp_lookup_t lookup);
struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
int udp_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
int __udp_disconnect(struct sock *sk, int flags);
int udp_disconnect(struct sock *sk, int flags);
-__poll_t udp_poll_mask(struct socket *sock, __poll_t events);
+__poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait);
struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
netdev_features_t features,
bool is_ipv6);
typedef int (*udp_tunnel_encap_rcv_t)(struct sock *sk, struct sk_buff *skb);
typedef void (*udp_tunnel_encap_destroy_t)(struct sock *sk);
-typedef struct sk_buff **(*udp_tunnel_gro_receive_t)(struct sock *sk,
- struct sk_buff **head,
- struct sk_buff *skb);
+typedef struct sk_buff *(*udp_tunnel_gro_receive_t)(struct sock *sk,
+ struct list_head *head,
+ struct sk_buff *skb);
typedef int (*udp_tunnel_gro_complete_t)(struct sock *sk, struct sk_buff *skb,
int nhoff);
return unlikely(xdp->data_meta > xdp->data);
}
+struct xdp_attachment_info {
+ struct bpf_prog *prog;
+ u32 flags;
+};
+
+struct netdev_bpf;
+int xdp_attachment_query(struct xdp_attachment_info *info,
+ struct netdev_bpf *bpf);
+bool xdp_attachment_flags_ok(struct xdp_attachment_info *info,
+ struct netdev_bpf *bpf);
+void xdp_attachment_setup(struct xdp_attachment_info *info,
+ struct netdev_bpf *bpf);
+
#endif /* __LINUX_NET_XDP_H__ */
*
* Users can examine the cq structure to determine the actual CQ size.
*/
-struct ib_cq *ib_create_cq(struct ib_device *device,
- ib_comp_handler comp_handler,
- void (*event_handler)(struct ib_event *, void *),
- void *cq_context,
- const struct ib_cq_init_attr *cq_attr);
+struct ib_cq *__ib_create_cq(struct ib_device *device,
+ ib_comp_handler comp_handler,
+ void (*event_handler)(struct ib_event *, void *),
+ void *cq_context,
+ const struct ib_cq_init_attr *cq_attr,
+ const char *caller);
+#define ib_create_cq(device, cmp_hndlr, evt_hndlr, cq_ctxt, cq_attr) \
+ __ib_create_cq((device), (cmp_hndlr), (evt_hndlr), (cq_ctxt), (cq_attr), KBUILD_MODNAME)
/**
* ib_resize_cq - Modifies the capacity of the CQ.
TP_ARGS(skb)
);
+DEFINE_EVENT(net_dev_rx_verbose_template, netif_receive_skb_list_entry,
+
+ TP_PROTO(const struct sk_buff *skb),
+
+ TP_ARGS(skb)
+);
+
DEFINE_EVENT(net_dev_rx_verbose_template, netif_rx_entry,
TP_PROTO(const struct sk_buff *skb),
EM(TCP_CLOSING) \
EMe(TCP_NEW_SYN_RECV)
+#define skmem_kind_names \
+ EM(SK_MEM_SEND) \
+ EMe(SK_MEM_RECV)
+
/* enums need to be exported to user space */
#undef EM
#undef EMe
family_names
inet_protocol_names
tcp_state_names
+skmem_kind_names
#undef EM
#undef EMe
#define show_tcp_state_name(val) \
__print_symbolic(val, tcp_state_names)
+#define show_skmem_kind_names(val) \
+ __print_symbolic(val, skmem_kind_names)
+
TRACE_EVENT(sock_rcvqueue_full,
TP_PROTO(struct sock *sk, struct sk_buff *skb),
TRACE_EVENT(sock_exceed_buf_limit,
- TP_PROTO(struct sock *sk, struct proto *prot, long allocated),
+ TP_PROTO(struct sock *sk, struct proto *prot, long allocated, int kind),
- TP_ARGS(sk, prot, allocated),
+ TP_ARGS(sk, prot, allocated, kind),
TP_STRUCT__entry(
__array(char, name, 32)
__field(long, allocated)
__field(int, sysctl_rmem)
__field(int, rmem_alloc)
+ __field(int, sysctl_wmem)
+ __field(int, wmem_alloc)
+ __field(int, wmem_queued)
+ __field(int, kind)
),
TP_fast_assign(
__entry->allocated = allocated;
__entry->sysctl_rmem = sk_get_rmem0(sk, prot);
__entry->rmem_alloc = atomic_read(&sk->sk_rmem_alloc);
+ __entry->sysctl_wmem = sk_get_wmem0(sk, prot);
+ __entry->wmem_alloc = refcount_read(&sk->sk_wmem_alloc);
+ __entry->wmem_queued = sk->sk_wmem_queued;
+ __entry->kind = kind;
),
- TP_printk("proto:%s sysctl_mem=%ld,%ld,%ld allocated=%ld "
- "sysctl_rmem=%d rmem_alloc=%d",
+ TP_printk("proto:%s sysctl_mem=%ld,%ld,%ld allocated=%ld sysctl_rmem=%d rmem_alloc=%d sysctl_wmem=%d wmem_alloc=%d wmem_queued=%d kind=%s",
__entry->name,
__entry->sysctl_mem[0],
__entry->sysctl_mem[1],
__entry->sysctl_mem[2],
__entry->allocated,
__entry->sysctl_rmem,
- __entry->rmem_alloc)
+ __entry->rmem_alloc,
+ __entry->sysctl_wmem,
+ __entry->wmem_alloc,
+ __entry->wmem_queued,
+ show_skmem_kind_names(__entry->kind)
+ )
);
TRACE_EVENT(inet_sock_set_state,
#define SO_ZEROCOPY 60
+#define SO_TXTIME 61
+#define SCM_TXTIME SO_TXTIME
+
#endif /* __ASM_GENERIC_SOCKET_H */
IOCB_CMD_PWRITE = 1,
IOCB_CMD_FSYNC = 2,
IOCB_CMD_FDSYNC = 3,
- /* 4 was the experimental IOCB_CMD_PREADX */
- IOCB_CMD_POLL = 5,
+ /* These two are experimental.
+ * IOCB_CMD_PREADX = 4,
+ * IOCB_CMD_POLL = 5,
+ */
IOCB_CMD_NOOP = 6,
IOCB_CMD_PREADV = 7,
IOCB_CMD_PWRITEV = 8,
* A non-negative value equal to or less than *size* on success,
* or a negative error in case of failure.
*
- * int skb_load_bytes_relative(const struct sk_buff *skb, u32 offset, void *to, u32 len, u32 start_header)
+ * int bpf_skb_load_bytes_relative(const struct sk_buff *skb, u32 offset, void *to, u32 len, u32 start_header)
* Description
* This helper is similar to **bpf_skb_load_bytes**\ () in that
* it provides an easy way to load *len* bytes from *offset*
* is resolved), the nexthop address is returned in ipv4_dst
* or ipv6_dst based on family, smac is set to mac address of
* egress device, dmac is set to nexthop mac address, rt_metric
- * is set to metric from route (IPv4/IPv6 only).
+ * is set to metric from route (IPv4/IPv6 only), and ifindex
+ * is set to the device index of the nexthop from the FIB lookup.
*
* *plen* argument is the size of the passed in struct.
* *flags* argument can be a combination of one or more of the
* *ctx* is either **struct xdp_md** for XDP programs or
* **struct sk_buff** tc cls_act programs.
* Return
- * Egress device index on success, 0 if packet needs to continue
- * up the stack for further processing or a negative error in case
- * of failure.
+ * * < 0 if any input argument is invalid
+ * * 0 on success (packet is forwarded, nexthop neighbor exists)
+ * * > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the
+ * packet is not forwarded or needs assist from full stack
*
* int bpf_sock_hash_update(struct bpf_sock_ops_kern *skops, struct bpf_map *map, void *key, u64 flags)
* Description
* This helper is only available is the kernel was compiled with
* the **CONFIG_BPF_LIRC_MODE2** configuration option set to
* "**y**".
- *
* Return
* 0
*
* This helper is only available is the kernel was compiled with
* the **CONFIG_BPF_LIRC_MODE2** configuration option set to
* "**y**".
- *
* Return
* 0
*
* Arg1: old_state
* Arg2: new_state
*/
+ BPF_SOCK_OPS_TCP_LISTEN_CB, /* Called on listen(2), right after
+ * socket transition to LISTEN state.
+ */
};
/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
#define BPF_FIB_LOOKUP_DIRECT BIT(0)
#define BPF_FIB_LOOKUP_OUTPUT BIT(1)
+enum {
+ BPF_FIB_LKUP_RET_SUCCESS, /* lookup successful */
+ BPF_FIB_LKUP_RET_BLACKHOLE, /* dest is blackholed; can be dropped */
+ BPF_FIB_LKUP_RET_UNREACHABLE, /* dest is unreachable; can be dropped */
+ BPF_FIB_LKUP_RET_PROHIBIT, /* dest not allowed; can be dropped */
+ BPF_FIB_LKUP_RET_NOT_FWDED, /* packet is not forwarded */
+ BPF_FIB_LKUP_RET_FWD_DISABLED, /* fwding is not enabled on ingress */
+ BPF_FIB_LKUP_RET_UNSUPP_LWT, /* fwd requires encapsulation */
+ BPF_FIB_LKUP_RET_NO_NEIGH, /* no neighbor entry for nh */
+ BPF_FIB_LKUP_RET_FRAG_NEEDED, /* fragmentation required to fwd */
+};
+
struct bpf_fib_lookup {
/* input: network family for lookup (AF_INET, AF_INET6)
* output: network family of egress nexthop
/* total length of packet from network header - used for MTU check */
__u16 tot_len;
- __u32 ifindex; /* L3 device index for lookup */
+
+ /* input: L3 device index for lookup
+ * output: device index from FIB lookup
+ */
+ __u32 ifindex;
union {
/* inputs to lookup */
*/
DEVLINK_CMD_RELOAD,
+ DEVLINK_CMD_PARAM_GET, /* can dump */
+ DEVLINK_CMD_PARAM_SET,
+ DEVLINK_CMD_PARAM_NEW,
+ DEVLINK_CMD_PARAM_DEL,
+
+ DEVLINK_CMD_REGION_GET,
+ DEVLINK_CMD_REGION_SET,
+ DEVLINK_CMD_REGION_NEW,
+ DEVLINK_CMD_REGION_DEL,
+ DEVLINK_CMD_REGION_READ,
+
/* add new commands above here */
__DEVLINK_CMD_MAX,
DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1
*/
};
+enum devlink_param_cmode {
+ DEVLINK_PARAM_CMODE_RUNTIME,
+ DEVLINK_PARAM_CMODE_DRIVERINIT,
+ DEVLINK_PARAM_CMODE_PERMANENT,
+
+ /* Add new configuration modes above */
+ __DEVLINK_PARAM_CMODE_MAX,
+ DEVLINK_PARAM_CMODE_MAX = __DEVLINK_PARAM_CMODE_MAX - 1
+};
+
enum devlink_attr {
/* don't change the order or add anything between, this is ABI! */
DEVLINK_ATTR_UNSPEC,
DEVLINK_ATTR_PORT_NUMBER, /* u32 */
DEVLINK_ATTR_PORT_SPLIT_SUBPORT_NUMBER, /* u32 */
+ DEVLINK_ATTR_PARAM, /* nested */
+ DEVLINK_ATTR_PARAM_NAME, /* string */
+ DEVLINK_ATTR_PARAM_GENERIC, /* flag */
+ DEVLINK_ATTR_PARAM_TYPE, /* u8 */
+ DEVLINK_ATTR_PARAM_VALUES_LIST, /* nested */
+ DEVLINK_ATTR_PARAM_VALUE, /* nested */
+ DEVLINK_ATTR_PARAM_VALUE_DATA, /* dynamic */
+ DEVLINK_ATTR_PARAM_VALUE_CMODE, /* u8 */
+
+ DEVLINK_ATTR_REGION_NAME, /* string */
+ DEVLINK_ATTR_REGION_SIZE, /* u64 */
+ DEVLINK_ATTR_REGION_SNAPSHOTS, /* nested */
+ DEVLINK_ATTR_REGION_SNAPSHOT, /* nested */
+ DEVLINK_ATTR_REGION_SNAPSHOT_ID, /* u32 */
+
+ DEVLINK_ATTR_REGION_CHUNKS, /* nested */
+ DEVLINK_ATTR_REGION_CHUNK, /* nested */
+ DEVLINK_ATTR_REGION_CHUNK_DATA, /* binary */
+ DEVLINK_ATTR_REGION_CHUNK_ADDR, /* u64 */
+ DEVLINK_ATTR_REGION_CHUNK_LEN, /* u64 */
+
/* add new attributes above here, update the policy in devlink.c */
__DEVLINK_ATTR_MAX,
#define SO_EE_ORIGIN_ICMP6 3
#define SO_EE_ORIGIN_TXSTATUS 4
#define SO_EE_ORIGIN_ZEROCOPY 5
+#define SO_EE_ORIGIN_TXTIME 6
#define SO_EE_ORIGIN_TIMESTAMPING SO_EE_ORIGIN_TXSTATUS
#define SO_EE_OFFENDER(ee) ((struct sockaddr*)((ee)+1))
#define SO_EE_CODE_ZEROCOPY_COPIED 1
+#define SO_EE_CODE_TXTIME_INVALID_PARAM 1
+#define SO_EE_CODE_TXTIME_MISSED 2
+
/**
* struct scm_timestamping - timestamps exposed through cmsg
*
XDP_ATTACHED_DRV,
XDP_ATTACHED_SKB,
XDP_ATTACHED_HW,
+ XDP_ATTACHED_MULTI,
};
enum {
IFLA_XDP_ATTACHED,
IFLA_XDP_FLAGS,
IFLA_XDP_PROG_ID,
+ IFLA_XDP_DRV_PROG_ID,
+ IFLA_XDP_SKB_PROG_ID,
+ IFLA_XDP_HW_PROG_ID,
__IFLA_XDP_MAX,
};
ILA_CMD_ADD,
ILA_CMD_DEL,
ILA_CMD_GET,
+ ILA_CMD_FLUSH,
__ILA_CMD_MAX,
};
IPMRA_TABLE_MROUTE_DO_ASSERT,
IPMRA_TABLE_MROUTE_DO_PIM,
IPMRA_TABLE_VIFS,
+ IPMRA_TABLE_MROUTE_DO_WRVIFWHOLE,
__IPMRA_TABLE_MAX
};
#define IPMRA_TABLE_MAX (__IPMRA_TABLE_MAX - 1)
#define IGMPMSG_NOCACHE 1 /* Kern cache fill request to mrouted */
#define IGMPMSG_WRONGVIF 2 /* For PIM assert processing (unused) */
#define IGMPMSG_WHOLEPKT 3 /* For PIM Register processing */
+#define IGMPMSG_WRVIFWHOLE 4 /* For PIM Register and assert processing */
#endif /* _UAPI__LINUX_MROUTE_H */
/* These are client behavior specific flags. */
#define NBD_CFLAG_DESTROY_ON_DISCONNECT (1 << 0) /* delete the nbd device on
disconnect. */
+#define NBD_CFLAG_DISCONNECT_ON_CLOSE (1 << 1) /* disconnect the nbd device on
+ * close by last opener.
+ */
/* userspace doesn't need the nbd_device structure */
__u32 reserved[2];
};
+/*
+ * SO_TXTIME gets a struct sock_txtime with flags being an integer bit
+ * field comprised of these values.
+ */
+enum txtime_flags {
+ SOF_TXTIME_DEADLINE_MODE = (1 << 0),
+ SOF_TXTIME_REPORT_ERRORS = (1 << 1),
+
+ SOF_TXTIME_FLAGS_LAST = SOF_TXTIME_REPORT_ERRORS,
+ SOF_TXTIME_FLAGS_MASK = (SOF_TXTIME_FLAGS_LAST - 1) |
+ SOF_TXTIME_FLAGS_LAST
+};
+
+struct sock_txtime {
+ clockid_t clockid; /* reference clockid */
+ __u32 flags; /* as defined by enum txtime_flags */
+};
+
#endif /* _NET_TIMESTAMPING_H */
* enforced.
* @NL80211_ATTR_TXQ_QUANTUM: TXQ scheduler quantum (bytes). Number of bytes
* a flow is assigned on each round of the DRR scheduler.
+ * @NL80211_ATTR_HE_CAPABILITY: HE Capability information element (from
+ * association request when used with NL80211_CMD_NEW_STATION). Can be set
+ * only if %NL80211_STA_FLAG_WME is set.
*
* @NUM_NL80211_ATTR: total number of nl80211_attrs available
* @NL80211_ATTR_MAX: highest attribute number currently defined
NL80211_ATTR_TXQ_MEMORY_LIMIT,
NL80211_ATTR_TXQ_QUANTUM,
+ NL80211_ATTR_HE_CAPABILITY,
+
/* add attributes here, update the policy in nl80211.c */
__NL80211_ATTR_AFTER_LAST,
#define NL80211_TKIP_DATA_OFFSET_RX_MIC_KEY 24
#define NL80211_HT_CAPABILITY_LEN 26
#define NL80211_VHT_CAPABILITY_LEN 12
-
+#define NL80211_HE_MIN_CAPABILITY_LEN 16
+#define NL80211_HE_MAX_CAPABILITY_LEN 51
#define NL80211_MAX_NR_CIPHER_SUITES 5
#define NL80211_MAX_NR_AKM_SUITES 2
__u32 set;
} __attribute__((packed));
+/**
+ * enum nl80211_he_gi - HE guard interval
+ * @NL80211_RATE_INFO_HE_GI_0_8: 0.8 usec
+ * @NL80211_RATE_INFO_HE_GI_1_6: 1.6 usec
+ * @NL80211_RATE_INFO_HE_GI_3_2: 3.2 usec
+ */
+enum nl80211_he_gi {
+ NL80211_RATE_INFO_HE_GI_0_8,
+ NL80211_RATE_INFO_HE_GI_1_6,
+ NL80211_RATE_INFO_HE_GI_3_2,
+};
+
+/**
+ * enum nl80211_he_ru_alloc - HE RU allocation values
+ * @NL80211_RATE_INFO_HE_RU_ALLOC_26: 26-tone RU allocation
+ * @NL80211_RATE_INFO_HE_RU_ALLOC_52: 52-tone RU allocation
+ * @NL80211_RATE_INFO_HE_RU_ALLOC_106: 106-tone RU allocation
+ * @NL80211_RATE_INFO_HE_RU_ALLOC_242: 242-tone RU allocation
+ * @NL80211_RATE_INFO_HE_RU_ALLOC_484: 484-tone RU allocation
+ * @NL80211_RATE_INFO_HE_RU_ALLOC_996: 996-tone RU allocation
+ * @NL80211_RATE_INFO_HE_RU_ALLOC_2x996: 2x996-tone RU allocation
+ */
+enum nl80211_he_ru_alloc {
+ NL80211_RATE_INFO_HE_RU_ALLOC_26,
+ NL80211_RATE_INFO_HE_RU_ALLOC_52,
+ NL80211_RATE_INFO_HE_RU_ALLOC_106,
+ NL80211_RATE_INFO_HE_RU_ALLOC_242,
+ NL80211_RATE_INFO_HE_RU_ALLOC_484,
+ NL80211_RATE_INFO_HE_RU_ALLOC_996,
+ NL80211_RATE_INFO_HE_RU_ALLOC_2x996,
+};
+
/**
* enum nl80211_rate_info - bitrate information
*
* @NL80211_RATE_INFO_5_MHZ_WIDTH: 5 MHz width - note that this is
* a legacy rate and will be reported as the actual bitrate, i.e.
* a quarter of the base (20 MHz) rate
+ * @NL80211_RATE_INFO_HE_MCS: HE MCS index (u8, 0-11)
+ * @NL80211_RATE_INFO_HE_NSS: HE NSS value (u8, 1-8)
+ * @NL80211_RATE_INFO_HE_GI: HE guard interval identifier
+ * (u8, see &enum nl80211_he_gi)
+ * @NL80211_RATE_INFO_HE_DCM: HE DCM value (u8, 0/1)
+ * @NL80211_RATE_INFO_RU_ALLOC: HE RU allocation, if not present then
+ * non-OFDMA was used (u8, see &enum nl80211_he_ru_alloc)
* @__NL80211_RATE_INFO_AFTER_LAST: internal use
*/
enum nl80211_rate_info {
NL80211_RATE_INFO_160_MHZ_WIDTH,
NL80211_RATE_INFO_10_MHZ_WIDTH,
NL80211_RATE_INFO_5_MHZ_WIDTH,
+ NL80211_RATE_INFO_HE_MCS,
+ NL80211_RATE_INFO_HE_NSS,
+ NL80211_RATE_INFO_HE_GI,
+ NL80211_RATE_INFO_HE_DCM,
+ NL80211_RATE_INFO_HE_RU_ALLOC,
/* keep last */
__NL80211_RATE_INFO_AFTER_LAST,
NL80211_MPATH_INFO_MAX = __NL80211_MPATH_INFO_AFTER_LAST - 1
};
+/**
+ * enum nl80211_band_iftype_attr - Interface type data attributes
+ *
+ * @__NL80211_BAND_IFTYPE_ATTR_INVALID: attribute number 0 is reserved
+ * @NL80211_BAND_IFTYPE_ATTR_IFTYPES: nested attribute containing a flag attribute
+ * for each interface type that supports the band data
+ * @NL80211_BAND_IFTYPE_ATTR_HE_CAP_MAC: HE MAC capabilities as in HE
+ * capabilities IE
+ * @NL80211_BAND_IFTYPE_ATTR_HE_CAP_PHY: HE PHY capabilities as in HE
+ * capabilities IE
+ * @NL80211_BAND_IFTYPE_ATTR_HE_CAP_MCS_SET: HE supported NSS/MCS as in HE
+ * capabilities IE
+ * @NL80211_BAND_IFTYPE_ATTR_HE_CAP_PPE: HE PPE thresholds information as
+ * defined in HE capabilities IE
+ * @NL80211_BAND_IFTYPE_ATTR_MAX: highest band HE capability attribute currently
+ * defined
+ * @__NL80211_BAND_IFTYPE_ATTR_AFTER_LAST: internal use
+ */
+enum nl80211_band_iftype_attr {
+ __NL80211_BAND_IFTYPE_ATTR_INVALID,
+
+ NL80211_BAND_IFTYPE_ATTR_IFTYPES,
+ NL80211_BAND_IFTYPE_ATTR_HE_CAP_MAC,
+ NL80211_BAND_IFTYPE_ATTR_HE_CAP_PHY,
+ NL80211_BAND_IFTYPE_ATTR_HE_CAP_MCS_SET,
+ NL80211_BAND_IFTYPE_ATTR_HE_CAP_PPE,
+
+ /* keep last */
+ __NL80211_BAND_IFTYPE_ATTR_AFTER_LAST,
+ NL80211_BAND_IFTYPE_ATTR_MAX = __NL80211_BAND_IFTYPE_ATTR_AFTER_LAST - 1
+};
+
/**
* enum nl80211_band_attr - band attributes
* @__NL80211_BAND_ATTR_INVALID: attribute number 0 is reserved
* @NL80211_BAND_ATTR_VHT_MCS_SET: 32-byte attribute containing the MCS set as
* defined in 802.11ac
* @NL80211_BAND_ATTR_VHT_CAPA: VHT capabilities, as in the HT information IE
+ * @NL80211_BAND_ATTR_IFTYPE_DATA: nested array attribute, with each entry using
+ * attributes from &enum nl80211_band_iftype_attr
* @NL80211_BAND_ATTR_MAX: highest band attribute currently defined
* @__NL80211_BAND_ATTR_AFTER_LAST: internal use
*/
NL80211_BAND_ATTR_VHT_MCS_SET,
NL80211_BAND_ATTR_VHT_CAPA,
+ NL80211_BAND_ATTR_IFTYPE_DATA,
/* keep last */
__NL80211_BAND_ATTR_AFTER_LAST,
* support to nl80211.
* @NL80211_EXT_FEATURE_TXQS: Driver supports FQ-CoDel-enabled intermediate
* TXQs.
+ * @NL80211_EXT_FEATURE_SCAN_RANDOM_SN: Driver/device supports randomizing the
+ * SN in probe request frames if requested by %NL80211_SCAN_FLAG_RANDOM_SN.
+ * @NL80211_EXT_FEATURE_SCAN_MIN_PREQ_CONTENT: Driver/device can omit all data
+ * except for supported rates from the probe request content if requested
+ * by the %NL80211_SCAN_FLAG_MIN_PREQ_CONTENT flag.
*
* @NUM_NL80211_EXT_FEATURES: number of extended features.
* @MAX_NL80211_EXT_FEATURES: highest extended feature index.
NL80211_EXT_FEATURE_CONTROL_PORT_OVER_NL80211,
NL80211_EXT_FEATURE_DATA_ACK_SIGNAL_SUPPORT,
NL80211_EXT_FEATURE_TXQS,
+ NL80211_EXT_FEATURE_SCAN_RANDOM_SN,
+ NL80211_EXT_FEATURE_SCAN_MIN_PREQ_CONTENT,
/* add new features before the definition below */
NUM_NL80211_EXT_FEATURES,
* possible scan results. This flag hints the driver to use the best
* possible scan configuration to improve the accuracy in scanning.
* Latency and power use may get impacted with this flag.
+ * @NL80211_SCAN_FLAG_RANDOM_SN: randomize the sequence number in probe
+ * request frames from this scan to avoid correlation/tracking being
+ * possible.
+ * @NL80211_SCAN_FLAG_MIN_PREQ_CONTENT: minimize probe request content to
+ * only have supported rates and no additional capabilities (unless
+ * added by userspace explicitly.)
*/
enum nl80211_scan_flags {
NL80211_SCAN_FLAG_LOW_PRIORITY = 1<<0,
NL80211_SCAN_FLAG_LOW_SPAN = 1<<8,
NL80211_SCAN_FLAG_LOW_POWER = 1<<9,
NL80211_SCAN_FLAG_HIGH_ACCURACY = 1<<10,
+ NL80211_SCAN_FLAG_RANDOM_SN = 1<<11,
+ NL80211_SCAN_FLAG_MIN_PREQ_CONTENT = 1<<12,
};
/**
* @OVS_ACTION_ATTR_POP_NSH: pop the outermost NSH header off the packet.
* @OVS_ACTION_ATTR_METER: Run packet through a meter, which may drop the
* packet, or modify the packet (e.g., change the DSCP field).
+ * @OVS_ACTION_ATTR_CLONE: make a copy of the packet and execute a list of
+ * actions without affecting the original packet and key.
*
* Only a single header can be set with a single %OVS_ACTION_ATTR_SET. Not all
* fields within a header are modifiable, e.g. the IPv4 protocol and fragment
OVS_ACTION_ATTR_PUSH_NSH, /* Nested OVS_NSH_KEY_ATTR_*. */
OVS_ACTION_ATTR_POP_NSH, /* No argument. */
OVS_ACTION_ATTR_METER, /* u32 meter ID. */
+ OVS_ACTION_ATTR_CLONE, /* Nested OVS_CLONE_ATTR_*. */
__OVS_ACTION_ATTR_MAX, /* Nothing past this will be accepted
* from userspace. */
TCA_FLOWER_KEY_IP_TTL, /* u8 */
TCA_FLOWER_KEY_IP_TTL_MASK, /* u8 */
+ TCA_FLOWER_KEY_CVLAN_ID, /* be16 */
+ TCA_FLOWER_KEY_CVLAN_PRIO, /* u8 */
+ TCA_FLOWER_KEY_CVLAN_ETH_TYPE, /* be16 */
+
__TCA_FLOWER_MAX,
};
TCA_NETEM_LATENCY64,
TCA_NETEM_JITTER64,
TCA_NETEM_SLOT,
+ TCA_NETEM_SLOT_DIST,
__TCA_NETEM_MAX,
};
__s64 max_delay;
__s32 max_packets;
__s32 max_bytes;
+ __s64 dist_delay; /* nsec */
+ __s64 dist_jitter; /* nsec */
};
enum {
#define TCA_CBS_MAX (__TCA_CBS_MAX - 1)
+
+/* ETF */
+struct tc_etf_qopt {
+ __s32 delta;
+ __s32 clockid;
+ __u32 flags;
+#define TC_ETF_DEADLINE_MODE_ON BIT(0)
+#define TC_ETF_OFFLOAD_ON BIT(1)
+};
+
+enum {
+ TCA_ETF_UNSPEC,
+ TCA_ETF_PARMS,
+ __TCA_ETF_MAX,
+};
+
+#define TCA_ETF_MAX (__TCA_ETF_MAX - 1)
+
+
+/* CAKE */
+enum {
+ TCA_CAKE_UNSPEC,
+ TCA_CAKE_PAD,
+ TCA_CAKE_BASE_RATE64,
+ TCA_CAKE_DIFFSERV_MODE,
+ TCA_CAKE_ATM,
+ TCA_CAKE_FLOW_MODE,
+ TCA_CAKE_OVERHEAD,
+ TCA_CAKE_RTT,
+ TCA_CAKE_TARGET,
+ TCA_CAKE_AUTORATE,
+ TCA_CAKE_MEMORY,
+ TCA_CAKE_NAT,
+ TCA_CAKE_RAW,
+ TCA_CAKE_WASH,
+ TCA_CAKE_MPU,
+ TCA_CAKE_INGRESS,
+ TCA_CAKE_ACK_FILTER,
+ TCA_CAKE_SPLIT_GSO,
+ __TCA_CAKE_MAX
+};
+#define TCA_CAKE_MAX (__TCA_CAKE_MAX - 1)
+
+enum {
+ __TCA_CAKE_STATS_INVALID,
+ TCA_CAKE_STATS_PAD,
+ TCA_CAKE_STATS_CAPACITY_ESTIMATE64,
+ TCA_CAKE_STATS_MEMORY_LIMIT,
+ TCA_CAKE_STATS_MEMORY_USED,
+ TCA_CAKE_STATS_AVG_NETOFF,
+ TCA_CAKE_STATS_MIN_NETLEN,
+ TCA_CAKE_STATS_MAX_NETLEN,
+ TCA_CAKE_STATS_MIN_ADJLEN,
+ TCA_CAKE_STATS_MAX_ADJLEN,
+ TCA_CAKE_STATS_TIN_STATS,
+ TCA_CAKE_STATS_DEFICIT,
+ TCA_CAKE_STATS_COBALT_COUNT,
+ TCA_CAKE_STATS_DROPPING,
+ TCA_CAKE_STATS_DROP_NEXT_US,
+ TCA_CAKE_STATS_P_DROP,
+ TCA_CAKE_STATS_BLUE_TIMER_US,
+ __TCA_CAKE_STATS_MAX
+};
+#define TCA_CAKE_STATS_MAX (__TCA_CAKE_STATS_MAX - 1)
+
+enum {
+ __TCA_CAKE_TIN_STATS_INVALID,
+ TCA_CAKE_TIN_STATS_PAD,
+ TCA_CAKE_TIN_STATS_SENT_PACKETS,
+ TCA_CAKE_TIN_STATS_SENT_BYTES64,
+ TCA_CAKE_TIN_STATS_DROPPED_PACKETS,
+ TCA_CAKE_TIN_STATS_DROPPED_BYTES64,
+ TCA_CAKE_TIN_STATS_ACKS_DROPPED_PACKETS,
+ TCA_CAKE_TIN_STATS_ACKS_DROPPED_BYTES64,
+ TCA_CAKE_TIN_STATS_ECN_MARKED_PACKETS,
+ TCA_CAKE_TIN_STATS_ECN_MARKED_BYTES64,
+ TCA_CAKE_TIN_STATS_BACKLOG_PACKETS,
+ TCA_CAKE_TIN_STATS_BACKLOG_BYTES,
+ TCA_CAKE_TIN_STATS_THRESHOLD_RATE64,
+ TCA_CAKE_TIN_STATS_TARGET_US,
+ TCA_CAKE_TIN_STATS_INTERVAL_US,
+ TCA_CAKE_TIN_STATS_WAY_INDIRECT_HITS,
+ TCA_CAKE_TIN_STATS_WAY_MISSES,
+ TCA_CAKE_TIN_STATS_WAY_COLLISIONS,
+ TCA_CAKE_TIN_STATS_PEAK_DELAY_US,
+ TCA_CAKE_TIN_STATS_AVG_DELAY_US,
+ TCA_CAKE_TIN_STATS_BASE_DELAY_US,
+ TCA_CAKE_TIN_STATS_SPARSE_FLOWS,
+ TCA_CAKE_TIN_STATS_BULK_FLOWS,
+ TCA_CAKE_TIN_STATS_UNRESPONSIVE_FLOWS,
+ TCA_CAKE_TIN_STATS_MAX_SKBLEN,
+ TCA_CAKE_TIN_STATS_FLOW_QUANTUM,
+ __TCA_CAKE_TIN_STATS_MAX
+};
+#define TCA_CAKE_TIN_STATS_MAX (__TCA_CAKE_TIN_STATS_MAX - 1)
+#define TC_CAKE_MAX_TINS (8)
+
+enum {
+ CAKE_FLOW_NONE = 0,
+ CAKE_FLOW_SRC_IP,
+ CAKE_FLOW_DST_IP,
+ CAKE_FLOW_HOSTS, /* = CAKE_FLOW_SRC_IP | CAKE_FLOW_DST_IP */
+ CAKE_FLOW_FLOWS,
+ CAKE_FLOW_DUAL_SRC, /* = CAKE_FLOW_SRC_IP | CAKE_FLOW_FLOWS */
+ CAKE_FLOW_DUAL_DST, /* = CAKE_FLOW_DST_IP | CAKE_FLOW_FLOWS */
+ CAKE_FLOW_TRIPLE, /* = CAKE_FLOW_HOSTS | CAKE_FLOW_FLOWS */
+ CAKE_FLOW_MAX,
+};
+
+enum {
+ CAKE_DIFFSERV_DIFFSERV3 = 0,
+ CAKE_DIFFSERV_DIFFSERV4,
+ CAKE_DIFFSERV_DIFFSERV8,
+ CAKE_DIFFSERV_BESTEFFORT,
+ CAKE_DIFFSERV_PRECEDENCE,
+ CAKE_DIFFSERV_MAX
+};
+
+enum {
+ CAKE_ACK_NONE = 0,
+ CAKE_ACK_FILTER,
+ CAKE_ACK_AGGRESSIVE,
+ CAKE_ACK_MAX
+};
+
+enum {
+ CAKE_ATM_NONE = 0,
+ CAKE_ATM_ATM,
+ CAKE_ATM_PTM,
+ CAKE_ATM_MAX
+};
+
#endif
#define SCTP_RECVNXTINFO 33
#define SCTP_DEFAULT_SNDINFO 34
#define SCTP_AUTH_DEACTIVATE_KEY 35
+#define SCTP_REUSE_PORT 36
/* Internal Socket Options. Some of the sctp library functions are
* implemented using these socket options.
SPP_SACKDELAY_DISABLE = 1<<6, /*Disable SACK*/
SPP_SACKDELAY = SPP_SACKDELAY_ENABLE | SPP_SACKDELAY_DISABLE,
SPP_HB_TIME_IS_ZERO = 1<<7, /* Set HB delay to 0 */
+ SPP_IPV6_FLOWLABEL = 1<<8,
+ SPP_DSCP = 1<<9,
};
struct sctp_paddrparams {
__u32 spp_pathmtu;
__u32 spp_sackdelay;
__u32 spp_flags;
+ __u32 spp_ipv6_flowlabel;
+ __u8 spp_dscp;
} __attribute__((packed, aligned(4)));
/*
SMC_DIAG_CONNINFO,
SMC_DIAG_LGRINFO,
SMC_DIAG_SHUTDOWN,
+ SMC_DIAG_DMBINFO,
__SMC_DIAG_MAX,
};
struct smc_diag_linkinfo lnk[1];
__u8 role;
};
+
+struct smcd_diag_dmbinfo { /* SMC-D Socket internals */
+ __u32 linkid; /* Link identifier */
+ __u64 peer_gid; /* Peer GID */
+ __u64 my_gid; /* My GID */
+ __u64 token; /* Token of DMB */
+ __u64 peer_token; /* Token of remote DMBE */
+};
+
#endif /* _UAPI_SMC_DIAG_H_ */
LINUX_MIB_TCPDELIVERED, /* TCPDelivered */
LINUX_MIB_TCPDELIVEREDCE, /* TCPDeliveredCE */
LINUX_MIB_TCPACKCOMPRESSED, /* TCPAckCompressed */
+ LINUX_MIB_TCPZEROWINDOWDROP, /* TCPZeroWindowDrop */
+ LINUX_MIB_TCPRCVQDROP, /* TCPRcvQDrop */
__LINUX_MIB_MAX
};
#define TCMU_MAILBOX_VERSION 2
#define ALIGN_SIZE 64 /* Should be enough for most CPUs */
#define TCMU_MAILBOX_FLAG_CAP_OOOC (1 << 0) /* Out-of-order completions */
+#define TCMU_MAILBOX_FLAG_CAP_READ_LEN (1 << 1) /* Read data length */
struct tcmu_mailbox {
__u16 version;
__u16 cmd_id;
__u8 kflags;
#define TCMU_UFLAG_UNKNOWN_OP 0x1
+#define TCMU_UFLAG_READ_LEN 0x2
__u8 uflags;
} __packed;
__u8 scsi_status;
__u8 __pad1;
__u16 __pad2;
- __u32 __pad3;
+ __u32 read_len;
char sense_buffer[TCMU_SENSE_BUFFERSIZE];
} rsp;
};
TCA_PEDIT_KEY_EX,
__TCA_PEDIT_MAX
};
+
#define TCA_PEDIT_MAX (__TCA_PEDIT_MAX - 1)
-
+
enum {
TCA_PEDIT_KEY_EX_HTYPE = 1,
TCA_PEDIT_KEY_EX_CMD = 2,
__TCA_PEDIT_KEY_EX_MAX
};
+
#define TCA_PEDIT_KEY_EX_MAX (__TCA_PEDIT_KEY_EX_MAX - 1)
/* TCA_PEDIT_KEY_EX_HDR_TYPE_NETWROK is a special case for legacy users. It
TCA_PEDIT_KEY_EX_HDR_TYPE_UDP = 5,
__PEDIT_HDR_TYPE_MAX,
};
+
#define TCA_PEDIT_HDR_TYPE_MAX (__PEDIT_HDR_TYPE_MAX - 1)
enum pedit_cmd {
TCA_PEDIT_KEY_EX_CMD_ADD = 1,
__PEDIT_CMD_MAX,
};
+
#define TCA_PEDIT_CMD_MAX (__PEDIT_CMD_MAX - 1)
struct tc_pedit_key {
__u32 offmask;
__u32 shift;
};
-
+
struct tc_pedit_sel {
tc_gen;
unsigned char nkeys;
unsigned char flags;
struct tc_pedit_key keys[0];
};
+
#define tc_pedit tc_pedit_sel
#endif
#define SKBEDIT_F_MARK 0x4
#define SKBEDIT_F_PTYPE 0x8
#define SKBEDIT_F_MASK 0x10
+#define SKBEDIT_F_INHERITDSFIELD 0x20
struct tc_skbedit {
tc_gen;
TCA_SKBEDIT_PAD,
TCA_SKBEDIT_PTYPE,
TCA_SKBEDIT_MASK,
+ TCA_SKBEDIT_FLAGS,
__TCA_SKBEDIT_MAX
};
#define TCA_SKBEDIT_MAX (__TCA_SKBEDIT_MAX - 1)
TCA_TUNNEL_KEY_PAD,
TCA_TUNNEL_KEY_ENC_DST_PORT, /* be16 */
TCA_TUNNEL_KEY_NO_CSUM, /* u8 */
+ TCA_TUNNEL_KEY_ENC_OPTS, /* Nested TCA_TUNNEL_KEY_ENC_OPTS_
+ * attributes
+ */
__TCA_TUNNEL_KEY_MAX,
};
#define TCA_TUNNEL_KEY_MAX (__TCA_TUNNEL_KEY_MAX - 1)
+enum {
+ TCA_TUNNEL_KEY_ENC_OPTS_UNSPEC,
+ TCA_TUNNEL_KEY_ENC_OPTS_GENEVE, /* Nested
+ * TCA_TUNNEL_KEY_ENC_OPTS_
+ * attributes
+ */
+ __TCA_TUNNEL_KEY_ENC_OPTS_MAX,
+};
+
+#define TCA_TUNNEL_KEY_ENC_OPTS_MAX (__TCA_TUNNEL_KEY_ENC_OPTS_MAX - 1)
+
+enum {
+ TCA_TUNNEL_KEY_ENC_OPT_GENEVE_UNSPEC,
+ TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS, /* be16 */
+ TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE, /* u8 */
+ TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA, /* 4 to 128 bytes */
+
+ __TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX,
+};
+
+#define TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX \
+ (__TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX - 1)
+
#endif
TIPC_NLA_SOCK_TIPC_STATE, /* u32 */
TIPC_NLA_SOCK_COOKIE, /* u64 */
TIPC_NLA_SOCK_PAD, /* flag */
+ TIPC_NLA_SOCK_GROUP, /* nest */
__TIPC_NLA_SOCK_MAX,
TIPC_NLA_SOCK_MAX = __TIPC_NLA_SOCK_MAX - 1
TIPC_NLA_MON_PEER_MAX = __TIPC_NLA_MON_PEER_MAX - 1
};
+/* Nest, socket group info */
+enum {
+ TIPC_NLA_SOCK_GROUP_ID, /* u32 */
+ TIPC_NLA_SOCK_GROUP_OPEN, /* flag */
+ TIPC_NLA_SOCK_GROUP_NODE_SCOPE, /* flag */
+ TIPC_NLA_SOCK_GROUP_CLUSTER_SCOPE, /* flag */
+ TIPC_NLA_SOCK_GROUP_INSTANCE, /* u32 */
+ TIPC_NLA_SOCK_GROUP_BC_SEND_NEXT, /* u32 */
+
+ __TIPC_NLA_SOCK_GROUP_MAX,
+ TIPC_NLA_SOCK_GROUP_MAX = __TIPC_NLA_SOCK_GROUP_MAX - 1
+};
+
/* Nest, connection info */
enum {
TIPC_NLA_CON_UNSPEC,
#define xen_hvm_domain() (xen_domain_type == XEN_HVM_DOMAIN)
#define xen_pvh_domain() (xen_pvh)
+#include <linux/types.h>
+
+extern uint32_t xen_start_flags;
+
#ifdef CONFIG_XEN_DOM0
#include <xen/interface/xen.h>
#include <asm/xen/hypervisor.h>
#define xen_initial_domain() (xen_domain() && \
- xen_start_info && xen_start_info->flags & SIF_INITDOMAIN)
+ (xen_start_flags & SIF_INITDOMAIN))
#else /* !CONFIG_XEN_DOM0 */
#define xen_initial_domain() (0)
#endif /* CONFIG_XEN_DOM0 */
depends on HAVE_LD_DEAD_CODE_DATA_ELIMINATION
depends on EXPERT
help
- Select this if the architecture wants to do dead code and
- data elimination with the linker by compiling with
- -ffunction-sections -fdata-sections, and linking with
- --gc-sections.
+ Enable this if you want to do dead code and data elimination with
+ the linker by compiling with -ffunction-sections -fdata-sections,
+ and linking with --gc-sections.
This can reduce on disk and in-memory size of the kernel
code and static data, particularly for small configs and
endmenu # General setup
-config HAVE_GENERIC_DMA_COHERENT
- bool
- default n
-
config RT_MUTEXES
bool
#include <linux/rwsem.h>
#include <linux/nsproxy.h>
#include <linux/ipc_namespace.h>
+#include <linux/rhashtable.h>
#include <asm/current.h>
#include <linux/uaccess.h>
#include <linux/ipc_namespace.h>
#include <linux/sched/wake_q.h>
#include <linux/nospec.h>
+#include <linux/rhashtable.h>
#include <linux/uaccess.h>
#include "util.h"
#include <linux/nsproxy.h>
#include <linux/mount.h>
#include <linux/ipc_namespace.h>
+#include <linux/rhashtable.h>
#include <linux/uaccess.h>
#include <linux/rwsem.h>
#include <linux/memory.h>
#include <linux/ipc_namespace.h>
+#include <linux/rhashtable.h>
#include <asm/unistd.h>
obj-y += irq/
obj-y += rcu/
obj-y += livepatch/
+obj-y += dma/
obj-$(CONFIG_CHECKPOINT_RESTORE) += kcmp.o
obj-$(CONFIG_FREEZER) += freezer.o
return ret;
}
+int cgroup_bpf_prog_attach(const union bpf_attr *attr,
+ enum bpf_prog_type ptype, struct bpf_prog *prog)
+{
+ struct cgroup *cgrp;
+ int ret;
+
+ cgrp = cgroup_get_from_fd(attr->target_fd);
+ if (IS_ERR(cgrp))
+ return PTR_ERR(cgrp);
+
+ ret = cgroup_bpf_attach(cgrp, prog, attr->attach_type,
+ attr->attach_flags);
+ cgroup_put(cgrp);
+ return ret;
+}
+
+int cgroup_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype)
+{
+ struct bpf_prog *prog;
+ struct cgroup *cgrp;
+ int ret;
+
+ cgrp = cgroup_get_from_fd(attr->target_fd);
+ if (IS_ERR(cgrp))
+ return PTR_ERR(cgrp);
+
+ prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
+ if (IS_ERR(prog))
+ prog = NULL;
+
+ ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type, 0);
+ if (prog)
+ bpf_prog_put(prog);
+
+ cgroup_put(cgrp);
+ return ret;
+}
+
+int cgroup_bpf_prog_query(const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ struct cgroup *cgrp;
+ int ret;
+
+ cgrp = cgroup_get_from_fd(attr->query.target_fd);
+ if (IS_ERR(cgrp))
+ return PTR_ERR(cgrp);
+
+ ret = cgroup_bpf_query(cgrp, attr, uattr);
+
+ cgroup_put(cgrp);
+ return ret;
+}
+
/**
* __cgroup_bpf_run_filter_skb() - Run a program for packet filtering
* @sk: The socket sending or receiving traffic
return prog_adj;
}
+void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp)
+{
+ int i;
+
+ for (i = 0; i < fp->aux->func_cnt; i++)
+ bpf_prog_kallsyms_del(fp->aux->func[i]);
+}
+
+void bpf_prog_kallsyms_del_all(struct bpf_prog *fp)
+{
+ bpf_prog_kallsyms_del_subprogs(fp);
+ bpf_prog_kallsyms_del(fp);
+}
+
#ifdef CONFIG_BPF_JIT
/* All BPF JIT sysctl knobs here. */
int bpf_jit_enable __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_ALWAYS_ON);
return 0;
}
+static void bpf_prog_select_func(struct bpf_prog *fp)
+{
+#ifndef CONFIG_BPF_JIT_ALWAYS_ON
+ u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1);
+
+ fp->bpf_func = interpreters[(round_up(stack_depth, 32) / 32) - 1];
+#else
+ fp->bpf_func = __bpf_prog_ret0_warn;
+#endif
+}
+
/**
* bpf_prog_select_runtime - select exec runtime for BPF program
* @fp: bpf_prog populated with internal BPF program
*/
struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
{
-#ifndef CONFIG_BPF_JIT_ALWAYS_ON
- u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1);
+ /* In case of BPF to BPF calls, verifier did all the prep
+ * work with regards to JITing, etc.
+ */
+ if (fp->bpf_func)
+ goto finalize;
- fp->bpf_func = interpreters[(round_up(stack_depth, 32) / 32) - 1];
-#else
- fp->bpf_func = __bpf_prog_ret0_warn;
-#endif
+ bpf_prog_select_func(fp);
/* eBPF JITs can rewrite the program in case constant
* blinding is active. However, in case of error during
if (*err)
return fp;
}
+
+finalize:
bpf_prog_lock_ro(fp);
/* The tail call compatibility check can only be done at
return bq_enqueue(dst, xdpf, dev_rx);
}
+int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
+ struct bpf_prog *xdp_prog)
+{
+ int err;
+
+ err = __xdp_generic_ok_fwd_dev(skb, dst->dev);
+ if (unlikely(err))
+ return err;
+ skb->dev = dst->dev;
+ generic_xdp_tx(skb, xdp_prog);
+
+ return 0;
+}
+
static void *dev_map_lookup_elem(struct bpf_map *map, void *key)
{
struct bpf_dtab_netdev *obj = __dev_map_lookup_elem(map, *(u32 *)key);
u32 n_buckets;
u32 elem_size;
struct bpf_sock_progs progs;
+ struct rcu_head rcu;
};
struct htab_elem {
struct smap_psock_map_entry {
struct list_head list;
struct sock **entry;
- struct htab_elem *hash_link;
- struct bpf_htab *htab;
+ struct htab_elem __rcu *hash_link;
+ struct bpf_htab __rcu *htab;
};
struct smap_psock {
struct bpf_prog *bpf_parse;
struct bpf_prog *bpf_verdict;
struct list_head maps;
+ spinlock_t maps_lock;
/* Back reference used when sock callback trigger sockmap operations */
struct sock *sock;
static int bpf_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
static int bpf_tcp_sendpage(struct sock *sk, struct page *page,
int offset, size_t size, int flags);
+static void bpf_tcp_close(struct sock *sk, long timeout);
static inline struct smap_psock *smap_psock_sk(const struct sock *sk)
{
return !empty;
}
-static struct proto tcp_bpf_proto;
+enum {
+ SOCKMAP_IPV4,
+ SOCKMAP_IPV6,
+ SOCKMAP_NUM_PROTS,
+};
+
+enum {
+ SOCKMAP_BASE,
+ SOCKMAP_TX,
+ SOCKMAP_NUM_CONFIGS,
+};
+
+static struct proto *saved_tcpv6_prot __read_mostly;
+static DEFINE_SPINLOCK(tcpv6_prot_lock);
+static struct proto bpf_tcp_prots[SOCKMAP_NUM_PROTS][SOCKMAP_NUM_CONFIGS];
+static void build_protos(struct proto prot[SOCKMAP_NUM_CONFIGS],
+ struct proto *base)
+{
+ prot[SOCKMAP_BASE] = *base;
+ prot[SOCKMAP_BASE].close = bpf_tcp_close;
+ prot[SOCKMAP_BASE].recvmsg = bpf_tcp_recvmsg;
+ prot[SOCKMAP_BASE].stream_memory_read = bpf_tcp_stream_read;
+
+ prot[SOCKMAP_TX] = prot[SOCKMAP_BASE];
+ prot[SOCKMAP_TX].sendmsg = bpf_tcp_sendmsg;
+ prot[SOCKMAP_TX].sendpage = bpf_tcp_sendpage;
+}
+
+static void update_sk_prot(struct sock *sk, struct smap_psock *psock)
+{
+ int family = sk->sk_family == AF_INET6 ? SOCKMAP_IPV6 : SOCKMAP_IPV4;
+ int conf = psock->bpf_tx_msg ? SOCKMAP_TX : SOCKMAP_BASE;
+
+ sk->sk_prot = &bpf_tcp_prots[family][conf];
+}
+
static int bpf_tcp_init(struct sock *sk)
{
struct smap_psock *psock;
psock->save_close = sk->sk_prot->close;
psock->sk_proto = sk->sk_prot;
- if (psock->bpf_tx_msg) {
- tcp_bpf_proto.sendmsg = bpf_tcp_sendmsg;
- tcp_bpf_proto.sendpage = bpf_tcp_sendpage;
- tcp_bpf_proto.recvmsg = bpf_tcp_recvmsg;
- tcp_bpf_proto.stream_memory_read = bpf_tcp_stream_read;
+ /* Build IPv6 sockmap whenever the address of tcpv6_prot changes */
+ if (sk->sk_family == AF_INET6 &&
+ unlikely(sk->sk_prot != smp_load_acquire(&saved_tcpv6_prot))) {
+ spin_lock_bh(&tcpv6_prot_lock);
+ if (likely(sk->sk_prot != saved_tcpv6_prot)) {
+ build_protos(bpf_tcp_prots[SOCKMAP_IPV6], sk->sk_prot);
+ smp_store_release(&saved_tcpv6_prot, sk->sk_prot);
+ }
+ spin_unlock_bh(&tcpv6_prot_lock);
}
-
- sk->sk_prot = &tcp_bpf_proto;
+ update_sk_prot(sk, psock);
rcu_read_unlock();
return 0;
}
rcu_read_unlock();
}
+static struct htab_elem *lookup_elem_raw(struct hlist_head *head,
+ u32 hash, void *key, u32 key_size)
+{
+ struct htab_elem *l;
+
+ hlist_for_each_entry_rcu(l, head, hash_node) {
+ if (l->hash == hash && !memcmp(&l->key, key, key_size))
+ return l;
+ }
+
+ return NULL;
+}
+
+static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash)
+{
+ return &htab->buckets[hash & (htab->n_buckets - 1)];
+}
+
+static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash)
+{
+ return &__select_bucket(htab, hash)->head;
+}
+
static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
{
atomic_dec(&htab->count);
kfree_rcu(l, rcu);
}
+static struct smap_psock_map_entry *psock_map_pop(struct sock *sk,
+ struct smap_psock *psock)
+{
+ struct smap_psock_map_entry *e;
+
+ spin_lock_bh(&psock->maps_lock);
+ e = list_first_entry_or_null(&psock->maps,
+ struct smap_psock_map_entry,
+ list);
+ if (e)
+ list_del(&e->list);
+ spin_unlock_bh(&psock->maps_lock);
+ return e;
+}
+
static void bpf_tcp_close(struct sock *sk, long timeout)
{
void (*close_fun)(struct sock *sk, long timeout);
- struct smap_psock_map_entry *e, *tmp;
+ struct smap_psock_map_entry *e;
struct sk_msg_buff *md, *mtmp;
struct smap_psock *psock;
struct sock *osk;
*/
close_fun = psock->save_close;
- write_lock_bh(&sk->sk_callback_lock);
if (psock->cork) {
free_start_sg(psock->sock, psock->cork);
kfree(psock->cork);
kfree(md);
}
- list_for_each_entry_safe(e, tmp, &psock->maps, list) {
+ e = psock_map_pop(sk, psock);
+ while (e) {
if (e->entry) {
osk = cmpxchg(e->entry, sk, NULL);
if (osk == sk) {
- list_del(&e->list);
smap_release_sock(psock, sk);
}
} else {
- hlist_del_rcu(&e->hash_link->hash_node);
- smap_release_sock(psock, e->hash_link->sk);
- free_htab_elem(e->htab, e->hash_link);
+ struct htab_elem *link = rcu_dereference(e->hash_link);
+ struct bpf_htab *htab = rcu_dereference(e->htab);
+ struct hlist_head *head;
+ struct htab_elem *l;
+ struct bucket *b;
+
+ b = __select_bucket(htab, link->hash);
+ head = &b->head;
+ raw_spin_lock_bh(&b->lock);
+ l = lookup_elem_raw(head,
+ link->hash, link->key,
+ htab->map.key_size);
+ /* If another thread deleted this object skip deletion.
+ * The refcnt on psock may or may not be zero.
+ */
+ if (l) {
+ hlist_del_rcu(&link->hash_node);
+ smap_release_sock(psock, link->sk);
+ free_htab_elem(htab, link);
+ }
+ raw_spin_unlock_bh(&b->lock);
}
+ e = psock_map_pop(sk, psock);
}
- write_unlock_bh(&sk->sk_callback_lock);
rcu_read_unlock();
close_fun(sk, timeout);
}
static int bpf_tcp_ulp_register(void)
{
- tcp_bpf_proto = tcp_prot;
- tcp_bpf_proto.close = bpf_tcp_close;
+ build_protos(bpf_tcp_prots[SOCKMAP_IPV4], &tcp_prot);
/* Once BPF TX ULP is registered it is never unregistered. It
* will be in the ULP list for the lifetime of the system. Doing
* duplicate registers is not a problem.
{
if (refcount_dec_and_test(&psock->refcnt)) {
tcp_cleanup_ulp(sock);
+ write_lock_bh(&sock->sk_callback_lock);
smap_stop_sock(psock, sock);
+ write_unlock_bh(&sock->sk_callback_lock);
clear_bit(SMAP_TX_RUNNING, &psock->state);
rcu_assign_sk_user_data(sock, NULL);
call_rcu_sched(&psock->rcu, smap_destroy_psock);
INIT_LIST_HEAD(&psock->maps);
INIT_LIST_HEAD(&psock->ingress);
refcount_set(&psock->refcnt, 1);
+ spin_lock_init(&psock->maps_lock);
rcu_assign_sk_user_data(sock, psock);
sock_hold(sock);
return ERR_PTR(err);
}
-static void smap_list_remove(struct smap_psock *psock,
- struct sock **entry,
- struct htab_elem *hash_link)
+static void smap_list_map_remove(struct smap_psock *psock,
+ struct sock **entry)
{
struct smap_psock_map_entry *e, *tmp;
+ spin_lock_bh(&psock->maps_lock);
list_for_each_entry_safe(e, tmp, &psock->maps, list) {
- if (e->entry == entry || e->hash_link == hash_link) {
+ if (e->entry == entry)
list_del(&e->list);
- break;
- }
}
+ spin_unlock_bh(&psock->maps_lock);
+}
+
+static void smap_list_hash_remove(struct smap_psock *psock,
+ struct htab_elem *hash_link)
+{
+ struct smap_psock_map_entry *e, *tmp;
+
+ spin_lock_bh(&psock->maps_lock);
+ list_for_each_entry_safe(e, tmp, &psock->maps, list) {
+ struct htab_elem *c = rcu_dereference(e->hash_link);
+
+ if (c == hash_link)
+ list_del(&e->list);
+ }
+ spin_unlock_bh(&psock->maps_lock);
}
static void sock_map_free(struct bpf_map *map)
if (!sock)
continue;
- write_lock_bh(&sock->sk_callback_lock);
psock = smap_psock_sk(sock);
/* This check handles a racing sock event that can get the
* sk_callback_lock before this case but after xchg happens
* to be null and queued for garbage collection.
*/
if (likely(psock)) {
- smap_list_remove(psock, &stab->sock_map[i], NULL);
+ smap_list_map_remove(psock, &stab->sock_map[i]);
smap_release_sock(psock, sock);
}
- write_unlock_bh(&sock->sk_callback_lock);
}
rcu_read_unlock();
if (!sock)
return -EINVAL;
- write_lock_bh(&sock->sk_callback_lock);
psock = smap_psock_sk(sock);
if (!psock)
goto out;
if (psock->bpf_parse)
smap_stop_sock(psock, sock);
- smap_list_remove(psock, &stab->sock_map[k], NULL);
+ smap_list_map_remove(psock, &stab->sock_map[k]);
smap_release_sock(psock, sock);
out:
- write_unlock_bh(&sock->sk_callback_lock);
return 0;
}
}
}
- write_lock_bh(&sock->sk_callback_lock);
psock = smap_psock_sk(sock);
/* 2. Do not allow inheriting programs if psock exists and has
if (err)
goto out_free;
smap_init_progs(psock, verdict, parse);
+ write_lock_bh(&sock->sk_callback_lock);
smap_start_sock(psock, sock);
+ write_unlock_bh(&sock->sk_callback_lock);
}
/* 4. Place psock in sockmap for use and stop any programs on
*/
if (map_link) {
e->entry = map_link;
+ spin_lock_bh(&psock->maps_lock);
list_add_tail(&e->list, &psock->maps);
+ spin_unlock_bh(&psock->maps_lock);
}
- write_unlock_bh(&sock->sk_callback_lock);
return err;
out_free:
smap_release_sock(psock, sock);
}
if (tx_msg)
bpf_prog_put(tx_msg);
- write_unlock_bh(&sock->sk_callback_lock);
kfree(e);
return err;
}
if (osock) {
struct smap_psock *opsock = smap_psock_sk(osock);
- write_lock_bh(&osock->sk_callback_lock);
- smap_list_remove(opsock, &stab->sock_map[i], NULL);
+ smap_list_map_remove(opsock, &stab->sock_map[i]);
smap_release_sock(opsock, osock);
- write_unlock_bh(&osock->sk_callback_lock);
}
out:
return err;
return 0;
}
+int sockmap_get_from_fd(const union bpf_attr *attr, int type,
+ struct bpf_prog *prog)
+{
+ int ufd = attr->target_fd;
+ struct bpf_map *map;
+ struct fd f;
+ int err;
+
+ f = fdget(ufd);
+ map = __bpf_map_get(f);
+ if (IS_ERR(map))
+ return PTR_ERR(map);
+
+ err = sock_map_prog(map, prog, attr->attach_type);
+ fdput(f);
+ return err;
+}
+
static void *sock_map_lookup(struct bpf_map *map, void *key)
{
return NULL;
return ERR_PTR(err);
}
-static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash)
+static void __bpf_htab_free(struct rcu_head *rcu)
{
- return &htab->buckets[hash & (htab->n_buckets - 1)];
-}
+ struct bpf_htab *htab;
-static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash)
-{
- return &__select_bucket(htab, hash)->head;
+ htab = container_of(rcu, struct bpf_htab, rcu);
+ bpf_map_area_free(htab->buckets);
+ kfree(htab);
}
static void sock_hash_free(struct bpf_map *map)
*/
rcu_read_lock();
for (i = 0; i < htab->n_buckets; i++) {
- struct hlist_head *head = select_bucket(htab, i);
+ struct bucket *b = __select_bucket(htab, i);
+ struct hlist_head *head;
struct hlist_node *n;
struct htab_elem *l;
+ raw_spin_lock_bh(&b->lock);
+ head = &b->head;
hlist_for_each_entry_safe(l, n, head, hash_node) {
struct sock *sock = l->sk;
struct smap_psock *psock;
hlist_del_rcu(&l->hash_node);
- write_lock_bh(&sock->sk_callback_lock);
psock = smap_psock_sk(sock);
/* This check handles a racing sock event that can get
* the sk_callback_lock before this case but after xchg
* (psock) to be null and queued for garbage collection.
*/
if (likely(psock)) {
- smap_list_remove(psock, NULL, l);
+ smap_list_hash_remove(psock, l);
smap_release_sock(psock, sock);
}
- write_unlock_bh(&sock->sk_callback_lock);
- kfree(l);
+ free_htab_elem(htab, l);
}
+ raw_spin_unlock_bh(&b->lock);
}
rcu_read_unlock();
- bpf_map_area_free(htab->buckets);
- kfree(htab);
+ call_rcu(&htab->rcu, __bpf_htab_free);
}
static struct htab_elem *alloc_sock_hash_elem(struct bpf_htab *htab,
return l_new;
}
-static struct htab_elem *lookup_elem_raw(struct hlist_head *head,
- u32 hash, void *key, u32 key_size)
-{
- struct htab_elem *l;
-
- hlist_for_each_entry_rcu(l, head, hash_node) {
- if (l->hash == hash && !memcmp(&l->key, key, key_size))
- return l;
- }
-
- return NULL;
-}
-
static inline u32 htab_map_hash(const void *key, u32 key_len)
{
return jhash(key, key_len, 0);
goto bucket_err;
}
- e->hash_link = l_new;
- e->htab = container_of(map, struct bpf_htab, map);
+ rcu_assign_pointer(e->hash_link, l_new);
+ rcu_assign_pointer(e->htab,
+ container_of(map, struct bpf_htab, map));
+ spin_lock_bh(&psock->maps_lock);
list_add_tail(&e->list, &psock->maps);
+ spin_unlock_bh(&psock->maps_lock);
/* add new element to the head of the list, so that
* concurrent search will find it before old elem
psock = smap_psock_sk(l_old->sk);
hlist_del_rcu(&l_old->hash_node);
- smap_list_remove(psock, NULL, l_old);
+ smap_list_hash_remove(psock, l_old);
smap_release_sock(psock, l_old->sk);
free_htab_elem(htab, l_old);
}
struct smap_psock *psock;
hlist_del_rcu(&l->hash_node);
- write_lock_bh(&sock->sk_callback_lock);
psock = smap_psock_sk(sock);
/* This check handles a racing sock event that can get the
* sk_callback_lock before this case but after xchg happens
* to be null and queued for garbage collection.
*/
if (likely(psock)) {
- smap_list_remove(psock, NULL, l);
+ smap_list_hash_remove(psock, l);
smap_release_sock(psock, sock);
}
- write_unlock_bh(&sock->sk_callback_lock);
free_htab_elem(htab, l);
ret = 0;
}
.map_get_next_key = sock_hash_get_next_key,
.map_update_elem = sock_hash_update_elem,
.map_delete_elem = sock_hash_delete_elem,
+ .map_release_uref = sock_map_release,
};
BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock,
static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock)
{
if (atomic_dec_and_test(&prog->aux->refcnt)) {
- int i;
-
/* bpf_prog_free_id() must be called first */
bpf_prog_free_id(prog, do_idr_lock);
-
- for (i = 0; i < prog->aux->func_cnt; i++)
- bpf_prog_kallsyms_del(prog->aux->func[i]);
- bpf_prog_kallsyms_del(prog);
+ bpf_prog_kallsyms_del_all(prog);
call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu);
}
if (err < 0)
goto free_used_maps;
- /* eBPF program is ready to be JITed */
- if (!prog->bpf_func)
- prog = bpf_prog_select_runtime(prog, &err);
+ prog = bpf_prog_select_runtime(prog, &err);
if (err < 0)
goto free_used_maps;
return err;
free_used_maps:
+ bpf_prog_kallsyms_del_subprogs(prog);
free_used_maps(prog->aux);
free_prog:
bpf_prog_uncharge_memlock(prog);
return err;
}
-#ifdef CONFIG_CGROUP_BPF
-
static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
enum bpf_attach_type attach_type)
{
#define BPF_PROG_ATTACH_LAST_FIELD attach_flags
-static int sockmap_get_from_fd(const union bpf_attr *attr,
- int type, bool attach)
-{
- struct bpf_prog *prog = NULL;
- int ufd = attr->target_fd;
- struct bpf_map *map;
- struct fd f;
- int err;
-
- f = fdget(ufd);
- map = __bpf_map_get(f);
- if (IS_ERR(map))
- return PTR_ERR(map);
-
- if (attach) {
- prog = bpf_prog_get_type(attr->attach_bpf_fd, type);
- if (IS_ERR(prog)) {
- fdput(f);
- return PTR_ERR(prog);
- }
- }
-
- err = sock_map_prog(map, prog, attr->attach_type);
- if (err) {
- fdput(f);
- if (prog)
- bpf_prog_put(prog);
- return err;
- }
-
- fdput(f);
- return 0;
-}
-
#define BPF_F_ATTACH_MASK \
(BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI)
{
enum bpf_prog_type ptype;
struct bpf_prog *prog;
- struct cgroup *cgrp;
int ret;
if (!capable(CAP_NET_ADMIN))
ptype = BPF_PROG_TYPE_CGROUP_DEVICE;
break;
case BPF_SK_MSG_VERDICT:
- return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, true);
+ ptype = BPF_PROG_TYPE_SK_MSG;
+ break;
case BPF_SK_SKB_STREAM_PARSER:
case BPF_SK_SKB_STREAM_VERDICT:
- return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, true);
+ ptype = BPF_PROG_TYPE_SK_SKB;
+ break;
case BPF_LIRC_MODE2:
- return lirc_prog_attach(attr);
+ ptype = BPF_PROG_TYPE_LIRC_MODE2;
+ break;
default:
return -EINVAL;
}
return -EINVAL;
}
- cgrp = cgroup_get_from_fd(attr->target_fd);
- if (IS_ERR(cgrp)) {
- bpf_prog_put(prog);
- return PTR_ERR(cgrp);
+ switch (ptype) {
+ case BPF_PROG_TYPE_SK_SKB:
+ case BPF_PROG_TYPE_SK_MSG:
+ ret = sockmap_get_from_fd(attr, ptype, prog);
+ break;
+ case BPF_PROG_TYPE_LIRC_MODE2:
+ ret = lirc_prog_attach(attr, prog);
+ break;
+ default:
+ ret = cgroup_bpf_prog_attach(attr, ptype, prog);
}
- ret = cgroup_bpf_attach(cgrp, prog, attr->attach_type,
- attr->attach_flags);
if (ret)
bpf_prog_put(prog);
- cgroup_put(cgrp);
-
return ret;
}
static int bpf_prog_detach(const union bpf_attr *attr)
{
enum bpf_prog_type ptype;
- struct bpf_prog *prog;
- struct cgroup *cgrp;
- int ret;
if (!capable(CAP_NET_ADMIN))
return -EPERM;
ptype = BPF_PROG_TYPE_CGROUP_DEVICE;
break;
case BPF_SK_MSG_VERDICT:
- return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, false);
+ return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, NULL);
case BPF_SK_SKB_STREAM_PARSER:
case BPF_SK_SKB_STREAM_VERDICT:
- return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, false);
+ return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, NULL);
case BPF_LIRC_MODE2:
return lirc_prog_detach(attr);
default:
return -EINVAL;
}
- cgrp = cgroup_get_from_fd(attr->target_fd);
- if (IS_ERR(cgrp))
- return PTR_ERR(cgrp);
-
- prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
- if (IS_ERR(prog))
- prog = NULL;
-
- ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type, 0);
- if (prog)
- bpf_prog_put(prog);
- cgroup_put(cgrp);
- return ret;
+ return cgroup_bpf_prog_detach(attr, ptype);
}
#define BPF_PROG_QUERY_LAST_FIELD query.prog_cnt
static int bpf_prog_query(const union bpf_attr *attr,
union bpf_attr __user *uattr)
{
- struct cgroup *cgrp;
- int ret;
-
if (!capable(CAP_NET_ADMIN))
return -EPERM;
if (CHECK_ATTR(BPF_PROG_QUERY))
default:
return -EINVAL;
}
- cgrp = cgroup_get_from_fd(attr->query.target_fd);
- if (IS_ERR(cgrp))
- return PTR_ERR(cgrp);
- ret = cgroup_bpf_query(cgrp, attr, uattr);
- cgroup_put(cgrp);
- return ret;
+
+ return cgroup_bpf_prog_query(attr, uattr);
}
-#endif /* CONFIG_CGROUP_BPF */
#define BPF_PROG_TEST_RUN_LAST_FIELD test.duration
case BPF_OBJ_GET:
err = bpf_obj_get(&attr);
break;
-#ifdef CONFIG_CGROUP_BPF
case BPF_PROG_ATTACH:
err = bpf_prog_attach(&attr);
break;
case BPF_PROG_QUERY:
err = bpf_prog_query(&attr, uattr);
break;
-#endif
case BPF_PROG_TEST_RUN:
err = bpf_prog_test_run(&attr, uattr);
break;
--- /dev/null
+
+config HAS_DMA
+ bool
+ depends on !NO_DMA
+ default y
+
+config NEED_SG_DMA_LENGTH
+ bool
+
+config NEED_DMA_MAP_STATE
+ bool
+
+config ARCH_DMA_ADDR_T_64BIT
+ def_bool 64BIT || PHYS_ADDR_T_64BIT
+
+config HAVE_GENERIC_DMA_COHERENT
+ bool
+
+config ARCH_HAS_SYNC_DMA_FOR_DEVICE
+ bool
+
+config ARCH_HAS_SYNC_DMA_FOR_CPU
+ bool
+ select NEED_DMA_MAP_STATE
+
+config DMA_DIRECT_OPS
+ bool
+ depends on HAS_DMA
+
+config DMA_NONCOHERENT_OPS
+ bool
+ depends on HAS_DMA
+ select DMA_DIRECT_OPS
+
+config DMA_NONCOHERENT_MMAP
+ bool
+ depends on DMA_NONCOHERENT_OPS
+
+config DMA_NONCOHERENT_CACHE_SYNC
+ bool
+ depends on DMA_NONCOHERENT_OPS
+
+config DMA_VIRT_OPS
+ bool
+ depends on HAS_DMA
+
+config SWIOTLB
+ bool
+ select DMA_DIRECT_OPS
+ select NEED_DMA_MAP_STATE
--- /dev/null
+# SPDX-License-Identifier: GPL-2.0
+
+obj-$(CONFIG_HAS_DMA) += mapping.o
+obj-$(CONFIG_DMA_CMA) += contiguous.o
+obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += coherent.o
+obj-$(CONFIG_DMA_DIRECT_OPS) += direct.o
+obj-$(CONFIG_DMA_NONCOHERENT_OPS) += noncoherent.o
+obj-$(CONFIG_DMA_VIRT_OPS) += virt.o
+obj-$(CONFIG_DMA_API_DEBUG) += debug.o
+obj-$(CONFIG_SWIOTLB) += swiotlb.o
+
// SPDX-License-Identifier: GPL-2.0
/*
- * drivers/base/dma-mapping.c - arch-independent dma-mapping routines
+ * arch-independent dma-mapping routines
*
* Copyright (c) 2006 SUSE Linux Products GmbH
* Copyright (c) 2006 Tejun Heo <teheo@suse.de>
.unmap_page = swiotlb_unmap_page,
.dma_supported = dma_direct_supported,
};
+EXPORT_SYMBOL(swiotlb_dma_ops);
// SPDX-License-Identifier: GPL-2.0
/*
- * lib/dma-virt.c
- *
* DMA operations that map to virtual addresses without flushing memory.
*/
#include <linux/export.h>
data->phys_addr = perf_virt_to_phys(data->addr);
}
-static void __always_inline
+static __always_inline void
__perf_event_output(struct perf_event *event,
struct perf_sample_data *data,
struct pt_regs *regs,
preempt_enable();
}
-static bool __always_inline
+static __always_inline bool
ring_buffer_has_space(unsigned long head, unsigned long tail,
unsigned long data_size, unsigned int size,
bool backward)
return CIRC_SPACE(tail, head, data_size) >= size;
}
-static int __always_inline
+static __always_inline int
__perf_output_begin(struct perf_output_handle *handle,
struct perf_event *event, unsigned int size,
bool backward)
}
EXPORT_SYMBOL_GPL(perf_aux_output_begin);
-static bool __always_inline rb_need_aux_wakeup(struct ring_buffer *rb)
+static __always_inline bool rb_need_aux_wakeup(struct ring_buffer *rb)
{
if (rb->aux_overwrite)
return false;
BIT_MASK_DESCR(IRQCHIP_SKIP_SET_WAKE),
BIT_MASK_DESCR(IRQCHIP_ONESHOT_SAFE),
BIT_MASK_DESCR(IRQCHIP_EOI_THREADED),
+ BIT_MASK_DESCR(IRQCHIP_SUPPORTS_LEVEL_MSI),
};
static void
this.parent = NULL;
this.class = class;
- local_irq_save(flags);
+ raw_local_irq_save(flags);
arch_spin_lock(&lockdep_lock);
ret = __lockdep_count_forward_deps(&this);
arch_spin_unlock(&lockdep_lock);
- local_irq_restore(flags);
+ raw_local_irq_restore(flags);
return ret;
}
this.parent = NULL;
this.class = class;
- local_irq_save(flags);
+ raw_local_irq_save(flags);
arch_spin_lock(&lockdep_lock);
ret = __lockdep_count_backward_deps(&this);
arch_spin_unlock(&lockdep_lock);
- local_irq_restore(flags);
+ raw_local_irq_restore(flags);
return ret;
}
if (unlikely(!debug_locks))
return;
- local_irq_save(flags);
+ raw_local_irq_save(flags);
for (i = 0; i < curr->lockdep_depth; i++) {
hlock = curr->held_locks + i;
print_freed_lock_bug(curr, mem_from, mem_from + mem_len, hlock);
break;
}
- local_irq_restore(flags);
+ raw_local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(debug_check_no_locks_freed);
might_sleep();
__down_read(sem);
+ rwsem_set_reader_owned(sem);
}
EXPORT_SYMBOL(down_read_non_owner);
* respect to other threads scheduled on the same CPU, and with respect
* to signal handlers.
*/
-void __rseq_handle_notify_resume(struct pt_regs *regs)
+void __rseq_handle_notify_resume(struct ksignal *ksig, struct pt_regs *regs)
{
struct task_struct *t = current;
- int ret;
+ int ret, sig;
if (unlikely(t->flags & PF_EXITING))
return;
return;
error:
- force_sig(SIGSEGV, t);
+ sig = ksig ? ksig->sig : 0;
+ force_sigsegv(sig, t);
}
#ifdef CONFIG_DEBUG_RSEQ
{
lockdep_assert_irqs_disabled();
+ if (preempt_count() == cnt)
+ trace_preempt_on(CALLER_ADDR0, get_lock_parent_ip());
+
if (softirq_count() == (cnt & SOFTIRQ_MASK))
trace_softirqs_on(_RET_IP_);
- preempt_count_sub(cnt);
+
+ __preempt_count_sub(cnt);
}
/*
int nanosleep_copyout(struct restart_block *restart, struct timespec64 *ts)
{
switch(restart->nanosleep.type) {
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_32BIT_TIME
case TT_COMPAT:
if (compat_put_timespec64(ts, restart->nanosleep.compat_rmtp))
return -EFAULT;
/*
* Disarm any old timer after extracting its expiry time.
*/
- lockdep_assert_irqs_disabled();
ret = 0;
old_incr = timer->it.cpu.incr;
/*
* Now re-arm for the new expiry time.
*/
- lockdep_assert_irqs_disabled();
arm_timer(timer);
unlock:
unlock_task_sighand(p, &flags);
*/
#include <linux/export.h>
+#include <linux/kernel.h>
#include <linux/timex.h>
#include <linux/capability.h>
#include <linux/timekeeper_internal.h>
return (j + (HZ / MSEC_PER_SEC) - 1)/(HZ / MSEC_PER_SEC);
#else
# if BITS_PER_LONG == 32
- return (HZ_TO_MSEC_MUL32 * j) >> HZ_TO_MSEC_SHR32;
+ return (HZ_TO_MSEC_MUL32 * j + (1ULL << HZ_TO_MSEC_SHR32) - 1) >>
+ HZ_TO_MSEC_SHR32;
# else
- return (j * HZ_TO_MSEC_NUM) / HZ_TO_MSEC_DEN;
+ return DIV_ROUND_UP(j * HZ_TO_MSEC_NUM, HZ_TO_MSEC_DEN);
# endif
#endif
}
void
update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
{
- struct ring_buffer *buf;
-
if (tr->stop_count)
return;
arch_spin_lock(&tr->max_lock);
- buf = tr->trace_buffer.buffer;
- tr->trace_buffer.buffer = tr->max_buffer.buffer;
- tr->max_buffer.buffer = buf;
+ swap(tr->trace_buffer.buffer, tr->max_buffer.buffer);
__update_max_tr(tr, tsk, cpu);
arch_spin_unlock(&tr->max_lock);
C(TOO_MANY_PREDS, "Too many terms in predicate expression"), \
C(INVALID_FILTER, "Meaningless filter expression"), \
C(IP_FIELD_ONLY, "Only 'ip' field is supported for function trace"), \
- C(INVALID_VALUE, "Invalid value (did you forget quotes)?"),
+ C(INVALID_VALUE, "Invalid value (did you forget quotes)?"), \
+ C(NO_FILTER, "No filter found"),
#undef C
#define C(a, b) FILT_ERR_##a
goto out_free;
}
+ if (!N) {
+ /* No program? */
+ ret = -EINVAL;
+ parse_error(pe, FILT_ERR_NO_FILTER, ptr - str);
+ goto out_free;
+ }
+
prog[N].pred = NULL; /* #13 */
prog[N].target = 1; /* TRUE */
prog[N+1].pred = NULL;
depends on HAS_IOMEM && !NO_IOPORT_MAP
default y
-config HAS_DMA
- bool
- depends on !NO_DMA
- default y
+source "kernel/dma/Kconfig"
config SGL_ALLOC
bool
default n
-config NEED_SG_DMA_LENGTH
- bool
-
-config NEED_DMA_MAP_STATE
- bool
-
-config ARCH_DMA_ADDR_T_64BIT
- def_bool 64BIT || PHYS_ADDR_T_64BIT
-
config IOMMU_HELPER
bool
-config ARCH_HAS_SYNC_DMA_FOR_DEVICE
- bool
-
-config ARCH_HAS_SYNC_DMA_FOR_CPU
- bool
- select NEED_DMA_MAP_STATE
-
-config DMA_DIRECT_OPS
- bool
- depends on HAS_DMA
-
-config DMA_NONCOHERENT_OPS
- bool
- depends on HAS_DMA
- select DMA_DIRECT_OPS
-
-config DMA_NONCOHERENT_MMAP
- bool
- depends on DMA_NONCOHERENT_OPS
-
-config DMA_NONCOHERENT_CACHE_SYNC
- bool
- depends on DMA_NONCOHERENT_OPS
-
-config DMA_VIRT_OPS
- bool
- depends on HAS_DMA
-
-config SWIOTLB
- bool
- select DMA_DIRECT_OPS
- select NEED_DMA_MAP_STATE
-
config CHECK_SIGNATURE
bool
config KASAN
bool "KASan: runtime memory debugger"
depends on SLUB || (SLAB && !DEBUG_SLAB)
+ select SLUB_DEBUG if SLUB
select CONSTRUCTORS
select STACKDEPOT
help
sha1.o chacha20.o irq_regs.o argv_split.o \
flex_proportions.o ratelimit.o show_mem.o \
is_single_threaded.o plist.o decompress.o kobject_uevent.o \
- earlycpio.o seq_buf.o siphash.o \
+ earlycpio.o seq_buf.o siphash.o dec_and_lock.o \
nmi_backtrace.o nodemask.o win_minmax.o
lib-$(CONFIG_PRINTK) += dump_stack.o
lib-$(CONFIG_MMU) += ioremap.o
lib-$(CONFIG_SMP) += cpumask.o
-lib-$(CONFIG_DMA_DIRECT_OPS) += dma-direct.o
-lib-$(CONFIG_DMA_NONCOHERENT_OPS) += dma-noncoherent.o
-lib-$(CONFIG_DMA_VIRT_OPS) += dma-virt.o
lib-y += kobject.o klist.o
obj-y += lockref.o
obj-$(CONFIG_DEBUG_LIST) += list_debug.o
obj-$(CONFIG_DEBUG_OBJECTS) += debugobjects.o
-ifneq ($(CONFIG_HAVE_DEC_LOCK),y)
- lib-y += dec_and_lock.o
-endif
-
obj-$(CONFIG_BITREVERSE) += bitrev.o
obj-$(CONFIG_RATIONAL) += rational.o
obj-$(CONFIG_CRC_CCITT) += crc-ccitt.o
obj-$(CONFIG_AUDIT_GENERIC) += audit.o
obj-$(CONFIG_AUDIT_COMPAT_GENERIC) += compat_audit.o
-obj-$(CONFIG_SWIOTLB) += swiotlb.o
obj-$(CONFIG_IOMMU_HELPER) += iommu-helper.o
obj-$(CONFIG_FAULT_INJECTION) += fault-inject.o
obj-$(CONFIG_NOTIFIER_ERROR_INJECTION) += notifier-error-inject.o
obj-$(CONFIG_LRU_CACHE) += lru_cache.o
-obj-$(CONFIG_DMA_API_DEBUG) += dma-debug.o
-
obj-$(CONFIG_GENERIC_CSUM) += checksum.o
obj-$(CONFIG_GENERIC_ATOMIC64) += atomic64.o
}
EXPORT_SYMBOL(_atomic_dec_and_lock);
+
+int _atomic_dec_and_lock_irqsave(atomic_t *atomic, spinlock_t *lock,
+ unsigned long *flags)
+{
+ /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */
+ if (atomic_add_unless(atomic, -1, 1))
+ return 0;
+
+ /* Otherwise do it the slow way */
+ spin_lock_irqsave(lock, *flags);
+ if (atomic_dec_and_test(atomic))
+ return 1;
+ spin_unlock_irqrestore(lock, *flags);
+ return 0;
+}
+EXPORT_SYMBOL(_atomic_dec_and_lock_irqsave);
if (policy) {
err = validate_nla(nla, maxtype, policy);
if (err < 0) {
- if (extack)
- extack->bad_attr = nla;
+ NL_SET_ERR_MSG_ATTR(extack, nla,
+ "Attribute failed policy validation");
goto errout;
}
}
spin_lock_irqsave(&tags->lock, flags);
/* Fastpath */
- if (likely(tags->nr_free >= 0)) {
+ if (likely(tags->nr_free)) {
tag = tags->freelist[--tags->nr_free];
spin_unlock_irqrestore(&tags->lock, flags);
return tag;
// SPDX-License-Identifier: GPL-2.0
+#include <linux/bug.h>
#include <linux/kernel.h>
#include <asm/div64.h>
#include <linux/reciprocal_div.h>
return R;
}
EXPORT_SYMBOL(reciprocal_value);
+
+struct reciprocal_value_adv reciprocal_value_adv(u32 d, u8 prec)
+{
+ struct reciprocal_value_adv R;
+ u32 l, post_shift;
+ u64 mhigh, mlow;
+
+ /* ceil(log2(d)) */
+ l = fls(d - 1);
+ /* NOTE: mlow/mhigh could overflow u64 when l == 32. This case needs to
+ * be handled before calling "reciprocal_value_adv", please see the
+ * comment at include/linux/reciprocal_div.h.
+ */
+ WARN(l == 32,
+ "ceil(log2(0x%08x)) == 32, %s doesn't support such divisor",
+ d, __func__);
+ post_shift = l;
+ mlow = 1ULL << (32 + l);
+ do_div(mlow, d);
+ mhigh = (1ULL << (32 + l)) + (1ULL << (32 + l - prec));
+ do_div(mhigh, d);
+
+ for (; post_shift > 0; post_shift--) {
+ u64 lo = mlow >> 1, hi = mhigh >> 1;
+
+ if (lo >= hi)
+ break;
+
+ mlow = lo;
+ mhigh = hi;
+ }
+
+ R.m = (u32)mhigh;
+ R.sh = post_shift;
+ R.exp = l;
+ R.is_wide_m = mhigh > U32_MAX;
+
+ return R;
+}
+EXPORT_SYMBOL(reciprocal_value_adv);
}
EXPORT_SYMBOL(refcount_dec_and_lock);
+/**
+ * refcount_dec_and_lock_irqsave - return holding spinlock with disabled
+ * interrupts if able to decrement refcount to 0
+ * @r: the refcount
+ * @lock: the spinlock to be locked
+ * @flags: saved IRQ-flags if the is acquired
+ *
+ * Same as refcount_dec_and_lock() above except that the spinlock is acquired
+ * with disabled interupts.
+ *
+ * Return: true and hold spinlock if able to decrement refcount to 0, false
+ * otherwise
+ */
+bool refcount_dec_and_lock_irqsave(refcount_t *r, spinlock_t *lock,
+ unsigned long *flags)
+{
+ if (refcount_dec_not_one(r))
+ return false;
+
+ spin_lock_irqsave(lock, *flags);
+ if (!refcount_dec_and_test(r)) {
+ spin_unlock_irqrestore(lock, *flags);
+ return false;
+ }
+
+ return true;
+}
+EXPORT_SYMBOL(refcount_dec_and_lock_irqsave);
#include <linux/rhashtable.h>
#include <linux/err.h>
#include <linux/export.h>
+#include <linux/rhashtable.h>
#define HASH_DEFAULT_SIZE 64UL
#define HASH_MIN_SIZE 4U
static union nested_table *nested_table_alloc(struct rhashtable *ht,
union nested_table __rcu **prev,
- unsigned int shifted,
- unsigned int nhash)
+ bool leaf)
{
union nested_table *ntbl;
int i;
ntbl = kzalloc(PAGE_SIZE, GFP_ATOMIC);
- if (ntbl && shifted) {
- for (i = 0; i < PAGE_SIZE / sizeof(ntbl[0].bucket); i++)
- INIT_RHT_NULLS_HEAD(ntbl[i].bucket, ht,
- (i << shifted) | nhash);
+ if (ntbl && leaf) {
+ for (i = 0; i < PAGE_SIZE / sizeof(ntbl[0]); i++)
+ INIT_RHT_NULLS_HEAD(ntbl[i].bucket);
}
rcu_assign_pointer(*prev, ntbl);
return NULL;
if (!nested_table_alloc(ht, (union nested_table __rcu **)tbl->buckets,
- 0, 0)) {
+ false)) {
kfree(tbl);
return NULL;
}
tbl->hash_rnd = get_random_u32();
for (i = 0; i < nbuckets; i++)
- INIT_RHT_NULLS_HEAD(tbl->buckets[i], ht, i);
+ INIT_RHT_NULLS_HEAD(tbl->buckets[i]);
return tbl;
}
static int rhashtable_rehash_one(struct rhashtable *ht, unsigned int old_hash)
{
struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht);
- struct bucket_table *new_tbl = rhashtable_last_table(ht,
- rht_dereference_rcu(old_tbl->future_tbl, ht));
+ struct bucket_table *new_tbl = rhashtable_last_table(ht, old_tbl);
struct rhash_head __rcu **pprev = rht_bucket_var(old_tbl, old_hash);
int err = -EAGAIN;
struct rhash_head *head, *next, *entry;
struct bucket_table *old_tbl,
struct bucket_table *new_tbl)
{
- /* Protect future_tbl using the first bucket lock. */
- spin_lock_bh(old_tbl->locks);
-
- /* Did somebody beat us to it? */
- if (rcu_access_pointer(old_tbl->future_tbl)) {
- spin_unlock_bh(old_tbl->locks);
- return -EEXIST;
- }
-
/* Make insertions go into the new, empty table right away. Deletions
* and lookups will be attempted in both tables until we synchronize.
+ * As cmpxchg() provides strong barriers, we do not need
+ * rcu_assign_pointer().
*/
- rcu_assign_pointer(old_tbl->future_tbl, new_tbl);
- spin_unlock_bh(old_tbl->locks);
+ if (cmpxchg(&old_tbl->future_tbl, NULL, new_tbl) != NULL)
+ return -EEXIST;
return 0;
}
fail:
/* Do not fail the insert if someone else did a rehash. */
- if (likely(rcu_dereference_raw(tbl->future_tbl)))
+ if (likely(rcu_access_pointer(tbl->future_tbl)))
return 0;
/* Schedule async rehash to retry allocation in process context. */
if (PTR_ERR(data) != -EAGAIN && PTR_ERR(data) != -ENOENT)
return ERR_CAST(data);
- new_tbl = rcu_dereference(tbl->future_tbl);
+ new_tbl = rht_dereference_rcu(tbl->future_tbl, ht);
if (new_tbl)
return new_tbl;
break;
spin_unlock_bh(lock);
- tbl = rcu_dereference(tbl->future_tbl);
+ tbl = rht_dereference_rcu(tbl->future_tbl, ht);
}
data = rhashtable_lookup_one(ht, tbl, hash, key, obj);
* .key_offset = offsetof(struct test_obj, key),
* .key_len = sizeof(int),
* .hashfn = jhash,
- * .nulls_base = (1U << RHT_BASE_SHIFT),
* };
*
* Configuration Example 2: Variable length keys
(params->obj_hashfn && !params->obj_cmpfn))
return -EINVAL;
- if (params->nulls_base && params->nulls_base < (1U << RHT_BASE_SHIFT))
- return -EINVAL;
-
memset(ht, 0, sizeof(*ht));
mutex_init(&ht->mutex);
spin_lock_init(&ht->lock);
{
int err;
- /* No rhlist NULLs marking for now. */
- if (params->nulls_base)
- return -EINVAL;
-
err = rhashtable_init(&hlt->ht, params);
hlt->ht.rhlist = true;
return err;
unsigned int index = hash & ((1 << tbl->nest) - 1);
unsigned int size = tbl->size >> tbl->nest;
union nested_table *ntbl;
- unsigned int shifted;
- unsigned int nhash;
ntbl = (union nested_table *)rcu_dereference_raw(tbl->buckets[0]);
hash >>= tbl->nest;
- nhash = index;
- shifted = tbl->nest;
ntbl = nested_table_alloc(ht, &ntbl[index].table,
- size <= (1 << shift) ? shifted : 0, nhash);
+ size <= (1 << shift));
while (ntbl && size > (1 << shift)) {
index = hash & ((1 << shift) - 1);
size >>= shift;
hash >>= shift;
- nhash |= index << shifted;
- shifted += shift;
ntbl = nested_table_alloc(ht, &ntbl[index].table,
- size <= (1 << shift) ? shifted : 0,
- nhash);
+ size <= (1 << shift));
}
if (!ntbl)
**/
struct scatterlist *sg_next(struct scatterlist *sg)
{
-#ifdef CONFIG_DEBUG_SG
- BUG_ON(sg->sg_magic != SG_MAGIC);
-#endif
if (sg_is_last(sg))
return NULL;
for_each_sg(sgl, sg, nents, i)
ret = sg;
-#ifdef CONFIG_DEBUG_SG
- BUG_ON(sgl[0].sg_magic != SG_MAGIC);
BUG_ON(!sg_is_last(ret));
-#endif
return ret;
}
EXPORT_SYMBOL(sg_last);
{ /* Mainly checking JIT here. */
"BPF_MAXINSNS: Ctx heavy transformations",
{ },
+#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_S390)
+ CLASSIC | FLAG_EXPECTED_FAIL,
+#else
CLASSIC,
+#endif
{ },
{
{ 1, !!(SKB_VLAN_TCI & VLAN_TAG_PRESENT) },
{ 10, !!(SKB_VLAN_TCI & VLAN_TAG_PRESENT) }
},
.fill_helper = bpf_fill_maxinsns6,
+ .expected_errcode = -ENOTSUPP,
},
{ /* Mainly checking JIT here. */
"BPF_MAXINSNS: Call heavy transformations",
{ },
+#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_S390)
+ CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL,
+#else
CLASSIC | FLAG_NO_DATA,
+#endif
{ },
{ { 1, 0 }, { 10, 0 } },
.fill_helper = bpf_fill_maxinsns7,
+ .expected_errcode = -ENOTSUPP,
},
{ /* Mainly checking JIT here. */
"BPF_MAXINSNS: Jump heavy test",
{
"BPF_MAXINSNS: exec all MSH",
{ },
+#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_S390)
+ CLASSIC | FLAG_EXPECTED_FAIL,
+#else
CLASSIC,
+#endif
{ 0xfa, 0xfb, 0xfc, 0xfd, },
{ { 4, 0xababab83 } },
.fill_helper = bpf_fill_maxinsns13,
+ .expected_errcode = -ENOTSUPP,
},
{
"BPF_MAXINSNS: ld_abs+get_processor_id",
{ },
+#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_S390)
+ CLASSIC | FLAG_EXPECTED_FAIL,
+#else
CLASSIC,
+#endif
{ },
{ { 1, 0xbee } },
.fill_helper = bpf_fill_ld_abs_get_processor_id,
+ .expected_errcode = -ENOTSUPP,
},
/*
* LD_IND / LD_ABS on fragmented SKBs
{
int err;
- /*
- * Make sure crng is ready. Otherwise we get "(ptrval)" instead
- * of a hashed address when printing '%p' in plain_hash() and
- * plain_format().
- */
- wait_for_random_bytes();
-
err = plain_hash();
if (err) {
pr_warn("plain 'p' does not appear to be hashed\n");
{
const struct test_obj_rhl *obj = data;
- return (obj->value.id % 10) << RHT_HASH_RESERVED_SPACE;
+ return (obj->value.id % 10);
}
static int my_cmpfn(struct rhashtable_compare_arg *arg, const void *obj)
.key_offset = offsetof(struct test_obj, value),
.key_len = sizeof(struct test_obj_val),
.hashfn = jhash,
- .nulls_base = (3U << RHT_BASE_SHIFT),
};
static struct rhashtable_params test_rht_params_dup = {
if (!obj_in_table)
goto out_free;
- /* nulls_base not supported in rhlist interface */
- test_rht_params.nulls_base = 0;
err = rhltable_init(&rhlt, &test_rht_params);
if (WARN_ON(err))
goto out_free;
unsigned int i, cnt = 0;
ht = &rhlt->ht;
+ /* Take the mutex to avoid RCU warning */
+ mutex_lock(&ht->mutex);
tbl = rht_dereference(ht->tbl, ht);
for (i = 0; i < tbl->size; i++) {
struct rhash_head *pos, *next;
}
}
printk(KERN_ERR "\n---- ht: ----%s\n-------------\n", buff);
+ mutex_unlock(&ht->mutex);
return cnt;
}
spin_lock_bh(&wb->work_lock);
if (!test_and_clear_bit(WB_registered, &wb->state)) {
spin_unlock_bh(&wb->work_lock);
- /*
- * Wait for wb shutdown to finish if someone else is just
- * running wb_shutdown(). Otherwise we could proceed to wb /
- * bdi destruction before wb_shutdown() is finished.
- */
- wait_on_bit(&wb->state, WB_shutting_down, TASK_UNINTERRUPTIBLE);
return;
}
- set_bit(WB_shutting_down, &wb->state);
spin_unlock_bh(&wb->work_lock);
cgwb_remove_from_bdi_list(wb);
mod_delayed_work(bdi_wq, &wb->dwork, 0);
flush_delayed_work(&wb->dwork);
WARN_ON(!list_empty(&wb->work_list));
- /*
- * Make sure bit gets cleared after shutdown is finished. Matches with
- * the barrier provided by test_and_clear_bit() above.
- */
- smp_wmb();
- clear_and_wake_up_bit(WB_shutting_down, &wb->state);
}
static void wb_exit(struct bdi_writeback *wb)
struct bdi_writeback *wb = container_of(work, struct bdi_writeback,
release_work);
+ mutex_lock(&wb->bdi->cgwb_release_mutex);
wb_shutdown(wb);
css_put(wb->memcg_css);
css_put(wb->blkcg_css);
+ mutex_unlock(&wb->bdi->cgwb_release_mutex);
fprop_local_destroy_percpu(&wb->memcg_completions);
percpu_ref_exit(&wb->refcnt);
INIT_RADIX_TREE(&bdi->cgwb_tree, GFP_ATOMIC);
bdi->cgwb_congested_tree = RB_ROOT;
+ mutex_init(&bdi->cgwb_release_mutex);
ret = wb_init(&bdi->wb, bdi, 1, GFP_KERNEL);
if (!ret) {
spin_lock_irq(&cgwb_lock);
radix_tree_for_each_slot(slot, &bdi->cgwb_tree, &iter, 0)
cgwb_kill(*slot);
+ spin_unlock_irq(&cgwb_lock);
+ mutex_lock(&bdi->cgwb_release_mutex);
+ spin_lock_irq(&cgwb_lock);
while (!list_empty(&bdi->wb_list)) {
wb = list_first_entry(&bdi->wb_list, struct bdi_writeback,
bdi_node);
spin_lock_irq(&cgwb_lock);
}
spin_unlock_irq(&cgwb_lock);
+ mutex_unlock(&bdi->cgwb_release_mutex);
}
/**
#include <linux/kmemleak.h>
#include <linux/seq_file.h>
#include <linux/memblock.h>
-#include <linux/bootmem.h>
#include <asm/sections.h>
#include <linux/io.h>
list_del(&s->list);
if (s->flags & SLAB_TYPESAFE_BY_RCU) {
+#ifdef SLAB_SUPPORTS_SYSFS
+ sysfs_slab_unlink(s);
+#endif
list_add_tail(&s->list, &slab_caches_to_rcu_destroy);
schedule_work(&slab_caches_to_rcu_destroy_work);
} else {
#ifdef SLAB_SUPPORTS_SYSFS
+ sysfs_slab_unlink(s);
sysfs_slab_release(s);
#else
slab_kmem_cache_release(s);
kset_unregister(s->memcg_kset);
#endif
kobject_uevent(&s->kobj, KOBJ_REMOVE);
- kobject_del(&s->kobj);
out:
kobject_put(&s->kobj);
}
schedule_work(&s->kobj_remove_work);
}
+void sysfs_slab_unlink(struct kmem_cache *s)
+{
+ if (slab_state >= FULL)
+ kobject_del(&s->kobj);
+}
+
void sysfs_slab_release(struct kmem_cache *s)
{
if (slab_state >= FULL)
* to occur in the future. Keep on running the
* update worker thread.
*/
- preempt_disable();
queue_delayed_work_on(smp_processor_id(), mm_percpu_wq,
this_cpu_ptr(&vmstat_work),
round_jiffies_relative(sysctl_stat_interval));
- preempt_enable();
}
}
return err;
}
-static struct sk_buff **vlan_gro_receive(struct sk_buff **head,
- struct sk_buff *skb)
+static struct sk_buff *vlan_gro_receive(struct list_head *head,
+ struct sk_buff *skb)
{
- struct sk_buff *p, **pp = NULL;
- struct vlan_hdr *vhdr;
- unsigned int hlen, off_vlan;
const struct packet_offload *ptype;
+ unsigned int hlen, off_vlan;
+ struct sk_buff *pp = NULL;
+ struct vlan_hdr *vhdr;
+ struct sk_buff *p;
__be16 type;
int flush = 1;
flush = 0;
- for (p = *head; p; p = p->next) {
+ list_for_each_entry(p, head, list) {
struct vlan_hdr *vhdr2;
if (!NAPI_GRO_CB(p)->same_flow)
out_unlock:
rcu_read_unlock();
out:
- NAPI_GRO_CB(skb)->flush |= flush;
+ skb_gro_flush_final(skb, pp, flush);
return pp;
}
obj-$(CONFIG_XFRM) += xfrm/
obj-$(CONFIG_UNIX) += unix/
obj-$(CONFIG_NET) += ipv6/
-ifneq ($(CC_CAN_LINK),y)
-$(warning CC cannot link executables. Skipping bpfilter.)
-else
obj-$(CONFIG_BPFILTER) += bpfilter/
-endif
obj-$(CONFIG_PACKET) += packet/
obj-$(CONFIG_NET_KEY) += key/
obj-$(CONFIG_BRIDGE) += bridge/
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = atalk_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.ioctl = atalk_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = atalk_compat_ioctl,
ATM_SKB(skb)->vcc = atmvcc = brvcc->atmvcc;
pr_debug("atm_skb(%p)->vcc(%p)->dev(%p)\n", skb, atmvcc, atmvcc->dev);
- refcount_add(skb->truesize, &sk_atm(atmvcc)->sk_wmem_alloc);
- ATM_SKB(skb)->atm_options = atmvcc->atm_options;
+ atm_account_tx(atmvcc, skb);
dev->stats.tx_packets++;
dev->stats.tx_bytes += skb->len;
memcpy(here, llc_oui, sizeof(llc_oui));
((__be16 *) here)[3] = skb->protocol;
}
- refcount_add(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc);
- ATM_SKB(skb)->atm_options = vcc->atm_options;
+ atm_account_tx(vcc, skb);
entry->vccs->last_use = jiffies;
pr_debug("atm_skb(%p)->vcc(%p)->dev(%p)\n", skb, vcc, vcc->dev);
old = xchg(&entry->vccs->xoff, 1); /* assume XOFF ... */
goto out;
}
pr_debug("%d += %d\n", sk_wmem_alloc_get(sk), skb->truesize);
- refcount_add(skb->truesize, &sk->sk_wmem_alloc);
+ atm_account_tx(vcc, skb);
skb->dev = NULL; /* for paths shared with net_device interfaces */
- ATM_SKB(skb)->atm_options = vcc->atm_options;
if (!copy_from_iter_full(skb_put(skb, size), size, &m->msg_iter)) {
kfree_skb(skb);
error = -EFAULT;
return error;
}
-__poll_t vcc_poll_mask(struct socket *sock, __poll_t events)
+__poll_t vcc_poll(struct file *file, struct socket *sock, poll_table *wait)
{
struct sock *sk = sock->sk;
- struct atm_vcc *vcc = ATM_SD(sock);
- __poll_t mask = 0;
+ struct atm_vcc *vcc;
+ __poll_t mask;
+
+ sock_poll_wait(file, sk_sleep(sk), wait);
+ mask = 0;
+
+ vcc = ATM_SD(sock);
/* exceptional events */
if (sk->sk_err)
int vcc_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
int flags);
int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len);
-__poll_t vcc_poll_mask(struct socket *sock, __poll_t events);
+__poll_t vcc_poll(struct file *file, struct socket *sock, poll_table *wait);
int vcc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
int vcc_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
int vcc_setsockopt(struct socket *sock, int level, int optname,
struct net_device *dev = skb->dev;
ATM_SKB(skb)->vcc = vcc;
- ATM_SKB(skb)->atm_options = vcc->atm_options;
+ atm_account_tx(vcc, skb);
- refcount_add(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc);
if (vcc->send(vcc, skb) < 0) {
dev->stats.tx_dropped++;
return;
sizeof(struct llc_snap_hdr));
}
- refcount_add(skb->truesize, &sk_atm(entry->shortcut)->sk_wmem_alloc);
- ATM_SKB(skb)->atm_options = entry->shortcut->atm_options;
+ atm_account_tx(entry->shortcut, skb);
entry->shortcut->send(entry->shortcut, skb);
entry->packets_fwded++;
mpc->in_ops->put(entry);
return 1;
}
- refcount_add(skb->truesize, &sk_atm(ATM_SKB(skb)->vcc)->sk_wmem_alloc);
- ATM_SKB(skb)->atm_options = ATM_SKB(skb)->vcc->atm_options;
+ atm_account_tx(vcc, skb);
pr_debug("atm_skb(%p)->vcc(%p)->dev(%p)\n",
skb, ATM_SKB(skb)->vcc, ATM_SKB(skb)->vcc->dev);
ret = ATM_SKB(skb)->vcc->send(ATM_SKB(skb)->vcc, skb)
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = pvc_getname,
- .poll_mask = vcc_poll_mask,
+ .poll = vcc_poll,
.ioctl = vcc_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = vcc_compat_ioctl,
struct sock *sk = sk_atm(vcc);
pr_debug("(%d) %d -= %d\n",
- vcc->vci, sk_wmem_alloc_get(sk), skb->truesize);
- WARN_ON(refcount_sub_and_test(skb->truesize, &sk->sk_wmem_alloc));
+ vcc->vci, sk_wmem_alloc_get(sk), ATM_SKB(skb)->acct_truesize);
+ WARN_ON(refcount_sub_and_test(ATM_SKB(skb)->acct_truesize, &sk->sk_wmem_alloc));
dev_kfree_skb_any(skb);
sk->sk_write_space(sk);
}
.socketpair = sock_no_socketpair,
.accept = svc_accept,
.getname = svc_getname,
- .poll_mask = vcc_poll_mask,
+ .poll = vcc_poll,
.ioctl = svc_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = svc_compat_ioctl,
.socketpair = sock_no_socketpair,
.accept = ax25_accept,
.getname = ax25_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.ioctl = ax25_ioctl,
.listen = ax25_listen,
.shutdown = ax25_shutdown,
* detection frames. Set the locally administered bit to avoid
* collisions with users mac addresses.
*/
- random_ether_addr(bat_priv->bla.loopdetect_addr);
+ eth_random_addr(bat_priv->bla.loopdetect_addr);
bat_priv->bla.loopdetect_addr[0] = 0xba;
bat_priv->bla.loopdetect_addr[1] = 0xbe;
bat_priv->bla.loopdetect_lasttime = jiffies;
return 0;
}
-__poll_t bt_sock_poll_mask(struct socket *sock, __poll_t events)
+__poll_t bt_sock_poll(struct file *file, struct socket *sock,
+ poll_table *wait)
{
struct sock *sk = sock->sk;
__poll_t mask = 0;
BT_DBG("sock %p, sk %p", sock, sk);
+ poll_wait(file, sk_sleep(sk), wait);
+
if (sk->sk_state == BT_LISTEN)
return bt_accept_poll(sk);
return mask;
}
-EXPORT_SYMBOL(bt_sock_poll_mask);
+EXPORT_SYMBOL(bt_sock_poll);
int bt_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
.sendmsg = hci_sock_sendmsg,
.recvmsg = hci_sock_recvmsg,
.ioctl = hci_sock_ioctl,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.setsockopt = hci_sock_setsockopt,
.getname = l2cap_sock_getname,
.sendmsg = l2cap_sock_sendmsg,
.recvmsg = l2cap_sock_recvmsg,
- .poll_mask = bt_sock_poll_mask,
+ .poll = bt_sock_poll,
.ioctl = bt_sock_ioctl,
.mmap = sock_no_mmap,
.socketpair = sock_no_socketpair,
.setsockopt = rfcomm_sock_setsockopt,
.getsockopt = rfcomm_sock_getsockopt,
.ioctl = rfcomm_sock_ioctl,
- .poll_mask = bt_sock_poll_mask,
+ .poll = bt_sock_poll,
.socketpair = sock_no_socketpair,
.mmap = sock_no_mmap
};
.getname = sco_sock_getname,
.sendmsg = sco_sock_sendmsg,
.recvmsg = sco_sock_recvmsg,
- .poll_mask = bt_sock_poll_mask,
+ .poll = bt_sock_poll,
.ioctl = bt_sock_ioctl,
.mmap = sock_no_mmap,
.socketpair = sock_no_socketpair,
--- /dev/null
+bpfilter_umh
menuconfig BPFILTER
bool "BPF based packet filtering framework (BPFILTER)"
- default n
depends on NET && BPF && INET
help
This builds experimental bpfilter framework that is aiming to
if BPFILTER
config BPFILTER_UMH
tristate "bpfilter kernel module with user mode helper"
+ depends on $(success,$(srctree)/scripts/cc-can-link.sh $(CC))
default m
help
This builds bpfilter kernel module with embedded user mode helper
HOSTLDFLAGS += -static
endif
-# a bit of elf magic to convert bpfilter_umh binary into a binary blob
-# inside bpfilter_umh.o elf file referenced by
-# _binary_net_bpfilter_bpfilter_umh_start symbol
-# which bpfilter_kern.c passes further into umh blob loader at run-time
-quiet_cmd_copy_umh = GEN $@
- cmd_copy_umh = echo ':' > $(obj)/.bpfilter_umh.o.cmd; \
- $(OBJCOPY) -I binary -O `$(OBJDUMP) -f $<|grep format|cut -d' ' -f8` \
- -B `$(OBJDUMP) -f $<|grep architecture|cut -d, -f1|cut -d' ' -f2` \
- --rename-section .data=.init.rodata $< $@
-
-$(obj)/bpfilter_umh.o: $(obj)/bpfilter_umh
- $(call cmd,copy_umh)
+$(obj)/bpfilter_umh_blob.o: $(obj)/bpfilter_umh
obj-$(CONFIG_BPFILTER_UMH) += bpfilter.o
-bpfilter-objs += bpfilter_kern.o bpfilter_umh.o
+bpfilter-objs += bpfilter_kern.o bpfilter_umh_blob.o
#include <linux/file.h>
#include "msgfmt.h"
-#define UMH_start _binary_net_bpfilter_bpfilter_umh_start
-#define UMH_end _binary_net_bpfilter_bpfilter_umh_end
-
-extern char UMH_start;
-extern char UMH_end;
+extern char bpfilter_umh_start;
+extern char bpfilter_umh_end;
static struct umh_info info;
/* since ip_getsockopt() can run in parallel, serialize access to umh */
int err;
/* fork usermode process */
- err = fork_usermode_blob(&UMH_start, &UMH_end - &UMH_start, &info);
+ err = fork_usermode_blob(&bpfilter_umh_start,
+ &bpfilter_umh_end - &bpfilter_umh_start,
+ &info);
if (err)
return err;
pr_info("Loaded bpfilter_umh pid %d\n", info.pid);
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+ .section .init.rodata, "a"
+ .global bpfilter_umh_start
+bpfilter_umh_start:
+ .incbin "net/bpfilter/bpfilter_umh"
+ .global bpfilter_umh_end
+bpfilter_umh_end:
}
/* Copied from af_unix.c:unix_poll(), added CAIF tx_flow handling */
-static __poll_t caif_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t caif_poll(struct file *file,
+ struct socket *sock, poll_table *wait)
{
struct sock *sk = sock->sk;
+ __poll_t mask;
struct caifsock *cf_sk = container_of(sk, struct caifsock, sk);
- __poll_t mask = 0;
+
+ sock_poll_wait(file, sk_sleep(sk), wait);
+ mask = 0;
/* exceptional events? */
if (sk->sk_err)
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = sock_no_getname,
- .poll_mask = caif_poll_mask,
+ .poll = caif_poll,
.ioctl = sock_no_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = sock_no_getname,
- .poll_mask = caif_poll_mask,
+ .poll = caif_poll,
.ioctl = sock_no_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = sock_no_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.ioctl = can_ioctl, /* use can_ioctl() from af_can.c */
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = raw_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.ioctl = can_ioctl, /* use can_ioctl() from af_can.c */
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
/**
* datagram_poll - generic datagram poll
+ * @file: file struct
* @sock: socket
- * @events to wait for
+ * @wait: poll table
*
* Datagram poll: Again totally generic. This also handles
* sequenced packet sockets providing the socket receive queue
* and you use a different write policy from sock_writeable()
* then please supply your own write_space callback.
*/
-__poll_t datagram_poll_mask(struct socket *sock, __poll_t events)
+__poll_t datagram_poll(struct file *file, struct socket *sock,
+ poll_table *wait)
{
struct sock *sk = sock->sk;
- __poll_t mask = 0;
+ __poll_t mask;
+
+ sock_poll_wait(file, sk_sleep(sk), wait);
+ mask = 0;
/* exceptional events? */
if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
return mask;
}
-EXPORT_SYMBOL(datagram_poll_mask);
+EXPORT_SYMBOL(datagram_poll);
#include "net-sysfs.h"
-/* Instead of increasing this, you should create a hash table. */
#define MAX_GRO_SKBS 8
/* This should be increased if a protocol with a bigger head is added. */
struct netdev_tc_txq *tc = &dev->tc_to_txq[0];
int i;
+ /* walk through the TCs and see if it falls into any of them */
for (i = 0; i < TC_MAX_QUEUE; i++, tc++) {
if ((txq - tc->offset) < tc->count)
return i;
}
+ /* didn't find it, just return -1 to indicate no match */
return -1;
}
EXPORT_SYMBOL(netdev_txq_to_tc);
#ifdef CONFIG_XPS
+struct static_key xps_needed __read_mostly;
+EXPORT_SYMBOL(xps_needed);
+struct static_key xps_rxqs_needed __read_mostly;
+EXPORT_SYMBOL(xps_rxqs_needed);
static DEFINE_MUTEX(xps_map_mutex);
#define xmap_dereference(P) \
rcu_dereference_protected((P), lockdep_is_held(&xps_map_mutex))
int pos;
if (dev_maps)
- map = xmap_dereference(dev_maps->cpu_map[tci]);
+ map = xmap_dereference(dev_maps->attr_map[tci]);
if (!map)
return false;
break;
}
- RCU_INIT_POINTER(dev_maps->cpu_map[tci], NULL);
+ RCU_INIT_POINTER(dev_maps->attr_map[tci], NULL);
kfree_rcu(map, rcu);
return false;
}
return active;
}
+static void clean_xps_maps(struct net_device *dev, const unsigned long *mask,
+ struct xps_dev_maps *dev_maps, unsigned int nr_ids,
+ u16 offset, u16 count, bool is_rxqs_map)
+{
+ bool active = false;
+ int i, j;
+
+ for (j = -1; j = netif_attrmask_next(j, mask, nr_ids),
+ j < nr_ids;)
+ active |= remove_xps_queue_cpu(dev, dev_maps, j, offset,
+ count);
+ if (!active) {
+ if (is_rxqs_map) {
+ RCU_INIT_POINTER(dev->xps_rxqs_map, NULL);
+ } else {
+ RCU_INIT_POINTER(dev->xps_cpus_map, NULL);
+
+ for (i = offset + (count - 1); count--; i--)
+ netdev_queue_numa_node_write(
+ netdev_get_tx_queue(dev, i),
+ NUMA_NO_NODE);
+ }
+ kfree_rcu(dev_maps, rcu);
+ }
+}
+
static void netif_reset_xps_queues(struct net_device *dev, u16 offset,
u16 count)
{
+ const unsigned long *possible_mask = NULL;
struct xps_dev_maps *dev_maps;
- int cpu, i;
- bool active = false;
+ unsigned int nr_ids;
+
+ if (!static_key_false(&xps_needed))
+ return;
mutex_lock(&xps_map_mutex);
- dev_maps = xmap_dereference(dev->xps_maps);
+ if (static_key_false(&xps_rxqs_needed)) {
+ dev_maps = xmap_dereference(dev->xps_rxqs_map);
+ if (dev_maps) {
+ nr_ids = dev->num_rx_queues;
+ clean_xps_maps(dev, possible_mask, dev_maps, nr_ids,
+ offset, count, true);
+ }
+ }
+
+ dev_maps = xmap_dereference(dev->xps_cpus_map);
if (!dev_maps)
goto out_no_maps;
- for_each_possible_cpu(cpu)
- active |= remove_xps_queue_cpu(dev, dev_maps, cpu,
- offset, count);
-
- if (!active) {
- RCU_INIT_POINTER(dev->xps_maps, NULL);
- kfree_rcu(dev_maps, rcu);
- }
-
- for (i = offset + (count - 1); count--; i--)
- netdev_queue_numa_node_write(netdev_get_tx_queue(dev, i),
- NUMA_NO_NODE);
+ if (num_possible_cpus() > 1)
+ possible_mask = cpumask_bits(cpu_possible_mask);
+ nr_ids = nr_cpu_ids;
+ clean_xps_maps(dev, possible_mask, dev_maps, nr_ids, offset, count,
+ false);
out_no_maps:
+ if (static_key_enabled(&xps_rxqs_needed))
+ static_key_slow_dec(&xps_rxqs_needed);
+
+ static_key_slow_dec(&xps_needed);
mutex_unlock(&xps_map_mutex);
}
netif_reset_xps_queues(dev, index, dev->num_tx_queues - index);
}
-static struct xps_map *expand_xps_map(struct xps_map *map,
- int cpu, u16 index)
+static struct xps_map *expand_xps_map(struct xps_map *map, int attr_index,
+ u16 index, bool is_rxqs_map)
{
struct xps_map *new_map;
int alloc_len = XPS_MIN_MAP_ALLOC;
return map;
}
- /* Need to add queue to this CPU's existing map */
+ /* Need to add tx-queue to this CPU's/rx-queue's existing map */
if (map) {
if (pos < map->alloc_len)
return map;
alloc_len = map->alloc_len * 2;
}
- /* Need to allocate new map to store queue on this CPU's map */
- new_map = kzalloc_node(XPS_MAP_SIZE(alloc_len), GFP_KERNEL,
- cpu_to_node(cpu));
+ /* Need to allocate new map to store tx-queue on this CPU's/rx-queue's
+ * map
+ */
+ if (is_rxqs_map)
+ new_map = kzalloc(XPS_MAP_SIZE(alloc_len), GFP_KERNEL);
+ else
+ new_map = kzalloc_node(XPS_MAP_SIZE(alloc_len), GFP_KERNEL,
+ cpu_to_node(attr_index));
if (!new_map)
return NULL;
return new_map;
}
-int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask,
- u16 index)
+int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask,
+ u16 index, bool is_rxqs_map)
{
+ const unsigned long *online_mask = NULL, *possible_mask = NULL;
struct xps_dev_maps *dev_maps, *new_dev_maps = NULL;
- int i, cpu, tci, numa_node_id = -2;
+ int i, j, tci, numa_node_id = -2;
int maps_sz, num_tc = 1, tc = 0;
struct xps_map *map, *new_map;
bool active = false;
+ unsigned int nr_ids;
if (dev->num_tc) {
+ /* Do not allow XPS on subordinate device directly */
num_tc = dev->num_tc;
+ if (num_tc < 0)
+ return -EINVAL;
+
+ /* If queue belongs to subordinate dev use its map */
+ dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev;
+
tc = netdev_txq_to_tc(dev, index);
if (tc < 0)
return -EINVAL;
}
- maps_sz = XPS_DEV_MAPS_SIZE(num_tc);
- if (maps_sz < L1_CACHE_BYTES)
- maps_sz = L1_CACHE_BYTES;
-
mutex_lock(&xps_map_mutex);
+ if (is_rxqs_map) {
+ maps_sz = XPS_RXQ_DEV_MAPS_SIZE(num_tc, dev->num_rx_queues);
+ dev_maps = xmap_dereference(dev->xps_rxqs_map);
+ nr_ids = dev->num_rx_queues;
+ } else {
+ maps_sz = XPS_CPU_DEV_MAPS_SIZE(num_tc);
+ if (num_possible_cpus() > 1) {
+ online_mask = cpumask_bits(cpu_online_mask);
+ possible_mask = cpumask_bits(cpu_possible_mask);
+ }
+ dev_maps = xmap_dereference(dev->xps_cpus_map);
+ nr_ids = nr_cpu_ids;
+ }
- dev_maps = xmap_dereference(dev->xps_maps);
+ if (maps_sz < L1_CACHE_BYTES)
+ maps_sz = L1_CACHE_BYTES;
/* allocate memory for queue storage */
- for_each_cpu_and(cpu, cpu_online_mask, mask) {
+ for (j = -1; j = netif_attrmask_next_and(j, online_mask, mask, nr_ids),
+ j < nr_ids;) {
if (!new_dev_maps)
new_dev_maps = kzalloc(maps_sz, GFP_KERNEL);
if (!new_dev_maps) {
return -ENOMEM;
}
- tci = cpu * num_tc + tc;
- map = dev_maps ? xmap_dereference(dev_maps->cpu_map[tci]) :
+ tci = j * num_tc + tc;
+ map = dev_maps ? xmap_dereference(dev_maps->attr_map[tci]) :
NULL;
- map = expand_xps_map(map, cpu, index);
+ map = expand_xps_map(map, j, index, is_rxqs_map);
if (!map)
goto error;
- RCU_INIT_POINTER(new_dev_maps->cpu_map[tci], map);
+ RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map);
}
if (!new_dev_maps)
goto out_no_new_maps;
- for_each_possible_cpu(cpu) {
+ static_key_slow_inc(&xps_needed);
+ if (is_rxqs_map)
+ static_key_slow_inc(&xps_rxqs_needed);
+
+ for (j = -1; j = netif_attrmask_next(j, possible_mask, nr_ids),
+ j < nr_ids;) {
/* copy maps belonging to foreign traffic classes */
- for (i = tc, tci = cpu * num_tc; dev_maps && i--; tci++) {
+ for (i = tc, tci = j * num_tc; dev_maps && i--; tci++) {
/* fill in the new device map from the old device map */
- map = xmap_dereference(dev_maps->cpu_map[tci]);
- RCU_INIT_POINTER(new_dev_maps->cpu_map[tci], map);
+ map = xmap_dereference(dev_maps->attr_map[tci]);
+ RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map);
}
/* We need to explicitly update tci as prevous loop
* could break out early if dev_maps is NULL.
*/
- tci = cpu * num_tc + tc;
+ tci = j * num_tc + tc;
- if (cpumask_test_cpu(cpu, mask) && cpu_online(cpu)) {
- /* add queue to CPU maps */
+ if (netif_attr_test_mask(j, mask, nr_ids) &&
+ netif_attr_test_online(j, online_mask, nr_ids)) {
+ /* add tx-queue to CPU/rx-queue maps */
int pos = 0;
- map = xmap_dereference(new_dev_maps->cpu_map[tci]);
+ map = xmap_dereference(new_dev_maps->attr_map[tci]);
while ((pos < map->len) && (map->queues[pos] != index))
pos++;
if (pos == map->len)
map->queues[map->len++] = index;
#ifdef CONFIG_NUMA
- if (numa_node_id == -2)
- numa_node_id = cpu_to_node(cpu);
- else if (numa_node_id != cpu_to_node(cpu))
- numa_node_id = -1;
+ if (!is_rxqs_map) {
+ if (numa_node_id == -2)
+ numa_node_id = cpu_to_node(j);
+ else if (numa_node_id != cpu_to_node(j))
+ numa_node_id = -1;
+ }
#endif
} else if (dev_maps) {
/* fill in the new device map from the old device map */
- map = xmap_dereference(dev_maps->cpu_map[tci]);
- RCU_INIT_POINTER(new_dev_maps->cpu_map[tci], map);
+ map = xmap_dereference(dev_maps->attr_map[tci]);
+ RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map);
}
/* copy maps belonging to foreign traffic classes */
for (i = num_tc - tc, tci++; dev_maps && --i; tci++) {
/* fill in the new device map from the old device map */
- map = xmap_dereference(dev_maps->cpu_map[tci]);
- RCU_INIT_POINTER(new_dev_maps->cpu_map[tci], map);
+ map = xmap_dereference(dev_maps->attr_map[tci]);
+ RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map);
}
}
- rcu_assign_pointer(dev->xps_maps, new_dev_maps);
+ if (is_rxqs_map)
+ rcu_assign_pointer(dev->xps_rxqs_map, new_dev_maps);
+ else
+ rcu_assign_pointer(dev->xps_cpus_map, new_dev_maps);
/* Cleanup old maps */
if (!dev_maps)
goto out_no_old_maps;
- for_each_possible_cpu(cpu) {
- for (i = num_tc, tci = cpu * num_tc; i--; tci++) {
- new_map = xmap_dereference(new_dev_maps->cpu_map[tci]);
- map = xmap_dereference(dev_maps->cpu_map[tci]);
+ for (j = -1; j = netif_attrmask_next(j, possible_mask, nr_ids),
+ j < nr_ids;) {
+ for (i = num_tc, tci = j * num_tc; i--; tci++) {
+ new_map = xmap_dereference(new_dev_maps->attr_map[tci]);
+ map = xmap_dereference(dev_maps->attr_map[tci]);
if (map && map != new_map)
kfree_rcu(map, rcu);
}
active = true;
out_no_new_maps:
- /* update Tx queue numa node */
- netdev_queue_numa_node_write(netdev_get_tx_queue(dev, index),
- (numa_node_id >= 0) ? numa_node_id :
- NUMA_NO_NODE);
+ if (!is_rxqs_map) {
+ /* update Tx queue numa node */
+ netdev_queue_numa_node_write(netdev_get_tx_queue(dev, index),
+ (numa_node_id >= 0) ?
+ numa_node_id : NUMA_NO_NODE);
+ }
if (!dev_maps)
goto out_no_maps;
- /* removes queue from unused CPUs */
- for_each_possible_cpu(cpu) {
- for (i = tc, tci = cpu * num_tc; i--; tci++)
+ /* removes tx-queue from unused CPUs/rx-queues */
+ for (j = -1; j = netif_attrmask_next(j, possible_mask, nr_ids),
+ j < nr_ids;) {
+ for (i = tc, tci = j * num_tc; i--; tci++)
active |= remove_xps_queue(dev_maps, tci, index);
- if (!cpumask_test_cpu(cpu, mask) || !cpu_online(cpu))
+ if (!netif_attr_test_mask(j, mask, nr_ids) ||
+ !netif_attr_test_online(j, online_mask, nr_ids))
active |= remove_xps_queue(dev_maps, tci, index);
for (i = num_tc - tc, tci++; --i; tci++)
active |= remove_xps_queue(dev_maps, tci, index);
/* free map if not active */
if (!active) {
- RCU_INIT_POINTER(dev->xps_maps, NULL);
+ if (is_rxqs_map)
+ RCU_INIT_POINTER(dev->xps_rxqs_map, NULL);
+ else
+ RCU_INIT_POINTER(dev->xps_cpus_map, NULL);
kfree_rcu(dev_maps, rcu);
}
return 0;
error:
/* remove any maps that we added */
- for_each_possible_cpu(cpu) {
- for (i = num_tc, tci = cpu * num_tc; i--; tci++) {
- new_map = xmap_dereference(new_dev_maps->cpu_map[tci]);
+ for (j = -1; j = netif_attrmask_next(j, possible_mask, nr_ids),
+ j < nr_ids;) {
+ for (i = num_tc, tci = j * num_tc; i--; tci++) {
+ new_map = xmap_dereference(new_dev_maps->attr_map[tci]);
map = dev_maps ?
- xmap_dereference(dev_maps->cpu_map[tci]) :
+ xmap_dereference(dev_maps->attr_map[tci]) :
NULL;
if (new_map && new_map != map)
kfree(new_map);
kfree(new_dev_maps);
return -ENOMEM;
}
+
+int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask,
+ u16 index)
+{
+ return __netif_set_xps_queue(dev, cpumask_bits(mask), index, false);
+}
EXPORT_SYMBOL(netif_set_xps_queue);
#endif
+static void netdev_unbind_all_sb_channels(struct net_device *dev)
+{
+ struct netdev_queue *txq = &dev->_tx[dev->num_tx_queues];
+
+ /* Unbind any subordinate channels */
+ while (txq-- != &dev->_tx[0]) {
+ if (txq->sb_dev)
+ netdev_unbind_sb_channel(dev, txq->sb_dev);
+ }
+}
+
void netdev_reset_tc(struct net_device *dev)
{
#ifdef CONFIG_XPS
netif_reset_xps_queues_gt(dev, 0);
#endif
+ netdev_unbind_all_sb_channels(dev);
+
+ /* Reset TC configuration of device */
dev->num_tc = 0;
memset(dev->tc_to_txq, 0, sizeof(dev->tc_to_txq));
memset(dev->prio_tc_map, 0, sizeof(dev->prio_tc_map));
#ifdef CONFIG_XPS
netif_reset_xps_queues_gt(dev, 0);
#endif
+ netdev_unbind_all_sb_channels(dev);
+
dev->num_tc = num_tc;
return 0;
}
EXPORT_SYMBOL(netdev_set_num_tc);
+void netdev_unbind_sb_channel(struct net_device *dev,
+ struct net_device *sb_dev)
+{
+ struct netdev_queue *txq = &dev->_tx[dev->num_tx_queues];
+
+#ifdef CONFIG_XPS
+ netif_reset_xps_queues_gt(sb_dev, 0);
+#endif
+ memset(sb_dev->tc_to_txq, 0, sizeof(sb_dev->tc_to_txq));
+ memset(sb_dev->prio_tc_map, 0, sizeof(sb_dev->prio_tc_map));
+
+ while (txq-- != &dev->_tx[0]) {
+ if (txq->sb_dev == sb_dev)
+ txq->sb_dev = NULL;
+ }
+}
+EXPORT_SYMBOL(netdev_unbind_sb_channel);
+
+int netdev_bind_sb_channel_queue(struct net_device *dev,
+ struct net_device *sb_dev,
+ u8 tc, u16 count, u16 offset)
+{
+ /* Make certain the sb_dev and dev are already configured */
+ if (sb_dev->num_tc >= 0 || tc >= dev->num_tc)
+ return -EINVAL;
+
+ /* We cannot hand out queues we don't have */
+ if ((offset + count) > dev->real_num_tx_queues)
+ return -EINVAL;
+
+ /* Record the mapping */
+ sb_dev->tc_to_txq[tc].count = count;
+ sb_dev->tc_to_txq[tc].offset = offset;
+
+ /* Provide a way for Tx queue to find the tc_to_txq map or
+ * XPS map for itself.
+ */
+ while (count--)
+ netdev_get_tx_queue(dev, count + offset)->sb_dev = sb_dev;
+
+ return 0;
+}
+EXPORT_SYMBOL(netdev_bind_sb_channel_queue);
+
+int netdev_set_sb_channel(struct net_device *dev, u16 channel)
+{
+ /* Do not use a multiqueue device to represent a subordinate channel */
+ if (netif_is_multiqueue(dev))
+ return -ENODEV;
+
+ /* We allow channels 1 - 32767 to be used for subordinate channels.
+ * Channel 0 is meant to be "native" mode and used only to represent
+ * the main root device. We allow writing 0 to reset the device back
+ * to normal mode after being used as a subordinate channel.
+ */
+ if (channel > S16_MAX)
+ return -EINVAL;
+
+ dev->num_tc = -channel;
+
+ return 0;
+}
+EXPORT_SYMBOL(netdev_set_sb_channel);
+
/*
* Routine to help set real_num_tx_queues. To avoid skbs mapped to queues
* greater than real_num_tx_queues stale skbs on the qdisc must be flushed.
* Returns a Tx hash based on the given packet descriptor a Tx queues' number
* to be used as a distribution range.
*/
-static u16 skb_tx_hash(const struct net_device *dev, struct sk_buff *skb)
+static u16 skb_tx_hash(const struct net_device *dev,
+ const struct net_device *sb_dev,
+ struct sk_buff *skb)
{
u32 hash;
u16 qoffset = 0;
u16 qcount = dev->real_num_tx_queues;
+ if (dev->num_tc) {
+ u8 tc = netdev_get_prio_tc_map(dev, skb->priority);
+
+ qoffset = sb_dev->tc_to_txq[tc].offset;
+ qcount = sb_dev->tc_to_txq[tc].count;
+ }
+
if (skb_rx_queue_recorded(skb)) {
hash = skb_get_rx_queue(skb);
while (unlikely(hash >= qcount))
hash -= qcount;
- return hash;
- }
-
- if (dev->num_tc) {
- u8 tc = netdev_get_prio_tc_map(dev, skb->priority);
-
- qoffset = dev->tc_to_txq[tc].offset;
- qcount = dev->tc_to_txq[tc].count;
+ return hash + qoffset;
}
return (u16) reciprocal_scale(skb_get_hash(skb), qcount) + qoffset;
}
#endif /* CONFIG_NET_EGRESS */
-static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
+#ifdef CONFIG_XPS
+static int __get_xps_queue_idx(struct net_device *dev, struct sk_buff *skb,
+ struct xps_dev_maps *dev_maps, unsigned int tci)
+{
+ struct xps_map *map;
+ int queue_index = -1;
+
+ if (dev->num_tc) {
+ tci *= dev->num_tc;
+ tci += netdev_get_prio_tc_map(dev, skb->priority);
+ }
+
+ map = rcu_dereference(dev_maps->attr_map[tci]);
+ if (map) {
+ if (map->len == 1)
+ queue_index = map->queues[0];
+ else
+ queue_index = map->queues[reciprocal_scale(
+ skb_get_hash(skb), map->len)];
+ if (unlikely(queue_index >= dev->real_num_tx_queues))
+ queue_index = -1;
+ }
+ return queue_index;
+}
+#endif
+
+static int get_xps_queue(struct net_device *dev, struct net_device *sb_dev,
+ struct sk_buff *skb)
{
#ifdef CONFIG_XPS
struct xps_dev_maps *dev_maps;
- struct xps_map *map;
+ struct sock *sk = skb->sk;
int queue_index = -1;
+ if (!static_key_false(&xps_needed))
+ return -1;
+
rcu_read_lock();
- dev_maps = rcu_dereference(dev->xps_maps);
+ if (!static_key_false(&xps_rxqs_needed))
+ goto get_cpus_map;
+
+ dev_maps = rcu_dereference(sb_dev->xps_rxqs_map);
if (dev_maps) {
- unsigned int tci = skb->sender_cpu - 1;
+ int tci = sk_rx_queue_get(sk);
- if (dev->num_tc) {
- tci *= dev->num_tc;
- tci += netdev_get_prio_tc_map(dev, skb->priority);
- }
+ if (tci >= 0 && tci < dev->num_rx_queues)
+ queue_index = __get_xps_queue_idx(dev, skb, dev_maps,
+ tci);
+ }
- map = rcu_dereference(dev_maps->cpu_map[tci]);
- if (map) {
- if (map->len == 1)
- queue_index = map->queues[0];
- else
- queue_index = map->queues[reciprocal_scale(skb_get_hash(skb),
- map->len)];
- if (unlikely(queue_index >= dev->real_num_tx_queues))
- queue_index = -1;
+get_cpus_map:
+ if (queue_index < 0) {
+ dev_maps = rcu_dereference(sb_dev->xps_cpus_map);
+ if (dev_maps) {
+ unsigned int tci = skb->sender_cpu - 1;
+
+ queue_index = __get_xps_queue_idx(dev, skb, dev_maps,
+ tci);
}
}
rcu_read_unlock();
#endif
}
-static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb)
+u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb,
+ struct net_device *sb_dev,
+ select_queue_fallback_t fallback)
+{
+ return 0;
+}
+EXPORT_SYMBOL(dev_pick_tx_zero);
+
+u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb,
+ struct net_device *sb_dev,
+ select_queue_fallback_t fallback)
+{
+ return (u16)raw_smp_processor_id() % dev->real_num_tx_queues;
+}
+EXPORT_SYMBOL(dev_pick_tx_cpu_id);
+
+static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb,
+ struct net_device *sb_dev)
{
struct sock *sk = skb->sk;
int queue_index = sk_tx_queue_get(sk);
+ sb_dev = sb_dev ? : dev;
+
if (queue_index < 0 || skb->ooo_okay ||
queue_index >= dev->real_num_tx_queues) {
- int new_index = get_xps_queue(dev, skb);
+ int new_index = get_xps_queue(dev, sb_dev, skb);
if (new_index < 0)
- new_index = skb_tx_hash(dev, skb);
+ new_index = skb_tx_hash(dev, sb_dev, skb);
if (queue_index != new_index && sk &&
sk_fullsock(sk) &&
struct netdev_queue *netdev_pick_tx(struct net_device *dev,
struct sk_buff *skb,
- void *accel_priv)
+ struct net_device *sb_dev)
{
int queue_index = 0;
const struct net_device_ops *ops = dev->netdev_ops;
if (ops->ndo_select_queue)
- queue_index = ops->ndo_select_queue(dev, skb, accel_priv,
+ queue_index = ops->ndo_select_queue(dev, skb, sb_dev,
__netdev_pick_tx);
else
- queue_index = __netdev_pick_tx(dev, skb);
+ queue_index = __netdev_pick_tx(dev, skb, sb_dev);
queue_index = netdev_cap_txqueue(dev, queue_index);
}
/**
* __dev_queue_xmit - transmit a buffer
* @skb: buffer to transmit
- * @accel_priv: private data used for L2 forwarding offload
+ * @sb_dev: suboordinate device used for L2 forwarding offload
*
* Queue a buffer for transmission to a network device. The caller must
* have set the device and priority and built the buffer before calling
* the BH enable code must have IRQs enabled so that it will not deadlock.
* --BLG
*/
-static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv)
+static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
{
struct net_device *dev = skb->dev;
struct netdev_queue *txq;
else
skb_dst_force(skb);
- txq = netdev_pick_tx(dev, skb, accel_priv);
+ txq = netdev_pick_tx(dev, skb, sb_dev);
q = rcu_dereference_bh(txq->qdisc);
trace_net_dev_queue(skb);
}
EXPORT_SYMBOL(dev_queue_xmit);
-int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv)
+int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev)
{
- return __dev_queue_xmit(skb, accel_priv);
+ return __dev_queue_xmit(skb, sb_dev);
}
EXPORT_SYMBOL(dev_queue_xmit_accel);
return 0;
}
-static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc)
+static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc,
+ struct packet_type **ppt_prev)
{
struct packet_type *ptype, *pt_prev;
rx_handler_func_t *rx_handler;
if (pt_prev) {
if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC)))
goto drop;
- else
- ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
+ *ppt_prev = pt_prev;
} else {
drop:
if (!deliver_exact)
return ret;
}
+static int __netif_receive_skb_one_core(struct sk_buff *skb, bool pfmemalloc)
+{
+ struct net_device *orig_dev = skb->dev;
+ struct packet_type *pt_prev = NULL;
+ int ret;
+
+ ret = __netif_receive_skb_core(skb, pfmemalloc, &pt_prev);
+ if (pt_prev)
+ ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
+ return ret;
+}
+
/**
* netif_receive_skb_core - special purpose version of netif_receive_skb
* @skb: buffer to process
int ret;
rcu_read_lock();
- ret = __netif_receive_skb_core(skb, false);
+ ret = __netif_receive_skb_one_core(skb, false);
rcu_read_unlock();
return ret;
}
EXPORT_SYMBOL(netif_receive_skb_core);
+static inline void __netif_receive_skb_list_ptype(struct list_head *head,
+ struct packet_type *pt_prev,
+ struct net_device *orig_dev)
+{
+ struct sk_buff *skb, *next;
+
+ if (!pt_prev)
+ return;
+ if (list_empty(head))
+ return;
+ if (pt_prev->list_func != NULL)
+ pt_prev->list_func(head, pt_prev, orig_dev);
+ else
+ list_for_each_entry_safe(skb, next, head, list)
+ pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
+}
+
+static void __netif_receive_skb_list_core(struct list_head *head, bool pfmemalloc)
+{
+ /* Fast-path assumptions:
+ * - There is no RX handler.
+ * - Only one packet_type matches.
+ * If either of these fails, we will end up doing some per-packet
+ * processing in-line, then handling the 'last ptype' for the whole
+ * sublist. This can't cause out-of-order delivery to any single ptype,
+ * because the 'last ptype' must be constant across the sublist, and all
+ * other ptypes are handled per-packet.
+ */
+ /* Current (common) ptype of sublist */
+ struct packet_type *pt_curr = NULL;
+ /* Current (common) orig_dev of sublist */
+ struct net_device *od_curr = NULL;
+ struct list_head sublist;
+ struct sk_buff *skb, *next;
+
+ INIT_LIST_HEAD(&sublist);
+ list_for_each_entry_safe(skb, next, head, list) {
+ struct net_device *orig_dev = skb->dev;
+ struct packet_type *pt_prev = NULL;
+
+ list_del(&skb->list);
+ __netif_receive_skb_core(skb, pfmemalloc, &pt_prev);
+ if (!pt_prev)
+ continue;
+ if (pt_curr != pt_prev || od_curr != orig_dev) {
+ /* dispatch old sublist */
+ __netif_receive_skb_list_ptype(&sublist, pt_curr, od_curr);
+ /* start new sublist */
+ INIT_LIST_HEAD(&sublist);
+ pt_curr = pt_prev;
+ od_curr = orig_dev;
+ }
+ list_add_tail(&skb->list, &sublist);
+ }
+
+ /* dispatch final sublist */
+ __netif_receive_skb_list_ptype(&sublist, pt_curr, od_curr);
+}
+
static int __netif_receive_skb(struct sk_buff *skb)
{
int ret;
* context down to all allocation sites.
*/
noreclaim_flag = memalloc_noreclaim_save();
- ret = __netif_receive_skb_core(skb, true);
+ ret = __netif_receive_skb_one_core(skb, true);
memalloc_noreclaim_restore(noreclaim_flag);
} else
- ret = __netif_receive_skb_core(skb, false);
+ ret = __netif_receive_skb_one_core(skb, false);
return ret;
}
+static void __netif_receive_skb_list(struct list_head *head)
+{
+ unsigned long noreclaim_flag = 0;
+ struct sk_buff *skb, *next;
+ bool pfmemalloc = false; /* Is current sublist PF_MEMALLOC? */
+
+ list_for_each_entry_safe(skb, next, head, list) {
+ if ((sk_memalloc_socks() && skb_pfmemalloc(skb)) != pfmemalloc) {
+ struct list_head sublist;
+
+ /* Handle the previous sublist */
+ list_cut_before(&sublist, head, &skb->list);
+ if (!list_empty(&sublist))
+ __netif_receive_skb_list_core(&sublist, pfmemalloc);
+ pfmemalloc = !pfmemalloc;
+ /* See comments in __netif_receive_skb */
+ if (pfmemalloc)
+ noreclaim_flag = memalloc_noreclaim_save();
+ else
+ memalloc_noreclaim_restore(noreclaim_flag);
+ }
+ }
+ /* Handle the remaining sublist */
+ if (!list_empty(head))
+ __netif_receive_skb_list_core(head, pfmemalloc);
+ /* Restore pflags */
+ if (pfmemalloc)
+ memalloc_noreclaim_restore(noreclaim_flag);
+}
+
static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp)
{
struct bpf_prog *old = rtnl_dereference(dev->xdp_prog);
break;
case XDP_QUERY_PROG:
- xdp->prog_attached = !!old;
xdp->prog_id = old ? old->aux->id : 0;
break;
return ret;
}
+static void netif_receive_skb_list_internal(struct list_head *head)
+{
+ struct bpf_prog *xdp_prog = NULL;
+ struct sk_buff *skb, *next;
+ struct list_head sublist;
+
+ INIT_LIST_HEAD(&sublist);
+ list_for_each_entry_safe(skb, next, head, list) {
+ net_timestamp_check(netdev_tstamp_prequeue, skb);
+ list_del(&skb->list);
+ if (!skb_defer_rx_timestamp(skb))
+ list_add_tail(&skb->list, &sublist);
+ }
+ list_splice_init(&sublist, head);
+
+ if (static_branch_unlikely(&generic_xdp_needed_key)) {
+ preempt_disable();
+ rcu_read_lock();
+ list_for_each_entry_safe(skb, next, head, list) {
+ xdp_prog = rcu_dereference(skb->dev->xdp_prog);
+ list_del(&skb->list);
+ if (do_xdp_generic(xdp_prog, skb) == XDP_PASS)
+ list_add_tail(&skb->list, &sublist);
+ }
+ rcu_read_unlock();
+ preempt_enable();
+ /* Put passed packets back on main list */
+ list_splice_init(&sublist, head);
+ }
+
+ rcu_read_lock();
+#ifdef CONFIG_RPS
+ if (static_key_false(&rps_needed)) {
+ list_for_each_entry_safe(skb, next, head, list) {
+ struct rps_dev_flow voidflow, *rflow = &voidflow;
+ int cpu = get_rps_cpu(skb->dev, skb, &rflow);
+
+ if (cpu >= 0) {
+ /* Will be handled, remove from list */
+ list_del(&skb->list);
+ enqueue_to_backlog(skb, cpu, &rflow->last_qtail);
+ }
+ }
+ }
+#endif
+ __netif_receive_skb_list(head);
+ rcu_read_unlock();
+}
+
/**
* netif_receive_skb - process receive buffer from network
* @skb: buffer to process
}
EXPORT_SYMBOL(netif_receive_skb);
+/**
+ * netif_receive_skb_list - process many receive buffers from network
+ * @head: list of skbs to process.
+ *
+ * Since return value of netif_receive_skb() is normally ignored, and
+ * wouldn't be meaningful for a list, this function returns void.
+ *
+ * This function may only be called from softirq context and interrupts
+ * should be enabled.
+ */
+void netif_receive_skb_list(struct list_head *head)
+{
+ struct sk_buff *skb;
+
+ if (list_empty(head))
+ return;
+ list_for_each_entry(skb, head, list)
+ trace_netif_receive_skb_list_entry(skb);
+ netif_receive_skb_list_internal(head);
+}
+EXPORT_SYMBOL(netif_receive_skb_list);
+
DEFINE_PER_CPU(struct work_struct, flush_works);
/* Network device is going away, flush any packets still pending */
return netif_receive_skb_internal(skb);
}
-/* napi->gro_list contains packets ordered by age.
- * youngest packets at the head of it.
- * Complete skbs in reverse order to reduce latencies.
- */
-void napi_gro_flush(struct napi_struct *napi, bool flush_old)
+static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index,
+ bool flush_old)
{
- struct sk_buff *skb, *prev = NULL;
-
- /* scan list and build reverse chain */
- for (skb = napi->gro_list; skb != NULL; skb = skb->next) {
- skb->prev = prev;
- prev = skb;
- }
-
- for (skb = prev; skb; skb = prev) {
- skb->next = NULL;
+ struct list_head *head = &napi->gro_hash[index].list;
+ struct sk_buff *skb, *p;
+ list_for_each_entry_safe_reverse(skb, p, head, list) {
if (flush_old && NAPI_GRO_CB(skb)->age == jiffies)
return;
-
- prev = skb->prev;
+ list_del(&skb->list);
+ skb->next = NULL;
napi_gro_complete(skb);
- napi->gro_count--;
+ napi->gro_hash[index].count--;
}
- napi->gro_list = NULL;
+ if (!napi->gro_hash[index].count)
+ __clear_bit(index, &napi->gro_bitmask);
+}
+
+/* napi->gro_hash[].list contains packets ordered by age.
+ * youngest packets at the head of it.
+ * Complete skbs in reverse order to reduce latencies.
+ */
+void napi_gro_flush(struct napi_struct *napi, bool flush_old)
+{
+ u32 i;
+
+ for (i = 0; i < GRO_HASH_BUCKETS; i++) {
+ if (test_bit(i, &napi->gro_bitmask))
+ __napi_gro_flush_chain(napi, i, flush_old);
+ }
}
EXPORT_SYMBOL(napi_gro_flush);
-static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb)
+static struct list_head *gro_list_prepare(struct napi_struct *napi,
+ struct sk_buff *skb)
{
- struct sk_buff *p;
unsigned int maclen = skb->dev->hard_header_len;
u32 hash = skb_get_hash_raw(skb);
+ struct list_head *head;
+ struct sk_buff *p;
- for (p = napi->gro_list; p; p = p->next) {
+ head = &napi->gro_hash[hash & (GRO_HASH_BUCKETS - 1)].list;
+ list_for_each_entry(p, head, list) {
unsigned long diffs;
NAPI_GRO_CB(p)->flush = 0;
maclen);
NAPI_GRO_CB(p)->same_flow = !diffs;
}
+
+ return head;
}
static void skb_gro_reset_offset(struct sk_buff *skb)
}
}
+static void gro_flush_oldest(struct list_head *head)
+{
+ struct sk_buff *oldest;
+
+ oldest = list_last_entry(head, struct sk_buff, list);
+
+ /* We are called with head length >= MAX_GRO_SKBS, so this is
+ * impossible.
+ */
+ if (WARN_ON_ONCE(!oldest))
+ return;
+
+ /* Do not adjust napi->gro_hash[].count, caller is adding a new
+ * SKB to the chain.
+ */
+ list_del(&oldest->list);
+ napi_gro_complete(oldest);
+}
+
static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
{
- struct sk_buff **pp = NULL;
+ u32 hash = skb_get_hash_raw(skb) & (GRO_HASH_BUCKETS - 1);
+ struct list_head *head = &offload_base;
struct packet_offload *ptype;
__be16 type = skb->protocol;
- struct list_head *head = &offload_base;
- int same_flow;
+ struct list_head *gro_head;
+ struct sk_buff *pp = NULL;
enum gro_result ret;
+ int same_flow;
int grow;
if (netif_elide_gro(skb->dev))
goto normal;
- gro_list_prepare(napi, skb);
+ gro_head = gro_list_prepare(napi, skb);
rcu_read_lock();
list_for_each_entry_rcu(ptype, head, list) {
NAPI_GRO_CB(skb)->csum_valid = 0;
}
- pp = ptype->callbacks.gro_receive(&napi->gro_list, skb);
+ pp = ptype->callbacks.gro_receive(gro_head, skb);
break;
}
rcu_read_unlock();
ret = NAPI_GRO_CB(skb)->free ? GRO_MERGED_FREE : GRO_MERGED;
if (pp) {
- struct sk_buff *nskb = *pp;
-
- *pp = nskb->next;
- nskb->next = NULL;
- napi_gro_complete(nskb);
- napi->gro_count--;
+ list_del(&pp->list);
+ pp->next = NULL;
+ napi_gro_complete(pp);
+ napi->gro_hash[hash].count--;
}
if (same_flow)
if (NAPI_GRO_CB(skb)->flush)
goto normal;
- if (unlikely(napi->gro_count >= MAX_GRO_SKBS)) {
- struct sk_buff *nskb = napi->gro_list;
-
- /* locate the end of the list to select the 'oldest' flow */
- while (nskb->next) {
- pp = &nskb->next;
- nskb = *pp;
- }
- *pp = NULL;
- nskb->next = NULL;
- napi_gro_complete(nskb);
+ if (unlikely(napi->gro_hash[hash].count >= MAX_GRO_SKBS)) {
+ gro_flush_oldest(gro_head);
} else {
- napi->gro_count++;
+ napi->gro_hash[hash].count++;
}
NAPI_GRO_CB(skb)->count = 1;
NAPI_GRO_CB(skb)->age = jiffies;
NAPI_GRO_CB(skb)->last = skb;
skb_shinfo(skb)->gso_size = skb_gro_len(skb);
- skb->next = napi->gro_list;
- napi->gro_list = skb;
+ list_add(&skb->list, gro_head);
ret = GRO_HELD;
pull:
if (grow > 0)
gro_pull_from_frag0(skb, grow);
ok:
+ if (napi->gro_hash[hash].count) {
+ if (!test_bit(hash, &napi->gro_bitmask))
+ __set_bit(hash, &napi->gro_bitmask);
+ } else if (test_bit(hash, &napi->gro_bitmask)) {
+ __clear_bit(hash, &napi->gro_bitmask);
+ }
+
return ret;
normal:
NAPIF_STATE_IN_BUSY_POLL)))
return false;
- if (n->gro_list) {
+ if (n->gro_bitmask) {
unsigned long timeout = 0;
if (work_done)
/* Note : we use a relaxed variant of napi_schedule_prep() not setting
* NAPI_STATE_MISSED, since we do not react to a device IRQ.
*/
- if (napi->gro_list && !napi_disable_pending(napi) &&
+ if (napi->gro_bitmask && !napi_disable_pending(napi) &&
!test_and_set_bit(NAPI_STATE_SCHED, &napi->state))
__napi_schedule_irqoff(napi);
void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
int (*poll)(struct napi_struct *, int), int weight)
{
+ int i;
+
INIT_LIST_HEAD(&napi->poll_list);
hrtimer_init(&napi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
napi->timer.function = napi_watchdog;
- napi->gro_count = 0;
- napi->gro_list = NULL;
+ napi->gro_bitmask = 0;
+ for (i = 0; i < GRO_HASH_BUCKETS; i++) {
+ INIT_LIST_HEAD(&napi->gro_hash[i].list);
+ napi->gro_hash[i].count = 0;
+ }
napi->skb = NULL;
napi->poll = poll;
if (weight > NAPI_POLL_WEIGHT)
}
EXPORT_SYMBOL(napi_disable);
+static void flush_gro_hash(struct napi_struct *napi)
+{
+ int i;
+
+ for (i = 0; i < GRO_HASH_BUCKETS; i++) {
+ struct sk_buff *skb, *n;
+
+ list_for_each_entry_safe(skb, n, &napi->gro_hash[i].list, list)
+ kfree_skb(skb);
+ napi->gro_hash[i].count = 0;
+ }
+}
+
/* Must be called in process context */
void netif_napi_del(struct napi_struct *napi)
{
list_del_init(&napi->dev_list);
napi_free_frags(napi);
- kfree_skb_list(napi->gro_list);
- napi->gro_list = NULL;
- napi->gro_count = 0;
+ flush_gro_hash(napi);
+ napi->gro_bitmask = 0;
}
EXPORT_SYMBOL(netif_napi_del);
goto out_unlock;
}
- if (n->gro_list) {
+ if (n->gro_bitmask) {
/* flush too old packets
* If HZ < 1000, flush all packets.
*/
}
EXPORT_SYMBOL(dev_change_proto_down);
-void __dev_xdp_query(struct net_device *dev, bpf_op_t bpf_op,
- struct netdev_bpf *xdp)
+u32 __dev_xdp_query(struct net_device *dev, bpf_op_t bpf_op,
+ enum bpf_netdev_command cmd)
{
- memset(xdp, 0, sizeof(*xdp));
- xdp->command = XDP_QUERY_PROG;
+ struct netdev_bpf xdp;
- /* Query must always succeed. */
- WARN_ON(bpf_op(dev, xdp) < 0);
-}
+ if (!bpf_op)
+ return 0;
-static u8 __dev_xdp_attached(struct net_device *dev, bpf_op_t bpf_op)
-{
- struct netdev_bpf xdp;
+ memset(&xdp, 0, sizeof(xdp));
+ xdp.command = cmd;
- __dev_xdp_query(dev, bpf_op, &xdp);
+ /* Query must always succeed. */
+ WARN_ON(bpf_op(dev, &xdp) < 0 && cmd == XDP_QUERY_PROG);
- return xdp.prog_attached;
+ return xdp.prog_id;
}
static int dev_xdp_install(struct net_device *dev, bpf_op_t bpf_op,
if (!ndo_bpf)
return;
- __dev_xdp_query(dev, ndo_bpf, &xdp);
- if (xdp.prog_attached == XDP_ATTACHED_NONE)
- return;
+ memset(&xdp, 0, sizeof(xdp));
+ xdp.command = XDP_QUERY_PROG;
+ WARN_ON(ndo_bpf(dev, &xdp));
+ if (xdp.prog_id)
+ WARN_ON(dev_xdp_install(dev, ndo_bpf, NULL, xdp.prog_flags,
+ NULL));
- /* Program removal should always succeed */
- WARN_ON(dev_xdp_install(dev, ndo_bpf, NULL, xdp.prog_flags, NULL));
+ /* Remove HW offload */
+ memset(&xdp, 0, sizeof(xdp));
+ xdp.command = XDP_QUERY_PROG_HW;
+ if (!ndo_bpf(dev, &xdp) && xdp.prog_id)
+ WARN_ON(dev_xdp_install(dev, ndo_bpf, NULL, xdp.prog_flags,
+ NULL));
}
/**
int fd, u32 flags)
{
const struct net_device_ops *ops = dev->netdev_ops;
+ enum bpf_netdev_command query;
struct bpf_prog *prog = NULL;
bpf_op_t bpf_op, bpf_chk;
int err;
ASSERT_RTNL();
+ query = flags & XDP_FLAGS_HW_MODE ? XDP_QUERY_PROG_HW : XDP_QUERY_PROG;
+
bpf_op = bpf_chk = ops->ndo_bpf;
if (!bpf_op && (flags & (XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE)))
return -EOPNOTSUPP;
bpf_chk = generic_xdp_install;
if (fd >= 0) {
- if (bpf_chk && __dev_xdp_attached(dev, bpf_chk))
+ if (__dev_xdp_query(dev, bpf_chk, XDP_QUERY_PROG) ||
+ __dev_xdp_query(dev, bpf_chk, XDP_QUERY_PROG_HW))
return -EEXIST;
if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) &&
- __dev_xdp_attached(dev, bpf_op))
+ __dev_xdp_query(dev, bpf_op, query))
return -EBUSY;
prog = bpf_prog_get_type_dev(fd, BPF_PROG_TYPE_XDP,
/* We get here if we can't use the current device name */
if (!pat)
goto out;
- if (dev_get_valid_name(net, dev, pat) < 0)
+ err = dev_get_valid_name(net, dev, pat);
+ if (err < 0)
goto out;
}
dev_close(dev);
/* And unlink it from device chain */
- err = -ENODEV;
unlist_netdevice(dev);
synchronize_net();
/* Initialize per network namespace state */
static int __net_init netdev_init(struct net *net)
{
+ BUILD_BUG_ON(GRO_HASH_BUCKETS >
+ 8 * FIELD_SIZEOF(struct napi_struct, gro_bitmask));
+
if (net != &init_net)
INIT_LIST_HEAD(&net->dev_base_head);
if (ifr->ifr_qlen < 0)
return -EINVAL;
if (dev->tx_queue_len ^ ifr->ifr_qlen) {
- unsigned int orig_len = dev->tx_queue_len;
-
- dev->tx_queue_len = ifr->ifr_qlen;
- err = call_netdevice_notifiers(
- NETDEV_CHANGE_TX_QUEUE_LEN, dev);
- err = notifier_to_errno(err);
- if (err) {
- dev->tx_queue_len = orig_len;
+ err = dev_change_tx_queue_len(dev, ifr->ifr_qlen);
+ if (err)
return err;
- }
}
return 0;
pool_type, p_tc_index);
}
+struct devlink_region {
+ struct devlink *devlink;
+ struct list_head list;
+ const char *name;
+ struct list_head snapshot_list;
+ u32 max_snapshots;
+ u32 cur_snapshots;
+ u64 size;
+};
+
+struct devlink_snapshot {
+ struct list_head list;
+ struct devlink_region *region;
+ devlink_snapshot_data_dest_t *data_destructor;
+ u64 data_len;
+ u8 *data;
+ u32 id;
+};
+
+static struct devlink_region *
+devlink_region_get_by_name(struct devlink *devlink, const char *region_name)
+{
+ struct devlink_region *region;
+
+ list_for_each_entry(region, &devlink->region_list, list)
+ if (!strcmp(region->name, region_name))
+ return region;
+
+ return NULL;
+}
+
+static struct devlink_snapshot *
+devlink_region_snapshot_get_by_id(struct devlink_region *region, u32 id)
+{
+ struct devlink_snapshot *snapshot;
+
+ list_for_each_entry(snapshot, ®ion->snapshot_list, list)
+ if (snapshot->id == id)
+ return snapshot;
+
+ return NULL;
+}
+
+static void devlink_region_snapshot_del(struct devlink_snapshot *snapshot)
+{
+ snapshot->region->cur_snapshots--;
+ list_del(&snapshot->list);
+ (*snapshot->data_destructor)(snapshot->data);
+ kfree(snapshot);
+}
+
#define DEVLINK_NL_FLAG_NEED_DEVLINK BIT(0)
#define DEVLINK_NL_FLAG_NEED_PORT BIT(1)
#define DEVLINK_NL_FLAG_NEED_SB BIT(2)
return devlink->ops->reload(devlink, info->extack);
}
-static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
- [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING },
- [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING },
- [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32 },
- [DEVLINK_ATTR_PORT_TYPE] = { .type = NLA_U16 },
- [DEVLINK_ATTR_PORT_SPLIT_COUNT] = { .type = NLA_U32 },
- [DEVLINK_ATTR_SB_INDEX] = { .type = NLA_U32 },
- [DEVLINK_ATTR_SB_POOL_INDEX] = { .type = NLA_U16 },
- [DEVLINK_ATTR_SB_POOL_TYPE] = { .type = NLA_U8 },
- [DEVLINK_ATTR_SB_POOL_SIZE] = { .type = NLA_U32 },
- [DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE] = { .type = NLA_U8 },
- [DEVLINK_ATTR_SB_THRESHOLD] = { .type = NLA_U32 },
- [DEVLINK_ATTR_SB_TC_INDEX] = { .type = NLA_U16 },
- [DEVLINK_ATTR_ESWITCH_MODE] = { .type = NLA_U16 },
- [DEVLINK_ATTR_ESWITCH_INLINE_MODE] = { .type = NLA_U8 },
- [DEVLINK_ATTR_ESWITCH_ENCAP_MODE] = { .type = NLA_U8 },
- [DEVLINK_ATTR_DPIPE_TABLE_NAME] = { .type = NLA_NUL_STRING },
- [DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED] = { .type = NLA_U8 },
- [DEVLINK_ATTR_RESOURCE_ID] = { .type = NLA_U64},
- [DEVLINK_ATTR_RESOURCE_SIZE] = { .type = NLA_U64},
-};
-
-static const struct genl_ops devlink_nl_ops[] = {
- {
- .cmd = DEVLINK_CMD_GET,
- .doit = devlink_nl_cmd_get_doit,
- .dumpit = devlink_nl_cmd_get_dumpit,
- .policy = devlink_nl_policy,
- .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
- /* can be retrieved by unprivileged users */
- },
- {
- .cmd = DEVLINK_CMD_PORT_GET,
- .doit = devlink_nl_cmd_port_get_doit,
- .dumpit = devlink_nl_cmd_port_get_dumpit,
- .policy = devlink_nl_policy,
- .internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
- /* can be retrieved by unprivileged users */
- },
- {
- .cmd = DEVLINK_CMD_PORT_SET,
- .doit = devlink_nl_cmd_port_set_doit,
- .policy = devlink_nl_policy,
- .flags = GENL_ADMIN_PERM,
- .internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
- },
- {
- .cmd = DEVLINK_CMD_PORT_SPLIT,
- .doit = devlink_nl_cmd_port_split_doit,
- .policy = devlink_nl_policy,
- .flags = GENL_ADMIN_PERM,
- .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
- DEVLINK_NL_FLAG_NO_LOCK,
- },
- {
- .cmd = DEVLINK_CMD_PORT_UNSPLIT,
- .doit = devlink_nl_cmd_port_unsplit_doit,
- .policy = devlink_nl_policy,
- .flags = GENL_ADMIN_PERM,
- .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
- DEVLINK_NL_FLAG_NO_LOCK,
- },
- {
- .cmd = DEVLINK_CMD_SB_GET,
- .doit = devlink_nl_cmd_sb_get_doit,
- .dumpit = devlink_nl_cmd_sb_get_dumpit,
- .policy = devlink_nl_policy,
- .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
- DEVLINK_NL_FLAG_NEED_SB,
- /* can be retrieved by unprivileged users */
- },
- {
- .cmd = DEVLINK_CMD_SB_POOL_GET,
- .doit = devlink_nl_cmd_sb_pool_get_doit,
- .dumpit = devlink_nl_cmd_sb_pool_get_dumpit,
- .policy = devlink_nl_policy,
- .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
- DEVLINK_NL_FLAG_NEED_SB,
- /* can be retrieved by unprivileged users */
- },
- {
- .cmd = DEVLINK_CMD_SB_POOL_SET,
- .doit = devlink_nl_cmd_sb_pool_set_doit,
- .policy = devlink_nl_policy,
- .flags = GENL_ADMIN_PERM,
- .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
- DEVLINK_NL_FLAG_NEED_SB,
- },
- {
- .cmd = DEVLINK_CMD_SB_PORT_POOL_GET,
- .doit = devlink_nl_cmd_sb_port_pool_get_doit,
- .dumpit = devlink_nl_cmd_sb_port_pool_get_dumpit,
- .policy = devlink_nl_policy,
- .internal_flags = DEVLINK_NL_FLAG_NEED_PORT |
- DEVLINK_NL_FLAG_NEED_SB,
- /* can be retrieved by unprivileged users */
- },
- {
- .cmd = DEVLINK_CMD_SB_PORT_POOL_SET,
- .doit = devlink_nl_cmd_sb_port_pool_set_doit,
- .policy = devlink_nl_policy,
- .flags = GENL_ADMIN_PERM,
- .internal_flags = DEVLINK_NL_FLAG_NEED_PORT |
- DEVLINK_NL_FLAG_NEED_SB,
- },
+static const struct devlink_param devlink_param_generic[] = {
{
- .cmd = DEVLINK_CMD_SB_TC_POOL_BIND_GET,
- .doit = devlink_nl_cmd_sb_tc_pool_bind_get_doit,
- .dumpit = devlink_nl_cmd_sb_tc_pool_bind_get_dumpit,
- .policy = devlink_nl_policy,
- .internal_flags = DEVLINK_NL_FLAG_NEED_PORT |
- DEVLINK_NL_FLAG_NEED_SB,
- /* can be retrieved by unprivileged users */
- },
- {
- .cmd = DEVLINK_CMD_SB_TC_POOL_BIND_SET,
- .doit = devlink_nl_cmd_sb_tc_pool_bind_set_doit,
- .policy = devlink_nl_policy,
- .flags = GENL_ADMIN_PERM,
- .internal_flags = DEVLINK_NL_FLAG_NEED_PORT |
- DEVLINK_NL_FLAG_NEED_SB,
- },
- {
- .cmd = DEVLINK_CMD_SB_OCC_SNAPSHOT,
- .doit = devlink_nl_cmd_sb_occ_snapshot_doit,
- .policy = devlink_nl_policy,
- .flags = GENL_ADMIN_PERM,
- .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
- DEVLINK_NL_FLAG_NEED_SB,
- },
- {
- .cmd = DEVLINK_CMD_SB_OCC_MAX_CLEAR,
- .doit = devlink_nl_cmd_sb_occ_max_clear_doit,
- .policy = devlink_nl_policy,
- .flags = GENL_ADMIN_PERM,
- .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
- DEVLINK_NL_FLAG_NEED_SB,
- },
- {
- .cmd = DEVLINK_CMD_ESWITCH_GET,
- .doit = devlink_nl_cmd_eswitch_get_doit,
- .policy = devlink_nl_policy,
- .flags = GENL_ADMIN_PERM,
- .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
- },
- {
- .cmd = DEVLINK_CMD_ESWITCH_SET,
- .doit = devlink_nl_cmd_eswitch_set_doit,
- .policy = devlink_nl_policy,
- .flags = GENL_ADMIN_PERM,
- .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
- DEVLINK_NL_FLAG_NO_LOCK,
- },
- {
- .cmd = DEVLINK_CMD_DPIPE_TABLE_GET,
- .doit = devlink_nl_cmd_dpipe_table_get,
- .policy = devlink_nl_policy,
- .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
- /* can be retrieved by unprivileged users */
- },
- {
- .cmd = DEVLINK_CMD_DPIPE_ENTRIES_GET,
- .doit = devlink_nl_cmd_dpipe_entries_get,
- .policy = devlink_nl_policy,
- .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
- /* can be retrieved by unprivileged users */
- },
- {
- .cmd = DEVLINK_CMD_DPIPE_HEADERS_GET,
- .doit = devlink_nl_cmd_dpipe_headers_get,
- .policy = devlink_nl_policy,
- .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
- /* can be retrieved by unprivileged users */
- },
- {
- .cmd = DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET,
- .doit = devlink_nl_cmd_dpipe_table_counters_set,
- .policy = devlink_nl_policy,
- .flags = GENL_ADMIN_PERM,
- .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+ .id = DEVLINK_PARAM_GENERIC_ID_INT_ERR_RESET,
+ .name = DEVLINK_PARAM_GENERIC_INT_ERR_RESET_NAME,
+ .type = DEVLINK_PARAM_GENERIC_INT_ERR_RESET_TYPE,
},
{
- .cmd = DEVLINK_CMD_RESOURCE_SET,
- .doit = devlink_nl_cmd_resource_set,
- .policy = devlink_nl_policy,
- .flags = GENL_ADMIN_PERM,
- .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+ .id = DEVLINK_PARAM_GENERIC_ID_MAX_MACS,
+ .name = DEVLINK_PARAM_GENERIC_MAX_MACS_NAME,
+ .type = DEVLINK_PARAM_GENERIC_MAX_MACS_TYPE,
},
{
- .cmd = DEVLINK_CMD_RESOURCE_DUMP,
- .doit = devlink_nl_cmd_resource_dump,
- .policy = devlink_nl_policy,
- .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
- /* can be retrieved by unprivileged users */
+ .id = DEVLINK_PARAM_GENERIC_ID_ENABLE_SRIOV,
+ .name = DEVLINK_PARAM_GENERIC_ENABLE_SRIOV_NAME,
+ .type = DEVLINK_PARAM_GENERIC_ENABLE_SRIOV_TYPE,
},
{
- .cmd = DEVLINK_CMD_RELOAD,
- .doit = devlink_nl_cmd_reload,
- .policy = devlink_nl_policy,
- .flags = GENL_ADMIN_PERM,
- .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
- DEVLINK_NL_FLAG_NO_LOCK,
+ .id = DEVLINK_PARAM_GENERIC_ID_REGION_SNAPSHOT,
+ .name = DEVLINK_PARAM_GENERIC_REGION_SNAPSHOT_NAME,
+ .type = DEVLINK_PARAM_GENERIC_REGION_SNAPSHOT_TYPE,
},
};
-static struct genl_family devlink_nl_family __ro_after_init = {
- .name = DEVLINK_GENL_NAME,
- .version = DEVLINK_GENL_VERSION,
- .maxattr = DEVLINK_ATTR_MAX,
- .netnsok = true,
- .pre_doit = devlink_nl_pre_doit,
- .post_doit = devlink_nl_post_doit,
- .module = THIS_MODULE,
- .ops = devlink_nl_ops,
- .n_ops = ARRAY_SIZE(devlink_nl_ops),
- .mcgrps = devlink_nl_mcgrps,
- .n_mcgrps = ARRAY_SIZE(devlink_nl_mcgrps),
-};
+static int devlink_param_generic_verify(const struct devlink_param *param)
+{
+ /* verify it match generic parameter by id and name */
+ if (param->id > DEVLINK_PARAM_GENERIC_ID_MAX)
+ return -EINVAL;
+ if (strcmp(param->name, devlink_param_generic[param->id].name))
+ return -ENOENT;
-/**
- * devlink_alloc - Allocate new devlink instance resources
- *
- * @ops: ops
- * @priv_size: size of user private data
- *
- * Allocate new devlink instance resources, including devlink index
- * and name.
- */
-struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size)
+ WARN_ON(param->type != devlink_param_generic[param->id].type);
+
+ return 0;
+}
+
+static int devlink_param_driver_verify(const struct devlink_param *param)
{
- struct devlink *devlink;
+ int i;
- devlink = kzalloc(sizeof(*devlink) + priv_size, GFP_KERNEL);
- if (!devlink)
- return NULL;
- devlink->ops = ops;
- devlink_net_set(devlink, &init_net);
- INIT_LIST_HEAD(&devlink->port_list);
- INIT_LIST_HEAD(&devlink->sb_list);
+ if (param->id <= DEVLINK_PARAM_GENERIC_ID_MAX)
+ return -EINVAL;
+ /* verify no such name in generic params */
+ for (i = 0; i <= DEVLINK_PARAM_GENERIC_ID_MAX; i++)
+ if (!strcmp(param->name, devlink_param_generic[i].name))
+ return -EEXIST;
+
+ return 0;
+}
+
+static struct devlink_param_item *
+devlink_param_find_by_name(struct list_head *param_list,
+ const char *param_name)
+{
+ struct devlink_param_item *param_item;
+
+ list_for_each_entry(param_item, param_list, list)
+ if (!strcmp(param_item->param->name, param_name))
+ return param_item;
+ return NULL;
+}
+
+static struct devlink_param_item *
+devlink_param_find_by_id(struct list_head *param_list, u32 param_id)
+{
+ struct devlink_param_item *param_item;
+
+ list_for_each_entry(param_item, param_list, list)
+ if (param_item->param->id == param_id)
+ return param_item;
+ return NULL;
+}
+
+static bool
+devlink_param_cmode_is_supported(const struct devlink_param *param,
+ enum devlink_param_cmode cmode)
+{
+ return test_bit(cmode, ¶m->supported_cmodes);
+}
+
+static int devlink_param_get(struct devlink *devlink,
+ const struct devlink_param *param,
+ struct devlink_param_gset_ctx *ctx)
+{
+ if (!param->get)
+ return -EOPNOTSUPP;
+ return param->get(devlink, param->id, ctx);
+}
+
+static int devlink_param_set(struct devlink *devlink,
+ const struct devlink_param *param,
+ struct devlink_param_gset_ctx *ctx)
+{
+ if (!param->set)
+ return -EOPNOTSUPP;
+ return param->set(devlink, param->id, ctx);
+}
+
+static int
+devlink_param_type_to_nla_type(enum devlink_param_type param_type)
+{
+ switch (param_type) {
+ case DEVLINK_PARAM_TYPE_U8:
+ return NLA_U8;
+ case DEVLINK_PARAM_TYPE_U16:
+ return NLA_U16;
+ case DEVLINK_PARAM_TYPE_U32:
+ return NLA_U32;
+ case DEVLINK_PARAM_TYPE_STRING:
+ return NLA_STRING;
+ case DEVLINK_PARAM_TYPE_BOOL:
+ return NLA_FLAG;
+ default:
+ return -EINVAL;
+ }
+}
+
+static int
+devlink_nl_param_value_fill_one(struct sk_buff *msg,
+ enum devlink_param_type type,
+ enum devlink_param_cmode cmode,
+ union devlink_param_value val)
+{
+ struct nlattr *param_value_attr;
+
+ param_value_attr = nla_nest_start(msg, DEVLINK_ATTR_PARAM_VALUE);
+ if (!param_value_attr)
+ goto nla_put_failure;
+
+ if (nla_put_u8(msg, DEVLINK_ATTR_PARAM_VALUE_CMODE, cmode))
+ goto value_nest_cancel;
+
+ switch (type) {
+ case DEVLINK_PARAM_TYPE_U8:
+ if (nla_put_u8(msg, DEVLINK_ATTR_PARAM_VALUE_DATA, val.vu8))
+ goto value_nest_cancel;
+ break;
+ case DEVLINK_PARAM_TYPE_U16:
+ if (nla_put_u16(msg, DEVLINK_ATTR_PARAM_VALUE_DATA, val.vu16))
+ goto value_nest_cancel;
+ break;
+ case DEVLINK_PARAM_TYPE_U32:
+ if (nla_put_u32(msg, DEVLINK_ATTR_PARAM_VALUE_DATA, val.vu32))
+ goto value_nest_cancel;
+ break;
+ case DEVLINK_PARAM_TYPE_STRING:
+ if (nla_put_string(msg, DEVLINK_ATTR_PARAM_VALUE_DATA,
+ val.vstr))
+ goto value_nest_cancel;
+ break;
+ case DEVLINK_PARAM_TYPE_BOOL:
+ if (val.vbool &&
+ nla_put_flag(msg, DEVLINK_ATTR_PARAM_VALUE_DATA))
+ goto value_nest_cancel;
+ break;
+ }
+
+ nla_nest_end(msg, param_value_attr);
+ return 0;
+
+value_nest_cancel:
+ nla_nest_cancel(msg, param_value_attr);
+nla_put_failure:
+ return -EMSGSIZE;
+}
+
+static int devlink_nl_param_fill(struct sk_buff *msg, struct devlink *devlink,
+ struct devlink_param_item *param_item,
+ enum devlink_command cmd,
+ u32 portid, u32 seq, int flags)
+{
+ union devlink_param_value param_value[DEVLINK_PARAM_CMODE_MAX + 1];
+ const struct devlink_param *param = param_item->param;
+ struct devlink_param_gset_ctx ctx;
+ struct nlattr *param_values_list;
+ struct nlattr *param_attr;
+ int nla_type;
+ void *hdr;
+ int err;
+ int i;
+
+ /* Get value from driver part to driverinit configuration mode */
+ for (i = 0; i <= DEVLINK_PARAM_CMODE_MAX; i++) {
+ if (!devlink_param_cmode_is_supported(param, i))
+ continue;
+ if (i == DEVLINK_PARAM_CMODE_DRIVERINIT) {
+ if (!param_item->driverinit_value_valid)
+ return -EOPNOTSUPP;
+ param_value[i] = param_item->driverinit_value;
+ } else {
+ ctx.cmode = i;
+ err = devlink_param_get(devlink, param, &ctx);
+ if (err)
+ return err;
+ param_value[i] = ctx.val;
+ }
+ }
+
+ hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
+ if (!hdr)
+ return -EMSGSIZE;
+
+ if (devlink_nl_put_handle(msg, devlink))
+ goto genlmsg_cancel;
+ param_attr = nla_nest_start(msg, DEVLINK_ATTR_PARAM);
+ if (!param_attr)
+ goto genlmsg_cancel;
+ if (nla_put_string(msg, DEVLINK_ATTR_PARAM_NAME, param->name))
+ goto param_nest_cancel;
+ if (param->generic && nla_put_flag(msg, DEVLINK_ATTR_PARAM_GENERIC))
+ goto param_nest_cancel;
+
+ nla_type = devlink_param_type_to_nla_type(param->type);
+ if (nla_type < 0)
+ goto param_nest_cancel;
+ if (nla_put_u8(msg, DEVLINK_ATTR_PARAM_TYPE, nla_type))
+ goto param_nest_cancel;
+
+ param_values_list = nla_nest_start(msg, DEVLINK_ATTR_PARAM_VALUES_LIST);
+ if (!param_values_list)
+ goto param_nest_cancel;
+
+ for (i = 0; i <= DEVLINK_PARAM_CMODE_MAX; i++) {
+ if (!devlink_param_cmode_is_supported(param, i))
+ continue;
+ err = devlink_nl_param_value_fill_one(msg, param->type,
+ i, param_value[i]);
+ if (err)
+ goto values_list_nest_cancel;
+ }
+
+ nla_nest_end(msg, param_values_list);
+ nla_nest_end(msg, param_attr);
+ genlmsg_end(msg, hdr);
+ return 0;
+
+values_list_nest_cancel:
+ nla_nest_end(msg, param_values_list);
+param_nest_cancel:
+ nla_nest_cancel(msg, param_attr);
+genlmsg_cancel:
+ genlmsg_cancel(msg, hdr);
+ return -EMSGSIZE;
+}
+
+static void devlink_param_notify(struct devlink *devlink,
+ struct devlink_param_item *param_item,
+ enum devlink_command cmd)
+{
+ struct sk_buff *msg;
+ int err;
+
+ WARN_ON(cmd != DEVLINK_CMD_PARAM_NEW && cmd != DEVLINK_CMD_PARAM_DEL);
+
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg)
+ return;
+ err = devlink_nl_param_fill(msg, devlink, param_item, cmd, 0, 0, 0);
+ if (err) {
+ nlmsg_free(msg);
+ return;
+ }
+
+ genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
+ msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+}
+
+static int devlink_nl_cmd_param_get_dumpit(struct sk_buff *msg,
+ struct netlink_callback *cb)
+{
+ struct devlink_param_item *param_item;
+ struct devlink *devlink;
+ int start = cb->args[0];
+ int idx = 0;
+ int err;
+
+ mutex_lock(&devlink_mutex);
+ list_for_each_entry(devlink, &devlink_list, list) {
+ if (!net_eq(devlink_net(devlink), sock_net(msg->sk)))
+ continue;
+ mutex_lock(&devlink->lock);
+ list_for_each_entry(param_item, &devlink->param_list, list) {
+ if (idx < start) {
+ idx++;
+ continue;
+ }
+ err = devlink_nl_param_fill(msg, devlink, param_item,
+ DEVLINK_CMD_PARAM_GET,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq,
+ NLM_F_MULTI);
+ if (err) {
+ mutex_unlock(&devlink->lock);
+ goto out;
+ }
+ idx++;
+ }
+ mutex_unlock(&devlink->lock);
+ }
+out:
+ mutex_unlock(&devlink_mutex);
+
+ cb->args[0] = idx;
+ return msg->len;
+}
+
+static int
+devlink_param_type_get_from_info(struct genl_info *info,
+ enum devlink_param_type *param_type)
+{
+ if (!info->attrs[DEVLINK_ATTR_PARAM_TYPE])
+ return -EINVAL;
+
+ switch (nla_get_u8(info->attrs[DEVLINK_ATTR_PARAM_TYPE])) {
+ case NLA_U8:
+ *param_type = DEVLINK_PARAM_TYPE_U8;
+ break;
+ case NLA_U16:
+ *param_type = DEVLINK_PARAM_TYPE_U16;
+ break;
+ case NLA_U32:
+ *param_type = DEVLINK_PARAM_TYPE_U32;
+ break;
+ case NLA_STRING:
+ *param_type = DEVLINK_PARAM_TYPE_STRING;
+ break;
+ case NLA_FLAG:
+ *param_type = DEVLINK_PARAM_TYPE_BOOL;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int
+devlink_param_value_get_from_info(const struct devlink_param *param,
+ struct genl_info *info,
+ union devlink_param_value *value)
+{
+ if (param->type != DEVLINK_PARAM_TYPE_BOOL &&
+ !info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA])
+ return -EINVAL;
+
+ switch (param->type) {
+ case DEVLINK_PARAM_TYPE_U8:
+ value->vu8 = nla_get_u8(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]);
+ break;
+ case DEVLINK_PARAM_TYPE_U16:
+ value->vu16 = nla_get_u16(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]);
+ break;
+ case DEVLINK_PARAM_TYPE_U32:
+ value->vu32 = nla_get_u32(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]);
+ break;
+ case DEVLINK_PARAM_TYPE_STRING:
+ if (nla_len(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]) >
+ DEVLINK_PARAM_MAX_STRING_VALUE)
+ return -EINVAL;
+ value->vstr = nla_data(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]);
+ break;
+ case DEVLINK_PARAM_TYPE_BOOL:
+ value->vbool = info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA] ?
+ true : false;
+ break;
+ }
+ return 0;
+}
+
+static struct devlink_param_item *
+devlink_param_get_from_info(struct devlink *devlink,
+ struct genl_info *info)
+{
+ char *param_name;
+
+ if (!info->attrs[DEVLINK_ATTR_PARAM_NAME])
+ return NULL;
+
+ param_name = nla_data(info->attrs[DEVLINK_ATTR_PARAM_NAME]);
+ return devlink_param_find_by_name(&devlink->param_list, param_name);
+}
+
+static int devlink_nl_cmd_param_get_doit(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct devlink *devlink = info->user_ptr[0];
+ struct devlink_param_item *param_item;
+ struct sk_buff *msg;
+ int err;
+
+ param_item = devlink_param_get_from_info(devlink, info);
+ if (!param_item)
+ return -EINVAL;
+
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg)
+ return -ENOMEM;
+
+ err = devlink_nl_param_fill(msg, devlink, param_item,
+ DEVLINK_CMD_PARAM_GET,
+ info->snd_portid, info->snd_seq, 0);
+ if (err) {
+ nlmsg_free(msg);
+ return err;
+ }
+
+ return genlmsg_reply(msg, info);
+}
+
+static int devlink_nl_cmd_param_set_doit(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct devlink *devlink = info->user_ptr[0];
+ enum devlink_param_type param_type;
+ struct devlink_param_gset_ctx ctx;
+ enum devlink_param_cmode cmode;
+ struct devlink_param_item *param_item;
+ const struct devlink_param *param;
+ union devlink_param_value value;
+ int err = 0;
+
+ param_item = devlink_param_get_from_info(devlink, info);
+ if (!param_item)
+ return -EINVAL;
+ param = param_item->param;
+ err = devlink_param_type_get_from_info(info, ¶m_type);
+ if (err)
+ return err;
+ if (param_type != param->type)
+ return -EINVAL;
+ err = devlink_param_value_get_from_info(param, info, &value);
+ if (err)
+ return err;
+ if (param->validate) {
+ err = param->validate(devlink, param->id, value, info->extack);
+ if (err)
+ return err;
+ }
+
+ if (!info->attrs[DEVLINK_ATTR_PARAM_VALUE_CMODE])
+ return -EINVAL;
+ cmode = nla_get_u8(info->attrs[DEVLINK_ATTR_PARAM_VALUE_CMODE]);
+ if (!devlink_param_cmode_is_supported(param, cmode))
+ return -EOPNOTSUPP;
+
+ if (cmode == DEVLINK_PARAM_CMODE_DRIVERINIT) {
+ param_item->driverinit_value = value;
+ param_item->driverinit_value_valid = true;
+ } else {
+ if (!param->set)
+ return -EOPNOTSUPP;
+ ctx.val = value;
+ ctx.cmode = cmode;
+ err = devlink_param_set(devlink, param, &ctx);
+ if (err)
+ return err;
+ }
+
+ devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_NEW);
+ return 0;
+}
+
+static int devlink_param_register_one(struct devlink *devlink,
+ const struct devlink_param *param)
+{
+ struct devlink_param_item *param_item;
+
+ if (devlink_param_find_by_name(&devlink->param_list,
+ param->name))
+ return -EEXIST;
+
+ if (param->supported_cmodes == BIT(DEVLINK_PARAM_CMODE_DRIVERINIT))
+ WARN_ON(param->get || param->set);
+ else
+ WARN_ON(!param->get || !param->set);
+
+ param_item = kzalloc(sizeof(*param_item), GFP_KERNEL);
+ if (!param_item)
+ return -ENOMEM;
+ param_item->param = param;
+
+ list_add_tail(¶m_item->list, &devlink->param_list);
+ devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_NEW);
+ return 0;
+}
+
+static void devlink_param_unregister_one(struct devlink *devlink,
+ const struct devlink_param *param)
+{
+ struct devlink_param_item *param_item;
+
+ param_item = devlink_param_find_by_name(&devlink->param_list,
+ param->name);
+ WARN_ON(!param_item);
+ devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_DEL);
+ list_del(¶m_item->list);
+ kfree(param_item);
+}
+
+static int devlink_nl_region_snapshot_id_put(struct sk_buff *msg,
+ struct devlink *devlink,
+ struct devlink_snapshot *snapshot)
+{
+ struct nlattr *snap_attr;
+ int err;
+
+ snap_attr = nla_nest_start(msg, DEVLINK_ATTR_REGION_SNAPSHOT);
+ if (!snap_attr)
+ return -EINVAL;
+
+ err = nla_put_u32(msg, DEVLINK_ATTR_REGION_SNAPSHOT_ID, snapshot->id);
+ if (err)
+ goto nla_put_failure;
+
+ nla_nest_end(msg, snap_attr);
+ return 0;
+
+nla_put_failure:
+ nla_nest_cancel(msg, snap_attr);
+ return err;
+}
+
+static int devlink_nl_region_snapshots_id_put(struct sk_buff *msg,
+ struct devlink *devlink,
+ struct devlink_region *region)
+{
+ struct devlink_snapshot *snapshot;
+ struct nlattr *snapshots_attr;
+ int err;
+
+ snapshots_attr = nla_nest_start(msg, DEVLINK_ATTR_REGION_SNAPSHOTS);
+ if (!snapshots_attr)
+ return -EINVAL;
+
+ list_for_each_entry(snapshot, ®ion->snapshot_list, list) {
+ err = devlink_nl_region_snapshot_id_put(msg, devlink, snapshot);
+ if (err)
+ goto nla_put_failure;
+ }
+
+ nla_nest_end(msg, snapshots_attr);
+ return 0;
+
+nla_put_failure:
+ nla_nest_cancel(msg, snapshots_attr);
+ return err;
+}
+
+static int devlink_nl_region_fill(struct sk_buff *msg, struct devlink *devlink,
+ enum devlink_command cmd, u32 portid,
+ u32 seq, int flags,
+ struct devlink_region *region)
+{
+ void *hdr;
+ int err;
+
+ hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
+ if (!hdr)
+ return -EMSGSIZE;
+
+ err = devlink_nl_put_handle(msg, devlink);
+ if (err)
+ goto nla_put_failure;
+
+ err = nla_put_string(msg, DEVLINK_ATTR_REGION_NAME, region->name);
+ if (err)
+ goto nla_put_failure;
+
+ err = nla_put_u64_64bit(msg, DEVLINK_ATTR_REGION_SIZE,
+ region->size,
+ DEVLINK_ATTR_PAD);
+ if (err)
+ goto nla_put_failure;
+
+ err = devlink_nl_region_snapshots_id_put(msg, devlink, region);
+ if (err)
+ goto nla_put_failure;
+
+ genlmsg_end(msg, hdr);
+ return 0;
+
+nla_put_failure:
+ genlmsg_cancel(msg, hdr);
+ return err;
+}
+
+static void devlink_nl_region_notify(struct devlink_region *region,
+ struct devlink_snapshot *snapshot,
+ enum devlink_command cmd)
+{
+ struct devlink *devlink = region->devlink;
+ struct sk_buff *msg;
+ void *hdr;
+ int err;
+
+ WARN_ON(cmd != DEVLINK_CMD_REGION_NEW && cmd != DEVLINK_CMD_REGION_DEL);
+
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg)
+ return;
+
+ hdr = genlmsg_put(msg, 0, 0, &devlink_nl_family, 0, cmd);
+ if (!hdr)
+ goto out_free_msg;
+
+ err = devlink_nl_put_handle(msg, devlink);
+ if (err)
+ goto out_cancel_msg;
+
+ err = nla_put_string(msg, DEVLINK_ATTR_REGION_NAME,
+ region->name);
+ if (err)
+ goto out_cancel_msg;
+
+ if (snapshot) {
+ err = nla_put_u32(msg, DEVLINK_ATTR_REGION_SNAPSHOT_ID,
+ snapshot->id);
+ if (err)
+ goto out_cancel_msg;
+ } else {
+ err = nla_put_u64_64bit(msg, DEVLINK_ATTR_REGION_SIZE,
+ region->size, DEVLINK_ATTR_PAD);
+ if (err)
+ goto out_cancel_msg;
+ }
+ genlmsg_end(msg, hdr);
+
+ genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
+ msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+
+ return;
+
+out_cancel_msg:
+ genlmsg_cancel(msg, hdr);
+out_free_msg:
+ nlmsg_free(msg);
+}
+
+static int devlink_nl_cmd_region_get_doit(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct devlink *devlink = info->user_ptr[0];
+ struct devlink_region *region;
+ const char *region_name;
+ struct sk_buff *msg;
+ int err;
+
+ if (!info->attrs[DEVLINK_ATTR_REGION_NAME])
+ return -EINVAL;
+
+ region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]);
+ region = devlink_region_get_by_name(devlink, region_name);
+ if (!region)
+ return -EINVAL;
+
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg)
+ return -ENOMEM;
+
+ err = devlink_nl_region_fill(msg, devlink, DEVLINK_CMD_REGION_GET,
+ info->snd_portid, info->snd_seq, 0,
+ region);
+ if (err) {
+ nlmsg_free(msg);
+ return err;
+ }
+
+ return genlmsg_reply(msg, info);
+}
+
+static int devlink_nl_cmd_region_get_dumpit(struct sk_buff *msg,
+ struct netlink_callback *cb)
+{
+ struct devlink_region *region;
+ struct devlink *devlink;
+ int start = cb->args[0];
+ int idx = 0;
+ int err;
+
+ mutex_lock(&devlink_mutex);
+ list_for_each_entry(devlink, &devlink_list, list) {
+ if (!net_eq(devlink_net(devlink), sock_net(msg->sk)))
+ continue;
+
+ mutex_lock(&devlink->lock);
+ list_for_each_entry(region, &devlink->region_list, list) {
+ if (idx < start) {
+ idx++;
+ continue;
+ }
+ err = devlink_nl_region_fill(msg, devlink,
+ DEVLINK_CMD_REGION_GET,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq,
+ NLM_F_MULTI, region);
+ if (err) {
+ mutex_unlock(&devlink->lock);
+ goto out;
+ }
+ idx++;
+ }
+ mutex_unlock(&devlink->lock);
+ }
+out:
+ mutex_unlock(&devlink_mutex);
+ cb->args[0] = idx;
+ return msg->len;
+}
+
+static int devlink_nl_cmd_region_del(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct devlink *devlink = info->user_ptr[0];
+ struct devlink_snapshot *snapshot;
+ struct devlink_region *region;
+ const char *region_name;
+ u32 snapshot_id;
+
+ if (!info->attrs[DEVLINK_ATTR_REGION_NAME] ||
+ !info->attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID])
+ return -EINVAL;
+
+ region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]);
+ snapshot_id = nla_get_u32(info->attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]);
+
+ region = devlink_region_get_by_name(devlink, region_name);
+ if (!region)
+ return -EINVAL;
+
+ snapshot = devlink_region_snapshot_get_by_id(region, snapshot_id);
+ if (!snapshot)
+ return -EINVAL;
+
+ devlink_nl_region_notify(region, snapshot, DEVLINK_CMD_REGION_DEL);
+ devlink_region_snapshot_del(snapshot);
+ return 0;
+}
+
+static int devlink_nl_cmd_region_read_chunk_fill(struct sk_buff *msg,
+ struct devlink *devlink,
+ u8 *chunk, u32 chunk_size,
+ u64 addr)
+{
+ struct nlattr *chunk_attr;
+ int err;
+
+ chunk_attr = nla_nest_start(msg, DEVLINK_ATTR_REGION_CHUNK);
+ if (!chunk_attr)
+ return -EINVAL;
+
+ err = nla_put(msg, DEVLINK_ATTR_REGION_CHUNK_DATA, chunk_size, chunk);
+ if (err)
+ goto nla_put_failure;
+
+ err = nla_put_u64_64bit(msg, DEVLINK_ATTR_REGION_CHUNK_ADDR, addr,
+ DEVLINK_ATTR_PAD);
+ if (err)
+ goto nla_put_failure;
+
+ nla_nest_end(msg, chunk_attr);
+ return 0;
+
+nla_put_failure:
+ nla_nest_cancel(msg, chunk_attr);
+ return err;
+}
+
+#define DEVLINK_REGION_READ_CHUNK_SIZE 256
+
+static int devlink_nl_region_read_snapshot_fill(struct sk_buff *skb,
+ struct devlink *devlink,
+ struct devlink_region *region,
+ struct nlattr **attrs,
+ u64 start_offset,
+ u64 end_offset,
+ bool dump,
+ u64 *new_offset)
+{
+ struct devlink_snapshot *snapshot;
+ u64 curr_offset = start_offset;
+ u32 snapshot_id;
+ int err = 0;
+
+ *new_offset = start_offset;
+
+ snapshot_id = nla_get_u32(attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]);
+ snapshot = devlink_region_snapshot_get_by_id(region, snapshot_id);
+ if (!snapshot)
+ return -EINVAL;
+
+ if (end_offset > snapshot->data_len || dump)
+ end_offset = snapshot->data_len;
+
+ while (curr_offset < end_offset) {
+ u32 data_size;
+ u8 *data;
+
+ if (end_offset - curr_offset < DEVLINK_REGION_READ_CHUNK_SIZE)
+ data_size = end_offset - curr_offset;
+ else
+ data_size = DEVLINK_REGION_READ_CHUNK_SIZE;
+
+ data = &snapshot->data[curr_offset];
+ err = devlink_nl_cmd_region_read_chunk_fill(skb, devlink,
+ data, data_size,
+ curr_offset);
+ if (err)
+ break;
+
+ curr_offset += data_size;
+ }
+ *new_offset = curr_offset;
+
+ return err;
+}
+
+static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb,
+ struct netlink_callback *cb)
+{
+ u64 ret_offset, start_offset, end_offset = 0;
+ struct nlattr *attrs[DEVLINK_ATTR_MAX + 1];
+ const struct genl_ops *ops = cb->data;
+ struct devlink_region *region;
+ struct nlattr *chunks_attr;
+ const char *region_name;
+ struct devlink *devlink;
+ bool dump = true;
+ void *hdr;
+ int err;
+
+ start_offset = *((u64 *)&cb->args[0]);
+
+ err = nlmsg_parse(cb->nlh, GENL_HDRLEN + devlink_nl_family.hdrsize,
+ attrs, DEVLINK_ATTR_MAX, ops->policy, NULL);
+ if (err)
+ goto out;
+
+ devlink = devlink_get_from_attrs(sock_net(cb->skb->sk), attrs);
+ if (IS_ERR(devlink))
+ goto out;
+
+ mutex_lock(&devlink_mutex);
+ mutex_lock(&devlink->lock);
+
+ if (!attrs[DEVLINK_ATTR_REGION_NAME] ||
+ !attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID])
+ goto out_unlock;
+
+ region_name = nla_data(attrs[DEVLINK_ATTR_REGION_NAME]);
+ region = devlink_region_get_by_name(devlink, region_name);
+ if (!region)
+ goto out_unlock;
+
+ hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
+ &devlink_nl_family, NLM_F_ACK | NLM_F_MULTI,
+ DEVLINK_CMD_REGION_READ);
+ if (!hdr)
+ goto out_unlock;
+
+ err = devlink_nl_put_handle(skb, devlink);
+ if (err)
+ goto nla_put_failure;
+
+ err = nla_put_string(skb, DEVLINK_ATTR_REGION_NAME, region_name);
+ if (err)
+ goto nla_put_failure;
+
+ chunks_attr = nla_nest_start(skb, DEVLINK_ATTR_REGION_CHUNKS);
+ if (!chunks_attr)
+ goto nla_put_failure;
+
+ if (attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR] &&
+ attrs[DEVLINK_ATTR_REGION_CHUNK_LEN]) {
+ if (!start_offset)
+ start_offset =
+ nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR]);
+
+ end_offset = nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR]);
+ end_offset += nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_LEN]);
+ dump = false;
+ }
+
+ err = devlink_nl_region_read_snapshot_fill(skb, devlink,
+ region, attrs,
+ start_offset,
+ end_offset, dump,
+ &ret_offset);
+
+ if (err && err != -EMSGSIZE)
+ goto nla_put_failure;
+
+ /* Check if there was any progress done to prevent infinite loop */
+ if (ret_offset == start_offset)
+ goto nla_put_failure;
+
+ *((u64 *)&cb->args[0]) = ret_offset;
+
+ nla_nest_end(skb, chunks_attr);
+ genlmsg_end(skb, hdr);
+ mutex_unlock(&devlink->lock);
+ mutex_unlock(&devlink_mutex);
+
+ return skb->len;
+
+nla_put_failure:
+ genlmsg_cancel(skb, hdr);
+out_unlock:
+ mutex_unlock(&devlink->lock);
+ mutex_unlock(&devlink_mutex);
+out:
+ return 0;
+}
+
+static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
+ [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING },
+ [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING },
+ [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32 },
+ [DEVLINK_ATTR_PORT_TYPE] = { .type = NLA_U16 },
+ [DEVLINK_ATTR_PORT_SPLIT_COUNT] = { .type = NLA_U32 },
+ [DEVLINK_ATTR_SB_INDEX] = { .type = NLA_U32 },
+ [DEVLINK_ATTR_SB_POOL_INDEX] = { .type = NLA_U16 },
+ [DEVLINK_ATTR_SB_POOL_TYPE] = { .type = NLA_U8 },
+ [DEVLINK_ATTR_SB_POOL_SIZE] = { .type = NLA_U32 },
+ [DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE] = { .type = NLA_U8 },
+ [DEVLINK_ATTR_SB_THRESHOLD] = { .type = NLA_U32 },
+ [DEVLINK_ATTR_SB_TC_INDEX] = { .type = NLA_U16 },
+ [DEVLINK_ATTR_ESWITCH_MODE] = { .type = NLA_U16 },
+ [DEVLINK_ATTR_ESWITCH_INLINE_MODE] = { .type = NLA_U8 },
+ [DEVLINK_ATTR_ESWITCH_ENCAP_MODE] = { .type = NLA_U8 },
+ [DEVLINK_ATTR_DPIPE_TABLE_NAME] = { .type = NLA_NUL_STRING },
+ [DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED] = { .type = NLA_U8 },
+ [DEVLINK_ATTR_RESOURCE_ID] = { .type = NLA_U64},
+ [DEVLINK_ATTR_RESOURCE_SIZE] = { .type = NLA_U64},
+ [DEVLINK_ATTR_PARAM_NAME] = { .type = NLA_NUL_STRING },
+ [DEVLINK_ATTR_PARAM_TYPE] = { .type = NLA_U8 },
+ [DEVLINK_ATTR_PARAM_VALUE_CMODE] = { .type = NLA_U8 },
+ [DEVLINK_ATTR_REGION_NAME] = { .type = NLA_NUL_STRING },
+ [DEVLINK_ATTR_REGION_SNAPSHOT_ID] = { .type = NLA_U32 },
+};
+
+static const struct genl_ops devlink_nl_ops[] = {
+ {
+ .cmd = DEVLINK_CMD_GET,
+ .doit = devlink_nl_cmd_get_doit,
+ .dumpit = devlink_nl_cmd_get_dumpit,
+ .policy = devlink_nl_policy,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+ /* can be retrieved by unprivileged users */
+ },
+ {
+ .cmd = DEVLINK_CMD_PORT_GET,
+ .doit = devlink_nl_cmd_port_get_doit,
+ .dumpit = devlink_nl_cmd_port_get_dumpit,
+ .policy = devlink_nl_policy,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
+ /* can be retrieved by unprivileged users */
+ },
+ {
+ .cmd = DEVLINK_CMD_PORT_SET,
+ .doit = devlink_nl_cmd_port_set_doit,
+ .policy = devlink_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
+ },
+ {
+ .cmd = DEVLINK_CMD_PORT_SPLIT,
+ .doit = devlink_nl_cmd_port_split_doit,
+ .policy = devlink_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
+ DEVLINK_NL_FLAG_NO_LOCK,
+ },
+ {
+ .cmd = DEVLINK_CMD_PORT_UNSPLIT,
+ .doit = devlink_nl_cmd_port_unsplit_doit,
+ .policy = devlink_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
+ DEVLINK_NL_FLAG_NO_LOCK,
+ },
+ {
+ .cmd = DEVLINK_CMD_SB_GET,
+ .doit = devlink_nl_cmd_sb_get_doit,
+ .dumpit = devlink_nl_cmd_sb_get_dumpit,
+ .policy = devlink_nl_policy,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
+ DEVLINK_NL_FLAG_NEED_SB,
+ /* can be retrieved by unprivileged users */
+ },
+ {
+ .cmd = DEVLINK_CMD_SB_POOL_GET,
+ .doit = devlink_nl_cmd_sb_pool_get_doit,
+ .dumpit = devlink_nl_cmd_sb_pool_get_dumpit,
+ .policy = devlink_nl_policy,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
+ DEVLINK_NL_FLAG_NEED_SB,
+ /* can be retrieved by unprivileged users */
+ },
+ {
+ .cmd = DEVLINK_CMD_SB_POOL_SET,
+ .doit = devlink_nl_cmd_sb_pool_set_doit,
+ .policy = devlink_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
+ DEVLINK_NL_FLAG_NEED_SB,
+ },
+ {
+ .cmd = DEVLINK_CMD_SB_PORT_POOL_GET,
+ .doit = devlink_nl_cmd_sb_port_pool_get_doit,
+ .dumpit = devlink_nl_cmd_sb_port_pool_get_dumpit,
+ .policy = devlink_nl_policy,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_PORT |
+ DEVLINK_NL_FLAG_NEED_SB,
+ /* can be retrieved by unprivileged users */
+ },
+ {
+ .cmd = DEVLINK_CMD_SB_PORT_POOL_SET,
+ .doit = devlink_nl_cmd_sb_port_pool_set_doit,
+ .policy = devlink_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_PORT |
+ DEVLINK_NL_FLAG_NEED_SB,
+ },
+ {
+ .cmd = DEVLINK_CMD_SB_TC_POOL_BIND_GET,
+ .doit = devlink_nl_cmd_sb_tc_pool_bind_get_doit,
+ .dumpit = devlink_nl_cmd_sb_tc_pool_bind_get_dumpit,
+ .policy = devlink_nl_policy,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_PORT |
+ DEVLINK_NL_FLAG_NEED_SB,
+ /* can be retrieved by unprivileged users */
+ },
+ {
+ .cmd = DEVLINK_CMD_SB_TC_POOL_BIND_SET,
+ .doit = devlink_nl_cmd_sb_tc_pool_bind_set_doit,
+ .policy = devlink_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_PORT |
+ DEVLINK_NL_FLAG_NEED_SB,
+ },
+ {
+ .cmd = DEVLINK_CMD_SB_OCC_SNAPSHOT,
+ .doit = devlink_nl_cmd_sb_occ_snapshot_doit,
+ .policy = devlink_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
+ DEVLINK_NL_FLAG_NEED_SB,
+ },
+ {
+ .cmd = DEVLINK_CMD_SB_OCC_MAX_CLEAR,
+ .doit = devlink_nl_cmd_sb_occ_max_clear_doit,
+ .policy = devlink_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
+ DEVLINK_NL_FLAG_NEED_SB,
+ },
+ {
+ .cmd = DEVLINK_CMD_ESWITCH_GET,
+ .doit = devlink_nl_cmd_eswitch_get_doit,
+ .policy = devlink_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+ },
+ {
+ .cmd = DEVLINK_CMD_ESWITCH_SET,
+ .doit = devlink_nl_cmd_eswitch_set_doit,
+ .policy = devlink_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
+ DEVLINK_NL_FLAG_NO_LOCK,
+ },
+ {
+ .cmd = DEVLINK_CMD_DPIPE_TABLE_GET,
+ .doit = devlink_nl_cmd_dpipe_table_get,
+ .policy = devlink_nl_policy,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+ /* can be retrieved by unprivileged users */
+ },
+ {
+ .cmd = DEVLINK_CMD_DPIPE_ENTRIES_GET,
+ .doit = devlink_nl_cmd_dpipe_entries_get,
+ .policy = devlink_nl_policy,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+ /* can be retrieved by unprivileged users */
+ },
+ {
+ .cmd = DEVLINK_CMD_DPIPE_HEADERS_GET,
+ .doit = devlink_nl_cmd_dpipe_headers_get,
+ .policy = devlink_nl_policy,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+ /* can be retrieved by unprivileged users */
+ },
+ {
+ .cmd = DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET,
+ .doit = devlink_nl_cmd_dpipe_table_counters_set,
+ .policy = devlink_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+ },
+ {
+ .cmd = DEVLINK_CMD_RESOURCE_SET,
+ .doit = devlink_nl_cmd_resource_set,
+ .policy = devlink_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+ },
+ {
+ .cmd = DEVLINK_CMD_RESOURCE_DUMP,
+ .doit = devlink_nl_cmd_resource_dump,
+ .policy = devlink_nl_policy,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+ /* can be retrieved by unprivileged users */
+ },
+ {
+ .cmd = DEVLINK_CMD_RELOAD,
+ .doit = devlink_nl_cmd_reload,
+ .policy = devlink_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
+ DEVLINK_NL_FLAG_NO_LOCK,
+ },
+ {
+ .cmd = DEVLINK_CMD_PARAM_GET,
+ .doit = devlink_nl_cmd_param_get_doit,
+ .dumpit = devlink_nl_cmd_param_get_dumpit,
+ .policy = devlink_nl_policy,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+ /* can be retrieved by unprivileged users */
+ },
+ {
+ .cmd = DEVLINK_CMD_PARAM_SET,
+ .doit = devlink_nl_cmd_param_set_doit,
+ .policy = devlink_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+ },
+ {
+ .cmd = DEVLINK_CMD_REGION_GET,
+ .doit = devlink_nl_cmd_region_get_doit,
+ .dumpit = devlink_nl_cmd_region_get_dumpit,
+ .policy = devlink_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+ },
+ {
+ .cmd = DEVLINK_CMD_REGION_DEL,
+ .doit = devlink_nl_cmd_region_del,
+ .policy = devlink_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+ },
+ {
+ .cmd = DEVLINK_CMD_REGION_READ,
+ .dumpit = devlink_nl_cmd_region_read_dumpit,
+ .policy = devlink_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+ },
+};
+
+static struct genl_family devlink_nl_family __ro_after_init = {
+ .name = DEVLINK_GENL_NAME,
+ .version = DEVLINK_GENL_VERSION,
+ .maxattr = DEVLINK_ATTR_MAX,
+ .netnsok = true,
+ .pre_doit = devlink_nl_pre_doit,
+ .post_doit = devlink_nl_post_doit,
+ .module = THIS_MODULE,
+ .ops = devlink_nl_ops,
+ .n_ops = ARRAY_SIZE(devlink_nl_ops),
+ .mcgrps = devlink_nl_mcgrps,
+ .n_mcgrps = ARRAY_SIZE(devlink_nl_mcgrps),
+};
+
+/**
+ * devlink_alloc - Allocate new devlink instance resources
+ *
+ * @ops: ops
+ * @priv_size: size of user private data
+ *
+ * Allocate new devlink instance resources, including devlink index
+ * and name.
+ */
+struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size)
+{
+ struct devlink *devlink;
+
+ devlink = kzalloc(sizeof(*devlink) + priv_size, GFP_KERNEL);
+ if (!devlink)
+ return NULL;
+ devlink->ops = ops;
+ devlink_net_set(devlink, &init_net);
+ INIT_LIST_HEAD(&devlink->port_list);
+ INIT_LIST_HEAD(&devlink->sb_list);
INIT_LIST_HEAD_RCU(&devlink->dpipe_table_list);
INIT_LIST_HEAD(&devlink->resource_list);
+ INIT_LIST_HEAD(&devlink->param_list);
+ INIT_LIST_HEAD(&devlink->region_list);
mutex_init(&devlink->lock);
return devlink;
}
}
EXPORT_SYMBOL_GPL(devlink_resource_occ_get_unregister);
+/**
+ * devlink_params_register - register configuration parameters
+ *
+ * @devlink: devlink
+ * @params: configuration parameters array
+ * @params_count: number of parameters provided
+ *
+ * Register the configuration parameters supported by the driver.
+ */
+int devlink_params_register(struct devlink *devlink,
+ const struct devlink_param *params,
+ size_t params_count)
+{
+ const struct devlink_param *param = params;
+ int i;
+ int err;
+
+ mutex_lock(&devlink->lock);
+ for (i = 0; i < params_count; i++, param++) {
+ if (!param || !param->name || !param->supported_cmodes) {
+ err = -EINVAL;
+ goto rollback;
+ }
+ if (param->generic) {
+ err = devlink_param_generic_verify(param);
+ if (err)
+ goto rollback;
+ } else {
+ err = devlink_param_driver_verify(param);
+ if (err)
+ goto rollback;
+ }
+ err = devlink_param_register_one(devlink, param);
+ if (err)
+ goto rollback;
+ }
+
+ mutex_unlock(&devlink->lock);
+ return 0;
+
+rollback:
+ if (!i)
+ goto unlock;
+ for (param--; i > 0; i--, param--)
+ devlink_param_unregister_one(devlink, param);
+unlock:
+ mutex_unlock(&devlink->lock);
+ return err;
+}
+EXPORT_SYMBOL_GPL(devlink_params_register);
+
+/**
+ * devlink_params_unregister - unregister configuration parameters
+ * @devlink: devlink
+ * @params: configuration parameters to unregister
+ * @params_count: number of parameters provided
+ */
+void devlink_params_unregister(struct devlink *devlink,
+ const struct devlink_param *params,
+ size_t params_count)
+{
+ const struct devlink_param *param = params;
+ int i;
+
+ mutex_lock(&devlink->lock);
+ for (i = 0; i < params_count; i++, param++)
+ devlink_param_unregister_one(devlink, param);
+ mutex_unlock(&devlink->lock);
+}
+EXPORT_SYMBOL_GPL(devlink_params_unregister);
+
+/**
+ * devlink_param_driverinit_value_get - get configuration parameter
+ * value for driver initializing
+ *
+ * @devlink: devlink
+ * @param_id: parameter ID
+ * @init_val: value of parameter in driverinit configuration mode
+ *
+ * This function should be used by the driver to get driverinit
+ * configuration for initialization after reload command.
+ */
+int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id,
+ union devlink_param_value *init_val)
+{
+ struct devlink_param_item *param_item;
+
+ if (!devlink->ops || !devlink->ops->reload)
+ return -EOPNOTSUPP;
+
+ param_item = devlink_param_find_by_id(&devlink->param_list, param_id);
+ if (!param_item)
+ return -EINVAL;
+
+ if (!param_item->driverinit_value_valid ||
+ !devlink_param_cmode_is_supported(param_item->param,
+ DEVLINK_PARAM_CMODE_DRIVERINIT))
+ return -EOPNOTSUPP;
+
+ *init_val = param_item->driverinit_value;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(devlink_param_driverinit_value_get);
+
+/**
+ * devlink_param_driverinit_value_set - set value of configuration
+ * parameter for driverinit
+ * configuration mode
+ *
+ * @devlink: devlink
+ * @param_id: parameter ID
+ * @init_val: value of parameter to set for driverinit configuration mode
+ *
+ * This function should be used by the driver to set driverinit
+ * configuration mode default value.
+ */
+int devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id,
+ union devlink_param_value init_val)
+{
+ struct devlink_param_item *param_item;
+
+ param_item = devlink_param_find_by_id(&devlink->param_list, param_id);
+ if (!param_item)
+ return -EINVAL;
+
+ if (!devlink_param_cmode_is_supported(param_item->param,
+ DEVLINK_PARAM_CMODE_DRIVERINIT))
+ return -EOPNOTSUPP;
+
+ param_item->driverinit_value = init_val;
+ param_item->driverinit_value_valid = true;
+
+ devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_NEW);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(devlink_param_driverinit_value_set);
+
+/**
+ * devlink_param_value_changed - notify devlink on a parameter's value
+ * change. Should be called by the driver
+ * right after the change.
+ *
+ * @devlink: devlink
+ * @param_id: parameter ID
+ *
+ * This function should be used by the driver to notify devlink on value
+ * change, excluding driverinit configuration mode.
+ * For driverinit configuration mode driver should use the function
+ * devlink_param_driverinit_value_set() instead.
+ */
+void devlink_param_value_changed(struct devlink *devlink, u32 param_id)
+{
+ struct devlink_param_item *param_item;
+
+ param_item = devlink_param_find_by_id(&devlink->param_list, param_id);
+ WARN_ON(!param_item);
+
+ devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_NEW);
+}
+EXPORT_SYMBOL_GPL(devlink_param_value_changed);
+
+/**
+ * devlink_region_create - create a new address region
+ *
+ * @devlink: devlink
+ * @region_name: region name
+ * @region_max_snapshots: Maximum supported number of snapshots for region
+ * @region_size: size of region
+ */
+struct devlink_region *devlink_region_create(struct devlink *devlink,
+ const char *region_name,
+ u32 region_max_snapshots,
+ u64 region_size)
+{
+ struct devlink_region *region;
+ int err = 0;
+
+ mutex_lock(&devlink->lock);
+
+ if (devlink_region_get_by_name(devlink, region_name)) {
+ err = -EEXIST;
+ goto unlock;
+ }
+
+ region = kzalloc(sizeof(*region), GFP_KERNEL);
+ if (!region) {
+ err = -ENOMEM;
+ goto unlock;
+ }
+
+ region->devlink = devlink;
+ region->max_snapshots = region_max_snapshots;
+ region->name = region_name;
+ region->size = region_size;
+ INIT_LIST_HEAD(®ion->snapshot_list);
+ list_add_tail(®ion->list, &devlink->region_list);
+ devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_NEW);
+
+ mutex_unlock(&devlink->lock);
+ return region;
+
+unlock:
+ mutex_unlock(&devlink->lock);
+ return ERR_PTR(err);
+}
+EXPORT_SYMBOL_GPL(devlink_region_create);
+
+/**
+ * devlink_region_destroy - destroy address region
+ *
+ * @region: devlink region to destroy
+ */
+void devlink_region_destroy(struct devlink_region *region)
+{
+ struct devlink *devlink = region->devlink;
+ struct devlink_snapshot *snapshot, *ts;
+
+ mutex_lock(&devlink->lock);
+
+ /* Free all snapshots of region */
+ list_for_each_entry_safe(snapshot, ts, ®ion->snapshot_list, list)
+ devlink_region_snapshot_del(snapshot);
+
+ list_del(®ion->list);
+
+ devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_DEL);
+ mutex_unlock(&devlink->lock);
+ kfree(region);
+}
+EXPORT_SYMBOL_GPL(devlink_region_destroy);
+
+/**
+ * devlink_region_shapshot_id_get - get snapshot ID
+ *
+ * This callback should be called when adding a new snapshot,
+ * Driver should use the same id for multiple snapshots taken
+ * on multiple regions at the same time/by the same trigger.
+ *
+ * @devlink: devlink
+ */
+u32 devlink_region_shapshot_id_get(struct devlink *devlink)
+{
+ u32 id;
+
+ mutex_lock(&devlink->lock);
+ id = ++devlink->snapshot_id;
+ mutex_unlock(&devlink->lock);
+
+ return id;
+}
+EXPORT_SYMBOL_GPL(devlink_region_shapshot_id_get);
+
+/**
+ * devlink_region_snapshot_create - create a new snapshot
+ * This will add a new snapshot of a region. The snapshot
+ * will be stored on the region struct and can be accessed
+ * from devlink. This is useful for future analyses of snapshots.
+ * Multiple snapshots can be created on a region.
+ * The @snapshot_id should be obtained using the getter function.
+ *
+ * @devlink_region: devlink region of the snapshot
+ * @data_len: size of snapshot data
+ * @data: snapshot data
+ * @snapshot_id: snapshot id to be created
+ * @data_destructor: pointer to destructor function to free data
+ */
+int devlink_region_snapshot_create(struct devlink_region *region, u64 data_len,
+ u8 *data, u32 snapshot_id,
+ devlink_snapshot_data_dest_t *data_destructor)
+{
+ struct devlink *devlink = region->devlink;
+ struct devlink_snapshot *snapshot;
+ int err;
+
+ mutex_lock(&devlink->lock);
+
+ /* check if region can hold one more snapshot */
+ if (region->cur_snapshots == region->max_snapshots) {
+ err = -ENOMEM;
+ goto unlock;
+ }
+
+ if (devlink_region_snapshot_get_by_id(region, snapshot_id)) {
+ err = -EEXIST;
+ goto unlock;
+ }
+
+ snapshot = kzalloc(sizeof(*snapshot), GFP_KERNEL);
+ if (!snapshot) {
+ err = -ENOMEM;
+ goto unlock;
+ }
+
+ snapshot->id = snapshot_id;
+ snapshot->region = region;
+ snapshot->data = data;
+ snapshot->data_len = data_len;
+ snapshot->data_destructor = data_destructor;
+
+ list_add_tail(&snapshot->list, ®ion->snapshot_list);
+
+ region->cur_snapshots++;
+
+ devlink_nl_region_notify(region, snapshot, DEVLINK_CMD_REGION_NEW);
+ mutex_unlock(&devlink->lock);
+ return 0;
+
+unlock:
+ mutex_unlock(&devlink->lock);
+ return err;
+}
+EXPORT_SYMBOL_GPL(devlink_region_snapshot_create);
+
static int __init devlink_module_init(void)
{
return genl_register_family(&devlink_nl_family);
[NETIF_F_RX_UDP_TUNNEL_PORT_BIT] = "rx-udp_tunnel-port-offload",
[NETIF_F_HW_TLS_RECORD_BIT] = "tls-hw-record",
[NETIF_F_HW_TLS_TX_BIT] = "tls-hw-tx-offload",
+ [NETIF_F_HW_TLS_RX_BIT] = "tls-hw-rx-offload",
};
static const char
if (rule->mark && r->mark != rule->mark)
continue;
+ if (rule->suppress_ifgroup != -1 &&
+ r->suppress_ifgroup != rule->suppress_ifgroup)
+ continue;
+
+ if (rule->suppress_prefixlen != -1 &&
+ r->suppress_prefixlen != rule->suppress_prefixlen)
+ continue;
+
if (rule->mark_mask && r->mark_mask != rule->mark_mask)
continue;
if (rule->ip_proto && r->ip_proto != rule->ip_proto)
continue;
+ if (rule->proto && r->proto != rule->proto)
+ continue;
+
if (fib_rule_port_range_set(&rule->sport_range) &&
!fib_rule_port_range_compare(&r->sport_range,
&rule->sport_range))
return err;
}
+static int rule_exists(struct fib_rules_ops *ops, struct fib_rule_hdr *frh,
+ struct nlattr **tb, struct fib_rule *rule)
+{
+ struct fib_rule *r;
+
+ list_for_each_entry(r, &ops->rules_list, list) {
+ if (r->action != rule->action)
+ continue;
+
+ if (r->table != rule->table)
+ continue;
+
+ if (r->pref != rule->pref)
+ continue;
+
+ if (memcmp(r->iifname, rule->iifname, IFNAMSIZ))
+ continue;
+
+ if (memcmp(r->oifname, rule->oifname, IFNAMSIZ))
+ continue;
+
+ if (r->mark != rule->mark)
+ continue;
+
+ if (r->suppress_ifgroup != rule->suppress_ifgroup)
+ continue;
+
+ if (r->suppress_prefixlen != rule->suppress_prefixlen)
+ continue;
+
+ if (r->mark_mask != rule->mark_mask)
+ continue;
+
+ if (r->tun_id != rule->tun_id)
+ continue;
+
+ if (r->fr_net != rule->fr_net)
+ continue;
+
+ if (r->l3mdev != rule->l3mdev)
+ continue;
+
+ if (!uid_eq(r->uid_range.start, rule->uid_range.start) ||
+ !uid_eq(r->uid_range.end, rule->uid_range.end))
+ continue;
+
+ if (r->ip_proto != rule->ip_proto)
+ continue;
+
+ if (r->proto != rule->proto)
+ continue;
+
+ if (!fib_rule_port_range_compare(&r->sport_range,
+ &rule->sport_range))
+ continue;
+
+ if (!fib_rule_port_range_compare(&r->dport_range,
+ &rule->dport_range))
+ continue;
+
+ if (!ops->compare(r, frh, tb))
+ continue;
+ return 1;
+ }
+ return 0;
+}
+
int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
goto errout;
if ((nlh->nlmsg_flags & NLM_F_EXCL) &&
- rule_find(ops, frh, tb, rule, user_priority)) {
+ rule_exists(ops, frh, tb, rule)) {
err = -EEXIST;
goto errout_free;
}
}
EXPORT_SYMBOL_GPL(xdp_do_redirect);
-static int __xdp_generic_ok_fwd_dev(struct sk_buff *skb, struct net_device *fwd)
-{
- unsigned int len;
-
- if (unlikely(!(fwd->flags & IFF_UP)))
- return -ENETDOWN;
-
- len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN;
- if (skb->len > len)
- return -EMSGSIZE;
-
- return 0;
-}
-
static int xdp_do_generic_redirect_map(struct net_device *dev,
struct sk_buff *skb,
struct xdp_buff *xdp,
}
if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
- if (unlikely((err = __xdp_generic_ok_fwd_dev(skb, fwd))))
+ struct bpf_dtab_netdev *dst = fwd;
+
+ err = dev_map_generic_redirect(dst, skb, xdp_prog);
+ if (unlikely(err))
goto err;
- skb->dev = fwd;
- generic_xdp_tx(skb, xdp_prog);
} else if (map->map_type == BPF_MAP_TYPE_XSKMAP) {
struct xdp_sock *xs = fwd;
if (unlikely(size > IP_TUNNEL_OPTS_MAX))
return -ENOMEM;
- ip_tunnel_info_opts_set(info, from, size);
+ ip_tunnel_info_opts_set(info, from, size, TUNNEL_OPTIONS_PRESENT);
return 0;
}
memcpy(params->smac, dev->dev_addr, ETH_ALEN);
params->h_vlan_TCI = 0;
params->h_vlan_proto = 0;
+ params->ifindex = dev->ifindex;
- return dev->ifindex;
+ return 0;
}
#endif
/* verify forwarding is enabled on this interface */
in_dev = __in_dev_get_rcu(dev);
if (unlikely(!in_dev || !IN_DEV_FORWARD(in_dev)))
- return 0;
+ return BPF_FIB_LKUP_RET_FWD_DISABLED;
if (flags & BPF_FIB_LOOKUP_OUTPUT) {
fl4.flowi4_iif = 1;
tb = fib_get_table(net, tbid);
if (unlikely(!tb))
- return 0;
+ return BPF_FIB_LKUP_RET_NOT_FWDED;
err = fib_table_lookup(tb, &fl4, &res, FIB_LOOKUP_NOREF);
} else {
err = fib_lookup(net, &fl4, &res, FIB_LOOKUP_NOREF);
}
- if (err || res.type != RTN_UNICAST)
- return 0;
+ if (err) {
+ /* map fib lookup errors to RTN_ type */
+ if (err == -EINVAL)
+ return BPF_FIB_LKUP_RET_BLACKHOLE;
+ if (err == -EHOSTUNREACH)
+ return BPF_FIB_LKUP_RET_UNREACHABLE;
+ if (err == -EACCES)
+ return BPF_FIB_LKUP_RET_PROHIBIT;
+
+ return BPF_FIB_LKUP_RET_NOT_FWDED;
+ }
+
+ if (res.type != RTN_UNICAST)
+ return BPF_FIB_LKUP_RET_NOT_FWDED;
if (res.fi->fib_nhs > 1)
fib_select_path(net, &res, &fl4, NULL);
if (check_mtu) {
mtu = ip_mtu_from_fib_result(&res, params->ipv4_dst);
if (params->tot_len > mtu)
- return 0;
+ return BPF_FIB_LKUP_RET_FRAG_NEEDED;
}
nh = &res.fi->fib_nh[res.nh_sel];
/* do not handle lwt encaps right now */
if (nh->nh_lwtstate)
- return 0;
+ return BPF_FIB_LKUP_RET_UNSUPP_LWT;
dev = nh->nh_dev;
- if (unlikely(!dev))
- return 0;
-
if (nh->nh_gw)
params->ipv4_dst = nh->nh_gw;
* rcu_read_lock_bh is not needed here
*/
neigh = __ipv4_neigh_lookup_noref(dev, (__force u32)params->ipv4_dst);
- if (neigh)
- return bpf_fib_set_fwd_params(params, neigh, dev);
+ if (!neigh)
+ return BPF_FIB_LKUP_RET_NO_NEIGH;
- return 0;
+ return bpf_fib_set_fwd_params(params, neigh, dev);
}
#endif
/* link local addresses are never forwarded */
if (rt6_need_strict(dst) || rt6_need_strict(src))
- return 0;
+ return BPF_FIB_LKUP_RET_NOT_FWDED;
dev = dev_get_by_index_rcu(net, params->ifindex);
if (unlikely(!dev))
idev = __in6_dev_get_safely(dev);
if (unlikely(!idev || !net->ipv6.devconf_all->forwarding))
- return 0;
+ return BPF_FIB_LKUP_RET_FWD_DISABLED;
if (flags & BPF_FIB_LOOKUP_OUTPUT) {
fl6.flowi6_iif = 1;
tb = ipv6_stub->fib6_get_table(net, tbid);
if (unlikely(!tb))
- return 0;
+ return BPF_FIB_LKUP_RET_NOT_FWDED;
f6i = ipv6_stub->fib6_table_lookup(net, tb, oif, &fl6, strict);
} else {
}
if (unlikely(IS_ERR_OR_NULL(f6i) || f6i == net->ipv6.fib6_null_entry))
- return 0;
+ return BPF_FIB_LKUP_RET_NOT_FWDED;
+
+ if (unlikely(f6i->fib6_flags & RTF_REJECT)) {
+ switch (f6i->fib6_type) {
+ case RTN_BLACKHOLE:
+ return BPF_FIB_LKUP_RET_BLACKHOLE;
+ case RTN_UNREACHABLE:
+ return BPF_FIB_LKUP_RET_UNREACHABLE;
+ case RTN_PROHIBIT:
+ return BPF_FIB_LKUP_RET_PROHIBIT;
+ default:
+ return BPF_FIB_LKUP_RET_NOT_FWDED;
+ }
+ }
- if (unlikely(f6i->fib6_flags & RTF_REJECT ||
- f6i->fib6_type != RTN_UNICAST))
- return 0;
+ if (f6i->fib6_type != RTN_UNICAST)
+ return BPF_FIB_LKUP_RET_NOT_FWDED;
if (f6i->fib6_nsiblings && fl6.flowi6_oif == 0)
f6i = ipv6_stub->fib6_multipath_select(net, f6i, &fl6,
if (check_mtu) {
mtu = ipv6_stub->ip6_mtu_from_fib6(f6i, dst, src);
if (params->tot_len > mtu)
- return 0;
+ return BPF_FIB_LKUP_RET_FRAG_NEEDED;
}
if (f6i->fib6_nh.nh_lwtstate)
- return 0;
+ return BPF_FIB_LKUP_RET_UNSUPP_LWT;
if (f6i->fib6_flags & RTF_GATEWAY)
*dst = f6i->fib6_nh.nh_gw;
*/
neigh = ___neigh_lookup_noref(ipv6_stub->nd_tbl, neigh_key_eq128,
ndisc_hashfn, dst, dev);
- if (neigh)
- return bpf_fib_set_fwd_params(params, neigh, dev);
+ if (!neigh)
+ return BPF_FIB_LKUP_RET_NO_NEIGH;
- return 0;
+ return bpf_fib_set_fwd_params(params, neigh, dev);
}
#endif
struct bpf_fib_lookup *, params, int, plen, u32, flags)
{
struct net *net = dev_net(skb->dev);
- int index = -EAFNOSUPPORT;
+ int rc = -EAFNOSUPPORT;
if (plen < sizeof(*params))
return -EINVAL;
switch (params->family) {
#if IS_ENABLED(CONFIG_INET)
case AF_INET:
- index = bpf_ipv4_fib_lookup(net, params, flags, false);
+ rc = bpf_ipv4_fib_lookup(net, params, flags, false);
break;
#endif
#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
- index = bpf_ipv6_fib_lookup(net, params, flags, false);
+ rc = bpf_ipv6_fib_lookup(net, params, flags, false);
break;
#endif
}
- if (index > 0) {
+ if (!rc) {
struct net_device *dev;
- dev = dev_get_by_index_rcu(net, index);
+ dev = dev_get_by_index_rcu(net, params->ifindex);
if (!is_skb_forwardable(dev, skb))
- index = 0;
+ rc = BPF_FIB_LKUP_RET_FRAG_NEEDED;
}
- return index;
+ return rc;
}
static const struct bpf_func_proto bpf_skb_fib_lookup_proto = {
case BPF_FUNC_trace_printk:
if (capable(CAP_SYS_ADMIN))
return bpf_get_trace_printk_proto();
+ /* else: fall through */
default:
return NULL;
}
struct flow_dissector_key_tags *key_tags;
struct flow_dissector_key_vlan *key_vlan;
enum flow_dissect_ret fdret;
- bool skip_vlan = false;
+ enum flow_dissector_key_id dissector_vlan = FLOW_DISSECTOR_KEY_MAX;
int num_hdrs = 0;
u8 ip_proto = 0;
bool ret;
}
case htons(ETH_P_8021AD):
case htons(ETH_P_8021Q): {
- const struct vlan_hdr *vlan;
+ const struct vlan_hdr *vlan = NULL;
struct vlan_hdr _vlan;
- bool vlan_tag_present = skb && skb_vlan_tag_present(skb);
+ __be16 saved_vlan_tpid = proto;
- if (vlan_tag_present)
+ if (dissector_vlan == FLOW_DISSECTOR_KEY_MAX &&
+ skb && skb_vlan_tag_present(skb)) {
proto = skb->protocol;
-
- if (!vlan_tag_present || eth_type_vlan(skb->protocol)) {
+ } else {
vlan = __skb_header_pointer(skb, nhoff, sizeof(_vlan),
data, hlen, &_vlan);
if (!vlan) {
proto = vlan->h_vlan_encapsulated_proto;
nhoff += sizeof(*vlan);
- if (skip_vlan) {
- fdret = FLOW_DISSECT_RET_PROTO_AGAIN;
- break;
- }
}
- skip_vlan = true;
- if (dissector_uses_key(flow_dissector,
- FLOW_DISSECTOR_KEY_VLAN)) {
+ if (dissector_vlan == FLOW_DISSECTOR_KEY_MAX) {
+ dissector_vlan = FLOW_DISSECTOR_KEY_VLAN;
+ } else if (dissector_vlan == FLOW_DISSECTOR_KEY_VLAN) {
+ dissector_vlan = FLOW_DISSECTOR_KEY_CVLAN;
+ } else {
+ fdret = FLOW_DISSECT_RET_PROTO_AGAIN;
+ break;
+ }
+
+ if (dissector_uses_key(flow_dissector, dissector_vlan)) {
key_vlan = skb_flow_dissector_target(flow_dissector,
- FLOW_DISSECTOR_KEY_VLAN,
+ dissector_vlan,
target_container);
- if (vlan_tag_present) {
+ if (!vlan) {
key_vlan->vlan_id = skb_vlan_tag_get_id(skb);
key_vlan->vlan_priority =
(skb_vlan_tag_get_prio(skb) >> VLAN_PRIO_SHIFT);
(ntohs(vlan->h_vlan_TCI) &
VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
}
+ key_vlan->vlan_tpid = saved_vlan_tpid;
}
fdret = FLOW_DISSECT_RET_PROTO_AGAIN;
neigh->nud_state = new;
err = 0;
notify = old & NUD_VALID;
- if ((old & (NUD_INCOMPLETE | NUD_PROBE)) &&
+ if (((old & (NUD_INCOMPLETE | NUD_PROBE)) ||
+ (flags & NEIGH_UPDATE_F_ADMIN)) &&
(new & NUD_FAILED)) {
neigh_invalidate(neigh);
notify = 1;
char *buf)
{
struct net_device *dev = queue->dev;
- int index = get_netdev_queue_index(queue);
- int tc = netdev_txq_to_tc(dev, index);
+ int index;
+ int tc;
+ if (!netif_is_multiqueue(dev))
+ return -ENOENT;
+
+ index = get_netdev_queue_index(queue);
+
+ /* If queue belongs to subordinate dev use its TC mapping */
+ dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev;
+
+ tc = netdev_txq_to_tc(dev, index);
if (tc < 0)
return -EINVAL;
- return sprintf(buf, "%u\n", tc);
+ /* We can report the traffic class one of two ways:
+ * Subordinate device traffic classes are reported with the traffic
+ * class first, and then the subordinate class so for example TC0 on
+ * subordinate device 2 will be reported as "0-2". If the queue
+ * belongs to the root device it will be reported with just the
+ * traffic class, so just "0" for TC 0 for example.
+ */
+ return dev->num_tc < 0 ? sprintf(buf, "%u%d\n", tc, dev->num_tc) :
+ sprintf(buf, "%u\n", tc);
}
#ifdef CONFIG_XPS
cpumask_var_t mask;
unsigned long index;
+ if (!netif_is_multiqueue(dev))
+ return -ENOENT;
+
index = get_netdev_queue_index(queue);
if (dev->num_tc) {
+ /* Do not allow XPS on subordinate device directly */
num_tc = dev->num_tc;
+ if (num_tc < 0)
+ return -EINVAL;
+
+ /* If queue belongs to subordinate dev use its map */
+ dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev;
+
tc = netdev_txq_to_tc(dev, index);
if (tc < 0)
return -EINVAL;
return -ENOMEM;
rcu_read_lock();
- dev_maps = rcu_dereference(dev->xps_maps);
+ dev_maps = rcu_dereference(dev->xps_cpus_map);
if (dev_maps) {
for_each_possible_cpu(cpu) {
int i, tci = cpu * num_tc + tc;
struct xps_map *map;
- map = rcu_dereference(dev_maps->cpu_map[tci]);
+ map = rcu_dereference(dev_maps->attr_map[tci]);
if (!map)
continue;
cpumask_var_t mask;
int err;
+ if (!netif_is_multiqueue(dev))
+ return -ENOENT;
+
if (!capable(CAP_NET_ADMIN))
return -EPERM;
static struct netdev_queue_attribute xps_cpus_attribute __ro_after_init
= __ATTR_RW(xps_cpus);
+
+static ssize_t xps_rxqs_show(struct netdev_queue *queue, char *buf)
+{
+ struct net_device *dev = queue->dev;
+ struct xps_dev_maps *dev_maps;
+ unsigned long *mask, index;
+ int j, len, num_tc = 1, tc = 0;
+
+ index = get_netdev_queue_index(queue);
+
+ if (dev->num_tc) {
+ num_tc = dev->num_tc;
+ tc = netdev_txq_to_tc(dev, index);
+ if (tc < 0)
+ return -EINVAL;
+ }
+ mask = kcalloc(BITS_TO_LONGS(dev->num_rx_queues), sizeof(long),
+ GFP_KERNEL);
+ if (!mask)
+ return -ENOMEM;
+
+ rcu_read_lock();
+ dev_maps = rcu_dereference(dev->xps_rxqs_map);
+ if (!dev_maps)
+ goto out_no_maps;
+
+ for (j = -1; j = netif_attrmask_next(j, NULL, dev->num_rx_queues),
+ j < dev->num_rx_queues;) {
+ int i, tci = j * num_tc + tc;
+ struct xps_map *map;
+
+ map = rcu_dereference(dev_maps->attr_map[tci]);
+ if (!map)
+ continue;
+
+ for (i = map->len; i--;) {
+ if (map->queues[i] == index) {
+ set_bit(j, mask);
+ break;
+ }
+ }
+ }
+out_no_maps:
+ rcu_read_unlock();
+
+ len = bitmap_print_to_pagebuf(false, buf, mask, dev->num_rx_queues);
+ kfree(mask);
+
+ return len < PAGE_SIZE ? len : -EINVAL;
+}
+
+static ssize_t xps_rxqs_store(struct netdev_queue *queue, const char *buf,
+ size_t len)
+{
+ struct net_device *dev = queue->dev;
+ struct net *net = dev_net(dev);
+ unsigned long *mask, index;
+ int err;
+
+ if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
+ return -EPERM;
+
+ mask = kcalloc(BITS_TO_LONGS(dev->num_rx_queues), sizeof(long),
+ GFP_KERNEL);
+ if (!mask)
+ return -ENOMEM;
+
+ index = get_netdev_queue_index(queue);
+
+ err = bitmap_parse(buf, len, mask, dev->num_rx_queues);
+ if (err) {
+ kfree(mask);
+ return err;
+ }
+
+ err = __netif_set_xps_queue(dev, mask, index, true);
+ kfree(mask);
+ return err ? : len;
+}
+
+static struct netdev_queue_attribute xps_rxqs_attribute __ro_after_init
+ = __ATTR_RW(xps_rxqs);
#endif /* CONFIG_XPS */
static struct attribute *netdev_queue_default_attrs[] __ro_after_init = {
&queue_traffic_class.attr,
#ifdef CONFIG_XPS
&xps_cpus_attribute.attr,
+ &xps_rxqs_attribute.attr,
&queue_tx_maxrate.attr,
#endif
NULL
{
size_t xdp_size = nla_total_size(0) + /* nest IFLA_XDP */
nla_total_size(1) + /* XDP_ATTACHED */
- nla_total_size(4); /* XDP_PROG_ID */
+ nla_total_size(4) + /* XDP_PROG_ID (or 1st mode) */
+ nla_total_size(4); /* XDP_<mode>_PROG_ID */
return xdp_size;
}
return 0;
}
-static u8 rtnl_xdp_attached_mode(struct net_device *dev, u32 *prog_id)
+static u32 rtnl_xdp_prog_skb(struct net_device *dev)
{
- const struct net_device_ops *ops = dev->netdev_ops;
const struct bpf_prog *generic_xdp_prog;
- struct netdev_bpf xdp;
ASSERT_RTNL();
- *prog_id = 0;
generic_xdp_prog = rtnl_dereference(dev->xdp_prog);
- if (generic_xdp_prog) {
- *prog_id = generic_xdp_prog->aux->id;
- return XDP_ATTACHED_SKB;
- }
- if (!ops->ndo_bpf)
- return XDP_ATTACHED_NONE;
+ if (!generic_xdp_prog)
+ return 0;
+ return generic_xdp_prog->aux->id;
+}
- __dev_xdp_query(dev, ops->ndo_bpf, &xdp);
- *prog_id = xdp.prog_id;
+static u32 rtnl_xdp_prog_drv(struct net_device *dev)
+{
+ return __dev_xdp_query(dev, dev->netdev_ops->ndo_bpf, XDP_QUERY_PROG);
+}
- return xdp.prog_attached;
+static u32 rtnl_xdp_prog_hw(struct net_device *dev)
+{
+ return __dev_xdp_query(dev, dev->netdev_ops->ndo_bpf,
+ XDP_QUERY_PROG_HW);
+}
+
+static int rtnl_xdp_report_one(struct sk_buff *skb, struct net_device *dev,
+ u32 *prog_id, u8 *mode, u8 tgt_mode, u32 attr,
+ u32 (*get_prog_id)(struct net_device *dev))
+{
+ u32 curr_id;
+ int err;
+
+ curr_id = get_prog_id(dev);
+ if (!curr_id)
+ return 0;
+
+ *prog_id = curr_id;
+ err = nla_put_u32(skb, attr, curr_id);
+ if (err)
+ return err;
+
+ if (*mode != XDP_ATTACHED_NONE)
+ *mode = XDP_ATTACHED_MULTI;
+ else
+ *mode = tgt_mode;
+
+ return 0;
}
static int rtnl_xdp_fill(struct sk_buff *skb, struct net_device *dev)
struct nlattr *xdp;
u32 prog_id;
int err;
+ u8 mode;
xdp = nla_nest_start(skb, IFLA_XDP);
if (!xdp)
return -EMSGSIZE;
- err = nla_put_u8(skb, IFLA_XDP_ATTACHED,
- rtnl_xdp_attached_mode(dev, &prog_id));
+ prog_id = 0;
+ mode = XDP_ATTACHED_NONE;
+ if (rtnl_xdp_report_one(skb, dev, &prog_id, &mode, XDP_ATTACHED_SKB,
+ IFLA_XDP_SKB_PROG_ID, rtnl_xdp_prog_skb))
+ goto err_cancel;
+ if (rtnl_xdp_report_one(skb, dev, &prog_id, &mode, XDP_ATTACHED_DRV,
+ IFLA_XDP_DRV_PROG_ID, rtnl_xdp_prog_drv))
+ goto err_cancel;
+ if (rtnl_xdp_report_one(skb, dev, &prog_id, &mode, XDP_ATTACHED_HW,
+ IFLA_XDP_HW_PROG_ID, rtnl_xdp_prog_hw))
+ goto err_cancel;
+
+ err = nla_put_u8(skb, IFLA_XDP_ATTACHED, mode);
if (err)
goto err_cancel;
- if (prog_id) {
+ if (prog_id && mode != XDP_ATTACHED_MULTI) {
err = nla_put_u32(skb, IFLA_XDP_PROG_ID, prog_id);
if (err)
goto err_cancel;
return err;
}
- dev->rtnl_link_state = RTNL_LINK_INITIALIZED;
-
- __dev_notify_flags(dev, old_flags, ~0U);
+ if (dev->rtnl_link_state == RTNL_LINK_INITIALIZED) {
+ __dev_notify_flags(dev, old_flags, 0U);
+ } else {
+ dev->rtnl_link_state = RTNL_LINK_INITIALIZED;
+ __dev_notify_flags(dev, old_flags, ~0U);
+ }
return 0;
}
EXPORT_SYMBOL(rtnl_configure_link);
* It is not yet because we do not want to have a 16 bit hole
*/
new->queue_mapping = old->queue_mapping;
+#ifdef CONFIG_TLS_DEVICE
+ new->decrypted = old->decrypted;
+#endif
memcpy(&new->headers_start, &old->headers_start,
offsetof(struct sk_buff, headers_end) -
C(head_frag);
C(data);
C(truesize);
+#ifdef CONFIG_TLS_DEVICE
+ C(decrypted);
+#endif
refcount_set(&n->users, 1);
atomic_inc(&(skb_shinfo(skb)->dataref));
}
EXPORT_SYMBOL_GPL(skb_segment);
-int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
+int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb)
{
struct skb_shared_info *pinfo, *skbinfo = skb_shinfo(skb);
unsigned int offset = skb_gro_offset(skb);
unsigned int headlen = skb_headlen(skb);
unsigned int len = skb_gro_len(skb);
- struct sk_buff *lp, *p = *head;
unsigned int delta_truesize;
+ struct sk_buff *lp;
if (unlikely(p->len + len >= 65536))
return -E2BIG;
*/
void skb_scrub_packet(struct sk_buff *skb, bool xnet)
{
- skb->tstamp = 0;
skb->pkt_type = PACKET_HOST;
skb->skb_iif = 0;
skb->ignore_df = 0;
return;
ipvs_reset(skb);
- skb_orphan(skb);
skb->mark = 0;
+ skb->tstamp = 0;
}
EXPORT_SYMBOL_GPL(skb_scrub_packet);
if (npages >= 1 << order) {
page = alloc_pages((gfp_mask & ~__GFP_DIRECT_RECLAIM) |
__GFP_COMP |
- __GFP_NOWARN |
- __GFP_NORETRY,
+ __GFP_NOWARN,
order);
if (page)
goto fill_page;
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <asm/unaligned.h>
#include <linux/capability.h>
#include <linux/errno.h>
#include <linux/errqueue.h>
int sock_setsockopt(struct socket *sock, int level, int optname,
char __user *optval, unsigned int optlen)
{
+ struct sock_txtime sk_txtime;
struct sock *sk = sock->sk;
int val;
int valbool;
}
break;
+ case SO_TXTIME:
+ if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
+ ret = -EPERM;
+ } else if (optlen != sizeof(struct sock_txtime)) {
+ ret = -EINVAL;
+ } else if (copy_from_user(&sk_txtime, optval,
+ sizeof(struct sock_txtime))) {
+ ret = -EFAULT;
+ } else if (sk_txtime.flags & ~SOF_TXTIME_FLAGS_MASK) {
+ ret = -EINVAL;
+ } else {
+ sock_valbool_flag(sk, SOCK_TXTIME, true);
+ sk->sk_clockid = sk_txtime.clockid;
+ sk->sk_txtime_deadline_mode =
+ !!(sk_txtime.flags & SOF_TXTIME_DEADLINE_MODE);
+ sk->sk_txtime_report_errors =
+ !!(sk_txtime.flags & SOF_TXTIME_REPORT_ERRORS);
+ }
+ break;
+
default:
ret = -ENOPROTOOPT;
break;
u64 val64;
struct linger ling;
struct timeval tm;
+ struct sock_txtime txtime;
} v;
int lv = sizeof(int);
v.val = sock_flag(sk, SOCK_ZEROCOPY);
break;
+ case SO_TXTIME:
+ lv = sizeof(v.txtime);
+ v.txtime.clockid = sk->sk_clockid;
+ v.txtime.flags |= sk->sk_txtime_deadline_mode ?
+ SOF_TXTIME_DEADLINE_MODE : 0;
+ v.txtime.flags |= sk->sk_txtime_report_errors ?
+ SOF_TXTIME_REPORT_ERRORS : 0;
+ break;
+
default:
/* We implement the SO_SNDLOWAT etc to not be settable
* (1003.1g 7).
sockc->tsflags &= ~SOF_TIMESTAMPING_TX_RECORD_MASK;
sockc->tsflags |= tsflags;
break;
+ case SCM_TXTIME:
+ if (!sock_flag(sk, SOCK_TXTIME))
+ return -EINVAL;
+ if (cmsg->cmsg_len != CMSG_LEN(sizeof(u64)))
+ return -EINVAL;
+ sockc->transmit_time = get_unaligned((u64 *)CMSG_DATA(cmsg));
+ break;
/* SCM_RIGHTS and SCM_CREDENTIALS are semantically in SOL_UNIX. */
case SCM_RIGHTS:
case SCM_CREDENTIALS:
{
struct proto *prot = sk->sk_prot;
long allocated = sk_memory_allocated_add(sk, amt);
+ bool charged = true;
if (mem_cgroup_sockets_enabled && sk->sk_memcg &&
- !mem_cgroup_charge_skmem(sk->sk_memcg, amt))
+ !(charged = mem_cgroup_charge_skmem(sk->sk_memcg, amt)))
goto suppress_allocation;
/* Under limit. */
return 1;
}
- trace_sock_exceed_buf_limit(sk, prot, allocated);
+ if (kind == SK_MEM_SEND || (kind == SK_MEM_RECV && charged))
+ trace_sock_exceed_buf_limit(sk, prot, allocated, kind);
sk_memory_allocated_sub(sk, amt);
sk->sk_pacing_rate = ~0U;
sk->sk_pacing_shift = 10;
sk->sk_incoming_cpu = -1;
+
+ sk_rx_queue_clear(sk);
/*
* Before updating sk_refcnt, we must commit prior changes to memory
* (Documentation/RCU/rculist_nulls.txt for details)
rsk_prot->slab = kmem_cache_create(rsk_prot->slab_name,
rsk_prot->obj_size, 0,
- prot->slab_flags, NULL);
+ SLAB_ACCOUNT | prot->slab_flags,
+ NULL);
if (!rsk_prot->slab) {
pr_crit("%s: Can't create request sock SLAB cache!\n",
if (alloc_slab) {
prot->slab = kmem_cache_create_usercopy(prot->name,
prot->obj_size, 0,
- SLAB_HWCACHE_ALIGN | prot->slab_flags,
+ SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT |
+ prot->slab_flags,
prot->useroffset, prot->usersize,
NULL);
kmem_cache_create(prot->twsk_prot->twsk_slab_name,
prot->twsk_prot->twsk_obj_size,
0,
+ SLAB_ACCOUNT |
prot->slab_flags,
NULL);
if (prot->twsk_prot->twsk_slab == NULL)
* Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc.
* Released under terms in GPL version 2. See COPYING.
*/
+#include <linux/bpf.h>
+#include <linux/filter.h>
#include <linux/types.h>
#include <linux/mm.h>
+#include <linux/netdevice.h>
#include <linux/slab.h>
#include <linux/idr.h>
#include <linux/rhashtable.h>
BUILD_BUG_ON(FIELD_SIZEOF(struct xdp_mem_allocator, mem.id)
!= sizeof(u32));
- /* Use cyclic increasing ID as direct hash key, see rht_bucket_index */
- return key << RHT_HASH_RESERVED_SPACE;
+ /* Use cyclic increasing ID as direct hash key */
+ return key;
}
static int xdp_mem_id_cmp(struct rhashtable_compare_arg *arg,
__xdp_return(xdp->data, &xdp->rxq->mem, true, xdp->handle);
}
EXPORT_SYMBOL_GPL(xdp_return_buff);
+
+int xdp_attachment_query(struct xdp_attachment_info *info,
+ struct netdev_bpf *bpf)
+{
+ bpf->prog_id = info->prog ? info->prog->aux->id : 0;
+ bpf->prog_flags = info->prog ? info->flags : 0;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(xdp_attachment_query);
+
+bool xdp_attachment_flags_ok(struct xdp_attachment_info *info,
+ struct netdev_bpf *bpf)
+{
+ if (info->prog && (bpf->flags ^ info->flags) & XDP_FLAGS_MODES) {
+ NL_SET_ERR_MSG(bpf->extack,
+ "program loaded with different flags");
+ return false;
+ }
+ return true;
+}
+EXPORT_SYMBOL_GPL(xdp_attachment_flags_ok);
+
+void xdp_attachment_setup(struct xdp_attachment_info *info,
+ struct netdev_bpf *bpf)
+{
+ if (info->prog)
+ bpf_prog_put(info->prog);
+ info->prog = bpf->prog;
+ info->flags = bpf->flags;
+}
+EXPORT_SYMBOL_GPL(xdp_attachment_setup);
{
struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk);
struct dccp_sock *dp = dccp_sk(sk);
- ktime_t now = ktime_get_real();
+ ktime_t now = ktime_get();
s64 delta = 0;
switch (fbtype) {
case CCID3_FBACK_PERIODIC:
delta = ktime_us_delta(now, hc->rx_tstamp_last_feedback);
if (delta <= 0)
- DCCP_BUG("delta (%ld) <= 0", (long)delta);
- else
- hc->rx_x_recv = scaled_div32(hc->rx_bytes_recv, delta);
+ delta = 1;
+ hc->rx_x_recv = scaled_div32(hc->rx_bytes_recv, delta);
break;
default:
return;
}
- ccid3_pr_debug("Interval %ldusec, X_recv=%u, 1/p=%u\n", (long)delta,
+ ccid3_pr_debug("Interval %lldusec, X_recv=%u, 1/p=%u\n", delta,
hc->rx_x_recv, hc->rx_pinv);
hc->rx_tstamp_last_feedback = now;
static u32 ccid3_first_li(struct sock *sk)
{
struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk);
- u32 x_recv, p, delta;
+ u32 x_recv, p;
+ s64 delta;
u64 fval;
if (hc->rx_rtt == 0) {
hc->rx_rtt = DCCP_FALLBACK_RTT;
}
- delta = ktime_to_us(net_timedelta(hc->rx_tstamp_last_feedback));
+ delta = ktime_us_delta(ktime_get(), hc->rx_tstamp_last_feedback);
+ if (delta <= 0)
+ delta = 1;
x_recv = scaled_div32(hc->rx_bytes_recv, delta);
if (x_recv == 0) { /* would also trigger divide-by-zero */
DCCP_WARN("X_recv==0\n");
int flags, int *addr_len);
void dccp_shutdown(struct sock *sk, int how);
int inet_dccp_listen(struct socket *sock, int backlog);
-__poll_t dccp_poll_mask(struct socket *sock, __poll_t events);
+__poll_t dccp_poll(struct file *file, struct socket *sock,
+ poll_table *wait);
int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
void dccp_req_err(struct sock *sk, u64 seq);
.accept = inet_accept,
.getname = inet_getname,
/* FIXME: work on tcp_poll to rename it to inet_csk_poll */
- .poll_mask = dccp_poll_mask,
+ .poll = dccp_poll,
.ioctl = inet_ioctl,
/* FIXME: work on inet_listen to rename it to sock_common_listen */
.listen = inet_dccp_listen,
.socketpair = sock_no_socketpair,
.accept = inet_accept,
.getname = inet6_getname,
- .poll_mask = dccp_poll_mask,
+ .poll = dccp_poll,
.ioctl = inet6_ioctl,
.listen = inet_dccp_listen,
.shutdown = inet_shutdown,
EXPORT_SYMBOL_GPL(dccp_disconnect);
-__poll_t dccp_poll_mask(struct socket *sock, __poll_t events)
+/*
+ * Wait for a DCCP event.
+ *
+ * Note that we don't need to lock the socket, as the upper poll layers
+ * take care of normal races (between the test and the event) and we don't
+ * go look at any of the socket buffers directly.
+ */
+__poll_t dccp_poll(struct file *file, struct socket *sock,
+ poll_table *wait)
{
__poll_t mask;
struct sock *sk = sock->sk;
+ sock_poll_wait(file, sk_sleep(sk), wait);
if (sk->sk_state == DCCP_LISTEN)
return inet_csk_listen_poll(sk);
return mask;
}
-EXPORT_SYMBOL_GPL(dccp_poll_mask);
+EXPORT_SYMBOL_GPL(dccp_poll);
int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg)
{
}
-static __poll_t dn_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t dn_poll(struct file *file, struct socket *sock, poll_table *wait)
{
struct sock *sk = sock->sk;
struct dn_scp *scp = DN_SK(sk);
- __poll_t mask = datagram_poll_mask(sock, events);
+ __poll_t mask = datagram_poll(file, sock, wait);
if (!skb_queue_empty(&scp->other_receive_queue))
mask |= EPOLLRDBAND;
.socketpair = sock_no_socketpair,
.accept = dn_accept,
.getname = dn_getname,
- .poll_mask = dn_poll_mask,
+ .poll = dn_poll,
.ioctl = dn_ioctl,
.listen = dn_listen,
.shutdown = dn_shutdown,
break;
case DN_RUN:
sk->sk_shutdown |= SHUTDOWN_MASK;
+ /* fall through */
case DN_CC:
scp->state = DN_CN;
}
switch (f->command) {
case TC_BLOCK_BIND:
- return tcf_block_cb_register(f->block, cb, dev, dev);
+ return tcf_block_cb_register(f->block, cb, dev, dev, f->extack);
case TC_BLOCK_UNBIND:
tcf_block_cb_unregister(f->block, cb, dev);
return 0;
}
EXPORT_SYMBOL(sysfs_format_mac);
-struct sk_buff **eth_gro_receive(struct sk_buff **head,
- struct sk_buff *skb)
+struct sk_buff *eth_gro_receive(struct list_head *head, struct sk_buff *skb)
{
- struct sk_buff *p, **pp = NULL;
- struct ethhdr *eh, *eh2;
- unsigned int hlen, off_eth;
const struct packet_offload *ptype;
+ unsigned int hlen, off_eth;
+ struct sk_buff *pp = NULL;
+ struct ethhdr *eh, *eh2;
+ struct sk_buff *p;
__be16 type;
int flush = 1;
flush = 0;
- for (p = *head; p; p = p->next) {
+ list_for_each_entry(p, head, list) {
if (!NAPI_GRO_CB(p)->same_flow)
continue;
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = sock_no_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.ioctl = ieee802154_sock_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = sock_no_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.ioctl = ieee802154_sock_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
err = inet_csk_listen_start(sk, backlog);
if (err)
goto out;
+ tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_LISTEN_CB, 0, NULL);
}
sk->sk_max_ack_backlog = backlog;
err = 0;
.socketpair = sock_no_socketpair,
.accept = inet_accept,
.getname = inet_getname,
- .poll_mask = tcp_poll_mask,
+ .poll = tcp_poll,
.ioctl = inet_ioctl,
.listen = inet_listen,
.shutdown = inet_shutdown,
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = inet_getname,
- .poll_mask = udp_poll_mask,
+ .poll = udp_poll,
.ioctl = inet_ioctl,
.listen = sock_no_listen,
.shutdown = inet_shutdown,
/*
* For SOCK_RAW sockets; should be the same as inet_dgram_ops but without
- * udp_poll_mask
+ * udp_poll
*/
static const struct proto_ops inet_sockraw_ops = {
.family = PF_INET,
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = inet_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.ioctl = inet_ioctl,
.listen = sock_no_listen,
.shutdown = inet_shutdown,
}
EXPORT_SYMBOL(inet_gso_segment);
-struct sk_buff **inet_gro_receive(struct sk_buff **head, struct sk_buff *skb)
+struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb)
{
const struct net_offload *ops;
- struct sk_buff **pp = NULL;
- struct sk_buff *p;
+ struct sk_buff *pp = NULL;
const struct iphdr *iph;
+ struct sk_buff *p;
unsigned int hlen;
unsigned int off;
unsigned int id;
flush = (u16)((ntohl(*(__be32 *)iph) ^ skb_gro_len(skb)) | (id & ~IP_DF));
id >>= 16;
- for (p = *head; p; p = p->next) {
+ list_for_each_entry(p, head, list) {
struct iphdr *iph2;
u16 flush_id;
}
EXPORT_SYMBOL(inet_gro_receive);
-static struct sk_buff **ipip_gro_receive(struct sk_buff **head,
- struct sk_buff *skb)
+static struct sk_buff *ipip_gro_receive(struct list_head *head,
+ struct sk_buff *skb)
{
if (NAPI_GRO_CB(skb)->encap_mark) {
NAPI_GRO_CB(skb)->flush = 1;
static struct packet_type ip_packet_type __read_mostly = {
.type = cpu_to_be16(ETH_P_IP),
.func = ip_rcv,
+ .list_func = ip_list_rcv,
};
static int __init inet_init(void)
#include <linux/spinlock.h>
#include <net/udp.h>
-static struct sk_buff **esp4_gro_receive(struct sk_buff **head,
- struct sk_buff *skb)
+static struct sk_buff *esp4_gro_receive(struct list_head *head,
+ struct sk_buff *skb)
{
int offset = skb_gro_offset(skb);
struct xfrm_offload *xo;
return 0;
}
-static struct sk_buff **fou_gro_receive(struct sock *sk,
- struct sk_buff **head,
- struct sk_buff *skb)
+static struct sk_buff *fou_gro_receive(struct sock *sk,
+ struct list_head *head,
+ struct sk_buff *skb)
{
- const struct net_offload *ops;
- struct sk_buff **pp = NULL;
u8 proto = fou_from_sock(sk)->protocol;
const struct net_offload **offloads;
+ const struct net_offload *ops;
+ struct sk_buff *pp = NULL;
/* We can clear the encap_mark for FOU as we are essentially doing
* one of two possible things. We are either adding an L4 tunnel
return guehdr;
}
-static struct sk_buff **gue_gro_receive(struct sock *sk,
- struct sk_buff **head,
- struct sk_buff *skb)
+static struct sk_buff *gue_gro_receive(struct sock *sk,
+ struct list_head *head,
+ struct sk_buff *skb)
{
const struct net_offload **offloads;
const struct net_offload *ops;
- struct sk_buff **pp = NULL;
+ struct sk_buff *pp = NULL;
struct sk_buff *p;
struct guehdr *guehdr;
size_t len, optlen, hdrlen, off;
skb_gro_pull(skb, hdrlen);
- for (p = *head; p; p = p->next) {
+ list_for_each_entry(p, head, list) {
const struct guehdr *guehdr2;
if (!NAPI_GRO_CB(p)->same_flow)
out_unlock:
rcu_read_unlock();
out:
- NAPI_GRO_CB(skb)->flush |= flush;
- skb_gro_remcsum_cleanup(skb, &grc);
- skb->remcsum_offload = 0;
+ skb_gro_flush_final_remcsum(skb, pp, flush, &grc);
return pp;
}
return segs;
}
-static struct sk_buff **gre_gro_receive(struct sk_buff **head,
- struct sk_buff *skb)
+static struct sk_buff *gre_gro_receive(struct list_head *head,
+ struct sk_buff *skb)
{
- struct sk_buff **pp = NULL;
+ struct sk_buff *pp = NULL;
struct sk_buff *p;
const struct gre_base_hdr *greh;
unsigned int hlen, grehlen;
null_compute_pseudo);
}
- for (p = *head; p; p = p->next) {
+ list_for_each_entry(p, head, list) {
const struct gre_base_hdr *greh2;
if (!NAPI_GRO_CB(p)->same_flow)
out_unlock:
rcu_read_unlock();
out:
- NAPI_GRO_CB(skb)->flush |= flush;
+ skb_gro_flush_final(skb, pp, flush);
return pp;
}
icmp_param->data.icmph.checksum = 0;
+ ipcm_init(&ipc);
inet->tos = ip_hdr(skb)->tos;
sk->sk_mark = mark;
daddr = ipc.addr = ip_hdr(skb)->saddr;
saddr = fib_compute_spec_dst(skb);
- ipc.opt = NULL;
- ipc.tx_flags = 0;
- ipc.ttl = 0;
- ipc.tos = -1;
if (icmp_param->replyopts.opt.opt.optlen) {
ipc.opt = &icmp_param->replyopts.opt;
icmp_param.offset = skb_network_offset(skb_in);
inet_sk(sk)->tos = tos;
sk->sk_mark = mark;
+ ipcm_init(&ipc);
ipc.addr = iph->saddr;
ipc.opt = &icmp_param.replyopts.opt;
- ipc.tx_flags = 0;
- ipc.ttl = 0;
- ipc.tos = -1;
rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos, mark,
type, code, &icmp_param);
#include <linux/skbuff.h>
#include <linux/rtnetlink.h>
#include <linux/slab.h>
+#include <linux/rhashtable.h>
#include <net/sock.h>
#include <net/inet_frag.h>
bool dev_match = (sk->sk_bound_dev_if == dif ||
sk->sk_bound_dev_if == sdif);
- if (exact_dif && !dev_match)
+ if (!dev_match)
return -1;
- if (sk->sk_bound_dev_if && dev_match)
+ if (sk->sk_bound_dev_if)
score += 4;
}
if (sk->sk_incoming_cpu == raw_smp_processor_id())
goto err_free_skb;
key = &tun_info->key;
+ if (!(tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT))
+ goto err_free_rt;
md = ip_tunnel_info_opts(tun_info);
if (!md)
goto err_free_rt;
return true;
}
-static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
+static int ip_rcv_finish_core(struct net *net, struct sock *sk,
+ struct sk_buff *skb)
{
const struct iphdr *iph = ip_hdr(skb);
int (*edemux)(struct sk_buff *skb);
struct rtable *rt;
int err;
- /* if ingress device is enslaved to an L3 master device pass the
- * skb to its handler for processing
- */
- skb = l3mdev_ip_rcv(skb);
- if (!skb)
- return NET_RX_SUCCESS;
-
if (net->ipv4.sysctl_ip_early_demux &&
!skb_dst(skb) &&
!skb->sk &&
goto drop;
}
- return dst_input(skb);
+ return NET_RX_SUCCESS;
drop:
kfree_skb(skb);
goto drop;
}
+static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+ int ret;
+
+ /* if ingress device is enslaved to an L3 master device pass the
+ * skb to its handler for processing
+ */
+ skb = l3mdev_ip_rcv(skb);
+ if (!skb)
+ return NET_RX_SUCCESS;
+
+ ret = ip_rcv_finish_core(net, sk, skb);
+ if (ret != NET_RX_DROP)
+ ret = dst_input(skb);
+ return ret;
+}
+
/*
* Main IP Receive routine.
*/
-int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)
+static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net)
{
const struct iphdr *iph;
- struct net *net;
u32 len;
/* When the interface is in promisc. mode, drop all the crap
goto drop;
- net = dev_net(dev);
__IP_UPD_PO_STATS(net, IPSTATS_MIB_IN, skb->len);
skb = skb_share_check(skb, GFP_ATOMIC);
/* Must drop socket now because of tproxy. */
skb_orphan(skb);
- return NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING,
- net, NULL, skb, dev, NULL,
- ip_rcv_finish);
+ return skb;
csum_error:
__IP_INC_STATS(net, IPSTATS_MIB_CSUMERRORS);
drop:
kfree_skb(skb);
out:
- return NET_RX_DROP;
+ return NULL;
+}
+
+/*
+ * IP receive entry point
+ */
+int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt,
+ struct net_device *orig_dev)
+{
+ struct net *net = dev_net(dev);
+
+ skb = ip_rcv_core(skb, net);
+ if (skb == NULL)
+ return NET_RX_DROP;
+ return NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING,
+ net, NULL, skb, dev, NULL,
+ ip_rcv_finish);
+}
+
+static void ip_sublist_rcv_finish(struct list_head *head)
+{
+ struct sk_buff *skb, *next;
+
+ list_for_each_entry_safe(skb, next, head, list) {
+ list_del(&skb->list);
+ /* Handle ip{6}_forward case, as sch_direct_xmit have
+ * another kind of SKB-list usage (see validate_xmit_skb_list)
+ */
+ skb->next = NULL;
+ dst_input(skb);
+ }
+}
+
+static void ip_list_rcv_finish(struct net *net, struct sock *sk,
+ struct list_head *head)
+{
+ struct dst_entry *curr_dst = NULL;
+ struct sk_buff *skb, *next;
+ struct list_head sublist;
+
+ INIT_LIST_HEAD(&sublist);
+ list_for_each_entry_safe(skb, next, head, list) {
+ struct dst_entry *dst;
+
+ list_del(&skb->list);
+ /* if ingress device is enslaved to an L3 master device pass the
+ * skb to its handler for processing
+ */
+ skb = l3mdev_ip_rcv(skb);
+ if (!skb)
+ continue;
+ if (ip_rcv_finish_core(net, sk, skb) == NET_RX_DROP)
+ continue;
+
+ dst = skb_dst(skb);
+ if (curr_dst != dst) {
+ /* dispatch old sublist */
+ if (!list_empty(&sublist))
+ ip_sublist_rcv_finish(&sublist);
+ /* start new sublist */
+ INIT_LIST_HEAD(&sublist);
+ curr_dst = dst;
+ }
+ list_add_tail(&skb->list, &sublist);
+ }
+ /* dispatch final sublist */
+ ip_sublist_rcv_finish(&sublist);
+}
+
+static void ip_sublist_rcv(struct list_head *head, struct net_device *dev,
+ struct net *net)
+{
+ NF_HOOK_LIST(NFPROTO_IPV4, NF_INET_PRE_ROUTING, net, NULL,
+ head, dev, NULL, ip_rcv_finish);
+ ip_list_rcv_finish(net, NULL, head);
+}
+
+/* Receive a list of IP packets */
+void ip_list_rcv(struct list_head *head, struct packet_type *pt,
+ struct net_device *orig_dev)
+{
+ struct net_device *curr_dev = NULL;
+ struct net *curr_net = NULL;
+ struct sk_buff *skb, *next;
+ struct list_head sublist;
+
+ INIT_LIST_HEAD(&sublist);
+ list_for_each_entry_safe(skb, next, head, list) {
+ struct net_device *dev = skb->dev;
+ struct net *net = dev_net(dev);
+
+ list_del(&skb->list);
+ skb = ip_rcv_core(skb, net);
+ if (skb == NULL)
+ continue;
+
+ if (curr_dev != dev || curr_net != net) {
+ /* dispatch old sublist */
+ if (!list_empty(&sublist))
+ ip_sublist_rcv(&sublist, curr_dev, curr_net);
+ /* start new sublist */
+ INIT_LIST_HEAD(&sublist);
+ curr_dev = dev;
+ curr_net = net;
+ }
+ list_add_tail(&skb->list, &sublist);
+ }
+ /* dispatch final sublist */
+ ip_sublist_rcv(&sublist, curr_dev, curr_net);
}
}
/* Note: skb->sk can be different from sk, in case of tunnels */
-int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl)
+int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
+ __u8 tos)
{
struct inet_sock *inet = inet_sk(sk);
struct net *net = sock_net(sk);
inet->inet_dport,
inet->inet_sport,
sk->sk_protocol,
- RT_CONN_FLAGS(sk),
+ RT_CONN_FLAGS_TOS(sk, tos),
sk->sk_bound_dev_if);
if (IS_ERR(rt))
goto no_route;
skb_push(skb, sizeof(struct iphdr) + (inet_opt ? inet_opt->opt.optlen : 0));
skb_reset_network_header(skb);
iph = ip_hdr(skb);
- *((__be16 *)iph) = htons((4 << 12) | (5 << 8) | (inet->tos & 0xff));
+ *((__be16 *)iph) = htons((4 << 12) | (5 << 8) | (tos & 0xff));
if (ip_dont_fragment(sk, &rt->dst) && !skb->ignore_df)
iph->frag_off = htons(IP_DF);
else
kfree_skb(skb);
return -EHOSTUNREACH;
}
-EXPORT_SYMBOL(ip_queue_xmit);
+EXPORT_SYMBOL(__ip_queue_xmit);
static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
{
cork->fragsize = ip_sk_use_pmtu(sk) ?
dst_mtu(&rt->dst) : rt->dst.dev->mtu;
- cork->gso_size = sk->sk_type == SOCK_DGRAM ? ipc->gso_size : 0;
+ cork->gso_size = ipc->gso_size;
cork->dst = &rt->dst;
cork->length = 0;
cork->ttl = ipc->ttl;
cork->tos = ipc->tos;
cork->priority = ipc->priority;
- cork->tx_flags = ipc->tx_flags;
+ cork->transmit_time = ipc->sockc.transmit_time;
+ cork->tx_flags = 0;
+ sock_tx_timestamp(sk, ipc->sockc.tsflags, &cork->tx_flags);
return 0;
}
skb->priority = (cork->tos != -1) ? cork->priority: sk->sk_priority;
skb->mark = sk->sk_mark;
+ skb->tstamp = cork->transmit_time;
/*
* Steal rt from cork.dst to avoid a pair of atomic_inc/atomic_dec
* on dst refcount
if (__ip_options_echo(net, &replyopts.opt.opt, skb, sopt))
return;
+ ipcm_init(&ipc);
ipc.addr = daddr;
- ipc.opt = NULL;
- ipc.tx_flags = 0;
- ipc.ttl = 0;
- ipc.tos = -1;
if (replyopts.opt.opt.optlen) {
ipc.opt = &replyopts.opt;
#include <linux/netfilter_ipv4.h>
#include <linux/compat.h>
#include <linux/export.h>
+#include <linux/rhashtable.h>
#include <net/ip_tunnels.h>
#include <net/checksum.h>
#include <net/netlink.h>
struct sk_buff *skb;
int ret;
- if (assert == IGMPMSG_WHOLEPKT)
+ if (assert == IGMPMSG_WHOLEPKT || assert == IGMPMSG_WRVIFWHOLE)
skb = skb_realloc_headroom(pkt, sizeof(struct iphdr));
else
skb = alloc_skb(128, GFP_ATOMIC);
if (!skb)
return -ENOBUFS;
- if (assert == IGMPMSG_WHOLEPKT) {
+ if (assert == IGMPMSG_WHOLEPKT || assert == IGMPMSG_WRVIFWHOLE) {
/* Ugly, but we have no choice with this interface.
* Duplicate old header, fix ihl, length etc.
* And all this only to mangle msg->im_msgtype and
skb_reset_transport_header(skb);
msg = (struct igmpmsg *)skb_network_header(skb);
memcpy(msg, skb_network_header(pkt), sizeof(struct iphdr));
- msg->im_msgtype = IGMPMSG_WHOLEPKT;
+ msg->im_msgtype = assert;
msg->im_mbz = 0;
- msg->im_vif = mrt->mroute_reg_vif_num;
+ if (assert == IGMPMSG_WRVIFWHOLE)
+ msg->im_vif = vifi;
+ else
+ msg->im_vif = mrt->mroute_reg_vif_num;
ip_hdr(skb)->ihl = sizeof(struct iphdr) >> 2;
ip_hdr(skb)->tot_len = htons(ntohs(ip_hdr(pkt)->tot_len) +
sizeof(struct iphdr));
struct mr_table *mrt;
struct vifctl vif;
struct mfcctl mfc;
+ bool do_wrvifwhole;
u32 uval;
/* There's one exception to the lock - MRT_DONE which needs to unlock */
break;
}
+ do_wrvifwhole = (val == IGMPMSG_WRVIFWHOLE);
val = !!val;
if (val != mrt->mroute_do_pim) {
mrt->mroute_do_pim = val;
mrt->mroute_do_assert = val;
+ mrt->mroute_do_wrvifwhole = do_wrvifwhole;
}
break;
case MRT_TABLE:
MFC_ASSERT_THRESH)) {
c->_c.mfc_un.res.last_assert = jiffies;
ipmr_cache_report(mrt, skb, true_vifi, IGMPMSG_WRONGVIF);
+ if (mrt->mroute_do_wrvifwhole)
+ ipmr_cache_report(mrt, skb, true_vifi,
+ IGMPMSG_WRVIFWHOLE);
}
goto dont_forward;
}
mrt->mroute_reg_vif_num) ||
nla_put_u8(skb, IPMRA_TABLE_MROUTE_DO_ASSERT,
mrt->mroute_do_assert) ||
- nla_put_u8(skb, IPMRA_TABLE_MROUTE_DO_PIM, mrt->mroute_do_pim))
+ nla_put_u8(skb, IPMRA_TABLE_MROUTE_DO_PIM, mrt->mroute_do_pim) ||
+ nla_put_u8(skb, IPMRA_TABLE_MROUTE_DO_WRVIFWHOLE,
+ mrt->mroute_do_wrvifwhole))
return false;
return true;
* Common logic shared by IPv4 [ipmr] and IPv6 [ip6mr] implementation
*/
+#include <linux/rhashtable.h>
#include <linux/mroute_base.h>
/* Sets everything common except 'dev', since that is done under locking */
};
/* One level of recursion won't kill us */
-static void dump_ipv4_packet(struct nf_log_buf *m,
+static void dump_ipv4_packet(struct net *net, struct nf_log_buf *m,
const struct nf_loginfo *info,
const struct sk_buff *skb, unsigned int iphoff)
{
/* Max length: 3+maxlen */
if (!iphoff) { /* Only recurse once. */
nf_log_buf_add(m, "[");
- dump_ipv4_packet(m, info, skb,
+ dump_ipv4_packet(net, m, info, skb,
iphoff + ih->ihl*4+sizeof(_icmph));
nf_log_buf_add(m, "] ");
}
/* Max length: 15 "UID=4294967295 " */
if ((logflags & NF_LOG_UID) && !iphoff)
- nf_log_dump_sk_uid_gid(m, skb->sk);
+ nf_log_dump_sk_uid_gid(net, m, skb->sk);
/* Max length: 16 "MARK=0xFFFFFFFF " */
if (!iphoff && skb->mark)
if (in != NULL)
dump_ipv4_mac_header(m, loginfo, skb);
- dump_ipv4_packet(m, loginfo, skb, 0);
+ dump_ipv4_packet(net, m, loginfo, skb, 0);
nf_log_buf_close(m);
}
/* no remote port */
}
- ipc.sockc.tsflags = sk->sk_tsflags;
- ipc.addr = inet->inet_saddr;
- ipc.opt = NULL;
- ipc.oif = sk->sk_bound_dev_if;
- ipc.tx_flags = 0;
- ipc.ttl = 0;
- ipc.tos = -1;
+ ipcm_init_sk(&ipc, inet);
if (msg->msg_controllen) {
err = ip_cmsg_send(sk, msg, &ipc, false);
rcu_read_unlock();
}
- sock_tx_timestamp(sk, ipc.sockc.tsflags, &ipc.tx_flags);
-
saddr = ipc.addr;
ipc.addr = faddr = daddr;
SNMP_MIB_ITEM("TCPDelivered", LINUX_MIB_TCPDELIVERED),
SNMP_MIB_ITEM("TCPDeliveredCE", LINUX_MIB_TCPDELIVEREDCE),
SNMP_MIB_ITEM("TCPAckCompressed", LINUX_MIB_TCPACKCOMPRESSED),
+ SNMP_MIB_ITEM("TCPZeroWindowDrop", LINUX_MIB_TCPZEROWINDOWDROP),
+ SNMP_MIB_ITEM("TCPRcvQDrop", LINUX_MIB_TCPRCVQDROP),
SNMP_MIB_SENTINEL
};
skb->priority = sk->sk_priority;
skb->mark = sk->sk_mark;
+ skb->tstamp = sockc->transmit_time;
skb_dst_set(skb, &rt->dst);
*rtp = NULL;
daddr = inet->inet_daddr;
}
- ipc.sockc.tsflags = sk->sk_tsflags;
- ipc.addr = inet->inet_saddr;
- ipc.opt = NULL;
- ipc.tx_flags = 0;
- ipc.ttl = 0;
- ipc.tos = -1;
- ipc.oif = sk->sk_bound_dev_if;
+ ipcm_init_sk(&ipc, inet);
if (msg->msg_controllen) {
err = ip_cmsg_send(sk, msg, &ipc, false);
&rt, msg->msg_flags, &ipc.sockc);
else {
- sock_tx_timestamp(sk, ipc.sockc.tsflags, &ipc.tx_flags);
-
if (!ipc.addr)
ipc.addr = fl4.daddr;
lock_sock(sk);
ipv4.sysctl_tcp_fastopen);
struct ctl_table tbl = { .maxlen = (TCP_FASTOPEN_KEY_LENGTH * 2 + 10) };
struct tcp_fastopen_context *ctxt;
- int ret;
u32 user_key[4]; /* 16 bytes, matching TCP_FASTOPEN_KEY_LENGTH */
+ __le32 key[4];
+ int ret, i;
tbl.data = kmalloc(tbl.maxlen, GFP_KERNEL);
if (!tbl.data)
rcu_read_lock();
ctxt = rcu_dereference(net->ipv4.tcp_fastopen_ctx);
if (ctxt)
- memcpy(user_key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH);
+ memcpy(key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH);
else
- memset(user_key, 0, sizeof(user_key));
+ memset(key, 0, sizeof(key));
rcu_read_unlock();
+ for (i = 0; i < ARRAY_SIZE(key); i++)
+ user_key[i] = le32_to_cpu(key[i]);
+
snprintf(tbl.data, tbl.maxlen, "%08x-%08x-%08x-%08x",
user_key[0], user_key[1], user_key[2], user_key[3]);
ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
ret = -EINVAL;
goto bad_key;
}
- tcp_fastopen_reset_cipher(net, NULL, user_key,
+
+ for (i = 0; i < ARRAY_SIZE(user_key); i++)
+ key[i] = cpu_to_le32(user_key[i]);
+
+ tcp_fastopen_reset_cipher(net, NULL, key,
TCP_FASTOPEN_KEY_LENGTH);
}
bad_key:
pr_debug("proc FO key set 0x%x-%x-%x-%x <- 0x%s: %u\n",
- user_key[0], user_key[1], user_key[2], user_key[3],
+ user_key[0], user_key[1], user_key[2], user_key[3],
(char *)tbl.data, ret);
kfree(tbl.data);
return ret;
}
/*
- * Socket is not locked. We are protected from async events by poll logic and
- * correct handling of state changes made by other threads is impossible in
- * any case.
+ * Wait for a TCP event.
+ *
+ * Note that we don't need to lock the socket, as the upper poll layers
+ * take care of normal races (between the test and the event) and we don't
+ * go look at any of the socket buffers directly.
*/
-__poll_t tcp_poll_mask(struct socket *sock, __poll_t events)
+__poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
{
+ __poll_t mask;
struct sock *sk = sock->sk;
const struct tcp_sock *tp = tcp_sk(sk);
- __poll_t mask = 0;
int state;
+ sock_poll_wait(file, sk_sleep(sk), wait);
+
state = inet_sk_state_load(sk);
if (state == TCP_LISTEN)
return inet_csk_listen_poll(sk);
+ /* Socket is not locked. We are protected from async events
+ * by poll logic and correct handling of state changes
+ * made by other threads is impossible in any case.
+ */
+
+ mask = 0;
+
/*
* EPOLLHUP is certainly not done right. But poll() doesn't
* have a notion of HUP in just one direction, and for a
return mask;
}
-EXPORT_SYMBOL(tcp_poll_mask);
+EXPORT_SYMBOL(tcp_poll);
int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
{
* This occurs when user tries to read
* from never connected socket.
*/
- if (!sock_flag(sk, SOCK_DONE))
- ret = -ENOTCONN;
+ ret = -ENOTCONN;
break;
}
if (!timeo) {
/* 'common' sending to sendq */
}
- sockc.tsflags = sk->sk_tsflags;
+ sockcm_init(&sockc, sk);
if (msg->msg_controllen) {
err = sock_cmsg_send(sk, msg, &sockc);
if (unlikely(err)) {
int linear;
new_segment:
- /* Allocate new segment. If the interface is SG,
- * allocate skb fitting to single page.
- */
if (!sk_stream_memory_free(sk))
goto wait_for_sndbuf;
break;
if (sk->sk_state == TCP_CLOSE) {
- if (!sock_flag(sk, SOCK_DONE)) {
- /* This occurs when user tries to read
- * from never connected socket.
- */
- copied = -ENOTCONN;
- break;
- }
+ /* This occurs when user tries to read
+ * from never connected socket.
+ */
+ copied = -ENOTCONN;
break;
}
sk->sk_shutdown = 0;
sock_reset_flag(sk, SOCK_DONE);
tp->srtt_us = 0;
+ tp->rcv_rtt_last_tsecr = 0;
tp->write_seq += tp->max_window + 2;
if (tp->write_seq == 0)
tp->write_seq = 1;
*/
static u64 bbr_rate_bytes_per_sec(struct sock *sk, u64 rate, int gain)
{
- rate *= tcp_mss_to_mtu(sk, tcp_sk(sk)->mss_cache);
+ unsigned int mss = tcp_sk(sk)->mss_cache;
+
+ if (!tcp_needs_internal_pacing(sk))
+ mss = tcp_mss_to_mtu(sk, mss);
+ rate *= mss;
rate *= gain;
rate >>= BBR_SCALE;
rate *= USEC_PER_SEC;
#include <linux/errqueue.h>
#include <trace/events/tcp.h>
#include <linux/static_key.h>
+#include <net/busy_poll.h>
int sysctl_tcp_max_orphans __read_mostly = NR_FILE;
* it is probably a retransmit.
*/
if (tp->ecn_flags & TCP_ECN_SEEN)
- tcp_enter_quickack_mode(sk, 1);
+ tcp_enter_quickack_mode(sk, 2);
break;
case INET_ECN_CE:
if (tcp_ca_needs_ecn(sk))
if (!(tp->ecn_flags & TCP_ECN_DEMAND_CWR)) {
/* Better not delay acks, sender can have a very low cwnd */
- tcp_enter_quickack_mode(sk, 1);
+ tcp_enter_quickack_mode(sk, 2);
tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
}
tp->ecn_flags |= TCP_ECN_SEEN;
{
struct tcp_sock *tp = tcp_sk(sk);
- if (tp->rx_opt.rcv_tsecr &&
- (TCP_SKB_CB(skb)->end_seq -
- TCP_SKB_CB(skb)->seq >= inet_csk(sk)->icsk_ack.rcv_mss)) {
+ if (tp->rx_opt.rcv_tsecr == tp->rcv_rtt_last_tsecr)
+ return;
+ tp->rcv_rtt_last_tsecr = tp->rx_opt.rcv_tsecr;
+
+ if (TCP_SKB_CB(skb)->end_seq -
+ TCP_SKB_CB(skb)->seq >= inet_csk(sk)->icsk_ack.rcv_mss) {
u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr;
u32 delta_us;
if (tcp_is_reno(tp)) {
tcp_remove_reno_sacks(sk, pkts_acked);
+
+ /* If any of the cumulatively ACKed segments was
+ * retransmitted, non-SACK case cannot confirm that
+ * progress was due to original transmission due to
+ * lack of TCPCB_SACKED_ACKED bits even if some of
+ * the packets may have been never retransmitted.
+ */
+ if (flag & FLAG_RETRANS_DATA_ACKED)
+ flag &= ~FLAG_ORIG_SACK_ACKED;
} else {
int delta;
static void tcp_store_ts_recent(struct tcp_sock *tp)
{
tp->rx_opt.ts_recent = tp->rx_opt.rcv_tsval;
- tp->rx_opt.ts_recent_stamp = get_seconds();
+ tp->rx_opt.ts_recent_stamp = ktime_get_seconds();
}
static void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq)
if (TCP_SKB_CB(from)->seq != TCP_SKB_CB(to)->end_seq)
return false;
+#ifdef CONFIG_TLS_DEVICE
+ if (from->decrypted != to->decrypted)
+ return false;
+#endif
+
if (!skb_try_coalesce(to, from, fragstolen, &delta))
return false;
skb->data_len = data_len;
skb->len = size;
- if (tcp_try_rmem_schedule(sk, skb, skb->truesize))
+ if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) {
+ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVQDROP);
goto err_free;
+ }
err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, size);
if (err)
* Out of sequence packets to the out_of_order_queue.
*/
if (TCP_SKB_CB(skb)->seq == tp->rcv_nxt) {
- if (tcp_receive_window(tp) == 0)
+ if (tcp_receive_window(tp) == 0) {
+ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPZEROWINDOWDROP);
goto out_of_window;
+ }
/* Ok. In sequence. In window. */
queue_and_out:
if (skb_queue_len(&sk->sk_receive_queue) == 0)
sk_forced_mem_schedule(sk, skb->truesize);
- else if (tcp_try_rmem_schedule(sk, skb, skb->truesize))
+ else if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) {
+ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVQDROP);
goto drop;
+ }
eaten = tcp_queue_rcv(sk, skb, 0, &fragstolen);
- tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq);
if (skb->len)
tcp_event_data_recv(sk, skb);
if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
/* If window is closed, drop tail of packet. But after
* remembering D-SACK for its head made in previous line.
*/
- if (!tcp_receive_window(tp))
+ if (!tcp_receive_window(tp)) {
+ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPZEROWINDOWDROP);
goto out_of_window;
+ }
goto queue_and_out;
}
break;
memcpy(nskb->cb, skb->cb, sizeof(skb->cb));
+#ifdef CONFIG_TLS_DEVICE
+ nskb->decrypted = skb->decrypted;
+#endif
TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(nskb)->end_seq = start;
if (list)
__skb_queue_before(list, skb, nskb);
skb == tail ||
(TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)))
goto end;
+#ifdef CONFIG_TLS_DEVICE
+ if (skb->decrypted != nskb->decrypted)
+ goto end;
+#endif
}
}
}
tcp_ack(sk, skb, 0);
__kfree_skb(skb);
tcp_data_snd_check(sk);
+ /* When receiving pure ack in fast path, update
+ * last ts ecr directly instead of calling
+ * tcp_rcv_rtt_measure_ts()
+ */
+ tp->rcv_rtt_last_tsecr = tp->rx_opt.rcv_tsecr;
return;
} else { /* Header too small */
TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS);
if (skb) {
icsk->icsk_af_ops->sk_rx_dst_set(sk, skb);
security_inet_conn_established(sk, skb);
+ sk_mark_napi_id(sk, skb);
}
tcp_init_transfer(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB);
tcp_rsk(req)->snt_isn = isn;
tcp_rsk(req)->txhash = net_tx_rndhash();
tcp_openreq_init_rwin(req, sk, dst);
+ sk_rx_queue_set(req_to_sk(req), skb);
if (!want_cookie) {
tcp_reqsk_record_syn(sk, req, skb);
fastopen_sk = tcp_try_fastopen(sk, skb, req, &foc, dst);
and use initial timestamp retrieved from peer table.
*/
if (tcptw->tw_ts_recent_stamp &&
- (!twp || (reuse && get_seconds() - tcptw->tw_ts_recent_stamp > 1))) {
+ (!twp || (reuse && time_after32(ktime_get_seconds(),
+ tcptw->tw_ts_recent_stamp)))) {
tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2;
if (tp->write_seq == 0)
tp->write_seq = 1;
tw->tw_substate = TCP_TIME_WAIT;
tcptw->tw_rcv_nxt = TCP_SKB_CB(skb)->end_seq;
if (tmp_opt.saw_tstamp) {
- tcptw->tw_ts_recent_stamp = get_seconds();
+ tcptw->tw_ts_recent_stamp = ktime_get_seconds();
tcptw->tw_ts_recent = tmp_opt.rcv_tsval;
}
if (tmp_opt.saw_tstamp) {
tcptw->tw_ts_recent = tmp_opt.rcv_tsval;
- tcptw->tw_ts_recent_stamp = get_seconds();
+ tcptw->tw_ts_recent_stamp = ktime_get_seconds();
}
inet_twsk_put(tw);
struct sk_buff *skb)
{
struct sock *newsk = inet_csk_clone_lock(sk, req, GFP_ATOMIC);
+ const struct inet_request_sock *ireq = inet_rsk(req);
+ struct tcp_request_sock *treq = tcp_rsk(req);
+ struct inet_connection_sock *newicsk;
+ struct tcp_sock *oldtp, *newtp;
- if (newsk) {
- const struct inet_request_sock *ireq = inet_rsk(req);
- struct tcp_request_sock *treq = tcp_rsk(req);
- struct inet_connection_sock *newicsk = inet_csk(newsk);
- struct tcp_sock *newtp = tcp_sk(newsk);
- struct tcp_sock *oldtp = tcp_sk(sk);
-
- smc_check_reset_syn_req(oldtp, req, newtp);
-
- /* Now setup tcp_sock */
- newtp->pred_flags = 0;
-
- newtp->rcv_wup = newtp->copied_seq =
- newtp->rcv_nxt = treq->rcv_isn + 1;
- newtp->segs_in = 1;
-
- newtp->snd_sml = newtp->snd_una =
- newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1;
-
- INIT_LIST_HEAD(&newtp->tsq_node);
- INIT_LIST_HEAD(&newtp->tsorted_sent_queue);
-
- tcp_init_wl(newtp, treq->rcv_isn);
-
- newtp->srtt_us = 0;
- newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
- minmax_reset(&newtp->rtt_min, tcp_jiffies32, ~0U);
- newicsk->icsk_rto = TCP_TIMEOUT_INIT;
- newicsk->icsk_ack.lrcvtime = tcp_jiffies32;
-
- newtp->packets_out = 0;
- newtp->retrans_out = 0;
- newtp->sacked_out = 0;
- newtp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
- newtp->tlp_high_seq = 0;
- newtp->lsndtime = tcp_jiffies32;
- newsk->sk_txhash = treq->txhash;
- newtp->last_oow_ack_time = 0;
- newtp->total_retrans = req->num_retrans;
-
- /* So many TCP implementations out there (incorrectly) count the
- * initial SYN frame in their delayed-ACK and congestion control
- * algorithms that we must have the following bandaid to talk
- * efficiently to them. -DaveM
- */
- newtp->snd_cwnd = TCP_INIT_CWND;
- newtp->snd_cwnd_cnt = 0;
-
- /* There's a bubble in the pipe until at least the first ACK. */
- newtp->app_limited = ~0U;
-
- tcp_init_xmit_timers(newsk);
- newtp->write_seq = newtp->pushed_seq = treq->snt_isn + 1;
-
- newtp->rx_opt.saw_tstamp = 0;
-
- newtp->rx_opt.dsack = 0;
- newtp->rx_opt.num_sacks = 0;
-
- newtp->urg_data = 0;
-
- if (sock_flag(newsk, SOCK_KEEPOPEN))
- inet_csk_reset_keepalive_timer(newsk,
- keepalive_time_when(newtp));
-
- newtp->rx_opt.tstamp_ok = ireq->tstamp_ok;
- newtp->rx_opt.sack_ok = ireq->sack_ok;
- newtp->window_clamp = req->rsk_window_clamp;
- newtp->rcv_ssthresh = req->rsk_rcv_wnd;
- newtp->rcv_wnd = req->rsk_rcv_wnd;
- newtp->rx_opt.wscale_ok = ireq->wscale_ok;
- if (newtp->rx_opt.wscale_ok) {
- newtp->rx_opt.snd_wscale = ireq->snd_wscale;
- newtp->rx_opt.rcv_wscale = ireq->rcv_wscale;
- } else {
- newtp->rx_opt.snd_wscale = newtp->rx_opt.rcv_wscale = 0;
- newtp->window_clamp = min(newtp->window_clamp, 65535U);
- }
- newtp->snd_wnd = (ntohs(tcp_hdr(skb)->window) <<
- newtp->rx_opt.snd_wscale);
- newtp->max_window = newtp->snd_wnd;
-
- if (newtp->rx_opt.tstamp_ok) {
- newtp->rx_opt.ts_recent = req->ts_recent;
- newtp->rx_opt.ts_recent_stamp = get_seconds();
- newtp->tcp_header_len = sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED;
- } else {
- newtp->rx_opt.ts_recent_stamp = 0;
- newtp->tcp_header_len = sizeof(struct tcphdr);
- }
- newtp->tsoffset = treq->ts_off;
+ if (!newsk)
+ return NULL;
+
+ newicsk = inet_csk(newsk);
+ newtp = tcp_sk(newsk);
+ oldtp = tcp_sk(sk);
+
+ smc_check_reset_syn_req(oldtp, req, newtp);
+
+ /* Now setup tcp_sock */
+ newtp->pred_flags = 0;
+
+ newtp->rcv_wup = newtp->copied_seq =
+ newtp->rcv_nxt = treq->rcv_isn + 1;
+ newtp->segs_in = 1;
+
+ newtp->snd_sml = newtp->snd_una =
+ newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1;
+
+ INIT_LIST_HEAD(&newtp->tsq_node);
+ INIT_LIST_HEAD(&newtp->tsorted_sent_queue);
+
+ tcp_init_wl(newtp, treq->rcv_isn);
+
+ newtp->srtt_us = 0;
+ newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
+ minmax_reset(&newtp->rtt_min, tcp_jiffies32, ~0U);
+ newicsk->icsk_rto = TCP_TIMEOUT_INIT;
+ newicsk->icsk_ack.lrcvtime = tcp_jiffies32;
+
+ newtp->packets_out = 0;
+ newtp->retrans_out = 0;
+ newtp->sacked_out = 0;
+ newtp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
+ newtp->tlp_high_seq = 0;
+ newtp->lsndtime = tcp_jiffies32;
+ newsk->sk_txhash = treq->txhash;
+ newtp->last_oow_ack_time = 0;
+ newtp->total_retrans = req->num_retrans;
+
+ /* So many TCP implementations out there (incorrectly) count the
+ * initial SYN frame in their delayed-ACK and congestion control
+ * algorithms that we must have the following bandaid to talk
+ * efficiently to them. -DaveM
+ */
+ newtp->snd_cwnd = TCP_INIT_CWND;
+ newtp->snd_cwnd_cnt = 0;
+
+ /* There's a bubble in the pipe until at least the first ACK. */
+ newtp->app_limited = ~0U;
+
+ tcp_init_xmit_timers(newsk);
+ newtp->write_seq = newtp->pushed_seq = treq->snt_isn + 1;
+
+ newtp->rx_opt.saw_tstamp = 0;
+
+ newtp->rx_opt.dsack = 0;
+ newtp->rx_opt.num_sacks = 0;
+
+ newtp->urg_data = 0;
+
+ if (sock_flag(newsk, SOCK_KEEPOPEN))
+ inet_csk_reset_keepalive_timer(newsk,
+ keepalive_time_when(newtp));
+
+ newtp->rx_opt.tstamp_ok = ireq->tstamp_ok;
+ newtp->rx_opt.sack_ok = ireq->sack_ok;
+ newtp->window_clamp = req->rsk_window_clamp;
+ newtp->rcv_ssthresh = req->rsk_rcv_wnd;
+ newtp->rcv_wnd = req->rsk_rcv_wnd;
+ newtp->rx_opt.wscale_ok = ireq->wscale_ok;
+ if (newtp->rx_opt.wscale_ok) {
+ newtp->rx_opt.snd_wscale = ireq->snd_wscale;
+ newtp->rx_opt.rcv_wscale = ireq->rcv_wscale;
+ } else {
+ newtp->rx_opt.snd_wscale = newtp->rx_opt.rcv_wscale = 0;
+ newtp->window_clamp = min(newtp->window_clamp, 65535U);
+ }
+ newtp->snd_wnd = ntohs(tcp_hdr(skb)->window) << newtp->rx_opt.snd_wscale;
+ newtp->max_window = newtp->snd_wnd;
+
+ if (newtp->rx_opt.tstamp_ok) {
+ newtp->rx_opt.ts_recent = req->ts_recent;
+ newtp->rx_opt.ts_recent_stamp = ktime_get_seconds();
+ newtp->tcp_header_len = sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED;
+ } else {
+ newtp->rx_opt.ts_recent_stamp = 0;
+ newtp->tcp_header_len = sizeof(struct tcphdr);
+ }
+ newtp->tsoffset = treq->ts_off;
#ifdef CONFIG_TCP_MD5SIG
- newtp->md5sig_info = NULL; /*XXX*/
- if (newtp->af_specific->md5_lookup(sk, newsk))
- newtp->tcp_header_len += TCPOLEN_MD5SIG_ALIGNED;
+ newtp->md5sig_info = NULL; /*XXX*/
+ if (newtp->af_specific->md5_lookup(sk, newsk))
+ newtp->tcp_header_len += TCPOLEN_MD5SIG_ALIGNED;
#endif
- if (skb->len >= TCP_MSS_DEFAULT + newtp->tcp_header_len)
- newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len;
- newtp->rx_opt.mss_clamp = req->mss;
- tcp_ecn_openreq_child(newtp, req);
- newtp->fastopen_req = NULL;
- newtp->fastopen_rsk = NULL;
- newtp->syn_data_acked = 0;
- newtp->rack.mstamp = 0;
- newtp->rack.advanced = 0;
- newtp->rack.reo_wnd_steps = 1;
- newtp->rack.last_delivered = 0;
- newtp->rack.reo_wnd_persist = 0;
- newtp->rack.dsack_seen = 0;
-
- __TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS);
- }
+ if (skb->len >= TCP_MSS_DEFAULT + newtp->tcp_header_len)
+ newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len;
+ newtp->rx_opt.mss_clamp = req->mss;
+ tcp_ecn_openreq_child(newtp, req);
+ newtp->fastopen_req = NULL;
+ newtp->fastopen_rsk = NULL;
+ newtp->syn_data_acked = 0;
+ newtp->rack.mstamp = 0;
+ newtp->rack.advanced = 0;
+ newtp->rack.reo_wnd_steps = 1;
+ newtp->rack.last_delivered = 0;
+ newtp->rack.reo_wnd_persist = 0;
+ newtp->rack.dsack_seen = 0;
+
+ __TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS);
+
return newsk;
}
EXPORT_SYMBOL(tcp_create_openreq_child);
* it can be estimated (approximately)
* from another data.
*/
- tmp_opt.ts_recent_stamp = get_seconds() - ((TCP_TIMEOUT_INIT/HZ)<<req->num_timeout);
+ tmp_opt.ts_recent_stamp = ktime_get_seconds() - ((TCP_TIMEOUT_INIT/HZ)<<req->num_timeout);
paws_reject = tcp_paws_reject(&tmp_opt, th->rst);
}
}
return segs;
}
-struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb)
+struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb)
{
- struct sk_buff **pp = NULL;
+ struct sk_buff *pp = NULL;
struct sk_buff *p;
struct tcphdr *th;
struct tcphdr *th2;
len = skb_gro_len(skb);
flags = tcp_flag_word(th);
- for (; (p = *head); head = &p->next) {
+ list_for_each_entry(p, head, list) {
if (!NAPI_GRO_CB(p)->same_flow)
continue;
goto found;
}
-
+ p = NULL;
goto out_check_final;
found:
flush |= (len - 1) >= mss;
flush |= (ntohl(th2->seq) + skb_gro_len(p)) ^ ntohl(th->seq);
+#ifdef CONFIG_TLS_DEVICE
+ flush |= p->decrypted ^ skb->decrypted;
+#endif
- if (flush || skb_gro_receive(head, skb)) {
+ if (flush || skb_gro_receive(p, skb)) {
mss = 1;
goto out_check_final;
}
TCP_FLAG_FIN));
if (p && (!NAPI_GRO_CB(skb)->same_flow || flush))
- pp = head;
+ pp = p;
out:
NAPI_GRO_CB(skb)->flush |= (flush != 0);
}
EXPORT_SYMBOL(tcp_gro_complete);
-static struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *skb)
+static struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb)
{
/* Don't bother verifying checksum if we're going to flush anyway. */
if (!NAPI_GRO_CB(skb)->flush &&
return HRTIMER_NORESTART;
}
-/* BBR congestion control needs pacing.
- * Same remark for SO_MAX_PACING_RATE.
- * sch_fq packet scheduler is efficiently handling pacing,
- * but is not always installed/used.
- * Return true if TCP stack should pace packets itself.
- */
-static bool tcp_needs_internal_pacing(const struct sock *sk)
-{
- return smp_load_acquire(&sk->sk_pacing_status) == SK_PACING_NEEDED;
-}
-
static void tcp_internal_pacing(struct sock *sk, const struct sk_buff *skb)
{
u64 len_ns;
if (!rate || rate == ~0U)
return;
- /* Should account for header sizes as sch_fq does,
- * but lets make things simple.
- */
len_ns = (u64)skb->len * NSEC_PER_SEC;
do_div(len_ns, rate);
hrtimer_start(&tcp_sk(sk)->pacing_timer,
rs->prior_mstamp); /* ack phase */
rs->interval_us = max(snd_us, ack_us);
+ /* Record both segment send and ack receive intervals */
+ rs->snd_interval_us = snd_us;
+ rs->rcv_interval_us = ack_us;
+
/* Normally we expect interval_us >= min-rtt.
* Note that rate may still be over-estimated when a spuriously
* retransmistted skb was first (s)acked because "interval_us"
if (msg->msg_flags & MSG_OOB) /* Mirror BSD error message compatibility */
return -EOPNOTSUPP;
- ipc.opt = NULL;
- ipc.tx_flags = 0;
- ipc.ttl = 0;
- ipc.tos = -1;
-
getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag;
fl4 = &inet->cork.fl.u.ip4;
connected = 1;
}
- ipc.sockc.tsflags = sk->sk_tsflags;
- ipc.addr = inet->inet_saddr;
- ipc.oif = sk->sk_bound_dev_if;
+ ipcm_init_sk(&ipc, inet);
ipc.gso_size = up->gso_size;
if (msg->msg_controllen) {
saddr = ipc.addr;
ipc.addr = faddr = daddr;
- sock_tx_timestamp(sk, ipc.sockc.tsflags, &ipc.tx_flags);
-
if (ipc.opt && ipc.opt->opt.srr) {
if (!daddr) {
err = -EINVAL;
* udp_poll - wait for a UDP event.
* @file - file struct
* @sock - socket
- * @events - events to wait for
+ * @wait - poll table
*
* This is same as datagram poll, except for the special case of
* blocking sockets. If application is using a blocking fd
* but then block when reading it. Add special case code
* to work around these arguably broken applications.
*/
-__poll_t udp_poll_mask(struct socket *sock, __poll_t events)
+__poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait)
{
- __poll_t mask = datagram_poll_mask(sock, events);
+ __poll_t mask = datagram_poll(file, sock, wait);
struct sock *sk = sock->sk;
if (!skb_queue_empty(&udp_sk(sk)->reader_queue))
mask |= EPOLLIN | EPOLLRDNORM;
/* Check for false positives due to checksum errors */
- if ((mask & EPOLLRDNORM) && !(sock->file->f_flags & O_NONBLOCK) &&
+ if ((mask & EPOLLRDNORM) && !(file->f_flags & O_NONBLOCK) &&
!(sk->sk_shutdown & RCV_SHUTDOWN) && first_packet_length(sk) == -1)
mask &= ~(EPOLLIN | EPOLLRDNORM);
return mask;
}
-EXPORT_SYMBOL(udp_poll_mask);
+EXPORT_SYMBOL(udp_poll);
int udp_abort(struct sock *sk, int err)
{
return segs;
}
-struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb,
- struct udphdr *uh, udp_lookup_t lookup)
+struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
+ struct udphdr *uh, udp_lookup_t lookup)
{
- struct sk_buff *p, **pp = NULL;
+ struct sk_buff *pp = NULL;
+ struct sk_buff *p;
struct udphdr *uh2;
unsigned int off = skb_gro_offset(skb);
int flush = 1;
unflush:
flush = 0;
- for (p = *head; p; p = p->next) {
+ list_for_each_entry(p, head, list) {
if (!NAPI_GRO_CB(p)->same_flow)
continue;
out_unlock:
rcu_read_unlock();
out:
- NAPI_GRO_CB(skb)->flush |= flush;
+ skb_gro_flush_final(skb, pp, flush);
return pp;
}
EXPORT_SYMBOL(udp_gro_receive);
-static struct sk_buff **udp4_gro_receive(struct sk_buff **head,
- struct sk_buff *skb)
+static struct sk_buff *udp4_gro_receive(struct list_head *head,
+ struct sk_buff *skb)
{
struct udphdr *uh = udp_gro_udphdr(skb);
if (ndev->cnf.stable_secret.initialized)
ndev->cnf.addr_gen_mode = IN6_ADDR_GEN_MODE_STABLE_PRIVACY;
- else
- ndev->cnf.addr_gen_mode = ipv6_devconf_dflt.addr_gen_mode;
ndev->cnf.mtu6 = dev->mtu;
ndev->nd_parms = neigh_parms_alloc(dev, &nd_tbl);
unsigned long expires, u32 flags)
{
struct fib6_info *f6i;
+ u32 prio;
f6i = addrconf_get_prefix_route(&ifp->addr,
ifp->prefix_len,
if (!f6i)
return -ENOENT;
- if (f6i->fib6_metric != ifp->rt_priority) {
+ prio = ifp->rt_priority ? : IP6_RT_PRIO_ADDRCONF;
+ if (f6i->fib6_metric != prio) {
+ /* delete old one */
+ ip6_del_rt(dev_net(ifp->idev->dev), f6i);
+
/* add new one */
addrconf_prefix_route(&ifp->addr, ifp->prefix_len,
ifp->rt_priority, ifp->idev->dev,
expires, flags, GFP_KERNEL);
- /* delete old one */
- ip6_del_rt(dev_net(ifp->idev->dev), f6i);
} else {
if (!expires)
fib6_clean_expires(f6i);
+ nla_total_size(DEVCONF_MAX * 4) /* IFLA_INET6_CONF */
+ nla_total_size(IPSTATS_MIB_MAX * 8) /* IFLA_INET6_STATS */
+ nla_total_size(ICMP6_MIB_MAX * 8) /* IFLA_INET6_ICMP6STATS */
- + nla_total_size(sizeof(struct in6_addr)); /* IFLA_INET6_TOKEN */
+ + nla_total_size(sizeof(struct in6_addr)) /* IFLA_INET6_TOKEN */
+ + nla_total_size(1) /* IFLA_INET6_ADDR_GEN_MODE */
+ + 0;
}
static inline size_t inet6_if_nlmsg_size(void)
loff_t *ppos)
{
int ret = 0;
- int new_val;
+ u32 new_val;
struct inet6_dev *idev = (struct inet6_dev *)ctl->extra1;
struct net *net = (struct net *)ctl->extra2;
+ struct ctl_table tmp = {
+ .data = &new_val,
+ .maxlen = sizeof(new_val),
+ .mode = ctl->mode,
+ };
if (!rtnl_trylock())
return restart_syscall();
- ret = proc_dointvec(ctl, write, buffer, lenp, ppos);
+ new_val = *((u32 *)ctl->data);
- if (write) {
- new_val = *((int *)ctl->data);
+ ret = proc_douintvec(&tmp, write, buffer, lenp, ppos);
+ if (ret != 0)
+ goto out;
+ if (write) {
if (check_addr_gen_mode(new_val) < 0) {
ret = -EINVAL;
goto out;
}
- /* request for default */
- if (&net->ipv6.devconf_dflt->addr_gen_mode == ctl->data) {
- ipv6_devconf_dflt.addr_gen_mode = new_val;
-
- /* request for individual net device */
- } else {
- if (!idev)
- goto out;
-
+ if (idev) {
if (check_stable_privacy(idev, net, new_val) < 0) {
ret = -EINVAL;
goto out;
idev->cnf.addr_gen_mode = new_val;
addrconf_dev_config(idev->dev);
}
+ } else if (&net->ipv6.devconf_all->addr_gen_mode == ctl->data) {
+ struct net_device *dev;
+
+ net->ipv6.devconf_dflt->addr_gen_mode = new_val;
+ for_each_netdev(net, dev) {
+ idev = __in6_dev_get(dev);
+ if (idev &&
+ idev->cnf.addr_gen_mode != new_val) {
+ idev->cnf.addr_gen_mode = new_val;
+ addrconf_dev_config(idev->dev);
+ }
+ }
}
+
+ *((u32 *)ctl->data) = new_val;
}
out:
.socketpair = sock_no_socketpair, /* a do nothing */
.accept = inet_accept, /* ok */
.getname = inet6_getname,
- .poll_mask = tcp_poll_mask, /* ok */
+ .poll = tcp_poll, /* ok */
.ioctl = inet6_ioctl, /* must change */
.listen = inet_listen, /* ok */
.shutdown = inet_shutdown, /* ok */
.socketpair = sock_no_socketpair, /* a do nothing */
.accept = sock_no_accept, /* a do nothing */
.getname = inet6_getname,
- .poll_mask = udp_poll_mask, /* ok */
+ .poll = udp_poll, /* ok */
.ioctl = inet6_ioctl, /* must change */
.listen = sock_no_listen, /* ok */
.shutdown = inet_shutdown, /* ok */
static struct packet_type ipv6_packet_type __read_mostly = {
.type = cpu_to_be16(ETH_P_IPV6),
.func = ipv6_rcv,
+ .list_func = ipv6_list_rcv,
};
static int __init ipv6_packet_init(void)
int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
struct msghdr *msg, struct flowi6 *fl6,
- struct ipcm6_cookie *ipc6, struct sockcm_cookie *sockc)
+ struct ipcm6_cookie *ipc6)
{
struct in6_pktinfo *src_info;
struct cmsghdr *cmsg;
}
if (cmsg->cmsg_level == SOL_SOCKET) {
- err = __sock_cmsg_send(sk, msg, cmsg, sockc);
+ err = __sock_cmsg_send(sk, msg, cmsg, &ipc6->sockc);
if (err)
return err;
continue;
return 0;
}
-static struct sk_buff **esp6_gro_receive(struct sk_buff **head,
- struct sk_buff *skb)
+static struct sk_buff *esp6_gro_receive(struct list_head *head,
+ struct sk_buff *skb)
{
int offset = skb_gro_offset(skb);
struct xfrm_offload *xo;
struct icmp6hdr tmp_hdr;
struct flowi6 fl6;
struct icmpv6_msg msg;
- struct sockcm_cookie sockc_unused = {0};
struct ipcm6_cookie ipc6;
int iif = 0;
int addr_type = 0;
else if (!fl6.flowi6_oif)
fl6.flowi6_oif = np->ucast_oif;
- ipc6.tclass = np->tclass;
+ ipcm6_init_sk(&ipc6, np);
fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
dst = icmpv6_route_lookup(net, skb, sk, &fl6);
goto out;
ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
- ipc6.dontfrag = np->dontfrag;
- ipc6.opt = NULL;
msg.skb = skb;
msg.offset = skb_network_offset(skb);
len + sizeof(struct icmp6hdr),
sizeof(struct icmp6hdr),
&ipc6, &fl6, (struct rt6_info *)dst,
- MSG_DONTWAIT, &sockc_unused)) {
+ MSG_DONTWAIT)) {
ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS);
ip6_flush_pending_frames(sk);
} else {
struct dst_entry *dst;
struct ipcm6_cookie ipc6;
u32 mark = IP6_REPLY_MARK(net, skb->mark);
- struct sockcm_cookie sockc_unused = {0};
saddr = &ipv6_hdr(skb)->daddr;
msg.offset = 0;
msg.type = ICMPV6_ECHO_REPLY;
+ ipcm6_init_sk(&ipc6, np);
ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
ipc6.tclass = ipv6_get_dsfield(ipv6_hdr(skb));
- ipc6.dontfrag = np->dontfrag;
- ipc6.opt = NULL;
if (ip6_append_data(sk, icmpv6_getfrag, &msg,
skb->len + sizeof(struct icmp6hdr),
sizeof(struct icmp6hdr), &ipc6, &fl6,
- (struct rt6_info *)dst, MSG_DONTWAIT,
- &sockc_unused)) {
+ (struct rt6_info *)dst, MSG_DONTWAIT)) {
__ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS);
ip6_flush_pending_frames(sk);
} else {
obj-$(CONFIG_IPV6_ILA) += ila.o
-ila-objs := ila_common.o ila_lwt.o ila_xlat.o
+ila-objs := ila_main.o ila_common.o ila_lwt.o ila_xlat.o
#include <linux/skbuff.h>
#include <linux/types.h>
#include <net/checksum.h>
+#include <net/genetlink.h>
#include <net/ip.h>
#include <net/protocol.h>
#include <uapi/linux/ila.h>
void ila_init_saved_csum(struct ila_params *p);
+struct ila_net {
+ struct {
+ struct rhashtable rhash_table;
+ spinlock_t *locks; /* Bucket locks for entry manipulation */
+ unsigned int locks_mask;
+ bool hooks_registered;
+ } xlat;
+};
+
int ila_lwt_init(void);
void ila_lwt_fini(void);
-int ila_xlat_init(void);
-void ila_xlat_fini(void);
+
+int ila_xlat_init_net(struct net *net);
+void ila_xlat_exit_net(struct net *net);
+
+int ila_xlat_nl_cmd_add_mapping(struct sk_buff *skb, struct genl_info *info);
+int ila_xlat_nl_cmd_del_mapping(struct sk_buff *skb, struct genl_info *info);
+int ila_xlat_nl_cmd_get_mapping(struct sk_buff *skb, struct genl_info *info);
+int ila_xlat_nl_cmd_flush(struct sk_buff *skb, struct genl_info *info);
+int ila_xlat_nl_dump_start(struct netlink_callback *cb);
+int ila_xlat_nl_dump_done(struct netlink_callback *cb);
+int ila_xlat_nl_dump(struct sk_buff *skb, struct netlink_callback *cb);
+
+extern unsigned int ila_net_id;
+
+extern struct genl_family ila_nl_family;
#endif /* __ILA_H */
iaddr->loc = p->locator;
}
-static int __init ila_init(void)
-{
- int ret;
-
- ret = ila_lwt_init();
-
- if (ret)
- goto fail_lwt;
-
- ret = ila_xlat_init();
- if (ret)
- goto fail_xlat;
-
- return 0;
-fail_xlat:
- ila_lwt_fini();
-fail_lwt:
- return ret;
-}
-
-static void __exit ila_fini(void)
-{
- ila_xlat_fini();
- ila_lwt_fini();
-}
-
-module_init(ila_init);
-module_exit(ila_fini);
-MODULE_AUTHOR("Tom Herbert <tom@herbertland.com>");
-MODULE_LICENSE("GPL");
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#include <net/genetlink.h>
+#include <net/ila.h>
+#include <net/netns/generic.h>
+#include <uapi/linux/genetlink.h>
+#include "ila.h"
+
+static const struct nla_policy ila_nl_policy[ILA_ATTR_MAX + 1] = {
+ [ILA_ATTR_LOCATOR] = { .type = NLA_U64, },
+ [ILA_ATTR_LOCATOR_MATCH] = { .type = NLA_U64, },
+ [ILA_ATTR_IFINDEX] = { .type = NLA_U32, },
+ [ILA_ATTR_CSUM_MODE] = { .type = NLA_U8, },
+ [ILA_ATTR_IDENT_TYPE] = { .type = NLA_U8, },
+};
+
+static const struct genl_ops ila_nl_ops[] = {
+ {
+ .cmd = ILA_CMD_ADD,
+ .doit = ila_xlat_nl_cmd_add_mapping,
+ .policy = ila_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ },
+ {
+ .cmd = ILA_CMD_DEL,
+ .doit = ila_xlat_nl_cmd_del_mapping,
+ .policy = ila_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ },
+ {
+ .cmd = ILA_CMD_FLUSH,
+ .doit = ila_xlat_nl_cmd_flush,
+ .policy = ila_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ },
+ {
+ .cmd = ILA_CMD_GET,
+ .doit = ila_xlat_nl_cmd_get_mapping,
+ .start = ila_xlat_nl_dump_start,
+ .dumpit = ila_xlat_nl_dump,
+ .done = ila_xlat_nl_dump_done,
+ .policy = ila_nl_policy,
+ },
+};
+
+unsigned int ila_net_id;
+
+struct genl_family ila_nl_family __ro_after_init = {
+ .hdrsize = 0,
+ .name = ILA_GENL_NAME,
+ .version = ILA_GENL_VERSION,
+ .maxattr = ILA_ATTR_MAX,
+ .netnsok = true,
+ .parallel_ops = true,
+ .module = THIS_MODULE,
+ .ops = ila_nl_ops,
+ .n_ops = ARRAY_SIZE(ila_nl_ops),
+};
+
+static __net_init int ila_init_net(struct net *net)
+{
+ int err;
+
+ err = ila_xlat_init_net(net);
+ if (err)
+ goto ila_xlat_init_fail;
+
+ return 0;
+
+ila_xlat_init_fail:
+ return err;
+}
+
+static __net_exit void ila_exit_net(struct net *net)
+{
+ ila_xlat_exit_net(net);
+}
+
+static struct pernet_operations ila_net_ops = {
+ .init = ila_init_net,
+ .exit = ila_exit_net,
+ .id = &ila_net_id,
+ .size = sizeof(struct ila_net),
+};
+
+static int __init ila_init(void)
+{
+ int ret;
+
+ ret = register_pernet_device(&ila_net_ops);
+ if (ret)
+ goto register_device_fail;
+
+ ret = genl_register_family(&ila_nl_family);
+ if (ret)
+ goto register_family_fail;
+
+ ret = ila_lwt_init();
+ if (ret)
+ goto fail_lwt;
+
+ return 0;
+
+fail_lwt:
+ genl_unregister_family(&ila_nl_family);
+register_family_fail:
+ unregister_pernet_device(&ila_net_ops);
+register_device_fail:
+ return ret;
+}
+
+static void __exit ila_fini(void)
+{
+ ila_lwt_fini();
+ genl_unregister_family(&ila_nl_family);
+ unregister_pernet_device(&ila_net_ops);
+}
+
+module_init(ila_init);
+module_exit(ila_fini);
+MODULE_AUTHOR("Tom Herbert <tom@herbertland.com>");
+MODULE_LICENSE("GPL");
struct rcu_head rcu;
};
-static unsigned int ila_net_id;
-
-struct ila_net {
- struct rhashtable rhash_table;
- spinlock_t *locks; /* Bucket locks for entry manipulation */
- unsigned int locks_mask;
- bool hooks_registered;
-};
-
+#define MAX_LOCKS 1024
#define LOCKS_PER_CPU 10
static int alloc_ila_locks(struct ila_net *ilan)
{
- unsigned int i, size;
- unsigned int nr_pcpus = num_possible_cpus();
-
- nr_pcpus = min_t(unsigned int, nr_pcpus, 32UL);
- size = roundup_pow_of_two(nr_pcpus * LOCKS_PER_CPU);
-
- if (sizeof(spinlock_t) != 0) {
- ilan->locks = kvmalloc_array(size, sizeof(spinlock_t),
- GFP_KERNEL);
- if (!ilan->locks)
- return -ENOMEM;
- for (i = 0; i < size; i++)
- spin_lock_init(&ilan->locks[i]);
- }
- ilan->locks_mask = size - 1;
-
- return 0;
+ return alloc_bucket_spinlocks(&ilan->xlat.locks, &ilan->xlat.locks_mask,
+ MAX_LOCKS, LOCKS_PER_CPU,
+ GFP_KERNEL);
}
static u32 hashrnd __read_mostly;
static inline spinlock_t *ila_get_lock(struct ila_net *ilan,
struct ila_locator loc)
{
- return &ilan->locks[ila_locator_hash(loc) & ilan->locks_mask];
+ return &ilan->xlat.locks[ila_locator_hash(loc) & ilan->xlat.locks_mask];
}
static inline int ila_cmp_wildcards(struct ila_map *ila,
.obj_cmpfn = ila_cmpfn,
};
-static struct genl_family ila_nl_family;
-
-static const struct nla_policy ila_nl_policy[ILA_ATTR_MAX + 1] = {
- [ILA_ATTR_LOCATOR] = { .type = NLA_U64, },
- [ILA_ATTR_LOCATOR_MATCH] = { .type = NLA_U64, },
- [ILA_ATTR_IFINDEX] = { .type = NLA_U32, },
- [ILA_ATTR_CSUM_MODE] = { .type = NLA_U8, },
- [ILA_ATTR_IDENT_TYPE] = { .type = NLA_U8, },
-};
-
static int parse_nl_config(struct genl_info *info,
struct ila_xlat_params *xp)
{
{
struct ila_map *ila;
- ila = rhashtable_lookup_fast(&ilan->rhash_table, &iaddr->loc,
+ ila = rhashtable_lookup_fast(&ilan->xlat.rhash_table, &iaddr->loc,
rht_params);
while (ila) {
if (!ila_cmp_wildcards(ila, iaddr, ifindex))
{
struct ila_map *ila;
- ila = rhashtable_lookup_fast(&ilan->rhash_table,
+ ila = rhashtable_lookup_fast(&ilan->xlat.rhash_table,
&xp->ip.locator_match,
rht_params);
while (ila) {
kfree_rcu(ila, rcu);
}
-static void ila_free_cb(void *ptr, void *arg)
+static void ila_free_node(struct ila_map *ila)
{
- struct ila_map *ila = (struct ila_map *)ptr, *next;
+ struct ila_map *next;
/* Assume rcu_readlock held */
while (ila) {
}
}
+static void ila_free_cb(void *ptr, void *arg)
+{
+ ila_free_node((struct ila_map *)ptr);
+}
+
static int ila_xlat_addr(struct sk_buff *skb, bool sir2ila);
static unsigned int
spinlock_t *lock = ila_get_lock(ilan, xp->ip.locator_match);
int err = 0, order;
- if (!ilan->hooks_registered) {
+ if (!ilan->xlat.hooks_registered) {
/* We defer registering net hooks in the namespace until the
* first mapping is added.
*/
if (err)
return err;
- ilan->hooks_registered = true;
+ ilan->xlat.hooks_registered = true;
}
ila = kzalloc(sizeof(*ila), GFP_KERNEL);
spin_lock(lock);
- head = rhashtable_lookup_fast(&ilan->rhash_table,
+ head = rhashtable_lookup_fast(&ilan->xlat.rhash_table,
&xp->ip.locator_match,
rht_params);
if (!head) {
/* New entry for the rhash_table */
- err = rhashtable_lookup_insert_fast(&ilan->rhash_table,
+ err = rhashtable_lookup_insert_fast(&ilan->xlat.rhash_table,
&ila->node, rht_params);
} else {
struct ila_map *tila = head, *prev = NULL;
} else {
/* Make this ila new head */
RCU_INIT_POINTER(ila->next, head);
- err = rhashtable_replace_fast(&ilan->rhash_table,
+ err = rhashtable_replace_fast(&ilan->xlat.rhash_table,
&head->node,
&ila->node, rht_params);
if (err)
spin_lock(lock);
- head = rhashtable_lookup_fast(&ilan->rhash_table,
+ head = rhashtable_lookup_fast(&ilan->xlat.rhash_table,
&xp->ip.locator_match, rht_params);
ila = head;
* table
*/
err = rhashtable_replace_fast(
- &ilan->rhash_table, &ila->node,
+ &ilan->xlat.rhash_table, &ila->node,
&head->node, rht_params);
if (err)
goto out;
} else {
/* Entry no longer used */
- err = rhashtable_remove_fast(&ilan->rhash_table,
- &ila->node,
- rht_params);
+ err = rhashtable_remove_fast(
+ &ilan->xlat.rhash_table,
+ &ila->node, rht_params);
}
}
return err;
}
-static int ila_nl_cmd_add_mapping(struct sk_buff *skb, struct genl_info *info)
+int ila_xlat_nl_cmd_add_mapping(struct sk_buff *skb, struct genl_info *info)
{
struct net *net = genl_info_net(info);
struct ila_xlat_params p;
return ila_add_mapping(net, &p);
}
-static int ila_nl_cmd_del_mapping(struct sk_buff *skb, struct genl_info *info)
+int ila_xlat_nl_cmd_del_mapping(struct sk_buff *skb, struct genl_info *info)
{
struct net *net = genl_info_net(info);
struct ila_xlat_params xp;
return 0;
}
+static inline spinlock_t *lock_from_ila_map(struct ila_net *ilan,
+ struct ila_map *ila)
+{
+ return ila_get_lock(ilan, ila->xp.ip.locator_match);
+}
+
+int ila_xlat_nl_cmd_flush(struct sk_buff *skb, struct genl_info *info)
+{
+ struct net *net = genl_info_net(info);
+ struct ila_net *ilan = net_generic(net, ila_net_id);
+ struct rhashtable_iter iter;
+ struct ila_map *ila;
+ spinlock_t *lock;
+ int ret;
+
+ ret = rhashtable_walk_init(&ilan->xlat.rhash_table, &iter, GFP_KERNEL);
+ if (ret)
+ goto done;
+
+ rhashtable_walk_start(&iter);
+
+ for (;;) {
+ ila = rhashtable_walk_next(&iter);
+
+ if (IS_ERR(ila)) {
+ if (PTR_ERR(ila) == -EAGAIN)
+ continue;
+ ret = PTR_ERR(ila);
+ goto done;
+ } else if (!ila) {
+ break;
+ }
+
+ lock = lock_from_ila_map(ilan, ila);
+
+ spin_lock(lock);
+
+ ret = rhashtable_remove_fast(&ilan->xlat.rhash_table,
+ &ila->node, rht_params);
+ if (!ret)
+ ila_free_node(ila);
+
+ spin_unlock(lock);
+
+ if (ret)
+ break;
+ }
+
+done:
+ rhashtable_walk_stop(&iter);
+ return ret;
+}
+
static int ila_fill_info(struct ila_map *ila, struct sk_buff *msg)
{
if (nla_put_u64_64bit(msg, ILA_ATTR_LOCATOR,
return -EMSGSIZE;
}
-static int ila_nl_cmd_get_mapping(struct sk_buff *skb, struct genl_info *info)
+int ila_xlat_nl_cmd_get_mapping(struct sk_buff *skb, struct genl_info *info)
{
struct net *net = genl_info_net(info);
struct ila_net *ilan = net_generic(net, ila_net_id);
struct ila_dump_iter {
struct rhashtable_iter rhiter;
+ int skip;
};
-static int ila_nl_dump_start(struct netlink_callback *cb)
+int ila_xlat_nl_dump_start(struct netlink_callback *cb)
{
struct net *net = sock_net(cb->skb->sk);
struct ila_net *ilan = net_generic(net, ila_net_id);
- struct ila_dump_iter *iter = (struct ila_dump_iter *)cb->args[0];
+ struct ila_dump_iter *iter;
+ int ret;
- if (!iter) {
- iter = kmalloc(sizeof(*iter), GFP_KERNEL);
- if (!iter)
- return -ENOMEM;
+ iter = kmalloc(sizeof(*iter), GFP_KERNEL);
+ if (!iter)
+ return -ENOMEM;
- cb->args[0] = (long)iter;
+ ret = rhashtable_walk_init(&ilan->xlat.rhash_table, &iter->rhiter,
+ GFP_KERNEL);
+ if (ret) {
+ kfree(iter);
+ return ret;
}
- return rhashtable_walk_init(&ilan->rhash_table, &iter->rhiter,
- GFP_KERNEL);
+ iter->skip = 0;
+ cb->args[0] = (long)iter;
+
+ return ret;
}
-static int ila_nl_dump_done(struct netlink_callback *cb)
+int ila_xlat_nl_dump_done(struct netlink_callback *cb)
{
struct ila_dump_iter *iter = (struct ila_dump_iter *)cb->args[0];
return 0;
}
-static int ila_nl_dump(struct sk_buff *skb, struct netlink_callback *cb)
+int ila_xlat_nl_dump(struct sk_buff *skb, struct netlink_callback *cb)
{
struct ila_dump_iter *iter = (struct ila_dump_iter *)cb->args[0];
struct rhashtable_iter *rhiter = &iter->rhiter;
+ int skip = iter->skip;
struct ila_map *ila;
int ret;
rhashtable_walk_start(rhiter);
- for (;;) {
- ila = rhashtable_walk_next(rhiter);
+ /* Get first entry */
+ ila = rhashtable_walk_peek(rhiter);
+
+ if (ila && !IS_ERR(ila) && skip) {
+ /* Skip over visited entries */
+ while (ila && skip) {
+ /* Skip over any ila entries in this list that we
+ * have already dumped.
+ */
+ ila = rcu_access_pointer(ila->next);
+ skip--;
+ }
+ }
+
+ skip = 0;
+
+ for (;;) {
if (IS_ERR(ila)) {
- if (PTR_ERR(ila) == -EAGAIN)
- continue;
ret = PTR_ERR(ila);
- goto done;
+ if (ret == -EAGAIN) {
+ /* Table has changed and iter has reset. Return
+ * -EAGAIN to the application even if we have
+ * written data to the skb. The application
+ * needs to deal with this.
+ */
+
+ goto out_ret;
+ } else {
+ break;
+ }
} else if (!ila) {
+ ret = 0;
break;
}
cb->nlh->nlmsg_seq, NLM_F_MULTI,
skb, ILA_CMD_GET);
if (ret)
- goto done;
+ goto out;
+ skip++;
ila = rcu_access_pointer(ila->next);
}
+
+ skip = 0;
+ ila = rhashtable_walk_next(rhiter);
}
- ret = skb->len;
+out:
+ iter->skip = skip;
+ ret = (skb->len ? : ret);
-done:
+out_ret:
rhashtable_walk_stop(rhiter);
return ret;
}
-static const struct genl_ops ila_nl_ops[] = {
- {
- .cmd = ILA_CMD_ADD,
- .doit = ila_nl_cmd_add_mapping,
- .policy = ila_nl_policy,
- .flags = GENL_ADMIN_PERM,
- },
- {
- .cmd = ILA_CMD_DEL,
- .doit = ila_nl_cmd_del_mapping,
- .policy = ila_nl_policy,
- .flags = GENL_ADMIN_PERM,
- },
- {
- .cmd = ILA_CMD_GET,
- .doit = ila_nl_cmd_get_mapping,
- .start = ila_nl_dump_start,
- .dumpit = ila_nl_dump,
- .done = ila_nl_dump_done,
- .policy = ila_nl_policy,
- },
-};
-
-static struct genl_family ila_nl_family __ro_after_init = {
- .hdrsize = 0,
- .name = ILA_GENL_NAME,
- .version = ILA_GENL_VERSION,
- .maxattr = ILA_ATTR_MAX,
- .netnsok = true,
- .parallel_ops = true,
- .module = THIS_MODULE,
- .ops = ila_nl_ops,
- .n_ops = ARRAY_SIZE(ila_nl_ops),
-};
-
#define ILA_HASH_TABLE_SIZE 1024
-static __net_init int ila_init_net(struct net *net)
+int ila_xlat_init_net(struct net *net)
{
- int err;
struct ila_net *ilan = net_generic(net, ila_net_id);
+ int err;
err = alloc_ila_locks(ilan);
if (err)
return err;
- rhashtable_init(&ilan->rhash_table, &rht_params);
+ rhashtable_init(&ilan->xlat.rhash_table, &rht_params);
return 0;
}
-static __net_exit void ila_exit_net(struct net *net)
+void ila_xlat_exit_net(struct net *net)
{
struct ila_net *ilan = net_generic(net, ila_net_id);
- rhashtable_free_and_destroy(&ilan->rhash_table, ila_free_cb, NULL);
+ rhashtable_free_and_destroy(&ilan->xlat.rhash_table, ila_free_cb, NULL);
- kvfree(ilan->locks);
+ free_bucket_spinlocks(ilan->xlat.locks);
- if (ilan->hooks_registered)
+ if (ilan->xlat.hooks_registered)
nf_unregister_net_hooks(net, ila_nf_hook_ops,
ARRAY_SIZE(ila_nf_hook_ops));
}
-static struct pernet_operations ila_net_ops = {
- .init = ila_init_net,
- .exit = ila_exit_net,
- .id = &ila_net_id,
- .size = sizeof(struct ila_net),
-};
-
static int ila_xlat_addr(struct sk_buff *skb, bool sir2ila)
{
struct ila_map *ila;
return 0;
}
-int __init ila_xlat_init(void)
-{
- int ret;
-
- ret = register_pernet_device(&ila_net_ops);
- if (ret)
- goto exit;
-
- ret = genl_register_family(&ila_nl_family);
- if (ret < 0)
- goto unregister;
-
- return 0;
-
-unregister:
- unregister_pernet_device(&ila_net_ops);
-exit:
- return ret;
-}
-
-void ila_xlat_fini(void)
-{
- genl_unregister_family(&ila_nl_family);
- unregister_pernet_device(&ila_net_ops);
-}
bool dev_match = (sk->sk_bound_dev_if == dif ||
sk->sk_bound_dev_if == sdif);
- if (exact_dif && !dev_match)
+ if (!dev_match)
return -1;
- if (sk->sk_bound_dev_if && dev_match)
+ if (sk->sk_bound_dev_if)
score++;
}
if (sk->sk_incoming_cpu == raw_smp_processor_id())
return f6i;
}
-void fib6_info_destroy(struct fib6_info *f6i)
+void fib6_info_destroy_rcu(struct rcu_head *head)
{
+ struct fib6_info *f6i = container_of(head, struct fib6_info, rcu);
struct rt6_exception_bucket *bucket;
struct dst_metrics *m;
kfree(f6i);
}
-EXPORT_SYMBOL_GPL(fib6_info_destroy);
+EXPORT_SYMBOL_GPL(fib6_info_destroy_rcu);
static struct fib6_node *node_alloc(struct net *net)
{
if (olen > 0) {
struct msghdr msg;
struct flowi6 flowi6;
- struct sockcm_cookie sockc_junk;
struct ipcm6_cookie ipc6;
err = -ENOMEM;
memset(&flowi6, 0, sizeof(flowi6));
ipc6.opt = fl->opt;
- err = ip6_datagram_send_ctl(net, sk, &msg, &flowi6, &ipc6, &sockc_junk);
+ err = ip6_datagram_send_ctl(net, sk, &msg, &flowi6, &ipc6);
if (err)
goto done;
err = -EINVAL;
fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
dsfield = key->tos;
+ if (!(tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT))
+ goto tx_err;
md = ip_tunnel_info_opts(tun_info);
if (!md)
goto tx_err;
#include <net/inet_ecn.h>
#include <net/dst_metadata.h>
-int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
+static void ip6_rcv_finish_core(struct net *net, struct sock *sk,
+ struct sk_buff *skb)
{
void (*edemux)(struct sk_buff *skb);
- /* if ingress device is enslaved to an L3 master device pass the
- * skb to its handler for processing
- */
- skb = l3mdev_ip6_rcv(skb);
- if (!skb)
- return NET_RX_SUCCESS;
-
if (net->ipv4.sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) {
const struct inet6_protocol *ipprot;
}
if (!skb_valid_dst(skb))
ip6_route_input(skb);
+}
+
+int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+ /* if ingress device is enslaved to an L3 master device pass the
+ * skb to its handler for processing
+ */
+ skb = l3mdev_ip6_rcv(skb);
+ if (!skb)
+ return NET_RX_SUCCESS;
+ ip6_rcv_finish_core(net, sk, skb);
return dst_input(skb);
}
-int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)
+static void ip6_sublist_rcv_finish(struct list_head *head)
+{
+ struct sk_buff *skb, *next;
+
+ list_for_each_entry_safe(skb, next, head, list)
+ dst_input(skb);
+}
+
+static void ip6_list_rcv_finish(struct net *net, struct sock *sk,
+ struct list_head *head)
+{
+ struct dst_entry *curr_dst = NULL;
+ struct sk_buff *skb, *next;
+ struct list_head sublist;
+
+ INIT_LIST_HEAD(&sublist);
+ list_for_each_entry_safe(skb, next, head, list) {
+ struct dst_entry *dst;
+
+ list_del(&skb->list);
+ /* if ingress device is enslaved to an L3 master device pass the
+ * skb to its handler for processing
+ */
+ skb = l3mdev_ip6_rcv(skb);
+ if (!skb)
+ continue;
+ ip6_rcv_finish_core(net, sk, skb);
+ dst = skb_dst(skb);
+ if (curr_dst != dst) {
+ /* dispatch old sublist */
+ if (!list_empty(&sublist))
+ ip6_sublist_rcv_finish(&sublist);
+ /* start new sublist */
+ INIT_LIST_HEAD(&sublist);
+ curr_dst = dst;
+ }
+ list_add_tail(&skb->list, &sublist);
+ }
+ /* dispatch final sublist */
+ ip6_sublist_rcv_finish(&sublist);
+}
+
+static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev,
+ struct net *net)
{
const struct ipv6hdr *hdr;
u32 pkt_len;
struct inet6_dev *idev;
- struct net *net = dev_net(skb->dev);
if (skb->pkt_type == PACKET_OTHERHOST) {
kfree_skb(skb);
- return NET_RX_DROP;
+ return NULL;
}
rcu_read_lock();
if (ipv6_parse_hopopts(skb) < 0) {
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
rcu_read_unlock();
- return NET_RX_DROP;
+ return NULL;
}
}
/* Must drop socket now because of tproxy. */
skb_orphan(skb);
- return NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING,
- net, NULL, skb, dev, NULL,
- ip6_rcv_finish);
+ return skb;
err:
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
drop:
rcu_read_unlock();
kfree_skb(skb);
- return NET_RX_DROP;
+ return NULL;
+}
+
+int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)
+{
+ struct net *net = dev_net(skb->dev);
+
+ skb = ip6_rcv_core(skb, dev, net);
+ if (skb == NULL)
+ return NET_RX_DROP;
+ return NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING,
+ net, NULL, skb, dev, NULL,
+ ip6_rcv_finish);
+}
+
+static void ip6_sublist_rcv(struct list_head *head, struct net_device *dev,
+ struct net *net)
+{
+ NF_HOOK_LIST(NFPROTO_IPV6, NF_INET_PRE_ROUTING, net, NULL,
+ head, dev, NULL, ip6_rcv_finish);
+ ip6_list_rcv_finish(net, NULL, head);
+}
+
+/* Receive a list of IPv6 packets */
+void ipv6_list_rcv(struct list_head *head, struct packet_type *pt,
+ struct net_device *orig_dev)
+{
+ struct net_device *curr_dev = NULL;
+ struct net *curr_net = NULL;
+ struct sk_buff *skb, *next;
+ struct list_head sublist;
+
+ INIT_LIST_HEAD(&sublist);
+ list_for_each_entry_safe(skb, next, head, list) {
+ struct net_device *dev = skb->dev;
+ struct net *net = dev_net(dev);
+
+ list_del(&skb->list);
+ skb = ip6_rcv_core(skb, dev, net);
+ if (skb == NULL)
+ continue;
+
+ if (curr_dev != dev || curr_net != net) {
+ /* dispatch old sublist */
+ if (!list_empty(&sublist))
+ ip6_sublist_rcv(&sublist, curr_dev, curr_net);
+ /* start new sublist */
+ INIT_LIST_HEAD(&sublist);
+ curr_dev = dev;
+ curr_net = net;
+ }
+ list_add_tail(&skb->list, &sublist);
+ }
+ /* dispatch final sublist */
+ ip6_sublist_rcv(&sublist, curr_dev, curr_net);
}
/*
return len;
}
-static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
- struct sk_buff *skb)
+static struct sk_buff *ipv6_gro_receive(struct list_head *head,
+ struct sk_buff *skb)
{
const struct net_offload *ops;
- struct sk_buff **pp = NULL;
+ struct sk_buff *pp = NULL;
struct sk_buff *p;
struct ipv6hdr *iph;
unsigned int nlen;
flush--;
nlen = skb_network_header_len(skb);
- for (p = *head; p; p = p->next) {
+ list_for_each_entry(p, head, list) {
const struct ipv6hdr *iph2;
__be32 first_word; /* <Version:4><Traffic_Class:8><Flow_Label:20> */
return pp;
}
-static struct sk_buff **sit_ip6ip6_gro_receive(struct sk_buff **head,
- struct sk_buff *skb)
+static struct sk_buff *sit_ip6ip6_gro_receive(struct list_head *head,
+ struct sk_buff *skb)
{
/* Common GRO receive for SIT and IP6IP6 */
return ipv6_gro_receive(head, skb);
}
-static struct sk_buff **ip4ip6_gro_receive(struct sk_buff **head,
- struct sk_buff *skb)
+static struct sk_buff *ip4ip6_gro_receive(struct list_head *head,
+ struct sk_buff *skb)
{
/* Common GRO receive for SIT and IP6IP6 */
if (mtu < IPV6_MIN_MTU)
return -EINVAL;
cork->base.fragsize = mtu;
- cork->base.gso_size = sk->sk_type == SOCK_DGRAM ? ipc6->gso_size : 0;
+ cork->base.gso_size = ipc6->gso_size;
+ cork->base.tx_flags = 0;
+ sock_tx_timestamp(sk, ipc6->sockc.tsflags, &cork->base.tx_flags);
if (dst_allfrag(xfrm_dst_path(&rt->dst)))
cork->base.flags |= IPCORK_ALLFRAG;
cork->base.length = 0;
+ cork->base.transmit_time = ipc6->sockc.transmit_time;
+
return 0;
}
int getfrag(void *from, char *to, int offset,
int len, int odd, struct sk_buff *skb),
void *from, int length, int transhdrlen,
- unsigned int flags, struct ipcm6_cookie *ipc6,
- const struct sockcm_cookie *sockc)
+ unsigned int flags, struct ipcm6_cookie *ipc6)
{
struct sk_buff *skb, *skb_prev = NULL;
unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu, pmtu;
int copy;
int err;
int offset = 0;
- __u8 tx_flags = 0;
u32 tskey = 0;
struct rt6_info *rt = (struct rt6_info *)cork->dst;
struct ipv6_txoptions *opt = v6_cork->opt;
mtu = cork->gso_size ? IP6_MAX_MTU : cork->fragsize;
orig_mtu = mtu;
+ if (cork->tx_flags & SKBTX_ANY_SW_TSTAMP &&
+ sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)
+ tskey = sk->sk_tskey++;
+
hh_len = LL_RESERVED_SPACE(rt->dst.dev);
fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len +
rt->dst.dev->features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM))
csummode = CHECKSUM_PARTIAL;
- if (sk->sk_type == SOCK_DGRAM || sk->sk_type == SOCK_RAW) {
- sock_tx_timestamp(sk, sockc->tsflags, &tx_flags);
- if (tx_flags & SKBTX_ANY_SW_TSTAMP &&
- sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)
- tskey = sk->sk_tskey++;
- }
-
/*
* Let's try using as much space as possible.
* Use MTU if total length of the message fits into the MTU.
dst_exthdrlen);
/* Only the initial fragment is time stamped */
- skb_shinfo(skb)->tx_flags = tx_flags;
- tx_flags = 0;
+ skb_shinfo(skb)->tx_flags = cork->tx_flags;
+ cork->tx_flags = 0;
skb_shinfo(skb)->tskey = tskey;
tskey = 0;
int odd, struct sk_buff *skb),
void *from, int length, int transhdrlen,
struct ipcm6_cookie *ipc6, struct flowi6 *fl6,
- struct rt6_info *rt, unsigned int flags,
- const struct sockcm_cookie *sockc)
+ struct rt6_info *rt, unsigned int flags)
{
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
return __ip6_append_data(sk, fl6, &sk->sk_write_queue, &inet->cork.base,
&np->cork, sk_page_frag(sk), getfrag,
- from, length, transhdrlen, flags, ipc6, sockc);
+ from, length, transhdrlen, flags, ipc6);
}
EXPORT_SYMBOL_GPL(ip6_append_data);
skb->priority = sk->sk_priority;
skb->mark = sk->sk_mark;
+ skb->tstamp = cork->base.transmit_time;
+
skb_dst_set(skb, dst_clone(&rt->dst));
IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len);
if (proto == IPPROTO_ICMPV6) {
void *from, int length, int transhdrlen,
struct ipcm6_cookie *ipc6, struct flowi6 *fl6,
struct rt6_info *rt, unsigned int flags,
- struct inet_cork_full *cork,
- const struct sockcm_cookie *sockc)
+ struct inet_cork_full *cork)
{
struct inet6_cork v6_cork;
struct sk_buff_head queue;
err = __ip6_append_data(sk, fl6, &queue, &cork->base, &v6_cork,
¤t->task_frag, getfrag, from,
length + exthdrlen, transhdrlen + exthdrlen,
- flags, ipc6, sockc);
+ flags, ipc6);
if (err) {
__ip6_flush_pending_frames(sk, &queue, cork, &v6_cork);
return ERR_PTR(err);
#include <linux/seq_file.h>
#include <linux/init.h>
#include <linux/compat.h>
+#include <linux/rhashtable.h>
#include <net/protocol.h>
#include <linux/skbuff.h>
#include <net/raw.h>
struct ipv6_txoptions *opt = NULL;
struct msghdr msg;
struct flowi6 fl6;
- struct sockcm_cookie sockc_junk;
struct ipcm6_cookie ipc6;
memset(&fl6, 0, sizeof(fl6));
msg.msg_control = (void *)(opt+1);
ipc6.opt = opt;
- retv = ip6_datagram_send_ctl(net, sk, &msg, &fl6, &ipc6, &sockc_junk);
+ retv = ip6_datagram_send_ctl(net, sk, &msg, &fl6, &ipc6);
if (retv)
goto done;
update:
mld_send_initial_cr(idev);
idev->mc_dad_count--;
if (idev->mc_dad_count)
- mld_dad_start_timer(idev, idev->mc_maxdelay);
+ mld_dad_start_timer(idev,
+ unsolicited_report_interval(idev));
}
}
if (idev->mc_dad_count) {
idev->mc_dad_count--;
if (idev->mc_dad_count)
- mld_dad_start_timer(idev, idev->mc_maxdelay);
+ mld_dad_start_timer(idev,
+ unsolicited_report_interval(idev));
}
in6_dev_put(idev);
}
if (idev->mc_ifc_count) {
idev->mc_ifc_count--;
if (idev->mc_ifc_count)
- mld_ifc_start_timer(idev, idev->mc_maxdelay);
+ mld_ifc_start_timer(idev,
+ unsolicited_report_interval(idev));
}
in6_dev_put(idev);
}
if (hdr == NULL)
goto err_reg;
- net->nf_frag.sysctl.frags_hdr = hdr;
+ net->nf_frag_frags_hdr = hdr;
return 0;
err_reg:
{
struct ctl_table *table;
- table = net->nf_frag.sysctl.frags_hdr->ctl_table_arg;
- unregister_net_sysctl_table(net->nf_frag.sysctl.frags_hdr);
+ table = net->nf_frag_frags_hdr->ctl_table_arg;
+ unregister_net_sysctl_table(net->nf_frag_frags_hdr);
if (!net_eq(net, &init_net))
kfree(table);
}
};
/* One level of recursion won't kill us */
-static void dump_ipv6_packet(struct nf_log_buf *m,
+static void dump_ipv6_packet(struct net *net, struct nf_log_buf *m,
const struct nf_loginfo *info,
const struct sk_buff *skb, unsigned int ip6hoff,
int recurse)
/* Max length: 3+maxlen */
if (recurse) {
nf_log_buf_add(m, "[");
- dump_ipv6_packet(m, info, skb,
+ dump_ipv6_packet(net, m, info, skb,
ptr + sizeof(_icmp6h), 0);
nf_log_buf_add(m, "] ");
}
/* Max length: 15 "UID=4294967295 " */
if ((logflags & NF_LOG_UID) && recurse)
- nf_log_dump_sk_uid_gid(m, skb->sk);
+ nf_log_dump_sk_uid_gid(net, m, skb->sk);
/* Max length: 16 "MARK=0xFFFFFFFF " */
if (recurse && skb->mark)
if (in != NULL)
dump_ipv6_mac_header(m, loginfo, skb);
- dump_ipv6_packet(m, loginfo, skb, skb_network_offset(skb), 1);
+ dump_ipv6_packet(net, m, loginfo, skb, skb_network_offset(skb), 1);
nf_log_buf_close(m);
}
struct dst_entry *dst;
struct rt6_info *rt;
struct pingfakehdr pfh;
- struct sockcm_cookie junk = {0};
struct ipcm6_cookie ipc6;
pr_debug("ping_v6_sendmsg(sk=%p,sk->num=%u)\n", inet, inet->inet_num);
fl6.fl6_icmp_code = user_icmph.icmp6_code;
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
- ipc6.tclass = np->tclass;
+ ipcm6_init_sk(&ipc6, np);
fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
dst = ip6_sk_dst_lookup_flow(sk, &fl6, daddr, false);
pfh.family = AF_INET6;
ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
- ipc6.dontfrag = np->dontfrag;
- ipc6.opt = NULL;
lock_sock(sk);
err = ip6_append_data(sk, ping_getfrag, &pfh, len,
0, &ipc6, &fl6, rt,
- MSG_DONTWAIT, &junk);
+ MSG_DONTWAIT);
if (err) {
ICMP6_INC_STATS(sock_net(sk), rt->rt6i_idev,
static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length,
struct flowi6 *fl6, struct dst_entry **dstp,
- unsigned int flags)
+ unsigned int flags, const struct sockcm_cookie *sockc)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct net *net = sock_net(sk);
skb->protocol = htons(ETH_P_IPV6);
skb->priority = sk->sk_priority;
skb->mark = sk->sk_mark;
+ skb->tstamp = sockc->transmit_time;
skb_dst_set(skb, &rt->dst);
*dstp = NULL;
struct dst_entry *dst = NULL;
struct raw6_frag_vec rfv;
struct flowi6 fl6;
- struct sockcm_cookie sockc;
struct ipcm6_cookie ipc6;
int addr_len = msg->msg_namelen;
u16 proto;
fl6.flowi6_mark = sk->sk_mark;
fl6.flowi6_uid = sk->sk_uid;
- ipc6.hlimit = -1;
- ipc6.tclass = -1;
- ipc6.dontfrag = -1;
- ipc6.opt = NULL;
+ ipcm6_init(&ipc6);
+ ipc6.sockc.tsflags = sk->sk_tsflags;
if (sin6) {
if (addr_len < SIN6_LEN_RFC2133)
if (fl6.flowi6_oif == 0)
fl6.flowi6_oif = sk->sk_bound_dev_if;
- sockc.tsflags = sk->sk_tsflags;
if (msg->msg_controllen) {
opt = &opt_space;
memset(opt, 0, sizeof(struct ipv6_txoptions));
opt->tot_len = sizeof(struct ipv6_txoptions);
ipc6.opt = opt;
- err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, &ipc6, &sockc);
+ err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, &ipc6);
if (err < 0) {
fl6_sock_release(flowlabel);
return err;
back_from_confirm:
if (inet->hdrincl)
- err = rawv6_send_hdrinc(sk, msg, len, &fl6, &dst, msg->msg_flags);
+ err = rawv6_send_hdrinc(sk, msg, len, &fl6, &dst,
+ msg->msg_flags, &ipc6.sockc);
else {
ipc6.opt = opt;
lock_sock(sk);
err = ip6_append_data(sk, raw6_getfrag, &rfv,
len, 0, &ipc6, &fl6, (struct rt6_info *)dst,
- msg->msg_flags, &sockc);
+ msg->msg_flags);
if (err)
ip6_flush_pending_frames(sk);
}
#endif /* CONFIG_PROC_FS */
-/* Same as inet6_dgram_ops, sans udp_poll_mask. */
+/* Same as inet6_dgram_ops, sans udp_poll. */
const struct proto_ops inet6_sockraw_ops = {
.family = PF_INET6,
.owner = THIS_MODULE,
.socketpair = sock_no_socketpair, /* a do nothing */
.accept = sock_no_accept, /* a do nothing */
.getname = inet6_getname,
- .poll_mask = datagram_poll_mask, /* ok */
+ .poll = datagram_poll, /* ok */
.ioctl = inet6_ioctl, /* must change */
.listen = sock_no_listen, /* ok */
.shutdown = inet_shutdown, /* ok */
#include <linux/net.h>
#include <linux/in6.h>
#include <linux/slab.h>
+#include <linux/rhashtable.h>
#include <net/ipv6.h>
#include <net/protocol.h>
#include <linux/icmpv6.h>
#include <linux/mroute6.h>
#include <linux/slab.h>
+#include <linux/rhashtable.h>
#include <linux/netfilter.h>
#include <linux/netfilter_ipv6.h>
return -ENOMEM;
for_each_possible_cpu(cpu) {
- tfm = crypto_alloc_shash(algo->name, 0, GFP_KERNEL);
+ tfm = crypto_alloc_shash(algo->name, 0, 0);
if (IS_ERR(tfm))
return PTR_ERR(tfm);
p_tfm = per_cpu_ptr(algo->tfms, cpu);
#include <net/ip6_checksum.h>
#include "ip6_offload.h"
-static struct sk_buff **tcp6_gro_receive(struct sk_buff **head,
- struct sk_buff *skb)
+static struct sk_buff *tcp6_gro_receive(struct list_head *head,
+ struct sk_buff *skb)
{
/* Don't bother verifying checksum if we're going to flush anyway. */
if (!NAPI_GRO_CB(skb)->flush &&
int err;
int is_udplite = IS_UDPLITE(sk);
int (*getfrag)(void *, char *, int, int, int, struct sk_buff *);
- struct sockcm_cookie sockc;
- ipc6.hlimit = -1;
- ipc6.tclass = -1;
- ipc6.dontfrag = -1;
+ ipcm6_init(&ipc6);
ipc6.gso_size = up->gso_size;
- sockc.tsflags = sk->sk_tsflags;
+ ipc6.sockc.tsflags = sk->sk_tsflags;
/* destination address check */
if (sin6) {
err = udp_cmsg_send(sk, msg, &ipc6.gso_size);
if (err > 0)
err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6,
- &ipc6, &sockc);
+ &ipc6);
if (err < 0) {
fl6_sock_release(flowlabel);
return err;
skb = ip6_make_skb(sk, getfrag, msg, ulen,
sizeof(struct udphdr), &ipc6,
&fl6, (struct rt6_info *)dst,
- msg->msg_flags, &cork, &sockc);
+ msg->msg_flags, &cork);
err = PTR_ERR(skb);
if (!IS_ERR_OR_NULL(skb))
err = udp_v6_send_skb(skb, &fl6, &cork.base);
up->len += ulen;
err = ip6_append_data(sk, getfrag, msg, ulen, sizeof(struct udphdr),
&ipc6, &fl6, (struct rt6_info *)dst,
- corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags, &sockc);
+ corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags);
if (err)
udp_v6_flush_pending_frames(sk);
else if (!corkreq)
return segs;
}
-static struct sk_buff **udp6_gro_receive(struct sk_buff **head,
- struct sk_buff *skb)
+static struct sk_buff *udp6_gro_receive(struct list_head *head,
+ struct sk_buff *skb)
{
struct udphdr *uh = udp_gro_udphdr(skb);
return 0;
}
-static __poll_t iucv_sock_poll_mask(struct socket *sock, __poll_t events)
+__poll_t iucv_sock_poll(struct file *file, struct socket *sock,
+ poll_table *wait)
{
struct sock *sk = sock->sk;
__poll_t mask = 0;
+ sock_poll_wait(file, sk_sleep(sk), wait);
+
if (sk->sk_state == IUCV_LISTEN)
return iucv_accept_poll(sk);
.getname = iucv_sock_getname,
.sendmsg = iucv_sock_sendmsg,
.recvmsg = iucv_sock_recvmsg,
- .poll_mask = iucv_sock_poll_mask,
+ .poll = iucv_sock_poll,
.ioctl = sock_no_ioctl,
.mmap = sock_no_mmap,
.socketpair = sock_no_socketpair,
struct list_head *head;
int index = 0;
- /* For SOCK_SEQPACKET sock type, datagram_poll_mask checks the sk_state,
- * so we set sk_state, otherwise epoll_wait always returns right away
- * with EPOLLHUP
+ /* For SOCK_SEQPACKET sock type, datagram_poll checks the sk_state, so
+ * we set sk_state, otherwise epoll_wait always returns right away with
+ * EPOLLHUP
*/
kcm->sk.sk_state = TCP_ESTABLISHED;
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = sock_no_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.ioctl = kcm_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = sock_no_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.ioctl = kcm_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
/* Now the operations that really occur. */
.release = pfkey_release,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.sendmsg = pfkey_sendmsg,
.recvmsg = pfkey_recvmsg,
};
if (tunnel->version == L2TP_HDR_VER_3) {
pn = l2tp_pernet(tunnel->l2tp_net);
- g_head = l2tp_session_id_hash_2(l2tp_pernet(tunnel->l2tp_net),
- session->session_id);
+ g_head = l2tp_session_id_hash_2(pn, session->session_id);
spin_lock_bh(&pn->l2tp_session_hlist_lock);
/* Drop skbs from the session's reorder_q
*/
-int l2tp_session_queue_purge(struct l2tp_session *session)
+static int l2tp_session_queue_purge(struct l2tp_session *session)
{
struct sk_buff *skb = NULL;
BUG_ON(!session);
}
return 0;
}
-EXPORT_SYMBOL_GPL(l2tp_session_queue_purge);
/* Internal UDP receive frame. Do the real work of receiving an L2TP data frame
* here. The skb is not on a list when we get here.
return bufp - optr;
}
-static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb,
- struct flowi *fl, size_t data_len)
+static void l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb,
+ struct flowi *fl, size_t data_len)
{
struct l2tp_tunnel *tunnel = session->tunnel;
unsigned int len = skb->len;
atomic_long_inc(&tunnel->stats.tx_errors);
atomic_long_inc(&session->stats.tx_errors);
}
-
- return 0;
}
/* If caller requires the skb to have a ppp header, the header must be
/* When the tunnel is closed, all the attached sessions need to go too.
*/
-void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel)
+static void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel)
{
int hash;
struct hlist_node *walk;
}
write_unlock_bh(&tunnel->hlist_lock);
}
-EXPORT_SYMBOL_GPL(l2tp_tunnel_closeall);
/* Tunnel socket destroy hook for UDP encapsulation */
static void l2tp_udp_encap_destroy(struct sock *sk)
struct net *l2tp_net; /* the net we belong to */
refcount_t ref_count;
-#ifdef CONFIG_DEBUG_FS
- void (*show)(struct seq_file *m, void *arg);
-#endif
int (*recv_payload_hook)(struct sk_buff *skb);
void (*old_sk_destruct)(struct sock *);
struct sock *sock; /* Parent socket */
* was created by userspace */
struct work_struct del_work;
-
- uint8_t priv[0]; /* private data */
};
struct l2tp_nl_cmd_ops {
int (*session_delete)(struct l2tp_session *session);
};
-static inline void *l2tp_tunnel_priv(struct l2tp_tunnel *tunnel)
-{
- return &tunnel->priv[0];
-}
-
static inline void *l2tp_session_priv(struct l2tp_session *session)
{
return &session->priv[0];
int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
struct l2tp_tunnel_cfg *cfg);
-void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel);
void l2tp_tunnel_delete(struct l2tp_tunnel *tunnel);
struct l2tp_session *l2tp_session_create(int priv_size,
struct l2tp_tunnel *tunnel,
void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
unsigned char *ptr, unsigned char *optr, u16 hdrflags,
int length, int (*payload_hook)(struct sk_buff *skb));
-int l2tp_session_queue_purge(struct l2tp_session *session);
int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb);
void l2tp_session_set_header_len(struct l2tp_session *session, int version);
atomic_long_read(&tunnel->stats.rx_packets),
atomic_long_read(&tunnel->stats.rx_bytes),
atomic_long_read(&tunnel->stats.rx_errors));
-
- if (tunnel->show != NULL)
- tunnel->show(m, tunnel);
}
static void l2tp_dfs_seq_session_show(struct seq_file *m, void *v)
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = l2tp_ip_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.ioctl = inet_ioctl,
.listen = sock_no_listen,
.shutdown = inet_shutdown,
struct ip6_flowlabel *flowlabel = NULL;
struct dst_entry *dst = NULL;
struct flowi6 fl6;
- struct sockcm_cookie sockc_unused = {0};
struct ipcm6_cookie ipc6;
int addr_len = msg->msg_namelen;
int transhdrlen = 4; /* zero session-id */
fl6.flowi6_mark = sk->sk_mark;
fl6.flowi6_uid = sk->sk_uid;
- ipc6.hlimit = -1;
- ipc6.tclass = -1;
- ipc6.dontfrag = -1;
+ ipcm6_init(&ipc6);
if (lsa) {
if (addr_len < SIN6_LEN_RFC2133)
opt->tot_len = sizeof(struct ipv6_txoptions);
ipc6.opt = opt;
- err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, &ipc6,
- &sockc_unused);
+ err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, &ipc6);
if (err < 0) {
fl6_sock_release(flowlabel);
return err;
err = ip6_append_data(sk, ip_generic_getfrag, msg,
ulen, transhdrlen, &ipc6,
&fl6, (struct rt6_info *)dst,
- msg->msg_flags, &sockc_unused);
+ msg->msg_flags);
if (err)
ip6_flush_pending_frames(sk);
else if (!(msg->msg_flags & MSG_MORE))
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = l2tp_ip6_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.ioctl = inet6_ioctl,
.listen = sock_no_listen,
.shutdown = inet_shutdown,
sock_put(ps->__sk);
}
-/* Called by l2tp_core when a session socket is being closed.
- */
-static void pppol2tp_session_close(struct l2tp_session *session)
-{
-}
-
/* Really kill the session socket. (Called from sock_put() if
* refcnt == 0.)
*/
struct dst_entry *dst;
session->recv_skb = pppol2tp_recv;
- session->session_close = pppol2tp_session_close;
#if IS_ENABLED(CONFIG_L2TP_DEBUGFS)
session->show = pppol2tp_show;
#endif
}
}
+struct l2tp_connect_info {
+ u8 version;
+ int fd;
+ u32 tunnel_id;
+ u32 peer_tunnel_id;
+ u32 session_id;
+ u32 peer_session_id;
+};
+
+static int pppol2tp_sockaddr_get_info(const void *sa, int sa_len,
+ struct l2tp_connect_info *info)
+{
+ switch (sa_len) {
+ case sizeof(struct sockaddr_pppol2tp):
+ {
+ const struct sockaddr_pppol2tp *sa_v2in4 = sa;
+
+ if (sa_v2in4->sa_protocol != PX_PROTO_OL2TP)
+ return -EINVAL;
+
+ info->version = 2;
+ info->fd = sa_v2in4->pppol2tp.fd;
+ info->tunnel_id = sa_v2in4->pppol2tp.s_tunnel;
+ info->peer_tunnel_id = sa_v2in4->pppol2tp.d_tunnel;
+ info->session_id = sa_v2in4->pppol2tp.s_session;
+ info->peer_session_id = sa_v2in4->pppol2tp.d_session;
+
+ break;
+ }
+ case sizeof(struct sockaddr_pppol2tpv3):
+ {
+ const struct sockaddr_pppol2tpv3 *sa_v3in4 = sa;
+
+ if (sa_v3in4->sa_protocol != PX_PROTO_OL2TP)
+ return -EINVAL;
+
+ info->version = 3;
+ info->fd = sa_v3in4->pppol2tp.fd;
+ info->tunnel_id = sa_v3in4->pppol2tp.s_tunnel;
+ info->peer_tunnel_id = sa_v3in4->pppol2tp.d_tunnel;
+ info->session_id = sa_v3in4->pppol2tp.s_session;
+ info->peer_session_id = sa_v3in4->pppol2tp.d_session;
+
+ break;
+ }
+ case sizeof(struct sockaddr_pppol2tpin6):
+ {
+ const struct sockaddr_pppol2tpin6 *sa_v2in6 = sa;
+
+ if (sa_v2in6->sa_protocol != PX_PROTO_OL2TP)
+ return -EINVAL;
+
+ info->version = 2;
+ info->fd = sa_v2in6->pppol2tp.fd;
+ info->tunnel_id = sa_v2in6->pppol2tp.s_tunnel;
+ info->peer_tunnel_id = sa_v2in6->pppol2tp.d_tunnel;
+ info->session_id = sa_v2in6->pppol2tp.s_session;
+ info->peer_session_id = sa_v2in6->pppol2tp.d_session;
+
+ break;
+ }
+ case sizeof(struct sockaddr_pppol2tpv3in6):
+ {
+ const struct sockaddr_pppol2tpv3in6 *sa_v3in6 = sa;
+
+ if (sa_v3in6->sa_protocol != PX_PROTO_OL2TP)
+ return -EINVAL;
+
+ info->version = 3;
+ info->fd = sa_v3in6->pppol2tp.fd;
+ info->tunnel_id = sa_v3in6->pppol2tp.s_tunnel;
+ info->peer_tunnel_id = sa_v3in6->pppol2tp.d_tunnel;
+ info->session_id = sa_v3in6->pppol2tp.s_session;
+ info->peer_session_id = sa_v3in6->pppol2tp.d_session;
+
+ break;
+ }
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
/* connect() handler. Attach a PPPoX socket to a tunnel UDP socket
*/
static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
int sockaddr_len, int flags)
{
struct sock *sk = sock->sk;
- struct sockaddr_pppol2tp *sp = (struct sockaddr_pppol2tp *) uservaddr;
struct pppox_sock *po = pppox_sk(sk);
struct l2tp_session *session = NULL;
+ struct l2tp_connect_info info;
struct l2tp_tunnel *tunnel;
struct pppol2tp_session *ps;
struct l2tp_session_cfg cfg = { 0, };
- int error = 0;
- u32 tunnel_id, peer_tunnel_id;
- u32 session_id, peer_session_id;
bool drop_refcnt = false;
bool drop_tunnel = false;
bool new_session = false;
bool new_tunnel = false;
- int ver = 2;
- int fd;
-
- lock_sock(sk);
-
- error = -EINVAL;
+ int error;
- if (sockaddr_len != sizeof(struct sockaddr_pppol2tp) &&
- sockaddr_len != sizeof(struct sockaddr_pppol2tpv3) &&
- sockaddr_len != sizeof(struct sockaddr_pppol2tpin6) &&
- sockaddr_len != sizeof(struct sockaddr_pppol2tpv3in6))
- goto end;
+ error = pppol2tp_sockaddr_get_info(uservaddr, sockaddr_len, &info);
+ if (error < 0)
+ return error;
- if (sp->sa_protocol != PX_PROTO_OL2TP)
- goto end;
+ lock_sock(sk);
/* Check for already bound sockets */
error = -EBUSY;
if (sk->sk_user_data)
goto end; /* socket is already attached */
- /* Get params from socket address. Handle L2TPv2 and L2TPv3.
- * This is nasty because there are different sockaddr_pppol2tp
- * structs for L2TPv2, L2TPv3, over IPv4 and IPv6. We use
- * the sockaddr size to determine which structure the caller
- * is using.
- */
- peer_tunnel_id = 0;
- if (sockaddr_len == sizeof(struct sockaddr_pppol2tp)) {
- fd = sp->pppol2tp.fd;
- tunnel_id = sp->pppol2tp.s_tunnel;
- peer_tunnel_id = sp->pppol2tp.d_tunnel;
- session_id = sp->pppol2tp.s_session;
- peer_session_id = sp->pppol2tp.d_session;
- } else if (sockaddr_len == sizeof(struct sockaddr_pppol2tpv3)) {
- struct sockaddr_pppol2tpv3 *sp3 =
- (struct sockaddr_pppol2tpv3 *) sp;
- ver = 3;
- fd = sp3->pppol2tp.fd;
- tunnel_id = sp3->pppol2tp.s_tunnel;
- peer_tunnel_id = sp3->pppol2tp.d_tunnel;
- session_id = sp3->pppol2tp.s_session;
- peer_session_id = sp3->pppol2tp.d_session;
- } else if (sockaddr_len == sizeof(struct sockaddr_pppol2tpin6)) {
- struct sockaddr_pppol2tpin6 *sp6 =
- (struct sockaddr_pppol2tpin6 *) sp;
- fd = sp6->pppol2tp.fd;
- tunnel_id = sp6->pppol2tp.s_tunnel;
- peer_tunnel_id = sp6->pppol2tp.d_tunnel;
- session_id = sp6->pppol2tp.s_session;
- peer_session_id = sp6->pppol2tp.d_session;
- } else if (sockaddr_len == sizeof(struct sockaddr_pppol2tpv3in6)) {
- struct sockaddr_pppol2tpv3in6 *sp6 =
- (struct sockaddr_pppol2tpv3in6 *) sp;
- ver = 3;
- fd = sp6->pppol2tp.fd;
- tunnel_id = sp6->pppol2tp.s_tunnel;
- peer_tunnel_id = sp6->pppol2tp.d_tunnel;
- session_id = sp6->pppol2tp.s_session;
- peer_session_id = sp6->pppol2tp.d_session;
- } else {
- error = -EINVAL;
- goto end; /* bad socket address */
- }
-
/* Don't bind if tunnel_id is 0 */
error = -EINVAL;
- if (tunnel_id == 0)
+ if (!info.tunnel_id)
goto end;
- tunnel = l2tp_tunnel_get(sock_net(sk), tunnel_id);
+ tunnel = l2tp_tunnel_get(sock_net(sk), info.tunnel_id);
if (tunnel)
drop_tunnel = true;
* peer_session_id is 0. Otherwise look up tunnel using supplied
* tunnel id.
*/
- if ((session_id == 0) && (peer_session_id == 0)) {
+ if (!info.session_id && !info.peer_session_id) {
if (tunnel == NULL) {
struct l2tp_tunnel_cfg tcfg = {
.encap = L2TP_ENCAPTYPE_UDP,
/* Prevent l2tp_tunnel_register() from trying to set up
* a kernel socket.
*/
- if (fd < 0) {
+ if (info.fd < 0) {
error = -EBADF;
goto end;
}
- error = l2tp_tunnel_create(sock_net(sk), fd, ver, tunnel_id, peer_tunnel_id, &tcfg, &tunnel);
+ error = l2tp_tunnel_create(sock_net(sk), info.fd,
+ info.version,
+ info.tunnel_id,
+ info.peer_tunnel_id, &tcfg,
+ &tunnel);
if (error < 0)
goto end;
tunnel->recv_payload_hook = pppol2tp_recv_payload_hook;
if (tunnel->peer_tunnel_id == 0)
- tunnel->peer_tunnel_id = peer_tunnel_id;
+ tunnel->peer_tunnel_id = info.peer_tunnel_id;
- session = l2tp_session_get(sock_net(sk), tunnel, session_id);
+ session = l2tp_session_get(sock_net(sk), tunnel, info.session_id);
if (session) {
drop_refcnt = true;
cfg.pw_type = L2TP_PWTYPE_PPP;
session = l2tp_session_create(sizeof(struct pppol2tp_session),
- tunnel, session_id,
- peer_session_id, &cfg);
+ tunnel, info.session_id,
+ info.peer_session_id, &cfg);
if (IS_ERR(session)) {
error = PTR_ERR(session);
goto end;
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = pppol2tp_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.setsockopt = pppol2tp_setsockopt,
.socketpair = sock_no_socketpair,
.accept = llc_ui_accept,
.getname = llc_ui_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.ioctl = llc_ui_ioctl,
.listen = llc_ui_listen,
.shutdown = llc_ui_shutdown,
scan.o offchannel.o \
ht.o agg-tx.o agg-rx.o \
vht.o \
+ he.o \
ibss.o \
iface.o \
rate.o \
};
int i, ret = -EOPNOTSUPP;
u16 status = WLAN_STATUS_REQUEST_DECLINED;
+ u16 max_buf_size;
if (tid >= IEEE80211_FIRST_TSPEC_TSID) {
ht_dbg(sta->sdata,
goto end;
}
+ if (sta->sta.he_cap.has_he)
+ max_buf_size = IEEE80211_MAX_AMPDU_BUF;
+ else
+ max_buf_size = IEEE80211_MAX_AMPDU_BUF_HT;
+
/* sanity check for incoming parameters:
* check if configuration can support the BA policy
* and if buffer size does not exceeds max value */
/* XXX: check own ht delayed BA capability?? */
if (((ba_policy != 1) &&
(!(sta->sta.ht_cap.cap & IEEE80211_HT_CAP_DELAY_BA))) ||
- (buf_size > IEEE80211_MAX_AMPDU_BUF)) {
+ (buf_size > max_buf_size)) {
status = WLAN_STATUS_INVALID_QOS_PARAM;
ht_dbg_ratelimited(sta->sdata,
"AddBA Req with bad params from %pM on tid %u. policy %d, buffer size %d\n",
}
/* determine default buffer size */
if (buf_size == 0)
- buf_size = IEEE80211_MAX_AMPDU_BUF;
+ buf_size = max_buf_size;
/* make sure the size doesn't exceed the maximum supported by the hw */
if (buf_size > sta->sta.max_rx_aggregation_subframes)
.timeout = 0,
};
int ret;
+ u16 buf_size;
tid_tx = rcu_dereference_protected_tid_tx(sta, tid);
sta->ampdu_mlme.addba_req_num[tid]++;
spin_unlock_bh(&sta->lock);
+ if (sta->sta.he_cap.has_he) {
+ buf_size = local->hw.max_tx_aggregation_subframes;
+ } else {
+ /*
+ * We really should use what the driver told us it will
+ * transmit as the maximum, but certain APs (e.g. the
+ * LinkSys WRT120N with FW v1.0.07 build 002 Jun 18 2012)
+ * will crash when we use a lower number.
+ */
+ buf_size = IEEE80211_MAX_AMPDU_BUF_HT;
+ }
+
/* send AddBA request */
ieee80211_send_addba_request(sdata, sta->sta.addr, tid,
tid_tx->dialog_token, params.ssn,
- IEEE80211_MAX_AMPDU_BUF,
- tid_tx->timeout);
+ buf_size, tid_tx->timeout);
}
/*
{
struct tid_ampdu_tx *tid_tx;
struct ieee80211_txq *txq;
- u16 capab, tid;
- u8 buf_size;
+ u16 capab, tid, buf_size;
bool amsdu;
capab = le16_to_cpu(mgmt->u.action.u.addba_resp.capab);
ieee80211_vht_cap_ie_to_sta_vht_cap(sdata, sband,
params->vht_capa, sta);
+ if (params->he_capa)
+ ieee80211_he_cap_ie_to_sta_he_cap(sdata, sband,
+ (void *)params->he_capa,
+ params->he_capa_len, sta);
+
if (params->opmode_notif_used) {
/* returned value is only needed for rc update, but the
* rc isn't initialized here yet, so ignore it
}
local_bh_disable();
- ieee80211_xmit(sdata, sta, skb);
+ ieee80211_xmit(sdata, sta, skb, 0);
local_bh_enable();
ret = 0;
data[i++] = sta->sta_state;
- if (sinfo.filled & BIT(NL80211_STA_INFO_TX_BITRATE))
+ if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_TX_BITRATE))
data[i] = 100000ULL *
cfg80211_calculate_bitrate(&sinfo.txrate);
i++;
- if (sinfo.filled & BIT(NL80211_STA_INFO_RX_BITRATE))
+ if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_RX_BITRATE))
data[i] = 100000ULL *
cfg80211_calculate_bitrate(&sinfo.rxrate);
i++;
- if (sinfo.filled & BIT(NL80211_STA_INFO_SIGNAL_AVG))
+ if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_SIGNAL_AVG))
data[i] = (u8)sinfo.signal_avg;
i++;
} else {
--- /dev/null
+/*
+ * HE handling
+ *
+ * Copyright(c) 2017 Intel Deutschland GmbH
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "ieee80211_i.h"
+
+void
+ieee80211_he_cap_ie_to_sta_he_cap(struct ieee80211_sub_if_data *sdata,
+ struct ieee80211_supported_band *sband,
+ const u8 *he_cap_ie, u8 he_cap_len,
+ struct sta_info *sta)
+{
+ struct ieee80211_sta_he_cap *he_cap = &sta->sta.he_cap;
+ struct ieee80211_he_cap_elem *he_cap_ie_elem = (void *)he_cap_ie;
+ u8 he_ppe_size;
+ u8 mcs_nss_size;
+ u8 he_total_size;
+
+ memset(he_cap, 0, sizeof(*he_cap));
+
+ if (!he_cap_ie || !ieee80211_get_he_sta_cap(sband))
+ return;
+
+ /* Make sure size is OK */
+ mcs_nss_size = ieee80211_he_mcs_nss_size(he_cap_ie_elem);
+ he_ppe_size =
+ ieee80211_he_ppe_size(he_cap_ie[sizeof(he_cap->he_cap_elem) +
+ mcs_nss_size],
+ he_cap_ie_elem->phy_cap_info);
+ he_total_size = sizeof(he_cap->he_cap_elem) + mcs_nss_size +
+ he_ppe_size;
+ if (he_cap_len < he_total_size)
+ return;
+
+ memcpy(&he_cap->he_cap_elem, he_cap_ie, sizeof(he_cap->he_cap_elem));
+
+ /* HE Tx/Rx HE MCS NSS Support Field */
+ memcpy(&he_cap->he_mcs_nss_supp,
+ &he_cap_ie[sizeof(he_cap->he_cap_elem)], mcs_nss_size);
+
+ /* Check if there are (optional) PPE Thresholds */
+ if (he_cap->he_cap_elem.phy_cap_info[6] &
+ IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT)
+ memcpy(he_cap->ppe_thres,
+ &he_cap_ie[sizeof(he_cap->he_cap_elem) + mcs_nss_size],
+ he_ppe_size);
+
+ he_cap->has_he = true;
+}
test_and_clear_bit(tid,
sta->ampdu_mlme.tid_rx_manage_offl))
___ieee80211_start_rx_ba_session(sta, 0, 0, 0, 1, tid,
- IEEE80211_MAX_AMPDU_BUF,
+ IEEE80211_MAX_AMPDU_BUF_HT,
false, true);
if (test_and_clear_bit(tid + IEEE80211_NUM_TIDS,
#define TX_DROP ((__force ieee80211_tx_result) 1u)
#define TX_QUEUED ((__force ieee80211_tx_result) 2u)
+#define IEEE80211_TX_NO_SEQNO BIT(0)
#define IEEE80211_TX_UNICAST BIT(1)
#define IEEE80211_TX_PS_BUFFERED BIT(2)
IEEE80211_STA_DISABLE_160MHZ = BIT(13),
IEEE80211_STA_DISABLE_WMM = BIT(14),
IEEE80211_STA_ENABLE_RRM = BIT(15),
+ IEEE80211_STA_DISABLE_HE = BIT(16),
};
struct ieee80211_mgd_auth_data {
const struct ieee80211_vht_cap *vht_cap_elem;
const struct ieee80211_vht_operation *vht_operation;
const struct ieee80211_meshconf_ie *mesh_config;
+ const u8 *he_cap;
+ const struct ieee80211_he_operation *he_operation;
+ const struct ieee80211_mu_edca_param_set *mu_edca_param_set;
+ const u8 *uora_element;
const u8 *mesh_id;
const u8 *peering;
const __le16 *awake_window;
u8 ext_supp_rates_len;
u8 wmm_info_len;
u8 wmm_param_len;
+ u8 he_cap_len;
u8 mesh_id_len;
u8 peering_len;
u8 preq_len;
enum nl80211_chan_width
ieee80211_sta_rx_bw_to_chan_width(struct sta_info *sta);
+/* HE */
+void
+ieee80211_he_cap_ie_to_sta_he_cap(struct ieee80211_sub_if_data *sdata,
+ struct ieee80211_supported_band *sband,
+ const u8 *he_cap_ie, u8 he_cap_len,
+ struct sta_info *sta);
+
/* Spectrum management */
void ieee80211_process_measurement_req(struct ieee80211_sub_if_data *sdata,
struct ieee80211_mgmt *mgmt,
void ieee80211_set_wmm_default(struct ieee80211_sub_if_data *sdata,
bool bss_notify, bool enable_qos);
void ieee80211_xmit(struct ieee80211_sub_if_data *sdata,
- struct sta_info *sta, struct sk_buff *skb);
+ struct sta_info *sta, struct sk_buff *skb,
+ u32 txdata_flags);
void __ieee80211_tx_skb_tid_band(struct ieee80211_sub_if_data *sdata,
struct sk_buff *skb, int tid,
- enum nl80211_band band);
+ enum nl80211_band band, u32 txdata_flags);
static inline void
ieee80211_tx_skb_tid_band(struct ieee80211_sub_if_data *sdata,
struct sk_buff *skb, int tid,
- enum nl80211_band band)
+ enum nl80211_band band, u32 txdata_flags)
{
rcu_read_lock();
- __ieee80211_tx_skb_tid_band(sdata, skb, tid, band);
+ __ieee80211_tx_skb_tid_band(sdata, skb, tid, band, txdata_flags);
rcu_read_unlock();
}
}
__ieee80211_tx_skb_tid_band(sdata, skb, tid,
- chanctx_conf->def.chan->band);
+ chanctx_conf->def.chan->band, 0);
rcu_read_unlock();
}
void ieee80211_send_deauth_disassoc(struct ieee80211_sub_if_data *sdata,
const u8 *bssid, u16 stype, u16 reason,
bool send_frame, u8 *frame_buf);
+
+enum {
+ IEEE80211_PROBE_FLAG_DIRECTED = BIT(0),
+ IEEE80211_PROBE_FLAG_MIN_CONTENT = BIT(1),
+ IEEE80211_PROBE_FLAG_RANDOM_SN = BIT(2),
+};
+
int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer,
size_t buffer_len,
struct ieee80211_scan_ies *ie_desc,
const u8 *ie, size_t ie_len,
u8 bands_used, u32 *rate_masks,
- struct cfg80211_chan_def *chandef);
+ struct cfg80211_chan_def *chandef,
+ u32 flags);
struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata,
const u8 *src, const u8 *dst,
u32 ratemask,
struct ieee80211_channel *chan,
const u8 *ssid, size_t ssid_len,
const u8 *ie, size_t ie_len,
- bool directed);
-void ieee80211_send_probe_req(struct ieee80211_sub_if_data *sdata,
- const u8 *src, const u8 *dst,
- const u8 *ssid, size_t ssid_len,
- const u8 *ie, size_t ie_len,
- u32 ratemask, bool directed, u32 tx_flags,
- struct ieee80211_channel *channel, bool scan);
-
+ u32 flags);
u32 ieee80211_sta_get_rates(struct ieee80211_sub_if_data *sdata,
struct ieee802_11_elems *elems,
enum nl80211_band band, u32 *basic_rates);
u32 cap);
u8 *ieee80211_ie_build_vht_oper(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap,
const struct cfg80211_chan_def *chandef);
+u8 *ieee80211_ie_build_he_cap(u8 *pos,
+ const struct ieee80211_sta_he_cap *he_cap,
+ u8 *end);
int ieee80211_parse_bitrates(struct cfg80211_chan_def *chandef,
const struct ieee80211_supported_band *sband,
const u8 *srates, int srates_len, u32 *rates);
static u16 ieee80211_netdev_select_queue(struct net_device *dev,
struct sk_buff *skb,
- void *accel_priv,
+ struct net_device *sb_dev,
select_queue_fallback_t fallback)
{
return ieee80211_select_queue(IEEE80211_DEV_TO_SUB_IF(dev), skb);
static u16 ieee80211_monitor_select_queue(struct net_device *dev,
struct sk_buff *skb,
- void *accel_priv,
+ struct net_device *sb_dev,
select_queue_fallback_t fallback)
{
struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
* Copyright 2005-2006, Devicescape Software, Inc.
* Copyright 2006-2007 Jiri Benc <jbenc@suse.cz>
* Copyright 2013-2014 Intel Mobile Communications GmbH
+ * Copyright (C) 2017 Intel Deutschland GmbH
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
wiphy_ext_feature_set(wiphy,
NL80211_EXT_FEATURE_CONTROL_PORT_OVER_NL80211);
- if (!ops->hw_scan)
+ if (!ops->hw_scan) {
wiphy->features |= NL80211_FEATURE_LOW_PRIORITY_SCAN |
NL80211_FEATURE_AP_SCAN;
-
+ /*
+ * if the driver behaves correctly using the probe request
+ * (template) from mac80211, then both of these should be
+ * supported even with hw scan - but let drivers opt in.
+ */
+ wiphy_ext_feature_set(wiphy,
+ NL80211_EXT_FEATURE_SCAN_RANDOM_SN);
+ wiphy_ext_feature_set(wiphy,
+ NL80211_EXT_FEATURE_SCAN_MIN_PREQ_CONTENT);
+ }
if (!ops->set_key)
wiphy->flags |= WIPHY_FLAG_IBSS_RSN;
local->hw.queues = 1;
local->hw.max_rates = 1;
local->hw.max_report_rates = 0;
- local->hw.max_rx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF;
- local->hw.max_tx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF;
+ local->hw.max_rx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF_HT;
+ local->hw.max_tx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF_HT;
local->hw.offchannel_tx_hw_queue = IEEE80211_INVAL_HW_QUEUE;
local->hw.conf.long_frame_max_tx_count = wiphy->retry_long;
local->hw.conf.short_frame_max_tx_count = wiphy->retry_short;
int result, i;
enum nl80211_band band;
int channels, max_bitrates;
- bool supp_ht, supp_vht;
+ bool supp_ht, supp_vht, supp_he;
netdev_features_t feature_whitelist;
struct cfg80211_chan_def dflt_chandef = {};
max_bitrates = 0;
supp_ht = false;
supp_vht = false;
+ supp_he = false;
for (band = 0; band < NUM_NL80211_BANDS; band++) {
struct ieee80211_supported_band *sband;
supp_ht = supp_ht || sband->ht_cap.ht_supported;
supp_vht = supp_vht || sband->vht_cap.vht_supported;
+ if (!supp_he)
+ supp_he = !!ieee80211_get_he_sta_cap(sband);
+
if (!sband->ht_cap.ht_supported)
continue;
local->scan_ies_len +=
2 + sizeof(struct ieee80211_vht_cap);
+ /* HE cap element is variable in size - set len to allow max size */
+ /*
+ * TODO: 1 is added at the end of the calculation to accommodate for
+ * the temporary placing of the HE capabilities IE under EXT.
+ * Remove it once it is placed in the final place.
+ */
+ if (supp_he)
+ local->scan_ies_len +=
+ 2 + sizeof(struct ieee80211_he_cap_elem) +
+ sizeof(struct ieee80211_he_mcs_nss_supp) +
+ IEEE80211_HE_PPE_THRES_MAX_LEN + 1;
+
if (!local->ops->hw_scan) {
/* For hw_scan, driver needs to set these up. */
local->hw.wiphy->max_scan_ssids = 4;
struct ieee80211_channel *channel,
const struct ieee80211_ht_operation *ht_oper,
const struct ieee80211_vht_operation *vht_oper,
+ const struct ieee80211_he_operation *he_oper,
struct cfg80211_chan_def *chandef, bool tracking)
{
struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
}
vht_chandef = *chandef;
- if (!ieee80211_chandef_vht_oper(vht_oper, &vht_chandef)) {
+ if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HE) && he_oper &&
+ (le32_to_cpu(he_oper->he_oper_params) &
+ IEEE80211_HE_OPERATION_VHT_OPER_INFO)) {
+ struct ieee80211_vht_operation he_oper_vht_cap;
+
+ /*
+ * Set only first 3 bytes (other 2 aren't used in
+ * ieee80211_chandef_vht_oper() anyway)
+ */
+ memcpy(&he_oper_vht_cap, he_oper->optional, 3);
+ he_oper_vht_cap.basic_mcs_set = cpu_to_le16(0);
+
+ if (!ieee80211_chandef_vht_oper(&he_oper_vht_cap,
+ &vht_chandef)) {
+ if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HE))
+ sdata_info(sdata,
+ "HE AP VHT information is invalid, disable HE\n");
+ ret = IEEE80211_STA_DISABLE_HE;
+ goto out;
+ }
+ } else if (!ieee80211_chandef_vht_oper(vht_oper, &vht_chandef)) {
if (!(ifmgd->flags & IEEE80211_STA_DISABLE_VHT))
sdata_info(sdata,
"AP VHT information is invalid, disable VHT\n");
const struct ieee80211_ht_cap *ht_cap,
const struct ieee80211_ht_operation *ht_oper,
const struct ieee80211_vht_operation *vht_oper,
+ const struct ieee80211_he_operation *he_oper,
const u8 *bssid, u32 *changed)
{
struct ieee80211_local *local = sdata->local;
struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
- struct ieee80211_supported_band *sband;
- struct ieee80211_channel *chan;
+ struct ieee80211_channel *chan = sdata->vif.bss_conf.chandef.chan;
+ struct ieee80211_supported_band *sband =
+ local->hw.wiphy->bands[chan->band];
struct cfg80211_chan_def chandef;
u16 ht_opmode;
u32 flags;
if (ifmgd->flags & IEEE80211_STA_DISABLE_VHT)
vht_oper = NULL;
+ /* don't check HE if we associated as non-HE station */
+ if (ifmgd->flags & IEEE80211_STA_DISABLE_HE ||
+ !ieee80211_get_he_sta_cap(sband))
+ he_oper = NULL;
+
if (WARN_ON_ONCE(!sta))
return -EINVAL;
sdata->vif.bss_conf.ht_operation_mode = ht_opmode;
}
- chan = sdata->vif.bss_conf.chandef.chan;
- sband = local->hw.wiphy->bands[chan->band];
-
- /* calculate new channel (type) based on HT/VHT operation IEs */
+ /* calculate new channel (type) based on HT/VHT/HE operation IEs */
flags = ieee80211_determine_chantype(sdata, sband, chan,
- ht_oper, vht_oper,
+ ht_oper, vht_oper, he_oper,
&chandef, true);
/*
ieee80211_ie_build_vht_cap(pos, &vht_cap, cap);
}
+/* This function determines HE capability flags for the association
+ * and builds the IE.
+ */
+static void ieee80211_add_he_ie(struct ieee80211_sub_if_data *sdata,
+ struct sk_buff *skb,
+ struct ieee80211_supported_band *sband)
+{
+ u8 *pos;
+ const struct ieee80211_sta_he_cap *he_cap = NULL;
+ u8 he_cap_size;
+
+ he_cap = ieee80211_get_he_sta_cap(sband);
+ if (!he_cap)
+ return;
+
+ /*
+ * TODO: the 1 added is because this temporarily is under the EXTENSION
+ * IE. Get rid of it when it moves.
+ */
+ he_cap_size =
+ 2 + 1 + sizeof(he_cap->he_cap_elem) +
+ ieee80211_he_mcs_nss_size(&he_cap->he_cap_elem) +
+ ieee80211_he_ppe_size(he_cap->ppe_thres[0],
+ he_cap->he_cap_elem.phy_cap_info);
+ pos = skb_put(skb, he_cap_size);
+ ieee80211_ie_build_he_cap(pos, he_cap, pos + he_cap_size);
+}
+
static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
{
struct ieee80211_local *local = sdata->local;
2 + 2 * sband->n_channels + /* supported channels */
2 + sizeof(struct ieee80211_ht_cap) + /* HT */
2 + sizeof(struct ieee80211_vht_cap) + /* VHT */
+ 2 + 1 + sizeof(struct ieee80211_he_cap_elem) + /* HE */
+ sizeof(struct ieee80211_he_mcs_nss_supp) +
+ IEEE80211_HE_PPE_THRES_MAX_LEN +
assoc_data->ie_len + /* extra IEs */
(assoc_data->fils_kek_len ? 16 /* AES-SIV */ : 0) +
9, /* WMM */
offset = noffset;
}
+ /* if present, add any custom IEs that go before HE */
+ if (assoc_data->ie_len) {
+ static const u8 before_he[] = {
+ /*
+ * no need to list the ones split off before VHT
+ * or generated here
+ */
+ WLAN_EID_OPMODE_NOTIF,
+ WLAN_EID_EXTENSION, WLAN_EID_EXT_FUTURE_CHAN_GUIDANCE,
+ /* 11ai elements */
+ WLAN_EID_EXTENSION, WLAN_EID_EXT_FILS_SESSION,
+ WLAN_EID_EXTENSION, WLAN_EID_EXT_FILS_PUBLIC_KEY,
+ WLAN_EID_EXTENSION, WLAN_EID_EXT_FILS_KEY_CONFIRM,
+ WLAN_EID_EXTENSION, WLAN_EID_EXT_FILS_HLP_CONTAINER,
+ WLAN_EID_EXTENSION, WLAN_EID_EXT_FILS_IP_ADDR_ASSIGN,
+ /* TODO: add 11ah/11aj/11ak elements */
+ };
+
+ /* RIC already taken above, so no need to handle here anymore */
+ noffset = ieee80211_ie_split(assoc_data->ie, assoc_data->ie_len,
+ before_he, ARRAY_SIZE(before_he),
+ offset);
+ pos = skb_put(skb, noffset - offset);
+ memcpy(pos, assoc_data->ie + offset, noffset - offset);
+ offset = noffset;
+ }
+
if (!(ifmgd->flags & IEEE80211_STA_DISABLE_VHT))
ieee80211_add_vht_ie(sdata, skb, sband,
&assoc_data->ap_vht_cap);
- /* if present, add any custom non-vendor IEs that go after HT */
+ if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HE))
+ ieee80211_add_he_ie(sdata, skb, sband);
+
+ /* if present, add any custom non-vendor IEs that go after HE */
if (assoc_data->ie_len) {
noffset = ieee80211_ie_split_vendor(assoc_data->ie,
assoc_data->ie_len,
struct ieee80211_hdr_3addr *nullfunc;
struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
+ /* Don't send NDPs when STA is connected HE */
+ if (sdata->vif.type == NL80211_IFTYPE_STATION &&
+ !(ifmgd->flags & IEEE80211_STA_DISABLE_HE))
+ return;
+
skb = ieee80211_nullfunc_get(&local->hw, &sdata->vif,
!ieee80211_hw_check(&local->hw, DOESNT_SUPPORT_QOS_NDP));
if (!skb)
if (WARN_ON(sdata->vif.type != NL80211_IFTYPE_STATION))
return;
+ /* Don't send NDPs when connected HE */
+ if (!(sdata->u.mgd.flags & IEEE80211_STA_DISABLE_HE))
+ return;
+
skb = dev_alloc_skb(local->hw.extra_tx_headroom + 30);
if (!skb)
return;
}
/* MLME */
-static bool ieee80211_sta_wmm_params(struct ieee80211_local *local,
- struct ieee80211_sub_if_data *sdata,
- const u8 *wmm_param, size_t wmm_param_len)
+static bool
+ieee80211_sta_wmm_params(struct ieee80211_local *local,
+ struct ieee80211_sub_if_data *sdata,
+ const u8 *wmm_param, size_t wmm_param_len,
+ const struct ieee80211_mu_edca_param_set *mu_edca)
{
struct ieee80211_tx_queue_params params[IEEE80211_NUM_ACS];
struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
sdata->wmm_acm |= BIT(1) | BIT(2); /* BK/- */
if (uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_BK)
uapsd = true;
+ params[ac].mu_edca = !!mu_edca;
+ if (mu_edca)
+ params[ac].mu_edca_param_rec = mu_edca->ac_bk;
break;
case 2: /* AC_VI */
ac = IEEE80211_AC_VI;
sdata->wmm_acm |= BIT(4) | BIT(5); /* CL/VI */
if (uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_VI)
uapsd = true;
+ params[ac].mu_edca = !!mu_edca;
+ if (mu_edca)
+ params[ac].mu_edca_param_rec = mu_edca->ac_vi;
break;
case 3: /* AC_VO */
ac = IEEE80211_AC_VO;
sdata->wmm_acm |= BIT(6) | BIT(7); /* VO/NC */
if (uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_VO)
uapsd = true;
+ params[ac].mu_edca = !!mu_edca;
+ if (mu_edca)
+ params[ac].mu_edca_param_rec = mu_edca->ac_vo;
break;
case 0: /* AC_BE */
default:
sdata->wmm_acm |= BIT(0) | BIT(3); /* BE/EE */
if (uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_BE)
uapsd = true;
+ params[ac].mu_edca = !!mu_edca;
+ if (mu_edca)
+ params[ac].mu_edca_param_rec = mu_edca->ac_be;
break;
}
ieee80211_sta_reset_conn_monitor(sdata);
}
+static void ieee80211_mlme_send_probe_req(struct ieee80211_sub_if_data *sdata,
+ const u8 *src, const u8 *dst,
+ const u8 *ssid, size_t ssid_len,
+ struct ieee80211_channel *channel)
+{
+ struct sk_buff *skb;
+
+ skb = ieee80211_build_probe_req(sdata, src, dst, (u32)-1, channel,
+ ssid, ssid_len, NULL, 0,
+ IEEE80211_PROBE_FLAG_DIRECTED);
+ if (skb)
+ ieee80211_tx_skb(sdata, skb);
+}
+
static void ieee80211_mgd_probe_ap_send(struct ieee80211_sub_if_data *sdata)
{
struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
else
ssid_len = ssid[1];
- ieee80211_send_probe_req(sdata, sdata->vif.addr, dst,
- ssid + 2, ssid_len, NULL,
- 0, (u32) -1, true, 0,
- ifmgd->associated->channel, false);
+ ieee80211_mlme_send_probe_req(sdata, sdata->vif.addr, dst,
+ ssid + 2, ssid_len,
+ ifmgd->associated->channel);
rcu_read_unlock();
}
skb = ieee80211_build_probe_req(sdata, sdata->vif.addr, cbss->bssid,
(u32) -1, cbss->channel,
ssid + 2, ssid_len,
- NULL, 0, true);
+ NULL, 0, IEEE80211_PROBE_FLAG_DIRECTED);
rcu_read_unlock();
return skb;
goto out;
}
+ /*
+ * If AP doesn't support HT, or it doesn't have HE mandatory IEs, mark
+ * HE as disabled. If on the 5GHz band, make sure it supports VHT.
+ */
+ if (ifmgd->flags & IEEE80211_STA_DISABLE_HT ||
+ (sband->band == NL80211_BAND_5GHZ &&
+ ifmgd->flags & IEEE80211_STA_DISABLE_VHT) ||
+ (!elems.he_cap && !elems.he_operation))
+ ifmgd->flags |= IEEE80211_STA_DISABLE_HE;
+
+ if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HE) &&
+ (!elems.he_cap || !elems.he_operation)) {
+ mutex_unlock(&sdata->local->sta_mtx);
+ sdata_info(sdata,
+ "HE AP is missing HE capability/operation\n");
+ ret = false;
+ goto out;
+ }
+
/* Set up internal HT/VHT capabilities */
if (elems.ht_cap_elem && !(ifmgd->flags & IEEE80211_STA_DISABLE_HT))
ieee80211_ht_cap_ie_to_sta_ht_cap(sdata, sband,
ieee80211_vht_cap_ie_to_sta_vht_cap(sdata, sband,
elems.vht_cap_elem, sta);
+ if (elems.he_operation && !(ifmgd->flags & IEEE80211_STA_DISABLE_HE) &&
+ elems.he_cap) {
+ ieee80211_he_cap_ie_to_sta_he_cap(sdata, sband,
+ elems.he_cap,
+ elems.he_cap_len,
+ sta);
+
+ bss_conf->he_support = sta->sta.he_cap.has_he;
+ } else {
+ bss_conf->he_support = false;
+ }
+
+ if (bss_conf->he_support) {
+ u32 he_oper_params =
+ le32_to_cpu(elems.he_operation->he_oper_params);
+
+ bss_conf->bss_color = he_oper_params &
+ IEEE80211_HE_OPERATION_BSS_COLOR_MASK;
+ bss_conf->htc_trig_based_pkt_ext =
+ (he_oper_params &
+ IEEE80211_HE_OPERATION_DFLT_PE_DURATION_MASK) <<
+ IEEE80211_HE_OPERATION_DFLT_PE_DURATION_OFFSET;
+ bss_conf->frame_time_rts_th =
+ (he_oper_params &
+ IEEE80211_HE_OPERATION_RTS_THRESHOLD_MASK) <<
+ IEEE80211_HE_OPERATION_RTS_THRESHOLD_OFFSET;
+
+ bss_conf->multi_sta_back_32bit =
+ sta->sta.he_cap.he_cap_elem.mac_cap_info[2] &
+ IEEE80211_HE_MAC_CAP2_32BIT_BA_BITMAP;
+
+ bss_conf->ack_enabled =
+ sta->sta.he_cap.he_cap_elem.mac_cap_info[2] &
+ IEEE80211_HE_MAC_CAP2_ACK_EN;
+
+ bss_conf->uora_exists = !!elems.uora_element;
+ if (elems.uora_element)
+ bss_conf->uora_ocw_range = elems.uora_element[0];
+
+ /* TODO: OPEN: what happens if BSS color disable is set? */
+ }
+
/*
* Some APs, e.g. Netgear WNDR3700, report invalid HT operation data
* in their association response, so ignore that data for our own
if (ifmgd->flags & IEEE80211_STA_DISABLE_WMM) {
ieee80211_set_wmm_default(sdata, false, false);
} else if (!ieee80211_sta_wmm_params(local, sdata, elems.wmm_param,
- elems.wmm_param_len)) {
+ elems.wmm_param_len,
+ elems.mu_edca_param_set)) {
/* still enable QoS since we might have HT/VHT */
ieee80211_set_wmm_default(sdata, false, true);
/* set the disable-WMM flag in this case to disable
if (!(ifmgd->flags & IEEE80211_STA_DISABLE_WMM) &&
ieee80211_sta_wmm_params(local, sdata, elems.wmm_param,
- elems.wmm_param_len))
+ elems.wmm_param_len,
+ elems.mu_edca_param_set))
changed |= BSS_CHANGED_QOS;
/*
if (ieee80211_config_bw(sdata, sta,
elems.ht_cap_elem, elems.ht_operation,
- elems.vht_operation, bssid, &changed)) {
+ elems.vht_operation, elems.he_operation,
+ bssid, &changed)) {
mutex_unlock(&local->sta_mtx);
sdata_info(sdata,
"failed to follow AP %pM bandwidth change, disconnect\n",
return chains;
}
+static bool
+ieee80211_verify_sta_he_mcs_support(struct ieee80211_supported_band *sband,
+ const struct ieee80211_he_operation *he_op)
+{
+ const struct ieee80211_sta_he_cap *sta_he_cap =
+ ieee80211_get_he_sta_cap(sband);
+ u16 ap_min_req_set;
+ int i;
+
+ if (!sta_he_cap || !he_op)
+ return false;
+
+ ap_min_req_set = le16_to_cpu(he_op->he_mcs_nss_set);
+
+ /* Need to go over for 80MHz, 160MHz and for 80+80 */
+ for (i = 0; i < 3; i++) {
+ const struct ieee80211_he_mcs_nss_supp *sta_mcs_nss_supp =
+ &sta_he_cap->he_mcs_nss_supp;
+ u16 sta_mcs_map_rx =
+ le16_to_cpu(((__le16 *)sta_mcs_nss_supp)[2 * i]);
+ u16 sta_mcs_map_tx =
+ le16_to_cpu(((__le16 *)sta_mcs_nss_supp)[2 * i + 1]);
+ u8 nss;
+ bool verified = true;
+
+ /*
+ * For each band there is a maximum of 8 spatial streams
+ * possible. Each of the sta_mcs_map_* is a 16-bit struct built
+ * of 2 bits per NSS (1-8), with the values defined in enum
+ * ieee80211_he_mcs_support. Need to make sure STA TX and RX
+ * capabilities aren't less than the AP's minimum requirements
+ * for this HE BSS per SS.
+ * It is enough to find one such band that meets the reqs.
+ */
+ for (nss = 8; nss > 0; nss--) {
+ u8 sta_rx_val = (sta_mcs_map_rx >> (2 * (nss - 1))) & 3;
+ u8 sta_tx_val = (sta_mcs_map_tx >> (2 * (nss - 1))) & 3;
+ u8 ap_val = (ap_min_req_set >> (2 * (nss - 1))) & 3;
+
+ if (ap_val == IEEE80211_HE_MCS_NOT_SUPPORTED)
+ continue;
+
+ /*
+ * Make sure the HE AP doesn't require MCSs that aren't
+ * supported by the client
+ */
+ if (sta_rx_val == IEEE80211_HE_MCS_NOT_SUPPORTED ||
+ sta_tx_val == IEEE80211_HE_MCS_NOT_SUPPORTED ||
+ (ap_val > sta_rx_val) || (ap_val > sta_tx_val)) {
+ verified = false;
+ break;
+ }
+ }
+
+ if (verified)
+ return true;
+ }
+
+ /* If here, STA doesn't meet AP's HE min requirements */
+ return false;
+}
+
static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
struct cfg80211_bss *cbss)
{
const struct ieee80211_ht_cap *ht_cap = NULL;
const struct ieee80211_ht_operation *ht_oper = NULL;
const struct ieee80211_vht_operation *vht_oper = NULL;
+ const struct ieee80211_he_operation *he_oper = NULL;
struct ieee80211_supported_band *sband;
struct cfg80211_chan_def chandef;
int ret;
}
}
+ if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HE) &&
+ ieee80211_get_he_sta_cap(sband)) {
+ const struct cfg80211_bss_ies *ies;
+ const u8 *he_oper_ie;
+
+ ies = rcu_dereference(cbss->ies);
+ he_oper_ie = cfg80211_find_ext_ie(WLAN_EID_EXT_HE_OPERATION,
+ ies->data, ies->len);
+ if (he_oper_ie &&
+ he_oper_ie[1] == ieee80211_he_oper_size(&he_oper_ie[3]))
+ he_oper = (void *)(he_oper_ie + 3);
+ else
+ he_oper = NULL;
+
+ if (!ieee80211_verify_sta_he_mcs_support(sband, he_oper))
+ ifmgd->flags |= IEEE80211_STA_DISABLE_HE;
+ }
+
/* Allow VHT if at least one channel on the sband supports 80 MHz */
have_80mhz = false;
for (i = 0; i < sband->n_channels; i++) {
ifmgd->flags |= ieee80211_determine_chantype(sdata, sband,
cbss->channel,
- ht_oper, vht_oper,
+ ht_oper, vht_oper, he_oper,
&chandef, false);
sdata->needed_rx_chains = min(ieee80211_ht_vht_rx_chains(sdata, cbss),
req->crypto.ciphers_pairwise[i] == WLAN_CIPHER_SUITE_WEP104) {
ifmgd->flags |= IEEE80211_STA_DISABLE_HT;
ifmgd->flags |= IEEE80211_STA_DISABLE_VHT;
+ ifmgd->flags |= IEEE80211_STA_DISABLE_HE;
netdev_info(sdata->dev,
- "disabling HT/VHT due to WEP/TKIP use\n");
+ "disabling HE/HT/VHT due to WEP/TKIP use\n");
}
}
if (roc->mgmt_tx_cookie) {
if (!WARN_ON(!roc->frame)) {
ieee80211_tx_skb_tid_band(roc->sdata, roc->frame, 7,
- roc->chan->band);
+ roc->chan->band, 0);
roc->frame = NULL;
}
} else {
len += 12;
}
+ if (status->encoding == RX_ENC_HE &&
+ status->flag & RX_FLAG_RADIOTAP_HE) {
+ len = ALIGN(len, 2);
+ len += 12;
+ BUILD_BUG_ON(sizeof(struct ieee80211_radiotap_he) != 12);
+ }
+
+ if (status->encoding == RX_ENC_HE &&
+ status->flag & RX_FLAG_RADIOTAP_HE_MU) {
+ len = ALIGN(len, 2);
+ len += 12;
+ BUILD_BUG_ON(sizeof(struct ieee80211_radiotap_he_mu) != 12);
+ }
+
if (status->chains) {
/* antenna and antenna signal fields */
len += 2 * hweight8(status->chains);
int mpdulen, chain;
unsigned long chains = status->chains;
struct ieee80211_vendor_radiotap rtap = {};
+ struct ieee80211_radiotap_he he = {};
+ struct ieee80211_radiotap_he_mu he_mu = {};
+
+ if (status->flag & RX_FLAG_RADIOTAP_HE) {
+ he = *(struct ieee80211_radiotap_he *)skb->data;
+ skb_pull(skb, sizeof(he));
+ WARN_ON_ONCE(status->encoding != RX_ENC_HE);
+ }
+
+ if (status->flag & RX_FLAG_RADIOTAP_HE_MU) {
+ he_mu = *(struct ieee80211_radiotap_he_mu *)skb->data;
+ skb_pull(skb, sizeof(he_mu));
+ }
if (status->flag & RX_FLAG_RADIOTAP_VENDOR_DATA) {
rtap = *(struct ieee80211_vendor_radiotap *)skb->data;
*pos++ = flags;
}
+ if (status->encoding == RX_ENC_HE &&
+ status->flag & RX_FLAG_RADIOTAP_HE) {
+#define HE_PREP(f, val) cpu_to_le16(FIELD_PREP(IEEE80211_RADIOTAP_HE_##f, val))
+
+ if (status->enc_flags & RX_ENC_FLAG_STBC_MASK) {
+ he.data6 |= HE_PREP(DATA6_NSTS,
+ FIELD_GET(RX_ENC_FLAG_STBC_MASK,
+ status->enc_flags));
+ he.data3 |= HE_PREP(DATA3_STBC, 1);
+ } else {
+ he.data6 |= HE_PREP(DATA6_NSTS, status->nss);
+ }
+
+#define CHECK_GI(s) \
+ BUILD_BUG_ON(IEEE80211_RADIOTAP_HE_DATA5_GI_##s != \
+ (int)NL80211_RATE_INFO_HE_GI_##s)
+
+ CHECK_GI(0_8);
+ CHECK_GI(1_6);
+ CHECK_GI(3_2);
+
+ he.data3 |= HE_PREP(DATA3_DATA_MCS, status->rate_idx);
+ he.data3 |= HE_PREP(DATA3_DATA_DCM, status->he_dcm);
+ he.data3 |= HE_PREP(DATA3_CODING,
+ !!(status->enc_flags & RX_ENC_FLAG_LDPC));
+
+ he.data5 |= HE_PREP(DATA5_GI, status->he_gi);
+
+ switch (status->bw) {
+ case RATE_INFO_BW_20:
+ he.data5 |= HE_PREP(DATA5_DATA_BW_RU_ALLOC,
+ IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_20MHZ);
+ break;
+ case RATE_INFO_BW_40:
+ he.data5 |= HE_PREP(DATA5_DATA_BW_RU_ALLOC,
+ IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_40MHZ);
+ break;
+ case RATE_INFO_BW_80:
+ he.data5 |= HE_PREP(DATA5_DATA_BW_RU_ALLOC,
+ IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_80MHZ);
+ break;
+ case RATE_INFO_BW_160:
+ he.data5 |= HE_PREP(DATA5_DATA_BW_RU_ALLOC,
+ IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_160MHZ);
+ break;
+ case RATE_INFO_BW_HE_RU:
+#define CHECK_RU_ALLOC(s) \
+ BUILD_BUG_ON(IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_##s##T != \
+ NL80211_RATE_INFO_HE_RU_ALLOC_##s + 4)
+
+ CHECK_RU_ALLOC(26);
+ CHECK_RU_ALLOC(52);
+ CHECK_RU_ALLOC(106);
+ CHECK_RU_ALLOC(242);
+ CHECK_RU_ALLOC(484);
+ CHECK_RU_ALLOC(996);
+ CHECK_RU_ALLOC(2x996);
+
+ he.data5 |= HE_PREP(DATA5_DATA_BW_RU_ALLOC,
+ status->he_ru + 4);
+ break;
+ default:
+ WARN_ONCE(1, "Invalid SU BW %d\n", status->bw);
+ }
+
+ /* ensure 2 byte alignment */
+ while ((pos - (u8 *)rthdr) & 1)
+ pos++;
+ rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_HE);
+ memcpy(pos, &he, sizeof(he));
+ pos += sizeof(he);
+ }
+
+ if (status->encoding == RX_ENC_HE &&
+ status->flag & RX_FLAG_RADIOTAP_HE_MU) {
+ /* ensure 2 byte alignment */
+ while ((pos - (u8 *)rthdr) & 1)
+ pos++;
+ rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_HE_MU);
+ memcpy(pos, &he_mu, sizeof(he_mu));
+ pos += sizeof(he_mu);
+ }
+
for_each_set_bit(chain, &chains, IEEE80211_MAX_CHAINS) {
*pos++ = status->chain_signal[chain];
*pos++ = chain;
rcu_dereference(local->monitor_sdata);
bool only_monitor = false;
+ if (status->flag & RX_FLAG_RADIOTAP_HE)
+ rtap_space += sizeof(struct ieee80211_radiotap_he);
+
+ if (status->flag & RX_FLAG_RADIOTAP_HE_MU)
+ rtap_space += sizeof(struct ieee80211_radiotap_he_mu);
+
if (unlikely(status->flag & RX_FLAG_RADIOTAP_VENDOR_DATA)) {
struct ieee80211_vendor_radiotap *rtap = (void *)origskb->data;
}
__ieee80211_tx_skb_tid_band(rx->sdata, nskb, 7,
- status->band);
+ status->band, 0);
}
dev_kfree_skb(rx->skb);
return RX_QUEUED;
status = IEEE80211_SKB_RXCB((rx->skb));
sband = rx->local->hw.wiphy->bands[status->band];
- if (!(status->encoding == RX_ENC_HT) &&
- !(status->encoding == RX_ENC_VHT))
+ if (status->encoding == RX_ENC_LEGACY)
rate = &sband->bitrates[status->rate_idx];
ieee80211_rx_cooked_monitor(rx, rate);
status->rate_idx, status->nss))
goto drop;
break;
+ case RX_ENC_HE:
+ if (WARN_ONCE(status->rate_idx > 11 ||
+ !status->nss ||
+ status->nss > 8,
+ "Rate marked as an HE rate but data is invalid: MCS: %d, NSS: %d\n",
+ status->rate_idx, status->nss))
+ goto drop;
+ break;
default:
WARN_ON_ONCE(1);
/* fall through */
#include <net/sch_generic.h>
#include <linux/slab.h>
#include <linux/export.h>
+#include <linux/random.h>
#include <net/mac80211.h>
#include "ieee80211_i.h"
struct cfg80211_chan_def chandef;
u8 bands_used = 0;
int i, ielen, n_chans;
+ u32 flags = 0;
req = rcu_dereference_protected(local->scan_req,
lockdep_is_held(&local->mtx));
local->hw_scan_req->req.n_channels = n_chans;
ieee80211_prepare_scan_chandef(&chandef, req->scan_width);
+ if (req->flags & NL80211_SCAN_FLAG_MIN_PREQ_CONTENT)
+ flags |= IEEE80211_PROBE_FLAG_MIN_CONTENT;
+
ielen = ieee80211_build_preq_ies(local,
(u8 *)local->hw_scan_req->req.ie,
local->hw_scan_ies_bufsize,
&local->hw_scan_req->ies,
req->ie, req->ie_len,
- bands_used, req->rates, &chandef);
+ bands_used, req->rates, &chandef,
+ flags);
local->hw_scan_req->req.ie_len = ielen;
local->hw_scan_req->req.no_cck = req->no_cck;
ether_addr_copy(local->hw_scan_req->req.mac_addr, req->mac_addr);
round_jiffies_relative(0));
}
+static void ieee80211_send_scan_probe_req(struct ieee80211_sub_if_data *sdata,
+ const u8 *src, const u8 *dst,
+ const u8 *ssid, size_t ssid_len,
+ const u8 *ie, size_t ie_len,
+ u32 ratemask, u32 flags, u32 tx_flags,
+ struct ieee80211_channel *channel)
+{
+ struct sk_buff *skb;
+ u32 txdata_flags = 0;
+
+ skb = ieee80211_build_probe_req(sdata, src, dst, ratemask, channel,
+ ssid, ssid_len,
+ ie, ie_len, flags);
+
+ if (skb) {
+ if (flags & IEEE80211_PROBE_FLAG_RANDOM_SN) {
+ struct ieee80211_hdr *hdr = (void *)skb->data;
+ u16 sn = get_random_u32();
+
+ txdata_flags |= IEEE80211_TX_NO_SEQNO;
+ hdr->seq_ctrl =
+ cpu_to_le16(IEEE80211_SN_TO_SEQ(sn));
+ }
+ IEEE80211_SKB_CB(skb)->flags |= tx_flags;
+ ieee80211_tx_skb_tid_band(sdata, skb, 7, channel->band,
+ txdata_flags);
+ }
+}
+
static void ieee80211_scan_state_send_probe(struct ieee80211_local *local,
unsigned long *next_delay)
{
struct ieee80211_sub_if_data *sdata;
struct cfg80211_scan_request *scan_req;
enum nl80211_band band = local->hw.conf.chandef.chan->band;
- u32 tx_flags;
+ u32 flags = 0, tx_flags;
scan_req = rcu_dereference_protected(local->scan_req,
lockdep_is_held(&local->mtx));
tx_flags = IEEE80211_TX_INTFL_OFFCHAN_TX_OK;
if (scan_req->no_cck)
tx_flags |= IEEE80211_TX_CTL_NO_CCK_RATE;
+ if (scan_req->flags & NL80211_SCAN_FLAG_MIN_PREQ_CONTENT)
+ flags |= IEEE80211_PROBE_FLAG_MIN_CONTENT;
+ if (scan_req->flags & NL80211_SCAN_FLAG_RANDOM_SN)
+ flags |= IEEE80211_PROBE_FLAG_RANDOM_SN;
sdata = rcu_dereference_protected(local->scan_sdata,
lockdep_is_held(&local->mtx));
for (i = 0; i < scan_req->n_ssids; i++)
- ieee80211_send_probe_req(
+ ieee80211_send_scan_probe_req(
sdata, local->scan_addr, scan_req->bssid,
scan_req->ssids[i].ssid, scan_req->ssids[i].ssid_len,
scan_req->ie, scan_req->ie_len,
- scan_req->rates[band], false,
- tx_flags, local->hw.conf.chandef.chan, true);
+ scan_req->rates[band], flags,
+ tx_flags, local->hw.conf.chandef.chan);
/*
* After sending probe requests, wait for probe responses
u32 rate_masks[NUM_NL80211_BANDS] = {};
u8 bands_used = 0;
u8 *ie;
+ u32 flags = 0;
iebufsz = local->scan_ies_len + req->ie_len;
}
}
+ if (req->flags & NL80211_SCAN_FLAG_MIN_PREQ_CONTENT)
+ flags |= IEEE80211_PROBE_FLAG_MIN_CONTENT;
+
ie = kcalloc(iebufsz, num_bands, GFP_KERNEL);
if (!ie) {
ret = -ENOMEM;
ieee80211_build_preq_ies(local, ie, num_bands * iebufsz,
&sched_scan_ies, req->ie,
- req->ie_len, bands_used, rate_masks, &chandef);
+ req->ie_len, bands_used, rate_masks, &chandef,
+ flags);
ret = drv_sched_scan_start(local, sdata, req, &sched_scan_ies);
if (ret == 0) {
struct ieee80211_tx_info *info;
struct ieee80211_chanctx_conf *chanctx_conf;
+ /* Don't send NDPs when STA is connected HE */
+ if (sdata->vif.type == NL80211_IFTYPE_STATION &&
+ !(sdata->u.mgd.flags & IEEE80211_STA_DISABLE_HE))
+ return;
+
if (qos) {
fc = cpu_to_le16(IEEE80211_FTYPE_DATA |
IEEE80211_STYPE_QOS_NULLFUNC |
}
info->band = chanctx_conf->def.chan->band;
- ieee80211_xmit(sdata, sta, skb);
+ ieee80211_xmit(sdata, sta, skb, 0);
rcu_read_unlock();
}
return stats;
}
-static void sta_stats_decode_rate(struct ieee80211_local *local, u16 rate,
+static void sta_stats_decode_rate(struct ieee80211_local *local, u32 rate,
struct rate_info *rinfo)
{
rinfo->bw = STA_STATS_GET(BW, rate);
rinfo->legacy = DIV_ROUND_UP(brate, 1 << shift);
break;
}
+ case STA_STATS_RATE_TYPE_HE:
+ rinfo->flags = RATE_INFO_FLAGS_HE_MCS;
+ rinfo->mcs = STA_STATS_GET(HE_MCS, rate);
+ rinfo->nss = STA_STATS_GET(HE_NSS, rate);
+ rinfo->he_gi = STA_STATS_GET(HE_GI, rate);
+ rinfo->he_ru_alloc = STA_STATS_GET(HE_RU, rate);
+ rinfo->he_dcm = STA_STATS_GET(HE_DCM, rate);
+ break;
}
}
drv_sta_statistics(local, sdata, &sta->sta, sinfo);
- sinfo->filled |= BIT(NL80211_STA_INFO_INACTIVE_TIME) |
- BIT(NL80211_STA_INFO_STA_FLAGS) |
- BIT(NL80211_STA_INFO_BSS_PARAM) |
- BIT(NL80211_STA_INFO_CONNECTED_TIME) |
- BIT(NL80211_STA_INFO_RX_DROP_MISC);
+ sinfo->filled |= BIT_ULL(NL80211_STA_INFO_INACTIVE_TIME) |
+ BIT_ULL(NL80211_STA_INFO_STA_FLAGS) |
+ BIT_ULL(NL80211_STA_INFO_BSS_PARAM) |
+ BIT_ULL(NL80211_STA_INFO_CONNECTED_TIME) |
+ BIT_ULL(NL80211_STA_INFO_RX_DROP_MISC);
if (sdata->vif.type == NL80211_IFTYPE_STATION) {
sinfo->beacon_loss_count = sdata->u.mgd.beacon_loss_count;
- sinfo->filled |= BIT(NL80211_STA_INFO_BEACON_LOSS);
+ sinfo->filled |= BIT_ULL(NL80211_STA_INFO_BEACON_LOSS);
}
sinfo->connected_time = ktime_get_seconds() - sta->last_connected;
sinfo->inactive_time =
jiffies_to_msecs(jiffies - ieee80211_sta_last_active(sta));
- if (!(sinfo->filled & (BIT(NL80211_STA_INFO_TX_BYTES64) |
- BIT(NL80211_STA_INFO_TX_BYTES)))) {
+ if (!(sinfo->filled & (BIT_ULL(NL80211_STA_INFO_TX_BYTES64) |
+ BIT_ULL(NL80211_STA_INFO_TX_BYTES)))) {
sinfo->tx_bytes = 0;
for (ac = 0; ac < IEEE80211_NUM_ACS; ac++)
sinfo->tx_bytes += sta->tx_stats.bytes[ac];
- sinfo->filled |= BIT(NL80211_STA_INFO_TX_BYTES64);
+ sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BYTES64);
}
- if (!(sinfo->filled & BIT(NL80211_STA_INFO_TX_PACKETS))) {
+ if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_TX_PACKETS))) {
sinfo->tx_packets = 0;
for (ac = 0; ac < IEEE80211_NUM_ACS; ac++)
sinfo->tx_packets += sta->tx_stats.packets[ac];
- sinfo->filled |= BIT(NL80211_STA_INFO_TX_PACKETS);
+ sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_PACKETS);
}
- if (!(sinfo->filled & (BIT(NL80211_STA_INFO_RX_BYTES64) |
- BIT(NL80211_STA_INFO_RX_BYTES)))) {
+ if (!(sinfo->filled & (BIT_ULL(NL80211_STA_INFO_RX_BYTES64) |
+ BIT_ULL(NL80211_STA_INFO_RX_BYTES)))) {
sinfo->rx_bytes += sta_get_stats_bytes(&sta->rx_stats);
if (sta->pcpu_rx_stats) {
}
}
- sinfo->filled |= BIT(NL80211_STA_INFO_RX_BYTES64);
+ sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_BYTES64);
}
- if (!(sinfo->filled & BIT(NL80211_STA_INFO_RX_PACKETS))) {
+ if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_RX_PACKETS))) {
sinfo->rx_packets = sta->rx_stats.packets;
if (sta->pcpu_rx_stats) {
for_each_possible_cpu(cpu) {
sinfo->rx_packets += cpurxs->packets;
}
}
- sinfo->filled |= BIT(NL80211_STA_INFO_RX_PACKETS);
+ sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_PACKETS);
}
- if (!(sinfo->filled & BIT(NL80211_STA_INFO_TX_RETRIES))) {
+ if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_TX_RETRIES))) {
sinfo->tx_retries = sta->status_stats.retry_count;
- sinfo->filled |= BIT(NL80211_STA_INFO_TX_RETRIES);
+ sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_RETRIES);
}
- if (!(sinfo->filled & BIT(NL80211_STA_INFO_TX_FAILED))) {
+ if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_TX_FAILED))) {
sinfo->tx_failed = sta->status_stats.retry_failed;
- sinfo->filled |= BIT(NL80211_STA_INFO_TX_FAILED);
+ sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_FAILED);
}
sinfo->rx_dropped_misc = sta->rx_stats.dropped;
if (sdata->vif.type == NL80211_IFTYPE_STATION &&
!(sdata->vif.driver_flags & IEEE80211_VIF_BEACON_FILTER)) {
- sinfo->filled |= BIT(NL80211_STA_INFO_BEACON_RX) |
- BIT(NL80211_STA_INFO_BEACON_SIGNAL_AVG);
+ sinfo->filled |= BIT_ULL(NL80211_STA_INFO_BEACON_RX) |
+ BIT_ULL(NL80211_STA_INFO_BEACON_SIGNAL_AVG);
sinfo->rx_beacon_signal_avg = ieee80211_ave_rssi(&sdata->vif);
}
if (ieee80211_hw_check(&sta->local->hw, SIGNAL_DBM) ||
ieee80211_hw_check(&sta->local->hw, SIGNAL_UNSPEC)) {
- if (!(sinfo->filled & BIT(NL80211_STA_INFO_SIGNAL))) {
+ if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_SIGNAL))) {
sinfo->signal = (s8)last_rxstats->last_signal;
- sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL);
+ sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL);
}
if (!sta->pcpu_rx_stats &&
- !(sinfo->filled & BIT(NL80211_STA_INFO_SIGNAL_AVG))) {
+ !(sinfo->filled & BIT_ULL(NL80211_STA_INFO_SIGNAL_AVG))) {
sinfo->signal_avg =
-ewma_signal_read(&sta->rx_stats_avg.signal);
- sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL_AVG);
+ sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL_AVG);
}
}
* pcpu statistics
*/
if (last_rxstats->chains &&
- !(sinfo->filled & (BIT(NL80211_STA_INFO_CHAIN_SIGNAL) |
- BIT(NL80211_STA_INFO_CHAIN_SIGNAL_AVG)))) {
- sinfo->filled |= BIT(NL80211_STA_INFO_CHAIN_SIGNAL);
+ !(sinfo->filled & (BIT_ULL(NL80211_STA_INFO_CHAIN_SIGNAL) |
+ BIT_ULL(NL80211_STA_INFO_CHAIN_SIGNAL_AVG)))) {
+ sinfo->filled |= BIT_ULL(NL80211_STA_INFO_CHAIN_SIGNAL);
if (!sta->pcpu_rx_stats)
- sinfo->filled |= BIT(NL80211_STA_INFO_CHAIN_SIGNAL_AVG);
+ sinfo->filled |= BIT_ULL(NL80211_STA_INFO_CHAIN_SIGNAL_AVG);
sinfo->chains = last_rxstats->chains;
}
}
- if (!(sinfo->filled & BIT(NL80211_STA_INFO_TX_BITRATE))) {
+ if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_TX_BITRATE))) {
sta_set_rate_info_tx(sta, &sta->tx_stats.last_rate,
&sinfo->txrate);
- sinfo->filled |= BIT(NL80211_STA_INFO_TX_BITRATE);
+ sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BITRATE);
}
- if (!(sinfo->filled & BIT(NL80211_STA_INFO_RX_BITRATE))) {
+ if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_RX_BITRATE))) {
if (sta_set_rate_info_rx(sta, &sinfo->rxrate) == 0)
- sinfo->filled |= BIT(NL80211_STA_INFO_RX_BITRATE);
+ sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_BITRATE);
}
if (tidstats && !cfg80211_sinfo_alloc_tid_stats(sinfo, GFP_KERNEL)) {
if (ieee80211_vif_is_mesh(&sdata->vif)) {
#ifdef CONFIG_MAC80211_MESH
- sinfo->filled |= BIT(NL80211_STA_INFO_LLID) |
- BIT(NL80211_STA_INFO_PLID) |
- BIT(NL80211_STA_INFO_PLINK_STATE) |
- BIT(NL80211_STA_INFO_LOCAL_PM) |
- BIT(NL80211_STA_INFO_PEER_PM) |
- BIT(NL80211_STA_INFO_NONPEER_PM);
+ sinfo->filled |= BIT_ULL(NL80211_STA_INFO_LLID) |
+ BIT_ULL(NL80211_STA_INFO_PLID) |
+ BIT_ULL(NL80211_STA_INFO_PLINK_STATE) |
+ BIT_ULL(NL80211_STA_INFO_LOCAL_PM) |
+ BIT_ULL(NL80211_STA_INFO_PEER_PM) |
+ BIT_ULL(NL80211_STA_INFO_NONPEER_PM);
sinfo->llid = sta->mesh->llid;
sinfo->plid = sta->mesh->plid;
sinfo->plink_state = sta->mesh->plink_state;
if (test_sta_flag(sta, WLAN_STA_TOFFSET_KNOWN)) {
- sinfo->filled |= BIT(NL80211_STA_INFO_T_OFFSET);
+ sinfo->filled |= BIT_ULL(NL80211_STA_INFO_T_OFFSET);
sinfo->t_offset = sta->mesh->t_offset;
}
sinfo->local_pm = sta->mesh->local_pm;
thr = sta_get_expected_throughput(sta);
if (thr != 0) {
- sinfo->filled |= BIT(NL80211_STA_INFO_EXPECTED_THROUGHPUT);
+ sinfo->filled |= BIT_ULL(NL80211_STA_INFO_EXPECTED_THROUGHPUT);
sinfo->expected_throughput = thr;
}
u8 dialog_token;
u8 stop_initiator;
bool tx_stop;
- u8 buf_size;
+ u16 buf_size;
u16 failed_bar_ssn;
bool bar_pending;
int last_signal;
u8 chains;
s8 chain_signal_last[IEEE80211_MAX_CHAINS];
- u16 last_rate;
+ u32 last_rate;
struct u64_stats_sync syncp;
u64 bytes;
u64 msdu[IEEE80211_NUM_TIDS + 1];
STA_STATS_RATE_TYPE_LEGACY,
STA_STATS_RATE_TYPE_HT,
STA_STATS_RATE_TYPE_VHT,
+ STA_STATS_RATE_TYPE_HE,
};
#define STA_STATS_FIELD_HT_MCS GENMASK( 7, 0)
#define STA_STATS_FIELD_LEGACY_BAND GENMASK( 7, 4)
#define STA_STATS_FIELD_VHT_MCS GENMASK( 3, 0)
#define STA_STATS_FIELD_VHT_NSS GENMASK( 7, 4)
+#define STA_STATS_FIELD_HE_MCS GENMASK( 3, 0)
+#define STA_STATS_FIELD_HE_NSS GENMASK( 7, 4)
#define STA_STATS_FIELD_BW GENMASK(11, 8)
#define STA_STATS_FIELD_SGI GENMASK(12, 12)
#define STA_STATS_FIELD_TYPE GENMASK(15, 13)
+#define STA_STATS_FIELD_HE_RU GENMASK(18, 16)
+#define STA_STATS_FIELD_HE_GI GENMASK(20, 19)
+#define STA_STATS_FIELD_HE_DCM GENMASK(21, 21)
#define STA_STATS_FIELD(_n, _v) FIELD_PREP(STA_STATS_FIELD_ ## _n, _v)
#define STA_STATS_GET(_n, _v) FIELD_GET(STA_STATS_FIELD_ ## _n, _v)
static inline u32 sta_stats_encode_rate(struct ieee80211_rx_status *s)
{
- u16 r;
+ u32 r;
r = STA_STATS_FIELD(BW, s->bw);
r |= STA_STATS_FIELD(LEGACY_BAND, s->band);
r |= STA_STATS_FIELD(LEGACY_IDX, s->rate_idx);
break;
+ case RX_ENC_HE:
+ r |= STA_STATS_FIELD(TYPE, STA_STATS_RATE_TYPE_HE);
+ r |= STA_STATS_FIELD(HE_NSS, s->nss);
+ r |= STA_STATS_FIELD(HE_MCS, s->rate_idx);
+ r |= STA_STATS_FIELD(HE_GI, s->he_gi);
+ r |= STA_STATS_FIELD(HE_RU, s->he_ru);
+ r |= STA_STATS_FIELD(HE_DCM, s->he_dcm);
+ break;
default:
WARN_ON(1);
return STA_STATS_RATE_INVALID;
STA_ENTRY \
__field(u16, tid) \
__field(u16, ssn) \
- __field(u8, buf_size) \
+ __field(u16, buf_size) \
__field(bool, amsdu) \
__field(u16, timeout) \
__field(u16, action)
*/
if (!ieee80211_is_data_qos(hdr->frame_control) ||
is_multicast_ether_addr(hdr->addr1)) {
+ if (tx->flags & IEEE80211_TX_NO_SEQNO)
+ return TX_CONTINUE;
/* driver should assign sequence number */
info->flags |= IEEE80211_TX_CTL_ASSIGN_SEQ;
/* for pure STA mode without beacons, we can do it */
*/
static bool ieee80211_tx(struct ieee80211_sub_if_data *sdata,
struct sta_info *sta, struct sk_buff *skb,
- bool txpending)
+ bool txpending, u32 txdata_flags)
{
struct ieee80211_local *local = sdata->local;
struct ieee80211_tx_data tx;
led_len = skb->len;
res_prepare = ieee80211_tx_prepare(sdata, &tx, sta, skb);
+ tx.flags |= txdata_flags;
+
if (unlikely(res_prepare == TX_DROP)) {
ieee80211_free_txskb(&local->hw, skb);
return true;
}
void ieee80211_xmit(struct ieee80211_sub_if_data *sdata,
- struct sta_info *sta, struct sk_buff *skb)
+ struct sta_info *sta, struct sk_buff *skb,
+ u32 txdata_flags)
{
struct ieee80211_local *local = sdata->local;
struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
}
ieee80211_set_qos_hdr(sdata, skb);
- ieee80211_tx(sdata, sta, skb, false);
+ ieee80211_tx(sdata, sta, skb, false, txdata_flags);
}
static bool ieee80211_parse_tx_radiotap(struct ieee80211_local *local,
if (!ieee80211_parse_tx_radiotap(local, skb))
goto fail_rcu;
- ieee80211_xmit(sdata, NULL, skb);
+ ieee80211_xmit(sdata, NULL, skb, 0);
rcu_read_unlock();
return NETDEV_TX_OK;
ieee80211_tx_stats(dev, skb->len);
- ieee80211_xmit(sdata, sta, skb);
+ ieee80211_xmit(sdata, sta, skb, 0);
}
goto out;
out_free:
return true;
}
info->band = chanctx_conf->def.chan->band;
- result = ieee80211_tx(sdata, NULL, skb, true);
+ result = ieee80211_tx(sdata, NULL, skb, true, 0);
} else {
struct sk_buff_head skbs;
void __ieee80211_tx_skb_tid_band(struct ieee80211_sub_if_data *sdata,
struct sk_buff *skb, int tid,
- enum nl80211_band band)
+ enum nl80211_band band, u32 txdata_flags)
{
int ac = ieee80211_ac_from_tid(tid);
*/
local_bh_disable();
IEEE80211_SKB_CB(skb)->band = band;
- ieee80211_xmit(sdata, NULL, skb);
+ ieee80211_xmit(sdata, NULL, skb, txdata_flags);
local_bh_enable();
}
skb_reset_network_header(skb);
skb_reset_mac_header(skb);
+ local_bh_disable();
__ieee80211_subif_start_xmit(skb, skb->dev, flags);
+ local_bh_enable();
return 0;
}
if (elen >= sizeof(*elems->max_idle_period_ie))
elems->max_idle_period_ie = (void *)pos;
break;
+ case WLAN_EID_EXTENSION:
+ if (pos[0] == WLAN_EID_EXT_HE_MU_EDCA &&
+ elen >= (sizeof(*elems->mu_edca_param_set) + 1)) {
+ elems->mu_edca_param_set = (void *)&pos[1];
+ } else if (pos[0] == WLAN_EID_EXT_HE_CAPABILITY) {
+ elems->he_cap = (void *)&pos[1];
+ elems->he_cap_len = elen - 1;
+ } else if (pos[0] == WLAN_EID_EXT_HE_OPERATION &&
+ elen >= sizeof(*elems->he_operation) &&
+ elen >= ieee80211_he_oper_size(&pos[1])) {
+ elems->he_operation = (void *)&pos[1];
+ } else if (pos[0] == WLAN_EID_EXT_UORA && elen >= 1) {
+ elems->uora_element = (void *)&pos[1];
+ }
+ break;
default:
break;
}
enum nl80211_band band,
u32 rate_mask,
struct cfg80211_chan_def *chandef,
- size_t *offset)
+ size_t *offset, u32 flags)
{
struct ieee80211_supported_band *sband;
+ const struct ieee80211_sta_he_cap *he_cap;
u8 *pos = buffer, *end = buffer + buffer_len;
size_t noffset;
int supp_rates_len, i;
chandef->chan->center_freq);
}
+ if (flags & IEEE80211_PROBE_FLAG_MIN_CONTENT)
+ goto done;
+
/* insert custom IEs that go before HT */
if (ie && ie_len) {
static const u8 before_ht[] = {
sband->ht_cap.cap);
}
- /*
- * If adding more here, adjust code in main.c
- * that calculates local->scan_ies_len.
- */
-
/* insert custom IEs that go before VHT */
if (ie && ie_len) {
static const u8 before_vht[] = {
sband->vht_cap.cap);
}
+ /* insert custom IEs that go before HE */
+ if (ie && ie_len) {
+ static const u8 before_he[] = {
+ /*
+ * no need to list the ones split off before VHT
+ * or generated here
+ */
+ WLAN_EID_EXTENSION, WLAN_EID_EXT_FILS_REQ_PARAMS,
+ WLAN_EID_AP_CSN,
+ /* TODO: add 11ah/11aj/11ak elements */
+ };
+ noffset = ieee80211_ie_split(ie, ie_len,
+ before_he, ARRAY_SIZE(before_he),
+ *offset);
+ if (end - pos < noffset - *offset)
+ goto out_err;
+ memcpy(pos, ie + *offset, noffset - *offset);
+ pos += noffset - *offset;
+ *offset = noffset;
+ }
+
+ he_cap = ieee80211_get_he_sta_cap(sband);
+ if (he_cap) {
+ pos = ieee80211_ie_build_he_cap(pos, he_cap, end);
+ if (!pos)
+ goto out_err;
+ }
+
+ /*
+ * If adding more here, adjust code in main.c
+ * that calculates local->scan_ies_len.
+ */
+
return pos - buffer;
out_err:
WARN_ONCE(1, "not enough space for preq IEs\n");
+ done:
return pos - buffer;
}
struct ieee80211_scan_ies *ie_desc,
const u8 *ie, size_t ie_len,
u8 bands_used, u32 *rate_masks,
- struct cfg80211_chan_def *chandef)
+ struct cfg80211_chan_def *chandef,
+ u32 flags)
{
size_t pos = 0, old_pos = 0, custom_ie_offset = 0;
int i;
ie, ie_len, i,
rate_masks[i],
chandef,
- &custom_ie_offset);
+ &custom_ie_offset,
+ flags);
ie_desc->ies[i] = buffer + old_pos;
ie_desc->len[i] = pos - old_pos;
old_pos = pos;
struct ieee80211_channel *chan,
const u8 *ssid, size_t ssid_len,
const u8 *ie, size_t ie_len,
- bool directed)
+ u32 flags)
{
struct ieee80211_local *local = sdata->local;
struct cfg80211_chan_def chandef;
* badly-behaved APs don't respond when this parameter is included.
*/
chandef.width = sdata->vif.bss_conf.chandef.width;
- if (directed)
+ if (flags & IEEE80211_PROBE_FLAG_DIRECTED)
chandef.chan = NULL;
else
chandef.chan = chan;
ies_len = ieee80211_build_preq_ies(local, skb_tail_pointer(skb),
skb_tailroom(skb), &dummy_ie_desc,
ie, ie_len, BIT(chan->band),
- rate_masks, &chandef);
+ rate_masks, &chandef, flags);
skb_put(skb, ies_len);
if (dst) {
return skb;
}
-void ieee80211_send_probe_req(struct ieee80211_sub_if_data *sdata,
- const u8 *src, const u8 *dst,
- const u8 *ssid, size_t ssid_len,
- const u8 *ie, size_t ie_len,
- u32 ratemask, bool directed, u32 tx_flags,
- struct ieee80211_channel *channel, bool scan)
-{
- struct sk_buff *skb;
-
- skb = ieee80211_build_probe_req(sdata, src, dst, ratemask, channel,
- ssid, ssid_len,
- ie, ie_len, directed);
- if (skb) {
- IEEE80211_SKB_CB(skb)->flags |= tx_flags;
- if (scan)
- ieee80211_tx_skb_tid_band(sdata, skb, 7, channel->band);
- else
- ieee80211_tx_skb(sdata, skb);
- }
-}
-
u32 ieee80211_sta_get_rates(struct ieee80211_sub_if_data *sdata,
struct ieee802_11_elems *elems,
enum nl80211_band band, u32 *basic_rates)
return pos;
}
+u8 *ieee80211_ie_build_he_cap(u8 *pos,
+ const struct ieee80211_sta_he_cap *he_cap,
+ u8 *end)
+{
+ u8 n;
+ u8 ie_len;
+ u8 *orig_pos = pos;
+
+ /* Make sure we have place for the IE */
+ /*
+ * TODO: the 1 added is because this temporarily is under the EXTENSION
+ * IE. Get rid of it when it moves.
+ */
+ if (!he_cap)
+ return orig_pos;
+
+ n = ieee80211_he_mcs_nss_size(&he_cap->he_cap_elem);
+ ie_len = 2 + 1 +
+ sizeof(he_cap->he_cap_elem) + n +
+ ieee80211_he_ppe_size(he_cap->ppe_thres[0],
+ he_cap->he_cap_elem.phy_cap_info);
+
+ if ((end - pos) < ie_len)
+ return orig_pos;
+
+ *pos++ = WLAN_EID_EXTENSION;
+ pos++; /* We'll set the size later below */
+ *pos++ = WLAN_EID_EXT_HE_CAPABILITY;
+
+ /* Fixed data */
+ memcpy(pos, &he_cap->he_cap_elem, sizeof(he_cap->he_cap_elem));
+ pos += sizeof(he_cap->he_cap_elem);
+
+ memcpy(pos, &he_cap->he_mcs_nss_supp, n);
+ pos += n;
+
+ /* Check if PPE Threshold should be present */
+ if ((he_cap->he_cap_elem.phy_cap_info[6] &
+ IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT) == 0)
+ goto end;
+
+ /*
+ * Calculate how many PPET16/PPET8 pairs are to come. Algorithm:
+ * (NSS_M1 + 1) x (num of 1 bits in RU_INDEX_BITMASK)
+ */
+ n = hweight8(he_cap->ppe_thres[0] &
+ IEEE80211_PPE_THRES_RU_INDEX_BITMASK_MASK);
+ n *= (1 + ((he_cap->ppe_thres[0] & IEEE80211_PPE_THRES_NSS_MASK) >>
+ IEEE80211_PPE_THRES_NSS_POS));
+
+ /*
+ * Each pair is 6 bits, and we need to add the 7 "header" bits to the
+ * total size.
+ */
+ n = (n * IEEE80211_PPE_THRES_INFO_PPET_SIZE * 2) + 7;
+ n = DIV_ROUND_UP(n, 8);
+
+ /* Copy PPE Thresholds */
+ memcpy(pos, &he_cap->ppe_thres, n);
+ pos += n;
+
+end:
+ orig_pos[1] = (pos - orig_pos) - 2;
+ return pos;
+}
+
u8 *ieee80211_ie_build_ht_oper(u8 *pos, struct ieee80211_sta_ht_cap *ht_cap,
const struct cfg80211_chan_def *chandef,
u16 prot_mode, bool rifs_mode)
ncm->data[2] = data;
ncm->data[4] = ntohl(lsc->oem_status);
- netdev_info(ndp->ndev.dev, "NCSI: LSC AEN - channel %u state %s\n",
- nc->id, data & 0x1 ? "up" : "down");
+ netdev_dbg(ndp->ndev.dev, "NCSI: LSC AEN - channel %u state %s\n",
+ nc->id, data & 0x1 ? "up" : "down");
chained = !list_empty(&nc->link);
state = nc->state;
hncdsc = (struct ncsi_aen_hncdsc_pkt *)h;
ncm->data[3] = ntohl(hncdsc->status);
spin_unlock_irqrestore(&nc->lock, flags);
- netdev_printk(KERN_DEBUG, ndp->ndev.dev,
- "NCSI: host driver %srunning on channel %u\n",
- ncm->data[3] & 0x1 ? "" : "not ", nc->id);
+ netdev_dbg(ndp->ndev.dev,
+ "NCSI: host driver %srunning on channel %u\n",
+ ncm->data[3] & 0x1 ? "" : "not ", nc->id);
return 0;
}
}
break;
case ncsi_dev_state_config_done:
- netdev_printk(KERN_DEBUG, ndp->ndev.dev,
- "NCSI: channel %u config done\n", nc->id);
+ netdev_dbg(ndp->ndev.dev, "NCSI: channel %u config done\n",
+ nc->id);
spin_lock_irqsave(&nc->lock, flags);
if (nc->reconfigure_needed) {
/* This channel's configuration has been updated
list_add_tail_rcu(&nc->link, &ndp->channel_queue);
spin_unlock_irqrestore(&ndp->lock, flags);
- netdev_printk(KERN_DEBUG, dev,
- "Dirty NCSI channel state reset\n");
+ netdev_dbg(dev, "Dirty NCSI channel state reset\n");
ncsi_process_next_channel(ndp);
break;
}
} else {
hot_nc = NULL;
nc->state = NCSI_CHANNEL_INACTIVE;
- netdev_warn(ndp->ndev.dev,
- "NCSI: channel %u link down after config\n",
- nc->id);
+ netdev_dbg(ndp->ndev.dev,
+ "NCSI: channel %u link down after config\n",
+ nc->id);
}
spin_unlock_irqrestore(&nc->lock, flags);
}
ncm = &found->modes[NCSI_MODE_LINK];
- netdev_printk(KERN_DEBUG, ndp->ndev.dev,
- "NCSI: Channel %u added to queue (link %s)\n",
- found->id, ncm->data[2] & 0x1 ? "up" : "down");
+ netdev_dbg(ndp->ndev.dev,
+ "NCSI: Channel %u added to queue (link %s)\n",
+ found->id, ncm->data[2] & 0x1 ? "up" : "down");
out:
spin_lock_irqsave(&ndp->lock, flags);
switch (old_state) {
case NCSI_CHANNEL_INACTIVE:
ndp->ndev.state = ncsi_dev_state_config;
- netdev_info(ndp->ndev.dev, "NCSI: configuring channel %u\n",
- nc->id);
+ netdev_dbg(ndp->ndev.dev, "NCSI: configuring channel %u\n",
+ nc->id);
ncsi_configure_channel(ndp);
break;
case NCSI_CHANNEL_ACTIVE:
ndp->ndev.state = ncsi_dev_state_suspend;
- netdev_info(ndp->ndev.dev, "NCSI: suspending channel %u\n",
- nc->id);
+ netdev_dbg(ndp->ndev.dev, "NCSI: suspending channel %u\n",
+ nc->id);
ncsi_suspend_channel(ndp);
break;
default:
return ncsi_choose_active_channel(ndp);
}
- netdev_printk(KERN_DEBUG, ndp->ndev.dev,
- "NCSI: No more channels to process\n");
ncsi_report_link(ndp, false);
return -ENODEV;
}
if ((ndp->ndev.state & 0xff00) ==
ncsi_dev_state_config ||
!list_empty(&nc->link)) {
- netdev_printk(KERN_DEBUG, nd->dev,
- "NCSI: channel %p marked dirty\n",
- nc);
+ netdev_dbg(nd->dev,
+ "NCSI: channel %p marked dirty\n",
+ nc);
nc->reconfigure_needed = true;
}
spin_unlock_irqrestore(&nc->lock, flags);
list_add_tail_rcu(&nc->link, &ndp->channel_queue);
spin_unlock_irqrestore(&ndp->lock, flags);
- netdev_printk(KERN_DEBUG, nd->dev,
- "NCSI: kicked channel %p\n", nc);
+ netdev_dbg(nd->dev, "NCSI: kicked channel %p\n", nc);
n++;
}
}
list_for_each_entry_rcu(vlan, &ndp->vlan_vids, list) {
n_vids++;
if (vlan->vid == vid) {
- netdev_printk(KERN_DEBUG, dev,
- "NCSI: vid %u already registered\n", vid);
+ netdev_dbg(dev, "NCSI: vid %u already registered\n",
+ vid);
return 0;
}
}
vlan->vid = vid;
list_add_rcu(&vlan->list, &ndp->vlan_vids);
- netdev_printk(KERN_DEBUG, dev, "NCSI: Added new vid %u\n", vid);
+ netdev_dbg(dev, "NCSI: Added new vid %u\n", vid);
found = ncsi_kick_channels(ndp) != 0;
/* Remove the VLAN id from our internal list */
list_for_each_entry_safe(vlan, tmp, &ndp->vlan_vids, list)
if (vlan->vid == vid) {
- netdev_printk(KERN_DEBUG, dev,
- "NCSI: vid %u found, removing\n", vid);
+ netdev_dbg(dev, "NCSI: vid %u found, removing\n", vid);
list_del_rcu(&vlan->list);
found = true;
kfree(vlan);
}
}
- netdev_printk(KERN_DEBUG, ndp->ndev.dev, "NCSI: Stopping device\n");
+ netdev_dbg(ndp->ndev.dev, "NCSI: Stopping device\n");
ncsi_report_link(ndp, true);
}
EXPORT_SYMBOL_GPL(ncsi_stop_dev);
}
EXPORT_SYMBOL(nf_conntrack_destroy);
+bool nf_ct_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple,
+ const struct sk_buff *skb)
+{
+ struct nf_ct_hook *ct_hook;
+ bool ret = false;
+
+ rcu_read_lock();
+ ct_hook = rcu_dereference(nf_ct_hook);
+ if (ct_hook)
+ ret = ct_hook->get_tuple_skb(dst_tuple, skb);
+ rcu_read_unlock();
+ return ret;
+}
+EXPORT_SYMBOL(nf_ct_get_tuple_skb);
+
/* Built-in default zone used e.g. by modules. */
const struct nf_conntrack_zone nf_ct_zone_dflt = {
.id = NF_CT_DEFAULT_ZONE_ID,
struct hlist_node node;
struct nf_conntrack_tuple tuple;
struct nf_conntrack_zone zone;
+ int cpu;
+ u32 jiffies32;
};
struct nf_conncount_rb {
return false;
conn->tuple = *tuple;
conn->zone = *zone;
+ conn->cpu = raw_smp_processor_id();
+ conn->jiffies32 = (u32)jiffies;
hlist_add_head(&conn->node, head);
return true;
}
EXPORT_SYMBOL_GPL(nf_conncount_add);
+static const struct nf_conntrack_tuple_hash *
+find_or_evict(struct net *net, struct nf_conncount_tuple *conn)
+{
+ const struct nf_conntrack_tuple_hash *found;
+ unsigned long a, b;
+ int cpu = raw_smp_processor_id();
+ __s32 age;
+
+ found = nf_conntrack_find_get(net, &conn->zone, &conn->tuple);
+ if (found)
+ return found;
+ b = conn->jiffies32;
+ a = (u32)jiffies;
+
+ /* conn might have been added just before by another cpu and
+ * might still be unconfirmed. In this case, nf_conntrack_find()
+ * returns no result. Thus only evict if this cpu added the
+ * stale entry or if the entry is older than two jiffies.
+ */
+ age = a - b;
+ if (conn->cpu == cpu || age >= 2) {
+ hlist_del(&conn->node);
+ kmem_cache_free(conncount_conn_cachep, conn);
+ return ERR_PTR(-ENOENT);
+ }
+
+ return ERR_PTR(-EAGAIN);
+}
+
unsigned int nf_conncount_lookup(struct net *net, struct hlist_head *head,
const struct nf_conntrack_tuple *tuple,
const struct nf_conntrack_zone *zone,
{
const struct nf_conntrack_tuple_hash *found;
struct nf_conncount_tuple *conn;
- struct hlist_node *n;
struct nf_conn *found_ct;
+ struct hlist_node *n;
unsigned int length = 0;
*addit = tuple ? true : false;
/* check the saved connections */
hlist_for_each_entry_safe(conn, n, head, node) {
- found = nf_conntrack_find_get(net, &conn->zone, &conn->tuple);
- if (found == NULL) {
- hlist_del(&conn->node);
- kmem_cache_free(conncount_conn_cachep, conn);
+ found = find_or_evict(net, conn);
+ if (IS_ERR(found)) {
+ /* Not found, but might be about to be confirmed */
+ if (PTR_ERR(found) == -EAGAIN) {
+ length++;
+ if (!tuple)
+ continue;
+
+ if (nf_ct_tuple_equal(&conn->tuple, tuple) &&
+ nf_ct_zone_id(&conn->zone, conn->zone.dir) ==
+ nf_ct_zone_id(zone, zone->dir))
+ *addit = false;
+ }
continue;
}
__be32 mask = 0;
/* we're only interested in locally generated packets */
- if (skb->sk == NULL)
+ if (skb->sk == NULL || !net_eq(nf_ct_net(ct), sock_net(skb->sk)))
goto out;
if (rt == NULL || !(rt->rt_flags & RTCF_BROADCAST))
goto out;
return 0;
}
+static bool nf_conntrack_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple,
+ const struct sk_buff *skb)
+{
+ const struct nf_conntrack_tuple *src_tuple;
+ const struct nf_conntrack_tuple_hash *hash;
+ struct nf_conntrack_tuple srctuple;
+ enum ip_conntrack_info ctinfo;
+ struct nf_conn *ct;
+
+ ct = nf_ct_get(skb, &ctinfo);
+ if (ct) {
+ src_tuple = nf_ct_tuple(ct, CTINFO2DIR(ctinfo));
+ memcpy(dst_tuple, src_tuple, sizeof(*dst_tuple));
+ return true;
+ }
+
+ if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb),
+ NFPROTO_IPV4, dev_net(skb->dev),
+ &srctuple))
+ return false;
+
+ hash = nf_conntrack_find_get(dev_net(skb->dev),
+ &nf_ct_zone_dflt,
+ &srctuple);
+ if (!hash)
+ return false;
+
+ ct = nf_ct_tuplehash_to_ctrack(hash);
+ src_tuple = nf_ct_tuple(ct, !hash->tuple.dst.dir);
+ memcpy(dst_tuple, src_tuple, sizeof(*dst_tuple));
+ nf_ct_put(ct);
+
+ return true;
+}
+
/* Bring out ya dead! */
static struct nf_conn *
get_next_corpse(int (*iter)(struct nf_conn *i, void *data),
static struct nf_ct_hook nf_conntrack_hook = {
.update = nf_conntrack_update,
.destroy = destroy_conntrack,
+ .get_tuple_skb = nf_conntrack_get_tuple_skb,
};
void nf_conntrack_init_end(void)
nf_ct_expect_iterate_destroy(expect_iter_me, NULL);
nf_ct_iterate_destroy(unhelp, me);
+
+ /* Maybe someone has gotten the helper already when unhelp above.
+ * So need to wait it.
+ */
+ synchronize_rcu();
}
EXPORT_SYMBOL_GPL(nf_conntrack_helper_unregister);
if (write) {
struct ctl_table tmp = *table;
+ /* proc_dostring() can append to existing strings, so we need to
+ * initialize it as an empty string.
+ */
+ buf[0] = '\0';
tmp.data = buf;
r = proc_dostring(&tmp, write, buffer, lenp, ppos);
if (r)
rcu_assign_pointer(net->nf.nf_loggers[tindex], logger);
mutex_unlock(&nf_log_mutex);
} else {
+ struct ctl_table tmp = *table;
+
+ tmp.data = buf;
mutex_lock(&nf_log_mutex);
logger = nft_log_dereference(net->nf.nf_loggers[tindex]);
if (!logger)
- table->data = "NONE";
+ strlcpy(buf, "NONE", sizeof(buf));
else
- table->data = logger->name;
- r = proc_dostring(table, write, buffer, lenp, ppos);
+ strlcpy(buf, logger->name, sizeof(buf));
mutex_unlock(&nf_log_mutex);
+ r = proc_dostring(&tmp, write, buffer, lenp, ppos);
}
return r;
}
EXPORT_SYMBOL_GPL(nf_log_dump_tcp_header);
-void nf_log_dump_sk_uid_gid(struct nf_log_buf *m, struct sock *sk)
+void nf_log_dump_sk_uid_gid(struct net *net, struct nf_log_buf *m,
+ struct sock *sk)
{
- if (!sk || !sk_fullsock(sk))
+ if (!sk || !sk_fullsock(sk) || !net_eq(net, sock_net(sk)))
return;
read_lock_bh(&sk->sk_callback_lock);
struct flowi fl;
unsigned int hh_len;
struct dst_entry *dst;
+ struct sock *sk = skb->sk;
int err;
err = xfrm_decode_session(skb, &fl, family);
dst = ((struct xfrm_dst *)dst)->route;
dst_hold(dst);
- dst = xfrm_lookup(net, dst, &fl, skb->sk, 0);
+ if (sk && !net_eq(net, sock_net(sk)))
+ sk = NULL;
+
+ dst = xfrm_lookup(net, dst, &fl, sk, 0);
if (IS_ERR(dst))
return PTR_ERR(dst);
#include <linux/skbuff.h>
#include <linux/netlink.h>
#include <linux/vmalloc.h>
+#include <linux/rhashtable.h>
#include <linux/netfilter.h>
#include <linux/netfilter/nfnetlink.h>
#include <linux/netfilter/nf_tables.h>
static const struct nla_policy nfqa_cfg_policy[NFQA_CFG_MAX+1] = {
[NFQA_CFG_CMD] = { .len = sizeof(struct nfqnl_msg_config_cmd) },
[NFQA_CFG_PARAMS] = { .len = sizeof(struct nfqnl_msg_config_params) },
+ [NFQA_CFG_QUEUE_MAXLEN] = { .type = NLA_U32 },
+ [NFQA_CFG_MASK] = { .type = NLA_U32 },
+ [NFQA_CFG_FLAGS] = { .type = NLA_U32 },
};
static const struct nf_queue_handler nfqh = {
break;
case NFT_META_SKUID:
sk = skb_to_full_sk(skb);
- if (!sk || !sk_fullsock(sk))
+ if (!sk || !sk_fullsock(sk) ||
+ !net_eq(nft_net(pkt), sock_net(sk)))
goto err;
read_lock_bh(&sk->sk_callback_lock);
break;
case NFT_META_SKGID:
sk = skb_to_full_sk(skb);
- if (!sk || !sk_fullsock(sk))
+ if (!sk || !sk_fullsock(sk) ||
+ !net_eq(nft_net(pkt), sock_net(sk)))
goto err;
read_lock_bh(&sk->sk_callback_lock);
#ifdef CONFIG_CGROUP_NET_CLASSID
case NFT_META_CGROUP:
sk = skb_to_full_sk(skb);
- if (!sk || !sk_fullsock(sk))
+ if (!sk || !sk_fullsock(sk) ||
+ !net_eq(nft_net(pkt), sock_net(sk)))
goto err;
*dest = sock_cgroup_classid(&sk->sk_cgrp_data);
break;
struct sock *sk = skb->sk;
u32 *dest = ®s->data[priv->dreg];
+ if (sk && !net_eq(nft_net(pkt), sock_net(sk)))
+ sk = NULL;
+
if (!sk)
switch(nft_pf(pkt)) {
case NFPROTO_IPV4:
return;
}
- if(!sk) {
+ if (!sk) {
nft_reg_store8(dest, 0);
return;
}
cgroup_mt_v0(const struct sk_buff *skb, struct xt_action_param *par)
{
const struct xt_cgroup_info_v0 *info = par->matchinfo;
+ struct sock *sk = skb->sk;
- if (skb->sk == NULL || !sk_fullsock(skb->sk))
+ if (!sk || !sk_fullsock(sk) || !net_eq(xt_net(par), sock_net(sk)))
return false;
return (info->id == sock_cgroup_classid(&skb->sk->sk_cgrp_data)) ^
const struct xt_cgroup_info_v1 *info = par->matchinfo;
struct sock_cgroup_data *skcd = &skb->sk->sk_cgrp_data;
struct cgroup *ancestor = info->priv;
+ struct sock *sk = skb->sk;
- if (!skb->sk || !sk_fullsock(skb->sk))
+ if (!sk || !sk_fullsock(sk) || !net_eq(xt_net(par), sock_net(sk)))
return false;
if (ancestor)
struct sock *sk = skb_to_full_sk(skb);
struct net *net = xt_net(par);
- if (sk == NULL || sk->sk_socket == NULL)
+ if (!sk || !sk->sk_socket || !net_eq(net, sock_net(sk)))
return (info->match ^ info->invert) == 0;
else if (info->match & info->invert & XT_OWNER_SOCKET)
/*
}
/* use TTL as seen before forwarding */
- if (xt_out(par) != NULL && skb->sk == NULL)
+ if (xt_out(par) != NULL &&
+ (!skb->sk || !net_eq(net, sock_net(skb->sk))))
ttl++;
spin_lock_bh(&recent_lock);
struct sk_buff *pskb = (struct sk_buff *)skb;
struct sock *sk = skb->sk;
+ if (!net_eq(xt_net(par), sock_net(sk)))
+ sk = NULL;
+
if (!sk)
sk = nf_sk_lookup_slow_v4(xt_net(par), skb, xt_in(par));
+
if (sk) {
bool wildcard;
bool transparent = true;
struct sk_buff *pskb = (struct sk_buff *)skb;
struct sock *sk = skb->sk;
+ if (!net_eq(xt_net(par), sock_net(sk)))
+ sk = NULL;
+
if (!sk)
sk = nf_sk_lookup_slow_v6(xt_net(par), skb, xt_in(par));
+
if (sk) {
bool wildcard;
bool transparent = true;
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = netlink_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.ioctl = netlink_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.socketpair = sock_no_socketpair,
.accept = nr_accept,
.getname = nr_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.ioctl = nr_ioctl,
.listen = nr_listen,
.shutdown = sock_no_shutdown,
return 0;
}
-static __poll_t llcp_sock_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t llcp_sock_poll(struct file *file, struct socket *sock,
+ poll_table *wait)
{
struct sock *sk = sock->sk;
__poll_t mask = 0;
pr_debug("%p\n", sk);
+ sock_poll_wait(file, sk_sleep(sk), wait);
+
if (sk->sk_state == LLCP_LISTEN)
return llcp_accept_poll(sk);
.socketpair = sock_no_socketpair,
.accept = llcp_sock_accept,
.getname = llcp_sock_getname,
- .poll_mask = llcp_sock_poll_mask,
+ .poll = llcp_sock_poll,
.ioctl = sock_no_ioctl,
.listen = llcp_sock_listen,
.shutdown = sock_no_shutdown,
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = llcp_sock_getname,
- .poll_mask = llcp_sock_poll_mask,
+ .poll = llcp_sock_poll,
.ioctl = sock_no_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = sock_no_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.ioctl = sock_no_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = sock_no_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.ioctl = sock_no_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
clone_flow_key);
}
+/* When 'last' is true, clone() should always consume the 'skb'.
+ * Otherwise, clone() should keep 'skb' intact regardless what
+ * actions are executed within clone().
+ */
+static int clone(struct datapath *dp, struct sk_buff *skb,
+ struct sw_flow_key *key, const struct nlattr *attr,
+ bool last)
+{
+ struct nlattr *actions;
+ struct nlattr *clone_arg;
+ int rem = nla_len(attr);
+ bool dont_clone_flow_key;
+
+ /* The first action is always 'OVS_CLONE_ATTR_ARG'. */
+ clone_arg = nla_data(attr);
+ dont_clone_flow_key = nla_get_u32(clone_arg);
+ actions = nla_next(clone_arg, &rem);
+
+ return clone_execute(dp, skb, key, 0, actions, rem, last,
+ !dont_clone_flow_key);
+}
+
static void execute_hash(struct sk_buff *skb, struct sw_flow_key *key,
const struct nlattr *attr)
{
consume_skb(skb);
return 0;
}
+ break;
+
+ case OVS_ACTION_ATTR_CLONE: {
+ bool last = nla_is_last(a, rem);
+
+ err = clone(dp, skb, key, a, last);
+ if (last)
+ return err;
+
+ break;
+ }
}
if (unlikely(err)) {
return 0;
}
+static int validate_and_copy_clone(struct net *net,
+ const struct nlattr *attr,
+ const struct sw_flow_key *key,
+ struct sw_flow_actions **sfa,
+ __be16 eth_type, __be16 vlan_tci,
+ bool log, bool last)
+{
+ int start, err;
+ u32 exec;
+
+ if (nla_len(attr) && nla_len(attr) < NLA_HDRLEN)
+ return -EINVAL;
+
+ start = add_nested_action_start(sfa, OVS_ACTION_ATTR_CLONE, log);
+ if (start < 0)
+ return start;
+
+ exec = last || !actions_may_change_flow(attr);
+
+ err = ovs_nla_add_action(sfa, OVS_CLONE_ATTR_EXEC, &exec,
+ sizeof(exec), log);
+ if (err)
+ return err;
+
+ err = __ovs_nla_copy_actions(net, attr, key, sfa,
+ eth_type, vlan_tci, log);
+ if (err)
+ return err;
+
+ add_nested_action_end(*sfa, start);
+
+ return 0;
+}
+
void ovs_match_init(struct sw_flow_match *match,
struct sw_flow_key *key,
bool reset_key,
struct ovs_tunnel_info *ovs_tun;
struct nlattr *a;
int err = 0, start, opts_type;
+ __be16 dst_opt_type;
+ dst_opt_type = 0;
ovs_match_init(&match, &key, true, NULL);
opts_type = ip_tun_from_nlattr(nla_data(attr), &match, false, log);
if (opts_type < 0)
err = validate_geneve_opts(&key);
if (err < 0)
return err;
+ dst_opt_type = TUNNEL_GENEVE_OPT;
break;
case OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS:
+ dst_opt_type = TUNNEL_VXLAN_OPT;
break;
case OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS:
+ dst_opt_type = TUNNEL_ERSPAN_OPT;
break;
}
}
*/
ip_tunnel_info_opts_set(tun_info,
TUN_METADATA_OPTS(&key, key.tun_opts_len),
- key.tun_opts_len);
+ key.tun_opts_len, dst_opt_type);
add_nested_action_end(*sfa, start);
return err;
[OVS_ACTION_ATTR_PUSH_NSH] = (u32)-1,
[OVS_ACTION_ATTR_POP_NSH] = 0,
[OVS_ACTION_ATTR_METER] = sizeof(u32),
+ [OVS_ACTION_ATTR_CLONE] = (u32)-1,
};
const struct ovs_action_push_vlan *vlan;
int type = nla_type(a);
/* Non-existent meters are simply ignored. */
break;
+ case OVS_ACTION_ATTR_CLONE: {
+ bool last = nla_is_last(a, rem);
+
+ err = validate_and_copy_clone(net, a, key, sfa,
+ eth_type, vlan_tci,
+ log, last);
+ if (err)
+ return err;
+ skip_copy = true;
+ break;
+ }
+
default:
OVS_NLERR(log, "Unknown Action type %d", type);
return -EINVAL;
return err;
}
+static int clone_action_to_attr(const struct nlattr *attr,
+ struct sk_buff *skb)
+{
+ struct nlattr *start;
+ int err = 0, rem = nla_len(attr);
+
+ start = nla_nest_start(skb, OVS_ACTION_ATTR_CLONE);
+ if (!start)
+ return -EMSGSIZE;
+
+ err = ovs_nla_put_actions(nla_data(attr), rem, skb);
+
+ if (err)
+ nla_nest_cancel(skb, start);
+ else
+ nla_nest_end(skb, start);
+
+ return err;
+}
+
static int set_action_to_attr(const struct nlattr *a, struct sk_buff *skb)
{
const struct nlattr *ovs_key = nla_data(a);
return err;
break;
+ case OVS_ACTION_ATTR_CLONE:
+ err = clone_action_to_attr(a, skb);
+ if (err)
+ return err;
+ break;
+
default:
if (nla_put(skb, type, nla_len(a), nla_data(a)))
return -EMSGSIZE;
return po->xmit == packet_direct_xmit;
}
-static u16 __packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb)
+static u16 __packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb,
+ struct net_device *sb_dev)
{
- return (u16) raw_smp_processor_id() % dev->real_num_tx_queues;
+ return dev_pick_tx_cpu_id(dev, skb, sb_dev, NULL);
}
static u16 packet_pick_tx_queue(struct sk_buff *skb)
__packet_pick_tx_queue);
queue_index = netdev_cap_txqueue(dev, queue_index);
} else {
- queue_index = __packet_pick_tx_queue(dev, skb);
+ queue_index = __packet_pick_tx_queue(dev, skb, NULL);
}
return queue_index;
goto out_unlock;
}
- sockc.tsflags = sk->sk_tsflags;
+ sockcm_init(&sockc, sk);
if (msg->msg_controllen) {
err = sock_cmsg_send(sk, msg, &sockc);
if (unlikely(err))
skb->dev = dev;
skb->priority = sk->sk_priority;
skb->mark = sk->sk_mark;
+ skb->tstamp = sockc.transmit_time;
sock_tx_timestamp(sk, sockc.tsflags, &skb_shinfo(skb)->tx_flags);
if (po->stats.stats1.tp_drops)
status |= TP_STATUS_LOSING;
}
+
+ if (do_vnet &&
+ virtio_net_hdr_from_skb(skb, h.raw + macoff -
+ sizeof(struct virtio_net_hdr),
+ vio_le(), true, 0))
+ goto drop_n_account;
+
po->stats.stats1.tp_packets++;
if (copy_skb) {
status |= TP_STATUS_COPY;
}
spin_unlock(&sk->sk_receive_queue.lock);
- if (do_vnet) {
- if (virtio_net_hdr_from_skb(skb, h.raw + macoff -
- sizeof(struct virtio_net_hdr),
- vio_le(), true, 0)) {
- spin_lock(&sk->sk_receive_queue.lock);
- goto drop_n_account;
- }
- }
-
skb_copy_bits(skb, 0, h.raw + macoff, snaplen);
if (!(ts_status = tpacket_get_timestamp(skb, &ts, po->tp_tstamp)))
skb->dev = dev;
skb->priority = po->sk.sk_priority;
skb->mark = po->sk.sk_mark;
+ skb->tstamp = sockc->transmit_time;
sock_tx_timestamp(&po->sk, sockc->tsflags, &skb_shinfo(skb)->tx_flags);
skb_shinfo(skb)->destructor_arg = ph.raw;
if (unlikely(!(dev->flags & IFF_UP)))
goto out_put;
- sockc.tsflags = po->sk.sk_tsflags;
+ sockcm_init(&sockc, &po->sk);
if (msg->msg_controllen) {
err = sock_cmsg_send(&po->sk, msg, &sockc);
if (unlikely(err))
if (unlikely(!(dev->flags & IFF_UP)))
goto out_unlock;
- sockc.tsflags = sk->sk_tsflags;
+ sockcm_init(&sockc, sk);
sockc.mark = sk->sk_mark;
if (msg->msg_controllen) {
err = sock_cmsg_send(sk, msg, &sockc);
skb->dev = dev;
skb->priority = sk->sk_priority;
skb->mark = sockc.mark;
+ skb->tstamp = sockc.transmit_time;
if (has_vnet_hdr) {
err = virtio_net_hdr_to_skb(skb, &vnet_hdr, vio_le());
return 0;
}
-static __poll_t packet_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t packet_poll(struct file *file, struct socket *sock,
+ poll_table *wait)
{
struct sock *sk = sock->sk;
struct packet_sock *po = pkt_sk(sk);
- __poll_t mask = datagram_poll_mask(sock, events);
+ __poll_t mask = datagram_poll(file, sock, wait);
spin_lock_bh(&sk->sk_receive_queue.lock);
if (po->rx_ring.pg_vec) {
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = packet_getname_spkt,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.ioctl = packet_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = packet_getname,
- .poll_mask = packet_poll_mask,
+ .poll = packet_poll,
.ioctl = packet_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
return sizeof(struct sockaddr_pn);
}
-static __poll_t pn_socket_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t pn_socket_poll(struct file *file, struct socket *sock,
+ poll_table *wait)
{
struct sock *sk = sock->sk;
struct pep_sock *pn = pep_sk(sk);
__poll_t mask = 0;
+ poll_wait(file, sk_sleep(sk), wait);
+
if (sk->sk_state == TCP_CLOSE)
return EPOLLERR;
if (!skb_queue_empty(&sk->sk_receive_queue))
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = pn_socket_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.ioctl = pn_socket_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.socketpair = sock_no_socketpair,
.accept = pn_socket_accept,
.getname = pn_socket_getname,
- .poll_mask = pn_socket_poll_mask,
+ .poll = pn_socket_poll,
.ioctl = pn_socket_ioctl,
.listen = pn_socket_listen,
.shutdown = sock_no_shutdown,
.recvmsg = qrtr_recvmsg,
.getname = qrtr_getname,
.ioctl = qrtr_ioctl,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.shutdown = sock_no_shutdown,
.setsockopt = sock_no_setsockopt,
.getsockopt = sock_no_getsockopt,
int rds_conn_init(void)
{
+ int ret;
+
+ ret = rds_loop_net_init(); /* register pernet callback */
+ if (ret)
+ return ret;
+
rds_conn_slab = kmem_cache_create("rds_connection",
sizeof(struct rds_connection),
0, 0, NULL);
- if (!rds_conn_slab)
+ if (!rds_conn_slab) {
+ rds_loop_net_exit();
return -ENOMEM;
+ }
rds_info_register_func(RDS_INFO_CONNECTIONS, rds_conn_info);
rds_info_register_func(RDS_INFO_SEND_MESSAGES,
void rds_conn_exit(void)
{
+ rds_loop_net_exit(); /* unregister pernet callback */
rds_loop_exit();
WARN_ON(!hlist_empty(rds_conn_hash));
* This tries to allocate and post unused work requests after making sure that
* they have all the allocations they need to queue received fragments into
* sockets.
- *
- * -1 is returned if posting fails due to temporary resource exhaustion.
*/
void rds_ib_recv_refill(struct rds_connection *conn, int prefill, gfp_t gfp)
{
{
struct rds_connection *conn = cp->cp_conn;
struct rds_ib_connection *ic = conn->c_transport_data;
- int ret = 0;
rdsdebug("conn %p\n", conn);
if (rds_conn_up(conn)) {
rds_ib_stats_inc(s_ib_rx_refill_from_thread);
}
- return ret;
+ return 0;
}
int rds_ib_recv_init(void)
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/in.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
#include "rds_single_path.h"
#include "rds.h"
static DEFINE_SPINLOCK(loop_conns_lock);
static LIST_HEAD(loop_conns);
+static atomic_t rds_loop_unloading = ATOMIC_INIT(0);
+
+static void rds_loop_set_unloading(void)
+{
+ atomic_set(&rds_loop_unloading, 1);
+}
+
+static bool rds_loop_is_unloading(struct rds_connection *conn)
+{
+ return atomic_read(&rds_loop_unloading) != 0;
+}
/*
* This 'loopback' transport is a special case for flows that originate
struct rds_loop_connection *lc, *_lc;
LIST_HEAD(tmp_list);
+ rds_loop_set_unloading();
+ synchronize_rcu();
/* avoid calling conn_destroy with irqs off */
spin_lock_irq(&loop_conns_lock);
list_splice(&loop_conns, &tmp_list);
}
}
+static void rds_loop_kill_conns(struct net *net)
+{
+ struct rds_loop_connection *lc, *_lc;
+ LIST_HEAD(tmp_list);
+
+ spin_lock_irq(&loop_conns_lock);
+ list_for_each_entry_safe(lc, _lc, &loop_conns, loop_node) {
+ struct net *c_net = read_pnet(&lc->conn->c_net);
+
+ if (net != c_net)
+ continue;
+ list_move_tail(&lc->loop_node, &tmp_list);
+ }
+ spin_unlock_irq(&loop_conns_lock);
+
+ list_for_each_entry_safe(lc, _lc, &tmp_list, loop_node) {
+ WARN_ON(lc->conn->c_passive);
+ rds_conn_destroy(lc->conn);
+ }
+}
+
+static void __net_exit rds_loop_exit_net(struct net *net)
+{
+ rds_loop_kill_conns(net);
+}
+
+static struct pernet_operations rds_loop_net_ops = {
+ .exit = rds_loop_exit_net,
+};
+
+int rds_loop_net_init(void)
+{
+ return register_pernet_device(&rds_loop_net_ops);
+}
+
+void rds_loop_net_exit(void)
+{
+ unregister_pernet_device(&rds_loop_net_ops);
+}
+
/*
* This is missing .xmit_* because loop doesn't go through generic
* rds_send_xmit() and doesn't call rds_recv_incoming(). .listen_stop and
.inc_free = rds_loop_inc_free,
.t_name = "loopback",
.t_type = RDS_TRANS_LOOP,
+ .t_unloading = rds_loop_is_unloading,
};
/* loop.c */
extern struct rds_transport rds_loop_transport;
+int rds_loop_net_init(void);
+void rds_loop_net_exit(void);
void rds_loop_exit(void);
#endif
.socketpair = sock_no_socketpair,
.accept = rose_accept,
.getname = rose_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.ioctl = rose_ioctl,
.listen = rose_listen,
.shutdown = sock_no_shutdown,
/*
* permit an RxRPC socket to be polled
*/
-static __poll_t rxrpc_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t rxrpc_poll(struct file *file, struct socket *sock,
+ poll_table *wait)
{
struct sock *sk = sock->sk;
struct rxrpc_sock *rx = rxrpc_sk(sk);
- __poll_t mask = 0;
+ __poll_t mask;
+
+ sock_poll_wait(file, sk_sleep(sk), wait);
+ mask = 0;
/* the socket is readable if there are any messages waiting on the Rx
* queue */
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = sock_no_getname,
- .poll_mask = rxrpc_poll_mask,
+ .poll = rxrpc_poll,
.ioctl = sock_no_ioctl,
.listen = rxrpc_listen,
.shutdown = rxrpc_shutdown,
To compile this code as a module, choose M here: the
module will be called sch_cbs.
+config NET_SCH_ETF
+ tristate "Earliest TxTime First (ETF)"
+ help
+ Say Y here if you want to use the Earliest TxTime First (ETF) packet
+ scheduling algorithm.
+
+ See the top of <file:net/sched/sch_etf.c> for more details.
+
+ To compile this code as a module, choose M here: the
+ module will be called sch_etf.
+
config NET_SCH_GRED
tristate "Generic Random Early Detection (GRED)"
---help---
If unsure, say N.
+config NET_SCH_CAKE
+ tristate "Common Applications Kept Enhanced (CAKE)"
+ help
+ Say Y here if you want to use the Common Applications Kept Enhanced
+ (CAKE) queue management algorithm.
+
+ To compile this driver as a module, choose M here: the module
+ will be called sch_cake.
+
+ If unsure, say N.
+
config NET_SCH_FQ
tristate "Fair Queue"
help
obj-$(CONFIG_NET_SCH_QFQ) += sch_qfq.o
obj-$(CONFIG_NET_SCH_CODEL) += sch_codel.o
obj-$(CONFIG_NET_SCH_FQ_CODEL) += sch_fq_codel.o
+obj-$(CONFIG_NET_SCH_CAKE) += sch_cake.o
obj-$(CONFIG_NET_SCH_FQ) += sch_fq.o
obj-$(CONFIG_NET_SCH_HHF) += sch_hhf.o
obj-$(CONFIG_NET_SCH_PIE) += sch_pie.o
obj-$(CONFIG_NET_SCH_CBS) += sch_cbs.o
+obj-$(CONFIG_NET_SCH_ETF) += sch_etf.o
obj-$(CONFIG_NET_CLS_U32) += cls_u32.o
obj-$(CONFIG_NET_CLS_ROUTE4) += cls_route.o
res->goto_tp = rcu_dereference_bh(chain->filter_chain);
}
+static void tcf_free_cookie_rcu(struct rcu_head *p)
+{
+ struct tc_cookie *cookie = container_of(p, struct tc_cookie, rcu);
+
+ kfree(cookie->data);
+ kfree(cookie);
+}
+
+static void tcf_set_action_cookie(struct tc_cookie __rcu **old_cookie,
+ struct tc_cookie *new_cookie)
+{
+ struct tc_cookie *old;
+
+ old = xchg((__force struct tc_cookie **)old_cookie, new_cookie);
+ if (old)
+ call_rcu(&old->rcu, tcf_free_cookie_rcu);
+}
+
/* XXX: For standalone actions, we don't need a RCU grace period either, because
* actions are always connected to filters and filters are already destroyed in
* RCU callbacks, so after a RCU grace period actions are already disconnected
free_percpu(p->cpu_bstats);
free_percpu(p->cpu_qstats);
- if (p->act_cookie) {
- kfree(p->act_cookie->data);
- kfree(p->act_cookie);
- }
+ tcf_set_action_cookie(&p->act_cookie, NULL);
if (p->goto_chain)
tcf_action_goto_chain_fini(p);
kfree(p);
}
-static void tcf_idr_remove(struct tcf_idrinfo *idrinfo, struct tc_action *p)
+static void tcf_action_cleanup(struct tc_action *p)
{
- spin_lock(&idrinfo->lock);
- idr_remove(&idrinfo->action_idr, p->tcfa_index);
- spin_unlock(&idrinfo->lock);
+ if (p->ops->cleanup)
+ p->ops->cleanup(p);
+
gen_kill_estimator(&p->tcfa_rate_est);
free_tcf(p);
}
+static int __tcf_action_put(struct tc_action *p, bool bind)
+{
+ struct tcf_idrinfo *idrinfo = p->idrinfo;
+
+ if (refcount_dec_and_lock(&p->tcfa_refcnt, &idrinfo->lock)) {
+ if (bind)
+ atomic_dec(&p->tcfa_bindcnt);
+ idr_remove(&idrinfo->action_idr, p->tcfa_index);
+ spin_unlock(&idrinfo->lock);
+
+ tcf_action_cleanup(p);
+ return 1;
+ }
+
+ if (bind)
+ atomic_dec(&p->tcfa_bindcnt);
+
+ return 0;
+}
+
int __tcf_idr_release(struct tc_action *p, bool bind, bool strict)
{
int ret = 0;
- ASSERT_RTNL();
-
+ /* Release with strict==1 and bind==0 is only called through act API
+ * interface (classifiers always bind). Only case when action with
+ * positive reference count and zero bind count can exist is when it was
+ * also created with act API (unbinding last classifier will destroy the
+ * action if it was created by classifier). So only case when bind count
+ * can be changed after initial check is when unbound action is
+ * destroyed by act API while classifier binds to action with same id
+ * concurrently. This result either creation of new action(same behavior
+ * as before), or reusing existing action if concurrent process
+ * increments reference count before action is deleted. Both scenarios
+ * are acceptable.
+ */
if (p) {
- if (bind)
- p->tcfa_bindcnt--;
- else if (strict && p->tcfa_bindcnt > 0)
+ if (!bind && strict && atomic_read(&p->tcfa_bindcnt) > 0)
return -EPERM;
- p->tcfa_refcnt--;
- if (p->tcfa_bindcnt <= 0 && p->tcfa_refcnt <= 0) {
- if (p->ops->cleanup)
- p->ops->cleanup(p);
- tcf_idr_remove(p->idrinfo, p);
+ if (__tcf_action_put(p, bind))
ret = ACT_P_DELETED;
- }
}
return ret;
static size_t tcf_action_shared_attrs_size(const struct tc_action *act)
{
+ struct tc_cookie *act_cookie;
u32 cookie_len = 0;
- if (act->act_cookie)
- cookie_len = nla_total_size(act->act_cookie->len);
+ rcu_read_lock();
+ act_cookie = rcu_dereference(act->act_cookie);
+
+ if (act_cookie)
+ cookie_len = nla_total_size(act_cookie->len);
+ rcu_read_unlock();
return nla_total_size(0) /* action number nested */
+ nla_total_size(IFNAMSIZ) /* TCA_ACT_KIND */
}
EXPORT_SYMBOL(tcf_generic_walker);
-static struct tc_action *tcf_idr_lookup(u32 index, struct tcf_idrinfo *idrinfo)
+static bool __tcf_idr_check(struct tc_action_net *tn, u32 index,
+ struct tc_action **a, int bind)
{
- struct tc_action *p = NULL;
+ struct tcf_idrinfo *idrinfo = tn->idrinfo;
+ struct tc_action *p;
spin_lock(&idrinfo->lock);
p = idr_find(&idrinfo->action_idr, index);
+ if (IS_ERR(p)) {
+ p = NULL;
+ } else if (p) {
+ refcount_inc(&p->tcfa_refcnt);
+ if (bind)
+ atomic_inc(&p->tcfa_bindcnt);
+ }
spin_unlock(&idrinfo->lock);
- return p;
+ if (p) {
+ *a = p;
+ return true;
+ }
+ return false;
}
int tcf_idr_search(struct tc_action_net *tn, struct tc_action **a, u32 index)
{
- struct tcf_idrinfo *idrinfo = tn->idrinfo;
- struct tc_action *p = tcf_idr_lookup(index, idrinfo);
-
- if (p) {
- *a = p;
- return 1;
- }
- return 0;
+ return __tcf_idr_check(tn, index, a, 0);
}
EXPORT_SYMBOL(tcf_idr_search);
bool tcf_idr_check(struct tc_action_net *tn, u32 index, struct tc_action **a,
int bind)
+{
+ return __tcf_idr_check(tn, index, a, bind);
+}
+EXPORT_SYMBOL(tcf_idr_check);
+
+int tcf_idr_delete_index(struct tc_action_net *tn, u32 index)
{
struct tcf_idrinfo *idrinfo = tn->idrinfo;
- struct tc_action *p = tcf_idr_lookup(index, idrinfo);
+ struct tc_action *p;
+ int ret = 0;
- if (index && p) {
- if (bind)
- p->tcfa_bindcnt++;
- p->tcfa_refcnt++;
- *a = p;
- return true;
+ spin_lock(&idrinfo->lock);
+ p = idr_find(&idrinfo->action_idr, index);
+ if (!p) {
+ spin_unlock(&idrinfo->lock);
+ return -ENOENT;
}
- return false;
+
+ if (!atomic_read(&p->tcfa_bindcnt)) {
+ if (refcount_dec_and_test(&p->tcfa_refcnt)) {
+ struct module *owner = p->ops->owner;
+
+ WARN_ON(p != idr_remove(&idrinfo->action_idr,
+ p->tcfa_index));
+ spin_unlock(&idrinfo->lock);
+
+ tcf_action_cleanup(p);
+ module_put(owner);
+ return 0;
+ }
+ ret = 0;
+ } else {
+ ret = -EPERM;
+ }
+
+ spin_unlock(&idrinfo->lock);
+ return ret;
}
-EXPORT_SYMBOL(tcf_idr_check);
+EXPORT_SYMBOL(tcf_idr_delete_index);
int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
struct tc_action **a, const struct tc_action_ops *ops,
{
struct tc_action *p = kzalloc(ops->size, GFP_KERNEL);
struct tcf_idrinfo *idrinfo = tn->idrinfo;
- struct idr *idr = &idrinfo->action_idr;
int err = -ENOMEM;
if (unlikely(!p))
return -ENOMEM;
- p->tcfa_refcnt = 1;
+ refcount_set(&p->tcfa_refcnt, 1);
if (bind)
- p->tcfa_bindcnt = 1;
+ atomic_set(&p->tcfa_bindcnt, 1);
if (cpustats) {
p->cpu_bstats = netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu);
goto err2;
}
spin_lock_init(&p->tcfa_lock);
- idr_preload(GFP_KERNEL);
- spin_lock(&idrinfo->lock);
- /* user doesn't specify an index */
- if (!index) {
- index = 1;
- err = idr_alloc_u32(idr, NULL, &index, UINT_MAX, GFP_ATOMIC);
- } else {
- err = idr_alloc_u32(idr, NULL, &index, index, GFP_ATOMIC);
- }
- spin_unlock(&idrinfo->lock);
- idr_preload_end();
- if (err)
- goto err3;
-
p->tcfa_index = index;
p->tcfa_tm.install = jiffies;
p->tcfa_tm.lastuse = jiffies;
&p->tcfa_rate_est,
&p->tcfa_lock, NULL, est);
if (err)
- goto err4;
+ goto err3;
}
p->idrinfo = idrinfo;
INIT_LIST_HEAD(&p->list);
*a = p;
return 0;
-err4:
- idr_remove(idr, index);
err3:
free_percpu(p->cpu_qstats);
err2:
struct tcf_idrinfo *idrinfo = tn->idrinfo;
spin_lock(&idrinfo->lock);
- idr_replace(&idrinfo->action_idr, a, a->tcfa_index);
+ /* Replace ERR_PTR(-EBUSY) allocated by tcf_idr_check_alloc */
+ WARN_ON(!IS_ERR(idr_replace(&idrinfo->action_idr, a, a->tcfa_index)));
spin_unlock(&idrinfo->lock);
}
EXPORT_SYMBOL(tcf_idr_insert);
+/* Cleanup idr index that was allocated but not initialized. */
+
+void tcf_idr_cleanup(struct tc_action_net *tn, u32 index)
+{
+ struct tcf_idrinfo *idrinfo = tn->idrinfo;
+
+ spin_lock(&idrinfo->lock);
+ /* Remove ERR_PTR(-EBUSY) allocated by tcf_idr_check_alloc */
+ WARN_ON(!IS_ERR(idr_remove(&idrinfo->action_idr, index)));
+ spin_unlock(&idrinfo->lock);
+}
+EXPORT_SYMBOL(tcf_idr_cleanup);
+
+/* Check if action with specified index exists. If actions is found, increments
+ * its reference and bind counters, and return 1. Otherwise insert temporary
+ * error pointer (to prevent concurrent users from inserting actions with same
+ * index) and return 0.
+ */
+
+int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index,
+ struct tc_action **a, int bind)
+{
+ struct tcf_idrinfo *idrinfo = tn->idrinfo;
+ struct tc_action *p;
+ int ret;
+
+again:
+ spin_lock(&idrinfo->lock);
+ if (*index) {
+ p = idr_find(&idrinfo->action_idr, *index);
+ if (IS_ERR(p)) {
+ /* This means that another process allocated
+ * index but did not assign the pointer yet.
+ */
+ spin_unlock(&idrinfo->lock);
+ goto again;
+ }
+
+ if (p) {
+ refcount_inc(&p->tcfa_refcnt);
+ if (bind)
+ atomic_inc(&p->tcfa_bindcnt);
+ *a = p;
+ ret = 1;
+ } else {
+ *a = NULL;
+ ret = idr_alloc_u32(&idrinfo->action_idr, NULL, index,
+ *index, GFP_ATOMIC);
+ if (!ret)
+ idr_replace(&idrinfo->action_idr,
+ ERR_PTR(-EBUSY), *index);
+ }
+ } else {
+ *index = 1;
+ *a = NULL;
+ ret = idr_alloc_u32(&idrinfo->action_idr, NULL, index,
+ UINT_MAX, GFP_ATOMIC);
+ if (!ret)
+ idr_replace(&idrinfo->action_idr, ERR_PTR(-EBUSY),
+ *index);
+ }
+ spin_unlock(&idrinfo->lock);
+ return ret;
+}
+EXPORT_SYMBOL(tcf_idr_check_alloc);
+
void tcf_idrinfo_destroy(const struct tc_action_ops *ops,
struct tcf_idrinfo *idrinfo)
{
}
EXPORT_SYMBOL(tcf_action_exec);
-int tcf_action_destroy(struct list_head *actions, int bind)
+int tcf_action_destroy(struct tc_action *actions[], int bind)
{
const struct tc_action_ops *ops;
- struct tc_action *a, *tmp;
- int ret = 0;
+ struct tc_action *a;
+ int ret = 0, i;
- list_for_each_entry_safe(a, tmp, actions, list) {
+ for (i = 0; i < TCA_ACT_MAX_PRIO && actions[i]; i++) {
+ a = actions[i];
+ actions[i] = NULL;
ops = a->ops;
ret = __tcf_idr_release(a, bind, true);
if (ret == ACT_P_DELETED)
return ret;
}
+static int tcf_action_put(struct tc_action *p)
+{
+ return __tcf_action_put(p, false);
+}
+
+static void tcf_action_put_many(struct tc_action *actions[])
+{
+ int i;
+
+ for (i = 0; i < TCA_ACT_MAX_PRIO && actions[i]; i++) {
+ struct tc_action *a = actions[i];
+ const struct tc_action_ops *ops = a->ops;
+
+ if (tcf_action_put(a))
+ module_put(ops->owner);
+ }
+}
+
int
tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
{
int err = -EINVAL;
unsigned char *b = skb_tail_pointer(skb);
struct nlattr *nest;
+ struct tc_cookie *cookie;
if (nla_put_string(skb, TCA_KIND, a->ops->kind))
goto nla_put_failure;
if (tcf_action_copy_stats(skb, a, 0))
goto nla_put_failure;
- if (a->act_cookie) {
- if (nla_put(skb, TCA_ACT_COOKIE, a->act_cookie->len,
- a->act_cookie->data))
+
+ rcu_read_lock();
+ cookie = rcu_dereference(a->act_cookie);
+ if (cookie) {
+ if (nla_put(skb, TCA_ACT_COOKIE, cookie->len, cookie->data)) {
+ rcu_read_unlock();
goto nla_put_failure;
+ }
}
+ rcu_read_unlock();
nest = nla_nest_start(skb, TCA_OPTIONS);
if (nest == NULL)
}
EXPORT_SYMBOL(tcf_action_dump_1);
-int tcf_action_dump(struct sk_buff *skb, struct list_head *actions,
+int tcf_action_dump(struct sk_buff *skb, struct tc_action *actions[],
int bind, int ref)
{
struct tc_action *a;
- int err = -EINVAL;
+ int err = -EINVAL, i;
struct nlattr *nest;
- list_for_each_entry(a, actions, list) {
+ for (i = 0; i < TCA_ACT_MAX_PRIO && actions[i]; i++) {
+ a = actions[i];
nest = nla_nest_start(skb, a->order);
if (nest == NULL)
goto nla_put_failure;
struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
struct nlattr *nla, struct nlattr *est,
char *name, int ovr, int bind,
+ bool rtnl_held,
struct netlink_ext_ack *extack)
{
struct tc_action *a;
a_o = tc_lookup_action_n(act_name);
if (a_o == NULL) {
#ifdef CONFIG_MODULES
- rtnl_unlock();
+ if (rtnl_held)
+ rtnl_unlock();
request_module("act_%s", act_name);
- rtnl_lock();
+ if (rtnl_held)
+ rtnl_lock();
a_o = tc_lookup_action_n(act_name);
/* backward compatibility for policer */
if (name == NULL)
err = a_o->init(net, tb[TCA_ACT_OPTIONS], est, &a, ovr, bind,
- extack);
+ rtnl_held, extack);
else
- err = a_o->init(net, nla, est, &a, ovr, bind, extack);
+ err = a_o->init(net, nla, est, &a, ovr, bind, rtnl_held,
+ extack);
if (err < 0)
goto err_mod;
- if (name == NULL && tb[TCA_ACT_COOKIE]) {
- if (a->act_cookie) {
- kfree(a->act_cookie->data);
- kfree(a->act_cookie);
- }
- a->act_cookie = cookie;
- }
+ if (!name && tb[TCA_ACT_COOKIE])
+ tcf_set_action_cookie(&a->act_cookie, cookie);
/* module count goes up only when brand new policy is created
* if it exists and is only bound to in a_o->init() then
if (TC_ACT_EXT_CMP(a->tcfa_action, TC_ACT_GOTO_CHAIN)) {
err = tcf_action_goto_chain_init(a, tp);
if (err) {
- LIST_HEAD(actions);
+ struct tc_action *actions[] = { a, NULL };
- list_add_tail(&a->list, &actions);
- tcf_action_destroy(&actions, bind);
+ tcf_action_destroy(actions, bind);
NL_SET_ERR_MSG(extack, "Failed to init TC action chain");
return ERR_PTR(err);
}
return ERR_PTR(err);
}
-static void cleanup_a(struct list_head *actions, int ovr)
-{
- struct tc_action *a;
-
- if (!ovr)
- return;
-
- list_for_each_entry(a, actions, list)
- a->tcfa_refcnt--;
-}
+/* Returns numbers of initialized actions or negative error. */
int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
struct nlattr *est, char *name, int ovr, int bind,
- struct list_head *actions, size_t *attr_size,
- struct netlink_ext_ack *extack)
+ struct tc_action *actions[], size_t *attr_size,
+ bool rtnl_held, struct netlink_ext_ack *extack)
{
struct nlattr *tb[TCA_ACT_MAX_PRIO + 1];
struct tc_action *act;
for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) {
act = tcf_action_init_1(net, tp, tb[i], est, name, ovr, bind,
- extack);
+ rtnl_held, extack);
if (IS_ERR(act)) {
err = PTR_ERR(act);
goto err;
}
act->order = i;
sz += tcf_action_fill_size(act);
- if (ovr)
- act->tcfa_refcnt++;
- list_add_tail(&act->list, actions);
+ /* Start from index 0 */
+ actions[i - 1] = act;
}
*attr_size = tcf_action_full_attrs_size(sz);
-
- /* Remove the temp refcnt which was necessary to protect against
- * destroying an existing action which was being replaced
- */
- cleanup_a(actions, ovr);
- return 0;
+ return i - 1;
err:
tcf_action_destroy(actions, bind);
return -1;
}
-static int tca_get_fill(struct sk_buff *skb, struct list_head *actions,
+static int tca_get_fill(struct sk_buff *skb, struct tc_action *actions[],
u32 portid, u32 seq, u16 flags, int event, int bind,
int ref)
{
static int
tcf_get_notify(struct net *net, u32 portid, struct nlmsghdr *n,
- struct list_head *actions, int event,
+ struct tc_action *actions[], int event,
struct netlink_ext_ack *extack)
{
struct sk_buff *skb;
if (!skb)
return -ENOBUFS;
if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, 0, event,
- 0, 0) <= 0) {
+ 0, 1) <= 0) {
NL_SET_ERR_MSG(extack, "Failed to fill netlink attributes while adding TC action");
kfree_skb(skb);
return -EINVAL;
return err;
}
+static int tcf_action_delete(struct net *net, struct tc_action *actions[],
+ int *acts_deleted, struct netlink_ext_ack *extack)
+{
+ u32 act_index;
+ int ret, i;
+
+ for (i = 0; i < TCA_ACT_MAX_PRIO && actions[i]; i++) {
+ struct tc_action *a = actions[i];
+ const struct tc_action_ops *ops = a->ops;
+
+ /* Actions can be deleted concurrently so we must save their
+ * type and id to search again after reference is released.
+ */
+ act_index = a->tcfa_index;
+
+ if (tcf_action_put(a)) {
+ /* last reference, action was deleted concurrently */
+ module_put(ops->owner);
+ } else {
+ /* now do the delete */
+ ret = ops->delete(net, act_index);
+ if (ret < 0) {
+ *acts_deleted = i + 1;
+ return ret;
+ }
+ }
+ }
+ *acts_deleted = i;
+ return 0;
+}
+
static int
-tcf_del_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions,
- u32 portid, size_t attr_size, struct netlink_ext_ack *extack)
+tcf_del_notify(struct net *net, struct nlmsghdr *n, struct tc_action *actions[],
+ int *acts_deleted, u32 portid, size_t attr_size,
+ struct netlink_ext_ack *extack)
{
int ret;
struct sk_buff *skb;
return -ENOBUFS;
if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, 0, RTM_DELACTION,
- 0, 1) <= 0) {
+ 0, 2) <= 0) {
NL_SET_ERR_MSG(extack, "Failed to fill netlink TC action attributes");
kfree_skb(skb);
return -EINVAL;
}
/* now do the delete */
- ret = tcf_action_destroy(actions, 0);
+ ret = tcf_action_delete(net, actions, acts_deleted, extack);
if (ret < 0) {
NL_SET_ERR_MSG(extack, "Failed to delete TC action");
kfree_skb(skb);
struct nlattr *tb[TCA_ACT_MAX_PRIO + 1];
struct tc_action *act;
size_t attr_size = 0;
- LIST_HEAD(actions);
+ struct tc_action *actions[TCA_ACT_MAX_PRIO + 1] = {};
+ int acts_deleted = 0;
ret = nla_parse_nested(tb, TCA_ACT_MAX_PRIO, nla, NULL, extack);
if (ret < 0)
}
act->order = i;
attr_size += tcf_action_fill_size(act);
- list_add_tail(&act->list, &actions);
+ actions[i - 1] = act;
}
attr_size = tcf_action_full_attrs_size(attr_size);
if (event == RTM_GETACTION)
- ret = tcf_get_notify(net, portid, n, &actions, event, extack);
+ ret = tcf_get_notify(net, portid, n, actions, event, extack);
else { /* delete */
- ret = tcf_del_notify(net, n, &actions, portid, attr_size, extack);
+ ret = tcf_del_notify(net, n, actions, &acts_deleted, portid,
+ attr_size, extack);
if (ret)
goto err;
return ret;
}
err:
- if (event != RTM_GETACTION)
- tcf_action_destroy(&actions, 0);
+ tcf_action_put_many(&actions[acts_deleted]);
return ret;
}
static int
-tcf_add_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions,
+tcf_add_notify(struct net *net, struct nlmsghdr *n, struct tc_action *actions[],
u32 portid, size_t attr_size, struct netlink_ext_ack *extack)
{
struct sk_buff *skb;
{
size_t attr_size = 0;
int ret = 0;
- LIST_HEAD(actions);
+ struct tc_action *actions[TCA_ACT_MAX_PRIO] = {};
- ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, &actions,
- &attr_size, extack);
- if (ret)
+ ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, actions,
+ &attr_size, true, extack);
+ if (ret < 0)
return ret;
+ ret = tcf_add_notify(net, n, actions, portid, attr_size, extack);
+ if (ovr)
+ tcf_action_put_many(actions);
- return tcf_add_notify(net, n, &actions, portid, attr_size, extack);
+ return ret;
}
static u32 tcaa_root_flags_allowed = TCA_FLAG_LARGE_DUMP_ON;
struct tcf_bpf *prog = to_bpf(act);
struct tc_act_bpf opt = {
.index = prog->tcf_index,
- .refcnt = prog->tcf_refcnt - ref,
- .bindcnt = prog->tcf_bindcnt - bind,
+ .refcnt = refcount_read(&prog->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&prog->tcf_bindcnt) - bind,
.action = prog->tcf_action,
};
struct tcf_t tm;
static int tcf_bpf_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **act,
- int replace, int bind, struct netlink_ext_ack *extack)
+ int replace, int bind, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, bpf_net_id);
struct nlattr *tb[TCA_ACT_BPF_MAX + 1];
parm = nla_data(tb[TCA_ACT_BPF_PARMS]);
- if (!tcf_idr_check(tn, parm->index, act, bind)) {
+ ret = tcf_idr_check_alloc(tn, &parm->index, act, bind);
+ if (!ret) {
ret = tcf_idr_create(tn, parm->index, est, act,
&act_bpf_ops, bind, true);
- if (ret < 0)
+ if (ret < 0) {
+ tcf_idr_cleanup(tn, parm->index);
return ret;
+ }
res = ACT_P_CREATED;
- } else {
+ } else if (ret > 0) {
/* Don't override defaults. */
if (bind)
return 0;
- tcf_idr_release(*act, bind);
- if (!replace)
+ if (!replace) {
+ tcf_idr_release(*act, bind);
return -EEXIST;
+ }
+ } else {
+ return ret;
}
is_bpf = tb[TCA_ACT_BPF_OPS_LEN] && tb[TCA_ACT_BPF_OPS];
return res;
out:
- if (res == ACT_P_CREATED)
- tcf_idr_release(*act, bind);
+ tcf_idr_release(*act, bind);
return ret;
}
return tcf_idr_search(tn, a, index);
}
+static int tcf_bpf_delete(struct net *net, u32 index)
+{
+ struct tc_action_net *tn = net_generic(net, bpf_net_id);
+
+ return tcf_idr_delete_index(tn, index);
+}
+
static struct tc_action_ops act_bpf_ops __read_mostly = {
.kind = "bpf",
.type = TCA_ACT_BPF,
.init = tcf_bpf_init,
.walk = tcf_bpf_walker,
.lookup = tcf_bpf_search,
+ .delete = tcf_bpf_delete,
.size = sizeof(struct tcf_bpf),
};
static int tcf_connmark_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
- int ovr, int bind,
+ int ovr, int bind, bool rtnl_held,
struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, connmark_net_id);
parm = nla_data(tb[TCA_CONNMARK_PARMS]);
- if (!tcf_idr_check(tn, parm->index, a, bind)) {
+ ret = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ if (!ret) {
ret = tcf_idr_create(tn, parm->index, est, a,
&act_connmark_ops, bind, false);
- if (ret)
+ if (ret) {
+ tcf_idr_cleanup(tn, parm->index);
return ret;
+ }
ci = to_connmark(*a);
ci->tcf_action = parm->action;
tcf_idr_insert(tn, *a);
ret = ACT_P_CREATED;
- } else {
+ } else if (ret > 0) {
ci = to_connmark(*a);
if (bind)
return 0;
- tcf_idr_release(*a, bind);
- if (!ovr)
+ if (!ovr) {
+ tcf_idr_release(*a, bind);
return -EEXIST;
+ }
/* replacing action and zone */
ci->tcf_action = parm->action;
ci->zone = parm->zone;
+ ret = 0;
}
return ret;
struct tc_connmark opt = {
.index = ci->tcf_index,
- .refcnt = ci->tcf_refcnt - ref,
- .bindcnt = ci->tcf_bindcnt - bind,
+ .refcnt = refcount_read(&ci->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&ci->tcf_bindcnt) - bind,
.action = ci->tcf_action,
.zone = ci->zone,
};
return tcf_idr_search(tn, a, index);
}
+static int tcf_connmark_delete(struct net *net, u32 index)
+{
+ struct tc_action_net *tn = net_generic(net, connmark_net_id);
+
+ return tcf_idr_delete_index(tn, index);
+}
+
static struct tc_action_ops act_connmark_ops = {
.kind = "connmark",
.type = TCA_ACT_CONNMARK,
.init = tcf_connmark_init,
.walk = tcf_connmark_walker,
.lookup = tcf_connmark_search,
+ .delete = tcf_connmark_delete,
.size = sizeof(struct tcf_connmark_info),
};
static int tcf_csum_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a, int ovr,
- int bind, struct netlink_ext_ack *extack)
+ int bind, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, csum_net_id);
struct tcf_csum_params *params_old, *params_new;
return -EINVAL;
parm = nla_data(tb[TCA_CSUM_PARMS]);
- if (!tcf_idr_check(tn, parm->index, a, bind)) {
+ err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ if (!err) {
ret = tcf_idr_create(tn, parm->index, est, a,
&act_csum_ops, bind, true);
- if (ret)
+ if (ret) {
+ tcf_idr_cleanup(tn, parm->index);
return ret;
+ }
ret = ACT_P_CREATED;
- } else {
+ } else if (err > 0) {
if (bind)/* dont override defaults */
return 0;
- tcf_idr_release(*a, bind);
- if (!ovr)
+ if (!ovr) {
+ tcf_idr_release(*a, bind);
return -EEXIST;
+ }
+ } else {
+ return err;
}
p = to_tcf_csum(*a);
params_new = kzalloc(sizeof(*params_new), GFP_KERNEL);
if (unlikely(!params_new)) {
- if (ret == ACT_P_CREATED)
- tcf_idr_release(*a, bind);
+ tcf_idr_release(*a, bind);
return -ENOMEM;
}
params_old = rtnl_dereference(p->params);
struct tcf_csum_params *params;
struct tc_csum opt = {
.index = p->tcf_index,
- .refcnt = p->tcf_refcnt - ref,
- .bindcnt = p->tcf_bindcnt - bind,
+ .refcnt = refcount_read(&p->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&p->tcf_bindcnt) - bind,
};
struct tcf_t t;
return nla_total_size(sizeof(struct tc_csum));
}
+static int tcf_csum_delete(struct net *net, u32 index)
+{
+ struct tc_action_net *tn = net_generic(net, csum_net_id);
+
+ return tcf_idr_delete_index(tn, index);
+}
+
static struct tc_action_ops act_csum_ops = {
.kind = "csum",
.type = TCA_ACT_CSUM,
.walk = tcf_csum_walker,
.lookup = tcf_csum_search,
.get_fill_size = tcf_csum_get_fill_size,
+ .delete = tcf_csum_delete,
.size = sizeof(struct tcf_csum),
};
static int tcf_gact_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
- int ovr, int bind, struct netlink_ext_ack *extack)
+ int ovr, int bind, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, gact_net_id);
struct nlattr *tb[TCA_GACT_MAX + 1];
}
#endif
- if (!tcf_idr_check(tn, parm->index, a, bind)) {
+ err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ if (!err) {
ret = tcf_idr_create(tn, parm->index, est, a,
&act_gact_ops, bind, true);
- if (ret)
+ if (ret) {
+ tcf_idr_cleanup(tn, parm->index);
return ret;
+ }
ret = ACT_P_CREATED;
- } else {
+ } else if (err > 0) {
if (bind)/* dont override defaults */
return 0;
- tcf_idr_release(*a, bind);
- if (!ovr)
+ if (!ovr) {
+ tcf_idr_release(*a, bind);
return -EEXIST;
+ }
+ } else {
+ return err;
}
gact = to_gact(*a);
struct tcf_gact *gact = to_gact(a);
struct tc_gact opt = {
.index = gact->tcf_index,
- .refcnt = gact->tcf_refcnt - ref,
- .bindcnt = gact->tcf_bindcnt - bind,
+ .refcnt = refcount_read(&gact->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&gact->tcf_bindcnt) - bind,
.action = gact->tcf_action,
};
struct tcf_t t;
return sz;
}
+static int tcf_gact_delete(struct net *net, u32 index)
+{
+ struct tc_action_net *tn = net_generic(net, gact_net_id);
+
+ return tcf_idr_delete_index(tn, index);
+}
+
static struct tc_action_ops act_gact_ops = {
.kind = "gact",
.type = TCA_ACT_GACT,
.walk = tcf_gact_walker,
.lookup = tcf_gact_search,
.get_fill_size = tcf_gact_get_fill_size,
+ .delete = tcf_gact_delete,
.size = sizeof(struct tcf_gact),
};
spin_unlock_bh(&ife->tcf_lock);
p = rcu_dereference_protected(ife->params, 1);
- kfree_rcu(p, rcu);
+ if (p)
+ kfree_rcu(p, rcu);
}
/* under ife->tcf_lock for existing action */
static int tcf_ife_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
- int ovr, int bind, struct netlink_ext_ack *extack)
+ int ovr, int bind, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, ife_net_id);
struct nlattr *tb[TCA_IFE_MAX + 1];
if (!p)
return -ENOMEM;
- exists = tcf_idr_check(tn, parm->index, a, bind);
+ err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ if (err < 0) {
+ kfree(p);
+ return err;
+ }
+ exists = err;
if (exists && bind) {
kfree(p);
return 0;
ret = tcf_idr_create(tn, parm->index, est, a, &act_ife_ops,
bind, true);
if (ret) {
+ tcf_idr_cleanup(tn, parm->index);
kfree(p);
return ret;
}
ret = ACT_P_CREATED;
- } else {
+ } else if (!ovr) {
tcf_idr_release(*a, bind);
- if (!ovr) {
- kfree(p);
- return -EEXIST;
- }
+ kfree(p);
+ return -EEXIST;
}
ife = to_ife(*a);
saddr = nla_data(tb[TCA_IFE_SMAC]);
}
- ife->tcf_action = parm->action;
-
if (parm->flags & IFE_ENCODE) {
if (daddr)
ether_addr_copy(p->eth_dst, daddr);
NULL, NULL);
if (err) {
metadata_parse_err:
- if (exists)
- tcf_idr_release(*a, bind);
if (ret == ACT_P_CREATED)
- _tcf_ife_cleanup(*a);
+ tcf_idr_release(*a, bind);
if (exists)
spin_unlock_bh(&ife->tcf_lock);
+ tcf_idr_release(*a, bind);
+
kfree(p);
return err;
}
err = use_all_metadata(ife);
if (err) {
if (ret == ACT_P_CREATED)
- _tcf_ife_cleanup(*a);
+ tcf_idr_release(*a, bind);
if (exists)
spin_unlock_bh(&ife->tcf_lock);
}
}
+ ife->tcf_action = parm->action;
if (exists)
spin_unlock_bh(&ife->tcf_lock);
struct tcf_ife_params *p = rtnl_dereference(ife->params);
struct tc_ife opt = {
.index = ife->tcf_index,
- .refcnt = ife->tcf_refcnt - ref,
- .bindcnt = ife->tcf_bindcnt - bind,
+ .refcnt = refcount_read(&ife->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&ife->tcf_bindcnt) - bind,
.action = ife->tcf_action,
.flags = p->flags,
};
return tcf_idr_search(tn, a, index);
}
+static int tcf_ife_delete(struct net *net, u32 index)
+{
+ struct tc_action_net *tn = net_generic(net, ife_net_id);
+
+ return tcf_idr_delete_index(tn, index);
+}
+
static struct tc_action_ops act_ife_ops = {
.kind = "ife",
.type = TCA_ACT_IFE,
.init = tcf_ife_init,
.walk = tcf_ife_walker,
.lookup = tcf_ife_search,
+ .delete = tcf_ife_delete,
.size = sizeof(struct tcf_ife_info),
};
if (tb[TCA_IPT_INDEX] != NULL)
index = nla_get_u32(tb[TCA_IPT_INDEX]);
- exists = tcf_idr_check(tn, index, a, bind);
+ err = tcf_idr_check_alloc(tn, &index, a, bind);
+ if (err < 0)
+ return err;
+ exists = err;
if (exists && bind)
return 0;
if (tb[TCA_IPT_HOOK] == NULL || tb[TCA_IPT_TARG] == NULL) {
if (exists)
tcf_idr_release(*a, bind);
+ else
+ tcf_idr_cleanup(tn, index);
return -EINVAL;
}
if (nla_len(tb[TCA_IPT_TARG]) < td->u.target_size) {
if (exists)
tcf_idr_release(*a, bind);
+ else
+ tcf_idr_cleanup(tn, index);
return -EINVAL;
}
if (!exists) {
ret = tcf_idr_create(tn, index, est, a, ops, bind,
false);
- if (ret)
+ if (ret) {
+ tcf_idr_cleanup(tn, index);
return ret;
+ }
ret = ACT_P_CREATED;
} else {
if (bind)/* dont override defaults */
return 0;
- tcf_idr_release(*a, bind);
- if (!ovr)
+ if (!ovr) {
+ tcf_idr_release(*a, bind);
return -EEXIST;
+ }
}
hook = nla_get_u32(tb[TCA_IPT_HOOK]);
static int tcf_ipt_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a, int ovr,
- int bind, struct netlink_ext_ack *extack)
+ int bind, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
return __tcf_ipt_init(net, ipt_net_id, nla, est, a, &act_ipt_ops, ovr,
bind);
static int tcf_xt_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a, int ovr,
- int bind, struct netlink_ext_ack *extack)
+ int bind, bool unlocked,
+ struct netlink_ext_ack *extack)
{
return __tcf_ipt_init(net, xt_net_id, nla, est, a, &act_xt_ops, ovr,
bind);
if (unlikely(!t))
goto nla_put_failure;
- c.bindcnt = ipt->tcf_bindcnt - bind;
- c.refcnt = ipt->tcf_refcnt - ref;
+ c.bindcnt = atomic_read(&ipt->tcf_bindcnt) - bind;
+ c.refcnt = refcount_read(&ipt->tcf_refcnt) - ref;
strcpy(t->u.user.name, ipt->tcfi_t->u.kernel.target->name);
if (nla_put(skb, TCA_IPT_TARG, ipt->tcfi_t->u.user.target_size, t) ||
return tcf_idr_search(tn, a, index);
}
+static int tcf_ipt_delete(struct net *net, u32 index)
+{
+ struct tc_action_net *tn = net_generic(net, ipt_net_id);
+
+ return tcf_idr_delete_index(tn, index);
+}
+
static struct tc_action_ops act_ipt_ops = {
.kind = "ipt",
.type = TCA_ACT_IPT,
.init = tcf_ipt_init,
.walk = tcf_ipt_walker,
.lookup = tcf_ipt_search,
+ .delete = tcf_ipt_delete,
.size = sizeof(struct tcf_ipt),
};
return tcf_idr_search(tn, a, index);
}
+static int tcf_xt_delete(struct net *net, u32 index)
+{
+ struct tc_action_net *tn = net_generic(net, xt_net_id);
+
+ return tcf_idr_delete_index(tn, index);
+}
+
static struct tc_action_ops act_xt_ops = {
.kind = "xt",
.type = TCA_ACT_XT,
.init = tcf_xt_init,
.walk = tcf_xt_walker,
.lookup = tcf_xt_search,
+ .delete = tcf_xt_delete,
.size = sizeof(struct tcf_ipt),
};
static struct tc_action_ops act_mirred_ops;
static int tcf_mirred_init(struct net *net, struct nlattr *nla,
- struct nlattr *est, struct tc_action **a, int ovr,
- int bind, struct netlink_ext_ack *extack)
+ struct nlattr *est, struct tc_action **a,
+ int ovr, int bind, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, mirred_net_id);
struct nlattr *tb[TCA_MIRRED_MAX + 1];
struct tcf_mirred *m;
struct net_device *dev;
bool exists = false;
- int ret;
+ int ret, err;
if (!nla) {
NL_SET_ERR_MSG_MOD(extack, "Mirred requires attributes to be passed");
}
parm = nla_data(tb[TCA_MIRRED_PARMS]);
- exists = tcf_idr_check(tn, parm->index, a, bind);
+ err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ if (err < 0)
+ return err;
+ exists = err;
if (exists && bind)
return 0;
default:
if (exists)
tcf_idr_release(*a, bind);
+ else
+ tcf_idr_cleanup(tn, parm->index);
NL_SET_ERR_MSG_MOD(extack, "Unknown mirred option");
return -EINVAL;
}
if (dev == NULL) {
if (exists)
tcf_idr_release(*a, bind);
+ else
+ tcf_idr_cleanup(tn, parm->index);
return -ENODEV;
}
mac_header_xmit = dev_is_mac_header_xmit(dev);
if (!exists) {
if (!dev) {
+ tcf_idr_cleanup(tn, parm->index);
NL_SET_ERR_MSG_MOD(extack, "Specified device does not exist");
return -EINVAL;
}
ret = tcf_idr_create(tn, parm->index, est, a,
&act_mirred_ops, bind, true);
- if (ret)
+ if (ret) {
+ tcf_idr_cleanup(tn, parm->index);
return ret;
+ }
ret = ACT_P_CREATED;
- } else {
+ } else if (!ovr) {
tcf_idr_release(*a, bind);
- if (!ovr)
- return -EEXIST;
+ return -EEXIST;
}
m = to_mirred(*a);
struct tc_mirred opt = {
.index = m->tcf_index,
.action = m->tcf_action,
- .refcnt = m->tcf_refcnt - ref,
- .bindcnt = m->tcf_bindcnt - bind,
+ .refcnt = refcount_read(&m->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&m->tcf_bindcnt) - bind,
.eaction = m->tcfm_eaction,
.ifindex = dev ? dev->ifindex : 0,
};
return rtnl_dereference(m->tcfm_dev);
}
+static int tcf_mirred_delete(struct net *net, u32 index)
+{
+ struct tc_action_net *tn = net_generic(net, mirred_net_id);
+
+ return tcf_idr_delete_index(tn, index);
+}
+
static struct tc_action_ops act_mirred_ops = {
.kind = "mirred",
.type = TCA_ACT_MIRRED,
.lookup = tcf_mirred_search,
.size = sizeof(struct tcf_mirred),
.get_dev = tcf_mirred_get_dev,
+ .delete = tcf_mirred_delete,
};
static __net_init int mirred_init_net(struct net *net)
static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est,
struct tc_action **a, int ovr, int bind,
- struct netlink_ext_ack *extack)
+ bool rtnl_held, struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, nat_net_id);
struct nlattr *tb[TCA_NAT_MAX + 1];
return -EINVAL;
parm = nla_data(tb[TCA_NAT_PARMS]);
- if (!tcf_idr_check(tn, parm->index, a, bind)) {
+ err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ if (!err) {
ret = tcf_idr_create(tn, parm->index, est, a,
&act_nat_ops, bind, false);
- if (ret)
+ if (ret) {
+ tcf_idr_cleanup(tn, parm->index);
return ret;
+ }
ret = ACT_P_CREATED;
- } else {
+ } else if (err > 0) {
if (bind)
return 0;
- tcf_idr_release(*a, bind);
- if (!ovr)
+ if (!ovr) {
+ tcf_idr_release(*a, bind);
return -EEXIST;
+ }
+ } else {
+ return err;
}
p = to_tcf_nat(*a);
.index = p->tcf_index,
.action = p->tcf_action,
- .refcnt = p->tcf_refcnt - ref,
- .bindcnt = p->tcf_bindcnt - bind,
+ .refcnt = refcount_read(&p->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&p->tcf_bindcnt) - bind,
};
struct tcf_t t;
return tcf_idr_search(tn, a, index);
}
+static int tcf_nat_delete(struct net *net, u32 index)
+{
+ struct tc_action_net *tn = net_generic(net, nat_net_id);
+
+ return tcf_idr_delete_index(tn, index);
+}
+
static struct tc_action_ops act_nat_ops = {
.kind = "nat",
.type = TCA_ACT_NAT,
.init = tcf_nat_init,
.walk = tcf_nat_walker,
.lookup = tcf_nat_search,
+ .delete = tcf_nat_delete,
.size = sizeof(struct tcf_nat),
};
static int tcf_pedit_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
- int ovr, int bind, struct netlink_ext_ack *extack)
+ int ovr, int bind, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, pedit_net_id);
struct nlattr *tb[TCA_PEDIT_MAX + 1];
- struct nlattr *pattr;
- struct tc_pedit *parm;
- int ret = 0, err;
- struct tcf_pedit *p;
struct tc_pedit_key *keys = NULL;
struct tcf_pedit_key_ex *keys_ex;
+ struct tc_pedit *parm;
+ struct nlattr *pattr;
+ struct tcf_pedit *p;
+ int ret = 0, err;
int ksize;
- if (nla == NULL)
+ if (!nla) {
+ NL_SET_ERR_MSG_MOD(extack, "Pedit requires attributes to be passed");
return -EINVAL;
+ }
err = nla_parse_nested(tb, TCA_PEDIT_MAX, nla, pedit_policy, NULL);
if (err < 0)
pattr = tb[TCA_PEDIT_PARMS];
if (!pattr)
pattr = tb[TCA_PEDIT_PARMS_EX];
- if (!pattr)
+ if (!pattr) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing required TCA_PEDIT_PARMS or TCA_PEDIT_PARMS_EX pedit attribute");
return -EINVAL;
+ }
parm = nla_data(pattr);
ksize = parm->nkeys * sizeof(struct tc_pedit_key);
- if (nla_len(pattr) < sizeof(*parm) + ksize)
+ if (nla_len(pattr) < sizeof(*parm) + ksize) {
+ NL_SET_ERR_MSG_ATTR(extack, pattr, "Length of TCA_PEDIT_PARMS or TCA_PEDIT_PARMS_EX pedit attribute is invalid");
return -EINVAL;
+ }
keys_ex = tcf_pedit_keys_ex_parse(tb[TCA_PEDIT_KEYS_EX], parm->nkeys);
if (IS_ERR(keys_ex))
return PTR_ERR(keys_ex);
- if (!tcf_idr_check(tn, parm->index, a, bind)) {
- if (!parm->nkeys)
- return -EINVAL;
+ err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ if (!err) {
+ if (!parm->nkeys) {
+ tcf_idr_cleanup(tn, parm->index);
+ NL_SET_ERR_MSG_MOD(extack, "Pedit requires keys to be passed");
+ ret = -EINVAL;
+ goto out_free;
+ }
ret = tcf_idr_create(tn, parm->index, est, a,
&act_pedit_ops, bind, false);
- if (ret)
- return ret;
+ if (ret) {
+ tcf_idr_cleanup(tn, parm->index);
+ goto out_free;
+ }
p = to_pedit(*a);
keys = kmalloc(ksize, GFP_KERNEL);
- if (keys == NULL) {
+ if (!keys) {
tcf_idr_release(*a, bind);
- kfree(keys_ex);
- return -ENOMEM;
+ ret = -ENOMEM;
+ goto out_free;
}
ret = ACT_P_CREATED;
- } else {
+ } else if (err > 0) {
if (bind)
- return 0;
- tcf_idr_release(*a, bind);
- if (!ovr)
- return -EEXIST;
+ goto out_free;
+ if (!ovr) {
+ tcf_idr_release(*a, bind);
+ ret = -EEXIST;
+ goto out_free;
+ }
p = to_pedit(*a);
if (p->tcfp_nkeys && p->tcfp_nkeys != parm->nkeys) {
keys = kmalloc(ksize, GFP_KERNEL);
if (!keys) {
- kfree(keys_ex);
- return -ENOMEM;
+ ret = -ENOMEM;
+ goto out_free;
}
}
+ } else {
+ return err;
}
spin_lock_bh(&p->tcf_lock);
if (ret == ACT_P_CREATED)
tcf_idr_insert(tn, *a);
return ret;
+out_free:
+ kfree(keys_ex);
+ return ret;
+
}
static void tcf_pedit_cleanup(struct tc_action *a)
{
struct tcf_pedit *p = to_pedit(a);
struct tc_pedit_key *keys = p->tcfp_keys;
+
kfree(keys);
kfree(p->tcfp_keys_ex);
}
if (p->tcfp_nkeys > 0) {
struct tc_pedit_key *tkey = p->tcfp_keys;
struct tcf_pedit_key_ex *tkey_ex = p->tcfp_keys_ex;
- enum pedit_header_type htype = TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK;
+ enum pedit_header_type htype =
+ TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK;
enum pedit_cmd cmd = TCA_PEDIT_KEY_EX_CMD_SET;
for (i = p->tcfp_nkeys; i > 0; i--, tkey++) {
- u32 *ptr, _data;
+ u32 *ptr, hdata;
int offset = tkey->off;
int hoffset;
u32 val;
rc = pedit_skb_hdr_offset(skb, htype, &hoffset);
if (rc) {
- pr_info("tc filter pedit bad header type specified (0x%x)\n",
+ pr_info("tc action pedit bad header type specified (0x%x)\n",
htype);
goto bad;
}
if (tkey->offmask) {
- char *d, _d;
+ u8 *d, _d;
if (!offset_valid(skb, hoffset + tkey->at)) {
- pr_info("tc filter pedit 'at' offset %d out of bounds\n",
+ pr_info("tc action pedit 'at' offset %d out of bounds\n",
hoffset + tkey->at);
goto bad;
}
- d = skb_header_pointer(skb, hoffset + tkey->at, 1,
- &_d);
+ d = skb_header_pointer(skb, hoffset + tkey->at,
+ sizeof(_d), &_d);
if (!d)
goto bad;
offset += (*d & tkey->offmask) >> tkey->shift;
}
if (offset % 4) {
- pr_info("tc filter pedit"
- " offset must be on 32 bit boundaries\n");
+ pr_info("tc action pedit offset must be on 32 bit boundaries\n");
goto bad;
}
if (!offset_valid(skb, hoffset + offset)) {
- pr_info("tc filter pedit offset %d out of bounds\n",
+ pr_info("tc action pedit offset %d out of bounds\n",
hoffset + offset);
goto bad;
}
- ptr = skb_header_pointer(skb, hoffset + offset, 4, &_data);
+ ptr = skb_header_pointer(skb, hoffset + offset,
+ sizeof(hdata), &hdata);
if (!ptr)
goto bad;
/* just do it, baby */
val = (*ptr + tkey->val) & ~tkey->mask;
break;
default:
- pr_info("tc filter pedit bad command (%d)\n",
+ pr_info("tc action pedit bad command (%d)\n",
cmd);
goto bad;
}
*ptr = ((*ptr & tkey->mask) ^ val);
- if (ptr == &_data)
+ if (ptr == &hdata)
skb_store_bits(skb, hoffset + offset, ptr, 4);
}
goto done;
- } else
+ } else {
WARN(1, "pedit BUG: index %d\n", p->tcf_index);
+ }
bad:
p->tcf_qstats.overlimits++;
opt->nkeys = p->tcfp_nkeys;
opt->flags = p->tcfp_flags;
opt->action = p->tcf_action;
- opt->refcnt = p->tcf_refcnt - ref;
- opt->bindcnt = p->tcf_bindcnt - bind;
+ opt->refcnt = refcount_read(&p->tcf_refcnt) - ref;
+ opt->bindcnt = atomic_read(&p->tcf_bindcnt) - bind;
if (p->tcfp_keys_ex) {
tcf_pedit_key_ex_dump(skb, p->tcfp_keys_ex, p->tcfp_nkeys);
return tcf_idr_search(tn, a, index);
}
+static int tcf_pedit_delete(struct net *net, u32 index)
+{
+ struct tc_action_net *tn = net_generic(net, pedit_net_id);
+
+ return tcf_idr_delete_index(tn, index);
+}
+
static struct tc_action_ops act_pedit_ops = {
.kind = "pedit",
.type = TCA_ACT_PEDIT,
.init = tcf_pedit_init,
.walk = tcf_pedit_walker,
.lookup = tcf_pedit_search,
+ .delete = tcf_pedit_delete,
.size = sizeof(struct tcf_pedit),
};
static int tcf_act_police_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
- int ovr, int bind,
+ int ovr, int bind, bool rtnl_held,
struct netlink_ext_ack *extack)
{
int ret = 0, err;
return -EINVAL;
parm = nla_data(tb[TCA_POLICE_TBF]);
- exists = tcf_idr_check(tn, parm->index, a, bind);
+ err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ if (err < 0)
+ return err;
+ exists = err;
if (exists && bind)
return 0;
if (!exists) {
ret = tcf_idr_create(tn, parm->index, NULL, a,
&act_police_ops, bind, false);
- if (ret)
+ if (ret) {
+ tcf_idr_cleanup(tn, parm->index);
return ret;
+ }
ret = ACT_P_CREATED;
- } else {
+ } else if (!ovr) {
tcf_idr_release(*a, bind);
- if (!ovr)
- return -EEXIST;
+ return -EEXIST;
}
police = to_police(*a);
failure:
qdisc_put_rtab(P_tab);
qdisc_put_rtab(R_tab);
- if (ret == ACT_P_CREATED)
- tcf_idr_release(*a, bind);
+ tcf_idr_release(*a, bind);
return err;
}
.action = police->tcf_action,
.mtu = police->tcfp_mtu,
.burst = PSCHED_NS2TICKS(police->tcfp_burst),
- .refcnt = police->tcf_refcnt - ref,
- .bindcnt = police->tcf_bindcnt - bind,
+ .refcnt = refcount_read(&police->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&police->tcf_bindcnt) - bind,
};
struct tcf_t t;
return tcf_idr_search(tn, a, index);
}
+static int tcf_police_delete(struct net *net, u32 index)
+{
+ struct tc_action_net *tn = net_generic(net, police_net_id);
+
+ return tcf_idr_delete_index(tn, index);
+}
+
MODULE_AUTHOR("Alexey Kuznetsov");
MODULE_DESCRIPTION("Policing actions");
MODULE_LICENSE("GPL");
.init = tcf_act_police_init,
.walk = tcf_act_police_walker,
.lookup = tcf_police_search,
+ .delete = tcf_police_delete,
.size = sizeof(struct tcf_police),
};
static int tcf_sample_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a, int ovr,
- int bind, struct netlink_ext_ack *extack)
+ int bind, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, sample_net_id);
struct nlattr *tb[TCA_SAMPLE_MAX + 1];
struct tc_sample *parm;
struct tcf_sample *s;
bool exists = false;
- int ret;
+ int ret, err;
if (!nla)
return -EINVAL;
parm = nla_data(tb[TCA_SAMPLE_PARMS]);
- exists = tcf_idr_check(tn, parm->index, a, bind);
+ err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ if (err < 0)
+ return err;
+ exists = err;
if (exists && bind)
return 0;
if (!exists) {
ret = tcf_idr_create(tn, parm->index, est, a,
&act_sample_ops, bind, false);
- if (ret)
+ if (ret) {
+ tcf_idr_cleanup(tn, parm->index);
return ret;
+ }
ret = ACT_P_CREATED;
- } else {
+ } else if (!ovr) {
tcf_idr_release(*a, bind);
- if (!ovr)
- return -EEXIST;
+ return -EEXIST;
}
s = to_sample(*a);
s->psample_group_num = nla_get_u32(tb[TCA_SAMPLE_PSAMPLE_GROUP]);
psample_group = psample_group_get(net, s->psample_group_num);
if (!psample_group) {
- if (ret == ACT_P_CREATED)
- tcf_idr_release(*a, bind);
+ tcf_idr_release(*a, bind);
return -ENOMEM;
}
RCU_INIT_POINTER(s->psample_group, psample_group);
struct tc_sample opt = {
.index = s->tcf_index,
.action = s->tcf_action,
- .refcnt = s->tcf_refcnt - ref,
- .bindcnt = s->tcf_bindcnt - bind,
+ .refcnt = refcount_read(&s->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&s->tcf_bindcnt) - bind,
};
struct tcf_t t;
return tcf_idr_search(tn, a, index);
}
+static int tcf_sample_delete(struct net *net, u32 index)
+{
+ struct tc_action_net *tn = net_generic(net, sample_net_id);
+
+ return tcf_idr_delete_index(tn, index);
+}
+
static struct tc_action_ops act_sample_ops = {
.kind = "sample",
.type = TCA_ACT_SAMPLE,
.cleanup = tcf_sample_cleanup,
.walk = tcf_sample_walker,
.lookup = tcf_sample_search,
+ .delete = tcf_sample_delete,
.size = sizeof(struct tcf_sample),
};
static int tcf_simp_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
- int ovr, int bind, struct netlink_ext_ack *extack)
+ int ovr, int bind, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, simp_net_id);
struct nlattr *tb[TCA_DEF_MAX + 1];
return -EINVAL;
parm = nla_data(tb[TCA_DEF_PARMS]);
- exists = tcf_idr_check(tn, parm->index, a, bind);
+ err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ if (err < 0)
+ return err;
+ exists = err;
if (exists && bind)
return 0;
if (tb[TCA_DEF_DATA] == NULL) {
if (exists)
tcf_idr_release(*a, bind);
+ else
+ tcf_idr_cleanup(tn, parm->index);
return -EINVAL;
}
if (!exists) {
ret = tcf_idr_create(tn, parm->index, est, a,
&act_simp_ops, bind, false);
- if (ret)
+ if (ret) {
+ tcf_idr_cleanup(tn, parm->index);
return ret;
+ }
d = to_defact(*a);
ret = alloc_defdata(d, tb[TCA_DEF_DATA]);
} else {
d = to_defact(*a);
- tcf_idr_release(*a, bind);
- if (!ovr)
+ if (!ovr) {
+ tcf_idr_release(*a, bind);
return -EEXIST;
+ }
reset_policy(d, tb[TCA_DEF_DATA], parm);
}
struct tcf_defact *d = to_defact(a);
struct tc_defact opt = {
.index = d->tcf_index,
- .refcnt = d->tcf_refcnt - ref,
- .bindcnt = d->tcf_bindcnt - bind,
+ .refcnt = refcount_read(&d->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&d->tcf_bindcnt) - bind,
.action = d->tcf_action,
};
struct tcf_t t;
return tcf_idr_search(tn, a, index);
}
+static int tcf_simp_delete(struct net *net, u32 index)
+{
+ struct tc_action_net *tn = net_generic(net, simp_net_id);
+
+ return tcf_idr_delete_index(tn, index);
+}
+
static struct tc_action_ops act_simp_ops = {
.kind = "simple",
.type = TCA_ACT_SIMP,
.init = tcf_simp_init,
.walk = tcf_simp_walker,
.lookup = tcf_simp_search,
+ .delete = tcf_simp_delete,
.size = sizeof(struct tcf_defact),
};
#include <linux/rtnetlink.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <net/dsfield.h>
#include <linux/tc_act/tc_skbedit.h>
#include <net/tc_act/tc_skbedit.h>
struct tcf_result *res)
{
struct tcf_skbedit *d = to_skbedit(a);
+ struct tcf_skbedit_params *params;
+ int action;
- spin_lock(&d->tcf_lock);
tcf_lastuse_update(&d->tcf_tm);
- bstats_update(&d->tcf_bstats, skb);
-
- if (d->flags & SKBEDIT_F_PRIORITY)
- skb->priority = d->priority;
- if (d->flags & SKBEDIT_F_QUEUE_MAPPING &&
- skb->dev->real_num_tx_queues > d->queue_mapping)
- skb_set_queue_mapping(skb, d->queue_mapping);
- if (d->flags & SKBEDIT_F_MARK) {
- skb->mark &= ~d->mask;
- skb->mark |= d->mark & d->mask;
+ bstats_cpu_update(this_cpu_ptr(d->common.cpu_bstats), skb);
+
+ rcu_read_lock();
+ params = rcu_dereference(d->params);
+ action = READ_ONCE(d->tcf_action);
+
+ if (params->flags & SKBEDIT_F_PRIORITY)
+ skb->priority = params->priority;
+ if (params->flags & SKBEDIT_F_INHERITDSFIELD) {
+ int wlen = skb_network_offset(skb);
+
+ switch (tc_skb_protocol(skb)) {
+ case htons(ETH_P_IP):
+ wlen += sizeof(struct iphdr);
+ if (!pskb_may_pull(skb, wlen))
+ goto err;
+ skb->priority = ipv4_get_dsfield(ip_hdr(skb)) >> 2;
+ break;
+
+ case htons(ETH_P_IPV6):
+ wlen += sizeof(struct ipv6hdr);
+ if (!pskb_may_pull(skb, wlen))
+ goto err;
+ skb->priority = ipv6_get_dsfield(ipv6_hdr(skb)) >> 2;
+ break;
+ }
}
- if (d->flags & SKBEDIT_F_PTYPE)
- skb->pkt_type = d->ptype;
-
- spin_unlock(&d->tcf_lock);
- return d->tcf_action;
+ if (params->flags & SKBEDIT_F_QUEUE_MAPPING &&
+ skb->dev->real_num_tx_queues > params->queue_mapping)
+ skb_set_queue_mapping(skb, params->queue_mapping);
+ if (params->flags & SKBEDIT_F_MARK) {
+ skb->mark &= ~params->mask;
+ skb->mark |= params->mark & params->mask;
+ }
+ if (params->flags & SKBEDIT_F_PTYPE)
+ skb->pkt_type = params->ptype;
+
+unlock:
+ rcu_read_unlock();
+ return action;
+err:
+ qstats_drop_inc(this_cpu_ptr(d->common.cpu_qstats));
+ action = TC_ACT_SHOT;
+ goto unlock;
}
static const struct nla_policy skbedit_policy[TCA_SKBEDIT_MAX + 1] = {
[TCA_SKBEDIT_MARK] = { .len = sizeof(u32) },
[TCA_SKBEDIT_PTYPE] = { .len = sizeof(u16) },
[TCA_SKBEDIT_MASK] = { .len = sizeof(u32) },
+ [TCA_SKBEDIT_FLAGS] = { .len = sizeof(u64) },
};
static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
- int ovr, int bind, struct netlink_ext_ack *extack)
+ int ovr, int bind, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, skbedit_net_id);
+ struct tcf_skbedit_params *params_old, *params_new;
struct nlattr *tb[TCA_SKBEDIT_MAX + 1];
struct tc_skbedit *parm;
struct tcf_skbedit *d;
mask = nla_data(tb[TCA_SKBEDIT_MASK]);
}
+ if (tb[TCA_SKBEDIT_FLAGS] != NULL) {
+ u64 *pure_flags = nla_data(tb[TCA_SKBEDIT_FLAGS]);
+
+ if (*pure_flags & SKBEDIT_F_INHERITDSFIELD)
+ flags |= SKBEDIT_F_INHERITDSFIELD;
+ }
+
parm = nla_data(tb[TCA_SKBEDIT_PARMS]);
- exists = tcf_idr_check(tn, parm->index, a, bind);
+ err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ if (err < 0)
+ return err;
+ exists = err;
if (exists && bind)
return 0;
if (!flags) {
if (exists)
tcf_idr_release(*a, bind);
+ else
+ tcf_idr_cleanup(tn, parm->index);
return -EINVAL;
}
if (!exists) {
ret = tcf_idr_create(tn, parm->index, est, a,
- &act_skbedit_ops, bind, false);
- if (ret)
+ &act_skbedit_ops, bind, true);
+ if (ret) {
+ tcf_idr_cleanup(tn, parm->index);
return ret;
+ }
d = to_skbedit(*a);
ret = ACT_P_CREATED;
} else {
d = to_skbedit(*a);
- tcf_idr_release(*a, bind);
- if (!ovr)
+ if (!ovr) {
+ tcf_idr_release(*a, bind);
return -EEXIST;
+ }
}
- spin_lock_bh(&d->tcf_lock);
+ ASSERT_RTNL();
+
+ params_new = kzalloc(sizeof(*params_new), GFP_KERNEL);
+ if (unlikely(!params_new)) {
+ if (ret == ACT_P_CREATED)
+ tcf_idr_release(*a, bind);
+ return -ENOMEM;
+ }
- d->flags = flags;
+ params_new->flags = flags;
if (flags & SKBEDIT_F_PRIORITY)
- d->priority = *priority;
+ params_new->priority = *priority;
if (flags & SKBEDIT_F_QUEUE_MAPPING)
- d->queue_mapping = *queue_mapping;
+ params_new->queue_mapping = *queue_mapping;
if (flags & SKBEDIT_F_MARK)
- d->mark = *mark;
+ params_new->mark = *mark;
if (flags & SKBEDIT_F_PTYPE)
- d->ptype = *ptype;
+ params_new->ptype = *ptype;
/* default behaviour is to use all the bits */
- d->mask = 0xffffffff;
+ params_new->mask = 0xffffffff;
if (flags & SKBEDIT_F_MASK)
- d->mask = *mask;
+ params_new->mask = *mask;
d->tcf_action = parm->action;
-
- spin_unlock_bh(&d->tcf_lock);
+ params_old = rtnl_dereference(d->params);
+ rcu_assign_pointer(d->params, params_new);
+ if (params_old)
+ kfree_rcu(params_old, rcu);
if (ret == ACT_P_CREATED)
tcf_idr_insert(tn, *a);
{
unsigned char *b = skb_tail_pointer(skb);
struct tcf_skbedit *d = to_skbedit(a);
+ struct tcf_skbedit_params *params;
struct tc_skbedit opt = {
.index = d->tcf_index,
- .refcnt = d->tcf_refcnt - ref,
- .bindcnt = d->tcf_bindcnt - bind,
+ .refcnt = refcount_read(&d->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&d->tcf_bindcnt) - bind,
.action = d->tcf_action,
};
+ u64 pure_flags = 0;
struct tcf_t t;
+ params = rtnl_dereference(d->params);
+
if (nla_put(skb, TCA_SKBEDIT_PARMS, sizeof(opt), &opt))
goto nla_put_failure;
- if ((d->flags & SKBEDIT_F_PRIORITY) &&
- nla_put_u32(skb, TCA_SKBEDIT_PRIORITY, d->priority))
+ if ((params->flags & SKBEDIT_F_PRIORITY) &&
+ nla_put_u32(skb, TCA_SKBEDIT_PRIORITY, params->priority))
+ goto nla_put_failure;
+ if ((params->flags & SKBEDIT_F_QUEUE_MAPPING) &&
+ nla_put_u16(skb, TCA_SKBEDIT_QUEUE_MAPPING, params->queue_mapping))
goto nla_put_failure;
- if ((d->flags & SKBEDIT_F_QUEUE_MAPPING) &&
- nla_put_u16(skb, TCA_SKBEDIT_QUEUE_MAPPING, d->queue_mapping))
+ if ((params->flags & SKBEDIT_F_MARK) &&
+ nla_put_u32(skb, TCA_SKBEDIT_MARK, params->mark))
goto nla_put_failure;
- if ((d->flags & SKBEDIT_F_MARK) &&
- nla_put_u32(skb, TCA_SKBEDIT_MARK, d->mark))
+ if ((params->flags & SKBEDIT_F_PTYPE) &&
+ nla_put_u16(skb, TCA_SKBEDIT_PTYPE, params->ptype))
goto nla_put_failure;
- if ((d->flags & SKBEDIT_F_PTYPE) &&
- nla_put_u16(skb, TCA_SKBEDIT_PTYPE, d->ptype))
+ if ((params->flags & SKBEDIT_F_MASK) &&
+ nla_put_u32(skb, TCA_SKBEDIT_MASK, params->mask))
goto nla_put_failure;
- if ((d->flags & SKBEDIT_F_MASK) &&
- nla_put_u32(skb, TCA_SKBEDIT_MASK, d->mask))
+ if (params->flags & SKBEDIT_F_INHERITDSFIELD)
+ pure_flags |= SKBEDIT_F_INHERITDSFIELD;
+ if (pure_flags != 0 &&
+ nla_put(skb, TCA_SKBEDIT_FLAGS, sizeof(pure_flags), &pure_flags))
goto nla_put_failure;
tcf_tm_dump(&t, &d->tcf_tm);
return -1;
}
+static void tcf_skbedit_cleanup(struct tc_action *a)
+{
+ struct tcf_skbedit *d = to_skbedit(a);
+ struct tcf_skbedit_params *params;
+
+ params = rcu_dereference_protected(d->params, 1);
+ if (params)
+ kfree_rcu(params, rcu);
+}
+
static int tcf_skbedit_walker(struct net *net, struct sk_buff *skb,
struct netlink_callback *cb, int type,
const struct tc_action_ops *ops,
return tcf_idr_search(tn, a, index);
}
+static int tcf_skbedit_delete(struct net *net, u32 index)
+{
+ struct tc_action_net *tn = net_generic(net, skbedit_net_id);
+
+ return tcf_idr_delete_index(tn, index);
+}
+
static struct tc_action_ops act_skbedit_ops = {
.kind = "skbedit",
.type = TCA_ACT_SKBEDIT,
.act = tcf_skbedit,
.dump = tcf_skbedit_dump,
.init = tcf_skbedit_init,
+ .cleanup = tcf_skbedit_cleanup,
.walk = tcf_skbedit_walker,
.lookup = tcf_skbedit_search,
+ .delete = tcf_skbedit_delete,
.size = sizeof(struct tcf_skbedit),
};
static int tcf_skbmod_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
- int ovr, int bind, struct netlink_ext_ack *extack)
+ int ovr, int bind, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, skbmod_net_id);
struct nlattr *tb[TCA_SKBMOD_MAX + 1];
if (parm->flags & SKBMOD_F_SWAPMAC)
lflags = SKBMOD_F_SWAPMAC;
- exists = tcf_idr_check(tn, parm->index, a, bind);
+ err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ if (err < 0)
+ return err;
+ exists = err;
if (exists && bind)
return 0;
if (!lflags) {
if (exists)
tcf_idr_release(*a, bind);
+ else
+ tcf_idr_cleanup(tn, parm->index);
return -EINVAL;
}
if (!exists) {
ret = tcf_idr_create(tn, parm->index, est, a,
&act_skbmod_ops, bind, true);
- if (ret)
+ if (ret) {
+ tcf_idr_cleanup(tn, parm->index);
return ret;
+ }
ret = ACT_P_CREATED;
- } else {
+ } else if (!ovr) {
tcf_idr_release(*a, bind);
- if (!ovr)
- return -EEXIST;
+ return -EEXIST;
}
d = to_skbmod(*a);
ASSERT_RTNL();
p = kzalloc(sizeof(struct tcf_skbmod_params), GFP_KERNEL);
if (unlikely(!p)) {
- if (ret == ACT_P_CREATED)
- tcf_idr_release(*a, bind);
+ tcf_idr_release(*a, bind);
return -ENOMEM;
}
struct tcf_skbmod_params *p = rtnl_dereference(d->skbmod_p);
struct tc_skbmod opt = {
.index = d->tcf_index,
- .refcnt = d->tcf_refcnt - ref,
- .bindcnt = d->tcf_bindcnt - bind,
+ .refcnt = refcount_read(&d->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&d->tcf_bindcnt) - bind,
.action = d->tcf_action,
};
struct tcf_t t;
return tcf_idr_search(tn, a, index);
}
+static int tcf_skbmod_delete(struct net *net, u32 index)
+{
+ struct tc_action_net *tn = net_generic(net, skbmod_net_id);
+
+ return tcf_idr_delete_index(tn, index);
+}
+
static struct tc_action_ops act_skbmod_ops = {
.kind = "skbmod",
.type = TCA_ACT_SKBMOD,
.cleanup = tcf_skbmod_cleanup,
.walk = tcf_skbmod_walker,
.lookup = tcf_skbmod_search,
+ .delete = tcf_skbmod_delete,
.size = sizeof(struct tcf_skbmod),
};
#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <linux/rtnetlink.h>
+#include <net/geneve.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
#include <net/dst.h>
return action;
}
+static const struct nla_policy
+enc_opts_policy[TCA_TUNNEL_KEY_ENC_OPTS_MAX + 1] = {
+ [TCA_TUNNEL_KEY_ENC_OPTS_GENEVE] = { .type = NLA_NESTED },
+};
+
+static const struct nla_policy
+geneve_opt_policy[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX + 1] = {
+ [TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS] = { .type = NLA_U16 },
+ [TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE] = { .type = NLA_U8 },
+ [TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA] = { .type = NLA_BINARY,
+ .len = 128 },
+};
+
+static int
+tunnel_key_copy_geneve_opt(const struct nlattr *nla, void *dst, int dst_len,
+ struct netlink_ext_ack *extack)
+{
+ struct nlattr *tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX + 1];
+ int err, data_len, opt_len;
+ u8 *data;
+
+ err = nla_parse_nested(tb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX,
+ nla, geneve_opt_policy, extack);
+ if (err < 0)
+ return err;
+
+ if (!tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS] ||
+ !tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE] ||
+ !tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA]) {
+ NL_SET_ERR_MSG(extack, "Missing tunnel key geneve option class, type or data");
+ return -EINVAL;
+ }
+
+ data = nla_data(tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA]);
+ data_len = nla_len(tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA]);
+ if (data_len < 4) {
+ NL_SET_ERR_MSG(extack, "Tunnel key geneve option data is less than 4 bytes long");
+ return -ERANGE;
+ }
+ if (data_len % 4) {
+ NL_SET_ERR_MSG(extack, "Tunnel key geneve option data is not a multiple of 4 bytes long");
+ return -ERANGE;
+ }
+
+ opt_len = sizeof(struct geneve_opt) + data_len;
+ if (dst) {
+ struct geneve_opt *opt = dst;
+
+ WARN_ON(dst_len < opt_len);
+
+ opt->opt_class =
+ nla_get_be16(tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS]);
+ opt->type = nla_get_u8(tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE]);
+ opt->length = data_len / 4; /* length is in units of 4 bytes */
+ opt->r1 = 0;
+ opt->r2 = 0;
+ opt->r3 = 0;
+
+ memcpy(opt + 1, data, data_len);
+ }
+
+ return opt_len;
+}
+
+static int tunnel_key_copy_opts(const struct nlattr *nla, u8 *dst,
+ int dst_len, struct netlink_ext_ack *extack)
+{
+ int err, rem, opt_len, len = nla_len(nla), opts_len = 0;
+ const struct nlattr *attr, *head = nla_data(nla);
+
+ err = nla_validate(head, len, TCA_TUNNEL_KEY_ENC_OPTS_MAX,
+ enc_opts_policy, extack);
+ if (err)
+ return err;
+
+ nla_for_each_attr(attr, head, len, rem) {
+ switch (nla_type(attr)) {
+ case TCA_TUNNEL_KEY_ENC_OPTS_GENEVE:
+ opt_len = tunnel_key_copy_geneve_opt(attr, dst,
+ dst_len, extack);
+ if (opt_len < 0)
+ return opt_len;
+ opts_len += opt_len;
+ if (dst) {
+ dst_len -= opt_len;
+ dst += opt_len;
+ }
+ break;
+ }
+ }
+
+ if (!opts_len) {
+ NL_SET_ERR_MSG(extack, "Empty list of tunnel options");
+ return -EINVAL;
+ }
+
+ if (rem > 0) {
+ NL_SET_ERR_MSG(extack, "Trailing data after parsing tunnel key options attributes");
+ return -EINVAL;
+ }
+
+ return opts_len;
+}
+
+static int tunnel_key_get_opts_len(struct nlattr *nla,
+ struct netlink_ext_ack *extack)
+{
+ return tunnel_key_copy_opts(nla, NULL, 0, extack);
+}
+
+static int tunnel_key_opts_set(struct nlattr *nla, struct ip_tunnel_info *info,
+ int opts_len, struct netlink_ext_ack *extack)
+{
+ info->options_len = opts_len;
+ switch (nla_type(nla_data(nla))) {
+ case TCA_TUNNEL_KEY_ENC_OPTS_GENEVE:
+#if IS_ENABLED(CONFIG_INET)
+ info->key.tun_flags |= TUNNEL_GENEVE_OPT;
+ return tunnel_key_copy_opts(nla, ip_tunnel_info_opts(info),
+ opts_len, extack);
+#else
+ return -EAFNOSUPPORT;
+#endif
+ default:
+ NL_SET_ERR_MSG(extack, "Cannot set tunnel options for unknown tunnel type");
+ return -EINVAL;
+ }
+}
+
static const struct nla_policy tunnel_key_policy[TCA_TUNNEL_KEY_MAX + 1] = {
[TCA_TUNNEL_KEY_PARMS] = { .len = sizeof(struct tc_tunnel_key) },
[TCA_TUNNEL_KEY_ENC_IPV4_SRC] = { .type = NLA_U32 },
[TCA_TUNNEL_KEY_ENC_KEY_ID] = { .type = NLA_U32 },
[TCA_TUNNEL_KEY_ENC_DST_PORT] = {.type = NLA_U16},
[TCA_TUNNEL_KEY_NO_CSUM] = { .type = NLA_U8 },
+ [TCA_TUNNEL_KEY_ENC_OPTS] = { .type = NLA_NESTED },
};
static int tunnel_key_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
- int ovr, int bind, struct netlink_ext_ack *extack)
+ int ovr, int bind, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, tunnel_key_net_id);
struct nlattr *tb[TCA_TUNNEL_KEY_MAX + 1];
struct tcf_tunnel_key *t;
bool exists = false;
__be16 dst_port = 0;
+ int opts_len = 0;
__be64 key_id;
__be16 flags;
int ret = 0;
int err;
- if (!nla)
+ if (!nla) {
+ NL_SET_ERR_MSG(extack, "Tunnel requires attributes to be passed");
return -EINVAL;
+ }
err = nla_parse_nested(tb, TCA_TUNNEL_KEY_MAX, nla, tunnel_key_policy,
- NULL);
- if (err < 0)
+ extack);
+ if (err < 0) {
+ NL_SET_ERR_MSG(extack, "Failed to parse nested tunnel key attributes");
return err;
+ }
- if (!tb[TCA_TUNNEL_KEY_PARMS])
+ if (!tb[TCA_TUNNEL_KEY_PARMS]) {
+ NL_SET_ERR_MSG(extack, "Missing tunnel key parameters");
return -EINVAL;
+ }
parm = nla_data(tb[TCA_TUNNEL_KEY_PARMS]);
- exists = tcf_idr_check(tn, parm->index, a, bind);
+ err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ if (err < 0)
+ return err;
+ exists = err;
if (exists && bind)
return 0;
break;
case TCA_TUNNEL_KEY_ACT_SET:
if (!tb[TCA_TUNNEL_KEY_ENC_KEY_ID]) {
+ NL_SET_ERR_MSG(extack, "Missing tunnel key id");
ret = -EINVAL;
goto err_out;
}
if (tb[TCA_TUNNEL_KEY_ENC_DST_PORT])
dst_port = nla_get_be16(tb[TCA_TUNNEL_KEY_ENC_DST_PORT]);
+ if (tb[TCA_TUNNEL_KEY_ENC_OPTS]) {
+ opts_len = tunnel_key_get_opts_len(tb[TCA_TUNNEL_KEY_ENC_OPTS],
+ extack);
+ if (opts_len < 0) {
+ ret = opts_len;
+ goto err_out;
+ }
+ }
+
if (tb[TCA_TUNNEL_KEY_ENC_IPV4_SRC] &&
tb[TCA_TUNNEL_KEY_ENC_IPV4_DST]) {
__be32 saddr;
metadata = __ip_tun_set_dst(saddr, daddr, 0, 0,
dst_port, flags,
- key_id, 0);
+ key_id, opts_len);
} else if (tb[TCA_TUNNEL_KEY_ENC_IPV6_SRC] &&
tb[TCA_TUNNEL_KEY_ENC_IPV6_DST]) {
struct in6_addr saddr;
metadata = __ipv6_tun_set_dst(&saddr, &daddr, 0, 0, dst_port,
0, flags,
key_id, 0);
+ } else {
+ NL_SET_ERR_MSG(extack, "Missing either ipv4 or ipv6 src and dst");
+ ret = -EINVAL;
+ goto err_out;
}
if (!metadata) {
- ret = -EINVAL;
+ NL_SET_ERR_MSG(extack, "Cannot allocate tunnel metadata dst");
+ ret = -ENOMEM;
goto err_out;
}
+ if (opts_len) {
+ ret = tunnel_key_opts_set(tb[TCA_TUNNEL_KEY_ENC_OPTS],
+ &metadata->u.tun_info,
+ opts_len, extack);
+ if (ret < 0)
+ goto err_out;
+ }
+
metadata->u.tun_info.mode |= IP_TUNNEL_INFO_TX;
break;
default:
+ NL_SET_ERR_MSG(extack, "Unknown tunnel key action");
ret = -EINVAL;
goto err_out;
}
if (!exists) {
ret = tcf_idr_create(tn, parm->index, est, a,
&act_tunnel_key_ops, bind, true);
- if (ret)
- return ret;
+ if (ret) {
+ NL_SET_ERR_MSG(extack, "Cannot create TC IDR");
+ goto err_out;
+ }
ret = ACT_P_CREATED;
- } else {
+ } else if (!ovr) {
tcf_idr_release(*a, bind);
- if (!ovr)
- return -EEXIST;
+ NL_SET_ERR_MSG(extack, "TC IDR already exists");
+ return -EEXIST;
}
t = to_tunnel_key(*a);
ASSERT_RTNL();
params_new = kzalloc(sizeof(*params_new), GFP_KERNEL);
if (unlikely(!params_new)) {
- if (ret == ACT_P_CREATED)
- tcf_idr_release(*a, bind);
+ tcf_idr_release(*a, bind);
+ NL_SET_ERR_MSG(extack, "Cannot allocate tunnel key parameters");
return -ENOMEM;
}
err_out:
if (exists)
tcf_idr_release(*a, bind);
+ else
+ tcf_idr_cleanup(tn, parm->index);
return ret;
}
}
}
+static int tunnel_key_geneve_opts_dump(struct sk_buff *skb,
+ const struct ip_tunnel_info *info)
+{
+ int len = info->options_len;
+ u8 *src = (u8 *)(info + 1);
+ struct nlattr *start;
+
+ start = nla_nest_start(skb, TCA_TUNNEL_KEY_ENC_OPTS_GENEVE);
+ if (!start)
+ return -EMSGSIZE;
+
+ while (len > 0) {
+ struct geneve_opt *opt = (struct geneve_opt *)src;
+
+ if (nla_put_be16(skb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS,
+ opt->opt_class) ||
+ nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE,
+ opt->type) ||
+ nla_put(skb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA,
+ opt->length * 4, opt + 1))
+ return -EMSGSIZE;
+
+ len -= sizeof(struct geneve_opt) + opt->length * 4;
+ src += sizeof(struct geneve_opt) + opt->length * 4;
+ }
+
+ nla_nest_end(skb, start);
+ return 0;
+}
+
+static int tunnel_key_opts_dump(struct sk_buff *skb,
+ const struct ip_tunnel_info *info)
+{
+ struct nlattr *start;
+ int err;
+
+ if (!info->options_len)
+ return 0;
+
+ start = nla_nest_start(skb, TCA_TUNNEL_KEY_ENC_OPTS);
+ if (!start)
+ return -EMSGSIZE;
+
+ if (info->key.tun_flags & TUNNEL_GENEVE_OPT) {
+ err = tunnel_key_geneve_opts_dump(skb, info);
+ if (err)
+ return err;
+ } else {
+ return -EINVAL;
+ }
+
+ nla_nest_end(skb, start);
+ return 0;
+}
+
static int tunnel_key_dump_addresses(struct sk_buff *skb,
const struct ip_tunnel_info *info)
{
struct tcf_tunnel_key_params *params;
struct tc_tunnel_key opt = {
.index = t->tcf_index,
- .refcnt = t->tcf_refcnt - ref,
- .bindcnt = t->tcf_bindcnt - bind,
+ .refcnt = refcount_read(&t->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&t->tcf_bindcnt) - bind,
};
struct tcf_t tm;
goto nla_put_failure;
if (params->tcft_action == TCA_TUNNEL_KEY_ACT_SET) {
- struct ip_tunnel_key *key =
- ¶ms->tcft_enc_metadata->u.tun_info.key;
+ struct ip_tunnel_info *info =
+ ¶ms->tcft_enc_metadata->u.tun_info;
+ struct ip_tunnel_key *key = &info->key;
__be32 key_id = tunnel_id_to_key32(key->tun_id);
if (nla_put_be32(skb, TCA_TUNNEL_KEY_ENC_KEY_ID, key_id) ||
¶ms->tcft_enc_metadata->u.tun_info) ||
nla_put_be16(skb, TCA_TUNNEL_KEY_ENC_DST_PORT, key->tp_dst) ||
nla_put_u8(skb, TCA_TUNNEL_KEY_NO_CSUM,
- !(key->tun_flags & TUNNEL_CSUM)))
+ !(key->tun_flags & TUNNEL_CSUM)) ||
+ tunnel_key_opts_dump(skb, info))
goto nla_put_failure;
}
return tcf_idr_search(tn, a, index);
}
+static int tunnel_key_delete(struct net *net, u32 index)
+{
+ struct tc_action_net *tn = net_generic(net, tunnel_key_net_id);
+
+ return tcf_idr_delete_index(tn, index);
+}
+
static struct tc_action_ops act_tunnel_key_ops = {
.kind = "tunnel_key",
.type = TCA_ACT_TUNNEL_KEY,
.cleanup = tunnel_key_release,
.walk = tunnel_key_walker,
.lookup = tunnel_key_search,
+ .delete = tunnel_key_delete,
.size = sizeof(struct tcf_tunnel_key),
};
static int tcf_vlan_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
- int ovr, int bind, struct netlink_ext_ack *extack)
+ int ovr, int bind, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, vlan_net_id);
struct nlattr *tb[TCA_VLAN_MAX + 1];
if (!tb[TCA_VLAN_PARMS])
return -EINVAL;
parm = nla_data(tb[TCA_VLAN_PARMS]);
- exists = tcf_idr_check(tn, parm->index, a, bind);
+ err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ if (err < 0)
+ return err;
+ exists = err;
if (exists && bind)
return 0;
if (!tb[TCA_VLAN_PUSH_VLAN_ID]) {
if (exists)
tcf_idr_release(*a, bind);
+ else
+ tcf_idr_cleanup(tn, parm->index);
return -EINVAL;
}
push_vid = nla_get_u16(tb[TCA_VLAN_PUSH_VLAN_ID]);
if (push_vid >= VLAN_VID_MASK) {
if (exists)
tcf_idr_release(*a, bind);
+ else
+ tcf_idr_cleanup(tn, parm->index);
return -ERANGE;
}
default:
if (exists)
tcf_idr_release(*a, bind);
+ else
+ tcf_idr_cleanup(tn, parm->index);
return -EPROTONOSUPPORT;
}
} else {
default:
if (exists)
tcf_idr_release(*a, bind);
+ else
+ tcf_idr_cleanup(tn, parm->index);
return -EINVAL;
}
action = parm->v_action;
if (!exists) {
ret = tcf_idr_create(tn, parm->index, est, a,
&act_vlan_ops, bind, true);
- if (ret)
+ if (ret) {
+ tcf_idr_cleanup(tn, parm->index);
return ret;
+ }
ret = ACT_P_CREATED;
- } else {
+ } else if (!ovr) {
tcf_idr_release(*a, bind);
- if (!ovr)
- return -EEXIST;
+ return -EEXIST;
}
v = to_vlan(*a);
ASSERT_RTNL();
p = kzalloc(sizeof(*p), GFP_KERNEL);
if (!p) {
- if (ret == ACT_P_CREATED)
- tcf_idr_release(*a, bind);
+ tcf_idr_release(*a, bind);
return -ENOMEM;
}
struct tcf_vlan_params *p = rtnl_dereference(v->vlan_p);
struct tc_vlan opt = {
.index = v->tcf_index,
- .refcnt = v->tcf_refcnt - ref,
- .bindcnt = v->tcf_bindcnt - bind,
+ .refcnt = refcount_read(&v->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&v->tcf_bindcnt) - bind,
.action = v->tcf_action,
.v_action = p->tcfv_action,
};
return tcf_idr_search(tn, a, index);
}
+static int tcf_vlan_delete(struct net *net, u32 index)
+{
+ struct tc_action_net *tn = net_generic(net, vlan_net_id);
+
+ return tcf_idr_delete_index(tn, index);
+}
+
static struct tc_action_ops act_vlan_ops = {
.kind = "vlan",
.type = TCA_ACT_VLAN,
.cleanup = tcf_vlan_cleanup,
.walk = tcf_vlan_walker,
.lookup = tcf_vlan_search,
+ .delete = tcf_vlan_delete,
.size = sizeof(struct tcf_vlan),
};
static int tcf_block_offload_cmd(struct tcf_block *block,
struct net_device *dev,
struct tcf_block_ext_info *ei,
- enum tc_block_command command)
+ enum tc_block_command command,
+ struct netlink_ext_ack *extack)
{
struct tc_block_offload bo = {};
bo.command = command;
bo.binder_type = ei->binder_type;
bo.block = block;
+ bo.extack = extack;
return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo);
}
static int tcf_block_offload_bind(struct tcf_block *block, struct Qdisc *q,
- struct tcf_block_ext_info *ei)
+ struct tcf_block_ext_info *ei,
+ struct netlink_ext_ack *extack)
{
struct net_device *dev = q->dev_queue->dev;
int err;
/* If tc offload feature is disabled and the block we try to bind
* to already has some offloaded filters, forbid to bind.
*/
- if (!tc_can_offload(dev) && tcf_block_offload_in_use(block))
+ if (!tc_can_offload(dev) && tcf_block_offload_in_use(block)) {
+ NL_SET_ERR_MSG(extack, "Bind to offloaded block failed as dev has offload disabled");
return -EOPNOTSUPP;
+ }
- err = tcf_block_offload_cmd(block, dev, ei, TC_BLOCK_BIND);
+ err = tcf_block_offload_cmd(block, dev, ei, TC_BLOCK_BIND, extack);
if (err == -EOPNOTSUPP)
goto no_offload_dev_inc;
return err;
if (!dev->netdev_ops->ndo_setup_tc)
goto no_offload_dev_dec;
- err = tcf_block_offload_cmd(block, dev, ei, TC_BLOCK_UNBIND);
+ err = tcf_block_offload_cmd(block, dev, ei, TC_BLOCK_UNBIND, NULL);
if (err == -EOPNOTSUPP)
goto no_offload_dev_dec;
return;
if (err)
goto err_chain_head_change_cb_add;
- err = tcf_block_offload_bind(block, q, ei);
+ err = tcf_block_offload_bind(block, q, ei, extack);
if (err)
goto err_block_offload_bind;
}
EXPORT_SYMBOL(tcf_block_cb_decref);
+static int
+tcf_block_playback_offloads(struct tcf_block *block, tc_setup_cb_t *cb,
+ void *cb_priv, bool add, bool offload_in_use,
+ struct netlink_ext_ack *extack)
+{
+ struct tcf_chain *chain;
+ struct tcf_proto *tp;
+ int err;
+
+ list_for_each_entry(chain, &block->chain_list, list) {
+ for (tp = rtnl_dereference(chain->filter_chain); tp;
+ tp = rtnl_dereference(tp->next)) {
+ if (tp->ops->reoffload) {
+ err = tp->ops->reoffload(tp, add, cb, cb_priv,
+ extack);
+ if (err && add)
+ goto err_playback_remove;
+ } else if (add && offload_in_use) {
+ err = -EOPNOTSUPP;
+ NL_SET_ERR_MSG(extack, "Filter HW offload failed - classifier without re-offloading support");
+ goto err_playback_remove;
+ }
+ }
+ }
+
+ return 0;
+
+err_playback_remove:
+ tcf_block_playback_offloads(block, cb, cb_priv, false, offload_in_use,
+ extack);
+ return err;
+}
+
struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block,
tc_setup_cb_t *cb, void *cb_ident,
- void *cb_priv)
+ void *cb_priv,
+ struct netlink_ext_ack *extack)
{
struct tcf_block_cb *block_cb;
+ int err;
- /* At this point, playback of previous block cb calls is not supported,
- * so forbid to register to block which already has some offloaded
- * filters present.
- */
- if (tcf_block_offload_in_use(block))
- return ERR_PTR(-EOPNOTSUPP);
+ /* Replay any already present rules */
+ err = tcf_block_playback_offloads(block, cb, cb_priv, true,
+ tcf_block_offload_in_use(block),
+ extack);
+ if (err)
+ return ERR_PTR(err);
block_cb = kzalloc(sizeof(*block_cb), GFP_KERNEL);
if (!block_cb)
int tcf_block_cb_register(struct tcf_block *block,
tc_setup_cb_t *cb, void *cb_ident,
- void *cb_priv)
+ void *cb_priv, struct netlink_ext_ack *extack)
{
struct tcf_block_cb *block_cb;
- block_cb = __tcf_block_cb_register(block, cb, cb_ident, cb_priv);
+ block_cb = __tcf_block_cb_register(block, cb, cb_ident, cb_priv,
+ extack);
return IS_ERR(block_cb) ? PTR_ERR(block_cb) : 0;
}
EXPORT_SYMBOL(tcf_block_cb_register);
-void __tcf_block_cb_unregister(struct tcf_block_cb *block_cb)
+void __tcf_block_cb_unregister(struct tcf_block *block,
+ struct tcf_block_cb *block_cb)
{
+ tcf_block_playback_offloads(block, block_cb->cb, block_cb->cb_priv,
+ false, tcf_block_offload_in_use(block),
+ NULL);
list_del(&block_cb->list);
kfree(block_cb);
}
block_cb = tcf_block_cb_lookup(block, cb, cb_ident);
if (!block_cb)
return;
- __tcf_block_cb_unregister(block_cb);
+ __tcf_block_cb_unregister(block, block_cb);
}
EXPORT_SYMBOL(tcf_block_cb_unregister);
arg.w.stop = 0;
arg.w.skip = cb->args[1] - 1;
arg.w.count = 0;
+ arg.w.cookie = cb->args[2];
tp->ops->walk(tp, &arg.w);
+ cb->args[2] = arg.w.cookie;
cb->args[1] = arg.w.count + 1;
if (arg.w.stop)
return false;
void tcf_exts_destroy(struct tcf_exts *exts)
{
#ifdef CONFIG_NET_CLS_ACT
- LIST_HEAD(actions);
-
- ASSERT_RTNL();
- tcf_exts_to_list(exts, &actions);
- tcf_action_destroy(&actions, TCA_ACT_UNBIND);
+ tcf_action_destroy(exts->actions, TCA_ACT_UNBIND);
kfree(exts->actions);
exts->nr_actions = 0;
#endif
if (exts->police && tb[exts->police]) {
act = tcf_action_init_1(net, tp, tb[exts->police],
rate_tlv, "police", ovr,
- TCA_ACT_BIND, extack);
+ TCA_ACT_BIND, true, extack);
if (IS_ERR(act))
return PTR_ERR(act);
exts->actions[0] = act;
exts->nr_actions = 1;
} else if (exts->action && tb[exts->action]) {
- LIST_HEAD(actions);
- int err, i = 0;
+ int err;
err = tcf_action_init(net, tp, tb[exts->action],
rate_tlv, NULL, ovr, TCA_ACT_BIND,
- &actions, &attr_size, extack);
- if (err)
+ exts->actions, &attr_size, true,
+ extack);
+ if (err < 0)
return err;
- list_for_each_entry(act, &actions, list)
- exts->actions[i++] = act;
- exts->nr_actions = i;
+ exts->nr_actions = err;
}
exts->net = net;
}
* tc data even if iproute2 was newer - jhs
*/
if (exts->type != TCA_OLD_COMPAT) {
- LIST_HEAD(actions);
-
nest = nla_nest_start(skb, exts->action);
if (nest == NULL)
goto nla_put_failure;
- tcf_exts_to_list(exts, &actions);
- if (tcf_action_dump(skb, &actions, 0, 0) < 0)
+ if (tcf_action_dump(skb, exts->actions, 0, 0) < 0)
goto nla_put_failure;
nla_nest_end(skb, nest);
} else if (exts->police) {
struct tcf_result res;
bool exts_integrated;
u32 gen_flags;
+ unsigned int in_hw_count;
struct tcf_exts exts;
u32 handle;
u16 bpf_num_ops;
cls_bpf_offload_cmd(tp, oldprog, prog, extack);
return err;
} else if (err > 0) {
+ prog->in_hw_count = err;
tcf_block_offload_inc(block, &prog->gen_flags);
}
}
}
}
+static int cls_bpf_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb,
+ void *cb_priv, struct netlink_ext_ack *extack)
+{
+ struct cls_bpf_head *head = rtnl_dereference(tp->root);
+ struct tcf_block *block = tp->chain->block;
+ struct tc_cls_bpf_offload cls_bpf = {};
+ struct cls_bpf_prog *prog;
+ int err;
+
+ list_for_each_entry(prog, &head->plist, link) {
+ if (tc_skip_hw(prog->gen_flags))
+ continue;
+
+ tc_cls_common_offload_init(&cls_bpf.common, tp, prog->gen_flags,
+ extack);
+ cls_bpf.command = TC_CLSBPF_OFFLOAD;
+ cls_bpf.exts = &prog->exts;
+ cls_bpf.prog = add ? prog->filter : NULL;
+ cls_bpf.oldprog = add ? NULL : prog->filter;
+ cls_bpf.name = prog->bpf_name;
+ cls_bpf.exts_integrated = prog->exts_integrated;
+
+ err = cb(TC_SETUP_CLSBPF, &cls_bpf, cb_priv);
+ if (err) {
+ if (add && tc_skip_sw(prog->gen_flags))
+ return err;
+ continue;
+ }
+
+ tc_cls_offload_cnt_update(block, &prog->in_hw_count,
+ &prog->gen_flags, add);
+ }
+
+ return 0;
+}
+
static struct tcf_proto_ops cls_bpf_ops __read_mostly = {
.kind = "bpf",
.owner = THIS_MODULE,
.change = cls_bpf_change,
.delete = cls_bpf_delete,
.walk = cls_bpf_walk,
+ .reoffload = cls_bpf_reoffload,
.dump = cls_bpf_dump,
.bind_class = cls_bpf_bind_class,
};
struct flow_dissector_key_basic basic;
struct flow_dissector_key_eth_addrs eth;
struct flow_dissector_key_vlan vlan;
+ struct flow_dissector_key_vlan cvlan;
union {
struct flow_dissector_key_ipv4_addrs ipv4;
struct flow_dissector_key_ipv6_addrs ipv6;
struct rhashtable_params filter_ht_params;
struct flow_dissector dissector;
struct list_head filters;
- struct rcu_head rcu;
+ struct rcu_work rwork;
struct list_head list;
};
struct list_head list;
u32 handle;
u32 flags;
+ unsigned int in_hw_count;
struct rcu_work rwork;
struct net_device *hw_dev;
};
return rhashtable_init(&head->ht, &mask_ht_params);
}
+static void fl_mask_free(struct fl_flow_mask *mask)
+{
+ rhashtable_destroy(&mask->ht);
+ kfree(mask);
+}
+
+static void fl_mask_free_work(struct work_struct *work)
+{
+ struct fl_flow_mask *mask = container_of(to_rcu_work(work),
+ struct fl_flow_mask, rwork);
+
+ fl_mask_free(mask);
+}
+
static bool fl_mask_put(struct cls_fl_head *head, struct fl_flow_mask *mask,
bool async)
{
return false;
rhashtable_remove_fast(&head->ht, &mask->ht_node, mask_ht_params);
- rhashtable_destroy(&mask->ht);
list_del_rcu(&mask->list);
if (async)
- kfree_rcu(mask, rcu);
+ tcf_queue_work(&mask->rwork, fl_mask_free_work);
else
- kfree(mask);
+ fl_mask_free(mask);
return true;
}
fl_hw_destroy_filter(tp, f, NULL);
return err;
} else if (err > 0) {
+ f->in_hw_count = err;
tcf_block_offload_inc(block, &f->flags);
}
[TCA_FLOWER_KEY_IP_TOS_MASK] = { .type = NLA_U8 },
[TCA_FLOWER_KEY_IP_TTL] = { .type = NLA_U8 },
[TCA_FLOWER_KEY_IP_TTL_MASK] = { .type = NLA_U8 },
+ [TCA_FLOWER_KEY_CVLAN_ID] = { .type = NLA_U16 },
+ [TCA_FLOWER_KEY_CVLAN_PRIO] = { .type = NLA_U8 },
+ [TCA_FLOWER_KEY_CVLAN_ETH_TYPE] = { .type = NLA_U16 },
};
static void fl_set_key_val(struct nlattr **tb,
}
static void fl_set_key_vlan(struct nlattr **tb,
+ __be16 ethertype,
+ int vlan_id_key, int vlan_prio_key,
struct flow_dissector_key_vlan *key_val,
struct flow_dissector_key_vlan *key_mask)
{
#define VLAN_PRIORITY_MASK 0x7
- if (tb[TCA_FLOWER_KEY_VLAN_ID]) {
+ if (tb[vlan_id_key]) {
key_val->vlan_id =
- nla_get_u16(tb[TCA_FLOWER_KEY_VLAN_ID]) & VLAN_VID_MASK;
+ nla_get_u16(tb[vlan_id_key]) & VLAN_VID_MASK;
key_mask->vlan_id = VLAN_VID_MASK;
}
- if (tb[TCA_FLOWER_KEY_VLAN_PRIO]) {
+ if (tb[vlan_prio_key]) {
key_val->vlan_priority =
- nla_get_u8(tb[TCA_FLOWER_KEY_VLAN_PRIO]) &
+ nla_get_u8(tb[vlan_prio_key]) &
VLAN_PRIORITY_MASK;
key_mask->vlan_priority = VLAN_PRIORITY_MASK;
}
+ key_val->vlan_tpid = ethertype;
+ key_mask->vlan_tpid = cpu_to_be16(~0);
}
static void fl_set_key_flag(u32 flower_key, u32 flower_mask,
if (tb[TCA_FLOWER_KEY_ETH_TYPE]) {
ethertype = nla_get_be16(tb[TCA_FLOWER_KEY_ETH_TYPE]);
- if (ethertype == htons(ETH_P_8021Q)) {
- fl_set_key_vlan(tb, &key->vlan, &mask->vlan);
- fl_set_key_val(tb, &key->basic.n_proto,
- TCA_FLOWER_KEY_VLAN_ETH_TYPE,
- &mask->basic.n_proto, TCA_FLOWER_UNSPEC,
- sizeof(key->basic.n_proto));
+ if (eth_type_vlan(ethertype)) {
+ fl_set_key_vlan(tb, ethertype, TCA_FLOWER_KEY_VLAN_ID,
+ TCA_FLOWER_KEY_VLAN_PRIO, &key->vlan,
+ &mask->vlan);
+
+ if (tb[TCA_FLOWER_KEY_VLAN_ETH_TYPE]) {
+ ethertype = nla_get_be16(tb[TCA_FLOWER_KEY_VLAN_ETH_TYPE]);
+ if (eth_type_vlan(ethertype)) {
+ fl_set_key_vlan(tb, ethertype,
+ TCA_FLOWER_KEY_CVLAN_ID,
+ TCA_FLOWER_KEY_CVLAN_PRIO,
+ &key->cvlan, &mask->cvlan);
+ fl_set_key_val(tb, &key->basic.n_proto,
+ TCA_FLOWER_KEY_CVLAN_ETH_TYPE,
+ &mask->basic.n_proto,
+ TCA_FLOWER_UNSPEC,
+ sizeof(key->basic.n_proto));
+ } else {
+ key->basic.n_proto = ethertype;
+ mask->basic.n_proto = cpu_to_be16(~0);
+ }
+ }
} else {
key->basic.n_proto = ethertype;
mask->basic.n_proto = cpu_to_be16(~0);
FLOW_DISSECTOR_KEY_MPLS, mpls);
FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
FLOW_DISSECTOR_KEY_VLAN, vlan);
+ FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+ FLOW_DISSECTOR_KEY_CVLAN, cvlan);
FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
FLOW_DISSECTOR_KEY_ENC_KEYID, enc_key_id);
FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
{
struct cls_fl_head *head = rtnl_dereference(tp->root);
struct cls_fl_filter *f;
+
+ arg->count = arg->skip;
+
+ while ((f = idr_get_next_ul(&head->handle_idr,
+ &arg->cookie)) != NULL) {
+ if (arg->fn(tp, f, arg) < 0) {
+ arg->stop = 1;
+ break;
+ }
+ arg->cookie = f->handle + 1;
+ arg->count++;
+ }
+}
+
+static int fl_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb,
+ void *cb_priv, struct netlink_ext_ack *extack)
+{
+ struct cls_fl_head *head = rtnl_dereference(tp->root);
+ struct tc_cls_flower_offload cls_flower = {};
+ struct tcf_block *block = tp->chain->block;
struct fl_flow_mask *mask;
+ struct cls_fl_filter *f;
+ int err;
- list_for_each_entry_rcu(mask, &head->masks, list) {
- list_for_each_entry_rcu(f, &mask->filters, list) {
- if (arg->count < arg->skip)
- goto skip;
- if (arg->fn(tp, f, arg) < 0) {
- arg->stop = 1;
- break;
+ list_for_each_entry(mask, &head->masks, list) {
+ list_for_each_entry(f, &mask->filters, list) {
+ if (tc_skip_hw(f->flags))
+ continue;
+
+ tc_cls_common_offload_init(&cls_flower.common, tp,
+ f->flags, extack);
+ cls_flower.command = add ?
+ TC_CLSFLOWER_REPLACE : TC_CLSFLOWER_DESTROY;
+ cls_flower.cookie = (unsigned long)f;
+ cls_flower.dissector = &mask->dissector;
+ cls_flower.mask = &f->mkey;
+ cls_flower.key = &f->key;
+ cls_flower.exts = &f->exts;
+ cls_flower.classid = f->res.classid;
+
+ err = cb(TC_SETUP_CLSFLOWER, &cls_flower, cb_priv);
+ if (err) {
+ if (add && tc_skip_sw(f->flags))
+ return err;
+ continue;
}
-skip:
- arg->count++;
+
+ tc_cls_offload_cnt_update(block, &f->in_hw_count,
+ &f->flags, add);
}
}
+
+ return 0;
}
static int fl_dump_key_val(struct sk_buff *skb,
}
static int fl_dump_key_vlan(struct sk_buff *skb,
+ int vlan_id_key, int vlan_prio_key,
struct flow_dissector_key_vlan *vlan_key,
struct flow_dissector_key_vlan *vlan_mask)
{
if (!memchr_inv(vlan_mask, 0, sizeof(*vlan_mask)))
return 0;
if (vlan_mask->vlan_id) {
- err = nla_put_u16(skb, TCA_FLOWER_KEY_VLAN_ID,
+ err = nla_put_u16(skb, vlan_id_key,
vlan_key->vlan_id);
if (err)
return err;
}
if (vlan_mask->vlan_priority) {
- err = nla_put_u8(skb, TCA_FLOWER_KEY_VLAN_PRIO,
+ err = nla_put_u8(skb, vlan_prio_key,
vlan_key->vlan_priority);
if (err)
return err;
if (fl_dump_key_mpls(skb, &key->mpls, &mask->mpls))
goto nla_put_failure;
- if (fl_dump_key_vlan(skb, &key->vlan, &mask->vlan))
+ if (fl_dump_key_vlan(skb, TCA_FLOWER_KEY_VLAN_ID,
+ TCA_FLOWER_KEY_VLAN_PRIO, &key->vlan, &mask->vlan))
+ goto nla_put_failure;
+
+ if (fl_dump_key_vlan(skb, TCA_FLOWER_KEY_CVLAN_ID,
+ TCA_FLOWER_KEY_CVLAN_PRIO,
+ &key->cvlan, &mask->cvlan) ||
+ (mask->cvlan.vlan_tpid &&
+ nla_put_u16(skb, TCA_FLOWER_KEY_VLAN_ETH_TYPE,
+ key->cvlan.vlan_tpid)))
goto nla_put_failure;
+ if (mask->basic.n_proto) {
+ if (mask->cvlan.vlan_tpid) {
+ if (nla_put_be16(skb, TCA_FLOWER_KEY_CVLAN_ETH_TYPE,
+ key->basic.n_proto))
+ goto nla_put_failure;
+ } else if (mask->vlan.vlan_tpid) {
+ if (nla_put_be16(skb, TCA_FLOWER_KEY_VLAN_ETH_TYPE,
+ key->basic.n_proto))
+ goto nla_put_failure;
+ }
+ }
+
if ((key->basic.n_proto == htons(ETH_P_IP) ||
key->basic.n_proto == htons(ETH_P_IPV6)) &&
(fl_dump_key_val(skb, &key->basic.ip_proto, TCA_FLOWER_KEY_IP_PROTO,
.change = fl_change,
.delete = fl_delete,
.walk = fl_walk,
+ .reoffload = fl_reoffload,
.dump = fl_dump,
.bind_class = fl_bind_class,
.owner = THIS_MODULE,
struct tcf_result res;
u32 handle;
u32 flags;
+ unsigned int in_hw_count;
struct rcu_work rwork;
};
mall_destroy_hw_filter(tp, head, cookie, NULL);
return err;
} else if (err > 0) {
+ head->in_hw_count = err;
tcf_block_offload_inc(block, &head->flags);
}
arg->count++;
}
+static int mall_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb,
+ void *cb_priv, struct netlink_ext_ack *extack)
+{
+ struct cls_mall_head *head = rtnl_dereference(tp->root);
+ struct tc_cls_matchall_offload cls_mall = {};
+ struct tcf_block *block = tp->chain->block;
+ int err;
+
+ if (tc_skip_hw(head->flags))
+ return 0;
+
+ tc_cls_common_offload_init(&cls_mall.common, tp, head->flags, extack);
+ cls_mall.command = add ?
+ TC_CLSMATCHALL_REPLACE : TC_CLSMATCHALL_DESTROY;
+ cls_mall.exts = &head->exts;
+ cls_mall.cookie = (unsigned long)head;
+
+ err = cb(TC_SETUP_CLSMATCHALL, &cls_mall, cb_priv);
+ if (err) {
+ if (add && tc_skip_sw(head->flags))
+ return err;
+ return 0;
+ }
+
+ tc_cls_offload_cnt_update(block, &head->in_hw_count, &head->flags, add);
+
+ return 0;
+}
+
static int mall_dump(struct net *net, struct tcf_proto *tp, void *fh,
struct sk_buff *skb, struct tcmsg *t)
{
.change = mall_change,
.delete = mall_delete,
.walk = mall_walk,
+ .reoffload = mall_reoffload,
.dump = mall_dump,
.bind_class = mall_bind_class,
.owner = THIS_MODULE,
struct tc_u32_pcnt __percpu *pf;
#endif
u32 flags;
+ unsigned int in_hw_count;
#ifdef CONFIG_CLS_U32_MARK
u32 val;
u32 mask;
u32_remove_hw_knode(tp, n, NULL);
return err;
} else if (err > 0) {
+ n->in_hw_count = err;
tcf_block_offload_inc(block, &n->flags);
}
}
}
+static int u32_reoffload_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht,
+ bool add, tc_setup_cb_t *cb, void *cb_priv,
+ struct netlink_ext_ack *extack)
+{
+ struct tc_cls_u32_offload cls_u32 = {};
+ int err;
+
+ tc_cls_common_offload_init(&cls_u32.common, tp, ht->flags, extack);
+ cls_u32.command = add ? TC_CLSU32_NEW_HNODE : TC_CLSU32_DELETE_HNODE;
+ cls_u32.hnode.divisor = ht->divisor;
+ cls_u32.hnode.handle = ht->handle;
+ cls_u32.hnode.prio = ht->prio;
+
+ err = cb(TC_SETUP_CLSU32, &cls_u32, cb_priv);
+ if (err && add && tc_skip_sw(ht->flags))
+ return err;
+
+ return 0;
+}
+
+static int u32_reoffload_knode(struct tcf_proto *tp, struct tc_u_knode *n,
+ bool add, tc_setup_cb_t *cb, void *cb_priv,
+ struct netlink_ext_ack *extack)
+{
+ struct tc_u_hnode *ht = rtnl_dereference(n->ht_down);
+ struct tcf_block *block = tp->chain->block;
+ struct tc_cls_u32_offload cls_u32 = {};
+ int err;
+
+ tc_cls_common_offload_init(&cls_u32.common, tp, n->flags, extack);
+ cls_u32.command = add ?
+ TC_CLSU32_REPLACE_KNODE : TC_CLSU32_DELETE_KNODE;
+ cls_u32.knode.handle = n->handle;
+
+ if (add) {
+ cls_u32.knode.fshift = n->fshift;
+#ifdef CONFIG_CLS_U32_MARK
+ cls_u32.knode.val = n->val;
+ cls_u32.knode.mask = n->mask;
+#else
+ cls_u32.knode.val = 0;
+ cls_u32.knode.mask = 0;
+#endif
+ cls_u32.knode.sel = &n->sel;
+ cls_u32.knode.exts = &n->exts;
+ if (n->ht_down)
+ cls_u32.knode.link_handle = ht->handle;
+ }
+
+ err = cb(TC_SETUP_CLSU32, &cls_u32, cb_priv);
+ if (err) {
+ if (add && tc_skip_sw(n->flags))
+ return err;
+ return 0;
+ }
+
+ tc_cls_offload_cnt_update(block, &n->in_hw_count, &n->flags, add);
+
+ return 0;
+}
+
+static int u32_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb,
+ void *cb_priv, struct netlink_ext_ack *extack)
+{
+ struct tc_u_common *tp_c = tp->data;
+ struct tc_u_hnode *ht;
+ struct tc_u_knode *n;
+ unsigned int h;
+ int err;
+
+ for (ht = rtnl_dereference(tp_c->hlist);
+ ht;
+ ht = rtnl_dereference(ht->next)) {
+ if (ht->prio != tp->prio)
+ continue;
+
+ /* When adding filters to a new dev, try to offload the
+ * hashtable first. When removing, do the filters before the
+ * hashtable.
+ */
+ if (add && !tc_skip_hw(ht->flags)) {
+ err = u32_reoffload_hnode(tp, ht, add, cb, cb_priv,
+ extack);
+ if (err)
+ return err;
+ }
+
+ for (h = 0; h <= ht->divisor; h++) {
+ for (n = rtnl_dereference(ht->ht[h]);
+ n;
+ n = rtnl_dereference(n->next)) {
+ if (tc_skip_hw(n->flags))
+ continue;
+
+ err = u32_reoffload_knode(tp, n, add, cb,
+ cb_priv, extack);
+ if (err)
+ return err;
+ }
+ }
+
+ if (!add && !tc_skip_hw(ht->flags))
+ u32_reoffload_hnode(tp, ht, add, cb, cb_priv, extack);
+ }
+
+ return 0;
+}
+
static void u32_bind_class(void *fh, u32 classid, unsigned long cl)
{
struct tc_u_knode *n = fh;
.change = u32_change,
.delete = u32_delete,
.walk = u32_walk,
+ .reoffload = u32_reoffload,
.dump = u32_dump,
.bind_class = u32_bind_class,
.owner = THIS_MODULE,
return HRTIMER_NORESTART;
}
-void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc)
+void qdisc_watchdog_init_clockid(struct qdisc_watchdog *wd, struct Qdisc *qdisc,
+ clockid_t clockid)
{
- hrtimer_init(&wd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
+ hrtimer_init(&wd->timer, clockid, HRTIMER_MODE_ABS_PINNED);
wd->timer.function = qdisc_watchdog;
wd->qdisc = qdisc;
}
+EXPORT_SYMBOL(qdisc_watchdog_init_clockid);
+
+void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc)
+{
+ qdisc_watchdog_init_clockid(wd, qdisc, CLOCK_MONOTONIC);
+}
EXPORT_SYMBOL(qdisc_watchdog_init);
void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires)
struct sk_buff **to_free)
{
qdisc_drop(skb, sch, to_free);
- return NET_XMIT_SUCCESS;
+ return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
}
static struct sk_buff *blackhole_dequeue(struct Qdisc *sch)
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+
+/* COMMON Applications Kept Enhanced (CAKE) discipline
+ *
+ * Copyright (C) 2014-2018 Jonathan Morton <chromatix99@gmail.com>
+ * Copyright (C) 2015-2018 Toke Høiland-Jørgensen <toke@toke.dk>
+ * Copyright (C) 2014-2018 Dave Täht <dave.taht@gmail.com>
+ * Copyright (C) 2015-2018 Sebastian Moeller <moeller0@gmx.de>
+ * (C) 2015-2018 Kevin Darbyshire-Bryant <kevin@darbyshire-bryant.me.uk>
+ * Copyright (C) 2017-2018 Ryan Mounce <ryan@mounce.com.au>
+ *
+ * The CAKE Principles:
+ * (or, how to have your cake and eat it too)
+ *
+ * This is a combination of several shaping, AQM and FQ techniques into one
+ * easy-to-use package:
+ *
+ * - An overall bandwidth shaper, to move the bottleneck away from dumb CPE
+ * equipment and bloated MACs. This operates in deficit mode (as in sch_fq),
+ * eliminating the need for any sort of burst parameter (eg. token bucket
+ * depth). Burst support is limited to that necessary to overcome scheduling
+ * latency.
+ *
+ * - A Diffserv-aware priority queue, giving more priority to certain classes,
+ * up to a specified fraction of bandwidth. Above that bandwidth threshold,
+ * the priority is reduced to avoid starving other tins.
+ *
+ * - Each priority tin has a separate Flow Queue system, to isolate traffic
+ * flows from each other. This prevents a burst on one flow from increasing
+ * the delay to another. Flows are distributed to queues using a
+ * set-associative hash function.
+ *
+ * - Each queue is actively managed by Cobalt, which is a combination of the
+ * Codel and Blue AQM algorithms. This serves flows fairly, and signals
+ * congestion early via ECN (if available) and/or packet drops, to keep
+ * latency low. The codel parameters are auto-tuned based on the bandwidth
+ * setting, as is necessary at low bandwidths.
+ *
+ * The configuration parameters are kept deliberately simple for ease of use.
+ * Everything has sane defaults. Complete generality of configuration is *not*
+ * a goal.
+ *
+ * The priority queue operates according to a weighted DRR scheme, combined with
+ * a bandwidth tracker which reuses the shaper logic to detect which side of the
+ * bandwidth sharing threshold the tin is operating. This determines whether a
+ * priority-based weight (high) or a bandwidth-based weight (low) is used for
+ * that tin in the current pass.
+ *
+ * This qdisc was inspired by Eric Dumazet's fq_codel code, which he kindly
+ * granted us permission to leverage.
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/jiffies.h>
+#include <linux/string.h>
+#include <linux/in.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/skbuff.h>
+#include <linux/jhash.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/reciprocal_div.h>
+#include <net/netlink.h>
+#include <linux/version.h>
+#include <linux/if_vlan.h>
+#include <net/pkt_sched.h>
+#include <net/pkt_cls.h>
+#include <net/tcp.h>
+#include <net/flow_dissector.h>
+
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+#include <net/netfilter/nf_conntrack_core.h>
+#endif
+
+#define CAKE_SET_WAYS (8)
+#define CAKE_MAX_TINS (8)
+#define CAKE_QUEUES (1024)
+#define CAKE_FLOW_MASK 63
+#define CAKE_FLOW_NAT_FLAG 64
+#define CAKE_SPLIT_GSO_THRESHOLD (125000000) /* 1Gbps */
+
+/* struct cobalt_params - contains codel and blue parameters
+ * @interval: codel initial drop rate
+ * @target: maximum persistent sojourn time & blue update rate
+ * @mtu_time: serialisation delay of maximum-size packet
+ * @p_inc: increment of blue drop probability (0.32 fxp)
+ * @p_dec: decrement of blue drop probability (0.32 fxp)
+ */
+struct cobalt_params {
+ u64 interval;
+ u64 target;
+ u64 mtu_time;
+ u32 p_inc;
+ u32 p_dec;
+};
+
+/* struct cobalt_vars - contains codel and blue variables
+ * @count: codel dropping frequency
+ * @rec_inv_sqrt: reciprocal value of sqrt(count) >> 1
+ * @drop_next: time to drop next packet, or when we dropped last
+ * @blue_timer: Blue time to next drop
+ * @p_drop: BLUE drop probability (0.32 fxp)
+ * @dropping: set if in dropping state
+ * @ecn_marked: set if marked
+ */
+struct cobalt_vars {
+ u32 count;
+ u32 rec_inv_sqrt;
+ ktime_t drop_next;
+ ktime_t blue_timer;
+ u32 p_drop;
+ bool dropping;
+ bool ecn_marked;
+};
+
+enum {
+ CAKE_SET_NONE = 0,
+ CAKE_SET_SPARSE,
+ CAKE_SET_SPARSE_WAIT, /* counted in SPARSE, actually in BULK */
+ CAKE_SET_BULK,
+ CAKE_SET_DECAYING
+};
+
+struct cake_flow {
+ /* this stuff is all needed per-flow at dequeue time */
+ struct sk_buff *head;
+ struct sk_buff *tail;
+ struct list_head flowchain;
+ s32 deficit;
+ u32 dropped;
+ struct cobalt_vars cvars;
+ u16 srchost; /* index into cake_host table */
+ u16 dsthost;
+ u8 set;
+}; /* please try to keep this structure <= 64 bytes */
+
+struct cake_host {
+ u32 srchost_tag;
+ u32 dsthost_tag;
+ u16 srchost_refcnt;
+ u16 dsthost_refcnt;
+};
+
+struct cake_heap_entry {
+ u16 t:3, b:10;
+};
+
+struct cake_tin_data {
+ struct cake_flow flows[CAKE_QUEUES];
+ u32 backlogs[CAKE_QUEUES];
+ u32 tags[CAKE_QUEUES]; /* for set association */
+ u16 overflow_idx[CAKE_QUEUES];
+ struct cake_host hosts[CAKE_QUEUES]; /* for triple isolation */
+ u16 flow_quantum;
+
+ struct cobalt_params cparams;
+ u32 drop_overlimit;
+ u16 bulk_flow_count;
+ u16 sparse_flow_count;
+ u16 decaying_flow_count;
+ u16 unresponsive_flow_count;
+
+ u32 max_skblen;
+
+ struct list_head new_flows;
+ struct list_head old_flows;
+ struct list_head decaying_flows;
+
+ /* time_next = time_this + ((len * rate_ns) >> rate_shft) */
+ ktime_t time_next_packet;
+ u64 tin_rate_ns;
+ u64 tin_rate_bps;
+ u16 tin_rate_shft;
+
+ u16 tin_quantum_prio;
+ u16 tin_quantum_band;
+ s32 tin_deficit;
+ u32 tin_backlog;
+ u32 tin_dropped;
+ u32 tin_ecn_mark;
+
+ u32 packets;
+ u64 bytes;
+
+ u32 ack_drops;
+
+ /* moving averages */
+ u64 avge_delay;
+ u64 peak_delay;
+ u64 base_delay;
+
+ /* hash function stats */
+ u32 way_directs;
+ u32 way_hits;
+ u32 way_misses;
+ u32 way_collisions;
+}; /* number of tins is small, so size of this struct doesn't matter much */
+
+struct cake_sched_data {
+ struct tcf_proto __rcu *filter_list; /* optional external classifier */
+ struct tcf_block *block;
+ struct cake_tin_data *tins;
+
+ struct cake_heap_entry overflow_heap[CAKE_QUEUES * CAKE_MAX_TINS];
+ u16 overflow_timeout;
+
+ u16 tin_cnt;
+ u8 tin_mode;
+ u8 flow_mode;
+ u8 ack_filter;
+ u8 atm_mode;
+
+ /* time_next = time_this + ((len * rate_ns) >> rate_shft) */
+ u16 rate_shft;
+ ktime_t time_next_packet;
+ ktime_t failsafe_next_packet;
+ u64 rate_ns;
+ u64 rate_bps;
+ u16 rate_flags;
+ s16 rate_overhead;
+ u16 rate_mpu;
+ u64 interval;
+ u64 target;
+
+ /* resource tracking */
+ u32 buffer_used;
+ u32 buffer_max_used;
+ u32 buffer_limit;
+ u32 buffer_config_limit;
+
+ /* indices for dequeue */
+ u16 cur_tin;
+ u16 cur_flow;
+
+ struct qdisc_watchdog watchdog;
+ const u8 *tin_index;
+ const u8 *tin_order;
+
+ /* bandwidth capacity estimate */
+ ktime_t last_packet_time;
+ ktime_t avg_window_begin;
+ u64 avg_packet_interval;
+ u64 avg_window_bytes;
+ u64 avg_peak_bandwidth;
+ ktime_t last_reconfig_time;
+
+ /* packet length stats */
+ u32 avg_netoff;
+ u16 max_netlen;
+ u16 max_adjlen;
+ u16 min_netlen;
+ u16 min_adjlen;
+};
+
+enum {
+ CAKE_FLAG_OVERHEAD = BIT(0),
+ CAKE_FLAG_AUTORATE_INGRESS = BIT(1),
+ CAKE_FLAG_INGRESS = BIT(2),
+ CAKE_FLAG_WASH = BIT(3),
+ CAKE_FLAG_SPLIT_GSO = BIT(4)
+};
+
+/* COBALT operates the Codel and BLUE algorithms in parallel, in order to
+ * obtain the best features of each. Codel is excellent on flows which
+ * respond to congestion signals in a TCP-like way. BLUE is more effective on
+ * unresponsive flows.
+ */
+
+struct cobalt_skb_cb {
+ ktime_t enqueue_time;
+ u32 adjusted_len;
+};
+
+static u64 us_to_ns(u64 us)
+{
+ return us * NSEC_PER_USEC;
+}
+
+static struct cobalt_skb_cb *get_cobalt_cb(const struct sk_buff *skb)
+{
+ qdisc_cb_private_validate(skb, sizeof(struct cobalt_skb_cb));
+ return (struct cobalt_skb_cb *)qdisc_skb_cb(skb)->data;
+}
+
+static ktime_t cobalt_get_enqueue_time(const struct sk_buff *skb)
+{
+ return get_cobalt_cb(skb)->enqueue_time;
+}
+
+static void cobalt_set_enqueue_time(struct sk_buff *skb,
+ ktime_t now)
+{
+ get_cobalt_cb(skb)->enqueue_time = now;
+}
+
+static u16 quantum_div[CAKE_QUEUES + 1] = {0};
+
+/* Diffserv lookup tables */
+
+static const u8 precedence[] = {
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 1, 1, 1, 1, 1, 1, 1, 1,
+ 2, 2, 2, 2, 2, 2, 2, 2,
+ 3, 3, 3, 3, 3, 3, 3, 3,
+ 4, 4, 4, 4, 4, 4, 4, 4,
+ 5, 5, 5, 5, 5, 5, 5, 5,
+ 6, 6, 6, 6, 6, 6, 6, 6,
+ 7, 7, 7, 7, 7, 7, 7, 7,
+};
+
+static const u8 diffserv8[] = {
+ 2, 5, 1, 2, 4, 2, 2, 2,
+ 0, 2, 1, 2, 1, 2, 1, 2,
+ 5, 2, 4, 2, 4, 2, 4, 2,
+ 3, 2, 3, 2, 3, 2, 3, 2,
+ 6, 2, 3, 2, 3, 2, 3, 2,
+ 6, 2, 2, 2, 6, 2, 6, 2,
+ 7, 2, 2, 2, 2, 2, 2, 2,
+ 7, 2, 2, 2, 2, 2, 2, 2,
+};
+
+static const u8 diffserv4[] = {
+ 0, 2, 0, 0, 2, 0, 0, 0,
+ 1, 0, 0, 0, 0, 0, 0, 0,
+ 2, 0, 2, 0, 2, 0, 2, 0,
+ 2, 0, 2, 0, 2, 0, 2, 0,
+ 3, 0, 2, 0, 2, 0, 2, 0,
+ 3, 0, 0, 0, 3, 0, 3, 0,
+ 3, 0, 0, 0, 0, 0, 0, 0,
+ 3, 0, 0, 0, 0, 0, 0, 0,
+};
+
+static const u8 diffserv3[] = {
+ 0, 0, 0, 0, 2, 0, 0, 0,
+ 1, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 2, 0, 2, 0,
+ 2, 0, 0, 0, 0, 0, 0, 0,
+ 2, 0, 0, 0, 0, 0, 0, 0,
+};
+
+static const u8 besteffort[] = {
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+};
+
+/* tin priority order for stats dumping */
+
+static const u8 normal_order[] = {0, 1, 2, 3, 4, 5, 6, 7};
+static const u8 bulk_order[] = {1, 0, 2, 3};
+
+#define REC_INV_SQRT_CACHE (16)
+static u32 cobalt_rec_inv_sqrt_cache[REC_INV_SQRT_CACHE] = {0};
+
+/* http://en.wikipedia.org/wiki/Methods_of_computing_square_roots
+ * new_invsqrt = (invsqrt / 2) * (3 - count * invsqrt^2)
+ *
+ * Here, invsqrt is a fixed point number (< 1.0), 32bit mantissa, aka Q0.32
+ */
+
+static void cobalt_newton_step(struct cobalt_vars *vars)
+{
+ u32 invsqrt, invsqrt2;
+ u64 val;
+
+ invsqrt = vars->rec_inv_sqrt;
+ invsqrt2 = ((u64)invsqrt * invsqrt) >> 32;
+ val = (3LL << 32) - ((u64)vars->count * invsqrt2);
+
+ val >>= 2; /* avoid overflow in following multiply */
+ val = (val * invsqrt) >> (32 - 2 + 1);
+
+ vars->rec_inv_sqrt = val;
+}
+
+static void cobalt_invsqrt(struct cobalt_vars *vars)
+{
+ if (vars->count < REC_INV_SQRT_CACHE)
+ vars->rec_inv_sqrt = cobalt_rec_inv_sqrt_cache[vars->count];
+ else
+ cobalt_newton_step(vars);
+}
+
+/* There is a big difference in timing between the accurate values placed in
+ * the cache and the approximations given by a single Newton step for small
+ * count values, particularly when stepping from count 1 to 2 or vice versa.
+ * Above 16, a single Newton step gives sufficient accuracy in either
+ * direction, given the precision stored.
+ *
+ * The magnitude of the error when stepping up to count 2 is such as to give
+ * the value that *should* have been produced at count 4.
+ */
+
+static void cobalt_cache_init(void)
+{
+ struct cobalt_vars v;
+
+ memset(&v, 0, sizeof(v));
+ v.rec_inv_sqrt = ~0U;
+ cobalt_rec_inv_sqrt_cache[0] = v.rec_inv_sqrt;
+
+ for (v.count = 1; v.count < REC_INV_SQRT_CACHE; v.count++) {
+ cobalt_newton_step(&v);
+ cobalt_newton_step(&v);
+ cobalt_newton_step(&v);
+ cobalt_newton_step(&v);
+
+ cobalt_rec_inv_sqrt_cache[v.count] = v.rec_inv_sqrt;
+ }
+}
+
+static void cobalt_vars_init(struct cobalt_vars *vars)
+{
+ memset(vars, 0, sizeof(*vars));
+
+ if (!cobalt_rec_inv_sqrt_cache[0]) {
+ cobalt_cache_init();
+ cobalt_rec_inv_sqrt_cache[0] = ~0;
+ }
+}
+
+/* CoDel control_law is t + interval/sqrt(count)
+ * We maintain in rec_inv_sqrt the reciprocal value of sqrt(count) to avoid
+ * both sqrt() and divide operation.
+ */
+static ktime_t cobalt_control(ktime_t t,
+ u64 interval,
+ u32 rec_inv_sqrt)
+{
+ return ktime_add_ns(t, reciprocal_scale(interval,
+ rec_inv_sqrt));
+}
+
+/* Call this when a packet had to be dropped due to queue overflow. Returns
+ * true if the BLUE state was quiescent before but active after this call.
+ */
+static bool cobalt_queue_full(struct cobalt_vars *vars,
+ struct cobalt_params *p,
+ ktime_t now)
+{
+ bool up = false;
+
+ if (ktime_to_ns(ktime_sub(now, vars->blue_timer)) > p->target) {
+ up = !vars->p_drop;
+ vars->p_drop += p->p_inc;
+ if (vars->p_drop < p->p_inc)
+ vars->p_drop = ~0;
+ vars->blue_timer = now;
+ }
+ vars->dropping = true;
+ vars->drop_next = now;
+ if (!vars->count)
+ vars->count = 1;
+
+ return up;
+}
+
+/* Call this when the queue was serviced but turned out to be empty. Returns
+ * true if the BLUE state was active before but quiescent after this call.
+ */
+static bool cobalt_queue_empty(struct cobalt_vars *vars,
+ struct cobalt_params *p,
+ ktime_t now)
+{
+ bool down = false;
+
+ if (vars->p_drop &&
+ ktime_to_ns(ktime_sub(now, vars->blue_timer)) > p->target) {
+ if (vars->p_drop < p->p_dec)
+ vars->p_drop = 0;
+ else
+ vars->p_drop -= p->p_dec;
+ vars->blue_timer = now;
+ down = !vars->p_drop;
+ }
+ vars->dropping = false;
+
+ if (vars->count && ktime_to_ns(ktime_sub(now, vars->drop_next)) >= 0) {
+ vars->count--;
+ cobalt_invsqrt(vars);
+ vars->drop_next = cobalt_control(vars->drop_next,
+ p->interval,
+ vars->rec_inv_sqrt);
+ }
+
+ return down;
+}
+
+/* Call this with a freshly dequeued packet for possible congestion marking.
+ * Returns true as an instruction to drop the packet, false for delivery.
+ */
+static bool cobalt_should_drop(struct cobalt_vars *vars,
+ struct cobalt_params *p,
+ ktime_t now,
+ struct sk_buff *skb,
+ u32 bulk_flows)
+{
+ bool next_due, over_target, drop = false;
+ ktime_t schedule;
+ u64 sojourn;
+
+/* The 'schedule' variable records, in its sign, whether 'now' is before or
+ * after 'drop_next'. This allows 'drop_next' to be updated before the next
+ * scheduling decision is actually branched, without destroying that
+ * information. Similarly, the first 'schedule' value calculated is preserved
+ * in the boolean 'next_due'.
+ *
+ * As for 'drop_next', we take advantage of the fact that 'interval' is both
+ * the delay between first exceeding 'target' and the first signalling event,
+ * *and* the scaling factor for the signalling frequency. It's therefore very
+ * natural to use a single mechanism for both purposes, and eliminates a
+ * significant amount of reference Codel's spaghetti code. To help with this,
+ * both the '0' and '1' entries in the invsqrt cache are 0xFFFFFFFF, as close
+ * as possible to 1.0 in fixed-point.
+ */
+
+ sojourn = ktime_to_ns(ktime_sub(now, cobalt_get_enqueue_time(skb)));
+ schedule = ktime_sub(now, vars->drop_next);
+ over_target = sojourn > p->target &&
+ sojourn > p->mtu_time * bulk_flows * 2 &&
+ sojourn > p->mtu_time * 4;
+ next_due = vars->count && ktime_to_ns(schedule) >= 0;
+
+ vars->ecn_marked = false;
+
+ if (over_target) {
+ if (!vars->dropping) {
+ vars->dropping = true;
+ vars->drop_next = cobalt_control(now,
+ p->interval,
+ vars->rec_inv_sqrt);
+ }
+ if (!vars->count)
+ vars->count = 1;
+ } else if (vars->dropping) {
+ vars->dropping = false;
+ }
+
+ if (next_due && vars->dropping) {
+ /* Use ECN mark if possible, otherwise drop */
+ drop = !(vars->ecn_marked = INET_ECN_set_ce(skb));
+
+ vars->count++;
+ if (!vars->count)
+ vars->count--;
+ cobalt_invsqrt(vars);
+ vars->drop_next = cobalt_control(vars->drop_next,
+ p->interval,
+ vars->rec_inv_sqrt);
+ schedule = ktime_sub(now, vars->drop_next);
+ } else {
+ while (next_due) {
+ vars->count--;
+ cobalt_invsqrt(vars);
+ vars->drop_next = cobalt_control(vars->drop_next,
+ p->interval,
+ vars->rec_inv_sqrt);
+ schedule = ktime_sub(now, vars->drop_next);
+ next_due = vars->count && ktime_to_ns(schedule) >= 0;
+ }
+ }
+
+ /* Simple BLUE implementation. Lack of ECN is deliberate. */
+ if (vars->p_drop)
+ drop |= (prandom_u32() < vars->p_drop);
+
+ /* Overload the drop_next field as an activity timeout */
+ if (!vars->count)
+ vars->drop_next = ktime_add_ns(now, p->interval);
+ else if (ktime_to_ns(schedule) > 0 && !drop)
+ vars->drop_next = now;
+
+ return drop;
+}
+
+static void cake_update_flowkeys(struct flow_keys *keys,
+ const struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+ struct nf_conntrack_tuple tuple = {};
+ bool rev = !skb->_nfct;
+
+ if (tc_skb_protocol(skb) != htons(ETH_P_IP))
+ return;
+
+ if (!nf_ct_get_tuple_skb(&tuple, skb))
+ return;
+
+ keys->addrs.v4addrs.src = rev ? tuple.dst.u3.ip : tuple.src.u3.ip;
+ keys->addrs.v4addrs.dst = rev ? tuple.src.u3.ip : tuple.dst.u3.ip;
+
+ if (keys->ports.ports) {
+ keys->ports.src = rev ? tuple.dst.u.all : tuple.src.u.all;
+ keys->ports.dst = rev ? tuple.src.u.all : tuple.dst.u.all;
+ }
+#endif
+}
+
+/* Cake has several subtle multiple bit settings. In these cases you
+ * would be matching triple isolate mode as well.
+ */
+
+static bool cake_dsrc(int flow_mode)
+{
+ return (flow_mode & CAKE_FLOW_DUAL_SRC) == CAKE_FLOW_DUAL_SRC;
+}
+
+static bool cake_ddst(int flow_mode)
+{
+ return (flow_mode & CAKE_FLOW_DUAL_DST) == CAKE_FLOW_DUAL_DST;
+}
+
+static u32 cake_hash(struct cake_tin_data *q, const struct sk_buff *skb,
+ int flow_mode)
+{
+ u32 flow_hash = 0, srchost_hash, dsthost_hash;
+ u16 reduced_hash, srchost_idx, dsthost_idx;
+ struct flow_keys keys, host_keys;
+
+ if (unlikely(flow_mode == CAKE_FLOW_NONE))
+ return 0;
+
+ skb_flow_dissect_flow_keys(skb, &keys,
+ FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL);
+
+ if (flow_mode & CAKE_FLOW_NAT_FLAG)
+ cake_update_flowkeys(&keys, skb);
+
+ /* flow_hash_from_keys() sorts the addresses by value, so we have
+ * to preserve their order in a separate data structure to treat
+ * src and dst host addresses as independently selectable.
+ */
+ host_keys = keys;
+ host_keys.ports.ports = 0;
+ host_keys.basic.ip_proto = 0;
+ host_keys.keyid.keyid = 0;
+ host_keys.tags.flow_label = 0;
+
+ switch (host_keys.control.addr_type) {
+ case FLOW_DISSECTOR_KEY_IPV4_ADDRS:
+ host_keys.addrs.v4addrs.src = 0;
+ dsthost_hash = flow_hash_from_keys(&host_keys);
+ host_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src;
+ host_keys.addrs.v4addrs.dst = 0;
+ srchost_hash = flow_hash_from_keys(&host_keys);
+ break;
+
+ case FLOW_DISSECTOR_KEY_IPV6_ADDRS:
+ memset(&host_keys.addrs.v6addrs.src, 0,
+ sizeof(host_keys.addrs.v6addrs.src));
+ dsthost_hash = flow_hash_from_keys(&host_keys);
+ host_keys.addrs.v6addrs.src = keys.addrs.v6addrs.src;
+ memset(&host_keys.addrs.v6addrs.dst, 0,
+ sizeof(host_keys.addrs.v6addrs.dst));
+ srchost_hash = flow_hash_from_keys(&host_keys);
+ break;
+
+ default:
+ dsthost_hash = 0;
+ srchost_hash = 0;
+ }
+
+ /* This *must* be after the above switch, since as a
+ * side-effect it sorts the src and dst addresses.
+ */
+ if (flow_mode & CAKE_FLOW_FLOWS)
+ flow_hash = flow_hash_from_keys(&keys);
+
+ if (!(flow_mode & CAKE_FLOW_FLOWS)) {
+ if (flow_mode & CAKE_FLOW_SRC_IP)
+ flow_hash ^= srchost_hash;
+
+ if (flow_mode & CAKE_FLOW_DST_IP)
+ flow_hash ^= dsthost_hash;
+ }
+
+ reduced_hash = flow_hash % CAKE_QUEUES;
+
+ /* set-associative hashing */
+ /* fast path if no hash collision (direct lookup succeeds) */
+ if (likely(q->tags[reduced_hash] == flow_hash &&
+ q->flows[reduced_hash].set)) {
+ q->way_directs++;
+ } else {
+ u32 inner_hash = reduced_hash % CAKE_SET_WAYS;
+ u32 outer_hash = reduced_hash - inner_hash;
+ bool allocate_src = false;
+ bool allocate_dst = false;
+ u32 i, k;
+
+ /* check if any active queue in the set is reserved for
+ * this flow.
+ */
+ for (i = 0, k = inner_hash; i < CAKE_SET_WAYS;
+ i++, k = (k + 1) % CAKE_SET_WAYS) {
+ if (q->tags[outer_hash + k] == flow_hash) {
+ if (i)
+ q->way_hits++;
+
+ if (!q->flows[outer_hash + k].set) {
+ /* need to increment host refcnts */
+ allocate_src = cake_dsrc(flow_mode);
+ allocate_dst = cake_ddst(flow_mode);
+ }
+
+ goto found;
+ }
+ }
+
+ /* no queue is reserved for this flow, look for an
+ * empty one.
+ */
+ for (i = 0; i < CAKE_SET_WAYS;
+ i++, k = (k + 1) % CAKE_SET_WAYS) {
+ if (!q->flows[outer_hash + k].set) {
+ q->way_misses++;
+ allocate_src = cake_dsrc(flow_mode);
+ allocate_dst = cake_ddst(flow_mode);
+ goto found;
+ }
+ }
+
+ /* With no empty queues, default to the original
+ * queue, accept the collision, update the host tags.
+ */
+ q->way_collisions++;
+ q->hosts[q->flows[reduced_hash].srchost].srchost_refcnt--;
+ q->hosts[q->flows[reduced_hash].dsthost].dsthost_refcnt--;
+ allocate_src = cake_dsrc(flow_mode);
+ allocate_dst = cake_ddst(flow_mode);
+found:
+ /* reserve queue for future packets in same flow */
+ reduced_hash = outer_hash + k;
+ q->tags[reduced_hash] = flow_hash;
+
+ if (allocate_src) {
+ srchost_idx = srchost_hash % CAKE_QUEUES;
+ inner_hash = srchost_idx % CAKE_SET_WAYS;
+ outer_hash = srchost_idx - inner_hash;
+ for (i = 0, k = inner_hash; i < CAKE_SET_WAYS;
+ i++, k = (k + 1) % CAKE_SET_WAYS) {
+ if (q->hosts[outer_hash + k].srchost_tag ==
+ srchost_hash)
+ goto found_src;
+ }
+ for (i = 0; i < CAKE_SET_WAYS;
+ i++, k = (k + 1) % CAKE_SET_WAYS) {
+ if (!q->hosts[outer_hash + k].srchost_refcnt)
+ break;
+ }
+ q->hosts[outer_hash + k].srchost_tag = srchost_hash;
+found_src:
+ srchost_idx = outer_hash + k;
+ q->hosts[srchost_idx].srchost_refcnt++;
+ q->flows[reduced_hash].srchost = srchost_idx;
+ }
+
+ if (allocate_dst) {
+ dsthost_idx = dsthost_hash % CAKE_QUEUES;
+ inner_hash = dsthost_idx % CAKE_SET_WAYS;
+ outer_hash = dsthost_idx - inner_hash;
+ for (i = 0, k = inner_hash; i < CAKE_SET_WAYS;
+ i++, k = (k + 1) % CAKE_SET_WAYS) {
+ if (q->hosts[outer_hash + k].dsthost_tag ==
+ dsthost_hash)
+ goto found_dst;
+ }
+ for (i = 0; i < CAKE_SET_WAYS;
+ i++, k = (k + 1) % CAKE_SET_WAYS) {
+ if (!q->hosts[outer_hash + k].dsthost_refcnt)
+ break;
+ }
+ q->hosts[outer_hash + k].dsthost_tag = dsthost_hash;
+found_dst:
+ dsthost_idx = outer_hash + k;
+ q->hosts[dsthost_idx].dsthost_refcnt++;
+ q->flows[reduced_hash].dsthost = dsthost_idx;
+ }
+ }
+
+ return reduced_hash;
+}
+
+/* helper functions : might be changed when/if skb use a standard list_head */
+/* remove one skb from head of slot queue */
+
+static struct sk_buff *dequeue_head(struct cake_flow *flow)
+{
+ struct sk_buff *skb = flow->head;
+
+ if (skb) {
+ flow->head = skb->next;
+ skb->next = NULL;
+ }
+
+ return skb;
+}
+
+/* add skb to flow queue (tail add) */
+
+static void flow_queue_add(struct cake_flow *flow, struct sk_buff *skb)
+{
+ if (!flow->head)
+ flow->head = skb;
+ else
+ flow->tail->next = skb;
+ flow->tail = skb;
+ skb->next = NULL;
+}
+
+static struct iphdr *cake_get_iphdr(const struct sk_buff *skb,
+ struct ipv6hdr *buf)
+{
+ unsigned int offset = skb_network_offset(skb);
+ struct iphdr *iph;
+
+ iph = skb_header_pointer(skb, offset, sizeof(struct iphdr), buf);
+
+ if (!iph)
+ return NULL;
+
+ if (iph->version == 4 && iph->protocol == IPPROTO_IPV6)
+ return skb_header_pointer(skb, offset + iph->ihl * 4,
+ sizeof(struct ipv6hdr), buf);
+
+ else if (iph->version == 4)
+ return iph;
+
+ else if (iph->version == 6)
+ return skb_header_pointer(skb, offset, sizeof(struct ipv6hdr),
+ buf);
+
+ return NULL;
+}
+
+static struct tcphdr *cake_get_tcphdr(const struct sk_buff *skb,
+ void *buf, unsigned int bufsize)
+{
+ unsigned int offset = skb_network_offset(skb);
+ const struct ipv6hdr *ipv6h;
+ const struct tcphdr *tcph;
+ const struct iphdr *iph;
+ struct ipv6hdr _ipv6h;
+ struct tcphdr _tcph;
+
+ ipv6h = skb_header_pointer(skb, offset, sizeof(_ipv6h), &_ipv6h);
+
+ if (!ipv6h)
+ return NULL;
+
+ if (ipv6h->version == 4) {
+ iph = (struct iphdr *)ipv6h;
+ offset += iph->ihl * 4;
+
+ /* special-case 6in4 tunnelling, as that is a common way to get
+ * v6 connectivity in the home
+ */
+ if (iph->protocol == IPPROTO_IPV6) {
+ ipv6h = skb_header_pointer(skb, offset,
+ sizeof(_ipv6h), &_ipv6h);
+
+ if (!ipv6h || ipv6h->nexthdr != IPPROTO_TCP)
+ return NULL;
+
+ offset += sizeof(struct ipv6hdr);
+
+ } else if (iph->protocol != IPPROTO_TCP) {
+ return NULL;
+ }
+
+ } else if (ipv6h->version == 6) {
+ if (ipv6h->nexthdr != IPPROTO_TCP)
+ return NULL;
+
+ offset += sizeof(struct ipv6hdr);
+ } else {
+ return NULL;
+ }
+
+ tcph = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph);
+ if (!tcph)
+ return NULL;
+
+ return skb_header_pointer(skb, offset,
+ min(__tcp_hdrlen(tcph), bufsize), buf);
+}
+
+static const void *cake_get_tcpopt(const struct tcphdr *tcph,
+ int code, int *oplen)
+{
+ /* inspired by tcp_parse_options in tcp_input.c */
+ int length = __tcp_hdrlen(tcph) - sizeof(struct tcphdr);
+ const u8 *ptr = (const u8 *)(tcph + 1);
+
+ while (length > 0) {
+ int opcode = *ptr++;
+ int opsize;
+
+ if (opcode == TCPOPT_EOL)
+ break;
+ if (opcode == TCPOPT_NOP) {
+ length--;
+ continue;
+ }
+ opsize = *ptr++;
+ if (opsize < 2 || opsize > length)
+ break;
+
+ if (opcode == code) {
+ *oplen = opsize;
+ return ptr;
+ }
+
+ ptr += opsize - 2;
+ length -= opsize;
+ }
+
+ return NULL;
+}
+
+/* Compare two SACK sequences. A sequence is considered greater if it SACKs more
+ * bytes than the other. In the case where both sequences ACKs bytes that the
+ * other doesn't, A is considered greater. DSACKs in A also makes A be
+ * considered greater.
+ *
+ * @return -1, 0 or 1 as normal compare functions
+ */
+static int cake_tcph_sack_compare(const struct tcphdr *tcph_a,
+ const struct tcphdr *tcph_b)
+{
+ const struct tcp_sack_block_wire *sack_a, *sack_b;
+ u32 ack_seq_a = ntohl(tcph_a->ack_seq);
+ u32 bytes_a = 0, bytes_b = 0;
+ int oplen_a, oplen_b;
+ bool first = true;
+
+ sack_a = cake_get_tcpopt(tcph_a, TCPOPT_SACK, &oplen_a);
+ sack_b = cake_get_tcpopt(tcph_b, TCPOPT_SACK, &oplen_b);
+
+ /* pointers point to option contents */
+ oplen_a -= TCPOLEN_SACK_BASE;
+ oplen_b -= TCPOLEN_SACK_BASE;
+
+ if (sack_a && oplen_a >= sizeof(*sack_a) &&
+ (!sack_b || oplen_b < sizeof(*sack_b)))
+ return -1;
+ else if (sack_b && oplen_b >= sizeof(*sack_b) &&
+ (!sack_a || oplen_a < sizeof(*sack_a)))
+ return 1;
+ else if ((!sack_a || oplen_a < sizeof(*sack_a)) &&
+ (!sack_b || oplen_b < sizeof(*sack_b)))
+ return 0;
+
+ while (oplen_a >= sizeof(*sack_a)) {
+ const struct tcp_sack_block_wire *sack_tmp = sack_b;
+ u32 start_a = get_unaligned_be32(&sack_a->start_seq);
+ u32 end_a = get_unaligned_be32(&sack_a->end_seq);
+ int oplen_tmp = oplen_b;
+ bool found = false;
+
+ /* DSACK; always considered greater to prevent dropping */
+ if (before(start_a, ack_seq_a))
+ return -1;
+
+ bytes_a += end_a - start_a;
+
+ while (oplen_tmp >= sizeof(*sack_tmp)) {
+ u32 start_b = get_unaligned_be32(&sack_tmp->start_seq);
+ u32 end_b = get_unaligned_be32(&sack_tmp->end_seq);
+
+ /* first time through we count the total size */
+ if (first)
+ bytes_b += end_b - start_b;
+
+ if (!after(start_b, start_a) && !before(end_b, end_a)) {
+ found = true;
+ if (!first)
+ break;
+ }
+ oplen_tmp -= sizeof(*sack_tmp);
+ sack_tmp++;
+ }
+
+ if (!found)
+ return -1;
+
+ oplen_a -= sizeof(*sack_a);
+ sack_a++;
+ first = false;
+ }
+
+ /* If we made it this far, all ranges SACKed by A are covered by B, so
+ * either the SACKs are equal, or B SACKs more bytes.
+ */
+ return bytes_b > bytes_a ? 1 : 0;
+}
+
+static void cake_tcph_get_tstamp(const struct tcphdr *tcph,
+ u32 *tsval, u32 *tsecr)
+{
+ const u8 *ptr;
+ int opsize;
+
+ ptr = cake_get_tcpopt(tcph, TCPOPT_TIMESTAMP, &opsize);
+
+ if (ptr && opsize == TCPOLEN_TIMESTAMP) {
+ *tsval = get_unaligned_be32(ptr);
+ *tsecr = get_unaligned_be32(ptr + 4);
+ }
+}
+
+static bool cake_tcph_may_drop(const struct tcphdr *tcph,
+ u32 tstamp_new, u32 tsecr_new)
+{
+ /* inspired by tcp_parse_options in tcp_input.c */
+ int length = __tcp_hdrlen(tcph) - sizeof(struct tcphdr);
+ const u8 *ptr = (const u8 *)(tcph + 1);
+ u32 tstamp, tsecr;
+
+ /* 3 reserved flags must be unset to avoid future breakage
+ * ACK must be set
+ * ECE/CWR are handled separately
+ * All other flags URG/PSH/RST/SYN/FIN must be unset
+ * 0x0FFF0000 = all TCP flags (confirm ACK=1, others zero)
+ * 0x00C00000 = CWR/ECE (handled separately)
+ * 0x0F3F0000 = 0x0FFF0000 & ~0x00C00000
+ */
+ if (((tcp_flag_word(tcph) &
+ cpu_to_be32(0x0F3F0000)) != TCP_FLAG_ACK))
+ return false;
+
+ while (length > 0) {
+ int opcode = *ptr++;
+ int opsize;
+
+ if (opcode == TCPOPT_EOL)
+ break;
+ if (opcode == TCPOPT_NOP) {
+ length--;
+ continue;
+ }
+ opsize = *ptr++;
+ if (opsize < 2 || opsize > length)
+ break;
+
+ switch (opcode) {
+ case TCPOPT_MD5SIG: /* doesn't influence state */
+ break;
+
+ case TCPOPT_SACK: /* stricter checking performed later */
+ if (opsize % 8 != 2)
+ return false;
+ break;
+
+ case TCPOPT_TIMESTAMP:
+ /* only drop timestamps lower than new */
+ if (opsize != TCPOLEN_TIMESTAMP)
+ return false;
+ tstamp = get_unaligned_be32(ptr);
+ tsecr = get_unaligned_be32(ptr + 4);
+ if (after(tstamp, tstamp_new) ||
+ after(tsecr, tsecr_new))
+ return false;
+ break;
+
+ case TCPOPT_MSS: /* these should only be set on SYN */
+ case TCPOPT_WINDOW:
+ case TCPOPT_SACK_PERM:
+ case TCPOPT_FASTOPEN:
+ case TCPOPT_EXP:
+ default: /* don't drop if any unknown options are present */
+ return false;
+ }
+
+ ptr += opsize - 2;
+ length -= opsize;
+ }
+
+ return true;
+}
+
+static struct sk_buff *cake_ack_filter(struct cake_sched_data *q,
+ struct cake_flow *flow)
+{
+ bool aggressive = q->ack_filter == CAKE_ACK_AGGRESSIVE;
+ struct sk_buff *elig_ack = NULL, *elig_ack_prev = NULL;
+ struct sk_buff *skb_check, *skb_prev = NULL;
+ const struct ipv6hdr *ipv6h, *ipv6h_check;
+ unsigned char _tcph[64], _tcph_check[64];
+ const struct tcphdr *tcph, *tcph_check;
+ const struct iphdr *iph, *iph_check;
+ struct ipv6hdr _iph, _iph_check;
+ const struct sk_buff *skb;
+ int seglen, num_found = 0;
+ u32 tstamp = 0, tsecr = 0;
+ __be32 elig_flags = 0;
+ int sack_comp;
+
+ /* no other possible ACKs to filter */
+ if (flow->head == flow->tail)
+ return NULL;
+
+ skb = flow->tail;
+ tcph = cake_get_tcphdr(skb, _tcph, sizeof(_tcph));
+ iph = cake_get_iphdr(skb, &_iph);
+ if (!tcph)
+ return NULL;
+
+ cake_tcph_get_tstamp(tcph, &tstamp, &tsecr);
+
+ /* the 'triggering' packet need only have the ACK flag set.
+ * also check that SYN is not set, as there won't be any previous ACKs.
+ */
+ if ((tcp_flag_word(tcph) &
+ (TCP_FLAG_ACK | TCP_FLAG_SYN)) != TCP_FLAG_ACK)
+ return NULL;
+
+ /* the 'triggering' ACK is at the tail of the queue, we have already
+ * returned if it is the only packet in the flow. loop through the rest
+ * of the queue looking for pure ACKs with the same 5-tuple as the
+ * triggering one.
+ */
+ for (skb_check = flow->head;
+ skb_check && skb_check != skb;
+ skb_prev = skb_check, skb_check = skb_check->next) {
+ iph_check = cake_get_iphdr(skb_check, &_iph_check);
+ tcph_check = cake_get_tcphdr(skb_check, &_tcph_check,
+ sizeof(_tcph_check));
+
+ /* only TCP packets with matching 5-tuple are eligible, and only
+ * drop safe headers
+ */
+ if (!tcph_check || iph->version != iph_check->version ||
+ tcph_check->source != tcph->source ||
+ tcph_check->dest != tcph->dest)
+ continue;
+
+ if (iph_check->version == 4) {
+ if (iph_check->saddr != iph->saddr ||
+ iph_check->daddr != iph->daddr)
+ continue;
+
+ seglen = ntohs(iph_check->tot_len) -
+ (4 * iph_check->ihl);
+ } else if (iph_check->version == 6) {
+ ipv6h = (struct ipv6hdr *)iph;
+ ipv6h_check = (struct ipv6hdr *)iph_check;
+
+ if (ipv6_addr_cmp(&ipv6h_check->saddr, &ipv6h->saddr) ||
+ ipv6_addr_cmp(&ipv6h_check->daddr, &ipv6h->daddr))
+ continue;
+
+ seglen = ntohs(ipv6h_check->payload_len);
+ } else {
+ WARN_ON(1); /* shouldn't happen */
+ continue;
+ }
+
+ /* If the ECE/CWR flags changed from the previous eligible
+ * packet in the same flow, we should no longer be dropping that
+ * previous packet as this would lose information.
+ */
+ if (elig_ack && (tcp_flag_word(tcph_check) &
+ (TCP_FLAG_ECE | TCP_FLAG_CWR)) != elig_flags) {
+ elig_ack = NULL;
+ elig_ack_prev = NULL;
+ num_found--;
+ }
+
+ /* Check TCP options and flags, don't drop ACKs with segment
+ * data, and don't drop ACKs with a higher cumulative ACK
+ * counter than the triggering packet. Check ACK seqno here to
+ * avoid parsing SACK options of packets we are going to exclude
+ * anyway.
+ */
+ if (!cake_tcph_may_drop(tcph_check, tstamp, tsecr) ||
+ (seglen - __tcp_hdrlen(tcph_check)) != 0 ||
+ after(ntohl(tcph_check->ack_seq), ntohl(tcph->ack_seq)))
+ continue;
+
+ /* Check SACK options. The triggering packet must SACK more data
+ * than the ACK under consideration, or SACK the same range but
+ * have a larger cumulative ACK counter. The latter is a
+ * pathological case, but is contained in the following check
+ * anyway, just to be safe.
+ */
+ sack_comp = cake_tcph_sack_compare(tcph_check, tcph);
+
+ if (sack_comp < 0 ||
+ (ntohl(tcph_check->ack_seq) == ntohl(tcph->ack_seq) &&
+ sack_comp == 0))
+ continue;
+
+ /* At this point we have found an eligible pure ACK to drop; if
+ * we are in aggressive mode, we are done. Otherwise, keep
+ * searching unless this is the second eligible ACK we
+ * found.
+ *
+ * Since we want to drop ACK closest to the head of the queue,
+ * save the first eligible ACK we find, even if we need to loop
+ * again.
+ */
+ if (!elig_ack) {
+ elig_ack = skb_check;
+ elig_ack_prev = skb_prev;
+ elig_flags = (tcp_flag_word(tcph_check)
+ & (TCP_FLAG_ECE | TCP_FLAG_CWR));
+ }
+
+ if (num_found++ > 0)
+ goto found;
+ }
+
+ /* We made it through the queue without finding two eligible ACKs . If
+ * we found a single eligible ACK we can drop it in aggressive mode if
+ * we can guarantee that this does not interfere with ECN flag
+ * information. We ensure this by dropping it only if the enqueued
+ * packet is consecutive with the eligible ACK, and their flags match.
+ */
+ if (elig_ack && aggressive && elig_ack->next == skb &&
+ (elig_flags == (tcp_flag_word(tcph) &
+ (TCP_FLAG_ECE | TCP_FLAG_CWR))))
+ goto found;
+
+ return NULL;
+
+found:
+ if (elig_ack_prev)
+ elig_ack_prev->next = elig_ack->next;
+ else
+ flow->head = elig_ack->next;
+
+ elig_ack->next = NULL;
+
+ return elig_ack;
+}
+
+static u64 cake_ewma(u64 avg, u64 sample, u32 shift)
+{
+ avg -= avg >> shift;
+ avg += sample >> shift;
+ return avg;
+}
+
+static u32 cake_calc_overhead(struct cake_sched_data *q, u32 len, u32 off)
+{
+ if (q->rate_flags & CAKE_FLAG_OVERHEAD)
+ len -= off;
+
+ if (q->max_netlen < len)
+ q->max_netlen = len;
+ if (q->min_netlen > len)
+ q->min_netlen = len;
+
+ len += q->rate_overhead;
+
+ if (len < q->rate_mpu)
+ len = q->rate_mpu;
+
+ if (q->atm_mode == CAKE_ATM_ATM) {
+ len += 47;
+ len /= 48;
+ len *= 53;
+ } else if (q->atm_mode == CAKE_ATM_PTM) {
+ /* Add one byte per 64 bytes or part thereof.
+ * This is conservative and easier to calculate than the
+ * precise value.
+ */
+ len += (len + 63) / 64;
+ }
+
+ if (q->max_adjlen < len)
+ q->max_adjlen = len;
+ if (q->min_adjlen > len)
+ q->min_adjlen = len;
+
+ return len;
+}
+
+static u32 cake_overhead(struct cake_sched_data *q, const struct sk_buff *skb)
+{
+ const struct skb_shared_info *shinfo = skb_shinfo(skb);
+ unsigned int hdr_len, last_len = 0;
+ u32 off = skb_network_offset(skb);
+ u32 len = qdisc_pkt_len(skb);
+ u16 segs = 1;
+
+ q->avg_netoff = cake_ewma(q->avg_netoff, off << 16, 8);
+
+ if (!shinfo->gso_size)
+ return cake_calc_overhead(q, len, off);
+
+ /* borrowed from qdisc_pkt_len_init() */
+ hdr_len = skb_transport_header(skb) - skb_mac_header(skb);
+
+ /* + transport layer */
+ if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 |
+ SKB_GSO_TCPV6))) {
+ const struct tcphdr *th;
+ struct tcphdr _tcphdr;
+
+ th = skb_header_pointer(skb, skb_transport_offset(skb),
+ sizeof(_tcphdr), &_tcphdr);
+ if (likely(th))
+ hdr_len += __tcp_hdrlen(th);
+ } else {
+ struct udphdr _udphdr;
+
+ if (skb_header_pointer(skb, skb_transport_offset(skb),
+ sizeof(_udphdr), &_udphdr))
+ hdr_len += sizeof(struct udphdr);
+ }
+
+ if (unlikely(shinfo->gso_type & SKB_GSO_DODGY))
+ segs = DIV_ROUND_UP(skb->len - hdr_len,
+ shinfo->gso_size);
+ else
+ segs = shinfo->gso_segs;
+
+ len = shinfo->gso_size + hdr_len;
+ last_len = skb->len - shinfo->gso_size * (segs - 1);
+
+ return (cake_calc_overhead(q, len, off) * (segs - 1) +
+ cake_calc_overhead(q, last_len, off));
+}
+
+static void cake_heap_swap(struct cake_sched_data *q, u16 i, u16 j)
+{
+ struct cake_heap_entry ii = q->overflow_heap[i];
+ struct cake_heap_entry jj = q->overflow_heap[j];
+
+ q->overflow_heap[i] = jj;
+ q->overflow_heap[j] = ii;
+
+ q->tins[ii.t].overflow_idx[ii.b] = j;
+ q->tins[jj.t].overflow_idx[jj.b] = i;
+}
+
+static u32 cake_heap_get_backlog(const struct cake_sched_data *q, u16 i)
+{
+ struct cake_heap_entry ii = q->overflow_heap[i];
+
+ return q->tins[ii.t].backlogs[ii.b];
+}
+
+static void cake_heapify(struct cake_sched_data *q, u16 i)
+{
+ static const u32 a = CAKE_MAX_TINS * CAKE_QUEUES;
+ u32 mb = cake_heap_get_backlog(q, i);
+ u32 m = i;
+
+ while (m < a) {
+ u32 l = m + m + 1;
+ u32 r = l + 1;
+
+ if (l < a) {
+ u32 lb = cake_heap_get_backlog(q, l);
+
+ if (lb > mb) {
+ m = l;
+ mb = lb;
+ }
+ }
+
+ if (r < a) {
+ u32 rb = cake_heap_get_backlog(q, r);
+
+ if (rb > mb) {
+ m = r;
+ mb = rb;
+ }
+ }
+
+ if (m != i) {
+ cake_heap_swap(q, i, m);
+ i = m;
+ } else {
+ break;
+ }
+ }
+}
+
+static void cake_heapify_up(struct cake_sched_data *q, u16 i)
+{
+ while (i > 0 && i < CAKE_MAX_TINS * CAKE_QUEUES) {
+ u16 p = (i - 1) >> 1;
+ u32 ib = cake_heap_get_backlog(q, i);
+ u32 pb = cake_heap_get_backlog(q, p);
+
+ if (ib > pb) {
+ cake_heap_swap(q, i, p);
+ i = p;
+ } else {
+ break;
+ }
+ }
+}
+
+static int cake_advance_shaper(struct cake_sched_data *q,
+ struct cake_tin_data *b,
+ struct sk_buff *skb,
+ ktime_t now, bool drop)
+{
+ u32 len = get_cobalt_cb(skb)->adjusted_len;
+
+ /* charge packet bandwidth to this tin
+ * and to the global shaper.
+ */
+ if (q->rate_ns) {
+ u64 tin_dur = (len * b->tin_rate_ns) >> b->tin_rate_shft;
+ u64 global_dur = (len * q->rate_ns) >> q->rate_shft;
+ u64 failsafe_dur = global_dur + (global_dur >> 1);
+
+ if (ktime_before(b->time_next_packet, now))
+ b->time_next_packet = ktime_add_ns(b->time_next_packet,
+ tin_dur);
+
+ else if (ktime_before(b->time_next_packet,
+ ktime_add_ns(now, tin_dur)))
+ b->time_next_packet = ktime_add_ns(now, tin_dur);
+
+ q->time_next_packet = ktime_add_ns(q->time_next_packet,
+ global_dur);
+ if (!drop)
+ q->failsafe_next_packet = \
+ ktime_add_ns(q->failsafe_next_packet,
+ failsafe_dur);
+ }
+ return len;
+}
+
+static unsigned int cake_drop(struct Qdisc *sch, struct sk_buff **to_free)
+{
+ struct cake_sched_data *q = qdisc_priv(sch);
+ ktime_t now = ktime_get();
+ u32 idx = 0, tin = 0, len;
+ struct cake_heap_entry qq;
+ struct cake_tin_data *b;
+ struct cake_flow *flow;
+ struct sk_buff *skb;
+
+ if (!q->overflow_timeout) {
+ int i;
+ /* Build fresh max-heap */
+ for (i = CAKE_MAX_TINS * CAKE_QUEUES / 2; i >= 0; i--)
+ cake_heapify(q, i);
+ }
+ q->overflow_timeout = 65535;
+
+ /* select longest queue for pruning */
+ qq = q->overflow_heap[0];
+ tin = qq.t;
+ idx = qq.b;
+
+ b = &q->tins[tin];
+ flow = &b->flows[idx];
+ skb = dequeue_head(flow);
+ if (unlikely(!skb)) {
+ /* heap has gone wrong, rebuild it next time */
+ q->overflow_timeout = 0;
+ return idx + (tin << 16);
+ }
+
+ if (cobalt_queue_full(&flow->cvars, &b->cparams, now))
+ b->unresponsive_flow_count++;
+
+ len = qdisc_pkt_len(skb);
+ q->buffer_used -= skb->truesize;
+ b->backlogs[idx] -= len;
+ b->tin_backlog -= len;
+ sch->qstats.backlog -= len;
+ qdisc_tree_reduce_backlog(sch, 1, len);
+
+ flow->dropped++;
+ b->tin_dropped++;
+ sch->qstats.drops++;
+
+ if (q->rate_flags & CAKE_FLAG_INGRESS)
+ cake_advance_shaper(q, b, skb, now, true);
+
+ __qdisc_drop(skb, to_free);
+ sch->q.qlen--;
+
+ cake_heapify(q, 0);
+
+ return idx + (tin << 16);
+}
+
+static void cake_wash_diffserv(struct sk_buff *skb)
+{
+ switch (skb->protocol) {
+ case htons(ETH_P_IP):
+ ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, 0);
+ break;
+ case htons(ETH_P_IPV6):
+ ipv6_change_dsfield(ipv6_hdr(skb), INET_ECN_MASK, 0);
+ break;
+ default:
+ break;
+ }
+}
+
+static u8 cake_handle_diffserv(struct sk_buff *skb, u16 wash)
+{
+ u8 dscp;
+
+ switch (skb->protocol) {
+ case htons(ETH_P_IP):
+ dscp = ipv4_get_dsfield(ip_hdr(skb)) >> 2;
+ if (wash && dscp)
+ ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, 0);
+ return dscp;
+
+ case htons(ETH_P_IPV6):
+ dscp = ipv6_get_dsfield(ipv6_hdr(skb)) >> 2;
+ if (wash && dscp)
+ ipv6_change_dsfield(ipv6_hdr(skb), INET_ECN_MASK, 0);
+ return dscp;
+
+ case htons(ETH_P_ARP):
+ return 0x38; /* CS7 - Net Control */
+
+ default:
+ /* If there is no Diffserv field, treat as best-effort */
+ return 0;
+ }
+}
+
+static struct cake_tin_data *cake_select_tin(struct Qdisc *sch,
+ struct sk_buff *skb)
+{
+ struct cake_sched_data *q = qdisc_priv(sch);
+ u32 tin;
+
+ if (TC_H_MAJ(skb->priority) == sch->handle &&
+ TC_H_MIN(skb->priority) > 0 &&
+ TC_H_MIN(skb->priority) <= q->tin_cnt) {
+ tin = q->tin_order[TC_H_MIN(skb->priority) - 1];
+
+ if (q->rate_flags & CAKE_FLAG_WASH)
+ cake_wash_diffserv(skb);
+ } else if (q->tin_mode != CAKE_DIFFSERV_BESTEFFORT) {
+ /* extract the Diffserv Precedence field, if it exists */
+ /* and clear DSCP bits if washing */
+ tin = q->tin_index[cake_handle_diffserv(skb,
+ q->rate_flags & CAKE_FLAG_WASH)];
+ if (unlikely(tin >= q->tin_cnt))
+ tin = 0;
+ } else {
+ tin = 0;
+ if (q->rate_flags & CAKE_FLAG_WASH)
+ cake_wash_diffserv(skb);
+ }
+
+ return &q->tins[tin];
+}
+
+static u32 cake_classify(struct Qdisc *sch, struct cake_tin_data **t,
+ struct sk_buff *skb, int flow_mode, int *qerr)
+{
+ struct cake_sched_data *q = qdisc_priv(sch);
+ struct tcf_proto *filter;
+ struct tcf_result res;
+ u32 flow = 0;
+ int result;
+
+ filter = rcu_dereference_bh(q->filter_list);
+ if (!filter)
+ goto hash;
+
+ *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
+ result = tcf_classify(skb, filter, &res, false);
+
+ if (result >= 0) {
+#ifdef CONFIG_NET_CLS_ACT
+ switch (result) {
+ case TC_ACT_STOLEN:
+ case TC_ACT_QUEUED:
+ case TC_ACT_TRAP:
+ *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
+ /* fall through */
+ case TC_ACT_SHOT:
+ return 0;
+ }
+#endif
+ if (TC_H_MIN(res.classid) <= CAKE_QUEUES)
+ flow = TC_H_MIN(res.classid);
+ }
+hash:
+ *t = cake_select_tin(sch, skb);
+ return flow ?: cake_hash(*t, skb, flow_mode) + 1;
+}
+
+static void cake_reconfigure(struct Qdisc *sch);
+
+static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+ struct sk_buff **to_free)
+{
+ struct cake_sched_data *q = qdisc_priv(sch);
+ int len = qdisc_pkt_len(skb);
+ int uninitialized_var(ret);
+ struct sk_buff *ack = NULL;
+ ktime_t now = ktime_get();
+ struct cake_tin_data *b;
+ struct cake_flow *flow;
+ u32 idx;
+
+ /* choose flow to insert into */
+ idx = cake_classify(sch, &b, skb, q->flow_mode, &ret);
+ if (idx == 0) {
+ if (ret & __NET_XMIT_BYPASS)
+ qdisc_qstats_drop(sch);
+ __qdisc_drop(skb, to_free);
+ return ret;
+ }
+ idx--;
+ flow = &b->flows[idx];
+
+ /* ensure shaper state isn't stale */
+ if (!b->tin_backlog) {
+ if (ktime_before(b->time_next_packet, now))
+ b->time_next_packet = now;
+
+ if (!sch->q.qlen) {
+ if (ktime_before(q->time_next_packet, now)) {
+ q->failsafe_next_packet = now;
+ q->time_next_packet = now;
+ } else if (ktime_after(q->time_next_packet, now) &&
+ ktime_after(q->failsafe_next_packet, now)) {
+ u64 next = \
+ min(ktime_to_ns(q->time_next_packet),
+ ktime_to_ns(
+ q->failsafe_next_packet));
+ sch->qstats.overlimits++;
+ qdisc_watchdog_schedule_ns(&q->watchdog, next);
+ }
+ }
+ }
+
+ if (unlikely(len > b->max_skblen))
+ b->max_skblen = len;
+
+ if (skb_is_gso(skb) && q->rate_flags & CAKE_FLAG_SPLIT_GSO) {
+ struct sk_buff *segs, *nskb;
+ netdev_features_t features = netif_skb_features(skb);
+ unsigned int slen = 0;
+
+ segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
+ if (IS_ERR_OR_NULL(segs))
+ return qdisc_drop(skb, sch, to_free);
+
+ while (segs) {
+ nskb = segs->next;
+ segs->next = NULL;
+ qdisc_skb_cb(segs)->pkt_len = segs->len;
+ cobalt_set_enqueue_time(segs, now);
+ get_cobalt_cb(segs)->adjusted_len = cake_overhead(q,
+ segs);
+ flow_queue_add(flow, segs);
+
+ sch->q.qlen++;
+ slen += segs->len;
+ q->buffer_used += segs->truesize;
+ b->packets++;
+ segs = nskb;
+ }
+
+ /* stats */
+ b->bytes += slen;
+ b->backlogs[idx] += slen;
+ b->tin_backlog += slen;
+ sch->qstats.backlog += slen;
+ q->avg_window_bytes += slen;
+
+ qdisc_tree_reduce_backlog(sch, 1, len);
+ consume_skb(skb);
+ } else {
+ /* not splitting */
+ cobalt_set_enqueue_time(skb, now);
+ get_cobalt_cb(skb)->adjusted_len = cake_overhead(q, skb);
+ flow_queue_add(flow, skb);
+
+ if (q->ack_filter)
+ ack = cake_ack_filter(q, flow);
+
+ if (ack) {
+ b->ack_drops++;
+ sch->qstats.drops++;
+ b->bytes += qdisc_pkt_len(ack);
+ len -= qdisc_pkt_len(ack);
+ q->buffer_used += skb->truesize - ack->truesize;
+ if (q->rate_flags & CAKE_FLAG_INGRESS)
+ cake_advance_shaper(q, b, ack, now, true);
+
+ qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(ack));
+ consume_skb(ack);
+ } else {
+ sch->q.qlen++;
+ q->buffer_used += skb->truesize;
+ }
+
+ /* stats */
+ b->packets++;
+ b->bytes += len;
+ b->backlogs[idx] += len;
+ b->tin_backlog += len;
+ sch->qstats.backlog += len;
+ q->avg_window_bytes += len;
+ }
+
+ if (q->overflow_timeout)
+ cake_heapify_up(q, b->overflow_idx[idx]);
+
+ /* incoming bandwidth capacity estimate */
+ if (q->rate_flags & CAKE_FLAG_AUTORATE_INGRESS) {
+ u64 packet_interval = \
+ ktime_to_ns(ktime_sub(now, q->last_packet_time));
+
+ if (packet_interval > NSEC_PER_SEC)
+ packet_interval = NSEC_PER_SEC;
+
+ /* filter out short-term bursts, eg. wifi aggregation */
+ q->avg_packet_interval = \
+ cake_ewma(q->avg_packet_interval,
+ packet_interval,
+ (packet_interval > q->avg_packet_interval ?
+ 2 : 8));
+
+ q->last_packet_time = now;
+
+ if (packet_interval > q->avg_packet_interval) {
+ u64 window_interval = \
+ ktime_to_ns(ktime_sub(now,
+ q->avg_window_begin));
+ u64 b = q->avg_window_bytes * (u64)NSEC_PER_SEC;
+
+ do_div(b, window_interval);
+ q->avg_peak_bandwidth =
+ cake_ewma(q->avg_peak_bandwidth, b,
+ b > q->avg_peak_bandwidth ? 2 : 8);
+ q->avg_window_bytes = 0;
+ q->avg_window_begin = now;
+
+ if (ktime_after(now,
+ ktime_add_ms(q->last_reconfig_time,
+ 250))) {
+ q->rate_bps = (q->avg_peak_bandwidth * 15) >> 4;
+ cake_reconfigure(sch);
+ }
+ }
+ } else {
+ q->avg_window_bytes = 0;
+ q->last_packet_time = now;
+ }
+
+ /* flowchain */
+ if (!flow->set || flow->set == CAKE_SET_DECAYING) {
+ struct cake_host *srchost = &b->hosts[flow->srchost];
+ struct cake_host *dsthost = &b->hosts[flow->dsthost];
+ u16 host_load = 1;
+
+ if (!flow->set) {
+ list_add_tail(&flow->flowchain, &b->new_flows);
+ } else {
+ b->decaying_flow_count--;
+ list_move_tail(&flow->flowchain, &b->new_flows);
+ }
+ flow->set = CAKE_SET_SPARSE;
+ b->sparse_flow_count++;
+
+ if (cake_dsrc(q->flow_mode))
+ host_load = max(host_load, srchost->srchost_refcnt);
+
+ if (cake_ddst(q->flow_mode))
+ host_load = max(host_load, dsthost->dsthost_refcnt);
+
+ flow->deficit = (b->flow_quantum *
+ quantum_div[host_load]) >> 16;
+ } else if (flow->set == CAKE_SET_SPARSE_WAIT) {
+ /* this flow was empty, accounted as a sparse flow, but actually
+ * in the bulk rotation.
+ */
+ flow->set = CAKE_SET_BULK;
+ b->sparse_flow_count--;
+ b->bulk_flow_count++;
+ }
+
+ if (q->buffer_used > q->buffer_max_used)
+ q->buffer_max_used = q->buffer_used;
+
+ if (q->buffer_used > q->buffer_limit) {
+ u32 dropped = 0;
+
+ while (q->buffer_used > q->buffer_limit) {
+ dropped++;
+ cake_drop(sch, to_free);
+ }
+ b->drop_overlimit += dropped;
+ }
+ return NET_XMIT_SUCCESS;
+}
+
+static struct sk_buff *cake_dequeue_one(struct Qdisc *sch)
+{
+ struct cake_sched_data *q = qdisc_priv(sch);
+ struct cake_tin_data *b = &q->tins[q->cur_tin];
+ struct cake_flow *flow = &b->flows[q->cur_flow];
+ struct sk_buff *skb = NULL;
+ u32 len;
+
+ if (flow->head) {
+ skb = dequeue_head(flow);
+ len = qdisc_pkt_len(skb);
+ b->backlogs[q->cur_flow] -= len;
+ b->tin_backlog -= len;
+ sch->qstats.backlog -= len;
+ q->buffer_used -= skb->truesize;
+ sch->q.qlen--;
+
+ if (q->overflow_timeout)
+ cake_heapify(q, b->overflow_idx[q->cur_flow]);
+ }
+ return skb;
+}
+
+/* Discard leftover packets from a tin no longer in use. */
+static void cake_clear_tin(struct Qdisc *sch, u16 tin)
+{
+ struct cake_sched_data *q = qdisc_priv(sch);
+ struct sk_buff *skb;
+
+ q->cur_tin = tin;
+ for (q->cur_flow = 0; q->cur_flow < CAKE_QUEUES; q->cur_flow++)
+ while (!!(skb = cake_dequeue_one(sch)))
+ kfree_skb(skb);
+}
+
+static struct sk_buff *cake_dequeue(struct Qdisc *sch)
+{
+ struct cake_sched_data *q = qdisc_priv(sch);
+ struct cake_tin_data *b = &q->tins[q->cur_tin];
+ struct cake_host *srchost, *dsthost;
+ ktime_t now = ktime_get();
+ struct cake_flow *flow;
+ struct list_head *head;
+ bool first_flow = true;
+ struct sk_buff *skb;
+ u16 host_load;
+ u64 delay;
+ u32 len;
+
+begin:
+ if (!sch->q.qlen)
+ return NULL;
+
+ /* global hard shaper */
+ if (ktime_after(q->time_next_packet, now) &&
+ ktime_after(q->failsafe_next_packet, now)) {
+ u64 next = min(ktime_to_ns(q->time_next_packet),
+ ktime_to_ns(q->failsafe_next_packet));
+
+ sch->qstats.overlimits++;
+ qdisc_watchdog_schedule_ns(&q->watchdog, next);
+ return NULL;
+ }
+
+ /* Choose a class to work on. */
+ if (!q->rate_ns) {
+ /* In unlimited mode, can't rely on shaper timings, just balance
+ * with DRR
+ */
+ bool wrapped = false, empty = true;
+
+ while (b->tin_deficit < 0 ||
+ !(b->sparse_flow_count + b->bulk_flow_count)) {
+ if (b->tin_deficit <= 0)
+ b->tin_deficit += b->tin_quantum_band;
+ if (b->sparse_flow_count + b->bulk_flow_count)
+ empty = false;
+
+ q->cur_tin++;
+ b++;
+ if (q->cur_tin >= q->tin_cnt) {
+ q->cur_tin = 0;
+ b = q->tins;
+
+ if (wrapped) {
+ /* It's possible for q->qlen to be
+ * nonzero when we actually have no
+ * packets anywhere.
+ */
+ if (empty)
+ return NULL;
+ } else {
+ wrapped = true;
+ }
+ }
+ }
+ } else {
+ /* In shaped mode, choose:
+ * - Highest-priority tin with queue and meeting schedule, or
+ * - The earliest-scheduled tin with queue.
+ */
+ ktime_t best_time = KTIME_MAX;
+ int tin, best_tin = 0;
+
+ for (tin = 0; tin < q->tin_cnt; tin++) {
+ b = q->tins + tin;
+ if ((b->sparse_flow_count + b->bulk_flow_count) > 0) {
+ ktime_t time_to_pkt = \
+ ktime_sub(b->time_next_packet, now);
+
+ if (ktime_to_ns(time_to_pkt) <= 0 ||
+ ktime_compare(time_to_pkt,
+ best_time) <= 0) {
+ best_time = time_to_pkt;
+ best_tin = tin;
+ }
+ }
+ }
+
+ q->cur_tin = best_tin;
+ b = q->tins + best_tin;
+
+ /* No point in going further if no packets to deliver. */
+ if (unlikely(!(b->sparse_flow_count + b->bulk_flow_count)))
+ return NULL;
+ }
+
+retry:
+ /* service this class */
+ head = &b->decaying_flows;
+ if (!first_flow || list_empty(head)) {
+ head = &b->new_flows;
+ if (list_empty(head)) {
+ head = &b->old_flows;
+ if (unlikely(list_empty(head))) {
+ head = &b->decaying_flows;
+ if (unlikely(list_empty(head)))
+ goto begin;
+ }
+ }
+ }
+ flow = list_first_entry(head, struct cake_flow, flowchain);
+ q->cur_flow = flow - b->flows;
+ first_flow = false;
+
+ /* triple isolation (modified DRR++) */
+ srchost = &b->hosts[flow->srchost];
+ dsthost = &b->hosts[flow->dsthost];
+ host_load = 1;
+
+ if (cake_dsrc(q->flow_mode))
+ host_load = max(host_load, srchost->srchost_refcnt);
+
+ if (cake_ddst(q->flow_mode))
+ host_load = max(host_load, dsthost->dsthost_refcnt);
+
+ WARN_ON(host_load > CAKE_QUEUES);
+
+ /* flow isolation (DRR++) */
+ if (flow->deficit <= 0) {
+ /* The shifted prandom_u32() is a way to apply dithering to
+ * avoid accumulating roundoff errors
+ */
+ flow->deficit += (b->flow_quantum * quantum_div[host_load] +
+ (prandom_u32() >> 16)) >> 16;
+ list_move_tail(&flow->flowchain, &b->old_flows);
+
+ /* Keep all flows with deficits out of the sparse and decaying
+ * rotations. No non-empty flow can go into the decaying
+ * rotation, so they can't get deficits
+ */
+ if (flow->set == CAKE_SET_SPARSE) {
+ if (flow->head) {
+ b->sparse_flow_count--;
+ b->bulk_flow_count++;
+ flow->set = CAKE_SET_BULK;
+ } else {
+ /* we've moved it to the bulk rotation for
+ * correct deficit accounting but we still want
+ * to count it as a sparse flow, not a bulk one.
+ */
+ flow->set = CAKE_SET_SPARSE_WAIT;
+ }
+ }
+ goto retry;
+ }
+
+ /* Retrieve a packet via the AQM */
+ while (1) {
+ skb = cake_dequeue_one(sch);
+ if (!skb) {
+ /* this queue was actually empty */
+ if (cobalt_queue_empty(&flow->cvars, &b->cparams, now))
+ b->unresponsive_flow_count--;
+
+ if (flow->cvars.p_drop || flow->cvars.count ||
+ ktime_before(now, flow->cvars.drop_next)) {
+ /* keep in the flowchain until the state has
+ * decayed to rest
+ */
+ list_move_tail(&flow->flowchain,
+ &b->decaying_flows);
+ if (flow->set == CAKE_SET_BULK) {
+ b->bulk_flow_count--;
+ b->decaying_flow_count++;
+ } else if (flow->set == CAKE_SET_SPARSE ||
+ flow->set == CAKE_SET_SPARSE_WAIT) {
+ b->sparse_flow_count--;
+ b->decaying_flow_count++;
+ }
+ flow->set = CAKE_SET_DECAYING;
+ } else {
+ /* remove empty queue from the flowchain */
+ list_del_init(&flow->flowchain);
+ if (flow->set == CAKE_SET_SPARSE ||
+ flow->set == CAKE_SET_SPARSE_WAIT)
+ b->sparse_flow_count--;
+ else if (flow->set == CAKE_SET_BULK)
+ b->bulk_flow_count--;
+ else
+ b->decaying_flow_count--;
+
+ flow->set = CAKE_SET_NONE;
+ srchost->srchost_refcnt--;
+ dsthost->dsthost_refcnt--;
+ }
+ goto begin;
+ }
+
+ /* Last packet in queue may be marked, shouldn't be dropped */
+ if (!cobalt_should_drop(&flow->cvars, &b->cparams, now, skb,
+ (b->bulk_flow_count *
+ !!(q->rate_flags &
+ CAKE_FLAG_INGRESS))) ||
+ !flow->head)
+ break;
+
+ /* drop this packet, get another one */
+ if (q->rate_flags & CAKE_FLAG_INGRESS) {
+ len = cake_advance_shaper(q, b, skb,
+ now, true);
+ flow->deficit -= len;
+ b->tin_deficit -= len;
+ }
+ flow->dropped++;
+ b->tin_dropped++;
+ qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(skb));
+ qdisc_qstats_drop(sch);
+ kfree_skb(skb);
+ if (q->rate_flags & CAKE_FLAG_INGRESS)
+ goto retry;
+ }
+
+ b->tin_ecn_mark += !!flow->cvars.ecn_marked;
+ qdisc_bstats_update(sch, skb);
+
+ /* collect delay stats */
+ delay = ktime_to_ns(ktime_sub(now, cobalt_get_enqueue_time(skb)));
+ b->avge_delay = cake_ewma(b->avge_delay, delay, 8);
+ b->peak_delay = cake_ewma(b->peak_delay, delay,
+ delay > b->peak_delay ? 2 : 8);
+ b->base_delay = cake_ewma(b->base_delay, delay,
+ delay < b->base_delay ? 2 : 8);
+
+ len = cake_advance_shaper(q, b, skb, now, false);
+ flow->deficit -= len;
+ b->tin_deficit -= len;
+
+ if (ktime_after(q->time_next_packet, now) && sch->q.qlen) {
+ u64 next = min(ktime_to_ns(q->time_next_packet),
+ ktime_to_ns(q->failsafe_next_packet));
+
+ qdisc_watchdog_schedule_ns(&q->watchdog, next);
+ } else if (!sch->q.qlen) {
+ int i;
+
+ for (i = 0; i < q->tin_cnt; i++) {
+ if (q->tins[i].decaying_flow_count) {
+ ktime_t next = \
+ ktime_add_ns(now,
+ q->tins[i].cparams.target);
+
+ qdisc_watchdog_schedule_ns(&q->watchdog,
+ ktime_to_ns(next));
+ break;
+ }
+ }
+ }
+
+ if (q->overflow_timeout)
+ q->overflow_timeout--;
+
+ return skb;
+}
+
+static void cake_reset(struct Qdisc *sch)
+{
+ u32 c;
+
+ for (c = 0; c < CAKE_MAX_TINS; c++)
+ cake_clear_tin(sch, c);
+}
+
+static const struct nla_policy cake_policy[TCA_CAKE_MAX + 1] = {
+ [TCA_CAKE_BASE_RATE64] = { .type = NLA_U64 },
+ [TCA_CAKE_DIFFSERV_MODE] = { .type = NLA_U32 },
+ [TCA_CAKE_ATM] = { .type = NLA_U32 },
+ [TCA_CAKE_FLOW_MODE] = { .type = NLA_U32 },
+ [TCA_CAKE_OVERHEAD] = { .type = NLA_S32 },
+ [TCA_CAKE_RTT] = { .type = NLA_U32 },
+ [TCA_CAKE_TARGET] = { .type = NLA_U32 },
+ [TCA_CAKE_AUTORATE] = { .type = NLA_U32 },
+ [TCA_CAKE_MEMORY] = { .type = NLA_U32 },
+ [TCA_CAKE_NAT] = { .type = NLA_U32 },
+ [TCA_CAKE_RAW] = { .type = NLA_U32 },
+ [TCA_CAKE_WASH] = { .type = NLA_U32 },
+ [TCA_CAKE_MPU] = { .type = NLA_U32 },
+ [TCA_CAKE_INGRESS] = { .type = NLA_U32 },
+ [TCA_CAKE_ACK_FILTER] = { .type = NLA_U32 },
+};
+
+static void cake_set_rate(struct cake_tin_data *b, u64 rate, u32 mtu,
+ u64 target_ns, u64 rtt_est_ns)
+{
+ /* convert byte-rate into time-per-byte
+ * so it will always unwedge in reasonable time.
+ */
+ static const u64 MIN_RATE = 64;
+ u32 byte_target = mtu;
+ u64 byte_target_ns;
+ u8 rate_shft = 0;
+ u64 rate_ns = 0;
+
+ b->flow_quantum = 1514;
+ if (rate) {
+ b->flow_quantum = max(min(rate >> 12, 1514ULL), 300ULL);
+ rate_shft = 34;
+ rate_ns = ((u64)NSEC_PER_SEC) << rate_shft;
+ rate_ns = div64_u64(rate_ns, max(MIN_RATE, rate));
+ while (!!(rate_ns >> 34)) {
+ rate_ns >>= 1;
+ rate_shft--;
+ }
+ } /* else unlimited, ie. zero delay */
+
+ b->tin_rate_bps = rate;
+ b->tin_rate_ns = rate_ns;
+ b->tin_rate_shft = rate_shft;
+
+ byte_target_ns = (byte_target * rate_ns) >> rate_shft;
+
+ b->cparams.target = max((byte_target_ns * 3) / 2, target_ns);
+ b->cparams.interval = max(rtt_est_ns +
+ b->cparams.target - target_ns,
+ b->cparams.target * 2);
+ b->cparams.mtu_time = byte_target_ns;
+ b->cparams.p_inc = 1 << 24; /* 1/256 */
+ b->cparams.p_dec = 1 << 20; /* 1/4096 */
+}
+
+static int cake_config_besteffort(struct Qdisc *sch)
+{
+ struct cake_sched_data *q = qdisc_priv(sch);
+ struct cake_tin_data *b = &q->tins[0];
+ u32 mtu = psched_mtu(qdisc_dev(sch));
+ u64 rate = q->rate_bps;
+
+ q->tin_cnt = 1;
+
+ q->tin_index = besteffort;
+ q->tin_order = normal_order;
+
+ cake_set_rate(b, rate, mtu,
+ us_to_ns(q->target), us_to_ns(q->interval));
+ b->tin_quantum_band = 65535;
+ b->tin_quantum_prio = 65535;
+
+ return 0;
+}
+
+static int cake_config_precedence(struct Qdisc *sch)
+{
+ /* convert high-level (user visible) parameters into internal format */
+ struct cake_sched_data *q = qdisc_priv(sch);
+ u32 mtu = psched_mtu(qdisc_dev(sch));
+ u64 rate = q->rate_bps;
+ u32 quantum1 = 256;
+ u32 quantum2 = 256;
+ u32 i;
+
+ q->tin_cnt = 8;
+ q->tin_index = precedence;
+ q->tin_order = normal_order;
+
+ for (i = 0; i < q->tin_cnt; i++) {
+ struct cake_tin_data *b = &q->tins[i];
+
+ cake_set_rate(b, rate, mtu, us_to_ns(q->target),
+ us_to_ns(q->interval));
+
+ b->tin_quantum_prio = max_t(u16, 1U, quantum1);
+ b->tin_quantum_band = max_t(u16, 1U, quantum2);
+
+ /* calculate next class's parameters */
+ rate *= 7;
+ rate >>= 3;
+
+ quantum1 *= 3;
+ quantum1 >>= 1;
+
+ quantum2 *= 7;
+ quantum2 >>= 3;
+ }
+
+ return 0;
+}
+
+/* List of known Diffserv codepoints:
+ *
+ * Least Effort (CS1)
+ * Best Effort (CS0)
+ * Max Reliability & LLT "Lo" (TOS1)
+ * Max Throughput (TOS2)
+ * Min Delay (TOS4)
+ * LLT "La" (TOS5)
+ * Assured Forwarding 1 (AF1x) - x3
+ * Assured Forwarding 2 (AF2x) - x3
+ * Assured Forwarding 3 (AF3x) - x3
+ * Assured Forwarding 4 (AF4x) - x3
+ * Precedence Class 2 (CS2)
+ * Precedence Class 3 (CS3)
+ * Precedence Class 4 (CS4)
+ * Precedence Class 5 (CS5)
+ * Precedence Class 6 (CS6)
+ * Precedence Class 7 (CS7)
+ * Voice Admit (VA)
+ * Expedited Forwarding (EF)
+
+ * Total 25 codepoints.
+ */
+
+/* List of traffic classes in RFC 4594:
+ * (roughly descending order of contended priority)
+ * (roughly ascending order of uncontended throughput)
+ *
+ * Network Control (CS6,CS7) - routing traffic
+ * Telephony (EF,VA) - aka. VoIP streams
+ * Signalling (CS5) - VoIP setup
+ * Multimedia Conferencing (AF4x) - aka. video calls
+ * Realtime Interactive (CS4) - eg. games
+ * Multimedia Streaming (AF3x) - eg. YouTube, NetFlix, Twitch
+ * Broadcast Video (CS3)
+ * Low Latency Data (AF2x,TOS4) - eg. database
+ * Ops, Admin, Management (CS2,TOS1) - eg. ssh
+ * Standard Service (CS0 & unrecognised codepoints)
+ * High Throughput Data (AF1x,TOS2) - eg. web traffic
+ * Low Priority Data (CS1) - eg. BitTorrent
+
+ * Total 12 traffic classes.
+ */
+
+static int cake_config_diffserv8(struct Qdisc *sch)
+{
+/* Pruned list of traffic classes for typical applications:
+ *
+ * Network Control (CS6, CS7)
+ * Minimum Latency (EF, VA, CS5, CS4)
+ * Interactive Shell (CS2, TOS1)
+ * Low Latency Transactions (AF2x, TOS4)
+ * Video Streaming (AF4x, AF3x, CS3)
+ * Bog Standard (CS0 etc.)
+ * High Throughput (AF1x, TOS2)
+ * Background Traffic (CS1)
+ *
+ * Total 8 traffic classes.
+ */
+
+ struct cake_sched_data *q = qdisc_priv(sch);
+ u32 mtu = psched_mtu(qdisc_dev(sch));
+ u64 rate = q->rate_bps;
+ u32 quantum1 = 256;
+ u32 quantum2 = 256;
+ u32 i;
+
+ q->tin_cnt = 8;
+
+ /* codepoint to class mapping */
+ q->tin_index = diffserv8;
+ q->tin_order = normal_order;
+
+ /* class characteristics */
+ for (i = 0; i < q->tin_cnt; i++) {
+ struct cake_tin_data *b = &q->tins[i];
+
+ cake_set_rate(b, rate, mtu, us_to_ns(q->target),
+ us_to_ns(q->interval));
+
+ b->tin_quantum_prio = max_t(u16, 1U, quantum1);
+ b->tin_quantum_band = max_t(u16, 1U, quantum2);
+
+ /* calculate next class's parameters */
+ rate *= 7;
+ rate >>= 3;
+
+ quantum1 *= 3;
+ quantum1 >>= 1;
+
+ quantum2 *= 7;
+ quantum2 >>= 3;
+ }
+
+ return 0;
+}
+
+static int cake_config_diffserv4(struct Qdisc *sch)
+{
+/* Further pruned list of traffic classes for four-class system:
+ *
+ * Latency Sensitive (CS7, CS6, EF, VA, CS5, CS4)
+ * Streaming Media (AF4x, AF3x, CS3, AF2x, TOS4, CS2, TOS1)
+ * Best Effort (CS0, AF1x, TOS2, and those not specified)
+ * Background Traffic (CS1)
+ *
+ * Total 4 traffic classes.
+ */
+
+ struct cake_sched_data *q = qdisc_priv(sch);
+ u32 mtu = psched_mtu(qdisc_dev(sch));
+ u64 rate = q->rate_bps;
+ u32 quantum = 1024;
+
+ q->tin_cnt = 4;
+
+ /* codepoint to class mapping */
+ q->tin_index = diffserv4;
+ q->tin_order = bulk_order;
+
+ /* class characteristics */
+ cake_set_rate(&q->tins[0], rate, mtu,
+ us_to_ns(q->target), us_to_ns(q->interval));
+ cake_set_rate(&q->tins[1], rate >> 4, mtu,
+ us_to_ns(q->target), us_to_ns(q->interval));
+ cake_set_rate(&q->tins[2], rate >> 1, mtu,
+ us_to_ns(q->target), us_to_ns(q->interval));
+ cake_set_rate(&q->tins[3], rate >> 2, mtu,
+ us_to_ns(q->target), us_to_ns(q->interval));
+
+ /* priority weights */
+ q->tins[0].tin_quantum_prio = quantum;
+ q->tins[1].tin_quantum_prio = quantum >> 4;
+ q->tins[2].tin_quantum_prio = quantum << 2;
+ q->tins[3].tin_quantum_prio = quantum << 4;
+
+ /* bandwidth-sharing weights */
+ q->tins[0].tin_quantum_band = quantum;
+ q->tins[1].tin_quantum_band = quantum >> 4;
+ q->tins[2].tin_quantum_band = quantum >> 1;
+ q->tins[3].tin_quantum_band = quantum >> 2;
+
+ return 0;
+}
+
+static int cake_config_diffserv3(struct Qdisc *sch)
+{
+/* Simplified Diffserv structure with 3 tins.
+ * Low Priority (CS1)
+ * Best Effort
+ * Latency Sensitive (TOS4, VA, EF, CS6, CS7)
+ */
+ struct cake_sched_data *q = qdisc_priv(sch);
+ u32 mtu = psched_mtu(qdisc_dev(sch));
+ u64 rate = q->rate_bps;
+ u32 quantum = 1024;
+
+ q->tin_cnt = 3;
+
+ /* codepoint to class mapping */
+ q->tin_index = diffserv3;
+ q->tin_order = bulk_order;
+
+ /* class characteristics */
+ cake_set_rate(&q->tins[0], rate, mtu,
+ us_to_ns(q->target), us_to_ns(q->interval));
+ cake_set_rate(&q->tins[1], rate >> 4, mtu,
+ us_to_ns(q->target), us_to_ns(q->interval));
+ cake_set_rate(&q->tins[2], rate >> 2, mtu,
+ us_to_ns(q->target), us_to_ns(q->interval));
+
+ /* priority weights */
+ q->tins[0].tin_quantum_prio = quantum;
+ q->tins[1].tin_quantum_prio = quantum >> 4;
+ q->tins[2].tin_quantum_prio = quantum << 4;
+
+ /* bandwidth-sharing weights */
+ q->tins[0].tin_quantum_band = quantum;
+ q->tins[1].tin_quantum_band = quantum >> 4;
+ q->tins[2].tin_quantum_band = quantum >> 2;
+
+ return 0;
+}
+
+static void cake_reconfigure(struct Qdisc *sch)
+{
+ struct cake_sched_data *q = qdisc_priv(sch);
+ int c, ft;
+
+ switch (q->tin_mode) {
+ case CAKE_DIFFSERV_BESTEFFORT:
+ ft = cake_config_besteffort(sch);
+ break;
+
+ case CAKE_DIFFSERV_PRECEDENCE:
+ ft = cake_config_precedence(sch);
+ break;
+
+ case CAKE_DIFFSERV_DIFFSERV8:
+ ft = cake_config_diffserv8(sch);
+ break;
+
+ case CAKE_DIFFSERV_DIFFSERV4:
+ ft = cake_config_diffserv4(sch);
+ break;
+
+ case CAKE_DIFFSERV_DIFFSERV3:
+ default:
+ ft = cake_config_diffserv3(sch);
+ break;
+ }
+
+ for (c = q->tin_cnt; c < CAKE_MAX_TINS; c++) {
+ cake_clear_tin(sch, c);
+ q->tins[c].cparams.mtu_time = q->tins[ft].cparams.mtu_time;
+ }
+
+ q->rate_ns = q->tins[ft].tin_rate_ns;
+ q->rate_shft = q->tins[ft].tin_rate_shft;
+
+ if (q->buffer_config_limit) {
+ q->buffer_limit = q->buffer_config_limit;
+ } else if (q->rate_bps) {
+ u64 t = q->rate_bps * q->interval;
+
+ do_div(t, USEC_PER_SEC / 4);
+ q->buffer_limit = max_t(u32, t, 4U << 20);
+ } else {
+ q->buffer_limit = ~0;
+ }
+
+ sch->flags &= ~TCQ_F_CAN_BYPASS;
+
+ q->buffer_limit = min(q->buffer_limit,
+ max(sch->limit * psched_mtu(qdisc_dev(sch)),
+ q->buffer_config_limit));
+}
+
+static int cake_change(struct Qdisc *sch, struct nlattr *opt,
+ struct netlink_ext_ack *extack)
+{
+ struct cake_sched_data *q = qdisc_priv(sch);
+ struct nlattr *tb[TCA_CAKE_MAX + 1];
+ int err;
+
+ if (!opt)
+ return -EINVAL;
+
+ err = nla_parse_nested(tb, TCA_CAKE_MAX, opt, cake_policy, extack);
+ if (err < 0)
+ return err;
+
+ if (tb[TCA_CAKE_NAT]) {
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+ q->flow_mode &= ~CAKE_FLOW_NAT_FLAG;
+ q->flow_mode |= CAKE_FLOW_NAT_FLAG *
+ !!nla_get_u32(tb[TCA_CAKE_NAT]);
+#else
+ NL_SET_ERR_MSG_ATTR(extack, tb[TCA_CAKE_NAT],
+ "No conntrack support in kernel");
+ return -EOPNOTSUPP;
+#endif
+ }
+
+ if (tb[TCA_CAKE_BASE_RATE64])
+ q->rate_bps = nla_get_u64(tb[TCA_CAKE_BASE_RATE64]);
+
+ if (tb[TCA_CAKE_DIFFSERV_MODE])
+ q->tin_mode = nla_get_u32(tb[TCA_CAKE_DIFFSERV_MODE]);
+
+ if (tb[TCA_CAKE_WASH]) {
+ if (!!nla_get_u32(tb[TCA_CAKE_WASH]))
+ q->rate_flags |= CAKE_FLAG_WASH;
+ else
+ q->rate_flags &= ~CAKE_FLAG_WASH;
+ }
+
+ if (tb[TCA_CAKE_FLOW_MODE])
+ q->flow_mode = ((q->flow_mode & CAKE_FLOW_NAT_FLAG) |
+ (nla_get_u32(tb[TCA_CAKE_FLOW_MODE]) &
+ CAKE_FLOW_MASK));
+
+ if (tb[TCA_CAKE_ATM])
+ q->atm_mode = nla_get_u32(tb[TCA_CAKE_ATM]);
+
+ if (tb[TCA_CAKE_OVERHEAD]) {
+ q->rate_overhead = nla_get_s32(tb[TCA_CAKE_OVERHEAD]);
+ q->rate_flags |= CAKE_FLAG_OVERHEAD;
+
+ q->max_netlen = 0;
+ q->max_adjlen = 0;
+ q->min_netlen = ~0;
+ q->min_adjlen = ~0;
+ }
+
+ if (tb[TCA_CAKE_RAW]) {
+ q->rate_flags &= ~CAKE_FLAG_OVERHEAD;
+
+ q->max_netlen = 0;
+ q->max_adjlen = 0;
+ q->min_netlen = ~0;
+ q->min_adjlen = ~0;
+ }
+
+ if (tb[TCA_CAKE_MPU])
+ q->rate_mpu = nla_get_u32(tb[TCA_CAKE_MPU]);
+
+ if (tb[TCA_CAKE_RTT]) {
+ q->interval = nla_get_u32(tb[TCA_CAKE_RTT]);
+
+ if (!q->interval)
+ q->interval = 1;
+ }
+
+ if (tb[TCA_CAKE_TARGET]) {
+ q->target = nla_get_u32(tb[TCA_CAKE_TARGET]);
+
+ if (!q->target)
+ q->target = 1;
+ }
+
+ if (tb[TCA_CAKE_AUTORATE]) {
+ if (!!nla_get_u32(tb[TCA_CAKE_AUTORATE]))
+ q->rate_flags |= CAKE_FLAG_AUTORATE_INGRESS;
+ else
+ q->rate_flags &= ~CAKE_FLAG_AUTORATE_INGRESS;
+ }
+
+ if (tb[TCA_CAKE_INGRESS]) {
+ if (!!nla_get_u32(tb[TCA_CAKE_INGRESS]))
+ q->rate_flags |= CAKE_FLAG_INGRESS;
+ else
+ q->rate_flags &= ~CAKE_FLAG_INGRESS;
+ }
+
+ if (tb[TCA_CAKE_ACK_FILTER])
+ q->ack_filter = nla_get_u32(tb[TCA_CAKE_ACK_FILTER]);
+
+ if (tb[TCA_CAKE_MEMORY])
+ q->buffer_config_limit = nla_get_u32(tb[TCA_CAKE_MEMORY]);
+
+ if (q->rate_bps && q->rate_bps <= CAKE_SPLIT_GSO_THRESHOLD)
+ q->rate_flags |= CAKE_FLAG_SPLIT_GSO;
+ else
+ q->rate_flags &= ~CAKE_FLAG_SPLIT_GSO;
+
+ if (q->tins) {
+ sch_tree_lock(sch);
+ cake_reconfigure(sch);
+ sch_tree_unlock(sch);
+ }
+
+ return 0;
+}
+
+static void cake_destroy(struct Qdisc *sch)
+{
+ struct cake_sched_data *q = qdisc_priv(sch);
+
+ qdisc_watchdog_cancel(&q->watchdog);
+ tcf_block_put(q->block);
+ kvfree(q->tins);
+}
+
+static int cake_init(struct Qdisc *sch, struct nlattr *opt,
+ struct netlink_ext_ack *extack)
+{
+ struct cake_sched_data *q = qdisc_priv(sch);
+ int i, j, err;
+
+ sch->limit = 10240;
+ q->tin_mode = CAKE_DIFFSERV_DIFFSERV3;
+ q->flow_mode = CAKE_FLOW_TRIPLE;
+
+ q->rate_bps = 0; /* unlimited by default */
+
+ q->interval = 100000; /* 100ms default */
+ q->target = 5000; /* 5ms: codel RFC argues
+ * for 5 to 10% of interval
+ */
+
+ q->cur_tin = 0;
+ q->cur_flow = 0;
+
+ qdisc_watchdog_init(&q->watchdog, sch);
+
+ if (opt) {
+ int err = cake_change(sch, opt, extack);
+
+ if (err)
+ return err;
+ }
+
+ err = tcf_block_get(&q->block, &q->filter_list, sch, extack);
+ if (err)
+ return err;
+
+ quantum_div[0] = ~0;
+ for (i = 1; i <= CAKE_QUEUES; i++)
+ quantum_div[i] = 65535 / i;
+
+ q->tins = kvzalloc(CAKE_MAX_TINS * sizeof(struct cake_tin_data),
+ GFP_KERNEL);
+ if (!q->tins)
+ goto nomem;
+
+ for (i = 0; i < CAKE_MAX_TINS; i++) {
+ struct cake_tin_data *b = q->tins + i;
+
+ INIT_LIST_HEAD(&b->new_flows);
+ INIT_LIST_HEAD(&b->old_flows);
+ INIT_LIST_HEAD(&b->decaying_flows);
+ b->sparse_flow_count = 0;
+ b->bulk_flow_count = 0;
+ b->decaying_flow_count = 0;
+
+ for (j = 0; j < CAKE_QUEUES; j++) {
+ struct cake_flow *flow = b->flows + j;
+ u32 k = j * CAKE_MAX_TINS + i;
+
+ INIT_LIST_HEAD(&flow->flowchain);
+ cobalt_vars_init(&flow->cvars);
+
+ q->overflow_heap[k].t = i;
+ q->overflow_heap[k].b = j;
+ b->overflow_idx[j] = k;
+ }
+ }
+
+ cake_reconfigure(sch);
+ q->avg_peak_bandwidth = q->rate_bps;
+ q->min_netlen = ~0;
+ q->min_adjlen = ~0;
+ return 0;
+
+nomem:
+ cake_destroy(sch);
+ return -ENOMEM;
+}
+
+static int cake_dump(struct Qdisc *sch, struct sk_buff *skb)
+{
+ struct cake_sched_data *q = qdisc_priv(sch);
+ struct nlattr *opts;
+
+ opts = nla_nest_start(skb, TCA_OPTIONS);
+ if (!opts)
+ goto nla_put_failure;
+
+ if (nla_put_u64_64bit(skb, TCA_CAKE_BASE_RATE64, q->rate_bps,
+ TCA_CAKE_PAD))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, TCA_CAKE_FLOW_MODE,
+ q->flow_mode & CAKE_FLOW_MASK))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, TCA_CAKE_RTT, q->interval))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, TCA_CAKE_TARGET, q->target))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, TCA_CAKE_MEMORY, q->buffer_config_limit))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, TCA_CAKE_AUTORATE,
+ !!(q->rate_flags & CAKE_FLAG_AUTORATE_INGRESS)))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, TCA_CAKE_INGRESS,
+ !!(q->rate_flags & CAKE_FLAG_INGRESS)))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, TCA_CAKE_ACK_FILTER, q->ack_filter))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, TCA_CAKE_NAT,
+ !!(q->flow_mode & CAKE_FLOW_NAT_FLAG)))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, TCA_CAKE_DIFFSERV_MODE, q->tin_mode))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, TCA_CAKE_WASH,
+ !!(q->rate_flags & CAKE_FLAG_WASH)))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, TCA_CAKE_OVERHEAD, q->rate_overhead))
+ goto nla_put_failure;
+
+ if (!(q->rate_flags & CAKE_FLAG_OVERHEAD))
+ if (nla_put_u32(skb, TCA_CAKE_RAW, 0))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, TCA_CAKE_ATM, q->atm_mode))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, TCA_CAKE_MPU, q->rate_mpu))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, TCA_CAKE_SPLIT_GSO,
+ !!(q->rate_flags & CAKE_FLAG_SPLIT_GSO)))
+ goto nla_put_failure;
+
+ return nla_nest_end(skb, opts);
+
+nla_put_failure:
+ return -1;
+}
+
+static int cake_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
+{
+ struct nlattr *stats = nla_nest_start(d->skb, TCA_STATS_APP);
+ struct cake_sched_data *q = qdisc_priv(sch);
+ struct nlattr *tstats, *ts;
+ int i;
+
+ if (!stats)
+ return -1;
+
+#define PUT_STAT_U32(attr, data) do { \
+ if (nla_put_u32(d->skb, TCA_CAKE_STATS_ ## attr, data)) \
+ goto nla_put_failure; \
+ } while (0)
+#define PUT_STAT_U64(attr, data) do { \
+ if (nla_put_u64_64bit(d->skb, TCA_CAKE_STATS_ ## attr, \
+ data, TCA_CAKE_STATS_PAD)) \
+ goto nla_put_failure; \
+ } while (0)
+
+ PUT_STAT_U64(CAPACITY_ESTIMATE64, q->avg_peak_bandwidth);
+ PUT_STAT_U32(MEMORY_LIMIT, q->buffer_limit);
+ PUT_STAT_U32(MEMORY_USED, q->buffer_max_used);
+ PUT_STAT_U32(AVG_NETOFF, ((q->avg_netoff + 0x8000) >> 16));
+ PUT_STAT_U32(MAX_NETLEN, q->max_netlen);
+ PUT_STAT_U32(MAX_ADJLEN, q->max_adjlen);
+ PUT_STAT_U32(MIN_NETLEN, q->min_netlen);
+ PUT_STAT_U32(MIN_ADJLEN, q->min_adjlen);
+
+#undef PUT_STAT_U32
+#undef PUT_STAT_U64
+
+ tstats = nla_nest_start(d->skb, TCA_CAKE_STATS_TIN_STATS);
+ if (!tstats)
+ goto nla_put_failure;
+
+#define PUT_TSTAT_U32(attr, data) do { \
+ if (nla_put_u32(d->skb, TCA_CAKE_TIN_STATS_ ## attr, data)) \
+ goto nla_put_failure; \
+ } while (0)
+#define PUT_TSTAT_U64(attr, data) do { \
+ if (nla_put_u64_64bit(d->skb, TCA_CAKE_TIN_STATS_ ## attr, \
+ data, TCA_CAKE_TIN_STATS_PAD)) \
+ goto nla_put_failure; \
+ } while (0)
+
+ for (i = 0; i < q->tin_cnt; i++) {
+ struct cake_tin_data *b = &q->tins[q->tin_order[i]];
+
+ ts = nla_nest_start(d->skb, i + 1);
+ if (!ts)
+ goto nla_put_failure;
+
+ PUT_TSTAT_U64(THRESHOLD_RATE64, b->tin_rate_bps);
+ PUT_TSTAT_U64(SENT_BYTES64, b->bytes);
+ PUT_TSTAT_U32(BACKLOG_BYTES, b->tin_backlog);
+
+ PUT_TSTAT_U32(TARGET_US,
+ ktime_to_us(ns_to_ktime(b->cparams.target)));
+ PUT_TSTAT_U32(INTERVAL_US,
+ ktime_to_us(ns_to_ktime(b->cparams.interval)));
+
+ PUT_TSTAT_U32(SENT_PACKETS, b->packets);
+ PUT_TSTAT_U32(DROPPED_PACKETS, b->tin_dropped);
+ PUT_TSTAT_U32(ECN_MARKED_PACKETS, b->tin_ecn_mark);
+ PUT_TSTAT_U32(ACKS_DROPPED_PACKETS, b->ack_drops);
+
+ PUT_TSTAT_U32(PEAK_DELAY_US,
+ ktime_to_us(ns_to_ktime(b->peak_delay)));
+ PUT_TSTAT_U32(AVG_DELAY_US,
+ ktime_to_us(ns_to_ktime(b->avge_delay)));
+ PUT_TSTAT_U32(BASE_DELAY_US,
+ ktime_to_us(ns_to_ktime(b->base_delay)));
+
+ PUT_TSTAT_U32(WAY_INDIRECT_HITS, b->way_hits);
+ PUT_TSTAT_U32(WAY_MISSES, b->way_misses);
+ PUT_TSTAT_U32(WAY_COLLISIONS, b->way_collisions);
+
+ PUT_TSTAT_U32(SPARSE_FLOWS, b->sparse_flow_count +
+ b->decaying_flow_count);
+ PUT_TSTAT_U32(BULK_FLOWS, b->bulk_flow_count);
+ PUT_TSTAT_U32(UNRESPONSIVE_FLOWS, b->unresponsive_flow_count);
+ PUT_TSTAT_U32(MAX_SKBLEN, b->max_skblen);
+
+ PUT_TSTAT_U32(FLOW_QUANTUM, b->flow_quantum);
+ nla_nest_end(d->skb, ts);
+ }
+
+#undef PUT_TSTAT_U32
+#undef PUT_TSTAT_U64
+
+ nla_nest_end(d->skb, tstats);
+ return nla_nest_end(d->skb, stats);
+
+nla_put_failure:
+ nla_nest_cancel(d->skb, stats);
+ return -1;
+}
+
+static struct Qdisc *cake_leaf(struct Qdisc *sch, unsigned long arg)
+{
+ return NULL;
+}
+
+static unsigned long cake_find(struct Qdisc *sch, u32 classid)
+{
+ return 0;
+}
+
+static unsigned long cake_bind(struct Qdisc *sch, unsigned long parent,
+ u32 classid)
+{
+ return 0;
+}
+
+static void cake_unbind(struct Qdisc *q, unsigned long cl)
+{
+}
+
+static struct tcf_block *cake_tcf_block(struct Qdisc *sch, unsigned long cl,
+ struct netlink_ext_ack *extack)
+{
+ struct cake_sched_data *q = qdisc_priv(sch);
+
+ if (cl)
+ return NULL;
+ return q->block;
+}
+
+static int cake_dump_class(struct Qdisc *sch, unsigned long cl,
+ struct sk_buff *skb, struct tcmsg *tcm)
+{
+ tcm->tcm_handle |= TC_H_MIN(cl);
+ return 0;
+}
+
+static int cake_dump_class_stats(struct Qdisc *sch, unsigned long cl,
+ struct gnet_dump *d)
+{
+ struct cake_sched_data *q = qdisc_priv(sch);
+ const struct cake_flow *flow = NULL;
+ struct gnet_stats_queue qs = { 0 };
+ struct nlattr *stats;
+ u32 idx = cl - 1;
+
+ if (idx < CAKE_QUEUES * q->tin_cnt) {
+ const struct cake_tin_data *b = \
+ &q->tins[q->tin_order[idx / CAKE_QUEUES]];
+ const struct sk_buff *skb;
+
+ flow = &b->flows[idx % CAKE_QUEUES];
+
+ if (flow->head) {
+ sch_tree_lock(sch);
+ skb = flow->head;
+ while (skb) {
+ qs.qlen++;
+ skb = skb->next;
+ }
+ sch_tree_unlock(sch);
+ }
+ qs.backlog = b->backlogs[idx % CAKE_QUEUES];
+ qs.drops = flow->dropped;
+ }
+ if (gnet_stats_copy_queue(d, NULL, &qs, qs.qlen) < 0)
+ return -1;
+ if (flow) {
+ ktime_t now = ktime_get();
+
+ stats = nla_nest_start(d->skb, TCA_STATS_APP);
+ if (!stats)
+ return -1;
+
+#define PUT_STAT_U32(attr, data) do { \
+ if (nla_put_u32(d->skb, TCA_CAKE_STATS_ ## attr, data)) \
+ goto nla_put_failure; \
+ } while (0)
+#define PUT_STAT_S32(attr, data) do { \
+ if (nla_put_s32(d->skb, TCA_CAKE_STATS_ ## attr, data)) \
+ goto nla_put_failure; \
+ } while (0)
+
+ PUT_STAT_S32(DEFICIT, flow->deficit);
+ PUT_STAT_U32(DROPPING, flow->cvars.dropping);
+ PUT_STAT_U32(COBALT_COUNT, flow->cvars.count);
+ PUT_STAT_U32(P_DROP, flow->cvars.p_drop);
+ if (flow->cvars.p_drop) {
+ PUT_STAT_S32(BLUE_TIMER_US,
+ ktime_to_us(
+ ktime_sub(now,
+ flow->cvars.blue_timer)));
+ }
+ if (flow->cvars.dropping) {
+ PUT_STAT_S32(DROP_NEXT_US,
+ ktime_to_us(
+ ktime_sub(now,
+ flow->cvars.drop_next)));
+ }
+
+ if (nla_nest_end(d->skb, stats) < 0)
+ return -1;
+ }
+
+ return 0;
+
+nla_put_failure:
+ nla_nest_cancel(d->skb, stats);
+ return -1;
+}
+
+static void cake_walk(struct Qdisc *sch, struct qdisc_walker *arg)
+{
+ struct cake_sched_data *q = qdisc_priv(sch);
+ unsigned int i, j;
+
+ if (arg->stop)
+ return;
+
+ for (i = 0; i < q->tin_cnt; i++) {
+ struct cake_tin_data *b = &q->tins[q->tin_order[i]];
+
+ for (j = 0; j < CAKE_QUEUES; j++) {
+ if (list_empty(&b->flows[j].flowchain) ||
+ arg->count < arg->skip) {
+ arg->count++;
+ continue;
+ }
+ if (arg->fn(sch, i * CAKE_QUEUES + j + 1, arg) < 0) {
+ arg->stop = 1;
+ break;
+ }
+ arg->count++;
+ }
+ }
+}
+
+static const struct Qdisc_class_ops cake_class_ops = {
+ .leaf = cake_leaf,
+ .find = cake_find,
+ .tcf_block = cake_tcf_block,
+ .bind_tcf = cake_bind,
+ .unbind_tcf = cake_unbind,
+ .dump = cake_dump_class,
+ .dump_stats = cake_dump_class_stats,
+ .walk = cake_walk,
+};
+
+static struct Qdisc_ops cake_qdisc_ops __read_mostly = {
+ .cl_ops = &cake_class_ops,
+ .id = "cake",
+ .priv_size = sizeof(struct cake_sched_data),
+ .enqueue = cake_enqueue,
+ .dequeue = cake_dequeue,
+ .peek = qdisc_peek_dequeued,
+ .init = cake_init,
+ .reset = cake_reset,
+ .destroy = cake_destroy,
+ .change = cake_change,
+ .dump = cake_dump,
+ .dump_stats = cake_dump_stats,
+ .owner = THIS_MODULE,
+};
+
+static int __init cake_module_init(void)
+{
+ return register_qdisc(&cake_qdisc_ops);
+}
+
+static void __exit cake_module_exit(void)
+{
+ unregister_qdisc(&cake_qdisc_ops);
+}
+
+module_init(cake_module_init)
+module_exit(cake_module_exit)
+MODULE_AUTHOR("Jonathan Morton");
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("The CAKE shaper.");
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+
+/* net/sched/sch_etf.c Earliest TxTime First queueing discipline.
+ *
+ * Authors: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
+ * Vinicius Costa Gomes <vinicius.gomes@intel.com>
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/errqueue.h>
+#include <linux/rbtree.h>
+#include <linux/skbuff.h>
+#include <linux/posix-timers.h>
+#include <net/netlink.h>
+#include <net/sch_generic.h>
+#include <net/pkt_sched.h>
+#include <net/sock.h>
+
+#define DEADLINE_MODE_IS_ON(x) ((x)->flags & TC_ETF_DEADLINE_MODE_ON)
+#define OFFLOAD_IS_ON(x) ((x)->flags & TC_ETF_OFFLOAD_ON)
+
+struct etf_sched_data {
+ bool offload;
+ bool deadline_mode;
+ int clockid;
+ int queue;
+ s32 delta; /* in ns */
+ ktime_t last; /* The txtime of the last skb sent to the netdevice. */
+ struct rb_root head;
+ struct qdisc_watchdog watchdog;
+ ktime_t (*get_time)(void);
+};
+
+static const struct nla_policy etf_policy[TCA_ETF_MAX + 1] = {
+ [TCA_ETF_PARMS] = { .len = sizeof(struct tc_etf_qopt) },
+};
+
+static inline int validate_input_params(struct tc_etf_qopt *qopt,
+ struct netlink_ext_ack *extack)
+{
+ /* Check if params comply to the following rules:
+ * * Clockid and delta must be valid.
+ *
+ * * Dynamic clockids are not supported.
+ *
+ * * Delta must be a positive integer.
+ *
+ * Also note that for the HW offload case, we must
+ * expect that system clocks have been synchronized to PHC.
+ */
+ if (qopt->clockid < 0) {
+ NL_SET_ERR_MSG(extack, "Dynamic clockids are not supported");
+ return -ENOTSUPP;
+ }
+
+ if (qopt->clockid != CLOCK_TAI) {
+ NL_SET_ERR_MSG(extack, "Invalid clockid. CLOCK_TAI must be used");
+ return -EINVAL;
+ }
+
+ if (qopt->delta < 0) {
+ NL_SET_ERR_MSG(extack, "Delta must be positive");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static bool is_packet_valid(struct Qdisc *sch, struct sk_buff *nskb)
+{
+ struct etf_sched_data *q = qdisc_priv(sch);
+ ktime_t txtime = nskb->tstamp;
+ struct sock *sk = nskb->sk;
+ ktime_t now;
+
+ if (!sk)
+ return false;
+
+ if (!sock_flag(sk, SOCK_TXTIME))
+ return false;
+
+ /* We don't perform crosstimestamping.
+ * Drop if packet's clockid differs from qdisc's.
+ */
+ if (sk->sk_clockid != q->clockid)
+ return false;
+
+ if (sk->sk_txtime_deadline_mode != q->deadline_mode)
+ return false;
+
+ now = q->get_time();
+ if (ktime_before(txtime, now) || ktime_before(txtime, q->last))
+ return false;
+
+ return true;
+}
+
+static struct sk_buff *etf_peek_timesortedlist(struct Qdisc *sch)
+{
+ struct etf_sched_data *q = qdisc_priv(sch);
+ struct rb_node *p;
+
+ p = rb_first(&q->head);
+ if (!p)
+ return NULL;
+
+ return rb_to_skb(p);
+}
+
+static void reset_watchdog(struct Qdisc *sch)
+{
+ struct etf_sched_data *q = qdisc_priv(sch);
+ struct sk_buff *skb = etf_peek_timesortedlist(sch);
+ ktime_t next;
+
+ if (!skb)
+ return;
+
+ next = ktime_sub_ns(skb->tstamp, q->delta);
+ qdisc_watchdog_schedule_ns(&q->watchdog, ktime_to_ns(next));
+}
+
+static void report_sock_error(struct sk_buff *skb, u32 err, u8 code)
+{
+ struct sock_exterr_skb *serr;
+ struct sk_buff *clone;
+ ktime_t txtime = skb->tstamp;
+
+ if (!skb->sk || !(skb->sk->sk_txtime_report_errors))
+ return;
+
+ clone = skb_clone(skb, GFP_ATOMIC);
+ if (!clone)
+ return;
+
+ serr = SKB_EXT_ERR(clone);
+ serr->ee.ee_errno = err;
+ serr->ee.ee_origin = SO_EE_ORIGIN_TXTIME;
+ serr->ee.ee_type = 0;
+ serr->ee.ee_code = code;
+ serr->ee.ee_pad = 0;
+ serr->ee.ee_data = (txtime >> 32); /* high part of tstamp */
+ serr->ee.ee_info = txtime; /* low part of tstamp */
+
+ if (sock_queue_err_skb(skb->sk, clone))
+ kfree_skb(clone);
+}
+
+static int etf_enqueue_timesortedlist(struct sk_buff *nskb, struct Qdisc *sch,
+ struct sk_buff **to_free)
+{
+ struct etf_sched_data *q = qdisc_priv(sch);
+ struct rb_node **p = &q->head.rb_node, *parent = NULL;
+ ktime_t txtime = nskb->tstamp;
+
+ if (!is_packet_valid(sch, nskb)) {
+ report_sock_error(nskb, EINVAL,
+ SO_EE_CODE_TXTIME_INVALID_PARAM);
+ return qdisc_drop(nskb, sch, to_free);
+ }
+
+ while (*p) {
+ struct sk_buff *skb;
+
+ parent = *p;
+ skb = rb_to_skb(parent);
+ if (ktime_after(txtime, skb->tstamp))
+ p = &parent->rb_right;
+ else
+ p = &parent->rb_left;
+ }
+ rb_link_node(&nskb->rbnode, parent, p);
+ rb_insert_color(&nskb->rbnode, &q->head);
+
+ qdisc_qstats_backlog_inc(sch, nskb);
+ sch->q.qlen++;
+
+ /* Now we may need to re-arm the qdisc watchdog for the next packet. */
+ reset_watchdog(sch);
+
+ return NET_XMIT_SUCCESS;
+}
+
+static void timesortedlist_erase(struct Qdisc *sch, struct sk_buff *skb,
+ bool drop)
+{
+ struct etf_sched_data *q = qdisc_priv(sch);
+
+ rb_erase(&skb->rbnode, &q->head);
+
+ /* The rbnode field in the skb re-uses these fields, now that
+ * we are done with the rbnode, reset them.
+ */
+ skb->next = NULL;
+ skb->prev = NULL;
+ skb->dev = qdisc_dev(sch);
+
+ qdisc_qstats_backlog_dec(sch, skb);
+
+ if (drop) {
+ struct sk_buff *to_free = NULL;
+
+ report_sock_error(skb, ECANCELED, SO_EE_CODE_TXTIME_MISSED);
+
+ qdisc_drop(skb, sch, &to_free);
+ kfree_skb_list(to_free);
+ qdisc_qstats_overlimit(sch);
+ } else {
+ qdisc_bstats_update(sch, skb);
+
+ q->last = skb->tstamp;
+ }
+
+ sch->q.qlen--;
+}
+
+static struct sk_buff *etf_dequeue_timesortedlist(struct Qdisc *sch)
+{
+ struct etf_sched_data *q = qdisc_priv(sch);
+ struct sk_buff *skb;
+ ktime_t now, next;
+
+ skb = etf_peek_timesortedlist(sch);
+ if (!skb)
+ return NULL;
+
+ now = q->get_time();
+
+ /* Drop if packet has expired while in queue. */
+ if (ktime_before(skb->tstamp, now)) {
+ timesortedlist_erase(sch, skb, true);
+ skb = NULL;
+ goto out;
+ }
+
+ /* When in deadline mode, dequeue as soon as possible and change the
+ * txtime from deadline to (now + delta).
+ */
+ if (q->deadline_mode) {
+ timesortedlist_erase(sch, skb, false);
+ skb->tstamp = now;
+ goto out;
+ }
+
+ next = ktime_sub_ns(skb->tstamp, q->delta);
+
+ /* Dequeue only if now is within the [txtime - delta, txtime] range. */
+ if (ktime_after(now, next))
+ timesortedlist_erase(sch, skb, false);
+ else
+ skb = NULL;
+
+out:
+ /* Now we may need to re-arm the qdisc watchdog for the next packet. */
+ reset_watchdog(sch);
+
+ return skb;
+}
+
+static void etf_disable_offload(struct net_device *dev,
+ struct etf_sched_data *q)
+{
+ struct tc_etf_qopt_offload etf = { };
+ const struct net_device_ops *ops;
+ int err;
+
+ if (!q->offload)
+ return;
+
+ ops = dev->netdev_ops;
+ if (!ops->ndo_setup_tc)
+ return;
+
+ etf.queue = q->queue;
+ etf.enable = 0;
+
+ err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_ETF, &etf);
+ if (err < 0)
+ pr_warn("Couldn't disable ETF offload for queue %d\n",
+ etf.queue);
+}
+
+static int etf_enable_offload(struct net_device *dev, struct etf_sched_data *q,
+ struct netlink_ext_ack *extack)
+{
+ const struct net_device_ops *ops = dev->netdev_ops;
+ struct tc_etf_qopt_offload etf = { };
+ int err;
+
+ if (q->offload)
+ return 0;
+
+ if (!ops->ndo_setup_tc) {
+ NL_SET_ERR_MSG(extack, "Specified device does not support ETF offload");
+ return -EOPNOTSUPP;
+ }
+
+ etf.queue = q->queue;
+ etf.enable = 1;
+
+ err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_ETF, &etf);
+ if (err < 0) {
+ NL_SET_ERR_MSG(extack, "Specified device failed to setup ETF hardware offload");
+ return err;
+ }
+
+ return 0;
+}
+
+static int etf_init(struct Qdisc *sch, struct nlattr *opt,
+ struct netlink_ext_ack *extack)
+{
+ struct etf_sched_data *q = qdisc_priv(sch);
+ struct net_device *dev = qdisc_dev(sch);
+ struct nlattr *tb[TCA_ETF_MAX + 1];
+ struct tc_etf_qopt *qopt;
+ int err;
+
+ if (!opt) {
+ NL_SET_ERR_MSG(extack,
+ "Missing ETF qdisc options which are mandatory");
+ return -EINVAL;
+ }
+
+ err = nla_parse_nested(tb, TCA_ETF_MAX, opt, etf_policy, extack);
+ if (err < 0)
+ return err;
+
+ if (!tb[TCA_ETF_PARMS]) {
+ NL_SET_ERR_MSG(extack, "Missing mandatory ETF parameters");
+ return -EINVAL;
+ }
+
+ qopt = nla_data(tb[TCA_ETF_PARMS]);
+
+ pr_debug("delta %d clockid %d offload %s deadline %s\n",
+ qopt->delta, qopt->clockid,
+ OFFLOAD_IS_ON(qopt) ? "on" : "off",
+ DEADLINE_MODE_IS_ON(qopt) ? "on" : "off");
+
+ err = validate_input_params(qopt, extack);
+ if (err < 0)
+ return err;
+
+ q->queue = sch->dev_queue - netdev_get_tx_queue(dev, 0);
+
+ if (OFFLOAD_IS_ON(qopt)) {
+ err = etf_enable_offload(dev, q, extack);
+ if (err < 0)
+ return err;
+ }
+
+ /* Everything went OK, save the parameters used. */
+ q->delta = qopt->delta;
+ q->clockid = qopt->clockid;
+ q->offload = OFFLOAD_IS_ON(qopt);
+ q->deadline_mode = DEADLINE_MODE_IS_ON(qopt);
+
+ switch (q->clockid) {
+ case CLOCK_REALTIME:
+ q->get_time = ktime_get_real;
+ break;
+ case CLOCK_MONOTONIC:
+ q->get_time = ktime_get;
+ break;
+ case CLOCK_BOOTTIME:
+ q->get_time = ktime_get_boottime;
+ break;
+ case CLOCK_TAI:
+ q->get_time = ktime_get_clocktai;
+ break;
+ default:
+ NL_SET_ERR_MSG(extack, "Clockid is not supported");
+ return -ENOTSUPP;
+ }
+
+ qdisc_watchdog_init_clockid(&q->watchdog, sch, q->clockid);
+
+ return 0;
+}
+
+static void timesortedlist_clear(struct Qdisc *sch)
+{
+ struct etf_sched_data *q = qdisc_priv(sch);
+ struct rb_node *p = rb_first(&q->head);
+
+ while (p) {
+ struct sk_buff *skb = rb_to_skb(p);
+
+ p = rb_next(p);
+
+ rb_erase(&skb->rbnode, &q->head);
+ rtnl_kfree_skbs(skb, skb);
+ sch->q.qlen--;
+ }
+}
+
+static void etf_reset(struct Qdisc *sch)
+{
+ struct etf_sched_data *q = qdisc_priv(sch);
+
+ /* Only cancel watchdog if it's been initialized. */
+ if (q->watchdog.qdisc == sch)
+ qdisc_watchdog_cancel(&q->watchdog);
+
+ /* No matter which mode we are on, it's safe to clear both lists. */
+ timesortedlist_clear(sch);
+ __qdisc_reset_queue(&sch->q);
+
+ sch->qstats.backlog = 0;
+ sch->q.qlen = 0;
+
+ q->last = 0;
+}
+
+static void etf_destroy(struct Qdisc *sch)
+{
+ struct etf_sched_data *q = qdisc_priv(sch);
+ struct net_device *dev = qdisc_dev(sch);
+
+ /* Only cancel watchdog if it's been initialized. */
+ if (q->watchdog.qdisc == sch)
+ qdisc_watchdog_cancel(&q->watchdog);
+
+ etf_disable_offload(dev, q);
+}
+
+static int etf_dump(struct Qdisc *sch, struct sk_buff *skb)
+{
+ struct etf_sched_data *q = qdisc_priv(sch);
+ struct tc_etf_qopt opt = { };
+ struct nlattr *nest;
+
+ nest = nla_nest_start(skb, TCA_OPTIONS);
+ if (!nest)
+ goto nla_put_failure;
+
+ opt.delta = q->delta;
+ opt.clockid = q->clockid;
+ if (q->offload)
+ opt.flags |= TC_ETF_OFFLOAD_ON;
+
+ if (q->deadline_mode)
+ opt.flags |= TC_ETF_DEADLINE_MODE_ON;
+
+ if (nla_put(skb, TCA_ETF_PARMS, sizeof(opt), &opt))
+ goto nla_put_failure;
+
+ return nla_nest_end(skb, nest);
+
+nla_put_failure:
+ nla_nest_cancel(skb, nest);
+ return -1;
+}
+
+static struct Qdisc_ops etf_qdisc_ops __read_mostly = {
+ .id = "etf",
+ .priv_size = sizeof(struct etf_sched_data),
+ .enqueue = etf_enqueue_timesortedlist,
+ .dequeue = etf_dequeue_timesortedlist,
+ .peek = etf_peek_timesortedlist,
+ .init = etf_init,
+ .reset = etf_reset,
+ .destroy = etf_destroy,
+ .dump = etf_dump,
+ .owner = THIS_MODULE,
+};
+
+static int __init etf_module_init(void)
+{
+ return register_qdisc(&etf_qdisc_ops);
+}
+
+static void __exit etf_module_exit(void)
+{
+ unregister_qdisc(&etf_qdisc_ops);
+}
+module_init(etf_module_init)
+module_exit(etf_module_exit)
+MODULE_LICENSE("GPL");
if (next_time == 0 || next_time > q->root.cl_cfmin)
next_time = q->root.cl_cfmin;
}
- WARN_ON(next_time == 0);
- qdisc_watchdog_schedule(&q->watchdog, next_time);
+ if (next_time)
+ qdisc_watchdog_schedule(&q->watchdog, next_time);
}
static int
union {
struct htb_class_leaf {
- struct list_head drop_list;
int deficit[TC_HTB_MAXDEPTH];
struct Qdisc *q;
} leaf;
struct qdisc_watchdog watchdog;
s64 now; /* cached dequeue time */
- struct list_head drops[TC_HTB_NUMPRIO];/* active leaves (for drops) */
/* time of nearest event per level (row) */
s64 near_ev_cache[TC_HTB_MAXDEPTH];
if (!cl->prio_activity) {
cl->prio_activity = 1 << cl->prio;
htb_activate_prios(q, cl);
- list_add_tail(&cl->un.leaf.drop_list,
- q->drops + cl->prio);
}
}
htb_deactivate_prios(q, cl);
cl->prio_activity = 0;
- list_del_init(&cl->un.leaf.drop_list);
}
static void htb_enqueue_tail(struct sk_buff *skb, struct Qdisc *sch,
else {
if (cl->un.leaf.q)
qdisc_reset(cl->un.leaf.q);
- INIT_LIST_HEAD(&cl->un.leaf.drop_list);
}
cl->prio_activity = 0;
cl->cmode = HTB_CAN_SEND;
sch->qstats.backlog = 0;
memset(q->hlevel, 0, sizeof(q->hlevel));
memset(q->row_mask, 0, sizeof(q->row_mask));
- for (i = 0; i < TC_HTB_NUMPRIO; i++)
- INIT_LIST_HEAD(q->drops + i);
}
static const struct nla_policy htb_policy[TCA_HTB_MAX + 1] = {
struct nlattr *tb[TCA_HTB_MAX + 1];
struct tc_htb_glob *gopt;
int err;
- int i;
qdisc_watchdog_init(&q->watchdog, sch);
INIT_WORK(&q->work, htb_work_func);
err = qdisc_class_hash_init(&q->clhash);
if (err < 0)
return err;
- for (i = 0; i < TC_HTB_NUMPRIO; i++)
- INIT_LIST_HEAD(q->drops + i);
qdisc_skb_head_init(&q->direct_queue);
parent->level = 0;
memset(&parent->un.inner, 0, sizeof(parent->un.inner));
- INIT_LIST_HEAD(&parent->un.leaf.drop_list);
parent->un.leaf.q = new_q ? new_q : &noop_qdisc;
parent->tokens = parent->buffer;
parent->ctokens = parent->cbuffer;
}
cl->children = 0;
- INIT_LIST_HEAD(&cl->un.leaf.drop_list);
RB_CLEAR_NODE(&cl->pq_node);
for (prio = 0; prio < TC_HTB_NUMPRIO; prio++)
Fabio Ludovici <fabio.ludovici at yahoo.it>
*/
+struct disttable {
+ u32 size;
+ s16 table[0];
+};
+
struct netem_sched_data {
/* internal t(ime)fifo qdisc uses t_root and sch->limit */
struct rb_root t_root;
u32 rho;
} delay_cor, loss_cor, dup_cor, reorder_cor, corrupt_cor;
- struct disttable {
- u32 size;
- s16 table[0];
- } *delay_dist;
+ struct disttable *delay_dist;
enum {
CLG_RANDOM,
s32 bytes_left;
} slot;
+ struct disttable *slot_dist;
};
/* Time stamp put into socket buffer control block
u64 value, rho;
unsigned long answer;
- if (state->rho == 0) /* no correlation */
+ if (!state || state->rho == 0) /* no correlation */
return prandom_u32();
value = prandom_u32();
static void get_slot_next(struct netem_sched_data *q, u64 now)
{
- q->slot.slot_next = now + q->slot_config.min_delay +
- (prandom_u32() *
- (q->slot_config.max_delay -
- q->slot_config.min_delay) >> 32);
+ s64 next_delay;
+
+ if (!q->slot_dist)
+ next_delay = q->slot_config.min_delay +
+ (prandom_u32() *
+ (q->slot_config.max_delay -
+ q->slot_config.min_delay) >> 32);
+ else
+ next_delay = tabledist(q->slot_config.dist_delay,
+ (s32)(q->slot_config.dist_jitter),
+ NULL, q->slot_dist);
+
+ q->slot.slot_next = now + next_delay;
q->slot.packets_left = q->slot_config.max_packets;
q->slot.bytes_left = q->slot_config.max_bytes;
}
* signed 16 bit values.
*/
-static int get_dist_table(struct Qdisc *sch, const struct nlattr *attr)
+static int get_dist_table(struct Qdisc *sch, struct disttable **tbl,
+ const struct nlattr *attr)
{
- struct netem_sched_data *q = qdisc_priv(sch);
size_t n = nla_len(attr)/sizeof(__s16);
const __s16 *data = nla_data(attr);
spinlock_t *root_lock;
root_lock = qdisc_root_sleeping_lock(sch);
spin_lock_bh(root_lock);
- swap(q->delay_dist, d);
+ swap(*tbl, d);
spin_unlock_bh(root_lock);
dist_free(d);
q->slot_config.max_bytes = INT_MAX;
q->slot.packets_left = q->slot_config.max_packets;
q->slot.bytes_left = q->slot_config.max_bytes;
- if (q->slot_config.min_delay | q->slot_config.max_delay)
+ if (q->slot_config.min_delay | q->slot_config.max_delay |
+ q->slot_config.dist_jitter)
q->slot.slot_next = ktime_get_ns();
else
q->slot.slot_next = 0;
}
if (tb[TCA_NETEM_DELAY_DIST]) {
- ret = get_dist_table(sch, tb[TCA_NETEM_DELAY_DIST]);
- if (ret) {
- /* recover clg and loss_model, in case of
- * q->clg and q->loss_model were modified
- * in get_loss_clg()
- */
- q->clg = old_clg;
- q->loss_model = old_loss_model;
- return ret;
- }
+ ret = get_dist_table(sch, &q->delay_dist,
+ tb[TCA_NETEM_DELAY_DIST]);
+ if (ret)
+ goto get_table_failure;
+ }
+
+ if (tb[TCA_NETEM_SLOT_DIST]) {
+ ret = get_dist_table(sch, &q->slot_dist,
+ tb[TCA_NETEM_SLOT_DIST]);
+ if (ret)
+ goto get_table_failure;
}
sch->limit = qopt->limit;
get_slot(q, tb[TCA_NETEM_SLOT]);
return ret;
+
+get_table_failure:
+ /* recover clg and loss_model, in case of
+ * q->clg and q->loss_model were modified
+ * in get_loss_clg()
+ */
+ q->clg = old_clg;
+ q->loss_model = old_loss_model;
+ return ret;
}
static int netem_init(struct Qdisc *sch, struct nlattr *opt,
if (q->qdisc)
qdisc_destroy(q->qdisc);
dist_free(q->delay_dist);
+ dist_free(q->slot_dist);
}
static int dump_loss_model(const struct netem_sched_data *q,
if (dump_loss_model(q, skb) != 0)
goto nla_put_failure;
- if (q->slot_config.min_delay | q->slot_config.max_delay) {
+ if (q->slot_config.min_delay | q->slot_config.max_delay |
+ q->slot_config.dist_jitter) {
slot = q->slot_config;
if (slot.max_packets == INT_MAX)
slot.max_packets = 0;
/* Initialize path max retrans value. */
asoc->pathmaxrxt = sp->pathmaxrxt;
+ asoc->flowlabel = sp->flowlabel;
+ asoc->dscp = sp->dscp;
+
/* Initialize default path MTU. */
asoc->pathmtu = sp->pathmtu;
peer->sackdelay = asoc->sackdelay;
peer->sackfreq = asoc->sackfreq;
+ if (addr->sa.sa_family == AF_INET6) {
+ __be32 info = addr->v6.sin6_flowinfo;
+
+ if (info) {
+ peer->flowlabel = ntohl(info & IPV6_FLOWLABEL_MASK);
+ peer->flowlabel |= SCTP_FLOWLABEL_SET_MASK;
+ } else {
+ peer->flowlabel = asoc->flowlabel;
+ }
+ }
+ peer->dscp = asoc->dscp;
+
/* Enable/disable heartbeat, SACK delay, and path MTU discovery
* based on association setting.
*/
/* Account for a different sized first fragment */
if (msg_len >= first_len) {
msg->can_delay = 0;
- SCTP_INC_STATS(sock_net(asoc->base.sk), SCTP_MIB_FRAGUSRMSGS);
+ if (msg_len > first_len)
+ SCTP_INC_STATS(sock_net(asoc->base.sk),
+ SCTP_MIB_FRAGUSRMSGS);
} else {
/* Which may be the only one... */
first_len = msg_len;
#include <net/sctp/sm.h>
#include <net/sctp/checksum.h>
#include <net/net_namespace.h>
+#include <linux/rhashtable.h>
/* Forward declarations for internal helpers. */
static int sctp_rcv_ootb(struct sk_buff *);
struct sock *sk = skb->sk;
struct ipv6_pinfo *np = inet6_sk(sk);
struct flowi6 *fl6 = &transport->fl.u.ip6;
+ __u8 tclass = np->tclass;
int res;
pr_debug("%s: skb:%p, len:%d, src:%pI6 dst:%pI6\n", __func__, skb,
skb->len, &fl6->saddr, &fl6->daddr);
- IP6_ECN_flow_xmit(sk, fl6->flowlabel);
+ if (transport->dscp & SCTP_DSCP_SET_MASK)
+ tclass = transport->dscp & SCTP_DSCP_VAL_MASK;
+
+ if (INET_ECN_is_capable(tclass))
+ IP6_ECN_flow_xmit(sk, fl6->flowlabel);
if (!(transport->param_flags & SPP_PMTUD_ENABLE))
skb->ignore_df = 1;
rcu_read_lock();
res = ip6_xmit(sk, skb, fl6, sk->sk_mark, rcu_dereference(np->opt),
- np->tclass);
+ tclass);
rcu_read_unlock();
return res;
}
fl6->flowi6_oif = daddr->v6.sin6_scope_id;
else if (asoc)
fl6->flowi6_oif = asoc->base.sk->sk_bound_dev_if;
+ if (t->flowlabel & SCTP_FLOWLABEL_SET_MASK)
+ fl6->flowlabel = htonl(t->flowlabel & SCTP_FLOWLABEL_VAL_MASK);
+
+ if (np->sndflow && (fl6->flowlabel & IPV6_FLOWLABEL_MASK)) {
+ struct ip6_flowlabel *flowlabel;
+
+ flowlabel = fl6_sock_lookup(sk, fl6->flowlabel);
+ if (!flowlabel)
+ goto out;
+ fl6_sock_release(flowlabel);
+ }
pr_debug("%s: dst=%pI6 ", __func__, &fl6->daddr);
.socketpair = sock_no_socketpair,
.accept = inet_accept,
.getname = sctp_getname,
- .poll_mask = sctp_poll_mask,
+ .poll = sctp_poll,
.ioctl = inet6_ioctl,
.listen = sctp_inet_listen,
.shutdown = inet_shutdown,
struct dst_entry *dst = NULL;
union sctp_addr *daddr = &t->ipaddr;
union sctp_addr dst_saddr;
+ __u8 tos = inet_sk(sk)->tos;
+ if (t->dscp & SCTP_DSCP_SET_MASK)
+ tos = t->dscp & SCTP_DSCP_VAL_MASK;
memset(fl4, 0x0, sizeof(struct flowi4));
fl4->daddr = daddr->v4.sin_addr.s_addr;
fl4->fl4_dport = daddr->v4.sin_port;
fl4->flowi4_proto = IPPROTO_SCTP;
if (asoc) {
- fl4->flowi4_tos = RT_CONN_FLAGS(asoc->base.sk);
+ fl4->flowi4_tos = RT_CONN_FLAGS_TOS(asoc->base.sk, tos);
fl4->flowi4_oif = asoc->base.sk->sk_bound_dev_if;
fl4->fl4_sport = htons(asoc->base.bind_addr.port);
}
fl4->fl4_sport = laddr->a.v4.sin_port;
flowi4_update_output(fl4,
asoc->base.sk->sk_bound_dev_if,
- RT_CONN_FLAGS(asoc->base.sk),
+ RT_CONN_FLAGS_TOS(asoc->base.sk, tos),
daddr->v4.sin_addr.s_addr,
laddr->a.v4.sin_addr.s_addr);
struct sctp_transport *transport)
{
struct inet_sock *inet = inet_sk(skb->sk);
+ __u8 dscp = inet->tos;
pr_debug("%s: skb:%p, len:%d, src:%pI4, dst:%pI4\n", __func__, skb,
- skb->len, &transport->fl.u.ip4.saddr, &transport->fl.u.ip4.daddr);
+ skb->len, &transport->fl.u.ip4.saddr,
+ &transport->fl.u.ip4.daddr);
+
+ if (transport->dscp & SCTP_DSCP_SET_MASK)
+ dscp = transport->dscp & SCTP_DSCP_VAL_MASK;
inet->pmtudisc = transport->param_flags & SPP_PMTUD_ENABLE ?
IP_PMTUDISC_DO : IP_PMTUDISC_DONT;
SCTP_INC_STATS(sock_net(&inet->sk), SCTP_MIB_OUTSCTPPACKS);
- return ip_queue_xmit(&inet->sk, skb, &transport->fl);
+ return __ip_queue_xmit(&inet->sk, skb, &transport->fl, dscp);
}
static struct sctp_af sctp_af_inet;
.socketpair = sock_no_socketpair,
.accept = inet_accept,
.getname = inet_getname, /* Semantics are different. */
- .poll_mask = sctp_poll_mask,
+ .poll = sctp_poll,
.ioctl = inet_ioctl,
.listen = sctp_inet_listen,
.shutdown = inet_shutdown, /* Looks harmless. */
#include <linux/slab.h>
#include <linux/file.h>
#include <linux/compat.h>
+#include <linux/rhashtable.h>
#include <net/ip.h>
#include <net/icmp.h>
struct sctp_association *asoc;
enum sctp_scope scope;
struct cmsghdr *cmsg;
+ __be32 flowinfo = 0;
struct sctp_af *af;
int err;
if (!cmsgs->addrs_msg)
return 0;
+ if (daddr->sa.sa_family == AF_INET6)
+ flowinfo = daddr->v6.sin6_flowinfo;
+
/* sendv addr list parse */
for_each_cmsghdr(cmsg, cmsgs->addrs_msg) {
struct sctp_transport *transport;
}
dlen = sizeof(struct in6_addr);
+ daddr->v6.sin6_flowinfo = flowinfo;
daddr->v6.sin6_family = AF_INET6;
daddr->v6.sin6_port = htons(asoc->peer.port);
memcpy(&daddr->v6.sin6_addr, CMSG_DATA(cmsg), dlen);
* uint32_t spp_pathmtu;
* uint32_t spp_sackdelay;
* uint32_t spp_flags;
+ * uint32_t spp_ipv6_flowlabel;
+ * uint8_t spp_dscp;
* };
*
* spp_assoc_id - (one-to-many style socket) This is filled in the
* also that this field is mutually exclusive to
* SPP_SACKDELAY_ENABLE, setting both will have undefined
* results.
+ *
+ * SPP_IPV6_FLOWLABEL: Setting this flag enables the
+ * setting of the IPV6 flow label value. The value is
+ * contained in the spp_ipv6_flowlabel field.
+ * Upon retrieval, this flag will be set to indicate that
+ * the spp_ipv6_flowlabel field has a valid value returned.
+ * If a specific destination address is set (in the
+ * spp_address field), then the value returned is that of
+ * the address. If just an association is specified (and
+ * no address), then the association's default flow label
+ * is returned. If neither an association nor a destination
+ * is specified, then the socket's default flow label is
+ * returned. For non-IPv6 sockets, this flag will be left
+ * cleared.
+ *
+ * SPP_DSCP: Setting this flag enables the setting of the
+ * Differentiated Services Code Point (DSCP) value
+ * associated with either the association or a specific
+ * address. The value is obtained in the spp_dscp field.
+ * Upon retrieval, this flag will be set to indicate that
+ * the spp_dscp field has a valid value returned. If a
+ * specific destination address is set when called (in the
+ * spp_address field), then that specific destination
+ * address's DSCP value is returned. If just an association
+ * is specified, then the association's default DSCP is
+ * returned. If neither an association nor a destination is
+ * specified, then the socket's default DSCP is returned.
+ *
+ * spp_ipv6_flowlabel
+ * - This field is used in conjunction with the
+ * SPP_IPV6_FLOWLABEL flag and contains the IPv6 flow label.
+ * The 20 least significant bits are used for the flow
+ * label. This setting has precedence over any IPv6-layer
+ * setting.
+ *
+ * spp_dscp - This field is used in conjunction with the SPP_DSCP flag
+ * and contains the DSCP. The 6 most significant bits are
+ * used for the DSCP. This setting has precedence over any
+ * IPv4- or IPv6- layer setting.
*/
static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params,
struct sctp_transport *trans,
}
}
+ if (params->spp_flags & SPP_IPV6_FLOWLABEL) {
+ if (trans && trans->ipaddr.sa.sa_family == AF_INET6) {
+ trans->flowlabel = params->spp_ipv6_flowlabel &
+ SCTP_FLOWLABEL_VAL_MASK;
+ trans->flowlabel |= SCTP_FLOWLABEL_SET_MASK;
+ } else if (asoc) {
+ list_for_each_entry(trans,
+ &asoc->peer.transport_addr_list,
+ transports) {
+ if (trans->ipaddr.sa.sa_family != AF_INET6)
+ continue;
+ trans->flowlabel = params->spp_ipv6_flowlabel &
+ SCTP_FLOWLABEL_VAL_MASK;
+ trans->flowlabel |= SCTP_FLOWLABEL_SET_MASK;
+ }
+ asoc->flowlabel = params->spp_ipv6_flowlabel &
+ SCTP_FLOWLABEL_VAL_MASK;
+ asoc->flowlabel |= SCTP_FLOWLABEL_SET_MASK;
+ } else if (sctp_opt2sk(sp)->sk_family == AF_INET6) {
+ sp->flowlabel = params->spp_ipv6_flowlabel &
+ SCTP_FLOWLABEL_VAL_MASK;
+ sp->flowlabel |= SCTP_FLOWLABEL_SET_MASK;
+ }
+ }
+
+ if (params->spp_flags & SPP_DSCP) {
+ if (trans) {
+ trans->dscp = params->spp_dscp & SCTP_DSCP_VAL_MASK;
+ trans->dscp |= SCTP_DSCP_SET_MASK;
+ } else if (asoc) {
+ list_for_each_entry(trans,
+ &asoc->peer.transport_addr_list,
+ transports) {
+ trans->dscp = params->spp_dscp &
+ SCTP_DSCP_VAL_MASK;
+ trans->dscp |= SCTP_DSCP_SET_MASK;
+ }
+ asoc->dscp = params->spp_dscp & SCTP_DSCP_VAL_MASK;
+ asoc->dscp |= SCTP_DSCP_SET_MASK;
+ } else {
+ sp->dscp = params->spp_dscp & SCTP_DSCP_VAL_MASK;
+ sp->dscp |= SCTP_DSCP_SET_MASK;
+ }
+ }
+
return 0;
}
int error;
int hb_change, pmtud_change, sackdelay_change;
- if (optlen != sizeof(struct sctp_paddrparams))
+ if (optlen == sizeof(params)) {
+ if (copy_from_user(¶ms, optval, optlen))
+ return -EFAULT;
+ } else if (optlen == ALIGN(offsetof(struct sctp_paddrparams,
+ spp_ipv6_flowlabel), 4)) {
+ if (copy_from_user(¶ms, optval, optlen))
+ return -EFAULT;
+ if (params.spp_flags & (SPP_DSCP | SPP_IPV6_FLOWLABEL))
+ return -EINVAL;
+ } else {
return -EINVAL;
-
- if (copy_from_user(¶ms, optval, optlen))
- return -EFAULT;
+ }
/* Validate flags and value parameters. */
hb_change = params.spp_flags & SPP_HB;
return retval;
}
+static int sctp_setsockopt_reuse_port(struct sock *sk, char __user *optval,
+ unsigned int optlen)
+{
+ int val;
+
+ if (!sctp_style(sk, TCP))
+ return -EOPNOTSUPP;
+
+ if (sctp_sk(sk)->ep->base.bind_addr.port)
+ return -EFAULT;
+
+ if (optlen < sizeof(int))
+ return -EINVAL;
+
+ if (get_user(val, (int __user *)optval))
+ return -EFAULT;
+
+ sctp_sk(sk)->reuse = !!val;
+
+ return 0;
+}
+
/* API 6.2 setsockopt(), getsockopt()
*
* Applications use setsockopt() and getsockopt() to set or retrieve
retval = sctp_setsockopt_interleaving_supported(sk, optval,
optlen);
break;
+ case SCTP_REUSE_PORT:
+ retval = sctp_setsockopt_reuse_port(sk, optval, optlen);
+ break;
default:
retval = -ENOPROTOOPT;
break;
* also that this field is mutually exclusive to
* SPP_SACKDELAY_ENABLE, setting both will have undefined
* results.
+ *
+ * SPP_IPV6_FLOWLABEL: Setting this flag enables the
+ * setting of the IPV6 flow label value. The value is
+ * contained in the spp_ipv6_flowlabel field.
+ * Upon retrieval, this flag will be set to indicate that
+ * the spp_ipv6_flowlabel field has a valid value returned.
+ * If a specific destination address is set (in the
+ * spp_address field), then the value returned is that of
+ * the address. If just an association is specified (and
+ * no address), then the association's default flow label
+ * is returned. If neither an association nor a destination
+ * is specified, then the socket's default flow label is
+ * returned. For non-IPv6 sockets, this flag will be left
+ * cleared.
+ *
+ * SPP_DSCP: Setting this flag enables the setting of the
+ * Differentiated Services Code Point (DSCP) value
+ * associated with either the association or a specific
+ * address. The value is obtained in the spp_dscp field.
+ * Upon retrieval, this flag will be set to indicate that
+ * the spp_dscp field has a valid value returned. If a
+ * specific destination address is set when called (in the
+ * spp_address field), then that specific destination
+ * address's DSCP value is returned. If just an association
+ * is specified, then the association's default DSCP is
+ * returned. If neither an association nor a destination is
+ * specified, then the socket's default DSCP is returned.
+ *
+ * spp_ipv6_flowlabel
+ * - This field is used in conjunction with the
+ * SPP_IPV6_FLOWLABEL flag and contains the IPv6 flow label.
+ * The 20 least significant bits are used for the flow
+ * label. This setting has precedence over any IPv6-layer
+ * setting.
+ *
+ * spp_dscp - This field is used in conjunction with the SPP_DSCP flag
+ * and contains the DSCP. The 6 most significant bits are
+ * used for the DSCP. This setting has precedence over any
+ * IPv4- or IPv6- layer setting.
*/
static int sctp_getsockopt_peer_addr_params(struct sock *sk, int len,
char __user *optval, int __user *optlen)
struct sctp_association *asoc = NULL;
struct sctp_sock *sp = sctp_sk(sk);
- if (len < sizeof(struct sctp_paddrparams))
+ if (len >= sizeof(params))
+ len = sizeof(params);
+ else if (len >= ALIGN(offsetof(struct sctp_paddrparams,
+ spp_ipv6_flowlabel), 4))
+ len = ALIGN(offsetof(struct sctp_paddrparams,
+ spp_ipv6_flowlabel), 4);
+ else
return -EINVAL;
- len = sizeof(struct sctp_paddrparams);
+
if (copy_from_user(¶ms, optval, len))
return -EFAULT;
/*draft-11 doesn't say what to return in spp_flags*/
params.spp_flags = trans->param_flags;
+ if (trans->flowlabel & SCTP_FLOWLABEL_SET_MASK) {
+ params.spp_ipv6_flowlabel = trans->flowlabel &
+ SCTP_FLOWLABEL_VAL_MASK;
+ params.spp_flags |= SPP_IPV6_FLOWLABEL;
+ }
+ if (trans->dscp & SCTP_DSCP_SET_MASK) {
+ params.spp_dscp = trans->dscp & SCTP_DSCP_VAL_MASK;
+ params.spp_flags |= SPP_DSCP;
+ }
} else if (asoc) {
/* Fetch association values. */
params.spp_hbinterval = jiffies_to_msecs(asoc->hbinterval);
/*draft-11 doesn't say what to return in spp_flags*/
params.spp_flags = asoc->param_flags;
+ if (asoc->flowlabel & SCTP_FLOWLABEL_SET_MASK) {
+ params.spp_ipv6_flowlabel = asoc->flowlabel &
+ SCTP_FLOWLABEL_VAL_MASK;
+ params.spp_flags |= SPP_IPV6_FLOWLABEL;
+ }
+ if (asoc->dscp & SCTP_DSCP_SET_MASK) {
+ params.spp_dscp = asoc->dscp & SCTP_DSCP_VAL_MASK;
+ params.spp_flags |= SPP_DSCP;
+ }
} else {
/* Fetch socket values. */
params.spp_hbinterval = sp->hbinterval;
/*draft-11 doesn't say what to return in spp_flags*/
params.spp_flags = sp->param_flags;
+ if (sp->flowlabel & SCTP_FLOWLABEL_SET_MASK) {
+ params.spp_ipv6_flowlabel = sp->flowlabel &
+ SCTP_FLOWLABEL_VAL_MASK;
+ params.spp_flags |= SPP_IPV6_FLOWLABEL;
+ }
+ if (sp->dscp & SCTP_DSCP_SET_MASK) {
+ params.spp_dscp = sp->dscp & SCTP_DSCP_VAL_MASK;
+ params.spp_flags |= SPP_DSCP;
+ }
}
if (copy_to_user(optval, ¶ms, len))
return retval;
}
+static int sctp_getsockopt_reuse_port(struct sock *sk, int len,
+ char __user *optval,
+ int __user *optlen)
+{
+ int val;
+
+ if (len < sizeof(int))
+ return -EINVAL;
+
+ len = sizeof(int);
+ val = sctp_sk(sk)->reuse;
+ if (put_user(len, optlen))
+ return -EFAULT;
+
+ if (copy_to_user(optval, &val, len))
+ return -EFAULT;
+
+ return 0;
+}
+
static int sctp_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen)
{
retval = sctp_getsockopt_interleaving_supported(sk, len, optval,
optlen);
break;
+ case SCTP_REUSE_PORT:
+ retval = sctp_getsockopt_reuse_port(sk, len, optval, optlen);
+ break;
default:
retval = -ENOPROTOOPT;
break;
static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr)
{
+ bool reuse = (sk->sk_reuse || sctp_sk(sk)->reuse);
struct sctp_bind_hashbucket *head; /* hash list */
struct sctp_bind_bucket *pp;
unsigned short snum;
* used by other socket (pp->owner not empty); that other
* socket is going to be sk2.
*/
- int reuse = sk->sk_reuse;
struct sock *sk2;
pr_debug("%s: found a possible match\n", __func__);
- if (pp->fastreuse && sk->sk_reuse &&
- sk->sk_state != SCTP_SS_LISTENING)
+ if (pp->fastreuse && reuse && sk->sk_state != SCTP_SS_LISTENING)
goto success;
/* Run through the list of sockets bound to the port
ep2 = sctp_sk(sk2)->ep;
if (sk == sk2 ||
- (reuse && sk2->sk_reuse &&
+ (reuse && (sk2->sk_reuse || sctp_sk(sk2)->reuse) &&
sk2->sk_state != SCTP_SS_LISTENING))
continue;
* SO_REUSEADDR on this socket -sk-).
*/
if (hlist_empty(&pp->owner)) {
- if (sk->sk_reuse && sk->sk_state != SCTP_SS_LISTENING)
+ if (reuse && sk->sk_state != SCTP_SS_LISTENING)
pp->fastreuse = 1;
else
pp->fastreuse = 0;
} else if (pp->fastreuse &&
- (!sk->sk_reuse || sk->sk_state == SCTP_SS_LISTENING))
+ (!reuse || sk->sk_state == SCTP_SS_LISTENING))
pp->fastreuse = 0;
/* We are set, so fill up all the data in the hash table
err = 0;
sctp_unhash_endpoint(ep);
sk->sk_state = SCTP_SS_CLOSED;
- if (sk->sk_reuse)
+ if (sk->sk_reuse || sctp_sk(sk)->reuse)
sctp_sk(sk)->bind_hash->fastreuse = 1;
goto out;
}
* here, again, by modeling the current TCP/UDP code. We don't have
* a good way to test with it yet.
*/
-__poll_t sctp_poll_mask(struct socket *sock, __poll_t events)
+__poll_t sctp_poll(struct file *file, struct socket *sock, poll_table *wait)
{
struct sock *sk = sock->sk;
struct sctp_sock *sp = sctp_sk(sk);
__poll_t mask;
+ poll_wait(file, sk_sleep(sk), wait);
+
sock_rps_record_flow(sk);
/* A TCP-style listening socket becomes readable when the accept queue
newsk->sk_no_check_tx = sk->sk_no_check_tx;
newsk->sk_no_check_rx = sk->sk_no_check_rx;
newsk->sk_reuse = sk->sk_reuse;
+ sctp_sk(newsk)->reuse = sp->reuse;
newsk->sk_shutdown = sk->sk_shutdown;
newsk->sk_destruct = sctp_destruct_sock;
obj-$(CONFIG_SMC) += smc.o
obj-$(CONFIG_SMC_DIAG) += smc_diag.o
smc-y := af_smc.o smc_pnet.o smc_ib.o smc_clc.o smc_core.o smc_wr.o smc_llc.o
-smc-y += smc_cdc.o smc_tx.o smc_rx.o smc_close.o
+smc-y += smc_cdc.o smc_tx.o smc_rx.o smc_close.o smc_ism.o
#include <linux/workqueue.h>
#include <linux/in.h>
#include <linux/sched/signal.h>
+#include <linux/if_vlan.h>
#include <net/sock.h>
#include <net/tcp.h>
#include "smc_cdc.h"
#include "smc_core.h"
#include "smc_ib.h"
+#include "smc_ism.h"
#include "smc_pnet.h"
#include "smc_tx.h"
#include "smc_rx.h"
*/
static void smc_tcp_listen_work(struct work_struct *);
+static void smc_connect_work(struct work_struct *);
static void smc_set_keepalive(struct sock *sk, int val)
{
goto out;
smc = smc_sk(sk);
+
+ /* cleanup for a dangling non-blocking connect */
+ flush_work(&smc->connect_work);
+ kfree(smc->connect_info);
+ smc->connect_info = NULL;
+
if (sk->sk_state == SMC_LISTEN)
/* smc_close_non_accepted() is called and acquires
* sock lock for child sockets again
sk->sk_protocol = protocol;
smc = smc_sk(sk);
INIT_WORK(&smc->tcp_listen_work, smc_tcp_listen_work);
+ INIT_WORK(&smc->connect_work, smc_connect_work);
INIT_DELAYED_WORK(&smc->conn.tx_work, smc_tx_work);
INIT_LIST_HEAD(&smc->accept_q);
spin_lock_init(&smc->accept_q_lock);
return 0;
}
-static void smc_conn_save_peer_info(struct smc_sock *smc,
- struct smc_clc_msg_accept_confirm *clc)
+static void smcr_conn_save_peer_info(struct smc_sock *smc,
+ struct smc_clc_msg_accept_confirm *clc)
{
int bufsize = smc_uncompress_bufsize(clc->rmbe_size);
smc->conn.tx_off = bufsize * (smc->conn.peer_rmbe_idx - 1);
}
+static void smcd_conn_save_peer_info(struct smc_sock *smc,
+ struct smc_clc_msg_accept_confirm *clc)
+{
+ int bufsize = smc_uncompress_bufsize(clc->dmbe_size);
+
+ smc->conn.peer_rmbe_idx = clc->dmbe_idx;
+ smc->conn.peer_token = clc->token;
+ /* msg header takes up space in the buffer */
+ smc->conn.peer_rmbe_size = bufsize - sizeof(struct smcd_cdc_msg);
+ atomic_set(&smc->conn.peer_rmbe_space, smc->conn.peer_rmbe_size);
+ smc->conn.tx_off = bufsize * smc->conn.peer_rmbe_idx;
+}
+
+static void smc_conn_save_peer_info(struct smc_sock *smc,
+ struct smc_clc_msg_accept_confirm *clc)
+{
+ if (smc->conn.lgr->is_smcd)
+ smcd_conn_save_peer_info(smc, clc);
+ else
+ smcr_conn_save_peer_info(smc, clc);
+}
+
static void smc_link_save_peer_info(struct smc_link *link,
struct smc_clc_msg_accept_confirm *clc)
{
return reason_code;
}
+/* check if there is an ISM device available for this connection. */
+/* called for connect and listen */
+static int smc_check_ism(struct smc_sock *smc, struct smcd_dev **ismdev)
+{
+ /* Find ISM device with same PNETID as connecting interface */
+ smc_pnet_find_ism_resource(smc->clcsock->sk, ismdev);
+ if (!(*ismdev))
+ return SMC_CLC_DECL_CNFERR; /* configuration error */
+ return 0;
+}
+
+/* Check for VLAN ID and register it on ISM device just for CLC handshake */
+static int smc_connect_ism_vlan_setup(struct smc_sock *smc,
+ struct smcd_dev *ismdev,
+ unsigned short vlan_id)
+{
+ if (vlan_id && smc_ism_get_vlan(ismdev, vlan_id))
+ return SMC_CLC_DECL_CNFERR;
+ return 0;
+}
+
+/* cleanup temporary VLAN ID registration used for CLC handshake. If ISM is
+ * used, the VLAN ID will be registered again during the connection setup.
+ */
+static int smc_connect_ism_vlan_cleanup(struct smc_sock *smc, bool is_smcd,
+ struct smcd_dev *ismdev,
+ unsigned short vlan_id)
+{
+ if (!is_smcd)
+ return 0;
+ if (vlan_id && smc_ism_put_vlan(ismdev, vlan_id))
+ return SMC_CLC_DECL_CNFERR;
+ return 0;
+}
+
/* CLC handshake during connect */
-static int smc_connect_clc(struct smc_sock *smc,
+static int smc_connect_clc(struct smc_sock *smc, int smc_type,
struct smc_clc_msg_accept_confirm *aclc,
- struct smc_ib_device *ibdev, u8 ibport)
+ struct smc_ib_device *ibdev, u8 ibport,
+ struct smcd_dev *ismdev)
{
int rc = 0;
/* do inband token exchange */
- rc = smc_clc_send_proposal(smc, ibdev, ibport);
+ rc = smc_clc_send_proposal(smc, smc_type, ibdev, ibport, ismdev);
if (rc)
return rc;
/* receive SMC Accept CLC message */
int reason_code = 0;
mutex_lock(&smc_create_lgr_pending);
- local_contact = smc_conn_create(smc, ibdev, ibport, &aclc->lcl,
- aclc->hdr.flag);
+ local_contact = smc_conn_create(smc, false, aclc->hdr.flag, ibdev,
+ ibport, &aclc->lcl, NULL, 0);
if (local_contact < 0) {
if (local_contact == -ENOMEM)
reason_code = SMC_CLC_DECL_MEM;/* insufficient memory*/
smc_conn_save_peer_info(smc, aclc);
/* create send buffer and rmb */
- if (smc_buf_create(smc))
+ if (smc_buf_create(smc, false))
return smc_connect_abort(smc, SMC_CLC_DECL_MEM, local_contact);
if (local_contact == SMC_FIRST_CONTACT)
return 0;
}
+/* setup for ISM connection of client */
+static int smc_connect_ism(struct smc_sock *smc,
+ struct smc_clc_msg_accept_confirm *aclc,
+ struct smcd_dev *ismdev)
+{
+ int local_contact = SMC_FIRST_CONTACT;
+ int rc = 0;
+
+ mutex_lock(&smc_create_lgr_pending);
+ local_contact = smc_conn_create(smc, true, aclc->hdr.flag, NULL, 0,
+ NULL, ismdev, aclc->gid);
+ if (local_contact < 0)
+ return smc_connect_abort(smc, SMC_CLC_DECL_MEM, 0);
+
+ /* Create send and receive buffers */
+ if (smc_buf_create(smc, true))
+ return smc_connect_abort(smc, SMC_CLC_DECL_MEM, local_contact);
+
+ smc_conn_save_peer_info(smc, aclc);
+ smc_close_init(smc);
+ smc_rx_init(smc);
+ smc_tx_init(smc);
+
+ rc = smc_clc_send_confirm(smc);
+ if (rc)
+ return smc_connect_abort(smc, rc, local_contact);
+ mutex_unlock(&smc_create_lgr_pending);
+
+ smc_copy_sock_settings_to_clc(smc);
+ if (smc->sk.sk_state == SMC_INIT)
+ smc->sk.sk_state = SMC_ACTIVE;
+
+ return 0;
+}
+
/* perform steps before actually connecting */
static int __smc_connect(struct smc_sock *smc)
{
+ bool ism_supported = false, rdma_supported = false;
struct smc_clc_msg_accept_confirm aclc;
struct smc_ib_device *ibdev;
+ struct smcd_dev *ismdev;
+ unsigned short vlan;
+ int smc_type;
int rc = 0;
u8 ibport;
if (using_ipsec(smc))
return smc_connect_decline_fallback(smc, SMC_CLC_DECL_IPSEC);
- /* check if a RDMA device is available; if not, fall back */
- if (smc_check_rdma(smc, &ibdev, &ibport))
+ /* check for VLAN ID */
+ if (smc_vlan_by_tcpsk(smc->clcsock, &vlan))
+ return smc_connect_decline_fallback(smc, SMC_CLC_DECL_CNFERR);
+
+ /* check if there is an ism device available */
+ if (!smc_check_ism(smc, &ismdev) &&
+ !smc_connect_ism_vlan_setup(smc, ismdev, vlan)) {
+ /* ISM is supported for this connection */
+ ism_supported = true;
+ smc_type = SMC_TYPE_D;
+ }
+
+ /* check if there is a rdma device available */
+ if (!smc_check_rdma(smc, &ibdev, &ibport)) {
+ /* RDMA is supported for this connection */
+ rdma_supported = true;
+ if (ism_supported)
+ smc_type = SMC_TYPE_B; /* both */
+ else
+ smc_type = SMC_TYPE_R; /* only RDMA */
+ }
+
+ /* if neither ISM nor RDMA are supported, fallback */
+ if (!rdma_supported && !ism_supported)
return smc_connect_decline_fallback(smc, SMC_CLC_DECL_CNFERR);
/* perform CLC handshake */
- rc = smc_connect_clc(smc, &aclc, ibdev, ibport);
- if (rc)
+ rc = smc_connect_clc(smc, smc_type, &aclc, ibdev, ibport, ismdev);
+ if (rc) {
+ smc_connect_ism_vlan_cleanup(smc, ism_supported, ismdev, vlan);
return smc_connect_decline_fallback(smc, rc);
+ }
- /* connect using rdma */
- rc = smc_connect_rdma(smc, &aclc, ibdev, ibport);
- if (rc)
+ /* depending on previous steps, connect using rdma or ism */
+ if (rdma_supported && aclc.hdr.path == SMC_TYPE_R)
+ rc = smc_connect_rdma(smc, &aclc, ibdev, ibport);
+ else if (ism_supported && aclc.hdr.path == SMC_TYPE_D)
+ rc = smc_connect_ism(smc, &aclc, ismdev);
+ else
+ rc = SMC_CLC_DECL_CNFERR;
+ if (rc) {
+ smc_connect_ism_vlan_cleanup(smc, ism_supported, ismdev, vlan);
return smc_connect_decline_fallback(smc, rc);
+ }
+ smc_connect_ism_vlan_cleanup(smc, ism_supported, ismdev, vlan);
return 0;
}
+static void smc_connect_work(struct work_struct *work)
+{
+ struct smc_sock *smc = container_of(work, struct smc_sock,
+ connect_work);
+ int rc;
+
+ lock_sock(&smc->sk);
+ rc = kernel_connect(smc->clcsock, &smc->connect_info->addr,
+ smc->connect_info->alen, smc->connect_info->flags);
+ if (smc->clcsock->sk->sk_err) {
+ smc->sk.sk_err = smc->clcsock->sk->sk_err;
+ goto out;
+ }
+ if (rc < 0) {
+ smc->sk.sk_err = -rc;
+ goto out;
+ }
+
+ rc = __smc_connect(smc);
+ if (rc < 0)
+ smc->sk.sk_err = -rc;
+
+out:
+ smc->sk.sk_state_change(&smc->sk);
+ kfree(smc->connect_info);
+ smc->connect_info = NULL;
+ release_sock(&smc->sk);
+}
+
static int smc_connect(struct socket *sock, struct sockaddr *addr,
int alen, int flags)
{
smc_copy_sock_settings_to_clc(smc);
tcp_sk(smc->clcsock->sk)->syn_smc = 1;
- rc = kernel_connect(smc->clcsock, addr, alen, flags);
- if (rc)
- goto out;
+ if (flags & O_NONBLOCK) {
+ if (smc->connect_info) {
+ rc = -EALREADY;
+ goto out;
+ }
+ smc->connect_info = kzalloc(alen + 2 * sizeof(int), GFP_KERNEL);
+ if (!smc->connect_info) {
+ rc = -ENOMEM;
+ goto out;
+ }
+ smc->connect_info->alen = alen;
+ smc->connect_info->flags = flags ^ O_NONBLOCK;
+ memcpy(&smc->connect_info->addr, addr, alen);
+ schedule_work(&smc->connect_work);
+ rc = -EINPROGRESS;
+ } else {
+ rc = kernel_connect(smc->clcsock, addr, alen, flags);
+ if (rc)
+ goto out;
- rc = __smc_connect(smc);
- if (rc < 0)
- goto out;
- else
- rc = 0; /* success cases including fallback */
+ rc = __smc_connect(smc);
+ if (rc < 0)
+ goto out;
+ else
+ rc = 0; /* success cases including fallback */
+ }
out:
release_sock(sk);
int *local_contact)
{
/* allocate connection / link group */
- *local_contact = smc_conn_create(new_smc, ibdev, ibport, &pclc->lcl, 0);
+ *local_contact = smc_conn_create(new_smc, false, 0, ibdev, ibport,
+ &pclc->lcl, NULL, 0);
if (*local_contact < 0) {
if (*local_contact == -ENOMEM)
return SMC_CLC_DECL_MEM;/* insufficient memory*/
}
/* create send buffer and rmb */
- if (smc_buf_create(new_smc))
+ if (smc_buf_create(new_smc, false))
+ return SMC_CLC_DECL_MEM;
+
+ return 0;
+}
+
+/* listen worker: initialize connection and buffers for SMC-D */
+static int smc_listen_ism_init(struct smc_sock *new_smc,
+ struct smc_clc_msg_proposal *pclc,
+ struct smcd_dev *ismdev,
+ int *local_contact)
+{
+ struct smc_clc_msg_smcd *pclc_smcd;
+
+ pclc_smcd = smc_get_clc_msg_smcd(pclc);
+ *local_contact = smc_conn_create(new_smc, true, 0, NULL, 0, NULL,
+ ismdev, pclc_smcd->gid);
+ if (*local_contact < 0) {
+ if (*local_contact == -ENOMEM)
+ return SMC_CLC_DECL_MEM;/* insufficient memory*/
+ return SMC_CLC_DECL_INTERR; /* other error */
+ }
+
+ /* Check if peer can be reached via ISM device */
+ if (smc_ism_cantalk(new_smc->conn.lgr->peer_gid,
+ new_smc->conn.lgr->vlan_id,
+ new_smc->conn.lgr->smcd)) {
+ if (*local_contact == SMC_FIRST_CONTACT)
+ smc_lgr_forget(new_smc->conn.lgr);
+ smc_conn_free(&new_smc->conn);
+ return SMC_CLC_DECL_CNFERR;
+ }
+
+ /* Create send and receive buffers */
+ if (smc_buf_create(new_smc, true)) {
+ if (*local_contact == SMC_FIRST_CONTACT)
+ smc_lgr_forget(new_smc->conn.lgr);
+ smc_conn_free(&new_smc->conn);
return SMC_CLC_DECL_MEM;
+ }
return 0;
}
struct smc_clc_msg_accept_confirm cclc;
struct smc_clc_msg_proposal *pclc;
struct smc_ib_device *ibdev;
+ bool ism_supported = false;
+ struct smcd_dev *ismdev;
u8 buf[SMC_CLC_MAX_LEN];
int local_contact = 0;
int reason_code = 0;
smc_rx_init(new_smc);
smc_tx_init(new_smc);
+ /* check if ISM is available */
+ if ((pclc->hdr.path == SMC_TYPE_D || pclc->hdr.path == SMC_TYPE_B) &&
+ !smc_check_ism(new_smc, &ismdev) &&
+ !smc_listen_ism_init(new_smc, pclc, ismdev, &local_contact)) {
+ ism_supported = true;
+ }
+
/* check if RDMA is available */
- if (smc_check_rdma(new_smc, &ibdev, &ibport) ||
- smc_listen_rdma_check(new_smc, pclc) ||
- smc_listen_rdma_init(new_smc, pclc, ibdev, ibport,
- &local_contact) ||
- smc_listen_rdma_reg(new_smc, local_contact)) {
+ if (!ism_supported &&
+ ((pclc->hdr.path != SMC_TYPE_R && pclc->hdr.path != SMC_TYPE_B) ||
+ smc_check_rdma(new_smc, &ibdev, &ibport) ||
+ smc_listen_rdma_check(new_smc, pclc) ||
+ smc_listen_rdma_init(new_smc, pclc, ibdev, ibport,
+ &local_contact) ||
+ smc_listen_rdma_reg(new_smc, local_contact))) {
/* SMC not supported, decline */
mutex_unlock(&smc_create_lgr_pending);
smc_listen_decline(new_smc, SMC_CLC_DECL_CNFERR, local_contact);
}
/* finish worker */
- smc_listen_rdma_finish(new_smc, &cclc, local_contact);
+ if (!ism_supported)
+ smc_listen_rdma_finish(new_smc, &cclc, local_contact);
smc_conn_save_peer_info(new_smc, &cclc);
mutex_unlock(&smc_create_lgr_pending);
smc_listen_out_connected(new_smc);
return mask;
}
-static __poll_t smc_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t smc_poll(struct file *file, struct socket *sock,
+ poll_table *wait)
{
struct sock *sk = sock->sk;
__poll_t mask = 0;
struct smc_sock *smc;
- int rc;
if (!sk)
return EPOLLNVAL;
smc = smc_sk(sock->sk);
- sock_hold(sk);
- lock_sock(sk);
if ((sk->sk_state == SMC_INIT) || smc->use_fallback) {
/* delegate to CLC child sock */
- release_sock(sk);
- mask = smc->clcsock->ops->poll_mask(smc->clcsock, events);
- lock_sock(sk);
+ mask = smc->clcsock->ops->poll(file, smc->clcsock, wait);
sk->sk_err = smc->clcsock->sk->sk_err;
- if (sk->sk_err) {
+ if (sk->sk_err)
mask |= EPOLLERR;
- } else {
- /* if non-blocking connect finished ... */
- if (sk->sk_state == SMC_INIT &&
- mask & EPOLLOUT &&
- smc->clcsock->sk->sk_state != TCP_CLOSE) {
- rc = __smc_connect(smc);
- if (rc < 0)
- mask |= EPOLLERR;
- /* success cases including fallback */
- mask |= EPOLLOUT | EPOLLWRNORM;
- }
- }
} else {
if (sk->sk_err)
mask |= EPOLLERR;
mask |= EPOLLPRI;
}
- release_sock(sk);
- sock_put(sk);
return mask;
}
.socketpair = sock_no_socketpair,
.accept = smc_accept,
.getname = smc_getname,
- .poll_mask = smc_poll_mask,
+ .poll = smc_poll,
.ioctl = smc_ioctl,
.listen = smc_listen,
.shutdown = smc_shutdown,
#define SMCPROTO_SMC 0 /* SMC protocol, IPv4 */
#define SMCPROTO_SMC6 1 /* SMC protocol, IPv6 */
-#define SMC_MAX_PORTS 2 /* Max # of ports */
-
extern struct proto smc_proto;
extern struct proto smc_proto6;
spinlock_t acurs_lock; /* protect cursors */
#endif
struct work_struct close_work; /* peer sent some closing */
+ struct tasklet_struct rx_tsklet; /* Receiver tasklet for SMC-D */
+ u8 rx_off; /* receive offset:
+ * 0 for SMC-R, 32 for SMC-D
+ */
+ u64 peer_token; /* SMC-D token of peer */
+};
+
+struct smc_connect_info {
+ int flags;
+ int alen;
+ struct sockaddr addr;
};
struct smc_sock { /* smc sock container */
struct socket *clcsock; /* internal tcp socket */
struct smc_connection conn; /* smc connection */
struct smc_sock *listen_smc; /* listen parent */
+ struct smc_connect_info *connect_info; /* connect address & flags */
+ struct work_struct connect_work; /* handle non-blocking connect*/
struct work_struct tcp_listen_work;/* handle tcp socket accepts */
struct work_struct smc_listen_work;/* prepare new accept socket */
struct list_head accept_q; /* sockets to be accepted */
return rc;
}
-int smc_cdc_get_slot_and_msg_send(struct smc_connection *conn)
+static int smcr_cdc_get_slot_and_msg_send(struct smc_connection *conn)
{
struct smc_cdc_tx_pend *pend;
struct smc_wr_buf *wr_buf;
return smc_cdc_msg_send(conn, wr_buf, pend);
}
+int smc_cdc_get_slot_and_msg_send(struct smc_connection *conn)
+{
+ int rc;
+
+ if (conn->lgr->is_smcd) {
+ spin_lock_bh(&conn->send_lock);
+ rc = smcd_cdc_msg_send(conn);
+ spin_unlock_bh(&conn->send_lock);
+ } else {
+ rc = smcr_cdc_get_slot_and_msg_send(conn);
+ }
+
+ return rc;
+}
+
static bool smc_cdc_tx_filter(struct smc_wr_tx_pend_priv *tx_pend,
unsigned long data)
{
(unsigned long)conn);
}
+/* Send a SMC-D CDC header.
+ * This increments the free space available in our send buffer.
+ * Also update the confirmed receive buffer with what was sent to the peer.
+ */
+int smcd_cdc_msg_send(struct smc_connection *conn)
+{
+ struct smc_sock *smc = container_of(conn, struct smc_sock, conn);
+ struct smcd_cdc_msg cdc;
+ int rc, diff;
+
+ memset(&cdc, 0, sizeof(cdc));
+ cdc.common.type = SMC_CDC_MSG_TYPE;
+ cdc.prod_wrap = conn->local_tx_ctrl.prod.wrap;
+ cdc.prod_count = conn->local_tx_ctrl.prod.count;
+
+ cdc.cons_wrap = conn->local_tx_ctrl.cons.wrap;
+ cdc.cons_count = conn->local_tx_ctrl.cons.count;
+ cdc.prod_flags = conn->local_tx_ctrl.prod_flags;
+ cdc.conn_state_flags = conn->local_tx_ctrl.conn_state_flags;
+ rc = smcd_tx_ism_write(conn, &cdc, sizeof(cdc), 0, 1);
+ if (rc)
+ return rc;
+ smc_curs_write(&conn->rx_curs_confirmed,
+ smc_curs_read(&conn->local_tx_ctrl.cons, conn), conn);
+ /* Calculate transmitted data and increment free send buffer space */
+ diff = smc_curs_diff(conn->sndbuf_desc->len, &conn->tx_curs_fin,
+ &conn->tx_curs_sent);
+ /* increased by confirmed number of bytes */
+ smp_mb__before_atomic();
+ atomic_add(diff, &conn->sndbuf_space);
+ /* guarantee 0 <= sndbuf_space <= sndbuf_desc->len */
+ smp_mb__after_atomic();
+ smc_curs_write(&conn->tx_curs_fin,
+ smc_curs_read(&conn->tx_curs_sent, conn), conn);
+
+ smc_tx_sndbuf_nonfull(smc);
+ return rc;
+}
+
/********************************* receive ***********************************/
static inline bool smc_cdc_before(u16 seq1, u16 seq2)
if (!sock_flag(&smc->sk, SOCK_URGINLINE))
/* we'll skip the urgent byte, so don't account for it */
(*diff_prod)--;
- base = (char *)conn->rmb_desc->cpu_addr;
+ base = (char *)conn->rmb_desc->cpu_addr + conn->rx_off;
if (conn->urg_curs.count)
conn->urg_rx_byte = *(base + conn->urg_curs.count - 1);
else
sock_put(&smc->sk); /* no free sk in softirq-context */
}
+/* Schedule a tasklet for this connection. Triggered from the ISM device IRQ
+ * handler to indicate update in the DMBE.
+ *
+ * Context:
+ * - tasklet context
+ */
+static void smcd_cdc_rx_tsklet(unsigned long data)
+{
+ struct smc_connection *conn = (struct smc_connection *)data;
+ struct smcd_cdc_msg cdc;
+ struct smc_sock *smc;
+
+ if (!conn)
+ return;
+
+ memcpy(&cdc, conn->rmb_desc->cpu_addr, sizeof(cdc));
+ smc = container_of(conn, struct smc_sock, conn);
+ smc_cdc_msg_recv(smc, (struct smc_cdc_msg *)&cdc);
+}
+
+/* Initialize receive tasklet. Called from ISM device IRQ handler to start
+ * receiver side.
+ */
+void smcd_cdc_rx_init(struct smc_connection *conn)
+{
+ tasklet_init(&conn->rx_tsklet, smcd_cdc_rx_tsklet, (unsigned long)conn);
+}
+
/***************************** init, exit, misc ******************************/
static void smc_cdc_rx_handler(struct ib_wc *wc, void *buf)
u8 reserved[18];
} __packed; /* format defined in RFC7609 */
+/* CDC message for SMC-D */
+struct smcd_cdc_msg {
+ struct smc_wr_rx_hdr common; /* Type = 0xFE */
+ u8 res1[7];
+ u16 prod_wrap;
+ u32 prod_count;
+ u8 res2[2];
+ u16 cons_wrap;
+ u32 cons_count;
+ struct smc_cdc_producer_flags prod_flags;
+ struct smc_cdc_conn_state_flags conn_state_flags;
+ u8 res3[8];
+} __packed;
+
static inline bool smc_cdc_rxed_any_close(struct smc_connection *conn)
{
return conn->local_rx_ctrl.conn_state_flags.peer_conn_abort ||
smc_curs_write(local, smc_curs_read(&temp, conn), conn);
}
-static inline void smc_cdc_msg_to_host(struct smc_host_cdc_msg *local,
- struct smc_cdc_msg *peer,
- struct smc_connection *conn)
+static inline void smcr_cdc_msg_to_host(struct smc_host_cdc_msg *local,
+ struct smc_cdc_msg *peer,
+ struct smc_connection *conn)
{
local->common.type = peer->common.type;
local->len = peer->len;
local->conn_state_flags = peer->conn_state_flags;
}
+static inline void smcd_cdc_msg_to_host(struct smc_host_cdc_msg *local,
+ struct smcd_cdc_msg *peer)
+{
+ local->prod.wrap = peer->prod_wrap;
+ local->prod.count = peer->prod_count;
+ local->cons.wrap = peer->cons_wrap;
+ local->cons.count = peer->cons_count;
+ local->prod_flags = peer->prod_flags;
+ local->conn_state_flags = peer->conn_state_flags;
+}
+
+static inline void smc_cdc_msg_to_host(struct smc_host_cdc_msg *local,
+ struct smc_cdc_msg *peer,
+ struct smc_connection *conn)
+{
+ if (conn->lgr->is_smcd)
+ smcd_cdc_msg_to_host(local, (struct smcd_cdc_msg *)peer);
+ else
+ smcr_cdc_msg_to_host(local, peer, conn);
+}
+
struct smc_cdc_tx_pend;
int smc_cdc_get_free_slot(struct smc_connection *conn,
int smc_cdc_msg_send(struct smc_connection *conn, struct smc_wr_buf *wr_buf,
struct smc_cdc_tx_pend *pend);
int smc_cdc_get_slot_and_msg_send(struct smc_connection *conn);
+int smcd_cdc_msg_send(struct smc_connection *conn);
int smc_cdc_init(void) __init;
+void smcd_cdc_rx_init(struct smc_connection *conn);
#endif /* SMC_CDC_H */
#include "smc_core.h"
#include "smc_clc.h"
#include "smc_ib.h"
+#include "smc_ism.h"
+
+#define SMCR_CLC_ACCEPT_CONFIRM_LEN 68
+#define SMCD_CLC_ACCEPT_CONFIRM_LEN 48
/* eye catcher "SMCR" EBCDIC for CLC messages */
static const char SMC_EYECATCHER[4] = {'\xe2', '\xd4', '\xc3', '\xd9'};
+/* eye catcher "SMCD" EBCDIC for CLC messages */
+static const char SMCD_EYECATCHER[4] = {'\xe2', '\xd4', '\xc3', '\xc4'};
/* check if received message has a correct header length and contains valid
* heading and trailing eyecatchers
struct smc_clc_msg_decline *dclc;
struct smc_clc_msg_trail *trl;
- if (memcmp(clcm->eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)))
+ if (memcmp(clcm->eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)) &&
+ memcmp(clcm->eyecatcher, SMCD_EYECATCHER, sizeof(SMCD_EYECATCHER)))
return false;
switch (clcm->type) {
case SMC_CLC_PROPOSAL:
+ if (clcm->path != SMC_TYPE_R && clcm->path != SMC_TYPE_D &&
+ clcm->path != SMC_TYPE_B)
+ return false;
pclc = (struct smc_clc_msg_proposal *)clcm;
pclc_prfx = smc_clc_proposal_get_prefix(pclc);
if (ntohs(pclc->hdr.length) !=
break;
case SMC_CLC_ACCEPT:
case SMC_CLC_CONFIRM:
+ if (clcm->path != SMC_TYPE_R && clcm->path != SMC_TYPE_D)
+ return false;
clc = (struct smc_clc_msg_accept_confirm *)clcm;
- if (ntohs(clc->hdr.length) != sizeof(*clc))
+ if ((clcm->path == SMC_TYPE_R &&
+ ntohs(clc->hdr.length) != SMCR_CLC_ACCEPT_CONFIRM_LEN) ||
+ (clcm->path == SMC_TYPE_D &&
+ ntohs(clc->hdr.length) != SMCD_CLC_ACCEPT_CONFIRM_LEN))
return false;
- trl = &clc->trl;
+ trl = (struct smc_clc_msg_trail *)
+ ((u8 *)clc + ntohs(clc->hdr.length) - sizeof(*trl));
break;
case SMC_CLC_DECLINE:
dclc = (struct smc_clc_msg_decline *)clcm;
default:
return false;
}
- if (memcmp(trl->eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)))
+ if (memcmp(trl->eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)) &&
+ memcmp(trl->eyecatcher, SMCD_EYECATCHER, sizeof(SMCD_EYECATCHER)))
return false;
return true;
}
datlen = ntohs(clcm->length);
if ((len < sizeof(struct smc_clc_msg_hdr)) ||
(datlen > buflen) ||
+ (clcm->version != SMC_CLC_V1) ||
+ (clcm->path != SMC_TYPE_R && clcm->path != SMC_TYPE_D &&
+ clcm->path != SMC_TYPE_B) ||
((clcm->type != SMC_CLC_DECLINE) &&
(clcm->type != expected_type))) {
smc->sk.sk_err = EPROTO;
}
/* send CLC PROPOSAL message across internal TCP socket */
-int smc_clc_send_proposal(struct smc_sock *smc,
- struct smc_ib_device *smcibdev,
- u8 ibport)
+int smc_clc_send_proposal(struct smc_sock *smc, int smc_type,
+ struct smc_ib_device *ibdev, u8 ibport,
+ struct smcd_dev *ismdev)
{
struct smc_clc_ipv6_prefix ipv6_prfx[SMC_CLC_MAX_V6_PREFIX];
struct smc_clc_msg_proposal_prefix pclc_prfx;
+ struct smc_clc_msg_smcd pclc_smcd;
struct smc_clc_msg_proposal pclc;
struct smc_clc_msg_trail trl;
int len, i, plen, rc;
int reason_code = 0;
- struct kvec vec[4];
+ struct kvec vec[5];
struct msghdr msg;
/* retrieve ip prefixes for CLC proposal msg */
memset(&pclc, 0, sizeof(pclc));
memcpy(pclc.hdr.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
pclc.hdr.type = SMC_CLC_PROPOSAL;
- pclc.hdr.length = htons(plen);
pclc.hdr.version = SMC_CLC_V1; /* SMC version */
- memcpy(pclc.lcl.id_for_peer, local_systemid, sizeof(local_systemid));
- memcpy(&pclc.lcl.gid, &smcibdev->gid[ibport - 1], SMC_GID_SIZE);
- memcpy(&pclc.lcl.mac, &smcibdev->mac[ibport - 1], ETH_ALEN);
- pclc.iparea_offset = htons(0);
+ pclc.hdr.path = smc_type;
+ if (smc_type == SMC_TYPE_R || smc_type == SMC_TYPE_B) {
+ /* add SMC-R specifics */
+ memcpy(pclc.lcl.id_for_peer, local_systemid,
+ sizeof(local_systemid));
+ memcpy(&pclc.lcl.gid, &ibdev->gid[ibport - 1], SMC_GID_SIZE);
+ memcpy(&pclc.lcl.mac, &ibdev->mac[ibport - 1], ETH_ALEN);
+ pclc.iparea_offset = htons(0);
+ }
+ if (smc_type == SMC_TYPE_D || smc_type == SMC_TYPE_B) {
+ /* add SMC-D specifics */
+ memset(&pclc_smcd, 0, sizeof(pclc_smcd));
+ plen += sizeof(pclc_smcd);
+ pclc.iparea_offset = htons(SMC_CLC_PROPOSAL_MAX_OFFSET);
+ pclc_smcd.gid = ismdev->local_gid;
+ }
+ pclc.hdr.length = htons(plen);
memcpy(trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
memset(&msg, 0, sizeof(msg));
i = 0;
vec[i].iov_base = &pclc;
vec[i++].iov_len = sizeof(pclc);
+ if (smc_type == SMC_TYPE_D || smc_type == SMC_TYPE_B) {
+ vec[i].iov_base = &pclc_smcd;
+ vec[i++].iov_len = sizeof(pclc_smcd);
+ }
vec[i].iov_base = &pclc_prfx;
vec[i++].iov_len = sizeof(pclc_prfx);
if (pclc_prfx.ipv6_prefixes_cnt > 0) {
struct kvec vec;
int len;
- link = &conn->lgr->lnk[SMC_SINGLE_LINK];
/* send SMC Confirm CLC msg */
memset(&cclc, 0, sizeof(cclc));
- memcpy(cclc.hdr.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
cclc.hdr.type = SMC_CLC_CONFIRM;
- cclc.hdr.length = htons(sizeof(cclc));
cclc.hdr.version = SMC_CLC_V1; /* SMC version */
- memcpy(cclc.lcl.id_for_peer, local_systemid, sizeof(local_systemid));
- memcpy(&cclc.lcl.gid, &link->smcibdev->gid[link->ibport - 1],
- SMC_GID_SIZE);
- memcpy(&cclc.lcl.mac, &link->smcibdev->mac[link->ibport - 1], ETH_ALEN);
- hton24(cclc.qpn, link->roce_qp->qp_num);
- cclc.rmb_rkey =
- htonl(conn->rmb_desc->mr_rx[SMC_SINGLE_LINK]->rkey);
- cclc.rmbe_idx = 1; /* for now: 1 RMB = 1 RMBE */
- cclc.rmbe_alert_token = htonl(conn->alert_token_local);
- cclc.qp_mtu = min(link->path_mtu, link->peer_mtu);
- cclc.rmbe_size = conn->rmbe_size_short;
- cclc.rmb_dma_addr = cpu_to_be64(
- (u64)sg_dma_address(conn->rmb_desc->sgt[SMC_SINGLE_LINK].sgl));
- hton24(cclc.psn, link->psn_initial);
-
- memcpy(cclc.trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
+ if (smc->conn.lgr->is_smcd) {
+ /* SMC-D specific settings */
+ memcpy(cclc.hdr.eyecatcher, SMCD_EYECATCHER,
+ sizeof(SMCD_EYECATCHER));
+ cclc.hdr.path = SMC_TYPE_D;
+ cclc.hdr.length = htons(SMCD_CLC_ACCEPT_CONFIRM_LEN);
+ cclc.gid = conn->lgr->smcd->local_gid;
+ cclc.token = conn->rmb_desc->token;
+ cclc.dmbe_size = conn->rmbe_size_short;
+ cclc.dmbe_idx = 0;
+ memcpy(&cclc.linkid, conn->lgr->id, SMC_LGR_ID_SIZE);
+ memcpy(cclc.smcd_trl.eyecatcher, SMCD_EYECATCHER,
+ sizeof(SMCD_EYECATCHER));
+ } else {
+ /* SMC-R specific settings */
+ link = &conn->lgr->lnk[SMC_SINGLE_LINK];
+ memcpy(cclc.hdr.eyecatcher, SMC_EYECATCHER,
+ sizeof(SMC_EYECATCHER));
+ cclc.hdr.path = SMC_TYPE_R;
+ cclc.hdr.length = htons(SMCR_CLC_ACCEPT_CONFIRM_LEN);
+ memcpy(cclc.lcl.id_for_peer, local_systemid,
+ sizeof(local_systemid));
+ memcpy(&cclc.lcl.gid, &link->smcibdev->gid[link->ibport - 1],
+ SMC_GID_SIZE);
+ memcpy(&cclc.lcl.mac, &link->smcibdev->mac[link->ibport - 1],
+ ETH_ALEN);
+ hton24(cclc.qpn, link->roce_qp->qp_num);
+ cclc.rmb_rkey =
+ htonl(conn->rmb_desc->mr_rx[SMC_SINGLE_LINK]->rkey);
+ cclc.rmbe_idx = 1; /* for now: 1 RMB = 1 RMBE */
+ cclc.rmbe_alert_token = htonl(conn->alert_token_local);
+ cclc.qp_mtu = min(link->path_mtu, link->peer_mtu);
+ cclc.rmbe_size = conn->rmbe_size_short;
+ cclc.rmb_dma_addr = cpu_to_be64((u64)sg_dma_address
+ (conn->rmb_desc->sgt[SMC_SINGLE_LINK].sgl));
+ hton24(cclc.psn, link->psn_initial);
+ memcpy(cclc.smcr_trl.eyecatcher, SMC_EYECATCHER,
+ sizeof(SMC_EYECATCHER));
+ }
memset(&msg, 0, sizeof(msg));
vec.iov_base = &cclc;
- vec.iov_len = sizeof(cclc);
- len = kernel_sendmsg(smc->clcsock, &msg, &vec, 1, sizeof(cclc));
- if (len < sizeof(cclc)) {
+ vec.iov_len = ntohs(cclc.hdr.length);
+ len = kernel_sendmsg(smc->clcsock, &msg, &vec, 1,
+ ntohs(cclc.hdr.length));
+ if (len < ntohs(cclc.hdr.length)) {
if (len >= 0) {
reason_code = -ENETUNREACH;
smc->sk.sk_err = -reason_code;
int rc = 0;
int len;
- link = &conn->lgr->lnk[SMC_SINGLE_LINK];
memset(&aclc, 0, sizeof(aclc));
- memcpy(aclc.hdr.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
aclc.hdr.type = SMC_CLC_ACCEPT;
- aclc.hdr.length = htons(sizeof(aclc));
aclc.hdr.version = SMC_CLC_V1; /* SMC version */
if (srv_first_contact)
aclc.hdr.flag = 1;
- memcpy(aclc.lcl.id_for_peer, local_systemid, sizeof(local_systemid));
- memcpy(&aclc.lcl.gid, &link->smcibdev->gid[link->ibport - 1],
- SMC_GID_SIZE);
- memcpy(&aclc.lcl.mac, link->smcibdev->mac[link->ibport - 1], ETH_ALEN);
- hton24(aclc.qpn, link->roce_qp->qp_num);
- aclc.rmb_rkey =
- htonl(conn->rmb_desc->mr_rx[SMC_SINGLE_LINK]->rkey);
- aclc.rmbe_idx = 1; /* as long as 1 RMB = 1 RMBE */
- aclc.rmbe_alert_token = htonl(conn->alert_token_local);
- aclc.qp_mtu = link->path_mtu;
- aclc.rmbe_size = conn->rmbe_size_short,
- aclc.rmb_dma_addr = cpu_to_be64(
- (u64)sg_dma_address(conn->rmb_desc->sgt[SMC_SINGLE_LINK].sgl));
- hton24(aclc.psn, link->psn_initial);
- memcpy(aclc.trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
+
+ if (new_smc->conn.lgr->is_smcd) {
+ /* SMC-D specific settings */
+ aclc.hdr.length = htons(SMCD_CLC_ACCEPT_CONFIRM_LEN);
+ memcpy(aclc.hdr.eyecatcher, SMCD_EYECATCHER,
+ sizeof(SMCD_EYECATCHER));
+ aclc.hdr.path = SMC_TYPE_D;
+ aclc.gid = conn->lgr->smcd->local_gid;
+ aclc.token = conn->rmb_desc->token;
+ aclc.dmbe_size = conn->rmbe_size_short;
+ aclc.dmbe_idx = 0;
+ memcpy(&aclc.linkid, conn->lgr->id, SMC_LGR_ID_SIZE);
+ memcpy(aclc.smcd_trl.eyecatcher, SMCD_EYECATCHER,
+ sizeof(SMCD_EYECATCHER));
+ } else {
+ /* SMC-R specific settings */
+ aclc.hdr.length = htons(SMCR_CLC_ACCEPT_CONFIRM_LEN);
+ memcpy(aclc.hdr.eyecatcher, SMC_EYECATCHER,
+ sizeof(SMC_EYECATCHER));
+ aclc.hdr.path = SMC_TYPE_R;
+ link = &conn->lgr->lnk[SMC_SINGLE_LINK];
+ memcpy(aclc.lcl.id_for_peer, local_systemid,
+ sizeof(local_systemid));
+ memcpy(&aclc.lcl.gid, &link->smcibdev->gid[link->ibport - 1],
+ SMC_GID_SIZE);
+ memcpy(&aclc.lcl.mac, link->smcibdev->mac[link->ibport - 1],
+ ETH_ALEN);
+ hton24(aclc.qpn, link->roce_qp->qp_num);
+ aclc.rmb_rkey =
+ htonl(conn->rmb_desc->mr_rx[SMC_SINGLE_LINK]->rkey);
+ aclc.rmbe_idx = 1; /* as long as 1 RMB = 1 RMBE */
+ aclc.rmbe_alert_token = htonl(conn->alert_token_local);
+ aclc.qp_mtu = link->path_mtu;
+ aclc.rmbe_size = conn->rmbe_size_short,
+ aclc.rmb_dma_addr = cpu_to_be64((u64)sg_dma_address
+ (conn->rmb_desc->sgt[SMC_SINGLE_LINK].sgl));
+ hton24(aclc.psn, link->psn_initial);
+ memcpy(aclc.smcr_trl.eyecatcher, SMC_EYECATCHER,
+ sizeof(SMC_EYECATCHER));
+ }
memset(&msg, 0, sizeof(msg));
vec.iov_base = &aclc;
- vec.iov_len = sizeof(aclc);
- len = kernel_sendmsg(new_smc->clcsock, &msg, &vec, 1, sizeof(aclc));
- if (len < sizeof(aclc)) {
+ vec.iov_len = ntohs(aclc.hdr.length);
+ len = kernel_sendmsg(new_smc->clcsock, &msg, &vec, 1,
+ ntohs(aclc.hdr.length));
+ if (len < ntohs(aclc.hdr.length)) {
if (len >= 0)
new_smc->sk.sk_err = EPROTO;
else
#define SMC_CLC_DECLINE 0x04
#define SMC_CLC_V1 0x1 /* SMC version */
+#define SMC_TYPE_R 0 /* SMC-R only */
+#define SMC_TYPE_D 1 /* SMC-D only */
+#define SMC_TYPE_B 3 /* SMC-R and SMC-D */
#define CLC_WAIT_TIME (6 * HZ) /* max. wait time on clcsock */
#define SMC_CLC_DECL_MEM 0x01010000 /* insufficient memory resources */
#define SMC_CLC_DECL_TIMEOUT 0x02000000 /* timeout */
#if defined(__BIG_ENDIAN_BITFIELD)
u8 version : 4,
flag : 1,
- rsvd : 3;
+ rsvd : 1,
+ path : 2;
#elif defined(__LITTLE_ENDIAN_BITFIELD)
- u8 rsvd : 3,
+ u8 path : 2,
+ rsvd : 1,
flag : 1,
version : 4;
#endif
u8 ipv6_prefixes_cnt; /* number of IPv6 prefixes in prefix array */
} __aligned(4);
+struct smc_clc_msg_smcd { /* SMC-D GID information */
+ u64 gid; /* ISM GID of requestor */
+ u8 res[32];
+};
+
struct smc_clc_msg_proposal { /* clc proposal message sent by Linux */
struct smc_clc_msg_hdr hdr;
struct smc_clc_msg_local lcl;
struct smc_clc_msg_accept_confirm { /* clc accept / confirm message */
struct smc_clc_msg_hdr hdr;
- struct smc_clc_msg_local lcl;
- u8 qpn[3]; /* QP number */
- __be32 rmb_rkey; /* RMB rkey */
- u8 rmbe_idx; /* Index of RMBE in RMB */
- __be32 rmbe_alert_token;/* unique connection id */
+ union {
+ struct { /* SMC-R */
+ struct smc_clc_msg_local lcl;
+ u8 qpn[3]; /* QP number */
+ __be32 rmb_rkey; /* RMB rkey */
+ u8 rmbe_idx; /* Index of RMBE in RMB */
+ __be32 rmbe_alert_token;/* unique connection id */
#if defined(__BIG_ENDIAN_BITFIELD)
- u8 rmbe_size : 4, /* RMBE buf size (compressed notation) */
- qp_mtu : 4; /* QP mtu */
+ u8 rmbe_size : 4, /* buf size (compressed) */
+ qp_mtu : 4; /* QP mtu */
#elif defined(__LITTLE_ENDIAN_BITFIELD)
- u8 qp_mtu : 4,
- rmbe_size : 4;
+ u8 qp_mtu : 4,
+ rmbe_size : 4;
#endif
- u8 reserved;
- __be64 rmb_dma_addr; /* RMB virtual address */
- u8 reserved2;
- u8 psn[3]; /* initial packet sequence number */
- struct smc_clc_msg_trail trl; /* eye catcher "SMCR" EBCDIC */
+ u8 reserved;
+ __be64 rmb_dma_addr; /* RMB virtual address */
+ u8 reserved2;
+ u8 psn[3]; /* packet sequence number */
+ struct smc_clc_msg_trail smcr_trl;
+ /* eye catcher "SMCR" EBCDIC */
+ } __packed;
+ struct { /* SMC-D */
+ u64 gid; /* Sender GID */
+ u64 token; /* DMB token */
+ u8 dmbe_idx; /* DMBE index */
+#if defined(__BIG_ENDIAN_BITFIELD)
+ u8 dmbe_size : 4, /* buf size (compressed) */
+ reserved3 : 4;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+ u8 reserved3 : 4,
+ dmbe_size : 4;
+#endif
+ u16 reserved4;
+ u32 linkid; /* Link identifier */
+ u32 reserved5[3];
+ struct smc_clc_msg_trail smcd_trl;
+ /* eye catcher "SMCD" EBCDIC */
+ } __packed;
+ };
} __packed; /* format defined in RFC7609 */
struct smc_clc_msg_decline { /* clc decline message */
((u8 *)pclc + sizeof(*pclc) + ntohs(pclc->iparea_offset));
}
+/* get SMC-D info from proposal message */
+static inline struct smc_clc_msg_smcd *
+smc_get_clc_msg_smcd(struct smc_clc_msg_proposal *prop)
+{
+ if (ntohs(prop->iparea_offset) != sizeof(struct smc_clc_msg_smcd))
+ return NULL;
+
+ return (struct smc_clc_msg_smcd *)(prop + 1);
+}
+
+struct smcd_dev;
+
int smc_clc_prfx_match(struct socket *clcsock,
struct smc_clc_msg_proposal_prefix *prop);
int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
u8 expected_type);
int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info);
-int smc_clc_send_proposal(struct smc_sock *smc, struct smc_ib_device *smcibdev,
- u8 ibport);
+int smc_clc_send_proposal(struct smc_sock *smc, int smc_type,
+ struct smc_ib_device *smcibdev, u8 ibport,
+ struct smcd_dev *ismdev);
int smc_clc_send_confirm(struct smc_sock *smc);
int smc_clc_send_accept(struct smc_sock *smc, int srv_first_contact);
#include "smc_llc.h"
#include "smc_cdc.h"
#include "smc_close.h"
+#include "smc_ism.h"
#define SMC_LGR_NUM_INCR 256
#define SMC_LGR_FREE_DELAY_SERV (600 * HZ)
* otherwise there is a risk of out-of-sync link groups.
*/
mod_delayed_work(system_wq, &lgr->free_work,
- lgr->role == SMC_CLNT ? SMC_LGR_FREE_DELAY_CLNT :
- SMC_LGR_FREE_DELAY_SERV);
+ (!lgr->is_smcd && lgr->role == SMC_CLNT) ?
+ SMC_LGR_FREE_DELAY_CLNT : SMC_LGR_FREE_DELAY_SERV);
}
/* Register connection's alert token in our lookup structure.
free:
spin_unlock_bh(&smc_lgr_list.lock);
if (!delayed_work_pending(&lgr->free_work)) {
- if (lgr->lnk[SMC_SINGLE_LINK].state != SMC_LNK_INACTIVE)
+ if (!lgr->is_smcd &&
+ lgr->lnk[SMC_SINGLE_LINK].state != SMC_LNK_INACTIVE)
smc_llc_link_inactive(&lgr->lnk[SMC_SINGLE_LINK]);
smc_lgr_free(lgr);
}
}
/* create a new SMC link group */
-static int smc_lgr_create(struct smc_sock *smc,
+static int smc_lgr_create(struct smc_sock *smc, bool is_smcd,
struct smc_ib_device *smcibdev, u8 ibport,
- char *peer_systemid, unsigned short vlan_id)
+ char *peer_systemid, unsigned short vlan_id,
+ struct smcd_dev *smcismdev, u64 peer_gid)
{
struct smc_link_group *lgr;
struct smc_link *lnk;
int rc = 0;
int i;
+ if (is_smcd && vlan_id) {
+ rc = smc_ism_get_vlan(smcismdev, vlan_id);
+ if (rc)
+ goto out;
+ }
+
lgr = kzalloc(sizeof(*lgr), GFP_KERNEL);
if (!lgr) {
rc = -ENOMEM;
goto out;
}
- lgr->role = smc->listen_smc ? SMC_SERV : SMC_CLNT;
+ lgr->is_smcd = is_smcd;
lgr->sync_err = 0;
- memcpy(lgr->peer_systemid, peer_systemid, SMC_SYSTEMID_LEN);
lgr->vlan_id = vlan_id;
rwlock_init(&lgr->sndbufs_lock);
rwlock_init(&lgr->rmbs_lock);
+ rwlock_init(&lgr->conns_lock);
for (i = 0; i < SMC_RMBE_SIZES; i++) {
INIT_LIST_HEAD(&lgr->sndbufs[i]);
INIT_LIST_HEAD(&lgr->rmbs[i]);
memcpy(&lgr->id, (u8 *)&smc_lgr_list.num, SMC_LGR_ID_SIZE);
INIT_DELAYED_WORK(&lgr->free_work, smc_lgr_free_work);
lgr->conns_all = RB_ROOT;
-
- lnk = &lgr->lnk[SMC_SINGLE_LINK];
- /* initialize link */
- lnk->state = SMC_LNK_ACTIVATING;
- lnk->link_id = SMC_SINGLE_LINK;
- lnk->smcibdev = smcibdev;
- lnk->ibport = ibport;
- lnk->path_mtu = smcibdev->pattr[ibport - 1].active_mtu;
- if (!smcibdev->initialized)
- smc_ib_setup_per_ibdev(smcibdev);
- get_random_bytes(rndvec, sizeof(rndvec));
- lnk->psn_initial = rndvec[0] + (rndvec[1] << 8) + (rndvec[2] << 16);
- rc = smc_llc_link_init(lnk);
- if (rc)
- goto free_lgr;
- rc = smc_wr_alloc_link_mem(lnk);
- if (rc)
- goto clear_llc_lnk;
- rc = smc_ib_create_protection_domain(lnk);
- if (rc)
- goto free_link_mem;
- rc = smc_ib_create_queue_pair(lnk);
- if (rc)
- goto dealloc_pd;
- rc = smc_wr_create_link(lnk);
- if (rc)
- goto destroy_qp;
-
+ if (is_smcd) {
+ /* SMC-D specific settings */
+ lgr->peer_gid = peer_gid;
+ lgr->smcd = smcismdev;
+ } else {
+ /* SMC-R specific settings */
+ lgr->role = smc->listen_smc ? SMC_SERV : SMC_CLNT;
+ memcpy(lgr->peer_systemid, peer_systemid, SMC_SYSTEMID_LEN);
+
+ lnk = &lgr->lnk[SMC_SINGLE_LINK];
+ /* initialize link */
+ lnk->state = SMC_LNK_ACTIVATING;
+ lnk->link_id = SMC_SINGLE_LINK;
+ lnk->smcibdev = smcibdev;
+ lnk->ibport = ibport;
+ lnk->path_mtu = smcibdev->pattr[ibport - 1].active_mtu;
+ if (!smcibdev->initialized)
+ smc_ib_setup_per_ibdev(smcibdev);
+ get_random_bytes(rndvec, sizeof(rndvec));
+ lnk->psn_initial = rndvec[0] + (rndvec[1] << 8) +
+ (rndvec[2] << 16);
+ rc = smc_llc_link_init(lnk);
+ if (rc)
+ goto free_lgr;
+ rc = smc_wr_alloc_link_mem(lnk);
+ if (rc)
+ goto clear_llc_lnk;
+ rc = smc_ib_create_protection_domain(lnk);
+ if (rc)
+ goto free_link_mem;
+ rc = smc_ib_create_queue_pair(lnk);
+ if (rc)
+ goto dealloc_pd;
+ rc = smc_wr_create_link(lnk);
+ if (rc)
+ goto destroy_qp;
+ }
smc->conn.lgr = lgr;
- rwlock_init(&lgr->conns_lock);
spin_lock_bh(&smc_lgr_list.lock);
list_add(&lgr->list, &smc_lgr_list.list);
spin_unlock_bh(&smc_lgr_list.lock);
{
if (!conn->lgr)
return;
- smc_cdc_tx_dismiss_slots(conn);
+ if (conn->lgr->is_smcd) {
+ smc_ism_unset_conn(conn);
+ tasklet_kill(&conn->rx_tsklet);
+ } else {
+ smc_cdc_tx_dismiss_slots(conn);
+ }
smc_lgr_unregister_conn(conn);
smc_buf_unuse(conn);
}
smc_wr_free_link_mem(lnk);
}
-static void smc_buf_free(struct smc_link_group *lgr, bool is_rmb,
- struct smc_buf_desc *buf_desc)
+static void smcr_buf_free(struct smc_link_group *lgr, bool is_rmb,
+ struct smc_buf_desc *buf_desc)
{
struct smc_link *lnk = &lgr->lnk[SMC_SINGLE_LINK];
kfree(buf_desc);
}
+static void smcd_buf_free(struct smc_link_group *lgr, bool is_dmb,
+ struct smc_buf_desc *buf_desc)
+{
+ if (is_dmb) {
+ /* restore original buf len */
+ buf_desc->len += sizeof(struct smcd_cdc_msg);
+ smc_ism_unregister_dmb(lgr->smcd, buf_desc);
+ } else {
+ kfree(buf_desc->cpu_addr);
+ }
+ kfree(buf_desc);
+}
+
+static void smc_buf_free(struct smc_link_group *lgr, bool is_rmb,
+ struct smc_buf_desc *buf_desc)
+{
+ if (lgr->is_smcd)
+ smcd_buf_free(lgr, is_rmb, buf_desc);
+ else
+ smcr_buf_free(lgr, is_rmb, buf_desc);
+}
+
static void __smc_lgr_free_bufs(struct smc_link_group *lgr, bool is_rmb)
{
struct smc_buf_desc *buf_desc, *bf_desc;
void smc_lgr_free(struct smc_link_group *lgr)
{
smc_lgr_free_bufs(lgr);
- smc_link_clear(&lgr->lnk[SMC_SINGLE_LINK]);
+ if (lgr->is_smcd)
+ smc_ism_put_vlan(lgr->smcd, lgr->vlan_id);
+ else
+ smc_link_clear(&lgr->lnk[SMC_SINGLE_LINK]);
kfree(lgr);
}
lgr->terminating = 1;
if (!list_empty(&lgr->list)) /* forget lgr */
list_del_init(&lgr->list);
- smc_llc_link_inactive(&lgr->lnk[SMC_SINGLE_LINK]);
+ if (!lgr->is_smcd)
+ smc_llc_link_inactive(&lgr->lnk[SMC_SINGLE_LINK]);
write_lock_bh(&lgr->conns_lock);
node = rb_first(&lgr->conns_all);
node = rb_first(&lgr->conns_all);
}
write_unlock_bh(&lgr->conns_lock);
- wake_up(&lgr->lnk[SMC_SINGLE_LINK].wr_reg_wait);
+ if (!lgr->is_smcd)
+ wake_up(&lgr->lnk[SMC_SINGLE_LINK].wr_reg_wait);
smc_lgr_schedule_free_work(lgr);
}
spin_lock_bh(&smc_lgr_list.lock);
list_for_each_entry_safe(lgr, l, &smc_lgr_list.list, list) {
- if (lgr->lnk[SMC_SINGLE_LINK].smcibdev == smcibdev &&
+ if (!lgr->is_smcd &&
+ lgr->lnk[SMC_SINGLE_LINK].smcibdev == smcibdev &&
lgr->lnk[SMC_SINGLE_LINK].ibport == ibport)
__smc_lgr_terminate(lgr);
}
spin_unlock_bh(&smc_lgr_list.lock);
}
+/* Called when SMC-D device is terminated or peer is lost */
+void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid)
+{
+ struct smc_link_group *lgr, *l;
+ LIST_HEAD(lgr_free_list);
+
+ /* run common cleanup function and build free list */
+ spin_lock_bh(&smc_lgr_list.lock);
+ list_for_each_entry_safe(lgr, l, &smc_lgr_list.list, list) {
+ if (lgr->is_smcd && lgr->smcd == dev &&
+ (!peer_gid || lgr->peer_gid == peer_gid) &&
+ !list_empty(&lgr->list)) {
+ __smc_lgr_terminate(lgr);
+ list_move(&lgr->list, &lgr_free_list);
+ }
+ }
+ spin_unlock_bh(&smc_lgr_list.lock);
+
+ /* cancel the regular free workers and actually free lgrs */
+ list_for_each_entry_safe(lgr, l, &lgr_free_list, list) {
+ list_del_init(&lgr->list);
+ cancel_delayed_work_sync(&lgr->free_work);
+ smc_lgr_free(lgr);
+ }
+}
+
/* Determine vlan of internal TCP socket.
* @vlan_id: address to store the determined vlan id into
*/
-static int smc_vlan_by_tcpsk(struct socket *clcsock, unsigned short *vlan_id)
+int smc_vlan_by_tcpsk(struct socket *clcsock, unsigned short *vlan_id)
{
struct dst_entry *dst = sk_dst_get(clcsock->sk);
struct net_device *ndev;
return -ENODEV;
}
+static bool smcr_lgr_match(struct smc_link_group *lgr,
+ struct smc_clc_msg_local *lcl,
+ enum smc_lgr_role role)
+{
+ return !memcmp(lgr->peer_systemid, lcl->id_for_peer,
+ SMC_SYSTEMID_LEN) &&
+ !memcmp(lgr->lnk[SMC_SINGLE_LINK].peer_gid, &lcl->gid,
+ SMC_GID_SIZE) &&
+ !memcmp(lgr->lnk[SMC_SINGLE_LINK].peer_mac, lcl->mac,
+ sizeof(lcl->mac)) &&
+ lgr->role == role;
+}
+
+static bool smcd_lgr_match(struct smc_link_group *lgr,
+ struct smcd_dev *smcismdev, u64 peer_gid)
+{
+ return lgr->peer_gid == peer_gid && lgr->smcd == smcismdev;
+}
+
/* create a new SMC connection (and a new link group if necessary) */
-int smc_conn_create(struct smc_sock *smc,
+int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact,
struct smc_ib_device *smcibdev, u8 ibport,
- struct smc_clc_msg_local *lcl, int srv_first_contact)
+ struct smc_clc_msg_local *lcl, struct smcd_dev *smcd,
+ u64 peer_gid)
{
struct smc_connection *conn = &smc->conn;
int local_contact = SMC_FIRST_CONTACT;
spin_lock_bh(&smc_lgr_list.lock);
list_for_each_entry(lgr, &smc_lgr_list.list, list) {
write_lock_bh(&lgr->conns_lock);
- if (!memcmp(lgr->peer_systemid, lcl->id_for_peer,
- SMC_SYSTEMID_LEN) &&
- !memcmp(lgr->lnk[SMC_SINGLE_LINK].peer_gid, &lcl->gid,
- SMC_GID_SIZE) &&
- !memcmp(lgr->lnk[SMC_SINGLE_LINK].peer_mac, lcl->mac,
- sizeof(lcl->mac)) &&
+ if ((is_smcd ? smcd_lgr_match(lgr, smcd, peer_gid) :
+ smcr_lgr_match(lgr, lcl, role)) &&
!lgr->sync_err &&
- (lgr->role == role) &&
- (lgr->vlan_id == vlan_id) &&
- ((role == SMC_CLNT) ||
- (lgr->conns_num < SMC_RMBS_PER_LGR_MAX))) {
+ lgr->vlan_id == vlan_id &&
+ (role == SMC_CLNT ||
+ lgr->conns_num < SMC_RMBS_PER_LGR_MAX)) {
/* link group found */
local_contact = SMC_REUSE_CONTACT;
conn->lgr = lgr;
create:
if (local_contact == SMC_FIRST_CONTACT) {
- rc = smc_lgr_create(smc, smcibdev, ibport,
- lcl->id_for_peer, vlan_id);
+ rc = smc_lgr_create(smc, is_smcd, smcibdev, ibport,
+ lcl->id_for_peer, vlan_id, smcd, peer_gid);
if (rc)
goto out;
smc_lgr_register_conn(conn); /* add smc conn to lgr */
- rc = smc_link_determine_gid(conn->lgr);
+ if (!is_smcd)
+ rc = smc_link_determine_gid(conn->lgr);
}
conn->local_tx_ctrl.common.type = SMC_CDC_MSG_TYPE;
conn->local_tx_ctrl.len = SMC_WR_TX_SIZE;
conn->urg_state = SMC_URG_READ;
+ if (is_smcd) {
+ conn->rx_off = sizeof(struct smcd_cdc_msg);
+ smcd_cdc_rx_init(conn); /* init tasklet for this conn */
+ }
#ifndef KERNEL_HAS_ATOMIC64
spin_lock_init(&conn->acurs_lock);
#endif
return min_t(int, rmbe_size / 10, SOCK_MIN_SNDBUF / 2);
}
-static struct smc_buf_desc *smc_new_buf_create(struct smc_link_group *lgr,
- bool is_rmb, int bufsize)
+static struct smc_buf_desc *smcr_new_buf_create(struct smc_link_group *lgr,
+ bool is_rmb, int bufsize)
{
struct smc_buf_desc *buf_desc;
struct smc_link *lnk;
return buf_desc;
}
-static int __smc_buf_create(struct smc_sock *smc, bool is_rmb)
+#define SMCD_DMBE_SIZES 7 /* 0 -> 16KB, 1 -> 32KB, .. 6 -> 1MB */
+
+static struct smc_buf_desc *smcd_new_buf_create(struct smc_link_group *lgr,
+ bool is_dmb, int bufsize)
+{
+ struct smc_buf_desc *buf_desc;
+ int rc;
+
+ if (smc_compress_bufsize(bufsize) > SMCD_DMBE_SIZES)
+ return ERR_PTR(-EAGAIN);
+
+ /* try to alloc a new DMB */
+ buf_desc = kzalloc(sizeof(*buf_desc), GFP_KERNEL);
+ if (!buf_desc)
+ return ERR_PTR(-ENOMEM);
+ if (is_dmb) {
+ rc = smc_ism_register_dmb(lgr, bufsize, buf_desc);
+ if (rc) {
+ kfree(buf_desc);
+ return ERR_PTR(-EAGAIN);
+ }
+ buf_desc->pages = virt_to_page(buf_desc->cpu_addr);
+ /* CDC header stored in buf. So, pretend it was smaller */
+ buf_desc->len = bufsize - sizeof(struct smcd_cdc_msg);
+ } else {
+ buf_desc->cpu_addr = kzalloc(bufsize, GFP_KERNEL |
+ __GFP_NOWARN | __GFP_NORETRY |
+ __GFP_NOMEMALLOC);
+ if (!buf_desc->cpu_addr) {
+ kfree(buf_desc);
+ return ERR_PTR(-EAGAIN);
+ }
+ buf_desc->len = bufsize;
+ }
+ return buf_desc;
+}
+
+static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb)
{
struct smc_buf_desc *buf_desc = ERR_PTR(-ENOMEM);
struct smc_connection *conn = &smc->conn;
break; /* found reusable slot */
}
- buf_desc = smc_new_buf_create(lgr, is_rmb, bufsize);
+ if (is_smcd)
+ buf_desc = smcd_new_buf_create(lgr, is_rmb, bufsize);
+ else
+ buf_desc = smcr_new_buf_create(lgr, is_rmb, bufsize);
+
if (PTR_ERR(buf_desc) == -ENOMEM)
break;
if (IS_ERR(buf_desc))
conn->rmbe_size_short = bufsize_short;
smc->sk.sk_rcvbuf = bufsize * 2;
atomic_set(&conn->bytes_to_rcv, 0);
- conn->rmbe_update_limit = smc_rmb_wnd_update_limit(bufsize);
+ conn->rmbe_update_limit =
+ smc_rmb_wnd_update_limit(buf_desc->len);
+ if (is_smcd)
+ smc_ism_set_conn(conn); /* map RMB/smcd_dev to conn */
} else {
conn->sndbuf_desc = buf_desc;
smc->sk.sk_sndbuf = bufsize * 2;
{
struct smc_link_group *lgr = conn->lgr;
+ if (!conn->lgr || conn->lgr->is_smcd)
+ return;
smc_ib_sync_sg_for_cpu(lgr->lnk[SMC_SINGLE_LINK].smcibdev,
conn->sndbuf_desc, DMA_TO_DEVICE);
}
{
struct smc_link_group *lgr = conn->lgr;
+ if (!conn->lgr || conn->lgr->is_smcd)
+ return;
smc_ib_sync_sg_for_device(lgr->lnk[SMC_SINGLE_LINK].smcibdev,
conn->sndbuf_desc, DMA_TO_DEVICE);
}
{
struct smc_link_group *lgr = conn->lgr;
+ if (!conn->lgr || conn->lgr->is_smcd)
+ return;
smc_ib_sync_sg_for_cpu(lgr->lnk[SMC_SINGLE_LINK].smcibdev,
conn->rmb_desc, DMA_FROM_DEVICE);
}
{
struct smc_link_group *lgr = conn->lgr;
+ if (!conn->lgr || conn->lgr->is_smcd)
+ return;
smc_ib_sync_sg_for_device(lgr->lnk[SMC_SINGLE_LINK].smcibdev,
conn->rmb_desc, DMA_FROM_DEVICE);
}
* the Linux implementation uses just one RMB-element per RMB, i.e. uses an
* extra RMB for every connection in a link group
*/
-int smc_buf_create(struct smc_sock *smc)
+int smc_buf_create(struct smc_sock *smc, bool is_smcd)
{
int rc;
/* create send buffer */
- rc = __smc_buf_create(smc, false);
+ rc = __smc_buf_create(smc, is_smcd, false);
if (rc)
return rc;
/* create rmb */
- rc = __smc_buf_create(smc, true);
+ rc = __smc_buf_create(smc, is_smcd, true);
if (rc)
smc_buf_free(smc->conn.lgr, false, smc->conn.sndbuf_desc);
return rc;
spin_unlock_bh(&smc_lgr_list.lock);
list_for_each_entry_safe(lgr, lg, &lgr_freeing_list, list) {
list_del_init(&lgr->list);
- smc_llc_link_inactive(&lgr->lnk[SMC_SINGLE_LINK]);
+ if (!lgr->is_smcd)
+ smc_llc_link_inactive(&lgr->lnk[SMC_SINGLE_LINK]);
cancel_delayed_work_sync(&lgr->free_work);
smc_lgr_free(lgr); /* free link group */
}
void *cpu_addr; /* virtual address of buffer */
struct page *pages;
int len; /* length of buffer */
- struct sg_table sgt[SMC_LINKS_PER_LGR_MAX];/* virtual buffer */
- struct ib_mr *mr_rx[SMC_LINKS_PER_LGR_MAX];
- /* for rmb only: memory region
- * incl. rkey provided to peer
- */
- u32 order; /* allocation order */
u32 used; /* currently used / unused */
u8 reused : 1; /* new created / reused */
u8 regerr : 1; /* err during registration */
+ union {
+ struct { /* SMC-R */
+ struct sg_table sgt[SMC_LINKS_PER_LGR_MAX];
+ /* virtual buffer */
+ struct ib_mr *mr_rx[SMC_LINKS_PER_LGR_MAX];
+ /* for rmb only: memory region
+ * incl. rkey provided to peer
+ */
+ u32 order; /* allocation order */
+ };
+ struct { /* SMC-D */
+ unsigned short sba_idx;
+ /* SBA index number */
+ u64 token;
+ /* DMB token number */
+ dma_addr_t dma_addr;
+ /* DMA address */
+ };
+ };
};
struct smc_rtoken { /* address/key of remote RMB */
* struct smc_clc_msg_accept_confirm.rmbe_size being a 4 bit value (0..15)
*/
+struct smcd_dev;
+
struct smc_link_group {
struct list_head list;
- enum smc_lgr_role role; /* client or server */
- struct smc_link lnk[SMC_LINKS_PER_LGR_MAX]; /* smc link */
- char peer_systemid[SMC_SYSTEMID_LEN];
- /* unique system_id of peer */
struct rb_root conns_all; /* connection tree */
rwlock_t conns_lock; /* protects conns_all */
unsigned int conns_num; /* current # of connections */
rwlock_t sndbufs_lock; /* protects tx buffers */
struct list_head rmbs[SMC_RMBE_SIZES]; /* rx buffers */
rwlock_t rmbs_lock; /* protects rx buffers */
- struct smc_rtoken rtokens[SMC_RMBS_PER_LGR_MAX]
- [SMC_LINKS_PER_LGR_MAX];
- /* remote addr/key pairs */
- unsigned long rtokens_used_mask[BITS_TO_LONGS(
- SMC_RMBS_PER_LGR_MAX)];
- /* used rtoken elements */
u8 id[SMC_LGR_ID_SIZE]; /* unique lgr id */
struct delayed_work free_work; /* delayed freeing of an lgr */
u8 sync_err : 1; /* lgr no longer fits to peer */
u8 terminating : 1;/* lgr is terminating */
+
+ bool is_smcd; /* SMC-R or SMC-D */
+ union {
+ struct { /* SMC-R */
+ enum smc_lgr_role role;
+ /* client or server */
+ struct smc_link lnk[SMC_LINKS_PER_LGR_MAX];
+ /* smc link */
+ char peer_systemid[SMC_SYSTEMID_LEN];
+ /* unique system_id of peer */
+ struct smc_rtoken rtokens[SMC_RMBS_PER_LGR_MAX]
+ [SMC_LINKS_PER_LGR_MAX];
+ /* remote addr/key pairs */
+ unsigned long rtokens_used_mask[BITS_TO_LONGS
+ (SMC_RMBS_PER_LGR_MAX)];
+ /* used rtoken elements */
+ };
+ struct { /* SMC-D */
+ u64 peer_gid;
+ /* Peer GID (remote) */
+ struct smcd_dev *smcd;
+ /* ISM device for VLAN reg. */
+ };
+ };
};
/* Find the connection associated with the given alert token in the link group.
void smc_lgr_forget(struct smc_link_group *lgr);
void smc_lgr_terminate(struct smc_link_group *lgr);
void smc_port_terminate(struct smc_ib_device *smcibdev, u8 ibport);
-int smc_buf_create(struct smc_sock *smc);
+void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid);
+int smc_buf_create(struct smc_sock *smc, bool is_smcd);
int smc_uncompress_bufsize(u8 compressed);
int smc_rmb_rtoken_handling(struct smc_connection *conn,
struct smc_clc_msg_accept_confirm *clc);
void smc_sndbuf_sync_sg_for_device(struct smc_connection *conn);
void smc_rmb_sync_sg_for_cpu(struct smc_connection *conn);
void smc_rmb_sync_sg_for_device(struct smc_connection *conn);
+int smc_vlan_by_tcpsk(struct socket *clcsock, unsigned short *vlan_id);
+
void smc_conn_free(struct smc_connection *conn);
-int smc_conn_create(struct smc_sock *smc,
+int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact,
struct smc_ib_device *smcibdev, u8 ibport,
- struct smc_clc_msg_local *lcl, int srv_first_contact);
+ struct smc_clc_msg_local *lcl, struct smcd_dev *smcd,
+ u64 peer_gid);
+void smcd_conn_free(struct smc_connection *conn);
void smc_core_exit(void);
#endif
goto errout;
}
- if ((req->diag_ext & (1 << (SMC_DIAG_LGRINFO - 1))) && smc->conn.lgr &&
+ if (smc->conn.lgr && !smc->conn.lgr->is_smcd &&
+ (req->diag_ext & (1 << (SMC_DIAG_LGRINFO - 1))) &&
!list_empty(&smc->conn.lgr->list)) {
struct smc_diag_lgrinfo linfo = {
.role = smc->conn.lgr->role,
if (nla_put(skb, SMC_DIAG_LGRINFO, sizeof(linfo), &linfo) < 0)
goto errout;
}
+ if (smc->conn.lgr && smc->conn.lgr->is_smcd &&
+ (req->diag_ext & (1 << (SMC_DIAG_DMBINFO - 1))) &&
+ !list_empty(&smc->conn.lgr->list)) {
+ struct smc_connection *conn = &smc->conn;
+ struct smcd_diag_dmbinfo dinfo = {
+ .linkid = *((u32 *)conn->lgr->id),
+ .peer_gid = conn->lgr->peer_gid,
+ .my_gid = conn->lgr->smcd->local_gid,
+ .token = conn->rmb_desc->token,
+ .peer_token = conn->peer_token
+ };
+
+ if (nla_put(skb, SMC_DIAG_DMBINFO, sizeof(dinfo), &dinfo) < 0)
+ goto errout;
+ }
nlmsg_end(skb, nlh);
return 0;
return rc;
}
+static int smc_ib_fill_gid_and_mac(struct smc_ib_device *smcibdev, u8 ibport)
+{
+ struct ib_gid_attr gattr;
+ int rc;
+
+ rc = ib_query_gid(smcibdev->ibdev, ibport, 0,
+ &smcibdev->gid[ibport - 1], &gattr);
+ if (rc || !gattr.ndev)
+ return -ENODEV;
+
+ memcpy(smcibdev->mac[ibport - 1], gattr.ndev->dev_addr, ETH_ALEN);
+ dev_put(gattr.ndev);
+ return 0;
+}
+
+/* Create an identifier unique for this instance of SMC-R.
+ * The MAC-address of the first active registered IB device
+ * plus a random 2-byte number is used to create this identifier.
+ * This name is delivered to the peer during connection initialization.
+ */
+static inline void smc_ib_define_local_systemid(struct smc_ib_device *smcibdev,
+ u8 ibport)
+{
+ memcpy(&local_systemid[2], &smcibdev->mac[ibport - 1],
+ sizeof(smcibdev->mac[ibport - 1]));
+ get_random_bytes(&local_systemid[0], 2);
+}
+
+bool smc_ib_port_active(struct smc_ib_device *smcibdev, u8 ibport)
+{
+ return smcibdev->pattr[ibport - 1].state == IB_PORT_ACTIVE;
+}
+
+static int smc_ib_remember_port_attr(struct smc_ib_device *smcibdev, u8 ibport)
+{
+ int rc;
+
+ memset(&smcibdev->pattr[ibport - 1], 0,
+ sizeof(smcibdev->pattr[ibport - 1]));
+ rc = ib_query_port(smcibdev->ibdev, ibport,
+ &smcibdev->pattr[ibport - 1]);
+ if (rc)
+ goto out;
+ /* the SMC protocol requires specification of the RoCE MAC address */
+ rc = smc_ib_fill_gid_and_mac(smcibdev, ibport);
+ if (rc)
+ goto out;
+ if (!strncmp(local_systemid, SMC_LOCAL_SYSTEMID_RESET,
+ sizeof(local_systemid)) &&
+ smc_ib_port_active(smcibdev, ibport))
+ /* create unique system identifier */
+ smc_ib_define_local_systemid(smcibdev, ibport);
+out:
+ return rc;
+}
+
/* process context wrapper for might_sleep smc_ib_remember_port_attr */
static void smc_ib_port_event_work(struct work_struct *work)
{
buf_slot->sgt[SMC_SINGLE_LINK].sgl->dma_address = 0;
}
-static int smc_ib_fill_gid_and_mac(struct smc_ib_device *smcibdev, u8 ibport)
-{
- struct ib_gid_attr gattr;
- int rc;
-
- rc = ib_query_gid(smcibdev->ibdev, ibport, 0,
- &smcibdev->gid[ibport - 1], &gattr);
- if (rc || !gattr.ndev)
- return -ENODEV;
-
- memcpy(smcibdev->mac[ibport - 1], gattr.ndev->dev_addr, ETH_ALEN);
- dev_put(gattr.ndev);
- return 0;
-}
-
-/* Create an identifier unique for this instance of SMC-R.
- * The MAC-address of the first active registered IB device
- * plus a random 2-byte number is used to create this identifier.
- * This name is delivered to the peer during connection initialization.
- */
-static inline void smc_ib_define_local_systemid(struct smc_ib_device *smcibdev,
- u8 ibport)
-{
- memcpy(&local_systemid[2], &smcibdev->mac[ibport - 1],
- sizeof(smcibdev->mac[ibport - 1]));
- get_random_bytes(&local_systemid[0], 2);
-}
-
-bool smc_ib_port_active(struct smc_ib_device *smcibdev, u8 ibport)
-{
- return smcibdev->pattr[ibport - 1].state == IB_PORT_ACTIVE;
-}
-
-int smc_ib_remember_port_attr(struct smc_ib_device *smcibdev, u8 ibport)
-{
- int rc;
-
- memset(&smcibdev->pattr[ibport - 1], 0,
- sizeof(smcibdev->pattr[ibport - 1]));
- rc = ib_query_port(smcibdev->ibdev, ibport,
- &smcibdev->pattr[ibport - 1]);
- if (rc)
- goto out;
- /* the SMC protocol requires specification of the RoCE MAC address */
- rc = smc_ib_fill_gid_and_mac(smcibdev, ibport);
- if (rc)
- goto out;
- if (!strncmp(local_systemid, SMC_LOCAL_SYSTEMID_RESET,
- sizeof(local_systemid)) &&
- smc_ib_port_active(smcibdev, ibport))
- /* create unique system identifier */
- smc_ib_define_local_systemid(smcibdev, ibport);
-out:
- return rc;
-}
-
long smc_ib_setup_per_ibdev(struct smc_ib_device *smcibdev)
{
struct ib_cq_init_attr cqattr = {
smcibdev->roce_cq_recv = NULL;
goto err;
}
- INIT_IB_EVENT_HANDLER(&smcibdev->event_handler, smcibdev->ibdev,
- smc_ib_global_event_handler);
- ib_register_event_handler(&smcibdev->event_handler);
smc_wr_add_dev(smcibdev);
smcibdev->initialized = 1;
return rc;
return;
smcibdev->initialized = 0;
smc_wr_remove_dev(smcibdev);
- ib_unregister_event_handler(&smcibdev->event_handler);
ib_destroy_cq(smcibdev->roce_cq_recv);
ib_destroy_cq(smcibdev->roce_cq_send);
}
static void smc_ib_add_dev(struct ib_device *ibdev)
{
struct smc_ib_device *smcibdev;
+ u8 port_cnt;
+ int i;
if (ibdev->node_type != RDMA_NODE_IB_CA)
return;
list_add_tail(&smcibdev->list, &smc_ib_devices.list);
spin_unlock(&smc_ib_devices.lock);
ib_set_client_data(ibdev, &smc_ib_client, smcibdev);
+ INIT_IB_EVENT_HANDLER(&smcibdev->event_handler, smcibdev->ibdev,
+ smc_ib_global_event_handler);
+ ib_register_event_handler(&smcibdev->event_handler);
+
+ /* trigger reading of the port attributes */
+ port_cnt = smcibdev->ibdev->phys_port_cnt;
+ for (i = 0;
+ i < min_t(size_t, port_cnt, SMC_MAX_PORTS);
+ i++) {
+ set_bit(i, &smcibdev->port_event_mask);
+ /* determine pnetids of the port */
+ smc_pnetid_by_dev_port(ibdev->dev.parent, i,
+ smcibdev->pnetid[i]);
+ }
+ schedule_work(&smcibdev->port_event_work);
}
/* callback function for ib_register_client() */
spin_unlock(&smc_ib_devices.lock);
smc_pnet_remove_by_ibdev(smcibdev);
smc_ib_cleanup_per_ibdev(smcibdev);
+ ib_unregister_event_handler(&smcibdev->event_handler);
kfree(smcibdev);
}
#include <linux/interrupt.h>
#include <linux/if_ether.h>
#include <rdma/ib_verbs.h>
+#include <net/smc.h>
#define SMC_MAX_PORTS 2 /* Max # of ports */
#define SMC_GID_SIZE sizeof(union ib_gid)
char mac[SMC_MAX_PORTS][ETH_ALEN];
/* mac address per port*/
union ib_gid gid[SMC_MAX_PORTS]; /* gid per port */
+ u8 pnetid[SMC_MAX_PORTS][SMC_MAX_PNETID_LEN];
+ /* pnetid per port */
u8 initialized : 1; /* ib dev CQ, evthdl done */
struct work_struct port_event_work;
unsigned long port_event_mask;
int smc_ib_register_client(void) __init;
void smc_ib_unregister_client(void);
bool smc_ib_port_active(struct smc_ib_device *smcibdev, u8 ibport);
-int smc_ib_remember_port_attr(struct smc_ib_device *smcibdev, u8 ibport);
int smc_ib_buf_map_sg(struct smc_ib_device *smcibdev,
struct smc_buf_desc *buf_slot,
enum dma_data_direction data_direction);
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Shared Memory Communications Direct over ISM devices (SMC-D)
+ *
+ * Functions for ISM device.
+ *
+ * Copyright IBM Corp. 2018
+ */
+
+#include <linux/spinlock.h>
+#include <linux/slab.h>
+#include <asm/page.h>
+
+#include "smc.h"
+#include "smc_core.h"
+#include "smc_ism.h"
+#include "smc_pnet.h"
+
+struct smcd_dev_list smcd_dev_list = {
+ .list = LIST_HEAD_INIT(smcd_dev_list.list),
+ .lock = __SPIN_LOCK_UNLOCKED(smcd_dev_list.lock)
+};
+
+/* Test if an ISM communication is possible. */
+int smc_ism_cantalk(u64 peer_gid, unsigned short vlan_id, struct smcd_dev *smcd)
+{
+ return smcd->ops->query_remote_gid(smcd, peer_gid, vlan_id ? 1 : 0,
+ vlan_id);
+}
+
+int smc_ism_write(struct smcd_dev *smcd, const struct smc_ism_position *pos,
+ void *data, size_t len)
+{
+ int rc;
+
+ rc = smcd->ops->move_data(smcd, pos->token, pos->index, pos->signal,
+ pos->offset, data, len);
+
+ return rc < 0 ? rc : 0;
+}
+
+/* Set a connection using this DMBE. */
+void smc_ism_set_conn(struct smc_connection *conn)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&conn->lgr->smcd->lock, flags);
+ conn->lgr->smcd->conn[conn->rmb_desc->sba_idx] = conn;
+ spin_unlock_irqrestore(&conn->lgr->smcd->lock, flags);
+}
+
+/* Unset a connection using this DMBE. */
+void smc_ism_unset_conn(struct smc_connection *conn)
+{
+ unsigned long flags;
+
+ if (!conn->rmb_desc)
+ return;
+
+ spin_lock_irqsave(&conn->lgr->smcd->lock, flags);
+ conn->lgr->smcd->conn[conn->rmb_desc->sba_idx] = NULL;
+ spin_unlock_irqrestore(&conn->lgr->smcd->lock, flags);
+}
+
+/* Register a VLAN identifier with the ISM device. Use a reference count
+ * and add a VLAN identifier only when the first DMB using this VLAN is
+ * registered.
+ */
+int smc_ism_get_vlan(struct smcd_dev *smcd, unsigned short vlanid)
+{
+ struct smc_ism_vlanid *new_vlan, *vlan;
+ unsigned long flags;
+ int rc = 0;
+
+ if (!vlanid) /* No valid vlan id */
+ return -EINVAL;
+
+ /* create new vlan entry, in case we need it */
+ new_vlan = kzalloc(sizeof(*new_vlan), GFP_KERNEL);
+ if (!new_vlan)
+ return -ENOMEM;
+ new_vlan->vlanid = vlanid;
+ refcount_set(&new_vlan->refcnt, 1);
+
+ /* if there is an existing entry, increase count and return */
+ spin_lock_irqsave(&smcd->lock, flags);
+ list_for_each_entry(vlan, &smcd->vlan, list) {
+ if (vlan->vlanid == vlanid) {
+ refcount_inc(&vlan->refcnt);
+ kfree(new_vlan);
+ goto out;
+ }
+ }
+
+ /* no existing entry found.
+ * add new entry to device; might fail, e.g., if HW limit reached
+ */
+ if (smcd->ops->add_vlan_id(smcd, vlanid)) {
+ kfree(new_vlan);
+ rc = -EIO;
+ goto out;
+ }
+ list_add_tail(&new_vlan->list, &smcd->vlan);
+out:
+ spin_unlock_irqrestore(&smcd->lock, flags);
+ return rc;
+}
+
+/* Unregister a VLAN identifier with the ISM device. Use a reference count
+ * and remove a VLAN identifier only when the last DMB using this VLAN is
+ * unregistered.
+ */
+int smc_ism_put_vlan(struct smcd_dev *smcd, unsigned short vlanid)
+{
+ struct smc_ism_vlanid *vlan;
+ unsigned long flags;
+ bool found = false;
+ int rc = 0;
+
+ if (!vlanid) /* No valid vlan id */
+ return -EINVAL;
+
+ spin_lock_irqsave(&smcd->lock, flags);
+ list_for_each_entry(vlan, &smcd->vlan, list) {
+ if (vlan->vlanid == vlanid) {
+ if (!refcount_dec_and_test(&vlan->refcnt))
+ goto out;
+ found = true;
+ break;
+ }
+ }
+ if (!found) {
+ rc = -ENOENT;
+ goto out; /* VLAN id not in table */
+ }
+
+ /* Found and the last reference just gone */
+ if (smcd->ops->del_vlan_id(smcd, vlanid))
+ rc = -EIO;
+ list_del(&vlan->list);
+ kfree(vlan);
+out:
+ spin_unlock_irqrestore(&smcd->lock, flags);
+ return rc;
+}
+
+int smc_ism_unregister_dmb(struct smcd_dev *smcd, struct smc_buf_desc *dmb_desc)
+{
+ struct smcd_dmb dmb;
+
+ memset(&dmb, 0, sizeof(dmb));
+ dmb.dmb_tok = dmb_desc->token;
+ dmb.sba_idx = dmb_desc->sba_idx;
+ dmb.cpu_addr = dmb_desc->cpu_addr;
+ dmb.dma_addr = dmb_desc->dma_addr;
+ dmb.dmb_len = dmb_desc->len;
+ return smcd->ops->unregister_dmb(smcd, &dmb);
+}
+
+int smc_ism_register_dmb(struct smc_link_group *lgr, int dmb_len,
+ struct smc_buf_desc *dmb_desc)
+{
+ struct smcd_dmb dmb;
+ int rc;
+
+ memset(&dmb, 0, sizeof(dmb));
+ dmb.dmb_len = dmb_len;
+ dmb.sba_idx = dmb_desc->sba_idx;
+ dmb.vlan_id = lgr->vlan_id;
+ dmb.rgid = lgr->peer_gid;
+ rc = lgr->smcd->ops->register_dmb(lgr->smcd, &dmb);
+ if (!rc) {
+ dmb_desc->sba_idx = dmb.sba_idx;
+ dmb_desc->token = dmb.dmb_tok;
+ dmb_desc->cpu_addr = dmb.cpu_addr;
+ dmb_desc->dma_addr = dmb.dma_addr;
+ dmb_desc->len = dmb.dmb_len;
+ }
+ return rc;
+}
+
+struct smc_ism_event_work {
+ struct work_struct work;
+ struct smcd_dev *smcd;
+ struct smcd_event event;
+};
+
+/* worker for SMC-D events */
+static void smc_ism_event_work(struct work_struct *work)
+{
+ struct smc_ism_event_work *wrk =
+ container_of(work, struct smc_ism_event_work, work);
+
+ switch (wrk->event.type) {
+ case ISM_EVENT_GID: /* GID event, token is peer GID */
+ smc_smcd_terminate(wrk->smcd, wrk->event.tok);
+ break;
+ case ISM_EVENT_DMB:
+ break;
+ }
+ kfree(wrk);
+}
+
+static void smcd_release(struct device *dev)
+{
+ struct smcd_dev *smcd = container_of(dev, struct smcd_dev, dev);
+
+ kfree(smcd->conn);
+ kfree(smcd);
+}
+
+struct smcd_dev *smcd_alloc_dev(struct device *parent, const char *name,
+ const struct smcd_ops *ops, int max_dmbs)
+{
+ struct smcd_dev *smcd;
+
+ smcd = kzalloc(sizeof(*smcd), GFP_KERNEL);
+ if (!smcd)
+ return NULL;
+ smcd->conn = kcalloc(max_dmbs, sizeof(struct smc_connection *),
+ GFP_KERNEL);
+ if (!smcd->conn) {
+ kfree(smcd);
+ return NULL;
+ }
+
+ smcd->dev.parent = parent;
+ smcd->dev.release = smcd_release;
+ device_initialize(&smcd->dev);
+ dev_set_name(&smcd->dev, name);
+ smcd->ops = ops;
+ smc_pnetid_by_dev_port(parent, 0, smcd->pnetid);
+
+ spin_lock_init(&smcd->lock);
+ INIT_LIST_HEAD(&smcd->vlan);
+ smcd->event_wq = alloc_ordered_workqueue("ism_evt_wq-%s)",
+ WQ_MEM_RECLAIM, name);
+ return smcd;
+}
+EXPORT_SYMBOL_GPL(smcd_alloc_dev);
+
+int smcd_register_dev(struct smcd_dev *smcd)
+{
+ spin_lock(&smcd_dev_list.lock);
+ list_add_tail(&smcd->list, &smcd_dev_list.list);
+ spin_unlock(&smcd_dev_list.lock);
+
+ return device_add(&smcd->dev);
+}
+EXPORT_SYMBOL_GPL(smcd_register_dev);
+
+void smcd_unregister_dev(struct smcd_dev *smcd)
+{
+ spin_lock(&smcd_dev_list.lock);
+ list_del(&smcd->list);
+ spin_unlock(&smcd_dev_list.lock);
+ flush_workqueue(smcd->event_wq);
+ destroy_workqueue(smcd->event_wq);
+ smc_smcd_terminate(smcd, 0);
+
+ device_del(&smcd->dev);
+}
+EXPORT_SYMBOL_GPL(smcd_unregister_dev);
+
+void smcd_free_dev(struct smcd_dev *smcd)
+{
+ put_device(&smcd->dev);
+}
+EXPORT_SYMBOL_GPL(smcd_free_dev);
+
+/* SMCD Device event handler. Called from ISM device interrupt handler.
+ * Parameters are smcd device pointer,
+ * - event->type (0 --> DMB, 1 --> GID),
+ * - event->code (event code),
+ * - event->tok (either DMB token when event type 0, or GID when event type 1)
+ * - event->time (time of day)
+ * - event->info (debug info).
+ *
+ * Context:
+ * - Function called in IRQ context from ISM device driver event handler.
+ */
+void smcd_handle_event(struct smcd_dev *smcd, struct smcd_event *event)
+{
+ struct smc_ism_event_work *wrk;
+
+ /* copy event to event work queue, and let it be handled there */
+ wrk = kmalloc(sizeof(*wrk), GFP_ATOMIC);
+ if (!wrk)
+ return;
+ INIT_WORK(&wrk->work, smc_ism_event_work);
+ wrk->smcd = smcd;
+ wrk->event = *event;
+ queue_work(smcd->event_wq, &wrk->work);
+}
+EXPORT_SYMBOL_GPL(smcd_handle_event);
+
+/* SMCD Device interrupt handler. Called from ISM device interrupt handler.
+ * Parameters are smcd device pointer and DMB number. Find the connection and
+ * schedule the tasklet for this connection.
+ *
+ * Context:
+ * - Function called in IRQ context from ISM device driver IRQ handler.
+ */
+void smcd_handle_irq(struct smcd_dev *smcd, unsigned int dmbno)
+{
+ struct smc_connection *conn = NULL;
+ unsigned long flags;
+
+ spin_lock_irqsave(&smcd->lock, flags);
+ conn = smcd->conn[dmbno];
+ if (conn)
+ tasklet_schedule(&conn->rx_tsklet);
+ spin_unlock_irqrestore(&smcd->lock, flags);
+}
+EXPORT_SYMBOL_GPL(smcd_handle_irq);
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Shared Memory Communications Direct over ISM devices (SMC-D)
+ *
+ * SMC-D ISM device structure definitions.
+ *
+ * Copyright IBM Corp. 2018
+ */
+
+#ifndef SMCD_ISM_H
+#define SMCD_ISM_H
+
+#include <linux/uio.h>
+
+#include "smc.h"
+
+struct smcd_dev_list { /* List of SMCD devices */
+ struct list_head list;
+ spinlock_t lock; /* Protects list of devices */
+};
+
+extern struct smcd_dev_list smcd_dev_list; /* list of smcd devices */
+
+struct smc_ism_vlanid { /* VLAN id set on ISM device */
+ struct list_head list;
+ unsigned short vlanid; /* Vlan id */
+ refcount_t refcnt; /* Reference count */
+};
+
+struct smc_ism_position { /* ISM device position to write to */
+ u64 token; /* Token of DMB */
+ u32 offset; /* Offset into DMBE */
+ u8 index; /* Index of DMBE */
+ u8 signal; /* Generate interrupt on owner side */
+};
+
+struct smcd_dev;
+
+int smc_ism_cantalk(u64 peer_gid, unsigned short vlan_id, struct smcd_dev *dev);
+void smc_ism_set_conn(struct smc_connection *conn);
+void smc_ism_unset_conn(struct smc_connection *conn);
+int smc_ism_get_vlan(struct smcd_dev *dev, unsigned short vlan_id);
+int smc_ism_put_vlan(struct smcd_dev *dev, unsigned short vlan_id);
+int smc_ism_register_dmb(struct smc_link_group *lgr, int buf_size,
+ struct smc_buf_desc *dmb_desc);
+int smc_ism_unregister_dmb(struct smcd_dev *dev, struct smc_buf_desc *dmb_desc);
+int smc_ism_write(struct smcd_dev *dev, const struct smc_ism_position *pos,
+ void *data, size_t len);
+#endif
#include "smc_pnet.h"
#include "smc_ib.h"
-
-#define SMC_MAX_PNET_ID_LEN 16 /* Max. length of PNET id */
+#include "smc_ism.h"
static struct nla_policy smc_pnet_policy[SMC_PNETID_MAX + 1] = {
[SMC_PNETID_NAME] = {
.type = NLA_NUL_STRING,
- .len = SMC_MAX_PNET_ID_LEN - 1
+ .len = SMC_MAX_PNETID_LEN - 1
},
[SMC_PNETID_ETHNAME] = {
.type = NLA_NUL_STRING,
*/
struct smc_pnetentry {
struct list_head list;
- char pnet_name[SMC_MAX_PNET_ID_LEN + 1];
+ char pnet_name[SMC_MAX_PNETID_LEN + 1];
struct net_device *ndev;
struct smc_ib_device *smcibdev;
u8 ib_port;
return false;
while (--end >= bf && isspace(*end))
;
- if (end - bf >= SMC_MAX_PNET_ID_LEN)
+ if (end - bf >= SMC_MAX_PNETID_LEN)
return false;
while (bf <= end) {
if (!isalnum(*bf))
kfree(pnetelem);
return rc;
}
- rc = smc_ib_remember_port_attr(pnetelem->smcibdev, pnetelem->ib_port);
- if (rc)
- smc_pnet_remove_by_pnetid(pnetelem->pnet_name);
return rc;
}
case NETDEV_REBOOT:
case NETDEV_UNREGISTER:
smc_pnet_remove_by_ndev(event_dev);
+ return NOTIFY_OK;
default:
- break;
+ return NOTIFY_DONE;
}
- return NOTIFY_DONE;
}
static struct notifier_block smc_netdev_notifier = {
genl_unregister_family(&smc_pnet_nl_family);
}
-/* PNET table analysis for a given sock:
- * determine ib_device and port belonging to used internal TCP socket
- * ethernet interface.
+/* Determine one base device for stacked net devices.
+ * If the lower device level contains more than one devices
+ * (for instance with bonding slaves), just the first device
+ * is used to reach a base device.
*/
-void smc_pnet_find_roce_resource(struct sock *sk,
- struct smc_ib_device **smcibdev, u8 *ibport)
+static struct net_device *pnet_find_base_ndev(struct net_device *ndev)
{
- struct dst_entry *dst = sk_dst_get(sk);
- struct smc_pnetentry *pnetelem;
+ int i, nest_lvl;
- *smcibdev = NULL;
- *ibport = 0;
+ rtnl_lock();
+ nest_lvl = dev_get_nest_level(ndev);
+ for (i = 0; i < nest_lvl; i++) {
+ struct list_head *lower = &ndev->adj_list.lower;
+
+ if (list_empty(lower))
+ break;
+ lower = lower->next;
+ ndev = netdev_lower_get_next(ndev, &lower);
+ }
+ rtnl_unlock();
+ return ndev;
+}
+
+/* Determine the corresponding IB device port based on the hardware PNETID.
+ * Searching stops at the first matching active IB device port.
+ */
+static void smc_pnet_find_roce_by_pnetid(struct net_device *ndev,
+ struct smc_ib_device **smcibdev,
+ u8 *ibport)
+{
+ u8 ndev_pnetid[SMC_MAX_PNETID_LEN];
+ struct smc_ib_device *ibdev;
+ int i;
+
+ ndev = pnet_find_base_ndev(ndev);
+ if (smc_pnetid_by_dev_port(ndev->dev.parent, ndev->dev_port,
+ ndev_pnetid))
+ return; /* pnetid could not be determined */
+
+ spin_lock(&smc_ib_devices.lock);
+ list_for_each_entry(ibdev, &smc_ib_devices.list, list) {
+ for (i = 1; i <= SMC_MAX_PORTS; i++) {
+ if (!memcmp(ibdev->pnetid[i - 1], ndev_pnetid,
+ SMC_MAX_PNETID_LEN) &&
+ smc_ib_port_active(ibdev, i)) {
+ *smcibdev = ibdev;
+ *ibport = i;
+ break;
+ }
+ }
+ }
+ spin_unlock(&smc_ib_devices.lock);
+}
+
+static void smc_pnet_find_ism_by_pnetid(struct net_device *ndev,
+ struct smcd_dev **smcismdev)
+{
+ u8 ndev_pnetid[SMC_MAX_PNETID_LEN];
+ struct smcd_dev *ismdev;
+
+ ndev = pnet_find_base_ndev(ndev);
+ if (smc_pnetid_by_dev_port(ndev->dev.parent, ndev->dev_port,
+ ndev_pnetid))
+ return; /* pnetid could not be determined */
+
+ spin_lock(&smcd_dev_list.lock);
+ list_for_each_entry(ismdev, &smcd_dev_list.list, list) {
+ if (!memcmp(ismdev->pnetid, ndev_pnetid, SMC_MAX_PNETID_LEN)) {
+ *smcismdev = ismdev;
+ break;
+ }
+ }
+ spin_unlock(&smcd_dev_list.lock);
+}
+
+/* Lookup of coupled ib_device via SMC pnet table */
+static void smc_pnet_find_roce_by_table(struct net_device *netdev,
+ struct smc_ib_device **smcibdev,
+ u8 *ibport)
+{
+ struct smc_pnetentry *pnetelem;
- if (!dst)
- return;
- if (!dst->dev)
- goto out_rel;
read_lock(&smc_pnettable.lock);
list_for_each_entry(pnetelem, &smc_pnettable.pnetlist, list) {
- if (dst->dev == pnetelem->ndev) {
+ if (netdev == pnetelem->ndev) {
if (smc_ib_port_active(pnetelem->smcibdev,
pnetelem->ib_port)) {
*smcibdev = pnetelem->smcibdev;
}
}
read_unlock(&smc_pnettable.lock);
+}
+
+/* PNET table analysis for a given sock:
+ * determine ib_device and port belonging to used internal TCP socket
+ * ethernet interface.
+ */
+void smc_pnet_find_roce_resource(struct sock *sk,
+ struct smc_ib_device **smcibdev, u8 *ibport)
+{
+ struct dst_entry *dst = sk_dst_get(sk);
+
+ *smcibdev = NULL;
+ *ibport = 0;
+
+ if (!dst)
+ goto out;
+ if (!dst->dev)
+ goto out_rel;
+
+ /* if possible, lookup via hardware-defined pnetid */
+ smc_pnet_find_roce_by_pnetid(dst->dev, smcibdev, ibport);
+ if (*smcibdev)
+ goto out_rel;
+
+ /* lookup via SMC PNET table */
+ smc_pnet_find_roce_by_table(dst->dev, smcibdev, ibport);
+
+out_rel:
+ dst_release(dst);
+out:
+ return;
+}
+
+void smc_pnet_find_ism_resource(struct sock *sk, struct smcd_dev **smcismdev)
+{
+ struct dst_entry *dst = sk_dst_get(sk);
+
+ *smcismdev = NULL;
+ if (!dst)
+ goto out;
+ if (!dst->dev)
+ goto out_rel;
+
+ /* if possible, lookup via hardware-defined pnetid */
+ smc_pnet_find_ism_by_pnetid(dst->dev, smcismdev);
+
out_rel:
dst_release(dst);
+out:
+ return;
}
#ifndef _SMC_PNET_H
#define _SMC_PNET_H
+#if IS_ENABLED(CONFIG_HAVE_PNETID)
+#include <asm/pnet.h>
+#endif
+
struct smc_ib_device;
+struct smcd_dev;
+
+static inline int smc_pnetid_by_dev_port(struct device *dev,
+ unsigned short port, u8 *pnetid)
+{
+#if IS_ENABLED(CONFIG_HAVE_PNETID)
+ return pnet_id_by_dev_port(dev, port, pnetid);
+#else
+ return -ENOENT;
+#endif
+}
int smc_pnet_init(void) __init;
void smc_pnet_exit(void);
int smc_pnet_remove_by_ibdev(struct smc_ib_device *ibdev);
void smc_pnet_find_roce_resource(struct sock *sk,
struct smc_ib_device **smcibdev, u8 *ibport);
+void smc_pnet_find_ism_resource(struct sock *sk, struct smcd_dev **smcismdev);
#endif
target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);
/* we currently use 1 RMBE per RMB, so RMBE == RMB base addr */
- rcvbuf_base = conn->rmb_desc->cpu_addr;
+ rcvbuf_base = conn->rx_off + conn->rmb_desc->cpu_addr;
do { /* while (read_remaining) */
if (read_done >= target || (pipe && read_done))
#include "smc.h"
#include "smc_wr.h"
#include "smc_cdc.h"
+#include "smc_ism.h"
#include "smc_tx.h"
#define SMC_TX_WORK_DELAY HZ
/***************************** sndbuf consumer *******************************/
+/* sndbuf consumer: actual data transfer of one target chunk with ISM write */
+int smcd_tx_ism_write(struct smc_connection *conn, void *data, size_t len,
+ u32 offset, int signal)
+{
+ struct smc_ism_position pos;
+ int rc;
+
+ memset(&pos, 0, sizeof(pos));
+ pos.token = conn->peer_token;
+ pos.index = conn->peer_rmbe_idx;
+ pos.offset = conn->tx_off + offset;
+ pos.signal = signal;
+ rc = smc_ism_write(conn->lgr->smcd, &pos, data, len);
+ if (rc)
+ conn->local_tx_ctrl.conn_state_flags.peer_conn_abort = 1;
+ return rc;
+}
+
/* sndbuf consumer: actual data transfer of one target chunk with RDMA write */
static int smc_tx_rdma_write(struct smc_connection *conn, int peer_rmbe_offset,
int num_sges, struct ib_sge sges[])
smc_curs_add(conn->sndbuf_desc->len, sent, len);
}
+/* SMC-R helper for smc_tx_rdma_writes() */
+static int smcr_tx_rdma_writes(struct smc_connection *conn, size_t len,
+ size_t src_off, size_t src_len,
+ size_t dst_off, size_t dst_len)
+{
+ dma_addr_t dma_addr =
+ sg_dma_address(conn->sndbuf_desc->sgt[SMC_SINGLE_LINK].sgl);
+ struct smc_link *link = &conn->lgr->lnk[SMC_SINGLE_LINK];
+ int src_len_sum = src_len, dst_len_sum = dst_len;
+ struct ib_sge sges[SMC_IB_MAX_SEND_SGE];
+ int sent_count = src_off;
+ int srcchunk, dstchunk;
+ int num_sges;
+ int rc;
+
+ for (dstchunk = 0; dstchunk < 2; dstchunk++) {
+ num_sges = 0;
+ for (srcchunk = 0; srcchunk < 2; srcchunk++) {
+ sges[srcchunk].addr = dma_addr + src_off;
+ sges[srcchunk].length = src_len;
+ sges[srcchunk].lkey = link->roce_pd->local_dma_lkey;
+ num_sges++;
+
+ src_off += src_len;
+ if (src_off >= conn->sndbuf_desc->len)
+ src_off -= conn->sndbuf_desc->len;
+ /* modulo in send ring */
+ if (src_len_sum == dst_len)
+ break; /* either on 1st or 2nd iteration */
+ /* prepare next (== 2nd) iteration */
+ src_len = dst_len - src_len; /* remainder */
+ src_len_sum += src_len;
+ }
+ rc = smc_tx_rdma_write(conn, dst_off, num_sges, sges);
+ if (rc)
+ return rc;
+ if (dst_len_sum == len)
+ break; /* either on 1st or 2nd iteration */
+ /* prepare next (== 2nd) iteration */
+ dst_off = 0; /* modulo offset in RMBE ring buffer */
+ dst_len = len - dst_len; /* remainder */
+ dst_len_sum += dst_len;
+ src_len = min_t(int, dst_len, conn->sndbuf_desc->len -
+ sent_count);
+ src_len_sum = src_len;
+ }
+ return 0;
+}
+
+/* SMC-D helper for smc_tx_rdma_writes() */
+static int smcd_tx_rdma_writes(struct smc_connection *conn, size_t len,
+ size_t src_off, size_t src_len,
+ size_t dst_off, size_t dst_len)
+{
+ int src_len_sum = src_len, dst_len_sum = dst_len;
+ int srcchunk, dstchunk;
+ int rc;
+
+ for (dstchunk = 0; dstchunk < 2; dstchunk++) {
+ for (srcchunk = 0; srcchunk < 2; srcchunk++) {
+ void *data = conn->sndbuf_desc->cpu_addr + src_off;
+
+ rc = smcd_tx_ism_write(conn, data, src_len, dst_off +
+ sizeof(struct smcd_cdc_msg), 0);
+ if (rc)
+ return rc;
+ dst_off += src_len;
+ src_off += src_len;
+ if (src_off >= conn->sndbuf_desc->len)
+ src_off -= conn->sndbuf_desc->len;
+ /* modulo in send ring */
+ if (src_len_sum == dst_len)
+ break; /* either on 1st or 2nd iteration */
+ /* prepare next (== 2nd) iteration */
+ src_len = dst_len - src_len; /* remainder */
+ src_len_sum += src_len;
+ }
+ if (dst_len_sum == len)
+ break; /* either on 1st or 2nd iteration */
+ /* prepare next (== 2nd) iteration */
+ dst_off = 0; /* modulo offset in RMBE ring buffer */
+ dst_len = len - dst_len; /* remainder */
+ dst_len_sum += dst_len;
+ src_len = min_t(int, dst_len, conn->sndbuf_desc->len - src_off);
+ src_len_sum = src_len;
+ }
+ return 0;
+}
+
/* sndbuf consumer: prepare all necessary (src&dst) chunks of data transmit;
* usable snd_wnd as max transmit
*/
static int smc_tx_rdma_writes(struct smc_connection *conn)
{
- size_t src_off, src_len, dst_off, dst_len; /* current chunk values */
- size_t len, dst_len_sum, src_len_sum, dstchunk, srcchunk;
+ size_t len, src_len, dst_off, dst_len; /* current chunk values */
union smc_host_cursor sent, prep, prod, cons;
- struct ib_sge sges[SMC_IB_MAX_SEND_SGE];
- struct smc_link_group *lgr = conn->lgr;
struct smc_cdc_producer_flags *pflags;
int to_send, rmbespace;
- struct smc_link *link;
- dma_addr_t dma_addr;
- int num_sges;
int rc;
/* source: sndbuf */
len = min(to_send, rmbespace);
/* initialize variables for first iteration of subsequent nested loop */
- link = &lgr->lnk[SMC_SINGLE_LINK];
dst_off = prod.count;
if (prod.wrap == cons.wrap) {
/* the filled destination area is unwrapped,
*/
dst_len = len;
}
- dst_len_sum = dst_len;
- src_off = sent.count;
/* dst_len determines the maximum src_len */
if (sent.count + dst_len <= conn->sndbuf_desc->len) {
/* unwrapped src case: single chunk of entire dst_len */
/* wrapped src case: 2 chunks of sum dst_len; start with 1st: */
src_len = conn->sndbuf_desc->len - sent.count;
}
- src_len_sum = src_len;
- dma_addr = sg_dma_address(conn->sndbuf_desc->sgt[SMC_SINGLE_LINK].sgl);
- for (dstchunk = 0; dstchunk < 2; dstchunk++) {
- num_sges = 0;
- for (srcchunk = 0; srcchunk < 2; srcchunk++) {
- sges[srcchunk].addr = dma_addr + src_off;
- sges[srcchunk].length = src_len;
- sges[srcchunk].lkey = link->roce_pd->local_dma_lkey;
- num_sges++;
- src_off += src_len;
- if (src_off >= conn->sndbuf_desc->len)
- src_off -= conn->sndbuf_desc->len;
- /* modulo in send ring */
- if (src_len_sum == dst_len)
- break; /* either on 1st or 2nd iteration */
- /* prepare next (== 2nd) iteration */
- src_len = dst_len - src_len; /* remainder */
- src_len_sum += src_len;
- }
- rc = smc_tx_rdma_write(conn, dst_off, num_sges, sges);
- if (rc)
- return rc;
- if (dst_len_sum == len)
- break; /* either on 1st or 2nd iteration */
- /* prepare next (== 2nd) iteration */
- dst_off = 0; /* modulo offset in RMBE ring buffer */
- dst_len = len - dst_len; /* remainder */
- dst_len_sum += dst_len;
- src_len = min_t(int,
- dst_len, conn->sndbuf_desc->len - sent.count);
- src_len_sum = src_len;
- }
+
+ if (conn->lgr->is_smcd)
+ rc = smcd_tx_rdma_writes(conn, len, sent.count, src_len,
+ dst_off, dst_len);
+ else
+ rc = smcr_tx_rdma_writes(conn, len, sent.count, src_len,
+ dst_off, dst_len);
+ if (rc)
+ return rc;
if (conn->urg_tx_pend && len == to_send)
pflags->urg_data_present = 1;
/* Wakeup sndbuf consumers from any context (IRQ or process)
* since there is more data to transmit; usable snd_wnd as max transmit
*/
-int smc_tx_sndbuf_nonempty(struct smc_connection *conn)
+static int smcr_tx_sndbuf_nonempty(struct smc_connection *conn)
{
struct smc_cdc_producer_flags *pflags;
struct smc_cdc_tx_pend *pend;
return rc;
}
+static int smcd_tx_sndbuf_nonempty(struct smc_connection *conn)
+{
+ struct smc_cdc_producer_flags *pflags = &conn->local_tx_ctrl.prod_flags;
+ int rc = 0;
+
+ spin_lock_bh(&conn->send_lock);
+ if (!pflags->urg_data_present)
+ rc = smc_tx_rdma_writes(conn);
+ if (!rc)
+ rc = smcd_cdc_msg_send(conn);
+
+ if (!rc && pflags->urg_data_present) {
+ pflags->urg_data_pending = 0;
+ pflags->urg_data_present = 0;
+ }
+ spin_unlock_bh(&conn->send_lock);
+ return rc;
+}
+
+int smc_tx_sndbuf_nonempty(struct smc_connection *conn)
+{
+ int rc;
+
+ if (conn->lgr->is_smcd)
+ rc = smcd_tx_sndbuf_nonempty(conn);
+ else
+ rc = smcr_tx_sndbuf_nonempty(conn);
+
+ return rc;
+}
+
/* Wakeup sndbuf consumers from process context
* since there is more data to transmit
*/
void smc_tx_consumer_update(struct smc_connection *conn, bool force)
{
- union smc_host_cursor cfed, cons;
+ union smc_host_cursor cfed, cons, prod;
+ int sender_free = conn->rmb_desc->len;
int to_confirm;
smc_curs_write(&cons,
smc_curs_read(&conn->rx_curs_confirmed, conn),
conn);
to_confirm = smc_curs_diff(conn->rmb_desc->len, &cfed, &cons);
+ if (to_confirm > conn->rmbe_update_limit) {
+ smc_curs_write(&prod,
+ smc_curs_read(&conn->local_rx_ctrl.prod, conn),
+ conn);
+ sender_free = conn->rmb_desc->len -
+ smc_curs_diff(conn->rmb_desc->len, &prod, &cfed);
+ }
if (conn->local_rx_ctrl.prod_flags.cons_curs_upd_req ||
force ||
((to_confirm > conn->rmbe_update_limit) &&
- ((to_confirm > (conn->rmb_desc->len / 2)) ||
+ ((sender_free <= (conn->rmb_desc->len / 2)) ||
conn->local_rx_ctrl.prod_flags.write_blocked))) {
if ((smc_cdc_get_slot_and_msg_send(conn) < 0) &&
conn->alert_token_local) { /* connection healthy */
int smc_tx_sndbuf_nonempty(struct smc_connection *conn);
void smc_tx_sndbuf_nonfull(struct smc_sock *smc);
void smc_tx_consumer_update(struct smc_connection *conn, bool force);
+int smcd_tx_ism_write(struct smc_connection *conn, void *data, size_t len,
+ u32 offset, int signal);
#endif /* SMC_TX_H */
static int sock_mmap(struct file *file, struct vm_area_struct *vma);
static int sock_close(struct inode *inode, struct file *file);
-static struct wait_queue_head *sock_get_poll_head(struct file *file,
- __poll_t events);
-static __poll_t sock_poll_mask(struct file *file, __poll_t);
-static __poll_t sock_poll(struct file *file, struct poll_table_struct *wait);
+static __poll_t sock_poll(struct file *file,
+ struct poll_table_struct *wait);
static long sock_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
#ifdef CONFIG_COMPAT
static long compat_sock_ioctl(struct file *file,
.llseek = no_llseek,
.read_iter = sock_read_iter,
.write_iter = sock_write_iter,
- .get_poll_head = sock_get_poll_head,
- .poll_mask = sock_poll_mask,
.poll = sock_poll,
.unlocked_ioctl = sock_ioctl,
#ifdef CONFIG_COMPAT
}
EXPORT_SYMBOL(sock_create_lite);
-static struct wait_queue_head *sock_get_poll_head(struct file *file,
- __poll_t events)
-{
- struct socket *sock = file->private_data;
-
- if (!sock->ops->poll_mask)
- return NULL;
- sock_poll_busy_loop(sock, events);
- return sk_sleep(sock->sk);
-}
-
-static __poll_t sock_poll_mask(struct file *file, __poll_t events)
-{
- struct socket *sock = file->private_data;
-
- /*
- * We need to be sure we are in sync with the socket flags modification.
- *
- * This memory barrier is paired in the wq_has_sleeper.
- */
- smp_mb();
-
- /* this socket can poll_ll so tell the system call */
- return sock->ops->poll_mask(sock, events) |
- (sk_can_busy_loop(sock->sk) ? POLL_BUSY_LOOP : 0);
-}
-
/* No kernel lock held - perfect */
static __poll_t sock_poll(struct file *file, poll_table *wait)
{
struct socket *sock = file->private_data;
- __poll_t events = poll_requested_events(wait), mask = 0;
-
- if (sock->ops->poll) {
- sock_poll_busy_loop(sock, events);
- mask = sock->ops->poll(file, sock, wait);
- } else if (sock->ops->poll_mask) {
- sock_poll_wait(file, sock_get_poll_head(file, events), wait);
- mask = sock->ops->poll_mask(sock, events);
- }
+ __poll_t events = poll_requested_events(wait);
- return mask | sock_poll_busy_flag(sock);
+ sock_poll_busy_loop(sock, events);
+ if (!sock->ops->poll)
+ return 0;
+ return sock->ops->poll(file, sock, wait) | sock_poll_busy_flag(sock);
}
static int sock_mmap(struct file *file, struct vm_area_struct *vma)
*/
struct strp_msg strp;
int accum_len;
- int early_eaten;
};
static inline struct _strp_msg *_strp_msg(struct sk_buff *skb)
head = strp->skb_head;
if (head) {
/* Message already in progress */
-
- stm = _strp_msg(head);
- if (unlikely(stm->early_eaten)) {
- /* Already some number of bytes on the receive sock
- * data saved in skb_head, just indicate they
- * are consumed.
- */
- eaten = orig_len <= stm->early_eaten ?
- orig_len : stm->early_eaten;
- stm->early_eaten -= eaten;
-
- return eaten;
- }
-
if (unlikely(orig_offset)) {
/* Getting data with a non-zero offset when a message is
* in progress is not expected. If it does happen, we
/* We are going to append to the frags_list of head.
* Need to unshare the frag_list.
*/
- err = skb_unclone(head, GFP_ATOMIC);
- if (err) {
- STRP_STATS_INCR(strp->stats.mem_fail);
- desc->error = err;
- return 0;
+ if (skb_has_frag_list(head)) {
+ err = skb_unclone(head, GFP_ATOMIC);
+ if (err) {
+ STRP_STATS_INCR(strp->stats.mem_fail);
+ desc->error = err;
+ return 0;
+ }
}
if (unlikely(skb_shinfo(head)->frag_list)) {
memset(stm, 0, sizeof(*stm));
stm->strp.offset = orig_offset + eaten;
} else {
- /* Unclone since we may be appending to an skb that we
+ /* Unclone if we are appending to an skb that we
* already share a frag_list with.
*/
- err = skb_unclone(skb, GFP_ATOMIC);
- if (err) {
- STRP_STATS_INCR(strp->stats.mem_fail);
- desc->error = err;
- break;
+ if (skb_has_frag_list(skb)) {
+ err = skb_unclone(skb, GFP_ATOMIC);
+ if (err) {
+ STRP_STATS_INCR(strp->stats.mem_fail);
+ desc->error = err;
+ break;
+ }
}
stm = _strp_msg(head);
}
stm->accum_len += cand_len;
+ eaten += cand_len;
strp->need_bytes = stm->strp.full_len -
stm->accum_len;
- stm->early_eaten = cand_len;
STRP_STATS_ADD(strp->stats.bytes, cand_len);
desc->count = 0; /* Stop reading socket */
break;
/* Lower sock lock held */
void strp_data_ready(struct strparser *strp)
{
- if (unlikely(strp->stopped))
+ if (unlikely(strp->stopped) || strp->paused)
return;
/* This check is needed to synchronize with do_strp_work.
return;
}
- if (strp->paused)
- return;
-
if (strp->need_bytes) {
if (strp_peek_len(strp) < strp->need_bytes)
return;
task->tk_status = -EAGAIN;
goto out_unlock;
}
- if (!bc_prealloc(req) && !req->rq_xmit_bytes_sent)
- req->rq_xid = xprt_alloc_xid(xprt);
ret = true;
out_unlock:
spin_unlock_bh(&xprt->transport_lock);
static inline __be32 xprt_alloc_xid(struct rpc_xprt *xprt)
{
- return (__force __be32)xprt->xid++;
+ __be32 xid;
+
+ spin_lock(&xprt->reserve_lock);
+ xid = (__force __be32)xprt->xid++;
+ spin_unlock(&xprt->reserve_lock);
+ return xid;
}
static inline void xprt_init_xid(struct rpc_xprt *xprt)
req->rq_task = task;
req->rq_xprt = xprt;
req->rq_buffer = NULL;
+ req->rq_xid = xprt_alloc_xid(xprt);
req->rq_connect_cookie = xprt->connect_cookie - 1;
req->rq_bytes_sent = 0;
req->rq_snd_buf.len = 0;
case NETDEV_CHANGE:
if (netif_carrier_ok(dev))
break;
+ /* else: fall through */
case NETDEV_UP:
test_and_set_bit_lock(0, &b->up);
break;
}
*sk_rcvbuf = tipc_group_rcvbuf_limit(grp);
}
+
+int tipc_group_fill_sock_diag(struct tipc_group *grp, struct sk_buff *skb)
+{
+ struct nlattr *group = nla_nest_start(skb, TIPC_NLA_SOCK_GROUP);
+
+ if (nla_put_u32(skb, TIPC_NLA_SOCK_GROUP_ID,
+ grp->type) ||
+ nla_put_u32(skb, TIPC_NLA_SOCK_GROUP_INSTANCE,
+ grp->instance) ||
+ nla_put_u32(skb, TIPC_NLA_SOCK_GROUP_BC_SEND_NEXT,
+ grp->bc_snd_nxt))
+ goto group_msg_cancel;
+
+ if (grp->scope == TIPC_NODE_SCOPE)
+ if (nla_put_flag(skb, TIPC_NLA_SOCK_GROUP_NODE_SCOPE))
+ goto group_msg_cancel;
+
+ if (grp->scope == TIPC_CLUSTER_SCOPE)
+ if (nla_put_flag(skb, TIPC_NLA_SOCK_GROUP_CLUSTER_SCOPE))
+ goto group_msg_cancel;
+
+ if (*grp->open)
+ if (nla_put_flag(skb, TIPC_NLA_SOCK_GROUP_OPEN))
+ goto group_msg_cancel;
+
+ nla_nest_end(skb, group);
+ return 0;
+
+group_msg_cancel:
+ nla_nest_cancel(skb, group);
+ return -1;
+}
u32 port, struct sk_buff_head *xmitq);
u16 tipc_group_bc_snd_nxt(struct tipc_group *grp);
void tipc_group_update_member(struct tipc_member *m, int len);
+int tipc_group_fill_sock_diag(struct tipc_group *grp, struct sk_buff *skb);
#endif
* @backlogq: queue for messages waiting to be sent
* @snt_nxt: next sequence number to use for outbound messages
* @last_retransmitted: sequence number of most recently retransmitted message
- * @stale_count: # of identical retransmit requests made by peer
+ * @stale_cnt: counter for number of identical retransmit attempts
+ * @stale_limit: time when repeated identical retransmits must force link reset
* @ackers: # of peers that needs to ack each packet before it can be released
* @acked: # last packet acked by a certain peer. Used for broadcast.
* @rcv_nxt: next sequence number to expect for inbound messages
struct net *net;
/* Management and link supervision data */
- u32 peer_session;
- u32 session;
+ u16 peer_session;
+ u16 session;
+ u16 snd_nxt_state;
+ u16 rcv_nxt_state;
u32 peer_bearer_id;
u32 bearer_id;
u32 tolerance;
u32 abort_limit;
u32 state;
u16 peer_caps;
+ bool in_session;
bool active;
u32 silent_intv_cnt;
char if_name[TIPC_MAX_IF_NAME];
u16 snd_nxt;
u16 last_retransm;
u16 window;
- u32 stale_count;
+ u16 stale_cnt;
+ unsigned long stale_limit;
/* Reception */
u16 rcv_nxt;
*/
#define TIPC_NACK_INTV (TIPC_MIN_LINK_WIN * 2)
-/* Wildcard value for link session numbers. When it is known that
- * peer endpoint is down, any session number must be accepted.
- */
-#define ANY_SESSION 0x10000
-
/* Link FSM states:
*/
enum {
return l->net_plane;
}
+void tipc_link_update_caps(struct tipc_link *l, u16 capabilities)
+{
+ l->peer_caps = capabilities;
+}
+
void tipc_link_add_bc_peer(struct tipc_link *snd_l,
struct tipc_link *uc_l,
struct sk_buff_head *xmitq)
l->addr = peer;
l->peer_caps = peer_caps;
l->net = net;
- l->peer_session = ANY_SESSION;
+ l->in_session = false;
l->bearer_id = bearer_id;
l->tolerance = tolerance;
l->net_plane = net_plane;
void tipc_link_reset(struct tipc_link *l)
{
- l->peer_session = ANY_SESSION;
+ l->in_session = false;
l->session++;
l->mtu = l->advertised_mtu;
__skb_queue_purge(&l->transmq);
l->rcv_unacked = 0;
l->snd_nxt = 1;
l->rcv_nxt = 1;
+ l->snd_nxt_state = 1;
+ l->rcv_nxt_state = 1;
l->acked = 0;
l->silent_intv_cnt = 0;
l->rst_cnt = 0;
- l->stale_count = 0;
+ l->stale_cnt = 0;
l->bc_peer_is_up = false;
memset(&l->mon_state, 0, sizeof(l->mon_state));
tipc_link_reset_stats(l);
msg_seqno(hdr), msg_prevnode(hdr), msg_orignode(hdr));
}
-int tipc_link_retrans(struct tipc_link *l, struct tipc_link *nacker,
+/* tipc_link_retrans() - retransmit one or more packets
+ * @l: the link to transmit on
+ * @r: the receiving link ordering the retransmit. Same as l if unicast
+ * @from: retransmit from (inclusive) this sequence number
+ * @to: retransmit to (inclusive) this sequence number
+ * xmitq: queue for accumulating the retransmitted packets
+ */
+int tipc_link_retrans(struct tipc_link *l, struct tipc_link *r,
u16 from, u16 to, struct sk_buff_head *xmitq)
{
struct sk_buff *_skb, *skb = skb_peek(&l->transmq);
- struct tipc_msg *hdr;
- u16 ack = l->rcv_nxt - 1;
u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1;
+ u16 ack = l->rcv_nxt - 1;
+ struct tipc_msg *hdr;
if (!skb)
return 0;
/* Detect repeated retransmit failures on same packet */
- if (nacker->last_retransm != buf_seqno(skb)) {
- nacker->last_retransm = buf_seqno(skb);
- nacker->stale_count = 1;
- } else if (++nacker->stale_count > 100) {
+ if (r->last_retransm != buf_seqno(skb)) {
+ r->last_retransm = buf_seqno(skb);
+ r->stale_limit = jiffies + msecs_to_jiffies(l->tolerance);
+ } else if (++r->stale_cnt > 99 && time_after(jiffies, r->stale_limit)) {
link_retransmit_failure(l, skb);
- nacker->stale_count = 0;
if (link_is_bc_sndlink(l))
return TIPC_LINK_DOWN_EVT;
return tipc_link_fsm_evt(l, LINK_FAILURE_EVT);
}
- /* Move forward to where retransmission should start */
skb_queue_walk(&l->transmq, skb) {
- if (!less(buf_seqno(skb), from))
- break;
- }
-
- skb_queue_walk_from(&l->transmq, skb) {
- if (more(buf_seqno(skb), to))
- break;
hdr = buf_msg(skb);
+ if (less(msg_seqno(hdr), from))
+ continue;
+ if (more(msg_seqno(hdr), to))
+ break;
_skb = __pskb_copy(skb, MIN_H_SIZE, GFP_ATOMIC);
if (!_skb)
return 0;
skb_queue_tail(mc_inputq, skb);
return true;
}
+ /* else: fall through */
case CONN_MANAGER:
skb_queue_tail(inputq, skb);
return true;
/* Forward queues and wake up waiting users */
if (likely(tipc_link_release_pkts(l, msg_ack(hdr)))) {
+ l->stale_cnt = 0;
tipc_link_advance_backlog(l, xmitq);
if (unlikely(!skb_queue_empty(&l->wakeupq)))
link_prepare_wakeup(l);
msg_set_seqno(hdr, l->snd_nxt + U16_MAX / 2);
if (mtyp == STATE_MSG) {
+ if (l->peer_caps & TIPC_LINK_PROTO_SEQNO)
+ msg_set_seqno(hdr, l->snd_nxt_state++);
msg_set_seq_gap(hdr, rcvgap);
msg_set_bc_gap(hdr, link_bc_rcv_gap(bcl));
msg_set_probe(hdr, probe);
}
}
+/* tipc_link_validate_msg(): validate message against current link state
+ * Returns true if message should be accepted, otherwise false
+ */
+bool tipc_link_validate_msg(struct tipc_link *l, struct tipc_msg *hdr)
+{
+ u16 curr_session = l->peer_session;
+ u16 session = msg_session(hdr);
+ int mtyp = msg_type(hdr);
+
+ if (msg_user(hdr) != LINK_PROTOCOL)
+ return true;
+
+ switch (mtyp) {
+ case RESET_MSG:
+ if (!l->in_session)
+ return true;
+ /* Accept only RESET with new session number */
+ return more(session, curr_session);
+ case ACTIVATE_MSG:
+ if (!l->in_session)
+ return true;
+ /* Accept only ACTIVATE with new or current session number */
+ return !less(session, curr_session);
+ case STATE_MSG:
+ /* Accept only STATE with current session number */
+ if (!l->in_session)
+ return false;
+ if (session != curr_session)
+ return false;
+ if (!(l->peer_caps & TIPC_LINK_PROTO_SEQNO))
+ return true;
+ /* Accept only STATE with new sequence number */
+ return !less(msg_seqno(hdr), l->rcv_nxt_state);
+ default:
+ return false;
+ }
+}
+
/* tipc_link_proto_rcv(): receive link level protocol message :
* Note that network plane id propagates through the network, and may
* change at any time. The node with lowest numerical id determines
hdr = buf_msg(skb);
data = msg_data(hdr);
+ if (!tipc_link_validate_msg(l, hdr))
+ goto exit;
+
switch (mtyp) {
case RESET_MSG:
-
- /* Ignore duplicate RESET with old session number */
- if ((less_eq(msg_session(hdr), l->peer_session)) &&
- (l->peer_session != ANY_SESSION))
- break;
- /* fall thru' */
-
case ACTIVATE_MSG:
-
/* Complete own link name with peer's interface name */
if_name = strrchr(l->name, ':') + 1;
if (sizeof(l->name) - (if_name - l->name) <= TIPC_MAX_IF_NAME)
rc = TIPC_LINK_UP_EVT;
l->peer_session = msg_session(hdr);
+ l->in_session = true;
l->peer_bearer_id = msg_bearer_id(hdr);
if (l->mtu > msg_max_pkt(hdr))
l->mtu = msg_max_pkt(hdr);
break;
case STATE_MSG:
+ l->rcv_nxt_state = msg_seqno(hdr) + 1;
/* Update own tolerance if peer indicates a non-zero value */
if (in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL))
char tipc_link_plane(struct tipc_link *l);
int tipc_link_prio(struct tipc_link *l);
int tipc_link_window(struct tipc_link *l);
+void tipc_link_update_caps(struct tipc_link *l, u16 capabilities);
+bool tipc_link_validate_msg(struct tipc_link *l, struct tipc_msg *hdr);
unsigned long tipc_link_tolerance(struct tipc_link *l);
void tipc_link_set_tolerance(struct tipc_link *l, u32 tol,
struct sk_buff_head *xmitq);
*/
bool tipc_msg_extract(struct sk_buff *skb, struct sk_buff **iskb, int *pos)
{
- struct tipc_msg *msg;
- int imsz, offset;
+ struct tipc_msg *hdr, *ihdr;
+ int imsz;
*iskb = NULL;
if (unlikely(skb_linearize(skb)))
goto none;
- msg = buf_msg(skb);
- offset = msg_hdr_sz(msg) + *pos;
- if (unlikely(offset > (msg_size(msg) - MIN_H_SIZE)))
+ hdr = buf_msg(skb);
+ if (unlikely(*pos > (msg_data_sz(hdr) - MIN_H_SIZE)))
goto none;
- *iskb = skb_clone(skb, GFP_ATOMIC);
- if (unlikely(!*iskb))
+ ihdr = (struct tipc_msg *)(msg_data(hdr) + *pos);
+ imsz = msg_size(ihdr);
+
+ if ((*pos + imsz) > msg_data_sz(hdr))
goto none;
- skb_pull(*iskb, offset);
- imsz = msg_size(buf_msg(*iskb));
- skb_trim(*iskb, imsz);
+
+ *iskb = tipc_buf_acquire(imsz, GFP_ATOMIC);
+ if (!*iskb)
+ goto none;
+
+ skb_copy_to_linear_data(*iskb, ihdr, imsz);
if (unlikely(!tipc_msg_validate(iskb)))
goto none;
+
*pos += align(imsz);
return true;
none:
msg_set_hdr_sz(hdr, BASIC_H_SIZE);
}
- if (skb_cloned(_skb) &&
- pskb_expand_head(_skb, BUF_HEADROOM, BUF_TAILROOM, GFP_ATOMIC))
- goto exit;
-
- /* reassign after skb header modifications */
- hdr = buf_msg(_skb);
/* Now reverse the concerned fields */
msg_set_errcode(hdr, err);
msg_set_non_seq(hdr, 0);
if (!skb_cloned(skb))
return true;
- /* Unclone buffer in case it was bundled */
- if (pskb_expand_head(skb, BUF_HEADROOM, BUF_TAILROOM, GFP_ATOMIC))
- return false;
-
return true;
}
#include "netlink.h"
#define INVALID_NODE_SIG 0x10000
+#define NODE_CLEANUP_AFTER 300000
/* Flags used to take different actions according to flag type
* TIPC_NOTIFY_NODE_DOWN: notify node is down
* @link_id: local and remote bearer ids of changing link, if any
* @publ_list: list of publications
* @rcu: rcu struct for tipc_node
+ * @delete_at: indicates the time for deleting a down node
*/
struct tipc_node {
u32 addr;
unsigned long keepalive_intv;
struct timer_list timer;
struct rcu_head rcu;
+ unsigned long delete_at;
};
/* Node FSM states and events:
static struct tipc_node *tipc_node_find_by_id(struct net *net, u8 *id);
static void tipc_node_put(struct tipc_node *node);
static bool node_is_up(struct tipc_node *n);
+static void tipc_node_delete_from_list(struct tipc_node *node);
struct tipc_sock_conn {
u32 port;
{
struct tipc_net *tn = net_generic(net, tipc_net_id);
struct tipc_node *n, *temp_node;
+ struct tipc_link *l;
+ int bearer_id;
int i;
spin_lock_bh(&tn->node_list_lock);
if (n) {
/* Same node may come back with new capabilities */
n->capabilities = capabilities;
+ for (bearer_id = 0; bearer_id < MAX_BEARERS; bearer_id++) {
+ l = n->links[bearer_id].link;
+ if (l)
+ tipc_link_update_caps(l, capabilities);
+ }
goto exit;
}
n = kzalloc(sizeof(*n), GFP_ATOMIC);
for (i = 0; i < MAX_BEARERS; i++)
spin_lock_init(&n->links[i].lock);
n->state = SELF_DOWN_PEER_LEAVING;
+ n->delete_at = jiffies + msecs_to_jiffies(NODE_CLEANUP_AFTER);
n->signature = INVALID_NODE_SIG;
n->active_links[0] = INVALID_BEARER_ID;
n->active_links[1] = INVALID_BEARER_ID;
tipc_link_set_abort_limit(l, tol / n->keepalive_intv);
}
-static void tipc_node_delete(struct tipc_node *node)
+static void tipc_node_delete_from_list(struct tipc_node *node)
{
list_del_rcu(&node->list);
hlist_del_rcu(&node->hash);
tipc_node_put(node);
+}
+
+static void tipc_node_delete(struct tipc_node *node)
+{
+ tipc_node_delete_from_list(node);
del_timer_sync(&node->timer);
tipc_node_put(node);
tipc_node_put(node);
}
+static void tipc_node_clear_links(struct tipc_node *node)
+{
+ int i;
+
+ for (i = 0; i < MAX_BEARERS; i++) {
+ struct tipc_link_entry *le = &node->links[i];
+
+ if (le->link) {
+ kfree(le->link);
+ le->link = NULL;
+ node->link_cnt--;
+ }
+ }
+}
+
+/* tipc_node_cleanup - delete nodes that does not
+ * have active links for NODE_CLEANUP_AFTER time
+ */
+static int tipc_node_cleanup(struct tipc_node *peer)
+{
+ struct tipc_net *tn = tipc_net(peer->net);
+ bool deleted = false;
+
+ spin_lock_bh(&tn->node_list_lock);
+ tipc_node_write_lock(peer);
+
+ if (!node_is_up(peer) && time_after(jiffies, peer->delete_at)) {
+ tipc_node_clear_links(peer);
+ tipc_node_delete_from_list(peer);
+ deleted = true;
+ }
+ tipc_node_write_unlock(peer);
+ spin_unlock_bh(&tn->node_list_lock);
+ return deleted;
+}
+
/* tipc_node_timeout - handle expiration of node timer
*/
static void tipc_node_timeout(struct timer_list *t)
struct tipc_node *n = from_timer(n, t, timer);
struct tipc_link_entry *le;
struct sk_buff_head xmitq;
+ int remains = n->link_cnt;
int bearer_id;
int rc = 0;
+ if (!node_is_up(n) && tipc_node_cleanup(n)) {
+ /*Removing the reference of Timer*/
+ tipc_node_put(n);
+ return;
+ }
+
__skb_queue_head_init(&xmitq);
- for (bearer_id = 0; bearer_id < MAX_BEARERS; bearer_id++) {
+ for (bearer_id = 0; remains && (bearer_id < MAX_BEARERS); bearer_id++) {
tipc_node_read_lock(n);
le = &n->links[bearer_id];
- spin_lock_bh(&le->lock);
if (le->link) {
+ spin_lock_bh(&le->lock);
/* Link tolerance may change asynchronously: */
tipc_node_calculate_timer(n, le->link);
rc = tipc_link_timeout(le->link, &xmitq);
+ spin_unlock_bh(&le->lock);
+ remains--;
}
- spin_unlock_bh(&le->lock);
tipc_node_read_unlock(n);
tipc_bearer_xmit(n->net, bearer_id, &xmitq, &le->maddr);
if (rc & TIPC_LINK_DOWN_EVT)
uint i;
pr_debug("Lost contact with %x\n", n->addr);
+ n->delete_at = jiffies + msecs_to_jiffies(NODE_CLEANUP_AFTER);
/* Clean up broadcast state */
tipc_bcast_remove_peer(n->net, n->bc_entry.link);
* tipc_node_check_state - check and if necessary update node state
* @skb: TIPC packet
* @bearer_id: identity of bearer delivering the packet
- * Returns true if state is ok, otherwise consumes buffer and returns false
+ * Returns true if state and msg are ok, otherwise false
*/
static bool tipc_node_check_state(struct tipc_node *n, struct sk_buff *skb,
int bearer_id, struct sk_buff_head *xmitq)
}
}
+ if (!tipc_link_validate_msg(l, hdr))
+ return false;
+
/* Check and update node accesibility if applicable */
if (state == SELF_UP_PEER_COMING) {
if (!tipc_link_is_up(l))
struct tipc_node *peer;
u32 addr;
int err;
- int i;
/* We identify the peer by its net */
if (!info->attrs[TIPC_NLA_NET])
goto err_out;
}
- for (i = 0; i < MAX_BEARERS; i++) {
- struct tipc_link_entry *le = &peer->links[i];
-
- if (le->link) {
- kfree(le->link);
- le->link = NULL;
- peer->link_cnt--;
- }
- }
+ tipc_node_clear_links(peer);
tipc_node_write_unlock(peer);
tipc_node_delete(peer);
TIPC_BCAST_STATE_NACK = (1 << 2),
TIPC_BLOCK_FLOWCTL = (1 << 3),
TIPC_BCAST_RCAST = (1 << 4),
- TIPC_NODE_ID128 = (1 << 5)
+ TIPC_NODE_ID128 = (1 << 5),
+ TIPC_LINK_PROTO_SEQNO = (1 << 6)
};
-#define TIPC_NODE_CAPABILITIES (TIPC_BCAST_SYNCH | \
- TIPC_BCAST_STATE_NACK | \
- TIPC_BCAST_RCAST | \
- TIPC_BLOCK_FLOWCTL | \
- TIPC_NODE_ID128)
+#define TIPC_NODE_CAPABILITIES (TIPC_BCAST_SYNCH | \
+ TIPC_BCAST_STATE_NACK | \
+ TIPC_BCAST_RCAST | \
+ TIPC_BLOCK_FLOWCTL | \
+ TIPC_NODE_ID128 | \
+ TIPC_LINK_PROTO_SEQNO)
#define INVALID_BEARER_ID -1
void tipc_node_stop(struct net *net);
}
/**
- * tipc_poll - read pollmask
+ * tipc_poll - read and possibly block on pollmask
* @file: file structure associated with the socket
* @sock: socket for which to calculate the poll bits
+ * @wait: ???
*
* Returns pollmask value
*
* imply that the operation will succeed, merely that it should be performed
* and will not block.
*/
-static __poll_t tipc_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t tipc_poll(struct file *file, struct socket *sock,
+ poll_table *wait)
{
struct sock *sk = sock->sk;
struct tipc_sock *tsk = tipc_sk(sk);
__poll_t revents = 0;
+ sock_poll_wait(file, sk_sleep(sk), wait);
+
if (sk->sk_shutdown & RCV_SHUTDOWN)
revents |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM;
if (sk->sk_shutdown == SHUTDOWN_MASK)
.socketpair = tipc_socketpair,
.accept = sock_no_accept,
.getname = tipc_getname,
- .poll_mask = tipc_poll_mask,
+ .poll = tipc_poll,
.ioctl = tipc_ioctl,
.listen = sock_no_listen,
.shutdown = tipc_shutdown,
.socketpair = tipc_socketpair,
.accept = tipc_accept,
.getname = tipc_getname,
- .poll_mask = tipc_poll_mask,
+ .poll = tipc_poll,
.ioctl = tipc_ioctl,
.listen = tipc_listen,
.shutdown = tipc_shutdown,
.socketpair = tipc_socketpair,
.accept = tipc_accept,
.getname = tipc_getname,
- .poll_mask = tipc_poll_mask,
+ .poll = tipc_poll,
.ioctl = tipc_ioctl,
.listen = tipc_listen,
.shutdown = tipc_shutdown,
goto stat_msg_cancel;
nla_nest_end(skb, stat);
+
+ if (tsk->group)
+ if (tipc_group_fill_sock_diag(tsk->group, skb))
+ goto stat_msg_cancel;
+
nla_nest_end(skb, attrs);
return 0;
static void tls_device_free_ctx(struct tls_context *ctx)
{
- struct tls_offload_context *offload_ctx = tls_offload_ctx(ctx);
+ if (ctx->tx_conf == TLS_HW)
+ kfree(tls_offload_ctx_tx(ctx));
+
+ if (ctx->rx_conf == TLS_HW)
+ kfree(tls_offload_ctx_rx(ctx));
- kfree(offload_ctx);
kfree(ctx);
}
list_for_each_entry_safe(ctx, tmp, &gc_list, list) {
struct net_device *netdev = ctx->netdev;
- if (netdev) {
+ if (netdev && ctx->tx_conf == TLS_HW) {
netdev->tlsdev_ops->tls_dev_del(netdev, ctx,
TLS_OFFLOAD_CTX_DIR_TX);
dev_put(netdev);
+ ctx->netdev = NULL;
}
list_del(&ctx->list);
}
}
+static void tls_device_attach(struct tls_context *ctx, struct sock *sk,
+ struct net_device *netdev)
+{
+ if (sk->sk_destruct != tls_device_sk_destruct) {
+ refcount_set(&ctx->refcount, 1);
+ dev_hold(netdev);
+ ctx->netdev = netdev;
+ spin_lock_irq(&tls_device_lock);
+ list_add_tail(&ctx->list, &tls_device_list);
+ spin_unlock_irq(&tls_device_lock);
+
+ ctx->sk_destruct = sk->sk_destruct;
+ sk->sk_destruct = tls_device_sk_destruct;
+ }
+}
+
static void tls_device_queue_ctx_destruction(struct tls_context *ctx)
{
unsigned long flags;
kfree(record);
}
-static void delete_all_records(struct tls_offload_context *offload_ctx)
+static void delete_all_records(struct tls_offload_context_tx *offload_ctx)
{
struct tls_record_info *info, *temp;
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_record_info *info, *temp;
- struct tls_offload_context *ctx;
+ struct tls_offload_context_tx *ctx;
u64 deleted_records = 0;
unsigned long flags;
if (!tls_ctx)
return;
- ctx = tls_offload_ctx(tls_ctx);
+ ctx = tls_offload_ctx_tx(tls_ctx);
spin_lock_irqsave(&ctx->lock, flags);
info = ctx->retransmit_hint;
void tls_device_sk_destruct(struct sock *sk)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
- struct tls_offload_context *ctx = tls_offload_ctx(tls_ctx);
+ struct tls_offload_context_tx *ctx = tls_offload_ctx_tx(tls_ctx);
- if (ctx->open_record)
- destroy_record(ctx->open_record);
+ tls_ctx->sk_destruct(sk);
- delete_all_records(ctx);
- crypto_free_aead(ctx->aead_send);
- ctx->sk_destruct(sk);
- clean_acked_data_disable(inet_csk(sk));
+ if (tls_ctx->tx_conf == TLS_HW) {
+ if (ctx->open_record)
+ destroy_record(ctx->open_record);
+ delete_all_records(ctx);
+ crypto_free_aead(ctx->aead_send);
+ clean_acked_data_disable(inet_csk(sk));
+ }
if (refcount_dec_and_test(&tls_ctx->refcount))
tls_device_queue_ctx_destruction(tls_ctx);
static int tls_push_record(struct sock *sk,
struct tls_context *ctx,
- struct tls_offload_context *offload_ctx,
+ struct tls_offload_context_tx *offload_ctx,
struct tls_record_info *record,
struct page_frag *pfrag,
int flags,
return tls_push_sg(sk, ctx, offload_ctx->sg_tx_data, 0, flags);
}
-static int tls_create_new_record(struct tls_offload_context *offload_ctx,
+static int tls_create_new_record(struct tls_offload_context_tx *offload_ctx,
struct page_frag *pfrag,
size_t prepend_size)
{
}
static int tls_do_allocation(struct sock *sk,
- struct tls_offload_context *offload_ctx,
+ struct tls_offload_context_tx *offload_ctx,
struct page_frag *pfrag,
size_t prepend_size)
{
unsigned char record_type)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
- struct tls_offload_context *ctx = tls_offload_ctx(tls_ctx);
+ struct tls_offload_context_tx *ctx = tls_offload_ctx_tx(tls_ctx);
int tls_push_record_flags = flags | MSG_SENDPAGE_NOTLAST;
int more = flags & (MSG_SENDPAGE_NOTLAST | MSG_MORE);
struct tls_record_info *record = ctx->open_record;
return rc;
}
-struct tls_record_info *tls_get_record(struct tls_offload_context *context,
+struct tls_record_info *tls_get_record(struct tls_offload_context_tx *context,
u32 seq, u64 *p_record_sn)
{
u64 record_sn = context->hint_record_sn;
return tls_push_data(sk, &msg_iter, 0, flags, TLS_RECORD_TYPE_DATA);
}
+void handle_device_resync(struct sock *sk, u32 seq, u64 rcd_sn)
+{
+ struct tls_context *tls_ctx = tls_get_ctx(sk);
+ struct net_device *netdev = tls_ctx->netdev;
+ struct tls_offload_context_rx *rx_ctx;
+ u32 is_req_pending;
+ s64 resync_req;
+ u32 req_seq;
+
+ if (tls_ctx->rx_conf != TLS_HW)
+ return;
+
+ rx_ctx = tls_offload_ctx_rx(tls_ctx);
+ resync_req = atomic64_read(&rx_ctx->resync_req);
+ req_seq = ntohl(resync_req >> 32) - ((u32)TLS_HEADER_SIZE - 1);
+ is_req_pending = resync_req;
+
+ if (unlikely(is_req_pending) && req_seq == seq &&
+ atomic64_try_cmpxchg(&rx_ctx->resync_req, &resync_req, 0))
+ netdev->tlsdev_ops->tls_dev_resync_rx(netdev, sk,
+ seq + TLS_HEADER_SIZE - 1,
+ rcd_sn);
+}
+
+static int tls_device_reencrypt(struct sock *sk, struct sk_buff *skb)
+{
+ struct strp_msg *rxm = strp_msg(skb);
+ int err = 0, offset = rxm->offset, copy, nsg;
+ struct sk_buff *skb_iter, *unused;
+ struct scatterlist sg[1];
+ char *orig_buf, *buf;
+
+ orig_buf = kmalloc(rxm->full_len + TLS_HEADER_SIZE +
+ TLS_CIPHER_AES_GCM_128_IV_SIZE, sk->sk_allocation);
+ if (!orig_buf)
+ return -ENOMEM;
+ buf = orig_buf;
+
+ nsg = skb_cow_data(skb, 0, &unused);
+ if (unlikely(nsg < 0)) {
+ err = nsg;
+ goto free_buf;
+ }
+
+ sg_init_table(sg, 1);
+ sg_set_buf(&sg[0], buf,
+ rxm->full_len + TLS_HEADER_SIZE +
+ TLS_CIPHER_AES_GCM_128_IV_SIZE);
+ skb_copy_bits(skb, offset, buf,
+ TLS_HEADER_SIZE + TLS_CIPHER_AES_GCM_128_IV_SIZE);
+
+ /* We are interested only in the decrypted data not the auth */
+ err = decrypt_skb(sk, skb, sg);
+ if (err != -EBADMSG)
+ goto free_buf;
+ else
+ err = 0;
+
+ copy = min_t(int, skb_pagelen(skb) - offset,
+ rxm->full_len - TLS_CIPHER_AES_GCM_128_TAG_SIZE);
+
+ if (skb->decrypted)
+ skb_store_bits(skb, offset, buf, copy);
+
+ offset += copy;
+ buf += copy;
+
+ skb_walk_frags(skb, skb_iter) {
+ copy = min_t(int, skb_iter->len,
+ rxm->full_len - offset + rxm->offset -
+ TLS_CIPHER_AES_GCM_128_TAG_SIZE);
+
+ if (skb_iter->decrypted)
+ skb_store_bits(skb, offset, buf, copy);
+
+ offset += copy;
+ buf += copy;
+ }
+
+free_buf:
+ kfree(orig_buf);
+ return err;
+}
+
+int tls_device_decrypted(struct sock *sk, struct sk_buff *skb)
+{
+ struct tls_context *tls_ctx = tls_get_ctx(sk);
+ struct tls_offload_context_rx *ctx = tls_offload_ctx_rx(tls_ctx);
+ int is_decrypted = skb->decrypted;
+ int is_encrypted = !is_decrypted;
+ struct sk_buff *skb_iter;
+
+ /* Skip if it is already decrypted */
+ if (ctx->sw.decrypted)
+ return 0;
+
+ /* Check if all the data is decrypted already */
+ skb_walk_frags(skb, skb_iter) {
+ is_decrypted &= skb_iter->decrypted;
+ is_encrypted &= !skb_iter->decrypted;
+ }
+
+ ctx->sw.decrypted |= is_decrypted;
+
+ /* Return immedeatly if the record is either entirely plaintext or
+ * entirely ciphertext. Otherwise handle reencrypt partially decrypted
+ * record.
+ */
+ return (is_encrypted || is_decrypted) ? 0 :
+ tls_device_reencrypt(sk, skb);
+}
+
int tls_set_device_offload(struct sock *sk, struct tls_context *ctx)
{
u16 nonce_size, tag_size, iv_size, rec_seq_size;
struct tls_record_info *start_marker_record;
- struct tls_offload_context *offload_ctx;
+ struct tls_offload_context_tx *offload_ctx;
struct tls_crypto_info *crypto_info;
struct net_device *netdev;
char *iv, *rec_seq;
goto out;
}
- offload_ctx = kzalloc(TLS_OFFLOAD_CONTEXT_SIZE, GFP_KERNEL);
+ offload_ctx = kzalloc(TLS_OFFLOAD_CONTEXT_SIZE_TX, GFP_KERNEL);
if (!offload_ctx) {
rc = -ENOMEM;
goto free_marker_record;
clean_acked_data_enable(inet_csk(sk), &tls_icsk_clean_acked);
ctx->push_pending_record = tls_device_push_pending_record;
- offload_ctx->sk_destruct = sk->sk_destruct;
/* TLS offload is greatly simplified if we don't send
* SKBs where only part of the payload needs to be encrypted.
if (skb)
TCP_SKB_CB(skb)->eor = 1;
- refcount_set(&ctx->refcount, 1);
-
/* We support starting offload on multiple sockets
* concurrently, so we only need a read lock here.
* This lock must precede get_netdev_for_sock to prevent races between
if (rc)
goto release_netdev;
- ctx->netdev = netdev;
-
- spin_lock_irq(&tls_device_lock);
- list_add_tail(&ctx->list, &tls_device_list);
- spin_unlock_irq(&tls_device_lock);
+ tls_device_attach(ctx, sk, netdev);
- sk->sk_validate_xmit_skb = tls_validate_xmit_skb;
/* following this assignment tls_is_sk_tx_device_offloaded
* will return true and the context might be accessed
* by the netdev's xmit function.
*/
- smp_store_release(&sk->sk_destruct,
- &tls_device_sk_destruct);
+ smp_store_release(&sk->sk_validate_xmit_skb, tls_validate_xmit_skb);
+ dev_put(netdev);
up_read(&device_offload_lock);
goto out;
return rc;
}
+int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx)
+{
+ struct tls_offload_context_rx *context;
+ struct net_device *netdev;
+ int rc = 0;
+
+ /* We support starting offload on multiple sockets
+ * concurrently, so we only need a read lock here.
+ * This lock must precede get_netdev_for_sock to prevent races between
+ * NETDEV_DOWN and setsockopt.
+ */
+ down_read(&device_offload_lock);
+ netdev = get_netdev_for_sock(sk);
+ if (!netdev) {
+ pr_err_ratelimited("%s: netdev not found\n", __func__);
+ rc = -EINVAL;
+ goto release_lock;
+ }
+
+ if (!(netdev->features & NETIF_F_HW_TLS_RX)) {
+ pr_err_ratelimited("%s: netdev %s with no TLS offload\n",
+ __func__, netdev->name);
+ rc = -ENOTSUPP;
+ goto release_netdev;
+ }
+
+ /* Avoid offloading if the device is down
+ * We don't want to offload new flows after
+ * the NETDEV_DOWN event
+ */
+ if (!(netdev->flags & IFF_UP)) {
+ rc = -EINVAL;
+ goto release_netdev;
+ }
+
+ context = kzalloc(TLS_OFFLOAD_CONTEXT_SIZE_RX, GFP_KERNEL);
+ if (!context) {
+ rc = -ENOMEM;
+ goto release_netdev;
+ }
+
+ ctx->priv_ctx_rx = context;
+ rc = tls_set_sw_offload(sk, ctx, 0);
+ if (rc)
+ goto release_ctx;
+
+ rc = netdev->tlsdev_ops->tls_dev_add(netdev, sk, TLS_OFFLOAD_CTX_DIR_RX,
+ &ctx->crypto_recv,
+ tcp_sk(sk)->copied_seq);
+ if (rc) {
+ pr_err_ratelimited("%s: The netdev has refused to offload this socket\n",
+ __func__);
+ goto free_sw_resources;
+ }
+
+ tls_device_attach(ctx, sk, netdev);
+ goto release_netdev;
+
+free_sw_resources:
+ tls_sw_free_resources_rx(sk);
+release_ctx:
+ ctx->priv_ctx_rx = NULL;
+release_netdev:
+ dev_put(netdev);
+release_lock:
+ up_read(&device_offload_lock);
+ return rc;
+}
+
+void tls_device_offload_cleanup_rx(struct sock *sk)
+{
+ struct tls_context *tls_ctx = tls_get_ctx(sk);
+ struct net_device *netdev;
+
+ down_read(&device_offload_lock);
+ netdev = tls_ctx->netdev;
+ if (!netdev)
+ goto out;
+
+ if (!(netdev->features & NETIF_F_HW_TLS_RX)) {
+ pr_err_ratelimited("%s: device is missing NETIF_F_HW_TLS_RX cap\n",
+ __func__);
+ goto out;
+ }
+
+ netdev->tlsdev_ops->tls_dev_del(netdev, tls_ctx,
+ TLS_OFFLOAD_CTX_DIR_RX);
+
+ if (tls_ctx->tx_conf != TLS_HW) {
+ dev_put(netdev);
+ tls_ctx->netdev = NULL;
+ }
+out:
+ up_read(&device_offload_lock);
+ kfree(tls_ctx->rx.rec_seq);
+ kfree(tls_ctx->rx.iv);
+ tls_sw_release_resources_rx(sk);
+}
+
static int tls_device_down(struct net_device *netdev)
{
struct tls_context *ctx, *tmp;
spin_unlock_irqrestore(&tls_device_lock, flags);
list_for_each_entry_safe(ctx, tmp, &list, list) {
- netdev->tlsdev_ops->tls_dev_del(netdev, ctx,
- TLS_OFFLOAD_CTX_DIR_TX);
+ if (ctx->tx_conf == TLS_HW)
+ netdev->tlsdev_ops->tls_dev_del(netdev, ctx,
+ TLS_OFFLOAD_CTX_DIR_TX);
+ if (ctx->rx_conf == TLS_HW)
+ netdev->tlsdev_ops->tls_dev_del(netdev, ctx,
+ TLS_OFFLOAD_CTX_DIR_RX);
ctx->netdev = NULL;
dev_put(netdev);
list_del_init(&ctx->list);
{
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
- if (!(dev->features & NETIF_F_HW_TLS_TX))
+ if (!(dev->features & (NETIF_F_HW_TLS_RX | NETIF_F_HW_TLS_TX)))
return NOTIFY_DONE;
switch (event) {
case NETDEV_REGISTER:
case NETDEV_FEAT_CHANGE:
+ if ((dev->features & NETIF_F_HW_TLS_RX) &&
+ !dev->tlsdev_ops->tls_dev_resync_rx)
+ return NOTIFY_BAD;
+
if (dev->tlsdev_ops &&
dev->tlsdev_ops->tls_dev_add &&
dev->tlsdev_ops->tls_dev_del)
static int fill_sg_in(struct scatterlist *sg_in,
struct sk_buff *skb,
- struct tls_offload_context *ctx,
+ struct tls_offload_context_tx *ctx,
u64 *rcd_sn,
s32 *sync_size,
int *resync_sgs)
s32 sync_size, u64 rcd_sn)
{
int tcp_payload_offset = skb_transport_offset(skb) + tcp_hdrlen(skb);
- struct tls_offload_context *ctx = tls_offload_ctx(tls_ctx);
+ struct tls_offload_context_tx *ctx = tls_offload_ctx_tx(tls_ctx);
int payload_len = skb->len - tcp_payload_offset;
void *buf, *iv, *aad, *dummy_buf;
struct aead_request *aead_req;
{
int tcp_payload_offset = skb_transport_offset(skb) + tcp_hdrlen(skb);
struct tls_context *tls_ctx = tls_get_ctx(sk);
- struct tls_offload_context *ctx = tls_offload_ctx(tls_ctx);
+ struct tls_offload_context_tx *ctx = tls_offload_ctx_tx(tls_ctx);
int payload_len = skb->len - tcp_payload_offset;
struct scatterlist *sg_in, sg_out[3];
struct sk_buff *nskb = NULL;
return tls_sw_fallback(sk, skb);
}
+EXPORT_SYMBOL_GPL(tls_validate_xmit_skb);
int tls_sw_fallback_init(struct sock *sk,
- struct tls_offload_context *offload_ctx,
+ struct tls_offload_context_tx *offload_ctx,
struct tls_crypto_info *crypto_info)
{
const u8 *key;
TLSV6,
TLS_NUM_PROTS,
};
-enum {
- TLS_BASE,
- TLS_SW,
-#ifdef CONFIG_TLS_DEVICE
- TLS_HW,
-#endif
- TLS_HW_RECORD,
- TLS_NUM_CONFIG,
-};
static struct proto *saved_tcpv6_prot;
static DEFINE_MUTEX(tcpv6_prot_mutex);
}
#ifdef CONFIG_TLS_DEVICE
- if (ctx->tx_conf != TLS_HW) {
+ if (ctx->rx_conf == TLS_HW)
+ tls_device_offload_cleanup_rx(sk);
+
+ if (ctx->tx_conf != TLS_HW && ctx->rx_conf != TLS_HW) {
#else
{
#endif
conf = TLS_SW;
}
} else {
- rc = tls_set_sw_offload(sk, ctx, 0);
- conf = TLS_SW;
+#ifdef CONFIG_TLS_DEVICE
+ rc = tls_set_device_offload_rx(sk, ctx);
+ conf = TLS_HW;
+ if (rc) {
+#else
+ {
+#endif
+ rc = tls_set_sw_offload(sk, ctx, 0);
+ conf = TLS_SW;
+ }
}
if (rc)
prot[TLS_HW][TLS_SW] = prot[TLS_BASE][TLS_SW];
prot[TLS_HW][TLS_SW].sendmsg = tls_device_sendmsg;
prot[TLS_HW][TLS_SW].sendpage = tls_device_sendpage;
+
+ prot[TLS_BASE][TLS_HW] = prot[TLS_BASE][TLS_SW];
+
+ prot[TLS_SW][TLS_HW] = prot[TLS_SW][TLS_SW];
+
+ prot[TLS_HW][TLS_HW] = prot[TLS_HW][TLS_SW];
#endif
prot[TLS_HW_RECORD][TLS_HW_RECORD] = *base;
build_protos(tls_prots[TLSV4], &tcp_prot);
tls_sw_proto_ops = inet_stream_ops;
- tls_sw_proto_ops.poll_mask = tls_sw_poll_mask;
+ tls_sw_proto_ops.poll = tls_sw_poll;
tls_sw_proto_ops.splice_read = tls_sw_splice_read;
#ifdef CONFIG_TLS_DEVICE
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
- struct strp_msg *rxm = strp_msg(skb);
struct aead_request *aead_req;
int ret;
- unsigned int req_size = sizeof(struct aead_request) +
- crypto_aead_reqsize(ctx->aead_recv);
- aead_req = kzalloc(req_size, flags);
+ aead_req = aead_request_alloc(ctx->aead_recv, flags);
if (!aead_req)
return -ENOMEM;
- aead_request_set_tfm(aead_req, ctx->aead_recv);
aead_request_set_ad(aead_req, TLS_AAD_SPACE_SIZE);
aead_request_set_crypt(aead_req, sgin, sgout,
data_len + tls_ctx->rx.tag_size,
ret = crypto_wait_req(crypto_aead_decrypt(aead_req), &ctx->async_wait);
- if (ret < 0)
- goto out;
-
- rxm->offset += tls_ctx->rx.prepend_size;
- rxm->full_len -= tls_ctx->rx.overhead_size;
- tls_advance_record_sn(sk, &tls_ctx->rx);
-
- ctx->decrypted = true;
-
- ctx->saved_data_ready(sk);
-
-out:
- kfree(aead_req);
+ aead_request_free(aead_req);
return ret;
}
struct aead_request *req;
int rc;
- req = kzalloc(sizeof(struct aead_request) +
- crypto_aead_reqsize(ctx->aead_send), sk->sk_allocation);
+ req = aead_request_alloc(ctx->aead_send, sk->sk_allocation);
if (!req)
return -ENOMEM;
tls_advance_record_sn(sk, &tls_ctx->tx);
out_req:
- kfree(req);
+ aead_request_free(req);
return rc;
}
int length, int *pages_used,
unsigned int *size_used,
struct scatterlist *to, int to_max_pages,
- bool charge)
+ bool charge, bool revert)
{
struct page *pages[MAX_SKB_FRAGS];
out:
*size_used = size;
*pages_used = num_elem;
+ if (revert)
+ iov_iter_revert(from, size);
return rc;
}
&ctx->sg_plaintext_size,
ctx->sg_plaintext_data,
ARRAY_SIZE(ctx->sg_plaintext_data),
- true);
+ true, false);
if (ret)
goto fallback_to_reg_send;
return skb;
}
-static int decrypt_skb(struct sock *sk, struct sk_buff *skb,
- struct scatterlist *sgout)
+static int decrypt_skb_update(struct sock *sk, struct sk_buff *skb,
+ struct scatterlist *sgout, bool *zc)
+{
+ struct tls_context *tls_ctx = tls_get_ctx(sk);
+ struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
+ struct strp_msg *rxm = strp_msg(skb);
+ int err = 0;
+
+#ifdef CONFIG_TLS_DEVICE
+ err = tls_device_decrypted(sk, skb);
+ if (err < 0)
+ return err;
+#endif
+ if (!ctx->decrypted) {
+ err = decrypt_skb(sk, skb, sgout);
+ if (err < 0)
+ return err;
+ } else {
+ *zc = false;
+ }
+
+ rxm->offset += tls_ctx->rx.prepend_size;
+ rxm->full_len -= tls_ctx->rx.overhead_size;
+ tls_advance_record_sn(sk, &tls_ctx->rx);
+ ctx->decrypted = true;
+ ctx->saved_data_ready(sk);
+
+ return err;
+}
+
+int decrypt_skb(struct sock *sk, struct sk_buff *skb,
+ struct scatterlist *sgout)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
err = zerocopy_from_iter(sk, &msg->msg_iter,
to_copy, &pages,
&chunk, &sgin[1],
- MAX_SKB_FRAGS, false);
+ MAX_SKB_FRAGS, false, true);
if (err < 0)
goto fallback_to_reg_recv;
- err = decrypt_skb(sk, skb, sgin);
+ err = decrypt_skb_update(sk, skb, sgin, &zc);
for (; pages > 0; pages--)
put_page(sg_page(&sgin[pages]));
if (err < 0) {
}
} else {
fallback_to_reg_recv:
- err = decrypt_skb(sk, skb, NULL);
+ err = decrypt_skb_update(sk, skb, NULL, &zc);
if (err < 0) {
tls_err_abort(sk, EBADMSG);
goto recv_end;
int err = 0;
long timeo;
int chunk;
+ bool zc;
lock_sock(sk);
}
if (!ctx->decrypted) {
- err = decrypt_skb(sk, skb, NULL);
+ err = decrypt_skb_update(sk, skb, NULL, &zc);
if (err < 0) {
tls_err_abort(sk, EBADMSG);
return copied ? : err;
}
-__poll_t tls_sw_poll_mask(struct socket *sock, __poll_t events)
+unsigned int tls_sw_poll(struct file *file, struct socket *sock,
+ struct poll_table_struct *wait)
{
+ unsigned int ret;
struct sock *sk = sock->sk;
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
- __poll_t mask;
- /* Grab EPOLLOUT and EPOLLHUP from the underlying socket */
- mask = ctx->sk_poll_mask(sock, events);
+ /* Grab POLLOUT and POLLHUP from the underlying socket */
+ ret = ctx->sk_poll(file, sock, wait);
- /* Clear EPOLLIN bits, and set based on recv_pkt */
- mask &= ~(EPOLLIN | EPOLLRDNORM);
+ /* Clear POLLIN bits, and set based on recv_pkt */
+ ret &= ~(POLLIN | POLLRDNORM);
if (ctx->recv_pkt)
- mask |= EPOLLIN | EPOLLRDNORM;
+ ret |= POLLIN | POLLRDNORM;
- return mask;
+ return ret;
}
static int tls_read_size(struct strparser *strp, struct sk_buff *skb)
{
struct tls_context *tls_ctx = tls_get_ctx(strp->sk);
struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
- char header[tls_ctx->rx.prepend_size];
+ char header[TLS_HEADER_SIZE + MAX_IV_SIZE];
struct strp_msg *rxm = strp_msg(skb);
size_t cipher_overhead;
size_t data_len = 0;
if (rxm->offset + tls_ctx->rx.prepend_size > skb->len)
return 0;
+ /* Sanity-check size of on-stack buffer. */
+ if (WARN_ON(tls_ctx->rx.prepend_size > sizeof(header))) {
+ ret = -EINVAL;
+ goto read_failure;
+ }
+
/* Linearize header to local buffer */
ret = skb_copy_bits(skb, rxm->offset, header, tls_ctx->rx.prepend_size);
goto read_failure;
}
+#ifdef CONFIG_TLS_DEVICE
+ handle_device_resync(strp->sk, TCP_SKB_CB(skb)->seq + rxm->offset,
+ *(u64*)tls_ctx->rx.rec_seq);
+#endif
return data_len + TLS_HEADER_SIZE;
read_failure:
{
struct tls_context *tls_ctx = tls_get_ctx(strp->sk);
struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
- struct strp_msg *rxm;
-
- rxm = strp_msg(skb);
ctx->decrypted = false;
kfree(ctx);
}
-void tls_sw_free_resources_rx(struct sock *sk)
+void tls_sw_release_resources_rx(struct sock *sk)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
strp_done(&ctx->strp);
lock_sock(sk);
}
+}
+
+void tls_sw_free_resources_rx(struct sock *sk)
+{
+ struct tls_context *tls_ctx = tls_get_ctx(sk);
+ struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
+
+ tls_sw_release_resources_rx(sk);
kfree(ctx);
}
}
if (tx) {
- sw_ctx_tx = kzalloc(sizeof(*sw_ctx_tx), GFP_KERNEL);
- if (!sw_ctx_tx) {
- rc = -ENOMEM;
- goto out;
+ if (!ctx->priv_ctx_tx) {
+ sw_ctx_tx = kzalloc(sizeof(*sw_ctx_tx), GFP_KERNEL);
+ if (!sw_ctx_tx) {
+ rc = -ENOMEM;
+ goto out;
+ }
+ ctx->priv_ctx_tx = sw_ctx_tx;
+ } else {
+ sw_ctx_tx =
+ (struct tls_sw_context_tx *)ctx->priv_ctx_tx;
}
- crypto_init_wait(&sw_ctx_tx->async_wait);
- ctx->priv_ctx_tx = sw_ctx_tx;
} else {
- sw_ctx_rx = kzalloc(sizeof(*sw_ctx_rx), GFP_KERNEL);
- if (!sw_ctx_rx) {
- rc = -ENOMEM;
- goto out;
+ if (!ctx->priv_ctx_rx) {
+ sw_ctx_rx = kzalloc(sizeof(*sw_ctx_rx), GFP_KERNEL);
+ if (!sw_ctx_rx) {
+ rc = -ENOMEM;
+ goto out;
+ }
+ ctx->priv_ctx_rx = sw_ctx_rx;
+ } else {
+ sw_ctx_rx =
+ (struct tls_sw_context_rx *)ctx->priv_ctx_rx;
}
- crypto_init_wait(&sw_ctx_rx->async_wait);
- ctx->priv_ctx_rx = sw_ctx_rx;
}
if (tx) {
+ crypto_init_wait(&sw_ctx_tx->async_wait);
crypto_info = &ctx->crypto_send;
cctx = &ctx->tx;
aead = &sw_ctx_tx->aead_send;
} else {
+ crypto_init_wait(&sw_ctx_rx->async_wait);
crypto_info = &ctx->crypto_recv;
cctx = &ctx->rx;
aead = &sw_ctx_rx->aead_recv;
}
/* Sanity-check the IV size for stack allocations. */
- if (iv_size > MAX_IV_SIZE) {
+ if (iv_size > MAX_IV_SIZE || nonce_size > MAX_IV_SIZE) {
rc = -EINVAL;
goto free_priv;
}
sk->sk_data_ready = tls_data_ready;
write_unlock_bh(&sk->sk_callback_lock);
- sw_ctx_rx->sk_poll_mask = sk->sk_socket->ops->poll_mask;
+ sw_ctx_rx->sk_poll = sk->sk_socket->ops->poll;
strp_check_rcv(&sw_ctx_rx->strp);
}
static int unix_socketpair(struct socket *, struct socket *);
static int unix_accept(struct socket *, struct socket *, int, bool);
static int unix_getname(struct socket *, struct sockaddr *, int);
-static __poll_t unix_poll_mask(struct socket *, __poll_t);
-static __poll_t unix_dgram_poll_mask(struct socket *, __poll_t);
+static __poll_t unix_poll(struct file *, struct socket *, poll_table *);
+static __poll_t unix_dgram_poll(struct file *, struct socket *,
+ poll_table *);
static int unix_ioctl(struct socket *, unsigned int, unsigned long);
static int unix_shutdown(struct socket *, int);
static int unix_stream_sendmsg(struct socket *, struct msghdr *, size_t);
.socketpair = unix_socketpair,
.accept = unix_accept,
.getname = unix_getname,
- .poll_mask = unix_poll_mask,
+ .poll = unix_poll,
.ioctl = unix_ioctl,
.listen = unix_listen,
.shutdown = unix_shutdown,
.socketpair = unix_socketpair,
.accept = sock_no_accept,
.getname = unix_getname,
- .poll_mask = unix_dgram_poll_mask,
+ .poll = unix_dgram_poll,
.ioctl = unix_ioctl,
.listen = sock_no_listen,
.shutdown = unix_shutdown,
.socketpair = unix_socketpair,
.accept = unix_accept,
.getname = unix_getname,
- .poll_mask = unix_dgram_poll_mask,
+ .poll = unix_dgram_poll,
.ioctl = unix_ioctl,
.listen = unix_listen,
.shutdown = unix_shutdown,
return err;
}
-static __poll_t unix_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wait)
{
struct sock *sk = sock->sk;
- __poll_t mask = 0;
+ __poll_t mask;
+
+ sock_poll_wait(file, sk_sleep(sk), wait);
+ mask = 0;
/* exceptional events? */
if (sk->sk_err)
return mask;
}
-static __poll_t unix_dgram_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t unix_dgram_poll(struct file *file, struct socket *sock,
+ poll_table *wait)
{
struct sock *sk = sock->sk, *other;
- int writable;
- __poll_t mask = 0;
+ unsigned int writable;
+ __poll_t mask;
+
+ sock_poll_wait(file, sk_sleep(sk), wait);
+ mask = 0;
/* exceptional events? */
if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
}
/* No write status requested, avoid expensive OUT tests. */
- if (!(events & (EPOLLWRBAND|EPOLLWRNORM|EPOLLOUT)))
+ if (!(poll_requested_events(wait) & (EPOLLWRBAND|EPOLLWRNORM|EPOLLOUT)))
return mask;
writable = unix_writable(sk);
return err;
}
-static __poll_t vsock_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t vsock_poll(struct file *file, struct socket *sock,
+ poll_table *wait)
{
- struct sock *sk = sock->sk;
- struct vsock_sock *vsk = vsock_sk(sk);
- __poll_t mask = 0;
+ struct sock *sk;
+ __poll_t mask;
+ struct vsock_sock *vsk;
+
+ sk = sock->sk;
+ vsk = vsock_sk(sk);
+
+ poll_wait(file, sk_sleep(sk), wait);
+ mask = 0;
if (sk->sk_err)
/* Signify that there has been an error on this socket. */
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = vsock_getname,
- .poll_mask = vsock_poll_mask,
+ .poll = vsock_poll,
.ioctl = sock_no_ioctl,
.listen = sock_no_listen,
.shutdown = vsock_shutdown,
.socketpair = sock_no_socketpair,
.accept = vsock_accept,
.getname = vsock_getname,
- .poll_mask = vsock_poll_mask,
+ .poll = vsock_poll,
.ioctl = sock_no_ioctl,
.listen = vsock_listen,
.shutdown = vsock_shutdown,
return -ENODEV;
}
- if (le32_to_cpu(pkt->hdr.dst_cid) == vsock->guest_cid)
+ if (le64_to_cpu(pkt->hdr.dst_cid) == vsock->guest_cid)
return virtio_transport_send_pkt_loopback(vsock, pkt);
if (pkt->reply)
*
* Copyright 2006-2010 Johannes Berg <johannes@sipsolutions.net>
* Copyright 2013-2014 Intel Mobile Communications GmbH
- * Copyright 2015 Intel Deutschland GmbH
+ * Copyright 2015-2017 Intel Deutschland GmbH
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
/* sanity check supported bands/channels */
for (band = 0; band < NUM_NL80211_BANDS; band++) {
+ u16 types = 0;
+
sband = wiphy->bands[band];
if (!sband)
continue;
sband->channels[i].band = band;
}
+ for (i = 0; i < sband->n_iftype_data; i++) {
+ const struct ieee80211_sband_iftype_data *iftd;
+
+ iftd = &sband->iftype_data[i];
+
+ if (WARN_ON(!iftd->types_mask))
+ return -EINVAL;
+ if (WARN_ON(types & iftd->types_mask))
+ return -EINVAL;
+
+ /* at least one piece of information must be present */
+ if (WARN_ON(!iftd->he_cap.has_he))
+ return -EINVAL;
+
+ types |= iftd->types_mask;
+ }
+
have_band = true;
}
struct cfg80211_scan_request *scan_req; /* protected by RTNL */
struct sk_buff *scan_msg;
struct list_head sched_scan_req_list;
- unsigned long suspend_at;
+ time64_t suspend_at;
struct work_struct scan_done_wk;
struct genl_info *cur_cmd_info;
[NL80211_ATTR_TXQ_LIMIT] = { .type = NLA_U32 },
[NL80211_ATTR_TXQ_MEMORY_LIMIT] = { .type = NLA_U32 },
[NL80211_ATTR_TXQ_QUANTUM] = { .type = NLA_U32 },
+ [NL80211_ATTR_HE_CAPABILITY] = { .type = NLA_BINARY,
+ .len = NL80211_HE_MAX_CAPABILITY_LEN },
};
/* policy for the key attributes */
return 0;
}
+static int
+nl80211_send_iftype_data(struct sk_buff *msg,
+ const struct ieee80211_sband_iftype_data *iftdata)
+{
+ const struct ieee80211_sta_he_cap *he_cap = &iftdata->he_cap;
+
+ if (nl80211_put_iftypes(msg, NL80211_BAND_IFTYPE_ATTR_IFTYPES,
+ iftdata->types_mask))
+ return -ENOBUFS;
+
+ if (he_cap->has_he) {
+ if (nla_put(msg, NL80211_BAND_IFTYPE_ATTR_HE_CAP_MAC,
+ sizeof(he_cap->he_cap_elem.mac_cap_info),
+ he_cap->he_cap_elem.mac_cap_info) ||
+ nla_put(msg, NL80211_BAND_IFTYPE_ATTR_HE_CAP_PHY,
+ sizeof(he_cap->he_cap_elem.phy_cap_info),
+ he_cap->he_cap_elem.phy_cap_info) ||
+ nla_put(msg, NL80211_BAND_IFTYPE_ATTR_HE_CAP_MCS_SET,
+ sizeof(he_cap->he_mcs_nss_supp),
+ &he_cap->he_mcs_nss_supp) ||
+ nla_put(msg, NL80211_BAND_IFTYPE_ATTR_HE_CAP_PPE,
+ sizeof(he_cap->ppe_thres), he_cap->ppe_thres))
+ return -ENOBUFS;
+ }
+
+ return 0;
+}
+
static int nl80211_send_band_rateinfo(struct sk_buff *msg,
struct ieee80211_supported_band *sband)
{
sband->vht_cap.cap)))
return -ENOBUFS;
+ if (sband->n_iftype_data) {
+ struct nlattr *nl_iftype_data =
+ nla_nest_start(msg, NL80211_BAND_ATTR_IFTYPE_DATA);
+ int err;
+
+ if (!nl_iftype_data)
+ return -ENOBUFS;
+
+ for (i = 0; i < sband->n_iftype_data; i++) {
+ struct nlattr *iftdata;
+
+ iftdata = nla_nest_start(msg, i + 1);
+ if (!iftdata)
+ return -ENOBUFS;
+
+ err = nl80211_send_iftype_data(msg,
+ &sband->iftype_data[i]);
+ if (err)
+ return err;
+
+ nla_nest_end(msg, iftdata);
+ }
+
+ nla_nest_end(msg, nl_iftype_data);
+ }
+
/* add bitrates */
nl_rates = nla_nest_start(msg, NL80211_BAND_ATTR_RATES);
if (!nl_rates)
nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, wdev_address(wdev)) ||
nla_put_u32(msg, NL80211_ATTR_GENERATION,
rdev->devlist_generation ^
- (cfg80211_rdev_list_generation << 2)))
+ (cfg80211_rdev_list_generation << 2)) ||
+ nla_put_u8(msg, NL80211_ATTR_4ADDR, wdev->use_4addr))
goto nla_put_failure;
if (rdev->ops->get_channel) {
case RATE_INFO_BW_160:
rate_flg = NL80211_RATE_INFO_160_MHZ_WIDTH;
break;
+ case RATE_INFO_BW_HE_RU:
+ rate_flg = 0;
+ WARN_ON(!(info->flags & RATE_INFO_FLAGS_HE_MCS));
}
if (rate_flg && nla_put_flag(msg, rate_flg))
if (info->flags & RATE_INFO_FLAGS_SHORT_GI &&
nla_put_flag(msg, NL80211_RATE_INFO_SHORT_GI))
return false;
+ } else if (info->flags & RATE_INFO_FLAGS_HE_MCS) {
+ if (nla_put_u8(msg, NL80211_RATE_INFO_HE_MCS, info->mcs))
+ return false;
+ if (nla_put_u8(msg, NL80211_RATE_INFO_HE_NSS, info->nss))
+ return false;
+ if (nla_put_u8(msg, NL80211_RATE_INFO_HE_GI, info->he_gi))
+ return false;
+ if (nla_put_u8(msg, NL80211_RATE_INFO_HE_DCM, info->he_dcm))
+ return false;
+ if (info->bw == RATE_INFO_BW_HE_RU &&
+ nla_put_u8(msg, NL80211_RATE_INFO_HE_RU_ALLOC,
+ info->he_ru_alloc))
+ return false;
}
nla_nest_end(msg, rate);
#define PUT_SINFO(attr, memb, type) do { \
BUILD_BUG_ON(sizeof(type) == sizeof(u64)); \
- if (sinfo->filled & (1ULL << NL80211_STA_INFO_ ## attr) && \
+ if (sinfo->filled & BIT_ULL(NL80211_STA_INFO_ ## attr) && \
nla_put_ ## type(msg, NL80211_STA_INFO_ ## attr, \
sinfo->memb)) \
goto nla_put_failure; \
} while (0)
#define PUT_SINFO_U64(attr, memb) do { \
- if (sinfo->filled & (1ULL << NL80211_STA_INFO_ ## attr) && \
+ if (sinfo->filled & BIT_ULL(NL80211_STA_INFO_ ## attr) && \
nla_put_u64_64bit(msg, NL80211_STA_INFO_ ## attr, \
sinfo->memb, NL80211_STA_INFO_PAD)) \
goto nla_put_failure; \
PUT_SINFO(CONNECTED_TIME, connected_time, u32);
PUT_SINFO(INACTIVE_TIME, inactive_time, u32);
- if (sinfo->filled & (BIT(NL80211_STA_INFO_RX_BYTES) |
- BIT(NL80211_STA_INFO_RX_BYTES64)) &&
+ if (sinfo->filled & (BIT_ULL(NL80211_STA_INFO_RX_BYTES) |
+ BIT_ULL(NL80211_STA_INFO_RX_BYTES64)) &&
nla_put_u32(msg, NL80211_STA_INFO_RX_BYTES,
(u32)sinfo->rx_bytes))
goto nla_put_failure;
- if (sinfo->filled & (BIT(NL80211_STA_INFO_TX_BYTES) |
- BIT(NL80211_STA_INFO_TX_BYTES64)) &&
+ if (sinfo->filled & (BIT_ULL(NL80211_STA_INFO_TX_BYTES) |
+ BIT_ULL(NL80211_STA_INFO_TX_BYTES64)) &&
nla_put_u32(msg, NL80211_STA_INFO_TX_BYTES,
(u32)sinfo->tx_bytes))
goto nla_put_failure;
default:
break;
}
- if (sinfo->filled & BIT(NL80211_STA_INFO_CHAIN_SIGNAL)) {
+ if (sinfo->filled & BIT_ULL(NL80211_STA_INFO_CHAIN_SIGNAL)) {
if (!nl80211_put_signal(msg, sinfo->chains,
sinfo->chain_signal,
NL80211_STA_INFO_CHAIN_SIGNAL))
goto nla_put_failure;
}
- if (sinfo->filled & BIT(NL80211_STA_INFO_CHAIN_SIGNAL_AVG)) {
+ if (sinfo->filled & BIT_ULL(NL80211_STA_INFO_CHAIN_SIGNAL_AVG)) {
if (!nl80211_put_signal(msg, sinfo->chains,
sinfo->chain_signal_avg,
NL80211_STA_INFO_CHAIN_SIGNAL_AVG))
goto nla_put_failure;
}
- if (sinfo->filled & BIT(NL80211_STA_INFO_TX_BITRATE)) {
+ if (sinfo->filled & BIT_ULL(NL80211_STA_INFO_TX_BITRATE)) {
if (!nl80211_put_sta_rate(msg, &sinfo->txrate,
NL80211_STA_INFO_TX_BITRATE))
goto nla_put_failure;
}
- if (sinfo->filled & BIT(NL80211_STA_INFO_RX_BITRATE)) {
+ if (sinfo->filled & BIT_ULL(NL80211_STA_INFO_RX_BITRATE)) {
if (!nl80211_put_sta_rate(msg, &sinfo->rxrate,
NL80211_STA_INFO_RX_BITRATE))
goto nla_put_failure;
PUT_SINFO(PEER_PM, peer_pm, u32);
PUT_SINFO(NONPEER_PM, nonpeer_pm, u32);
- if (sinfo->filled & BIT(NL80211_STA_INFO_BSS_PARAM)) {
+ if (sinfo->filled & BIT_ULL(NL80211_STA_INFO_BSS_PARAM)) {
bss_param = nla_nest_start(msg, NL80211_STA_INFO_BSS_PARAM);
if (!bss_param)
goto nla_put_failure;
nla_nest_end(msg, bss_param);
}
- if ((sinfo->filled & BIT(NL80211_STA_INFO_STA_FLAGS)) &&
+ if ((sinfo->filled & BIT_ULL(NL80211_STA_INFO_STA_FLAGS)) &&
nla_put(msg, NL80211_STA_INFO_STA_FLAGS,
sizeof(struct nl80211_sta_flag_update),
&sinfo->sta_flags))
return -EINVAL;
if (params->supported_rates)
return -EINVAL;
- if (params->ext_capab || params->ht_capa || params->vht_capa)
+ if (params->ext_capab || params->ht_capa || params->vht_capa ||
+ params->he_capa)
return -EINVAL;
}
if (info->attrs[NL80211_ATTR_VHT_CAPABILITY])
params->vht_capa =
nla_data(info->attrs[NL80211_ATTR_VHT_CAPABILITY]);
+ if (info->attrs[NL80211_ATTR_HE_CAPABILITY]) {
+ params->he_capa =
+ nla_data(info->attrs[NL80211_ATTR_HE_CAPABILITY]);
+ params->he_capa_len =
+ nla_len(info->attrs[NL80211_ATTR_HE_CAPABILITY]);
+
+ if (params->he_capa_len < NL80211_HE_MIN_CAPABILITY_LEN)
+ return -EINVAL;
+ }
err = nl80211_parse_sta_channel_info(info, params);
if (err)
params.vht_capa =
nla_data(info->attrs[NL80211_ATTR_VHT_CAPABILITY]);
+ if (info->attrs[NL80211_ATTR_HE_CAPABILITY]) {
+ params.he_capa =
+ nla_data(info->attrs[NL80211_ATTR_HE_CAPABILITY]);
+ params.he_capa_len =
+ nla_len(info->attrs[NL80211_ATTR_HE_CAPABILITY]);
+
+ /* max len is validated in nla policy */
+ if (params.he_capa_len < NL80211_HE_MIN_CAPABILITY_LEN)
+ return -EINVAL;
+ }
+
if (info->attrs[NL80211_ATTR_OPMODE_NOTIF]) {
params.opmode_notif_used = true;
params.opmode_notif =
if (!(params.sta_flags_set & BIT(NL80211_STA_FLAG_WME))) {
params.ht_capa = NULL;
params.vht_capa = NULL;
+
+ /* HE requires WME */
+ if (params.he_capa_len)
+ return -EINVAL;
}
/* When you run into this, adjust the code below for the new flag */
nl80211_check_s32);
/*
* Check HT operation mode based on
- * IEEE 802.11 2012 8.4.2.59 HT Operation element.
+ * IEEE 802.11-2016 9.4.2.57 HT Operation element.
*/
if (tb[NL80211_MESHCONF_HT_OPMODE]) {
ht_opmode = nla_get_u16(tb[NL80211_MESHCONF_HT_OPMODE]);
IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT))
return -EINVAL;
- if ((ht_opmode & IEEE80211_HT_OP_MODE_NON_GF_STA_PRSNT) &&
- (ht_opmode & IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT))
- return -EINVAL;
+ /* NON_HT_STA bit is reserved, but some programs set it */
+ ht_opmode &= ~IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT;
- switch (ht_opmode & IEEE80211_HT_OP_MODE_PROTECTION) {
- case IEEE80211_HT_OP_MODE_PROTECTION_NONE:
- case IEEE80211_HT_OP_MODE_PROTECTION_20MHZ:
- if (ht_opmode & IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT)
- return -EINVAL;
- break;
- case IEEE80211_HT_OP_MODE_PROTECTION_NONMEMBER:
- case IEEE80211_HT_OP_MODE_PROTECTION_NONHT_MIXED:
- if (!(ht_opmode & IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT))
- return -EINVAL;
- break;
- }
cfg->ht_opmode = ht_opmode;
mask |= (1 << (NL80211_MESHCONF_HT_OPMODE - 1));
}
return regulatory_pre_cac_allowed(wdev->wiphy);
}
+static bool nl80211_check_scan_feat(struct wiphy *wiphy, u32 flags, u32 flag,
+ enum nl80211_ext_feature_index feat)
+{
+ if (!(flags & flag))
+ return true;
+ if (wiphy_ext_feature_isset(wiphy, feat))
+ return true;
+ return false;
+}
+
static int
nl80211_check_scan_flags(struct wiphy *wiphy, struct wireless_dev *wdev,
void *request, struct nlattr **attrs,
if (((*flags & NL80211_SCAN_FLAG_LOW_PRIORITY) &&
!(wiphy->features & NL80211_FEATURE_LOW_PRIORITY_SCAN)) ||
- ((*flags & NL80211_SCAN_FLAG_LOW_SPAN) &&
- !wiphy_ext_feature_isset(wiphy,
- NL80211_EXT_FEATURE_LOW_SPAN_SCAN)) ||
- ((*flags & NL80211_SCAN_FLAG_LOW_POWER) &&
- !wiphy_ext_feature_isset(wiphy,
- NL80211_EXT_FEATURE_LOW_POWER_SCAN)) ||
- ((*flags & NL80211_SCAN_FLAG_HIGH_ACCURACY) &&
- !wiphy_ext_feature_isset(wiphy,
- NL80211_EXT_FEATURE_HIGH_ACCURACY_SCAN)))
+ !nl80211_check_scan_feat(wiphy, *flags,
+ NL80211_SCAN_FLAG_LOW_SPAN,
+ NL80211_EXT_FEATURE_LOW_SPAN_SCAN) ||
+ !nl80211_check_scan_feat(wiphy, *flags,
+ NL80211_SCAN_FLAG_LOW_POWER,
+ NL80211_EXT_FEATURE_LOW_POWER_SCAN) ||
+ !nl80211_check_scan_feat(wiphy, *flags,
+ NL80211_SCAN_FLAG_HIGH_ACCURACY,
+ NL80211_EXT_FEATURE_HIGH_ACCURACY_SCAN) ||
+ !nl80211_check_scan_feat(wiphy, *flags,
+ NL80211_SCAN_FLAG_FILS_MAX_CHANNEL_TIME,
+ NL80211_EXT_FEATURE_FILS_MAX_CHANNEL_TIME) ||
+ !nl80211_check_scan_feat(wiphy, *flags,
+ NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP,
+ NL80211_EXT_FEATURE_ACCEPT_BCAST_PROBE_RESP) ||
+ !nl80211_check_scan_feat(wiphy, *flags,
+ NL80211_SCAN_FLAG_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION,
+ NL80211_EXT_FEATURE_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION) ||
+ !nl80211_check_scan_feat(wiphy, *flags,
+ NL80211_SCAN_FLAG_OCE_PROBE_REQ_HIGH_TX_RATE,
+ NL80211_EXT_FEATURE_OCE_PROBE_REQ_HIGH_TX_RATE) ||
+ !nl80211_check_scan_feat(wiphy, *flags,
+ NL80211_SCAN_FLAG_RANDOM_SN,
+ NL80211_EXT_FEATURE_SCAN_RANDOM_SN) ||
+ !nl80211_check_scan_feat(wiphy, *flags,
+ NL80211_SCAN_FLAG_MIN_PREQ_CONTENT,
+ NL80211_EXT_FEATURE_SCAN_MIN_PREQ_CONTENT))
return -EOPNOTSUPP;
if (*flags & NL80211_SCAN_FLAG_RANDOM_ADDR) {
return err;
}
- if ((*flags & NL80211_SCAN_FLAG_FILS_MAX_CHANNEL_TIME) &&
- !wiphy_ext_feature_isset(wiphy,
- NL80211_EXT_FEATURE_FILS_MAX_CHANNEL_TIME))
- return -EOPNOTSUPP;
-
- if ((*flags & NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP) &&
- !wiphy_ext_feature_isset(wiphy,
- NL80211_EXT_FEATURE_ACCEPT_BCAST_PROBE_RESP))
- return -EOPNOTSUPP;
-
- if ((*flags & NL80211_SCAN_FLAG_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION) &&
- !wiphy_ext_feature_isset(wiphy,
- NL80211_EXT_FEATURE_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION))
- return -EOPNOTSUPP;
-
- if ((*flags & NL80211_SCAN_FLAG_OCE_PROBE_REQ_HIGH_TX_RATE) &&
- !wiphy_ext_feature_isset(wiphy,
- NL80211_EXT_FEATURE_OCE_PROBE_REQ_HIGH_TX_RATE))
- return -EOPNOTSUPP;
-
return 0;
}
if (err)
return err;
- if (sinfo.filled & BIT(NL80211_STA_INFO_BEACON_SIGNAL_AVG))
+ if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_BEACON_SIGNAL_AVG))
wdev->cqm_config->last_rssi_event_value =
(s8) sinfo.rx_beacon_signal_avg;
}
rem) {
u8 *mask_pat;
- nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat,
- nl80211_packet_pattern_policy,
- info->extack);
+ err = nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat,
+ nl80211_packet_pattern_policy,
+ info->extack);
+ if (err)
+ goto error;
+
err = -EINVAL;
if (!pat_tb[NL80211_PKTPAT_MASK] ||
!pat_tb[NL80211_PKTPAT_PATTERN])
rem) {
u8 *mask_pat;
- nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat,
- nl80211_packet_pattern_policy, NULL);
+ err = nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat,
+ nl80211_packet_pattern_policy, NULL);
+ if (err)
+ return err;
+
if (!pat_tb[NL80211_PKTPAT_MASK] ||
!pat_tb[NL80211_PKTPAT_PATTERN])
return -EINVAL;
struct cfg80211_registered_device *rdev = dev_to_rdev(dev);
int ret = 0;
- rdev->suspend_at = get_seconds();
+ rdev->suspend_at = ktime_get_boottime_seconds();
rtnl_lock();
if (rdev->wiphy.registered) {
int ret = 0;
/* Age scan results with time spent in suspend */
- cfg80211_bss_age(rdev, get_seconds() - rdev->suspend_at);
+ cfg80211_bss_age(rdev, ktime_get_boottime_seconds() - rdev->suspend_at);
rtnl_lock();
if (rdev->wiphy.registered && rdev->ops->resume)
*
* Copyright 2007-2009 Johannes Berg <johannes@sipsolutions.net>
* Copyright 2013-2014 Intel Mobile Communications GmbH
+ * Copyright 2017 Intel Deutschland GmbH
*/
#include <linux/export.h>
#include <linux/bitops.h>
return 0;
}
+static u32 cfg80211_calculate_bitrate_he(struct rate_info *rate)
+{
+#define SCALE 2048
+ u16 mcs_divisors[12] = {
+ 34133, /* 16.666666... */
+ 17067, /* 8.333333... */
+ 11378, /* 5.555555... */
+ 8533, /* 4.166666... */
+ 5689, /* 2.777777... */
+ 4267, /* 2.083333... */
+ 3923, /* 1.851851... */
+ 3413, /* 1.666666... */
+ 2844, /* 1.388888... */
+ 2560, /* 1.250000... */
+ 2276, /* 1.111111... */
+ 2048, /* 1.000000... */
+ };
+ u32 rates_160M[3] = { 960777777, 907400000, 816666666 };
+ u32 rates_969[3] = { 480388888, 453700000, 408333333 };
+ u32 rates_484[3] = { 229411111, 216666666, 195000000 };
+ u32 rates_242[3] = { 114711111, 108333333, 97500000 };
+ u32 rates_106[3] = { 40000000, 37777777, 34000000 };
+ u32 rates_52[3] = { 18820000, 17777777, 16000000 };
+ u32 rates_26[3] = { 9411111, 8888888, 8000000 };
+ u64 tmp;
+ u32 result;
+
+ if (WARN_ON_ONCE(rate->mcs > 11))
+ return 0;
+
+ if (WARN_ON_ONCE(rate->he_gi > NL80211_RATE_INFO_HE_GI_3_2))
+ return 0;
+ if (WARN_ON_ONCE(rate->he_ru_alloc >
+ NL80211_RATE_INFO_HE_RU_ALLOC_2x996))
+ return 0;
+ if (WARN_ON_ONCE(rate->nss < 1 || rate->nss > 8))
+ return 0;
+
+ if (rate->bw == RATE_INFO_BW_160)
+ result = rates_160M[rate->he_gi];
+ else if (rate->bw == RATE_INFO_BW_80 ||
+ (rate->bw == RATE_INFO_BW_HE_RU &&
+ rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_996))
+ result = rates_969[rate->he_gi];
+ else if (rate->bw == RATE_INFO_BW_40 ||
+ (rate->bw == RATE_INFO_BW_HE_RU &&
+ rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_484))
+ result = rates_484[rate->he_gi];
+ else if (rate->bw == RATE_INFO_BW_20 ||
+ (rate->bw == RATE_INFO_BW_HE_RU &&
+ rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_242))
+ result = rates_242[rate->he_gi];
+ else if (rate->bw == RATE_INFO_BW_HE_RU &&
+ rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_106)
+ result = rates_106[rate->he_gi];
+ else if (rate->bw == RATE_INFO_BW_HE_RU &&
+ rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_52)
+ result = rates_52[rate->he_gi];
+ else if (rate->bw == RATE_INFO_BW_HE_RU &&
+ rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_26)
+ result = rates_26[rate->he_gi];
+ else if (WARN(1, "invalid HE MCS: bw:%d, ru:%d\n",
+ rate->bw, rate->he_ru_alloc))
+ return 0;
+
+ /* now scale to the appropriate MCS */
+ tmp = result;
+ tmp *= SCALE;
+ do_div(tmp, mcs_divisors[rate->mcs]);
+ result = tmp;
+
+ /* and take NSS, DCM into account */
+ result = (result * rate->nss) / 8;
+ if (rate->he_dcm)
+ result /= 2;
+
+ return result;
+}
+
u32 cfg80211_calculate_bitrate(struct rate_info *rate)
{
if (rate->flags & RATE_INFO_FLAGS_MCS)
return cfg80211_calculate_bitrate_60g(rate);
if (rate->flags & RATE_INFO_FLAGS_VHT_MCS)
return cfg80211_calculate_bitrate_vht(rate);
+ if (rate->flags & RATE_INFO_FLAGS_HE_MCS)
+ return cfg80211_calculate_bitrate_he(rate);
return rate->legacy;
}
int cfg80211_sinfo_alloc_tid_stats(struct station_info *sinfo, gfp_t gfp)
{
- sinfo->pertid = kcalloc(sizeof(*(sinfo->pertid)),
- IEEE80211_NUM_TIDS + 1, gfp);
+ sinfo->pertid = kcalloc(IEEE80211_NUM_TIDS + 1,
+ sizeof(*(sinfo->pertid)),
+ gfp);
if (!sinfo->pertid)
return -ENOMEM;
if (err)
return err;
- if (!(sinfo.filled & BIT(NL80211_STA_INFO_TX_BITRATE)))
+ if (!(sinfo.filled & BIT_ULL(NL80211_STA_INFO_TX_BITRATE)))
return -EOPNOTSUPP;
rate->value = 100000 * cfg80211_calculate_bitrate(&sinfo.txrate);
switch (rdev->wiphy.signal_type) {
case CFG80211_SIGNAL_TYPE_MBM:
- if (sinfo.filled & BIT(NL80211_STA_INFO_SIGNAL)) {
+ if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_SIGNAL)) {
int sig = sinfo.signal;
wstats.qual.updated |= IW_QUAL_LEVEL_UPDATED;
wstats.qual.updated |= IW_QUAL_QUAL_UPDATED;
break;
}
case CFG80211_SIGNAL_TYPE_UNSPEC:
- if (sinfo.filled & BIT(NL80211_STA_INFO_SIGNAL)) {
+ if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_SIGNAL)) {
wstats.qual.updated |= IW_QUAL_LEVEL_UPDATED;
wstats.qual.updated |= IW_QUAL_QUAL_UPDATED;
wstats.qual.level = sinfo.signal;
}
wstats.qual.updated |= IW_QUAL_NOISE_INVALID;
- if (sinfo.filled & BIT(NL80211_STA_INFO_RX_DROP_MISC))
+ if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_RX_DROP_MISC))
wstats.discard.misc = sinfo.rx_dropped_misc;
- if (sinfo.filled & BIT(NL80211_STA_INFO_TX_FAILED))
+ if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_TX_FAILED))
wstats.discard.retries = sinfo.tx_failed;
return &wstats;
.socketpair = sock_no_socketpair,
.accept = x25_accept,
.getname = x25_getname,
- .poll_mask = datagram_poll_mask,
+ .poll = datagram_poll,
.ioctl = x25_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = compat_x25_ioctl,
u64 addr;
int err;
+ if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index)
+ return -EINVAL;
+
if (!xskq_peek_addr(xs->umem->fq, &addr) ||
len > xs->umem->chunk_size_nohr) {
xs->rx_dropped++;
return (xs->zc) ? xsk_zc_xmit(sk) : xsk_generic_xmit(sk, m, total_len);
}
-static __poll_t xsk_poll_mask(struct socket *sock, __poll_t events)
+static unsigned int xsk_poll(struct file *file, struct socket *sock,
+ struct poll_table_struct *wait)
{
- __poll_t mask = datagram_poll_mask(sock, events);
+ unsigned int mask = datagram_poll(file, sock, wait);
struct sock *sk = sock->sk;
struct xdp_sock *xs = xdp_sk(sk);
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = sock_no_getname,
- .poll_mask = xsk_poll_mask,
+ .poll = xsk_poll,
.ioctl = sock_no_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
hostprogs-y += xdpsock
hostprogs-y += xdp_fwd
hostprogs-y += task_fd_query
+hostprogs-y += xdp_sample_pkts
# Libbpf dependencies
LIBBPF = $(TOOLS_PATH)/lib/bpf/libbpf.a
xdpsock-objs := bpf_load.o xdpsock_user.o
xdp_fwd-objs := bpf_load.o xdp_fwd_user.o
task_fd_query-objs := bpf_load.o task_fd_query_user.o $(TRACE_HELPERS)
+xdp_sample_pkts-objs := xdp_sample_pkts_user.o $(TRACE_HELPERS)
# Tell kbuild to always build the programs
always := $(hostprogs-y)
always += xdpsock_kern.o
always += xdp_fwd_kern.o
always += task_fd_query_kern.o
+always += xdp_sample_pkts_kern.o
HOSTCFLAGS += -I$(objtree)/usr/include
HOSTCFLAGS += -I$(srctree)/tools/lib/
HOSTCFLAGS_trace_event_user.o += -I$(srctree)/tools/lib/bpf/
HOSTCFLAGS_sampleip_user.o += -I$(srctree)/tools/lib/bpf/
HOSTCFLAGS_task_fd_query_user.o += -I$(srctree)/tools/lib/bpf/
+HOSTCFLAGS_xdp_sample_pkts_user.o += -I$(srctree)/tools/lib/bpf/
HOST_LOADLIBES += $(LIBBPF) -lelf
HOSTLOADLIBES_tracex4 += -lrt
struct ethhdr *eth = data;
struct ipv6hdr *ip6h;
struct iphdr *iph;
- int out_index;
u16 h_proto;
u64 nh_off;
+ int rc;
nh_off = sizeof(*eth);
if (data + nh_off > data_end)
fib_params.ifindex = ctx->ingress_ifindex;
- out_index = bpf_fib_lookup(ctx, &fib_params, sizeof(fib_params), flags);
+ rc = bpf_fib_lookup(ctx, &fib_params, sizeof(fib_params), flags);
/* verify egress index has xdp support
* TO-DO bpf_map_lookup_elem(&tx_port, &key) fails with
* NOTE: without verification that egress index supports XDP
* forwarding packets are dropped.
*/
- if (out_index > 0) {
+ if (rc == 0) {
if (h_proto == htons(ETH_P_IP))
ip_decrease_ttl(iph);
else if (h_proto == htons(ETH_P_IPV6))
memcpy(eth->h_dest, fib_params.dmac, ETH_ALEN);
memcpy(eth->h_source, fib_params.smac, ETH_ALEN);
- return bpf_redirect_map(&tx_port, out_index, 0);
+ return bpf_redirect_map(&tx_port, fib_params.ifindex, 0);
}
return XDP_PASS;
return false;
eth_type = vlan_hdr->h_vlan_encapsulated_proto;
}
- /* TODO: Handle double VLAN tagged packet */
+ /* Handle double VLAN tagged packet */
+ if (eth_type == htons(ETH_P_8021Q) || eth_type == htons(ETH_P_8021AD)) {
+ struct vlan_hdr *vlan_hdr;
+
+ vlan_hdr = (void *)eth + offset;
+ offset += sizeof(*vlan_hdr);
+ if ((void *)eth + offset > data_end)
+ return false;
+ eth_type = vlan_hdr->h_vlan_encapsulated_proto;
+ }
*eth_proto = ntohs(eth_type);
*l3_offset = offset;
* Example howto extract XDP RX-queue info
*/
#include <uapi/linux/bpf.h>
+#include <uapi/linux/if_ether.h>
+#include <uapi/linux/in.h>
#include "bpf_helpers.h"
/* Config setup from with userspace
struct config {
__u32 action;
int ifindex;
+ __u32 options;
+};
+enum cfg_options_flags {
+ NO_TOUCH = 0x0U,
+ READ_MEM = 0x1U,
+ SWAP_MAC = 0x2U,
};
struct bpf_map_def SEC("maps") config_map = {
.type = BPF_MAP_TYPE_ARRAY,
.max_entries = MAX_RXQs + 1,
};
+static __always_inline
+void swap_src_dst_mac(void *data)
+{
+ unsigned short *p = data;
+ unsigned short dst[3];
+
+ dst[0] = p[0];
+ dst[1] = p[1];
+ dst[2] = p[2];
+ p[0] = p[3];
+ p[1] = p[4];
+ p[2] = p[5];
+ p[3] = dst[0];
+ p[4] = dst[1];
+ p[5] = dst[2];
+}
+
SEC("xdp_prog0")
int xdp_prognum0(struct xdp_md *ctx)
{
if (key == MAX_RXQs)
rxq_rec->issue++;
+ /* Default: Don't touch packet data, only count packets */
+ if (unlikely(config->options & (READ_MEM|SWAP_MAC))) {
+ struct ethhdr *eth = data;
+
+ if (eth + 1 > data_end)
+ return XDP_ABORTED;
+
+ /* Avoid compiler removing this: Drop non 802.3 Ethertypes */
+ if (ntohs(eth->h_proto) < ETH_P_802_3_MIN)
+ return XDP_ABORTED;
+
+ /* XDP_TX requires changing MAC-addrs, else HW may drop.
+ * Can also be enabled with --swapmac (for test purposes)
+ */
+ if (unlikely(config->options & SWAP_MAC))
+ swap_src_dst_mac(data);
+ }
+
return config->action;
}
{"sec", required_argument, NULL, 's' },
{"no-separators", no_argument, NULL, 'z' },
{"action", required_argument, NULL, 'a' },
+ {"readmem", no_argument, NULL, 'r' },
+ {"swapmac", no_argument, NULL, 'm' },
{0, 0, NULL, 0 }
};
struct config {
__u32 action;
int ifindex;
+ __u32 options;
+};
+enum cfg_options_flags {
+ NO_TOUCH = 0x0U,
+ READ_MEM = 0x1U,
+ SWAP_MAC = 0x2U,
};
#define XDP_ACTION_MAX (XDP_TX + 1)
#define XDP_ACTION_MAX_STRLEN 11
printf("\n");
}
+static char* options2str(enum cfg_options_flags flag)
+{
+ if (flag == NO_TOUCH)
+ return "no_touch";
+ if (flag & SWAP_MAC)
+ return "swapmac";
+ if (flag & READ_MEM)
+ return "read";
+ fprintf(stderr, "ERR: Unknown config option flags");
+ exit(EXIT_FAIL);
+}
+
static void usage(char *argv[])
{
int i;
static void stats_print(struct stats_record *stats_rec,
struct stats_record *stats_prev,
- int action)
+ int action, __u32 cfg_opt)
{
unsigned int nr_rxqs = bpf_map__def(rx_queue_index_map)->max_entries;
unsigned int nr_cpus = bpf_num_possible_cpus();
int i;
/* Header */
- printf("\nRunning XDP on dev:%s (ifindex:%d) action:%s\n",
- ifname, ifindex, action2str(action));
+ printf("\nRunning XDP on dev:%s (ifindex:%d) action:%s options:%s\n",
+ ifname, ifindex, action2str(action), options2str(cfg_opt));
/* stats_global_map */
{
*b = tmp;
}
-static void stats_poll(int interval, int action)
+static void stats_poll(int interval, int action, __u32 cfg_opt)
{
struct stats_record *record, *prev;
while (1) {
swap(&prev, &record);
stats_collect(record);
- stats_print(record, prev, action);
+ stats_print(record, prev, action, cfg_opt);
sleep(interval);
}
int main(int argc, char **argv)
{
+ __u32 cfg_options= NO_TOUCH ; /* Default: Don't touch packet memory */
struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY};
struct bpf_prog_load_attr prog_load_attr = {
.prog_type = BPF_PROG_TYPE_XDP,
int interval = 2;
__u32 key = 0;
+
char action_str_buf[XDP_ACTION_MAX_STRLEN + 1 /* for \0 */] = { 0 };
int action = XDP_PASS; /* Default action */
char *action_str = NULL;
action_str = (char *)&action_str_buf;
strncpy(action_str, optarg, XDP_ACTION_MAX_STRLEN);
break;
+ case 'r':
+ cfg_options |= READ_MEM;
+ break;
+ case 'm':
+ cfg_options |= SWAP_MAC;
+ break;
case 'h':
error:
default:
}
cfg.action = action;
+ /* XDP_TX requires changing MAC-addrs, else HW may drop */
+ if (action == XDP_TX)
+ cfg_options |= SWAP_MAC;
+ cfg.options = cfg_options;
+
/* Trick to pretty printf with thousands separators use %' */
if (use_separators)
setlocale(LC_NUMERIC, "en_US");
return EXIT_FAIL_XDP;
}
- stats_poll(interval, action);
+ stats_poll(interval, action, cfg_options);
return EXIT_OK;
}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/ptrace.h>
+#include <linux/version.h>
+#include <uapi/linux/bpf.h>
+#include "bpf_helpers.h"
+
+#define SAMPLE_SIZE 64ul
+#define MAX_CPUS 128
+
+#define bpf_printk(fmt, ...) \
+({ \
+ char ____fmt[] = fmt; \
+ bpf_trace_printk(____fmt, sizeof(____fmt), \
+ ##__VA_ARGS__); \
+})
+
+struct bpf_map_def SEC("maps") my_map = {
+ .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
+ .key_size = sizeof(int),
+ .value_size = sizeof(u32),
+ .max_entries = MAX_CPUS,
+};
+
+SEC("xdp_sample")
+int xdp_sample_prog(struct xdp_md *ctx)
+{
+ void *data_end = (void *)(long)ctx->data_end;
+ void *data = (void *)(long)ctx->data;
+
+ /* Metadata will be in the perf event before the packet data. */
+ struct S {
+ u16 cookie;
+ u16 pkt_len;
+ } __packed metadata;
+
+ if (data < data_end) {
+ /* The XDP perf_event_output handler will use the upper 32 bits
+ * of the flags argument as a number of bytes to include of the
+ * packet payload in the event data. If the size is too big, the
+ * call to bpf_perf_event_output will fail and return -EFAULT.
+ *
+ * See bpf_xdp_event_output in net/core/filter.c.
+ *
+ * The BPF_F_CURRENT_CPU flag means that the event output fd
+ * will be indexed by the CPU number in the event map.
+ */
+ u64 flags = BPF_F_CURRENT_CPU;
+ u16 sample_size;
+ int ret;
+
+ metadata.cookie = 0xdead;
+ metadata.pkt_len = (u16)(data_end - data);
+ sample_size = min(metadata.pkt_len, SAMPLE_SIZE);
+ flags |= (u64)sample_size << 32;
+
+ ret = bpf_perf_event_output(ctx, &my_map, flags,
+ &metadata, sizeof(metadata));
+ if (ret)
+ bpf_printk("perf_event_output failed: %d\n", ret);
+ }
+
+ return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
+u32 _version SEC("version") = LINUX_VERSION_CODE;
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <linux/perf_event.h>
+#include <linux/bpf.h>
+#include <net/if.h>
+#include <errno.h>
+#include <assert.h>
+#include <sys/sysinfo.h>
+#include <sys/ioctl.h>
+#include <signal.h>
+#include <libbpf.h>
+#include <bpf/bpf.h>
+
+#include "perf-sys.h"
+#include "trace_helpers.h"
+
+#define MAX_CPUS 128
+static int pmu_fds[MAX_CPUS], if_idx;
+static struct perf_event_mmap_page *headers[MAX_CPUS];
+static char *if_name;
+
+static int do_attach(int idx, int fd, const char *name)
+{
+ int err;
+
+ err = bpf_set_link_xdp_fd(idx, fd, 0);
+ if (err < 0)
+ printf("ERROR: failed to attach program to %s\n", name);
+
+ return err;
+}
+
+static int do_detach(int idx, const char *name)
+{
+ int err;
+
+ err = bpf_set_link_xdp_fd(idx, -1, 0);
+ if (err < 0)
+ printf("ERROR: failed to detach program from %s\n", name);
+
+ return err;
+}
+
+#define SAMPLE_SIZE 64
+
+static int print_bpf_output(void *data, int size)
+{
+ struct {
+ __u16 cookie;
+ __u16 pkt_len;
+ __u8 pkt_data[SAMPLE_SIZE];
+ } __packed *e = data;
+ int i;
+
+ if (e->cookie != 0xdead) {
+ printf("BUG cookie %x sized %d\n",
+ e->cookie, size);
+ return LIBBPF_PERF_EVENT_ERROR;
+ }
+
+ printf("Pkt len: %-5d bytes. Ethernet hdr: ", e->pkt_len);
+ for (i = 0; i < 14 && i < e->pkt_len; i++)
+ printf("%02x ", e->pkt_data[i]);
+ printf("\n");
+
+ return LIBBPF_PERF_EVENT_CONT;
+}
+
+static void test_bpf_perf_event(int map_fd, int num)
+{
+ struct perf_event_attr attr = {
+ .sample_type = PERF_SAMPLE_RAW,
+ .type = PERF_TYPE_SOFTWARE,
+ .config = PERF_COUNT_SW_BPF_OUTPUT,
+ .wakeup_events = 1, /* get an fd notification for every event */
+ };
+ int i;
+
+ for (i = 0; i < num; i++) {
+ int key = i;
+
+ pmu_fds[i] = sys_perf_event_open(&attr, -1/*pid*/, i/*cpu*/,
+ -1/*group_fd*/, 0);
+
+ assert(pmu_fds[i] >= 0);
+ assert(bpf_map_update_elem(map_fd, &key,
+ &pmu_fds[i], BPF_ANY) == 0);
+ ioctl(pmu_fds[i], PERF_EVENT_IOC_ENABLE, 0);
+ }
+}
+
+static void sig_handler(int signo)
+{
+ do_detach(if_idx, if_name);
+ exit(0);
+}
+
+int main(int argc, char **argv)
+{
+ struct bpf_prog_load_attr prog_load_attr = {
+ .prog_type = BPF_PROG_TYPE_XDP,
+ };
+ struct bpf_object *obj;
+ struct bpf_map *map;
+ int prog_fd, map_fd;
+ char filename[256];
+ int ret, err, i;
+ int numcpus;
+
+ if (argc < 2) {
+ printf("Usage: %s <ifname>\n", argv[0]);
+ return 1;
+ }
+
+ numcpus = get_nprocs();
+ if (numcpus > MAX_CPUS)
+ numcpus = MAX_CPUS;
+
+ snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+ prog_load_attr.file = filename;
+
+ if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd))
+ return 1;
+
+ if (!prog_fd) {
+ printf("load_bpf_file: %s\n", strerror(errno));
+ return 1;
+ }
+
+ map = bpf_map__next(NULL, obj);
+ if (!map) {
+ printf("finding a map in obj file failed\n");
+ return 1;
+ }
+ map_fd = bpf_map__fd(map);
+
+ if_idx = if_nametoindex(argv[1]);
+ if (!if_idx)
+ if_idx = strtoul(argv[1], NULL, 0);
+
+ if (!if_idx) {
+ fprintf(stderr, "Invalid ifname\n");
+ return 1;
+ }
+ if_name = argv[1];
+ err = do_attach(if_idx, prog_fd, argv[1]);
+ if (err)
+ return err;
+
+ if (signal(SIGINT, sig_handler) ||
+ signal(SIGHUP, sig_handler) ||
+ signal(SIGTERM, sig_handler)) {
+ perror("signal");
+ return 1;
+ }
+
+ test_bpf_perf_event(map_fd, numcpus);
+
+ for (i = 0; i < numcpus; i++)
+ if (perf_event_mmap_header(pmu_fds[i], &headers[i]) < 0)
+ return 1;
+
+ ret = perf_event_poller_multi(pmu_fds, headers, numcpus,
+ print_bpf_output);
+ kill(0, SIGINT);
+ return ret;
+}
"$(CC_FLAGS_FTRACE)" ]; then \
$(sub_cmd_record_mcount) \
fi;
+endif # -record-mcount
endif # CONFIG_FTRACE_MCOUNT_RECORD
ifdef CONFIG_STACK_VALIDATION
objtool_args += --retpoline
endif
endif
-endif
ifdef CONFIG_MODVERSIONS
#!/bin/sh
# SPDX-License-Identifier: GPL-2.0
-cat << "END" | $@ -x c - -o /dev/null >/dev/null 2>&1 && echo "y"
+cat << "END" | $@ -x c - -o /dev/null >/dev/null 2>&1
#include <stdio.h>
int main(void)
{
"A patch subject line should describe the change not the tool that found it\n" . $herecurr);
}
-# Check for old stable address
- if ($line =~ /^\s*cc:\s*.*<?\bstable\@kernel\.org\b>?.*$/i) {
- ERROR("STABLE_ADDRESS",
- "The 'stable' address should be 'stable\@vger.kernel.org'\n" . $herecurr);
- }
-
# Check for unwanted Gerrit info
if ($in_commit_log && $line =~ /^\s*change-id:/i) {
ERROR("GERRIT_CHANGE_ID",
#!/bin/sh
# SPDX-License-Identifier: GPL-2.0
-echo "int foo(void) { char X[200]; return 3; }" | $* -S -x c -c -O0 -mcmodel=kernel -fno-PIE -fstack-protector - -o - 2> /dev/null | grep -q "%gs"
+echo "int foo(void) { char X[200]; return 3; }" | $* -S -x c -c -m64 -O0 -mcmodel=kernel -fno-PIE -fstack-protector - -o - 2> /dev/null | grep -q "%gs"
* config BAZ
* int "BAZ Value"
* range 1..255
+ *
+ * Please, also check zconf.y:print_symbol() when modifying the
+ * list of property types!
*/
enum prop_type {
P_UNKNOWN,
nread--;
/* remove trailing new lines */
- while (buf[nread - 1] == '\n')
+ while (nread > 0 && buf[nread - 1] == '\n')
nread--;
buf[nread] = 0;
static struct menu *current_menu, *current_entry;
%}
-%expect 32
+%expect 31
%union
{
/* if entry */
-if_entry: T_IF expr nl
+if_entry: T_IF expr T_EOL
{
printd(DEBUG_PARSE, "%s:%d:if\n", zconf_curname(), zconf_lineno());
menu_add_entry(NULL);
print_quoted_string(out, prop->text);
fputc('\n', out);
break;
+ case P_SYMBOL:
+ fputs( " symbol ", out);
+ fprintf(out, "%s\n", prop->sym->name);
+ break;
default:
fprintf(out, " unknown prop %d!\n", prop->type);
break;
* The src pointer is defined as Z || other info where Z is the shared secret
* from DH and other info is an arbitrary string (see SP800-56A section
* 5.8.1.2).
+ *
+ * 'dlen' must be a multiple of the digest size.
*/
static int kdf_ctr(struct kdf_sdesc *sdesc, const u8 *src, unsigned int slen,
u8 *dst, unsigned int dlen, unsigned int zlen)
{
uint8_t *outbuf = NULL;
int ret;
- size_t outbuf_len = round_up(buflen,
- crypto_shash_digestsize(sdesc->shash.tfm));
+ size_t outbuf_len = roundup(buflen,
+ crypto_shash_digestsize(sdesc->shash.tfm));
outbuf = kmalloc(outbuf_len, GFP_KERNEL);
if (!outbuf) {
static ssize_t sel_read_policy(struct file *filp, char __user *buf,
size_t count, loff_t *ppos)
{
- struct selinux_fs_info *fsi = file_inode(filp)->i_sb->s_fs_info;
struct policy_load_memory *plm = filp->private_data;
int ret;
- mutex_lock(&fsi->mutex);
-
ret = avc_has_perm(&selinux_state,
current_sid(), SECINITSID_SECURITY,
SECCLASS_SECURITY, SECURITY__READ_POLICY, NULL);
if (ret)
- goto out;
+ return ret;
- ret = simple_read_from_buffer(buf, count, ppos, plm->data, plm->len);
-out:
- mutex_unlock(&fsi->mutex);
- return ret;
+ return simple_read_from_buffer(buf, count, ppos, plm->data, plm->len);
}
static vm_fault_t sel_mmap_policy_fault(struct vm_fault *vmf)
ret = -EINVAL;
if (index >= fsi->bool_num || strcmp(name,
fsi->bool_pending_names[index]))
- goto out;
+ goto out_unlock;
ret = -ENOMEM;
page = (char *)get_zeroed_page(GFP_KERNEL);
if (!page)
- goto out;
+ goto out_unlock;
cur_enforcing = security_get_bool_value(fsi->state, index);
if (cur_enforcing < 0) {
ret = cur_enforcing;
- goto out;
+ goto out_unlock;
}
length = scnprintf(page, PAGE_SIZE, "%d %d", cur_enforcing,
fsi->bool_pending_values[index]);
- ret = simple_read_from_buffer(buf, count, ppos, page, length);
-out:
mutex_unlock(&fsi->mutex);
+ ret = simple_read_from_buffer(buf, count, ppos, page, length);
+out_free:
free_page((unsigned long)page);
return ret;
+
+out_unlock:
+ mutex_unlock(&fsi->mutex);
+ goto out_free;
}
static ssize_t sel_write_bool(struct file *filep, const char __user *buf,
unsigned index = file_inode(filep)->i_ino & SEL_INO_MASK;
const char *name = filep->f_path.dentry->d_name.name;
+ if (count >= PAGE_SIZE)
+ return -ENOMEM;
+
+ /* No partial writes. */
+ if (*ppos != 0)
+ return -EINVAL;
+
+ page = memdup_user_nul(buf, count);
+ if (IS_ERR(page))
+ return PTR_ERR(page);
+
mutex_lock(&fsi->mutex);
length = avc_has_perm(&selinux_state,
fsi->bool_pending_names[index]))
goto out;
- length = -ENOMEM;
- if (count >= PAGE_SIZE)
- goto out;
-
- /* No partial writes. */
- length = -EINVAL;
- if (*ppos != 0)
- goto out;
-
- page = memdup_user_nul(buf, count);
- if (IS_ERR(page)) {
- length = PTR_ERR(page);
- page = NULL;
- goto out;
- }
-
length = -EINVAL;
if (sscanf(page, "%d", &new_value) != 1)
goto out;
ssize_t length;
int new_value;
+ if (count >= PAGE_SIZE)
+ return -ENOMEM;
+
+ /* No partial writes. */
+ if (*ppos != 0)
+ return -EINVAL;
+
+ page = memdup_user_nul(buf, count);
+ if (IS_ERR(page))
+ return PTR_ERR(page);
+
mutex_lock(&fsi->mutex);
length = avc_has_perm(&selinux_state,
if (length)
goto out;
- length = -ENOMEM;
- if (count >= PAGE_SIZE)
- goto out;
-
- /* No partial writes. */
- length = -EINVAL;
- if (*ppos != 0)
- goto out;
-
- page = memdup_user_nul(buf, count);
- if (IS_ERR(page)) {
- length = PTR_ERR(page);
- page = NULL;
- goto out;
- }
-
length = -EINVAL;
if (sscanf(page, "%d", &new_value) != 1)
goto out;
struct smack_known *skp = smk_of_task_struct(p);
isp->smk_inode = skp;
+ isp->smk_flags |= SMK_INODE_INSTANT;
}
/*
struct snd_seq_client *cptr = NULL;
/* search for next client */
- info->client++;
+ if (info->client < INT_MAX)
+ info->client++;
if (info->client < 0)
info->client = 0;
for (; info->client < SNDRV_SEQ_MAX_CLIENTS; info->client++) {
} else {
if (id.subdevice < 0)
id.subdevice = 0;
- else
+ else if (id.subdevice < INT_MAX)
id.subdevice++;
}
}
list_for_each_entry(pcm, &codec->pcm_list_head, list)
snd_pcm_suspend_all(pcm->pcm);
state = hda_call_codec_suspend(codec);
- if (codec_has_clkstop(codec) && codec_has_epss(codec) &&
- (state & AC_PWRST_CLK_STOP_OK))
+ if (codec->link_down_at_suspend ||
+ (codec_has_clkstop(codec) && codec_has_epss(codec) &&
+ (state & AC_PWRST_CLK_STOP_OK)))
snd_hdac_codec_link_down(&codec->core);
snd_hdac_link_power(&codec->core, false);
return 0;
unsigned int power_save_node:1; /* advanced PM for each widget */
unsigned int auto_runtime_pm:1; /* enable automatic codec runtime pm */
unsigned int force_pin_prefix:1; /* Add location prefix */
+ unsigned int link_down_at_suspend:1; /* link down at runtime suspend */
#ifdef CONFIG_PM
unsigned long power_on_acct;
unsigned long power_off_acct;
enum {
QUIRK_NONE,
QUIRK_ALIENWARE,
+ QUIRK_ALIENWARE_M17XR4,
QUIRK_SBZ,
QUIRK_R3DI,
};
};
static const struct snd_pci_quirk ca0132_quirks[] = {
+ SND_PCI_QUIRK(0x1028, 0x057b, "Alienware M17x R4", QUIRK_ALIENWARE_M17XR4),
SND_PCI_QUIRK(0x1028, 0x0685, "Alienware 15 2015", QUIRK_ALIENWARE),
SND_PCI_QUIRK(0x1028, 0x0688, "Alienware 17 2015", QUIRK_ALIENWARE),
SND_PCI_QUIRK(0x1028, 0x0708, "Alienware 15 R2 2016", QUIRK_ALIENWARE),
* I think this has to do with the pin for rear surround being 0x11,
* and the center/lfe being 0x10. Usually the pin order is the opposite.
*/
-const struct snd_pcm_chmap_elem ca0132_alt_chmaps[] = {
+static const struct snd_pcm_chmap_elem ca0132_alt_chmaps[] = {
{ .channels = 2,
.map = { SNDRV_CHMAP_FL, SNDRV_CHMAP_FR } },
{ .channels = 4,
info->stream[SNDRV_PCM_STREAM_CAPTURE].nid = spec->adcs[0];
/* With the DSP enabled, desktops don't use this ADC. */
- if (spec->use_alt_functions) {
+ if (!spec->use_alt_functions) {
info = snd_hda_codec_pcm_new(codec, "CA0132 Analog Mic-In2");
if (!info)
return -ENOMEM;
* Bit 6: set to select Data2, clear for Data1
* Bit 7: set to enable DMic, clear for AMic
*/
- val = 0x23;
+ if (spec->quirk == QUIRK_ALIENWARE_M17XR4)
+ val = 0x33;
+ else
+ val = 0x23;
/* keep a copy of dmic ctl val for enable/disable dmic purpuse */
spec->dmic_ctl = val;
snd_hda_codec_write(codec, spec->input_pins[0], 0,
snd_hda_sequence_write(codec, spec->base_init_verbs);
- if (spec->quirk != QUIRK_NONE)
+ if (spec->use_alt_functions)
ca0132_alt_init(codec);
ca0132_download_dsp(codec);
case QUIRK_R3DI:
r3di_setup_defaults(codec);
break;
- case QUIRK_NONE:
- case QUIRK_ALIENWARE:
+ case QUIRK_SBZ:
+ break;
+ default:
ca0132_setup_defaults(codec);
ca0132_init_analog_mic2(codec);
ca0132_init_dmic(codec);
static void ca0132_config(struct hda_codec *codec)
{
struct ca0132_spec *spec = codec->spec;
- struct auto_pin_cfg *cfg = &spec->autocfg;
spec->dacs[0] = 0x2;
spec->dacs[1] = 0x3;
/* SPDIF I/O */
spec->dig_out = 0x05;
spec->multiout.dig_out_nid = spec->dig_out;
- cfg->dig_out_pins[0] = 0x0c;
- cfg->dig_outs = 1;
- cfg->dig_out_type[0] = HDA_PCM_TYPE_SPDIF;
spec->dig_in = 0x09;
- cfg->dig_in_pin = 0x0e;
- cfg->dig_in_type = HDA_PCM_TYPE_SPDIF;
break;
case QUIRK_R3DI:
codec_dbg(codec, "%s: QUIRK_R3DI applied.\n", __func__);
/* SPDIF I/O */
spec->dig_out = 0x05;
spec->multiout.dig_out_nid = spec->dig_out;
- cfg->dig_out_pins[0] = 0x0c;
- cfg->dig_outs = 1;
- cfg->dig_out_type[0] = HDA_PCM_TYPE_SPDIF;
break;
default:
spec->num_outputs = 2;
/* SPDIF I/O */
spec->dig_out = 0x05;
spec->multiout.dig_out_nid = spec->dig_out;
- cfg->dig_out_pins[0] = 0x0c;
- cfg->dig_outs = 1;
- cfg->dig_out_type[0] = HDA_PCM_TYPE_SPDIF;
spec->dig_in = 0x09;
- cfg->dig_in_pin = 0x0e;
- cfg->dig_in_type = HDA_PCM_TYPE_SPDIF;
break;
}
}
static int ca0132_prepare_verbs(struct hda_codec *codec)
{
/* Verbs + terminator (an empty element) */
-#define NUM_SPEC_VERBS 4
+#define NUM_SPEC_VERBS 2
struct ca0132_spec *spec = codec->spec;
spec->chip_init_verbs = ca0132_init_verbs0;
if (!spec->spec_init_verbs)
return -ENOMEM;
- /* HP jack autodetection */
- spec->spec_init_verbs[0].nid = spec->unsol_tag_hp;
- spec->spec_init_verbs[0].param = AC_VERB_SET_UNSOLICITED_ENABLE;
- spec->spec_init_verbs[0].verb = AC_USRSP_EN | spec->unsol_tag_hp;
-
- /* MIC1 jack autodetection */
- spec->spec_init_verbs[1].nid = spec->unsol_tag_amic1;
- spec->spec_init_verbs[1].param = AC_VERB_SET_UNSOLICITED_ENABLE;
- spec->spec_init_verbs[1].verb = AC_USRSP_EN | spec->unsol_tag_amic1;
-
/* config EAPD */
- spec->spec_init_verbs[2].nid = 0x0b;
- spec->spec_init_verbs[2].param = 0x78D;
- spec->spec_init_verbs[2].verb = 0x00;
+ spec->spec_init_verbs[0].nid = 0x0b;
+ spec->spec_init_verbs[0].param = 0x78D;
+ spec->spec_init_verbs[0].verb = 0x00;
/* Previously commented configuration */
/*
- spec->spec_init_verbs[3].nid = 0x0b;
- spec->spec_init_verbs[3].param = AC_VERB_SET_EAPD_BTLENABLE;
+ spec->spec_init_verbs[2].nid = 0x0b;
+ spec->spec_init_verbs[2].param = AC_VERB_SET_EAPD_BTLENABLE;
+ spec->spec_init_verbs[2].verb = 0x02;
+
+ spec->spec_init_verbs[3].nid = 0x10;
+ spec->spec_init_verbs[3].param = 0x78D;
spec->spec_init_verbs[3].verb = 0x02;
spec->spec_init_verbs[4].nid = 0x10;
- spec->spec_init_verbs[4].param = 0x78D;
+ spec->spec_init_verbs[4].param = AC_VERB_SET_EAPD_BTLENABLE;
spec->spec_init_verbs[4].verb = 0x02;
-
- spec->spec_init_verbs[5].nid = 0x10;
- spec->spec_init_verbs[5].param = AC_VERB_SET_EAPD_BTLENABLE;
- spec->spec_init_verbs[5].verb = 0x02;
*/
/* Terminator: spec->spec_init_verbs[NUM_SPEC_VERBS-1] */
spec->chmap.channels_max = max(spec->chmap.channels_max, 8u);
+ /* AMD GPUs have neither EPSS nor CLKSTOP bits, hence preventing
+ * the link-down as is. Tell the core to allow it.
+ */
+ codec->link_down_at_suspend = 1;
+
return 0;
}
SND_PCI_QUIRK(0x10cf, 0x1397, "Fujitsu Lifebook S7110", ALC262_FIXUP_FSC_S7110),
SND_PCI_QUIRK(0x10cf, 0x142d, "Fujitsu Lifebook E8410", ALC262_FIXUP_BENQ),
SND_PCI_QUIRK(0x10f1, 0x2915, "Tyan Thunder n6650W", ALC262_FIXUP_TYAN),
+ SND_PCI_QUIRK(0x1734, 0x1141, "FSC ESPRIMO U9210", ALC262_FIXUP_FSC_H270),
SND_PCI_QUIRK(0x1734, 0x1147, "FSC Celsius H270", ALC262_FIXUP_FSC_H270),
SND_PCI_QUIRK(0x17aa, 0x384e, "Lenovo 3000", ALC262_FIXUP_LENOVO_3000),
SND_PCI_QUIRK(0x17ff, 0x0560, "Benq ED8", ALC262_FIXUP_BENQ),
struct alc_spec *spec = codec->spec;
if (action == HDA_FIXUP_ACT_PRE_PROBE) {
- spec->shutup = alc_no_shutup; /* reduce click noise */
spec->reboot_notify = alc_d3_at_reboot; /* reduce noise */
spec->parse_flags = HDA_PINCFG_NO_HP_FIXUP;
codec->power_save_node = 0; /* avoid click noises */
/* for hda_fixup_thinkpad_acpi() */
#include "thinkpad_helper.c"
+static void alc_fixup_thinkpad_acpi(struct hda_codec *codec,
+ const struct hda_fixup *fix, int action)
+{
+ alc_fixup_no_shutup(codec, fix, action); /* reduce click noise */
+ hda_fixup_thinkpad_acpi(codec, fix, action);
+}
+
/* for dell wmi mic mute led */
#include "dell_wmi_helper.c"
},
[ALC269_FIXUP_THINKPAD_ACPI] = {
.type = HDA_FIXUP_FUNC,
- .v.func = hda_fixup_thinkpad_acpi,
+ .v.func = alc_fixup_thinkpad_acpi,
.chained = true,
.chain_id = ALC269_FIXUP_SKU_IGNORE,
},
SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
SND_PCI_QUIRK(0x17aa, 0x30e2, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
SND_PCI_QUIRK(0x17aa, 0x310c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
+ SND_PCI_QUIRK(0x17aa, 0x312a, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
SND_PCI_QUIRK(0x17aa, 0x312f, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
- SND_PCI_QUIRK(0x17aa, 0x3138, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
+ SND_PCI_QUIRK(0x17aa, 0x3136, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
SND_PCI_QUIRK(0x17aa, 0x313c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI),
SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC),
{0x14, 0x90170110},
{0x19, 0x02a11030},
{0x21, 0x02211020}),
+ SND_HDA_PIN_QUIRK(0x10ec0235, 0x17aa, "Lenovo", ALC294_FIXUP_LENOVO_MIC_LOCATION,
+ {0x14, 0x90170110},
+ {0x19, 0x02a11030},
+ {0x1a, 0x02a11040},
+ {0x1b, 0x01014020},
+ {0x21, 0x0221101f}),
SND_HDA_PIN_QUIRK(0x10ec0236, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
{0x12, 0x90a60140},
{0x14, 0x90170110},
chip->port_dsp_bar = pci_ioremap_bar(pci, 2);
if (!chip->port_dsp_bar) {
dev_err(card->dev, "cannot remap PCI memory region\n");
+ err = -ENOMEM;
goto remap_pci_failed;
}
#define KVM_VGIC_V3_ADDR_TYPE_DIST 2
#define KVM_VGIC_V3_ADDR_TYPE_REDIST 3
#define KVM_VGIC_ITS_ADDR_TYPE 4
+#define KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION 5
#define KVM_VGIC_V3_DIST_SIZE SZ_64K
#define KVM_VGIC_V3_REDIST_SIZE (2 * SZ_64K)
#define KVM_VGIC_V3_ADDR_TYPE_DIST 2
#define KVM_VGIC_V3_ADDR_TYPE_REDIST 3
#define KVM_VGIC_ITS_ADDR_TYPE 4
+#define KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION 5
#define KVM_VGIC_V3_DIST_SIZE SZ_64K
#define KVM_VGIC_V3_REDIST_SIZE (2 * SZ_64K)
#define KVM_REG_PPC_PSSCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbd)
#define KVM_REG_PPC_DEC_EXPIRY (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbe)
+#define KVM_REG_PPC_ONLINE (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xbf)
/* Transactional Memory checkpointed state:
* This is all GPRs, all VSX regs and a subset of SPRs
#define __NR_pkey_alloc 384
#define __NR_pkey_free 385
#define __NR_pkey_mprotect 386
+#define __NR_rseq 387
#endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */
#define X86_FEATURE_AMD_IBPB (13*32+12) /* "" Indirect Branch Prediction Barrier */
#define X86_FEATURE_AMD_IBRS (13*32+14) /* "" Indirect Branch Restricted Speculation */
#define X86_FEATURE_AMD_STIBP (13*32+15) /* "" Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_AMD_SSBD (13*32+24) /* "" Speculative Store Bypass Disable */
#define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */
+#define X86_FEATURE_AMD_SSB_NO (13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */
/* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */
#define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */
--- /dev/null
+ifndef allow-override
+ include ../scripts/Makefile.include
+ include ../scripts/utilities.mak
+else
+ # Assume Makefile.helpers is being run from bpftool/Documentation
+ # subdirectory. Go up two more directories to fetch bpf.h header and
+ # associated script.
+ UP2DIR := ../../
+endif
+
+INSTALL ?= install
+RM ?= rm -f
+RMDIR ?= rmdir --ignore-fail-on-non-empty
+
+ifeq ($(V),1)
+ Q =
+else
+ Q = @
+endif
+
+prefix ?= /usr/local
+mandir ?= $(prefix)/man
+man7dir = $(mandir)/man7
+
+HELPERS_RST = bpf-helpers.rst
+MAN7_RST = $(HELPERS_RST)
+
+_DOC_MAN7 = $(patsubst %.rst,%.7,$(MAN7_RST))
+DOC_MAN7 = $(addprefix $(OUTPUT),$(_DOC_MAN7))
+
+helpers: man7
+man7: $(DOC_MAN7)
+
+RST2MAN_DEP := $(shell command -v rst2man 2>/dev/null)
+
+$(OUTPUT)$(HELPERS_RST): $(UP2DIR)../../include/uapi/linux/bpf.h
+ $(QUIET_GEN)$(UP2DIR)../../scripts/bpf_helpers_doc.py --filename $< > $@
+
+$(OUTPUT)%.7: $(OUTPUT)%.rst
+ifndef RST2MAN_DEP
+ $(error "rst2man not found, but required to generate man pages")
+endif
+ $(QUIET_GEN)rst2man $< > $@
+
+helpers-clean:
+ $(call QUIET_CLEAN, eBPF_helpers-manpage)
+ $(Q)$(RM) $(DOC_MAN7) $(OUTPUT)$(HELPERS_RST)
+
+helpers-install: helpers
+ $(call QUIET_INSTALL, eBPF_helpers-manpage)
+ $(Q)$(INSTALL) -d -m 755 $(DESTDIR)$(man7dir)
+ $(Q)$(INSTALL) -m 644 $(DOC_MAN7) $(DESTDIR)$(man7dir)
+
+helpers-uninstall:
+ $(call QUIET_UNINST, eBPF_helpers-manpage)
+ $(Q)$(RM) $(addprefix $(DESTDIR)$(man7dir)/,$(_DOC_MAN7))
+ $(Q)$(RMDIR) $(DESTDIR)$(man7dir)
+
+.PHONY: helpers helpers-clean helpers-install helpers-uninstall
mandir ?= $(prefix)/man
man8dir = $(mandir)/man8
-MAN8_RST = $(wildcard *.rst)
+# Load targets for building eBPF helpers man page.
+include ../../Makefile.helpers
+
+MAN8_RST = $(filter-out $(HELPERS_RST),$(wildcard *.rst))
_DOC_MAN8 = $(patsubst %.rst,%.8,$(MAN8_RST))
DOC_MAN8 = $(addprefix $(OUTPUT),$(_DOC_MAN8))
-man: man8
+man: man8 helpers
man8: $(DOC_MAN8)
RST2MAN_DEP := $(shell command -v rst2man 2>/dev/null)
endif
$(QUIET_GEN)rst2man $< > $@
-clean:
+clean: helpers-clean
$(call QUIET_CLEAN, Documentation)
$(Q)$(RM) $(DOC_MAN8)
-install: man
+install: man helpers-install
$(call QUIET_INSTALL, Documentation-man)
$(Q)$(INSTALL) -d -m 755 $(DESTDIR)$(man8dir)
$(Q)$(INSTALL) -m 644 $(DOC_MAN8) $(DESTDIR)$(man8dir)
-uninstall:
+uninstall: helpers-uninstall
$(call QUIET_UNINST, Documentation-man)
$(Q)$(RM) $(addprefix $(DESTDIR)$(man8dir)/,$(_DOC_MAN8))
$(Q)$(RMDIR) $(DESTDIR)$(man8dir)
*OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-f** | **--bpffs** } }
*COMMANDS* :=
- { **show** | **list** | **attach** | **detach** | **help** }
+ { **show** | **list** | **tree** | **attach** | **detach** | **help** }
MAP COMMANDS
=============
| **bpftool** **cgroup { show | list }** *CGROUP*
+| **bpftool** **cgroup tree** [*CGROUP_ROOT*]
| **bpftool** **cgroup attach** *CGROUP* *ATTACH_TYPE* *PROG* [*ATTACH_FLAGS*]
| **bpftool** **cgroup detach** *CGROUP* *ATTACH_TYPE* *PROG*
| **bpftool** **cgroup help**
Output will start with program ID followed by attach type,
attach flags and program name.
+ **bpftool cgroup tree** [*CGROUP_ROOT*]
+ Iterate over all cgroups in *CGROUP_ROOT* and list all
+ attached programs. If *CGROUP_ROOT* is not specified,
+ bpftool uses cgroup v2 mountpoint.
+
+ The output is similar to the output of cgroup show/list
+ commands: it starts with absolute cgroup path, followed by
+ program ID, attach type, attach flags and program name.
+
**bpftool cgroup attach** *CGROUP* *ATTACH_TYPE* *PROG* [*ATTACH_FLAGS*]
Attach program *PROG* to the cgroup *CGROUP* with attach type
*ATTACH_TYPE* and optional *ATTACH_FLAGS*.
| **bpftool** **prog dump xlated** *PROG* [{**file** *FILE* | **opcodes** | **visual**}]
| **bpftool** **prog dump jited** *PROG* [{**file** *FILE* | **opcodes**}]
| **bpftool** **prog pin** *PROG* *FILE*
-| **bpftool** **prog load** *OBJ* *FILE*
+| **bpftool** **prog load** *OBJ* *FILE* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*]
| **bpftool** **prog help**
|
+| *MAP* := { **id** *MAP_ID* | **pinned** *FILE* }
| *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* }
+| *TYPE* := {
+| **socket** | **kprobe** | **kretprobe** | **classifier** | **action** |
+| **tracepoint** | **raw_tracepoint** | **xdp** | **perf_event** | **cgroup/skb** |
+| **cgroup/sock** | **cgroup/dev** | **lwt_in** | **lwt_out** | **lwt_xmit** |
+| **lwt_seg6local** | **sockops** | **sk_skb** | **sk_msg** | **lirc_mode2** |
+| **cgroup/bind4** | **cgroup/bind6** | **cgroup/post_bind4** | **cgroup/post_bind6** |
+| **cgroup/connect4** | **cgroup/connect6** | **cgroup/sendmsg4** | **cgroup/sendmsg6**
+| }
+
DESCRIPTION
===========
Note: *FILE* must be located in *bpffs* mount.
- **bpftool prog load** *OBJ* *FILE*
+ **bpftool prog load** *OBJ* *FILE* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*]
Load bpf program from binary *OBJ* and pin as *FILE*.
+ **type** is optional, if not specified program type will be
+ inferred from section names.
+ By default bpftool will create new maps as declared in the ELF
+ object being loaded. **map** parameter allows for the reuse
+ of existing maps. It can be specified multiple times, each
+ time for a different map. *IDX* refers to index of the map
+ to be replaced in the ELF file counting from 0, while *NAME*
+ allows to replace a map by name. *MAP* specifies the map to
+ use, referring to it by **id** or through a **pinned** file.
+ If **dev** *NAME* is specified program will be loaded onto
+ given networking device (offload).
Note: *FILE* must be located in *bpffs* mount.
mov %rbx,0x0(%rbp)
48 89 5d 00
+|
+| **# bpftool prog load xdp1_kern.o /sys/fs/bpf/xdp1 type xdp map name rxcnt id 7**
+| **# bpftool prog show pinned /sys/fs/bpf/xdp1**
+| 9: xdp name xdp_prog1 tag 539ec6ce11b52f98 gpl
+| loaded_at 2018-06-25T16:17:31-0700 uid 0
+| xlated 488B jited 336B memlock 4096B map_ids 7
+| **# rm /sys/fs/bpf/xdp1**
+|
SEE ALSO
========
LIBBPF = $(BPF_PATH)libbpf.a
-BPFTOOL_VERSION=$(shell make --no-print-directory -sC ../../.. kernelversion)
+BPFTOOL_VERSION := $(shell make --no-print-directory -sC ../../.. kernelversion)
$(LIBBPF): FORCE
$(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(OUTPUT) $(OUTPUT)libbpf.a FEATURES_DUMP=$(FEATURE_DUMP_EXPORT)
RM ?= rm -f
FEATURE_USER = .bpftool
-FEATURE_TESTS = libbfd disassembler-four-args
+FEATURE_TESTS = libbfd disassembler-four-args reallocarray
FEATURE_DISPLAY = libbfd disassembler-four-args
check_feat := 1
CFLAGS += -DDISASM_FOUR_ARGS_SIGNATURE
endif
+ifeq ($(feature-reallocarray), 0)
+CFLAGS += -DCOMPAT_NEED_REALLOCARRAY
+endif
+
include $(wildcard $(OUTPUT)*.d)
all: $(OUTPUT)bpftool
command sed -n 's/.*"tag": "\(.*\)",$/\1/p' )" -- "$cur" ) )
}
+_bpftool_get_obj_map_names()
+{
+ local obj
+
+ obj=$1
+
+ maps=$(objdump -j maps -t $obj 2>/dev/null | \
+ command awk '/g . maps/ {print $NF}')
+
+ COMPREPLY+=( $( compgen -W "$maps" -- "$cur" ) )
+}
+
+_bpftool_get_obj_map_idxs()
+{
+ local obj
+
+ obj=$1
+
+ nmaps=$(objdump -j maps -t $obj 2>/dev/null | grep -c 'g . maps')
+
+ COMPREPLY+=( $( compgen -W "$(seq 0 $((nmaps - 1)))" -- "$cur" ) )
+}
+
+_sysfs_get_netdevs()
+{
+ COMPREPLY+=( $( compgen -W "$( ls /sys/class/net 2>/dev/null )" -- \
+ "$cur" ) )
+}
+
# For bpftool map update: retrieve type of the map to update.
_bpftool_map_update_map_type()
{
local cur prev words objword
_init_completion || return
+ # Deal with options
+ if [[ ${words[cword]} == -* ]]; then
+ local c='--version --json --pretty --bpffs'
+ COMPREPLY=( $( compgen -W "$c" -- "$cur" ) )
+ return 0
+ fi
+
# Deal with simplest keywords
case $prev in
help|hex|opcodes|visual)
;;
esac
- # Search for object and command
- local object command cmdword
- for (( cmdword=1; cmdword < ${#words[@]}-1; cmdword++ )); do
- [[ -n $object ]] && command=${words[cmdword]} && break
- [[ ${words[cmdword]} != -* ]] && object=${words[cmdword]}
+ # Remove all options so completions don't have to deal with them.
+ local i
+ for (( i=1; i < ${#words[@]}; )); do
+ if [[ ${words[i]::1} == - ]]; then
+ words=( "${words[@]:0:i}" "${words[@]:i+1}" )
+ [[ $i -le $cword ]] && cword=$(( cword - 1 ))
+ else
+ i=$(( ++i ))
+ fi
done
+ cur=${words[cword]}
+ prev=${words[cword - 1]}
+
+ local object=${words[1]} command=${words[2]}
- if [[ -z $object ]]; then
+ if [[ -z $object || $cword -eq 1 ]]; then
case $cur in
- -*)
- local c='--version --json --pretty'
- COMPREPLY=( $( compgen -W "$c" -- "$cur" ) )
- return 0
- ;;
*)
COMPREPLY=( $( compgen -W "$( bpftool help 2>&1 | \
command sed \
# Completion depends on object and command in use
case $object in
prog)
- case $prev in
- id)
- _bpftool_get_prog_ids
- return 0
- ;;
- esac
+ if [[ $command != "load" ]]; then
+ case $prev in
+ id)
+ _bpftool_get_prog_ids
+ return 0
+ ;;
+ esac
+ fi
local PROG_TYPE='id pinned tag'
case $command in
return 0
;;
load)
- _filedir
- return 0
+ local obj
+
+ if [[ ${#words[@]} -lt 6 ]]; then
+ _filedir
+ return 0
+ fi
+
+ obj=${words[3]}
+
+ if [[ ${words[-4]} == "map" ]]; then
+ COMPREPLY=( $( compgen -W "id pinned" -- "$cur" ) )
+ return 0
+ fi
+ if [[ ${words[-3]} == "map" ]]; then
+ if [[ ${words[-2]} == "idx" ]]; then
+ _bpftool_get_obj_map_idxs $obj
+ elif [[ ${words[-2]} == "name" ]]; then
+ _bpftool_get_obj_map_names $obj
+ fi
+ return 0
+ fi
+ if [[ ${words[-2]} == "map" ]]; then
+ COMPREPLY=( $( compgen -W "idx name" -- "$cur" ) )
+ return 0
+ fi
+
+ case $prev in
+ type)
+ COMPREPLY=( $( compgen -W "socket kprobe kretprobe classifier action tracepoint raw_tracepoint xdp perf_event cgroup/skb cgroup/sock cgroup/dev lwt_in lwt_out lwt_xmit lwt_seg6local sockops sk_skb sk_msg lirc_mode2 cgroup/bind4 cgroup/bind6 cgroup/connect4 cgroup/connect6 cgroup/sendmsg4 cgroup/sendmsg6 cgroup/post_bind4 cgroup/post_bind6" -- \
+ "$cur" ) )
+ return 0
+ ;;
+ id)
+ _bpftool_get_map_ids
+ return 0
+ ;;
+ pinned)
+ _filedir
+ return 0
+ ;;
+ dev)
+ _sysfs_get_netdevs
+ return 0
+ ;;
+ *)
+ COMPREPLY=( $( compgen -W "map" -- "$cur" ) )
+ _bpftool_once_attr 'type'
+ _bpftool_once_attr 'dev'
+ return 0
+ ;;
+ esac
;;
*)
[[ $prev == $object ]] && \
_filedir
return 0
;;
+ tree)
+ _filedir
+ return 0
+ ;;
attach|detach)
local ATTACH_TYPES='ingress egress sock_create sock_ops \
device bind4 bind6 post_bind4 post_bind6 connect4 \
*)
[[ $prev == $object ]] && \
COMPREPLY=( $( compgen -W 'help attach detach \
- show list' -- "$cur" ) )
+ show list tree' -- "$cur" ) )
;;
esac
;;
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2018 Facebook */
+
+#include <ctype.h>
+#include <stdio.h> /* for (FILE *) used by json_writer */
+#include <string.h>
+#include <asm/byteorder.h>
+#include <linux/bitops.h>
+#include <linux/btf.h>
+#include <linux/err.h>
+
+#include "btf.h"
+#include "json_writer.h"
+#include "main.h"
+
+#define BITS_PER_BYTE_MASK (BITS_PER_BYTE - 1)
+#define BITS_PER_BYTE_MASKED(bits) ((bits) & BITS_PER_BYTE_MASK)
+#define BITS_ROUNDDOWN_BYTES(bits) ((bits) >> 3)
+#define BITS_ROUNDUP_BYTES(bits) \
+ (BITS_ROUNDDOWN_BYTES(bits) + !!BITS_PER_BYTE_MASKED(bits))
+
+static int btf_dumper_do_type(const struct btf_dumper *d, __u32 type_id,
+ __u8 bit_offset, const void *data);
+
+static void btf_dumper_ptr(const void *data, json_writer_t *jw,
+ bool is_plain_text)
+{
+ if (is_plain_text)
+ jsonw_printf(jw, "%p", *(unsigned long *)data);
+ else
+ jsonw_printf(jw, "%u", *(unsigned long *)data);
+}
+
+static int btf_dumper_modifier(const struct btf_dumper *d, __u32 type_id,
+ const void *data)
+{
+ int actual_type_id;
+
+ actual_type_id = btf__resolve_type(d->btf, type_id);
+ if (actual_type_id < 0)
+ return actual_type_id;
+
+ return btf_dumper_do_type(d, actual_type_id, 0, data);
+}
+
+static void btf_dumper_enum(const void *data, json_writer_t *jw)
+{
+ jsonw_printf(jw, "%d", *(int *)data);
+}
+
+static int btf_dumper_array(const struct btf_dumper *d, __u32 type_id,
+ const void *data)
+{
+ const struct btf_type *t = btf__type_by_id(d->btf, type_id);
+ struct btf_array *arr = (struct btf_array *)(t + 1);
+ long long elem_size;
+ int ret = 0;
+ __u32 i;
+
+ elem_size = btf__resolve_size(d->btf, arr->type);
+ if (elem_size < 0)
+ return elem_size;
+
+ jsonw_start_array(d->jw);
+ for (i = 0; i < arr->nelems; i++) {
+ ret = btf_dumper_do_type(d, arr->type, 0,
+ data + i * elem_size);
+ if (ret)
+ break;
+ }
+
+ jsonw_end_array(d->jw);
+ return ret;
+}
+
+static void btf_dumper_int_bits(__u32 int_type, __u8 bit_offset,
+ const void *data, json_writer_t *jw,
+ bool is_plain_text)
+{
+ int left_shift_bits, right_shift_bits;
+ int nr_bits = BTF_INT_BITS(int_type);
+ int total_bits_offset;
+ int bytes_to_copy;
+ int bits_to_copy;
+ __u64 print_num;
+
+ total_bits_offset = bit_offset + BTF_INT_OFFSET(int_type);
+ data += BITS_ROUNDDOWN_BYTES(total_bits_offset);
+ bit_offset = BITS_PER_BYTE_MASKED(total_bits_offset);
+ bits_to_copy = bit_offset + nr_bits;
+ bytes_to_copy = BITS_ROUNDUP_BYTES(bits_to_copy);
+
+ print_num = 0;
+ memcpy(&print_num, data, bytes_to_copy);
+#if defined(__BIG_ENDIAN_BITFIELD)
+ left_shift_bits = bit_offset;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+ left_shift_bits = 64 - bits_to_copy;
+#else
+#error neither big nor little endian
+#endif
+ right_shift_bits = 64 - nr_bits;
+
+ print_num <<= left_shift_bits;
+ print_num >>= right_shift_bits;
+ if (is_plain_text)
+ jsonw_printf(jw, "0x%llx", print_num);
+ else
+ jsonw_printf(jw, "%llu", print_num);
+}
+
+static int btf_dumper_int(const struct btf_type *t, __u8 bit_offset,
+ const void *data, json_writer_t *jw,
+ bool is_plain_text)
+{
+ __u32 *int_type;
+ __u32 nr_bits;
+
+ int_type = (__u32 *)(t + 1);
+ nr_bits = BTF_INT_BITS(*int_type);
+ /* if this is bit field */
+ if (bit_offset || BTF_INT_OFFSET(*int_type) ||
+ BITS_PER_BYTE_MASKED(nr_bits)) {
+ btf_dumper_int_bits(*int_type, bit_offset, data, jw,
+ is_plain_text);
+ return 0;
+ }
+
+ switch (BTF_INT_ENCODING(*int_type)) {
+ case 0:
+ if (BTF_INT_BITS(*int_type) == 64)
+ jsonw_printf(jw, "%lu", *(__u64 *)data);
+ else if (BTF_INT_BITS(*int_type) == 32)
+ jsonw_printf(jw, "%u", *(__u32 *)data);
+ else if (BTF_INT_BITS(*int_type) == 16)
+ jsonw_printf(jw, "%hu", *(__u16 *)data);
+ else if (BTF_INT_BITS(*int_type) == 8)
+ jsonw_printf(jw, "%hhu", *(__u8 *)data);
+ else
+ btf_dumper_int_bits(*int_type, bit_offset, data, jw,
+ is_plain_text);
+ break;
+ case BTF_INT_SIGNED:
+ if (BTF_INT_BITS(*int_type) == 64)
+ jsonw_printf(jw, "%ld", *(long long *)data);
+ else if (BTF_INT_BITS(*int_type) == 32)
+ jsonw_printf(jw, "%d", *(int *)data);
+ else if (BTF_INT_BITS(*int_type) == 16)
+ jsonw_printf(jw, "%hd", *(short *)data);
+ else if (BTF_INT_BITS(*int_type) == 8)
+ jsonw_printf(jw, "%hhd", *(char *)data);
+ else
+ btf_dumper_int_bits(*int_type, bit_offset, data, jw,
+ is_plain_text);
+ break;
+ case BTF_INT_CHAR:
+ if (isprint(*(char *)data))
+ jsonw_printf(jw, "\"%c\"", *(char *)data);
+ else
+ if (is_plain_text)
+ jsonw_printf(jw, "0x%hhx", *(char *)data);
+ else
+ jsonw_printf(jw, "\"\\u00%02hhx\"",
+ *(char *)data);
+ break;
+ case BTF_INT_BOOL:
+ jsonw_bool(jw, *(int *)data);
+ break;
+ default:
+ /* shouldn't happen */
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int btf_dumper_struct(const struct btf_dumper *d, __u32 type_id,
+ const void *data)
+{
+ const struct btf_type *t;
+ struct btf_member *m;
+ const void *data_off;
+ int ret = 0;
+ int i, vlen;
+
+ t = btf__type_by_id(d->btf, type_id);
+ if (!t)
+ return -EINVAL;
+
+ vlen = BTF_INFO_VLEN(t->info);
+ jsonw_start_object(d->jw);
+ m = (struct btf_member *)(t + 1);
+
+ for (i = 0; i < vlen; i++) {
+ data_off = data + BITS_ROUNDDOWN_BYTES(m[i].offset);
+ jsonw_name(d->jw, btf__name_by_offset(d->btf, m[i].name_off));
+ ret = btf_dumper_do_type(d, m[i].type,
+ BITS_PER_BYTE_MASKED(m[i].offset),
+ data_off);
+ if (ret)
+ break;
+ }
+
+ jsonw_end_object(d->jw);
+
+ return ret;
+}
+
+static int btf_dumper_do_type(const struct btf_dumper *d, __u32 type_id,
+ __u8 bit_offset, const void *data)
+{
+ const struct btf_type *t = btf__type_by_id(d->btf, type_id);
+
+ switch (BTF_INFO_KIND(t->info)) {
+ case BTF_KIND_INT:
+ return btf_dumper_int(t, bit_offset, data, d->jw,
+ d->is_plain_text);
+ case BTF_KIND_STRUCT:
+ case BTF_KIND_UNION:
+ return btf_dumper_struct(d, type_id, data);
+ case BTF_KIND_ARRAY:
+ return btf_dumper_array(d, type_id, data);
+ case BTF_KIND_ENUM:
+ btf_dumper_enum(data, d->jw);
+ return 0;
+ case BTF_KIND_PTR:
+ btf_dumper_ptr(data, d->jw, d->is_plain_text);
+ return 0;
+ case BTF_KIND_UNKN:
+ jsonw_printf(d->jw, "(unknown)");
+ return 0;
+ case BTF_KIND_FWD:
+ /* map key or value can't be forward */
+ jsonw_printf(d->jw, "(fwd-kind-invalid)");
+ return -EINVAL;
+ case BTF_KIND_TYPEDEF:
+ case BTF_KIND_VOLATILE:
+ case BTF_KIND_CONST:
+ case BTF_KIND_RESTRICT:
+ return btf_dumper_modifier(d, type_id, data);
+ default:
+ jsonw_printf(d->jw, "(unsupported-kind");
+ return -EINVAL;
+ }
+}
+
+int btf_dumper_type(const struct btf_dumper *d, __u32 type_id,
+ const void *data)
+{
+ return btf_dumper_do_type(d, type_id, 0, data);
+}
// Copyright (C) 2017 Facebook
// Author: Roman Gushchin <guro@fb.com>
+#define _XOPEN_SOURCE 500
+#include <errno.h>
#include <fcntl.h>
+#include <ftw.h>
+#include <mntent.h>
+#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/stat.h>
}
static int show_bpf_prog(int id, const char *attach_type_str,
- const char *attach_flags_str)
+ const char *attach_flags_str,
+ int level)
{
struct bpf_prog_info info = {};
__u32 info_len = sizeof(info);
jsonw_string_field(json_wtr, "name", info.name);
jsonw_end_object(json_wtr);
} else {
- printf("%-8u %-15s %-15s %-15s\n", info.id,
+ printf("%s%-8u %-15s %-15s %-15s\n", level ? " " : "",
+ info.id,
attach_type_str,
attach_flags_str,
info.name);
return 0;
}
-static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type)
+static int count_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type)
+{
+ __u32 prog_cnt = 0;
+ int ret;
+
+ ret = bpf_prog_query(cgroup_fd, type, 0, NULL, NULL, &prog_cnt);
+ if (ret)
+ return -1;
+
+ return prog_cnt;
+}
+
+static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type,
+ int level)
{
__u32 prog_ids[1024] = {0};
char *attach_flags_str;
for (iter = 0; iter < prog_cnt; iter++)
show_bpf_prog(prog_ids[iter], attach_type_strings[type],
- attach_flags_str);
+ attach_flags_str, level);
return 0;
}
* If we were able to get the show for at least one
* attach type, let's return 0.
*/
- if (show_attached_bpf_progs(cgroup_fd, type) == 0)
+ if (show_attached_bpf_progs(cgroup_fd, type, 0) == 0)
ret = 0;
}
return ret;
}
+/*
+ * To distinguish nftw() errors and do_show_tree_fn() errors
+ * and avoid duplicating error messages, let's return -2
+ * from do_show_tree_fn() in case of error.
+ */
+#define NFTW_ERR -1
+#define SHOW_TREE_FN_ERR -2
+static int do_show_tree_fn(const char *fpath, const struct stat *sb,
+ int typeflag, struct FTW *ftw)
+{
+ enum bpf_attach_type type;
+ bool skip = true;
+ int cgroup_fd;
+
+ if (typeflag != FTW_D)
+ return 0;
+
+ cgroup_fd = open(fpath, O_RDONLY);
+ if (cgroup_fd < 0) {
+ p_err("can't open cgroup %s: %s", fpath, strerror(errno));
+ return SHOW_TREE_FN_ERR;
+ }
+
+ for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++) {
+ int count = count_attached_bpf_progs(cgroup_fd, type);
+
+ if (count < 0 && errno != EINVAL) {
+ p_err("can't query bpf programs attached to %s: %s",
+ fpath, strerror(errno));
+ close(cgroup_fd);
+ return SHOW_TREE_FN_ERR;
+ }
+ if (count > 0) {
+ skip = false;
+ break;
+ }
+ }
+
+ if (skip) {
+ close(cgroup_fd);
+ return 0;
+ }
+
+ if (json_output) {
+ jsonw_start_object(json_wtr);
+ jsonw_string_field(json_wtr, "cgroup", fpath);
+ jsonw_name(json_wtr, "programs");
+ jsonw_start_array(json_wtr);
+ } else {
+ printf("%s\n", fpath);
+ }
+
+ for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++)
+ show_attached_bpf_progs(cgroup_fd, type, ftw->level);
+
+ if (json_output) {
+ jsonw_end_array(json_wtr);
+ jsonw_end_object(json_wtr);
+ }
+
+ close(cgroup_fd);
+
+ return 0;
+}
+
+static char *find_cgroup_root(void)
+{
+ struct mntent *mnt;
+ FILE *f;
+
+ f = fopen("/proc/mounts", "r");
+ if (f == NULL)
+ return NULL;
+
+ while ((mnt = getmntent(f))) {
+ if (strcmp(mnt->mnt_type, "cgroup2") == 0) {
+ fclose(f);
+ return strdup(mnt->mnt_dir);
+ }
+ }
+
+ fclose(f);
+ return NULL;
+}
+
+static int do_show_tree(int argc, char **argv)
+{
+ char *cgroup_root;
+ int ret;
+
+ switch (argc) {
+ case 0:
+ cgroup_root = find_cgroup_root();
+ if (!cgroup_root) {
+ p_err("cgroup v2 isn't mounted");
+ return -1;
+ }
+ break;
+ case 1:
+ cgroup_root = argv[0];
+ break;
+ default:
+ p_err("too many parameters for cgroup tree");
+ return -1;
+ }
+
+
+ if (json_output)
+ jsonw_start_array(json_wtr);
+ else
+ printf("%s\n"
+ "%-8s %-15s %-15s %-15s\n",
+ "CgroupPath",
+ "ID", "AttachType", "AttachFlags", "Name");
+
+ switch (nftw(cgroup_root, do_show_tree_fn, 1024, FTW_MOUNT)) {
+ case NFTW_ERR:
+ p_err("can't iterate over %s: %s", cgroup_root,
+ strerror(errno));
+ ret = -1;
+ break;
+ case SHOW_TREE_FN_ERR:
+ ret = -1;
+ break;
+ default:
+ ret = 0;
+ }
+
+ if (json_output)
+ jsonw_end_array(json_wtr);
+
+ if (argc == 0)
+ free(cgroup_root);
+
+ return ret;
+}
+
static int do_attach(int argc, char **argv)
{
enum bpf_attach_type attach_type;
fprintf(stderr,
"Usage: %s %s { show | list } CGROUP\n"
+ " %s %s tree [CGROUP_ROOT]\n"
" %s %s attach CGROUP ATTACH_TYPE PROG [ATTACH_FLAGS]\n"
" %s %s detach CGROUP ATTACH_TYPE PROG\n"
" %s %s help\n"
" " HELP_SPEC_PROGRAM "\n"
" " HELP_SPEC_OPTIONS "\n"
"",
+ bin_name, argv[-2],
bin_name, argv[-2], bin_name, argv[-2],
bin_name, argv[-2], bin_name, argv[-2]);
static const struct cmd cmds[] = {
{ "show", do_show },
{ "list", do_show },
+ { "tree", do_show_tree },
{ "attach", do_attach },
{ "detach", do_detach },
{ "help", do_help },
* SOFTWARE.
*/
-/* Author: Jakub Kicinski <kubakici@wp.pl> */
-
#include <ctype.h>
#include <errno.h>
#include <fcntl.h>
/*
- * Copyright (C) 2017 Netronome Systems, Inc.
+ * Copyright (C) 2017-2018 Netronome Systems, Inc.
*
* This software is dual licensed under the GNU General License Version 2,
* June 1991 as shown in the file COPYING in the top-level directory of this
* SOFTWARE.
*/
-/* Author: Jakub Kicinski <kubakici@wp.pl> */
-
#include <bfd.h>
#include <ctype.h>
#include <errno.h>
* SOFTWARE.
*/
-/* Author: Jakub Kicinski <kubakici@wp.pl> */
-
#ifndef __BPF_TOOL_H
#define __BPF_TOOL_H
#include <linux/compiler.h>
#include <linux/kernel.h>
#include <linux/hashtable.h>
+#include <tools/libc_compat.h>
#include "json_writer.h"
#define NEXT_ARG() ({ argc--; argv++; if (argc < 0) usage(); })
#define NEXT_ARGP() ({ (*argc)--; (*argv)++; if (*argc < 0) usage(); })
#define BAD_ARG() ({ p_err("what is '%s'?", *argv); -1; })
+#define GET_ARG() ({ argc--; *argv++; })
+#define REQ_ARGS(cnt) \
+ ({ \
+ int _cnt = (cnt); \
+ bool _res; \
+ \
+ if (argc < _cnt) { \
+ p_err("'%s' needs at least %d arguments, %d found", \
+ argv[-1], _cnt, argc); \
+ _res = false; \
+ } else { \
+ _res = true; \
+ } \
+ _res; \
+ })
#define ERR_MAX_LEN 1024
"PROG := { id PROG_ID | pinned FILE | tag PROG_TAG }"
#define HELP_SPEC_OPTIONS \
"OPTIONS := { {-j|--json} [{-p|--pretty}] | {-f|--bpffs} }"
+#define HELP_SPEC_MAP \
+ "MAP := { id MAP_ID | pinned FILE }"
enum bpf_obj_type {
BPF_OBJ_UNKNOWN,
int do_perf(int argc, char **arg);
int prog_parse_fd(int *argc, char ***argv);
+int map_parse_fd(int *argc, char ***argv);
int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len);
void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes,
unsigned int get_possible_cpus(void);
const char *ifindex_to_bfd_name_ns(__u32 ifindex, __u64 ns_dev, __u64 ns_ino);
+struct btf_dumper {
+ const struct btf *btf;
+ json_writer_t *jw;
+ bool is_plain_text;
+};
+
+/* btf_dumper_type - print data along with type information
+ * @d: an instance containing context for dumping types
+ * @type_id: index in btf->types array. this points to the type to be dumped
+ * @data: pointer the actual data, i.e. the values to be printed
+ *
+ * Returns zero on success and negative error code otherwise
+ */
+int btf_dumper_type(const struct btf_dumper *d, __u32 type_id,
+ const void *data);
#endif
* SOFTWARE.
*/
-/* Author: Jakub Kicinski <kubakici@wp.pl> */
-
#include <assert.h>
#include <errno.h>
#include <fcntl.h>
+#include <linux/err.h>
#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>
#include <bpf.h>
+#include "btf.h"
+#include "json_writer.h"
#include "main.h"
static const char * const map_type_name[] = {
return malloc(info->value_size);
}
-static int map_parse_fd(int *argc, char ***argv)
+int map_parse_fd(int *argc, char ***argv)
{
int fd;
return fd;
}
+static int do_dump_btf(const struct btf_dumper *d,
+ struct bpf_map_info *map_info, void *key,
+ void *value)
+{
+ int ret;
+
+ /* start of key-value pair */
+ jsonw_start_object(d->jw);
+
+ jsonw_name(d->jw, "key");
+
+ ret = btf_dumper_type(d, map_info->btf_key_type_id, key);
+ if (ret)
+ goto err_end_obj;
+
+ jsonw_name(d->jw, "value");
+
+ ret = btf_dumper_type(d, map_info->btf_value_type_id, value);
+
+err_end_obj:
+ /* end of key-value pair */
+ jsonw_end_object(d->jw);
+
+ return ret;
+}
+
+static int get_btf(struct bpf_map_info *map_info, struct btf **btf)
+{
+ struct bpf_btf_info btf_info = { 0 };
+ __u32 len = sizeof(btf_info);
+ __u32 last_size;
+ int btf_fd;
+ void *ptr;
+ int err;
+
+ err = 0;
+ *btf = NULL;
+ btf_fd = bpf_btf_get_fd_by_id(map_info->btf_id);
+ if (btf_fd < 0)
+ return 0;
+
+ /* we won't know btf_size until we call bpf_obj_get_info_by_fd(). so
+ * let's start with a sane default - 4KiB here - and resize it only if
+ * bpf_obj_get_info_by_fd() needs a bigger buffer.
+ */
+ btf_info.btf_size = 4096;
+ last_size = btf_info.btf_size;
+ ptr = malloc(last_size);
+ if (!ptr) {
+ err = -ENOMEM;
+ goto exit_free;
+ }
+
+ bzero(ptr, last_size);
+ btf_info.btf = ptr_to_u64(ptr);
+ err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len);
+
+ if (!err && btf_info.btf_size > last_size) {
+ void *temp_ptr;
+
+ last_size = btf_info.btf_size;
+ temp_ptr = realloc(ptr, last_size);
+ if (!temp_ptr) {
+ err = -ENOMEM;
+ goto exit_free;
+ }
+ ptr = temp_ptr;
+ bzero(ptr, last_size);
+ btf_info.btf = ptr_to_u64(ptr);
+ err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len);
+ }
+
+ if (err || btf_info.btf_size > last_size) {
+ err = errno;
+ goto exit_free;
+ }
+
+ *btf = btf__new((__u8 *)btf_info.btf, btf_info.btf_size, NULL);
+ if (IS_ERR(*btf)) {
+ err = PTR_ERR(btf);
+ *btf = NULL;
+ }
+
+exit_free:
+ close(btf_fd);
+ free(ptr);
+
+ return err;
+}
+
+static json_writer_t *get_btf_writer(void)
+{
+ json_writer_t *jw = jsonw_new(stdout);
+
+ if (!jw)
+ return NULL;
+ jsonw_pretty(jw, true);
+
+ return jw;
+}
+
static void print_entry_json(struct bpf_map_info *info, unsigned char *key,
- unsigned char *value)
+ unsigned char *value, struct btf *btf)
{
jsonw_start_object(json_wtr);
print_hex_data_json(key, info->key_size);
jsonw_name(json_wtr, "value");
print_hex_data_json(value, info->value_size);
+ if (btf) {
+ struct btf_dumper d = {
+ .btf = btf,
+ .jw = json_wtr,
+ .is_plain_text = false,
+ };
+
+ jsonw_name(json_wtr, "formatted");
+ do_dump_btf(&d, info, key, value);
+ }
} else {
unsigned int i, n;
static int do_dump(int argc, char **argv)
{
+ struct bpf_map_info info = {};
void *key, *value, *prev_key;
unsigned int num_elems = 0;
- struct bpf_map_info info = {};
__u32 len = sizeof(info);
+ json_writer_t *btf_wtr;
+ struct btf *btf = NULL;
int err;
int fd;
}
prev_key = NULL;
+
+ err = get_btf(&info, &btf);
+ if (err) {
+ p_err("failed to get btf");
+ goto exit_free;
+ }
+
if (json_output)
jsonw_start_array(json_wtr);
+ else
+ if (btf) {
+ btf_wtr = get_btf_writer();
+ if (!btf_wtr) {
+ p_info("failed to create json writer for btf. falling back to plain output");
+ btf__free(btf);
+ btf = NULL;
+ } else {
+ jsonw_start_array(btf_wtr);
+ }
+ }
+
while (true) {
err = bpf_map_get_next_key(fd, prev_key, key);
if (err) {
if (!bpf_map_lookup_elem(fd, key, value)) {
if (json_output)
- print_entry_json(&info, key, value);
+ print_entry_json(&info, key, value, btf);
else
- print_entry_plain(&info, key, value);
+ if (btf) {
+ struct btf_dumper d = {
+ .btf = btf,
+ .jw = btf_wtr,
+ .is_plain_text = true,
+ };
+
+ do_dump_btf(&d, &info, key, value);
+ } else {
+ print_entry_plain(&info, key, value);
+ }
} else {
if (json_output) {
jsonw_name(json_wtr, "key");
if (json_output)
jsonw_end_array(json_wtr);
- else
+ else if (btf) {
+ jsonw_end_array(btf_wtr);
+ jsonw_destroy(&btf_wtr);
+ } else {
printf("Found %u element%s\n", num_elems,
num_elems != 1 ? "s" : "");
+ }
exit_free:
free(key);
free(value);
close(fd);
+ btf__free(btf);
return err;
}
{
struct bpf_map_info info = {};
__u32 len = sizeof(info);
+ json_writer_t *btf_wtr;
+ struct btf *btf = NULL;
void *key, *value;
int err;
int fd;
goto exit_free;
err = bpf_map_lookup_elem(fd, key, value);
- if (!err) {
- if (json_output)
- print_entry_json(&info, key, value);
- else
+ if (err) {
+ if (errno == ENOENT) {
+ if (json_output) {
+ jsonw_null(json_wtr);
+ } else {
+ printf("key:\n");
+ fprint_hex(stdout, key, info.key_size, " ");
+ printf("\n\nNot found\n");
+ }
+ } else {
+ p_err("lookup failed: %s", strerror(errno));
+ }
+
+ goto exit_free;
+ }
+
+ /* here means bpf_map_lookup_elem() succeeded */
+ err = get_btf(&info, &btf);
+ if (err) {
+ p_err("failed to get btf");
+ goto exit_free;
+ }
+
+ if (json_output) {
+ print_entry_json(&info, key, value, btf);
+ } else if (btf) {
+ /* if here json_wtr wouldn't have been initialised,
+ * so let's create separate writer for btf
+ */
+ btf_wtr = get_btf_writer();
+ if (!btf_wtr) {
+ p_info("failed to create json writer for btf. falling back to plain output");
+ btf__free(btf);
+ btf = NULL;
print_entry_plain(&info, key, value);
- } else if (errno == ENOENT) {
- if (json_output) {
- jsonw_null(json_wtr);
} else {
- printf("key:\n");
- fprint_hex(stdout, key, info.key_size, " ");
- printf("\n\nNot found\n");
+ struct btf_dumper d = {
+ .btf = btf,
+ .jw = btf_wtr,
+ .is_plain_text = true,
+ };
+
+ do_dump_btf(&d, &info, key, value);
+ jsonw_destroy(&btf_wtr);
}
} else {
- p_err("lookup failed: %s", strerror(errno));
+ print_entry_plain(&info, key, value);
}
exit_free:
free(key);
free(value);
close(fd);
+ btf__free(btf);
return err;
}
" %s %s event_pipe MAP [cpu N index M]\n"
" %s %s help\n"
"\n"
- " MAP := { id MAP_ID | pinned FILE }\n"
+ " " HELP_SPEC_MAP "\n"
" DATA := { [hex] BYTES }\n"
" " HELP_SPEC_PROGRAM "\n"
" VALUE := { DATA | MAP | PROG }\n"
if (perf_query_supported)
goto out;
- fd = open(bin_name, O_RDONLY);
+ fd = open("/", O_RDONLY);
if (fd < 0) {
- p_err("perf_query_support: %s", strerror(errno));
+ p_err("perf_query_support: cannot open directory \"/\" (%s)",
+ strerror(errno));
goto out;
}
/*
- * Copyright (C) 2017 Netronome Systems, Inc.
+ * Copyright (C) 2017-2018 Netronome Systems, Inc.
*
* This software is dual licensed under the GNU General License Version 2,
* June 1991 as shown in the file COPYING in the top-level directory of this
* SOFTWARE.
*/
-/* Author: Jakub Kicinski <kubakici@wp.pl> */
-
+#define _GNU_SOURCE
#include <errno.h>
#include <fcntl.h>
#include <stdarg.h>
#include <string.h>
#include <time.h>
#include <unistd.h>
+#include <net/if.h>
#include <sys/types.h>
#include <sys/stat.h>
+#include <linux/err.h>
+
#include <bpf.h>
#include <libbpf.h>
}
wallclock_secs = (real_time_ts.tv_sec - boot_time_ts.tv_sec) +
- nsecs / 1000000000;
+ (real_time_ts.tv_nsec - boot_time_ts.tv_nsec + nsecs) /
+ 1000000000;
+
if (!localtime_r(&wallclock_secs, &load_tm)) {
snprintf(buf, size, "%llu", nsecs / 1000000000);
return err;
}
+struct map_replace {
+ int idx;
+ int fd;
+ char *name;
+};
+
+int map_replace_compar(const void *p1, const void *p2)
+{
+ const struct map_replace *a = p1, *b = p2;
+
+ return a->idx - b->idx;
+}
+
static int do_load(int argc, char **argv)
{
+ enum bpf_attach_type expected_attach_type;
+ struct bpf_object_open_attr attr = {
+ .prog_type = BPF_PROG_TYPE_UNSPEC,
+ };
+ struct map_replace *map_replace = NULL;
+ unsigned int old_map_fds = 0;
+ struct bpf_program *prog;
struct bpf_object *obj;
- int prog_fd;
-
- if (argc != 2)
- usage();
+ struct bpf_map *map;
+ const char *pinfile;
+ unsigned int i, j;
+ __u32 ifindex = 0;
+ int idx, err;
- if (bpf_prog_load(argv[0], BPF_PROG_TYPE_UNSPEC, &obj, &prog_fd)) {
- p_err("failed to load program");
+ if (!REQ_ARGS(2))
return -1;
+ attr.file = GET_ARG();
+ pinfile = GET_ARG();
+
+ while (argc) {
+ if (is_prefix(*argv, "type")) {
+ char *type;
+
+ NEXT_ARG();
+
+ if (attr.prog_type != BPF_PROG_TYPE_UNSPEC) {
+ p_err("program type already specified");
+ goto err_free_reuse_maps;
+ }
+ if (!REQ_ARGS(1))
+ goto err_free_reuse_maps;
+
+ /* Put a '/' at the end of type to appease libbpf */
+ type = malloc(strlen(*argv) + 2);
+ if (!type) {
+ p_err("mem alloc failed");
+ goto err_free_reuse_maps;
+ }
+ *type = 0;
+ strcat(type, *argv);
+ strcat(type, "/");
+
+ err = libbpf_prog_type_by_name(type, &attr.prog_type,
+ &expected_attach_type);
+ free(type);
+ if (err < 0) {
+ p_err("unknown program type '%s'", *argv);
+ goto err_free_reuse_maps;
+ }
+ NEXT_ARG();
+ } else if (is_prefix(*argv, "map")) {
+ char *endptr, *name;
+ int fd;
+
+ NEXT_ARG();
+
+ if (!REQ_ARGS(4))
+ goto err_free_reuse_maps;
+
+ if (is_prefix(*argv, "idx")) {
+ NEXT_ARG();
+
+ idx = strtoul(*argv, &endptr, 0);
+ if (*endptr) {
+ p_err("can't parse %s as IDX", *argv);
+ goto err_free_reuse_maps;
+ }
+ name = NULL;
+ } else if (is_prefix(*argv, "name")) {
+ NEXT_ARG();
+
+ name = *argv;
+ idx = -1;
+ } else {
+ p_err("expected 'idx' or 'name', got: '%s'?",
+ *argv);
+ goto err_free_reuse_maps;
+ }
+ NEXT_ARG();
+
+ fd = map_parse_fd(&argc, &argv);
+ if (fd < 0)
+ goto err_free_reuse_maps;
+
+ map_replace = reallocarray(map_replace, old_map_fds + 1,
+ sizeof(*map_replace));
+ if (!map_replace) {
+ p_err("mem alloc failed");
+ goto err_free_reuse_maps;
+ }
+ map_replace[old_map_fds].idx = idx;
+ map_replace[old_map_fds].name = name;
+ map_replace[old_map_fds].fd = fd;
+ old_map_fds++;
+ } else if (is_prefix(*argv, "dev")) {
+ NEXT_ARG();
+
+ if (ifindex) {
+ p_err("offload device already specified");
+ goto err_free_reuse_maps;
+ }
+ if (!REQ_ARGS(1))
+ goto err_free_reuse_maps;
+
+ ifindex = if_nametoindex(*argv);
+ if (!ifindex) {
+ p_err("unrecognized netdevice '%s': %s",
+ *argv, strerror(errno));
+ goto err_free_reuse_maps;
+ }
+ NEXT_ARG();
+ } else {
+ p_err("expected no more arguments, 'type', 'map' or 'dev', got: '%s'?",
+ *argv);
+ goto err_free_reuse_maps;
+ }
}
- if (do_pin_fd(prog_fd, argv[1])) {
- p_err("failed to pin program");
- return -1;
+ obj = bpf_object__open_xattr(&attr);
+ if (IS_ERR_OR_NULL(obj)) {
+ p_err("failed to open object file");
+ goto err_free_reuse_maps;
+ }
+
+ prog = bpf_program__next(NULL, obj);
+ if (!prog) {
+ p_err("object file doesn't contain any bpf program");
+ goto err_close_obj;
+ }
+
+ bpf_program__set_ifindex(prog, ifindex);
+ if (attr.prog_type == BPF_PROG_TYPE_UNSPEC) {
+ const char *sec_name = bpf_program__title(prog, false);
+
+ err = libbpf_prog_type_by_name(sec_name, &attr.prog_type,
+ &expected_attach_type);
+ if (err < 0) {
+ p_err("failed to guess program type based on section name %s\n",
+ sec_name);
+ goto err_close_obj;
+ }
+ }
+ bpf_program__set_type(prog, attr.prog_type);
+ bpf_program__set_expected_attach_type(prog, expected_attach_type);
+
+ qsort(map_replace, old_map_fds, sizeof(*map_replace),
+ map_replace_compar);
+
+ /* After the sort maps by name will be first on the list, because they
+ * have idx == -1. Resolve them.
+ */
+ j = 0;
+ while (j < old_map_fds && map_replace[j].name) {
+ i = 0;
+ bpf_map__for_each(map, obj) {
+ if (!strcmp(bpf_map__name(map), map_replace[j].name)) {
+ map_replace[j].idx = i;
+ break;
+ }
+ i++;
+ }
+ if (map_replace[j].idx == -1) {
+ p_err("unable to find map '%s'", map_replace[j].name);
+ goto err_close_obj;
+ }
+ j++;
+ }
+ /* Resort if any names were resolved */
+ if (j)
+ qsort(map_replace, old_map_fds, sizeof(*map_replace),
+ map_replace_compar);
+
+ /* Set ifindex and name reuse */
+ j = 0;
+ idx = 0;
+ bpf_map__for_each(map, obj) {
+ if (!bpf_map__is_offload_neutral(map))
+ bpf_map__set_ifindex(map, ifindex);
+
+ if (j < old_map_fds && idx == map_replace[j].idx) {
+ err = bpf_map__reuse_fd(map, map_replace[j++].fd);
+ if (err) {
+ p_err("unable to set up map reuse: %d", err);
+ goto err_close_obj;
+ }
+
+ /* Next reuse wants to apply to the same map */
+ if (j < old_map_fds && map_replace[j].idx == idx) {
+ p_err("replacement for map idx %d specified more than once",
+ idx);
+ goto err_close_obj;
+ }
+ }
+
+ idx++;
+ }
+ if (j < old_map_fds) {
+ p_err("map idx '%d' not used", map_replace[j].idx);
+ goto err_close_obj;
}
+ err = bpf_object__load(obj);
+ if (err) {
+ p_err("failed to load object file");
+ goto err_close_obj;
+ }
+
+ if (do_pin_fd(bpf_program__fd(prog), pinfile))
+ goto err_close_obj;
+
if (json_output)
jsonw_null(json_wtr);
+ bpf_object__close(obj);
+ for (i = 0; i < old_map_fds; i++)
+ close(map_replace[i].fd);
+ free(map_replace);
+
return 0;
+
+err_close_obj:
+ bpf_object__close(obj);
+err_free_reuse_maps:
+ for (i = 0; i < old_map_fds; i++)
+ close(map_replace[i].fd);
+ free(map_replace);
+ return -1;
}
static int do_help(int argc, char **argv)
" %s %s dump xlated PROG [{ file FILE | opcodes | visual }]\n"
" %s %s dump jited PROG [{ file FILE | opcodes }]\n"
" %s %s pin PROG FILE\n"
- " %s %s load OBJ FILE\n"
+ " %s %s load OBJ FILE [type TYPE] [dev NAME] \\\n"
+ " [map { idx IDX | name NAME } MAP]\n"
" %s %s help\n"
"\n"
+ " " HELP_SPEC_MAP "\n"
" " HELP_SPEC_PROGRAM "\n"
+ " TYPE := { socket | kprobe | kretprobe | classifier | action |\n"
+ " tracepoint | raw_tracepoint | xdp | perf_event | cgroup/skb |\n"
+ " cgroup/sock | cgroup/dev | lwt_in | lwt_out | lwt_xmit |\n"
+ " lwt_seg6local | sockops | sk_skb | sk_msg | lirc_mode2 |\n"
+ " cgroup/bind4 | cgroup/bind6 | cgroup/post_bind4 |\n"
+ " cgroup/post_bind6 | cgroup/connect4 | cgroup/connect6 |\n"
+ " cgroup/sendmsg4 | cgroup/sendmsg6 }\n"
" " HELP_SPEC_OPTIONS "\n"
"",
bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
* POSSIBILITY OF SUCH DAMAGE.
*/
+#define _GNU_SOURCE
#include <stdarg.h>
#include <stdio.h>
#include <stdlib.h>
while (!feof(fp)) {
if (!fgets(buff, sizeof(buff), fp))
break;
- tmp = realloc(dd->sym_mapping,
- (dd->sym_count + 1) *
- sizeof(*dd->sym_mapping));
+ tmp = reallocarray(dd->sym_mapping, dd->sym_count + 1,
+ sizeof(*dd->sym_mapping));
if (!tmp) {
out:
free(dd->sym_mapping);
libunwind-aarch64 \
pthread-attr-setaffinity-np \
pthread-barrier \
+ reallocarray \
stackprotector-all \
timerfd \
libdw-dwarf-unwind \
test-libaudit.bin \
test-libbfd.bin \
test-disassembler-four-args.bin \
+ test-reallocarray.bin \
test-liberty.bin \
test-liberty-z.bin \
test-cplus-demangle.bin \
$(OUTPUT)test-disassembler-four-args.bin:
$(BUILD) -DPACKAGE='"perf"' -lbfd -lopcodes
+$(OUTPUT)test-reallocarray.bin:
+ $(BUILD)
+
$(OUTPUT)test-liberty.bin:
$(CC) $(CFLAGS) -Wall -Werror -o $@ test-libbfd.c -DPACKAGE='"perf"' $(LDFLAGS) -lbfd -ldl -liberty
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <stdlib.h>
+
+int main(void)
+{
+ return !!reallocarray(NULL, 1, 1);
+}
#endif
#define __printf(a, b) __attribute__((format(printf, a, b)))
#define __scanf(a, b) __attribute__((format(scanf, a, b)))
+
+#if GCC_VERSION >= 50100
+#define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1
+#endif
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+#ifndef __LINUX_OVERFLOW_H
+#define __LINUX_OVERFLOW_H
+
+#include <linux/compiler.h>
+
+/*
+ * In the fallback code below, we need to compute the minimum and
+ * maximum values representable in a given type. These macros may also
+ * be useful elsewhere, so we provide them outside the
+ * COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW block.
+ *
+ * It would seem more obvious to do something like
+ *
+ * #define type_min(T) (T)(is_signed_type(T) ? (T)1 << (8*sizeof(T)-1) : 0)
+ * #define type_max(T) (T)(is_signed_type(T) ? ((T)1 << (8*sizeof(T)-1)) - 1 : ~(T)0)
+ *
+ * Unfortunately, the middle expressions, strictly speaking, have
+ * undefined behaviour, and at least some versions of gcc warn about
+ * the type_max expression (but not if -fsanitize=undefined is in
+ * effect; in that case, the warning is deferred to runtime...).
+ *
+ * The slightly excessive casting in type_min is to make sure the
+ * macros also produce sensible values for the exotic type _Bool. [The
+ * overflow checkers only almost work for _Bool, but that's
+ * a-feature-not-a-bug, since people shouldn't be doing arithmetic on
+ * _Bools. Besides, the gcc builtins don't allow _Bool* as third
+ * argument.]
+ *
+ * Idea stolen from
+ * https://mail-index.netbsd.org/tech-misc/2007/02/05/0000.html -
+ * credit to Christian Biere.
+ */
+#define is_signed_type(type) (((type)(-1)) < (type)1)
+#define __type_half_max(type) ((type)1 << (8*sizeof(type) - 1 - is_signed_type(type)))
+#define type_max(T) ((T)((__type_half_max(T) - 1) + __type_half_max(T)))
+#define type_min(T) ((T)((T)-type_max(T)-(T)1))
+
+
+#ifdef COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW
+/*
+ * For simplicity and code hygiene, the fallback code below insists on
+ * a, b and *d having the same type (similar to the min() and max()
+ * macros), whereas gcc's type-generic overflow checkers accept
+ * different types. Hence we don't just make check_add_overflow an
+ * alias for __builtin_add_overflow, but add type checks similar to
+ * below.
+ */
+#define check_add_overflow(a, b, d) ({ \
+ typeof(a) __a = (a); \
+ typeof(b) __b = (b); \
+ typeof(d) __d = (d); \
+ (void) (&__a == &__b); \
+ (void) (&__a == __d); \
+ __builtin_add_overflow(__a, __b, __d); \
+})
+
+#define check_sub_overflow(a, b, d) ({ \
+ typeof(a) __a = (a); \
+ typeof(b) __b = (b); \
+ typeof(d) __d = (d); \
+ (void) (&__a == &__b); \
+ (void) (&__a == __d); \
+ __builtin_sub_overflow(__a, __b, __d); \
+})
+
+#define check_mul_overflow(a, b, d) ({ \
+ typeof(a) __a = (a); \
+ typeof(b) __b = (b); \
+ typeof(d) __d = (d); \
+ (void) (&__a == &__b); \
+ (void) (&__a == __d); \
+ __builtin_mul_overflow(__a, __b, __d); \
+})
+
+#else
+
+
+/* Checking for unsigned overflow is relatively easy without causing UB. */
+#define __unsigned_add_overflow(a, b, d) ({ \
+ typeof(a) __a = (a); \
+ typeof(b) __b = (b); \
+ typeof(d) __d = (d); \
+ (void) (&__a == &__b); \
+ (void) (&__a == __d); \
+ *__d = __a + __b; \
+ *__d < __a; \
+})
+#define __unsigned_sub_overflow(a, b, d) ({ \
+ typeof(a) __a = (a); \
+ typeof(b) __b = (b); \
+ typeof(d) __d = (d); \
+ (void) (&__a == &__b); \
+ (void) (&__a == __d); \
+ *__d = __a - __b; \
+ __a < __b; \
+})
+/*
+ * If one of a or b is a compile-time constant, this avoids a division.
+ */
+#define __unsigned_mul_overflow(a, b, d) ({ \
+ typeof(a) __a = (a); \
+ typeof(b) __b = (b); \
+ typeof(d) __d = (d); \
+ (void) (&__a == &__b); \
+ (void) (&__a == __d); \
+ *__d = __a * __b; \
+ __builtin_constant_p(__b) ? \
+ __b > 0 && __a > type_max(typeof(__a)) / __b : \
+ __a > 0 && __b > type_max(typeof(__b)) / __a; \
+})
+
+/*
+ * For signed types, detecting overflow is much harder, especially if
+ * we want to avoid UB. But the interface of these macros is such that
+ * we must provide a result in *d, and in fact we must produce the
+ * result promised by gcc's builtins, which is simply the possibly
+ * wrapped-around value. Fortunately, we can just formally do the
+ * operations in the widest relevant unsigned type (u64) and then
+ * truncate the result - gcc is smart enough to generate the same code
+ * with and without the (u64) casts.
+ */
+
+/*
+ * Adding two signed integers can overflow only if they have the same
+ * sign, and overflow has happened iff the result has the opposite
+ * sign.
+ */
+#define __signed_add_overflow(a, b, d) ({ \
+ typeof(a) __a = (a); \
+ typeof(b) __b = (b); \
+ typeof(d) __d = (d); \
+ (void) (&__a == &__b); \
+ (void) (&__a == __d); \
+ *__d = (u64)__a + (u64)__b; \
+ (((~(__a ^ __b)) & (*__d ^ __a)) \
+ & type_min(typeof(__a))) != 0; \
+})
+
+/*
+ * Subtraction is similar, except that overflow can now happen only
+ * when the signs are opposite. In this case, overflow has happened if
+ * the result has the opposite sign of a.
+ */
+#define __signed_sub_overflow(a, b, d) ({ \
+ typeof(a) __a = (a); \
+ typeof(b) __b = (b); \
+ typeof(d) __d = (d); \
+ (void) (&__a == &__b); \
+ (void) (&__a == __d); \
+ *__d = (u64)__a - (u64)__b; \
+ ((((__a ^ __b)) & (*__d ^ __a)) \
+ & type_min(typeof(__a))) != 0; \
+})
+
+/*
+ * Signed multiplication is rather hard. gcc always follows C99, so
+ * division is truncated towards 0. This means that we can write the
+ * overflow check like this:
+ *
+ * (a > 0 && (b > MAX/a || b < MIN/a)) ||
+ * (a < -1 && (b > MIN/a || b < MAX/a) ||
+ * (a == -1 && b == MIN)
+ *
+ * The redundant casts of -1 are to silence an annoying -Wtype-limits
+ * (included in -Wextra) warning: When the type is u8 or u16, the
+ * __b_c_e in check_mul_overflow obviously selects
+ * __unsigned_mul_overflow, but unfortunately gcc still parses this
+ * code and warns about the limited range of __b.
+ */
+
+#define __signed_mul_overflow(a, b, d) ({ \
+ typeof(a) __a = (a); \
+ typeof(b) __b = (b); \
+ typeof(d) __d = (d); \
+ typeof(a) __tmax = type_max(typeof(a)); \
+ typeof(a) __tmin = type_min(typeof(a)); \
+ (void) (&__a == &__b); \
+ (void) (&__a == __d); \
+ *__d = (u64)__a * (u64)__b; \
+ (__b > 0 && (__a > __tmax/__b || __a < __tmin/__b)) || \
+ (__b < (typeof(__b))-1 && (__a > __tmin/__b || __a < __tmax/__b)) || \
+ (__b == (typeof(__b))-1 && __a == __tmin); \
+})
+
+
+#define check_add_overflow(a, b, d) \
+ __builtin_choose_expr(is_signed_type(typeof(a)), \
+ __signed_add_overflow(a, b, d), \
+ __unsigned_add_overflow(a, b, d))
+
+#define check_sub_overflow(a, b, d) \
+ __builtin_choose_expr(is_signed_type(typeof(a)), \
+ __signed_sub_overflow(a, b, d), \
+ __unsigned_sub_overflow(a, b, d))
+
+#define check_mul_overflow(a, b, d) \
+ __builtin_choose_expr(is_signed_type(typeof(a)), \
+ __signed_mul_overflow(a, b, d), \
+ __unsigned_mul_overflow(a, b, d))
+
+
+#endif /* COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW */
+
+/**
+ * array_size() - Calculate size of 2-dimensional array.
+ *
+ * @a: dimension one
+ * @b: dimension two
+ *
+ * Calculates size of 2-dimensional array: @a * @b.
+ *
+ * Returns: number of bytes needed to represent the array or SIZE_MAX on
+ * overflow.
+ */
+static inline __must_check size_t array_size(size_t a, size_t b)
+{
+ size_t bytes;
+
+ if (check_mul_overflow(a, b, &bytes))
+ return SIZE_MAX;
+
+ return bytes;
+}
+
+/**
+ * array3_size() - Calculate size of 3-dimensional array.
+ *
+ * @a: dimension one
+ * @b: dimension two
+ * @c: dimension three
+ *
+ * Calculates size of 3-dimensional array: @a * @b * @c.
+ *
+ * Returns: number of bytes needed to represent the array or SIZE_MAX on
+ * overflow.
+ */
+static inline __must_check size_t array3_size(size_t a, size_t b, size_t c)
+{
+ size_t bytes;
+
+ if (check_mul_overflow(a, b, &bytes))
+ return SIZE_MAX;
+ if (check_mul_overflow(bytes, c, &bytes))
+ return SIZE_MAX;
+
+ return bytes;
+}
+
+static inline __must_check size_t __ab_c_size(size_t n, size_t size, size_t c)
+{
+ size_t bytes;
+
+ if (check_mul_overflow(n, size, &bytes))
+ return SIZE_MAX;
+ if (check_add_overflow(bytes, c, &bytes))
+ return SIZE_MAX;
+
+ return bytes;
+}
+
+/**
+ * struct_size() - Calculate size of structure with trailing array.
+ * @p: Pointer to the structure.
+ * @member: Name of the array member.
+ * @n: Number of elements in the array.
+ *
+ * Calculates size of memory needed for structure @p followed by an
+ * array of @n @member elements.
+ *
+ * Return: number of bytes needed or SIZE_MAX on overflow.
+ */
+#define struct_size(p, member, n) \
+ __ab_c_size(n, \
+ sizeof(*(p)->member) + __must_be_array((p)->member),\
+ sizeof(*(p)))
+
+#endif /* __LINUX_OVERFLOW_H */
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright (C) 2018 Netronome Systems, Inc. */
+
+#ifndef __TOOLS_LIBC_COMPAT_H
+#define __TOOLS_LIBC_COMPAT_H
+
+#include <stdlib.h>
+#include <linux/overflow.h>
+
+#ifdef COMPAT_NEED_REALLOCARRAY
+static inline void *reallocarray(void *ptr, size_t nmemb, size_t size)
+{
+ size_t bytes;
+
+ if (unlikely(check_mul_overflow(nmemb, size, &bytes)))
+ return NULL;
+ return realloc(ptr, bytes);
+}
+#endif
+#endif
*/
#define DRM_CLIENT_CAP_ATOMIC 3
+/**
+ * DRM_CLIENT_CAP_ASPECT_RATIO
+ *
+ * If set to 1, the DRM core will provide aspect ratio information in modes.
+ */
+#define DRM_CLIENT_CAP_ASPECT_RATIO 4
+
/** DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */
struct drm_set_client_cap {
__u64 capability;
* A non-negative value equal to or less than *size* on success,
* or a negative error in case of failure.
*
- * int skb_load_bytes_relative(const struct sk_buff *skb, u32 offset, void *to, u32 len, u32 start_header)
+ * int bpf_skb_load_bytes_relative(const struct sk_buff *skb, u32 offset, void *to, u32 len, u32 start_header)
* Description
* This helper is similar to **bpf_skb_load_bytes**\ () in that
* it provides an easy way to load *len* bytes from *offset*
* is resolved), the nexthop address is returned in ipv4_dst
* or ipv6_dst based on family, smac is set to mac address of
* egress device, dmac is set to nexthop mac address, rt_metric
- * is set to metric from route (IPv4/IPv6 only).
+ * is set to metric from route (IPv4/IPv6 only), and ifindex
+ * is set to the device index of the nexthop from the FIB lookup.
*
* *plen* argument is the size of the passed in struct.
* *flags* argument can be a combination of one or more of the
* *ctx* is either **struct xdp_md** for XDP programs or
* **struct sk_buff** tc cls_act programs.
* Return
- * Egress device index on success, 0 if packet needs to continue
- * up the stack for further processing or a negative error in case
- * of failure.
+ * * < 0 if any input argument is invalid
+ * * 0 on success (packet is forwarded, nexthop neighbor exists)
+ * * > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the
+ * packet is not forwarded or needs assist from full stack
*
* int bpf_sock_hash_update(struct bpf_sock_ops_kern *skops, struct bpf_map *map, void *key, u64 flags)
* Description
* This helper is only available is the kernel was compiled with
* the **CONFIG_BPF_LIRC_MODE2** configuration option set to
* "**y**".
- *
* Return
* 0
*
* This helper is only available is the kernel was compiled with
* the **CONFIG_BPF_LIRC_MODE2** configuration option set to
* "**y**".
- *
* Return
* 0
*
* Arg1: old_state
* Arg2: new_state
*/
+ BPF_SOCK_OPS_TCP_LISTEN_CB, /* Called on listen(2), right after
+ * socket transition to LISTEN state.
+ */
};
/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
#define BPF_FIB_LOOKUP_DIRECT BIT(0)
#define BPF_FIB_LOOKUP_OUTPUT BIT(1)
+enum {
+ BPF_FIB_LKUP_RET_SUCCESS, /* lookup successful */
+ BPF_FIB_LKUP_RET_BLACKHOLE, /* dest is blackholed; can be dropped */
+ BPF_FIB_LKUP_RET_UNREACHABLE, /* dest is unreachable; can be dropped */
+ BPF_FIB_LKUP_RET_PROHIBIT, /* dest not allowed; can be dropped */
+ BPF_FIB_LKUP_RET_NOT_FWDED, /* packet is not forwarded */
+ BPF_FIB_LKUP_RET_FWD_DISABLED, /* fwding is not enabled on ingress */
+ BPF_FIB_LKUP_RET_UNSUPP_LWT, /* fwd requires encapsulation */
+ BPF_FIB_LKUP_RET_NO_NEIGH, /* no neighbor entry for nh */
+ BPF_FIB_LKUP_RET_FRAG_NEEDED, /* fragmentation required to fwd */
+};
+
struct bpf_fib_lookup {
/* input: network family for lookup (AF_INET, AF_INET6)
* output: network family of egress nexthop
/* total length of packet from network header - used for MTU check */
__u16 tot_len;
- __u32 ifindex; /* L3 device index for lookup */
+
+ /* input: L3 device index for lookup
+ * output: device index from FIB lookup
+ */
+ __u32 ifindex;
union {
/* inputs to lookup */
__u8 tos; /* AF_INET */
- __be32 flowlabel; /* AF_INET6 */
+ __be32 flowinfo; /* AF_INET6, flow_label + priority */
/* output: metric of fib result (IPv4/IPv6 only) */
__u32 rt_metric;
IFLA_BRPORT_BCAST_FLOOD,
IFLA_BRPORT_GROUP_FWD_MASK,
IFLA_BRPORT_NEIGH_SUPPRESS,
+ IFLA_BRPORT_ISOLATED,
__IFLA_BRPORT_MAX
};
#define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
IFLA_VXLAN_COLLECT_METADATA,
IFLA_VXLAN_LABEL,
IFLA_VXLAN_GPE,
+ IFLA_VXLAN_TTL_INHERIT,
__IFLA_VXLAN_MAX
};
#define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1)
#define KVM_CAP_S390_BPB 152
#define KVM_CAP_GET_MSR_FEATURES 153
#define KVM_CAP_HYPERV_EVENTFD 154
+#define KVM_CAP_HYPERV_TLBFLUSH 155
#ifdef KVM_CAP_IRQ_ROUTING
-libbpf-y := libbpf.o bpf.o nlattr.o btf.o
+libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o
endif
FEATURE_USER = .libbpf
-FEATURE_TESTS = libelf libelf-getphdrnum libelf-mmap bpf
+FEATURE_TESTS = libelf libelf-getphdrnum libelf-mmap bpf reallocarray
FEATURE_DISPLAY = libelf bpf
INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi -I$(srctree)/tools/perf
override CFLAGS += -DHAVE_ELF_GETPHDRNUM_SUPPORT
endif
+ifeq ($(feature-reallocarray), 0)
+ override CFLAGS += -DCOMPAT_NEED_REALLOCARRAY
+endif
+
# Append required CFLAGS
override CFLAGS += $(EXTRA_WARNINGS)
override CFLAGS += -Werror -Wall
#define BTF_MAX_NR_TYPES 65535
+#define IS_MODIFIER(k) (((k) == BTF_KIND_TYPEDEF) || \
+ ((k) == BTF_KIND_VOLATILE) || \
+ ((k) == BTF_KIND_CONST) || \
+ ((k) == BTF_KIND_RESTRICT))
+
static struct btf_type btf_void;
struct btf {
int fd;
};
-static const char *btf_name_by_offset(const struct btf *btf, uint32_t offset)
-{
- if (offset < btf->hdr->str_len)
- return &btf->strings[offset];
- else
- return NULL;
-}
-
static int btf_add_type(struct btf *btf, struct btf_type *t)
{
if (btf->types_size - btf->nr_types < 2) {
return 0;
}
-static const struct btf_type *btf_type_by_id(const struct btf *btf,
- uint32_t type_id)
-{
- if (type_id > btf->nr_types)
- return NULL;
-
- return btf->types[type_id];
-}
-
static bool btf_type_is_void(const struct btf_type *t)
{
return t == &btf_void || BTF_INFO_KIND(t->info) == BTF_KIND_FWD;
int64_t size = -1;
int i;
- t = btf_type_by_id(btf, type_id);
+ t = btf__type_by_id(btf, type_id);
for (i = 0; i < MAX_RESOLVE_DEPTH && !btf_type_is_void_or_null(t);
i++) {
size = btf_type_size(t);
return -EINVAL;
}
- t = btf_type_by_id(btf, type_id);
+ t = btf__type_by_id(btf, type_id);
}
if (size < 0)
return nelems * size;
}
+int btf__resolve_type(const struct btf *btf, __u32 type_id)
+{
+ const struct btf_type *t;
+ int depth = 0;
+
+ t = btf__type_by_id(btf, type_id);
+ while (depth < MAX_RESOLVE_DEPTH &&
+ !btf_type_is_void_or_null(t) &&
+ IS_MODIFIER(BTF_INFO_KIND(t->info))) {
+ type_id = t->type;
+ t = btf__type_by_id(btf, type_id);
+ depth++;
+ }
+
+ if (depth == MAX_RESOLVE_DEPTH || btf_type_is_void_or_null(t))
+ return -EINVAL;
+
+ return type_id;
+}
+
int32_t btf__find_by_name(const struct btf *btf, const char *type_name)
{
uint32_t i;
for (i = 1; i <= btf->nr_types; i++) {
const struct btf_type *t = btf->types[i];
- const char *name = btf_name_by_offset(btf, t->name_off);
+ const char *name = btf__name_by_offset(btf, t->name_off);
if (name && !strcmp(type_name, name))
return i;
{
return btf->fd;
}
+
+const char *btf__name_by_offset(const struct btf *btf, __u32 offset)
+{
+ if (offset < btf->hdr->str_len)
+ return &btf->strings[offset];
+ else
+ return NULL;
+}
+
+const struct btf_type *btf__type_by_id(const struct btf *btf,
+ __u32 type_id)
+{
+ if (type_id > btf->nr_types)
+ return NULL;
+
+ return btf->types[type_id];
+}
struct btf *btf__new(uint8_t *data, uint32_t size, btf_print_fn_t err_log);
int32_t btf__find_by_name(const struct btf *btf, const char *type_name);
int64_t btf__resolve_size(const struct btf *btf, uint32_t type_id);
+int btf__resolve_type(const struct btf *btf, __u32 type_id);
int btf__fd(const struct btf *btf);
+const char *btf__name_by_offset(const struct btf *btf, __u32 offset);
+const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 type_id);
#endif
* License along with this program; if not, see <http://www.gnu.org/licenses>
*/
+#define _GNU_SOURCE
#include <stdlib.h>
#include <stdio.h>
#include <stdarg.h>
#include <sys/stat.h>
#include <sys/types.h>
#include <sys/vfs.h>
+#include <tools/libc_compat.h>
#include <libelf.h>
#include <gelf.h>
#define STRERR_BUFSIZE 128
-#define ERRNO_OFFSET(e) ((e) - __LIBBPF_ERRNO__START)
-#define ERRCODE_OFFSET(c) ERRNO_OFFSET(LIBBPF_ERRNO__##c)
-#define NR_ERRNO (__LIBBPF_ERRNO__END - __LIBBPF_ERRNO__START)
-
-static const char *libbpf_strerror_table[NR_ERRNO] = {
- [ERRCODE_OFFSET(LIBELF)] = "Something wrong in libelf",
- [ERRCODE_OFFSET(FORMAT)] = "BPF object format invalid",
- [ERRCODE_OFFSET(KVERSION)] = "'version' section incorrect or lost",
- [ERRCODE_OFFSET(ENDIAN)] = "Endian mismatch",
- [ERRCODE_OFFSET(INTERNAL)] = "Internal error in libbpf",
- [ERRCODE_OFFSET(RELOC)] = "Relocation failed",
- [ERRCODE_OFFSET(VERIFY)] = "Kernel verifier blocks program loading",
- [ERRCODE_OFFSET(PROG2BIG)] = "Program too big",
- [ERRCODE_OFFSET(KVER)] = "Incorrect kernel version",
- [ERRCODE_OFFSET(PROGTYPE)] = "Kernel doesn't support this program type",
- [ERRCODE_OFFSET(WRNGPID)] = "Wrong pid in netlink message",
- [ERRCODE_OFFSET(INVSEQ)] = "Invalid netlink sequence",
-};
-
-int libbpf_strerror(int err, char *buf, size_t size)
-{
- if (!buf || !size)
- return -1;
-
- err = err > 0 ? err : -err;
-
- if (err < __LIBBPF_ERRNO__START) {
- int ret;
-
- ret = strerror_r(err, buf, size);
- buf[size - 1] = '\0';
- return ret;
- }
-
- if (err < __LIBBPF_ERRNO__END) {
- const char *msg;
-
- msg = libbpf_strerror_table[ERRNO_OFFSET(err)];
- snprintf(buf, size, "%s", msg);
- buf[size - 1] = '\0';
- return 0;
- }
-
- snprintf(buf, size, "Unknown libbpf error %d", err);
- buf[size - 1] = '\0';
- return -1;
-}
-
#define CHECK_ERR(action, err, out) do { \
err = action; \
if (err) \
size_t nr_maps;
bool loaded;
+ bool has_pseudo_calls;
/*
* Information when doing elf related work. Only valid if fd
progs = obj->programs;
nr_progs = obj->nr_programs;
- progs = realloc(progs, sizeof(progs[0]) * (nr_progs + 1));
+ progs = reallocarray(progs, nr_progs + 1, sizeof(progs[0]));
if (!progs) {
/*
* In this case the original obj->programs
const char *name = NULL;
prog = &obj->programs[pi];
- if (prog->idx == obj->efile.text_shndx) {
- name = ".text";
- goto skip_search;
- }
for (si = 0; si < symbols->d_size / sizeof(GElf_Sym) && !name;
si++) {
}
}
+ if (!name && prog->idx == obj->efile.text_shndx)
+ name = ".text";
+
if (!name) {
pr_warning("failed to find sym for prog %s\n",
prog->section_name);
return -EINVAL;
}
-skip_search:
+
prog->name = strdup(name);
if (!prog->name) {
pr_warning("failed to allocate memory for prog sym %s\n",
continue;
}
- reloc = realloc(reloc,
- sizeof(*obj->efile.reloc) * nr_reloc);
+ reloc = reallocarray(reloc, nr_reloc,
+ sizeof(*obj->efile.reloc));
if (!reloc) {
pr_warning("realloc failed\n");
err = -ENOMEM;
prog->reloc_desc[i].type = RELO_CALL;
prog->reloc_desc[i].insn_idx = insn_idx;
prog->reloc_desc[i].text_off = sym.st_value;
+ obj->has_pseudo_calls = true;
continue;
}
return 0;
}
+int bpf_map__reuse_fd(struct bpf_map *map, int fd)
+{
+ struct bpf_map_info info = {};
+ __u32 len = sizeof(info);
+ int new_fd, err;
+ char *new_name;
+
+ err = bpf_obj_get_info_by_fd(fd, &info, &len);
+ if (err)
+ return err;
+
+ new_name = strdup(info.name);
+ if (!new_name)
+ return -errno;
+
+ new_fd = open("/", O_RDONLY | O_CLOEXEC);
+ if (new_fd < 0)
+ goto err_free_new_name;
+
+ new_fd = dup3(fd, new_fd, O_CLOEXEC);
+ if (new_fd < 0)
+ goto err_close_new_fd;
+
+ err = zclose(map->fd);
+ if (err)
+ goto err_close_new_fd;
+ free(map->name);
+
+ map->fd = new_fd;
+ map->name = new_name;
+ map->def.type = info.type;
+ map->def.key_size = info.key_size;
+ map->def.value_size = info.value_size;
+ map->def.max_entries = info.max_entries;
+ map->def.map_flags = info.map_flags;
+ map->btf_key_type_id = info.btf_key_type_id;
+ map->btf_value_type_id = info.btf_value_type_id;
+
+ return 0;
+
+err_close_new_fd:
+ close(new_fd);
+err_free_new_name:
+ free(new_name);
+ return -errno;
+}
+
static int
bpf_object__create_maps(struct bpf_object *obj)
{
struct bpf_map_def *def = &map->def;
int *pfd = &map->fd;
+ if (map->fd >= 0) {
+ pr_debug("skip map create (preset) %s: fd=%d\n",
+ map->name, map->fd);
+ continue;
+ }
+
create_attr.name = map->name;
create_attr.map_ifindex = map->map_ifindex;
create_attr.map_type = def->type;
return -LIBBPF_ERRNO__RELOC;
}
new_cnt = prog->insns_cnt + text->insns_cnt;
- new_insn = realloc(prog->insns, new_cnt * sizeof(*insn));
+ new_insn = reallocarray(prog->insns, new_cnt, sizeof(*insn));
if (!new_insn) {
pr_warning("oom in prog realloc\n");
return -ENOMEM;
return err;
}
+static bool bpf_program__is_function_storage(struct bpf_program *prog,
+ struct bpf_object *obj)
+{
+ return prog->idx == obj->efile.text_shndx && obj->has_pseudo_calls;
+}
+
static int
bpf_object__load_progs(struct bpf_object *obj)
{
int err;
for (i = 0; i < obj->nr_programs; i++) {
- if (obj->programs[i].idx == obj->efile.text_shndx)
+ if (bpf_program__is_function_storage(&obj->programs[i], obj))
continue;
err = bpf_program__load(&obj->programs[i],
obj->license,
return ERR_PTR(err);
}
-struct bpf_object *bpf_object__open(const char *path)
+struct bpf_object *bpf_object__open_xattr(struct bpf_object_open_attr *attr)
{
/* param validation */
- if (!path)
+ if (!attr->file)
return NULL;
- pr_debug("loading %s\n", path);
+ pr_debug("loading %s\n", attr->file);
+
+ return __bpf_object__open(attr->file, NULL, 0,
+ bpf_prog_type__needs_kver(attr->prog_type));
+}
- return __bpf_object__open(path, NULL, 0, true);
+struct bpf_object *bpf_object__open(const char *path)
+{
+ struct bpf_object_open_attr attr = {
+ .file = path,
+ .prog_type = BPF_PROG_TYPE_UNSPEC,
+ };
+
+ return bpf_object__open_xattr(&attr);
}
struct bpf_object *bpf_object__open_buffer(void *obj_buf,
return obj ? obj->priv : ERR_PTR(-EINVAL);
}
-struct bpf_program *
-bpf_program__next(struct bpf_program *prev, struct bpf_object *obj)
+static struct bpf_program *
+__bpf_program__next(struct bpf_program *prev, struct bpf_object *obj)
{
size_t idx;
return &obj->programs[idx];
}
+struct bpf_program *
+bpf_program__next(struct bpf_program *prev, struct bpf_object *obj)
+{
+ struct bpf_program *prog = prev;
+
+ do {
+ prog = __bpf_program__next(prog, obj);
+ } while (prog && bpf_program__is_function_storage(prog, obj));
+
+ return prog;
+}
+
int bpf_program__set_priv(struct bpf_program *prog, void *priv,
bpf_program_clear_priv_t clear_priv)
{
return prog ? prog->priv : ERR_PTR(-EINVAL);
}
+void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex)
+{
+ prog->prog_ifindex = ifindex;
+}
+
const char *bpf_program__title(struct bpf_program *prog, bool needs_copy)
{
const char *title;
BPF_PROG_SEC("lwt_in", BPF_PROG_TYPE_LWT_IN),
BPF_PROG_SEC("lwt_out", BPF_PROG_TYPE_LWT_OUT),
BPF_PROG_SEC("lwt_xmit", BPF_PROG_TYPE_LWT_XMIT),
+ BPF_PROG_SEC("lwt_seg6local", BPF_PROG_TYPE_LWT_SEG6LOCAL),
BPF_PROG_SEC("sockops", BPF_PROG_TYPE_SOCK_OPS),
BPF_PROG_SEC("sk_skb", BPF_PROG_TYPE_SK_SKB),
BPF_PROG_SEC("sk_msg", BPF_PROG_TYPE_SK_MSG),
+ BPF_PROG_SEC("lirc_mode2", BPF_PROG_TYPE_LIRC_MODE2),
BPF_SA_PROG_SEC("cgroup/bind4", BPF_CGROUP_INET4_BIND),
BPF_SA_PROG_SEC("cgroup/bind6", BPF_CGROUP_INET6_BIND),
BPF_SA_PROG_SEC("cgroup/connect4", BPF_CGROUP_INET4_CONNECT),
#undef BPF_S_PROG_SEC
#undef BPF_SA_PROG_SEC
-static int bpf_program__identify_section(struct bpf_program *prog)
+int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
+ enum bpf_attach_type *expected_attach_type)
{
int i;
- if (!prog->section_name)
- goto err;
-
- for (i = 0; i < ARRAY_SIZE(section_names); i++)
- if (strncmp(prog->section_name, section_names[i].sec,
- section_names[i].len) == 0)
- return i;
+ if (!name)
+ return -EINVAL;
-err:
- pr_warning("failed to guess program type based on section name %s\n",
- prog->section_name);
+ for (i = 0; i < ARRAY_SIZE(section_names); i++) {
+ if (strncmp(name, section_names[i].sec, section_names[i].len))
+ continue;
+ *prog_type = section_names[i].prog_type;
+ *expected_attach_type = section_names[i].expected_attach_type;
+ return 0;
+ }
+ return -EINVAL;
+}
- return -1;
+static int
+bpf_program__identify_section(struct bpf_program *prog,
+ enum bpf_prog_type *prog_type,
+ enum bpf_attach_type *expected_attach_type)
+{
+ return libbpf_prog_type_by_name(prog->section_name, prog_type,
+ expected_attach_type);
}
int bpf_map__fd(struct bpf_map *map)
return map ? map->priv : ERR_PTR(-EINVAL);
}
+bool bpf_map__is_offload_neutral(struct bpf_map *map)
+{
+ return map->def.type == BPF_MAP_TYPE_PERF_EVENT_ARRAY;
+}
+
+void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex)
+{
+ map->map_ifindex = ifindex;
+}
+
struct bpf_map *
bpf_map__next(struct bpf_map *prev, struct bpf_object *obj)
{
int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
struct bpf_object **pobj, int *prog_fd)
{
+ struct bpf_object_open_attr open_attr = {
+ .file = attr->file,
+ .prog_type = attr->prog_type,
+ };
struct bpf_program *prog, *first_prog = NULL;
enum bpf_attach_type expected_attach_type;
enum bpf_prog_type prog_type;
struct bpf_object *obj;
struct bpf_map *map;
- int section_idx;
int err;
if (!attr)
if (!attr->file)
return -EINVAL;
- obj = __bpf_object__open(attr->file, NULL, 0,
- bpf_prog_type__needs_kver(attr->prog_type));
+ obj = bpf_object__open_xattr(&open_attr);
if (IS_ERR_OR_NULL(obj))
return -ENOENT;
prog->prog_ifindex = attr->ifindex;
expected_attach_type = attr->expected_attach_type;
if (prog_type == BPF_PROG_TYPE_UNSPEC) {
- section_idx = bpf_program__identify_section(prog);
- if (section_idx < 0) {
+ err = bpf_program__identify_section(prog, &prog_type,
+ &expected_attach_type);
+ if (err < 0) {
+ pr_warning("failed to guess program type based on section name %s\n",
+ prog->section_name);
bpf_object__close(obj);
return -EINVAL;
}
- prog_type = section_names[section_idx].prog_type;
- expected_attach_type =
- section_names[section_idx].expected_attach_type;
}
bpf_program__set_type(prog, prog_type);
bpf_program__set_expected_attach_type(prog,
expected_attach_type);
- if (prog->idx != obj->efile.text_shndx && !first_prog)
+ if (!bpf_program__is_function_storage(prog, obj) && !first_prog)
first_prog = prog;
}
bpf_map__for_each(map, obj) {
- map->map_ifindex = attr->ifindex;
+ if (!bpf_map__is_offload_neutral(map))
+ map->map_ifindex = attr->ifindex;
}
if (!first_prog) {
/* Hide internal to user */
struct bpf_object;
+struct bpf_object_open_attr {
+ const char *file;
+ enum bpf_prog_type prog_type;
+};
+
struct bpf_object *bpf_object__open(const char *path);
+struct bpf_object *bpf_object__open_xattr(struct bpf_object_open_attr *attr);
struct bpf_object *bpf_object__open_buffer(void *obj_buf,
size_t obj_buf_sz,
const char *name);
bpf_object_clear_priv_t clear_priv);
void *bpf_object__priv(struct bpf_object *prog);
+int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
+ enum bpf_attach_type *expected_attach_type);
+
/* Accessors of bpf_program */
struct bpf_program;
struct bpf_program *bpf_program__next(struct bpf_program *prog,
bpf_program_clear_priv_t clear_priv);
void *bpf_program__priv(struct bpf_program *prog);
+void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex);
const char *bpf_program__title(struct bpf_program *prog, bool needs_copy);
int bpf_map__set_priv(struct bpf_map *map, void *priv,
bpf_map_clear_priv_t clear_priv);
void *bpf_map__priv(struct bpf_map *map);
+int bpf_map__reuse_fd(struct bpf_map *map, int fd);
+bool bpf_map__is_offload_neutral(struct bpf_map *map);
+void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex);
int bpf_map__pin(struct bpf_map *map, const char *path);
long libbpf_get_error(const void *ptr);
--- /dev/null
+// SPDX-License-Identifier: LGPL-2.1
+
+/*
+ * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org>
+ * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
+ * Copyright (C) 2015 Huawei Inc.
+ * Copyright (C) 2017 Nicira, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation;
+ * version 2.1 of the License (not later!)
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not, see <http://www.gnu.org/licenses>
+ */
+
+#include <stdio.h>
+#include <string.h>
+
+#include "libbpf.h"
+
+#define ERRNO_OFFSET(e) ((e) - __LIBBPF_ERRNO__START)
+#define ERRCODE_OFFSET(c) ERRNO_OFFSET(LIBBPF_ERRNO__##c)
+#define NR_ERRNO (__LIBBPF_ERRNO__END - __LIBBPF_ERRNO__START)
+
+static const char *libbpf_strerror_table[NR_ERRNO] = {
+ [ERRCODE_OFFSET(LIBELF)] = "Something wrong in libelf",
+ [ERRCODE_OFFSET(FORMAT)] = "BPF object format invalid",
+ [ERRCODE_OFFSET(KVERSION)] = "'version' section incorrect or lost",
+ [ERRCODE_OFFSET(ENDIAN)] = "Endian mismatch",
+ [ERRCODE_OFFSET(INTERNAL)] = "Internal error in libbpf",
+ [ERRCODE_OFFSET(RELOC)] = "Relocation failed",
+ [ERRCODE_OFFSET(VERIFY)] = "Kernel verifier blocks program loading",
+ [ERRCODE_OFFSET(PROG2BIG)] = "Program too big",
+ [ERRCODE_OFFSET(KVER)] = "Incorrect kernel version",
+ [ERRCODE_OFFSET(PROGTYPE)] = "Kernel doesn't support this program type",
+ [ERRCODE_OFFSET(WRNGPID)] = "Wrong pid in netlink message",
+ [ERRCODE_OFFSET(INVSEQ)] = "Invalid netlink sequence",
+};
+
+int libbpf_strerror(int err, char *buf, size_t size)
+{
+ if (!buf || !size)
+ return -1;
+
+ err = err > 0 ? err : -err;
+
+ if (err < __LIBBPF_ERRNO__START) {
+ int ret;
+
+ ret = strerror_r(err, buf, size);
+ buf[size - 1] = '\0';
+ return ret;
+ }
+
+ if (err < __LIBBPF_ERRNO__END) {
+ const char *msg;
+
+ msg = libbpf_strerror_table[ERRNO_OFFSET(err)];
+ snprintf(buf, size, "%s", msg);
+ buf[size - 1] = '\0';
+ return 0;
+ }
+
+ snprintf(buf, size, "Unknown libbpf error %d", err);
+ buf[size - 1] = '\0';
+ return -1;
+}
"lbug_with_loc",
"fortify_panic",
"usercopy_abort",
+ "machine_real_restart",
};
if (func->bind == STB_WEAK)
This option should be used together with "-I" option.
example: 'perf stat -I 1000 --interval-count 2 -e cycles -a'
+--interval-clear::
+Clear the screen before next interval.
+
--timeout msecs::
Stop the 'perf stat' session and print count deltas after N milliseconds (minimum: 10 ms).
This option is not supported with the "-I" option.
u64 ip;
u64 skip_slot = -1;
- if (chain->nr < 3)
+ if (!chain || chain->nr < 3)
return skip_slot;
ip = chain->ips[2];
330 common pkey_alloc __x64_sys_pkey_alloc
331 common pkey_free __x64_sys_pkey_free
332 common statx __x64_sys_statx
+333 common io_pgetevents __x64_sys_io_pgetevents
+334 common rseq __x64_sys_rseq
#
# x32-specific system call numbers start at 512 to avoid cache impact
u8 *global_data;
u8 *process_data;
u8 *thread_data;
- u64 bytes_done;
+ u64 bytes_done, secs;
long work_done;
u32 l;
struct rusage rusage;
timersub(&stop, &start0, &diff);
td->runtime_ns = diff.tv_sec * NSEC_PER_SEC;
td->runtime_ns += diff.tv_usec * NSEC_PER_USEC;
- td->speed_gbs = bytes_done / (td->runtime_ns / NSEC_PER_SEC) / 1e9;
+ secs = td->runtime_ns / NSEC_PER_SEC;
+ td->speed_gbs = secs ? bytes_done / secs / 1e9 : 0;
getrusage(RUSAGE_THREAD, &rusage);
td->system_time_ns = rusage.ru_stime.tv_sec * NSEC_PER_SEC;
return ret;
}
+static int process_feature_event(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_session *session)
+{
+ if (event->feat.feat_id < HEADER_LAST_FEATURE)
+ return perf_event__process_feature(tool, event, session);
+ return 0;
+}
+
static int hist_entry__tty_annotate(struct hist_entry *he,
struct perf_evsel *evsel,
struct perf_annotate *ann)
.attr = perf_event__process_attr,
.build_id = perf_event__process_build_id,
.tracing_data = perf_event__process_tracing_data,
- .feature = perf_event__process_feature,
+ .feature = process_feature_event,
.ordered_events = true,
.ordering_requires_timestamps = true,
},
struct compute_stats cstats;
+ unsigned long paddr;
+ unsigned long paddr_cnt;
+ bool paddr_zero;
+ char *nodestr;
+
/*
* must be at the end,
* because of its callchain dynamic entry
*/
struct hist_entry he;
-
- unsigned long paddr;
- unsigned long paddr_cnt;
- bool paddr_zero;
- char *nodestr;
};
static char const *coalesce_default = "pid,iaddr";
}
/*
- * All features are received, we can force the
+ * (feat_id = HEADER_LAST_FEATURE) is the end marker which
+ * means all features are received, now we can force the
* group if needed.
*/
setup_forced_leader(rep, session->evlist);
PERF_OUTPUT_EVNAME | PERF_OUTPUT_TRACE
},
+ [PERF_TYPE_HW_CACHE] = {
+ .user_set = false,
+
+ .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
+ PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
+ PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
+ PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET |
+ PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD,
+
+ .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
+ },
+
[PERF_TYPE_RAW] = {
.user_set = false,
struct perf_evlist *evlist;
struct perf_evsel *evsel, *pos;
int err;
+ static struct perf_evsel_script *es;
err = perf_event__process_attr(tool, event, pevlist);
if (err)
evlist = *pevlist;
evsel = perf_evlist__last(*pevlist);
+ if (!evsel->priv) {
+ if (scr->per_event_dump) {
+ evsel->priv = perf_evsel_script__new(evsel,
+ scr->session->data);
+ } else {
+ es = zalloc(sizeof(*es));
+ if (!es)
+ return -ENOMEM;
+ es->fp = stdout;
+ evsel->priv = es;
+ }
+ }
+
if (evsel->attr.type >= PERF_TYPE_MAX &&
evsel->attr.type != PERF_TYPE_SYNTH)
return 0;
return set_maps(script);
}
+static int process_feature_event(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_session *session)
+{
+ if (event->feat.feat_id < HEADER_LAST_FEATURE)
+ return perf_event__process_feature(tool, event, session);
+ return 0;
+}
+
#ifdef HAVE_AUXTRACE_SUPPORT
static int perf_script__process_auxtrace_info(struct perf_tool *tool,
union perf_event *event,
.attr = process_attr,
.event_update = perf_event__process_event_update,
.tracing_data = perf_event__process_tracing_data,
- .feature = perf_event__process_feature,
+ .feature = process_feature_event,
.build_id = perf_event__process_build_id,
.id_index = perf_event__process_id_index,
.auxtrace_info = perf_script__process_auxtrace_info,
"+field to add and -field to remove."
"Valid types: hw,sw,trace,raw,synth. "
"Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
- "addr,symoff,period,iregs,uregs,brstack,brstacksym,flags,"
- "bpf-output,callindent,insn,insnlen,brstackinsn,synth,phys_addr",
+ "addr,symoff,srcline,period,iregs,uregs,brstack,"
+ "brstacksym,flags,bpf-output,brstackinsn,brstackoff,"
+ "callindent,insn,insnlen,synth,phys_addr,metric,misc",
parse_output_fields),
OPT_BOOLEAN('a', "all-cpus", &system_wide,
"system-wide collection from all CPUs"),
#include "util/tool.h"
#include "util/string2.h"
#include "util/metricgroup.h"
+#include "util/top.h"
#include "asm/bug.h"
#include <linux/time64.h>
typedef int (*aggr_get_id_t)(struct cpu_map *m, int cpu);
+#define METRIC_ONLY_LEN 20
+
static int run_count = 1;
static bool no_inherit = false;
static volatile pid_t child_pid = -1;
static aggr_get_id_t aggr_get_id;
static bool append_file;
static bool interval_count;
+static bool interval_clear;
static const char *output_name;
static int output_fd;
static int print_free_counters_hint;
static u64 *walltime_run;
static bool ru_display = false;
static struct rusage ru_data;
+static unsigned int metric_only_len = METRIC_ONLY_LEN;
struct perf_stat {
bool record;
fprintf(out, "%s%s%s%s", csv_sep, vals, csv_sep, unit);
}
-#define METRIC_ONLY_LEN 20
-
/* Filter out some columns that don't work well in metrics only mode */
static bool valid_only_metric(const char *unit)
{
struct outstate *os = ctx;
FILE *out = os->fh;
- int n;
- char buf[1024];
- unsigned mlen = METRIC_ONLY_LEN;
+ char buf[1024], str[1024];
+ unsigned mlen = metric_only_len;
if (!valid_only_metric(unit))
return;
unit = fixunit(buf, os->evsel, unit);
- if (color)
- n = color_fprintf(out, color, fmt, val);
- else
- n = fprintf(out, fmt, val);
- if (n > METRIC_ONLY_LEN)
- n = METRIC_ONLY_LEN;
if (mlen < strlen(unit))
mlen = strlen(unit) + 1;
- fprintf(out, "%*s", mlen - n, "");
+
+ if (color)
+ mlen += strlen(color) + sizeof(PERF_COLOR_RESET) - 1;
+
+ color_snprintf(str, sizeof(str), color ?: "", fmt, val);
+ fprintf(out, "%*s ", mlen, str);
}
static void print_metric_only_csv(void *ctx, const char *color __maybe_unused,
if (csv_output)
fprintf(os->fh, "%s%s", unit, csv_sep);
else
- fprintf(os->fh, "%-*s ", METRIC_ONLY_LEN, unit);
+ fprintf(os->fh, "%*s ", metric_only_len, unit);
}
static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
FILE *output = stat_config.output;
static int num_print_interval;
+ if (interval_clear)
+ puts(CONSOLE_CLEAR);
+
sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, csv_sep);
- if (num_print_interval == 0 && !csv_output) {
+ if ((num_print_interval == 0 && !csv_output) || interval_clear) {
switch (stat_config.aggr_mode) {
case AGGR_SOCKET:
fprintf(output, "# time socket cpus");
fprintf(output, " counts %*s events\n", unit_width, "unit");
break;
case AGGR_NONE:
- fprintf(output, "# time CPU");
+ fprintf(output, "# time CPU ");
if (!metric_only)
fprintf(output, " counts %*s events\n", unit_width, "unit");
break;
}
}
- if (num_print_interval == 0 && metric_only)
+ if ((num_print_interval == 0 && metric_only) || interval_clear)
print_metric_headers(" ", true);
if (++num_print_interval == 25)
num_print_interval = 0;
"(overhead is possible for values <= 100ms)"),
OPT_INTEGER(0, "interval-count", &stat_config.times,
"print counts for fixed number of times"),
+ OPT_BOOLEAN(0, "interval-clear", &interval_clear,
+ "clear screen in between new interval"),
OPT_UINTEGER(0, "timeout", &stat_config.timeout,
"stop workload and print counts after a timeout period in ms (>= 10ms)"),
OPT_SET_UINT(0, "per-socket", &stat_config.aggr_mode,
(PERF_COUNT_HW_CACHE_OP_PREFETCH << 8) |
(PERF_COUNT_HW_CACHE_RESULT_MISS << 16) },
};
+ struct parse_events_error errinfo;
/* Set attrs if no event is selected and !null_run: */
if (null_run)
return 0;
if (transaction_run) {
- struct parse_events_error errinfo;
-
if (pmu_have_event("cpu", "cycles-ct") &&
pmu_have_event("cpu", "el-start"))
err = parse_events(evsel_list, transaction_attrs,
&errinfo);
if (err) {
fprintf(stderr, "Cannot set up transaction events\n");
+ parse_events_print_error(&errinfo, transaction_attrs);
return -1;
}
return 0;
pmu_have_event("msr", "smi")) {
if (!force_metric_only)
metric_only = true;
- err = parse_events(evsel_list, smi_cost_attrs, NULL);
+ err = parse_events(evsel_list, smi_cost_attrs, &errinfo);
} else {
fprintf(stderr, "To measure SMI cost, it needs "
"msr/aperf/, msr/smi/ and cpu/cycles/ support\n");
+ parse_events_print_error(&errinfo, smi_cost_attrs);
return -1;
}
if (err) {
if (topdown_attrs[0] && str) {
if (warn)
arch_topdown_group_warn();
- err = parse_events(evsel_list, str, NULL);
+ err = parse_events(evsel_list, str, &errinfo);
if (err) {
fprintf(stderr,
"Cannot set up top down events %s: %d\n",
str, err);
free(str);
+ parse_events_print_error(&errinfo, str);
return -1;
}
} else {
return 0;
}
+static bool test__intel_pt_valid(void)
+{
+ return !!perf_pmu__find("intel_pt");
+}
+
static int test__intel_pt(struct perf_evlist *evlist)
{
struct perf_evsel *evsel = perf_evlist__first(evlist);
const char *name;
__u32 type;
const int id;
+ bool (*valid)(void);
int (*check)(struct perf_evlist *evlist);
};
},
{
.name = "intel_pt//u",
+ .valid = test__intel_pt_valid,
.check = test__intel_pt,
.id = 52,
},
static int test_event(struct evlist_test *e)
{
+ struct parse_events_error err = { .idx = 0, };
struct perf_evlist *evlist;
int ret;
+ if (e->valid && !e->valid()) {
+ pr_debug("... SKIP");
+ return 0;
+ }
+
evlist = perf_evlist__new();
if (evlist == NULL)
return -ENOMEM;
- ret = parse_events(evlist, e->name, NULL);
+ ret = parse_events(evlist, e->name, &err);
if (ret) {
- pr_debug("failed to parse event '%s', err %d\n",
- e->name, ret);
+ pr_debug("failed to parse event '%s', err %d, str '%s'\n",
+ e->name, ret, err.str);
+ parse_events_print_error(&err, e->name);
} else {
ret = e->check(evlist);
}
for (i = 0; i < cnt; i++) {
struct evlist_test *e = &events[i];
- pr_debug("running test %d '%s'\n", e->id, e->name);
+ pr_debug("running test %d '%s'", e->id, e->name);
ret1 = test_event(e);
if (ret1)
ret2 = ret1;
+ pr_debug("\n");
}
return ret2;
}
while (!ret && (ent = readdir(dir))) {
- struct evlist_test e;
+ struct evlist_test e = { .id = 0, };
char name[2 * NAME_MAX + 1 + 12 + 3];
/* Names containing . are special and cannot be used directly */
perf_header__set_feat(&session->header, HEADER_CPU_TOPOLOGY);
perf_header__set_feat(&session->header, HEADER_NRCPUS);
+ perf_header__set_feat(&session->header, HEADER_ARCH);
session->header.data_size += DATA_SIZE;
gtk_tree_store_set(store, &iter, col_idx++, s, -1);
}
- if (hists__has_callchains(hists) &&
+ if (hist_entry__has_callchains(h) &&
symbol_conf.use_callchain && hists__has(hists, sym)) {
if (callchain_param.mode == CHAIN_GRAPH_REL)
total = symbol_conf.cumulate_callchain ?
raw_svector_ostream ostream(*Buffer);
legacy::PassManager PM;
- if (TargetMachine->addPassesToEmitFile(PM, ostream,
- TargetMachine::CGFT_ObjectFile)) {
+ bool NotAdded;
+#if CLANG_VERSION_MAJOR < 7
+ NotAdded = TargetMachine->addPassesToEmitFile(PM, ostream,
+ TargetMachine::CGFT_ObjectFile);
+#else
+ NotAdded = TargetMachine->addPassesToEmitFile(PM, ostream, nullptr,
+ TargetMachine::CGFT_ObjectFile);
+#endif
+ if (NotAdded) {
llvm::errs() << "TargetMachine can't emit a file of this type\n";
return std::unique_ptr<llvm::SmallVectorImpl<char>>(nullptr);;
}
int cpu_nr = ff->ph->env.nr_cpus_avail;
u64 size = 0;
struct perf_header *ph = ff->ph;
+ bool do_core_id_test = true;
ph->env.cpu = calloc(cpu_nr, sizeof(*ph->env.cpu));
if (!ph->env.cpu)
return 0;
}
+ /* On s390 the socket_id number is not related to the numbers of cpus.
+ * The socket_id number might be higher than the numbers of cpus.
+ * This depends on the configuration.
+ */
+ if (ph->env.arch && !strncmp(ph->env.arch, "s390", 4))
+ do_core_id_test = false;
+
for (i = 0; i < (u32)cpu_nr; i++) {
if (do_read_u32(ff, &nr))
goto free_cpu;
if (do_read_u32(ff, &nr))
goto free_cpu;
- if (nr != (u32)-1 && nr > (u32)cpu_nr) {
+ if (do_core_id_test && nr != (u32)-1 && nr > (u32)cpu_nr) {
pr_debug("socket_id number is too big."
"You may need to upgrade the perf tool.\n");
goto free_cpu;
pr_warning("invalid record type %d in pipe-mode\n", type);
return 0;
}
- if (feat == HEADER_RESERVED || feat > HEADER_LAST_FEATURE) {
+ if (feat == HEADER_RESERVED || feat >= HEADER_LAST_FEATURE) {
pr_warning("invalid record type %d in pipe-mode\n", type);
return -1;
}
static int hist_entry__init(struct hist_entry *he,
struct hist_entry *template,
- bool sample_self)
+ bool sample_self,
+ size_t callchain_size)
{
*he = *template;
+ he->callchain_size = callchain_size;
if (symbol_conf.cumulate_callchain) {
he->stat_acc = malloc(sizeof(he->stat));
he = ops->new(callchain_size);
if (he) {
- err = hist_entry__init(he, template, sample_self);
+ err = hist_entry__init(he, template, sample_self, callchain_size);
if (err) {
ops->free(he);
he = NULL;
.raw_data = sample->raw_data,
.raw_size = sample->raw_size,
.ops = ops,
- };
+ }, *he = hists__findnew_entry(hists, &entry, al, sample_self);
- return hists__findnew_entry(hists, &entry, al, sample_self);
+ if (!hists->has_callchains && he && he->callchain_size != 0)
+ hists->has_callchains = true;
+ return he;
}
struct hist_entry *hists__add_entry(struct hists *hists,
struct events_stats stats;
u64 event_stream;
u16 col_len[HISTC_NR_COLS];
+ bool has_callchains;
int socket_filter;
struct perf_hpp_list *hpp_list;
struct list_head hpp_formats;
static __pure inline bool hists__has_callchains(struct hists *hists)
{
- const struct perf_evsel *evsel = hists_to_evsel(hists);
- return evsel__has_callchain(evsel);
+ return hists->has_callchains;
}
int hists__init(void);
if (len < offs)
return INTEL_PT_NEED_MORE_BYTES;
byte = buf[offs++];
- payload |= (byte >> 1) << shift;
+ payload |= ((uint64_t)byte >> 1) << shift;
}
packet->type = INTEL_PT_CYC;
event_pmu:
PE_NAME opt_pmu_config
{
+ struct parse_events_state *parse_state = _parse_state;
+ struct parse_events_error *error = parse_state->error;
struct list_head *list, *orig_terms, *terms;
if (parse_events_copy_term_list($2, &orig_terms))
YYABORT;
+ if (error)
+ error->idx = @1.first_column;
+
ALLOC_LIST(list);
if (parse_events_add_pmu(_parse_state, list, $1, $2, false, false)) {
struct perf_pmu *pmu = NULL;
return 0;
}
+static void perf_pmu_assign_str(char *name, const char *field, char **old_str,
+ char **new_str)
+{
+ if (!*old_str)
+ goto set_new;
+
+ if (*new_str) { /* Have new string, check with old */
+ if (strcasecmp(*old_str, *new_str))
+ pr_debug("alias %s differs in field '%s'\n",
+ name, field);
+ zfree(old_str);
+ } else /* Nothing new --> keep old string */
+ return;
+set_new:
+ *old_str = *new_str;
+ *new_str = NULL;
+}
+
+static void perf_pmu_update_alias(struct perf_pmu_alias *old,
+ struct perf_pmu_alias *newalias)
+{
+ perf_pmu_assign_str(old->name, "desc", &old->desc, &newalias->desc);
+ perf_pmu_assign_str(old->name, "long_desc", &old->long_desc,
+ &newalias->long_desc);
+ perf_pmu_assign_str(old->name, "topic", &old->topic, &newalias->topic);
+ perf_pmu_assign_str(old->name, "metric_expr", &old->metric_expr,
+ &newalias->metric_expr);
+ perf_pmu_assign_str(old->name, "metric_name", &old->metric_name,
+ &newalias->metric_name);
+ perf_pmu_assign_str(old->name, "value", &old->str, &newalias->str);
+ old->scale = newalias->scale;
+ old->per_pkg = newalias->per_pkg;
+ old->snapshot = newalias->snapshot;
+ memcpy(old->unit, newalias->unit, sizeof(old->unit));
+}
+
+/* Delete an alias entry. */
+static void perf_pmu_free_alias(struct perf_pmu_alias *newalias)
+{
+ zfree(&newalias->name);
+ zfree(&newalias->desc);
+ zfree(&newalias->long_desc);
+ zfree(&newalias->topic);
+ zfree(&newalias->str);
+ zfree(&newalias->metric_expr);
+ zfree(&newalias->metric_name);
+ parse_events_terms__purge(&newalias->terms);
+ free(newalias);
+}
+
+/* Merge an alias, search in alias list. If this name is already
+ * present merge both of them to combine all information.
+ */
+static bool perf_pmu_merge_alias(struct perf_pmu_alias *newalias,
+ struct list_head *alist)
+{
+ struct perf_pmu_alias *a;
+
+ list_for_each_entry(a, alist, list) {
+ if (!strcasecmp(newalias->name, a->name)) {
+ perf_pmu_update_alias(a, newalias);
+ perf_pmu_free_alias(newalias);
+ return true;
+ }
+ }
+ return false;
+}
+
static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
char *desc, char *val,
char *long_desc, char *topic,
char *metric_expr,
char *metric_name)
{
+ struct parse_events_term *term;
struct perf_pmu_alias *alias;
int ret;
int num;
+ char newval[256];
alias = malloc(sizeof(*alias));
if (!alias)
return ret;
}
+ /* Scan event and remove leading zeroes, spaces, newlines, some
+ * platforms have terms specified as
+ * event=0x0091 (read from files ../<PMU>/events/<FILE>
+ * and terms specified as event=0x91 (read from JSON files).
+ *
+ * Rebuild string to make alias->str member comparable.
+ */
+ memset(newval, 0, sizeof(newval));
+ ret = 0;
+ list_for_each_entry(term, &alias->terms, list) {
+ if (ret)
+ ret += scnprintf(newval + ret, sizeof(newval) - ret,
+ ",");
+ if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM)
+ ret += scnprintf(newval + ret, sizeof(newval) - ret,
+ "%s=%#x", term->config, term->val.num);
+ else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR)
+ ret += scnprintf(newval + ret, sizeof(newval) - ret,
+ "%s=%s", term->config, term->val.str);
+ }
+
alias->name = strdup(name);
if (dir) {
/*
snprintf(alias->unit, sizeof(alias->unit), "%s", unit);
}
alias->per_pkg = perpkg && sscanf(perpkg, "%d", &num) == 1 && num == 1;
- alias->str = strdup(val);
+ alias->str = strdup(newval);
- list_add_tail(&alias->list, list);
+ if (!perf_pmu_merge_alias(alias, list))
+ list_add_tail(&alias->list, list);
return 0;
}
buf[ret] = 0;
+ /* Remove trailing newline from sysfs file */
+ rtrim(buf);
+
return __perf_pmu__new_alias(list, dir, name, NULL, buf, NULL, NULL, NULL,
NULL, NULL, NULL);
}
char level;
u8 filtered;
+
+ u16 callchain_size;
union {
/*
* Since perf diff only supports the stdio output, TUI
static __pure inline bool hist_entry__has_callchains(struct hist_entry *he)
{
- return hists__has_callchains(he->hists);
+ return he->callchain_size != 0;
}
static inline bool hist_entry__has_pairs(struct hist_entry *he)
.PP
\fB--hide column\fP do not show the specified built-in columns. May be invoked multiple times, or with a comma-separated list of column names. Use "--hide sysfs" to hide the sysfs statistics columns as a group.
.PP
-\fB--enable column\fP show the specified built-in columns, which are otherwise disabled, by default. Currently the only built-in counters disabled by default are "usec" and "Time_Of_Day_Seconds".
+\fB--enable column\fP show the specified built-in columns, which are otherwise disabled, by default. Currently the only built-in counters disabled by default are "usec", "Time_Of_Day_Seconds", "APIC" and "X2APIC".
The column name "all" can be used to enable all disabled-by-default built-in counters.
.PP
\fB--show column\fP show only the specified built-in columns. May be invoked multiple times, or with a comma-separated list of column names. Use "--show sysfs" to show the sysfs statistics columns as a group.
unsigned int has_hwp_epp; /* IA32_HWP_REQUEST[bits 31:24] */
unsigned int has_hwp_pkg; /* IA32_HWP_REQUEST_PKG */
unsigned int has_misc_feature_control;
+unsigned int first_counter_read = 1;
#define RAPL_PKG (1 << 0)
/* 0x610 MSR_PKG_POWER_LIMIT */
unsigned long long irq_count;
unsigned int smi_count;
unsigned int cpu_id;
+ unsigned int apic_id;
+ unsigned int x2apic_id;
unsigned int flags;
#define CPU_IS_FIRST_THREAD_IN_CORE 0x2
#define CPU_IS_FIRST_CORE_IN_PACKAGE 0x4
}
/*
- * Each string in this array is compared in --show and --hide cmdline.
- * Thus, strings that are proper sub-sets must follow their more specific peers.
+ * This list matches the column headers, except
+ * 1. built-in only, the sysfs counters are not here -- we learn of those at run-time
+ * 2. Core and CPU are moved to the end, we can't have strings that contain them
+ * matching on them for --show and --hide.
*/
struct msr_counter bic[] = {
{ 0x0, "usec" },
{ 0x0, "Time_Of_Day_Seconds" },
{ 0x0, "Package" },
+ { 0x0, "Node" },
{ 0x0, "Avg_MHz" },
+ { 0x0, "Busy%" },
{ 0x0, "Bzy_MHz" },
{ 0x0, "TSC_MHz" },
{ 0x0, "IRQ" },
{ 0x0, "SMI", "", 32, 0, FORMAT_DELTA, NULL},
- { 0x0, "Busy%" },
+ { 0x0, "sysfs" },
{ 0x0, "CPU%c1" },
{ 0x0, "CPU%c3" },
{ 0x0, "CPU%c6" },
{ 0x0, "Cor_J" },
{ 0x0, "GFX_J" },
{ 0x0, "RAM_J" },
- { 0x0, "Core" },
- { 0x0, "CPU" },
{ 0x0, "Mod%c6" },
- { 0x0, "sysfs" },
{ 0x0, "Totl%C0" },
{ 0x0, "Any%C0" },
{ 0x0, "GFX%C0" },
{ 0x0, "CPUGFX%" },
- { 0x0, "Node%" },
+ { 0x0, "Core" },
+ { 0x0, "CPU" },
+ { 0x0, "APIC" },
+ { 0x0, "X2APIC" },
};
-
-
#define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter))
#define BIC_USEC (1ULL << 0)
#define BIC_TOD (1ULL << 1)
#define BIC_Package (1ULL << 2)
-#define BIC_Avg_MHz (1ULL << 3)
-#define BIC_Bzy_MHz (1ULL << 4)
-#define BIC_TSC_MHz (1ULL << 5)
-#define BIC_IRQ (1ULL << 6)
-#define BIC_SMI (1ULL << 7)
-#define BIC_Busy (1ULL << 8)
-#define BIC_CPU_c1 (1ULL << 9)
-#define BIC_CPU_c3 (1ULL << 10)
-#define BIC_CPU_c6 (1ULL << 11)
-#define BIC_CPU_c7 (1ULL << 12)
-#define BIC_ThreadC (1ULL << 13)
-#define BIC_CoreTmp (1ULL << 14)
-#define BIC_CoreCnt (1ULL << 15)
-#define BIC_PkgTmp (1ULL << 16)
-#define BIC_GFX_rc6 (1ULL << 17)
-#define BIC_GFXMHz (1ULL << 18)
-#define BIC_Pkgpc2 (1ULL << 19)
-#define BIC_Pkgpc3 (1ULL << 20)
-#define BIC_Pkgpc6 (1ULL << 21)
-#define BIC_Pkgpc7 (1ULL << 22)
-#define BIC_Pkgpc8 (1ULL << 23)
-#define BIC_Pkgpc9 (1ULL << 24)
-#define BIC_Pkgpc10 (1ULL << 25)
-#define BIC_CPU_LPI (1ULL << 26)
-#define BIC_SYS_LPI (1ULL << 27)
-#define BIC_PkgWatt (1ULL << 26)
-#define BIC_CorWatt (1ULL << 27)
-#define BIC_GFXWatt (1ULL << 28)
-#define BIC_PkgCnt (1ULL << 29)
-#define BIC_RAMWatt (1ULL << 30)
-#define BIC_PKG__ (1ULL << 31)
-#define BIC_RAM__ (1ULL << 32)
-#define BIC_Pkg_J (1ULL << 33)
-#define BIC_Cor_J (1ULL << 34)
-#define BIC_GFX_J (1ULL << 35)
-#define BIC_RAM_J (1ULL << 36)
-#define BIC_Core (1ULL << 37)
-#define BIC_CPU (1ULL << 38)
-#define BIC_Mod_c6 (1ULL << 39)
-#define BIC_sysfs (1ULL << 40)
-#define BIC_Totl_c0 (1ULL << 41)
-#define BIC_Any_c0 (1ULL << 42)
-#define BIC_GFX_c0 (1ULL << 43)
-#define BIC_CPUGFX (1ULL << 44)
-#define BIC_Node (1ULL << 45)
-
-#define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD)
+#define BIC_Node (1ULL << 3)
+#define BIC_Avg_MHz (1ULL << 4)
+#define BIC_Busy (1ULL << 5)
+#define BIC_Bzy_MHz (1ULL << 6)
+#define BIC_TSC_MHz (1ULL << 7)
+#define BIC_IRQ (1ULL << 8)
+#define BIC_SMI (1ULL << 9)
+#define BIC_sysfs (1ULL << 10)
+#define BIC_CPU_c1 (1ULL << 11)
+#define BIC_CPU_c3 (1ULL << 12)
+#define BIC_CPU_c6 (1ULL << 13)
+#define BIC_CPU_c7 (1ULL << 14)
+#define BIC_ThreadC (1ULL << 15)
+#define BIC_CoreTmp (1ULL << 16)
+#define BIC_CoreCnt (1ULL << 17)
+#define BIC_PkgTmp (1ULL << 18)
+#define BIC_GFX_rc6 (1ULL << 19)
+#define BIC_GFXMHz (1ULL << 20)
+#define BIC_Pkgpc2 (1ULL << 21)
+#define BIC_Pkgpc3 (1ULL << 22)
+#define BIC_Pkgpc6 (1ULL << 23)
+#define BIC_Pkgpc7 (1ULL << 24)
+#define BIC_Pkgpc8 (1ULL << 25)
+#define BIC_Pkgpc9 (1ULL << 26)
+#define BIC_Pkgpc10 (1ULL << 27)
+#define BIC_CPU_LPI (1ULL << 28)
+#define BIC_SYS_LPI (1ULL << 29)
+#define BIC_PkgWatt (1ULL << 30)
+#define BIC_CorWatt (1ULL << 31)
+#define BIC_GFXWatt (1ULL << 32)
+#define BIC_PkgCnt (1ULL << 33)
+#define BIC_RAMWatt (1ULL << 34)
+#define BIC_PKG__ (1ULL << 35)
+#define BIC_RAM__ (1ULL << 36)
+#define BIC_Pkg_J (1ULL << 37)
+#define BIC_Cor_J (1ULL << 38)
+#define BIC_GFX_J (1ULL << 39)
+#define BIC_RAM_J (1ULL << 40)
+#define BIC_Mod_c6 (1ULL << 41)
+#define BIC_Totl_c0 (1ULL << 42)
+#define BIC_Any_c0 (1ULL << 43)
+#define BIC_GFX_c0 (1ULL << 44)
+#define BIC_CPUGFX (1ULL << 45)
+#define BIC_Core (1ULL << 46)
+#define BIC_CPU (1ULL << 47)
+#define BIC_APIC (1ULL << 48)
+#define BIC_X2APIC (1ULL << 49)
+
+#define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC)
unsigned long long bic_enabled = (0xFFFFFFFFFFFFFFFFULL & ~BIC_DISABLED_BY_DEFAULT);
-unsigned long long bic_present = BIC_USEC | BIC_TOD | BIC_sysfs;
+unsigned long long bic_present = BIC_USEC | BIC_TOD | BIC_sysfs | BIC_APIC | BIC_X2APIC;
#define DO_BIC(COUNTER_NAME) (bic_enabled & bic_present & COUNTER_NAME)
#define ENABLE_BIC(COUNTER_NAME) (bic_enabled |= COUNTER_NAME)
"when COMMAND completes.\n"
"If no COMMAND is specified, turbostat wakes every 5-seconds\n"
"to print statistics, until interrupted.\n"
- "--add add a counter\n"
- " eg. --add msr0x10,u64,cpu,delta,MY_TSC\n"
- "--cpu cpu-set limit output to summary plus cpu-set:\n"
- " {core | package | j,k,l..m,n-p }\n"
- "--quiet skip decoding system configuration header\n"
- "--interval sec.subsec Override default 5-second measurement interval\n"
- "--help print this help message\n"
- "--list list column headers only\n"
- "--num_iterations num number of the measurement iterations\n"
- "--out file create or truncate \"file\" for all output\n"
- "--version print version information\n"
+ " -a, --add add a counter\n"
+ " eg. --add msr0x10,u64,cpu,delta,MY_TSC\n"
+ " -c, --cpu cpu-set limit output to summary plus cpu-set:\n"
+ " {core | package | j,k,l..m,n-p }\n"
+ " -d, --debug displays usec, Time_Of_Day_Seconds and more debugging\n"
+ " -D, --Dump displays the raw counter values\n"
+ " -e, --enable [all | column]\n"
+ " shows all or the specified disabled column\n"
+ " -H, --hide [column|column,column,...]\n"
+ " hide the specified column(s)\n"
+ " -i, --interval sec.subsec\n"
+ " Override default 5-second measurement interval\n"
+ " -J, --Joules displays energy in Joules instead of Watts\n"
+ " -l, --list list column headers only\n"
+ " -n, --num_iterations num\n"
+ " number of the measurement iterations\n"
+ " -o, --out file\n"
+ " create or truncate \"file\" for all output\n"
+ " -q, --quiet skip decoding system configuration header\n"
+ " -s, --show [column|column,column,...]\n"
+ " show only the specified column(s)\n"
+ " -S, --Summary\n"
+ " limits output to 1-line system summary per interval\n"
+ " -T, --TCC temperature\n"
+ " sets the Thermal Control Circuit temperature in\n"
+ " degrees Celsius\n"
+ " -h, --help print this help message\n"
+ " -v, --version print version information\n"
"\n"
"For more help, run \"man turbostat\"\n");
}
outp += sprintf(outp, "%sCore", (printed++ ? delim : ""));
if (DO_BIC(BIC_CPU))
outp += sprintf(outp, "%sCPU", (printed++ ? delim : ""));
+ if (DO_BIC(BIC_APIC))
+ outp += sprintf(outp, "%sAPIC", (printed++ ? delim : ""));
+ if (DO_BIC(BIC_X2APIC))
+ outp += sprintf(outp, "%sX2APIC", (printed++ ? delim : ""));
if (DO_BIC(BIC_Avg_MHz))
outp += sprintf(outp, "%sAvg_MHz", (printed++ ? delim : ""));
if (DO_BIC(BIC_Busy))
outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
if (DO_BIC(BIC_CPU))
outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
+ if (DO_BIC(BIC_APIC))
+ outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
+ if (DO_BIC(BIC_X2APIC))
+ outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
} else {
if (DO_BIC(BIC_Package)) {
if (p)
}
if (DO_BIC(BIC_CPU))
outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), t->cpu_id);
+ if (DO_BIC(BIC_APIC))
+ outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), t->apic_id);
+ if (DO_BIC(BIC_X2APIC))
+ outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), t->x2apic_id);
}
if (DO_BIC(BIC_Avg_MHz))
int i;
struct msr_counter *mp;
+ /* we run cpuid just the 1st time, copy the results */
+ if (DO_BIC(BIC_APIC))
+ new->apic_id = old->apic_id;
+ if (DO_BIC(BIC_X2APIC))
+ new->x2apic_id = old->x2apic_id;
+
/*
* the timestamps from start of measurement interval are in "old"
* the timestamp from end of measurement interval are in "new"
int i;
struct msr_counter *mp;
+ /* copy un-changing apic_id's */
+ if (DO_BIC(BIC_APIC))
+ average.threads.apic_id = t->apic_id;
+ if (DO_BIC(BIC_X2APIC))
+ average.threads.x2apic_id = t->x2apic_id;
+
/* remember first tv_begin */
if (average.threads.tv_begin.tv_sec == 0)
average.threads.tv_begin = t->tv_begin;
return 0;
}
+void get_apic_id(struct thread_data *t)
+{
+ unsigned int eax, ebx, ecx, edx, max_level;
+
+ eax = ebx = ecx = edx = 0;
+
+ if (!genuine_intel)
+ return;
+
+ __cpuid(0, max_level, ebx, ecx, edx);
+
+ __cpuid(1, eax, ebx, ecx, edx);
+ t->apic_id = (ebx >> 24) & 0xf;
+
+ if (max_level < 0xb)
+ return;
+
+ if (!DO_BIC(BIC_X2APIC))
+ return;
+
+ ecx = 0;
+ __cpuid(0xb, eax, ebx, ecx, edx);
+ t->x2apic_id = edx;
+
+ if (debug && (t->apic_id != t->x2apic_id))
+ fprintf(stderr, "cpu%d: apic 0x%x x2apic 0x%x\n", t->cpu_id, t->apic_id, t->x2apic_id);
+}
+
/*
* get_counters(...)
* migrate to cpu
struct msr_counter *mp;
int i;
-
gettimeofday(&t->tv_begin, (struct timezone *)NULL);
if (cpu_migrate(cpu)) {
return -1;
}
+ if (first_counter_read)
+ get_apic_id(t);
retry:
t->tsc = rdtsc(); /* we are running on local CPU of interest */
if (pni[pkg].count > topo.nodes_per_pkg)
topo.nodes_per_pkg = pni[0].count;
+ /* Fake 1 node per pkg for machines that don't
+ * expose nodes and thus avoid -nan results
+ */
+ if (topo.nodes_per_pkg == 0)
+ topo.nodes_per_pkg = 1;
+
for (cpu = 0; cpu < topo.num_cpus; cpu++) {
pkg = cpus[cpu].physical_package_id;
node = cpus[cpu].physical_node_id;
}
}
+
void turbostat_loop()
{
int retval;
snapshot_proc_sysfs_files();
retval = for_all_cpus(get_counters, EVEN_COUNTERS);
+ first_counter_read = 0;
if (retval < -1) {
exit(retval);
} else if (retval == -1) {
if (!quiet) {
fprintf(outf, "%d CPUID levels; family:model:stepping 0x%x:%x:%x (%d:%d:%d)\n",
max_level, family, model, stepping, family, model, stepping);
- fprintf(outf, "CPUID(1): %s %s %s %s %s %s %s %s %s\n",
+ fprintf(outf, "CPUID(1): %s %s %s %s %s %s %s %s %s %s\n",
ecx & (1 << 0) ? "SSE3" : "-",
ecx & (1 << 3) ? "MONITOR" : "-",
ecx & (1 << 6) ? "SMX" : "-",
edx & (1 << 4) ? "TSC" : "-",
edx & (1 << 5) ? "MSR" : "-",
edx & (1 << 22) ? "ACPI-TM" : "-",
+ edx & (1 << 28) ? "HT" : "-",
edx & (1 << 29) ? "TM" : "-");
}
return;
}
-
/*
* in /dev/cpu/ return success for names that are numbers
* ie. filter out ".", "..", "microcode".
struct core_data *c;
struct pkg_data *p;
+
+ /* Workaround for systems where physical_node_id==-1
+ * and logical_node_id==(-1 - topo.num_cpus)
+ */
+ if (node_id < 0)
+ node_id = 0;
+
t = GET_THREAD(thread_base, thread_id, core_id, node_id, pkg_id);
c = GET_CORE(core_base, core_id, node_id, pkg_id);
p = GET_PKG(pkg_base, pkg_id);
snapshot_proc_sysfs_files();
status = for_all_cpus(get_counters, EVEN_COUNTERS);
+ first_counter_read = 0;
if (status)
exit(status);
/* clear affinity side-effect of get_counters() */
}
void print_version() {
- fprintf(outf, "turbostat version 18.06.01"
+ fprintf(outf, "turbostat version 18.06.20"
" - Len Brown <lenb@kernel.org>\n");
}
break;
case 'e':
/* --enable specified counter */
- bic_enabled |= bic_lookup(optarg, SHOW_LIST);
+ bic_enabled = bic_enabled | bic_lookup(optarg, SHOW_LIST);
break;
case 'd':
debug++;
int main(int argc, char **argv)
{
outf = stderr;
-
cmdline(argc, argv);
if (!quiet)
$(OUTPUT)/test_sock: cgroup_helpers.c
$(OUTPUT)/test_sock_addr: cgroup_helpers.c
$(OUTPUT)/test_sockmap: cgroup_helpers.c
+$(OUTPUT)/test_tcpbpf_user: cgroup_helpers.c
$(OUTPUT)/test_progs: trace_helpers.c
$(OUTPUT)/get_cgroup_id_user: cgroup_helpers.c
*
* On success, it returns 0, otherwise on failure it returns 1.
*/
-int join_cgroup(char *path)
+int join_cgroup(const char *path)
{
char cgroup_path[PATH_MAX + 1];
* On success, it returns the file descriptor. On failure it returns 0.
* If there is a failure, it prints the error to stderr.
*/
-int create_and_get_cgroup(char *path)
+int create_and_get_cgroup(const char *path)
{
char cgroup_path[PATH_MAX + 1];
int fd;
* which is an invalid cgroup id.
* If there is a failure, it prints the error to stderr.
*/
-unsigned long long get_cgroup_id(char *path)
+unsigned long long get_cgroup_id(const char *path)
{
int dirfd, err, flags, mount_id, fhsize;
union {
__FILE__, __LINE__, clean_errno(), ##__VA_ARGS__)
-int create_and_get_cgroup(char *path);
-int join_cgroup(char *path);
+int create_and_get_cgroup(const char *path);
+int join_cgroup(const char *path);
int setup_cgroup_environment(void);
void cleanup_cgroup_environment(void);
-unsigned long long get_cgroup_id(char *path);
+unsigned long long get_cgroup_id(const char *path);
#endif
CONFIG_CGROUP_BPF=y
CONFIG_NETDEVSIM=m
CONFIG_NET_CLS_ACT=y
+CONFIG_NET_SCHED=y
CONFIG_NET_SCH_INGRESS=y
+CONFIG_NET_IPIP=y
+CONFIG_IPV6=y
+CONFIG_NET_IPGRE_DEMUX=y
+CONFIG_NET_IPGRE=y
+CONFIG_IPV6_GRE=y
+CONFIG_CRYPTO_USER_API_HASH=m
+CONFIG_CRYPTO_HMAC=m
+CONFIG_CRYPTO_SHA256=m
+CONFIG_VXLAN=y
+CONFIG_GENEVE=y
#!/bin/sh
# SPDX-License-Identifier: GPL-2.0
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+msg="skip all tests:"
+if [ "$(id -u)" != "0" ]; then
+ echo $msg please run this as root >&2
+ exit $ksft_skip
+fi
+
SRC_TREE=../../../../
test_run()
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+msg="skip all tests:"
+if [ $UID != 0 ]; then
+ echo $msg please run this as root >&2
+ exit $ksft_skip
+fi
+
GREEN='\033[0;92m'
RED='\033[0;31m'
NC='\033[0m' # No Color
# An UDP datagram is sent from fb00::1 to fb00::6. The test succeeds if this
# datagram can be read on NS6 when binding to fb00::6.
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+msg="skip all tests:"
+if [ $UID != 0 ]; then
+ echo $msg please run this as root >&2
+ exit $ksft_skip
+fi
+
TMP_FILE="/tmp/selftest_lwt_seg6local.txt"
cleanup()
def bpftool_prog_list(expected=None, ns=""):
_, progs = bpftool("prog show", JSON=True, ns=ns, fail=True)
+ # Remove the base progs
+ for p in base_progs:
+ if p in progs:
+ progs.remove(p)
if expected is not None:
if len(progs) != expected:
fail(True, "%d BPF programs loaded, expected %d" %
def bpftool_map_list(expected=None, ns=""):
_, maps = bpftool("map show", JSON=True, ns=ns, fail=True)
+ # Remove the base maps
+ for m in base_maps:
+ if m in maps:
+ maps.remove(m)
if expected is not None:
if len(maps) != expected:
fail(True, "%d BPF maps loaded, expected %d" %
self.dfs = DebugfsDir(self.dfs_dir)
return self.dfs
+ def dfs_read(self, f):
+ path = os.path.join(self.dfs_dir, f)
+ _, data = cmd('cat %s' % (path))
+ return data.strip()
+
def dfs_num_bound_progs(self):
path = os.path.join(self.dfs_dir, "bpf_bound_progs")
_, progs = cmd('ls %s' % (path))
if skip_extack:
return
lines = output.split("\n")
- comp = len(lines) >= 2 and lines[1] == reference
+ comp = len(lines) >= 2 and lines[1] == 'Error: ' + reference
fail(not comp, "Missing or incorrect netlink extack message")
def check_extack_nsim(output, reference, args):
- check_extack(output, "Error: netdevsim: " + reference, args)
+ check_extack(output, "netdevsim: " + reference, args)
def check_no_extack(res, needle):
fail((res[1] + res[2]).count(needle) or (res[1] + res[2]).count("Warning:"),
# Check tools
ret, progs = bpftool("prog", fail=False)
skip(ret != 0, "bpftool not installed")
-# Check no BPF programs are loaded
-skip(len(progs) != 0, "BPF programs already loaded on the system")
+base_progs = progs
+_, base_maps = bpftool("map")
# Check netdevsim
ret, out = cmd("modprobe netdevsim", fail=False)
ret, _, err = sim.cls_bpf_add_filter(obj, skip_sw=True,
fail=False, include_stderr=True)
fail(ret == 0, "TC filter loaded without enabling TC offloads")
- check_extack(err, "Error: TC offload is disabled on net device.", args)
+ check_extack(err, "TC offload is disabled on net device.", args)
sim.wait_for_flush()
sim.set_ethtool_tc_offloads(True)
skip_sw=True,
fail=False, include_stderr=True)
fail(ret == 0, "Offloaded a filter to chain other than 0")
- check_extack(err, "Error: Driver supports only offload of chain 0.", args)
+ check_extack(err, "Driver supports only offload of chain 0.", args)
sim.tc_flush_filters()
start_test("Test TC replace...")
"Device parameters reported for non-offloaded program")
start_test("Test XDP prog replace with bad flags...")
- ret, _, err = sim.set_xdp(obj, "offload", force=True,
+ ret, _, err = sim.set_xdp(obj, "generic", force=True,
fail=False, include_stderr=True)
fail(ret == 0, "Replaced XDP program with a program in different mode")
- check_extack_nsim(err, "program loaded with different flags.", args)
+ fail(err.count("File exists") != 1, "Replaced driver XDP with generic")
ret, _, err = sim.set_xdp(obj, "", force=True,
fail=False, include_stderr=True)
fail(ret == 0, "Replaced XDP program with a program in different mode")
- check_extack_nsim(err, "program loaded with different flags.", args)
+ check_extack(err, "program loaded with different flags.", args)
start_test("Test XDP prog remove with bad flags...")
- ret, _, err = sim.unset_xdp("offload", force=True,
- fail=False, include_stderr=True)
- fail(ret == 0, "Removed program with a bad mode mode")
- check_extack_nsim(err, "program loaded with different flags.", args)
ret, _, err = sim.unset_xdp("", force=True,
fail=False, include_stderr=True)
- fail(ret == 0, "Removed program with a bad mode mode")
- check_extack_nsim(err, "program loaded with different flags.", args)
+ fail(ret == 0, "Removed program with a bad mode")
+ check_extack(err, "program loaded with different flags.", args)
start_test("Test MTU restrictions...")
ret, _ = sim.set_mtu(9000, fail=False)
rm(pin_file)
bpftool_prog_list_wait(expected=0)
+ start_test("Test multi-attachment XDP - attach...")
+ sim.set_xdp(obj, "offload")
+ xdp = sim.ip_link_show(xdp=True)["xdp"]
+ offloaded = sim.dfs_read("bpf_offloaded_id")
+ fail("prog" not in xdp, "Base program not reported in single program mode")
+ fail(len(ipl["xdp"]["attached"]) != 1,
+ "Wrong attached program count with one program")
+
+ sim.set_xdp(obj, "")
+ two_xdps = sim.ip_link_show(xdp=True)["xdp"]
+ offloaded2 = sim.dfs_read("bpf_offloaded_id")
+
+ fail(two_xdps["mode"] != 4, "Bad mode reported with multiple programs")
+ fail("prog" in two_xdps, "Base program reported in multi program mode")
+ fail(xdp["attached"][0] not in two_xdps["attached"],
+ "Offload program not reported after driver activated")
+ fail(len(two_xdps["attached"]) != 2,
+ "Wrong attached program count with two programs")
+ fail(two_xdps["attached"][0]["prog"]["id"] ==
+ two_xdps["attached"][1]["prog"]["id"],
+ "offloaded and drv programs have the same id")
+ fail(offloaded != offloaded2,
+ "offload ID changed after loading driver program")
+
+ start_test("Test multi-attachment XDP - replace...")
+ ret, _, err = sim.set_xdp(obj, "offload", fail=False, include_stderr=True)
+ fail(err.count("busy") != 1, "Replaced one of programs without -force")
+
+ start_test("Test multi-attachment XDP - detach...")
+ ret, _, err = sim.unset_xdp("drv", force=True,
+ fail=False, include_stderr=True)
+ fail(ret == 0, "Removed program with a bad mode")
+ check_extack(err, "program loaded with different flags.", args)
+
+ sim.unset_xdp("offload")
+ xdp = sim.ip_link_show(xdp=True)["xdp"]
+ offloaded = sim.dfs_read("bpf_offloaded_id")
+
+ fail(xdp["mode"] != 1, "Bad mode reported after multiple programs")
+ fail("prog" not in xdp,
+ "Base program not reported after multi program mode")
+ fail(xdp["attached"][0] not in two_xdps["attached"],
+ "Offload program not reported after driver activated")
+ fail(len(ipl["xdp"]["attached"]) != 1,
+ "Wrong attached program count with remaining programs")
+ fail(offloaded != "0", "offload ID reported with only driver program left")
+
+ start_test("Test multi-attachment XDP - device remove...")
+ sim.set_xdp(obj, "offload")
+ sim.remove()
+
+ sim = NetdevSim()
+ sim.set_ethtool_tc_offloads(True)
+
start_test("Test mixing of TC and XDP...")
sim.tc_add_ingress()
sim.set_xdp(obj, "offload")
return 0;
}
-static int sendmsg_to_server(const struct sockaddr_storage *addr,
- socklen_t addr_len, int set_cmsg, int *syscall_err)
+static int sendmsg_to_server(int type, const struct sockaddr_storage *addr,
+ socklen_t addr_len, int set_cmsg, int flags,
+ int *syscall_err)
{
union {
char buf[CMSG_SPACE(sizeof(struct in6_pktinfo))];
goto err;
}
- fd = socket(domain, SOCK_DGRAM, 0);
+ fd = socket(domain, type, 0);
if (fd == -1) {
log_err("Failed to create client socket");
goto err;
}
}
- if (sendmsg(fd, &hdr, 0) != sizeof(data)) {
+ if (sendmsg(fd, &hdr, flags) != sizeof(data)) {
log_err("Fail to send message to server");
*syscall_err = errno;
goto err;
return fd;
}
+static int fastconnect_to_server(const struct sockaddr_storage *addr,
+ socklen_t addr_len)
+{
+ int sendmsg_err;
+
+ return sendmsg_to_server(SOCK_STREAM, addr, addr_len, /*set_cmsg*/0,
+ MSG_FASTOPEN, &sendmsg_err);
+}
+
static int recvmsg_from_client(int sockfd, struct sockaddr_storage *src_addr)
{
struct timeval tv;
if (cmp_local_ip(clientfd, &expected_src_addr))
goto err;
+ if (test->type == SOCK_STREAM) {
+ /* Test TCP Fast Open scenario */
+ clientfd = fastconnect_to_server(&requested_addr, addr_len);
+ if (clientfd == -1)
+ goto err;
+
+ /* Make sure src and dst addrs were overridden properly */
+ if (cmp_peer_addr(clientfd, &expected_addr))
+ goto err;
+
+ if (cmp_local_ip(clientfd, &expected_src_addr))
+ goto err;
+ }
+
goto out;
err:
err = -1;
if (clientfd >= 0)
close(clientfd);
- clientfd = sendmsg_to_server(&requested_addr, addr_len,
- set_cmsg, &err);
+ clientfd = sendmsg_to_server(test->type, &requested_addr,
+ addr_len, set_cmsg, /*flags*/0,
+ &err);
if (err)
goto out;
else if (clientfd == -1)
int main(int argc, char **argv)
{
- struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY};
int iov_count = 1, length = 1024, rate = 1;
struct sockmap_options options = {0};
int opt, longindex, err, cg_fd = 0;
char *bpf_file = BPF_SOCKMAP_FILENAME;
int test = PING_PONG;
- if (setrlimit(RLIMIT_MEMLOCK, &r)) {
- perror("setrlimit(RLIMIT_MEMLOCK)");
- return 1;
- }
-
if (argc < 2)
return test_suite();
__u32 good_cb_test_rv;
__u64 bytes_received;
__u64 bytes_acked;
+ __u32 num_listen;
};
#endif
if (!gp)
break;
g = *gp;
- g.total_retrans = skops->total_retrans;
- g.data_segs_in = skops->data_segs_in;
- g.data_segs_out = skops->data_segs_out;
- g.bytes_received = skops->bytes_received;
- g.bytes_acked = skops->bytes_acked;
+ if (skops->args[0] == BPF_TCP_LISTEN) {
+ g.num_listen++;
+ } else {
+ g.total_retrans = skops->total_retrans;
+ g.data_segs_in = skops->data_segs_in;
+ g.data_segs_out = skops->data_segs_out;
+ g.bytes_received = skops->bytes_received;
+ g.bytes_acked = skops->bytes_acked;
+ }
bpf_map_update_elem(&global_map, &key, &g,
BPF_ANY);
}
break;
+ case BPF_SOCK_OPS_TCP_LISTEN_CB:
+ bpf_sock_ops_cb_flags_set(skops, BPF_SOCK_OPS_STATE_CB_FLAG);
+ break;
default:
rv = -1;
}
// SPDX-License-Identifier: GPL-2.0
+#include <inttypes.h>
#include <stdio.h>
#include <stdlib.h>
-#include <stdio.h>
#include <unistd.h>
#include <errno.h>
-#include <signal.h>
#include <string.h>
-#include <assert.h>
-#include <linux/perf_event.h>
-#include <linux/ptrace.h>
#include <linux/bpf.h>
-#include <sys/ioctl.h>
-#include <sys/time.h>
#include <sys/types.h>
-#include <sys/stat.h>
-#include <fcntl.h>
#include <bpf/bpf.h>
#include <bpf/libbpf.h>
-#include "bpf_util.h"
+
#include "bpf_rlimit.h"
-#include <linux/perf_event.h>
+#include "bpf_util.h"
+#include "cgroup_helpers.h"
+
#include "test_tcpbpf.h"
+#define EXPECT_EQ(expected, actual, fmt) \
+ do { \
+ if ((expected) != (actual)) { \
+ printf(" Value of: " #actual "\n" \
+ " Actual: %" fmt "\n" \
+ " Expected: %" fmt "\n", \
+ (actual), (expected)); \
+ goto err; \
+ } \
+ } while (0)
+
+int verify_result(const struct tcpbpf_globals *result)
+{
+ __u32 expected_events;
+
+ expected_events = ((1 << BPF_SOCK_OPS_TIMEOUT_INIT) |
+ (1 << BPF_SOCK_OPS_RWND_INIT) |
+ (1 << BPF_SOCK_OPS_TCP_CONNECT_CB) |
+ (1 << BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB) |
+ (1 << BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB) |
+ (1 << BPF_SOCK_OPS_NEEDS_ECN) |
+ (1 << BPF_SOCK_OPS_STATE_CB) |
+ (1 << BPF_SOCK_OPS_TCP_LISTEN_CB));
+
+ EXPECT_EQ(expected_events, result->event_map, "#" PRIx32);
+ EXPECT_EQ(501ULL, result->bytes_received, "llu");
+ EXPECT_EQ(1002ULL, result->bytes_acked, "llu");
+ EXPECT_EQ(1, result->data_segs_in, PRIu32);
+ EXPECT_EQ(1, result->data_segs_out, PRIu32);
+ EXPECT_EQ(0x80, result->bad_cb_test_rv, PRIu32);
+ EXPECT_EQ(0, result->good_cb_test_rv, PRIu32);
+ EXPECT_EQ(1, result->num_listen, PRIu32);
+
+ return 0;
+err:
+ return -1;
+}
+
static int bpf_find_map(const char *test, struct bpf_object *obj,
const char *name)
{
return bpf_map__fd(map);
}
-#define SYSTEM(CMD) \
- do { \
- if (system(CMD)) { \
- printf("system(%s) FAILS!\n", CMD); \
- } \
- } while (0)
-
int main(int argc, char **argv)
{
const char *file = "test_tcpbpf_kern.o";
struct tcpbpf_globals g = {0};
- int cg_fd, prog_fd, map_fd;
- bool debug_flag = false;
+ const char *cg_path = "/foo";
int error = EXIT_FAILURE;
struct bpf_object *obj;
- char cmd[100], *dir;
- struct stat buffer;
+ int prog_fd, map_fd;
+ int cg_fd = -1;
__u32 key = 0;
- int pid;
int rv;
- if (argc > 1 && strcmp(argv[1], "-d") == 0)
- debug_flag = true;
+ if (setup_cgroup_environment())
+ goto err;
- dir = "/tmp/cgroupv2/foo";
+ cg_fd = create_and_get_cgroup(cg_path);
+ if (!cg_fd)
+ goto err;
- if (stat(dir, &buffer) != 0) {
- SYSTEM("mkdir -p /tmp/cgroupv2");
- SYSTEM("mount -t cgroup2 none /tmp/cgroupv2");
- SYSTEM("mkdir -p /tmp/cgroupv2/foo");
- }
- pid = (int) getpid();
- sprintf(cmd, "echo %d >> /tmp/cgroupv2/foo/cgroup.procs", pid);
- SYSTEM(cmd);
+ if (join_cgroup(cg_path))
+ goto err;
- cg_fd = open(dir, O_DIRECTORY, O_RDONLY);
if (bpf_prog_load(file, BPF_PROG_TYPE_SOCK_OPS, &obj, &prog_fd)) {
printf("FAILED: load_bpf_file failed for: %s\n", file);
goto err;
goto err;
}
- SYSTEM("./tcp_server.py");
+ if (system("./tcp_server.py")) {
+ printf("FAILED: TCP server\n");
+ goto err;
+ }
map_fd = bpf_find_map(__func__, obj, "global_map");
if (map_fd < 0)
goto err;
}
- if (g.bytes_received != 501 || g.bytes_acked != 1002 ||
- g.data_segs_in != 1 || g.data_segs_out != 1 ||
- (g.event_map ^ 0x47e) != 0 || g.bad_cb_test_rv != 0x80 ||
- g.good_cb_test_rv != 0) {
+ if (verify_result(&g)) {
printf("FAILED: Wrong stats\n");
- if (debug_flag) {
- printf("\n");
- printf("bytes_received: %d (expecting 501)\n",
- (int)g.bytes_received);
- printf("bytes_acked: %d (expecting 1002)\n",
- (int)g.bytes_acked);
- printf("data_segs_in: %d (expecting 1)\n",
- g.data_segs_in);
- printf("data_segs_out: %d (expecting 1)\n",
- g.data_segs_out);
- printf("event_map: 0x%x (at least 0x47e)\n",
- g.event_map);
- printf("bad_cb_test_rv: 0x%x (expecting 0x80)\n",
- g.bad_cb_test_rv);
- printf("good_cb_test_rv:0x%x (expecting 0)\n",
- g.good_cb_test_rv);
- }
goto err;
}
+
printf("PASSED!\n");
error = 0;
err:
bpf_prog_detach(cg_fd, BPF_CGROUP_SOCK_OPS);
+ close(cg_fd);
+ cleanup_cgroup_environment();
return error;
-
}
test_xfrm_tunnel()
{
config_device
- #tcpdump -nei veth1 ip &
- output=$(mktemp)
- cat /sys/kernel/debug/tracing/trace_pipe | tee $output &
- setup_xfrm_tunnel
+ > /sys/kernel/debug/tracing/trace
+ setup_xfrm_tunnel
tc qdisc add dev veth1 clsact
tc filter add dev veth1 proto ip ingress bpf da obj test_tunnel_kern.o \
sec xfrm_get_state
ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
sleep 1
- grep "reqid 1" $output
+ grep "reqid 1" /sys/kernel/debug/tracing/trace
check_err $?
- grep "spi 0x1" $output
+ grep "spi 0x1" /sys/kernel/debug/tracing/trace
check_err $?
- grep "remote ip 0xac100164" $output
+ grep "remote ip 0xac100164" /sys/kernel/debug/tracing/trace
check_err $?
cleanup
if [ $ret -ne 0 ]; then
- echo -e ${RED}"FAIL: xfrm tunnel"${NC}
- return 1
- fi
- echo -e ${GREEN}"PASS: xfrm tunnel"${NC}
+ echo -e ${RED}"FAIL: xfrm tunnel"${NC}
+ return 1
+ fi
+ echo -e ${GREEN}"PASS: xfrm tunnel"${NC}
}
attach_bpf()
ip link del ip6geneve11 2> /dev/null
ip link del erspan11 2> /dev/null
ip link del ip6erspan11 2> /dev/null
+ ip xfrm policy delete dir out src 10.1.1.200/32 dst 10.1.1.100/32 2> /dev/null
+ ip xfrm policy delete dir in src 10.1.1.100/32 dst 10.1.1.200/32 2> /dev/null
+ ip xfrm state delete src 172.16.1.100 dst 172.16.1.200 proto esp spi 0x1 2> /dev/null
+ ip xfrm state delete src 172.16.1.200 dst 172.16.1.100 proto esp spi 0x2 2> /dev/null
}
cleanup_exit()
check()
{
- ip link help $1 2>&1 | grep -q "^Usage:"
+ ip link help 2>&1 | grep -q "\s$1\s"
if [ $? -ne 0 ];then
echo "SKIP $1: iproute2 not support"
cleanup
static int page_cnt = 8;
static struct perf_event_mmap_page *header;
-int perf_event_mmap(int fd)
+int perf_event_mmap_header(int fd, struct perf_event_mmap_page **header)
{
void *base;
int mmap_size;
return -1;
}
- header = base;
+ *header = base;
return 0;
}
+int perf_event_mmap(int fd)
+{
+ return perf_event_mmap_header(fd, &header);
+}
+
static int perf_event_poll(int fd)
{
struct pollfd pfd = { .fd = fd, .events = POLLIN };
return ret;
}
+
+int perf_event_poller_multi(int *fds, struct perf_event_mmap_page **headers,
+ int num_fds, perf_event_print_fn output_fn)
+{
+ enum bpf_perf_event_ret ret;
+ struct pollfd *pfds;
+ void *buf = NULL;
+ size_t len = 0;
+ int i;
+
+ pfds = calloc(num_fds, sizeof(*pfds));
+ if (!pfds)
+ return LIBBPF_PERF_EVENT_ERROR;
+
+ for (i = 0; i < num_fds; i++) {
+ pfds[i].fd = fds[i];
+ pfds[i].events = POLLIN;
+ }
+
+ for (;;) {
+ poll(pfds, num_fds, 1000);
+ for (i = 0; i < num_fds; i++) {
+ if (!pfds[i].revents)
+ continue;
+
+ ret = bpf_perf_event_read_simple(headers[i],
+ page_cnt * page_size,
+ page_size, &buf, &len,
+ bpf_perf_event_print,
+ output_fn);
+ if (ret != LIBBPF_PERF_EVENT_CONT)
+ break;
+ }
+ }
+ free(buf);
+ free(pfds);
+
+ return ret;
+}
#define __TRACE_HELPER_H
#include <libbpf.h>
+#include <linux/perf_event.h>
struct ksym {
long addr;
typedef enum bpf_perf_event_ret (*perf_event_print_fn)(void *data, int size);
int perf_event_mmap(int fd);
+int perf_event_mmap_header(int fd, struct perf_event_mmap_page **header);
/* return LIBBPF_PERF_EVENT_DONE or LIBBPF_PERF_EVENT_ERROR */
int perf_event_poller(int fd, perf_event_print_fn output_fn);
+int perf_event_poller_multi(int *fds, struct perf_event_mmap_page **headers,
+ int num_fds, perf_event_print_fn output_fn);
#endif
--- /dev/null
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test uses standard topology for testing gretap. See
+# ../../../net/forwarding/mirror_gre_topo_lib.sh for more details.
+#
+# Test offloading various features of offloading gretap mirrors specific to
+# mlxsw.
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+NUM_NETIFS=6
+source $lib_dir/lib.sh
+source $lib_dir/mirror_lib.sh
+source $lib_dir/mirror_gre_lib.sh
+source $lib_dir/mirror_gre_topo_lib.sh
+
+setup_keyful()
+{
+ tunnel_create gt6-key ip6gretap 2001:db8:3::1 2001:db8:3::2 \
+ ttl 100 tos inherit allow-localremote \
+ key 1234
+
+ tunnel_create h3-gt6-key ip6gretap 2001:db8:3::2 2001:db8:3::1 \
+ key 1234
+ ip link set h3-gt6-key vrf v$h3
+ matchall_sink_create h3-gt6-key
+
+ ip address add dev $swp3 2001:db8:3::1/64
+ ip address add dev $h3 2001:db8:3::2/64
+}
+
+cleanup_keyful()
+{
+ ip address del dev $h3 2001:db8:3::2/64
+ ip address del dev $swp3 2001:db8:3::1/64
+
+ tunnel_destroy h3-gt6-key
+ tunnel_destroy gt6-key
+}
+
+setup_soft()
+{
+ # Set up a topology for testing underlay routes that point at an
+ # unsupported soft device.
+
+ tunnel_create gt6-soft ip6gretap 2001:db8:4::1 2001:db8:4::2 \
+ ttl 100 tos inherit allow-localremote
+
+ tunnel_create h3-gt6-soft ip6gretap 2001:db8:4::2 2001:db8:4::1
+ ip link set h3-gt6-soft vrf v$h3
+ matchall_sink_create h3-gt6-soft
+
+ ip link add name v1 type veth peer name v2
+ ip link set dev v1 up
+ ip address add dev v1 2001:db8:4::1/64
+
+ ip link set dev v2 vrf v$h3
+ ip link set dev v2 up
+ ip address add dev v2 2001:db8:4::2/64
+}
+
+cleanup_soft()
+{
+ ip link del dev v1
+
+ tunnel_destroy h3-gt6-soft
+ tunnel_destroy gt6-soft
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ swp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ swp3=${NETIFS[p5]}
+ h3=${NETIFS[p6]}
+
+ vrf_prepare
+ mirror_gre_topo_create
+
+ ip address add dev $swp3 2001:db8:2::1/64
+ ip address add dev $h3 2001:db8:2::2/64
+
+ ip address add dev $swp3 192.0.2.129/28
+ ip address add dev $h3 192.0.2.130/28
+
+ setup_keyful
+ setup_soft
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ cleanup_soft
+ cleanup_keyful
+
+ ip address del dev $h3 2001:db8:2::2/64
+ ip address del dev $swp3 2001:db8:2::1/64
+
+ ip address del dev $h3 192.0.2.130/28
+ ip address del dev $swp3 192.0.2.129/28
+
+ mirror_gre_topo_destroy
+ vrf_cleanup
+}
+
+test_span_gre_ttl_inherit()
+{
+ local tundev=$1; shift
+ local type=$1; shift
+ local what=$1; shift
+
+ RET=0
+
+ ip link set dev $tundev type $type ttl inherit
+ mirror_install $swp1 ingress $tundev "matchall $tcflags"
+ fail_test_span_gre_dir $tundev ingress
+
+ ip link set dev $tundev type $type ttl 100
+
+ quick_test_span_gre_dir $tundev ingress
+ mirror_uninstall $swp1 ingress
+
+ log_test "$what: no offload on TTL of inherit ($tcflags)"
+}
+
+test_span_gre_tos_fixed()
+{
+ local tundev=$1; shift
+ local type=$1; shift
+ local what=$1; shift
+
+ RET=0
+
+ ip link set dev $tundev type $type tos 0x10
+ mirror_install $swp1 ingress $tundev "matchall $tcflags"
+ fail_test_span_gre_dir $tundev ingress
+
+ ip link set dev $tundev type $type tos inherit
+ quick_test_span_gre_dir $tundev ingress
+ mirror_uninstall $swp1 ingress
+
+ log_test "$what: no offload on a fixed TOS ($tcflags)"
+}
+
+test_span_failable()
+{
+ local should_fail=$1; shift
+ local tundev=$1; shift
+ local what=$1; shift
+
+ RET=0
+
+ mirror_install $swp1 ingress $tundev "matchall $tcflags"
+ if ((should_fail)); then
+ fail_test_span_gre_dir $tundev ingress
+ else
+ quick_test_span_gre_dir $tundev ingress
+ fi
+ mirror_uninstall $swp1 ingress
+
+ log_test "$what: should_fail=$should_fail ($tcflags)"
+}
+
+test_failable()
+{
+ local should_fail=$1; shift
+
+ test_span_failable $should_fail gt6-key "mirror to keyful gretap"
+ test_span_failable $should_fail gt6-soft "mirror to gretap w/ soft underlay"
+}
+
+test_sw()
+{
+ slow_path_trap_install $swp1 ingress
+ slow_path_trap_install $swp1 egress
+
+ test_failable 0
+
+ slow_path_trap_uninstall $swp1 egress
+ slow_path_trap_uninstall $swp1 ingress
+}
+
+test_hw()
+{
+ test_failable 1
+
+ test_span_gre_tos_fixed gt4 gretap "mirror to gretap"
+ test_span_gre_tos_fixed gt6 ip6gretap "mirror to ip6gretap"
+
+ test_span_gre_ttl_inherit gt4 gretap "mirror to gretap"
+ test_span_gre_ttl_inherit gt6 ip6gretap "mirror to ip6gretap"
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+if ! tc_offload_check; then
+ check_err 1 "Could not test offloaded functionality"
+ log_test "mlxsw-specific tests for mirror to gretap"
+ exit
+fi
+
+tcflags="skip_hw"
+test_sw
+
+tcflags="skip_sw"
+test_hw
+
+exit $EXIT_STATUS
--- /dev/null
+# SPDX-License-Identifier: GPL-2.0
+
+# Test offloading a number of mirrors-to-gretap. The test creates a number of
+# tunnels. Then it adds one flower mirror for each of the tunnels, matching a
+# given host IP. Then it generates traffic at each of the host IPs and checks
+# that the traffic has been mirrored at the appropriate tunnel.
+#
+# +--------------------------+ +--------------------------+
+# | H1 | | H2 |
+# | + $h1 | | $h2 + |
+# | | 2001:db8:1:X::1/64 | | 2001:db8:1:X::2/64 | |
+# +-----|--------------------+ +--------------------|-----+
+# | |
+# +-----|-------------------------------------------------------------|-----+
+# | SW o--> mirrors | |
+# | +---|-------------------------------------------------------------|---+ |
+# | | + $swp1 BR $swp2 + | |
+# | +---------------------------------------------------------------------+ |
+# | |
+# | + $swp3 + gt6-<X> (ip6gretap) |
+# | | 2001:db8:2:X::1/64 : loc=2001:db8:2:X::1 |
+# | | : rem=2001:db8:2:X::2 |
+# | | : ttl=100 |
+# | | : tos=inherit |
+# | | : |
+# +-----|--------------------------------:----------------------------------+
+# | :
+# +-----|--------------------------------:----------------------------------+
+# | H3 + $h3 + h3-gt6-<X> (ip6gretap) |
+# | 2001:db8:2:X::2/64 loc=2001:db8:2:X::2 |
+# | rem=2001:db8:2:X::1 |
+# | ttl=100 |
+# | tos=inherit |
+# | |
+# +-------------------------------------------------------------------------+
+
+source ../../../../net/forwarding/mirror_lib.sh
+
+MIRROR_NUM_NETIFS=6
+
+mirror_gre_ipv6_addr()
+{
+ local net=$1; shift
+ local num=$1; shift
+
+ printf "2001:db8:%x:%x" $net $num
+}
+
+mirror_gre_tunnels_create()
+{
+ local count=$1; shift
+ local should_fail=$1; shift
+
+ MIRROR_GRE_BATCH_FILE="$(mktemp)"
+ for ((i=0; i < count; ++i)); do
+ local match_dip=$(mirror_gre_ipv6_addr 1 $i)::2
+ local htun=h3-gt6-$i
+ local tun=gt6-$i
+
+ ((mirror_gre_tunnels++))
+
+ ip address add dev $h1 $(mirror_gre_ipv6_addr 1 $i)::1/64
+ ip address add dev $h2 $(mirror_gre_ipv6_addr 1 $i)::2/64
+
+ ip address add dev $swp3 $(mirror_gre_ipv6_addr 2 $i)::1/64
+ ip address add dev $h3 $(mirror_gre_ipv6_addr 2 $i)::2/64
+
+ tunnel_create $tun ip6gretap \
+ $(mirror_gre_ipv6_addr 2 $i)::1 \
+ $(mirror_gre_ipv6_addr 2 $i)::2 \
+ ttl 100 tos inherit allow-localremote
+
+ tunnel_create $htun ip6gretap \
+ $(mirror_gre_ipv6_addr 2 $i)::2 \
+ $(mirror_gre_ipv6_addr 2 $i)::1
+ ip link set $htun vrf v$h3
+ matchall_sink_create $htun
+
+ cat >> $MIRROR_GRE_BATCH_FILE <<-EOF
+ filter add dev $swp1 ingress pref 1000 \
+ protocol ipv6 \
+ flower $tcflags dst_ip $match_dip \
+ action mirred egress mirror dev $tun
+ EOF
+ done
+
+ tc -b $MIRROR_GRE_BATCH_FILE
+ check_err_fail $should_fail $? "Mirror rule insertion"
+}
+
+mirror_gre_tunnels_destroy()
+{
+ local count=$1; shift
+
+ for ((i=0; i < count; ++i)); do
+ local htun=h3-gt6-$i
+ local tun=gt6-$i
+
+ ip address del dev $h3 $(mirror_gre_ipv6_addr 2 $i)::2/64
+ ip address del dev $swp3 $(mirror_gre_ipv6_addr 2 $i)::1/64
+
+ ip address del dev $h2 $(mirror_gre_ipv6_addr 1 $i)::2/64
+ ip address del dev $h1 $(mirror_gre_ipv6_addr 1 $i)::1/64
+
+ tunnel_destroy $htun
+ tunnel_destroy $tun
+ done
+}
+
+__mirror_gre_test()
+{
+ local count=$1; shift
+ local should_fail=$1; shift
+
+ mirror_gre_tunnels_create $count $should_fail
+ if ((should_fail)); then
+ return
+ fi
+
+ sleep 5
+
+ for ((i = 0; i < count; ++i)); do
+ local dip=$(mirror_gre_ipv6_addr 1 $i)::2
+ local htun=h3-gt6-$i
+ local message
+
+ icmp6_capture_install $htun
+ mirror_test v$h1 "" $dip $htun 100 10
+ icmp6_capture_uninstall $htun
+ done
+}
+
+mirror_gre_test()
+{
+ local count=$1; shift
+ local should_fail=$1; shift
+
+ if ! tc_offload_check $TC_FLOWER_NUM_NETIFS; then
+ check_err 1 "Could not test offloaded functionality"
+ return
+ fi
+
+ tcflags="skip_sw"
+ __mirror_gre_test $count $should_fail
+}
+
+mirror_gre_setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ swp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ swp3=${NETIFS[p5]}
+ h3=${NETIFS[p6]}
+
+ mirror_gre_tunnels=0
+
+ vrf_prepare
+
+ simple_if_init $h1
+ simple_if_init $h2
+ simple_if_init $h3
+
+ ip link add name br1 type bridge vlan_filtering 1
+ ip link set dev br1 up
+
+ ip link set dev $swp1 master br1
+ ip link set dev $swp1 up
+ tc qdisc add dev $swp1 clsact
+
+ ip link set dev $swp2 master br1
+ ip link set dev $swp2 up
+
+ ip link set dev $swp3 up
+}
+
+mirror_gre_cleanup()
+{
+ mirror_gre_tunnels_destroy $mirror_gre_tunnels
+
+ ip link set dev $swp3 down
+
+ ip link set dev $swp2 down
+
+ tc qdisc del dev $swp1 clsact
+ ip link set dev $swp1 down
+
+ ip link del dev br1
+
+ simple_if_fini $h3
+ simple_if_fini $h2
+ simple_if_fini $h1
+
+ vrf_cleanup
+}
--- /dev/null
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ROUTER_NUM_NETIFS=4
+
+router_h1_create()
+{
+ simple_if_init $h1 192.0.1.1/24
+ ip route add 193.0.0.0/8 via 192.0.1.2 dev $h1
+}
+
+router_h1_destroy()
+{
+ ip route del 193.0.0.0/8 via 192.0.1.2 dev $h1
+ simple_if_fini $h1 192.0.1.1/24
+}
+
+router_h2_create()
+{
+ simple_if_init $h2 192.0.2.1/24
+ tc qdisc add dev $h2 handle ffff: ingress
+}
+
+router_h2_destroy()
+{
+ tc qdisc del dev $h2 handle ffff: ingress
+ simple_if_fini $h2 192.0.2.1/24
+}
+
+router_create()
+{
+ ip link set dev $rp1 up
+ ip link set dev $rp2 up
+
+ ip address add 192.0.1.2/24 dev $rp1
+ ip address add 192.0.2.2/24 dev $rp2
+}
+
+router_destroy()
+{
+ ip address del 192.0.2.2/24 dev $rp2
+ ip address del 192.0.1.2/24 dev $rp1
+
+ ip link set dev $rp2 down
+ ip link set dev $rp1 down
+}
+
+router_setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ rp1=${NETIFS[p2]}
+
+ rp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ h1mac=$(mac_get $h1)
+ rp1mac=$(mac_get $rp1)
+
+ vrf_prepare
+
+ router_h1_create
+ router_h2_create
+
+ router_create
+}
+
+router_offload_validate()
+{
+ local route_count=$1
+ local offloaded_count
+
+ offloaded_count=$(ip route | grep -o 'offload' | wc -l)
+ [[ $offloaded_count -ge $route_count ]]
+}
+
+router_routes_create()
+{
+ local route_count=$1
+ local count=0
+
+ ROUTE_FILE="$(mktemp)"
+
+ for i in {0..255}
+ do
+ for j in {0..255}
+ do
+ for k in {0..255}
+ do
+ if [[ $count -eq $route_count ]]; then
+ break 3
+ fi
+
+ echo route add 193.${i}.${j}.${k}/32 via \
+ 192.0.2.1 dev $rp2 >> $ROUTE_FILE
+ ((count++))
+ done
+ done
+ done
+
+ ip -b $ROUTE_FILE &> /dev/null
+}
+
+router_routes_destroy()
+{
+ if [[ -v ROUTE_FILE ]]; then
+ rm -f $ROUTE_FILE
+ fi
+}
+
+router_test()
+{
+ local route_count=$1
+ local should_fail=$2
+ local count=0
+
+ RET=0
+
+ router_routes_create $route_count
+
+ router_offload_validate $route_count
+ check_err_fail $should_fail $? "Offload of $route_count routes"
+ if [[ $RET -ne 0 ]] || [[ $should_fail -eq 1 ]]; then
+ return
+ fi
+
+ tc filter add dev $h2 ingress protocol ip pref 1 flower \
+ skip_sw dst_ip 193.0.0.0/8 action drop
+
+ for i in {0..255}
+ do
+ for j in {0..255}
+ do
+ for k in {0..255}
+ do
+ if [[ $count -eq $route_count ]]; then
+ break 3
+ fi
+
+ $MZ $h1 -c 1 -p 64 -a $h1mac -b $rp1mac \
+ -A 192.0.1.1 -B 193.${i}.${j}.${k} \
+ -t ip -q
+ ((count++))
+ done
+ done
+ done
+
+ tc_check_packets "dev $h2 ingress" 1 $route_count
+ check_err $? "Offload mismatch"
+
+ tc filter del dev $h2 ingress protocol ip pref 1 flower \
+ skip_sw dst_ip 193.0.0.0/8 action drop
+
+ router_routes_destroy
+}
+
+router_cleanup()
+{
+ pre_cleanup
+
+ router_routes_destroy
+ router_destroy
+
+ router_h2_destroy
+ router_h1_destroy
+
+ vrf_cleanup
+}
--- /dev/null
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source "../../../../net/forwarding/devlink_lib.sh"
+
+if [ "$DEVLINK_VIDDID" != "15b3:cb84" ]; then
+ echo "SKIP: test is tailored for Mellanox Spectrum"
+ exit 1
+fi
+
+# Needed for returning to default
+declare -A KVD_DEFAULTS
+
+KVD_CHILDREN="linear hash_single hash_double"
+KVDL_CHILDREN="singles chunks large_chunks"
+
+devlink_sp_resource_minimize()
+{
+ local size
+ local i
+
+ for i in $KVD_CHILDREN; do
+ size=$(devlink_resource_get kvd "$i" | jq '.["size_min"]')
+ devlink_resource_size_set "$size" kvd "$i"
+ done
+
+ for i in $KVDL_CHILDREN; do
+ size=$(devlink_resource_get kvd linear "$i" | \
+ jq '.["size_min"]')
+ devlink_resource_size_set "$size" kvd linear "$i"
+ done
+}
+
+devlink_sp_size_kvd_to_default()
+{
+ local need_reload=0
+ local i
+
+ for i in $KVD_CHILDREN; do
+ local size=$(echo "${KVD_DEFAULTS[kvd_$i]}" | jq '.["size"]')
+ current_size=$(devlink_resource_size_get kvd "$i")
+
+ if [ "$size" -ne "$current_size" ]; then
+ devlink_resource_size_set "$size" kvd "$i"
+ need_reload=1
+ fi
+ done
+
+ for i in $KVDL_CHILDREN; do
+ local size=$(echo "${KVD_DEFAULTS[kvd_linear_$i]}" | \
+ jq '.["size"]')
+ current_size=$(devlink_resource_size_get kvd linear "$i")
+
+ if [ "$size" -ne "$current_size" ]; then
+ devlink_resource_size_set "$size" kvd linear "$i"
+ need_reload=1
+ fi
+ done
+
+ if [ "$need_reload" -ne "0" ]; then
+ devlink_reload
+ fi
+}
+
+devlink_sp_read_kvd_defaults()
+{
+ local key
+ local i
+
+ KVD_DEFAULTS[kvd]=$(devlink_resource_get "kvd")
+ for i in $KVD_CHILDREN; do
+ key=kvd_$i
+ KVD_DEFAULTS[$key]=$(devlink_resource_get kvd "$i")
+ done
+
+ for i in $KVDL_CHILDREN; do
+ key=kvd_linear_$i
+ KVD_DEFAULTS[$key]=$(devlink_resource_get kvd linear "$i")
+ done
+}
+
+KVD_PROFILES="default scale ipv4_max"
+
+devlink_sp_resource_kvd_profile_set()
+{
+ local profile=$1
+
+ case "$profile" in
+ scale)
+ devlink_resource_size_set 64000 kvd linear
+ devlink_resource_size_set 15616 kvd linear singles
+ devlink_resource_size_set 32000 kvd linear chunks
+ devlink_resource_size_set 16384 kvd linear large_chunks
+ devlink_resource_size_set 128000 kvd hash_single
+ devlink_resource_size_set 48000 kvd hash_double
+ devlink_reload
+ ;;
+ ipv4_max)
+ devlink_resource_size_set 64000 kvd linear
+ devlink_resource_size_set 15616 kvd linear singles
+ devlink_resource_size_set 32000 kvd linear chunks
+ devlink_resource_size_set 16384 kvd linear large_chunks
+ devlink_resource_size_set 144000 kvd hash_single
+ devlink_resource_size_set 32768 kvd hash_double
+ devlink_reload
+ ;;
+ default)
+ devlink_resource_size_set 98304 kvd linear
+ devlink_resource_size_set 16384 kvd linear singles
+ devlink_resource_size_set 49152 kvd linear chunks
+ devlink_resource_size_set 32768 kvd linear large_chunks
+ devlink_resource_size_set 87040 kvd hash_single
+ devlink_resource_size_set 60416 kvd hash_double
+ devlink_reload
+ ;;
+ *)
+ check_err 1 "Unknown profile $profile"
+ esac
+}
--- /dev/null
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+NUM_NETIFS=1
+source devlink_lib_spectrum.sh
+
+setup_prepare()
+{
+ devlink_sp_read_kvd_defaults
+}
+
+cleanup()
+{
+ pre_cleanup
+ devlink_sp_size_kvd_to_default
+}
+
+trap cleanup EXIT
+
+setup_prepare
+
+profiles_test()
+{
+ local i
+
+ log_info "Running profile tests"
+
+ for i in $KVD_PROFILES; do
+ RET=0
+ devlink_sp_resource_kvd_profile_set $i
+ log_test "'$i' profile"
+ done
+
+ # Default is explicitly tested at end to ensure it's actually applied
+ RET=0
+ devlink_sp_resource_kvd_profile_set "default"
+ log_test "'default' profile"
+}
+
+resources_min_test()
+{
+ local size
+ local i
+ local j
+
+ log_info "Running KVD-minimum tests"
+
+ for i in $KVD_CHILDREN; do
+ RET=0
+ size=$(devlink_resource_get kvd "$i" | jq '.["size_min"]')
+ devlink_resource_size_set "$size" kvd "$i"
+
+ # In case of linear, need to minimize sub-resources as well
+ if [[ "$i" == "linear" ]]; then
+ for j in $KVDL_CHILDREN; do
+ devlink_resource_size_set 0 kvd linear "$j"
+ done
+ fi
+
+ devlink_reload
+ devlink_sp_size_kvd_to_default
+ log_test "'$i' minimize [$size]"
+ done
+}
+
+resources_max_test()
+{
+ local min_size
+ local size
+ local i
+ local j
+
+ log_info "Running KVD-maximum tests"
+ for i in $KVD_CHILDREN; do
+ RET=0
+ devlink_sp_resource_minimize
+
+ # Calculate the maximum possible size for the given partition
+ size=$(devlink_resource_size_get kvd)
+ for j in $KVD_CHILDREN; do
+ if [ "$i" != "$j" ]; then
+ min_size=$(devlink_resource_get kvd "$j" | \
+ jq '.["size_min"]')
+ size=$((size - min_size))
+ fi
+ done
+
+ # Test almost maximum size
+ devlink_resource_size_set "$((size - 128))" kvd "$i"
+ devlink_reload
+ log_test "'$i' almost maximize [$((size - 128))]"
+
+ # Test above maximum size
+ devlink resource set "$DEVLINK_DEV" \
+ path "kvd/$i" size $((size + 128)) &> /dev/null
+ check_fail $? "Set kvd/$i to size $((size + 128)) should fail"
+ log_test "'$i' Overflow rejection [$((size + 128))]"
+
+ # Test maximum size
+ if [ "$i" == "hash_single" ] || [ "$i" == "hash_double" ]; then
+ echo "SKIP: Observed problem with exact max $i"
+ continue
+ fi
+
+ devlink_resource_size_set "$size" kvd "$i"
+ devlink_reload
+ log_test "'$i' maximize [$size]"
+
+ devlink_sp_size_kvd_to_default
+ done
+}
+
+profiles_test
+resources_min_test
+resources_max_test
+
+exit "$RET"
--- /dev/null
+# SPDX-License-Identifier: GPL-2.0
+source ../mirror_gre_scale.sh
+
+mirror_gre_get_target()
+{
+ local should_fail=$1; shift
+
+ if ((! should_fail)); then
+ echo 3
+ else
+ echo 4
+ fi
+}
--- /dev/null
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+NUM_NETIFS=6
+source ../../../../net/forwarding/lib.sh
+source ../../../../net/forwarding/tc_common.sh
+source devlink_lib_spectrum.sh
+
+current_test=""
+
+cleanup()
+{
+ pre_cleanup
+ if [ ! -z $current_test ]; then
+ ${current_test}_cleanup
+ fi
+ devlink_sp_size_kvd_to_default
+}
+
+devlink_sp_read_kvd_defaults
+trap cleanup EXIT
+
+ALL_TESTS="router tc_flower mirror_gre"
+for current_test in ${TESTS:-$ALL_TESTS}; do
+ source ${current_test}_scale.sh
+
+ num_netifs_var=${current_test^^}_NUM_NETIFS
+ num_netifs=${!num_netifs_var:-$NUM_NETIFS}
+
+ for profile in $KVD_PROFILES; do
+ RET=0
+ devlink_sp_resource_kvd_profile_set $profile
+ if [[ $RET -gt 0 ]]; then
+ log_test "'$current_test' [$profile] setting"
+ continue
+ fi
+
+ for should_fail in 0 1; do
+ RET=0
+ target=$(${current_test}_get_target "$should_fail")
+ ${current_test}_setup_prepare
+ setup_wait $num_netifs
+ ${current_test}_test "$target" "$should_fail"
+ ${current_test}_cleanup
+ if [[ "$should_fail" -eq 0 ]]; then
+ log_test "'$current_test' [$profile] $target"
+ else
+ log_test "'$current_test' [$profile] overflow $target"
+ fi
+ done
+ done
+done
+current_test=""
+
+exit "$RET"
--- /dev/null
+# SPDX-License-Identifier: GPL-2.0
+source ../router_scale.sh
+
+router_get_target()
+{
+ local should_fail=$1
+ local target
+
+ target=$(devlink_resource_size_get kvd hash_single)
+
+ if [[ $should_fail -eq 0 ]]; then
+ target=$((target * 85 / 100))
+ else
+ target=$((target + 1))
+ fi
+
+ echo $target
+}
--- /dev/null
+# SPDX-License-Identifier: GPL-2.0
+source ../tc_flower_scale.sh
+
+tc_flower_get_target()
+{
+ local should_fail=$1; shift
+
+ # 6144 (6x1024) is the theoretical maximum.
+ # One bank of 512 rules is taken by the 18-byte MC router rule.
+ # One rule is the ACL catch-all.
+ # 6144 - 512 - 1 = 5631
+ local target=5631
+
+ if ((! should_fail)); then
+ echo $target
+ else
+ echo $((target + 1))
+ fi
+}
--- /dev/null
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test for resource limit of offloaded flower rules. The test adds a given
+# number of flower matches for different IPv6 addresses, then generates traffic,
+# and ensures each was hit exactly once. This file contains functions to set up
+# a testing topology and run the test, and is meant to be sourced from a test
+# script that calls the testing routine with a given number of rules.
+
+TC_FLOWER_NUM_NETIFS=2
+
+tc_flower_h1_create()
+{
+ simple_if_init $h1
+ tc qdisc add dev $h1 clsact
+}
+
+tc_flower_h1_destroy()
+{
+ tc qdisc del dev $h1 clsact
+ simple_if_fini $h1
+}
+
+tc_flower_h2_create()
+{
+ simple_if_init $h2
+ tc qdisc add dev $h2 clsact
+}
+
+tc_flower_h2_destroy()
+{
+ tc qdisc del dev $h2 clsact
+ simple_if_fini $h2
+}
+
+tc_flower_setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ h2=${NETIFS[p2]}
+
+ vrf_prepare
+
+ tc_flower_h1_create
+ tc_flower_h2_create
+}
+
+tc_flower_cleanup()
+{
+ pre_cleanup
+
+ tc_flower_h2_destroy
+ tc_flower_h1_destroy
+
+ vrf_cleanup
+
+ if [[ -v TC_FLOWER_BATCH_FILE ]]; then
+ rm -f $TC_FLOWER_BATCH_FILE
+ fi
+}
+
+tc_flower_addr()
+{
+ local num=$1; shift
+
+ printf "2001:db8:1::%x" $num
+}
+
+tc_flower_rules_create()
+{
+ local count=$1; shift
+ local should_fail=$1; shift
+
+ TC_FLOWER_BATCH_FILE="$(mktemp)"
+
+ for ((i = 0; i < count; ++i)); do
+ cat >> $TC_FLOWER_BATCH_FILE <<-EOF
+ filter add dev $h2 ingress \
+ prot ipv6 \
+ pref 1000 \
+ flower $tcflags dst_ip $(tc_flower_addr $i) \
+ action drop
+ EOF
+ done
+
+ tc -b $TC_FLOWER_BATCH_FILE
+ check_err_fail $should_fail $? "Rule insertion"
+}
+
+__tc_flower_test()
+{
+ local count=$1; shift
+ local should_fail=$1; shift
+ local last=$((count - 1))
+
+ tc_flower_rules_create $count $should_fail
+
+ for ((i = 0; i < count; ++i)); do
+ $MZ $h1 -q -c 1 -t ip -p 20 -b bc -6 \
+ -A 2001:db8:2::1 \
+ -B $(tc_flower_addr $i)
+ done
+
+ MISMATCHES=$(
+ tc -j -s filter show dev $h2 ingress |
+ jq -r '[ .[] | select(.kind == "flower") | .options |
+ values as $rule | .actions[].stats.packets |
+ select(. != 1) | "\(.) on \($rule.keys.dst_ip)" ] |
+ join(", ")'
+ )
+
+ test -z "$MISMATCHES"
+ check_err $? "Expected to capture 1 packet for each IP, but got $MISMATCHES"
+}
+
+tc_flower_test()
+{
+ local count=$1; shift
+ local should_fail=$1; shift
+
+ # We use lower 16 bits of IPv6 address for match. Also there are only 16
+ # bits of rule priority space.
+ if ((count > 65536)); then
+ check_err 1 "Invalid count of $count. At most 65536 rules supported"
+ return
+ fi
+
+ if ! tc_offload_check $TC_FLOWER_NUM_NETIFS; then
+ check_err 1 "Could not test offloaded functionality"
+ return
+ fi
+
+ tcflags="skip_sw"
+ __tc_flower_test $count $should_fail
+}
udpgso
udpgso_bench_rx
udpgso_bench_tx
+tcp_inq
TEST_GEN_FILES += tcp_mmap tcp_inq psock_snd
TEST_GEN_FILES += udpgso udpgso_bench_tx udpgso_bench_rx
TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
-TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict
+TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls
include ../lib.mk
CONFIG_INET6_XFRM_MODE_TUNNEL=y
CONFIG_IPV6_VTI=y
CONFIG_DUMMY=y
+CONFIG_BRIDGE=y
+CONFIG_VLAN_8021Q=y
o Where possible, reuse an existing topology for different tests instead
of recreating the same topology.
+o Tests that use anything but the most trivial topologies should include
+ an ASCII art showing the topology.
o Where possible, IPv6 and IPv4 addresses shall conform to RFC 3849 and
RFC 5737, respectively.
o Where possible, tests shall be written so that they can be reused by
--- /dev/null
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="ping_ipv4 ping_ipv6 flooding"
+NUM_NETIFS=6
+CHECK_TC="yes"
+source lib.sh
+
+h1_create()
+{
+ simple_if_init $h1 192.0.2.1/24 2001:db8:1::1/64
+}
+
+h1_destroy()
+{
+ simple_if_fini $h1 192.0.2.1/24 2001:db8:1::1/64
+}
+
+h2_create()
+{
+ simple_if_init $h2 192.0.2.2/24 2001:db8:1::2/64
+}
+
+h2_destroy()
+{
+ simple_if_fini $h2 192.0.2.2/24 2001:db8:1::2/64
+}
+
+h3_create()
+{
+ simple_if_init $h3 192.0.2.3/24 2001:db8:1::3/64
+}
+
+h3_destroy()
+{
+ simple_if_fini $h3 192.0.2.3/24 2001:db8:1::3/64
+}
+
+switch_create()
+{
+ ip link add dev br0 type bridge
+
+ ip link set dev $swp1 master br0
+ ip link set dev $swp2 master br0
+ ip link set dev $swp3 master br0
+
+ ip link set dev $swp1 type bridge_slave isolated on
+ check_err $? "Can't set isolation on port $swp1"
+ ip link set dev $swp2 type bridge_slave isolated on
+ check_err $? "Can't set isolation on port $swp2"
+ ip link set dev $swp3 type bridge_slave isolated off
+ check_err $? "Can't disable isolation on port $swp3"
+
+ ip link set dev br0 up
+ ip link set dev $swp1 up
+ ip link set dev $swp2 up
+ ip link set dev $swp3 up
+}
+
+switch_destroy()
+{
+ ip link set dev $swp3 down
+ ip link set dev $swp2 down
+ ip link set dev $swp1 down
+
+ ip link del dev br0
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ swp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ swp3=${NETIFS[p5]}
+ h3=${NETIFS[p6]}
+
+ vrf_prepare
+
+ h1_create
+ h2_create
+ h3_create
+
+ switch_create
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ switch_destroy
+
+ h3_destroy
+ h2_destroy
+ h1_destroy
+
+ vrf_cleanup
+}
+
+ping_ipv4()
+{
+ RET=0
+ ping_do $h1 192.0.2.2
+ check_fail $? "Ping worked when it should not have"
+
+ RET=0
+ ping_do $h3 192.0.2.2
+ check_err $? "Ping didn't work when it should have"
+
+ log_test "Isolated port ping"
+}
+
+ping_ipv6()
+{
+ RET=0
+ ping6_do $h1 2001:db8:1::2
+ check_fail $? "Ping6 worked when it should not have"
+
+ RET=0
+ ping6_do $h3 2001:db8:1::2
+ check_err $? "Ping6 didn't work when it should have"
+
+ log_test "Isolated port ping6"
+}
+
+flooding()
+{
+ local mac=de:ad:be:ef:13:37
+ local ip=192.0.2.100
+
+ RET=0
+ flood_test_do false $mac $ip $h1 $h2
+ check_err $? "Packet was flooded when it should not have been"
+
+ RET=0
+ flood_test_do true $mac $ip $h3 $h2
+ check_err $? "Packet was not flooded when it should have been"
+
+ log_test "Isolated port flooding"
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
--- /dev/null
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+##############################################################################
+# Source library
+
+relative_path="${BASH_SOURCE%/*}"
+if [[ "$relative_path" == "${BASH_SOURCE}" ]]; then
+ relative_path="."
+fi
+
+source "$relative_path/lib.sh"
+
+##############################################################################
+# Defines
+
+DEVLINK_DEV=$(devlink port show | grep "${NETIFS[p1]}" | \
+ grep -v "${NETIFS[p1]}[0-9]" | cut -d" " -f1 | \
+ rev | cut -d"/" -f2- | rev)
+if [ -z "$DEVLINK_DEV" ]; then
+ echo "SKIP: ${NETIFS[p1]} has no devlink device registered for it"
+ exit 1
+fi
+if [[ "$(echo $DEVLINK_DEV | grep -c pci)" -eq 0 ]]; then
+ echo "SKIP: devlink device's bus is not PCI"
+ exit 1
+fi
+
+DEVLINK_VIDDID=$(lspci -s $(echo $DEVLINK_DEV | cut -d"/" -f2) \
+ -n | cut -d" " -f3)
+
+##############################################################################
+# Sanity checks
+
+devlink -j resource show "$DEVLINK_DEV" &> /dev/null
+if [ $? -ne 0 ]; then
+ echo "SKIP: iproute2 too old, missing devlink resource support"
+ exit 1
+fi
+
+##############################################################################
+# Devlink helpers
+
+devlink_resource_names_to_path()
+{
+ local resource
+ local path=""
+
+ for resource in "${@}"; do
+ if [ "$path" == "" ]; then
+ path="$resource"
+ else
+ path="${path}/$resource"
+ fi
+ done
+
+ echo "$path"
+}
+
+devlink_resource_get()
+{
+ local name=$1
+ local resource_name=.[][\"$DEVLINK_DEV\"]
+
+ resource_name="$resource_name | .[] | select (.name == \"$name\")"
+
+ shift
+ for resource in "${@}"; do
+ resource_name="${resource_name} | .[\"resources\"][] | \
+ select (.name == \"$resource\")"
+ done
+
+ devlink -j resource show "$DEVLINK_DEV" | jq "$resource_name"
+}
+
+devlink_resource_size_get()
+{
+ local size=$(devlink_resource_get "$@" | jq '.["size_new"]')
+
+ if [ "$size" == "null" ]; then
+ devlink_resource_get "$@" | jq '.["size"]'
+ else
+ echo "$size"
+ fi
+}
+
+devlink_resource_size_set()
+{
+ local new_size=$1
+ local path
+
+ shift
+ path=$(devlink_resource_names_to_path "$@")
+ devlink resource set "$DEVLINK_DEV" path "$path" size "$new_size"
+ check_err $? "Failed setting path $path to size $size"
+}
+
+devlink_reload()
+{
+ local still_pending
+
+ devlink dev reload "$DEVLINK_DEV" &> /dev/null
+ check_err $? "Failed reload"
+
+ still_pending=$(devlink resource show "$DEVLINK_DEV" | \
+ grep -c "size_new")
+ check_err $still_pending "Failed reload - There are still unset sizes"
+}
--- /dev/null
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test traffic distribution when a wECMP route forwards traffic to two GRE
+# tunnels.
+#
+# +-------------------------+
+# | H1 |
+# | $h1 + |
+# | 192.0.2.1/28 | |
+# | 2001:db8:1::1/64 | |
+# +-------------------|-----+
+# |
+# +-------------------|------------------------+
+# | SW1 | |
+# | $ol1 + |
+# | 192.0.2.2/28 |
+# | 2001:db8:1::2/64 |
+# | |
+# | + g1a (gre) + g1b (gre) |
+# | loc=192.0.2.65 loc=192.0.2.81 |
+# | rem=192.0.2.66 --. rem=192.0.2.82 --. |
+# | tos=inherit | tos=inherit | |
+# | .------------------' | |
+# | | .------------------' |
+# | v v |
+# | + $ul1.111 (vlan) + $ul1.222 (vlan) |
+# | | 192.0.2.129/28 | 192.0.2.145/28 |
+# | \ / |
+# | \________________/ |
+# | | |
+# | + $ul1 |
+# +------------|-------------------------------+
+# |
+# +------------|-------------------------------+
+# | SW2 + $ul2 |
+# | _______|________ |
+# | / \ |
+# | / \ |
+# | + $ul2.111 (vlan) + $ul2.222 (vlan) |
+# | ^ 192.0.2.130/28 ^ 192.0.2.146/28 |
+# | | | |
+# | | '------------------. |
+# | '------------------. | |
+# | + g2a (gre) | + g2b (gre) | |
+# | loc=192.0.2.66 | loc=192.0.2.82 | |
+# | rem=192.0.2.65 --' rem=192.0.2.81 --' |
+# | tos=inherit tos=inherit |
+# | |
+# | $ol2 + |
+# | 192.0.2.17/28 | |
+# | 2001:db8:2::1/64 | |
+# +-------------------|------------------------+
+# |
+# +-------------------|-----+
+# | H2 | |
+# | $h2 + |
+# | 192.0.2.18/28 |
+# | 2001:db8:2::2/64 |
+# +-------------------------+
+
+ALL_TESTS="
+ ping_ipv4
+ ping_ipv6
+ multipath_ipv4
+ multipath_ipv6
+ multipath_ipv6_l4
+"
+
+NUM_NETIFS=6
+source lib.sh
+
+h1_create()
+{
+ simple_if_init $h1 192.0.2.1/28 2001:db8:1::1/64
+ ip route add vrf v$h1 192.0.2.16/28 via 192.0.2.2
+ ip route add vrf v$h1 2001:db8:2::/64 via 2001:db8:1::2
+}
+
+h1_destroy()
+{
+ ip route del vrf v$h1 2001:db8:2::/64 via 2001:db8:1::2
+ ip route del vrf v$h1 192.0.2.16/28 via 192.0.2.2
+ simple_if_fini $h1 192.0.2.1/28
+}
+
+sw1_create()
+{
+ simple_if_init $ol1 192.0.2.2/28 2001:db8:1::2/64
+ __simple_if_init $ul1 v$ol1
+ vlan_create $ul1 111 v$ol1 192.0.2.129/28
+ vlan_create $ul1 222 v$ol1 192.0.2.145/28
+
+ tunnel_create g1a gre 192.0.2.65 192.0.2.66 tos inherit dev v$ol1
+ __simple_if_init g1a v$ol1 192.0.2.65/32
+ ip route add vrf v$ol1 192.0.2.66/32 via 192.0.2.130
+
+ tunnel_create g1b gre 192.0.2.81 192.0.2.82 tos inherit dev v$ol1
+ __simple_if_init g1b v$ol1 192.0.2.81/32
+ ip route add vrf v$ol1 192.0.2.82/32 via 192.0.2.146
+
+ ip route add vrf v$ol1 192.0.2.16/28 \
+ nexthop dev g1a \
+ nexthop dev g1b
+ ip route add vrf v$ol1 2001:db8:2::/64 \
+ nexthop dev g1a \
+ nexthop dev g1b
+
+ tc qdisc add dev $ul1 clsact
+ tc filter add dev $ul1 egress pref 111 prot 802.1q \
+ flower vlan_id 111 action pass
+ tc filter add dev $ul1 egress pref 222 prot 802.1q \
+ flower vlan_id 222 action pass
+}
+
+sw1_destroy()
+{
+ tc qdisc del dev $ul1 clsact
+
+ ip route del vrf v$ol1 2001:db8:2::/64
+ ip route del vrf v$ol1 192.0.2.16/28
+
+ ip route del vrf v$ol1 192.0.2.82/32 via 192.0.2.146
+ __simple_if_fini g1b 192.0.2.81/32
+ tunnel_destroy g1b
+
+ ip route del vrf v$ol1 192.0.2.66/32 via 192.0.2.130
+ __simple_if_fini g1a 192.0.2.65/32
+ tunnel_destroy g1a
+
+ vlan_destroy $ul1 222
+ vlan_destroy $ul1 111
+ __simple_if_fini $ul1
+ simple_if_fini $ol1 192.0.2.2/28 2001:db8:1::2/64
+}
+
+sw2_create()
+{
+ simple_if_init $ol2 192.0.2.17/28 2001:db8:2::1/64
+ __simple_if_init $ul2 v$ol2
+ vlan_create $ul2 111 v$ol2 192.0.2.130/28
+ vlan_create $ul2 222 v$ol2 192.0.2.146/28
+
+ tunnel_create g2a gre 192.0.2.66 192.0.2.65 tos inherit dev v$ol2
+ __simple_if_init g2a v$ol2 192.0.2.66/32
+ ip route add vrf v$ol2 192.0.2.65/32 via 192.0.2.129
+
+ tunnel_create g2b gre 192.0.2.82 192.0.2.81 tos inherit dev v$ol2
+ __simple_if_init g2b v$ol2 192.0.2.82/32
+ ip route add vrf v$ol2 192.0.2.81/32 via 192.0.2.145
+
+ ip route add vrf v$ol2 192.0.2.0/28 \
+ nexthop dev g2a \
+ nexthop dev g2b
+ ip route add vrf v$ol2 2001:db8:1::/64 \
+ nexthop dev g2a \
+ nexthop dev g2b
+}
+
+sw2_destroy()
+{
+ ip route del vrf v$ol2 2001:db8:1::/64
+ ip route del vrf v$ol2 192.0.2.0/28
+
+ ip route del vrf v$ol2 192.0.2.81/32 via 192.0.2.145
+ __simple_if_fini g2b 192.0.2.82/32
+ tunnel_destroy g2b
+
+ ip route del vrf v$ol2 192.0.2.65/32 via 192.0.2.129
+ __simple_if_fini g2a 192.0.2.66/32
+ tunnel_destroy g2a
+
+ vlan_destroy $ul2 222
+ vlan_destroy $ul2 111
+ __simple_if_fini $ul2
+ simple_if_fini $ol2 192.0.2.17/28 2001:db8:2::1/64
+}
+
+h2_create()
+{
+ simple_if_init $h2 192.0.2.18/28 2001:db8:2::2/64
+ ip route add vrf v$h2 192.0.2.0/28 via 192.0.2.17
+ ip route add vrf v$h2 2001:db8:1::/64 via 2001:db8:2::1
+}
+
+h2_destroy()
+{
+ ip route del vrf v$h2 2001:db8:1::/64 via 2001:db8:2::1
+ ip route del vrf v$h2 192.0.2.0/28 via 192.0.2.17
+ simple_if_fini $h2 192.0.2.18/28 2001:db8:2::2/64
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ ol1=${NETIFS[p2]}
+
+ ul1=${NETIFS[p3]}
+ ul2=${NETIFS[p4]}
+
+ ol2=${NETIFS[p5]}
+ h2=${NETIFS[p6]}
+
+ vrf_prepare
+ h1_create
+ sw1_create
+ sw2_create
+ h2_create
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ h2_destroy
+ sw2_destroy
+ sw1_destroy
+ h1_destroy
+ vrf_cleanup
+}
+
+multipath4_test()
+{
+ local what=$1; shift
+ local weight1=$1; shift
+ local weight2=$1; shift
+
+ sysctl_set net.ipv4.fib_multipath_hash_policy 1
+ ip route replace vrf v$ol1 192.0.2.16/28 \
+ nexthop dev g1a weight $weight1 \
+ nexthop dev g1b weight $weight2
+
+ local t0_111=$(tc_rule_stats_get $ul1 111 egress)
+ local t0_222=$(tc_rule_stats_get $ul1 222 egress)
+
+ ip vrf exec v$h1 \
+ $MZ $h1 -q -p 64 -A 192.0.2.1 -B 192.0.2.18 \
+ -d 1msec -t udp "sp=1024,dp=0-32768"
+
+ local t1_111=$(tc_rule_stats_get $ul1 111 egress)
+ local t1_222=$(tc_rule_stats_get $ul1 222 egress)
+
+ local d111=$((t1_111 - t0_111))
+ local d222=$((t1_222 - t0_222))
+ multipath_eval "$what" $weight1 $weight2 $d111 $d222
+
+ ip route replace vrf v$ol1 192.0.2.16/28 \
+ nexthop dev g1a \
+ nexthop dev g1b
+ sysctl_restore net.ipv4.fib_multipath_hash_policy
+}
+
+multipath6_l4_test()
+{
+ local what=$1; shift
+ local weight1=$1; shift
+ local weight2=$1; shift
+
+ sysctl_set net.ipv6.fib_multipath_hash_policy 1
+ ip route replace vrf v$ol1 2001:db8:2::/64 \
+ nexthop dev g1a weight $weight1 \
+ nexthop dev g1b weight $weight2
+
+ local t0_111=$(tc_rule_stats_get $ul1 111 egress)
+ local t0_222=$(tc_rule_stats_get $ul1 222 egress)
+
+ ip vrf exec v$h1 \
+ $MZ $h1 -6 -q -p 64 -A 2001:db8:1::1 -B 2001:db8:2::2 \
+ -d 1msec -t udp "sp=1024,dp=0-32768"
+
+ local t1_111=$(tc_rule_stats_get $ul1 111 egress)
+ local t1_222=$(tc_rule_stats_get $ul1 222 egress)
+
+ local d111=$((t1_111 - t0_111))
+ local d222=$((t1_222 - t0_222))
+ multipath_eval "$what" $weight1 $weight2 $d111 $d222
+
+ ip route replace vrf v$ol1 2001:db8:2::/64 \
+ nexthop dev g1a \
+ nexthop dev g1b
+ sysctl_restore net.ipv6.fib_multipath_hash_policy
+}
+
+multipath6_test()
+{
+ local what=$1; shift
+ local weight1=$1; shift
+ local weight2=$1; shift
+
+ ip route replace vrf v$ol1 2001:db8:2::/64 \
+ nexthop dev g1a weight $weight1 \
+ nexthop dev g1b weight $weight2
+
+ local t0_111=$(tc_rule_stats_get $ul1 111 egress)
+ local t0_222=$(tc_rule_stats_get $ul1 222 egress)
+
+ # Generate 16384 echo requests, each with a random flow label.
+ for ((i=0; i < 16384; ++i)); do
+ ip vrf exec v$h1 $PING6 2001:db8:2::2 -F 0 -c 1 -q &> /dev/null
+ done
+
+ local t1_111=$(tc_rule_stats_get $ul1 111 egress)
+ local t1_222=$(tc_rule_stats_get $ul1 222 egress)
+
+ local d111=$((t1_111 - t0_111))
+ local d222=$((t1_222 - t0_222))
+ multipath_eval "$what" $weight1 $weight2 $d111 $d222
+
+ ip route replace vrf v$ol1 2001:db8:2::/64 \
+ nexthop dev g1a \
+ nexthop dev g1b
+}
+
+ping_ipv4()
+{
+ ping_test $h1 192.0.2.18
+}
+
+ping_ipv6()
+{
+ ping6_test $h1 2001:db8:2::2
+}
+
+multipath_ipv4()
+{
+ log_info "Running IPv4 multipath tests"
+ multipath4_test "ECMP" 1 1
+ multipath4_test "Weighted MP 2:1" 2 1
+ multipath4_test "Weighted MP 11:45" 11 45
+}
+
+multipath_ipv6()
+{
+ log_info "Running IPv6 multipath tests"
+ multipath6_test "ECMP" 1 1
+ multipath6_test "Weighted MP 2:1" 2 1
+ multipath6_test "Weighted MP 11:45" 11 45
+}
+
+multipath_ipv6_l4()
+{
+ log_info "Running IPv6 L4 hash multipath tests"
+ multipath6_l4_test "ECMP" 1 1
+ multipath6_l4_test "Weighted MP 2:1" 2 1
+ multipath6_l4_test "Weighted MP 11:45" 11 45
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+tests_run
+
+exit $EXIT_STATUS
NETIF_TYPE=${NETIF_TYPE:=veth}
NETIF_CREATE=${NETIF_CREATE:=yes}
-if [[ -f forwarding.config ]]; then
- source forwarding.config
+relative_path="${BASH_SOURCE%/*}"
+if [[ "$relative_path" == "${BASH_SOURCE}" ]]; then
+ relative_path="."
+fi
+
+if [[ -f $relative_path/forwarding.config ]]; then
+ source "$relative_path/forwarding.config"
fi
##############################################################################
fi
}
+check_err_fail()
+{
+ local should_fail=$1; shift
+ local err=$1; shift
+ local what=$1; shift
+
+ if ((should_fail)); then
+ check_fail $err "$what succeeded, but should have failed"
+ else
+ check_err $err "$what failed"
+ fi
+}
+
log_test()
{
local test_name=$1
echo "INFO: $msg"
}
+setup_wait_dev()
+{
+ local dev=$1; shift
+
+ while true; do
+ ip link show dev $dev up \
+ | grep 'state UP' &> /dev/null
+ if [[ $? -ne 0 ]]; then
+ sleep 1
+ else
+ break
+ fi
+ done
+}
+
setup_wait()
{
- for i in $(eval echo {1..$NUM_NETIFS}); do
- while true; do
- ip link show dev ${NETIFS[p$i]} up \
- | grep 'state UP' &> /dev/null
- if [[ $? -ne 0 ]]; then
- sleep 1
- else
- break
- fi
- done
+ local num_netifs=${1:-$NUM_NETIFS}
+
+ for ((i = 1; i <= num_netifs; ++i)); do
+ setup_wait_dev ${NETIFS[p$i]}
done
# Make sure links are ready.
done
}
+__simple_if_init()
+{
+ local if_name=$1; shift
+ local vrf_name=$1; shift
+ local addrs=("${@}")
+
+ ip link set dev $if_name master $vrf_name
+ ip link set dev $if_name up
+
+ __addr_add_del $if_name add "${addrs[@]}"
+}
+
+__simple_if_fini()
+{
+ local if_name=$1; shift
+ local addrs=("${@}")
+
+ __addr_add_del $if_name del "${addrs[@]}"
+
+ ip link set dev $if_name down
+ ip link set dev $if_name nomaster
+}
+
simple_if_init()
{
local if_name=$1
array=("${@}")
vrf_create $vrf_name
- ip link set dev $if_name master $vrf_name
ip link set dev $vrf_name up
- ip link set dev $if_name up
-
- __addr_add_del $if_name add "${array[@]}"
+ __simple_if_init $if_name $vrf_name "${array[@]}"
}
simple_if_fini()
vrf_name=v$if_name
array=("${@}")
- __addr_add_del $if_name del "${array[@]}"
-
- ip link set dev $if_name down
+ __simple_if_fini $if_name "${array[@]}"
vrf_destroy $vrf_name
}
{
local dev=$1; shift
local pref=$1; shift
+ local dir=$1; shift
- tc -j -s filter show dev $dev ingress pref $pref |
- jq '.[1].options.actions[].stats.packets'
+ tc -j -s filter show dev $dev ${dir:-ingress} pref $pref \
+ | jq '.[1].options.actions[].stats.packets'
}
mac_get()
tc_offload_check()
{
- for i in $(eval echo {1..$NUM_NETIFS}); do
+ local num_netifs=${1:-$NUM_NETIFS}
+
+ for ((i = 1; i <= num_netifs; ++i)); do
ethtool -k ${NETIFS[p$i]} \
| grep "hw-tc-offload: on" &> /dev/null
if [[ $? -ne 0 ]]; then
local dev=$1; shift
local direction=$1; shift
- # For slow-path testing, we need to install a trap to get to
- # slow path the packets that would otherwise be switched in HW.
- tc filter add dev $dev $direction pref 1 flower skip_sw action trap
+ # Some devices may not support or need in-hardware trapping of traffic
+ # (e.g. the veth pairs that this library creates for non-existent
+ # loopbacks). Use continue instead, so that there is a filter in there
+ # (some tests check counters), and so that other filters are still
+ # processed.
+ tc filter add dev $dev $direction pref 1 \
+ flower skip_sw action trap 2>/dev/null \
+ || tc filter add dev $dev $direction pref 1 \
+ flower action continue
}
trap_uninstall()
local dev=$1; shift
local direction=$1; shift
- tc filter del dev $dev $direction pref 1 flower skip_sw
+ tc filter del dev $dev $direction pref 1 flower
}
slow_path_trap_install()
{
+ # For slow-path testing, we need to install a trap to get to
+ # slow path the packets that would otherwise be switched in HW.
if [ "${tcflags/skip_hw}" != "$tcflags" ]; then
trap_install "$@"
fi
done
}
+multipath_eval()
+{
+ local desc="$1"
+ local weight_rp12=$2
+ local weight_rp13=$3
+ local packets_rp12=$4
+ local packets_rp13=$5
+ local weights_ratio packets_ratio diff
+
+ RET=0
+
+ if [[ "$weight_rp12" -gt "$weight_rp13" ]]; then
+ weights_ratio=$(echo "scale=2; $weight_rp12 / $weight_rp13" \
+ | bc -l)
+ else
+ weights_ratio=$(echo "scale=2; $weight_rp13 / $weight_rp12" \
+ | bc -l)
+ fi
+
+ if [[ "$packets_rp12" -eq "0" || "$packets_rp13" -eq "0" ]]; then
+ check_err 1 "Packet difference is 0"
+ log_test "Multipath"
+ log_info "Expected ratio $weights_ratio"
+ return
+ fi
+
+ if [[ "$weight_rp12" -gt "$weight_rp13" ]]; then
+ packets_ratio=$(echo "scale=2; $packets_rp12 / $packets_rp13" \
+ | bc -l)
+ else
+ packets_ratio=$(echo "scale=2; $packets_rp13 / $packets_rp12" \
+ | bc -l)
+ fi
+
+ diff=$(echo $weights_ratio - $packets_ratio | bc -l)
+ diff=${diff#-}
+
+ test "$(echo "$diff / $weights_ratio > 0.15" | bc -l)" -eq 0
+ check_err $? "Too large discrepancy between expected and measured ratios"
+ log_test "$desc"
+ log_info "Expected ratio $weights_ratio Measured ratio $packets_ratio"
+}
+
##############################################################################
# Tests
-ping_test()
+ping_do()
{
local if_name=$1
local dip=$2
local vrf_name
- RET=0
-
vrf_name=$(master_name_get $if_name)
ip vrf exec $vrf_name $PING $dip -c 10 -i 0.1 -w 2 &> /dev/null
+}
+
+ping_test()
+{
+ RET=0
+
+ ping_do $1 $2
check_err $?
log_test "ping"
}
-ping6_test()
+ping6_do()
{
local if_name=$1
local dip=$2
local vrf_name
- RET=0
-
vrf_name=$(master_name_get $if_name)
ip vrf exec $vrf_name $PING6 $dip -c 10 -i 0.1 -w 2 &> /dev/null
+}
+
+ping6_test()
+{
+ RET=0
+
+ ping6_do $1 $2
check_err $?
log_test "ping6"
}
--- /dev/null
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test for "tc action mirred egress mirror" when the underlay route points at a
+# bridge device without vlan filtering (802.1d).
+#
+# This test uses standard topology for testing mirror-to-gretap. See
+# mirror_gre_topo_lib.sh for more details. The full topology is as follows:
+#
+# +---------------------+ +---------------------+
+# | H1 | | H2 |
+# | + $h1 | | $h2 + |
+# | | 192.0.2.1/28 | | 192.0.2.2/28 | |
+# +-----|---------------+ +---------------|-----+
+# | |
+# +-----|-------------------------------------------------------------|-----+
+# | SW o---> mirror | |
+# | +---|-------------------------------------------------------------|---+ |
+# | | + $swp1 + br1 (802.1q bridge) $swp2 + | |
+# | +---------------------------------------------------------------------+ |
+# | |
+# | +---------------------------------------------------------------------+ |
+# | | + br2 (802.1d bridge) | |
+# | | 192.0.2.129/28 | |
+# | | + $swp3 2001:db8:2::1/64 | |
+# | +---|-----------------------------------------------------------------+ |
+# | | ^ ^ |
+# | | + gt6 (ip6gretap) | + gt4 (gretap) | |
+# | | : loc=2001:db8:2::1 | : loc=192.0.2.129 | |
+# | | : rem=2001:db8:2::2 -+ : rem=192.0.2.130 -+ |
+# | | : ttl=100 : ttl=100 |
+# | | : tos=inherit : tos=inherit |
+# +-----|---------------------:----------------------:----------------------+
+# | : :
+# +-----|---------------------:----------------------:----------------------+
+# | H3 + $h3 + h3-gt6(ip6gretap) + h3-gt4 (gretap) |
+# | 192.0.2.130/28 loc=2001:db8:2::2 loc=192.0.2.130 |
+# | 2001:db8:2::2/64 rem=2001:db8:2::1 rem=192.0.2.129 |
+# | ttl=100 ttl=100 |
+# | tos=inherit tos=inherit |
+# +-------------------------------------------------------------------------+
+
+ALL_TESTS="
+ test_gretap
+ test_ip6gretap
+"
+
+NUM_NETIFS=6
+source lib.sh
+source mirror_lib.sh
+source mirror_gre_lib.sh
+source mirror_gre_topo_lib.sh
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ swp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ swp3=${NETIFS[p5]}
+ h3=${NETIFS[p6]}
+
+ vrf_prepare
+ mirror_gre_topo_create
+
+ ip link add name br2 type bridge vlan_filtering 0
+ ip link set dev br2 up
+
+ ip link set dev $swp3 master br2
+ ip route add 192.0.2.130/32 dev br2
+ ip -6 route add 2001:db8:2::2/128 dev br2
+
+ ip address add dev br2 192.0.2.129/28
+ ip address add dev br2 2001:db8:2::1/64
+
+ ip address add dev $h3 192.0.2.130/28
+ ip address add dev $h3 2001:db8:2::2/64
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ ip address del dev $h3 2001:db8:2::2/64
+ ip address del dev $h3 192.0.2.130/28
+ ip link del dev br2
+
+ mirror_gre_topo_destroy
+ vrf_cleanup
+}
+
+test_gretap()
+{
+ full_test_span_gre_dir gt4 ingress 8 0 "mirror to gretap"
+ full_test_span_gre_dir gt4 egress 0 8 "mirror to gretap"
+}
+
+test_ip6gretap()
+{
+ full_test_span_gre_dir gt6 ingress 8 0 "mirror to ip6gretap"
+ full_test_span_gre_dir gt6 egress 0 8 "mirror to ip6gretap"
+}
+
+test_all()
+{
+ slow_path_trap_install $swp1 ingress
+ slow_path_trap_install $swp1 egress
+
+ tests_run
+
+ slow_path_trap_uninstall $swp1 egress
+ slow_path_trap_uninstall $swp1 ingress
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tcflags="skip_hw"
+test_all
+
+if ! tc_offload_check; then
+ echo "WARN: Could not test offloaded functionality"
+else
+ tcflags="skip_sw"
+ test_all
+fi
+
+exit $EXIT_STATUS
test_gretap()
{
- test_vlan_match gt4 'vlan_id 555 vlan_ethtype ip' "mirror to gretap"
+ test_vlan_match gt4 'skip_hw vlan_id 555 vlan_ethtype ip' \
+ "mirror to gretap"
}
test_ip6gretap()
{
- test_vlan_match gt6 'vlan_id 555 vlan_ethtype ipv6' "mirror to ip6gretap"
+ test_vlan_match gt6 'skip_hw vlan_id 555 vlan_ethtype ip' \
+ "mirror to ip6gretap"
}
test_gretap_stp()
--- /dev/null
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test for "tc action mirred egress mirror" when the underlay route points at a
+# bridge device with vlan filtering (802.1q).
+#
+# This test uses standard topology for testing mirror-to-gretap. See
+# mirror_gre_topo_lib.sh for more details. The full topology is as follows:
+#
+# +---------------------+ +---------------------+
+# | H1 | | H2 |
+# | + $h1 | | $h2 + |
+# | | 192.0.2.1/28 | | 192.0.2.2/28 | |
+# +-----|---------------+ +---------------|-----+
+# | |
+# +-----|---------------------------------------------------------------|-----+
+# | SW o---> mirror | |
+# | +---|---------------------------------------------------------------|---+ |
+# | | + $swp1 + br1 (802.1q bridge) $swp2 + | |
+# | | 192.0.2.129/28 | |
+# | | + $swp3 2001:db8:2::1/64 | |
+# | | | vid555 vid555[pvid,untagged] | |
+# | +---|-------------------------------------------------------------------+ |
+# | | ^ ^ |
+# | | + gt6 (ip6gretap) | + gt4 (gretap) | |
+# | | : loc=2001:db8:2::1 | : loc=192.0.2.129 | |
+# | | : rem=2001:db8:2::2 -+ : rem=192.0.2.130 -+ |
+# | | : ttl=100 : ttl=100 |
+# | | : tos=inherit : tos=inherit |
+# +-----|---------------------:------------------------:----------------------+
+# | : :
+# +-----|---------------------:------------------------:----------------------+
+# | H3 + $h3 + h3-gt6(ip6gretap) + h3-gt4 (gretap) |
+# | | loc=2001:db8:2::2 loc=192.0.2.130 |
+# | + $h3.555 rem=2001:db8:2::1 rem=192.0.2.129 |
+# | 192.0.2.130/28 ttl=100 ttl=100 |
+# | 2001:db8:2::2/64 tos=inherit tos=inherit |
+# +---------------------------------------------------------------------------+
+
+ALL_TESTS="
+ test_gretap
+ test_ip6gretap
+"
+
+NUM_NETIFS=6
+source lib.sh
+source mirror_lib.sh
+source mirror_gre_lib.sh
+source mirror_gre_topo_lib.sh
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ swp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ swp3=${NETIFS[p5]}
+ h3=${NETIFS[p6]}
+
+ vrf_prepare
+ mirror_gre_topo_create
+
+ ip link set dev $swp3 master br1
+ bridge vlan add dev br1 vid 555 pvid untagged self
+ ip address add dev br1 192.0.2.129/28
+ ip address add dev br1 2001:db8:2::1/64
+
+ ip -4 route add 192.0.2.130/32 dev br1
+ ip -6 route add 2001:db8:2::2/128 dev br1
+
+ vlan_create $h3 555 v$h3 192.0.2.130/28 2001:db8:2::2/64
+ bridge vlan add dev $swp3 vid 555
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ ip link set dev $swp3 nomaster
+ vlan_destroy $h3 555
+
+ mirror_gre_topo_destroy
+ vrf_cleanup
+}
+
+test_gretap()
+{
+ full_test_span_gre_dir gt4 ingress 8 0 "mirror to gretap"
+ full_test_span_gre_dir gt4 egress 0 8 "mirror to gretap"
+}
+
+test_ip6gretap()
+{
+ full_test_span_gre_dir gt6 ingress 8 0 "mirror to ip6gretap"
+ full_test_span_gre_dir gt6 egress 0 8 "mirror to ip6gretap"
+}
+
+tests()
+{
+ slow_path_trap_install $swp1 ingress
+ slow_path_trap_install $swp1 egress
+
+ tests_run
+
+ slow_path_trap_uninstall $swp1 egress
+ slow_path_trap_uninstall $swp1 ingress
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tcflags="skip_hw"
+tests
+
+if ! tc_offload_check; then
+ echo "WARN: Could not test offloaded functionality"
+else
+ tcflags="skip_sw"
+ tests
+fi
+
+exit $EXIT_STATUS
# After setting the device up, wait for neighbor to get resolved so that
# we can expect mirroring to work.
ip link set dev $swp3 up
- while true; do
- ip neigh sh dev $swp3 $remote_ip nud reachable |
- grep -q ^
- if [[ $? -ne 0 ]]; then
- sleep 1
- else
- break
- fi
- done
+ setup_wait_dev $swp3
+ ping -c 1 -I $swp3 $remote_ip &>/dev/null
quick_test_span_gre_dir $tundev ingress
mirror_uninstall $swp1 ingress
# SPDX-License-Identifier: GPL-2.0
-source mirror_lib.sh
+source "$relative_path/mirror_lib.sh"
quick_test_span_gre_dir_ips()
{
"$backward_type" "$ip1" "$ip2"
tc filter add dev $h3 ingress pref 77 prot 802.1q \
- flower $vlan_match ip_proto 0x2f \
+ flower $vlan_match \
action pass
mirror_test v$h1 $ip1 $ip2 $h3 77 10
tc filter del dev $h3 ingress pref 77
vrf_prepare
mirror_gre_topo_create
+ sysctl_set net.ipv4.conf.v$h3.rp_filter 0
+
ip address add dev $swp3 192.0.2.161/28
ip address add dev $h3 192.0.2.162/28
ip address add dev gt4 192.0.2.129/32
ip address del dev $h3 192.0.2.162/28
ip address del dev $swp3 192.0.2.161/28
+ sysctl_restore net.ipv4.conf.v$h3.rp_filter 0
+
mirror_gre_topo_destroy
vrf_cleanup
# | |
# +-------------------------------------------------------------------------+
-source mirror_topo_lib.sh
+source "$relative_path/mirror_topo_lib.sh"
mirror_gre_topo_h3_create()
{
swp3=${NETIFS[p5]}
h3=${NETIFS[p6]}
+ # gt4's remote address is at $h3.555, not $h3. Thus the packets arriving
+ # directly to $h3 for test_gretap_untagged_egress() are rejected by
+ # rp_filter and the test spuriously fails.
+ sysctl_set net.ipv4.conf.all.rp_filter 0
+ sysctl_set net.ipv4.conf.$h3.rp_filter 0
+
vrf_prepare
mirror_gre_topo_create
mirror_gre_topo_destroy
vrf_cleanup
+
+ sysctl_restore net.ipv4.conf.$h3.rp_filter
+ sysctl_restore net.ipv4.conf.all.rp_filter
}
test_vlan_match()
test_gretap()
{
- test_vlan_match gt4 'vlan_id 555 vlan_ethtype ip' "mirror to gretap"
+ test_vlan_match gt4 'skip_hw vlan_id 555 vlan_ethtype ip' \
+ "mirror to gretap"
}
test_ip6gretap()
{
- test_vlan_match gt6 'vlan_id 555 vlan_ethtype ipv6' "mirror to ip6gretap"
+ test_vlan_match gt6 'skip_hw vlan_id 555 vlan_ethtype ip' \
+ "mirror to ip6gretap"
}
test_span_gre_forbidden_cpu()
# Install the capture as skip_hw to avoid double-counting of packets.
# The traffic is meant for local box anyway, so will be trapped to
# kernel.
- vlan_capture_install $dev "skip_hw vlan_id $vid"
+ vlan_capture_install $dev "skip_hw vlan_id $vid vlan_ethtype ip"
mirror_test v$h1 $ip1 $ip2 $dev 100 $expect
mirror_test v$h2 $ip2 $ip1 $dev 100 $expect
vlan_capture_uninstall $dev
--- /dev/null
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="
+ ping_ipv4
+ ping_ipv6
+"
+NUM_NETIFS=4
+source lib.sh
+
+h1_create()
+{
+ simple_if_init $h1 192.0.2.1/28 2001:db8:1::1/64
+ ip -4 route add 192.0.2.128/28 vrf v$h1 nexthop via 192.0.2.2
+ ip -6 route add 2001:db8:2::/64 vrf v$h1 nexthop via 2001:db8:1::2
+}
+
+h1_destroy()
+{
+ ip -6 route del 2001:db8:2::/64 vrf v$h1
+ ip -4 route del 192.0.2.128/28 vrf v$h1
+ simple_if_fini $h1 192.0.2.1/28 2001:db8:1::1/64
+}
+
+h2_create()
+{
+ simple_if_init $h2 192.0.2.130/28 2001:db8:2::2/64
+ ip -4 route add 192.0.2.0/28 vrf v$h2 nexthop via 192.0.2.129
+ ip -6 route add 2001:db8:1::/64 vrf v$h2 nexthop via 2001:db8:2::1
+}
+
+h2_destroy()
+{
+ ip -6 route del 2001:db8:1::/64 vrf v$h2
+ ip -4 route del 192.0.2.0/28 vrf v$h2
+ simple_if_fini $h2 192.0.2.130/28 2001:db8:2::2/64
+}
+
+router_create()
+{
+ ip link add name br1 type bridge vlan_filtering 1
+ ip link set dev br1 up
+
+ ip link set dev $swp1 master br1
+ ip link set dev $swp1 up
+ __addr_add_del br1 add 192.0.2.2/28 2001:db8:1::2/64
+
+ ip link set dev $swp2 up
+ __addr_add_del $swp2 add 192.0.2.129/28 2001:db8:2::1/64
+}
+
+router_destroy()
+{
+ __addr_add_del $swp2 del 192.0.2.129/28 2001:db8:2::1/64
+ ip link set dev $swp2 down
+
+ __addr_add_del br1 del 192.0.2.2/28 2001:db8:1::2/64
+ ip link set dev $swp1 down
+ ip link set dev $swp1 nomaster
+
+ ip link del dev br1
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ swp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ vrf_prepare
+
+ h1_create
+ h2_create
+
+ router_create
+
+ forwarding_enable
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ forwarding_restore
+
+ router_destroy
+
+ h2_destroy
+ h1_destroy
+
+ vrf_cleanup
+}
+
+ping_ipv4()
+{
+ ping_test $h1 192.0.2.130
+}
+
+ping_ipv6()
+{
+ ping6_test $h1 2001:db8:2::2
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
--- /dev/null
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="
+ ping_ipv4
+ ping_ipv6
+ vlan
+"
+NUM_NETIFS=4
+source lib.sh
+
+h1_create()
+{
+ simple_if_init $h1
+ vlan_create $h1 555 v$h1 192.0.2.1/28 2001:db8:1::1/64
+ ip -4 route add 192.0.2.128/28 vrf v$h1 nexthop via 192.0.2.2
+ ip -6 route add 2001:db8:2::/64 vrf v$h1 nexthop via 2001:db8:1::2
+}
+
+h1_destroy()
+{
+ ip -6 route del 2001:db8:2::/64 vrf v$h1
+ ip -4 route del 192.0.2.128/28 vrf v$h1
+ vlan_destroy $h1 555
+ simple_if_fini $h1
+}
+
+h2_create()
+{
+ simple_if_init $h2 192.0.2.130/28 2001:db8:2::2/64
+ ip -4 route add 192.0.2.0/28 vrf v$h2 nexthop via 192.0.2.129
+ ip -6 route add 2001:db8:1::/64 vrf v$h2 nexthop via 2001:db8:2::1
+}
+
+h2_destroy()
+{
+ ip -6 route del 2001:db8:1::/64 vrf v$h2
+ ip -4 route del 192.0.2.0/28 vrf v$h2
+ simple_if_fini $h2 192.0.2.130/28
+}
+
+router_create()
+{
+ ip link add name br1 type bridge vlan_filtering 1
+ ip link set dev br1 up
+
+ ip link set dev $swp1 master br1
+ ip link set dev $swp1 up
+
+ bridge vlan add dev br1 vid 555 self pvid untagged
+ bridge vlan add dev $swp1 vid 555
+
+ __addr_add_del br1 add 192.0.2.2/28 2001:db8:1::2/64
+
+ ip link set dev $swp2 up
+ __addr_add_del $swp2 add 192.0.2.129/28 2001:db8:2::1/64
+}
+
+router_destroy()
+{
+ __addr_add_del $swp2 del 192.0.2.129/28 2001:db8:2::1/64
+ ip link set dev $swp2 down
+
+ __addr_add_del br1 del 192.0.2.2/28 2001:db8:1::2/64
+ ip link set dev $swp1 down
+ ip link set dev $swp1 nomaster
+
+ ip link del dev br1
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ swp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ vrf_prepare
+
+ h1_create
+ h2_create
+
+ router_create
+
+ forwarding_enable
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ forwarding_restore
+
+ router_destroy
+
+ h2_destroy
+ h1_destroy
+
+ vrf_cleanup
+}
+
+vlan()
+{
+ RET=0
+
+ bridge vlan add dev br1 vid 333 self
+ check_err $? "Can't add a non-PVID VLAN"
+ bridge vlan del dev br1 vid 333 self
+ check_err $? "Can't remove a non-PVID VLAN"
+
+ log_test "vlan"
+}
+
+ping_ipv4()
+{
+ ping_test $h1 192.0.2.130
+}
+
+ping_ipv6()
+{
+ ping6_test $h1 2001:db8:2::2
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
vrf_destroy "vrf-r2"
}
-multipath_eval()
-{
- local desc="$1"
- local weight_rp12=$2
- local weight_rp13=$3
- local packets_rp12=$4
- local packets_rp13=$5
- local weights_ratio packets_ratio diff
-
- RET=0
-
- if [[ "$packets_rp12" -eq "0" || "$packets_rp13" -eq "0" ]]; then
- check_err 1 "Packet difference is 0"
- log_test "Multipath"
- log_info "Expected ratio $weights_ratio"
- return
- fi
-
- if [[ "$weight_rp12" -gt "$weight_rp13" ]]; then
- weights_ratio=$(echo "scale=2; $weight_rp12 / $weight_rp13" \
- | bc -l)
- packets_ratio=$(echo "scale=2; $packets_rp12 / $packets_rp13" \
- | bc -l)
- else
- weights_ratio=$(echo "scale=2; $weight_rp13 / $weight_rp12" | \
- bc -l)
- packets_ratio=$(echo "scale=2; $packets_rp13 / $packets_rp12" | \
- bc -l)
- fi
-
- diff=$(echo $weights_ratio - $packets_ratio | bc -l)
- diff=${diff#-}
-
- test "$(echo "$diff / $weights_ratio > 0.15" | bc -l)" -eq 0
- check_err $? "Too large discrepancy between expected and measured ratios"
- log_test "$desc"
- log_info "Expected ratio $weights_ratio Measured ratio $packets_ratio"
-}
-
multipath4_test()
{
local desc="$1"
--- /dev/null
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test that enough headroom is reserved for the first packet passing through an
+# IPv6 GRE-like netdevice.
+
+setup_prepare()
+{
+ ip link add h1 type veth peer name swp1
+ ip link add h3 type veth peer name swp3
+
+ ip link set dev h1 up
+ ip address add 192.0.2.1/28 dev h1
+
+ ip link add dev vh3 type vrf table 20
+ ip link set dev h3 master vh3
+ ip link set dev vh3 up
+ ip link set dev h3 up
+
+ ip link set dev swp3 up
+ ip address add dev swp3 2001:db8:2::1/64
+ ip address add dev swp3 2001:db8:2::3/64
+
+ ip link set dev swp1 up
+ tc qdisc add dev swp1 clsact
+
+ ip link add name er6 type ip6erspan \
+ local 2001:db8:2::1 remote 2001:db8:2::2 oseq okey 123
+ ip link set dev er6 up
+
+ ip link add name gt6 type ip6gretap \
+ local 2001:db8:2::3 remote 2001:db8:2::4
+ ip link set dev gt6 up
+
+ sleep 1
+}
+
+cleanup()
+{
+ ip link del dev gt6
+ ip link del dev er6
+ ip link del dev swp1
+ ip link del dev swp3
+ ip link del dev vh3
+}
+
+test_headroom()
+{
+ local type=$1; shift
+ local tundev=$1; shift
+
+ tc filter add dev swp1 ingress pref 1000 matchall skip_hw \
+ action mirred egress mirror dev $tundev
+ ping -I h1 192.0.2.2 -c 1 -w 2 &> /dev/null
+ tc filter del dev swp1 ingress pref 1000
+
+ # If it doesn't panic, it passes.
+ printf "TEST: %-60s [PASS]\n" "$type headroom"
+}
+
+trap cleanup EXIT
+
+setup_prepare
+test_headroom ip6gretap gt6
+test_headroom ip6erspan er6
#-------------------------------------------------------------------
kci_test_ipsec()
{
- srcip="14.0.0.52"
- dstip="14.0.0.70"
+ ret=0
algo="aead rfc4106(gcm(aes)) 0x3132333435363738393031323334353664636261 128"
+ srcip=192.168.123.1
+ dstip=192.168.123.2
+ spi=7
+
+ ip addr add $srcip dev $devdummy
# flush to be sure there's nothing configured
ip x s flush ; ip x p flush
check_err $?
# start the monitor in the background
- tmpfile=`mktemp ipsectestXXX`
- ip x m > $tmpfile &
- mpid=$!
+ tmpfile=`mktemp /var/run/ipsectestXXX`
+ mpid=`(ip x m > $tmpfile & echo $!) 2>/dev/null`
sleep 0.2
ipsecid="proto esp src $srcip dst $dstip spi 0x07"
check_err $?
ip x p flush
check_err $?
+ ip addr del $srcip/32 dev $devdummy
if [ $ret -ne 0 ]; then
echo "FAIL: ipsec"
echo "PASS: ipsec"
}
+#-------------------------------------------------------------------
+# Example commands
+# ip x s add proto esp src 14.0.0.52 dst 14.0.0.70 \
+# spi 0x07 mode transport reqid 0x07 replay-window 32 \
+# aead 'rfc4106(gcm(aes))' 1234567890123456dcba 128 \
+# sel src 14.0.0.52/24 dst 14.0.0.70/24
+# offload dev sim1 dir out
+# ip x p add dir out src 14.0.0.52/24 dst 14.0.0.70/24 \
+# tmpl proto esp src 14.0.0.52 dst 14.0.0.70 \
+# spi 0x07 mode transport reqid 0x07
+#
+#-------------------------------------------------------------------
+kci_test_ipsec_offload()
+{
+ ret=0
+ algo="aead rfc4106(gcm(aes)) 0x3132333435363738393031323334353664636261 128"
+ srcip=192.168.123.3
+ dstip=192.168.123.4
+ dev=simx1
+ sysfsd=/sys/kernel/debug/netdevsim/$dev
+ sysfsf=$sysfsd/ipsec
+
+ # setup netdevsim since dummydev doesn't have offload support
+ modprobe netdevsim
+ check_err $?
+ if [ $ret -ne 0 ]; then
+ echo "FAIL: ipsec_offload can't load netdevsim"
+ return 1
+ fi
+
+ ip link add $dev type netdevsim
+ ip addr add $srcip dev $dev
+ ip link set $dev up
+ if [ ! -d $sysfsd ] ; then
+ echo "FAIL: ipsec_offload can't create device $dev"
+ return 1
+ fi
+ if [ ! -f $sysfsf ] ; then
+ echo "FAIL: ipsec_offload netdevsim doesn't support IPsec offload"
+ return 1
+ fi
+
+ # flush to be sure there's nothing configured
+ ip x s flush ; ip x p flush
+
+ # create offloaded SAs, both in and out
+ ip x p add dir out src $srcip/24 dst $dstip/24 \
+ tmpl proto esp src $srcip dst $dstip spi 9 \
+ mode transport reqid 42
+ check_err $?
+ ip x p add dir out src $dstip/24 dst $srcip/24 \
+ tmpl proto esp src $dstip dst $srcip spi 9 \
+ mode transport reqid 42
+ check_err $?
+
+ ip x s add proto esp src $srcip dst $dstip spi 9 \
+ mode transport reqid 42 $algo sel src $srcip/24 dst $dstip/24 \
+ offload dev $dev dir out
+ check_err $?
+ ip x s add proto esp src $dstip dst $srcip spi 9 \
+ mode transport reqid 42 $algo sel src $dstip/24 dst $srcip/24 \
+ offload dev $dev dir in
+ check_err $?
+ if [ $ret -ne 0 ]; then
+ echo "FAIL: ipsec_offload can't create SA"
+ return 1
+ fi
+
+ # does offload show up in ip output
+ lines=`ip x s list | grep -c "crypto offload parameters: dev $dev dir"`
+ if [ $lines -ne 2 ] ; then
+ echo "FAIL: ipsec_offload SA offload missing from list output"
+ check_err 1
+ fi
+
+ # use ping to exercise the Tx path
+ ping -I $dev -c 3 -W 1 -i 0 $dstip >/dev/null
+
+ # does driver have correct offload info
+ diff $sysfsf - << EOF
+SA count=2 tx=3
+sa[0] tx ipaddr=0x00000000 00000000 00000000 00000000
+sa[0] spi=0x00000009 proto=0x32 salt=0x61626364 crypt=1
+sa[0] key=0x34333231 38373635 32313039 36353433
+sa[1] rx ipaddr=0x00000000 00000000 00000000 037ba8c0
+sa[1] spi=0x00000009 proto=0x32 salt=0x61626364 crypt=1
+sa[1] key=0x34333231 38373635 32313039 36353433
+EOF
+ if [ $? -ne 0 ] ; then
+ echo "FAIL: ipsec_offload incorrect driver data"
+ check_err 1
+ fi
+
+ # does offload get removed from driver
+ ip x s flush
+ ip x p flush
+ lines=`grep -c "SA count=0" $sysfsf`
+ if [ $lines -ne 1 ] ; then
+ echo "FAIL: ipsec_offload SA not removed from driver"
+ check_err 1
+ fi
+
+ # clean up any leftovers
+ ip link del $dev
+ rmmod netdevsim
+
+ if [ $ret -ne 0 ]; then
+ echo "FAIL: ipsec_offload"
+ return 1
+ fi
+ echo "PASS: ipsec_offload"
+}
+
kci_test_gretap()
{
testns="testns"
kci_test_encap
kci_test_macsec
kci_test_ipsec
+ kci_test_ipsec_offload
kci_del_dummy
}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+
+#include <arpa/inet.h>
+#include <errno.h>
+#include <error.h>
+#include <fcntl.h>
+#include <poll.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+#include <linux/tls.h>
+#include <linux/tcp.h>
+#include <linux/socket.h>
+
+#include <sys/types.h>
+#include <sys/sendfile.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+
+#include "../kselftest_harness.h"
+
+#define TLS_PAYLOAD_MAX_LEN 16384
+#define SOL_TLS 282
+
+FIXTURE(tls)
+{
+ int fd, cfd;
+ bool notls;
+};
+
+FIXTURE_SETUP(tls)
+{
+ struct tls12_crypto_info_aes_gcm_128 tls12;
+ struct sockaddr_in addr;
+ socklen_t len;
+ int sfd, ret;
+
+ self->notls = false;
+ len = sizeof(addr);
+
+ memset(&tls12, 0, sizeof(tls12));
+ tls12.info.version = TLS_1_2_VERSION;
+ tls12.info.cipher_type = TLS_CIPHER_AES_GCM_128;
+
+ addr.sin_family = AF_INET;
+ addr.sin_addr.s_addr = htonl(INADDR_ANY);
+ addr.sin_port = 0;
+
+ self->fd = socket(AF_INET, SOCK_STREAM, 0);
+ sfd = socket(AF_INET, SOCK_STREAM, 0);
+
+ ret = bind(sfd, &addr, sizeof(addr));
+ ASSERT_EQ(ret, 0);
+ ret = listen(sfd, 10);
+ ASSERT_EQ(ret, 0);
+
+ ret = getsockname(sfd, &addr, &len);
+ ASSERT_EQ(ret, 0);
+
+ ret = connect(self->fd, &addr, sizeof(addr));
+ ASSERT_EQ(ret, 0);
+
+ ret = setsockopt(self->fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls"));
+ if (ret != 0) {
+ self->notls = true;
+ printf("Failure setting TCP_ULP, testing without tls\n");
+ }
+
+ if (!self->notls) {
+ ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12,
+ sizeof(tls12));
+ ASSERT_EQ(ret, 0);
+ }
+
+ self->cfd = accept(sfd, &addr, &len);
+ ASSERT_GE(self->cfd, 0);
+
+ if (!self->notls) {
+ ret = setsockopt(self->cfd, IPPROTO_TCP, TCP_ULP, "tls",
+ sizeof("tls"));
+ ASSERT_EQ(ret, 0);
+
+ ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12,
+ sizeof(tls12));
+ ASSERT_EQ(ret, 0);
+ }
+
+ close(sfd);
+}
+
+FIXTURE_TEARDOWN(tls)
+{
+ close(self->fd);
+ close(self->cfd);
+}
+
+TEST_F(tls, sendfile)
+{
+ int filefd = open("/proc/self/exe", O_RDONLY);
+ struct stat st;
+
+ EXPECT_GE(filefd, 0);
+ fstat(filefd, &st);
+ EXPECT_GE(sendfile(self->fd, filefd, 0, st.st_size), 0);
+}
+
+TEST_F(tls, send_then_sendfile)
+{
+ int filefd = open("/proc/self/exe", O_RDONLY);
+ char const *test_str = "test_send";
+ int to_send = strlen(test_str) + 1;
+ char recv_buf[10];
+ struct stat st;
+ char *buf;
+
+ EXPECT_GE(filefd, 0);
+ fstat(filefd, &st);
+ buf = (char *)malloc(st.st_size);
+
+ EXPECT_EQ(send(self->fd, test_str, to_send, 0), to_send);
+ EXPECT_EQ(recv(self->cfd, recv_buf, to_send, 0), to_send);
+ EXPECT_EQ(memcmp(test_str, recv_buf, to_send), 0);
+
+ EXPECT_GE(sendfile(self->fd, filefd, 0, st.st_size), 0);
+ EXPECT_EQ(recv(self->cfd, buf, st.st_size, 0), st.st_size);
+}
+
+TEST_F(tls, recv_max)
+{
+ unsigned int send_len = TLS_PAYLOAD_MAX_LEN;
+ char recv_mem[TLS_PAYLOAD_MAX_LEN];
+ char buf[TLS_PAYLOAD_MAX_LEN];
+
+ EXPECT_GE(send(self->fd, buf, send_len, 0), 0);
+ EXPECT_NE(recv(self->cfd, recv_mem, send_len, 0), -1);
+ EXPECT_EQ(memcmp(buf, recv_mem, send_len), 0);
+}
+
+TEST_F(tls, recv_small)
+{
+ char const *test_str = "test_read";
+ int send_len = 10;
+ char buf[10];
+
+ send_len = strlen(test_str) + 1;
+ EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+ EXPECT_NE(recv(self->cfd, buf, send_len, 0), -1);
+ EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
+}
+
+TEST_F(tls, msg_more)
+{
+ char const *test_str = "test_read";
+ int send_len = 10;
+ char buf[10 * 2];
+
+ EXPECT_EQ(send(self->fd, test_str, send_len, MSG_MORE), send_len);
+ EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_DONTWAIT), -1);
+ EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+ EXPECT_EQ(recv(self->cfd, buf, send_len * 2, MSG_DONTWAIT),
+ send_len * 2);
+ EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
+}
+
+TEST_F(tls, sendmsg_single)
+{
+ struct msghdr msg;
+
+ char const *test_str = "test_sendmsg";
+ size_t send_len = 13;
+ struct iovec vec;
+ char buf[13];
+
+ vec.iov_base = (char *)test_str;
+ vec.iov_len = send_len;
+ memset(&msg, 0, sizeof(struct msghdr));
+ msg.msg_iov = &vec;
+ msg.msg_iovlen = 1;
+ EXPECT_EQ(sendmsg(self->fd, &msg, 0), send_len);
+ EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len);
+ EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
+}
+
+TEST_F(tls, sendmsg_large)
+{
+ void *mem = malloc(16384);
+ size_t send_len = 16384;
+ size_t sends = 128;
+ struct msghdr msg;
+ size_t recvs = 0;
+ size_t sent = 0;
+
+ memset(&msg, 0, sizeof(struct msghdr));
+ while (sent++ < sends) {
+ struct iovec vec = { (void *)mem, send_len };
+
+ msg.msg_iov = &vec;
+ msg.msg_iovlen = 1;
+ EXPECT_EQ(sendmsg(self->cfd, &msg, 0), send_len);
+ }
+
+ while (recvs++ < sends)
+ EXPECT_NE(recv(self->fd, mem, send_len, 0), -1);
+
+ free(mem);
+}
+
+TEST_F(tls, sendmsg_multiple)
+{
+ char const *test_str = "test_sendmsg_multiple";
+ struct iovec vec[5];
+ char *test_strs[5];
+ struct msghdr msg;
+ int total_len = 0;
+ int len_cmp = 0;
+ int iov_len = 5;
+ char *buf;
+ int i;
+
+ memset(&msg, 0, sizeof(struct msghdr));
+ for (i = 0; i < iov_len; i++) {
+ test_strs[i] = (char *)malloc(strlen(test_str) + 1);
+ snprintf(test_strs[i], strlen(test_str) + 1, "%s", test_str);
+ vec[i].iov_base = (void *)test_strs[i];
+ vec[i].iov_len = strlen(test_strs[i]) + 1;
+ total_len += vec[i].iov_len;
+ }
+ msg.msg_iov = vec;
+ msg.msg_iovlen = iov_len;
+
+ EXPECT_EQ(sendmsg(self->cfd, &msg, 0), total_len);
+ buf = malloc(total_len);
+ EXPECT_NE(recv(self->fd, buf, total_len, 0), -1);
+ for (i = 0; i < iov_len; i++) {
+ EXPECT_EQ(memcmp(test_strs[i], buf + len_cmp,
+ strlen(test_strs[i])),
+ 0);
+ len_cmp += strlen(buf + len_cmp) + 1;
+ }
+ for (i = 0; i < iov_len; i++)
+ free(test_strs[i]);
+ free(buf);
+}
+
+TEST_F(tls, sendmsg_multiple_stress)
+{
+ char const *test_str = "abcdefghijklmno";
+ struct iovec vec[1024];
+ char *test_strs[1024];
+ int iov_len = 1024;
+ int total_len = 0;
+ char buf[1 << 14];
+ struct msghdr msg;
+ int len_cmp = 0;
+ int i;
+
+ memset(&msg, 0, sizeof(struct msghdr));
+ for (i = 0; i < iov_len; i++) {
+ test_strs[i] = (char *)malloc(strlen(test_str) + 1);
+ snprintf(test_strs[i], strlen(test_str) + 1, "%s", test_str);
+ vec[i].iov_base = (void *)test_strs[i];
+ vec[i].iov_len = strlen(test_strs[i]) + 1;
+ total_len += vec[i].iov_len;
+ }
+ msg.msg_iov = vec;
+ msg.msg_iovlen = iov_len;
+
+ EXPECT_EQ(sendmsg(self->fd, &msg, 0), total_len);
+ EXPECT_NE(recv(self->cfd, buf, total_len, 0), -1);
+
+ for (i = 0; i < iov_len; i++)
+ len_cmp += strlen(buf + len_cmp) + 1;
+
+ for (i = 0; i < iov_len; i++)
+ free(test_strs[i]);
+}
+
+TEST_F(tls, splice_from_pipe)
+{
+ int send_len = TLS_PAYLOAD_MAX_LEN;
+ char mem_send[TLS_PAYLOAD_MAX_LEN];
+ char mem_recv[TLS_PAYLOAD_MAX_LEN];
+ int p[2];
+
+ ASSERT_GE(pipe(p), 0);
+ EXPECT_GE(write(p[1], mem_send, send_len), 0);
+ EXPECT_GE(splice(p[0], NULL, self->fd, NULL, send_len, 0), 0);
+ EXPECT_GE(recv(self->cfd, mem_recv, send_len, 0), 0);
+ EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0);
+}
+
+TEST_F(tls, splice_from_pipe2)
+{
+ int send_len = 16000;
+ char mem_send[16000];
+ char mem_recv[16000];
+ int p2[2];
+ int p[2];
+
+ ASSERT_GE(pipe(p), 0);
+ ASSERT_GE(pipe(p2), 0);
+ EXPECT_GE(write(p[1], mem_send, 8000), 0);
+ EXPECT_GE(splice(p[0], NULL, self->fd, NULL, 8000, 0), 0);
+ EXPECT_GE(write(p2[1], mem_send + 8000, 8000), 0);
+ EXPECT_GE(splice(p2[0], NULL, self->fd, NULL, 8000, 0), 0);
+ EXPECT_GE(recv(self->cfd, mem_recv, send_len, 0), 0);
+ EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0);
+}
+
+TEST_F(tls, send_and_splice)
+{
+ int send_len = TLS_PAYLOAD_MAX_LEN;
+ char mem_send[TLS_PAYLOAD_MAX_LEN];
+ char mem_recv[TLS_PAYLOAD_MAX_LEN];
+ char const *test_str = "test_read";
+ int send_len2 = 10;
+ char buf[10];
+ int p[2];
+
+ ASSERT_GE(pipe(p), 0);
+ EXPECT_EQ(send(self->fd, test_str, send_len2, 0), send_len2);
+ EXPECT_NE(recv(self->cfd, buf, send_len2, 0), -1);
+ EXPECT_EQ(memcmp(test_str, buf, send_len2), 0);
+
+ EXPECT_GE(write(p[1], mem_send, send_len), send_len);
+ EXPECT_GE(splice(p[0], NULL, self->fd, NULL, send_len, 0), send_len);
+
+ EXPECT_GE(recv(self->cfd, mem_recv, send_len, 0), 0);
+ EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0);
+}
+
+TEST_F(tls, splice_to_pipe)
+{
+ int send_len = TLS_PAYLOAD_MAX_LEN;
+ char mem_send[TLS_PAYLOAD_MAX_LEN];
+ char mem_recv[TLS_PAYLOAD_MAX_LEN];
+ int p[2];
+
+ ASSERT_GE(pipe(p), 0);
+ EXPECT_GE(send(self->fd, mem_send, send_len, 0), 0);
+ EXPECT_GE(splice(self->cfd, NULL, p[1], NULL, send_len, 0), 0);
+ EXPECT_GE(read(p[0], mem_recv, send_len), 0);
+ EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0);
+}
+
+TEST_F(tls, recvmsg_single)
+{
+ char const *test_str = "test_recvmsg_single";
+ int send_len = strlen(test_str) + 1;
+ char buf[20];
+ struct msghdr hdr;
+ struct iovec vec;
+
+ memset(&hdr, 0, sizeof(hdr));
+ EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+ vec.iov_base = (char *)buf;
+ vec.iov_len = send_len;
+ hdr.msg_iovlen = 1;
+ hdr.msg_iov = &vec;
+ EXPECT_NE(recvmsg(self->cfd, &hdr, 0), -1);
+ EXPECT_EQ(memcmp(test_str, buf, send_len), 0);
+}
+
+TEST_F(tls, recvmsg_single_max)
+{
+ int send_len = TLS_PAYLOAD_MAX_LEN;
+ char send_mem[TLS_PAYLOAD_MAX_LEN];
+ char recv_mem[TLS_PAYLOAD_MAX_LEN];
+ struct iovec vec;
+ struct msghdr hdr;
+
+ EXPECT_EQ(send(self->fd, send_mem, send_len, 0), send_len);
+ vec.iov_base = (char *)recv_mem;
+ vec.iov_len = TLS_PAYLOAD_MAX_LEN;
+
+ hdr.msg_iovlen = 1;
+ hdr.msg_iov = &vec;
+ EXPECT_NE(recvmsg(self->cfd, &hdr, 0), -1);
+ EXPECT_EQ(memcmp(send_mem, recv_mem, send_len), 0);
+}
+
+TEST_F(tls, recvmsg_multiple)
+{
+ unsigned int msg_iovlen = 1024;
+ unsigned int len_compared = 0;
+ struct iovec vec[1024];
+ char *iov_base[1024];
+ unsigned int iov_len = 16;
+ int send_len = 1 << 14;
+ char buf[1 << 14];
+ struct msghdr hdr;
+ int i;
+
+ EXPECT_EQ(send(self->fd, buf, send_len, 0), send_len);
+ for (i = 0; i < msg_iovlen; i++) {
+ iov_base[i] = (char *)malloc(iov_len);
+ vec[i].iov_base = iov_base[i];
+ vec[i].iov_len = iov_len;
+ }
+
+ hdr.msg_iovlen = msg_iovlen;
+ hdr.msg_iov = vec;
+ EXPECT_NE(recvmsg(self->cfd, &hdr, 0), -1);
+ for (i = 0; i < msg_iovlen; i++)
+ len_compared += iov_len;
+
+ for (i = 0; i < msg_iovlen; i++)
+ free(iov_base[i]);
+}
+
+TEST_F(tls, single_send_multiple_recv)
+{
+ unsigned int total_len = TLS_PAYLOAD_MAX_LEN * 2;
+ unsigned int send_len = TLS_PAYLOAD_MAX_LEN;
+ char send_mem[TLS_PAYLOAD_MAX_LEN * 2];
+ char recv_mem[TLS_PAYLOAD_MAX_LEN * 2];
+
+ EXPECT_GE(send(self->fd, send_mem, total_len, 0), 0);
+ memset(recv_mem, 0, total_len);
+
+ EXPECT_NE(recv(self->cfd, recv_mem, send_len, 0), -1);
+ EXPECT_NE(recv(self->cfd, recv_mem + send_len, send_len, 0), -1);
+ EXPECT_EQ(memcmp(send_mem, recv_mem, total_len), 0);
+}
+
+TEST_F(tls, multiple_send_single_recv)
+{
+ unsigned int total_len = 2 * 10;
+ unsigned int send_len = 10;
+ char recv_mem[2 * 10];
+ char send_mem[10];
+
+ EXPECT_GE(send(self->fd, send_mem, send_len, 0), 0);
+ EXPECT_GE(send(self->fd, send_mem, send_len, 0), 0);
+ memset(recv_mem, 0, total_len);
+ EXPECT_EQ(recv(self->cfd, recv_mem, total_len, 0), total_len);
+
+ EXPECT_EQ(memcmp(send_mem, recv_mem, send_len), 0);
+ EXPECT_EQ(memcmp(send_mem, recv_mem + send_len, send_len), 0);
+}
+
+TEST_F(tls, recv_partial)
+{
+ char const *test_str = "test_read_partial";
+ char const *test_str_first = "test_read";
+ char const *test_str_second = "_partial";
+ int send_len = strlen(test_str) + 1;
+ char recv_mem[18];
+
+ memset(recv_mem, 0, sizeof(recv_mem));
+ EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+ EXPECT_NE(recv(self->cfd, recv_mem, strlen(test_str_first), 0), -1);
+ EXPECT_EQ(memcmp(test_str_first, recv_mem, strlen(test_str_first)), 0);
+ memset(recv_mem, 0, sizeof(recv_mem));
+ EXPECT_NE(recv(self->cfd, recv_mem, strlen(test_str_second), 0), -1);
+ EXPECT_EQ(memcmp(test_str_second, recv_mem, strlen(test_str_second)),
+ 0);
+}
+
+TEST_F(tls, recv_nonblock)
+{
+ char buf[4096];
+ bool err;
+
+ EXPECT_EQ(recv(self->cfd, buf, sizeof(buf), MSG_DONTWAIT), -1);
+ err = (errno == EAGAIN || errno == EWOULDBLOCK);
+ EXPECT_EQ(err, true);
+}
+
+TEST_F(tls, recv_peek)
+{
+ char const *test_str = "test_read_peek";
+ int send_len = strlen(test_str) + 1;
+ char buf[15];
+
+ EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+ EXPECT_NE(recv(self->cfd, buf, send_len, MSG_PEEK), -1);
+ EXPECT_EQ(memcmp(test_str, buf, send_len), 0);
+ memset(buf, 0, sizeof(buf));
+ EXPECT_NE(recv(self->cfd, buf, send_len, 0), -1);
+ EXPECT_EQ(memcmp(test_str, buf, send_len), 0);
+}
+
+TEST_F(tls, recv_peek_multiple)
+{
+ char const *test_str = "test_read_peek";
+ int send_len = strlen(test_str) + 1;
+ unsigned int num_peeks = 100;
+ char buf[15];
+ int i;
+
+ EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+ for (i = 0; i < num_peeks; i++) {
+ EXPECT_NE(recv(self->cfd, buf, send_len, MSG_PEEK), -1);
+ EXPECT_EQ(memcmp(test_str, buf, send_len), 0);
+ memset(buf, 0, sizeof(buf));
+ }
+ EXPECT_NE(recv(self->cfd, buf, send_len, 0), -1);
+ EXPECT_EQ(memcmp(test_str, buf, send_len), 0);
+}
+
+TEST_F(tls, pollin)
+{
+ char const *test_str = "test_poll";
+ struct pollfd fd = { 0, 0, 0 };
+ char buf[10];
+ int send_len = 10;
+
+ EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+ fd.fd = self->cfd;
+ fd.events = POLLIN;
+
+ EXPECT_EQ(poll(&fd, 1, 20), 1);
+ EXPECT_EQ(fd.revents & POLLIN, 1);
+ EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len);
+ /* Test timing out */
+ EXPECT_EQ(poll(&fd, 1, 20), 0);
+}
+
+TEST_F(tls, poll_wait)
+{
+ char const *test_str = "test_poll_wait";
+ int send_len = strlen(test_str) + 1;
+ struct pollfd fd = { 0, 0, 0 };
+ char recv_mem[15];
+
+ fd.fd = self->cfd;
+ fd.events = POLLIN;
+ EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+ /* Set timeout to inf. secs */
+ EXPECT_EQ(poll(&fd, 1, -1), 1);
+ EXPECT_EQ(fd.revents & POLLIN, 1);
+ EXPECT_EQ(recv(self->cfd, recv_mem, send_len, 0), send_len);
+}
+
+TEST_F(tls, blocking)
+{
+ size_t data = 100000;
+ int res = fork();
+
+ EXPECT_NE(res, -1);
+
+ if (res) {
+ /* parent */
+ size_t left = data;
+ char buf[16384];
+ int status;
+ int pid2;
+
+ while (left) {
+ int res = send(self->fd, buf,
+ left > 16384 ? 16384 : left, 0);
+
+ EXPECT_GE(res, 0);
+ left -= res;
+ }
+
+ pid2 = wait(&status);
+ EXPECT_EQ(status, 0);
+ EXPECT_EQ(res, pid2);
+ } else {
+ /* child */
+ size_t left = data;
+ char buf[16384];
+
+ while (left) {
+ int res = recv(self->cfd, buf,
+ left > 16384 ? 16384 : left, 0);
+
+ EXPECT_GE(res, 0);
+ left -= res;
+ }
+ }
+}
+
+TEST_F(tls, nonblocking)
+{
+ size_t data = 100000;
+ int sendbuf = 100;
+ int flags;
+ int res;
+
+ flags = fcntl(self->fd, F_GETFL, 0);
+ fcntl(self->fd, F_SETFL, flags | O_NONBLOCK);
+ fcntl(self->cfd, F_SETFL, flags | O_NONBLOCK);
+
+ /* Ensure nonblocking behavior by imposing a small send
+ * buffer.
+ */
+ EXPECT_EQ(setsockopt(self->fd, SOL_SOCKET, SO_SNDBUF,
+ &sendbuf, sizeof(sendbuf)), 0);
+
+ res = fork();
+ EXPECT_NE(res, -1);
+
+ if (res) {
+ /* parent */
+ bool eagain = false;
+ size_t left = data;
+ char buf[16384];
+ int status;
+ int pid2;
+
+ while (left) {
+ int res = send(self->fd, buf,
+ left > 16384 ? 16384 : left, 0);
+
+ if (res == -1 && errno == EAGAIN) {
+ eagain = true;
+ usleep(10000);
+ continue;
+ }
+ EXPECT_GE(res, 0);
+ left -= res;
+ }
+
+ EXPECT_TRUE(eagain);
+ pid2 = wait(&status);
+
+ EXPECT_EQ(status, 0);
+ EXPECT_EQ(res, pid2);
+ } else {
+ /* child */
+ bool eagain = false;
+ size_t left = data;
+ char buf[16384];
+
+ while (left) {
+ int res = recv(self->cfd, buf,
+ left > 16384 ? 16384 : left, 0);
+
+ if (res == -1 && errno == EAGAIN) {
+ eagain = true;
+ usleep(10000);
+ continue;
+ }
+ EXPECT_GE(res, 0);
+ left -= res;
+ }
+ EXPECT_TRUE(eagain);
+ }
+}
+
+TEST_F(tls, control_msg)
+{
+ if (self->notls)
+ return;
+
+ char cbuf[CMSG_SPACE(sizeof(char))];
+ char const *test_str = "test_read";
+ int cmsg_len = sizeof(char);
+ char record_type = 100;
+ struct cmsghdr *cmsg;
+ struct msghdr msg;
+ int send_len = 10;
+ struct iovec vec;
+ char buf[10];
+
+ vec.iov_base = (char *)test_str;
+ vec.iov_len = 10;
+ memset(&msg, 0, sizeof(struct msghdr));
+ msg.msg_iov = &vec;
+ msg.msg_iovlen = 1;
+ msg.msg_control = cbuf;
+ msg.msg_controllen = sizeof(cbuf);
+ cmsg = CMSG_FIRSTHDR(&msg);
+ cmsg->cmsg_level = SOL_TLS;
+ /* test sending non-record types. */
+ cmsg->cmsg_type = TLS_SET_RECORD_TYPE;
+ cmsg->cmsg_len = CMSG_LEN(cmsg_len);
+ *CMSG_DATA(cmsg) = record_type;
+ msg.msg_controllen = cmsg->cmsg_len;
+
+ EXPECT_EQ(sendmsg(self->fd, &msg, 0), send_len);
+ /* Should fail because we didn't provide a control message */
+ EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1);
+
+ vec.iov_base = buf;
+ EXPECT_EQ(recvmsg(self->cfd, &msg, 0), send_len);
+ cmsg = CMSG_FIRSTHDR(&msg);
+ EXPECT_NE(cmsg, NULL);
+ EXPECT_EQ(cmsg->cmsg_level, SOL_TLS);
+ EXPECT_EQ(cmsg->cmsg_type, TLS_GET_RECORD_TYPE);
+ record_type = *((unsigned char *)CMSG_DATA(cmsg));
+ EXPECT_EQ(record_type, 100);
+ EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
+}
+
+TEST_HARNESS_MAIN
#
# Released under the terms of the GPL v2.
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
. ./common_tests
if [ -e $REBOOT_FLAG ]; then
rm $REBOOT_FLAG
else
prlog "pstore_crash_test has not been executed yet. we skip further tests."
- exit 0
+ exit $ksft_skip
fi
prlog -n "Mounting pstore filesystem ... "
"subic. %%" INJECT_ASM_REG ", %%" INJECT_ASM_REG ", 1\n\t" \
"bne 222b\n\t" \
"333:\n\t"
+
+#elif defined(__mips__)
+
+#define RSEQ_INJECT_INPUT \
+ , [loop_cnt_1]"m"(loop_cnt[1]) \
+ , [loop_cnt_2]"m"(loop_cnt[2]) \
+ , [loop_cnt_3]"m"(loop_cnt[3]) \
+ , [loop_cnt_4]"m"(loop_cnt[4]) \
+ , [loop_cnt_5]"m"(loop_cnt[5]) \
+ , [loop_cnt_6]"m"(loop_cnt[6])
+
+#define INJECT_ASM_REG "$5"
+
+#define RSEQ_INJECT_CLOBBER \
+ , INJECT_ASM_REG
+
+#define RSEQ_INJECT_ASM(n) \
+ "lw " INJECT_ASM_REG ", %[loop_cnt_" #n "]\n\t" \
+ "beqz " INJECT_ASM_REG ", 333f\n\t" \
+ "222:\n\t" \
+ "addiu " INJECT_ASM_REG ", -1\n\t" \
+ "bnez " INJECT_ASM_REG ", 222b\n\t" \
+ "333:\n\t"
+
#else
#error unsupported target
#endif
#define __RSEQ_ASM_DEFINE_ABORT(table_label, label, teardown, \
abort_label, version, flags, \
start_ip, post_commit_offset, abort_ip) \
+ ".balign 32\n\t" \
__rseq_str(table_label) ":\n\t" \
".word " __rseq_str(version) ", " __rseq_str(flags) "\n\t" \
".word " __rseq_str(start_ip) ", 0x0, " __rseq_str(post_commit_offset) ", 0x0, " __rseq_str(abort_ip) ", 0x0\n\t" \
--- /dev/null
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * Author: Paul Burton <paul.burton@mips.com>
+ * (C) Copyright 2018 MIPS Tech LLC
+ *
+ * Based on rseq-arm.h:
+ * (C) Copyright 2016-2018 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+#define RSEQ_SIG 0x53053053
+
+#define rseq_smp_mb() __asm__ __volatile__ ("sync" ::: "memory")
+#define rseq_smp_rmb() rseq_smp_mb()
+#define rseq_smp_wmb() rseq_smp_mb()
+
+#define rseq_smp_load_acquire(p) \
+__extension__ ({ \
+ __typeof(*p) ____p1 = RSEQ_READ_ONCE(*p); \
+ rseq_smp_mb(); \
+ ____p1; \
+})
+
+#define rseq_smp_acquire__after_ctrl_dep() rseq_smp_rmb()
+
+#define rseq_smp_store_release(p, v) \
+do { \
+ rseq_smp_mb(); \
+ RSEQ_WRITE_ONCE(*p, v); \
+} while (0)
+
+#ifdef RSEQ_SKIP_FASTPATH
+#include "rseq-skip.h"
+#else /* !RSEQ_SKIP_FASTPATH */
+
+#if _MIPS_SZLONG == 64
+# define LONG ".dword"
+# define LONG_LA "dla"
+# define LONG_L "ld"
+# define LONG_S "sd"
+# define LONG_ADDI "daddiu"
+# define U32_U64_PAD(x) x
+#elif _MIPS_SZLONG == 32
+# define LONG ".word"
+# define LONG_LA "la"
+# define LONG_L "lw"
+# define LONG_S "sw"
+# define LONG_ADDI "addiu"
+# ifdef __BIG_ENDIAN
+# define U32_U64_PAD(x) "0x0, " x
+# else
+# define U32_U64_PAD(x) x ", 0x0"
+# endif
+#else
+# error unsupported _MIPS_SZLONG
+#endif
+
+#define __RSEQ_ASM_DEFINE_TABLE(version, flags, start_ip, \
+ post_commit_offset, abort_ip) \
+ ".pushsection __rseq_table, \"aw\"\n\t" \
+ ".balign 32\n\t" \
+ ".word " __rseq_str(version) ", " __rseq_str(flags) "\n\t" \
+ LONG " " U32_U64_PAD(__rseq_str(start_ip)) "\n\t" \
+ LONG " " U32_U64_PAD(__rseq_str(post_commit_offset)) "\n\t" \
+ LONG " " U32_U64_PAD(__rseq_str(abort_ip)) "\n\t" \
+ ".popsection\n\t"
+
+#define RSEQ_ASM_DEFINE_TABLE(start_ip, post_commit_ip, abort_ip) \
+ __RSEQ_ASM_DEFINE_TABLE(0x0, 0x0, start_ip, \
+ (post_commit_ip - start_ip), abort_ip)
+
+#define RSEQ_ASM_STORE_RSEQ_CS(label, cs_label, rseq_cs) \
+ RSEQ_INJECT_ASM(1) \
+ LONG_LA " $4, " __rseq_str(cs_label) "\n\t" \
+ LONG_S " $4, %[" __rseq_str(rseq_cs) "]\n\t" \
+ __rseq_str(label) ":\n\t"
+
+#define RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, label) \
+ RSEQ_INJECT_ASM(2) \
+ "lw $4, %[" __rseq_str(current_cpu_id) "]\n\t" \
+ "bne $4, %[" __rseq_str(cpu_id) "], " __rseq_str(label) "\n\t"
+
+#define __RSEQ_ASM_DEFINE_ABORT(table_label, label, teardown, \
+ abort_label, version, flags, \
+ start_ip, post_commit_offset, abort_ip) \
+ ".balign 32\n\t" \
+ __rseq_str(table_label) ":\n\t" \
+ ".word " __rseq_str(version) ", " __rseq_str(flags) "\n\t" \
+ LONG " " U32_U64_PAD(__rseq_str(start_ip)) "\n\t" \
+ LONG " " U32_U64_PAD(__rseq_str(post_commit_offset)) "\n\t" \
+ LONG " " U32_U64_PAD(__rseq_str(abort_ip)) "\n\t" \
+ ".word " __rseq_str(RSEQ_SIG) "\n\t" \
+ __rseq_str(label) ":\n\t" \
+ teardown \
+ "b %l[" __rseq_str(abort_label) "]\n\t"
+
+#define RSEQ_ASM_DEFINE_ABORT(table_label, label, teardown, abort_label, \
+ start_ip, post_commit_ip, abort_ip) \
+ __RSEQ_ASM_DEFINE_ABORT(table_label, label, teardown, \
+ abort_label, 0x0, 0x0, start_ip, \
+ (post_commit_ip - start_ip), abort_ip)
+
+#define RSEQ_ASM_DEFINE_CMPFAIL(label, teardown, cmpfail_label) \
+ __rseq_str(label) ":\n\t" \
+ teardown \
+ "b %l[" __rseq_str(cmpfail_label) "]\n\t"
+
+#define rseq_workaround_gcc_asm_size_guess() __asm__ __volatile__("")
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
+{
+ RSEQ_INJECT_C(9)
+
+ rseq_workaround_gcc_asm_size_guess();
+ __asm__ __volatile__ goto (
+ RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */
+ /* Start rseq by storing table entry pointer into rseq_cs. */
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs)
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+ RSEQ_INJECT_ASM(3)
+ LONG_L " $4, %[v]\n\t"
+ "bne $4, %[expect], %l[cmpfail]\n\t"
+ RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+ LONG_L " $4, %[v]\n\t"
+ "bne $4, %[expect], %l[error2]\n\t"
+#endif
+ /* final store */
+ LONG_S " %[newv], %[v]\n\t"
+ "2:\n\t"
+ RSEQ_INJECT_ASM(5)
+ "b 5f\n\t"
+ RSEQ_ASM_DEFINE_ABORT(3, 4, "", abort, 1b, 2b, 4f)
+ "5:\n\t"
+ : /* gcc asm goto does not allow outputs */
+ : [cpu_id] "r" (cpu),
+ [current_cpu_id] "m" (__rseq_abi.cpu_id),
+ [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [v] "m" (*v),
+ [expect] "r" (expect),
+ [newv] "r" (newv)
+ RSEQ_INJECT_INPUT
+ : "$4", "memory"
+ RSEQ_INJECT_CLOBBER
+ : abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+ , error1, error2
+#endif
+ );
+ rseq_workaround_gcc_asm_size_guess();
+ return 0;
+abort:
+ rseq_workaround_gcc_asm_size_guess();
+ RSEQ_INJECT_FAILED
+ return -1;
+cmpfail:
+ rseq_workaround_gcc_asm_size_guess();
+ return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+ rseq_bug("cpu_id comparison failed");
+error2:
+ rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
+ off_t voffp, intptr_t *load, int cpu)
+{
+ RSEQ_INJECT_C(9)
+
+ rseq_workaround_gcc_asm_size_guess();
+ __asm__ __volatile__ goto (
+ RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */
+ /* Start rseq by storing table entry pointer into rseq_cs. */
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs)
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+ RSEQ_INJECT_ASM(3)
+ LONG_L " $4, %[v]\n\t"
+ "beq $4, %[expectnot], %l[cmpfail]\n\t"
+ RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+ LONG_L " $4, %[v]\n\t"
+ "beq $4, %[expectnot], %l[error2]\n\t"
+#endif
+ LONG_S " $4, %[load]\n\t"
+ LONG_ADDI " $4, %[voffp]\n\t"
+ LONG_L " $4, 0($4)\n\t"
+ /* final store */
+ LONG_S " $4, %[v]\n\t"
+ "2:\n\t"
+ RSEQ_INJECT_ASM(5)
+ "b 5f\n\t"
+ RSEQ_ASM_DEFINE_ABORT(3, 4, "", abort, 1b, 2b, 4f)
+ "5:\n\t"
+ : /* gcc asm goto does not allow outputs */
+ : [cpu_id] "r" (cpu),
+ [current_cpu_id] "m" (__rseq_abi.cpu_id),
+ [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ /* final store input */
+ [v] "m" (*v),
+ [expectnot] "r" (expectnot),
+ [voffp] "Ir" (voffp),
+ [load] "m" (*load)
+ RSEQ_INJECT_INPUT
+ : "$4", "memory"
+ RSEQ_INJECT_CLOBBER
+ : abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+ , error1, error2
+#endif
+ );
+ rseq_workaround_gcc_asm_size_guess();
+ return 0;
+abort:
+ rseq_workaround_gcc_asm_size_guess();
+ RSEQ_INJECT_FAILED
+ return -1;
+cmpfail:
+ rseq_workaround_gcc_asm_size_guess();
+ return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+ rseq_bug("cpu_id comparison failed");
+error2:
+ rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_addv(intptr_t *v, intptr_t count, int cpu)
+{
+ RSEQ_INJECT_C(9)
+
+ rseq_workaround_gcc_asm_size_guess();
+ __asm__ __volatile__ goto (
+ RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */
+ /* Start rseq by storing table entry pointer into rseq_cs. */
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs)
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+ RSEQ_INJECT_ASM(3)
+#ifdef RSEQ_COMPARE_TWICE
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+#endif
+ LONG_L " $4, %[v]\n\t"
+ LONG_ADDI " $4, %[count]\n\t"
+ /* final store */
+ LONG_S " $4, %[v]\n\t"
+ "2:\n\t"
+ RSEQ_INJECT_ASM(4)
+ "b 5f\n\t"
+ RSEQ_ASM_DEFINE_ABORT(3, 4, "", abort, 1b, 2b, 4f)
+ "5:\n\t"
+ : /* gcc asm goto does not allow outputs */
+ : [cpu_id] "r" (cpu),
+ [current_cpu_id] "m" (__rseq_abi.cpu_id),
+ [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [v] "m" (*v),
+ [count] "Ir" (count)
+ RSEQ_INJECT_INPUT
+ : "$4", "memory"
+ RSEQ_INJECT_CLOBBER
+ : abort
+#ifdef RSEQ_COMPARE_TWICE
+ , error1
+#endif
+ );
+ rseq_workaround_gcc_asm_size_guess();
+ return 0;
+abort:
+ rseq_workaround_gcc_asm_size_guess();
+ RSEQ_INJECT_FAILED
+ return -1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+ rseq_bug("cpu_id comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
+ intptr_t *v2, intptr_t newv2,
+ intptr_t newv, int cpu)
+{
+ RSEQ_INJECT_C(9)
+
+ rseq_workaround_gcc_asm_size_guess();
+ __asm__ __volatile__ goto (
+ RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */
+ /* Start rseq by storing table entry pointer into rseq_cs. */
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs)
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+ RSEQ_INJECT_ASM(3)
+ LONG_L " $4, %[v]\n\t"
+ "bne $4, %[expect], %l[cmpfail]\n\t"
+ RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+ LONG_L " $4, %[v]\n\t"
+ "bne $4, %[expect], %l[error2]\n\t"
+#endif
+ /* try store */
+ LONG_S " %[newv2], %[v2]\n\t"
+ RSEQ_INJECT_ASM(5)
+ /* final store */
+ LONG_S " %[newv], %[v]\n\t"
+ "2:\n\t"
+ RSEQ_INJECT_ASM(6)
+ "b 5f\n\t"
+ RSEQ_ASM_DEFINE_ABORT(3, 4, "", abort, 1b, 2b, 4f)
+ "5:\n\t"
+ : /* gcc asm goto does not allow outputs */
+ : [cpu_id] "r" (cpu),
+ [current_cpu_id] "m" (__rseq_abi.cpu_id),
+ [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ /* try store input */
+ [v2] "m" (*v2),
+ [newv2] "r" (newv2),
+ /* final store input */
+ [v] "m" (*v),
+ [expect] "r" (expect),
+ [newv] "r" (newv)
+ RSEQ_INJECT_INPUT
+ : "$4", "memory"
+ RSEQ_INJECT_CLOBBER
+ : abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+ , error1, error2
+#endif
+ );
+ rseq_workaround_gcc_asm_size_guess();
+ return 0;
+abort:
+ rseq_workaround_gcc_asm_size_guess();
+ RSEQ_INJECT_FAILED
+ return -1;
+cmpfail:
+ rseq_workaround_gcc_asm_size_guess();
+ return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+ rseq_bug("cpu_id comparison failed");
+error2:
+ rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
+ intptr_t *v2, intptr_t newv2,
+ intptr_t newv, int cpu)
+{
+ RSEQ_INJECT_C(9)
+
+ rseq_workaround_gcc_asm_size_guess();
+ __asm__ __volatile__ goto (
+ RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */
+ /* Start rseq by storing table entry pointer into rseq_cs. */
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs)
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+ RSEQ_INJECT_ASM(3)
+ LONG_L " $4, %[v]\n\t"
+ "bne $4, %[expect], %l[cmpfail]\n\t"
+ RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+ LONG_L " $4, %[v]\n\t"
+ "bne $4, %[expect], %l[error2]\n\t"
+#endif
+ /* try store */
+ LONG_S " %[newv2], %[v2]\n\t"
+ RSEQ_INJECT_ASM(5)
+ "sync\n\t" /* full sync provides store-release */
+ /* final store */
+ LONG_S " %[newv], %[v]\n\t"
+ "2:\n\t"
+ RSEQ_INJECT_ASM(6)
+ "b 5f\n\t"
+ RSEQ_ASM_DEFINE_ABORT(3, 4, "", abort, 1b, 2b, 4f)
+ "5:\n\t"
+ : /* gcc asm goto does not allow outputs */
+ : [cpu_id] "r" (cpu),
+ [current_cpu_id] "m" (__rseq_abi.cpu_id),
+ [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ /* try store input */
+ [v2] "m" (*v2),
+ [newv2] "r" (newv2),
+ /* final store input */
+ [v] "m" (*v),
+ [expect] "r" (expect),
+ [newv] "r" (newv)
+ RSEQ_INJECT_INPUT
+ : "$4", "memory"
+ RSEQ_INJECT_CLOBBER
+ : abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+ , error1, error2
+#endif
+ );
+ rseq_workaround_gcc_asm_size_guess();
+ return 0;
+abort:
+ rseq_workaround_gcc_asm_size_guess();
+ RSEQ_INJECT_FAILED
+ return -1;
+cmpfail:
+ rseq_workaround_gcc_asm_size_guess();
+ return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+ rseq_bug("cpu_id comparison failed");
+error2:
+ rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
+ intptr_t *v2, intptr_t expect2,
+ intptr_t newv, int cpu)
+{
+ RSEQ_INJECT_C(9)
+
+ rseq_workaround_gcc_asm_size_guess();
+ __asm__ __volatile__ goto (
+ RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */
+ /* Start rseq by storing table entry pointer into rseq_cs. */
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs)
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+ RSEQ_INJECT_ASM(3)
+ LONG_L " $4, %[v]\n\t"
+ "bne $4, %[expect], %l[cmpfail]\n\t"
+ RSEQ_INJECT_ASM(4)
+ LONG_L " $4, %[v2]\n\t"
+ "bne $4, %[expect2], %l[cmpfail]\n\t"
+ RSEQ_INJECT_ASM(5)
+#ifdef RSEQ_COMPARE_TWICE
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+ LONG_L " $4, %[v]\n\t"
+ "bne $4, %[expect], %l[error2]\n\t"
+ LONG_L " $4, %[v2]\n\t"
+ "bne $4, %[expect2], %l[error3]\n\t"
+#endif
+ /* final store */
+ LONG_S " %[newv], %[v]\n\t"
+ "2:\n\t"
+ RSEQ_INJECT_ASM(6)
+ "b 5f\n\t"
+ RSEQ_ASM_DEFINE_ABORT(3, 4, "", abort, 1b, 2b, 4f)
+ "5:\n\t"
+ : /* gcc asm goto does not allow outputs */
+ : [cpu_id] "r" (cpu),
+ [current_cpu_id] "m" (__rseq_abi.cpu_id),
+ [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ /* cmp2 input */
+ [v2] "m" (*v2),
+ [expect2] "r" (expect2),
+ /* final store input */
+ [v] "m" (*v),
+ [expect] "r" (expect),
+ [newv] "r" (newv)
+ RSEQ_INJECT_INPUT
+ : "$4", "memory"
+ RSEQ_INJECT_CLOBBER
+ : abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+ , error1, error2, error3
+#endif
+ );
+ rseq_workaround_gcc_asm_size_guess();
+ return 0;
+abort:
+ rseq_workaround_gcc_asm_size_guess();
+ RSEQ_INJECT_FAILED
+ return -1;
+cmpfail:
+ rseq_workaround_gcc_asm_size_guess();
+ return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+ rseq_bug("cpu_id comparison failed");
+error2:
+ rseq_bug("1st expected value comparison failed");
+error3:
+ rseq_bug("2nd expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
+ void *dst, void *src, size_t len,
+ intptr_t newv, int cpu)
+{
+ uintptr_t rseq_scratch[3];
+
+ RSEQ_INJECT_C(9)
+
+ rseq_workaround_gcc_asm_size_guess();
+ __asm__ __volatile__ goto (
+ RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */
+ LONG_S " %[src], %[rseq_scratch0]\n\t"
+ LONG_S " %[dst], %[rseq_scratch1]\n\t"
+ LONG_S " %[len], %[rseq_scratch2]\n\t"
+ /* Start rseq by storing table entry pointer into rseq_cs. */
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs)
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+ RSEQ_INJECT_ASM(3)
+ LONG_L " $4, %[v]\n\t"
+ "bne $4, %[expect], 5f\n\t"
+ RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 6f)
+ LONG_L " $4, %[v]\n\t"
+ "bne $4, %[expect], 7f\n\t"
+#endif
+ /* try memcpy */
+ "beqz %[len], 333f\n\t" \
+ "222:\n\t" \
+ "lb $4, 0(%[src])\n\t" \
+ "sb $4, 0(%[dst])\n\t" \
+ LONG_ADDI " %[src], 1\n\t" \
+ LONG_ADDI " %[dst], 1\n\t" \
+ LONG_ADDI " %[len], -1\n\t" \
+ "bnez %[len], 222b\n\t" \
+ "333:\n\t" \
+ RSEQ_INJECT_ASM(5)
+ /* final store */
+ LONG_S " %[newv], %[v]\n\t"
+ "2:\n\t"
+ RSEQ_INJECT_ASM(6)
+ /* teardown */
+ LONG_L " %[len], %[rseq_scratch2]\n\t"
+ LONG_L " %[dst], %[rseq_scratch1]\n\t"
+ LONG_L " %[src], %[rseq_scratch0]\n\t"
+ "b 8f\n\t"
+ RSEQ_ASM_DEFINE_ABORT(3, 4,
+ /* teardown */
+ LONG_L " %[len], %[rseq_scratch2]\n\t"
+ LONG_L " %[dst], %[rseq_scratch1]\n\t"
+ LONG_L " %[src], %[rseq_scratch0]\n\t",
+ abort, 1b, 2b, 4f)
+ RSEQ_ASM_DEFINE_CMPFAIL(5,
+ /* teardown */
+ LONG_L " %[len], %[rseq_scratch2]\n\t"
+ LONG_L " %[dst], %[rseq_scratch1]\n\t"
+ LONG_L " %[src], %[rseq_scratch0]\n\t",
+ cmpfail)
+#ifdef RSEQ_COMPARE_TWICE
+ RSEQ_ASM_DEFINE_CMPFAIL(6,
+ /* teardown */
+ LONG_L " %[len], %[rseq_scratch2]\n\t"
+ LONG_L " %[dst], %[rseq_scratch1]\n\t"
+ LONG_L " %[src], %[rseq_scratch0]\n\t",
+ error1)
+ RSEQ_ASM_DEFINE_CMPFAIL(7,
+ /* teardown */
+ LONG_L " %[len], %[rseq_scratch2]\n\t"
+ LONG_L " %[dst], %[rseq_scratch1]\n\t"
+ LONG_L " %[src], %[rseq_scratch0]\n\t",
+ error2)
+#endif
+ "8:\n\t"
+ : /* gcc asm goto does not allow outputs */
+ : [cpu_id] "r" (cpu),
+ [current_cpu_id] "m" (__rseq_abi.cpu_id),
+ [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ /* final store input */
+ [v] "m" (*v),
+ [expect] "r" (expect),
+ [newv] "r" (newv),
+ /* try memcpy input */
+ [dst] "r" (dst),
+ [src] "r" (src),
+ [len] "r" (len),
+ [rseq_scratch0] "m" (rseq_scratch[0]),
+ [rseq_scratch1] "m" (rseq_scratch[1]),
+ [rseq_scratch2] "m" (rseq_scratch[2])
+ RSEQ_INJECT_INPUT
+ : "$4", "memory"
+ RSEQ_INJECT_CLOBBER
+ : abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+ , error1, error2
+#endif
+ );
+ rseq_workaround_gcc_asm_size_guess();
+ return 0;
+abort:
+ rseq_workaround_gcc_asm_size_guess();
+ RSEQ_INJECT_FAILED
+ return -1;
+cmpfail:
+ rseq_workaround_gcc_asm_size_guess();
+ return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+ rseq_workaround_gcc_asm_size_guess();
+ rseq_bug("cpu_id comparison failed");
+error2:
+ rseq_workaround_gcc_asm_size_guess();
+ rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
+ void *dst, void *src, size_t len,
+ intptr_t newv, int cpu)
+{
+ uintptr_t rseq_scratch[3];
+
+ RSEQ_INJECT_C(9)
+
+ rseq_workaround_gcc_asm_size_guess();
+ __asm__ __volatile__ goto (
+ RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */
+ LONG_S " %[src], %[rseq_scratch0]\n\t"
+ LONG_S " %[dst], %[rseq_scratch1]\n\t"
+ LONG_S " %[len], %[rseq_scratch2]\n\t"
+ /* Start rseq by storing table entry pointer into rseq_cs. */
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs)
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+ RSEQ_INJECT_ASM(3)
+ LONG_L " $4, %[v]\n\t"
+ "bne $4, %[expect], 5f\n\t"
+ RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 6f)
+ LONG_L " $4, %[v]\n\t"
+ "bne $4, %[expect], 7f\n\t"
+#endif
+ /* try memcpy */
+ "beqz %[len], 333f\n\t" \
+ "222:\n\t" \
+ "lb $4, 0(%[src])\n\t" \
+ "sb $4, 0(%[dst])\n\t" \
+ LONG_ADDI " %[src], 1\n\t" \
+ LONG_ADDI " %[dst], 1\n\t" \
+ LONG_ADDI " %[len], -1\n\t" \
+ "bnez %[len], 222b\n\t" \
+ "333:\n\t" \
+ RSEQ_INJECT_ASM(5)
+ "sync\n\t" /* full sync provides store-release */
+ /* final store */
+ LONG_S " %[newv], %[v]\n\t"
+ "2:\n\t"
+ RSEQ_INJECT_ASM(6)
+ /* teardown */
+ LONG_L " %[len], %[rseq_scratch2]\n\t"
+ LONG_L " %[dst], %[rseq_scratch1]\n\t"
+ LONG_L " %[src], %[rseq_scratch0]\n\t"
+ "b 8f\n\t"
+ RSEQ_ASM_DEFINE_ABORT(3, 4,
+ /* teardown */
+ LONG_L " %[len], %[rseq_scratch2]\n\t"
+ LONG_L " %[dst], %[rseq_scratch1]\n\t"
+ LONG_L " %[src], %[rseq_scratch0]\n\t",
+ abort, 1b, 2b, 4f)
+ RSEQ_ASM_DEFINE_CMPFAIL(5,
+ /* teardown */
+ LONG_L " %[len], %[rseq_scratch2]\n\t"
+ LONG_L " %[dst], %[rseq_scratch1]\n\t"
+ LONG_L " %[src], %[rseq_scratch0]\n\t",
+ cmpfail)
+#ifdef RSEQ_COMPARE_TWICE
+ RSEQ_ASM_DEFINE_CMPFAIL(6,
+ /* teardown */
+ LONG_L " %[len], %[rseq_scratch2]\n\t"
+ LONG_L " %[dst], %[rseq_scratch1]\n\t"
+ LONG_L " %[src], %[rseq_scratch0]\n\t",
+ error1)
+ RSEQ_ASM_DEFINE_CMPFAIL(7,
+ /* teardown */
+ LONG_L " %[len], %[rseq_scratch2]\n\t"
+ LONG_L " %[dst], %[rseq_scratch1]\n\t"
+ LONG_L " %[src], %[rseq_scratch0]\n\t",
+ error2)
+#endif
+ "8:\n\t"
+ : /* gcc asm goto does not allow outputs */
+ : [cpu_id] "r" (cpu),
+ [current_cpu_id] "m" (__rseq_abi.cpu_id),
+ [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ /* final store input */
+ [v] "m" (*v),
+ [expect] "r" (expect),
+ [newv] "r" (newv),
+ /* try memcpy input */
+ [dst] "r" (dst),
+ [src] "r" (src),
+ [len] "r" (len),
+ [rseq_scratch0] "m" (rseq_scratch[0]),
+ [rseq_scratch1] "m" (rseq_scratch[1]),
+ [rseq_scratch2] "m" (rseq_scratch[2])
+ RSEQ_INJECT_INPUT
+ : "$4", "memory"
+ RSEQ_INJECT_CLOBBER
+ : abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+ , error1, error2
+#endif
+ );
+ rseq_workaround_gcc_asm_size_guess();
+ return 0;
+abort:
+ rseq_workaround_gcc_asm_size_guess();
+ RSEQ_INJECT_FAILED
+ return -1;
+cmpfail:
+ rseq_workaround_gcc_asm_size_guess();
+ return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+ rseq_workaround_gcc_asm_size_guess();
+ rseq_bug("cpu_id comparison failed");
+error2:
+ rseq_workaround_gcc_asm_size_guess();
+ rseq_bug("expected value comparison failed");
+#endif
+}
+
+#endif /* !RSEQ_SKIP_FASTPATH */
#include <rseq-arm.h>
#elif defined(__PPC__)
#include <rseq-ppc.h>
+#elif defined(__mips__)
+#include <rseq-mips.h>
#else
#error unsupported target
#endif
+# SPDX-License-Identifier: GPL-2.0
+uname_M := $(shell uname -m 2>/dev/null || echo not)
+ARCH ?= $(shell echo $(uname_M) | sed -e s/x86_64/x86/)
+
+ifneq ($(ARCH),sparc64)
+nothing:
+.PHONY: all clean run_tests install
+.SILENT:
+else
+
SUBDIRS := drivers
TEST_PROGS := run.sh
+
.PHONY: all clean
include ../lib.mk
fi \
done
-override define RUN_TESTS
- @cd $(OUTPUT); ./run.sh
-endef
-
override define INSTALL_RULE
mkdir -p $(INSTALL_PATH)
install -t $(INSTALL_PATH) $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES)
done;
endef
-override define EMIT_TESTS
- echo "./run.sh"
-endef
-
override define CLEAN
@for DIR in $(SUBDIRS); do \
BUILD_TARGET=$(OUTPUT)/$$DIR; \
make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\
done
endef
+endif
-
+# SPDX-License-Identifier: GPL-2.0
INCLUDEDIR := -I.
CFLAGS := $(CFLAGS) $(INCLUDEDIR) -Wall -O2 -g
# SPDX-License-Identifier: GPL-2.0
# Runs static keys kernel module tests
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+if ! /sbin/modprobe -q -n test_static_key_base; then
+ echo "static_key: module test_static_key_base is not found [SKIP]"
+ exit $ksft_skip
+fi
+
+if ! /sbin/modprobe -q -n test_static_keys; then
+ echo "static_key: module test_static_keys is not found [SKIP]"
+ exit $ksft_skip
+fi
+
if /sbin/modprobe -q test_static_key_base; then
if /sbin/modprobe -q test_static_keys; then
echo "static_key: ok"
--- /dev/null
+CONFIG_STAGING=y
+CONFIG_ANDROID=y
+CONFIG_SYNC=y
+CONFIG_SW_SYNC=y
# This performs a series tests against the proc sysctl interface.
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
TEST_NAME="sysctl"
TEST_DRIVER="test_${TEST_NAME}"
TEST_DIR=$(dirname $0)
echo "$0: $DIR not present" >&2
echo "You must have the following enabled in your kernel:" >&2
cat $TEST_DIR/config >&2
- exit 1
+ exit $ksft_skip
fi
}
uid=$(id -u)
if [ $uid -ne 0 ]; then
echo $msg must be run as root >&2
- exit 0
+ exit $ksft_skip
fi
if ! which perl 2> /dev/null > /dev/null; then
echo "$0: You need perl installed"
- exit 1
+ exit $ksft_skip
fi
if ! which getconf 2> /dev/null > /dev/null; then
echo "$0: You need getconf installed"
- exit 1
+ exit $ksft_skip
fi
if ! which diff 2> /dev/null > /dev/null; then
echo "$0: You need diff installed"
- exit 1
+ exit $ksft_skip
fi
}
function load_req_mod()
{
- trap "test_modprobe" EXIT
-
if [ ! -d $DIR ]; then
+ if ! modprobe -q -n $TEST_DRIVER; then
+ echo "$0: module $TEST_DRIVER not found [SKIP]"
+ exit $ksft_skip
+ fi
modprobe $TEST_DRIVER
if [ $? -ne 0 ]; then
exit
test_reqs
allow_user_defaults
check_production_sysctl_writes_strict
+test_modprobe
load_req_mod
trap "test_finish" EXIT
"$TC actions flush action csum"
]
},
+ {
+ "id": "b10b",
+ "name": "Add all 7 csum actions",
+ "category": [
+ "actions",
+ "csum"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action csum",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action csum icmp ip4h sctp igmp udplite udp tcp index 7",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action csum index 7",
+ "matchPattern": "action order [0-9]*: csum \\(iph, icmp, igmp, tcp, udp, udplite, sctp\\).*index 7 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action csum"
+ ]
+ },
{
"id": "ce92",
"name": "Add csum udp action with cookie",
--- /dev/null
+[
+ {
+ "id": "2b11",
+ "name": "Add tunnel_key set action with mandatory parameters",
+ "category": [
+ "actions",
+ "tunnel_key"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.20.2 id 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action tunnel_key",
+ "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 10.10.10.1.*dst_ip 20.20.20.2.*key_id 1",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action tunnel_key"
+ ]
+ },
+ {
+ "id": "dc6b",
+ "name": "Add tunnel_key set action with missing mandatory src_ip parameter",
+ "category": [
+ "actions",
+ "tunnel_key"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action tunnel_key set dst_ip 20.20.20.2 id 100",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions list action tunnel_key",
+ "matchPattern": "action order [0-9]+: tunnel_key set.*dst_ip 20.20.20.2.*key_id 100",
+ "matchCount": "0",
+ "teardown": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ]
+ },
+ {
+ "id": "7f25",
+ "name": "Add tunnel_key set action with missing mandatory dst_ip parameter",
+ "category": [
+ "actions",
+ "tunnel_key"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 10.10.10.1 id 100",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions list action tunnel_key",
+ "matchPattern": "action order [0-9]+: tunnel_key set.*src_ip 10.10.10.1.*key_id 100",
+ "matchCount": "0",
+ "teardown": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ]
+ },
+ {
+ "id": "ba4e",
+ "name": "Add tunnel_key set action with missing mandatory id parameter",
+ "category": [
+ "actions",
+ "tunnel_key"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.20.2",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions list action tunnel_key",
+ "matchPattern": "action order [0-9]+: tunnel_key set.*src_ip 10.10.10.1.*dst_ip 20.20.20.2",
+ "matchCount": "0",
+ "teardown": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ]
+ },
+ {
+ "id": "a5e0",
+ "name": "Add tunnel_key set action with invalid src_ip parameter",
+ "category": [
+ "actions",
+ "tunnel_key"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 300.168.100.1 dst_ip 192.168.200.1 id 7 index 1",
+ "expExitCode": "1",
+ "verifyCmd": "$TC actions get action tunnel_key index 1",
+ "matchPattern": "action order [0-9]+: tunnel_key set.*src_ip 300.168.100.1.*dst_ip 192.168.200.1.*key_id 7.*index 1 ref",
+ "matchCount": "0",
+ "teardown": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ]
+ },
+ {
+ "id": "eaa8",
+ "name": "Add tunnel_key set action with invalid dst_ip parameter",
+ "category": [
+ "actions",
+ "tunnel_key"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 192.168.100.1 dst_ip 192.168.800.1 id 10 index 11",
+ "expExitCode": "1",
+ "verifyCmd": "$TC actions get action tunnel_key index 11",
+ "matchPattern": "action order [0-9]+: tunnel_key set.*src_ip 192.168.100.1.*dst_ip 192.168.800.1.*key_id 10.*index 11 ref",
+ "matchCount": "0",
+ "teardown": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ]
+ },
+ {
+ "id": "3b09",
+ "name": "Add tunnel_key set action with invalid id parameter",
+ "category": [
+ "actions",
+ "tunnel_key"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 112233445566778899 index 1",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions get action tunnel_key index 1",
+ "matchPattern": "action order [0-9]+: tunnel_key set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 112233445566778899.*index 1 ref",
+ "matchCount": "0",
+ "teardown": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ]
+ },
+ {
+ "id": "9625",
+ "name": "Add tunnel_key set action with invalid dst_port parameter",
+ "category": [
+ "actions",
+ "tunnel_key"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 11 dst_port 998877 index 1",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions get action tunnel_key index 1",
+ "matchPattern": "action order [0-9]+: tunnel_key set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 11.*dst_port 998877.*index 1 ref",
+ "matchCount": "0",
+ "teardown": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ]
+ },
+ {
+ "id": "05af",
+ "name": "Add tunnel_key set action with optional dst_port parameter",
+ "category": [
+ "actions",
+ "tunnel_key"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 192.168.100.1 dst_ip 192.168.200.1 id 789 dst_port 4000 index 10",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action tunnel_key index 10",
+ "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 192.168.100.1.*dst_ip 192.168.200.1.*key_id 789.*dst_port 4000.*index 10 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action tunnel_key"
+ ]
+ },
+ {
+ "id": "da80",
+ "name": "Add tunnel_key set action with index at 32-bit maximum",
+ "category": [
+ "actions",
+ "tunnel_key"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 11 index 4294967295",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action tunnel_key index 4294967295",
+ "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*id 11.*index 4294967295 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action tunnel_key"
+ ]
+ },
+ {
+ "id": "d407",
+ "name": "Add tunnel_key set action with index exceeding 32-bit maximum",
+ "category": [
+ "actions",
+ "tunnel_key"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 11 index 4294967295678",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions get action tunnel_key index 4294967295678",
+ "matchPattern": "action order [0-9]+: tunnel_key set.*index 4294967295678 ref",
+ "matchCount": "0",
+ "teardown": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ]
+ },
+ {
+ "id": "5cba",
+ "name": "Add tunnel_key set action with id value at 32-bit maximum",
+ "category": [
+ "actions",
+ "tunnel_key"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 4294967295 index 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action tunnel_key index 1",
+ "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 4294967295.*index 1",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action tunnel_key"
+ ]
+ },
+ {
+ "id": "e84a",
+ "name": "Add tunnel_key set action with id value exceeding 32-bit maximum",
+ "category": [
+ "actions",
+ "tunnel_key"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 42949672955 index 1",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions get action tunnel_key index 4294967295",
+ "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 42949672955.*index 1",
+ "matchCount": "0",
+ "teardown": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ]
+ },
+ {
+ "id": "9c19",
+ "name": "Add tunnel_key set action with dst_port value at 16-bit maximum",
+ "category": [
+ "actions",
+ "tunnel_key"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 429 dst_port 65535 index 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action tunnel_key index 1",
+ "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 429.*dst_port 65535.*index 1",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action tunnel_key"
+ ]
+ },
+ {
+ "id": "3bd9",
+ "name": "Add tunnel_key set action with dst_port value exceeding 16-bit maximum",
+ "category": [
+ "actions",
+ "tunnel_key"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 429 dst_port 65535789 index 1",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions get action tunnel_key index 1",
+ "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 429.*dst_port 65535789.*index 1",
+ "matchCount": "0",
+ "teardown": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ]
+ },
+ {
+ "id": "68e2",
+ "name": "Add tunnel_key unset action",
+ "category": [
+ "actions",
+ "tunnel_key"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action tunnel_key unset index 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action tunnel_key index 1",
+ "matchPattern": "action order [0-9]+: tunnel_key.*unset.*index 1 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action tunnel_key"
+ ]
+ },
+ {
+ "id": "6192",
+ "name": "Add tunnel_key unset continue action",
+ "category": [
+ "actions",
+ "tunnel_key"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action tunnel_key unset continue index 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action tunnel_key index 1",
+ "matchPattern": "action order [0-9]+: tunnel_key.*unset continue.*index 1 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action tunnel_key"
+ ]
+ },
+ {
+ "id": "061d",
+ "name": "Add tunnel_key set continue action with cookie",
+ "category": [
+ "actions",
+ "tunnel_key"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 192.168.10.1 dst_ip 192.168.20.2 id 123 continue index 1 cookie aa11bb22cc33dd44ee55ff66aa11b1b2",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action tunnel_key index 1",
+ "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 192.168.10.1.*dst_ip 192.168.20.2.*key_id 123.*csum continue.*index 1.*cookie aa11bb22cc33dd44ee55ff66aa11b1b2",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action tunnel_key"
+ ]
+ },
+ {
+ "id": "8acb",
+ "name": "Add tunnel_key set continue action with invalid cookie",
+ "category": [
+ "actions",
+ "tunnel_key"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 192.168.10.1 dst_ip 192.168.20.2 id 123 continue index 1 cookie aa11bb22cc33dd44ee55ff66aa11b1b2777888",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions get action tunnel_key index 1",
+ "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 192.168.10.1.*dst_ip 192.168.20.2.*key_id 123.*csum continue.*index 1.*cookie aa11bb22cc33dd44ee55ff66aa11b1b2777888",
+ "matchCount": "0",
+ "teardown": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ]
+ },
+ {
+ "id": "a07e",
+ "name": "Add tunnel_key action with no set/unset command specified",
+ "category": [
+ "actions",
+ "tunnel_key"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action tunnel_key src_ip 10.10.10.1 dst_ip 20.20.20.2 id 1",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions get action tunnel_key index 1",
+ "matchPattern": "action order [0-9]+: tunnel_key.*src_ip 10.10.10.1.*dst_ip 20.20.20.2.*key_id 1",
+ "matchCount": "0",
+ "teardown": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ]
+ },
+ {
+ "id": "b227",
+ "name": "Add tunnel_key action with csum option",
+ "category": [
+ "actions",
+ "tunnel_key"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.20.2 id 1 csum index 99",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action tunnel_key index 99",
+ "matchPattern": "action order [0-9]+: tunnel_key.*src_ip 10.10.10.1.*dst_ip 20.20.20.2.*key_id 1.*csum pipe.*index 99",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action tunnel_key"
+ ]
+ },
+ {
+ "id": "58a7",
+ "name": "Add tunnel_key action with nocsum option",
+ "category": [
+ "actions",
+ "tunnel_key"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 10.10.10.2 id 7823 nocsum index 234",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action tunnel_key index 234",
+ "matchPattern": "action order [0-9]+: tunnel_key.*src_ip 10.10.10.1.*dst_ip 10.10.10.2.*key_id 7823.*nocsum pipe.*index 234",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action tunnel_key"
+ ]
+ },
+ {
+ "id": "2575",
+ "name": "Add tunnel_key action with not-supported parameter",
+ "category": [
+ "actions",
+ "tunnel_key"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 10.10.10.2 id 7 foobar 999 index 4",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions get action tunnel_key index 4",
+ "matchPattern": "action order [0-9]+: tunnel_key.*src_ip 10.10.10.1.*dst_ip 10.10.10.2.*key_id 7.*foobar 999.*index 4",
+ "matchCount": "0",
+ "teardown": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ]
+ },
+ {
+ "id": "7a88",
+ "name": "Add tunnel_key action with cookie parameter",
+ "category": [
+ "actions",
+ "tunnel_key"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 10.10.10.2 id 7 index 4 cookie aa11bb22cc33dd44ee55ff66aa11b1b2",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action tunnel_key index 4",
+ "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 10.10.10.1.*dst_ip 10.10.10.2.*key_id 7.*dst_port 0.*csum pipe.*index 4 ref.*cookie aa11bb22cc33dd44ee55ff66aa11b1b2",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action tunnel_key"
+ ]
+ },
+ {
+ "id": "4f20",
+ "name": "Add tunnel_key action with a single geneve option parameter",
+ "category": [
+ "actions",
+ "tunnel_key"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 42 dst_port 6081 geneve_opts 0102:80:00880022 index 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action tunnel_key index 1",
+ "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 42.*dst_port 6081.*geneve_opt 0102:80:00880022.*index 1",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action tunnel_key"
+ ]
+ },
+ {
+ "id": "e33d",
+ "name": "Add tunnel_key action with multiple geneve options parameter",
+ "category": [
+ "actions",
+ "tunnel_key"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 42 dst_port 6081 geneve_opts 0102:80:00880022,0408:42:0040007611223344,0111:02:1020304011223344 index 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action tunnel_key index 1",
+ "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 42.*dst_port 6081.*geneve_opt 0102:80:00880022,0408:42:0040007611223344,0111:02:1020304011223344.*index 1",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action tunnel_key"
+ ]
+ },
+ {
+ "id": "0778",
+ "name": "Add tunnel_key action with invalid class geneve option parameter",
+ "category": [
+ "actions",
+ "tunnel_key"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 42 dst_port 6081 geneve_opts 824212:80:00880022 index 1",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions get action tunnel_key index 1",
+ "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 42.*dst_port 6081.*geneve_opt 824212:80:00880022.*index 1",
+ "matchCount": "0",
+ "teardown": [
+ "$TC actions flush action tunnel_key"
+ ]
+ },
+ {
+ "id": "4ae8",
+ "name": "Add tunnel_key action with invalid type geneve option parameter",
+ "category": [
+ "actions",
+ "tunnel_key"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 42 dst_port 6081 geneve_opts 0102:4224:00880022 index 1",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions get action tunnel_key index 1",
+ "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 42.*dst_port 6081.*geneve_opt 0102:4224:00880022.*index 1",
+ "matchCount": "0",
+ "teardown": [
+ "$TC actions flush action tunnel_key"
+ ]
+ },
+ {
+ "id": "4039",
+ "name": "Add tunnel_key action with short data length geneve option parameter",
+ "category": [
+ "actions",
+ "tunnel_key"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 42 dst_port 6081 geneve_opts 0102:80:4288 index 1",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions get action tunnel_key index 1",
+ "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 42.*dst_port 6081.*geneve_opt 0102:80:4288.*index 1",
+ "matchCount": "0",
+ "teardown": [
+ "$TC actions flush action tunnel_key"
+ ]
+ },
+ {
+ "id": "26a6",
+ "name": "Add tunnel_key action with non-multiple of 4 data length geneve option parameter",
+ "category": [
+ "actions",
+ "tunnel_key"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 42 dst_port 6081 geneve_opts 0102:80:4288428822 index 1",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions get action tunnel_key index 1",
+ "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 42.*dst_port 6081.*geneve_opt 0102:80:4288428822.*index 1",
+ "matchCount": "0",
+ "teardown": [
+ "$TC actions flush action tunnel_key"
+ ]
+ },
+ {
+ "id": "f44d",
+ "name": "Add tunnel_key action with incomplete geneve options parameter",
+ "category": [
+ "actions",
+ "tunnel_key"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 42 dst_port 6081 geneve_opts 0102:80:00880022,0408:42: index 1",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions get action tunnel_key index 1",
+ "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 42.*dst_port 6081.*geneve_opt 0102:80:00880022,0408:42:.*index 1",
+ "matchCount": "0",
+ "teardown": [
+ "$TC actions flush action tunnel_key"
+ ]
+ },
+ {
+ "id": "7afc",
+ "name": "Replace tunnel_key set action with all parameters",
+ "category": [
+ "actions",
+ "tunnel_key"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ],
+ "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.20.2 dst_port 3128 csum id 1 index 1"
+ ],
+ "cmdUnderTest": "$TC actions replace action tunnel_key set src_ip 11.11.11.1 dst_ip 21.21.21.2 dst_port 3129 nocsum id 11 index 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action tunnel_key index 1",
+ "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 11.11.11.1.*dst_ip 21.21.21.2.*key_id 11.*dst_port 3129.*nocsum pipe.*index 1",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action tunnel_key"
+ ]
+ },
+ {
+ "id": "364d",
+ "name": "Replace tunnel_key set action with all parameters and cookie",
+ "category": [
+ "actions",
+ "tunnel_key"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ],
+ "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.20.2 dst_port 3128 nocsum id 1 index 1 cookie aabbccddeeff112233445566778800a"
+ ],
+ "cmdUnderTest": "$TC actions replace action tunnel_key set src_ip 11.11.11.1 dst_ip 21.21.21.2 dst_port 3129 id 11 csum reclassify index 1 cookie a1b1c1d1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action tunnel_key index 1",
+ "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 11.11.11.1.*dst_ip 21.21.21.2.*key_id 11.*dst_port 3129.*csum reclassify.*index 1.*cookie a1b1c1d1",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action tunnel_key"
+ ]
+ },
+ {
+ "id": "937c",
+ "name": "Fetch all existing tunnel_key actions",
+ "category": [
+ "actions",
+ "tunnel_key"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ],
+ "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.20.2 dst_port 3128 nocsum id 1 pipe index 1",
+ "$TC actions add action tunnel_key set src_ip 11.10.10.1 dst_ip 21.20.20.2 dst_port 3129 csum id 2 jump 10 index 2",
+ "$TC actions add action tunnel_key set src_ip 12.10.10.1 dst_ip 22.20.20.2 dst_port 3130 csum id 3 pass index 3",
+ "$TC actions add action tunnel_key set src_ip 13.10.10.1 dst_ip 23.20.20.2 dst_port 3131 nocsum id 4 continue index 4"
+ ],
+ "cmdUnderTest": "$TC actions list action tunnel_key",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action tunnel_key",
+ "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 10.10.10.1.*dst_ip 20.20.20.2.*key_id 1.*dst_port 3128.*nocsum pipe.*index 1.*set.*src_ip 11.10.10.1.*dst_ip 21.20.20.2.*key_id 2.*dst_port 3129.*csum jump 10.*index 2.*set.*src_ip 12.10.10.1.*dst_ip 22.20.20.2.*key_id 3.*dst_port 3130.*csum pass.*index 3.*set.*src_ip 13.10.10.1.*dst_ip 23.20.20.2.*key_id 4.*dst_port 3131.*nocsum continue.*index 4",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action tunnel_key"
+ ]
+ },
+ {
+ "id": "6783",
+ "name": "Flush all existing tunnel_key actions",
+ "category": [
+ "actions",
+ "tunnel_key"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action tunnel_key",
+ 0,
+ 1,
+ 255
+ ],
+ "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.20.2 dst_port 3128 nocsum id 1 pipe index 1",
+ "$TC actions add action tunnel_key set src_ip 11.10.10.1 dst_ip 21.20.20.2 dst_port 3129 csum id 2 reclassify index 2",
+ "$TC actions add action tunnel_key set src_ip 12.10.10.1 dst_ip 22.20.20.2 dst_port 3130 csum id 3 pass index 3",
+ "$TC actions add action tunnel_key set src_ip 13.10.10.1 dst_ip 23.20.20.2 dst_port 3131 nocsum id 4 continue index 4"
+ ],
+ "cmdUnderTest": "$TC actions flush action tunnel_key",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action tunnel_key",
+ "matchPattern": "action order [0-9]+:.*",
+ "matchCount": "0",
+ "teardown": [
+ "$TC actions flush action tunnel_key"
+ ]
+ }
+]
# SPDX-License-Identifier: GPL-2.0
# Runs copy_to/from_user infrastructure using test_user_copy kernel module
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+if ! /sbin/modprobe -q -n test_user_copy; then
+ echo "user: module test_user_copy is not found [SKIP]"
+ exit $ksft_skip
+fi
if /sbin/modprobe -q test_user_copy; then
/sbin/modprobe -q -r test_user_copy
echo "user_copy: ok"
#include <unistd.h>
#include <string.h>
+#include "../kselftest.h"
+
#define MAP_SIZE 1048576
struct map_list {
printf("Either the sysctl compact_unevictable_allowed is not\n"
"set to 1 or couldn't read the proc file.\n"
"Skipping the test\n");
- return 0;
+ return KSFT_SKIP;
}
lim.rlim_cur = RLIM_INFINITY;
#include <stdbool.h>
#include "mlock2.h"
+#include "../kselftest.h"
+
struct vm_boundaries {
unsigned long start;
unsigned long end;
if (mlock2_(map, 2 * page_size, 0)) {
if (errno == ENOSYS) {
printf("Cannot call new mlock family, skipping test\n");
- _exit(0);
+ _exit(KSFT_SKIP);
}
perror("mlock2(0)");
goto unmap;
if (mlock2_(map, 2 * page_size, MLOCK_ONFAULT)) {
if (errno == ENOSYS) {
printf("Cannot call new mlock family, skipping test\n");
- _exit(0);
+ _exit(KSFT_SKIP);
}
perror("mlock2(MLOCK_ONFAULT)");
goto unmap;
if (munlock(map, 2 * page_size)) {
if (errno == ENOSYS) {
printf("Cannot call new mlock family, skipping test\n");
- _exit(0);
+ _exit(KSFT_SKIP);
}
perror("munlock()");
goto unmap;
if (mlock2_(map, 2 * page_size, MLOCK_ONFAULT)) {
if (errno == ENOSYS) {
printf("Cannot call new mlock family, skipping test\n");
- _exit(0);
+ _exit(KSFT_SKIP);
}
perror("mlock2(MLOCK_ONFAULT)");
goto unmap;
if (call_mlock && mlock2_(map, 3 * page_size, MLOCK_ONFAULT)) {
if (errno == ENOSYS) {
printf("Cannot call new mlock family, skipping test\n");
- _exit(0);
+ _exit(KSFT_SKIP);
}
perror("mlock(ONFAULT)\n");
goto out;
# SPDX-License-Identifier: GPL-2.0
#please run as root
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
mnt=./huge
exitcode=0
echo $(( $lackpgs + $nr_hugepgs )) > /proc/sys/vm/nr_hugepages
if [ $? -ne 0 ]; then
echo "Please run this test as root"
- exit 1
+ exit $ksft_skip
fi
while read name size unit; do
if [ "$name" = "HugePages_Free:" ]; then
#include <setjmp.h>
#include <stdbool.h>
+#include "../kselftest.h"
+
#ifdef __NR_userfaultfd
static unsigned long nr_cpus, nr_pages, nr_pages_per_cpu, page_size;
int main(void)
{
printf("skip: Skipping userfaultfd test (missing __NR_userfaultfd)\n");
- return 0;
+ return KSFT_SKIP;
}
#endif /* __NR_userfaultfd */
*/
for (int i = 0; i < NGREG; i++) {
greg_t req = requested_regs[i], res = resulting_regs[i];
+
if (i == REG_TRAPNO || i == REG_IP)
continue; /* don't care */
- if (i == REG_SP) {
- printf("\tSP: %llx -> %llx\n", (unsigned long long)req,
- (unsigned long long)res);
+ if (i == REG_SP) {
/*
- * In many circumstances, the high 32 bits of rsp
- * are zeroed. For example, we could be a real
- * 32-bit program, or we could hit any of a number
- * of poorly-documented IRET or segmented ESP
- * oddities. If this happens, it's okay.
+ * If we were using a 16-bit stack segment, then
+ * the kernel is a bit stuck: IRET only restores
+ * the low 16 bits of ESP/RSP if SS is 16-bit.
+ * The kernel uses a hack to restore bits 31:16,
+ * but that hack doesn't help with bits 63:32.
+ * On Intel CPUs, bits 63:32 end up zeroed, and, on
+ * AMD CPUs, they leak the high bits of the kernel
+ * espfix64 stack pointer. There's very little that
+ * the kernel can do about it.
+ *
+ * Similarly, if we are returning to a 32-bit context,
+ * the CPU will often lose the high 32 bits of RSP.
*/
- if (res == (req & 0xFFFFFFFF))
- continue; /* OK; not expected to work */
+
+ if (res == req)
+ continue;
+
+ if (cs_bits != 64 && ((res ^ req) & 0xFFFFFFFF) == 0) {
+ printf("[NOTE]\tSP: %llx -> %llx\n",
+ (unsigned long long)req,
+ (unsigned long long)res);
+ continue;
+ }
+
+ printf("[FAIL]\tSP mismatch: requested 0x%llx; got 0x%llx\n",
+ (unsigned long long)requested_regs[i],
+ (unsigned long long)resulting_regs[i]);
+ nerrs++;
+ continue;
}
bool ignore_reg = false;
#endif
/* Sanity check on the kernel */
- if (i == REG_CX && requested_regs[i] != resulting_regs[i]) {
+ if (i == REG_CX && req != res) {
printf("[FAIL]\tCX (saved SP) mismatch: requested 0x%llx; got 0x%llx\n",
- (unsigned long long)requested_regs[i],
- (unsigned long long)resulting_regs[i]);
+ (unsigned long long)req,
+ (unsigned long long)res);
nerrs++;
continue;
}
- if (requested_regs[i] != resulting_regs[i] && !ignore_reg) {
- /*
- * SP is particularly interesting here. The
- * usual cause of failures is that we hit the
- * nasty IRET case of returning to a 16-bit SS,
- * in which case bits 16:31 of the *kernel*
- * stack pointer persist in ESP.
- */
+ if (req != res && !ignore_reg) {
printf("[FAIL]\tReg %d mismatch: requested 0x%llx; got 0x%llx\n",
- i, (unsigned long long)requested_regs[i],
- (unsigned long long)resulting_regs[i]);
+ i, (unsigned long long)req,
+ (unsigned long long)res);
nerrs++;
}
}
# SPDX-License-Identifier: GPL-2.0
TCID="zram.sh"
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
. ./zram_lib.sh
run_zram () {
else
echo "$TCID : No zram.ko module or /dev/zram0 device file not found"
echo "$TCID : CONFIG_ZRAM is not set"
- exit 1
+ exit $ksft_skip
fi
dev_makeswap=-1
dev_mounted=-1
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
trap INT
check_prereqs()
if [ $uid -ne 0 ]; then
echo $msg must be run as root >&2
- exit 0
+ exit $ksft_skip
fi
}
*/
BUG_ON((unsigned long) page & 0x03);
#ifdef CONFIG_DEBUG_SG
- BUG_ON(sg->sg_magic != SG_MAGIC);
BUG_ON(sg_is_chain(sg));
#endif
sg->page_link = page_link | (unsigned long) page;
static inline struct page *sg_page(struct scatterlist *sg)
{
#ifdef CONFIG_DEBUG_SG
- BUG_ON(sg->sg_magic != SG_MAGIC);
BUG_ON(sg_is_chain(sg));
#endif
return (struct page *)((sg)->page_link & ~0x3);
**/
static inline void sg_mark_end(struct scatterlist *sg)
{
-#ifdef CONFIG_DEBUG_SG
- BUG_ON(sg->sg_magic != SG_MAGIC);
-#endif
/*
* Set termination bit, clear potential chain bit
*/
**/
static inline void sg_unmark_end(struct scatterlist *sg)
{
-#ifdef CONFIG_DEBUG_SG
- BUG_ON(sg->sg_magic != SG_MAGIC);
-#endif
sg->page_link &= ~0x02;
}
static inline struct scatterlist *sg_next(struct scatterlist *sg)
{
-#ifdef CONFIG_DEBUG_SG
- BUG_ON(sg->sg_magic != SG_MAGIC);
-#endif
if (sg_is_last(sg))
return NULL;
static inline void sg_init_table(struct scatterlist *sgl, unsigned int nents)
{
memset(sgl, 0, sizeof(*sgl) * nents);
-#ifdef CONFIG_DEBUG_SG
- {
- unsigned int i;
- for (i = 0; i < nents; i++)
- sgl[i].sg_magic = SG_MAGIC;
- }
-#endif
sg_mark_end(&sgl[nents - 1]);
}
config KVM_COMPAT
def_bool y
- depends on KVM && COMPAT && !S390
+ depends on KVM && COMPAT && !(S390 || ARM64)
config HAVE_KVM_IRQ_BYPASS
bool
phys_addr_t next;
assert_spin_locked(&kvm->mmu_lock);
+ WARN_ON(size & ~PAGE_MASK);
+
pgd = kvm->arch.pgd + stage2_pgd_index(addr);
do {
/*
pr_warn("GICV physical address 0x%llx not page aligned\n",
(unsigned long long)info->vcpu.start);
kvm_vgic_global_state.vcpu_base = 0;
- } else if (!PAGE_ALIGNED(resource_size(&info->vcpu))) {
- pr_warn("GICV size 0x%llx not a multiple of page size 0x%lx\n",
- (unsigned long long)resource_size(&info->vcpu),
- PAGE_SIZE);
- kvm_vgic_global_state.vcpu_base = 0;
} else {
kvm_vgic_global_state.vcpu_base = info->vcpu.start;
kvm_vgic_global_state.can_emulate_gicv2 = true;
#ifdef CONFIG_KVM_COMPAT
static long kvm_vcpu_compat_ioctl(struct file *file, unsigned int ioctl,
unsigned long arg);
+#define KVM_COMPAT(c) .compat_ioctl = (c)
+#else
+static long kvm_no_compat_ioctl(struct file *file, unsigned int ioctl,
+ unsigned long arg) { return -EINVAL; }
+#define KVM_COMPAT(c) .compat_ioctl = kvm_no_compat_ioctl
#endif
static int hardware_enable_all(void);
static void hardware_disable_all(void);
static struct file_operations kvm_vcpu_fops = {
.release = kvm_vcpu_release,
.unlocked_ioctl = kvm_vcpu_ioctl,
-#ifdef CONFIG_KVM_COMPAT
- .compat_ioctl = kvm_vcpu_compat_ioctl,
-#endif
.mmap = kvm_vcpu_mmap,
.llseek = noop_llseek,
+ KVM_COMPAT(kvm_vcpu_compat_ioctl),
};
/*
static const struct file_operations kvm_device_fops = {
.unlocked_ioctl = kvm_device_ioctl,
-#ifdef CONFIG_KVM_COMPAT
- .compat_ioctl = kvm_device_ioctl,
-#endif
.release = kvm_device_release,
+ KVM_COMPAT(kvm_device_ioctl),
};
struct kvm_device *kvm_device_from_filp(struct file *filp)
static struct file_operations kvm_vm_fops = {
.release = kvm_vm_release,
.unlocked_ioctl = kvm_vm_ioctl,
-#ifdef CONFIG_KVM_COMPAT
- .compat_ioctl = kvm_vm_compat_ioctl,
-#endif
.llseek = noop_llseek,
+ KVM_COMPAT(kvm_vm_compat_ioctl),
};
static int kvm_dev_ioctl_create_vm(unsigned long type)
static struct file_operations kvm_chardev_ops = {
.unlocked_ioctl = kvm_dev_ioctl,
- .compat_ioctl = kvm_dev_ioctl,
.llseek = noop_llseek,
+ KVM_COMPAT(kvm_dev_ioctl),
};
static struct miscdevice kvm_dev = {