Required properties:
- - device_type : Should be "ethernet-phy"
- interrupts : <a b> where a is the interrupt number and b is a
field that represents an encoding of the sense and level
information for the interrupt. This should be encoded based on
- interrupt-parent : the phandle for the interrupt controller that
services interrupts for this device.
- reg : The ID number for the phy, usually a small integer
- - linux,phandle : phandle for this node; likely referenced by an
- ethernet controller node.
Optional Properties:
specifications. If neither of these are specified, the default is to
assume clause 22. The compatible list may also contain other
elements.
+ - max-speed: Maximum PHY supported speed (10, 100, 1000...)
Example:
ethernet-phy@0 {
compatible = "ethernet-phy-ieee802.3-c22";
- linux,phandle = <2452000>;
interrupt-parent = <40000>;
interrupts = <35 1>;
reg = <0>;
- device_type = "ethernet-phy";
};
N: Files and directories with regex patterns.
N: [^a-z]tegra all files whose path contains the word tegra
One pattern per line. Multiple N: lines acceptable.
+ scripts/get_maintainer.pl has different behavior for files that
+ match F: pattern and matches of N: patterns. By default,
+ get_maintainer will not look at git log history when an F: pattern
+ match occurs. When an N: match occurs, git log history is used
+ to also notify the people that have git commit signatures.
X: Files and directories that are NOT maintained, same rules as F:
Files exclusions are tested before file matches.
Can be useful for excluding a specific subdirectory, for instance:
F: drivers/pci/*acpi*
F: drivers/pci/*/*acpi*
F: drivers/pci/*/*/*acpi*
+F: tools/power/acpi
ACPI COMPONENT ARCHITECTURE (ACPICA)
M: Robert Moore <robert.moore@intel.com>
S: Supported
F: drivers/acpi/acpica/
F: include/acpi/
+F: tools/power/acpi/
ACPI FAN DRIVER
M: Zhang Rui <rui.zhang@intel.com>
L: linux-scsi@vger.kernel.org
S: Maintained
F: drivers/scsi/aic7xxx/
-F: drivers/scsi/aic7xxx_old/
AIMSLAB FM RADIO RECEIVER DRIVER
M: Hans Verkuil <hverkuil@xs4all.nl>
F: include/linux/altera_uart.h
F: include/linux/altera_jtaguart.h
+AMD CRYPTOGRAPHIC COPROCESSOR (CCP) DRIVER
+M: Tom Lendacky <thomas.lendacky@amd.com>
+L: linux-crypto@vger.kernel.org
+S: Supported
+F: drivers/crypto/ccp/
+F: include/linux/ccp.h
+
AMD FAM15H PROCESSOR POWER MONITORING DRIVER
M: Andreas Herrmann <herrmann.der.user@googlemail.com>
L: lm-sensors@lm-sensors.org
M: Maxime Ripard <maxime.ripard@free-electrons.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
-F: arch/arm/mach-sunxi/
+N: sun[x4567]i
+
+ARM/Allwinner SoC Clock Support
+M: Emilio López <emilio@elopez.com.ar>
+S: Maintained
+F: drivers/clk/sunxi/
ARM/ATMEL AT91RM9200 AND AT91SAM ARM ARCHITECTURES
M: Andrew Victor <linux@maxim.org.za>
F: arch/arm/mach-ebsa110/
F: drivers/net/ethernet/amd/am79c961a.*
+ARM/ENERGY MICRO (SILICON LABS) EFM32 SUPPORT
+M: Uwe Kleine-König <kernel@pengutronix.de>
+L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+S: Maintained
+N: efm32
+
ARM/EZX SMARTPHONES (A780, A910, A1200, E680, ROKR E2 and ROKR E6)
M: Daniel Ribeiro <drwyrm@gmail.com>
M: Stefan Schmidt <stefan@openezx.org>
S: Maintained
F: arch/arm/mach-mvebu/
+ARM/Marvell Berlin SoC support
+M: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
+L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+S: Maintained
+F: arch/arm/mach-berlin/
+
ARM/Marvell Dove/Kirkwood/MV78xx0/Orion SOC support
M: Jason Cooper <jason@lakedaemon.net>
M: Andrew Lunn <andrew@lunn.ch>
F: drivers/rtc/rtc-pl031.c
T: git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-stericsson.git
+ARM/Ux500 CLOCK FRAMEWORK SUPPORT
+M: Ulf Hansson <ulf.hansson@linaro.org>
+L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+T: git git://git.linaro.org/people/ulfh/clk.git
+S: Maintained
+F: drivers/clk/ux500/
+F: include/linux/platform_data/clk-ux500.h
+
ARM/VFP SUPPORT
M: Russell King <linux@arm.linux.org.uk>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
F: drivers/block/aoe/
ATHEROS ATH GENERIC UTILITIES
- M: "Luis R. Rodriguez" <mcgrof@qca.qualcomm.com>
+ M: "Luis R. Rodriguez" <mcgrof@do-not-panic.com>
L: linux-wireless@vger.kernel.org
S: Supported
F: drivers/net/wireless/ath/*
ATHEROS ATH5K WIRELESS DRIVER
M: Jiri Slaby <jirislaby@gmail.com>
M: Nick Kossifidis <mickflemm@gmail.com>
- M: "Luis R. Rodriguez" <mcgrof@qca.qualcomm.com>
+ M: "Luis R. Rodriguez" <mcgrof@do-not-panic.com>
L: linux-wireless@vger.kernel.org
L: ath5k-devel@lists.ath5k.org
W: http://wireless.kernel.org/en/users/Drivers/ath5k
S: Supported
F: drivers/net/wireless/ath/ath6kl/
- ATHEROS ATH9K WIRELESS DRIVER
- M: "Luis R. Rodriguez" <mcgrof@qca.qualcomm.com>
- M: Jouni Malinen <jouni@qca.qualcomm.com>
- M: Vasanthakumar Thiagarajan <vthiagar@qca.qualcomm.com>
- M: Senthil Balasubramanian <senthilb@qca.qualcomm.com>
- L: linux-wireless@vger.kernel.org
- L: ath9k-devel@lists.ath9k.org
- W: http://wireless.kernel.org/en/users/Drivers/ath9k
- S: Supported
- F: drivers/net/wireless/ath/ath9k/
-
WILOCITY WIL6210 WIRELESS DRIVER
M: Vladimir Kondratiev <qca_vkondrat@qca.qualcomm.com>
L: linux-wireless@vger.kernel.org
F: drivers/scsi/esas2r
AUDIT SUBSYSTEM
-M: Al Viro <viro@zeniv.linux.org.uk>
M: Eric Paris <eparis@redhat.com>
L: linux-audit@redhat.com (subscribers-only)
W: http://people.redhat.com/sgrubb/audit/
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/viro/audit-current.git
+T: git git://git.infradead.org/users/eparis/audit.git
S: Maintained
F: include/linux/audit.h
F: include/uapi/linux/audit.h
W: http://gitorious.org/linux-can
T: git git://gitorious.org/linux-can/linux-can-next.git
S: Maintained
+ F: Documentation/networking/can.txt
F: net/can/
F: include/linux/can/core.h
F: include/uapi/linux/can.h
S: Supported
F: drivers/net/ethernet/cisco/enic/
+CISCO VIC LOW LATENCY NIC DRIVER
+M: Upinder Malhi <umalhi@cisco.com>
+S: Supported
+F: drivers/infiniband/hw/usnic
+
CIRRUS LOGIC EP93XX ETHERNET DRIVER
M: Hartley Sweeten <hsweeten@visionengravers.com>
L: netdev@vger.kernel.org
F: drivers/platform/x86/dell-laptop.c
DELL LAPTOP SMM DRIVER
-S: Orphan
+M: Guenter Roeck <linux@roeck-us.net>
F: drivers/char/i8k.c
F: include/uapi/linux/i8k.h
M: Paul Zimmerman <paulz@synopsys.com>
L: linux-usb@vger.kernel.org
S: Maintained
-F: drivers/staging/dwc2/
+F: drivers/usb/dwc2/
DESIGNWARE USB3 DRD IP DRIVER
M: Felipe Balbi <balbi@ti.com>
M: MyungJoo Ham <myungjoo.ham@samsung.com>
M: Chanwoo Choi <cw00.choi@samsung.com>
L: linux-kernel@vger.kernel.org
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/chanwoo/extcon.git
S: Maintained
F: drivers/extcon/
F: Documentation/extcon/
L: linux-fbdev@vger.kernel.org
S: Maintained
F: drivers/video/exynos/exynos_dp*
-F: include/video/exynos_dp*
EXYNOS MIPI DISPLAY DRIVERS
M: Inki Dae <inki.dae@samsung.com>
T: git git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs.git
S: Maintained
F: Documentation/filesystems/f2fs.txt
+F: Documentation/ABI/testing/sysfs-fs-f2fs
F: fs/f2fs/
F: include/linux/f2fs_fs.h
F: Documentation/filesystems/hfs.txt
F: fs/hfs/
+HFSPLUS FILESYSTEM
+L: linux-fsdevel@vger.kernel.org
+S: Orphan
+F: Documentation/filesystems/hfsplus.txt
+F: fs/hfsplus/
+
HGA FRAMEBUFFER DRIVER
M: Ferenc Bakonyi <fero@drama.obuda.kando.hu>
L: linux-nvidia@lists.surfsouth.com
S: Maintained
F: drivers/char/hw_random/ixp4xx-rng.c
- INTEL ETHERNET DRIVERS (e100/e1000/e1000e/igb/igbvf/ixgb/ixgbe/ixgbevf/i40e)
+ INTEL ETHERNET DRIVERS (e100/e1000/e1000e/igb/igbvf/ixgb/ixgbe/ixgbevf/i40e/i40evf)
M: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
M: Jesse Brandeburg <jesse.brandeburg@intel.com>
M: Bruce Allan <bruce.w.allan@intel.com>
M: Greg Rose <gregory.v.rose@intel.com>
M: Alex Duyck <alexander.h.duyck@intel.com>
M: John Ronciak <john.ronciak@intel.com>
+ M: Mitch Williams <mitch.a.williams@intel.com>
L: e1000-devel@lists.sourceforge.net
W: http://www.intel.com/support/feedback.htm
W: http://e1000.sourceforge.net/
F: Documentation/networking/ixgbe.txt
F: Documentation/networking/ixgbevf.txt
F: Documentation/networking/i40e.txt
+ F: Documentation/networking/i40evf.txt
F: drivers/net/ethernet/intel/
INTEL-MID GPIO DRIVER
F: include/uapi/linux/sunrpc/
KERNEL VIRTUAL MACHINE (KVM)
-M: Gleb Natapov <gleb@redhat.com>
+M: Gleb Natapov <gleb@kernel.org>
M: Paolo Bonzini <pbonzini@redhat.com>
L: kvm@vger.kernel.org
W: http://www.linux-kvm.org
F: include/linux/lguest*.h
F: tools/lguest/
+LIBLOCKDEP
+M: Sasha Levin <sasha.levin@oracle.com>
+S: Maintained
+F: tools/lib/lockdep/
+
LINUX FOR IBM pSERIES (RS/6000)
M: Paul Mackerras <paulus@au.ibm.com>
W: http://www.ibm.com/linux/ltc/projects/ppc
F: kernel/*timer*
POWER SUPPLY CLASS/SUBSYSTEM and DRIVERS
-M: Anton Vorontsov <anton@enomsg.org>
+M: Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
M: David Woodhouse <dwmw2@infradead.org>
T: git git://git.infradead.org/battery-2.6.git
S: Maintained
F: drivers/scsi/qla1280.[ch]
QLOGIC QLA2XXX FC-SCSI DRIVER
-M: Andrew Vasquez <andrew.vasquez@qlogic.com>
-M: linux-driver@qlogic.com
+M: qla2xxx-upstream@qlogic.com
L: linux-scsi@vger.kernel.org
S: Supported
F: Documentation/scsi/LICENSE.qla2xxx
S: Maintained
F: drivers/media/tuners/qt1010*
+ QUALCOMM ATHEROS ATH9K WIRELESS DRIVER
+ M: QCA ath9k Development <ath9k-devel@qca.qualcomm.com>
+ L: linux-wireless@vger.kernel.org
+ L: ath9k-devel@lists.ath9k.org
+ W: http://wireless.kernel.org/en/users/Drivers/ath9k
+ S: Supported
+ F: drivers/net/wireless/ath/ath9k/
+
QUALCOMM ATHEROS ATH10K WIRELESS DRIVER
M: Kalle Valo <kvalo@qca.qualcomm.com>
L: ath10k@lists.infradead.org
F: Documentation/RCU/torture.txt
F: kernel/rcu/torture.c
+RCUTORTURE TEST FRAMEWORK
+M: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
+S: Supported
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
+F: tools/testing/selftests/rcutorture
+
RDC R-321X SoC
M: Florian Fainelli <florian@openwrt.org>
S: Maintained
S: Supported
F: drivers/media/i2c/s5c73m3/*
+SAMSUNG SOC CLOCK DRIVERS
+M: Tomasz Figa <t.figa@samsung.com>
+S: Supported
+L: linux-samsung-soc@vger.kernel.org (moderated for non-subscribers)
+F: drivers/clk/samsung/
+
SERIAL DRIVERS
M: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
L: linux-serial@vger.kernel.org
F: drivers/scsi/sr*
SCSI RDMA PROTOCOL (SRP) INITIATOR
-M: David Dillow <dillowda@ornl.gov>
+M: Bart Van Assche <bvanassche@acm.org>
L: linux-rdma@vger.kernel.org
S: Supported
W: http://www.openfabrics.org
SCSI SG DRIVER
M: Doug Gilbert <dgilbert@interlog.com>
L: linux-scsi@vger.kernel.org
-W: http://www.torque.net/sg
+W: http://sg.danny.cz/sg
S: Maintained
+F: Documentation/scsi/scsi-generic.txt
F: drivers/scsi/sg.c
F: include/scsi/sg.h
SFC NETWORK DRIVER
M: Solarflare linux maintainers <linux-net-drivers@solarflare.com>
- M: Ben Hutchings <bhutchings@solarflare.com>
+ M: Shradha Shah <sshah@solarflare.com>
L: netdev@vger.kernel.org
S: Supported
F: drivers/net/ethernet/sfc/
F: drivers/thermal/
F: include/linux/thermal.h
F: include/linux/cpu_cooling.h
+F: Documentation/devicetree/bindings/thermal/
THINGM BLINK(1) USB RGB LED DRIVER
M: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
F: sound/soc/codecs/twl4030*
TI WILINK WIRELESS DRIVERS
- M: Luciano Coelho <luca@coelho.fi>
L: linux-wireless@vger.kernel.org
W: http://wireless.kernel.org/en/users/Drivers/wl12xx
W: http://wireless.kernel.org/en/users/Drivers/wl1251
T: git git://git.kernel.org/pub/scm/linux/kernel/git/luca/wl12xx.git
- S: Maintained
+ S: Orphan
F: drivers/net/wireless/ti/
F: include/linux/wl12xx.h
F: drivers/media/usb/tm6000/
TPM DEVICE DRIVER
-M: Leonidas Da Silva Barbosa <leosilva@linux.vnet.ibm.com>
-M: Ashley Lai <ashley@ashleylai.com>
M: Peter Huewe <peterhuewe@gmx.de>
-M: Rajiv Andrade <mail@srajiv.net>
-W: http://tpmdd.sourceforge.net
+M: Ashley Lai <ashley@ashleylai.com>
M: Marcel Selhorst <tpmdd@selhorst.net>
-M: Sirrix AG <tpmdd@sirrix.com>
-W: http://www.sirrix.com
+W: http://tpmdd.sourceforge.net
L: tpmdd-devel@lists.sourceforge.net (moderated for non-subscribers)
S: Maintained
F: drivers/char/tpm/
M: Boris Ostrovsky <boris.ostrovsky@oracle.com>
M: David Vrabel <david.vrabel@citrix.com>
L: xen-devel@lists.xenproject.org (moderated for non-subscribers)
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip.git
S: Supported
F: arch/x86/xen/
F: drivers/*/xen-*front.c
generic-y += auxvec.h
+generic-y += barrier.h
generic-y += bugs.h
generic-y += bitsperlong.h
generic-y += clkdev.h
generic-y += fb.h
generic-y += ftrace.h
generic-y += hardirq.h
+ generic-y += hash.h
generic-y += hw_irq.h
generic-y += ioctl.h
generic-y += ioctls.h
generic-y += msgbuf.h
generic-y += mutex.h
generic-y += pci.h
-generic-y += percpu.h
generic-y += poll.h
generic-y += posix_types.h
generic-y += resource.h
generic-y += vga.h
generic-y += xor.h
generic-y += preempt.h
+ generic-y += hash.h
header-y += arch-v32/
+generic-y += barrier.h
generic-y += clkdev.h
generic-y += exec.h
+ generic-y += hash.h
generic-y += kvm_para.h
generic-y += linkage.h
generic-y += module.h
header-y += ucontext.h
generic-y += auxvec.h
+generic-y += barrier.h
generic-y += bug.h
generic-y += bugs.h
generic-y += clkdev.h
generic-y += fcntl.h
generic-y += ftrace.h
generic-y += hardirq.h
+ generic-y += hash.h
generic-y += hw_irq.h
generic-y += ioctl.h
generic-y += ioctls.h
+generic-y += barrier.h
generic-y += clkdev.h
generic-y += exec.h
+ generic-y += hash.h
generic-y += trace_clock.h
generic-y += syscalls.h
generic-y += preempt.h
+generic-y += barrier.h
generic-y += clkdev.h
generic-y += exec.h
+ generic-y += hash.h
generic-y += trace_clock.h
generic-y += preempt.h
+generic-y += barrier.h
generic-y += word-at-a-time.h auxvec.h user.h cputime.h emergency-restart.h \
segment.h topology.h vga.h device.h percpu.h hw_irq.h mutex.h \
div64.h irq_regs.h kdebug.h kvm_para.h local64.h local.h param.h \
poll.h xor.h clkdev.h exec.h
generic-y += trace_clock.h
generic-y += preempt.h
+ generic-y += hash.h
header-y +=
+generic-y += barrier.h
generic-y += clkdev.h
+ generic-y += hash.h
generic-y += trace_clock.h
generic-y += xor.h
generic-y += preempt.h
+
generic-y += errno.h
generic-y += exec.h
generic-y += fcntl.h
-generic-y += futex.h
generic-y += hardirq.h
generic-y += ioctl.h
generic-y += irq_regs.h
generic-y += trace_clock.h
generic-y += xor.h
generic-y += preempt.h
+ generic-y += hash.h
int ret;
if (addr->sa_family != AF_IB) {
- ret = rdma_translate_ip(addr, dev_addr);
+ ret = rdma_translate_ip(addr, dev_addr, NULL);
} else {
cma_translate_ib((struct sockaddr_ib *) addr, dev_addr);
ret = 0;
return -EINVAL;
mutex_lock(&lock);
- iboe_addr_get_sgid(dev_addr, &iboe_gid);
+ rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr,
+ &iboe_gid);
+
memcpy(&gid, dev_addr->src_dev_addr +
rdma_addr_gid_offset(dev_addr), sizeof gid);
if (listen_id_priv &&
{
struct ib_qp_attr qp_attr;
int qp_attr_mask, ret;
+ union ib_gid sgid;
mutex_lock(&id_priv->qp_mutex);
if (!id_priv->id.qp) {
if (ret)
goto out;
+ ret = ib_query_gid(id_priv->id.device, id_priv->id.port_num,
+ qp_attr.ah_attr.grh.sgid_index, &sgid);
+ if (ret)
+ goto out;
+
+ if (rdma_node_get_transport(id_priv->cma_dev->device->node_type)
+ == RDMA_TRANSPORT_IB &&
+ rdma_port_get_link_layer(id_priv->id.device, id_priv->id.port_num)
+ == IB_LINK_LAYER_ETHERNET) {
+ ret = rdma_addr_find_smac_by_sgid(&sgid, qp_attr.smac, NULL);
+
+ if (ret)
+ goto out;
+ }
if (conn_param)
qp_attr.max_dest_rd_atomic = conn_param->responder_resources;
ret = ib_modify_qp(id_priv->id.qp, &qp_attr, qp_attr_mask);
else
ret = ib_cm_init_qp_attr(id_priv->cm_id.ib, qp_attr,
qp_attr_mask);
+
if (qp_attr->qp_state == IB_QPS_RTR)
qp_attr->rq_psn = id_priv->seq_num;
break;
struct rdma_id_private *listen_id, *conn_id;
struct rdma_cm_event event;
int offset, ret;
+ u8 smac[ETH_ALEN];
+ u8 alt_smac[ETH_ALEN];
+ u8 *psmac = smac;
+ u8 *palt_smac = alt_smac;
+ int is_iboe = ((rdma_node_get_transport(cm_id->device->node_type) ==
+ RDMA_TRANSPORT_IB) &&
+ (rdma_port_get_link_layer(cm_id->device,
+ ib_event->param.req_rcvd.port) ==
+ IB_LINK_LAYER_ETHERNET));
listen_id = cm_id->context;
if (!cma_check_req_qp_type(&listen_id->id, ib_event))
if (ret)
goto err3;
+ if (is_iboe) {
+ if (ib_event->param.req_rcvd.primary_path != NULL)
+ rdma_addr_find_smac_by_sgid(
+ &ib_event->param.req_rcvd.primary_path->sgid,
+ psmac, NULL);
+ else
+ psmac = NULL;
+ if (ib_event->param.req_rcvd.alternate_path != NULL)
+ rdma_addr_find_smac_by_sgid(
+ &ib_event->param.req_rcvd.alternate_path->sgid,
+ palt_smac, NULL);
+ else
+ palt_smac = NULL;
+ }
/*
* Acquire mutex to prevent user executing rdma_destroy_id()
* while we're accessing the cm_id.
*/
mutex_lock(&lock);
- if (cma_comp(conn_id, RDMA_CM_CONNECT) && (conn_id->id.qp_type != IB_QPT_UD))
+ if (is_iboe)
+ ib_update_cm_av(cm_id, psmac, palt_smac);
+ if (cma_comp(conn_id, RDMA_CM_CONNECT) &&
+ (conn_id->id.qp_type != IB_QPT_UD))
ib_send_cm_mra(cm_id, CMA_CM_MRA_SETTING, NULL, 0);
mutex_unlock(&lock);
mutex_unlock(&conn_id->handler_mutex);
mutex_lock_nested(&conn_id->handler_mutex, SINGLE_DEPTH_NESTING);
conn_id->state = RDMA_CM_CONNECT;
- ret = rdma_translate_ip(laddr, &conn_id->id.route.addr.dev_addr);
+ ret = rdma_translate_ip(laddr, &conn_id->id.route.addr.dev_addr, NULL);
if (ret) {
mutex_unlock(&conn_id->handler_mutex);
rdma_destroy_id(new_cm_id);
struct cma_work *work;
int ret;
struct net_device *ndev = NULL;
- u16 vid;
+
work = kzalloc(sizeof *work, GFP_KERNEL);
if (!work)
goto err2;
}
- vid = rdma_vlan_dev_vlan_id(ndev);
+ route->path_rec->vlan_id = rdma_vlan_dev_vlan_id(ndev);
+ memcpy(route->path_rec->dmac, addr->dev_addr.dst_dev_addr, ETH_ALEN);
+ memcpy(route->path_rec->smac, ndev->dev_addr, ndev->addr_len);
- iboe_mac_vlan_to_ll(&route->path_rec->sgid, addr->dev_addr.src_dev_addr, vid);
- iboe_mac_vlan_to_ll(&route->path_rec->dgid, addr->dev_addr.dst_dev_addr, vid);
+ rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr,
+ &route->path_rec->sgid);
+ rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.dst_addr,
+ &route->path_rec->dgid);
route->path_rec->hop_limit = 1;
route->path_rec->reversible = 1;
RDMA_CM_ADDR_RESOLVED))
goto out;
+ memcpy(cma_src_addr(id_priv), src_addr, rdma_addr_size(src_addr));
if (!status && !id_priv->cma_dev)
status = cma_acquire_dev(id_priv, NULL);
goto out;
event.event = RDMA_CM_EVENT_ADDR_ERROR;
event.status = status;
- } else {
- memcpy(cma_src_addr(id_priv), src_addr, rdma_addr_size(src_addr));
+ } else
event.event = RDMA_CM_EVENT_ADDR_RESOLVED;
- }
if (id_priv->id.event_handler(&id_priv->id, &event)) {
cma_exch(id_priv, RDMA_CM_DESTROYING);
inet_get_local_port_range(&init_net, &low, &high);
remaining = (high - low) + 1;
- rover = net_random() % remaining + low;
+ rover = prandom_u32() % remaining + low;
retry:
if (last_used_port != rover &&
!idr_find(ps, (unsigned short) rover)) {
return 0;
sin6 = (struct sockaddr_in6 *) addr;
- if ((ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL) &&
- !sin6->sin6_scope_id)
+
+ if (!(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL))
+ return 0;
+
+ if (!sin6->sin6_scope_id)
return -EINVAL;
dev_addr->bound_dev_if = sin6->sin6_scope_id;
if (ret)
goto err1;
+ memcpy(cma_src_addr(id_priv), addr, rdma_addr_size(addr));
if (!cma_any_addr(addr)) {
ret = cma_translate_addr(addr, &id->route.addr.dev_addr);
if (ret)
goto err1;
}
- memcpy(cma_src_addr(id_priv), addr, rdma_addr_size(addr));
if (!(id_priv->options & (1 << CMA_OPTION_AFONLY))) {
if (addr->sa_family == AF_INET)
id_priv->afonly = 1;
err = -EINVAL;
goto out2;
}
- iboe_addr_get_sgid(dev_addr, &mc->multicast.ib->rec.port_gid);
+ rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr,
+ &mc->multicast.ib->rec.port_gid);
work->id = id_priv;
work->mc = mc;
INIT_WORK(&work->work, iboe_mcast_work_handler);
#include <net/pkt_sched.h>
#include <linux/rculist.h>
#include <net/flow_keys.h>
- #include <linux/reciprocal_div.h>
#include "bonding.h"
#include "bond_3ad.h"
#include "bond_alb.h"
/*---------------------------- Module parameters ----------------------------*/
/* monitor all links that often (in milliseconds). <=0 disables monitoring */
- #define BOND_LINK_MON_INTERV 0
- #define BOND_LINK_ARP_INTERV 0
static int max_bonds = BOND_DEFAULT_MAX_BONDS;
static int tx_queues = BOND_DEFAULT_TX_QUEUES;
static int num_peer_notif = 1;
- static int miimon = BOND_LINK_MON_INTERV;
+ static int miimon;
static int updelay;
static int downdelay;
static int use_carrier = 1;
static int min_links;
static char *ad_select;
static char *xmit_hash_policy;
- static int arp_interval = BOND_LINK_ARP_INTERV;
+ static int arp_interval;
static char *arp_ip_target[BOND_MAX_ARP_TARGETS];
static char *arp_validate;
static char *arp_all_targets;
static struct bond_params bonding_defaults;
static int resend_igmp = BOND_DEFAULT_RESEND_IGMP;
static int packets_per_slave = 1;
+ static int lp_interval = BOND_ALB_DEFAULT_LP_INTERVAL;
module_param(max_bonds, int, 0);
MODULE_PARM_DESC(max_bonds, "Max number of bonded devices");
MODULE_PARM_DESC(packets_per_slave, "Packets to send per slave in balance-rr "
"mode; 0 for a random slave, 1 packet per "
"slave (default), >1 packets per slave.");
+ module_param(lp_interval, uint, 0);
+ MODULE_PARM_DESC(lp_interval, "The number of seconds between instances where "
+ "the bonding driver sends learning packets to "
+ "each slaves peer switch. The default is 1.");
/*----------------------------- Global variables ----------------------------*/
static int xmit_hashtype = BOND_XMIT_POLICY_LAYER2;
static int lacp_fast;
- const struct bond_parm_tbl bond_lacp_tbl[] = {
- { "slow", AD_LACP_SLOW},
- { "fast", AD_LACP_FAST},
- { NULL, -1},
- };
-
- const struct bond_parm_tbl bond_mode_tbl[] = {
- { "balance-rr", BOND_MODE_ROUNDROBIN},
- { "active-backup", BOND_MODE_ACTIVEBACKUP},
- { "balance-xor", BOND_MODE_XOR},
- { "broadcast", BOND_MODE_BROADCAST},
- { "802.3ad", BOND_MODE_8023AD},
- { "balance-tlb", BOND_MODE_TLB},
- { "balance-alb", BOND_MODE_ALB},
- { NULL, -1},
- };
-
- const struct bond_parm_tbl xmit_hashtype_tbl[] = {
- { "layer2", BOND_XMIT_POLICY_LAYER2},
- { "layer3+4", BOND_XMIT_POLICY_LAYER34},
- { "layer2+3", BOND_XMIT_POLICY_LAYER23},
- { "encap2+3", BOND_XMIT_POLICY_ENCAP23},
- { "encap3+4", BOND_XMIT_POLICY_ENCAP34},
- { NULL, -1},
- };
-
- const struct bond_parm_tbl arp_all_targets_tbl[] = {
- { "any", BOND_ARP_TARGETS_ANY},
- { "all", BOND_ARP_TARGETS_ALL},
- { NULL, -1},
- };
-
- const struct bond_parm_tbl arp_validate_tbl[] = {
- { "none", BOND_ARP_VALIDATE_NONE},
- { "active", BOND_ARP_VALIDATE_ACTIVE},
- { "backup", BOND_ARP_VALIDATE_BACKUP},
- { "all", BOND_ARP_VALIDATE_ALL},
- { NULL, -1},
- };
-
- const struct bond_parm_tbl fail_over_mac_tbl[] = {
- { "none", BOND_FOM_NONE},
- { "active", BOND_FOM_ACTIVE},
- { "follow", BOND_FOM_FOLLOW},
- { NULL, -1},
- };
-
- const struct bond_parm_tbl pri_reselect_tbl[] = {
- { "always", BOND_PRI_RESELECT_ALWAYS},
- { "better", BOND_PRI_RESELECT_BETTER},
- { "failure", BOND_PRI_RESELECT_FAILURE},
- { NULL, -1},
- };
-
- struct bond_parm_tbl ad_select_tbl[] = {
- { "stable", BOND_AD_STABLE},
- { "bandwidth", BOND_AD_BANDWIDTH},
- { "count", BOND_AD_COUNT},
- { NULL, -1},
- };
-
/*-------------------------- Forward declarations ---------------------------*/
static int bond_init(struct net_device *bond_dev);
* @skb: hw accel VLAN tagged skb to transmit
* @slave_dev: slave that is supposed to xmit this skbuff
*/
- int bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb,
+ void bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb,
struct net_device *slave_dev)
{
skb->dev = slave_dev;
bond_netpoll_send_skb(bond_get_slave_by_dev(bond, slave_dev), skb);
else
dev_queue_xmit(skb);
-
- return 0;
}
/*
return;
}
+ const char *bond_slave_link_status(s8 link)
+ {
+ switch (link) {
+ case BOND_LINK_UP:
+ return "up";
+ case BOND_LINK_FAIL:
+ return "going down";
+ case BOND_LINK_DOWN:
+ return "down";
+ case BOND_LINK_BACK:
+ return "going back";
+ default:
+ return "unknown";
+ }
+ }
+
/*
* if <dev> supports MII link status reporting, check its link status.
*
* device and retransmit an IGMP JOIN request to the current active
* slave.
*/
- static void bond_resend_igmp_join_requests(struct bonding *bond)
+ static void bond_resend_igmp_join_requests_delayed(struct work_struct *work)
{
+ struct bonding *bond = container_of(work, struct bonding,
+ mcast_work.work);
+
if (!rtnl_trylock()) {
queue_delayed_work(bond->wq, &bond->mcast_work, 1);
return;
}
call_netdevice_notifiers(NETDEV_RESEND_IGMP, bond->dev);
- rtnl_unlock();
- /* We use curr_slave_lock to protect against concurrent access to
- * igmp_retrans from multiple running instances of this function and
- * bond_change_active_slave
- */
- write_lock_bh(&bond->curr_slave_lock);
if (bond->igmp_retrans > 1) {
bond->igmp_retrans--;
queue_delayed_work(bond->wq, &bond->mcast_work, HZ/5);
}
- write_unlock_bh(&bond->curr_slave_lock);
- }
-
- static void bond_resend_igmp_join_requests_delayed(struct work_struct *work)
- {
- struct bonding *bond = container_of(work, struct bonding,
- mcast_work.work);
-
- bond_resend_igmp_join_requests(bond);
+ rtnl_unlock();
}
/* Flush bond's hardware addresses from slave
*
* Perform special MAC address swapping for fail_over_mac settings
*
- * Called with RTNL, bond->lock for read, curr_slave_lock for write_bh.
+ * Called with RTNL, curr_slave_lock for write_bh.
*/
static void bond_do_fail_over_mac(struct bonding *bond,
struct slave *new_active,
struct slave *old_active)
__releases(&bond->curr_slave_lock)
- __releases(&bond->lock)
- __acquires(&bond->lock)
__acquires(&bond->curr_slave_lock)
{
u8 tmp_mac[ETH_ALEN];
case BOND_FOM_ACTIVE:
if (new_active) {
write_unlock_bh(&bond->curr_slave_lock);
- read_unlock(&bond->lock);
bond_set_dev_addr(bond->dev, new_active->dev);
- read_lock(&bond->lock);
write_lock_bh(&bond->curr_slave_lock);
}
break;
return;
write_unlock_bh(&bond->curr_slave_lock);
- read_unlock(&bond->lock);
if (old_active) {
memcpy(tmp_mac, new_active->dev->dev_addr, ETH_ALEN);
pr_err("%s: Error %d setting MAC of slave %s\n",
bond->dev->name, -rv, new_active->dev->name);
out:
- read_lock(&bond->lock);
write_lock_bh(&bond->curr_slave_lock);
break;
default:
static bool bond_should_notify_peers(struct bonding *bond)
{
- struct slave *slave = bond->curr_active_slave;
+ struct slave *slave;
+
+ rcu_read_lock();
+ slave = rcu_dereference(bond->curr_active_slave);
+ rcu_read_unlock();
pr_debug("bond_should_notify_peers: bond %s slave %s\n",
bond->dev->name, slave ? slave->dev->name : "NULL");
* because it is apparently the best available slave we have, even though its
* updelay hasn't timed out yet.
*
- * If new_active is not NULL, caller must hold bond->lock for read and
- * curr_slave_lock for write_bh.
+ * If new_active is not NULL, caller must hold curr_slave_lock for write_bh.
*/
void bond_change_active_slave(struct bonding *bond, struct slave *new_active)
{
}
write_unlock_bh(&bond->curr_slave_lock);
- read_unlock(&bond->lock);
call_netdevice_notifiers(NETDEV_BONDING_FAILOVER, bond->dev);
if (should_notify_peers)
call_netdevice_notifiers(NETDEV_NOTIFY_PEERS,
bond->dev);
- read_lock(&bond->lock);
write_lock_bh(&bond->curr_slave_lock);
}
}
* - The primary_slave has got its link back.
* - A slave has got its link back and there's no old curr_active_slave.
*
- * Caller must hold bond->lock for read and curr_slave_lock for write_bh.
+ * Caller must hold curr_slave_lock for write_bh.
*/
void bond_select_active_slave(struct bonding *bond)
{
goto err_unregister;
}
+ res = bond_sysfs_slave_add(new_slave);
+ if (res) {
+ pr_debug("Error %d calling bond_sysfs_slave_add\n", res);
+ goto err_upper_unlink;
+ }
+
bond->slave_cnt++;
bond_compute_features(bond);
bond_set_carrier(bond);
if (USES_PRIMARY(bond->params.mode)) {
- read_lock(&bond->lock);
write_lock_bh(&bond->curr_slave_lock);
bond_select_active_slave(bond);
write_unlock_bh(&bond->curr_slave_lock);
- read_unlock(&bond->lock);
}
pr_info("%s: enslaving %s as a%s interface with a%s link.\n",
return 0;
/* Undo stages on error */
+ err_upper_unlink:
+ bond_upper_dev_unlink(bond_dev, slave_dev);
+
err_unregister:
netdev_rx_handler_unregister(slave_dev);
bond_hw_addr_flush(bond_dev, slave_dev);
vlan_vids_del_by_dev(slave_dev, bond_dev);
- write_lock_bh(&bond->lock);
if (bond->primary_slave == new_slave)
bond->primary_slave = NULL;
if (bond->curr_active_slave == new_slave) {
- bond_change_active_slave(bond, NULL);
- write_unlock_bh(&bond->lock);
- read_lock(&bond->lock);
write_lock_bh(&bond->curr_slave_lock);
+ bond_change_active_slave(bond, NULL);
bond_select_active_slave(bond);
write_unlock_bh(&bond->curr_slave_lock);
- read_unlock(&bond->lock);
- } else {
- write_unlock_bh(&bond->lock);
}
slave_disable_netpoll(new_slave);
err_undo_flags:
/* Enslave of first slave has failed and we need to fix master's mac */
if (!bond_has_slaves(bond) &&
- ether_addr_equal(bond_dev->dev_addr, slave_dev->dev_addr))
+ ether_addr_equal_64bits(bond_dev->dev_addr, slave_dev->dev_addr))
eth_hw_addr_random(bond_dev);
return res;
}
block_netpoll_tx();
- write_lock_bh(&bond->lock);
slave = bond_get_slave_by_dev(bond, slave_dev);
if (!slave) {
/* not a slave of this bond */
pr_info("%s: %s not enslaved\n",
bond_dev->name, slave_dev->name);
- write_unlock_bh(&bond->lock);
unblock_netpoll_tx();
return -EINVAL;
}
- write_unlock_bh(&bond->lock);
-
/* release the slave from its bond */
bond->slave_cnt--;
+ bond_sysfs_slave_del(slave);
+
bond_upper_dev_unlink(bond_dev, slave_dev);
/* unregister rx_handler early so bond_handle_frame wouldn't be called
* for this slave anymore.
write_lock_bh(&bond->lock);
/* Inform AD package of unbinding of slave. */
- if (bond->params.mode == BOND_MODE_8023AD) {
- /* must be called before the slave is
- * detached from the list
- */
+ if (bond->params.mode == BOND_MODE_8023AD)
bond_3ad_unbind_slave(slave);
- }
+
+ write_unlock_bh(&bond->lock);
pr_info("%s: releasing %s interface %s\n",
bond_dev->name,
bond->current_arp_slave = NULL;
if (!all && !bond->params.fail_over_mac) {
- if (ether_addr_equal(bond_dev->dev_addr, slave->perm_hwaddr) &&
+ if (ether_addr_equal_64bits(bond_dev->dev_addr, slave->perm_hwaddr) &&
bond_has_slaves(bond))
pr_warn("%s: Warning: the permanent HWaddr of %s - %pM - is still in use by %s. Set the HWaddr of %s to a different address to avoid conflicts.\n",
bond_dev->name, slave_dev->name,
if (bond->primary_slave == slave)
bond->primary_slave = NULL;
- if (oldcurrent == slave)
+ if (oldcurrent == slave) {
+ write_lock_bh(&bond->curr_slave_lock);
bond_change_active_slave(bond, NULL);
+ write_unlock_bh(&bond->curr_slave_lock);
+ }
if (bond_is_lb(bond)) {
/* Must be called only after the slave has been
* has been cleared (if our_slave == old_current),
* but before a new active slave is selected.
*/
- write_unlock_bh(&bond->lock);
bond_alb_deinit_slave(bond, slave);
- write_lock_bh(&bond->lock);
}
if (all) {
- rcu_assign_pointer(bond->curr_active_slave, NULL);
+ RCU_INIT_POINTER(bond->curr_active_slave, NULL);
} else if (oldcurrent == slave) {
/*
* Note that we hold RTNL over this sequence, so there
* is no concern that another slave add/remove event
* will interfere.
*/
- write_unlock_bh(&bond->lock);
- read_lock(&bond->lock);
write_lock_bh(&bond->curr_slave_lock);
bond_select_active_slave(bond);
write_unlock_bh(&bond->curr_slave_lock);
- read_unlock(&bond->lock);
- write_lock_bh(&bond->lock);
}
if (!bond_has_slaves(bond)) {
}
}
- write_unlock_bh(&bond->lock);
unblock_netpoll_tx();
synchronize_rcu();
ignore_updelay = !bond->curr_active_slave ? true : false;
- bond_for_each_slave(bond, slave, iter) {
+ bond_for_each_slave_rcu(bond, slave, iter) {
slave->new_link = BOND_LINK_NOCHANGE;
link_state = bond_check_dev_link(bond, slave->dev, 0);
* an acquisition of appropriate locks followed by a commit phase to
* implement whatever link state changes are indicated.
*/
- void bond_mii_monitor(struct work_struct *work)
+ static void bond_mii_monitor(struct work_struct *work)
{
struct bonding *bond = container_of(work, struct bonding,
mii_work.work);
bool should_notify_peers = false;
unsigned long delay;
- read_lock(&bond->lock);
-
delay = msecs_to_jiffies(bond->params.miimon);
if (!bond_has_slaves(bond))
goto re_arm;
+ rcu_read_lock();
+
should_notify_peers = bond_should_notify_peers(bond);
if (bond_miimon_inspect(bond)) {
- read_unlock(&bond->lock);
+ rcu_read_unlock();
/* Race avoidance with bond_close cancel of workqueue */
if (!rtnl_trylock()) {
- read_lock(&bond->lock);
delay = 1;
should_notify_peers = false;
goto re_arm;
}
- read_lock(&bond->lock);
-
bond_miimon_commit(bond);
- read_unlock(&bond->lock);
rtnl_unlock(); /* might sleep, hold no other locks */
- read_lock(&bond->lock);
- }
+ } else
+ rcu_read_unlock();
re_arm:
if (bond->params.miimon)
queue_delayed_work(bond->wq, &bond->mii_work, delay);
- read_unlock(&bond->lock);
-
if (should_notify_peers) {
if (!rtnl_trylock())
return;
* arp is transmitted to generate traffic. see activebackup_arp_monitor for
* arp monitoring in active backup mode.
*/
- void bond_loadbalance_arp_mon(struct work_struct *work)
+ static void bond_loadbalance_arp_mon(struct work_struct *work)
{
struct bonding *bond = container_of(work, struct bonding,
arp_work.work);
struct list_head *iter;
int do_failover = 0;
- read_lock(&bond->lock);
-
if (!bond_has_slaves(bond))
goto re_arm;
- oldcurrent = bond->curr_active_slave;
+ rcu_read_lock();
+
+ oldcurrent = ACCESS_ONCE(bond->curr_active_slave);
/* see if any of the previous devices are up now (i.e. they have
* xmt and rcv traffic). the curr_active_slave does not come into
* the picture unless it is null. also, slave->jiffies is not needed
* TODO: what about up/down delay in arp mode? it wasn't here before
* so it can wait
*/
- bond_for_each_slave(bond, slave, iter) {
+ bond_for_each_slave_rcu(bond, slave, iter) {
unsigned long trans_start = dev_trans_start(slave->dev);
if (slave->link != BOND_LINK_UP) {
bond_arp_send_all(bond, slave);
}
+ rcu_read_unlock();
+
if (do_failover) {
+ /* the bond_select_active_slave must hold RTNL
+ * and curr_slave_lock for write.
+ */
+ if (!rtnl_trylock())
+ goto re_arm;
block_netpoll_tx();
write_lock_bh(&bond->curr_slave_lock);
write_unlock_bh(&bond->curr_slave_lock);
unblock_netpoll_tx();
+ rtnl_unlock();
}
re_arm:
if (bond->params.arp_interval)
queue_delayed_work(bond->wq, &bond->arp_work,
msecs_to_jiffies(bond->params.arp_interval));
-
- read_unlock(&bond->lock);
}
/*
* place for the slave. Returns 0 if no changes are found, >0 if changes
* to link states must be committed.
*
- * Called with bond->lock held for read.
+ * Called with rcu_read_lock hold.
*/
static int bond_ab_arp_inspect(struct bonding *bond)
{
struct slave *slave;
int commit = 0;
- bond_for_each_slave(bond, slave, iter) {
+ bond_for_each_slave_rcu(bond, slave, iter) {
slave->new_link = BOND_LINK_NOCHANGE;
last_rx = slave_last_rx(bond, slave);
* Called to commit link state changes noted by inspection step of
* active-backup mode ARP monitor.
*
- * Called with RTNL and bond->lock for read.
+ * Called with RTNL hold.
*/
static void bond_ab_arp_commit(struct bonding *bond)
{
/*
* Send ARP probes for active-backup mode ARP monitor.
*
- * Called with bond->lock held for read.
+ * Called with rcu_read_lock hold.
*/
static void bond_ab_arp_probe(struct bonding *bond)
{
- struct slave *slave, *before = NULL, *new_slave = NULL;
+ struct slave *slave, *before = NULL, *new_slave = NULL,
+ *curr_arp_slave = rcu_dereference(bond->current_arp_slave);
struct list_head *iter;
bool found = false;
read_lock(&bond->curr_slave_lock);
- if (bond->current_arp_slave && bond->curr_active_slave)
+ if (curr_arp_slave && bond->curr_active_slave)
pr_info("PROBE: c_arp %s && cas %s BAD\n",
- bond->current_arp_slave->dev->name,
+ curr_arp_slave->dev->name,
bond->curr_active_slave->dev->name);
if (bond->curr_active_slave) {
* for becoming the curr_active_slave
*/
- if (!bond->current_arp_slave) {
- bond->current_arp_slave = bond_first_slave(bond);
- if (!bond->current_arp_slave)
+ if (!curr_arp_slave) {
+ curr_arp_slave = bond_first_slave_rcu(bond);
+ if (!curr_arp_slave)
return;
}
- bond_set_slave_inactive_flags(bond->current_arp_slave);
+ bond_set_slave_inactive_flags(curr_arp_slave);
- bond_for_each_slave(bond, slave, iter) {
+ bond_for_each_slave_rcu(bond, slave, iter) {
if (!found && !before && IS_UP(slave->dev))
before = slave;
pr_info("%s: backup interface %s is now down.\n",
bond->dev->name, slave->dev->name);
}
- if (slave == bond->current_arp_slave)
+ if (slave == curr_arp_slave)
found = true;
}
bond_set_slave_active_flags(new_slave);
bond_arp_send_all(bond, new_slave);
new_slave->jiffies = jiffies;
- bond->current_arp_slave = new_slave;
-
+ rcu_assign_pointer(bond->current_arp_slave, new_slave);
}
- void bond_activebackup_arp_mon(struct work_struct *work)
+ static void bond_activebackup_arp_mon(struct work_struct *work)
{
struct bonding *bond = container_of(work, struct bonding,
arp_work.work);
bool should_notify_peers = false;
int delta_in_ticks;
- read_lock(&bond->lock);
-
delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval);
if (!bond_has_slaves(bond))
goto re_arm;
+ rcu_read_lock();
+
should_notify_peers = bond_should_notify_peers(bond);
if (bond_ab_arp_inspect(bond)) {
- read_unlock(&bond->lock);
+ rcu_read_unlock();
/* Race avoidance with bond_close flush of workqueue */
if (!rtnl_trylock()) {
- read_lock(&bond->lock);
delta_in_ticks = 1;
should_notify_peers = false;
goto re_arm;
}
- read_lock(&bond->lock);
-
bond_ab_arp_commit(bond);
- read_unlock(&bond->lock);
rtnl_unlock();
- read_lock(&bond->lock);
+ rcu_read_lock();
}
bond_ab_arp_probe(bond);
+ rcu_read_unlock();
re_arm:
if (bond->params.arp_interval)
queue_delayed_work(bond->wq, &bond->arp_work, delta_in_ticks);
- read_unlock(&bond->lock);
-
if (should_notify_peers) {
if (!rtnl_trylock())
return;
*/
break;
case NETDEV_CHANGENAME:
- /*
- * TODO: handle changing the primary's name
- */
+ /* we don't care if we don't have primary set */
+ if (!USES_PRIMARY(bond->params.mode) ||
+ !bond->params.primary[0])
+ break;
+
+ if (slave == bond->primary_slave) {
+ /* slave's name changed - he's no longer primary */
+ bond->primary_slave = NULL;
+ } else if (!strcmp(slave_dev->name, bond->params.primary)) {
+ /* we have a new primary slave */
+ bond->primary_slave = slave;
+ } else { /* we didn't change primary - exit */
+ break;
+ }
+
+ pr_info("%s: Primary slave changed to %s, reselecting active slave.\n",
+ bond->dev->name, bond->primary_slave ? slave_dev->name :
+ "none");
+ write_lock_bh(&bond->curr_slave_lock);
+ bond_select_active_slave(bond);
+ write_unlock_bh(&bond->curr_slave_lock);
break;
case NETDEV_FEAT_CHANGE:
bond_compute_features(bond);
struct ifslave k_sinfo;
struct ifslave __user *u_sinfo = NULL;
struct mii_ioctl_data *mii = NULL;
+ struct bond_opt_value newval;
struct net *net;
int res = 0;
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
return -EPERM;
- slave_dev = dev_get_by_name(net, ifr->ifr_slave);
+ slave_dev = __dev_get_by_name(net, ifr->ifr_slave);
pr_debug("slave_dev=%p:\n", slave_dev);
if (!slave_dev)
- res = -ENODEV;
- else {
- pr_debug("slave_dev->name=%s:\n", slave_dev->name);
- switch (cmd) {
- case BOND_ENSLAVE_OLD:
- case SIOCBONDENSLAVE:
- res = bond_enslave(bond_dev, slave_dev);
- break;
- case BOND_RELEASE_OLD:
- case SIOCBONDRELEASE:
- res = bond_release(bond_dev, slave_dev);
- break;
- case BOND_SETHWADDR_OLD:
- case SIOCBONDSETHWADDR:
- bond_set_dev_addr(bond_dev, slave_dev);
- res = 0;
- break;
- case BOND_CHANGE_ACTIVE_OLD:
- case SIOCBONDCHANGEACTIVE:
- res = bond_option_active_slave_set(bond, slave_dev);
- break;
- default:
- res = -EOPNOTSUPP;
- }
+ return -ENODEV;
- dev_put(slave_dev);
+ pr_debug("slave_dev->name=%s:\n", slave_dev->name);
+ switch (cmd) {
+ case BOND_ENSLAVE_OLD:
+ case SIOCBONDENSLAVE:
+ res = bond_enslave(bond_dev, slave_dev);
+ break;
+ case BOND_RELEASE_OLD:
+ case SIOCBONDRELEASE:
+ res = bond_release(bond_dev, slave_dev);
+ break;
+ case BOND_SETHWADDR_OLD:
+ case SIOCBONDSETHWADDR:
+ bond_set_dev_addr(bond_dev, slave_dev);
+ res = 0;
+ break;
+ case BOND_CHANGE_ACTIVE_OLD:
+ case SIOCBONDCHANGEACTIVE:
+ bond_opt_initstr(&newval, slave_dev->name);
+ res = __bond_opt_set(bond, BOND_OPT_ACTIVE_SLAVE, &newval);
+ break;
+ default:
+ res = -EOPNOTSUPP;
}
return res;
* it fails, it tries to find the first available slave for transmission.
* The skb is consumed in all cases, thus the function is void.
*/
- void bond_xmit_slave_id(struct bonding *bond, struct sk_buff *skb, int slave_id)
+ static void bond_xmit_slave_id(struct bonding *bond, struct sk_buff *skb, int slave_id)
{
struct list_head *iter;
struct slave *slave;
*/
static u32 bond_rr_gen_slave_id(struct bonding *bond)
{
- int packets_per_slave = bond->params.packets_per_slave;
u32 slave_id;
+ struct reciprocal_value reciprocal_packets_per_slave;
+ int packets_per_slave = bond->params.packets_per_slave;
switch (packets_per_slave) {
case 0:
slave_id = bond->rr_tx_counter;
break;
default:
+ reciprocal_packets_per_slave =
+ bond->params.reciprocal_packets_per_slave;
slave_id = reciprocal_divide(bond->rr_tx_counter,
- packets_per_slave);
+ reciprocal_packets_per_slave);
break;
}
bond->rr_tx_counter++;
struct sk_buff *skb)
{
struct slave *slave = NULL;
- struct slave *check_slave;
struct list_head *iter;
- int res = 1;
if (!skb->queue_mapping)
return 1;
/* Find out if any slaves have the same mapping as this skb. */
- bond_for_each_slave_rcu(bond, check_slave, iter) {
- if (check_slave->queue_id == skb->queue_mapping) {
- slave = check_slave;
+ bond_for_each_slave_rcu(bond, slave, iter) {
+ if (slave->queue_id == skb->queue_mapping) {
+ if (slave_can_tx(slave)) {
+ bond_dev_queue_xmit(bond, skb, slave->dev);
+ return 0;
+ }
+ /* If the slave isn't UP, use default transmit policy. */
break;
}
}
- /* If the slave isn't UP, use default transmit policy. */
- if (slave && slave->queue_id && IS_UP(slave->dev) &&
- (slave->link == BOND_LINK_UP)) {
- res = bond_dev_queue_xmit(bond, skb, slave->dev);
- }
-
- return res;
+ return 1;
}
* capable
*/
+ /* Don't allow bond devices to change network namespaces. */
+ bond_dev->features |= NETIF_F_NETNS_LOCAL;
+
bond_dev->hw_features = BOND_VLAN_FEATURES |
NETIF_F_HW_VLAN_CTAG_TX |
NETIF_F_HW_VLAN_CTAG_RX |
/*------------------------- Module initialization ---------------------------*/
+ int bond_parm_tbl_lookup(int mode, const struct bond_parm_tbl *tbl)
+ {
+ int i;
+
+ for (i = 0; tbl[i].modename; i++)
+ if (mode == tbl[i].mode)
+ return tbl[i].mode;
+
+ return -1;
+ }
+
+ static int bond_parm_tbl_lookup_name(const char *modename,
+ const struct bond_parm_tbl *tbl)
+ {
+ int i;
+
+ for (i = 0; tbl[i].modename; i++)
+ if (strcmp(modename, tbl[i].modename) == 0)
+ return tbl[i].mode;
+
+ return -1;
+ }
+
/*
* Convert string input module parms. Accept either the
* number of the mode or its string name. A bit complicated because
*/
int bond_parse_parm(const char *buf, const struct bond_parm_tbl *tbl)
{
- int modeint = -1, i, rv;
- char *p, modestr[BOND_MAX_MODENAME_LEN + 1] = { 0, };
+ int modeint;
+ char *p, modestr[BOND_MAX_MODENAME_LEN + 1];
for (p = (char *)buf; *p; p++)
if (!(isdigit(*p) || isspace(*p)))
break;
- if (*p)
- rv = sscanf(buf, "%20s", modestr);
- else
- rv = sscanf(buf, "%d", &modeint);
-
- if (!rv)
- return -1;
-
- for (i = 0; tbl[i].modename; i++) {
- if (modeint == tbl[i].mode)
- return tbl[i].mode;
- if (strcmp(modestr, tbl[i].modename) == 0)
- return tbl[i].mode;
- }
+ if (*p && sscanf(buf, "%20s", modestr) != 0)
+ return bond_parm_tbl_lookup_name(modestr, tbl);
+ else if (sscanf(buf, "%d", &modeint) != 0)
+ return bond_parm_tbl_lookup(modeint, tbl);
return -1;
}
static int bond_check_params(struct bond_params *params)
{
int arp_validate_value, fail_over_mac_value, primary_reselect_value, i;
+ struct bond_opt_value newval, *valptr;
int arp_all_targets_value;
/*
* Convert string parameters.
*/
if (mode) {
- bond_mode = bond_parse_parm(mode, bond_mode_tbl);
- if (bond_mode == -1) {
- pr_err("Error: Invalid bonding mode \"%s\"\n",
- mode == NULL ? "NULL" : mode);
+ bond_opt_initstr(&newval, mode);
+ valptr = bond_opt_parse(bond_opt_get(BOND_OPT_MODE), &newval);
+ if (!valptr) {
+ pr_err("Error: Invalid bonding mode \"%s\"\n", mode);
return -EINVAL;
}
+ bond_mode = valptr->value;
}
if (xmit_hash_policy) {
pr_info("xmit_hash_policy param is irrelevant in mode %s\n",
bond_mode_name(bond_mode));
} else {
- xmit_hashtype = bond_parse_parm(xmit_hash_policy,
- xmit_hashtype_tbl);
- if (xmit_hashtype == -1) {
+ bond_opt_initstr(&newval, xmit_hash_policy);
+ valptr = bond_opt_parse(bond_opt_get(BOND_OPT_XMIT_HASH),
+ &newval);
+ if (!valptr) {
pr_err("Error: Invalid xmit_hash_policy \"%s\"\n",
- xmit_hash_policy == NULL ? "NULL" :
xmit_hash_policy);
return -EINVAL;
}
+ xmit_hashtype = valptr->value;
}
}
pr_info("lacp_rate param is irrelevant in mode %s\n",
bond_mode_name(bond_mode));
} else {
- lacp_fast = bond_parse_parm(lacp_rate, bond_lacp_tbl);
- if (lacp_fast == -1) {
+ bond_opt_initstr(&newval, lacp_rate);
+ valptr = bond_opt_parse(bond_opt_get(BOND_OPT_LACP_RATE),
+ &newval);
+ if (!valptr) {
pr_err("Error: Invalid lacp rate \"%s\"\n",
- lacp_rate == NULL ? "NULL" : lacp_rate);
+ lacp_rate);
return -EINVAL;
}
+ lacp_fast = valptr->value;
}
}
if (ad_select) {
- params->ad_select = bond_parse_parm(ad_select, ad_select_tbl);
- if (params->ad_select == -1) {
- pr_err("Error: Invalid ad_select \"%s\"\n",
- ad_select == NULL ? "NULL" : ad_select);
+ bond_opt_initstr(&newval, lacp_rate);
+ valptr = bond_opt_parse(bond_opt_get(BOND_OPT_AD_SELECT),
+ &newval);
+ if (!valptr) {
+ pr_err("Error: Invalid ad_select \"%s\"\n", ad_select);
return -EINVAL;
}
-
- if (bond_mode != BOND_MODE_8023AD) {
+ params->ad_select = valptr->value;
+ if (bond_mode != BOND_MODE_8023AD)
pr_warning("ad_select param only affects 802.3ad mode\n");
- }
} else {
params->ad_select = BOND_AD_STABLE;
}
}
if (miimon < 0) {
- pr_warning("Warning: miimon module parameter (%d), not in range 0-%d, so it was reset to %d\n",
- miimon, INT_MAX, BOND_LINK_MON_INTERV);
- miimon = BOND_LINK_MON_INTERV;
+ pr_warning("Warning: miimon module parameter (%d), not in range 0-%d, so it was reset to 0\n",
+ miimon, INT_MAX);
+ miimon = 0;
}
if (updelay < 0) {
num_peer_notif = 1;
}
- /* reset values for 802.3ad */
- if (bond_mode == BOND_MODE_8023AD) {
+ /* reset values for 802.3ad/TLB/ALB */
+ if (BOND_NO_USES_ARP(bond_mode)) {
if (!miimon) {
pr_warning("Warning: miimon must be specified, otherwise bonding will not detect link failure, speed and duplex which are essential for 802.3ad operation\n");
pr_warning("Forcing miimon to 100msec\n");
resend_igmp = BOND_DEFAULT_RESEND_IGMP;
}
- if (packets_per_slave < 0 || packets_per_slave > USHRT_MAX) {
+ bond_opt_initval(&newval, packets_per_slave);
+ if (!bond_opt_parse(bond_opt_get(BOND_OPT_PACKETS_PER_SLAVE), &newval)) {
pr_warn("Warning: packets_per_slave (%d) should be between 0 and %u resetting to 1\n",
packets_per_slave, USHRT_MAX);
packets_per_slave = 1;
}
- /* reset values for TLB/ALB */
- if ((bond_mode == BOND_MODE_TLB) ||
- (bond_mode == BOND_MODE_ALB)) {
- if (!miimon) {
- pr_warning("Warning: miimon must be specified, otherwise bonding will not detect link failure and link speed which are essential for TLB/ALB load balancing\n");
- pr_warning("Forcing miimon to 100msec\n");
- miimon = BOND_DEFAULT_MIIMON;
- }
- }
-
if (bond_mode == BOND_MODE_ALB) {
pr_notice("In ALB mode you might experience client disconnections upon reconnection of a link if the bonding module updelay parameter (%d msec) is incompatible with the forwarding delay time of the switch\n",
updelay);
}
if (arp_interval < 0) {
- pr_warning("Warning: arp_interval module parameter (%d) , not in range 0-%d, so it was reset to %d\n",
- arp_interval, INT_MAX, BOND_LINK_ARP_INTERV);
- arp_interval = BOND_LINK_ARP_INTERV;
+ pr_warning("Warning: arp_interval module parameter (%d) , not in range 0-%d, so it was reset to 0\n",
+ arp_interval, INT_MAX);
+ arp_interval = 0;
}
for (arp_ip_count = 0, i = 0;
return -EINVAL;
}
- arp_validate_value = bond_parse_parm(arp_validate,
- arp_validate_tbl);
- if (arp_validate_value == -1) {
+ bond_opt_initstr(&newval, arp_validate);
+ valptr = bond_opt_parse(bond_opt_get(BOND_OPT_ARP_VALIDATE),
+ &newval);
+ if (!valptr) {
pr_err("Error: invalid arp_validate \"%s\"\n",
- arp_validate == NULL ? "NULL" : arp_validate);
+ arp_validate);
return -EINVAL;
}
- } else
+ arp_validate_value = valptr->value;
+ } else {
arp_validate_value = 0;
+ }
arp_all_targets_value = 0;
if (arp_all_targets) {
- arp_all_targets_value = bond_parse_parm(arp_all_targets,
- arp_all_targets_tbl);
-
- if (arp_all_targets_value == -1) {
+ bond_opt_initstr(&newval, arp_all_targets);
+ valptr = bond_opt_parse(bond_opt_get(BOND_OPT_ARP_ALL_TARGETS),
+ &newval);
+ if (!valptr) {
pr_err("Error: invalid arp_all_targets_value \"%s\"\n",
arp_all_targets);
arp_all_targets_value = 0;
+ } else {
+ arp_all_targets_value = valptr->value;
}
}
if (miimon) {
pr_info("MII link monitoring set to %d ms\n", miimon);
} else if (arp_interval) {
+ valptr = bond_opt_get_val(BOND_OPT_ARP_VALIDATE,
+ arp_validate_value);
pr_info("ARP monitoring set to %d ms, validate %s, with %d target(s):",
- arp_interval,
- arp_validate_tbl[arp_validate_value].modename,
- arp_ip_count);
+ arp_interval, valptr->string, arp_ip_count);
for (i = 0; i < arp_ip_count; i++)
pr_info(" %s", arp_ip_target[i]);
}
if (primary && primary_reselect) {
- primary_reselect_value = bond_parse_parm(primary_reselect,
- pri_reselect_tbl);
- if (primary_reselect_value == -1) {
+ bond_opt_initstr(&newval, primary_reselect);
+ valptr = bond_opt_parse(bond_opt_get(BOND_OPT_PRIMARY_RESELECT),
+ &newval);
+ if (!valptr) {
pr_err("Error: Invalid primary_reselect \"%s\"\n",
- primary_reselect ==
- NULL ? "NULL" : primary_reselect);
+ primary_reselect);
return -EINVAL;
}
+ primary_reselect_value = valptr->value;
} else {
primary_reselect_value = BOND_PRI_RESELECT_ALWAYS;
}
if (fail_over_mac) {
- fail_over_mac_value = bond_parse_parm(fail_over_mac,
- fail_over_mac_tbl);
- if (fail_over_mac_value == -1) {
+ bond_opt_initstr(&newval, fail_over_mac);
+ valptr = bond_opt_parse(bond_opt_get(BOND_OPT_FAIL_OVER_MAC),
+ &newval);
+ if (!valptr) {
pr_err("Error: invalid fail_over_mac \"%s\"\n",
- arp_validate == NULL ? "NULL" : arp_validate);
+ fail_over_mac);
return -EINVAL;
}
-
+ fail_over_mac_value = valptr->value;
if (bond_mode != BOND_MODE_ACTIVEBACKUP)
pr_warning("Warning: fail_over_mac only affects active-backup mode.\n");
} else {
fail_over_mac_value = BOND_FOM_NONE;
}
+ if (lp_interval == 0) {
+ pr_warning("Warning: ip_interval must be between 1 and %d, so it was reset to %d\n",
+ INT_MAX, BOND_ALB_DEFAULT_LP_INTERVAL);
+ lp_interval = BOND_ALB_DEFAULT_LP_INTERVAL;
+ }
+
/* fill params struct with the proper values */
params->mode = bond_mode;
params->xmit_policy = xmit_hashtype;
params->all_slaves_active = all_slaves_active;
params->resend_igmp = resend_igmp;
params->min_links = min_links;
- params->lp_interval = BOND_ALB_DEFAULT_LP_INTERVAL;
- if (packets_per_slave > 1)
- params->packets_per_slave = reciprocal_value(packets_per_slave);
- else
- params->packets_per_slave = packets_per_slave;
+ params->lp_interval = lp_interval;
+ params->packets_per_slave = packets_per_slave;
+ if (packets_per_slave > 0) {
+ params->reciprocal_packets_per_slave =
+ reciprocal_value(packets_per_slave);
+ } else {
+ /* reciprocal_packets_per_slave is unused if
+ * packets_per_slave is 0 or 1, just initialize it
+ */
+ params->reciprocal_packets_per_slave =
+ (struct reciprocal_value) { 0 };
+ }
+
if (primary) {
strncpy(params->primary, primary, IFNAMSIZ);
params->primary[IFNAMSIZ - 1] = 0;
static void hydra_block_output(struct net_device *dev, int count,
const unsigned char *buf, int start_page);
static void hydra_remove_one(struct zorro_dev *z);
+ static u32 hydra_msg_enable;
static struct zorro_device_id hydra_zorro_tbl[] = {
{ ZORRO_PROD_HYDRA_SYSTEMS_AMIGANET },
static int hydra_init(struct zorro_dev *z)
{
struct net_device *dev;
- unsigned long board = ZTWO_VADDR(z->resource.start);
+ unsigned long board = (unsigned long)ZTWO_VADDR(z->resource.start);
unsigned long ioaddr = board+HYDRA_NIC_BASE;
const char name[] = "NE2000";
int start_page, stop_page;
int j;
int err;
+ struct ei_device *ei_local;
static u32 hydra_offsets[16] = {
0x00, 0x02, 0x04, 0x06, 0x08, 0x0a, 0x0c, 0x0e,
start_page = NESM_START_PG;
stop_page = NESM_STOP_PG;
+ ei_local = netdev_priv(dev);
+ ei_local->msg_enable = hydra_msg_enable;
dev->base_addr = ioaddr;
dev->irq = IRQ_AMIGA_PORTS;
static int hydra_close(struct net_device *dev)
{
- if (ei_debug > 1)
- printk(KERN_DEBUG "%s: Shutting down ethercard.\n", dev->name);
+ struct ei_device *ei_local = netdev_priv(dev);
+
+ netif_dbg(ei_local, ifdown, dev, "Shutting down ethercard.\n");
__ei_close(dev);
return 0;
}
static void hydra_reset_8390(struct net_device *dev)
{
- printk(KERN_INFO "Hydra hw reset not there\n");
+ netdev_info(dev, "Hydra hw reset not there\n");
}
static void hydra_get_8390_hdr(struct net_device *dev,
static const char version[] =
"8390.c:v1.10cvs 9/23/94 Donald Becker (becker@cesdis.gsfc.nasa.gov)\n";
+ static u32 zorro8390_msg_enable;
+
#include "lib8390.c"
#define DRV_NAME "zorro8390"
static void zorro8390_reset_8390(struct net_device *dev)
{
unsigned long reset_start_time = jiffies;
+ struct ei_device *ei_local = netdev_priv(dev);
- if (ei_debug > 1)
- netdev_dbg(dev, "resetting - t=%ld...\n", jiffies);
+ netif_dbg(ei_local, hw, dev, "resetting - t=%ld...\n", jiffies);
z_writeb(z_readb(NE_BASE + NE_RESET), NE_BASE + NE_RESET);
* If it does, it's the last thing you'll see
*/
if (ei_status.dmaing) {
- netdev_err(dev, "%s: DMAing conflict [DMAstat:%d][irqlock:%d]\n",
- __func__, ei_status.dmaing, ei_status.irqlock);
+ netdev_warn(dev,
+ "%s: DMAing conflict [DMAstat:%d][irqlock:%d]\n",
+ __func__, ei_status.dmaing, ei_status.irqlock);
return;
}
while ((z_readb(NE_BASE + NE_EN0_ISR) & ENISR_RDC) == 0)
if (time_after(jiffies, dma_start + 2 * HZ / 100)) {
/* 20ms */
- netdev_err(dev, "timeout waiting for Tx RDC\n");
+ netdev_warn(dev, "timeout waiting for Tx RDC\n");
zorro8390_reset_8390(dev);
__NS8390_init(dev, 1);
break;
static int zorro8390_close(struct net_device *dev)
{
- if (ei_debug > 1)
- netdev_dbg(dev, "Shutting down ethercard\n");
+ struct ei_device *ei_local = netdev_priv(dev);
+
+ netif_dbg(ei_local, ifdown, dev, "Shutting down ethercard\n");
__ei_close(dev);
return 0;
}
};
static int zorro8390_init(struct net_device *dev, unsigned long board,
- const char *name, unsigned long ioaddr)
+ const char *name, void __iomem *ioaddr)
{
int i;
int err;
unsigned char SA_prom[32];
int start_page, stop_page;
+ struct ei_device *ei_local = netdev_priv(dev);
static u32 zorro8390_offsets[16] = {
0x00, 0x02, 0x04, 0x06, 0x08, 0x0a, 0x0c, 0x0e,
0x10, 0x12, 0x14, 0x16, 0x18, 0x1a, 0x1c, 0x1e,
start_page = NESM_START_PG;
stop_page = NESM_STOP_PG;
- dev->base_addr = ioaddr;
+ dev->base_addr = (unsigned long)ioaddr;
dev->irq = IRQ_AMIGA_PORTS;
/* Install the Interrupt handler */
dev->netdev_ops = &zorro8390_netdev_ops;
__NS8390_init(dev, 0);
+
+ ei_local->msg_enable = zorro8390_msg_enable;
+
err = register_netdev(dev);
if (err) {
free_irq(IRQ_AMIGA_PORTS, dev);
[5] = "Time stamping support",
[6] = "VST (control vlan insertion/stripping) support",
[7] = "FSM (MAC anti-spoofing) support",
- [8] = "Dynamic QP updates support"
+ [8] = "Dynamic QP updates support",
+ [9] = "TCP/IP offloads/flow-steering for VXLAN support"
};
int i;
/* when opcode modifier = 1 */
#define QUERY_FUNC_CAP_PHYS_PORT_OFFSET 0x3
- #define QUERY_FUNC_CAP_RDMA_PROPS_OFFSET 0x8
- #define QUERY_FUNC_CAP_ETH_PROPS_OFFSET 0xc
+ #define QUERY_FUNC_CAP_FLAGS0_OFFSET 0x8
+ #define QUERY_FUNC_CAP_FLAGS1_OFFSET 0xc
#define QUERY_FUNC_CAP_QP0_TUNNEL 0x10
#define QUERY_FUNC_CAP_QP0_PROXY 0x14
#define QUERY_FUNC_CAP_QP1_TUNNEL 0x18
#define QUERY_FUNC_CAP_QP1_PROXY 0x1c
+ #define QUERY_FUNC_CAP_PHYS_PORT_ID 0x28
- #define QUERY_FUNC_CAP_ETH_PROPS_FORCE_MAC 0x40
- #define QUERY_FUNC_CAP_ETH_PROPS_FORCE_VLAN 0x80
+ #define QUERY_FUNC_CAP_FLAGS1_FORCE_MAC 0x40
+ #define QUERY_FUNC_CAP_FLAGS1_FORCE_VLAN 0x80
+ #define QUERY_FUNC_CAP_FLAGS1_NIC_INFO 0x10
- #define QUERY_FUNC_CAP_RDMA_PROPS_FORCE_PHY_WQE_GID 0x80
+ #define QUERY_FUNC_CAP_FLAGS0_FORCE_PHY_WQE_GID 0x80
if (vhcr->op_modifier == 1) {
- field = 0;
- /* ensure force vlan and force mac bits are not set */
- MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_ETH_PROPS_OFFSET);
- /* ensure that phy_wqe_gid bit is not set */
- MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_RDMA_PROPS_OFFSET);
+ /* Set nic_info bit to mark new fields support */
+ field = QUERY_FUNC_CAP_FLAGS1_NIC_INFO;
+ MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_FLAGS1_OFFSET);
field = vhcr->in_modifier; /* phys-port = logical-port */
MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_PHYS_PORT_OFFSET);
size += 2;
MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_QP1_PROXY);
+ MLX4_PUT(outbox->buf, dev->caps.phys_port_id[vhcr->in_modifier],
+ QUERY_FUNC_CAP_PHYS_PORT_ID);
+
} else if (vhcr->op_modifier == 0) {
/* enable rdma and ethernet interfaces, and new quota locations */
field = (QUERY_FUNC_CAP_FLAG_ETH | QUERY_FUNC_CAP_FLAG_RDMA |
goto out;
}
+ MLX4_GET(func_cap->flags1, outbox, QUERY_FUNC_CAP_FLAGS1_OFFSET);
if (dev->caps.port_type[gen_or_port] == MLX4_PORT_TYPE_ETH) {
- MLX4_GET(field, outbox, QUERY_FUNC_CAP_ETH_PROPS_OFFSET);
- if (field & QUERY_FUNC_CAP_ETH_PROPS_FORCE_VLAN) {
+ if (func_cap->flags1 & QUERY_FUNC_CAP_FLAGS1_OFFSET) {
mlx4_err(dev, "VLAN is enforced on this port\n");
err = -EPROTONOSUPPORT;
goto out;
}
- if (field & QUERY_FUNC_CAP_ETH_PROPS_FORCE_MAC) {
+ if (func_cap->flags1 & QUERY_FUNC_CAP_FLAGS1_FORCE_MAC) {
mlx4_err(dev, "Force mac is enabled on this port\n");
err = -EPROTONOSUPPORT;
goto out;
}
} else if (dev->caps.port_type[gen_or_port] == MLX4_PORT_TYPE_IB) {
- MLX4_GET(field, outbox, QUERY_FUNC_CAP_RDMA_PROPS_OFFSET);
- if (field & QUERY_FUNC_CAP_RDMA_PROPS_FORCE_PHY_WQE_GID) {
+ MLX4_GET(field, outbox, QUERY_FUNC_CAP_FLAGS0_OFFSET);
+ if (field & QUERY_FUNC_CAP_FLAGS0_FORCE_PHY_WQE_GID) {
mlx4_err(dev, "phy_wqe_gid is "
"enforced on this ib port\n");
err = -EPROTONOSUPPORT;
MLX4_GET(size, outbox, QUERY_FUNC_CAP_QP1_PROXY);
func_cap->qp1_proxy_qpn = size & 0xFFFFFF;
+ if (func_cap->flags1 & QUERY_FUNC_CAP_FLAGS1_NIC_INFO)
+ MLX4_GET(func_cap->phys_port_id, outbox,
+ QUERY_FUNC_CAP_PHYS_PORT_ID);
+
/* All other resources are allocated by the master, but we still report
* 'num' and 'reserved' capabilities as follows:
* - num remains the maximum resource index
#define QUERY_DEV_CAP_MAX_XRC_OFFSET 0x67
#define QUERY_DEV_CAP_MAX_COUNTERS_OFFSET 0x68
#define QUERY_DEV_CAP_EXT_2_FLAGS_OFFSET 0x70
+#define QUERY_DEV_CAP_FLOW_STEERING_IPOIB_OFFSET 0x74
#define QUERY_DEV_CAP_FLOW_STEERING_RANGE_EN_OFFSET 0x76
#define QUERY_DEV_CAP_FLOW_STEERING_MAX_QP_OFFSET 0x77
#define QUERY_DEV_CAP_RDMARC_ENTRY_SZ_OFFSET 0x80
#define QUERY_DEV_CAP_RSVD_LKEY_OFFSET 0x98
#define QUERY_DEV_CAP_MAX_ICM_SZ_OFFSET 0xa0
#define QUERY_DEV_CAP_FW_REASSIGN_MAC 0x9d
+ #define QUERY_DEV_CAP_VXLAN 0x9e
dev_cap->flags2 = 0;
mailbox = mlx4_alloc_cmd_mailbox(dev);
if (field & 0x80)
dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_FS_EN;
dev_cap->fs_log_max_ucast_qp_range_size = field & 0x1f;
+ MLX4_GET(field, outbox, QUERY_DEV_CAP_FLOW_STEERING_IPOIB_OFFSET);
+ if (field & 0x80)
+ dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_DMFS_IPOIB;
MLX4_GET(field, outbox, QUERY_DEV_CAP_FLOW_STEERING_MAX_QP_OFFSET);
dev_cap->fs_max_num_qp_per_entry = field;
MLX4_GET(stat_rate, outbox, QUERY_DEV_CAP_RATE_SUPPORT_OFFSET);
MLX4_GET(field, outbox, QUERY_DEV_CAP_FW_REASSIGN_MAC);
if (field & 1<<6)
dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_REASSIGN_MAC_EN;
+ MLX4_GET(field, outbox, QUERY_DEV_CAP_VXLAN);
+ if (field & 1<<3)
+ dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_VXLAN_OFFLOADS;
MLX4_GET(dev_cap->max_icm_sz, outbox,
QUERY_DEV_CAP_MAX_ICM_SZ_OFFSET);
if (dev_cap->flags & MLX4_DEV_CAP_FLAG_COUNTERS)
field &= 0x7f;
MLX4_PUT(outbox->buf, field, QUERY_DEV_CAP_CQ_TS_SUPPORT_OFFSET);
+ /* For guests, disable vxlan tunneling */
+ MLX4_GET(field, outbox, QUERY_DEV_CAP_VXLAN);
+ field &= 0xf7;
+ MLX4_PUT(outbox->buf, field, QUERY_DEV_CAP_VXLAN);
+
/* For guests, report Blueflame disabled */
MLX4_GET(field, outbox->buf, QUERY_DEV_CAP_BF_OFFSET);
field &= 0x7f;
MLX4_PUT(outbox->buf, field,
QUERY_DEV_CAP_FLOW_STEERING_RANGE_EN_OFFSET);
}
+
+ /* turn off ipoib managed steering for guests */
+ MLX4_GET(field, outbox, QUERY_DEV_CAP_FLOW_STEERING_IPOIB_OFFSET);
+ field &= ~0x80;
+ MLX4_PUT(outbox->buf, field, QUERY_DEV_CAP_FLOW_STEERING_IPOIB_OFFSET);
+
return 0;
}
#define INIT_HCA_IN_SIZE 0x200
#define INIT_HCA_VERSION_OFFSET 0x000
#define INIT_HCA_VERSION 2
+ #define INIT_HCA_VXLAN_OFFSET 0x0c
#define INIT_HCA_CACHELINE_SZ_OFFSET 0x0e
#define INIT_HCA_FLAGS_OFFSET 0x014
#define INIT_HCA_QPC_OFFSET 0x020
MLX4_PUT(inbox, param->uar_page_sz, INIT_HCA_UAR_PAGE_SZ_OFFSET);
MLX4_PUT(inbox, param->log_uar_sz, INIT_HCA_LOG_UAR_SZ_OFFSET);
+ /* set parser VXLAN attributes */
+ if (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_VXLAN_OFFLOADS) {
+ u8 parser_params = 0;
+ MLX4_PUT(inbox, parser_params, INIT_HCA_VXLAN_OFFSET);
+ }
+
err = mlx4_cmd(dev, mailbox->dma, 0, 0, MLX4_CMD_INIT_HCA, 10000,
MLX4_CMD_NATIVE);
return mlx4_cmd(dev, 0, 0x1f, 0, MLX4_CMD_NOP, 100, MLX4_CMD_NATIVE);
}
+ int mlx4_get_phys_port_id(struct mlx4_dev *dev)
+ {
+ u8 port;
+ u32 *outbox;
+ struct mlx4_cmd_mailbox *mailbox;
+ u32 in_mod;
+ u32 guid_hi, guid_lo;
+ int err, ret = 0;
+ #define MOD_STAT_CFG_PORT_OFFSET 8
+ #define MOD_STAT_CFG_GUID_H 0X14
+ #define MOD_STAT_CFG_GUID_L 0X1c
+
+ mailbox = mlx4_alloc_cmd_mailbox(dev);
+ if (IS_ERR(mailbox))
+ return PTR_ERR(mailbox);
+ outbox = mailbox->buf;
+
+ for (port = 1; port <= dev->caps.num_ports; port++) {
+ in_mod = port << MOD_STAT_CFG_PORT_OFFSET;
+ err = mlx4_cmd_box(dev, 0, mailbox->dma, in_mod, 0x2,
+ MLX4_CMD_MOD_STAT_CFG, MLX4_CMD_TIME_CLASS_A,
+ MLX4_CMD_NATIVE);
+ if (err) {
+ mlx4_err(dev, "Fail to get port %d uplink guid\n",
+ port);
+ ret = err;
+ } else {
+ MLX4_GET(guid_hi, outbox, MOD_STAT_CFG_GUID_H);
+ MLX4_GET(guid_lo, outbox, MOD_STAT_CFG_GUID_L);
+ dev->caps.phys_port_id[port] = (u64)guid_lo |
+ (u64)guid_hi << 32;
+ }
+ }
+ mlx4_free_cmd_mailbox(dev, mailbox);
+ return ret;
+ }
+
#define MLX4_WOL_SETUP_MODE (5 << 28)
int mlx4_wol_read(struct mlx4_dev *dev, u64 *config, int port)
{
enum mlx4_steer_type steer,
u32 qpn)
{
- struct mlx4_steer *s_steer = &mlx4_priv(dev)->steer[port - 1];
+ struct mlx4_steer *s_steer;
struct mlx4_promisc_qp *pqp;
+ if (port < 1 || port > dev->caps.num_ports)
+ return NULL;
+
+ s_steer = &mlx4_priv(dev)->steer[port - 1];
+
list_for_each_entry(pqp, &s_steer->promisc_qps[steer], list) {
if (pqp->qpn == qpn)
return pqp;
u32 prot;
int err;
+ if (port < 1 || port > dev->caps.num_ports)
+ return -EINVAL;
+
s_steer = &mlx4_priv(dev)->steer[port - 1];
new_entry = kzalloc(sizeof *new_entry, GFP_KERNEL);
if (!new_entry)
struct mlx4_promisc_qp *pqp;
struct mlx4_promisc_qp *dqp;
+ if (port < 1 || port > dev->caps.num_ports)
+ return -EINVAL;
+
s_steer = &mlx4_priv(dev)->steer[port - 1];
pqp = get_promisc_qp(dev, port, steer, qpn);
struct mlx4_steer_index *tmp_entry, *entry = NULL;
struct mlx4_promisc_qp *dqp, *tmp_dqp;
+ if (port < 1 || port > dev->caps.num_ports)
+ return NULL;
+
s_steer = &mlx4_priv(dev)->steer[port - 1];
/* if qp is not promisc, it cannot be duplicated */
bool ret = false;
int i;
+ if (port < 1 || port > dev->caps.num_ports)
+ return NULL;
+
s_steer = &mlx4_priv(dev)->steer[port - 1];
mailbox = mlx4_alloc_cmd_mailbox(dev);
int err;
struct mlx4_priv *priv = mlx4_priv(dev);
+ if (port < 1 || port > dev->caps.num_ports)
+ return -EINVAL;
+
s_steer = &mlx4_priv(dev)->steer[port - 1];
mutex_lock(&priv->mcg_table.mutex);
int loc, i;
int err;
+ if (port < 1 || port > dev->caps.num_ports)
+ return -EINVAL;
+
s_steer = &mlx4_priv(dev)->steer[port - 1];
mutex_lock(&priv->mcg_table.mutex);
[MLX4_NET_TRANS_RULE_ID_IPV6] = 0xE003,
[MLX4_NET_TRANS_RULE_ID_IPV4] = 0xE002,
[MLX4_NET_TRANS_RULE_ID_TCP] = 0xE004,
- [MLX4_NET_TRANS_RULE_ID_UDP] = 0xE006
+ [MLX4_NET_TRANS_RULE_ID_UDP] = 0xE006,
+ [MLX4_NET_TRANS_RULE_ID_VXLAN] = 0xE008
};
int mlx4_map_sw_to_hw_steering_id(struct mlx4_dev *dev,
[MLX4_NET_TRANS_RULE_ID_TCP] =
sizeof(struct mlx4_net_trans_rule_hw_tcp_udp),
[MLX4_NET_TRANS_RULE_ID_UDP] =
- sizeof(struct mlx4_net_trans_rule_hw_tcp_udp)
+ sizeof(struct mlx4_net_trans_rule_hw_tcp_udp),
+ [MLX4_NET_TRANS_RULE_ID_VXLAN] =
+ sizeof(struct mlx4_net_trans_rule_hw_vxlan)
};
int mlx4_hw_rule_sz(struct mlx4_dev *dev,
rule_hw->tcp_udp.src_port_msk = spec->tcp_udp.src_port_msk;
break;
+ case MLX4_NET_TRANS_RULE_ID_VXLAN:
+ rule_hw->vxlan.vni =
+ cpu_to_be32(be32_to_cpu(spec->vxlan.vni) << 8);
+ rule_hw->vxlan.vni_mask =
+ cpu_to_be32(be32_to_cpu(spec->vxlan.vni_mask) << 8);
+ break;
+
default:
return -EINVAL;
}
}
EXPORT_SYMBOL_GPL(mlx4_flow_detach);
+int mlx4_FLOW_STEERING_IB_UC_QP_RANGE(struct mlx4_dev *dev, u32 min_range_qpn,
+ u32 max_range_qpn)
+{
+ int err;
+ u64 in_param;
+
+ in_param = ((u64) min_range_qpn) << 32;
+ in_param |= ((u64) max_range_qpn) & 0xFFFFFFFF;
+
+ err = mlx4_cmd(dev, in_param, 0, 0,
+ MLX4_FLOW_STEERING_IB_UC_QP_RANGE,
+ MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE);
+
+ return err;
+}
+EXPORT_SYMBOL_GPL(mlx4_FLOW_STEERING_IB_UC_QP_RANGE);
+
int mlx4_qp_attach_common(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
int block_mcast_loopback, enum mlx4_protocol prot,
enum mlx4_steer_type steer)
index, dev->caps.num_mgms);
else
mlx4_bitmap_free(&priv->mcg_table.bitmap,
- index - dev->caps.num_mgms);
+ index - dev->caps.num_mgms, MLX4_USE_RR);
}
mutex_unlock(&priv->mcg_table.mutex);
index, amgm_index, dev->caps.num_mgms);
else
mlx4_bitmap_free(&priv->mcg_table.bitmap,
- amgm_index - dev->caps.num_mgms);
+ amgm_index - dev->caps.num_mgms, MLX4_USE_RR);
}
} else {
/* Remove entry from AMGM */
prev, index, dev->caps.num_mgms);
else
mlx4_bitmap_free(&priv->mcg_table.bitmap,
- index - dev->caps.num_mgms);
+ index - dev->caps.num_mgms, MLX4_USE_RR);
}
out:
MLX4_PCI_DEV_FORCE_SENSE_PORT = 1 << 1,
};
+ enum {
+ MLX4_NO_RR = 0,
+ MLX4_USE_RR = 1,
+ };
+
struct mlx4_priv {
struct mlx4_dev dev;
extern struct workqueue_struct *mlx4_wq;
u32 mlx4_bitmap_alloc(struct mlx4_bitmap *bitmap);
- void mlx4_bitmap_free(struct mlx4_bitmap *bitmap, u32 obj);
+ void mlx4_bitmap_free(struct mlx4_bitmap *bitmap, u32 obj, int use_rr);
u32 mlx4_bitmap_alloc_range(struct mlx4_bitmap *bitmap, int cnt, int align);
- void mlx4_bitmap_free_range(struct mlx4_bitmap *bitmap, u32 obj, int cnt);
+ void mlx4_bitmap_free_range(struct mlx4_bitmap *bitmap, u32 obj, int cnt,
+ int use_rr);
u32 mlx4_bitmap_avail(struct mlx4_bitmap *bitmap);
int mlx4_bitmap_init(struct mlx4_bitmap *bitmap, u32 num, u32 mask,
u32 reserved_bot, u32 resetrved_top);
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
+int mlx4_FLOW_STEERING_IB_UC_QP_RANGE_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd);
int mlx4_get_mgm_entry_size(struct mlx4_dev *dev);
int mlx4_get_qp_per_mgm(struct mlx4_dev *dev);
return err;
}
+int mlx4_find_cached_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *idx)
+{
+ struct mlx4_port_info *info = &mlx4_priv(dev)->port[port];
+ struct mlx4_mac_table *table = &info->mac_table;
+ int i;
+
+ for (i = 0; i < MLX4_MAX_MAC_NUM; i++) {
+ if (!table->refs[i])
+ continue;
+
+ if (mac == (MLX4_MAC_MASK & be64_to_cpu(table->entries[i]))) {
+ *idx = i;
+ return 0;
+ }
+ }
+
+ return -ENOENT;
+}
+EXPORT_SYMBOL_GPL(mlx4_find_cached_mac);
+
int __mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac)
{
struct mlx4_port_info *info = &mlx4_priv(dev)->port[port];
}
EXPORT_SYMBOL(mlx4_SET_PORT_SCHEDULER);
+ enum {
+ VXLAN_ENABLE_MODIFY = 1 << 7,
+ VXLAN_STEERING_MODIFY = 1 << 6,
+
+ VXLAN_ENABLE = 1 << 7,
+ };
+
+ struct mlx4_set_port_vxlan_context {
+ u32 reserved1;
+ u8 modify_flags;
+ u8 reserved2;
+ u8 enable_flags;
+ u8 steering;
+ };
+
+ int mlx4_SET_PORT_VXLAN(struct mlx4_dev *dev, u8 port, u8 steering)
+ {
+ int err;
+ u32 in_mod;
+ struct mlx4_cmd_mailbox *mailbox;
+ struct mlx4_set_port_vxlan_context *context;
+
+ mailbox = mlx4_alloc_cmd_mailbox(dev);
+ if (IS_ERR(mailbox))
+ return PTR_ERR(mailbox);
+ context = mailbox->buf;
+ memset(context, 0, sizeof(*context));
+
+ context->modify_flags = VXLAN_ENABLE_MODIFY | VXLAN_STEERING_MODIFY;
+ context->enable_flags = VXLAN_ENABLE;
+ context->steering = steering;
+
+ in_mod = MLX4_SET_PORT_VXLAN << 8 | port;
+ err = mlx4_cmd(dev, mailbox->dma, in_mod, 1, MLX4_CMD_SET_PORT,
+ MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
+
+ mlx4_free_cmd_mailbox(dev, mailbox);
+ return err;
+ }
+ EXPORT_SYMBOL(mlx4_SET_PORT_VXLAN);
+
int mlx4_SET_MCAST_FLTR_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
spin_lock_irq(mlx4_tlock(dev));
r = res_tracker_lookup(&tracker->res_tree[RES_CQ], cqn);
- if (!r)
+ if (!r) {
err = -ENOENT;
- else if (r->com.owner != slave)
+ } else if (r->com.owner != slave) {
err = -EPERM;
- else {
- switch (state) {
- case RES_CQ_BUSY:
- err = -EBUSY;
- break;
-
- case RES_CQ_ALLOCATED:
- if (r->com.state != RES_CQ_HW)
- err = -EINVAL;
- else if (atomic_read(&r->ref_count))
- err = -EBUSY;
- else
- err = 0;
- break;
-
- case RES_CQ_HW:
- if (r->com.state != RES_CQ_ALLOCATED)
- err = -EINVAL;
- else
- err = 0;
- break;
-
- default:
+ } else if (state == RES_CQ_ALLOCATED) {
+ if (r->com.state != RES_CQ_HW)
err = -EINVAL;
- }
+ else if (atomic_read(&r->ref_count))
+ err = -EBUSY;
+ else
+ err = 0;
+ } else if (state != RES_CQ_HW || r->com.state != RES_CQ_ALLOCATED) {
+ err = -EINVAL;
+ } else {
+ err = 0;
+ }
- if (!err) {
- r->com.from_state = r->com.state;
- r->com.to_state = state;
- r->com.state = RES_CQ_BUSY;
- if (cq)
- *cq = r;
- }
+ if (!err) {
+ r->com.from_state = r->com.state;
+ r->com.to_state = state;
+ r->com.state = RES_CQ_BUSY;
+ if (cq)
+ *cq = r;
}
spin_unlock_irq(mlx4_tlock(dev));
}
static int srq_res_start_move_to(struct mlx4_dev *dev, int slave, int index,
- enum res_cq_states state, struct res_srq **srq)
+ enum res_srq_states state, struct res_srq **srq)
{
struct mlx4_priv *priv = mlx4_priv(dev);
struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
spin_lock_irq(mlx4_tlock(dev));
r = res_tracker_lookup(&tracker->res_tree[RES_SRQ], index);
- if (!r)
+ if (!r) {
err = -ENOENT;
- else if (r->com.owner != slave)
+ } else if (r->com.owner != slave) {
err = -EPERM;
- else {
- switch (state) {
- case RES_SRQ_BUSY:
- err = -EINVAL;
- break;
-
- case RES_SRQ_ALLOCATED:
- if (r->com.state != RES_SRQ_HW)
- err = -EINVAL;
- else if (atomic_read(&r->ref_count))
- err = -EBUSY;
- break;
-
- case RES_SRQ_HW:
- if (r->com.state != RES_SRQ_ALLOCATED)
- err = -EINVAL;
- break;
-
- default:
+ } else if (state == RES_SRQ_ALLOCATED) {
+ if (r->com.state != RES_SRQ_HW)
err = -EINVAL;
- }
+ else if (atomic_read(&r->ref_count))
+ err = -EBUSY;
+ } else if (state != RES_SRQ_HW || r->com.state != RES_SRQ_ALLOCATED) {
+ err = -EINVAL;
+ }
- if (!err) {
- r->com.from_state = r->com.state;
- r->com.to_state = state;
- r->com.state = RES_SRQ_BUSY;
- if (srq)
- *srq = r;
- }
+ if (!err) {
+ r->com.from_state = r->com.state;
+ r->com.to_state = state;
+ r->com.state = RES_SRQ_BUSY;
+ if (srq)
+ *srq = r;
}
spin_unlock_irq(mlx4_tlock(dev));
!is_broadcast_ether_addr(eth_header->eth.dst_mac)) {
list_for_each_entry_safe(res, tmp, rlist, list) {
be_mac = cpu_to_be64(res->mac << 16);
- if (!memcmp(&be_mac, eth_header->eth.dst_mac, ETH_ALEN))
+ if (ether_addr_equal((u8 *)&be_mac, eth_header->eth.dst_mac))
return 0;
}
pr_err("MAC %pM doesn't belong to VF %d, Steering rule rejected\n",
return err;
}
+int mlx4_FLOW_STEERING_IB_UC_QP_RANGE_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd)
+{
+ return -EPERM;
+}
+
+
static void detach_qp(struct mlx4_dev *dev, int slave, struct res_qp *rqp)
{
struct res_gid *rgid;
#include <linux/fcntl.h>
#include <linux/gfp.h>
#include <linux/interrupt.h>
- #include <linux/init.h>
#include <linux/ioport.h>
#include <linux/in.h>
#include <linux/string.h>
#include <linux/bitrev.h>
#include <linux/slab.h>
-#include <asm/bootinfo.h>
#include <asm/pgtable.h>
#include <asm/io.h>
#include <asm/hwtest.h>
#include <linux/pci.h>
#include <linux/delay.h>
#include <linux/hdlc.h>
- #include <linux/init.h>
#include <linux/in.h>
#include <linux/if_arp.h>
#include <linux/netdevice.h>
return 0;
err_hdlcdev:
- pci_set_drvdata(pdev, NULL);
kfree(sc);
err_kzalloc:
pci_release_regions(pdev);
free_netdev(dev);
pci_release_regions(pdev);
pci_disable_device(pdev);
- pci_set_drvdata(pdev, NULL);
}
}
spin_unlock_irqrestore(&sc->lmc_lock, flags);
- lmc_trace(dev, "lmc_driver_timout out");
+ lmc_trace(dev, "lmc_driver_timeout out");
}
tx->flags |= XEN_NETTXF_extra_info;
gso->u.gso.size = skb_shinfo(skb)->gso_size;
- gso->u.gso.type = XEN_NETIF_GSO_TYPE_TCPV4;
+ gso->u.gso.type = (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) ?
+ XEN_NETIF_GSO_TYPE_TCPV6 :
+ XEN_NETIF_GSO_TYPE_TCPV4;
gso->u.gso.pad = 0;
gso->u.gso.features = 0;
return -EINVAL;
}
- /* Currently only TCPv4 S.O. is supported. */
- if (gso->u.gso.type != XEN_NETIF_GSO_TYPE_TCPV4) {
+ if (gso->u.gso.type != XEN_NETIF_GSO_TYPE_TCPV4 &&
+ gso->u.gso.type != XEN_NETIF_GSO_TYPE_TCPV6) {
if (net_ratelimit())
pr_warn("Bad GSO type %d\n", gso->u.gso.type);
return -EINVAL;
}
skb_shinfo(skb)->gso_size = gso->u.gso.size;
- skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
+ skb_shinfo(skb)->gso_type =
+ (gso->u.gso.type == XEN_NETIF_GSO_TYPE_TCPV4) ?
+ SKB_GSO_TCPV4 :
+ SKB_GSO_TCPV6;
/* Header must be checked, and gso_segs computed. */
skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
static int checksum_setup(struct net_device *dev, struct sk_buff *skb)
{
- struct iphdr *iph;
- int err = -EPROTO;
- int recalculate_partial_csum = 0;
+ bool recalculate_partial_csum = false;
/*
* A GSO SKB must be CHECKSUM_PARTIAL. However some buggy
struct netfront_info *np = netdev_priv(dev);
np->rx_gso_checksum_fixup++;
skb->ip_summed = CHECKSUM_PARTIAL;
- recalculate_partial_csum = 1;
+ recalculate_partial_csum = true;
}
/* A non-CHECKSUM_PARTIAL SKB does not require setup. */
if (skb->ip_summed != CHECKSUM_PARTIAL)
return 0;
- if (skb->protocol != htons(ETH_P_IP))
- goto out;
-
- iph = (void *)skb->data;
-
- switch (iph->protocol) {
- case IPPROTO_TCP:
- if (!skb_partial_csum_set(skb, 4 * iph->ihl,
- offsetof(struct tcphdr, check)))
- goto out;
-
- if (recalculate_partial_csum) {
- struct tcphdr *tcph = tcp_hdr(skb);
- tcph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
- skb->len - iph->ihl*4,
- IPPROTO_TCP, 0);
- }
- break;
- case IPPROTO_UDP:
- if (!skb_partial_csum_set(skb, 4 * iph->ihl,
- offsetof(struct udphdr, check)))
- goto out;
-
- if (recalculate_partial_csum) {
- struct udphdr *udph = udp_hdr(skb);
- udph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
- skb->len - iph->ihl*4,
- IPPROTO_UDP, 0);
- }
- break;
- default:
- if (net_ratelimit())
- pr_err("Attempting to checksum a non-TCP/UDP packet, dropping a protocol %d packet\n",
- iph->protocol);
- goto out;
- }
-
- err = 0;
-
- out:
- return err;
+ return skb_checksum_setup(skb, recalculate_partial_csum);
}
static int handle_incoming_queue(struct net_device *dev,
features &= ~NETIF_F_SG;
}
+ if (features & NETIF_F_IPV6_CSUM) {
+ if (xenbus_scanf(XBT_NIL, np->xbdev->otherend,
+ "feature-ipv6-csum-offload", "%d", &val) < 0)
+ val = 0;
+
+ if (!val)
+ features &= ~NETIF_F_IPV6_CSUM;
+ }
+
if (features & NETIF_F_TSO) {
if (xenbus_scanf(XBT_NIL, np->xbdev->otherend,
"feature-gso-tcpv4", "%d", &val) < 0)
features &= ~NETIF_F_TSO;
}
+ if (features & NETIF_F_TSO6) {
+ if (xenbus_scanf(XBT_NIL, np->xbdev->otherend,
+ "feature-gso-tcpv6", "%d", &val) < 0)
+ val = 0;
+
+ if (!val)
+ features &= ~NETIF_F_TSO6;
+ }
+
return features;
}
netif_napi_add(netdev, &np->napi, xennet_poll, 64);
netdev->features = NETIF_F_IP_CSUM | NETIF_F_RXCSUM |
NETIF_F_GSO_ROBUST;
- netdev->hw_features = NETIF_F_IP_CSUM | NETIF_F_SG | NETIF_F_TSO;
+ netdev->hw_features = NETIF_F_SG |
+ NETIF_F_IPV6_CSUM |
+ NETIF_F_TSO | NETIF_F_TSO6;
/*
* Assume that all hw features are available for now. This set
goto abort_transaction;
}
+ err = xenbus_write(xbt, dev->nodename, "feature-gso-tcpv6", "1");
+ if (err) {
+ message = "writing feature-gso-tcpv6";
+ goto abort_transaction;
+ }
+
+ err = xenbus_write(xbt, dev->nodename, "feature-ipv6-csum-offload",
+ "1");
+ if (err) {
+ message = "writing feature-ipv6-csum-offload";
+ goto abort_transaction;
+ }
+
err = xenbus_transaction_end(xbt, 0);
if (err) {
if (err == -EAGAIN)
if (!xen_domain())
return -ENODEV;
- if (xen_hvm_domain() && !xen_platform_pci_unplug)
+ if (!xen_has_pv_nic_devices())
return -ENODEV;
pr_info("Initialising Xen virtual ethernet driver\n");
framework should select this config.
config PHY_EXYNOS_MIPI_VIDEO
+ depends on HAS_IOMEM
tristate "S5P/EXYNOS SoC series MIPI CSI-2/DSI PHY driver"
help
Support for MIPI CSI-2 and MIPI DSI DPHY found on Samsung S5P
and EXYNOS SoCs.
+config PHY_MVEBU_SATA
+ def_bool y
+ depends on ARCH_KIRKWOOD || ARCH_DOVE
+ depends on OF
+ select GENERIC_PHY
+
config OMAP_USB2
tristate "OMAP USB2 PHY Driver"
depends on ARCH_OMAP2PLUS
help
Support for Display Port PHY found on Samsung EXYNOS SoCs.
+config BCM_KONA_USB2_PHY
+ tristate "Broadcom Kona USB2 PHY Driver"
+ depends on GENERIC_PHY
+ help
+ Enable this to support the Broadcom Kona USB 2.0 PHY.
+
endmenu
runtime and in suspend-to-RAM by waking up the system periodically
with help of suspend_again support.
+config CHARGER_MAX14577
+ tristate "Maxim MAX14577 MUIC battery charger driver"
+ depends on MFD_MAX14577
+ help
+ Say Y to enable support for the battery charger control sysfs and
+ platform data of MAX14577 MUICs.
+
config CHARGER_MAX8997
tristate "Maxim MAX8997/MAX8966 PMIC battery charger driver"
depends on MFD_MAX8997 && REGULATOR_MAX8997
config BATTERY_GOLDFISH
tristate "Goldfish battery driver"
depends on GOLDFISH || COMPILE_TEST
+ depends on HAS_IOMEM
help
Say Y to enable support for the battery and AC power in the
Goldfish emulator.
* -----------------------------------------------------------------------------
*/
-#include <linux/init.h>
#include <linux/module.h>
#include <linux/timer.h>
#include <linux/sched.h>
#include <linux/netdevice.h>
+ #include <linux/etherdevice.h>
#include <linux/errno.h>
#include <linux/ieee80211.h>
#include "ozdbg.h"
spin_lock_bh(&g_polling_lock);
list_for_each(e, &g_pd_list) {
pd2 = container_of(e, struct oz_pd, link);
- if (memcmp(pd2->mac_addr, pd_addr, ETH_ALEN) == 0) {
+ if (ether_addr_equal(pd2->mac_addr, pd_addr)) {
free_pd = pd;
pd = pd2;
break;
oz_dbg(RX_FRAMES, "RX frame PN=0x%x LPN=0x%x control=0x%x\n",
oz_hdr->pkt_num, oz_hdr->last_pkt_num, oz_hdr->control);
mac_hdr = skb_mac_header(skb);
- src_addr = &mac_hdr[ETH_ALEN] ;
+ src_addr = &mac_hdr[ETH_ALEN];
length = skb->len;
/* Check the version field */
spin_lock_bh(&g_polling_lock);
list_for_each(e, &g_pd_list) {
pd = container_of(e, struct oz_pd, link);
- if (memcmp(pd->mac_addr, mac_addr, ETH_ALEN) == 0) {
+ if (ether_addr_equal(pd->mac_addr, mac_addr)) {
atomic_inc(&pd->ref_count);
spin_unlock_bh(&g_polling_lock);
return pd;
struct msghdr *msg, char *buf)
{
union sctp_notification *sn = (union sctp_notification *)buf;
+ struct linger linger;
switch (sn->sn_header.sn_type) {
case SCTP_SEND_FAILED:
return;
/* Peel off a new sock */
- sctp_lock_sock(con->sock->sk);
+ lock_sock(con->sock->sk);
ret = sctp_do_peeloff(con->sock->sk,
sn->sn_assoc_change.sac_assoc_id,
&new_con->sock);
- sctp_release_sock(con->sock->sk);
+ release_sock(con->sock->sk);
if (ret < 0) {
log_print("Can't peel off a socket for "
"connection %d to node %d: err=%d",
}
add_sock(new_con->sock, new_con);
+ linger.l_onoff = 1;
+ linger.l_linger = 0;
+ ret = kernel_setsockopt(new_con->sock, SOL_SOCKET, SO_LINGER,
+ (char *)&linger, sizeof(linger));
+ if (ret < 0)
+ log_print("set socket option SO_LINGER failed");
+
log_print("connecting to %d sctp association %d",
nodeid, (int)sn->sn_assoc_change.sac_assoc_id);
#define ULLONG_MAX (~0ULL)
#define SIZE_MAX (~(size_t)0)
+#define U8_MAX ((u8)~0U)
+#define S8_MAX ((s8)(U8_MAX>>1))
+#define S8_MIN ((s8)(-S8_MAX - 1))
+#define U16_MAX ((u16)~0U)
+#define S16_MAX ((s16)(U16_MAX>>1))
+#define S16_MIN ((s16)(-S16_MAX - 1))
+#define U32_MAX ((u32)~0U)
+#define S32_MAX ((s32)(U32_MAX>>1))
+#define S32_MIN ((s32)(-S32_MAX - 1))
+#define U64_MAX ((u64)~0ULL)
+#define S64_MAX ((s64)(U64_MAX>>1))
+#define S64_MIN ((s64)(-S64_MAX - 1))
+
#define STACK_MAGIC 0xdeadbeef
#define REPEAT_BYTE(x) ((~0ul / 0xff) * (x))
(__x < 0) ? -__x : __x; \
})
+ /**
+ * reciprocal_scale - "scale" a value into range [0, ep_ro)
+ * @val: value
+ * @ep_ro: right open interval endpoint
+ *
+ * Perform a "reciprocal multiplication" in order to "scale" a value into
+ * range [0, ep_ro), where the upper interval endpoint is right-open.
+ * This is useful, e.g. for accessing a index of an array containing
+ * ep_ro elements, for example. Think of it as sort of modulus, only that
+ * the result isn't that of modulo. ;) Note that if initial input is a
+ * small value, then result will return 0.
+ *
+ * Return: a result based on val in interval [0, ep_ro).
+ */
+ static inline u32 reciprocal_scale(u32 val, u32 ep_ro)
+ {
+ return (u32)(((u64) val * ep_ro) >> 32);
+ }
+
#if defined(CONFIG_MMU) && \
(defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP))
void might_fault(void);
extern int panic_on_unrecovered_nmi;
extern int panic_on_io_nmi;
extern int sysctl_panic_on_stackoverflow;
+/*
+ * Only to be used by arch init code. If the user over-wrote the default
+ * CONFIG_PANIC_TIMEOUT, honor it.
+ */
+static inline void set_arch_panic_timeout(int timeout, int arch_default_timeout)
+{
+ if (panic_timeout == arch_default_timeout)
+ panic_timeout = timeout;
+}
extern const char *print_tainted(void);
enum lockdep_ok {
LOCKDEP_STILL_OK,
/* register/delete flow steering network rules */
MLX4_QP_FLOW_STEERING_ATTACH = 0x65,
MLX4_QP_FLOW_STEERING_DETACH = 0x66,
+ MLX4_FLOW_STEERING_IB_UC_QP_RANGE = 0x64,
};
enum {
MLX4_SET_PORT_GID_TABLE = 0x5,
MLX4_SET_PORT_PRIO2TC = 0x8,
MLX4_SET_PORT_SCHEDULER = 0x9,
+ MLX4_SET_PORT_VXLAN = 0xB
};
enum {
#define MLX4_CQ_H
#include <linux/types.h>
+#include <uapi/linux/if_ether.h>
#include <linux/mlx4/device.h>
#include <linux/mlx4/doorbell.h>
__be32 immed_rss_invalid;
__be32 g_mlpath_rqpn;
__be16 sl_vid;
- __be16 rlid;
- __be16 status;
- u8 ipv6_ext_mask;
- u8 badfcs_enc;
+ union {
+ struct {
+ __be16 rlid;
+ __be16 status;
+ u8 ipv6_ext_mask;
+ u8 badfcs_enc;
+ };
+ u8 smac[ETH_ALEN];
+ };
__be32 byte_cnt;
__be16 wqe_index;
__be16 checksum;
} __packed;
enum {
+ MLX4_CQE_L2_TUNNEL_IPOK = 1 << 31,
MLX4_CQE_VLAN_PRESENT_MASK = 1 << 29,
+ MLX4_CQE_L2_TUNNEL = 1 << 27,
+ MLX4_CQE_L2_TUNNEL_CSUM = 1 << 26,
+ MLX4_CQE_L2_TUNNEL_IPV4 = 1 << 25,
+
MLX4_CQE_QPN_MASK = 0xffffff,
+ MLX4_CQE_VID_MASK = 0xfff,
};
enum {
}
}
+ enum {
+ MLX4_TUNNEL_OFFLOAD_MODE_NONE,
+ MLX4_TUNNEL_OFFLOAD_MODE_VXLAN
+ };
+
enum {
MLX4_DEV_CAP_FLAG_RC = 1LL << 0,
MLX4_DEV_CAP_FLAG_UC = 1LL << 1,
MLX4_DEV_CAP_FLAG2_VLAN_CONTROL = 1LL << 6,
MLX4_DEV_CAP_FLAG2_FSM = 1LL << 7,
MLX4_DEV_CAP_FLAG2_UPDATE_QP = 1LL << 8,
- MLX4_DEV_CAP_FLAG2_DMFS_IPOIB = 1LL << 9
- MLX4_DEV_CAP_FLAG2_VXLAN_OFFLOADS = 1LL << 9
++ MLX4_DEV_CAP_FLAG2_DMFS_IPOIB = 1LL << 9,
++ MLX4_DEV_CAP_FLAG2_VXLAN_OFFLOADS = 1LL << 10,
};
enum {
u32 userspace_caps; /* userspace must be aware of these */
u32 function_caps; /* VFs must be aware of these */
u16 hca_core_clock;
+ u64 phys_port_id[MLX4_MAX_PORTS + 1];
+ int tunnel_offload_mode;
};
struct mlx4_buf_list {
MLX4_NET_TRANS_RULE_ID_IPV4,
MLX4_NET_TRANS_RULE_ID_TCP,
MLX4_NET_TRANS_RULE_ID_UDP,
+ MLX4_NET_TRANS_RULE_ID_VXLAN,
MLX4_NET_TRANS_RULE_NUM, /* should be last */
};
u8 dst_gid_msk[16];
};
+ struct mlx4_spec_vxlan {
+ __be32 vni;
+ __be32 vni_mask;
+
+ };
+
struct mlx4_spec_list {
struct list_head list;
enum mlx4_net_trans_rule_id id;
struct mlx4_spec_ib ib;
struct mlx4_spec_ipv4 ipv4;
struct mlx4_spec_tcp_udp tcp_udp;
+ struct mlx4_spec_vxlan vxlan;
};
};
__be32 src_ip_msk;
} __packed;
+ struct mlx4_net_trans_rule_hw_vxlan {
+ u8 size;
+ u8 rsvd;
+ __be16 id;
+ __be32 rsvd1;
+ __be32 vni;
+ __be32 vni_mask;
+ } __packed;
+
struct _rule_hw {
union {
struct {
struct mlx4_net_trans_rule_hw_ib ib;
struct mlx4_net_trans_rule_hw_ipv4 ipv4;
struct mlx4_net_trans_rule_hw_tcp_udp tcp_udp;
+ struct mlx4_net_trans_rule_hw_vxlan vxlan;
};
};
+ enum {
+ VXLAN_STEER_BY_OUTER_MAC = 1 << 0,
+ VXLAN_STEER_BY_OUTER_VLAN = 1 << 1,
+ VXLAN_STEER_BY_VSID_VNI = 1 << 2,
+ VXLAN_STEER_BY_INNER_MAC = 1 << 3,
+ VXLAN_STEER_BY_INNER_VLAN = 1 << 4,
+ };
+
+
int mlx4_flow_steer_promisc_add(struct mlx4_dev *dev, u8 port, u32 qpn,
enum mlx4_net_trans_promisc_mode mode);
int mlx4_flow_steer_promisc_remove(struct mlx4_dev *dev, u8 port,
int mlx4_SET_PORT_PRIO2TC(struct mlx4_dev *dev, u8 port, u8 *prio2tc);
int mlx4_SET_PORT_SCHEDULER(struct mlx4_dev *dev, u8 port, u8 *tc_tx_bw,
u8 *pg, u16 *ratelimit);
+ int mlx4_SET_PORT_VXLAN(struct mlx4_dev *dev, u8 port, u8 steering);
+int mlx4_find_cached_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *idx);
int mlx4_find_cached_vlan(struct mlx4_dev *dev, u8 port, u16 vid, int *idx);
int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index);
void mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, u16 vlan);
int *vector);
void mlx4_release_eq(struct mlx4_dev *dev, int vec);
+ int mlx4_get_phys_port_id(struct mlx4_dev *dev);
int mlx4_wol_read(struct mlx4_dev *dev, u64 *config, int port);
int mlx4_wol_write(struct mlx4_dev *dev, u64 config, int port);
void mlx4_put_slave_node_guid(struct mlx4_dev *dev, int slave, __be64 guid);
__be64 mlx4_get_slave_node_guid(struct mlx4_dev *dev, int slave);
+int mlx4_FLOW_STEERING_IB_UC_QP_RANGE(struct mlx4_dev *dev, u32 min_range_qpn,
+ u32 max_range_qpn);
+
cycle_t mlx4_read_clock(struct mlx4_dev *dev);
#endif /* MLX4_DEVICE_H */
#include <linux/init.h>
#include <linux/kern_levels.h>
#include <linux/linkage.h>
+#include <linux/cache.h>
extern const char linux_banner[];
extern const char linux_proc_banner[];
*/
#define HW_ERR "[Hardware Error]: "
+ /*
+ * DEPRECATED
+ * Add this to a message whenever you want to warn user space about the use
+ * of a deprecated aspect of an API so they can stop using it
+ */
+ #define DEPRECATED "[Deprecated]: "
+
/*
* Dummy printk for disabled debugging statements to use whilst maintaining
* gcc's format and side-effect checking.
*/
#ifdef CONFIG_PRINTK
-#define printk_once(fmt, ...) \
-({ \
- static bool __print_once; \
- \
- if (!__print_once) { \
- __print_once = true; \
- printk(fmt, ##__VA_ARGS__); \
- } \
+#define printk_once(fmt, ...) \
+({ \
+ static bool __print_once __read_mostly; \
+ \
+ if (!__print_once) { \
+ __print_once = true; \
+ printk(fmt, ##__VA_ARGS__); \
+ } \
})
#else
-#define printk_once(fmt, ...) \
+#define printk_once(fmt, ...) \
no_printk(fmt, ##__VA_ARGS__)
#endif
#ifndef _LINUX_SLAB_DEF_H
#define _LINUX_SLAB_DEF_H
+ #include <linux/reciprocal_div.h>
+
/*
* Definitions unique to the original Linux SLAB allocator.
*/
struct kmem_cache {
-/* 1) Cache tunables. Protected by cache_chain_mutex */
+/* 1) Cache tunables. Protected by slab_mutex */
unsigned int batchcount;
unsigned int limit;
unsigned int shared;
unsigned int size;
- u32 reciprocal_buffer_size;
+ struct reciprocal_value reciprocal_buffer_size;
/* 2) touched by every alloc & free from the backend */
unsigned int flags; /* constant flags */
* 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, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
*
*/
struct netlbl_audit {
u32 secid;
kuid_t loginuid;
- u32 sessionid;
+ unsigned int sessionid;
};
/*
#define XFRM_INC_STATS_USER(net, field) ((void)(net))
#endif
- extern struct mutex xfrm_cfg_mutex;
/* Organization of SPD aka "XFRM rules"
------------------------------------
struct xfrm_audit {
u32 secid;
kuid_t loginuid;
- u32 sessionid;
+ unsigned int sessionid;
};
#ifdef CONFIG_AUDITSYSCALL
return audit_buf;
}
-static inline void xfrm_audit_helper_usrinfo(kuid_t auid, u32 ses, u32 secid,
+static inline void xfrm_audit_helper_usrinfo(kuid_t auid, unsigned int ses, u32 secid,
struct audit_buffer *audit_buf)
{
char *secctx;
}
void xfrm_audit_policy_add(struct xfrm_policy *xp, int result, kuid_t auid,
- u32 ses, u32 secid);
+ unsigned int ses, u32 secid);
void xfrm_audit_policy_delete(struct xfrm_policy *xp, int result, kuid_t auid,
- u32 ses, u32 secid);
+ unsigned int ses, u32 secid);
void xfrm_audit_state_add(struct xfrm_state *x, int result, kuid_t auid,
- u32 ses, u32 secid);
+ unsigned int ses, u32 secid);
void xfrm_audit_state_delete(struct xfrm_state *x, int result, kuid_t auid,
- u32 ses, u32 secid);
+ unsigned int ses, u32 secid);
void xfrm_audit_state_replay_overflow(struct xfrm_state *x,
struct sk_buff *skb);
void xfrm_audit_state_replay(struct xfrm_state *x, struct sk_buff *skb,
#else
static inline void xfrm_audit_policy_add(struct xfrm_policy *xp, int result,
- kuid_t auid, u32 ses, u32 secid)
+ kuid_t auid, unsigned int ses, u32 secid)
{
}
static inline void xfrm_audit_policy_delete(struct xfrm_policy *xp, int result,
- kuid_t auid, u32 ses, u32 secid)
+ kuid_t auid, unsigned int ses, u32 secid)
{
}
static inline void xfrm_audit_state_add(struct xfrm_state *x, int result,
- kuid_t auid, u32 ses, u32 secid)
+ kuid_t auid, unsigned int ses, u32 secid)
{
}
static inline void xfrm_audit_state_delete(struct xfrm_state *x, int result,
- kuid_t auid, u32 ses, u32 secid)
+ kuid_t auid, unsigned int ses, u32 secid)
{
}
void xfrm_state_walk_init(struct xfrm_state_walk *walk, u8 proto);
int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk,
int (*func)(struct xfrm_state *, int, void*), void *);
- void xfrm_state_walk_done(struct xfrm_state_walk *walk);
+ void xfrm_state_walk_done(struct xfrm_state_walk *walk, struct net *net);
struct xfrm_state *xfrm_state_alloc(struct net *net);
struct xfrm_state *xfrm_state_find(const xfrm_address_t *daddr,
const xfrm_address_t *saddr,
xfrm_address_t *saddr,
unsigned short family,
u8 mode, u8 proto, u32 reqid);
+ struct xfrm_state *xfrm_state_lookup_byspi(struct net *net, __be32 spi,
+ unsigned short family);
int xfrm_state_check_expire(struct xfrm_state *x);
void xfrm_state_insert(struct xfrm_state *x);
int xfrm_state_add(struct xfrm_state *x);
unsigned short family);
#ifdef CONFIG_XFRM_SUB_POLICY
int xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n,
- unsigned short family);
+ unsigned short family, struct net *net);
int xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n,
unsigned short family);
#else
static inline int xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src,
- int n, unsigned short family)
+ int n, unsigned short family, struct net *net)
{
return -ENOSYS;
}
int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk,
int (*func)(struct xfrm_policy *, int, int, void*),
void *);
- void xfrm_policy_walk_done(struct xfrm_policy_walk *walk);
+ void xfrm_policy_walk_done(struct xfrm_policy_walk *walk, struct net *net);
int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl);
struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark,
u8 type, int dir,
u32 id, int delete, int *err);
int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info);
u32 xfrm_get_acqseq(void);
+ int verify_spi_info(u8 proto, u32 min, u32 max);
int xfrm_alloc_spi(struct xfrm_state *x, u32 minspi, u32 maxspi);
struct xfrm_state *xfrm_find_acq(struct net *net, const struct xfrm_mark *mark,
u8 mode, u32 reqid, u8 proto,
int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
const struct xfrm_migrate *m, int num_bundles,
const struct xfrm_kmaddress *k);
- struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m);
+ struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net);
struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x,
struct xfrm_migrate *m);
int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
struct xfrm_migrate *m, int num_bundles,
- struct xfrm_kmaddress *k);
+ struct xfrm_kmaddress *k, struct net *net);
#endif
int km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport);
#define PCI_EXP_LNKSTA_CLS 0x000f /* Current Link Speed */
#define PCI_EXP_LNKSTA_CLS_2_5GB 0x0001 /* Current Link Speed 2.5GT/s */
#define PCI_EXP_LNKSTA_CLS_5_0GB 0x0002 /* Current Link Speed 5.0GT/s */
+ #define PCI_EXP_LNKSTA_CLS_8_0GB 0x0003 /* Current Link Speed 8.0GT/s */
#define PCI_EXP_LNKSTA_NLW 0x03f0 /* Negotiated Link Width */
+ #define PCI_EXP_LNKSTA_NLW_X1 0x0010 /* Current Link Width x1 */
+ #define PCI_EXP_LNKSTA_NLW_X2 0x0020 /* Current Link Width x2 */
+ #define PCI_EXP_LNKSTA_NLW_X4 0x0040 /* Current Link Width x4 */
+ #define PCI_EXP_LNKSTA_NLW_X8 0x0080 /* Current Link Width x8 */
#define PCI_EXP_LNKSTA_NLW_SHIFT 4 /* start of NLW mask in link status */
#define PCI_EXP_LNKSTA_LT 0x0800 /* Link Training */
#define PCI_EXP_LNKSTA_SLC 0x1000 /* Slot Clock Configuration */
#define PCI_EXP_SLTCTL_CCIE 0x0010 /* Command Completed Interrupt Enable */
#define PCI_EXP_SLTCTL_HPIE 0x0020 /* Hot-Plug Interrupt Enable */
#define PCI_EXP_SLTCTL_AIC 0x00c0 /* Attention Indicator Control */
+#define PCI_EXP_SLTCTL_ATTN_IND_ON 0x0040 /* Attention Indicator on */
+#define PCI_EXP_SLTCTL_ATTN_IND_BLINK 0x0080 /* Attention Indicator blinking */
+#define PCI_EXP_SLTCTL_ATTN_IND_OFF 0x00c0 /* Attention Indicator off */
#define PCI_EXP_SLTCTL_PIC 0x0300 /* Power Indicator Control */
+#define PCI_EXP_SLTCTL_PWR_IND_ON 0x0100 /* Power Indicator on */
+#define PCI_EXP_SLTCTL_PWR_IND_BLINK 0x0200 /* Power Indicator blinking */
+#define PCI_EXP_SLTCTL_PWR_IND_OFF 0x0300 /* Power Indicator off */
#define PCI_EXP_SLTCTL_PCC 0x0400 /* Power Controller Control */
+#define PCI_EXP_SLTCTL_PWR_ON 0x0000 /* Power On */
+#define PCI_EXP_SLTCTL_PWR_OFF 0x0400 /* Power Off */
#define PCI_EXP_SLTCTL_EIC 0x0800 /* Electromechanical Interlock Control */
#define PCI_EXP_SLTCTL_DLLSCE 0x1000 /* Data Link Layer State Changed Enable */
#define PCI_EXP_SLTSTA 26 /* Slot Status */
#define PCI_ERR_ROOT_ERR_SRC 52 /* Error Source Identification */
/* Virtual Channel */
-#define PCI_VC_PORT_REG1 4
-#define PCI_VC_REG1_EVCC 0x7 /* extended VC count */
-#define PCI_VC_PORT_REG2 8
-#define PCI_VC_REG2_32_PHASE 0x2
-#define PCI_VC_REG2_64_PHASE 0x4
-#define PCI_VC_REG2_128_PHASE 0x8
+#define PCI_VC_PORT_CAP1 4
+#define PCI_VC_CAP1_EVCC 0x00000007 /* extended VC count */
+#define PCI_VC_CAP1_LPEVCC 0x00000070 /* low prio extended VC count */
+#define PCI_VC_CAP1_ARB_SIZE 0x00000c00
+#define PCI_VC_PORT_CAP2 8
+#define PCI_VC_CAP2_32_PHASE 0x00000002
+#define PCI_VC_CAP2_64_PHASE 0x00000004
+#define PCI_VC_CAP2_128_PHASE 0x00000008
+#define PCI_VC_CAP2_ARB_OFF 0xff000000
#define PCI_VC_PORT_CTRL 12
+#define PCI_VC_PORT_CTRL_LOAD_TABLE 0x00000001
#define PCI_VC_PORT_STATUS 14
+#define PCI_VC_PORT_STATUS_TABLE 0x00000001
#define PCI_VC_RES_CAP 16
+#define PCI_VC_RES_CAP_32_PHASE 0x00000002
+#define PCI_VC_RES_CAP_64_PHASE 0x00000004
+#define PCI_VC_RES_CAP_128_PHASE 0x00000008
+#define PCI_VC_RES_CAP_128_PHASE_TB 0x00000010
+#define PCI_VC_RES_CAP_256_PHASE 0x00000020
+#define PCI_VC_RES_CAP_ARB_OFF 0xff000000
#define PCI_VC_RES_CTRL 20
+#define PCI_VC_RES_CTRL_LOAD_TABLE 0x00010000
+#define PCI_VC_RES_CTRL_ARB_SELECT 0x000e0000
+#define PCI_VC_RES_CTRL_ID 0x07000000
+#define PCI_VC_RES_CTRL_ENABLE 0x80000000
#define PCI_VC_RES_STATUS 26
+#define PCI_VC_RES_STATUS_TABLE 0x00000001
+#define PCI_VC_RES_STATUS_NEGO 0x00000002
#define PCI_CAP_VC_BASE_SIZEOF 0x10
#define PCI_CAP_VC_PER_VC_SIZEOF 0x0C
bust_spinlocks.o hexdump.o kasprintf.o bitmap.o scatterlist.o \
gcd.o lcm.o list_sort.o uuid.o flex_array.o iovec.o clz_ctz.o \
bsearch.o find_last_bit.o find_next_bit.o llist.o memweight.o kfifo.o \
- percpu-refcount.o percpu_ida.o
+ percpu-refcount.o percpu_ida.o hash.o
obj-y += string_helpers.o
obj-$(CONFIG_TEST_STRING_HELPERS) += test-string_helpers.o
obj-y += kstrtox.o
obj-$(CONFIG_TEST_KSTRTOX) += test-kstrtox.o
+obj-$(CONFIG_TEST_MODULE) += test_module.o
+obj-$(CONFIG_TEST_USER_COPY) += test_user_copy.o
ifeq ($(CONFIG_DEBUG_KOBJECT),y)
CFLAGS_kobject.o += -DDEBUG
struct list_head ptype_all __read_mostly; /* Taps */
static struct list_head offload_base __read_mostly;
+ static int netif_rx_internal(struct sk_buff *skb);
+
/*
* The @dev_base_head list is protected by @dev_base_lock and the rtnl
* semaphore.
* and must not be freed until after all the CPU's have gone
* through a quiescent state.
*/
- void __dev_remove_offload(struct packet_offload *po)
+ static void __dev_remove_offload(struct packet_offload *po)
{
struct list_head *head = &offload_base;
struct packet_offload *po1;
out:
spin_unlock(&offload_lock);
}
- EXPORT_SYMBOL(__dev_remove_offload);
/**
* dev_remove_offload - remove packet offload handler
write_seqcount_end(&devnet_rename_seq);
+ netdev_adjacent_rename_links(dev, oldname);
+
write_lock_bh(&dev_base_lock);
hlist_del_rcu(&dev->name_hlist);
write_unlock_bh(&dev_base_lock);
err = ret;
write_seqcount_begin(&devnet_rename_seq);
memcpy(dev->name, oldname, IFNAMSIZ);
+ memcpy(oldname, newname, IFNAMSIZ);
goto rollback;
} else {
pr_err("%s: name change rollback failed: %d\n",
* are as for raw_notifier_call_chain().
*/
- int call_netdevice_notifiers_info(unsigned long val, struct net_device *dev,
- struct netdev_notifier_info *info)
+ static int call_netdevice_notifiers_info(unsigned long val,
+ struct net_device *dev,
+ struct netdev_notifier_info *info)
{
ASSERT_RTNL();
netdev_notifier_info_init(info, dev);
return raw_notifier_call_chain(&netdev_chain, val, info);
}
- EXPORT_SYMBOL(call_netdevice_notifiers_info);
/**
* call_netdevice_notifiers - call all network notifier blocks
skb_scrub_packet(skb, true);
skb->protocol = eth_type_trans(skb, dev);
- return netif_rx(skb);
+ return netif_rx_internal(skb);
}
EXPORT_SYMBOL_GPL(dev_forward_skb);
}
EXPORT_SYMBOL(netif_set_real_num_tx_queues);
- #ifdef CONFIG_RPS
+ #ifdef CONFIG_SYSFS
/**
* netif_set_real_num_rx_queues - set actual number of RX queues used
* @dev: Network device
}
EXPORT_SYMBOL(__netif_schedule);
- void dev_kfree_skb_irq(struct sk_buff *skb)
+ struct dev_kfree_skb_cb {
+ enum skb_free_reason reason;
+ };
+
+ static struct dev_kfree_skb_cb *get_kfree_skb_cb(const struct sk_buff *skb)
{
- if (atomic_dec_and_test(&skb->users)) {
- struct softnet_data *sd;
- unsigned long flags;
+ return (struct dev_kfree_skb_cb *)skb->cb;
+ }
+
+ void __dev_kfree_skb_irq(struct sk_buff *skb, enum skb_free_reason reason)
+ {
+ unsigned long flags;
- local_irq_save(flags);
- sd = &__get_cpu_var(softnet_data);
- skb->next = sd->completion_queue;
- sd->completion_queue = skb;
- raise_softirq_irqoff(NET_TX_SOFTIRQ);
- local_irq_restore(flags);
+ if (likely(atomic_read(&skb->users) == 1)) {
+ smp_rmb();
+ atomic_set(&skb->users, 0);
+ } else if (likely(!atomic_dec_and_test(&skb->users))) {
+ return;
}
+ get_kfree_skb_cb(skb)->reason = reason;
+ local_irq_save(flags);
+ skb->next = __this_cpu_read(softnet_data.completion_queue);
+ __this_cpu_write(softnet_data.completion_queue, skb);
+ raise_softirq_irqoff(NET_TX_SOFTIRQ);
+ local_irq_restore(flags);
}
- EXPORT_SYMBOL(dev_kfree_skb_irq);
+ EXPORT_SYMBOL(__dev_kfree_skb_irq);
- void dev_kfree_skb_any(struct sk_buff *skb)
+ void __dev_kfree_skb_any(struct sk_buff *skb, enum skb_free_reason reason)
{
if (in_irq() || irqs_disabled())
- dev_kfree_skb_irq(skb);
+ __dev_kfree_skb_irq(skb, reason);
else
dev_kfree_skb(skb);
}
- EXPORT_SYMBOL(dev_kfree_skb_any);
+ EXPORT_SYMBOL(__dev_kfree_skb_any);
/**
{
struct dev_gso_cb *cb;
- do {
- struct sk_buff *nskb = skb->next;
-
- skb->next = nskb->next;
- nskb->next = NULL;
- kfree_skb(nskb);
- } while (skb->next);
+ kfree_skb_list(skb->next);
+ skb->next = NULL;
cb = DEV_GSO_CB(skb);
if (cb->destructor)
}
EXPORT_SYMBOL(netif_skb_features);
- /*
- * Returns true if either:
- * 1. skb has frag_list and the device doesn't support FRAGLIST, or
- * 2. skb is fragmented and the device does not support SG.
- */
- static inline int skb_needs_linearize(struct sk_buff *skb,
- netdev_features_t features)
- {
- return skb_is_nonlinear(skb) &&
- ((skb_has_frag_list(skb) &&
- !(features & NETIF_F_FRAGLIST)) ||
- (skb_shinfo(skb)->nr_frags &&
- !(features & NETIF_F_SG)));
- }
-
int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
struct netdev_queue *txq)
{
dev_queue_xmit_nit(skb, dev);
skb_len = skb->len;
- rc = ops->ndo_start_xmit(skb, dev);
-
+ trace_net_dev_start_xmit(skb, dev);
+ rc = ops->ndo_start_xmit(skb, dev);
trace_net_dev_xmit(skb, rc, dev, skb_len);
if (rc == NETDEV_TX_OK)
txq_trans_update(txq);
dev_queue_xmit_nit(nskb, dev);
skb_len = nskb->len;
+ trace_net_dev_start_xmit(nskb, dev);
rc = ops->ndo_start_xmit(nskb, dev);
trace_net_dev_xmit(nskb, rc, dev, skb_len);
if (unlikely(rc != NETDEV_TX_OK)) {
return rc;
}
- #if IS_ENABLED(CONFIG_NETPRIO_CGROUP)
+ #if IS_ENABLED(CONFIG_CGROUP_NET_PRIO)
static void skb_update_prio(struct sk_buff *skb)
{
struct netprio_map *map = rcu_dereference_bh(skb->dev->priomap);
EXPORT_SYMBOL(dev_loopback_xmit);
/**
- * dev_queue_xmit - transmit a buffer
+ * __dev_queue_xmit - transmit a buffer
* @skb: buffer to transmit
+ * @accel_priv: private data 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
}
skb_reset_network_header(skb);
- if (!skb_get_rxhash(skb))
+ if (!skb_get_hash(skb))
goto done;
flow_table = rcu_dereference(rxqueue->rps_flow_table);
rcu_read_lock();
fl = rcu_dereference(sd->flow_limit);
if (fl) {
- new_flow = skb_get_rxhash(skb) & (fl->num_buckets - 1);
+ new_flow = skb_get_hash(skb) & (fl->num_buckets - 1);
old_flow = fl->history[fl->history_head];
fl->history[fl->history_head] = new_flow;
return NET_RX_DROP;
}
- /**
- * netif_rx - post buffer to the network code
- * @skb: buffer to post
- *
- * This function receives a packet from a device driver and queues it for
- * the upper (protocol) levels to process. It always succeeds. The buffer
- * may be dropped during processing for congestion control or by the
- * protocol layers.
- *
- * return values:
- * NET_RX_SUCCESS (no congestion)
- * NET_RX_DROP (packet was dropped)
- *
- */
-
- int netif_rx(struct sk_buff *skb)
+ static int netif_rx_internal(struct sk_buff *skb)
{
int ret;
}
return ret;
}
+
+ /**
+ * netif_rx - post buffer to the network code
+ * @skb: buffer to post
+ *
+ * This function receives a packet from a device driver and queues it for
+ * the upper (protocol) levels to process. It always succeeds. The buffer
+ * may be dropped during processing for congestion control or by the
+ * protocol layers.
+ *
+ * return values:
+ * NET_RX_SUCCESS (no congestion)
+ * NET_RX_DROP (packet was dropped)
+ *
+ */
+
+ int netif_rx(struct sk_buff *skb)
+ {
+ trace_netif_rx_entry(skb);
+
+ return netif_rx_internal(skb);
+ }
EXPORT_SYMBOL(netif_rx);
int netif_rx_ni(struct sk_buff *skb)
{
int err;
+ trace_netif_rx_ni_entry(skb);
+
preempt_disable();
- err = netif_rx(skb);
+ err = netif_rx_internal(skb);
if (local_softirq_pending())
do_softirq();
preempt_enable();
clist = clist->next;
WARN_ON(atomic_read(&skb->users));
- trace_kfree_skb(skb, net_tx_action);
+ if (likely(get_kfree_skb_cb(skb)->reason == SKB_REASON_CONSUMED))
+ trace_consume_skb(skb);
+ else
+ trace_kfree_skb(skb, net_tx_action);
__kfree_skb(skb);
}
}
return ret;
}
- /**
- * netif_receive_skb - process receive buffer from network
- * @skb: buffer to process
- *
- * netif_receive_skb() is the main receive data processing function.
- * It always succeeds. The buffer may be dropped during processing
- * for congestion control or by the protocol layers.
- *
- * This function may only be called from softirq context and interrupts
- * should be enabled.
- *
- * Return values (usually ignored):
- * NET_RX_SUCCESS: no congestion
- * NET_RX_DROP: packet was dropped
- */
- int netif_receive_skb(struct sk_buff *skb)
+ static int netif_receive_skb_internal(struct sk_buff *skb)
{
net_timestamp_check(netdev_tstamp_prequeue, skb);
#endif
return __netif_receive_skb(skb);
}
+
+ /**
+ * netif_receive_skb - process receive buffer from network
+ * @skb: buffer to process
+ *
+ * netif_receive_skb() is the main receive data processing function.
+ * It always succeeds. The buffer may be dropped during processing
+ * for congestion control or by the protocol layers.
+ *
+ * This function may only be called from softirq context and interrupts
+ * should be enabled.
+ *
+ * Return values (usually ignored):
+ * NET_RX_SUCCESS: no congestion
+ * NET_RX_DROP: packet was dropped
+ */
+ int netif_receive_skb(struct sk_buff *skb)
+ {
+ trace_netif_receive_skb_entry(skb);
+
+ return netif_receive_skb_internal(skb);
+ }
EXPORT_SYMBOL(netif_receive_skb);
/* Network device is going away, flush any packets still pending
if (ptype->type != type || !ptype->callbacks.gro_complete)
continue;
- err = ptype->callbacks.gro_complete(skb);
+ err = ptype->callbacks.gro_complete(skb, 0);
break;
}
rcu_read_unlock();
}
out:
- return netif_receive_skb(skb);
+ return netif_receive_skb_internal(skb);
}
/* napi->gro_list contains packets ordered by age.
{
struct sk_buff *p;
unsigned int maclen = skb->dev->hard_header_len;
+ u32 hash = skb_get_hash_raw(skb);
for (p = napi->gro_list; p; p = p->next) {
unsigned long diffs;
+ NAPI_GRO_CB(p)->flush = 0;
+
+ if (hash != skb_get_hash_raw(p)) {
+ NAPI_GRO_CB(p)->same_flow = 0;
+ continue;
+ }
+
diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev;
diffs |= p->vlan_tci ^ skb->vlan_tci;
if (maclen == ETH_HLEN)
skb_gro_mac_header(skb),
maclen);
NAPI_GRO_CB(p)->same_flow = !diffs;
- NAPI_GRO_CB(p)->flush = 0;
+ }
+ }
+
+ static void skb_gro_reset_offset(struct sk_buff *skb)
+ {
+ const struct skb_shared_info *pinfo = skb_shinfo(skb);
+ const skb_frag_t *frag0 = &pinfo->frags[0];
+
+ NAPI_GRO_CB(skb)->data_offset = 0;
+ NAPI_GRO_CB(skb)->frag0 = NULL;
+ NAPI_GRO_CB(skb)->frag0_len = 0;
+
+ if (skb_mac_header(skb) == skb_tail_pointer(skb) &&
+ pinfo->nr_frags &&
+ !PageHighMem(skb_frag_page(frag0))) {
+ NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0);
+ NAPI_GRO_CB(skb)->frag0_len = skb_frag_size(frag0);
}
}
if (skb_is_gso(skb) || skb_has_frag_list(skb))
goto normal;
+ skb_gro_reset_offset(skb);
gro_list_prepare(napi, skb);
+ NAPI_GRO_CB(skb)->csum = skb->csum; /* Needed for CHECKSUM_COMPLETE */
rcu_read_lock();
list_for_each_entry_rcu(ptype, head, list) {
NAPI_GRO_CB(skb)->same_flow = 0;
NAPI_GRO_CB(skb)->flush = 0;
NAPI_GRO_CB(skb)->free = 0;
+ NAPI_GRO_CB(skb)->udp_mark = 0;
pp = ptype->callbacks.gro_receive(&napi->gro_list, skb);
break;
if (same_flow)
goto ok;
- if (NAPI_GRO_CB(skb)->flush || napi->gro_count >= MAX_GRO_SKBS)
+ if (NAPI_GRO_CB(skb)->flush)
goto normal;
- napi->gro_count++;
+ 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);
+ } else {
+ napi->gro_count++;
+ }
NAPI_GRO_CB(skb)->count = 1;
NAPI_GRO_CB(skb)->age = jiffies;
skb_shinfo(skb)->gso_size = skb_gro_len(skb);
goto pull;
}
+ struct packet_offload *gro_find_receive_by_type(__be16 type)
+ {
+ struct list_head *offload_head = &offload_base;
+ struct packet_offload *ptype;
+
+ list_for_each_entry_rcu(ptype, offload_head, list) {
+ if (ptype->type != type || !ptype->callbacks.gro_receive)
+ continue;
+ return ptype;
+ }
+ return NULL;
+ }
+ EXPORT_SYMBOL(gro_find_receive_by_type);
+
+ struct packet_offload *gro_find_complete_by_type(__be16 type)
+ {
+ struct list_head *offload_head = &offload_base;
+ struct packet_offload *ptype;
+
+ list_for_each_entry_rcu(ptype, offload_head, list) {
+ if (ptype->type != type || !ptype->callbacks.gro_complete)
+ continue;
+ return ptype;
+ }
+ return NULL;
+ }
+ EXPORT_SYMBOL(gro_find_complete_by_type);
static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb)
{
switch (ret) {
case GRO_NORMAL:
- if (netif_receive_skb(skb))
+ if (netif_receive_skb_internal(skb))
ret = GRO_DROP;
break;
return ret;
}
- static void skb_gro_reset_offset(struct sk_buff *skb)
- {
- const struct skb_shared_info *pinfo = skb_shinfo(skb);
- const skb_frag_t *frag0 = &pinfo->frags[0];
-
- NAPI_GRO_CB(skb)->data_offset = 0;
- NAPI_GRO_CB(skb)->frag0 = NULL;
- NAPI_GRO_CB(skb)->frag0_len = 0;
-
- if (skb_mac_header(skb) == skb_tail_pointer(skb) &&
- pinfo->nr_frags &&
- !PageHighMem(skb_frag_page(frag0))) {
- NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0);
- NAPI_GRO_CB(skb)->frag0_len = skb_frag_size(frag0);
- }
- }
-
gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
{
- skb_gro_reset_offset(skb);
+ trace_napi_gro_receive_entry(skb);
return napi_skb_finish(dev_gro_receive(napi, skb), skb);
}
if (!skb) {
skb = netdev_alloc_skb_ip_align(napi->dev, GRO_MAX_HEAD);
- if (skb)
- napi->skb = skb;
+ napi->skb = skb;
}
return skb;
}
{
switch (ret) {
case GRO_NORMAL:
- case GRO_HELD:
- skb->protocol = eth_type_trans(skb, skb->dev);
-
- if (ret == GRO_HELD)
- skb_gro_pull(skb, -ETH_HLEN);
- else if (netif_receive_skb(skb))
+ if (netif_receive_skb_internal(skb))
ret = GRO_DROP;
break;
napi_reuse_skb(napi, skb);
break;
+ case GRO_HELD:
case GRO_MERGED:
break;
}
static struct sk_buff *napi_frags_skb(struct napi_struct *napi)
{
struct sk_buff *skb = napi->skb;
- struct ethhdr *eth;
- unsigned int hlen;
- unsigned int off;
napi->skb = NULL;
- skb_reset_mac_header(skb);
- skb_gro_reset_offset(skb);
-
- off = skb_gro_offset(skb);
- hlen = off + sizeof(*eth);
- eth = skb_gro_header_fast(skb, off);
- if (skb_gro_header_hard(skb, hlen)) {
- eth = skb_gro_header_slow(skb, hlen, off);
- if (unlikely(!eth)) {
- napi_reuse_skb(napi, skb);
- skb = NULL;
- goto out;
- }
+ if (unlikely(!pskb_may_pull(skb, sizeof(struct ethhdr)))) {
+ napi_reuse_skb(napi, skb);
+ return NULL;
}
+ skb->protocol = eth_type_trans(skb, skb->dev);
- skb_gro_pull(skb, sizeof(*eth));
-
- /*
- * This works because the only protocols we care about don't require
- * special handling. We'll fix it up properly at the end.
- */
- skb->protocol = eth->h_proto;
-
- out:
return skb;
}
if (!skb)
return GRO_DROP;
+ trace_napi_gro_frags_entry(skb);
+
return napi_frags_finish(napi, skb, dev_gro_receive(napi, skb));
}
EXPORT_SYMBOL(napi_gro_frags);
/*
- * net_rps_action sends any pending IPI's for rps.
+ * net_rps_action_and_irq_enable sends any pending IPI's for rps.
* Note: called with local irq disabled, but exits with local irq enabled.
*/
static void net_rps_action_and_irq_enable(struct softnet_data *sd)
void netif_napi_del(struct napi_struct *napi)
{
- struct sk_buff *skb, *next;
-
list_del_init(&napi->dev_list);
napi_free_frags(napi);
- for (skb = napi->gro_list; skb; skb = next) {
- next = skb->next;
- skb->next = NULL;
- kfree_skb(skb);
- }
-
+ kfree_skb_list(napi->gro_list);
napi->gro_list = NULL;
napi->gro_count = 0;
}
struct rcu_head rcu;
};
- static struct netdev_adjacent *__netdev_find_adj_rcu(struct net_device *dev,
- struct net_device *adj_dev,
- struct list_head *adj_list)
- {
- struct netdev_adjacent *adj;
-
- list_for_each_entry_rcu(adj, adj_list, list) {
- if (adj->dev == adj_dev)
- return adj;
- }
- return NULL;
- }
-
static struct netdev_adjacent *__netdev_find_adj(struct net_device *dev,
struct net_device *adj_dev,
struct list_head *adj_list)
* Find out if a device is linked to an upper device and return true in case
* it is. The caller must hold the RTNL lock.
*/
- bool netdev_has_any_upper_dev(struct net_device *dev)
+ static bool netdev_has_any_upper_dev(struct net_device *dev)
{
ASSERT_RTNL();
return !list_empty(&dev->all_adj_list.upper);
}
- EXPORT_SYMBOL(netdev_has_any_upper_dev);
/**
* netdev_master_upper_dev_get - Get master upper device
}
EXPORT_SYMBOL(netdev_lower_get_next_private_rcu);
+ /**
+ * netdev_lower_get_first_private_rcu - Get the first ->private from the
+ * lower neighbour list, RCU
+ * variant
+ * @dev: device
+ *
+ * Gets the first netdev_adjacent->private from the dev's lower neighbour
+ * list. The caller must hold RCU read lock.
+ */
+ void *netdev_lower_get_first_private_rcu(struct net_device *dev)
+ {
+ struct netdev_adjacent *lower;
+
+ lower = list_first_or_null_rcu(&dev->adj_list.lower,
+ struct netdev_adjacent, list);
+ if (lower)
+ return lower->private;
+ return NULL;
+ }
+ EXPORT_SYMBOL(netdev_lower_get_first_private_rcu);
+
/**
* netdev_master_upper_dev_get_rcu - Get master upper device
* @dev: device
}
EXPORT_SYMBOL(netdev_master_upper_dev_get_rcu);
+ int netdev_adjacent_sysfs_add(struct net_device *dev,
+ struct net_device *adj_dev,
+ struct list_head *dev_list)
+ {
+ char linkname[IFNAMSIZ+7];
+ sprintf(linkname, dev_list == &dev->adj_list.upper ?
+ "upper_%s" : "lower_%s", adj_dev->name);
+ return sysfs_create_link(&(dev->dev.kobj), &(adj_dev->dev.kobj),
+ linkname);
+ }
+ void netdev_adjacent_sysfs_del(struct net_device *dev,
+ char *name,
+ struct list_head *dev_list)
+ {
+ char linkname[IFNAMSIZ+7];
+ sprintf(linkname, dev_list == &dev->adj_list.upper ?
+ "upper_%s" : "lower_%s", name);
+ sysfs_remove_link(&(dev->dev.kobj), linkname);
+ }
+
+ #define netdev_adjacent_is_neigh_list(dev, dev_list) \
+ (dev_list == &dev->adj_list.upper || \
+ dev_list == &dev->adj_list.lower)
+
static int __netdev_adjacent_dev_insert(struct net_device *dev,
struct net_device *adj_dev,
struct list_head *dev_list,
void *private, bool master)
{
struct netdev_adjacent *adj;
- char linkname[IFNAMSIZ+7];
int ret;
adj = __netdev_find_adj(dev, adj_dev, dev_list);
pr_debug("dev_hold for %s, because of link added from %s to %s\n",
adj_dev->name, dev->name, adj_dev->name);
- if (dev_list == &dev->adj_list.lower) {
- sprintf(linkname, "lower_%s", adj_dev->name);
- ret = sysfs_create_link(&(dev->dev.kobj),
- &(adj_dev->dev.kobj), linkname);
- if (ret)
- goto free_adj;
- } else if (dev_list == &dev->adj_list.upper) {
- sprintf(linkname, "upper_%s", adj_dev->name);
- ret = sysfs_create_link(&(dev->dev.kobj),
- &(adj_dev->dev.kobj), linkname);
+ if (netdev_adjacent_is_neigh_list(dev, dev_list)) {
+ ret = netdev_adjacent_sysfs_add(dev, adj_dev, dev_list);
if (ret)
goto free_adj;
}
return 0;
remove_symlinks:
- if (dev_list == &dev->adj_list.lower) {
- sprintf(linkname, "lower_%s", adj_dev->name);
- sysfs_remove_link(&(dev->dev.kobj), linkname);
- } else if (dev_list == &dev->adj_list.upper) {
- sprintf(linkname, "upper_%s", adj_dev->name);
- sysfs_remove_link(&(dev->dev.kobj), linkname);
- }
-
+ if (netdev_adjacent_is_neigh_list(dev, dev_list))
+ netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list);
free_adj:
kfree(adj);
dev_put(adj_dev);
return ret;
}
- void __netdev_adjacent_dev_remove(struct net_device *dev,
- struct net_device *adj_dev,
- struct list_head *dev_list)
+ static void __netdev_adjacent_dev_remove(struct net_device *dev,
+ struct net_device *adj_dev,
+ struct list_head *dev_list)
{
struct netdev_adjacent *adj;
- char linkname[IFNAMSIZ+7];
adj = __netdev_find_adj(dev, adj_dev, dev_list);
if (adj->master)
sysfs_remove_link(&(dev->dev.kobj), "master");
- if (dev_list == &dev->adj_list.lower) {
- sprintf(linkname, "lower_%s", adj_dev->name);
- sysfs_remove_link(&(dev->dev.kobj), linkname);
- } else if (dev_list == &dev->adj_list.upper) {
- sprintf(linkname, "upper_%s", adj_dev->name);
- sysfs_remove_link(&(dev->dev.kobj), linkname);
- }
+ if (netdev_adjacent_is_neigh_list(dev, dev_list))
+ netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list);
list_del_rcu(&adj->list);
pr_debug("dev_put for %s, because link removed from %s to %s\n",
kfree_rcu(adj, rcu);
}
- int __netdev_adjacent_dev_link_lists(struct net_device *dev,
- struct net_device *upper_dev,
- struct list_head *up_list,
- struct list_head *down_list,
- void *private, bool master)
+ static int __netdev_adjacent_dev_link_lists(struct net_device *dev,
+ struct net_device *upper_dev,
+ struct list_head *up_list,
+ struct list_head *down_list,
+ void *private, bool master)
{
int ret;
return 0;
}
- int __netdev_adjacent_dev_link(struct net_device *dev,
- struct net_device *upper_dev)
+ static int __netdev_adjacent_dev_link(struct net_device *dev,
+ struct net_device *upper_dev)
{
return __netdev_adjacent_dev_link_lists(dev, upper_dev,
&dev->all_adj_list.upper,
NULL, false);
}
- void __netdev_adjacent_dev_unlink_lists(struct net_device *dev,
- struct net_device *upper_dev,
- struct list_head *up_list,
- struct list_head *down_list)
+ static void __netdev_adjacent_dev_unlink_lists(struct net_device *dev,
+ struct net_device *upper_dev,
+ struct list_head *up_list,
+ struct list_head *down_list)
{
__netdev_adjacent_dev_remove(dev, upper_dev, up_list);
__netdev_adjacent_dev_remove(upper_dev, dev, down_list);
}
- void __netdev_adjacent_dev_unlink(struct net_device *dev,
- struct net_device *upper_dev)
+ static void __netdev_adjacent_dev_unlink(struct net_device *dev,
+ struct net_device *upper_dev)
{
__netdev_adjacent_dev_unlink_lists(dev, upper_dev,
&dev->all_adj_list.upper,
&upper_dev->all_adj_list.lower);
}
- int __netdev_adjacent_dev_link_neighbour(struct net_device *dev,
- struct net_device *upper_dev,
- void *private, bool master)
+ static int __netdev_adjacent_dev_link_neighbour(struct net_device *dev,
+ struct net_device *upper_dev,
+ void *private, bool master)
{
int ret = __netdev_adjacent_dev_link(dev, upper_dev);
return 0;
}
- void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev,
- struct net_device *upper_dev)
+ static void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev,
+ struct net_device *upper_dev)
{
__netdev_adjacent_dev_unlink(dev, upper_dev);
__netdev_adjacent_dev_unlink_lists(dev, upper_dev,
}
EXPORT_SYMBOL(netdev_upper_dev_unlink);
- void *netdev_lower_dev_get_private_rcu(struct net_device *dev,
- struct net_device *lower_dev)
+ void netdev_adjacent_rename_links(struct net_device *dev, char *oldname)
{
- struct netdev_adjacent *lower;
+ struct netdev_adjacent *iter;
- if (!lower_dev)
- return NULL;
- lower = __netdev_find_adj_rcu(dev, lower_dev, &dev->adj_list.lower);
- if (!lower)
- return NULL;
+ list_for_each_entry(iter, &dev->adj_list.upper, list) {
+ netdev_adjacent_sysfs_del(iter->dev, oldname,
+ &iter->dev->adj_list.lower);
+ netdev_adjacent_sysfs_add(iter->dev, dev,
+ &iter->dev->adj_list.lower);
+ }
- return lower->private;
+ list_for_each_entry(iter, &dev->adj_list.lower, list) {
+ netdev_adjacent_sysfs_del(iter->dev, oldname,
+ &iter->dev->adj_list.upper);
+ netdev_adjacent_sysfs_add(iter->dev, dev,
+ &iter->dev->adj_list.upper);
+ }
}
- EXPORT_SYMBOL(netdev_lower_dev_get_private_rcu);
void *netdev_lower_dev_get_private(struct net_device *dev,
struct net_device *lower_dev)
}
EXPORT_SYMBOL(dev_change_flags);
+ static int __dev_set_mtu(struct net_device *dev, int new_mtu)
+ {
+ const struct net_device_ops *ops = dev->netdev_ops;
+
+ if (ops->ndo_change_mtu)
+ return ops->ndo_change_mtu(dev, new_mtu);
+
+ dev->mtu = new_mtu;
+ return 0;
+ }
+
/**
* dev_set_mtu - Change maximum transfer unit
* @dev: device
*/
int dev_set_mtu(struct net_device *dev, int new_mtu)
{
- const struct net_device_ops *ops = dev->netdev_ops;
- int err;
+ int err, orig_mtu;
if (new_mtu == dev->mtu)
return 0;
if (!netif_device_present(dev))
return -ENODEV;
- err = 0;
- if (ops->ndo_change_mtu)
- err = ops->ndo_change_mtu(dev, new_mtu);
- else
- dev->mtu = new_mtu;
+ err = call_netdevice_notifiers(NETDEV_PRECHANGEMTU, dev);
+ err = notifier_to_errno(err);
+ if (err)
+ return err;
- if (!err)
- call_netdevice_notifiers(NETDEV_CHANGEMTU, dev);
+ orig_mtu = dev->mtu;
+ err = __dev_set_mtu(dev, new_mtu);
+
+ if (!err) {
+ err = call_netdevice_notifiers(NETDEV_CHANGEMTU, dev);
+ err = notifier_to_errno(err);
+ if (err) {
+ /* setting mtu back and notifying everyone again,
+ * so that they have a chance to revert changes.
+ */
+ __dev_set_mtu(dev, orig_mtu);
+ call_netdevice_notifiers(NETDEV_CHANGEMTU, dev);
+ }
+ }
return err;
}
EXPORT_SYMBOL(dev_set_mtu);
}
EXPORT_SYMBOL(netif_stacked_transfer_operstate);
- #ifdef CONFIG_RPS
+ #ifdef CONFIG_SYSFS
static int netif_alloc_rx_queues(struct net_device *dev)
{
unsigned int i, count = dev->num_rx_queues;
dev->features |= NETIF_F_SOFT_FEATURES;
dev->wanted_features = dev->features & dev->hw_features;
- /* Turn on no cache copy if HW is doing checksum */
if (!(dev->flags & IFF_LOOPBACK)) {
dev->hw_features |= NETIF_F_NOCACHE_COPY;
- if (dev->features & NETIF_F_ALL_CSUM) {
- dev->wanted_features |= NETIF_F_NOCACHE_COPY;
- dev->features |= NETIF_F_NOCACHE_COPY;
- }
}
/* Make NETIF_F_HIGHDMA inheritable to VLAN devices.
* @rxqs: the number of RX subqueues to allocate
*
* Allocates a struct net_device with private data area for driver use
- * and performs basic initialization. Also allocates subquue structs
+ * and performs basic initialization. Also allocates subqueue structs
* for each queue on the device.
*/
struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
return NULL;
}
- #ifdef CONFIG_RPS
+ #ifdef CONFIG_SYSFS
if (rxqs < 1) {
pr_err("alloc_netdev: Unable to allocate device with zero RX queues\n");
return NULL;
if (netif_alloc_netdev_queues(dev))
goto free_all;
- #ifdef CONFIG_RPS
+ #ifdef CONFIG_SYSFS
dev->num_rx_queues = rxqs;
dev->real_num_rx_queues = rxqs;
if (netif_alloc_rx_queues(dev))
free_pcpu:
free_percpu(dev->pcpu_refcnt);
netif_free_tx_queues(dev);
- #ifdef CONFIG_RPS
+ #ifdef CONFIG_SYSFS
kfree(dev->_rx);
#endif
release_net(dev_net(dev));
netif_free_tx_queues(dev);
- #ifdef CONFIG_RPS
+ #ifdef CONFIG_SYSFS
kfree(dev->_rx);
#endif
/* Process offline CPU's input_pkt_queue */
while ((skb = __skb_dequeue(&oldsd->process_queue))) {
- netif_rx(skb);
+ netif_rx_internal(skb);
input_queue_head_incr(oldsd);
}
while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) {
- netif_rx(skb);
+ netif_rx_internal(skb);
input_queue_head_incr(oldsd);
}
for_each_possible_cpu(i) {
struct softnet_data *sd = &per_cpu(softnet_data, i);
- memset(sd, 0, sizeof(*sd));
skb_queue_head_init(&sd->input_pkt_queue);
skb_queue_head_init(&sd->process_queue);
- sd->completion_queue = NULL;
INIT_LIST_HEAD(&sd->poll_list);
- sd->output_queue = NULL;
sd->output_queue_tailp = &sd->output_queue;
#ifdef CONFIG_RPS
sd->csd.func = rps_trigger_softirq;
sd->csd.info = sd;
- sd->csd.flags = 0;
sd->cpu = i;
#endif
sd->backlog.poll = process_backlog;
sd->backlog.weight = weight_p;
- sd->backlog.gro_list = NULL;
- sd->backlog.gro_count = 0;
-
- #ifdef CONFIG_NET_FLOW_LIMIT
- sd->flow_limit = NULL;
- #endif
}
dev_boot_phase = 0;
#define PRIOMAP_MIN_SZ 128
/*
- * Extend @dev->priomap so that it's large enough to accomodate
+ * Extend @dev->priomap so that it's large enough to accommodate
* @target_idx. @dev->priomap.priomap_len > @target_idx after successful
* return. Must be called under rtnl lock.
*/
return css->cgroup->id;
}
-static int read_priomap(struct cgroup_subsys_state *css, struct cftype *cft,
- struct cgroup_map_cb *cb)
+static int read_priomap(struct seq_file *sf, void *v)
{
struct net_device *dev;
rcu_read_lock();
for_each_netdev_rcu(&init_net, dev)
- cb->fill(cb, dev->name, netprio_prio(css, dev));
+ seq_printf(sf, "%s %u\n", dev->name,
+ netprio_prio(seq_css(sf), dev));
rcu_read_unlock();
return 0;
}
},
{
.name = "ifpriomap",
- .read_map = read_priomap,
+ .seq_show = read_priomap,
.write_string = write_priomap,
},
{ } /* terminate */
#include <net/dst.h>
#include <net/sock.h>
#include <net/checksum.h>
+ #include <net/ip6_checksum.h>
#include <net/xfrm.h>
#include <asm/uaccess.h>
struct kmem_cache *skbuff_head_cache __read_mostly;
static struct kmem_cache *skbuff_fclone_cache __read_mostly;
-static void sock_pipe_buf_release(struct pipe_inode_info *pipe,
- struct pipe_buffer *buf)
-{
- put_page(buf->page);
-}
-
-static void sock_pipe_buf_get(struct pipe_inode_info *pipe,
- struct pipe_buffer *buf)
-{
- get_page(buf->page);
-}
-
-static int sock_pipe_buf_steal(struct pipe_inode_info *pipe,
- struct pipe_buffer *buf)
-{
- return 1;
-}
-
-
-/* Pipe buffer operations for a socket. */
-static const struct pipe_buf_operations sock_pipe_buf_ops = {
- .can_merge = 0,
- .map = generic_pipe_buf_map,
- .unmap = generic_pipe_buf_unmap,
- .confirm = generic_pipe_buf_confirm,
- .release = sock_pipe_buf_release,
- .steal = sock_pipe_buf_steal,
- .get = sock_pipe_buf_get,
-};
-
/**
* skb_panic - private function for out-of-line support
* @skb: buffer
new->inner_network_header = old->inner_network_header;
new->inner_mac_header = old->inner_mac_header;
skb_dst_copy(new, old);
- new->rxhash = old->rxhash;
+ skb_copy_hash(new, old);
new->ooo_okay = old->ooo_okay;
- new->l4_rxhash = old->l4_rxhash;
new->no_fcs = old->no_fcs;
new->encapsulation = old->encapsulation;
#ifdef CONFIG_XFRM
.partial = partial,
.nr_pages_max = MAX_SKB_FRAGS,
.flags = flags,
- .ops = &sock_pipe_buf_ops,
+ .ops = &nosteal_pipe_buf_ops,
.spd_release = sock_spd_release,
};
struct sk_buff *frag_iter;
}
EXPORT_SYMBOL(skb_copy_and_csum_bits);
+ /**
+ * skb_zerocopy_headlen - Calculate headroom needed for skb_zerocopy()
+ * @from: source buffer
+ *
+ * Calculates the amount of linear headroom needed in the 'to' skb passed
+ * into skb_zerocopy().
+ */
+ unsigned int
+ skb_zerocopy_headlen(const struct sk_buff *from)
+ {
+ unsigned int hlen = 0;
+
+ if (!from->head_frag ||
+ skb_headlen(from) < L1_CACHE_BYTES ||
+ skb_shinfo(from)->nr_frags >= MAX_SKB_FRAGS)
+ hlen = skb_headlen(from);
+
+ if (skb_has_frag_list(from))
+ hlen = from->len;
+
+ return hlen;
+ }
+ EXPORT_SYMBOL_GPL(skb_zerocopy_headlen);
+
+ /**
+ * skb_zerocopy - Zero copy skb to skb
+ * @to: destination buffer
+ * @source: source buffer
+ * @len: number of bytes to copy from source buffer
+ * @hlen: size of linear headroom in destination buffer
+ *
+ * Copies up to `len` bytes from `from` to `to` by creating references
+ * to the frags in the source buffer.
+ *
+ * The `hlen` as calculated by skb_zerocopy_headlen() specifies the
+ * headroom in the `to` buffer.
+ */
+ void
+ skb_zerocopy(struct sk_buff *to, const struct sk_buff *from, int len, int hlen)
+ {
+ int i, j = 0;
+ int plen = 0; /* length of skb->head fragment */
+ struct page *page;
+ unsigned int offset;
+
+ BUG_ON(!from->head_frag && !hlen);
+
+ /* dont bother with small payloads */
+ if (len <= skb_tailroom(to)) {
+ skb_copy_bits(from, 0, skb_put(to, len), len);
+ return;
+ }
+
+ if (hlen) {
+ skb_copy_bits(from, 0, skb_put(to, hlen), hlen);
+ len -= hlen;
+ } else {
+ plen = min_t(int, skb_headlen(from), len);
+ if (plen) {
+ page = virt_to_head_page(from->head);
+ offset = from->data - (unsigned char *)page_address(page);
+ __skb_fill_page_desc(to, 0, page, offset, plen);
+ get_page(page);
+ j = 1;
+ len -= plen;
+ }
+ }
+
+ to->truesize += len + plen;
+ to->len += len + plen;
+ to->data_len += len + plen;
+
+ for (i = 0; i < skb_shinfo(from)->nr_frags; i++) {
+ if (!len)
+ break;
+ skb_shinfo(to)->frags[j] = skb_shinfo(from)->frags[i];
+ skb_shinfo(to)->frags[j].size = min_t(int, skb_shinfo(to)->frags[j].size, len);
+ len -= skb_shinfo(to)->frags[j].size;
+ skb_frag_ref(to, j);
+ j++;
+ }
+ skb_shinfo(to)->nr_frags = j;
+ }
+ EXPORT_SYMBOL_GPL(skb_zerocopy);
+
void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to)
{
__wsum csum;
return segs;
err:
- while ((skb = segs)) {
- segs = skb->next;
- kfree_skb(skb);
- }
+ kfree_skb_list(segs);
return ERR_PTR(err);
}
EXPORT_SYMBOL_GPL(skb_segment);
}
EXPORT_SYMBOL_GPL(skb_partial_csum_set);
+ static int skb_maybe_pull_tail(struct sk_buff *skb, unsigned int len,
+ unsigned int max)
+ {
+ if (skb_headlen(skb) >= len)
+ return 0;
+
+ /* If we need to pullup then pullup to the max, so we
+ * won't need to do it again.
+ */
+ if (max > skb->len)
+ max = skb->len;
+
+ if (__pskb_pull_tail(skb, max - skb_headlen(skb)) == NULL)
+ return -ENOMEM;
+
+ if (skb_headlen(skb) < len)
+ return -EPROTO;
+
+ return 0;
+ }
+
+ /* This value should be large enough to cover a tagged ethernet header plus
+ * maximally sized IP and TCP or UDP headers.
+ */
+ #define MAX_IP_HDR_LEN 128
+
+ static int skb_checksum_setup_ip(struct sk_buff *skb, bool recalculate)
+ {
+ unsigned int off;
+ bool fragment;
+ int err;
+
+ fragment = false;
+
+ err = skb_maybe_pull_tail(skb,
+ sizeof(struct iphdr),
+ MAX_IP_HDR_LEN);
+ if (err < 0)
+ goto out;
+
+ if (ip_hdr(skb)->frag_off & htons(IP_OFFSET | IP_MF))
+ fragment = true;
+
+ off = ip_hdrlen(skb);
+
+ err = -EPROTO;
+
+ if (fragment)
+ goto out;
+
+ switch (ip_hdr(skb)->protocol) {
+ case IPPROTO_TCP:
+ err = skb_maybe_pull_tail(skb,
+ off + sizeof(struct tcphdr),
+ MAX_IP_HDR_LEN);
+ if (err < 0)
+ goto out;
+
+ if (!skb_partial_csum_set(skb, off,
+ offsetof(struct tcphdr, check))) {
+ err = -EPROTO;
+ goto out;
+ }
+
+ if (recalculate)
+ tcp_hdr(skb)->check =
+ ~csum_tcpudp_magic(ip_hdr(skb)->saddr,
+ ip_hdr(skb)->daddr,
+ skb->len - off,
+ IPPROTO_TCP, 0);
+ break;
+ case IPPROTO_UDP:
+ err = skb_maybe_pull_tail(skb,
+ off + sizeof(struct udphdr),
+ MAX_IP_HDR_LEN);
+ if (err < 0)
+ goto out;
+
+ if (!skb_partial_csum_set(skb, off,
+ offsetof(struct udphdr, check))) {
+ err = -EPROTO;
+ goto out;
+ }
+
+ if (recalculate)
+ udp_hdr(skb)->check =
+ ~csum_tcpudp_magic(ip_hdr(skb)->saddr,
+ ip_hdr(skb)->daddr,
+ skb->len - off,
+ IPPROTO_UDP, 0);
+ break;
+ default:
+ goto out;
+ }
+
+ err = 0;
+
+ out:
+ return err;
+ }
+
+ /* This value should be large enough to cover a tagged ethernet header plus
+ * an IPv6 header, all options, and a maximal TCP or UDP header.
+ */
+ #define MAX_IPV6_HDR_LEN 256
+
+ #define OPT_HDR(type, skb, off) \
+ (type *)(skb_network_header(skb) + (off))
+
+ static int skb_checksum_setup_ipv6(struct sk_buff *skb, bool recalculate)
+ {
+ int err;
+ u8 nexthdr;
+ unsigned int off;
+ unsigned int len;
+ bool fragment;
+ bool done;
+
+ fragment = false;
+ done = false;
+
+ off = sizeof(struct ipv6hdr);
+
+ err = skb_maybe_pull_tail(skb, off, MAX_IPV6_HDR_LEN);
+ if (err < 0)
+ goto out;
+
+ nexthdr = ipv6_hdr(skb)->nexthdr;
+
+ len = sizeof(struct ipv6hdr) + ntohs(ipv6_hdr(skb)->payload_len);
+ while (off <= len && !done) {
+ switch (nexthdr) {
+ case IPPROTO_DSTOPTS:
+ case IPPROTO_HOPOPTS:
+ case IPPROTO_ROUTING: {
+ struct ipv6_opt_hdr *hp;
+
+ err = skb_maybe_pull_tail(skb,
+ off +
+ sizeof(struct ipv6_opt_hdr),
+ MAX_IPV6_HDR_LEN);
+ if (err < 0)
+ goto out;
+
+ hp = OPT_HDR(struct ipv6_opt_hdr, skb, off);
+ nexthdr = hp->nexthdr;
+ off += ipv6_optlen(hp);
+ break;
+ }
+ case IPPROTO_AH: {
+ struct ip_auth_hdr *hp;
+
+ err = skb_maybe_pull_tail(skb,
+ off +
+ sizeof(struct ip_auth_hdr),
+ MAX_IPV6_HDR_LEN);
+ if (err < 0)
+ goto out;
+
+ hp = OPT_HDR(struct ip_auth_hdr, skb, off);
+ nexthdr = hp->nexthdr;
+ off += ipv6_authlen(hp);
+ break;
+ }
+ case IPPROTO_FRAGMENT: {
+ struct frag_hdr *hp;
+
+ err = skb_maybe_pull_tail(skb,
+ off +
+ sizeof(struct frag_hdr),
+ MAX_IPV6_HDR_LEN);
+ if (err < 0)
+ goto out;
+
+ hp = OPT_HDR(struct frag_hdr, skb, off);
+
+ if (hp->frag_off & htons(IP6_OFFSET | IP6_MF))
+ fragment = true;
+
+ nexthdr = hp->nexthdr;
+ off += sizeof(struct frag_hdr);
+ break;
+ }
+ default:
+ done = true;
+ break;
+ }
+ }
+
+ err = -EPROTO;
+
+ if (!done || fragment)
+ goto out;
+
+ switch (nexthdr) {
+ case IPPROTO_TCP:
+ err = skb_maybe_pull_tail(skb,
+ off + sizeof(struct tcphdr),
+ MAX_IPV6_HDR_LEN);
+ if (err < 0)
+ goto out;
+
+ if (!skb_partial_csum_set(skb, off,
+ offsetof(struct tcphdr, check))) {
+ err = -EPROTO;
+ goto out;
+ }
+
+ if (recalculate)
+ tcp_hdr(skb)->check =
+ ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
+ &ipv6_hdr(skb)->daddr,
+ skb->len - off,
+ IPPROTO_TCP, 0);
+ break;
+ case IPPROTO_UDP:
+ err = skb_maybe_pull_tail(skb,
+ off + sizeof(struct udphdr),
+ MAX_IPV6_HDR_LEN);
+ if (err < 0)
+ goto out;
+
+ if (!skb_partial_csum_set(skb, off,
+ offsetof(struct udphdr, check))) {
+ err = -EPROTO;
+ goto out;
+ }
+
+ if (recalculate)
+ udp_hdr(skb)->check =
+ ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
+ &ipv6_hdr(skb)->daddr,
+ skb->len - off,
+ IPPROTO_UDP, 0);
+ break;
+ default:
+ goto out;
+ }
+
+ err = 0;
+
+ out:
+ return err;
+ }
+
+ /**
+ * skb_checksum_setup - set up partial checksum offset
+ * @skb: the skb to set up
+ * @recalculate: if true the pseudo-header checksum will be recalculated
+ */
+ int skb_checksum_setup(struct sk_buff *skb, bool recalculate)
+ {
+ int err;
+
+ switch (skb->protocol) {
+ case htons(ETH_P_IP):
+ err = skb_checksum_setup_ip(skb, recalculate);
+ break;
+
+ case htons(ETH_P_IPV6):
+ err = skb_checksum_setup_ipv6(skb, recalculate);
+ break;
+
+ default:
+ err = -EPROTO;
+ break;
+ }
+
+ return err;
+ }
+ EXPORT_SYMBOL(skb_checksum_setup);
+
void __skb_warn_lro_forwarding(const struct sk_buff *skb)
{
net_warn_ratelimited("%s: received packets cannot be forwarded while LRO is enabled\n",
int sysctl_tcp_min_tso_segs __read_mostly = 2;
+ int sysctl_tcp_autocorking __read_mostly = 1;
+
struct percpu_counter tcp_orphan_count;
EXPORT_SYMBOL_GPL(tcp_orphan_count);
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
- skb_queue_head_init(&tp->out_of_order_queue);
+ __skb_queue_head_init(&tp->out_of_order_queue);
tcp_init_xmit_timers(sk);
tcp_prequeue_init(tp);
INIT_LIST_HEAD(&tp->tsq_node);
tp->snd_up = tp->write_seq;
}
- static inline void tcp_push(struct sock *sk, int flags, int mss_now,
- int nonagle)
+ /* If a not yet filled skb is pushed, do not send it if
+ * we have data packets in Qdisc or NIC queues :
+ * Because TX completion will happen shortly, it gives a chance
+ * to coalesce future sendmsg() payload into this skb, without
+ * need for a timer, and with no latency trade off.
+ * As packets containing data payload have a bigger truesize
+ * than pure acks (dataless) packets, the last checks prevent
+ * autocorking if we only have an ACK in Qdisc/NIC queues,
+ * or if TX completion was delayed after we processed ACK packet.
+ */
+ static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb,
+ int size_goal)
{
- if (tcp_send_head(sk)) {
- struct tcp_sock *tp = tcp_sk(sk);
+ return skb->len < size_goal &&
+ sysctl_tcp_autocorking &&
+ skb != tcp_write_queue_head(sk) &&
+ atomic_read(&sk->sk_wmem_alloc) > skb->truesize;
+ }
+
+ static void tcp_push(struct sock *sk, int flags, int mss_now,
+ int nonagle, int size_goal)
+ {
+ struct tcp_sock *tp = tcp_sk(sk);
+ struct sk_buff *skb;
- if (!(flags & MSG_MORE) || forced_push(tp))
- tcp_mark_push(tp, tcp_write_queue_tail(sk));
+ if (!tcp_send_head(sk))
+ return;
- tcp_mark_urg(tp, flags);
- __tcp_push_pending_frames(sk, mss_now,
- (flags & MSG_MORE) ? TCP_NAGLE_CORK : nonagle);
+ skb = tcp_write_queue_tail(sk);
+ if (!(flags & MSG_MORE) || forced_push(tp))
+ tcp_mark_push(tp, skb);
+
+ tcp_mark_urg(tp, flags);
+
+ if (tcp_should_autocork(sk, skb, size_goal)) {
+
+ /* avoid atomic op if TSQ_THROTTLED bit is already set */
+ if (!test_bit(TSQ_THROTTLED, &tp->tsq_flags)) {
+ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAUTOCORKING);
+ set_bit(TSQ_THROTTLED, &tp->tsq_flags);
+ }
+ /* It is possible TX completion already happened
+ * before we set TSQ_THROTTLED.
+ */
+ if (atomic_read(&sk->sk_wmem_alloc) > skb->truesize)
+ return;
}
+
+ if (flags & MSG_MORE)
+ nonagle = TCP_NAGLE_CORK;
+
+ __tcp_push_pending_frames(sk, mss_now, nonagle);
}
static int tcp_splice_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb,
wait_for_sndbuf:
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
wait_for_memory:
- tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH);
+ tcp_push(sk, flags & ~MSG_MORE, mss_now,
+ TCP_NAGLE_PUSH, size_goal);
if ((err = sk_stream_wait_memory(sk, &timeo)) != 0)
goto do_error;
out:
if (copied && !(flags & MSG_SENDPAGE_NOTLAST))
- tcp_push(sk, flags, mss_now, tp->nonagle);
+ tcp_push(sk, flags, mss_now, tp->nonagle, size_goal);
return copied;
do_error:
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
wait_for_memory:
if (copied)
- tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH);
+ tcp_push(sk, flags & ~MSG_MORE, mss_now,
+ TCP_NAGLE_PUSH, size_goal);
if ((err = sk_stream_wait_memory(sk, &timeo)) != 0)
goto do_error;
out:
if (copied)
- tcp_push(sk, flags, mss_now, tp->nonagle);
+ tcp_push(sk, flags, mss_now, tp->nonagle, size_goal);
release_sock(sk);
return copied + copied_syn;
(len > sysctl_tcp_dma_copybreak) && !(flags & MSG_PEEK) &&
!sysctl_tcp_low_latency &&
net_dma_find_channel()) {
- preempt_enable_no_resched();
+ preempt_enable();
tp->ucopy.pinned_list =
dma_pin_iovec_pages(msg->msg_iov, len);
} else {
- preempt_enable_no_resched();
+ preempt_enable();
}
}
#endif
#define DIGITAL_ATR_REQ_MIN_SIZE 16
#define DIGITAL_ATR_REQ_MAX_SIZE 64
- #define DIGITAL_NFCID3_LEN ((u8)8)
#define DIGITAL_LR_BITS_PAYLOAD_SIZE_254B 0x30
#define DIGITAL_GB_BIT 0x02
atr_req->dir = DIGITAL_NFC_DEP_FRAME_DIR_OUT;
atr_req->cmd = DIGITAL_CMD_ATR_REQ;
if (target->nfcid2_len)
- memcpy(atr_req->nfcid3, target->nfcid2,
- max(target->nfcid2_len, DIGITAL_NFCID3_LEN));
+ memcpy(atr_req->nfcid3, target->nfcid2, NFC_NFCID2_MAXSIZE);
else
- get_random_bytes(atr_req->nfcid3, DIGITAL_NFCID3_LEN);
+ get_random_bytes(atr_req->nfcid3, NFC_NFCID3_MAXSIZE);
atr_req->did = 0;
atr_req->bs = 0;
data_exch);
}
+ static void digital_tg_set_rf_tech(struct nfc_digital_dev *ddev, u8 rf_tech)
+ {
+ ddev->curr_rf_tech = rf_tech;
+
+ ddev->skb_add_crc = digital_skb_add_crc_none;
+ ddev->skb_check_crc = digital_skb_check_crc_none;
+
+ if (DIGITAL_DRV_CAPS_TG_CRC(ddev))
+ return;
+
+ switch (ddev->curr_rf_tech) {
+ case NFC_DIGITAL_RF_TECH_106A:
+ ddev->skb_add_crc = digital_skb_add_crc_a;
+ ddev->skb_check_crc = digital_skb_check_crc_a;
+ break;
+
+ case NFC_DIGITAL_RF_TECH_212F:
+ case NFC_DIGITAL_RF_TECH_424F:
+ ddev->skb_add_crc = digital_skb_add_crc_f;
+ ddev->skb_check_crc = digital_skb_check_crc_f;
+ break;
+
+ default:
+ break;
+ }
+ }
+
static void digital_tg_recv_dep_req(struct nfc_digital_dev *ddev, void *arg,
struct sk_buff *resp)
{
static void digital_tg_send_psl_res_complete(struct nfc_digital_dev *ddev,
void *arg, struct sk_buff *resp)
{
- u8 rf_tech = PTR_ERR(arg);
+ u8 rf_tech = (unsigned long)arg;
if (IS_ERR(resp))
return;
+ digital_tg_set_rf_tech(ddev, rf_tech);
+
digital_tg_configure_hw(ddev, NFC_DIGITAL_CONFIG_RF_TECH, rf_tech);
digital_tg_listen(ddev, 1500, digital_tg_recv_dep_req, NULL);
ddev->skb_add_crc(skb);
rc = digital_tg_send_cmd(ddev, skb, 0, digital_tg_send_psl_res_complete,
- ERR_PTR(rf_tech));
+ (void *)(unsigned long)rf_tech);
if (rc)
kfree_skb(skb);
rf_tech = NFC_DIGITAL_RF_TECH_424F;
break;
default:
- pr_err("Unsuported dsi value %d\n", dsi);
+ pr_err("Unsupported dsi value %d\n", dsi);
goto exit;
}
if (resp->data[0] == DIGITAL_NFC_DEP_NFCA_SOD_SB) {
min_size = DIGITAL_ATR_REQ_MIN_SIZE + 2;
-
- ddev->curr_rf_tech = NFC_DIGITAL_RF_TECH_106A;
- ddev->skb_add_crc = digital_skb_add_crc_a;
- ddev->skb_check_crc = digital_skb_check_crc_a;
+ digital_tg_set_rf_tech(ddev, NFC_DIGITAL_RF_TECH_106A);
} else {
min_size = DIGITAL_ATR_REQ_MIN_SIZE + 1;
-
- ddev->curr_rf_tech = NFC_DIGITAL_RF_TECH_212F;
- ddev->skb_add_crc = digital_skb_add_crc_f;
- ddev->skb_check_crc = digital_skb_check_crc_f;
+ digital_tg_set_rf_tech(ddev, NFC_DIGITAL_RF_TECH_212F);
}
if (resp->len < min_size) {
goto exit;
}
- if (DIGITAL_DRV_CAPS_TG_CRC(ddev)) {
- ddev->skb_add_crc = digital_skb_add_crc_none;
- ddev->skb_check_crc = digital_skb_check_crc_none;
- }
+ ddev->curr_protocol = NFC_PROTO_NFC_DEP_MASK;
rc = ddev->skb_check_crc(resp);
if (rc) {
#define XFRM_QUEUE_TMO_MAX ((unsigned)(60*HZ))
#define XFRM_MAX_QUEUE_LEN 100
- DEFINE_MUTEX(xfrm_cfg_mutex);
- EXPORT_SYMBOL(xfrm_cfg_mutex);
-
- static DEFINE_SPINLOCK(xfrm_policy_sk_bundle_lock);
static struct dst_entry *xfrm_policy_sk_bundles;
- static DEFINE_RWLOCK(xfrm_policy_lock);
static DEFINE_SPINLOCK(xfrm_policy_afinfo_lock);
static struct xfrm_policy_afinfo __rcu *xfrm_policy_afinfo[NPROTO]
static void xfrm_policy_timer(unsigned long data)
{
- struct xfrm_policy *xp = (struct xfrm_policy*)data;
+ struct xfrm_policy *xp = (struct xfrm_policy *)data;
unsigned long now = get_seconds();
long next = LONG_MAX;
int warn = 0;
if (!ndst)
return;
- write_lock_bh(&xfrm_policy_lock);
+ write_lock_bh(&net->xfrm.xfrm_policy_lock);
for (i = hmask; i >= 0; i--)
xfrm_dst_hash_transfer(odst + i, ndst, nhashmask);
net->xfrm.policy_bydst[dir].table = ndst;
net->xfrm.policy_bydst[dir].hmask = nhashmask;
- write_unlock_bh(&xfrm_policy_lock);
+ write_unlock_bh(&net->xfrm.xfrm_policy_lock);
xfrm_hash_free(odst, (hmask + 1) * sizeof(struct hlist_head));
}
if (!nidx)
return;
- write_lock_bh(&xfrm_policy_lock);
+ write_lock_bh(&net->xfrm.xfrm_policy_lock);
for (i = hmask; i >= 0; i--)
xfrm_idx_hash_transfer(oidx + i, nidx, nhashmask);
net->xfrm.policy_byidx = nidx;
net->xfrm.policy_idx_hmask = nhashmask;
- write_unlock_bh(&xfrm_policy_lock);
+ write_unlock_bh(&net->xfrm.xfrm_policy_lock);
xfrm_hash_free(oidx, (hmask + 1) * sizeof(struct hlist_head));
}
void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si)
{
- read_lock_bh(&xfrm_policy_lock);
+ read_lock_bh(&net->xfrm.xfrm_policy_lock);
si->incnt = net->xfrm.policy_count[XFRM_POLICY_IN];
si->outcnt = net->xfrm.policy_count[XFRM_POLICY_OUT];
si->fwdcnt = net->xfrm.policy_count[XFRM_POLICY_FWD];
si->fwdscnt = net->xfrm.policy_count[XFRM_POLICY_FWD+XFRM_POLICY_MAX];
si->spdhcnt = net->xfrm.policy_idx_hmask;
si->spdhmcnt = xfrm_policy_hashmax;
- read_unlock_bh(&xfrm_policy_lock);
+ read_unlock_bh(&net->xfrm.xfrm_policy_lock);
}
EXPORT_SYMBOL(xfrm_spd_getinfo);
/* Generate new index... KAME seems to generate them ordered by cost
* of an absolute inpredictability of ordering of rules. This will not pass. */
- static u32 xfrm_gen_index(struct net *net, int dir)
+ static u32 xfrm_gen_index(struct net *net, int dir, u32 index)
{
static u32 idx_generator;
u32 idx;
int found;
- idx = (idx_generator | dir);
- idx_generator += 8;
+ if (!index) {
+ idx = (idx_generator | dir);
+ idx_generator += 8;
+ } else {
+ idx = index;
+ index = 0;
+ }
+
if (idx == 0)
idx = 8;
list = net->xfrm.policy_byidx + idx_hash(net, idx);
struct hlist_head *chain;
struct hlist_node *newpos;
- write_lock_bh(&xfrm_policy_lock);
+ write_lock_bh(&net->xfrm.xfrm_policy_lock);
chain = policy_hash_bysel(net, &policy->selector, policy->family, dir);
delpol = NULL;
newpos = NULL;
xfrm_sec_ctx_match(pol->security, policy->security) &&
!WARN_ON(delpol)) {
if (excl) {
- write_unlock_bh(&xfrm_policy_lock);
+ write_unlock_bh(&net->xfrm.xfrm_policy_lock);
return -EEXIST;
}
delpol = pol;
xfrm_policy_requeue(delpol, policy);
__xfrm_policy_unlink(delpol, dir);
}
- policy->index = delpol ? delpol->index : xfrm_gen_index(net, dir);
+ policy->index = delpol ? delpol->index : xfrm_gen_index(net, dir, policy->index);
hlist_add_head(&policy->byidx, net->xfrm.policy_byidx+idx_hash(net, policy->index));
policy->curlft.add_time = get_seconds();
policy->curlft.use_time = 0;
if (!mod_timer(&policy->timer, jiffies + HZ))
xfrm_pol_hold(policy);
list_add(&policy->walk.all, &net->xfrm.policy_all);
- write_unlock_bh(&xfrm_policy_lock);
+ write_unlock_bh(&net->xfrm.xfrm_policy_lock);
if (delpol)
xfrm_policy_kill(delpol);
struct hlist_head *chain;
*err = 0;
- write_lock_bh(&xfrm_policy_lock);
+ write_lock_bh(&net->xfrm.xfrm_policy_lock);
chain = policy_hash_bysel(net, sel, sel->family, dir);
ret = NULL;
hlist_for_each_entry(pol, chain, bydst) {
*err = security_xfrm_policy_delete(
pol->security);
if (*err) {
- write_unlock_bh(&xfrm_policy_lock);
+ write_unlock_bh(&net->xfrm.xfrm_policy_lock);
return pol;
}
__xfrm_policy_unlink(pol, dir);
break;
}
}
- write_unlock_bh(&xfrm_policy_lock);
+ write_unlock_bh(&net->xfrm.xfrm_policy_lock);
if (ret && delete)
xfrm_policy_kill(ret);
return NULL;
*err = 0;
- write_lock_bh(&xfrm_policy_lock);
+ write_lock_bh(&net->xfrm.xfrm_policy_lock);
chain = net->xfrm.policy_byidx + idx_hash(net, id);
ret = NULL;
hlist_for_each_entry(pol, chain, byidx) {
*err = security_xfrm_policy_delete(
pol->security);
if (*err) {
- write_unlock_bh(&xfrm_policy_lock);
+ write_unlock_bh(&net->xfrm.xfrm_policy_lock);
return pol;
}
__xfrm_policy_unlink(pol, dir);
break;
}
}
- write_unlock_bh(&xfrm_policy_lock);
+ write_unlock_bh(&net->xfrm.xfrm_policy_lock);
if (ret && delete)
xfrm_policy_kill(ret);
{
int dir, err = 0, cnt = 0;
- write_lock_bh(&xfrm_policy_lock);
+ write_lock_bh(&net->xfrm.xfrm_policy_lock);
err = xfrm_policy_flush_secctx_check(net, type, audit_info);
if (err)
if (pol->type != type)
continue;
__xfrm_policy_unlink(pol, dir);
- write_unlock_bh(&xfrm_policy_lock);
+ write_unlock_bh(&net->xfrm.xfrm_policy_lock);
cnt++;
xfrm_audit_policy_delete(pol, 1, audit_info->loginuid,
xfrm_policy_kill(pol);
- write_lock_bh(&xfrm_policy_lock);
+ write_lock_bh(&net->xfrm.xfrm_policy_lock);
goto again1;
}
if (pol->type != type)
continue;
__xfrm_policy_unlink(pol, dir);
- write_unlock_bh(&xfrm_policy_lock);
+ write_unlock_bh(&net->xfrm.xfrm_policy_lock);
cnt++;
xfrm_audit_policy_delete(pol, 1,
audit_info->secid);
xfrm_policy_kill(pol);
- write_lock_bh(&xfrm_policy_lock);
+ write_lock_bh(&net->xfrm.xfrm_policy_lock);
goto again2;
}
}
if (!cnt)
err = -ESRCH;
out:
- write_unlock_bh(&xfrm_policy_lock);
+ write_unlock_bh(&net->xfrm.xfrm_policy_lock);
return err;
}
EXPORT_SYMBOL(xfrm_policy_flush);
if (list_empty(&walk->walk.all) && walk->seq != 0)
return 0;
- write_lock_bh(&xfrm_policy_lock);
+ write_lock_bh(&net->xfrm.xfrm_policy_lock);
if (list_empty(&walk->walk.all))
x = list_first_entry(&net->xfrm.policy_all, struct xfrm_policy_walk_entry, all);
else
}
list_del_init(&walk->walk.all);
out:
- write_unlock_bh(&xfrm_policy_lock);
+ write_unlock_bh(&net->xfrm.xfrm_policy_lock);
return error;
}
EXPORT_SYMBOL(xfrm_policy_walk);
}
EXPORT_SYMBOL(xfrm_policy_walk_init);
- void xfrm_policy_walk_done(struct xfrm_policy_walk *walk)
+ void xfrm_policy_walk_done(struct xfrm_policy_walk *walk, struct net *net)
{
if (list_empty(&walk->walk.all))
return;
- write_lock_bh(&xfrm_policy_lock);
+ write_lock_bh(&net->xfrm.xfrm_policy_lock); /*FIXME where is net? */
list_del(&walk->walk.all);
- write_unlock_bh(&xfrm_policy_lock);
+ write_unlock_bh(&net->xfrm.xfrm_policy_lock);
}
EXPORT_SYMBOL(xfrm_policy_walk_done);
if (unlikely(!daddr || !saddr))
return NULL;
- read_lock_bh(&xfrm_policy_lock);
+ read_lock_bh(&net->xfrm.xfrm_policy_lock);
chain = policy_hash_direct(net, daddr, saddr, family, dir);
ret = NULL;
hlist_for_each_entry(pol, chain, bydst) {
if (ret)
xfrm_pol_hold(ret);
fail:
- read_unlock_bh(&xfrm_policy_lock);
+ read_unlock_bh(&net->xfrm.xfrm_policy_lock);
return ret;
}
const struct flowi *fl)
{
struct xfrm_policy *pol;
+ struct net *net = sock_net(sk);
- read_lock_bh(&xfrm_policy_lock);
+ read_lock_bh(&net->xfrm.xfrm_policy_lock);
if ((pol = sk->sk_policy[dir]) != NULL) {
bool match = xfrm_selector_match(&pol->selector, fl,
sk->sk_family);
pol = NULL;
}
out:
- read_unlock_bh(&xfrm_policy_lock);
+ read_unlock_bh(&net->xfrm.xfrm_policy_lock);
return pol;
}
int xfrm_policy_delete(struct xfrm_policy *pol, int dir)
{
- write_lock_bh(&xfrm_policy_lock);
+ struct net *net = xp_net(pol);
+
+ write_lock_bh(&net->xfrm.xfrm_policy_lock);
pol = __xfrm_policy_unlink(pol, dir);
- write_unlock_bh(&xfrm_policy_lock);
+ write_unlock_bh(&net->xfrm.xfrm_policy_lock);
if (pol) {
xfrm_policy_kill(pol);
return 0;
return -EINVAL;
#endif
- write_lock_bh(&xfrm_policy_lock);
+ write_lock_bh(&net->xfrm.xfrm_policy_lock);
old_pol = sk->sk_policy[dir];
sk->sk_policy[dir] = pol;
if (pol) {
pol->curlft.add_time = get_seconds();
- pol->index = xfrm_gen_index(net, XFRM_POLICY_MAX+dir);
+ pol->index = xfrm_gen_index(net, XFRM_POLICY_MAX+dir, 0);
__xfrm_policy_link(pol, XFRM_POLICY_MAX+dir);
}
if (old_pol) {
*/
__xfrm_policy_unlink(old_pol, XFRM_POLICY_MAX+dir);
}
- write_unlock_bh(&xfrm_policy_lock);
+ write_unlock_bh(&net->xfrm.xfrm_policy_lock);
if (old_pol) {
xfrm_policy_kill(old_pol);
static struct xfrm_policy *clone_policy(const struct xfrm_policy *old, int dir)
{
struct xfrm_policy *newp = xfrm_policy_alloc(xp_net(old), GFP_ATOMIC);
+ struct net *net = xp_net(old);
if (newp) {
newp->selector = old->selector;
newp->type = old->type;
memcpy(newp->xfrm_vec, old->xfrm_vec,
newp->xfrm_nr*sizeof(struct xfrm_tmpl));
- write_lock_bh(&xfrm_policy_lock);
+ write_lock_bh(&net->xfrm.xfrm_policy_lock);
__xfrm_policy_link(newp, XFRM_POLICY_MAX+dir);
- write_unlock_bh(&xfrm_policy_lock);
+ write_unlock_bh(&net->xfrm.xfrm_policy_lock);
xfrm_pol_put(newp);
}
return newp;
xfrm_address_t *saddr = xfrm_flowi_saddr(fl, family);
xfrm_address_t tmp;
- for (nx=0, i = 0; i < policy->xfrm_nr; i++) {
+ for (nx = 0, i = 0; i < policy->xfrm_nr; i++) {
struct xfrm_state *x;
xfrm_address_t *remote = daddr;
xfrm_address_t *local = saddr;
error = (x->km.state == XFRM_STATE_ERROR ?
-EINVAL : -EAGAIN);
xfrm_state_put(x);
- }
- else if (error == -ESRCH)
+ } else if (error == -ESRCH) {
error = -EAGAIN;
+ }
if (!tmpl->optional)
goto fail;
return nx;
fail:
- for (nx--; nx>=0; nx--)
+ for (nx--; nx >= 0; nx--)
xfrm_state_put(xfrm[nx]);
return error;
}
return cnx;
fail:
- for (cnx--; cnx>=0; cnx--)
+ for (cnx--; cnx >= 0; cnx--)
xfrm_state_put(tpp[cnx]);
return error;
goto out;
}
- static int inline
- xfrm_dst_alloc_copy(void **target, const void *src, int size)
+ #ifdef CONFIG_XFRM_SUB_POLICY
+ static int xfrm_dst_alloc_copy(void **target, const void *src, int size)
{
if (!*target) {
*target = kmalloc(size, GFP_ATOMIC);
if (!*target)
return -ENOMEM;
}
+
memcpy(*target, src, size);
return 0;
}
+ #endif
- static int inline
- xfrm_dst_update_parent(struct dst_entry *dst, const struct xfrm_selector *sel)
+ static int xfrm_dst_update_parent(struct dst_entry *dst,
+ const struct xfrm_selector *sel)
{
#ifdef CONFIG_XFRM_SUB_POLICY
struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
#endif
}
- static int inline
- xfrm_dst_update_origin(struct dst_entry *dst, const struct flowi *fl)
+ static int xfrm_dst_update_origin(struct dst_entry *dst,
+ const struct flowi *fl)
{
#ifdef CONFIG_XFRM_SUB_POLICY
struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
xfrm_pols_put(pols, *num_pols);
return PTR_ERR(pols[1]);
}
- (*num_pols) ++;
+ (*num_pols)++;
(*num_xfrms) += pols[1]->xfrm_nr;
}
}
}
xdst->num_pols = num_pols;
- memcpy(xdst->pols, pols, sizeof(struct xfrm_policy*) * num_pols);
+ memcpy(xdst->pols, pols, sizeof(struct xfrm_policy *) * num_pols);
xdst->policy_genid = atomic_read(&pols[0]->genid);
return xdst;
if (IS_ERR(xdst))
return xdst;
- if (net->xfrm.sysctl_larval_drop || num_xfrms <= 0 ||
- (fl->flowi_flags & FLOWI_FLAG_CAN_SLEEP))
+ if (net->xfrm.sysctl_larval_drop || num_xfrms <= 0)
return xdst;
dst1 = &xdst->u.dst;
}
xdst->num_pols = num_pols;
xdst->num_xfrms = num_xfrms;
- memcpy(xdst->pols, pols, sizeof(struct xfrm_policy*) * num_pols);
+ memcpy(xdst->pols, pols, sizeof(struct xfrm_policy *) * num_pols);
dst_hold(&xdst->u.dst);
return &xdst->flo;
u8 dir = policy_to_flow_dir(XFRM_POLICY_OUT);
int i, err, num_pols, num_xfrms = 0, drop_pols = 0;
- restart:
dst = NULL;
xdst = NULL;
route = NULL;
dst_hold(&xdst->u.dst);
- spin_lock_bh(&xfrm_policy_sk_bundle_lock);
+ spin_lock_bh(&net->xfrm.xfrm_policy_sk_bundle_lock);
xdst->u.dst.next = xfrm_policy_sk_bundles;
xfrm_policy_sk_bundles = &xdst->u.dst;
- spin_unlock_bh(&xfrm_policy_sk_bundle_lock);
+ spin_unlock_bh(&net->xfrm.xfrm_policy_sk_bundle_lock);
route = xdst->route;
}
num_pols = xdst->num_pols;
num_xfrms = xdst->num_xfrms;
- memcpy(pols, xdst->pols, sizeof(struct xfrm_policy*) * num_pols);
+ memcpy(pols, xdst->pols, sizeof(struct xfrm_policy *) * num_pols);
route = xdst->route;
}
return make_blackhole(net, family, dst_orig);
}
- if (fl->flowi_flags & FLOWI_FLAG_CAN_SLEEP) {
- DECLARE_WAITQUEUE(wait, current);
- add_wait_queue(&net->xfrm.km_waitq, &wait);
- set_current_state(TASK_INTERRUPTIBLE);
- schedule();
- set_current_state(TASK_RUNNING);
- remove_wait_queue(&net->xfrm.km_waitq, &wait);
-
- if (!signal_pending(current)) {
- dst_release(dst);
- goto restart;
- }
-
- err = -ERESTART;
- } else
- err = -EAGAIN;
+ err = -EAGAIN;
XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES);
goto error;
if (skb->sp) {
int i;
- for (i=skb->sp->len-1; i>=0; i--) {
+ for (i = skb->sp->len-1; i >= 0; i--) {
struct xfrm_state *x = skb->sp->xvec[i];
if (!xfrm_selector_match(&x->sel, &fl, family)) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMISMATCH);
pol->curlft.use_time = get_seconds();
pols[0] = pol;
- npols ++;
+ npols++;
#ifdef CONFIG_XFRM_SUB_POLICY
if (pols[0]->type != XFRM_POLICY_TYPE_MAIN) {
pols[1] = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN,
return 0;
}
pols[1]->curlft.use_time = get_seconds();
- npols ++;
+ npols++;
}
}
#endif
}
xfrm_nr = ti;
if (npols > 1) {
- xfrm_tmpl_sort(stp, tpp, xfrm_nr, family);
+ xfrm_tmpl_sort(stp, tpp, xfrm_nr, family, net);
tpp = stp;
}
{
struct dst_entry *head, *next;
- spin_lock_bh(&xfrm_policy_sk_bundle_lock);
+ spin_lock_bh(&net->xfrm.xfrm_policy_sk_bundle_lock);
head = xfrm_policy_sk_bundles;
xfrm_policy_sk_bundles = NULL;
- spin_unlock_bh(&xfrm_policy_sk_bundle_lock);
+ spin_unlock_bh(&net->xfrm.xfrm_policy_sk_bundle_lock);
while (head) {
next = head->next;
flush_work(&net->xfrm.policy_hash_work);
#ifdef CONFIG_XFRM_SUB_POLICY
audit_info.loginuid = INVALID_UID;
- audit_info.sessionid = -1;
+ audit_info.sessionid = (unsigned int)-1;
audit_info.secid = 0;
xfrm_policy_flush(net, XFRM_POLICY_TYPE_SUB, &audit_info);
#endif
audit_info.loginuid = INVALID_UID;
- audit_info.sessionid = -1;
+ audit_info.sessionid = (unsigned int)-1;
audit_info.secid = 0;
xfrm_policy_flush(net, XFRM_POLICY_TYPE_MAIN, &audit_info);
rv = xfrm_sysctl_init(net);
if (rv < 0)
goto out_sysctl;
+
+ /* Initialize the per-net locks here */
+ spin_lock_init(&net->xfrm.xfrm_state_lock);
+ rwlock_init(&net->xfrm.xfrm_policy_lock);
+ spin_lock_init(&net->xfrm.xfrm_policy_sk_bundle_lock);
+ mutex_init(&net->xfrm.xfrm_cfg_mutex);
+
return 0;
out_sysctl:
audit_log_format(audit_buf, " sec_alg=%u sec_doi=%u sec_obj=%s",
ctx->ctx_alg, ctx->ctx_doi, ctx->ctx_str);
- switch(sel->family) {
+ switch (sel->family) {
case AF_INET:
audit_log_format(audit_buf, " src=%pI4", &sel->saddr.a4);
if (sel->prefixlen_s != 32)
}
void xfrm_audit_policy_add(struct xfrm_policy *xp, int result,
- kuid_t auid, u32 sessionid, u32 secid)
+ kuid_t auid, unsigned int sessionid, u32 secid)
{
struct audit_buffer *audit_buf;
EXPORT_SYMBOL_GPL(xfrm_audit_policy_add);
void xfrm_audit_policy_delete(struct xfrm_policy *xp, int result,
- kuid_t auid, u32 sessionid, u32 secid)
+ kuid_t auid, unsigned int sessionid, u32 secid)
{
struct audit_buffer *audit_buf;
return false;
}
- static struct xfrm_policy * xfrm_migrate_policy_find(const struct xfrm_selector *sel,
- u8 dir, u8 type)
+ static struct xfrm_policy *xfrm_migrate_policy_find(const struct xfrm_selector *sel,
+ u8 dir, u8 type, struct net *net)
{
struct xfrm_policy *pol, *ret = NULL;
struct hlist_head *chain;
u32 priority = ~0U;
- read_lock_bh(&xfrm_policy_lock);
- chain = policy_hash_direct(&init_net, &sel->daddr, &sel->saddr, sel->family, dir);
+ read_lock_bh(&net->xfrm.xfrm_policy_lock); /*FIXME*/
+ chain = policy_hash_direct(net, &sel->daddr, &sel->saddr, sel->family, dir);
hlist_for_each_entry(pol, chain, bydst) {
if (xfrm_migrate_selector_match(sel, &pol->selector) &&
pol->type == type) {
break;
}
}
- chain = &init_net.xfrm.policy_inexact[dir];
+ chain = &net->xfrm.policy_inexact[dir];
hlist_for_each_entry(pol, chain, bydst) {
if (xfrm_migrate_selector_match(sel, &pol->selector) &&
pol->type == type &&
if (ret)
xfrm_pol_hold(ret);
- read_unlock_bh(&xfrm_policy_lock);
+ read_unlock_bh(&net->xfrm.xfrm_policy_lock);
return ret;
}
int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
struct xfrm_migrate *m, int num_migrate,
- struct xfrm_kmaddress *k)
+ struct xfrm_kmaddress *k, struct net *net)
{
int i, err, nx_cur = 0, nx_new = 0;
struct xfrm_policy *pol = NULL;
goto out;
/* Stage 1 - find policy */
- if ((pol = xfrm_migrate_policy_find(sel, dir, type)) == NULL) {
+ if ((pol = xfrm_migrate_policy_find(sel, dir, type, net)) == NULL) {
err = -ENOENT;
goto out;
}
/* Stage 2 - find and update state(s) */
for (i = 0, mp = m; i < num_migrate; i++, mp++) {
- if ((x = xfrm_migrate_state_find(mp))) {
+ if ((x = xfrm_migrate_state_find(mp, net))) {
x_cur[nx_cur] = x;
nx_cur++;
if ((xc = xfrm_state_migrate(x, mp))) {
destination/tunnel endpoint. (output)
*/
- static DEFINE_SPINLOCK(xfrm_state_lock);
-
static unsigned int xfrm_state_hashmax __read_mostly = 1 * 1024 * 1024;
static inline unsigned int xfrm_dst_hash(struct net *net,
goto out_unlock;
}
- spin_lock_bh(&xfrm_state_lock);
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
nhashmask = (nsize / sizeof(struct hlist_head)) - 1U;
for (i = net->xfrm.state_hmask; i >= 0; i--)
net->xfrm.state_byspi = nspi;
net->xfrm.state_hmask = nhashmask;
- spin_unlock_bh(&xfrm_state_lock);
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
osize = (ohashmask + 1) * sizeof(struct hlist_head);
xfrm_hash_free(odst, osize);
hlist_for_each_entry_safe(x, tmp, &gc_list, gclist)
xfrm_state_gc_destroy(x);
-
- wake_up(&net->xfrm.km_waitq);
}
static inline unsigned long make_jiffies(long secs)
return secs*HZ;
}
- static enum hrtimer_restart xfrm_timer_handler(struct hrtimer * me)
+ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me)
{
struct tasklet_hrtimer *thr = container_of(me, struct tasklet_hrtimer, timer);
struct xfrm_state *x = container_of(thr, struct xfrm_state, mtimer);
- struct net *net = xs_net(x);
unsigned long now = get_seconds();
long next = LONG_MAX;
int warn = 0;
if (warn)
km_state_expired(x, 0, 0);
resched:
- if (next != LONG_MAX){
+ if (next != LONG_MAX) {
tasklet_hrtimer_start(&x->mtimer, ktime_set(next, 0), HRTIMER_MODE_REL);
}
goto out;
expired:
- if (x->km.state == XFRM_STATE_ACQ && x->id.spi == 0) {
+ if (x->km.state == XFRM_STATE_ACQ && x->id.spi == 0)
x->km.state = XFRM_STATE_EXPIRED;
- wake_up(&net->xfrm.km_waitq);
- next = 2;
- goto resched;
- }
err = __xfrm_state_delete(x);
if (!err)
if (x->km.state != XFRM_STATE_DEAD) {
x->km.state = XFRM_STATE_DEAD;
- spin_lock(&xfrm_state_lock);
+ spin_lock(&net->xfrm.xfrm_state_lock);
list_del(&x->km.all);
hlist_del(&x->bydst);
hlist_del(&x->bysrc);
if (x->id.spi)
hlist_del(&x->byspi);
net->xfrm.state_num--;
- spin_unlock(&xfrm_state_lock);
+ spin_unlock(&net->xfrm.xfrm_state_lock);
/* All xfrm_state objects are created by xfrm_state_alloc.
* The xfrm_state_alloc call gives a reference, and that
{
int i, err = 0, cnt = 0;
- spin_lock_bh(&xfrm_state_lock);
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
err = xfrm_state_flush_secctx_check(net, proto, audit_info);
if (err)
goto out;
if (!xfrm_state_kern(x) &&
xfrm_id_proto_match(x->id.proto, proto)) {
xfrm_state_hold(x);
- spin_unlock_bh(&xfrm_state_lock);
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
err = xfrm_state_delete(x);
xfrm_audit_state_delete(x, err ? 0 : 1,
if (!err)
cnt++;
- spin_lock_bh(&xfrm_state_lock);
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
goto restart;
}
}
err = 0;
out:
- spin_unlock_bh(&xfrm_state_lock);
- wake_up(&net->xfrm.km_waitq);
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
return err;
}
EXPORT_SYMBOL(xfrm_state_flush);
void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si)
{
- spin_lock_bh(&xfrm_state_lock);
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
si->sadcnt = net->xfrm.state_num;
si->sadhcnt = net->xfrm.state_hmask;
si->sadhmcnt = xfrm_state_hashmax;
- spin_unlock_bh(&xfrm_state_lock);
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
}
EXPORT_SYMBOL(xfrm_sad_getinfo);
to_put = NULL;
- spin_lock_bh(&xfrm_state_lock);
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family);
hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) {
if (x->props.family == encap_family &&
xfrm_state_hold(x);
else
*err = acquire_in_progress ? -EAGAIN : error;
- spin_unlock_bh(&xfrm_state_lock);
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
if (to_put)
xfrm_state_put(to_put);
return x;
unsigned int h;
struct xfrm_state *rx = NULL, *x = NULL;
- spin_lock(&xfrm_state_lock);
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
h = xfrm_dst_hash(net, daddr, saddr, reqid, family);
hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) {
if (x->props.family == family &&
if (rx)
xfrm_state_hold(rx);
- spin_unlock(&xfrm_state_lock);
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
return rx;
}
EXPORT_SYMBOL(xfrm_stateonly_find);
+ struct xfrm_state *xfrm_state_lookup_byspi(struct net *net, __be32 spi,
+ unsigned short family)
+ {
+ struct xfrm_state *x;
+ struct xfrm_state_walk *w;
+
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
+ list_for_each_entry(w, &net->xfrm.state_all, all) {
+ x = container_of(w, struct xfrm_state, km);
+ if (x->props.family != family ||
+ x->id.spi != spi)
+ continue;
+
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+ xfrm_state_hold(x);
+ return x;
+ }
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+ return NULL;
+ }
+ EXPORT_SYMBOL(xfrm_state_lookup_byspi);
+
static void __xfrm_state_insert(struct xfrm_state *x)
{
struct net *net = xs_net(x);
if (x->replay_maxage)
mod_timer(&x->rtimer, jiffies + x->replay_maxage);
- wake_up(&net->xfrm.km_waitq);
-
net->xfrm.state_num++;
xfrm_hash_grow_check(net, x->bydst.next != NULL);
}
- /* xfrm_state_lock is held */
+ /* net->xfrm.xfrm_state_lock is held */
static void __xfrm_state_bump_genids(struct xfrm_state *xnew)
{
struct net *net = xs_net(xnew);
void xfrm_state_insert(struct xfrm_state *x)
{
- spin_lock_bh(&xfrm_state_lock);
+ struct net *net = xs_net(x);
+
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
__xfrm_state_bump_genids(x);
__xfrm_state_insert(x);
- spin_unlock_bh(&xfrm_state_lock);
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
}
EXPORT_SYMBOL(xfrm_state_insert);
- /* xfrm_state_lock is held */
+ /* net->xfrm.xfrm_state_lock is held */
static struct xfrm_state *__find_acq_core(struct net *net,
const struct xfrm_mark *m,
unsigned short family, u8 mode,
to_put = NULL;
- spin_lock_bh(&xfrm_state_lock);
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
x1 = __xfrm_state_locate(x, use_spi, family);
if (x1) {
err = 0;
out:
- spin_unlock_bh(&xfrm_state_lock);
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
if (x1) {
xfrm_state_delete(x1);
return NULL;
}
- /* xfrm_state_lock is held */
- struct xfrm_state * xfrm_migrate_state_find(struct xfrm_migrate *m)
+ /* net->xfrm.xfrm_state_lock is held */
+ struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net)
{
unsigned int h;
struct xfrm_state *x;
if (m->reqid) {
- h = xfrm_dst_hash(&init_net, &m->old_daddr, &m->old_saddr,
+ h = xfrm_dst_hash(net, &m->old_daddr, &m->old_saddr,
m->reqid, m->old_family);
- hlist_for_each_entry(x, init_net.xfrm.state_bydst+h, bydst) {
+ hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) {
if (x->props.mode != m->mode ||
x->id.proto != m->proto)
continue;
return x;
}
} else {
- h = xfrm_src_hash(&init_net, &m->old_daddr, &m->old_saddr,
+ h = xfrm_src_hash(net, &m->old_daddr, &m->old_saddr,
m->old_family);
- hlist_for_each_entry(x, init_net.xfrm.state_bysrc+h, bysrc) {
+ hlist_for_each_entry(x, net->xfrm.state_bysrc+h, bysrc) {
if (x->props.mode != m->mode ||
x->id.proto != m->proto)
continue;
}
EXPORT_SYMBOL(xfrm_migrate_state_find);
- struct xfrm_state * xfrm_state_migrate(struct xfrm_state *x,
- struct xfrm_migrate *m)
+ struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x,
+ struct xfrm_migrate *m)
{
struct xfrm_state *xc;
int err;
struct xfrm_state *x1, *to_put;
int err;
int use_spi = xfrm_id_proto_match(x->id.proto, IPSEC_PROTO_ANY);
+ struct net *net = xs_net(x);
to_put = NULL;
- spin_lock_bh(&xfrm_state_lock);
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
x1 = __xfrm_state_locate(x, use_spi, x->props.family);
err = -ESRCH;
err = 0;
out:
- spin_unlock_bh(&xfrm_state_lock);
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
if (to_put)
xfrm_state_put(to_put);
if (x->curlft.bytes >= x->lft.hard_byte_limit ||
x->curlft.packets >= x->lft.hard_packet_limit) {
x->km.state = XFRM_STATE_EXPIRED;
- tasklet_hrtimer_start(&x->mtimer, ktime_set(0,0), HRTIMER_MODE_REL);
+ tasklet_hrtimer_start(&x->mtimer, ktime_set(0, 0), HRTIMER_MODE_REL);
return -EINVAL;
}
{
struct xfrm_state *x;
- spin_lock_bh(&xfrm_state_lock);
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
x = __xfrm_state_lookup(net, mark, daddr, spi, proto, family);
- spin_unlock_bh(&xfrm_state_lock);
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
return x;
}
EXPORT_SYMBOL(xfrm_state_lookup);
{
struct xfrm_state *x;
- spin_lock_bh(&xfrm_state_lock);
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
x = __xfrm_state_lookup_byaddr(net, mark, daddr, saddr, proto, family);
- spin_unlock_bh(&xfrm_state_lock);
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
return x;
}
EXPORT_SYMBOL(xfrm_state_lookup_byaddr);
{
struct xfrm_state *x;
- spin_lock_bh(&xfrm_state_lock);
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
x = __find_acq_core(net, mark, family, mode, reqid, proto, daddr, saddr, create);
- spin_unlock_bh(&xfrm_state_lock);
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
return x;
}
#ifdef CONFIG_XFRM_SUB_POLICY
int
xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n,
- unsigned short family)
+ unsigned short family, struct net *net)
{
int err = 0;
struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family);
if (!afinfo)
return -EAFNOSUPPORT;
- spin_lock_bh(&xfrm_state_lock);
+ spin_lock_bh(&net->xfrm.xfrm_state_lock); /*FIXME*/
if (afinfo->tmpl_sort)
err = afinfo->tmpl_sort(dst, src, n);
- spin_unlock_bh(&xfrm_state_lock);
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
xfrm_state_put_afinfo(afinfo);
return err;
}
{
int err = 0;
struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family);
+ struct net *net = xs_net(*dst);
+
if (!afinfo)
return -EAFNOSUPPORT;
- spin_lock_bh(&xfrm_state_lock);
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
if (afinfo->state_sort)
err = afinfo->state_sort(dst, src, n);
- spin_unlock_bh(&xfrm_state_lock);
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
xfrm_state_put_afinfo(afinfo);
return err;
}
{
struct xfrm_state *x;
- spin_lock_bh(&xfrm_state_lock);
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
x = __xfrm_find_acq_byseq(net, mark, seq);
- spin_unlock_bh(&xfrm_state_lock);
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
return x;
}
EXPORT_SYMBOL(xfrm_find_acq_byseq);
}
EXPORT_SYMBOL(xfrm_get_acqseq);
+ int verify_spi_info(u8 proto, u32 min, u32 max)
+ {
+ switch (proto) {
+ case IPPROTO_AH:
+ case IPPROTO_ESP:
+ break;
+
+ case IPPROTO_COMP:
+ /* IPCOMP spi is 16-bits. */
+ if (max >= 0x10000)
+ return -EINVAL;
+ break;
+
+ default:
+ return -EINVAL;
+ }
+
+ if (min > max)
+ return -EINVAL;
+
+ return 0;
+ }
+ EXPORT_SYMBOL(verify_spi_info);
+
int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high)
{
struct net *net = xs_net(x);
x->id.spi = minspi;
} else {
u32 spi = 0;
- for (h=0; h<high-low+1; h++) {
- spi = low + net_random()%(high-low+1);
+ for (h = 0; h < high-low+1; h++) {
+ spi = low + prandom_u32()%(high-low+1);
x0 = xfrm_state_lookup(net, mark, &x->id.daddr, htonl(spi), x->id.proto, x->props.family);
if (x0 == NULL) {
x->id.spi = htonl(spi);
}
}
if (x->id.spi) {
- spin_lock_bh(&xfrm_state_lock);
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, x->props.family);
hlist_add_head(&x->byspi, net->xfrm.state_byspi+h);
- spin_unlock_bh(&xfrm_state_lock);
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
err = 0;
}
if (walk->seq != 0 && list_empty(&walk->all))
return 0;
- spin_lock_bh(&xfrm_state_lock);
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
if (list_empty(&walk->all))
x = list_first_entry(&net->xfrm.state_all, struct xfrm_state_walk, all);
else
}
list_del_init(&walk->all);
out:
- spin_unlock_bh(&xfrm_state_lock);
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
return err;
}
EXPORT_SYMBOL(xfrm_state_walk);
}
EXPORT_SYMBOL(xfrm_state_walk_init);
- void xfrm_state_walk_done(struct xfrm_state_walk *walk)
+ void xfrm_state_walk_done(struct xfrm_state_walk *walk, struct net *net)
{
if (list_empty(&walk->all))
return;
- spin_lock_bh(&xfrm_state_lock);
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
list_del(&walk->all);
- spin_unlock_bh(&xfrm_state_lock);
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
}
EXPORT_SYMBOL(xfrm_state_walk_done);
static void xfrm_replay_timer_handler(unsigned long data)
{
- struct xfrm_state *x = (struct xfrm_state*)data;
+ struct xfrm_state *x = (struct xfrm_state *)data;
spin_lock(&x->lock);
void km_state_expired(struct xfrm_state *x, int hard, u32 portid)
{
- struct net *net = xs_net(x);
struct km_event c;
c.data.hard = hard;
c.portid = portid;
c.event = XFRM_MSG_EXPIRE;
km_state_notify(x, &c);
-
- if (hard)
- wake_up(&net->xfrm.km_waitq);
}
EXPORT_SYMBOL(km_state_expired);
void km_policy_expired(struct xfrm_policy *pol, int dir, int hard, u32 portid)
{
- struct net *net = xp_net(pol);
struct km_event c;
c.data.hard = hard;
c.portid = portid;
c.event = XFRM_MSG_POLEXPIRE;
km_policy_notify(pol, dir, &c);
-
- if (hard)
- wake_up(&net->xfrm.km_waitq);
}
EXPORT_SYMBOL(km_policy_expired);
INIT_WORK(&net->xfrm.state_hash_work, xfrm_hash_resize);
INIT_HLIST_HEAD(&net->xfrm.state_gc_list);
INIT_WORK(&net->xfrm.state_gc_work, xfrm_state_gc_task);
- init_waitqueue_head(&net->xfrm.km_waitq);
+ spin_lock_init(&net->xfrm.xfrm_state_lock);
return 0;
out_byspi:
flush_work(&net->xfrm.state_hash_work);
audit_info.loginuid = INVALID_UID;
- audit_info.sessionid = -1;
+ audit_info.sessionid = (unsigned int)-1;
audit_info.secid = 0;
xfrm_state_flush(net, IPSEC_PROTO_ANY, &audit_info);
flush_work(&net->xfrm.state_gc_work);
audit_log_format(audit_buf, " sec_alg=%u sec_doi=%u sec_obj=%s",
ctx->ctx_alg, ctx->ctx_doi, ctx->ctx_str);
- switch(x->props.family) {
+ switch (x->props.family) {
case AF_INET:
audit_log_format(audit_buf, " src=%pI4 dst=%pI4",
&x->props.saddr.a4, &x->id.daddr.a4);
iph6 = ipv6_hdr(skb);
audit_log_format(audit_buf,
" src=%pI6 dst=%pI6 flowlbl=0x%x%02x%02x",
- &iph6->saddr,&iph6->daddr,
+ &iph6->saddr, &iph6->daddr,
iph6->flow_lbl[0] & 0x0f,
iph6->flow_lbl[1],
iph6->flow_lbl[2]);
}
void xfrm_audit_state_add(struct xfrm_state *x, int result,
- kuid_t auid, u32 sessionid, u32 secid)
+ kuid_t auid, unsigned int sessionid, u32 secid)
{
struct audit_buffer *audit_buf;
EXPORT_SYMBOL_GPL(xfrm_audit_state_add);
void xfrm_audit_state_delete(struct xfrm_state *x, int result,
- kuid_t auid, u32 sessionid, u32 secid)
+ kuid_t auid, unsigned int sessionid, u32 secid)
{
struct audit_buffer *audit_buf;
attrs[XFRMA_ALG_AEAD] ||
attrs[XFRMA_ALG_CRYPT] ||
attrs[XFRMA_ALG_COMP] ||
- attrs[XFRMA_TFCPAD])
+ attrs[XFRMA_TFCPAD] ||
+ (ntohl(p->id.spi) >= 0x10000))
+
goto out;
break;
int err;
struct km_event c;
kuid_t loginuid = audit_get_loginuid(current);
- u32 sessionid = audit_get_sessionid(current);
+ unsigned int sessionid = audit_get_sessionid(current);
u32 sid;
err = verify_newsa_info(p, attrs);
struct km_event c;
struct xfrm_usersa_id *p = nlmsg_data(nlh);
kuid_t loginuid = audit_get_loginuid(current);
- u32 sessionid = audit_get_sessionid(current);
+ unsigned int sessionid = audit_get_sessionid(current);
u32 sid;
x = xfrm_user_state_lookup(net, p, attrs, &err);
static int xfrm_dump_sa_done(struct netlink_callback *cb)
{
struct xfrm_state_walk *walk = (struct xfrm_state_walk *) &cb->args[1];
- xfrm_state_walk_done(walk);
+ struct sock *sk = cb->skb->sk;
+ struct net *net = sock_net(sk);
+
+ xfrm_state_walk_done(walk, net);
return 0;
}
return err;
}
- static int verify_userspi_info(struct xfrm_userspi_info *p)
- {
- switch (p->info.id.proto) {
- case IPPROTO_AH:
- case IPPROTO_ESP:
- break;
-
- case IPPROTO_COMP:
- /* IPCOMP spi is 16-bits. */
- if (p->max >= 0x10000)
- return -EINVAL;
- break;
-
- default:
- return -EINVAL;
- }
-
- if (p->min > p->max)
- return -EINVAL;
-
- return 0;
- }
-
static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh,
struct nlattr **attrs)
{
struct xfrm_mark m;
p = nlmsg_data(nlh);
- err = verify_userspi_info(p);
+ err = verify_spi_info(p->info.id.proto, p->min, p->max);
if (err)
goto out_noput;
static int verify_newpolicy_info(struct xfrm_userpolicy_info *p)
{
+ int ret;
+
switch (p->share) {
case XFRM_SHARE_ANY:
case XFRM_SHARE_SESSION:
return -EINVAL;
}
- return verify_policy_dir(p->dir);
+ ret = verify_policy_dir(p->dir);
+ if (ret)
+ return ret;
+ if (p->index && ((p->index & XFRM_POLICY_MAX) != p->dir))
+ return -EINVAL;
+
+ return 0;
}
static int copy_from_user_sec_ctx(struct xfrm_policy *pol, struct nlattr **attrs)
int err;
int excl;
kuid_t loginuid = audit_get_loginuid(current);
- u32 sessionid = audit_get_sessionid(current);
+ unsigned int sessionid = audit_get_sessionid(current);
u32 sid;
err = verify_newpolicy_info(p);
static int xfrm_dump_policy_done(struct netlink_callback *cb)
{
struct xfrm_policy_walk *walk = (struct xfrm_policy_walk *) &cb->args[1];
+ struct net *net = sock_net(cb->skb->sk);
- xfrm_policy_walk_done(walk);
+ xfrm_policy_walk_done(walk, net);
return 0;
}
}
} else {
kuid_t loginuid = audit_get_loginuid(current);
- u32 sessionid = audit_get_sessionid(current);
+ unsigned int sessionid = audit_get_sessionid(current);
u32 sid;
security_task_getsecid(current, &sid);
return -EMSGSIZE;
id = nlmsg_data(nlh);
- memcpy(&id->sa_id.daddr, &x->id.daddr,sizeof(x->id.daddr));
+ memcpy(&id->sa_id.daddr, &x->id.daddr, sizeof(x->id.daddr));
id->sa_id.spi = x->id.spi;
id->sa_id.family = x->props.family;
id->sa_id.proto = x->id.proto;
- memcpy(&id->saddr, &x->props.saddr,sizeof(x->props.saddr));
+ memcpy(&id->saddr, &x->props.saddr, sizeof(x->props.saddr));
id->reqid = x->props.reqid;
id->flags = c->data.aevent;
struct net *net = sock_net(skb->sk);
struct xfrm_state *x;
struct km_event c;
- int err = - EINVAL;
+ int err = -EINVAL;
u32 mark = 0;
struct xfrm_mark m;
struct xfrm_aevent_id *p = nlmsg_data(nlh);
err = 0;
if (up->hard) {
kuid_t loginuid = audit_get_loginuid(current);
- u32 sessionid = audit_get_sessionid(current);
+ unsigned int sessionid = audit_get_sessionid(current);
u32 sid;
security_task_getsecid(current, &sid);
if (ue->hard) {
kuid_t loginuid = audit_get_loginuid(current);
- u32 sessionid = audit_get_sessionid(current);
+ unsigned int sessionid = audit_get_sessionid(current);
u32 sid;
security_task_getsecid(current, &sid);
u8 type;
int err;
int n = 0;
+ struct net *net = sock_net(skb->sk);
if (attrs[XFRMA_MIGRATE] == NULL)
return -EINVAL;
if (!n)
return 0;
- xfrm_migrate(&pi->sel, pi->dir, type, m, n, kmp);
+ xfrm_migrate(&pi->sel, pi->dir, type, m, n, kmp, net);
return 0;
}
static void xfrm_netlink_rcv(struct sk_buff *skb)
{
- mutex_lock(&xfrm_cfg_mutex);
+ struct net *net = sock_net(skb->sk);
+
+ mutex_lock(&net->xfrm.xfrm_cfg_mutex);
netlink_rcv_skb(skb, &xfrm_user_rcv_msg);
- mutex_unlock(&xfrm_cfg_mutex);
+ mutex_unlock(&net->xfrm.xfrm_cfg_mutex);
}
static inline size_t xfrm_expire_msgsize(void)
projects / linux.git / commitdiff