- 'ata_qc_for_each_with_internal'
- 'ax25_for_each'
- 'ax25_uid_for_each'
+ - '__bio_for_each_bvec'
+ - 'bio_for_each_bvec'
- 'bio_for_each_integrity_vec'
- '__bio_for_each_segment'
- 'bio_for_each_segment'
- 'drm_for_each_legacy_plane'
- 'drm_for_each_plane'
- 'drm_for_each_plane_mask'
+ - 'drm_for_each_privobj'
- 'drm_mm_for_each_hole'
- 'drm_mm_for_each_node'
- 'drm_mm_for_each_node_in_range'
- 'drm_mm_for_each_node_safe'
+ - 'flow_action_for_each'
- 'for_each_active_drhd_unit'
- 'for_each_active_iommu'
- 'for_each_available_child_of_node'
- 'for_each_dss_dev'
- 'for_each_efi_memory_desc'
- 'for_each_efi_memory_desc_in_map'
+ - 'for_each_element'
+ - 'for_each_element_extid'
+ - 'for_each_element_id'
- 'for_each_endpoint_of_node'
- 'for_each_evictable_lru'
- 'for_each_fib6_node_rt_rcu'
- 'for_each_net_rcu'
- 'for_each_new_connector_in_state'
- 'for_each_new_crtc_in_state'
+ - 'for_each_new_mst_mgr_in_state'
- 'for_each_new_plane_in_state'
- 'for_each_new_private_obj_in_state'
- 'for_each_node'
- 'for_each_of_pci_range'
- 'for_each_old_connector_in_state'
- 'for_each_old_crtc_in_state'
+ - 'for_each_old_mst_mgr_in_state'
- 'for_each_oldnew_connector_in_state'
- 'for_each_oldnew_crtc_in_state'
+ - 'for_each_oldnew_mst_mgr_in_state'
- 'for_each_oldnew_plane_in_state'
- 'for_each_oldnew_plane_in_state_reverse'
- 'for_each_oldnew_private_obj_in_state'
- 'for_each_sg_dma_page'
- 'for_each_sg_page'
- 'for_each_sibling_event'
+ - 'for_each_subelement'
+ - 'for_each_subelement_extid'
+ - 'for_each_subelement_id'
- '__for_each_thread'
- 'for_each_thread'
- 'for_each_zone'
- 'fwnode_for_each_child_node'
- 'fwnode_graph_for_each_endpoint'
- 'gadget_for_each_ep'
+ - 'genradix_for_each'
+ - 'genradix_for_each_from'
- 'hash_for_each'
- 'hash_for_each_possible'
- 'hash_for_each_possible_rcu'
- 'key_for_each'
- 'key_for_each_safe'
- 'klp_for_each_func'
+ - 'klp_for_each_func_safe'
+ - 'klp_for_each_func_static'
- 'klp_for_each_object'
+ - 'klp_for_each_object_safe'
+ - 'klp_for_each_object_static'
- 'kvm_for_each_memslot'
- 'kvm_for_each_vcpu'
- 'list_for_each'
- 'media_device_for_each_intf'
- 'media_device_for_each_link'
- 'media_device_for_each_pad'
+ - 'mp_bvec_for_each_page'
+ - 'mp_bvec_for_each_segment'
- 'nanddev_io_for_each_page'
- 'netdev_for_each_lower_dev'
- 'netdev_for_each_lower_private'
- 'rht_for_each_rcu'
- 'rht_for_each_rcu_from'
- '__rq_for_each_bio'
+ - 'rq_for_each_bvec'
- 'rq_for_each_segment'
- 'scsi_for_each_prot_sg'
- 'scsi_for_each_sg'
- 'v4l2_m2m_for_each_src_buf_safe'
- 'virtio_device_for_each_vq'
- 'xa_for_each'
+ - 'xa_for_each_marked'
+ - 'xa_for_each_start'
- 'xas_for_each'
- 'xas_for_each_conflict'
- 'xas_for_each_marked'
Alan Cox <root@hraefn.swansea.linux.org.uk>
Aleksey Gorelov <aleksey_gorelov@phoenix.com>
Aleksandar Markovic <aleksandar.markovic@mips.com> <aleksandar.markovic@imgtec.com>
+Alexei Starovoitov <ast@kernel.org> <ast@plumgrid.com>
+Alexei Starovoitov <ast@kernel.org> <alexei.starovoitov@gmail.com>
+Alexei Starovoitov <ast@kernel.org> <ast@fb.com>
Al Viro <viro@ftp.linux.org.uk>
Al Viro <viro@zenIV.linux.org.uk>
Andi Shyti <andi@etezian.org> <andi.shyti@samsung.com>
Christophe Ricard <christophe.ricard@gmail.com>
Corey Minyard <minyard@acm.org>
Damian Hobson-Garcia <dhobsong@igel.co.jp>
+Daniel Borkmann <daniel@iogearbox.net> <dborkman@redhat.com>
+Daniel Borkmann <daniel@iogearbox.net> <dborkmann@redhat.com>
+Daniel Borkmann <daniel@iogearbox.net> <danborkmann@iogearbox.net>
+Daniel Borkmann <daniel@iogearbox.net> <daniel.borkmann@tik.ee.ethz.ch>
+Daniel Borkmann <daniel@iogearbox.net> <danborkmann@googlemail.com>
+Daniel Borkmann <daniel@iogearbox.net> <dxchgb@gmail.com>
David Brownell <david-b@pacbell.net>
David Woodhouse <dwmw2@shinybook.infradead.org>
Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@mips.com>
Morten Welinder <welinder@troll.com>
Mythri P K <mythripk@ti.com>
Nguyen Anh Quynh <aquynh@gmail.com>
+Nicolas Pitre <nico@fluxnic.net> <nicolas.pitre@linaro.org>
+Nicolas Pitre <nico@fluxnic.net> <nico@linaro.org>
Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it>
Patrick Mochel <mochel@digitalimplant.org>
Paul Burton <paul.burton@mips.com> <paul.burton@imgtec.com>
Yusuke Goda <goda.yusuke@renesas.com>
Gustavo Padovan <gustavo@las.ic.unicamp.br>
Gustavo Padovan <padovan@profusion.mobi>
+Changbin Du <changbin.du@intel.com> <changbin.du@intel.com>
+Changbin Du <changbin.du@intel.com> <changbin.du@gmail.com>
still doing productive work. As such, time spent in this subset of the
stall state is tracked separately and exported in the "full" averages.
-The ratios are tracked as recent trends over ten, sixty, and three
-hundred second windows, which gives insight into short term events as
-well as medium and long term trends. The total absolute stall time is
-tracked and exported as well, to allow detection of latency spikes
-which wouldn't necessarily make a dent in the time averages, or to
-average trends over custom time frames.
+The ratios (in %) are tracked as recent trends over ten, sixty, and
+three hundred second windows, which gives insight into short term events
+as well as medium and long term trends. The total absolute stall time
+(in us) is tracked and exported as well, to allow detection of latency
+spikes which wouldn't necessarily make a dent in the time averages,
+or to average trends over custom time frames.
Cgroup2 interface
=================
#define BTF_KIND_RESTRICT 11 /* Restrict */
#define BTF_KIND_FUNC 12 /* Function */
#define BTF_KIND_FUNC_PROTO 13 /* Function Proto */
+ #define BTF_KIND_VAR 14 /* Variable */
+ #define BTF_KIND_DATASEC 15 /* Section */
Note that the type section encodes debug info, not just pure types.
``BTF_KIND_FUNC`` is not a type, and it represents a defined subprogram.
for the type. The maximum value of ``BTF_INT_BITS()`` is 128.
The ``BTF_INT_OFFSET()`` specifies the starting bit offset to calculate values
-for this int. For example, a bitfield struct member has: * btf member bit
-offset 100 from the start of the structure, * btf member pointing to an int
-type, * the int type has ``BTF_INT_OFFSET() = 2`` and ``BTF_INT_BITS() = 4``
+for this int. For example, a bitfield struct member has:
+ * btf member bit offset 100 from the start of the structure,
+ * btf member pointing to an int type,
+ * the int type has ``BTF_INT_OFFSET() = 2`` and ``BTF_INT_BITS() = 4``
Then in the struct memory layout, this member will occupy ``4`` bits starting
from bits ``100 + 2 = 102``.
Alternatively, the bitfield struct member can be the following to access the
same bits as the above:
-
* btf member bit offset 102,
* btf member pointing to an int type,
* the int type has ``BTF_INT_OFFSET() = 0`` and ``BTF_INT_BITS() = 4``
If the function has variable arguments, the last parameter is encoded with
``name_off = 0`` and ``type = 0``.
+2.2.14 BTF_KIND_VAR
+~~~~~~~~~~~~~~~~~~~
+
+``struct btf_type`` encoding requirement:
+ * ``name_off``: offset to a valid C identifier
+ * ``info.kind_flag``: 0
+ * ``info.kind``: BTF_KIND_VAR
+ * ``info.vlen``: 0
+ * ``type``: the type of the variable
+
+``btf_type`` is followed by a single ``struct btf_variable`` with the
+following data::
+
+ struct btf_var {
+ __u32 linkage;
+ };
+
+``struct btf_var`` encoding:
+ * ``linkage``: currently only static variable 0, or globally allocated
+ variable in ELF sections 1
+
+Not all type of global variables are supported by LLVM at this point.
+The following is currently available:
+
+ * static variables with or without section attributes
+ * global variables with section attributes
+
+The latter is for future extraction of map key/value type id's from a
+map definition.
+
+2.2.15 BTF_KIND_DATASEC
+~~~~~~~~~~~~~~~~~~~~~~~
+
+``struct btf_type`` encoding requirement:
+ * ``name_off``: offset to a valid name associated with a variable or
+ one of .data/.bss/.rodata
+ * ``info.kind_flag``: 0
+ * ``info.kind``: BTF_KIND_DATASEC
+ * ``info.vlen``: # of variables
+ * ``size``: total section size in bytes (0 at compilation time, patched
+ to actual size by BPF loaders such as libbpf)
+
+``btf_type`` is followed by ``info.vlen`` number of ``struct btf_var_secinfo``.::
+
+ struct btf_var_secinfo {
+ __u32 type;
+ __u32 offset;
+ __u32 size;
+ };
+
+``struct btf_var_secinfo`` encoding:
+ * ``type``: the type of the BTF_KIND_VAR variable
+ * ``offset``: the in-section offset of the variable
+ * ``size``: the size of the variable in bytes
+
3. BTF Kernel API
*****************
- renesas,r9a06g032-smp
- rockchip,rk3036-smp
- rockchip,rk3066-smp
- - socionext,milbeaut-m10v-smp
+ - socionext,milbeaut-m10v-smp
- ste,dbx500-smp
cpu-release-addr:
Optional node properties:
- - ti,mode: Operation mode (see above).
+ - ti,mode: Operation mode (u8) (see above).
Example (operation mode 2):
adc128d818@1d {
compatible = "ti,adc128d818";
reg = <0x1d>;
- ti,mode = <2>;
+ ti,mode = /bits/ 8 <2>;
};
--- /dev/null
+Properties for the MDIO bus multiplexer/glue of Amlogic G12a SoC family.
+
+This is a special case of a MDIO bus multiplexer. It allows to choose between
+the internal mdio bus leading to the embedded 10/100 PHY or the external
+MDIO bus.
+
+Required properties in addition to the generic multiplexer properties:
+- compatible : amlogic,g12a-mdio-mux
+- reg: physical address and length of the multiplexer/glue registers
+- clocks: list of clock phandle, one for each entry clock-names.
+- clock-names: should contain the following:
+ * "pclk" : peripheral clock.
+ * "clkin0" : platform crytal
+ * "clkin1" : SoC 50MHz MPLL
+
+Example :
+
+mdio_mux: mdio-multiplexer@4c000 {
+ compatible = "amlogic,g12a-mdio-mux";
+ reg = <0x0 0x4c000 0x0 0xa4>;
+ clocks = <&clkc CLKID_ETH_PHY>,
+ <&xtal>,
+ <&clkc CLKID_MPLL_5OM>;
+ clock-names = "pclk", "clkin0", "clkin1";
+ mdio-parent-bus = <&mdio0>;
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ ext_mdio: mdio@0 {
+ reg = <0>;
+ #address-cells = <1>;
+ #size-cells = <0>;
+ };
+
+ int_mdio: mdio@1 {
+ reg = <1>;
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ internal_ephy: ethernet-phy@8 {
+ compatible = "ethernet-phy-id0180.3301",
+ "ethernet-phy-ieee802.3-c22";
+ interrupts = <GIC_SPI 9 IRQ_TYPE_LEVEL_HIGH>;
+ reg = <8>;
+ max-speed = <100>;
+ };
+ };
+};
* "mediatek,mt8127-uart" for MT8127 compatible UARTS
* "mediatek,mt8135-uart" for MT8135 compatible UARTS
* "mediatek,mt8173-uart" for MT8173 compatible UARTS
+ * "mediatek,mt8183-uart", "mediatek,mt6577-uart" for MT8183 compatible UARTS
* "mediatek,mt6577-uart" for MT6577 and all of the above
- reg: The base address of the UART register bank.
(4) Filesystem context security.
- (5) VFS filesystem context operations.
+ (5) VFS filesystem context API.
- (6) Parameter description.
+ (6) Superblock creation helpers.
- (7) Parameter helper functions.
+ (7) Parameter description.
+
+ (8) Parameter helper functions.
========
(7) Destroy the context.
-To support this, the file_system_type struct gains a new field:
+To support this, the file_system_type struct gains two new fields:
int (*init_fs_context)(struct fs_context *fc);
+ const struct fs_parameter_description *parameters;
-which is invoked to set up the filesystem-specific parts of a filesystem
-context, including the additional space.
+The first is invoked to set up the filesystem-specific parts of a filesystem
+context, including the additional space, and the second points to the
+parameter description for validation at registration time and querying by a
+future system call.
Note that security initialisation is done *after* the filesystem is called so
that the namespaces may be adjusted first.
void *s_fs_info;
unsigned int sb_flags;
unsigned int sb_flags_mask;
+ unsigned int s_iflags;
+ unsigned int lsm_flags;
enum fs_context_purpose purpose:8;
- bool sloppy:1;
- bool silent:1;
...
};
Which bits SB_* flags are to be set/cleared in super_block::s_flags.
+ (*) unsigned int s_iflags
+
+ These will be bitwise-OR'd with s->s_iflags when a superblock is created.
+
(*) enum fs_context_purpose
This indicates the purpose for which the context is intended. The
FS_CONTEXT_FOR_SUBMOUNT -- New automatic submount of extant mount
FS_CONTEXT_FOR_RECONFIGURE -- Change an existing mount
- (*) bool sloppy
- (*) bool silent
-
- These are set if the sloppy or silent mount options are given.
-
- [NOTE] sloppy is probably unnecessary when userspace passes over one
- option at a time since the error can just be ignored if userspace deems it
- to be unimportant.
-
- [NOTE] silent is probably redundant with sb_flags & SB_SILENT.
-
The mount context is created by calling vfs_new_fs_context() or
vfs_dup_fs_context() and is destroyed with put_fs_context(). Note that the
structure is not refcounted.
It should return 0 on success or a negative error code on failure.
-=================================
-VFS FILESYSTEM CONTEXT OPERATIONS
-=================================
+==========================
+VFS FILESYSTEM CONTEXT API
+==========================
-There are four operations for creating a filesystem context and
-one for destroying a context:
+There are four operations for creating a filesystem context and one for
+destroying a context:
- (*) struct fs_context *vfs_new_fs_context(struct file_system_type *fs_type,
- struct dentry *reference,
- unsigned int sb_flags,
- unsigned int sb_flags_mask,
- enum fs_context_purpose purpose);
+ (*) struct fs_context *fs_context_for_mount(
+ struct file_system_type *fs_type,
+ unsigned int sb_flags);
- Create a filesystem context for a given filesystem type and purpose. This
- allocates the filesystem context, sets the superblock flags, initialises
- the security and calls fs_type->init_fs_context() to initialise the
- filesystem private data.
+ Allocate a filesystem context for the purpose of setting up a new mount,
+ whether that be with a new superblock or sharing an existing one. This
+ sets the superblock flags, initialises the security and calls
+ fs_type->init_fs_context() to initialise the filesystem private data.
- reference can be NULL or it may indicate the root dentry of a superblock
- that is going to be reconfigured (FS_CONTEXT_FOR_RECONFIGURE) or
- the automount point that triggered a submount (FS_CONTEXT_FOR_SUBMOUNT).
- This is provided as a source of namespace information.
+ fs_type specifies the filesystem type that will manage the context and
+ sb_flags presets the superblock flags stored therein.
+
+ (*) struct fs_context *fs_context_for_reconfigure(
+ struct dentry *dentry,
+ unsigned int sb_flags,
+ unsigned int sb_flags_mask);
+
+ Allocate a filesystem context for the purpose of reconfiguring an
+ existing superblock. dentry provides a reference to the superblock to be
+ configured. sb_flags and sb_flags_mask indicate which superblock flags
+ need changing and to what.
+
+ (*) struct fs_context *fs_context_for_submount(
+ struct file_system_type *fs_type,
+ struct dentry *reference);
+
+ Allocate a filesystem context for the purpose of creating a new mount for
+ an automount point or other derived superblock. fs_type specifies the
+ filesystem type that will manage the context and the reference dentry
+ supplies the parameters. Namespaces are propagated from the reference
+ dentry's superblock also.
+
+ Note that it's not a requirement that the reference dentry be of the same
+ filesystem type as fs_type.
(*) struct fs_context *vfs_dup_fs_context(struct fs_context *src_fc);
For the remaining operations, if an error occurs, a negative error code will be
returned.
- (*) int vfs_get_tree(struct fs_context *fc);
-
- Get or create the mountable root and superblock, using the parameters in
- the filesystem context to select/configure the superblock. This invokes
- the ->validate() op and then the ->get_tree() op.
-
- [NOTE] ->validate() could perhaps be rolled into ->get_tree() and
- ->reconfigure().
-
- (*) struct vfsmount *vfs_create_mount(struct fs_context *fc);
-
- Create a mount given the parameters in the specified filesystem context.
- Note that this does not attach the mount to anything.
-
(*) int vfs_parse_fs_param(struct fs_context *fc,
struct fs_parameter *param);
clear the pointer, but then becomes responsible for disposing of the
object.
- (*) int vfs_parse_fs_string(struct fs_context *fc, char *key,
+ (*) int vfs_parse_fs_string(struct fs_context *fc, const char *key,
const char *value, size_t v_size);
- A wrapper around vfs_parse_fs_param() that just passes a constant string.
+ A wrapper around vfs_parse_fs_param() that copies the value string it is
+ passed.
(*) int generic_parse_monolithic(struct fs_context *fc, void *data);
Parse a sys_mount() data page, assuming the form to be a text list
consisting of key[=val] options separated by commas. Each item in the
list is passed to vfs_mount_option(). This is the default when the
- ->parse_monolithic() operation is NULL.
+ ->parse_monolithic() method is NULL.
+
+ (*) int vfs_get_tree(struct fs_context *fc);
+
+ Get or create the mountable root and superblock, using the parameters in
+ the filesystem context to select/configure the superblock. This invokes
+ the ->get_tree() method.
+
+ (*) struct vfsmount *vfs_create_mount(struct fs_context *fc);
+
+ Create a mount given the parameters in the specified filesystem context.
+ Note that this does not attach the mount to anything.
+
+
+===========================
+SUPERBLOCK CREATION HELPERS
+===========================
+
+A number of VFS helpers are available for use by filesystems for the creation
+or looking up of superblocks.
+
+ (*) struct super_block *
+ sget_fc(struct fs_context *fc,
+ int (*test)(struct super_block *sb, struct fs_context *fc),
+ int (*set)(struct super_block *sb, struct fs_context *fc));
+
+ This is the core routine. If test is non-NULL, it searches for an
+ existing superblock matching the criteria held in the fs_context, using
+ the test function to match them. If no match is found, a new superblock
+ is created and the set function is called to set it up.
+
+ Prior to the set function being called, fc->s_fs_info will be transferred
+ to sb->s_fs_info - and fc->s_fs_info will be cleared if set returns
+ success (ie. 0).
+
+The following helpers all wrap sget_fc():
+
+ (*) int vfs_get_super(struct fs_context *fc,
+ enum vfs_get_super_keying keying,
+ int (*fill_super)(struct super_block *sb,
+ struct fs_context *fc))
+
+ This creates/looks up a deviceless superblock. The keying indicates how
+ many superblocks of this type may exist and in what manner they may be
+ shared:
+
+ (1) vfs_get_single_super
+
+ Only one such superblock may exist in the system. Any further
+ attempt to get a new superblock gets this one (and any parameter
+ differences are ignored).
+
+ (2) vfs_get_keyed_super
+
+ Multiple superblocks of this type may exist and they're keyed on
+ their s_fs_info pointer (for example this may refer to a
+ namespace).
+
+ (3) vfs_get_independent_super
+
+ Multiple independent superblocks of this type may exist. This
+ function never matches an existing one and always creates a new
+ one.
=====================
struct fs_parameter_description {
const char name[16];
- u8 nr_params;
- u8 nr_alt_keys;
- u8 nr_enums;
- bool ignore_unknown;
- bool no_source;
- const char *const *keys;
- const struct constant_table *alt_keys;
const struct fs_parameter_spec *specs;
const struct fs_parameter_enum *enums;
};
For example:
- enum afs_param {
+ enum {
Opt_autocell,
Opt_bar,
Opt_dyn,
Opt_foo,
Opt_source,
- nr__afs_params
};
static const struct fs_parameter_description afs_fs_parameters = {
.name = "kAFS",
- .nr_params = nr__afs_params,
- .nr_alt_keys = ARRAY_SIZE(afs_param_alt_keys),
- .nr_enums = ARRAY_SIZE(afs_param_enums),
- .keys = afs_param_keys,
- .alt_keys = afs_param_alt_keys,
.specs = afs_param_specs,
.enums = afs_param_enums,
};
The name to be used in error messages generated by the parse helper
functions.
- (2) u8 nr_params;
-
- The number of discrete parameter identifiers. This indicates the number
- of elements in the ->types[] array and also limits the values that may be
- used in the values that the ->keys[] array maps to.
-
- It is expected that, for example, two parameters that are related, say
- "acl" and "noacl" with have the same ID, but will be flagged to indicate
- that one is the inverse of the other. The value can then be picked out
- from the parse result.
+ (2) const struct fs_parameter_specification *specs;
- (3) const struct fs_parameter_specification *specs;
+ Table of parameter specifications, terminated with a null entry, where the
+ entries are of type:
- Table of parameter specifications, where the entries are of type:
-
- struct fs_parameter_type {
- enum fs_parameter_spec type:8;
- u8 flags;
+ struct fs_parameter_spec {
+ const char *name;
+ u8 opt;
+ enum fs_parameter_type type:8;
+ unsigned short flags;
};
- and the parameter identifier is the index to the array. 'type' indicates
- the desired value type and must be one of:
+ The 'name' field is a string to match exactly to the parameter key (no
+ wildcards, patterns and no case-independence) and 'opt' is the value that
+ will be returned by the fs_parser() function in the case of a successful
+ match.
+
+ The 'type' field indicates the desired value type and must be one of:
TYPE NAME EXPECTED VALUE RESULT IN
======================= ======================= =====================
fs_param_is_u32_octal 32-bit octal int result->uint_32
fs_param_is_u32_hex 32-bit hex int result->uint_32
fs_param_is_s32 32-bit signed int result->int_32
+ fs_param_is_u64 64-bit unsigned int result->uint_64
fs_param_is_enum Enum value name result->uint_32
fs_param_is_string Arbitrary string param->string
fs_param_is_blob Binary blob param->blob
fs_param_is_blockdev Blockdev path * Needs lookup
fs_param_is_path Path * Needs lookup
- fs_param_is_fd File descriptor param->file
-
- And each parameter can be qualified with 'flags':
-
- fs_param_v_optional The value is optional
- fs_param_neg_with_no If key name is prefixed with "no", it is false
- fs_param_neg_with_empty If value is "", it is false
- fs_param_deprecated The parameter is deprecated.
-
- For example:
-
- static const struct fs_parameter_spec afs_param_specs[nr__afs_params] = {
- [Opt_autocell] = { fs_param_is flag },
- [Opt_bar] = { fs_param_is_enum },
- [Opt_dyn] = { fs_param_is flag },
- [Opt_foo] = { fs_param_is_bool, fs_param_neg_with_no },
- [Opt_source] = { fs_param_is_string },
- };
+ fs_param_is_fd File descriptor result->int_32
Note that if the value is of fs_param_is_bool type, fs_parse() will try
to match any string value against "0", "1", "no", "yes", "false", "true".
- [!] NOTE that the table must be sorted according to primary key name so
- that ->keys[] is also sorted.
-
- (4) const char *const *keys;
-
- Table of primary key names for the parameters. There must be one entry
- per defined parameter. The table is optional if ->nr_params is 0. The
- table is just an array of names e.g.:
+ Each parameter can also be qualified with 'flags':
- static const char *const afs_param_keys[nr__afs_params] = {
- [Opt_autocell] = "autocell",
- [Opt_bar] = "bar",
- [Opt_dyn] = "dyn",
- [Opt_foo] = "foo",
- [Opt_source] = "source",
- };
-
- [!] NOTE that the table must be sorted such that the table can be searched
- with bsearch() using strcmp(). This means that the Opt_* values must
- correspond to the entries in this table.
-
- (5) const struct constant_table *alt_keys;
- u8 nr_alt_keys;
-
- Table of additional key names and their mappings to parameter ID plus the
- number of elements in the table. This is optional. The table is just an
- array of { name, integer } pairs, e.g.:
+ fs_param_v_optional The value is optional
+ fs_param_neg_with_no result->negated set if key is prefixed with "no"
+ fs_param_neg_with_empty result->negated set if value is ""
+ fs_param_deprecated The parameter is deprecated.
- static const struct constant_table afs_param_keys[] = {
- { "baz", Opt_bar },
- { "dynamic", Opt_dyn },
+ These are wrapped with a number of convenience wrappers:
+
+ MACRO SPECIFIES
+ ======================= ===============================================
+ fsparam_flag() fs_param_is_flag
+ fsparam_flag_no() fs_param_is_flag, fs_param_neg_with_no
+ fsparam_bool() fs_param_is_bool
+ fsparam_u32() fs_param_is_u32
+ fsparam_u32oct() fs_param_is_u32_octal
+ fsparam_u32hex() fs_param_is_u32_hex
+ fsparam_s32() fs_param_is_s32
+ fsparam_u64() fs_param_is_u64
+ fsparam_enum() fs_param_is_enum
+ fsparam_string() fs_param_is_string
+ fsparam_blob() fs_param_is_blob
+ fsparam_bdev() fs_param_is_blockdev
+ fsparam_path() fs_param_is_path
+ fsparam_fd() fs_param_is_fd
+
+ all of which take two arguments, name string and option number - for
+ example:
+
+ static const struct fs_parameter_spec afs_param_specs[] = {
+ fsparam_flag ("autocell", Opt_autocell),
+ fsparam_flag ("dyn", Opt_dyn),
+ fsparam_string ("source", Opt_source),
+ fsparam_flag_no ("foo", Opt_foo),
+ {}
};
- [!] NOTE that the table must be sorted such that strcmp() can be used with
- bsearch() to search the entries.
-
- The parameter ID can also be fs_param_key_removed to indicate that a
- deprecated parameter has been removed and that an error will be given.
- This differs from fs_param_deprecated where the parameter may still have
- an effect.
-
- Further, the behaviour of the parameter may differ when an alternate name
- is used (for instance with NFS, "v3", "v4.2", etc. are alternate names).
+ An addition macro, __fsparam() is provided that takes an additional pair
+ of arguments to specify the type and the flags for anything that doesn't
+ match one of the above macros.
(6) const struct fs_parameter_enum *enums;
- u8 nr_enums;
- Table of enum value names to integer mappings and the number of elements
- stored therein. This is of type:
+ Table of enum value names to integer mappings, terminated with a null
+ entry. This is of type:
struct fs_parameter_enum {
- u8 param_id;
+ u8 opt;
char name[14];
u8 value;
};
try to look the value up in the enum table and the result will be stored
in the parse result.
- (7) bool no_source;
-
- If this is set, fs_parse() will ignore any "source" parameter and not
- pass it to the filesystem.
-
The parser should be pointed to by the parser pointer in the file_system_type
struct as this will provide validation on registration (if
CONFIG_VALIDATE_FS_PARSER=y) and will allow the description to be queried from
int value;
};
- and it must be sorted such that it can be searched using bsearch() using
- strcmp(). If a match is found, the corresponding value is returned. If a
- match isn't found, the not_found value is returned instead.
+ If a match is found, the corresponding value is returned. If a match
+ isn't found, the not_found value is returned instead.
(*) bool validate_constant_table(const struct constant_table *tbl,
size_t tbl_size,
should just be set to lie inside the low-to-high range.
If all is good, true is returned. If the table is invalid, errors are
- logged to dmesg, the stack is dumped and false is returned.
+ logged to dmesg and false is returned.
+
+ (*) bool fs_validate_description(const struct fs_parameter_description *desc);
+
+ This performs some validation checks on a parameter description. It
+ returns true if the description is good and false if it is not. It will
+ log errors to dmesg if validation fails.
(*) int fs_parse(struct fs_context *fc,
- const struct fs_param_parser *parser,
+ const struct fs_parameter_description *desc,
struct fs_parameter *param,
- struct fs_param_parse_result *result);
+ struct fs_parse_result *result);
This is the main interpreter of parameters. It uses the parameter
- description (parser) to look up the name of the parameter to use and to
- convert that to a parameter ID (stored in result->key).
+ description to look up a parameter by key name and to convert that to an
+ option number (which it returns).
If successful, and if the parameter type indicates the result is a
boolean, integer or enum type, the value is converted by this function and
- the result stored in result->{boolean,int_32,uint_32}.
+ the result stored in result->{boolean,int_32,uint_32,uint_64}.
If a match isn't initially made, the key is prefixed with "no" and no
value is present then an attempt will be made to look up the key with the
prefix removed. If this matches a parameter for which the type has flag
- fs_param_neg_with_no set, then a match will be made and the value will be
- set to false/0/NULL.
-
- If the parameter is successfully matched and, optionally, parsed
- correctly, 1 is returned. If the parameter isn't matched and
- parser->ignore_unknown is set, then 0 is returned. Otherwise -EINVAL is
- returned.
-
- (*) bool fs_validate_description(const struct fs_parameter_description *desc);
+ fs_param_neg_with_no set, then a match will be made and result->negated
+ will be set to true.
- This is validates the parameter description. It returns true if the
- description is good and false if it is not.
+ If the parameter isn't matched, -ENOPARAM will be returned; if the
+ parameter is matched, but the value is erroneous, -EINVAL will be
+ returned; otherwise the parameter's option number will be returned.
(*) int fs_lookup_param(struct fs_context *fc,
struct fs_parameter *value,
* Intel Cannon Lake (PCH)
* Intel Cedar Fork (PCH)
* Intel Ice Lake (PCH)
+ * Intel Comet Lake (PCH)
Datasheets: Publicly available at the Intel website
On Intel Patsburg and later chipsets, both the normal host SMBus controller
dictionary which is empty, and that it will always be
invalid at this place.
- 17 : bitstream version. If the first byte is 17, the next byte
- gives the bitstream version (version 1 only). If the first byte
- is not 17, the bitstream version is 0.
+ 17 : bitstream version. If the first byte is 17, and compressed
+ stream length is at least 5 bytes (length of shortest possible
+ versioned bitstream), the next byte gives the bitstream version
+ (version 1 only).
+ Otherwise, the bitstream version is 0.
18..21 : copy 0..3 literals
state = (byte - 17) = 0..3 [ copy <state> literals ]
--- /dev/null
+.. SPDX-License-Identifier: GPL-2.0
+
+==================
+BPF Flow Dissector
+==================
+
+Overview
+========
+
+Flow dissector is a routine that parses metadata out of the packets. It's
+used in the various places in the networking subsystem (RFS, flow hash, etc).
+
+BPF flow dissector is an attempt to reimplement C-based flow dissector logic
+in BPF to gain all the benefits of BPF verifier (namely, limits on the
+number of instructions and tail calls).
+
+API
+===
+
+BPF flow dissector programs operate on an ``__sk_buff``. However, only the
+limited set of fields is allowed: ``data``, ``data_end`` and ``flow_keys``.
+``flow_keys`` is ``struct bpf_flow_keys`` and contains flow dissector input
+and output arguments.
+
+The inputs are:
+ * ``nhoff`` - initial offset of the networking header
+ * ``thoff`` - initial offset of the transport header, initialized to nhoff
+ * ``n_proto`` - L3 protocol type, parsed out of L2 header
+
+Flow dissector BPF program should fill out the rest of the ``struct
+bpf_flow_keys`` fields. Input arguments ``nhoff/thoff/n_proto`` should be
+also adjusted accordingly.
+
+The return code of the BPF program is either BPF_OK to indicate successful
+dissection, or BPF_DROP to indicate parsing error.
+
+__sk_buff->data
+===============
+
+In the VLAN-less case, this is what the initial state of the BPF flow
+dissector looks like::
+
+ +------+------+------------+-----------+
+ | DMAC | SMAC | ETHER_TYPE | L3_HEADER |
+ +------+------+------------+-----------+
+ ^
+ |
+ +-- flow dissector starts here
+
+
+.. code:: c
+
+ skb->data + flow_keys->nhoff point to the first byte of L3_HEADER
+ flow_keys->thoff = nhoff
+ flow_keys->n_proto = ETHER_TYPE
+
+In case of VLAN, flow dissector can be called with the two different states.
+
+Pre-VLAN parsing::
+
+ +------+------+------+-----+-----------+-----------+
+ | DMAC | SMAC | TPID | TCI |ETHER_TYPE | L3_HEADER |
+ +------+------+------+-----+-----------+-----------+
+ ^
+ |
+ +-- flow dissector starts here
+
+.. code:: c
+
+ skb->data + flow_keys->nhoff point the to first byte of TCI
+ flow_keys->thoff = nhoff
+ flow_keys->n_proto = TPID
+
+Please note that TPID can be 802.1AD and, hence, BPF program would
+have to parse VLAN information twice for double tagged packets.
+
+
+Post-VLAN parsing::
+
+ +------+------+------+-----+-----------+-----------+
+ | DMAC | SMAC | TPID | TCI |ETHER_TYPE | L3_HEADER |
+ +------+------+------+-----+-----------+-----------+
+ ^
+ |
+ +-- flow dissector starts here
+
+.. code:: c
+
+ skb->data + flow_keys->nhoff point the to first byte of L3_HEADER
+ flow_keys->thoff = nhoff
+ flow_keys->n_proto = ETHER_TYPE
+
+In this case VLAN information has been processed before the flow dissector
+and BPF flow dissector is not required to handle it.
+
+
+The takeaway here is as follows: BPF flow dissector program can be called with
+the optional VLAN header and should gracefully handle both cases: when single
+or double VLAN is present and when it is not present. The same program
+can be called for both cases and would have to be written carefully to
+handle both cases.
+
+
+Reference Implementation
+========================
+
+See ``tools/testing/selftests/bpf/progs/bpf_flow.c`` for the reference
+implementation and ``tools/testing/selftests/bpf/flow_dissector_load.[hc]``
+for the loader. bpftool can be used to load BPF flow dissector program as well.
+
+The reference implementation is organized as follows:
+ * ``jmp_table`` map that contains sub-programs for each supported L3 protocol
+ * ``_dissect`` routine - entry point; it does input ``n_proto`` parsing and
+ does ``bpf_tail_call`` to the appropriate L3 handler
+
+Since BPF at this point doesn't support looping (or any jumping back),
+jmp_table is used instead to handle multiple levels of encapsulation (and
+IPv6 options).
+
+
+Current Limitations
+===================
+BPF flow dissector doesn't support exporting all the metadata that in-kernel
+C-based implementation can export. Notable example is single VLAN (802.1Q)
+and double VLAN (802.1AD) tags. Please refer to the ``struct bpf_flow_keys``
+for a set of information that's currently can be exported from the BPF context.
Version of the software responsible for supporting/handling the
Network Controller Sideband Interface.
+
+fw.psid
+=======
+
+Unique identifier of the firmware parameter set.
+=============================================
Broadcom Starfighter 2 Ethernet switch driver
=============================================
The switch hardware block is typically interfaced using MMIO accesses and
contains a bunch of sub-blocks/registers:
-* SWITCH_CORE: common switch registers
-* SWITCH_REG: external interfaces switch register
-* SWITCH_MDIO: external MDIO bus controller (there is another one in SWITCH_CORE,
+- ``SWITCH_CORE``: common switch registers
+- ``SWITCH_REG``: external interfaces switch register
+- ``SWITCH_MDIO``: external MDIO bus controller (there is another one in SWITCH_CORE,
which is used for indirect PHY accesses)
-* SWITCH_INDIR_RW: 64-bits wide register helper block
-* SWITCH_INTRL2_0/1: Level-2 interrupt controllers
-* SWITCH_ACB: Admission control block
-* SWITCH_FCB: Fail-over control block
+- ``SWITCH_INDIR_RW``: 64-bits wide register helper block
+- ``SWITCH_INTRL2_0/1``: Level-2 interrupt controllers
+- ``SWITCH_ACB``: Admission control block
+- ``SWITCH_FCB``: Fail-over control block
Implementation details
======================
-The driver is located in drivers/net/dsa/bcm_sf2.c and is implemented as a DSA
-driver; see Documentation/networking/dsa/dsa.txt for details on the subsystem
+The driver is located in ``drivers/net/dsa/bcm_sf2.c`` and is implemented as a DSA
+driver; see ``Documentation/networking/dsa/dsa.rst`` for details on the subsystem
and what it provides.
The SF2 switch is configured to enable a Broadcom specific 4-bytes switch tag
which gets inserted by the switch for every packet forwarded to the CPU
interface, conversely, the CPU network interface should insert a similar tag for
packets entering the CPU port. The tag format is described in
-net/dsa/tag_brcm.c.
+``net/dsa/tag_brcm.c``.
Overall, the SF2 driver is a fairly regular DSA driver; there are a few
specifics covered below.
-------------------
The DSA platform device driver is probed using a specific compatible string
-provided in net/dsa/dsa.c. The reason for that is because the DSA subsystem gets
+provided in ``net/dsa/dsa.c``. The reason for that is because the DSA subsystem gets
registered as a platform device driver currently. DSA will provide the needed
device_node pointers which are then accessible by the switch driver setup
function to setup resources such as register ranges and interrupts. This
in order to properly configure them. By default, the SF2 pseudo-PHY address, and
an external switch pseudo-PHY address will both be snooping for incoming MDIO
transactions, since they are at the same address (30), resulting in some kind of
-"double" programming. Using DSA, and setting ds->phys_mii_mask accordingly, we
+"double" programming. Using DSA, and setting ``ds->phys_mii_mask`` accordingly, we
selectively divert reads and writes towards external Broadcom switches
pseudo-PHY addresses. Newer revisions of the SF2 hardware have introduced a
configurable pseudo-PHY address which circumvents the initial design limitation.
MoCA interface carrier state and properly report this to the networking stack.
The MoCA interfaces are supported using the PHY library's fixed PHY/emulated PHY
-device and the switch driver registers a fixed_link_update callback for such
+device and the switch driver registers a ``fixed_link_update`` callback for such
PHYs which reflects the link state obtained from the interrupt handler.
-Distributed Switch Architecture
-===============================
-
-Introduction
+============
+Architecture
============
-This document describes the Distributed Switch Architecture (DSA) subsystem
+This document describes the **Distributed Switch Architecture (DSA)** subsystem
design principles, limitations, interactions with other subsystems, and how to
develop drivers for this subsystem as well as a TODO for developers interested
in joining the effort.
DSA currently supports 5 different tagging protocols, and a tag-less mode as
well. The different protocols are implemented in:
-net/dsa/tag_trailer.c: Marvell's 4 trailer tag mode (legacy)
-net/dsa/tag_dsa.c: Marvell's original DSA tag
-net/dsa/tag_edsa.c: Marvell's enhanced DSA tag
-net/dsa/tag_brcm.c: Broadcom's 4 bytes tag
-net/dsa/tag_qca.c: Qualcomm's 2 bytes tag
+- ``net/dsa/tag_trailer.c``: Marvell's 4 trailer tag mode (legacy)
+- ``net/dsa/tag_dsa.c``: Marvell's original DSA tag
+- ``net/dsa/tag_edsa.c``: Marvell's enhanced DSA tag
+- ``net/dsa/tag_brcm.c``: Broadcom's 4 bytes tag
+- ``net/dsa/tag_qca.c``: Qualcomm's 2 bytes tag
The exact format of the tag protocol is vendor specific, but in general, they
all contain something which:
the CPU/management Ethernet interface. Such a driver might occasionally need to
know whether DSA is enabled (e.g.: to enable/disable specific offload features),
but the DSA subsystem has been proven to work with industry standard drivers:
-e1000e, mv643xx_eth etc. without having to introduce modifications to these
+``e1000e,`` ``mv643xx_eth`` etc. without having to introduce modifications to these
drivers. Such network devices are also often referred to as conduit network
devices since they act as a pipe between the host processor and the hardware
Ethernet switch.
When a master netdev is used with DSA, a small hook is placed in in the
networking stack is in order to have the DSA subsystem process the Ethernet
switch specific tagging protocol. DSA accomplishes this by registering a
-specific (and fake) Ethernet type (later becoming skb->protocol) with the
-networking stack, this is also known as a ptype or packet_type. A typical
+specific (and fake) Ethernet type (later becoming ``skb->protocol``) with the
+networking stack, this is also known as a ``ptype`` or ``packet_type``. A typical
Ethernet Frame receive sequence looks like this:
Master network device (e.g.: e1000e):
-Receive interrupt fires:
-- receive function is invoked
-- basic packet processing is done: getting length, status etc.
-- packet is prepared to be processed by the Ethernet layer by calling
- eth_type_trans
+1. Receive interrupt fires:
+
+ - receive function is invoked
+ - basic packet processing is done: getting length, status etc.
+ - packet is prepared to be processed by the Ethernet layer by calling
+ ``eth_type_trans``
+
+2. net/ethernet/eth.c::
+
+ eth_type_trans(skb, dev)
+ if (dev->dsa_ptr != NULL)
+ -> skb->protocol = ETH_P_XDSA
-net/ethernet/eth.c:
+3. drivers/net/ethernet/\*::
-eth_type_trans(skb, dev)
- if (dev->dsa_ptr != NULL)
- -> skb->protocol = ETH_P_XDSA
+ netif_receive_skb(skb)
+ -> iterate over registered packet_type
+ -> invoke handler for ETH_P_XDSA, calls dsa_switch_rcv()
-drivers/net/ethernet/*:
+4. net/dsa/dsa.c::
-netif_receive_skb(skb)
- -> iterate over registered packet_type
- -> invoke handler for ETH_P_XDSA, calls dsa_switch_rcv()
+ -> dsa_switch_rcv()
+ -> invoke switch tag specific protocol handler in 'net/dsa/tag_*.c'
-net/dsa/dsa.c:
- -> dsa_switch_rcv()
- -> invoke switch tag specific protocol handler in
- net/dsa/tag_*.c
+5. net/dsa/tag_*.c:
-net/dsa/tag_*.c:
- -> inspect and strip switch tag protocol to determine originating port
- -> locate per-port network device
- -> invoke eth_type_trans() with the DSA slave network device
- -> invoked netif_receive_skb()
+ - inspect and strip switch tag protocol to determine originating port
+ - locate per-port network device
+ - invoke ``eth_type_trans()`` with the DSA slave network device
+ - invoked ``netif_receive_skb()``
Past this point, the DSA slave network devices get delivered regular Ethernet
frames that can be processed by the networking stack.
switch tag in the Ethernet frames.
These frames are then queued for transmission using the master network device
-ndo_start_xmit() function, since they contain the appropriate switch tag, the
+``ndo_start_xmit()`` function, since they contain the appropriate switch tag, the
Ethernet switch will be able to process these incoming frames from the
management interface and delivers these frames to the physical switch port.
------------------------
Summarized, this is basically how DSA looks like from a network device
-perspective:
-
-
- |---------------------------
- | CPU network device (eth0)|
- ----------------------------
- | <tag added by switch |
- | |
- | |
- | tag added by CPU> |
- |--------------------------------------------|
- | Switch driver |
- |--------------------------------------------|
- || || ||
- |-------| |-------| |-------|
- | sw0p0 | | sw0p1 | | sw0p2 |
- |-------| |-------| |-------|
+perspective::
+
+
+ |---------------------------
+ | CPU network device (eth0)|
+ ----------------------------
+ | <tag added by switch |
+ | |
+ | |
+ | tag added by CPU> |
+ |--------------------------------------------|
+ | Switch driver |
+ |--------------------------------------------|
+ || || ||
+ |-------| |-------| |-------|
+ | sw0p0 | | sw0p1 | | sw0p2 |
+ |-------| |-------| |-------|
+
+
Slave MDIO bus
--------------
Data structures
---------------
-DSA data structures are defined in include/net/dsa.h as well as
-net/dsa/dsa_priv.h.
+DSA data structures are defined in ``include/net/dsa.h`` as well as
+``net/dsa/dsa_priv.h``:
-dsa_chip_data: platform data configuration for a given switch device, this
-structure describes a switch device's parent device, its address, as well as
-various properties of its ports: names/labels, and finally a routing table
-indication (when cascading switches)
+- ``dsa_chip_data``: platform data configuration for a given switch device,
+ this structure describes a switch device's parent device, its address, as
+ well as various properties of its ports: names/labels, and finally a routing
+ table indication (when cascading switches)
-dsa_platform_data: platform device configuration data which can reference a
-collection of dsa_chip_data structure if multiples switches are cascaded, the
-master network device this switch tree is attached to needs to be referenced
+- ``dsa_platform_data``: platform device configuration data which can reference
+ a collection of dsa_chip_data structure if multiples switches are cascaded,
+ the master network device this switch tree is attached to needs to be
+ referenced
-dsa_switch_tree: structure assigned to the master network device under
-"dsa_ptr", this structure references a dsa_platform_data structure as well as
-the tagging protocol supported by the switch tree, and which receive/transmit
-function hooks should be invoked, information about the directly attached switch
-is also provided: CPU port. Finally, a collection of dsa_switch are referenced
-to address individual switches in the tree.
+- ``dsa_switch_tree``: structure assigned to the master network device under
+ ``dsa_ptr``, this structure references a dsa_platform_data structure as well as
+ the tagging protocol supported by the switch tree, and which receive/transmit
+ function hooks should be invoked, information about the directly attached
+ switch is also provided: CPU port. Finally, a collection of dsa_switch are
+ referenced to address individual switches in the tree.
-dsa_switch: structure describing a switch device in the tree, referencing a
-dsa_switch_tree as a backpointer, slave network devices, master network device,
-and a reference to the backing dsa_switch_ops
+- ``dsa_switch``: structure describing a switch device in the tree, referencing
+ a ``dsa_switch_tree`` as a backpointer, slave network devices, master network
+ device, and a reference to the backing``dsa_switch_ops``
-dsa_switch_ops: structure referencing function pointers, see below for a full
-description.
+- ``dsa_switch_ops``: structure referencing function pointers, see below for a
+ full description.
Design limitations
==================
-----------------------------------------
DSA currently limits the number of maximum switches within a tree to 4
-(DSA_MAX_SWITCHES), and the number of ports per switch to 12 (DSA_MAX_PORTS).
+(``DSA_MAX_SWITCHES``), and the number of ports per switch to 12 (``DSA_MAX_PORTS``).
These limits could be extended to support larger configurations would this need
arise.
DSA currently leverages the following subsystems:
-- MDIO/PHY library: drivers/net/phy/phy.c, mdio_bus.c
-- Switchdev: net/switchdev/*
+- MDIO/PHY library: ``drivers/net/phy/phy.c``, ``mdio_bus.c``
+- Switchdev:``net/switchdev/*``
- Device Tree for various of_* functions
MDIO/PHY library
----------------
Slave network devices exposed by DSA may or may not be interfacing with PHY
-devices (struct phy_device as defined in include/linux/phy.h), but the DSA
+devices (``struct phy_device`` as defined in ``include/linux/phy.h)``, but the DSA
subsystem deals with all possible combinations:
- internal PHY devices, built into the Ethernet switch hardware
- special, non-autonegotiated or non MDIO-managed PHY devices: SFPs, MoCA; a.k.a
fixed PHYs
-The PHY configuration is done by the dsa_slave_phy_setup() function and the
+The PHY configuration is done by the ``dsa_slave_phy_setup()`` function and the
logic basically looks like this:
- if Device Tree is used, the PHY device is looked up using the standard
"phy-handle" property, if found, this PHY device is created and registered
- using of_phy_connect()
+ using ``of_phy_connect()``
- if Device Tree is used, and the PHY device is "fixed", that is, conforms to
the definition of a non-MDIO managed PHY as defined in
- Documentation/devicetree/bindings/net/fixed-link.txt, the PHY is registered
+ ``Documentation/devicetree/bindings/net/fixed-link.txt``, the PHY is registered
and connected transparently using the special fixed MDIO bus driver
- finally, if the PHY is built into the switch, as is very common with
-----------
DSA features a standardized binding which is documented in
-Documentation/devicetree/bindings/net/dsa/dsa.txt. PHY/MDIO library helper
-functions such as of_get_phy_mode(), of_phy_connect() are also used to query
+``Documentation/devicetree/bindings/net/dsa/dsa.txt``. PHY/MDIO library helper
+functions such as ``of_get_phy_mode()``, ``of_phy_connect()`` are also used to query
per-port PHY specific details: interface connection, MDIO bus location etc..
Driver development
DSA switch drivers need to implement a dsa_switch_ops structure which will
contain the various members described below.
-register_switch_driver() registers this dsa_switch_ops in its internal list
-of drivers to probe for. unregister_switch_driver() does the exact opposite.
+``register_switch_driver()`` registers this dsa_switch_ops in its internal list
+of drivers to probe for. ``unregister_switch_driver()`` does the exact opposite.
Unless requested differently by setting the priv_size member accordingly, DSA
does not allocate any driver private context space.
Switch configuration
--------------------
-- tag_protocol: this is to indicate what kind of tagging protocol is supported,
- should be a valid value from the dsa_tag_protocol enum
+- ``tag_protocol``: this is to indicate what kind of tagging protocol is supported,
+ should be a valid value from the ``dsa_tag_protocol`` enum
-- probe: probe routine which will be invoked by the DSA platform device upon
+- ``probe``: probe routine which will be invoked by the DSA platform device upon
registration to test for the presence/absence of a switch device. For MDIO
devices, it is recommended to issue a read towards internal registers using
the switch pseudo-PHY and return whether this is a supported device. For other
buses, return a non-NULL string
-- setup: setup function for the switch, this function is responsible for setting
- up the dsa_switch_ops private structure with all it needs: register maps,
+- ``setup``: setup function for the switch, this function is responsible for setting
+ up the ``dsa_switch_ops`` private structure with all it needs: register maps,
interrupts, mutexes, locks etc.. This function is also expected to properly
configure the switch to separate all network interfaces from each other, that
is, they should be isolated by the switch hardware itself, typically by creating
PHY devices and link management
-------------------------------
-- get_phy_flags: Some switches are interfaced to various kinds of Ethernet PHYs,
+- ``get_phy_flags``: Some switches are interfaced to various kinds of Ethernet PHYs,
if the PHY library PHY driver needs to know about information it cannot obtain
on its own (e.g.: coming from switch memory mapped registers), this function
should return a 32-bits bitmask of "flags", that is private between the switch
- driver and the Ethernet PHY driver in drivers/net/phy/*.
+ driver and the Ethernet PHY driver in ``drivers/net/phy/\*``.
-- phy_read: Function invoked by the DSA slave MDIO bus when attempting to read
+- ``phy_read``: Function invoked by the DSA slave MDIO bus when attempting to read
the switch port MDIO registers. If unavailable, return 0xffff for each read.
For builtin switch Ethernet PHYs, this function should allow reading the link
status, auto-negotiation results, link partner pages etc..
-- phy_write: Function invoked by the DSA slave MDIO bus when attempting to write
+- ``phy_write``: Function invoked by the DSA slave MDIO bus when attempting to write
to the switch port MDIO registers. If unavailable return a negative error
code.
-- adjust_link: Function invoked by the PHY library when a slave network device
+- ``adjust_link``: Function invoked by the PHY library when a slave network device
is attached to a PHY device. This function is responsible for appropriately
configuring the switch port link parameters: speed, duplex, pause based on
- what the phy_device is providing.
+ what the ``phy_device`` is providing.
-- fixed_link_update: Function invoked by the PHY library, and specifically by
+- ``fixed_link_update``: Function invoked by the PHY library, and specifically by
the fixed PHY driver asking the switch driver for link parameters that could
not be auto-negotiated, or obtained by reading the PHY registers through MDIO.
This is particularly useful for specific kinds of hardware such as QSGMII,
Ethtool operations
------------------
-- get_strings: ethtool function used to query the driver's strings, will
+- ``get_strings``: ethtool function used to query the driver's strings, will
typically return statistics strings, private flags strings etc.
-- get_ethtool_stats: ethtool function used to query per-port statistics and
+- ``get_ethtool_stats``: ethtool function used to query per-port statistics and
return their values. DSA overlays slave network devices general statistics:
RX/TX counters from the network device, with switch driver specific statistics
per port
-- get_sset_count: ethtool function used to query the number of statistics items
+- ``get_sset_count``: ethtool function used to query the number of statistics items
-- get_wol: ethtool function used to obtain Wake-on-LAN settings per-port, this
+- ``get_wol``: ethtool function used to obtain Wake-on-LAN settings per-port, this
function may, for certain implementations also query the master network device
Wake-on-LAN settings if this interface needs to participate in Wake-on-LAN
-- set_wol: ethtool function used to configure Wake-on-LAN settings per-port,
+- ``set_wol``: ethtool function used to configure Wake-on-LAN settings per-port,
direct counterpart to set_wol with similar restrictions
-- set_eee: ethtool function which is used to configure a switch port EEE (Green
+- ``set_eee``: ethtool function which is used to configure a switch port EEE (Green
Ethernet) settings, can optionally invoke the PHY library to enable EEE at the
PHY level if relevant. This function should enable EEE at the switch port MAC
controller and data-processing logic
-- get_eee: ethtool function which is used to query a switch port EEE settings,
+- ``get_eee``: ethtool function which is used to query a switch port EEE settings,
this function should return the EEE state of the switch port MAC controller
and data-processing logic as well as query the PHY for its currently configured
EEE settings
-- get_eeprom_len: ethtool function returning for a given switch the EEPROM
+- ``get_eeprom_len``: ethtool function returning for a given switch the EEPROM
length/size in bytes
-- get_eeprom: ethtool function returning for a given switch the EEPROM contents
+- ``get_eeprom``: ethtool function returning for a given switch the EEPROM contents
-- set_eeprom: ethtool function writing specified data to a given switch EEPROM
+- ``set_eeprom``: ethtool function writing specified data to a given switch EEPROM
-- get_regs_len: ethtool function returning the register length for a given
+- ``get_regs_len``: ethtool function returning the register length for a given
switch
-- get_regs: ethtool function returning the Ethernet switch internal register
+- ``get_regs``: ethtool function returning the Ethernet switch internal register
contents. This function might require user-land code in ethtool to
pretty-print register values and registers
Power management
----------------
-- suspend: function invoked by the DSA platform device when the system goes to
+- ``suspend``: function invoked by the DSA platform device when the system goes to
suspend, should quiesce all Ethernet switch activities, but keep ports
participating in Wake-on-LAN active as well as additional wake-up logic if
supported
-- resume: function invoked by the DSA platform device when the system resumes,
+- ``resume``: function invoked by the DSA platform device when the system resumes,
should resume all Ethernet switch activities and re-configure the switch to be
in a fully active state
-- port_enable: function invoked by the DSA slave network device ndo_open
+- ``port_enable``: function invoked by the DSA slave network device ndo_open
function when a port is administratively brought up, this function should be
fully enabling a given switch port. DSA takes care of marking the port with
- BR_STATE_BLOCKING if the port is a bridge member, or BR_STATE_FORWARDING if it
+ ``BR_STATE_BLOCKING`` if the port is a bridge member, or ``BR_STATE_FORWARDING`` if it
was not, and propagating these changes down to the hardware
-- port_disable: function invoked by the DSA slave network device ndo_close
+- ``port_disable``: function invoked by the DSA slave network device ndo_close
function when a port is administratively brought down, this function should be
fully disabling a given switch port. DSA takes care of marking the port with
- BR_STATE_DISABLED and propagating changes to the hardware if this port is
+ ``BR_STATE_DISABLED`` and propagating changes to the hardware if this port is
disabled while being a bridge member
Bridge layer
------------
-- port_bridge_join: bridge layer function invoked when a given switch port is
+- ``port_bridge_join``: bridge layer function invoked when a given switch port is
added to a bridge, this function should be doing the necessary at the switch
level to permit the joining port from being added to the relevant logical
domain for it to ingress/egress traffic with other members of the bridge.
-- port_bridge_leave: bridge layer function invoked when a given switch port is
+- ``port_bridge_leave``: bridge layer function invoked when a given switch port is
removed from a bridge, this function should be doing the necessary at the
switch level to deny the leaving port from ingress/egress traffic from the
remaining bridge members. When the port leaves the bridge, it should be aged
out at the switch hardware for the switch to (re) learn MAC addresses behind
this port.
-- port_stp_state_set: bridge layer function invoked when a given switch port STP
+- ``port_stp_state_set``: bridge layer function invoked when a given switch port STP
state is computed by the bridge layer and should be propagated to switch
hardware to forward/block/learn traffic. The switch driver is responsible for
computing a STP state change based on current and asked parameters and perform
Bridge VLAN filtering
---------------------
-- port_vlan_filtering: bridge layer function invoked when the bridge gets
+- ``port_vlan_filtering``: bridge layer function invoked when the bridge gets
configured for turning on or off VLAN filtering. If nothing specific needs to
be done at the hardware level, this callback does not need to be implemented.
When VLAN filtering is turned on, the hardware must be programmed with
accept any 802.1Q frames irrespective of their VLAN ID, and untagged frames are
allowed.
-- port_vlan_prepare: bridge layer function invoked when the bridge prepares the
+- ``port_vlan_prepare``: bridge layer function invoked when the bridge prepares the
configuration of a VLAN on the given port. If the operation is not supported
- by the hardware, this function should return -EOPNOTSUPP to inform the bridge
+ by the hardware, this function should return ``-EOPNOTSUPP`` to inform the bridge
code to fallback to a software implementation. No hardware setup must be done
in this function. See port_vlan_add for this and details.
-- port_vlan_add: bridge layer function invoked when a VLAN is configured
+- ``port_vlan_add``: bridge layer function invoked when a VLAN is configured
(tagged or untagged) for the given switch port
-- port_vlan_del: bridge layer function invoked when a VLAN is removed from the
+- ``port_vlan_del``: bridge layer function invoked when a VLAN is removed from the
given switch port
-- port_vlan_dump: bridge layer function invoked with a switchdev callback
+- ``port_vlan_dump``: bridge layer function invoked with a switchdev callback
function that the driver has to call for each VLAN the given port is a member
of. A switchdev object is used to carry the VID and bridge flags.
-- port_fdb_add: bridge layer function invoked when the bridge wants to install a
+- ``port_fdb_add``: bridge layer function invoked when the bridge wants to install a
Forwarding Database entry, the switch hardware should be programmed with the
specified address in the specified VLAN Id in the forwarding database
associated with this VLAN ID. If the operation is not supported, this
- function should return -EOPNOTSUPP to inform the bridge code to fallback to
+ function should return ``-EOPNOTSUPP`` to inform the bridge code to fallback to
a software implementation.
-Note: VLAN ID 0 corresponds to the port private database, which, in the context
-of DSA, would be the its port-based VLAN, used by the associated bridge device.
+.. note:: VLAN ID 0 corresponds to the port private database, which, in the context
+ of DSA, would be the its port-based VLAN, used by the associated bridge device.
-- port_fdb_del: bridge layer function invoked when the bridge wants to remove a
+- ``port_fdb_del``: bridge layer function invoked when the bridge wants to remove a
Forwarding Database entry, the switch hardware should be programmed to delete
the specified MAC address from the specified VLAN ID if it was mapped into
this port forwarding database
-- port_fdb_dump: bridge layer function invoked with a switchdev callback
+- ``port_fdb_dump``: bridge layer function invoked with a switchdev callback
function that the driver has to call for each MAC address known to be behind
the given port. A switchdev object is used to carry the VID and FDB info.
-- port_mdb_prepare: bridge layer function invoked when the bridge prepares the
+- ``port_mdb_prepare``: bridge layer function invoked when the bridge prepares the
installation of a multicast database entry. If the operation is not supported,
- this function should return -EOPNOTSUPP to inform the bridge code to fallback
+ this function should return ``-EOPNOTSUPP`` to inform the bridge code to fallback
to a software implementation. No hardware setup must be done in this function.
- See port_fdb_add for this and details.
+ See ``port_fdb_add`` for this and details.
-- port_mdb_add: bridge layer function invoked when the bridge wants to install
+- ``port_mdb_add``: bridge layer function invoked when the bridge wants to install
a multicast database entry, the switch hardware should be programmed with the
specified address in the specified VLAN ID in the forwarding database
associated with this VLAN ID.
-Note: VLAN ID 0 corresponds to the port private database, which, in the context
-of DSA, would be the its port-based VLAN, used by the associated bridge device.
+.. note:: VLAN ID 0 corresponds to the port private database, which, in the context
+ of DSA, would be the its port-based VLAN, used by the associated bridge device.
-- port_mdb_del: bridge layer function invoked when the bridge wants to remove a
+- ``port_mdb_del``: bridge layer function invoked when the bridge wants to remove a
multicast database entry, the switch hardware should be programmed to delete
the specified MAC address from the specified VLAN ID if it was mapped into
this port forwarding database.
-- port_mdb_dump: bridge layer function invoked with a switchdev callback
+- ``port_mdb_dump``: bridge layer function invoked with a switchdev callback
function that the driver has to call for each MAC address known to be behind
the given port. A switchdev object is used to carry the VID and MDB info.
Other hanging fruits
--------------------
-- making the number of ports fully dynamic and not dependent on DSA_MAX_PORTS
+- making the number of ports fully dynamic and not dependent on ``DSA_MAX_PORTS``
- allowing more than one CPU/management interface:
http://comments.gmane.org/gmane.linux.network/365657
- porting more drivers from other vendors:
--- /dev/null
+===============================
+Distributed Switch Architecture
+===============================
+
+.. toctree::
+ :maxdepth: 1
+
+ dsa
+ bcm_sf2
+ lan9303
+==============================
LAN9303 Ethernet switch driver
==============================
Driver details
==============
-The driver is implemented as a DSA driver, see
-Documentation/networking/dsa/dsa.txt.
+The driver is implemented as a DSA driver, see ``Documentation/networking/dsa/dsa.rst``.
-See Documentation/devicetree/bindings/net/dsa/lan9303.txt for device tree
+See ``Documentation/devicetree/bindings/net/dsa/lan9303.txt`` for device tree
binding.
The LAN9303 can be managed both via MDIO and I2C, both supported by this driver.
netdev-FAQ
af_xdp
batman-adv
+ bpf_flow_dissector
can
can_ucan_protocol
device_drivers/freescale/dpaa2/index
device_drivers/intel/i40e
device_drivers/intel/iavf
device_drivers/intel/ice
+ dsa/index
devlink-info-versions
ieee802154
kapi
(*) Check call still alive.
- u32 rxrpc_kernel_check_life(struct socket *sock,
- struct rxrpc_call *call);
+ bool rxrpc_kernel_check_life(struct socket *sock,
+ struct rxrpc_call *call,
+ u32 *_life);
void rxrpc_kernel_probe_life(struct socket *sock,
struct rxrpc_call *call);
- The first function returns a number that is updated when ACKs are received
- from the peer (notably including PING RESPONSE ACKs which we can elicit by
- sending PING ACKs to see if the call still exists on the server). The
- caller should compare the numbers of two calls to see if the call is still
- alive after waiting for a suitable interval.
+ The first function passes back in *_life a number that is updated when
+ ACKs are received from the peer (notably including PING RESPONSE ACKs
+ which we can elicit by sending PING ACKs to see if the call still exists
+ on the server). The caller should compare the numbers of two calls to see
+ if the call is still alive after waiting for a suitable interval. It also
+ returns true as long as the call hasn't yet reached the completed state.
This allows the caller to work out if the server is still contactable and
if the call is still alive on the server while waiting for the server to
----------------------
The kvm API is a set of ioctls that are issued to control various aspects
-of a virtual machine. The ioctls belong to three classes
+of a virtual machine. The ioctls belong to three classes:
- System ioctls: These query and set global attributes which affect the
whole kvm subsystem. In addition a system ioctl is used to create
- virtual machines
+ virtual machines.
- VM ioctls: These query and set attributes that affect an entire virtual
machine, for example memory layout. In addition a VM ioctl is used to
- create virtual cpus (vcpus).
+ create virtual cpus (vcpus) and devices.
- Only run VM ioctls from the same process (address space) that was used
- to create the VM.
+ VM ioctls must be issued from the same process (address space) that was
+ used to create the VM.
- vcpu ioctls: These query and set attributes that control the operation
of a single virtual cpu.
- Only run vcpu ioctls from the same thread that was used to create the
- vcpu.
+ vcpu ioctls should be issued from the same thread that was used to create
+ the vcpu, except for asynchronous vcpu ioctl that are marked as such in
+ the documentation. Otherwise, the first ioctl after switching threads
+ could see a performance impact.
+ - device ioctls: These query and set attributes that control the operation
+ of a single device.
+
+ device ioctls must be issued from the same process (address space) that
+ was used to create the VM.
2. File descriptors
-------------------
open("/dev/kvm") obtains a handle to the kvm subsystem; this handle
can be used to issue system ioctls. A KVM_CREATE_VM ioctl on this
handle will create a VM file descriptor which can be used to issue VM
-ioctls. A KVM_CREATE_VCPU ioctl on a VM fd will create a virtual cpu
-and return a file descriptor pointing to it. Finally, ioctls on a vcpu
-fd can be used to control the vcpu, including the important task of
-actually running guest code.
+ioctls. A KVM_CREATE_VCPU or KVM_CREATE_DEVICE ioctl on a VM fd will
+create a virtual cpu or device and return a file descriptor pointing to
+the new resource. Finally, ioctls on a vcpu or device fd can be used
+to control the vcpu or device. For vcpus, this includes the important
+task of actually running guest code.
In general file descriptors can be migrated among processes by means
of fork() and the SCM_RIGHTS facility of unix domain socket. These
kinds of tricks are explicitly not supported by kvm. While they will
not cause harm to the host, their actual behavior is not guaranteed by
-the API. The only supported use is one virtual machine per process,
-and one vcpu per thread.
+the API. See "General description" for details on the ioctl usage
+model that is supported by KVM.
+
+It is important to note that althought VM ioctls may only be issued from
+the process that created the VM, a VM's lifecycle is associated with its
+file descriptor, not its creator (process). In other words, the VM and
+its resources, *including the associated address space*, are not freed
+until the last reference to the VM's file descriptor has been released.
+For example, if fork() is issued after ioctl(KVM_CREATE_VM), the VM will
+not be freed until both the parent (original) process and its child have
+put their references to the VM's file descriptor.
+
+Because a VM's resources are not freed until the last reference to its
+file descriptor is released, creating additional references to a VM via
+via fork(), dup(), etc... without careful consideration is strongly
+discouraged and may have unwanted side effects, e.g. memory allocated
+by and on behalf of the VM's process may not be freed/unaccounted when
+the VM is shut down.
It is important to note that althought VM ioctls may only be issued from
Note that any value for 'irq' other than the ones stated above is invalid
and incurs unexpected behavior.
+This is an asynchronous vcpu ioctl and can be invoked from any thread.
+
MIPS:
Queues an external interrupt to be injected into the virtual CPU. A negative
interrupt number dequeues the interrupt.
+This is an asynchronous vcpu ioctl and can be invoked from any thread.
+
4.17 KVM_DEBUG_GUEST
#define KVM_MEM_LOG_DIRTY_PAGES (1UL << 0)
#define KVM_MEM_READONLY (1UL << 1)
-This ioctl allows the user to create or modify a guest physical memory
-slot. When changing an existing slot, it may be moved in the guest
-physical memory space, or its flags may be modified. It may not be
-resized. Slots may not overlap in guest physical address space.
-Bits 0-15 of "slot" specifies the slot id and this value should be
-less than the maximum number of user memory slots supported per VM.
-The maximum allowed slots can be queried using KVM_CAP_NR_MEMSLOTS,
-if this capability is supported by the architecture.
+This ioctl allows the user to create, modify or delete a guest physical
+memory slot. Bits 0-15 of "slot" specify the slot id and this value
+should be less than the maximum number of user memory slots supported per
+VM. The maximum allowed slots can be queried using KVM_CAP_NR_MEMSLOTS,
+if this capability is supported by the architecture. Slots may not
+overlap in guest physical address space.
If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 of "slot"
specifies the address space which is being modified. They must be
are unrelated; the restriction on overlapping slots only applies within
each address space.
+Deleting a slot is done by passing zero for memory_size. When changing
+an existing slot, it may be moved in the guest physical memory space,
+or its flags may be modified, but it may not be resized.
+
Memory for the region is taken starting at the address denoted by the
field userspace_addr, which must point at user addressable memory for
the entire memory slot size. Any object may back this memory, including
machine checks needing further payload are not
supported by this ioctl)
-Note that the vcpu ioctl is asynchronous to vcpu execution.
+This is an asynchronous vcpu ioctl and can be invoked from any thread.
4.78 KVM_PPC_GET_HTAB_FD
KVM_S390_INT_EXTERNAL_CALL - sigp external call; parameters in .extcall
KVM_S390_MCHK - machine check interrupt; parameters in .mchk
-
-Note that the vcpu ioctl is asynchronous to vcpu execution.
+This is an asynchronous vcpu ioctl and can be invoked from any thread.
4.94 KVM_S390_GET_IRQ_STATE
If clear, this page corresponds to a guest page table denoted by the gfn
field.
role.quadrant:
- When role.cr4_pae=0, the guest uses 32-bit gptes while the host uses 64-bit
+ When role.gpte_is_8_bytes=0, the guest uses 32-bit gptes while the host uses 64-bit
sptes. That means a guest page table contains more ptes than the host,
so multiple shadow pages are needed to shadow one guest page.
For first-level shadow pages, role.quadrant can be 0 or 1 and denotes the
The page is invalid and should not be used. It is a root page that is
currently pinned (by a cpu hardware register pointing to it); once it is
unpinned it will be destroyed.
- role.cr4_pae:
- Contains the value of cr4.pae for which the page is valid (e.g. whether
- 32-bit or 64-bit gptes are in use).
+ role.gpte_is_8_bytes:
+ Reflects the size of the guest PTE for which the page is valid, i.e. '1'
+ if 64-bit gptes are in use, '0' if 32-bit gptes are in use.
role.nxe:
Contains the value of efer.nxe for which the page is valid.
role.cr0_wp:
Contains the value of cr4.smap && !cr0.wp for which the page is valid
(pages for which this is true are different from other pages; see the
treatment of cr0.wp=0 below).
+ role.ept_sp:
+ This is a virtual flag to denote a shadowed nested EPT page. ept_sp
+ is true if "cr0_wp && smap_andnot_wp", an otherwise invalid combination.
role.smm:
Is 1 if the page is valid in system management mode. This field
determines which of the kvm_memslots array was used to build this
ARM/NUVOTON NPCM ARCHITECTURE
M: Avi Fishman <avifishman70@gmail.com>
M: Tomer Maimon <tmaimon77@gmail.com>
+M: Tali Perry <tali.perry1@gmail.com>
R: Patrick Venture <venture@google.com>
R: Nancy Yuen <yuenn@google.com>
-R: Brendan Higgins <brendanhiggins@google.com>
+R: Benjamin Fair <benjaminfair@google.com>
L: openbmc@lists.ozlabs.org (moderated for non-subscribers)
S: Supported
F: arch/arm/mach-npcm/
F: arch/arm/boot/dts/nuvoton-npcm*
-F: include/dt-bindings/clock/nuvoton,npcm7xx-clks.h
+F: include/dt-bindings/clock/nuvoton,npcm7xx-clock.h
F: drivers/*/*npcm*
F: Documentation/devicetree/bindings/*/*npcm*
F: Documentation/devicetree/bindings/*/*/*npcm*
F: arch/arm64/boot/dts/socionext/uniphier*
F: drivers/bus/uniphier-system-bus.c
F: drivers/clk/uniphier/
-F: drivers/dmaengine/uniphier-mdmac.c
+F: drivers/dma/uniphier-mdmac.c
F: drivers/gpio/gpio-uniphier.c
F: drivers/i2c/busses/i2c-uniphier*
F: drivers/irqchip/irq-uniphier-aidet.c
F: include/linux/cpuidle.h
CRAMFS FILESYSTEM
-M: Nicolas Pitre <nico@linaro.org>
+M: Nicolas Pitre <nico@fluxnic.net>
S: Maintained
F: Documentation/filesystems/cramfs.txt
F: fs/cramfs/
S: Maintained
F: Documentation/ABI/testing/sysfs-bus-mdio
F: Documentation/devicetree/bindings/net/mdio*
-F: Documentation/networking/phy.txt
+F: Documentation/networking/phy.rst
F: drivers/net/phy/
F: drivers/of/of_mdio.c
F: drivers/of/of_net.c
T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git locking/core
S: Maintained
F: kernel/futex.c
-F: kernel/futex_compat.c
F: include/asm-generic/futex.h
F: include/linux/futex.h
F: include/uapi/linux/futex.h
F: include/net/af_ieee802154.h
F: include/net/cfg802154.h
F: include/net/ieee802154_netdev.h
-F: Documentation/networking/ieee802154.txt
+F: Documentation/networking/ieee802154.rst
IFE PROTOCOL
M: Yotam Gigi <yotam.gi@gmail.com>
F: Documentation/devicetree/bindings/mfd/atmel-usart.txt
MICROCHIP KSZ SERIES ETHERNET SWITCH DRIVER
-M: Woojung Huh <Woojung.Huh@microchip.com>
+M: Woojung Huh <woojung.huh@microchip.com>
M: Microchip Linux Driver Support <UNGLinuxDriver@microchip.com>
L: netdev@vger.kernel.org
S: Maintained
SFC NETWORK DRIVER
M: Solarflare linux maintainers <linux-net-drivers@solarflare.com>
M: Edward Cree <ecree@solarflare.com>
-M: Bert Kenward <bkenward@solarflare.com>
+M: Martin Habets <mhabets@solarflare.com>
L: netdev@vger.kernel.org
S: Supported
F: drivers/net/ethernet/sfc/
F: include/linux/virtio_console.h
F: include/uapi/linux/virtio_console.h
-VIRTIO CORE, NET AND BLOCK DRIVERS
+VIRTIO CORE AND NET DRIVERS
M: "Michael S. Tsirkin" <mst@redhat.com>
M: Jason Wang <jasowang@redhat.com>
L: virtualization@lists.linux-foundation.org
F: drivers/crypto/virtio/
F: mm/balloon_compaction.c
+VIRTIO BLOCK AND SCSI DRIVERS
+M: "Michael S. Tsirkin" <mst@redhat.com>
+M: Jason Wang <jasowang@redhat.com>
+R: Paolo Bonzini <pbonzini@redhat.com>
+R: Stefan Hajnoczi <stefanha@redhat.com>
+L: virtualization@lists.linux-foundation.org
+S: Maintained
+F: drivers/block/virtio_blk.c
+F: drivers/scsi/virtio_scsi.c
+F: include/uapi/linux/virtio_blk.h
+F: include/uapi/linux/virtio_scsi.h
+F: drivers/vhost/scsi.c
+
VIRTIO CRYPTO DRIVER
M: Gonglei <arei.gonglei@huawei.com>
L: virtualization@lists.linux-foundation.org
VERSION = 5
PATCHLEVEL = 1
SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc5
NAME = Shy Crocodile
# *DOCUMENTATION*
# descending is started. They are now explicitly listed as the
# prepare rule.
-# Ugly workaround for Debian make-kpkg:
-# make-kpkg directly includes the top Makefile of Linux kernel. In such a case,
-# skip sub-make to support debian_* targets in ruleset/kernel_version.mk, but
-# displays warning to discourage such abusage.
-ifneq ($(word 2, $(MAKEFILE_LIST)),)
-$(warning Do not include top Makefile of Linux Kernel)
-sub-make-done := 1
-MAKEFLAGS += -rR
-endif
-
-ifneq ($(sub-make-done),1)
+ifneq ($(sub_make_done),1)
# Do not use make's built-in rules and variables
# (this increases performance and avoids hard-to-debug behaviour)
MAKEFLAGS += -rR
-# 'MAKEFLAGS += -rR' does not become immediately effective for old
-# GNU Make versions. Cancel implicit rules for this Makefile.
-$(lastword $(MAKEFILE_LIST)): ;
-
# Avoid funny character set dependencies
unexport LC_ALL
LC_COLLATE=C
# 'sub-make' below.
MAKEFLAGS += --include-dir=$(CURDIR)
+need-sub-make := 1
else
# Do not print "Entering directory ..." at all for in-tree build.
endif # ifneq ($(KBUILD_OUTPUT),)
+ifneq ($(filter 3.%,$(MAKE_VERSION)),)
+# 'MAKEFLAGS += -rR' does not immediately become effective for GNU Make 3.x
+# We need to invoke sub-make to avoid implicit rules in the top Makefile.
+need-sub-make := 1
+# Cancel implicit rules for this Makefile.
+$(lastword $(MAKEFILE_LIST)): ;
+endif
+
+export sub_make_done := 1
+
+ifeq ($(need-sub-make),1)
+
PHONY += $(MAKECMDGOALS) sub-make
$(filter-out _all sub-make $(CURDIR)/Makefile, $(MAKECMDGOALS)) _all: sub-make
# Invoke a second make in the output directory, passing relevant variables
sub-make:
- $(Q)$(MAKE) sub-make-done=1 \
+ $(Q)$(MAKE) \
$(if $(KBUILD_OUTPUT),-C $(KBUILD_OUTPUT) KBUILD_SRC=$(CURDIR)) \
-f $(CURDIR)/Makefile $(filter-out _all sub-make,$(MAKECMDGOALS))
-else # sub-make-done
+endif # need-sub-make
+endif # sub_make_done
+
# We process the rest of the Makefile if this is the final invocation of make
+ifeq ($(need-sub-make),)
# Do not print "Entering directory ...",
# but we want to display it when entering to the output directory
STRIP = $(CROSS_COMPILE)strip
OBJCOPY = $(CROSS_COMPILE)objcopy
OBJDUMP = $(CROSS_COMPILE)objdump
+PAHOLE = pahole
LEX = flex
YACC = bison
AWK = awk
GCC_PLUGINS_CFLAGS :=
export ARCH SRCARCH CONFIG_SHELL HOSTCC KBUILD_HOSTCFLAGS CROSS_COMPILE AS LD CC
-export CPP AR NM STRIP OBJCOPY OBJDUMP KBUILD_HOSTLDFLAGS KBUILD_HOSTLDLIBS
+export CPP AR NM STRIP OBJCOPY OBJDUMP PAHOLE KBUILD_HOSTLDFLAGS KBUILD_HOSTLDLIBS
export MAKE LEX YACC AWK INSTALLKERNEL PERL PYTHON PYTHON2 PYTHON3 UTS_MACHINE
export HOSTCXX KBUILD_HOSTCXXFLAGS LDFLAGS_MODULE CHECK CHECKFLAGS
ifneq ($(KBUILD_SRC),)
$(Q)ln -fsn $(srctree) source
$(Q)$(CONFIG_SHELL) $(srctree)/scripts/mkmakefile $(srctree)
- $(Q){ echo "# this is build directory, ignore it"; echo "*"; } > .gitignore
+ $(Q)test -e .gitignore || \
+ { echo "# this is build directory, ignore it"; echo "*"; } > .gitignore
endif
ifneq ($(shell $(CC) --version 2>&1 | head -n 1 | grep clang),)
KBUILD_CFLAGS += $(call cc-disable-warning, int-in-bool-context)
ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE
-KBUILD_CFLAGS += $(call cc-option,-Oz,-Os)
+KBUILD_CFLAGS += -Os
else
KBUILD_CFLAGS += -O2
endif
endif
export mod_sign_cmd
+HOST_LIBELF_LIBS = $(shell pkg-config libelf --libs 2>/dev/null || echo -lelf)
+
ifdef CONFIG_STACK_VALIDATION
has_libelf := $(call try-run,\
- echo "int main() {}" | $(HOSTCC) -xc -o /dev/null -lelf -,1,0)
+ echo "int main() {}" | $(HOSTCC) -xc -o /dev/null $(HOST_LIBELF_LIBS) -,1,0)
ifeq ($(has_libelf),1)
objtool_target := tools/objtool FORCE
else
endif # ifeq ($(config-targets),1)
endif # ifeq ($(mixed-targets),1)
-endif # sub-make-done
+endif # need-sub-make
PHONY += FORCE
FORCE:
generic-y += export.h
generic-y += fb.h
generic-y += irq_work.h
+generic-y += kvm_para.h
generic-y += mcs_spinlock.h
generic-y += mm-arch-hooks.h
generic-y += preempt.h
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#include <asm-generic/kvm_para.h>
generic-y += hw_irq.h
generic-y += irq_regs.h
generic-y += irq_work.h
+generic-y += kvm_para.h
generic-y += local.h
generic-y += local64.h
generic-y += mcs_spinlock.h
*/
static inline void
syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
- unsigned int i, unsigned int n, unsigned long *args)
+ unsigned long *args)
{
unsigned long *inside_ptregs = &(regs->r0);
- inside_ptregs -= i;
-
- BUG_ON((i + n) > 6);
+ unsigned int n = 6;
+ unsigned int i = 0;
while (n--) {
args[i++] = (*inside_ptregs);
-generic-y += kvm_para.h
generic-y += ucontext.h
select HAVE_IDE
select PM_GENERIC_DOMAINS if PM
select PM_GENERIC_DOMAINS_OF if PM && OF
+ select REGMAP_MMIO
select RESET_CONTROLLER
select SPARSE_IRQ
select USE_OF
enable-active-high;
};
+ /* TPS79501 */
+ v1_8d_reg: fixedregulator-v1_8d {
+ compatible = "regulator-fixed";
+ regulator-name = "v1_8d";
+ vin-supply = <&vbat>;
+ regulator-min-microvolt = <1800000>;
+ regulator-max-microvolt = <1800000>;
+ };
+
+ /* TPS79501 */
+ v3_3d_reg: fixedregulator-v3_3d {
+ compatible = "regulator-fixed";
+ regulator-name = "v3_3d";
+ vin-supply = <&vbat>;
+ regulator-min-microvolt = <3300000>;
+ regulator-max-microvolt = <3300000>;
+ };
+
matrix_keypad: matrix_keypad0 {
compatible = "gpio-matrix-keypad";
debounce-delay-ms = <5>;
status = "okay";
/* Regulators */
- AVDD-supply = <&vaux2_reg>;
- IOVDD-supply = <&vaux2_reg>;
- DRVDD-supply = <&vaux2_reg>;
- DVDD-supply = <&vbat>;
+ AVDD-supply = <&v3_3d_reg>;
+ IOVDD-supply = <&v3_3d_reg>;
+ DRVDD-supply = <&v3_3d_reg>;
+ DVDD-supply = <&v1_8d_reg>;
};
};
enable-active-high;
};
+ /* TPS79518 */
+ v1_8d_reg: fixedregulator-v1_8d {
+ compatible = "regulator-fixed";
+ regulator-name = "v1_8d";
+ vin-supply = <&vbat>;
+ regulator-min-microvolt = <1800000>;
+ regulator-max-microvolt = <1800000>;
+ };
+
+ /* TPS78633 */
+ v3_3d_reg: fixedregulator-v3_3d {
+ compatible = "regulator-fixed";
+ regulator-name = "v3_3d";
+ vin-supply = <&vbat>;
+ regulator-min-microvolt = <3300000>;
+ regulator-max-microvolt = <3300000>;
+ };
+
leds {
pinctrl-names = "default";
pinctrl-0 = <&user_leds_s0>;
status = "okay";
/* Regulators */
- AVDD-supply = <&vaux2_reg>;
- IOVDD-supply = <&vaux2_reg>;
- DRVDD-supply = <&vaux2_reg>;
- DVDD-supply = <&vbat>;
+ AVDD-supply = <&v3_3d_reg>;
+ IOVDD-supply = <&v3_3d_reg>;
+ DRVDD-supply = <&v3_3d_reg>;
+ DVDD-supply = <&v1_8d_reg>;
};
};
reg = <0xcc000 0x4>;
reg-names = "rev";
/* Domains (P, C): per_pwrdm, l4ls_clkdm */
- clocks = <&l4ls_clkctrl AM3_D_CAN0_CLKCTRL 0>;
+ clocks = <&l4ls_clkctrl AM3_L4LS_D_CAN0_CLKCTRL 0>;
clock-names = "fck";
#address-cells = <1>;
#size-cells = <1>;
reg = <0xd0000 0x4>;
reg-names = "rev";
/* Domains (P, C): per_pwrdm, l4ls_clkdm */
- clocks = <&l4ls_clkctrl AM3_D_CAN1_CLKCTRL 0>;
+ clocks = <&l4ls_clkctrl AM3_L4LS_D_CAN1_CLKCTRL 0>;
clock-names = "fck";
#address-cells = <1>;
#size-cells = <1>;
};
&hdmi {
- hpd-gpios = <&gpio 46 GPIO_ACTIVE_LOW>;
+ hpd-gpios = <&gpio 46 GPIO_ACTIVE_HIGH>;
};
&pwm {
reg = <2>;
};
- switch@0 {
+ switch@10 {
compatible = "qca,qca8334";
- reg = <0>;
+ reg = <10>;
switch_ports: ports {
#address-cells = <1>;
ethphy0: port@0 {
reg = <0>;
label = "cpu";
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
ethernet = <&fec>;
fixed-link {
pinctrl-2 = <&pinctrl_usdhc3_200mhz>;
vmcc-supply = <®_sd3_vmmc>;
cd-gpios = <&gpio1 1 GPIO_ACTIVE_LOW>;
- bus-witdh = <4>;
+ bus-width = <4>;
no-1-8-v;
status = "okay";
};
pinctrl-1 = <&pinctrl_usdhc4_100mhz>;
pinctrl-2 = <&pinctrl_usdhc4_200mhz>;
vmcc-supply = <®_sd4_vmmc>;
- bus-witdh = <8>;
+ bus-width = <8>;
no-1-8-v;
non-removable;
status = "okay";
pinctrl-0 = <&pinctrl_enet>;
phy-handle = <ðphy>;
phy-mode = "rgmii";
+ phy-reset-duration = <10>; /* in msecs */
phy-reset-gpios = <&gpio3 23 GPIO_ACTIVE_LOW>;
phy-supply = <&vdd_eth_io_reg>;
status = "disabled";
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright (C) 2016 Freescale Semiconductor, Inc.
* Copyright (C) 2017 NXP
};
vccio_sd: LDO_REG5 {
+ regulator-boot-on;
regulator-min-microvolt = <1800000>;
regulator-max-microvolt = <3300000>;
regulator-name = "vccio_sd";
bus-width = <4>;
cap-mmc-highspeed;
cap-sd-highspeed;
- card-detect-delay = <200>;
+ broken-cd;
disable-wp; /* wp not hooked up */
pinctrl-names = "default";
pinctrl-0 = <&sdmmc_clk &sdmmc_cmd &sdmmc_cd &sdmmc_bus4>;
gpio_keys: gpio-keys {
compatible = "gpio-keys";
- #address-cells = <1>;
- #size-cells = <0>;
pinctrl-names = "default";
pinctrl-0 = <&pwr_key_l>;
compatible = "arm,cortex-a12";
reg = <0x501>;
resets = <&cru SRST_CORE1>;
- operating-points = <&cpu_opp_table>;
+ operating-points-v2 = <&cpu_opp_table>;
#cooling-cells = <2>; /* min followed by max */
clock-latency = <40000>;
clocks = <&cru ARMCLK>;
compatible = "arm,cortex-a12";
reg = <0x502>;
resets = <&cru SRST_CORE2>;
- operating-points = <&cpu_opp_table>;
+ operating-points-v2 = <&cpu_opp_table>;
#cooling-cells = <2>; /* min followed by max */
clock-latency = <40000>;
clocks = <&cru ARMCLK>;
compatible = "arm,cortex-a12";
reg = <0x503>;
resets = <&cru SRST_CORE3>;
- operating-points = <&cpu_opp_table>;
+ operating-points-v2 = <&cpu_opp_table>;
#cooling-cells = <2>; /* min followed by max */
clock-latency = <40000>;
clocks = <&cru ARMCLK>;
clock-names = "ref", "pclk";
power-domains = <&power RK3288_PD_VIO>;
rockchip,grf = <&grf>;
- #address-cells = <1>;
- #size-cells = <0>;
status = "disabled";
ports {
gpu_opp_table: gpu-opp-table {
compatible = "operating-points-v2";
- opp@100000000 {
+ opp-100000000 {
opp-hz = /bits/ 64 <100000000>;
opp-microvolt = <950000>;
};
- opp@200000000 {
+ opp-200000000 {
opp-hz = /bits/ 64 <200000000>;
opp-microvolt = <950000>;
};
- opp@300000000 {
+ opp-300000000 {
opp-hz = /bits/ 64 <300000000>;
opp-microvolt = <1000000>;
};
- opp@400000000 {
+ opp-400000000 {
opp-hz = /bits/ 64 <400000000>;
opp-microvolt = <1100000>;
};
- opp@500000000 {
+ opp-500000000 {
opp-hz = /bits/ 64 <500000000>;
opp-microvolt = <1200000>;
};
- opp@600000000 {
+ opp-600000000 {
opp-hz = /bits/ 64 <600000000>;
opp-microvolt = <1250000>;
};
#define PIN_PC9__GPIO PINMUX_PIN(PIN_PC9, 0, 0)
#define PIN_PC9__FIQ PINMUX_PIN(PIN_PC9, 1, 3)
#define PIN_PC9__GTSUCOMP PINMUX_PIN(PIN_PC9, 2, 1)
-#define PIN_PC9__ISC_D0 PINMUX_PIN(PIN_PC9, 2, 1)
+#define PIN_PC9__ISC_D0 PINMUX_PIN(PIN_PC9, 3, 1)
#define PIN_PC9__TIOA4 PINMUX_PIN(PIN_PC9, 4, 2)
#define PIN_PC10 74
#define PIN_PC10__GPIO PINMUX_PIN(PIN_PC10, 0, 0)
# CONFIG_IOMMU_SUPPORT is not set
CONFIG_IIO=y
CONFIG_FSL_MX25_ADC=y
+CONFIG_PWM=y
+CONFIG_PWM_IMX1=y
+CONFIG_PWM_IMX27=y
CONFIG_EXT4_FS=y
# CONFIG_DNOTIFY is not set
CONFIG_VFAT_FS=y
CONFIG_MPL3115=y
CONFIG_PWM=y
CONFIG_PWM_FSL_FTM=y
-CONFIG_PWM_IMX=y
+CONFIG_PWM_IMX27=y
CONFIG_NVMEM_IMX_OCOTP=y
CONFIG_NVMEM_VF610_OCOTP=y
CONFIG_TEE=y
return ret;
}
+static inline int kvm_write_guest_lock(struct kvm *kvm, gpa_t gpa,
+ const void *data, unsigned long len)
+{
+ int srcu_idx = srcu_read_lock(&kvm->srcu);
+ int ret = kvm_write_guest(kvm, gpa, data, len);
+
+ srcu_read_unlock(&kvm->srcu, srcu_idx);
+
+ return ret;
+}
+
static inline void *kvm_get_hyp_vector(void)
{
switch(read_cpuid_part()) {
#define S2_PMD_MASK PMD_MASK
#define S2_PMD_SIZE PMD_SIZE
+#define S2_PUD_MASK PUD_MASK
+#define S2_PUD_SIZE PUD_SIZE
static inline bool kvm_stage2_has_pmd(struct kvm *kvm)
{
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
- if (n == 0)
- return;
-
- if (i + n > SYSCALL_MAX_ARGS) {
- unsigned long *args_bad = args + SYSCALL_MAX_ARGS - i;
- unsigned int n_bad = n + i - SYSCALL_MAX_ARGS;
- pr_warn("%s called with max args %d, handling only %d\n",
- __func__, i + n, SYSCALL_MAX_ARGS);
- memset(args_bad, 0, n_bad * sizeof(args[0]));
- n = SYSCALL_MAX_ARGS - i;
- }
-
- if (i == 0) {
- args[0] = regs->ARM_ORIG_r0;
- args++;
- i++;
- n--;
- }
-
- memcpy(args, ®s->ARM_r0 + i, n * sizeof(args[0]));
+ args[0] = regs->ARM_ORIG_r0;
+ args++;
+
+ memcpy(args, ®s->ARM_r0 + 1, 5 * sizeof(args[0]));
}
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
- if (n == 0)
- return;
-
- if (i + n > SYSCALL_MAX_ARGS) {
- pr_warn("%s called with max args %d, handling only %d\n",
- __func__, i + n, SYSCALL_MAX_ARGS);
- n = SYSCALL_MAX_ARGS - i;
- }
-
- if (i == 0) {
- regs->ARM_ORIG_r0 = args[0];
- args++;
- i++;
- n--;
- }
-
- memcpy(®s->ARM_r0 + i, args, n * sizeof(args[0]));
+ regs->ARM_ORIG_r0 = args[0];
+ args++;
+
+ memcpy(®s->ARM_r0 + 1, args, 5 * sizeof(args[0]));
}
static inline int syscall_get_arch(void)
generated-y += unistd-common.h
generated-y += unistd-oabi.h
generated-y += unistd-eabi.h
+generic-y += kvm_para.h
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#include <asm-generic/kvm_para.h>
np = of_find_compatible_node(NULL, NULL, "atmel,sama5d2-securam");
if (!np)
- goto securam_fail;
+ goto securam_fail_no_ref_dev;
pdev = of_find_device_by_node(np);
of_node_put(np);
if (!pdev) {
pr_warn("%s: failed to find securam device!\n", __func__);
- goto securam_fail;
+ goto securam_fail_no_ref_dev;
}
sram_pool = gen_pool_get(&pdev->dev, NULL);
return 0;
securam_fail:
+ put_device(&pdev->dev);
+securam_fail_no_ref_dev:
iounmap(pm_data.sfrbu);
pm_data.sfrbu = NULL;
return ret;
#include "cpuidle.h"
#include "hardware.h"
-static atomic_t master = ATOMIC_INIT(0);
-static DEFINE_SPINLOCK(master_lock);
+static int num_idle_cpus = 0;
+static DEFINE_SPINLOCK(cpuidle_lock);
static int imx6q_enter_wait(struct cpuidle_device *dev,
struct cpuidle_driver *drv, int index)
{
- if (atomic_inc_return(&master) == num_online_cpus()) {
- /*
- * With this lock, we prevent other cpu to exit and enter
- * this function again and become the master.
- */
- if (!spin_trylock(&master_lock))
- goto idle;
+ spin_lock(&cpuidle_lock);
+ if (++num_idle_cpus == num_online_cpus())
imx6_set_lpm(WAIT_UNCLOCKED);
- cpu_do_idle();
- imx6_set_lpm(WAIT_CLOCKED);
- spin_unlock(&master_lock);
- goto done;
- }
+ spin_unlock(&cpuidle_lock);
-idle:
cpu_do_idle();
-done:
- atomic_dec(&master);
+
+ spin_lock(&cpuidle_lock);
+ if (num_idle_cpus-- == num_online_cpus())
+ imx6_set_lpm(WAIT_CLOCKED);
+ spin_unlock(&cpuidle_lock);
return index;
}
return;
m4if_base = of_iomap(np, 0);
+ of_node_put(np);
if (!m4if_base) {
pr_err("Unable to map M4IF registers\n");
return;
}
};
-static u64 iop13xx_adma_dmamask = DMA_BIT_MASK(64);
+static u64 iop13xx_adma_dmamask = DMA_BIT_MASK(32);
static struct iop_adma_platform_data iop13xx_adma_0_data = {
.hw_id = 0,
.pool_size = PAGE_SIZE,
.resource = iop13xx_adma_0_resources,
.dev = {
.dma_mask = &iop13xx_adma_dmamask,
- .coherent_dma_mask = DMA_BIT_MASK(64),
+ .coherent_dma_mask = DMA_BIT_MASK(32),
.platform_data = (void *) &iop13xx_adma_0_data,
},
};
.resource = iop13xx_adma_1_resources,
.dev = {
.dma_mask = &iop13xx_adma_dmamask,
- .coherent_dma_mask = DMA_BIT_MASK(64),
+ .coherent_dma_mask = DMA_BIT_MASK(32),
.platform_data = (void *) &iop13xx_adma_1_data,
},
};
.resource = iop13xx_adma_2_resources,
.dev = {
.dma_mask = &iop13xx_adma_dmamask,
- .coherent_dma_mask = DMA_BIT_MASK(64),
+ .coherent_dma_mask = DMA_BIT_MASK(32),
.platform_data = (void *) &iop13xx_adma_2_data,
},
};
}
};
-u64 iop13xx_tpmi_mask = DMA_BIT_MASK(64);
+u64 iop13xx_tpmi_mask = DMA_BIT_MASK(32);
static struct platform_device iop13xx_tpmi_0_device = {
.name = "iop-tpmi",
.id = 0,
.resource = iop13xx_tpmi_0_resources,
.dev = {
.dma_mask = &iop13xx_tpmi_mask,
- .coherent_dma_mask = DMA_BIT_MASK(64),
+ .coherent_dma_mask = DMA_BIT_MASK(32),
},
};
.resource = iop13xx_tpmi_1_resources,
.dev = {
.dma_mask = &iop13xx_tpmi_mask,
- .coherent_dma_mask = DMA_BIT_MASK(64),
+ .coherent_dma_mask = DMA_BIT_MASK(32),
},
};
.resource = iop13xx_tpmi_2_resources,
.dev = {
.dma_mask = &iop13xx_tpmi_mask,
- .coherent_dma_mask = DMA_BIT_MASK(64),
+ .coherent_dma_mask = DMA_BIT_MASK(32),
},
};
.resource = iop13xx_tpmi_3_resources,
.dev = {
.dma_mask = &iop13xx_tpmi_mask,
- .coherent_dma_mask = DMA_BIT_MASK(64),
+ .coherent_dma_mask = DMA_BIT_MASK(32),
},
};
writel(KERNEL_UNBOOT_FLAG, m10v_smp_base + cpu * 4);
}
+#ifdef CONFIG_HOTPLUG_CPU
static void m10v_cpu_die(unsigned int l_cpu)
{
gic_cpu_if_down(0);
return 1;
}
+#endif
static struct smp_operations m10v_smp_ops __initdata = {
.smp_prepare_cpus = m10v_smp_init,
.smp_boot_secondary = m10v_boot_secondary,
+#ifdef CONFIG_HOTPLUG_CPU
.cpu_die = m10v_cpu_die,
.cpu_kill = m10v_cpu_kill,
+#endif
};
CPU_METHOD_OF_DECLARE(m10v_smp, "socionext,milbeaut-m10v-smp", &m10v_smp_ops);
static struct bgpio_pdata latch1_pdata = {
.label = LATCH1_LABEL,
+ .base = -1,
.ngpio = LATCH1_NGPIO,
};
static struct bgpio_pdata latch2_pdata = {
.label = LATCH2_LABEL,
+ .base = -1,
.ngpio = LATCH2_NGPIO,
};
if (!node)
return 0;
- if (!of_device_is_available(node))
+ if (!of_device_is_available(node)) {
+ of_node_put(node);
return 0;
+ }
pdev = of_find_device_by_node(node);
.resource = iop3xx_dma_0_resources,
.dev = {
.dma_mask = &iop3xx_adma_dmamask,
- .coherent_dma_mask = DMA_BIT_MASK(64),
+ .coherent_dma_mask = DMA_BIT_MASK(32),
.platform_data = (void *) &iop3xx_dma_0_data,
},
};
.resource = iop3xx_dma_1_resources,
.dev = {
.dma_mask = &iop3xx_adma_dmamask,
- .coherent_dma_mask = DMA_BIT_MASK(64),
+ .coherent_dma_mask = DMA_BIT_MASK(32),
.platform_data = (void *) &iop3xx_dma_1_data,
},
};
.resource = iop3xx_aau_resources,
.dev = {
.dma_mask = &iop3xx_adma_dmamask,
- .coherent_dma_mask = DMA_BIT_MASK(64),
+ .coherent_dma_mask = DMA_BIT_MASK(32),
.platform_data = (void *) &iop3xx_aau_data,
},
};
.resource = orion_xor0_shared_resources,
.dev = {
.dma_mask = &orion_xor_dmamask,
- .coherent_dma_mask = DMA_BIT_MASK(64),
+ .coherent_dma_mask = DMA_BIT_MASK(32),
.platform_data = &orion_xor0_pdata,
},
};
.resource = orion_xor1_shared_resources,
.dev = {
.dma_mask = &orion_xor_dmamask,
- .coherent_dma_mask = DMA_BIT_MASK(64),
+ .coherent_dma_mask = DMA_BIT_MASK(32),
.platform_data = &orion_xor1_pdata,
},
};
bool "Broadcom BCM2835 family"
select TIMER_OF
select GPIOLIB
+ select MFD_CORE
select PINCTRL
select PINCTRL_BCM2835
select ARM_AMBA
rx-fifo-depth = <16384>;
snps,multicast-filter-bins = <256>;
iommus = <&smmu 1>;
+ altr,sysmgr-syscon = <&sysmgr 0x44 0>;
status = "disabled";
};
rx-fifo-depth = <16384>;
snps,multicast-filter-bins = <256>;
iommus = <&smmu 2>;
+ altr,sysmgr-syscon = <&sysmgr 0x48 0>;
status = "disabled";
};
rx-fifo-depth = <16384>;
snps,multicast-filter-bins = <256>;
iommus = <&smmu 3>;
+ altr,sysmgr-syscon = <&sysmgr 0x4c 0>;
status = "disabled";
};
nvidia,default-trim = <0x9>;
nvidia,dqs-trim = <63>;
mmc-hs400-1_8v;
- supports-cqe;
status = "disabled";
};
/*
* Device Tree Source for the RZ/G2E (R8A774C0) SoC
*
- * Copyright (C) 2018 Renesas Electronics Corp.
+ * Copyright (C) 2018-2019 Renesas Electronics Corp.
*/
#include <dt-bindings/clock/r8a774c0-cpg-mssr.h>
<&cpg CPG_CORE R8A774C0_CLK_S3D1C>,
<&scif_clk>;
clock-names = "fck", "brg_int", "scif_clk";
- dmas = <&dmac1 0x5b>, <&dmac1 0x5a>,
- <&dmac2 0x5b>, <&dmac2 0x5a>;
- dma-names = "tx", "rx", "tx", "rx";
+ dmas = <&dmac0 0x5b>, <&dmac0 0x5a>;
+ dma-names = "tx", "rx";
power-domains = <&sysc R8A774C0_PD_ALWAYS_ON>;
resets = <&cpg 202>;
status = "disabled";
/*
* Device Tree Source for the R-Car E3 (R8A77990) SoC
*
- * Copyright (C) 2018 Renesas Electronics Corp.
+ * Copyright (C) 2018-2019 Renesas Electronics Corp.
*/
#include <dt-bindings/clock/r8a77990-cpg-mssr.h>
<&cpg CPG_CORE R8A77990_CLK_S3D1C>,
<&scif_clk>;
clock-names = "fck", "brg_int", "scif_clk";
- dmas = <&dmac1 0x5b>, <&dmac1 0x5a>,
- <&dmac2 0x5b>, <&dmac2 0x5a>;
- dma-names = "tx", "rx", "tx", "rx";
+ dmas = <&dmac0 0x5b>, <&dmac0 0x5a>;
+ dma-names = "tx", "rx";
power-domains = <&sysc R8A77990_PD_ALWAYS_ON>;
resets = <&cpg 202>;
status = "disabled";
snps,reset-gpio = <&gpio1 RK_PC2 GPIO_ACTIVE_LOW>;
snps,reset-active-low;
snps,reset-delays-us = <0 10000 50000>;
- tx_delay = <0x25>;
- rx_delay = <0x11>;
+ tx_delay = <0x24>;
+ rx_delay = <0x18>;
status = "okay";
};
vcc_host1_5v: vcc_otg_5v: vcc-host1-5v-regulator {
compatible = "regulator-fixed";
- enable-active-high;
- gpio = <&gpio0 RK_PA2 GPIO_ACTIVE_HIGH>;
+ gpio = <&gpio0 RK_PA2 GPIO_ACTIVE_LOW>;
pinctrl-names = "default";
pinctrl-0 = <&usb20_host_drv>;
regulator-name = "vcc_host1_5v";
sdmmc0 {
sdmmc0_clk: sdmmc0-clk {
- rockchip,pins = <1 RK_PA6 1 &pcfg_pull_none_4ma>;
+ rockchip,pins = <1 RK_PA6 1 &pcfg_pull_none_8ma>;
};
sdmmc0_cmd: sdmmc0-cmd {
- rockchip,pins = <1 RK_PA4 1 &pcfg_pull_up_4ma>;
+ rockchip,pins = <1 RK_PA4 1 &pcfg_pull_up_8ma>;
};
sdmmc0_dectn: sdmmc0-dectn {
};
sdmmc0_bus1: sdmmc0-bus1 {
- rockchip,pins = <1 RK_PA0 1 &pcfg_pull_up_4ma>;
+ rockchip,pins = <1 RK_PA0 1 &pcfg_pull_up_8ma>;
};
sdmmc0_bus4: sdmmc0-bus4 {
- rockchip,pins = <1 RK_PA0 1 &pcfg_pull_up_4ma>,
- <1 RK_PA1 1 &pcfg_pull_up_4ma>,
- <1 RK_PA2 1 &pcfg_pull_up_4ma>,
- <1 RK_PA3 1 &pcfg_pull_up_4ma>;
+ rockchip,pins = <1 RK_PA0 1 &pcfg_pull_up_8ma>,
+ <1 RK_PA1 1 &pcfg_pull_up_8ma>,
+ <1 RK_PA2 1 &pcfg_pull_up_8ma>,
+ <1 RK_PA3 1 &pcfg_pull_up_8ma>;
};
sdmmc0_gpio: sdmmc0-gpio {
rgmiim1_pins: rgmiim1-pins {
rockchip,pins =
/* mac_txclk */
- <1 RK_PB4 2 &pcfg_pull_none_12ma>,
+ <1 RK_PB4 2 &pcfg_pull_none_8ma>,
/* mac_rxclk */
- <1 RK_PB5 2 &pcfg_pull_none_2ma>,
+ <1 RK_PB5 2 &pcfg_pull_none_4ma>,
/* mac_mdio */
- <1 RK_PC3 2 &pcfg_pull_none_2ma>,
+ <1 RK_PC3 2 &pcfg_pull_none_4ma>,
/* mac_txen */
- <1 RK_PD1 2 &pcfg_pull_none_12ma>,
+ <1 RK_PD1 2 &pcfg_pull_none_8ma>,
/* mac_clk */
- <1 RK_PC5 2 &pcfg_pull_none_2ma>,
+ <1 RK_PC5 2 &pcfg_pull_none_4ma>,
/* mac_rxdv */
- <1 RK_PC6 2 &pcfg_pull_none_2ma>,
+ <1 RK_PC6 2 &pcfg_pull_none_4ma>,
/* mac_mdc */
- <1 RK_PC7 2 &pcfg_pull_none_2ma>,
+ <1 RK_PC7 2 &pcfg_pull_none_4ma>,
/* mac_rxd1 */
- <1 RK_PB2 2 &pcfg_pull_none_2ma>,
+ <1 RK_PB2 2 &pcfg_pull_none_4ma>,
/* mac_rxd0 */
- <1 RK_PB3 2 &pcfg_pull_none_2ma>,
+ <1 RK_PB3 2 &pcfg_pull_none_4ma>,
/* mac_txd1 */
- <1 RK_PB0 2 &pcfg_pull_none_12ma>,
+ <1 RK_PB0 2 &pcfg_pull_none_8ma>,
/* mac_txd0 */
- <1 RK_PB1 2 &pcfg_pull_none_12ma>,
+ <1 RK_PB1 2 &pcfg_pull_none_8ma>,
/* mac_rxd3 */
- <1 RK_PB6 2 &pcfg_pull_none_2ma>,
+ <1 RK_PB6 2 &pcfg_pull_none_4ma>,
/* mac_rxd2 */
- <1 RK_PB7 2 &pcfg_pull_none_2ma>,
+ <1 RK_PB7 2 &pcfg_pull_none_4ma>,
/* mac_txd3 */
- <1 RK_PC0 2 &pcfg_pull_none_12ma>,
+ <1 RK_PC0 2 &pcfg_pull_none_8ma>,
/* mac_txd2 */
- <1 RK_PC1 2 &pcfg_pull_none_12ma>,
+ <1 RK_PC1 2 &pcfg_pull_none_8ma>,
/* mac_txclk */
- <0 RK_PB0 1 &pcfg_pull_none>,
+ <0 RK_PB0 1 &pcfg_pull_none_8ma>,
/* mac_txen */
- <0 RK_PB4 1 &pcfg_pull_none>,
+ <0 RK_PB4 1 &pcfg_pull_none_8ma>,
/* mac_clk */
- <0 RK_PD0 1 &pcfg_pull_none>,
+ <0 RK_PD0 1 &pcfg_pull_none_4ma>,
/* mac_txd1 */
- <0 RK_PC0 1 &pcfg_pull_none>,
+ <0 RK_PC0 1 &pcfg_pull_none_8ma>,
/* mac_txd0 */
- <0 RK_PC1 1 &pcfg_pull_none>,
+ <0 RK_PC1 1 &pcfg_pull_none_8ma>,
/* mac_txd3 */
- <0 RK_PC7 1 &pcfg_pull_none>,
+ <0 RK_PC7 1 &pcfg_pull_none_8ma>,
/* mac_txd2 */
- <0 RK_PC6 1 &pcfg_pull_none>;
+ <0 RK_PC6 1 &pcfg_pull_none_8ma>;
};
rmiim1_pins: rmiim1-pins {
};
&hdmi {
+ ddc-i2c-bus = <&i2c3>;
pinctrl-names = "default";
pinctrl-0 = <&hdmi_cec>;
status = "okay";
" prfm pstl1strm, %2\n" \
"1: ldxr %w1, %2\n" \
insn "\n" \
-"2: stlxr %w3, %w0, %2\n" \
-" cbnz %w3, 1b\n" \
+"2: stlxr %w0, %w3, %2\n" \
+" cbnz %w0, 1b\n" \
" dmb ish\n" \
"3:\n" \
" .pushsection .fixup,\"ax\"\n" \
static inline int
arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *_uaddr)
{
- int oldval = 0, ret, tmp;
+ int oldval, ret, tmp;
u32 __user *uaddr = __uaccess_mask_ptr(_uaddr);
pagefault_disable();
switch (op) {
case FUTEX_OP_SET:
- __futex_atomic_op("mov %w0, %w4",
+ __futex_atomic_op("mov %w3, %w4",
ret, oldval, uaddr, tmp, oparg);
break;
case FUTEX_OP_ADD:
- __futex_atomic_op("add %w0, %w1, %w4",
+ __futex_atomic_op("add %w3, %w1, %w4",
ret, oldval, uaddr, tmp, oparg);
break;
case FUTEX_OP_OR:
- __futex_atomic_op("orr %w0, %w1, %w4",
+ __futex_atomic_op("orr %w3, %w1, %w4",
ret, oldval, uaddr, tmp, oparg);
break;
case FUTEX_OP_ANDN:
- __futex_atomic_op("and %w0, %w1, %w4",
+ __futex_atomic_op("and %w3, %w1, %w4",
ret, oldval, uaddr, tmp, ~oparg);
break;
case FUTEX_OP_XOR:
- __futex_atomic_op("eor %w0, %w1, %w4",
+ __futex_atomic_op("eor %w3, %w1, %w4",
ret, oldval, uaddr, tmp, oparg);
break;
default:
return ret;
}
+static inline int kvm_write_guest_lock(struct kvm *kvm, gpa_t gpa,
+ const void *data, unsigned long len)
+{
+ int srcu_idx = srcu_read_lock(&kvm->srcu);
+ int ret = kvm_write_guest(kvm, gpa, data, len);
+
+ srcu_read_unlock(&kvm->srcu, srcu_idx);
+
+ return ret;
+}
+
#ifdef CONFIG_KVM_INDIRECT_VECTORS
/*
* EL2 vectors can be mapped and rerouted in a number of ways,
struct plt_entry get_plt_entry(u64 dst, void *pc);
bool plt_entries_equal(const struct plt_entry *a, const struct plt_entry *b);
+static inline bool plt_entry_is_initialized(const struct plt_entry *e)
+{
+ return e->adrp || e->add || e->br;
+}
+
#endif /* __ASM_MODULE_H */
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
- if (n == 0)
- return;
-
- if (i + n > SYSCALL_MAX_ARGS) {
- unsigned long *args_bad = args + SYSCALL_MAX_ARGS - i;
- unsigned int n_bad = n + i - SYSCALL_MAX_ARGS;
- pr_warning("%s called with max args %d, handling only %d\n",
- __func__, i + n, SYSCALL_MAX_ARGS);
- memset(args_bad, 0, n_bad * sizeof(args[0]));
- }
-
- if (i == 0) {
- args[0] = regs->orig_x0;
- args++;
- i++;
- n--;
- }
-
- memcpy(args, ®s->regs[i], n * sizeof(args[0]));
+ args[0] = regs->orig_x0;
+ args++;
+
+ memcpy(args, ®s->regs[1], 5 * sizeof(args[0]));
}
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
- if (n == 0)
- return;
-
- if (i + n > SYSCALL_MAX_ARGS) {
- pr_warning("%s called with max args %d, handling only %d\n",
- __func__, i + n, SYSCALL_MAX_ARGS);
- n = SYSCALL_MAX_ARGS - i;
- }
-
- if (i == 0) {
- regs->orig_x0 = args[0];
- args++;
- i++;
- n--;
- }
-
- memcpy(®s->regs[i], args, n * sizeof(args[0]));
+ regs->orig_x0 = args[0];
+ args++;
+
+ memcpy(®s->regs[1], args, 5 * sizeof(args[0]));
}
/*
trampoline = get_plt_entry(addr, mod->arch.ftrace_trampoline);
if (!plt_entries_equal(mod->arch.ftrace_trampoline,
&trampoline)) {
- if (!plt_entries_equal(mod->arch.ftrace_trampoline,
- &(struct plt_entry){})) {
+ if (plt_entry_is_initialized(mod->arch.ftrace_trampoline)) {
pr_err("ftrace: far branches to multiple entry points unsupported inside a single module\n");
return -EINVAL;
}
unsigned long low = (unsigned long)raw_cpu_read(sdei_stack_normal_ptr);
unsigned long high = low + SDEI_STACK_SIZE;
+ if (!low)
+ return false;
+
if (sp < low || sp >= high)
return false;
unsigned long low = (unsigned long)raw_cpu_read(sdei_stack_critical_ptr);
unsigned long high = low + SDEI_STACK_SIZE;
+ if (!low)
+ return false;
+
if (sp < low || sp >= high)
return false;
num_standard_resources = memblock.memory.cnt;
res_size = num_standard_resources * sizeof(*standard_resources);
- standard_resources = memblock_alloc_low(res_size, SMP_CACHE_BYTES);
+ standard_resources = memblock_alloc(res_size, SMP_CACHE_BYTES);
if (!standard_resources)
panic("%s: Failed to allocate %zu bytes\n", __func__, res_size);
void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
{
struct stackframe frame;
- int skip;
+ int skip = 0;
pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk);
+ if (regs) {
+ if (user_mode(regs))
+ return;
+ skip = 1;
+ }
+
if (!tsk)
tsk = current;
frame.graph = 0;
#endif
- skip = !!regs;
printk("Call trace:\n");
do {
/* skip until specified stack frame */
return ret;
print_modules();
- __show_regs(regs);
pr_emerg("Process %.*s (pid: %d, stack limit = 0x%p)\n",
TASK_COMM_LEN, tsk->comm, task_pid_nr(tsk),
end_of_stack(tsk));
+ show_regs(regs);
- if (!user_mode(regs)) {
- dump_backtrace(regs, tsk);
+ if (!user_mode(regs))
dump_instr(KERN_EMERG, regs);
- }
return ret;
}
int ret = -EINVAL;
bool loaded;
+ /* Reset PMU outside of the non-preemptible section */
+ kvm_pmu_vcpu_reset(vcpu);
+
preempt_disable();
loaded = (vcpu->cpu != -1);
if (loaded)
vcpu->arch.reset_state.reset = false;
}
- /* Reset PMU */
- kvm_pmu_vcpu_reset(vcpu);
-
/* Default workaround setup is enabled (if supported) */
if (kvm_arm_have_ssbd() == KVM_SSBD_KERNEL)
vcpu->arch.workaround_flags |= VCPU_WORKAROUND_2_FLAG;
generic-y += kdebug.h
generic-y += kmap_types.h
generic-y += kprobes.h
+generic-y += kvm_para.h
generic-y += local.h
generic-y += mcs_spinlock.h
generic-y += mm-arch-hooks.h
}
static inline void syscall_get_arguments(struct task_struct *task,
- struct pt_regs *regs, unsigned int i,
- unsigned int n, unsigned long *args)
+ struct pt_regs *regs,
+ unsigned long *args)
{
- switch (i) {
- case 0:
- if (!n--)
- break;
- *args++ = regs->a4;
- case 1:
- if (!n--)
- break;
- *args++ = regs->b4;
- case 2:
- if (!n--)
- break;
- *args++ = regs->a6;
- case 3:
- if (!n--)
- break;
- *args++ = regs->b6;
- case 4:
- if (!n--)
- break;
- *args++ = regs->a8;
- case 5:
- if (!n--)
- break;
- *args++ = regs->b8;
- case 6:
- if (!n--)
- break;
- default:
- BUG();
- }
+ *args++ = regs->a4;
+ *args++ = regs->b4;
+ *args++ = regs->a6;
+ *args++ = regs->b6;
+ *args++ = regs->a8;
+ *args = regs->b8;
}
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
- switch (i) {
- case 0:
- if (!n--)
- break;
- regs->a4 = *args++;
- case 1:
- if (!n--)
- break;
- regs->b4 = *args++;
- case 2:
- if (!n--)
- break;
- regs->a6 = *args++;
- case 3:
- if (!n--)
- break;
- regs->b6 = *args++;
- case 4:
- if (!n--)
- break;
- regs->a8 = *args++;
- case 5:
- if (!n--)
- break;
- regs->a9 = *args++;
- case 6:
- if (!n)
- break;
- default:
- BUG();
- }
+ regs->a4 = *args++;
+ regs->b4 = *args++;
+ regs->a6 = *args++;
+ regs->b6 = *args++;
+ regs->a8 = *args++;
+ regs->a9 = *args;
}
#endif /* __ASM_C6X_SYSCALLS_H */
-generic-y += kvm_para.h
generic-y += ucontext.h
static inline void
syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
- unsigned int i, unsigned int n, unsigned long *args)
+ unsigned long *args)
{
- BUG_ON(i + n > 6);
- if (i == 0) {
- args[0] = regs->orig_a0;
- args++;
- i++;
- n--;
- }
- memcpy(args, ®s->a1 + i * sizeof(regs->a1), n * sizeof(args[0]));
+ args[0] = regs->orig_a0;
+ args++;
+ memcpy(args, ®s->a1, 5 * sizeof(args[0]));
}
static inline void
syscall_set_arguments(struct task_struct *task, struct pt_regs *regs,
- unsigned int i, unsigned int n, const unsigned long *args)
+ const unsigned long *args)
{
- BUG_ON(i + n > 6);
- if (i == 0) {
- regs->orig_a0 = args[0];
- args++;
- i++;
- n--;
- }
- memcpy(®s->a1 + i * sizeof(regs->a1), args, n * sizeof(regs->a0));
+ regs->orig_a0 = args[0];
+ args++;
+ memcpy(®s->a1, args, 5 * sizeof(regs->a1));
}
static inline int
generic-y += kdebug.h
generic-y += kmap_types.h
generic-y += kprobes.h
+generic-y += kvm_para.h
generic-y += linkage.h
generic-y += local.h
generic-y += local64.h
static inline void
syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
- unsigned int i, unsigned int n, unsigned long *args)
+ unsigned long *args)
{
- BUG_ON(i + n > 6);
-
- while (n > 0) {
- switch (i) {
- case 0:
- *args++ = regs->er1;
- break;
- case 1:
- *args++ = regs->er2;
- break;
- case 2:
- *args++ = regs->er3;
- break;
- case 3:
- *args++ = regs->er4;
- break;
- case 4:
- *args++ = regs->er5;
- break;
- case 5:
- *args++ = regs->er6;
- break;
- }
- i++;
- n--;
- }
+ *args++ = regs->er1;
+ *args++ = regs->er2;
+ *args++ = regs->er3;
+ *args++ = regs->er4;
+ *args++ = regs->er5;
+ *args = regs->er6;
}
-generic-y += kvm_para.h
generic-y += ucontext.h
generic-y += kdebug.h
generic-y += kmap_types.h
generic-y += kprobes.h
+generic-y += kvm_para.h
generic-y += local.h
generic-y += local64.h
generic-y += mcs_spinlock.h
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
- BUG_ON(i + n > 6);
- memcpy(args, &(®s->r00)[i], n * sizeof(args[0]));
+ memcpy(args, &(®s->r00)[0], 6 * sizeof(args[0]));
}
#endif
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#include <asm-generic/kvm_para.h>
generic-y += compat.h
generic-y += exec.h
generic-y += irq_work.h
+generic-y += kvm_para.h
generic-y += mcs_spinlock.h
generic-y += mm-arch-hooks.h
generic-y += preempt.h
}
extern void ia64_syscall_get_set_arguments(struct task_struct *task,
- struct pt_regs *regs, unsigned int i, unsigned int n,
- unsigned long *args, int rw);
+ struct pt_regs *regs, unsigned long *args, int rw);
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
- BUG_ON(i + n > 6);
-
- ia64_syscall_get_set_arguments(task, regs, i, n, args, 0);
+ ia64_syscall_get_set_arguments(task, regs, args, 0);
}
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
- BUG_ON(i + n > 6);
-
- ia64_syscall_get_set_arguments(task, regs, i, n, args, 1);
+ ia64_syscall_get_set_arguments(task, regs, args, 1);
}
static inline int syscall_get_arch(void)
generated-y += unistd_64.h
-generic-y += kvm_para.h
}
void ia64_syscall_get_set_arguments(struct task_struct *task,
- struct pt_regs *regs, unsigned int i, unsigned int n,
- unsigned long *args, int rw)
+ struct pt_regs *regs, unsigned long *args, int rw)
{
struct syscall_get_set_args data = {
- .i = i,
- .n = n,
+ .i = 0,
+ .n = 6,
.args = args,
.regs = regs,
.rw = rw,
generic-y += kdebug.h
generic-y += kmap_types.h
generic-y += kprobes.h
+generic-y += kvm_para.h
generic-y += local.h
generic-y += local64.h
generic-y += mcs_spinlock.h
generated-y += unistd_32.h
-generic-y += kvm_para.h
generic-y += kdebug.h
generic-y += kmap_types.h
generic-y += kprobes.h
+generic-y += kvm_para.h
generic-y += linkage.h
generic-y += local.h
generic-y += local64.h
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
+ unsigned int i = 0;
+ unsigned int n = 6;
+
while (n--)
*args++ = microblaze_get_syscall_arg(regs, i++);
}
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
+ unsigned int i = 0;
+ unsigned int n = 6;
+
while (n--)
microblaze_set_syscall_arg(regs, i++, *args++);
}
generated-y += unistd_32.h
-generic-y += kvm_para.h
generic-y += ucontext.h
# require CONFIG_CPU_MIPS32_R2=y
CONFIG_LEGACY_BOARD_OCELOT=y
+CONFIG_FIT_IMAGE_FDT_OCELOT=y
+
+CONFIG_BRIDGE=y
+CONFIG_GENERIC_PHY=y
CONFIG_MTD=y
CONFIG_MTD_CMDLINE_PARTS=y
CONFIG_SERIAL_OF_PLATFORM=y
CONFIG_NETDEVICES=y
+CONFIG_NET_SWITCHDEV=y
+CONFIG_NET_DSA=y
CONFIG_MSCC_OCELOT_SWITCH=y
CONFIG_MSCC_OCELOT_SWITCH_OCELOT=y
CONFIG_MDIO_MSCC_MIIM=y
CONFIG_SPI_DW_MMIO=y
CONFIG_SPI_SPIDEV=y
+CONFIG_PINCTRL_OCELOT=y
+
CONFIG_GPIO_SYSFS=y
CONFIG_POWER_RESET=y
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
+ unsigned int i = 0;
+ unsigned int n = 6;
int ret;
/* O32 ABI syscall() */
#include <asm/processor.h>
#include <asm/sigcontext.h>
#include <linux/uaccess.h>
+#include <asm/irq_regs.h>
static struct hard_trap_info {
unsigned char tt; /* Trap type code for MIPS R3xxx and R4xxx */
old_fs = get_fs();
set_fs(KERNEL_DS);
- kgdb_nmicallback(raw_smp_processor_id(), NULL);
+ kgdb_nmicallback(raw_smp_processor_id(), get_irq_regs());
set_fs(old_fs);
}
sd.nr = syscall;
sd.arch = syscall_get_arch();
- syscall_get_arguments(current, regs, 0, 6, args);
+ syscall_get_arguments(current, regs, args);
for (i = 0; i < 6; i++)
sd.args[i] = args[i];
sd.instruction_pointer = KSTK_EIP(current);
{
struct hub_irq_data *hd = irq_data_get_irq_chip_data(d);
struct bridge_controller *bc;
- int pin = hd->pin;
if (!hd)
return;
disable_hub_irq(d);
bc = hd->bc;
- bridge_clr(bc, b_int_enable, (1 << pin));
+ bridge_clr(bc, b_int_enable, (1 << hd->pin));
bridge_read(bc, b_wid_tflush);
}
* syscall_get_arguments - extract system call parameter values
* @task: task of interest, must be blocked
* @regs: task_pt_regs() of @task
- * @i: argument index [0,5]
- * @n: number of arguments; n+i must be [1,6].
* @args: array filled with argument values
*
- * Fetches @n arguments to the system call starting with the @i'th argument
- * (from 0 through 5). Argument @i is stored in @args[0], and so on.
- * An arch inline version is probably optimal when @i and @n are constants.
+ * Fetches 6 arguments to the system call (from 0 through 5). The first
+ * argument is stored in @args[0], and so on.
*
* It's only valid to call this when @task is stopped for tracing on
* entry to a system call, due to %TIF_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
- * It's invalid to call this with @i + @n > 6; we only support system calls
- * taking up to 6 arguments.
*/
#define SYSCALL_MAX_ARGS 6
void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
- unsigned int i, unsigned int n, unsigned long *args)
+ unsigned long *args)
{
- if (n == 0)
- return;
- if (i + n > SYSCALL_MAX_ARGS) {
- unsigned long *args_bad = args + SYSCALL_MAX_ARGS - i;
- unsigned int n_bad = n + i - SYSCALL_MAX_ARGS;
- pr_warning("%s called with max args %d, handling only %d\n",
- __func__, i + n, SYSCALL_MAX_ARGS);
- memset(args_bad, 0, n_bad * sizeof(args[0]));
- memset(args_bad, 0, n_bad * sizeof(args[0]));
- }
-
- if (i == 0) {
- args[0] = regs->orig_r0;
- args++;
- i++;
- n--;
- }
-
- memcpy(args, ®s->uregs[0] + i, n * sizeof(args[0]));
+ args[0] = regs->orig_r0;
+ args++;
+ memcpy(args, ®s->uregs[0] + 1, 5 * sizeof(args[0]));
}
/**
* syscall_set_arguments - change system call parameter value
* @task: task of interest, must be in system call entry tracing
* @regs: task_pt_regs() of @task
- * @i: argument index [0,5]
- * @n: number of arguments; n+i must be [1,6].
* @args: array of argument values to store
*
- * Changes @n arguments to the system call starting with the @i'th argument.
- * Argument @i gets value @args[0], and so on.
- * An arch inline version is probably optimal when @i and @n are constants.
+ * Changes 6 arguments to the system call. The first argument gets value
+ * @args[0], and so on.
*
* It's only valid to call this when @task is stopped for tracing on
* entry to a system call, due to %TIF_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
- * It's invalid to call this with @i + @n > 6; we only support system calls
- * taking up to 6 arguments.
*/
void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
- if (n == 0)
- return;
-
- if (i + n > SYSCALL_MAX_ARGS) {
- pr_warn("%s called with max args %d, handling only %d\n",
- __func__, i + n, SYSCALL_MAX_ARGS);
- n = SYSCALL_MAX_ARGS - i;
- }
-
- if (i == 0) {
- regs->orig_r0 = args[0];
- args++;
- i++;
- n--;
- }
+ regs->orig_r0 = args[0];
+ args++;
- memcpy(®s->uregs[0] + i, args, n * sizeof(args[0]));
+ memcpy(®s->uregs[0] + 1, args, 5 * sizeof(args[0]));
}
#endif /* _ASM_NDS32_SYSCALL_H */
generic-y += kdebug.h
generic-y += kmap_types.h
generic-y += kprobes.h
+generic-y += kvm_para.h
generic-y += local.h
generic-y += mcs_spinlock.h
generic-y += mm-arch-hooks.h
}
static inline void syscall_get_arguments(struct task_struct *task,
- struct pt_regs *regs, unsigned int i, unsigned int n,
- unsigned long *args)
+ struct pt_regs *regs, unsigned long *args)
{
- BUG_ON(i + n > 6);
-
- switch (i) {
- case 0:
- if (!n--)
- break;
- *args++ = regs->r4;
- case 1:
- if (!n--)
- break;
- *args++ = regs->r5;
- case 2:
- if (!n--)
- break;
- *args++ = regs->r6;
- case 3:
- if (!n--)
- break;
- *args++ = regs->r7;
- case 4:
- if (!n--)
- break;
- *args++ = regs->r8;
- case 5:
- if (!n--)
- break;
- *args++ = regs->r9;
- case 6:
- if (!n--)
- break;
- default:
- BUG();
- }
+ *args++ = regs->r4;
+ *args++ = regs->r5;
+ *args++ = regs->r6;
+ *args++ = regs->r7;
+ *args++ = regs->r8;
+ *args = regs->r9;
}
static inline void syscall_set_arguments(struct task_struct *task,
- struct pt_regs *regs, unsigned int i, unsigned int n,
- const unsigned long *args)
+ struct pt_regs *regs, const unsigned long *args)
{
- BUG_ON(i + n > 6);
-
- switch (i) {
- case 0:
- if (!n--)
- break;
- regs->r4 = *args++;
- case 1:
- if (!n--)
- break;
- regs->r5 = *args++;
- case 2:
- if (!n--)
- break;
- regs->r6 = *args++;
- case 3:
- if (!n--)
- break;
- regs->r7 = *args++;
- case 4:
- if (!n--)
- break;
- regs->r8 = *args++;
- case 5:
- if (!n--)
- break;
- regs->r9 = *args++;
- case 6:
- if (!n)
- break;
- default:
- BUG();
- }
+ regs->r4 = *args++;
+ regs->r5 = *args++;
+ regs->r6 = *args++;
+ regs->r7 = *args++;
+ regs->r8 = *args++;
+ regs->r9 = *args;
}
#endif
-generic-y += kvm_para.h
generic-y += ucontext.h
generic-y += kdebug.h
generic-y += kmap_types.h
generic-y += kprobes.h
+generic-y += kvm_para.h
generic-y += local.h
generic-y += mcs_spinlock.h
generic-y += mm-arch-hooks.h
static inline void
syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
- unsigned int i, unsigned int n, unsigned long *args)
+ unsigned long *args)
{
- BUG_ON(i + n > 6);
-
- memcpy(args, ®s->gpr[3 + i], n * sizeof(args[0]));
+ memcpy(args, ®s->gpr[3], 6 * sizeof(args[0]));
}
static inline void
syscall_set_arguments(struct task_struct *task, struct pt_regs *regs,
- unsigned int i, unsigned int n, const unsigned long *args)
+ const unsigned long *args)
{
- BUG_ON(i + n > 6);
-
- memcpy(®s->gpr[3 + i], args, n * sizeof(args[0]));
+ memcpy(®s->gpr[3], args, 6 * sizeof(args[0]));
}
static inline int syscall_get_arch(void)
-generic-y += kvm_para.h
generic-y += ucontext.h
generic-y += irq_work.h
generic-y += kdebug.h
generic-y += kprobes.h
+generic-y += kvm_para.h
generic-y += local.h
generic-y += local64.h
generic-y += mcs_spinlock.h
static inline unsigned long regs_return_value(struct pt_regs *regs)
{
- return regs->gr[20];
+ return regs->gr[28];
}
static inline void instruction_pointer_set(struct pt_regs *regs,
unsigned long val)
{
- regs->iaoq[0] = val;
+ regs->iaoq[0] = val;
+ regs->iaoq[1] = val + 4;
}
/* Query offset/name of register from its name/offset */
}
static inline void syscall_get_arguments(struct task_struct *tsk,
- struct pt_regs *regs, unsigned int i,
- unsigned int n, unsigned long *args)
+ struct pt_regs *regs,
+ unsigned long *args)
{
- BUG_ON(i);
-
- switch (n) {
- case 6:
- args[5] = regs->gr[21];
- case 5:
- args[4] = regs->gr[22];
- case 4:
- args[3] = regs->gr[23];
- case 3:
- args[2] = regs->gr[24];
- case 2:
- args[1] = regs->gr[25];
- case 1:
- args[0] = regs->gr[26];
- case 0:
- break;
- default:
- BUG();
- }
+ args[5] = regs->gr[21];
+ args[4] = regs->gr[22];
+ args[3] = regs->gr[23];
+ args[2] = regs->gr[24];
+ args[1] = regs->gr[25];
+ args[0] = regs->gr[26];
}
static inline long syscall_get_return_value(struct task_struct *task,
generated-y += unistd_32.h
generated-y += unistd_64.h
-generic-y += kvm_para.h
static int __init parisc_idle_init(void)
{
- const char *marker;
-
- /* check QEMU/SeaBIOS marker in PAGE0 */
- marker = (char *) &PAGE0->pad0;
- running_on_qemu = (memcmp(marker, "SeaBIOS", 8) == 0);
-
if (!running_on_qemu)
cpu_idle_poll_ctrl(1);
int ret, cpunum;
struct pdc_coproc_cfg coproc_cfg;
+ /* check QEMU/SeaBIOS marker in PAGE0 */
+ running_on_qemu = (memcmp(&PAGE0->pad0, "SeaBIOS", 8) == 0);
+
cpunum = smp_processor_id();
init_cpu_topology();
#if defined(CONFIG_SPARSEMEM_VMEMMAP) && defined(CONFIG_SPARSEMEM_EXTREME) && \
defined (CONFIG_PPC_64K_PAGES)
#define MAX_PHYSMEM_BITS 51
-#elif defined(CONFIG_SPARSEMEM)
+#elif defined(CONFIG_PPC64)
#define MAX_PHYSMEM_BITS 46
#endif
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
unsigned long val, mask = -1UL;
-
- BUG_ON(i + n > 6);
+ unsigned int n = 6;
#ifdef CONFIG_COMPAT
if (test_tsk_thread_flag(task, TIF_32BIT))
mask = 0xffffffff;
#endif
while (n--) {
- if (n == 0 && i == 0)
+ if (n == 0)
val = regs->orig_gpr3;
else
- val = regs->gpr[3 + i + n];
+ val = regs->gpr[3 + n];
args[n] = val & mask;
}
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
- BUG_ON(i + n > 6);
- memcpy(®s->gpr[3 + i], args, n * sizeof(args[0]));
+ memcpy(®s->gpr[3], args, 6 * sizeof(args[0]));
/* Also copy the first argument into orig_gpr3 */
- if (i == 0 && n > 0)
- regs->orig_gpr3 = args[0];
+ regs->orig_gpr3 = args[0];
}
static inline int syscall_get_arch(void)
ld r4,PACA_EXSLB+EX_DAR(r13)
std r4,_DAR(r1)
addi r3,r1,STACK_FRAME_OVERHEAD
+BEGIN_MMU_FTR_SECTION
+ /* HPT case, do SLB fault */
bl do_slb_fault
cmpdi r3,0
bne- 1f
b fast_exception_return
1: /* Error case */
+MMU_FTR_SECTION_ELSE
+ /* Radix case, access is outside page table range */
+ li r3,-EFAULT
+ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
std r3,RESULT(r1)
bl save_nvgprs
RECONCILE_IRQ_STATE(r10, r11)
EXCEPTION_PROLOG_COMMON(0x480, PACA_EXSLB)
ld r4,_NIP(r1)
addi r3,r1,STACK_FRAME_OVERHEAD
+BEGIN_MMU_FTR_SECTION
+ /* HPT case, do SLB fault */
bl do_slb_fault
cmpdi r3,0
bne- 1f
b fast_exception_return
1: /* Error case */
+MMU_FTR_SECTION_ELSE
+ /* Radix case, access is outside page table range */
+ li r3,-EFAULT
+ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
std r3,RESULT(r1)
bl save_nvgprs
RECONCILE_IRQ_STATE(r10, r11)
tophys(r4,r2)
addi r4,r4,THREAD /* phys address of our thread_struct */
mtspr SPRN_SPRG_THREAD,r4
-#ifdef CONFIG_PPC_RTAS
- li r3,0
- stw r3, RTAS_SP(r4) /* 0 => not in RTAS */
-#endif
lis r4, (swapper_pg_dir - PAGE_OFFSET)@h
ori r4, r4, (swapper_pg_dir - PAGE_OFFSET)@l
mtspr SPRN_SPRG_PGDIR, r4
tophys(r4,r2)
addi r4,r4,THREAD /* init task's THREAD */
mtspr SPRN_SPRG_THREAD,r4
-#ifdef CONFIG_PPC_RTAS
- li r3,0
- stw r3, RTAS_SP(r4) /* 0 => not in RTAS */
-#endif
lis r4, (swapper_pg_dir - PAGE_OFFSET)@h
ori r4, r4, (swapper_pg_dir - PAGE_OFFSET)@l
mtspr SPRN_SPRG_PGDIR, r4
#include <linux/kvm_host.h>
#include <linux/init.h>
#include <linux/export.h>
+#include <linux/kmemleak.h>
#include <linux/kvm_para.h>
#include <linux/slab.h>
#include <linux/of.h>
static __init void kvm_free_tmp(void)
{
+ /*
+ * Inform kmemleak about the hole in the .bss section since the
+ * corresponding pages will be unmapped with DEBUG_PAGEALLOC=y.
+ */
+ kmemleak_free_part(&kvm_tmp[kvm_tmp_index],
+ ARRAY_SIZE(kvm_tmp) - kvm_tmp_index);
free_reserved_area(&kvm_tmp[kvm_tmp_index],
&kvm_tmp[ARRAY_SIZE(kvm_tmp)], -1, NULL);
}
* can be used, r7 contains NSEC_PER_SEC.
*/
- lwz r5,WTOM_CLOCK_SEC(r9)
+ lwz r5,(WTOM_CLOCK_SEC+LOPART)(r9)
lwz r6,WTOM_CLOCK_NSEC(r9)
/* We now have our offset in r5,r6. We create a fake dependency
beq .Lzero
.Lcmp_rest_lt8bytes:
- /* Here we have only less than 8 bytes to compare with. at least s1
- * Address is aligned with 8 bytes.
- * The next double words are load and shift right with appropriate
- * bits.
+ /*
+ * Here we have less than 8 bytes to compare. At least s1 is aligned to
+ * 8 bytes, but s2 may not be. We must make sure s2 + 7 doesn't cross a
+ * page boundary, otherwise we might read past the end of the buffer and
+ * trigger a page fault. We use 4K as the conservative minimum page
+ * size. If we detect that case we go to the byte-by-byte loop.
+ *
+ * Otherwise the next double word is loaded from s1 and s2, and shifted
+ * right to compare the appropriate bits.
*/
+ clrldi r6,r4,(64-12) // r6 = r4 & 0xfff
+ cmpdi r6,0xff8
+ bgt .Lshort
+
subfic r6,r5,8
slwi r6,r6,3
LD rA,0,r3
ret = drc.drc_index_start + (thread_index * drc.sequential_inc);
} else {
- const __be32 *indexes;
-
- indexes = of_get_property(dn, "ibm,drc-indexes", NULL);
- if (indexes == NULL)
- goto err_of_node_put;
+ u32 nr_drc_indexes, thread_drc_index;
/*
- * The first element indexes[0] is the number of drc_indexes
- * returned in the list. Hence thread_index+1 will get the
- * drc_index corresponding to core number thread_index.
+ * The first element of ibm,drc-indexes array is the
+ * number of drc_indexes returned in the list. Hence
+ * thread_index+1 will get the drc_index corresponding
+ * to core number thread_index.
*/
- ret = indexes[thread_index + 1];
+ rc = of_property_read_u32_index(dn, "ibm,drc-indexes",
+ 0, &nr_drc_indexes);
+ if (rc)
+ goto err_of_node_put;
+
+ WARN_ON_ONCE(thread_index > nr_drc_indexes);
+ rc = of_property_read_u32_index(dn, "ibm,drc-indexes",
+ thread_index + 1,
+ &thread_drc_index);
+ if (rc)
+ goto err_of_node_put;
+
+ ret = thread_drc_index;
}
rc = 0;
"UE",
"SLB",
"ERAT",
+ "Unknown",
"TLB",
"D-Cache",
"Unknown",
--- /dev/null
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_CGROUPS=y
+CONFIG_CGROUP_SCHED=y
+CONFIG_CFS_BANDWIDTH=y
+CONFIG_CGROUP_BPF=y
+CONFIG_NAMESPACES=y
+CONFIG_USER_NS=y
+CONFIG_CHECKPOINT_RESTORE=y
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_EXPERT=y
+CONFIG_BPF_SYSCALL=y
+CONFIG_ARCH_RV32I=y
+CONFIG_SMP=y
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_IP_PNP_RARP=y
+CONFIG_NETLINK_DIAG=y
+CONFIG_PCI=y
+CONFIG_PCIEPORTBUS=y
+CONFIG_PCI_HOST_GENERIC=y
+CONFIG_PCIE_XILINX=y
+CONFIG_DEVTMPFS=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_VIRTIO_BLK=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_BLK_DEV_SR=y
+CONFIG_ATA=y
+CONFIG_SATA_AHCI=y
+CONFIG_SATA_AHCI_PLATFORM=y
+CONFIG_NETDEVICES=y
+CONFIG_VIRTIO_NET=y
+CONFIG_MACB=y
+CONFIG_E1000E=y
+CONFIG_R8169=y
+CONFIG_MICROSEMI_PHY=y
+CONFIG_INPUT_MOUSEDEV=y
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_OF_PLATFORM=y
+CONFIG_SERIAL_EARLYCON_RISCV_SBI=y
+CONFIG_HVC_RISCV_SBI=y
+# CONFIG_PTP_1588_CLOCK is not set
+CONFIG_DRM=y
+CONFIG_DRM_RADEON=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_USB=y
+CONFIG_USB_XHCI_HCD=y
+CONFIG_USB_XHCI_PLATFORM=y
+CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_EHCI_HCD_PLATFORM=y
+CONFIG_USB_OHCI_HCD=y
+CONFIG_USB_OHCI_HCD_PLATFORM=y
+CONFIG_USB_STORAGE=y
+CONFIG_USB_UAS=y
+CONFIG_VIRTIO_MMIO=y
+CONFIG_SIFIVE_PLIC=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_AUTOFS4_FS=y
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_TMPFS=y
+CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_NFS_FS=y
+CONFIG_NFS_V4=y
+CONFIG_NFS_V4_1=y
+CONFIG_NFS_V4_2=y
+CONFIG_ROOT_NFS=y
+CONFIG_CRYPTO_USER_API_HASH=y
+CONFIG_CRYPTO_DEV_VIRTIO=y
+CONFIG_PRINTK_TIME=y
+# CONFIG_RCU_TRACE is not set
};
#define FIXADDR_SIZE (__end_of_fixed_addresses * PAGE_SIZE)
-#define FIXADDR_TOP (PAGE_OFFSET)
+#define FIXADDR_TOP (VMALLOC_START)
#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE)
#define FIXMAP_PAGE_IO PAGE_KERNEL
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
- BUG_ON(i + n > 6);
- if (i == 0) {
- args[0] = regs->orig_a0;
- args++;
- i++;
- n--;
- }
- memcpy(args, ®s->a1 + i * sizeof(regs->a1), n * sizeof(args[0]));
+ args[0] = regs->orig_a0;
+ args++;
+ memcpy(args, ®s->a1, 5 * sizeof(args[0]));
}
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
- BUG_ON(i + n > 6);
- if (i == 0) {
- regs->orig_a0 = args[0];
- args++;
- i++;
- n--;
- }
- memcpy(®s->a1 + i * sizeof(regs->a1), args, n * sizeof(regs->a0));
+ regs->orig_a0 = args[0];
+ args++;
+ memcpy(®s->a1, args, 5 * sizeof(regs->a1));
}
static inline int syscall_get_arch(void)
" .balign 4\n" \
"4:\n" \
" li %0, %6\n" \
- " jump 2b, %1\n" \
+ " jump 3b, %1\n" \
" .previous\n" \
" .section __ex_table,\"a\"\n" \
" .balign " RISCV_SZPTR "\n" \
ifdef CONFIG_FTRACE
CFLAGS_REMOVE_ftrace.o = -pg
-CFLAGS_REMOVE_setup.o = -pg
endif
extra-y += head.o
obj-y += cacheinfo.o
obj-y += vdso/
-CFLAGS_setup.o := -mcmodel=medany
-
obj-$(CONFIG_FPU) += fpu.o
obj-$(CONFIG_SMP) += smpboot.o
obj-$(CONFIG_SMP) += smp.o
{
s32 hi20;
- if (IS_ENABLED(CMODEL_MEDLOW)) {
+ if (IS_ENABLED(CONFIG_CMODEL_MEDLOW)) {
pr_err(
"%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n",
me->name, (long long)v, location);
};
#endif
-unsigned long va_pa_offset;
-EXPORT_SYMBOL(va_pa_offset);
-unsigned long pfn_base;
-EXPORT_SYMBOL(pfn_base);
-
-unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss;
-EXPORT_SYMBOL(empty_zero_page);
-
/* The lucky hart to first increment this variable will boot the other cores */
atomic_t hart_lottery;
unsigned long boot_cpu_hartid;
+
+CFLAGS_init.o := -mcmodel=medany
+ifdef CONFIG_FTRACE
+CFLAGS_REMOVE_init.o = -pg
+endif
+
obj-y += init.o
obj-y += fault.o
obj-y += extable.o
#include <asm/pgtable.h>
#include <asm/io.h>
+unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]
+ __page_aligned_bss;
+EXPORT_SYMBOL(empty_zero_page);
+
static void __init zone_sizes_init(void)
{
unsigned long max_zone_pfns[MAX_NR_ZONES] = { 0, };
*/
memblock_reserve(reg->base, vmlinux_end - reg->base);
mem_size = min(reg->size, (phys_addr_t)-PAGE_OFFSET);
+
+ /*
+ * Remove memblock from the end of usable area to the
+ * end of region
+ */
+ if (reg->base + mem_size < end)
+ memblock_remove(reg->base + mem_size,
+ end - reg->base - mem_size);
}
}
BUG_ON(mem_size == 0);
}
}
+unsigned long va_pa_offset;
+EXPORT_SYMBOL(va_pa_offset);
+unsigned long pfn_base;
+EXPORT_SYMBOL(pfn_base);
+
pgd_t swapper_pg_dir[PTRS_PER_PGD] __page_aligned_bss;
pgd_t trampoline_pg_dir[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE);
}
}
+/*
+ * setup_vm() is called from head.S with MMU-off.
+ *
+ * Following requirements should be honoured for setup_vm() to work
+ * correctly:
+ * 1) It should use PC-relative addressing for accessing kernel symbols.
+ * To achieve this we always use GCC cmodel=medany.
+ * 2) The compiler instrumentation for FTRACE will not work for setup_vm()
+ * so disable compiler instrumentation when FTRACE is enabled.
+ *
+ * Currently, the above requirements are honoured by using custom CFLAGS
+ * for init.o in mm/Makefile.
+ */
+
+#ifndef __riscv_cmodel_medany
+#error "setup_vm() is called from head.S before relocate so it should "
+ "not use absolute addressing."
+#endif
+
asmlinkage void __init setup_vm(void)
{
extern char _start;
return reg1;
}
+/*
+ * Interface to tell the AP bus code that a configuration
+ * change has happened. The bus code should at least do
+ * an ap bus resource rescan.
+ */
+#if IS_ENABLED(CONFIG_ZCRYPT)
+void ap_bus_cfg_chg(void);
+#else
+static inline void ap_bus_cfg_chg(void){};
+#endif
+
#endif /* _ASM_S390_AP_H_ */
/*
* Cache aliasing on the latest machines calls for a mapping granularity
- * of 512KB. For 64-bit processes use a 512KB alignment and a randomization
- * of up to 1GB. For 31-bit processes the virtual address space is limited,
- * use no alignment and limit the randomization to 8MB.
+ * of 512KB for the anonymous mapping base. For 64-bit processes use a
+ * 512KB alignment and a randomization of up to 1GB. For 31-bit processes
+ * the virtual address space is limited, use no alignment and limit the
+ * randomization to 8MB.
+ * For the additional randomization of the program break use 32MB for
+ * 64-bit and 8MB for 31-bit.
*/
-#define BRK_RND_MASK (is_compat_task() ? 0x7ffUL : 0x3ffffUL)
+#define BRK_RND_MASK (is_compat_task() ? 0x7ffUL : 0x1fffUL)
#define MMAP_RND_MASK (is_compat_task() ? 0x7ffUL : 0x3ff80UL)
#define MMAP_ALIGN_MASK (is_compat_task() ? 0 : 0x7fUL)
#define STACK_RND_MASK MMAP_RND_MASK
__u64 hardirq_timer; /* 0x02e8 */
__u64 softirq_timer; /* 0x02f0 */
__u64 steal_timer; /* 0x02f8 */
- __u64 last_update_timer; /* 0x0300 */
- __u64 last_update_clock; /* 0x0308 */
- __u64 int_clock; /* 0x0310 */
- __u64 mcck_clock; /* 0x0318 */
- __u64 clock_comparator; /* 0x0320 */
- __u64 boot_clock[2]; /* 0x0328 */
+ __u64 avg_steal_timer; /* 0x0300 */
+ __u64 last_update_timer; /* 0x0308 */
+ __u64 last_update_clock; /* 0x0310 */
+ __u64 int_clock; /* 0x0318*/
+ __u64 mcck_clock; /* 0x0320 */
+ __u64 clock_comparator; /* 0x0328 */
+ __u64 boot_clock[2]; /* 0x0330 */
/* Current process. */
- __u64 current_task; /* 0x0338 */
- __u64 kernel_stack; /* 0x0340 */
+ __u64 current_task; /* 0x0340 */
+ __u64 kernel_stack; /* 0x0348 */
/* Interrupt, DAT-off and restartstack. */
- __u64 async_stack; /* 0x0348 */
- __u64 nodat_stack; /* 0x0350 */
- __u64 restart_stack; /* 0x0358 */
+ __u64 async_stack; /* 0x0350 */
+ __u64 nodat_stack; /* 0x0358 */
+ __u64 restart_stack; /* 0x0360 */
/* Restart function and parameter. */
- __u64 restart_fn; /* 0x0360 */
- __u64 restart_data; /* 0x0368 */
- __u64 restart_source; /* 0x0370 */
+ __u64 restart_fn; /* 0x0368 */
+ __u64 restart_data; /* 0x0370 */
+ __u64 restart_source; /* 0x0378 */
/* Address space pointer. */
- __u64 kernel_asce; /* 0x0378 */
- __u64 user_asce; /* 0x0380 */
- __u64 vdso_asce; /* 0x0388 */
+ __u64 kernel_asce; /* 0x0380 */
+ __u64 user_asce; /* 0x0388 */
+ __u64 vdso_asce; /* 0x0390 */
/*
* The lpp and current_pid fields form a
* 64-bit value that is set as program
* parameter with the LPP instruction.
*/
- __u32 lpp; /* 0x0390 */
- __u32 current_pid; /* 0x0394 */
+ __u32 lpp; /* 0x0398 */
+ __u32 current_pid; /* 0x039c */
/* SMP info area */
- __u32 cpu_nr; /* 0x0398 */
- __u32 softirq_pending; /* 0x039c */
- __u32 preempt_count; /* 0x03a0 */
- __u32 spinlock_lockval; /* 0x03a4 */
- __u32 spinlock_index; /* 0x03a8 */
- __u32 fpu_flags; /* 0x03ac */
- __u64 percpu_offset; /* 0x03b0 */
- __u64 vdso_per_cpu_data; /* 0x03b8 */
- __u64 machine_flags; /* 0x03c0 */
- __u64 gmap; /* 0x03c8 */
- __u8 pad_0x03d0[0x0400-0x03d0]; /* 0x03d0 */
+ __u32 cpu_nr; /* 0x03a0 */
+ __u32 softirq_pending; /* 0x03a4 */
+ __u32 preempt_count; /* 0x03a8 */
+ __u32 spinlock_lockval; /* 0x03ac */
+ __u32 spinlock_index; /* 0x03b0 */
+ __u32 fpu_flags; /* 0x03b4 */
+ __u64 percpu_offset; /* 0x03b8 */
+ __u64 vdso_per_cpu_data; /* 0x03c0 */
+ __u64 machine_flags; /* 0x03c8 */
+ __u64 gmap; /* 0x03d0 */
+ __u8 pad_0x03d8[0x0400-0x03d8]; /* 0x03d8 */
/* br %r1 trampoline */
__u16 br_r1_trampoline; /* 0x0400 */
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
unsigned long mask = -1UL;
+ unsigned int n = 6;
- /*
- * No arguments for this syscall, there's nothing to do.
- */
- if (!n)
- return;
-
- BUG_ON(i + n > 6);
#ifdef CONFIG_COMPAT
if (test_tsk_thread_flag(task, TIF_31BIT))
mask = 0xffffffff;
#endif
while (n-- > 0)
- if (i + n > 0)
- args[n] = regs->gprs[2 + i + n] & mask;
- if (i == 0)
- args[0] = regs->orig_gpr2 & mask;
+ if (n > 0)
+ args[n] = regs->gprs[2 + n] & mask;
+
+ args[0] = regs->orig_gpr2 & mask;
}
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
- BUG_ON(i + n > 6);
+ unsigned int n = 6;
+
while (n-- > 0)
- if (i + n > 0)
- regs->gprs[2 + i + n] = args[n];
- if (i == 0)
- regs->orig_gpr2 = args[0];
+ if (n > 0)
+ regs->gprs[2 + n] = args[n];
+ regs->orig_gpr2 = args[0];
}
static inline int syscall_get_arch(void)
*/
static int __hw_perf_event_init(struct perf_event *event)
{
- struct cpu_cf_events *cpuhw = this_cpu_ptr(&cpu_cf_events);
struct perf_event_attr *attr = &event->attr;
+ struct cpu_cf_events *cpuhw;
enum cpumf_ctr_set i;
int err = 0;
- debug_sprintf_event(cf_diag_dbg, 5,
- "%s event %p cpu %d authorized %#x\n", __func__,
- event, event->cpu, cpuhw->info.auth_ctl);
+ debug_sprintf_event(cf_diag_dbg, 5, "%s event %p cpu %d\n", __func__,
+ event, event->cpu);
event->hw.config = attr->config;
event->hw.config_base = 0;
- local64_set(&event->count, 0);
- /* Add all authorized counter sets to config_base */
+ /* Add all authorized counter sets to config_base. The
+ * the hardware init function is either called per-cpu or just once
+ * for all CPUS (event->cpu == -1). This depends on the whether
+ * counting is started for all CPUs or on a per workload base where
+ * the perf event moves from one CPU to another CPU.
+ * Checking the authorization on any CPU is fine as the hardware
+ * applies the same authorization settings to all CPUs.
+ */
+ cpuhw = &get_cpu_var(cpu_cf_events);
for (i = CPUMF_CTR_SET_BASIC; i < CPUMF_CTR_SET_MAX; ++i)
if (cpuhw->info.auth_ctl & cpumf_ctr_ctl[i])
event->hw.config_base |= cpumf_ctr_ctl[i];
+ put_cpu_var(cpu_cf_events);
/* No authorized counter sets, nothing to count/sample */
if (!event->hw.config_base) {
lc->percpu_offset = __per_cpu_offset[cpu];
lc->kernel_asce = S390_lowcore.kernel_asce;
lc->machine_flags = S390_lowcore.machine_flags;
- lc->user_timer = lc->system_timer = lc->steal_timer = 0;
+ lc->user_timer = lc->system_timer =
+ lc->steal_timer = lc->avg_steal_timer = 0;
__ctl_store(lc->cregs_save_area, 0, 15);
save_access_regs((unsigned int *) lc->access_regs_save_area);
memcpy(lc->stfle_fac_list, S390_lowcore.stfle_fac_list,
*/
static int do_account_vtime(struct task_struct *tsk)
{
- u64 timer, clock, user, guest, system, hardirq, softirq, steal;
+ u64 timer, clock, user, guest, system, hardirq, softirq;
timer = S390_lowcore.last_update_timer;
clock = S390_lowcore.last_update_clock;
if (softirq)
account_system_index_scaled(tsk, softirq, CPUTIME_SOFTIRQ);
- steal = S390_lowcore.steal_timer;
- if ((s64) steal > 0) {
- S390_lowcore.steal_timer = 0;
- account_steal_time(cputime_to_nsecs(steal));
- }
-
return virt_timer_forward(user + guest + system + hardirq + softirq);
}
*/
void vtime_flush(struct task_struct *tsk)
{
+ u64 steal, avg_steal;
+
if (do_account_vtime(tsk))
virt_timer_expire();
+
+ steal = S390_lowcore.steal_timer;
+ avg_steal = S390_lowcore.avg_steal_timer / 2;
+ if ((s64) steal > 0) {
+ S390_lowcore.steal_timer = 0;
+ account_steal_time(steal);
+ avg_steal += steal;
+ }
+ S390_lowcore.avg_steal_timer = avg_steal;
}
/*
struct sh_clk_ops;
-void __init arch_init_clk_ops(struct sh_clk_ops **ops, int idx)
+void __init __weak arch_init_clk_ops(struct sh_clk_ops **ops, int idx)
{
}
-void __init plat_irq_setup(void)
+void __init __weak plat_irq_setup(void)
{
}
generic-y += exec.h
generic-y += irq_regs.h
generic-y += irq_work.h
+generic-y += kvm_para.h
generic-y += local.h
generic-y += local64.h
generic-y += mcs_spinlock.h
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
- /*
- * Do this simply for now. If we need to start supporting
- * fetching arguments from arbitrary indices, this will need some
- * extra logic. Presently there are no in-tree users that depend
- * on this behaviour.
- */
- BUG_ON(i);
/* Argument pattern is: R4, R5, R6, R7, R0, R1 */
- switch (n) {
- case 6: args[5] = regs->regs[1];
- case 5: args[4] = regs->regs[0];
- case 4: args[3] = regs->regs[7];
- case 3: args[2] = regs->regs[6];
- case 2: args[1] = regs->regs[5];
- case 1: args[0] = regs->regs[4];
- case 0:
- break;
- default:
- BUG();
- }
+ args[5] = regs->regs[1];
+ args[4] = regs->regs[0];
+ args[3] = regs->regs[7];
+ args[2] = regs->regs[6];
+ args[1] = regs->regs[5];
+ args[0] = regs->regs[4];
}
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
- /* Same note as above applies */
- BUG_ON(i);
-
- switch (n) {
- case 6: regs->regs[1] = args[5];
- case 5: regs->regs[0] = args[4];
- case 4: regs->regs[7] = args[3];
- case 3: regs->regs[6] = args[2];
- case 2: regs->regs[5] = args[1];
- case 1: regs->regs[4] = args[0];
- break;
- default:
- BUG();
- }
+ regs->regs[1] = args[5];
+ regs->regs[0] = args[4];
+ regs->regs[7] = args[3];
+ regs->regs[6] = args[2];
+ regs->regs[5] = args[1];
+ regs->regs[4] = args[0];
}
static inline int syscall_get_arch(void)
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
- BUG_ON(i + n > 6);
- memcpy(args, ®s->regs[2 + i], n * sizeof(args[0]));
+ memcpy(args, ®s->regs[2], 6 * sizeof(args[0]));
}
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
- BUG_ON(i + n > 6);
- memcpy(®s->regs[2 + i], args, n * sizeof(args[0]));
+ memcpy(®s->regs[2], args, 6 * sizeof(args[0]));
}
static inline int syscall_get_arch(void)
# SPDX-License-Identifier: GPL-2.0
generated-y += unistd_32.h
-generic-y += kvm_para.h
generic-y += ucontext.h
generic-y += export.h
generic-y += irq_regs.h
generic-y += irq_work.h
+generic-y += kvm_para.h
generic-y += linkage.h
generic-y += local.h
generic-y += local64.h
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
int zero_extend = 0;
unsigned int j;
+ unsigned int n = 6;
#ifdef CONFIG_SPARC64
if (test_tsk_thread_flag(task, TIF_32BIT))
#endif
for (j = 0; j < n; j++) {
- unsigned long val = regs->u_regs[UREG_I0 + i + j];
+ unsigned long val = regs->u_regs[UREG_I0 + j];
if (zero_extend)
args[j] = (u32) val;
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
- unsigned int j;
+ unsigned int i;
- for (j = 0; j < n; j++)
- regs->u_regs[UREG_I0 + i + j] = args[j];
+ for (i = 0; i < 6; i++)
+ regs->u_regs[UREG_I0 + i] = args[i];
}
static inline int syscall_get_arch(void)
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#include <asm-generic/kvm_para.h>
p->npages = 0;
}
+static inline bool iommu_use_atu(struct iommu *iommu, u64 mask)
+{
+ return iommu->atu && mask > DMA_BIT_MASK(32);
+}
+
/* Interrupts must be disabled. */
static long iommu_batch_flush(struct iommu_batch *p, u64 mask)
{
prot &= (HV_PCI_MAP_ATTR_READ | HV_PCI_MAP_ATTR_WRITE);
while (npages != 0) {
- if (mask <= DMA_BIT_MASK(32) || !pbm->iommu->atu) {
+ if (!iommu_use_atu(pbm->iommu, mask)) {
num = pci_sun4v_iommu_map(devhandle,
HV_PCI_TSBID(0, entry),
npages,
unsigned long flags, order, first_page, npages, n;
unsigned long prot = 0;
struct iommu *iommu;
- struct atu *atu;
struct iommu_map_table *tbl;
struct page *page;
void *ret;
memset((char *)first_page, 0, PAGE_SIZE << order);
iommu = dev->archdata.iommu;
- atu = iommu->atu;
-
mask = dev->coherent_dma_mask;
- if (mask <= DMA_BIT_MASK(32) || !atu)
+ if (!iommu_use_atu(iommu, mask))
tbl = &iommu->tbl;
else
- tbl = &atu->tbl;
+ tbl = &iommu->atu->tbl;
entry = iommu_tbl_range_alloc(dev, tbl, npages, NULL,
(unsigned long)(-1), 0);
atu = iommu->atu;
devhandle = pbm->devhandle;
- if (dvma <= DMA_BIT_MASK(32)) {
+ if (!iommu_use_atu(iommu, dvma)) {
tbl = &iommu->tbl;
iotsb_num = 0; /* we don't care for legacy iommu */
} else {
npages >>= IO_PAGE_SHIFT;
mask = *dev->dma_mask;
- if (mask <= DMA_BIT_MASK(32))
+ if (!iommu_use_atu(iommu, mask))
tbl = &iommu->tbl;
else
tbl = &atu->tbl;
IO_PAGE_SIZE) >> IO_PAGE_SHIFT;
mask = *dev->dma_mask;
- if (mask <= DMA_BIT_MASK(32))
+ if (!iommu_use_atu(iommu, mask))
tbl = &iommu->tbl;
else
tbl = &atu->tbl;
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
const struct uml_pt_regs *r = ®s->regs;
- switch (i) {
- case 0:
- if (!n--)
- break;
- *args++ = UPT_SYSCALL_ARG1(r);
- case 1:
- if (!n--)
- break;
- *args++ = UPT_SYSCALL_ARG2(r);
- case 2:
- if (!n--)
- break;
- *args++ = UPT_SYSCALL_ARG3(r);
- case 3:
- if (!n--)
- break;
- *args++ = UPT_SYSCALL_ARG4(r);
- case 4:
- if (!n--)
- break;
- *args++ = UPT_SYSCALL_ARG5(r);
- case 5:
- if (!n--)
- break;
- *args++ = UPT_SYSCALL_ARG6(r);
- case 6:
- if (!n--)
- break;
- default:
- BUG();
- break;
- }
+ *args++ = UPT_SYSCALL_ARG1(r);
+ *args++ = UPT_SYSCALL_ARG2(r);
+ *args++ = UPT_SYSCALL_ARG3(r);
+ *args++ = UPT_SYSCALL_ARG4(r);
+ *args++ = UPT_SYSCALL_ARG5(r);
+ *args = UPT_SYSCALL_ARG6(r);
}
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
struct uml_pt_regs *r = ®s->regs;
- switch (i) {
- case 0:
- if (!n--)
- break;
- UPT_SYSCALL_ARG1(r) = *args++;
- case 1:
- if (!n--)
- break;
- UPT_SYSCALL_ARG2(r) = *args++;
- case 2:
- if (!n--)
- break;
- UPT_SYSCALL_ARG3(r) = *args++;
- case 3:
- if (!n--)
- break;
- UPT_SYSCALL_ARG4(r) = *args++;
- case 4:
- if (!n--)
- break;
- UPT_SYSCALL_ARG5(r) = *args++;
- case 5:
- if (!n--)
- break;
- UPT_SYSCALL_ARG6(r) = *args++;
- case 6:
- if (!n--)
- break;
- default:
- BUG();
- break;
- }
+ UPT_SYSCALL_ARG1(r) = *args++;
+ UPT_SYSCALL_ARG2(r) = *args++;
+ UPT_SYSCALL_ARG3(r) = *args++;
+ UPT_SYSCALL_ARG4(r) = *args++;
+ UPT_SYSCALL_ARG5(r) = *args++;
+ UPT_SYSCALL_ARG6(r) = *args;
}
/* See arch/x86/um/asm/syscall.h for syscall_get_arch() definition. */
generic-y += kdebug.h
generic-y += kmap_types.h
generic-y += kprobes.h
+generic-y += kvm_para.h
generic-y += local.h
generic-y += mcs_spinlock.h
generic-y += mm-arch-hooks.h
-generic-y += kvm_para.h
generic-y += ucontext.h
If unsure, leave at the default value.
config HOTPLUG_CPU
- bool "Support for hot-pluggable CPUs"
+ def_bool y
depends on SMP
- ---help---
- Say Y here to allow turning CPUs off and on. CPUs can be
- controlled through /sys/devices/system/cpu.
- ( Note: power management support will enable this option
- automatically on SMP systems. )
- Say N if you want to disable CPU hotplug.
config BOOTPARAM_HOTPLUG_CPU0
bool "Set default setting of cpu0_hotpluggable"
# Additionally, avoid generating expensive indirect jumps which
# are subject to retpolines for small number of switch cases.
# clang turns off jump table generation by default when under
- # retpoline builds, however, gcc does not for x86.
- KBUILD_CFLAGS += $(call cc-option,--param=case-values-threshold=20)
+ # retpoline builds, however, gcc does not for x86. This has
+ # only been fixed starting from gcc stable version 8.4.0 and
+ # onwards, but not for older ones. See gcc bug #86952.
+ ifndef CONFIG_CC_IS_CLANG
+ KBUILD_CFLAGS += $(call cc-option,-fno-jump-tables)
+ endif
endif
archscripts: scripts_basic
void set_sev_encryption_mask(void);
-#endif
-
/* acpi.c */
#ifdef CONFIG_ACPI
acpi_physical_address get_rsdp_addr(void);
#else
static inline int count_immovable_mem_regions(void) { return 0; }
#endif
+
+#endif /* BOOT_COMPRESSED_MISC_H */
#include <linux/types.h>
#include <linux/init.h>
#include <linux/slab.h>
+#include <linux/delay.h>
#include <asm/apicdef.h>
+#include <asm/nmi.h>
#include "../perf_event.h"
+static DEFINE_PER_CPU(unsigned int, perf_nmi_counter);
+
static __initconst const u64 amd_hw_cache_event_ids
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
}
}
+/*
+ * When a PMC counter overflows, an NMI is used to process the event and
+ * reset the counter. NMI latency can result in the counter being updated
+ * before the NMI can run, which can result in what appear to be spurious
+ * NMIs. This function is intended to wait for the NMI to run and reset
+ * the counter to avoid possible unhandled NMI messages.
+ */
+#define OVERFLOW_WAIT_COUNT 50
+
+static void amd_pmu_wait_on_overflow(int idx)
+{
+ unsigned int i;
+ u64 counter;
+
+ /*
+ * Wait for the counter to be reset if it has overflowed. This loop
+ * should exit very, very quickly, but just in case, don't wait
+ * forever...
+ */
+ for (i = 0; i < OVERFLOW_WAIT_COUNT; i++) {
+ rdmsrl(x86_pmu_event_addr(idx), counter);
+ if (counter & (1ULL << (x86_pmu.cntval_bits - 1)))
+ break;
+
+ /* Might be in IRQ context, so can't sleep */
+ udelay(1);
+ }
+}
+
+static void amd_pmu_disable_all(void)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ int idx;
+
+ x86_pmu_disable_all();
+
+ /*
+ * This shouldn't be called from NMI context, but add a safeguard here
+ * to return, since if we're in NMI context we can't wait for an NMI
+ * to reset an overflowed counter value.
+ */
+ if (in_nmi())
+ return;
+
+ /*
+ * Check each counter for overflow and wait for it to be reset by the
+ * NMI if it has overflowed. This relies on the fact that all active
+ * counters are always enabled when this function is caled and
+ * ARCH_PERFMON_EVENTSEL_INT is always set.
+ */
+ for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+ if (!test_bit(idx, cpuc->active_mask))
+ continue;
+
+ amd_pmu_wait_on_overflow(idx);
+ }
+}
+
+static void amd_pmu_disable_event(struct perf_event *event)
+{
+ x86_pmu_disable_event(event);
+
+ /*
+ * This can be called from NMI context (via x86_pmu_stop). The counter
+ * may have overflowed, but either way, we'll never see it get reset
+ * by the NMI if we're already in the NMI. And the NMI latency support
+ * below will take care of any pending NMI that might have been
+ * generated by the overflow.
+ */
+ if (in_nmi())
+ return;
+
+ amd_pmu_wait_on_overflow(event->hw.idx);
+}
+
+/*
+ * Because of NMI latency, if multiple PMC counters are active or other sources
+ * of NMIs are received, the perf NMI handler can handle one or more overflowed
+ * PMC counters outside of the NMI associated with the PMC overflow. If the NMI
+ * doesn't arrive at the LAPIC in time to become a pending NMI, then the kernel
+ * back-to-back NMI support won't be active. This PMC handler needs to take into
+ * account that this can occur, otherwise this could result in unknown NMI
+ * messages being issued. Examples of this is PMC overflow while in the NMI
+ * handler when multiple PMCs are active or PMC overflow while handling some
+ * other source of an NMI.
+ *
+ * Attempt to mitigate this by using the number of active PMCs to determine
+ * whether to return NMI_HANDLED if the perf NMI handler did not handle/reset
+ * any PMCs. The per-CPU perf_nmi_counter variable is set to a minimum of the
+ * number of active PMCs or 2. The value of 2 is used in case an NMI does not
+ * arrive at the LAPIC in time to be collapsed into an already pending NMI.
+ */
+static int amd_pmu_handle_irq(struct pt_regs *regs)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ int active, handled;
+
+ /*
+ * Obtain the active count before calling x86_pmu_handle_irq() since
+ * it is possible that x86_pmu_handle_irq() may make a counter
+ * inactive (through x86_pmu_stop).
+ */
+ active = __bitmap_weight(cpuc->active_mask, X86_PMC_IDX_MAX);
+
+ /* Process any counter overflows */
+ handled = x86_pmu_handle_irq(regs);
+
+ /*
+ * If a counter was handled, record the number of possible remaining
+ * NMIs that can occur.
+ */
+ if (handled) {
+ this_cpu_write(perf_nmi_counter,
+ min_t(unsigned int, 2, active));
+
+ return handled;
+ }
+
+ if (!this_cpu_read(perf_nmi_counter))
+ return NMI_DONE;
+
+ this_cpu_dec(perf_nmi_counter);
+
+ return NMI_HANDLED;
+}
+
static struct event_constraint *
amd_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
struct perf_event *event)
static __initconst const struct x86_pmu amd_pmu = {
.name = "AMD",
- .handle_irq = x86_pmu_handle_irq,
- .disable_all = x86_pmu_disable_all,
+ .handle_irq = amd_pmu_handle_irq,
+ .disable_all = amd_pmu_disable_all,
.enable_all = x86_pmu_enable_all,
.enable = x86_pmu_enable_event,
- .disable = x86_pmu_disable_event,
+ .disable = amd_pmu_disable_event,
.hw_config = amd_pmu_hw_config,
.schedule_events = x86_schedule_events,
.eventsel = MSR_K7_EVNTSEL0,
cpuc->perf_ctr_virt_mask = 0;
/* Reload all events */
- x86_pmu_disable_all();
+ amd_pmu_disable_all();
x86_pmu_enable_all(0);
}
EXPORT_SYMBOL_GPL(amd_pmu_enable_virt);
cpuc->perf_ctr_virt_mask = AMD64_EVENTSEL_HOSTONLY;
/* Reload all events */
- x86_pmu_disable_all();
+ amd_pmu_disable_all();
x86_pmu_enable_all(0);
}
EXPORT_SYMBOL_GPL(amd_pmu_disable_virt);
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct hw_perf_event *hwc = &event->hw;
- if (__test_and_clear_bit(hwc->idx, cpuc->active_mask)) {
+ if (test_bit(hwc->idx, cpuc->active_mask)) {
x86_pmu.disable(event);
+ __clear_bit(hwc->idx, cpuc->active_mask);
cpuc->events[hwc->idx] = NULL;
WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
hwc->state |= PERF_HES_STOPPED;
apic_write(APIC_LVTPC, APIC_DM_NMI);
for (idx = 0; idx < x86_pmu.num_counters; idx++) {
- if (!test_bit(idx, cpuc->active_mask)) {
- /*
- * Though we deactivated the counter some cpus
- * might still deliver spurious interrupts still
- * in flight. Catch them:
- */
- if (__test_and_clear_bit(idx, cpuc->running))
- handled++;
+ if (!test_bit(idx, cpuc->active_mask))
continue;
- }
event = cpuc->events[idx];
return ret;
if (event->attr.precise_ip) {
- if (!event->attr.freq) {
+ if (!(event->attr.freq || event->attr.wakeup_events)) {
event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD;
if (!(event->attr.sample_type &
~intel_pmu_large_pebs_flags(event)))
cpuc->lbr_sel = NULL;
+ if (x86_pmu.flags & PMU_FL_TFA) {
+ WARN_ON_ONCE(cpuc->tfa_shadow);
+ cpuc->tfa_shadow = ~0ULL;
+ intel_set_tfa(cpuc, false);
+ }
+
if (x86_pmu.version > 1)
flip_smm_bit(&x86_pmu.attr_freeze_on_smi);
* bit 0 is the LSB of addr; bit 32 is the LSB of (addr+1).
*/
-#define BITOP_ADDR(x) "+m" (*(volatile long *) (x))
+#define RLONG_ADDR(x) "m" (*(volatile long *) (x))
+#define WBYTE_ADDR(x) "+m" (*(volatile char *) (x))
-#define ADDR BITOP_ADDR(addr)
+#define ADDR RLONG_ADDR(addr)
/*
* We do the locked ops that don't return the old value as
* a mask operation on a byte.
*/
#define IS_IMMEDIATE(nr) (__builtin_constant_p(nr))
-#define CONST_MASK_ADDR(nr, addr) BITOP_ADDR((void *)(addr) + ((nr)>>3))
+#define CONST_MASK_ADDR(nr, addr) WBYTE_ADDR((void *)(addr) + ((nr)>>3))
#define CONST_MASK(nr) (1 << ((nr) & 7))
/**
: "memory");
} else {
asm volatile(LOCK_PREFIX __ASM_SIZE(bts) " %1,%0"
- : BITOP_ADDR(addr) : "Ir" (nr) : "memory");
+ : : RLONG_ADDR(addr), "Ir" (nr) : "memory");
}
}
*/
static __always_inline void __set_bit(long nr, volatile unsigned long *addr)
{
- asm volatile(__ASM_SIZE(bts) " %1,%0" : ADDR : "Ir" (nr) : "memory");
+ asm volatile(__ASM_SIZE(bts) " %1,%0" : : ADDR, "Ir" (nr) : "memory");
}
/**
: "iq" ((u8)~CONST_MASK(nr)));
} else {
asm volatile(LOCK_PREFIX __ASM_SIZE(btr) " %1,%0"
- : BITOP_ADDR(addr)
- : "Ir" (nr));
+ : : RLONG_ADDR(addr), "Ir" (nr) : "memory");
}
}
static __always_inline void __clear_bit(long nr, volatile unsigned long *addr)
{
- asm volatile(__ASM_SIZE(btr) " %1,%0" : ADDR : "Ir" (nr));
+ asm volatile(__ASM_SIZE(btr) " %1,%0" : : ADDR, "Ir" (nr) : "memory");
}
static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr)
bool negative;
asm volatile(LOCK_PREFIX "andb %2,%1"
CC_SET(s)
- : CC_OUT(s) (negative), ADDR
+ : CC_OUT(s) (negative), WBYTE_ADDR(addr)
: "ir" ((char) ~(1 << nr)) : "memory");
return negative;
}
* __clear_bit() is non-atomic and implies release semantics before the memory
* operation. It can be used for an unlock if no other CPUs can concurrently
* modify other bits in the word.
- *
- * No memory barrier is required here, because x86 cannot reorder stores past
- * older loads. Same principle as spin_unlock.
*/
static __always_inline void __clear_bit_unlock(long nr, volatile unsigned long *addr)
{
- barrier();
__clear_bit(nr, addr);
}
*/
static __always_inline void __change_bit(long nr, volatile unsigned long *addr)
{
- asm volatile(__ASM_SIZE(btc) " %1,%0" : ADDR : "Ir" (nr));
+ asm volatile(__ASM_SIZE(btc) " %1,%0" : : ADDR, "Ir" (nr) : "memory");
}
/**
: "iq" ((u8)CONST_MASK(nr)));
} else {
asm volatile(LOCK_PREFIX __ASM_SIZE(btc) " %1,%0"
- : BITOP_ADDR(addr)
- : "Ir" (nr));
+ : : RLONG_ADDR(addr), "Ir" (nr) : "memory");
}
}
asm(__ASM_SIZE(bts) " %2,%1"
CC_SET(c)
- : CC_OUT(c) (oldbit), ADDR
- : "Ir" (nr));
+ : CC_OUT(c) (oldbit)
+ : ADDR, "Ir" (nr) : "memory");
return oldbit;
}
asm volatile(__ASM_SIZE(btr) " %2,%1"
CC_SET(c)
- : CC_OUT(c) (oldbit), ADDR
- : "Ir" (nr));
+ : CC_OUT(c) (oldbit)
+ : ADDR, "Ir" (nr) : "memory");
return oldbit;
}
asm volatile(__ASM_SIZE(btc) " %2,%1"
CC_SET(c)
- : CC_OUT(c) (oldbit), ADDR
- : "Ir" (nr) : "memory");
+ : CC_OUT(c) (oldbit)
+ : ADDR, "Ir" (nr) : "memory");
return oldbit;
}
asm volatile(__ASM_SIZE(bt) " %2,%1"
CC_SET(c)
: CC_OUT(c) (oldbit)
- : "m" (*(unsigned long *)addr), "Ir" (nr));
+ : "m" (*(unsigned long *)addr), "Ir" (nr) : "memory");
return oldbit;
}
test_cpu_cap(c, bit))
#define this_cpu_has(bit) \
- (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \
- x86_this_cpu_test_bit(bit, (unsigned long *)&cpu_info.x86_capability))
+ (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \
+ x86_this_cpu_test_bit(bit, \
+ (unsigned long __percpu *)&cpu_info.x86_capability))
/*
* This macro is for detection of features which need kernel
unsigned (*get_hflags)(struct x86_emulate_ctxt *ctxt);
void (*set_hflags)(struct x86_emulate_ctxt *ctxt, unsigned hflags);
- int (*pre_leave_smm)(struct x86_emulate_ctxt *ctxt, u64 smbase);
+ int (*pre_leave_smm)(struct x86_emulate_ctxt *ctxt,
+ const char *smstate);
+ void (*post_leave_smm)(struct x86_emulate_ctxt *ctxt);
};
}
#define KVM_PERMILLE_MMU_PAGES 20
-#define KVM_MIN_ALLOC_MMU_PAGES 64
+#define KVM_MIN_ALLOC_MMU_PAGES 64UL
#define KVM_MMU_HASH_SHIFT 12
#define KVM_NUM_MMU_PAGES (1 << KVM_MMU_HASH_SHIFT)
#define KVM_MIN_FREE_MMU_PAGES 5
* kvm_memory_slot.arch.gfn_track which is 16 bits, so the role bits used
* by indirect shadow page can not be more than 15 bits.
*
- * Currently, we used 14 bits that are @level, @cr4_pae, @quadrant, @access,
+ * Currently, we used 14 bits that are @level, @gpte_is_8_bytes, @quadrant, @access,
* @nxe, @cr0_wp, @smep_andnot_wp and @smap_andnot_wp.
*/
union kvm_mmu_page_role {
u32 word;
struct {
unsigned level:4;
- unsigned cr4_pae:1;
+ unsigned gpte_is_8_bytes:1;
unsigned quadrant:2;
unsigned direct:1;
unsigned access:3;
};
struct kvm_pio_request {
+ unsigned long linear_rip;
unsigned long count;
int in;
int port;
bool tpr_access_reporting;
u64 ia32_xss;
u64 microcode_version;
+ u64 arch_capabilities;
/*
* Paging state of the vcpu
};
struct kvm_arch {
- unsigned int n_used_mmu_pages;
- unsigned int n_requested_mmu_pages;
- unsigned int n_max_mmu_pages;
+ unsigned long n_used_mmu_pages;
+ unsigned long n_requested_mmu_pages;
+ unsigned long n_max_mmu_pages;
unsigned int indirect_shadow_pages;
struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES];
/*
int (*smi_allowed)(struct kvm_vcpu *vcpu);
int (*pre_enter_smm)(struct kvm_vcpu *vcpu, char *smstate);
- int (*pre_leave_smm)(struct kvm_vcpu *vcpu, u64 smbase);
+ int (*pre_leave_smm)(struct kvm_vcpu *vcpu, const char *smstate);
int (*enable_smi_window)(struct kvm_vcpu *vcpu);
int (*mem_enc_op)(struct kvm *kvm, void __user *argp);
int (*nested_enable_evmcs)(struct kvm_vcpu *vcpu,
uint16_t *vmcs_version);
uint16_t (*nested_get_evmcs_version)(struct kvm_vcpu *vcpu);
+
+ bool (*need_emulation_on_page_fault)(struct kvm_vcpu *vcpu);
};
struct kvm_arch_async_pf {
gfn_t gfn_offset, unsigned long mask);
void kvm_mmu_zap_all(struct kvm *kvm);
void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen);
-unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm);
-void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages);
+unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm);
+void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long kvm_nr_mmu_pages);
int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3);
bool pdptrs_changed(struct kvm_vcpu *vcpu);
#define put_smstate(type, buf, offset, val) \
*(type *)((buf) + (offset) - 0x7e00) = val
+#define GET_SMSTATE(type, buf, offset) \
+ (*(type *)((buf) + (offset) - 0x7e00))
+
#endif /* _ASM_X86_KVM_HOST_H */
return ALIGN(real_mode_blob_end - real_mode_blob, PAGE_SIZE);
}
-void set_real_mode_mem(phys_addr_t mem, size_t size);
+static inline void set_real_mode_mem(phys_addr_t mem)
+{
+ real_mode_header = (struct real_mode_header *) __va(mem);
+}
+
void reserve_real_mode(void);
#endif /* __ASSEMBLY__ */
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
- BUG_ON(i + n > 6);
- memcpy(args, ®s->bx + i, n * sizeof(args[0]));
+ memcpy(args, ®s->bx, 6 * sizeof(args[0]));
}
static inline void syscall_set_arguments(struct task_struct *task,
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
# ifdef CONFIG_IA32_EMULATION
- if (task->thread_info.status & TS_COMPAT)
- switch (i) {
- case 0:
- if (!n--) break;
- *args++ = regs->bx;
- case 1:
- if (!n--) break;
- *args++ = regs->cx;
- case 2:
- if (!n--) break;
- *args++ = regs->dx;
- case 3:
- if (!n--) break;
- *args++ = regs->si;
- case 4:
- if (!n--) break;
- *args++ = regs->di;
- case 5:
- if (!n--) break;
- *args++ = regs->bp;
- case 6:
- if (!n--) break;
- default:
- BUG();
- break;
- }
- else
+ if (task->thread_info.status & TS_COMPAT) {
+ *args++ = regs->bx;
+ *args++ = regs->cx;
+ *args++ = regs->dx;
+ *args++ = regs->si;
+ *args++ = regs->di;
+ *args = regs->bp;
+ } else
# endif
- switch (i) {
- case 0:
- if (!n--) break;
- *args++ = regs->di;
- case 1:
- if (!n--) break;
- *args++ = regs->si;
- case 2:
- if (!n--) break;
- *args++ = regs->dx;
- case 3:
- if (!n--) break;
- *args++ = regs->r10;
- case 4:
- if (!n--) break;
- *args++ = regs->r8;
- case 5:
- if (!n--) break;
- *args++ = regs->r9;
- case 6:
- if (!n--) break;
- default:
- BUG();
- break;
- }
+ {
+ *args++ = regs->di;
+ *args++ = regs->si;
+ *args++ = regs->dx;
+ *args++ = regs->r10;
+ *args++ = regs->r8;
+ *args = regs->r9;
+ }
}
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
# ifdef CONFIG_IA32_EMULATION
- if (task->thread_info.status & TS_COMPAT)
- switch (i) {
- case 0:
- if (!n--) break;
- regs->bx = *args++;
- case 1:
- if (!n--) break;
- regs->cx = *args++;
- case 2:
- if (!n--) break;
- regs->dx = *args++;
- case 3:
- if (!n--) break;
- regs->si = *args++;
- case 4:
- if (!n--) break;
- regs->di = *args++;
- case 5:
- if (!n--) break;
- regs->bp = *args++;
- case 6:
- if (!n--) break;
- default:
- BUG();
- break;
- }
- else
+ if (task->thread_info.status & TS_COMPAT) {
+ regs->bx = *args++;
+ regs->cx = *args++;
+ regs->dx = *args++;
+ regs->si = *args++;
+ regs->di = *args++;
+ regs->bp = *args;
+ } else
# endif
- switch (i) {
- case 0:
- if (!n--) break;
- regs->di = *args++;
- case 1:
- if (!n--) break;
- regs->si = *args++;
- case 2:
- if (!n--) break;
- regs->dx = *args++;
- case 3:
- if (!n--) break;
- regs->r10 = *args++;
- case 4:
- if (!n--) break;
- regs->r8 = *args++;
- case 5:
- if (!n--) break;
- regs->r9 = *args++;
- case 6:
- if (!n--) break;
- default:
- BUG();
- break;
- }
+ {
+ regs->di = *args++;
+ regs->si = *args++;
+ regs->dx = *args++;
+ regs->r10 = *args++;
+ regs->r8 = *args++;
+ regs->r9 = *args;
+ }
}
static inline int syscall_get_arch(void)
__HYPERCALL_DECLS;
__HYPERCALL_5ARG(a1, a2, a3, a4, a5);
+ if (call >= PAGE_SIZE / sizeof(hypercall_page[0]))
+ return -EINVAL;
+
asm volatile(CALL_NOSPEC
: __HYPERCALL_5PARAM
: [thunk_target] "a" (&hypercall_page[call])
#define VMX_ABORT_SAVE_GUEST_MSR_FAIL 1
#define VMX_ABORT_LOAD_HOST_PDPTE_FAIL 2
+#define VMX_ABORT_VMCS_CORRUPTED 3
#define VMX_ABORT_LOAD_HOST_MSR_FAIL 4
#endif /* _UAPIVMX_H */
void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms)
{
unsigned long delay = msecs_to_jiffies(delay_ms);
- struct rdt_resource *r;
int cpu;
- r = &rdt_resources_all[RDT_RESOURCE_L3];
-
cpu = cpumask_any(&dom->cpu_mask);
dom->cqm_work_cpu = cpu;
enum rdt_param {
Opt_cdp,
Opt_cdpl2,
- Opt_mba_mpbs,
+ Opt_mba_mbps,
nr__rdt_params
};
static const struct fs_parameter_spec rdt_param_specs[] = {
fsparam_flag("cdp", Opt_cdp),
fsparam_flag("cdpl2", Opt_cdpl2),
- fsparam_flag("mba_mpbs", Opt_mba_mpbs),
+ fsparam_flag("mba_MBps", Opt_mba_mbps),
{}
};
case Opt_cdpl2:
ctx->enable_cdpl2 = true;
return 0;
- case Opt_mba_mpbs:
+ case Opt_mba_mbps:
if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
return -EINVAL;
ctx->enable_mba_mbps = true;
static int emulator_has_longmode(struct x86_emulate_ctxt *ctxt)
{
+#ifdef CONFIG_X86_64
u32 eax, ebx, ecx, edx;
eax = 0x80000001;
ecx = 0;
ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false);
return edx & bit(X86_FEATURE_LM);
+#else
+ return false;
+#endif
}
-#define GET_SMSTATE(type, smbase, offset) \
- ({ \
- type __val; \
- int r = ctxt->ops->read_phys(ctxt, smbase + offset, &__val, \
- sizeof(__val)); \
- if (r != X86EMUL_CONTINUE) \
- return X86EMUL_UNHANDLEABLE; \
- __val; \
- })
-
static void rsm_set_desc_flags(struct desc_struct *desc, u32 flags)
{
desc->g = (flags >> 23) & 1;
desc->type = (flags >> 8) & 15;
}
-static int rsm_load_seg_32(struct x86_emulate_ctxt *ctxt, u64 smbase, int n)
+static int rsm_load_seg_32(struct x86_emulate_ctxt *ctxt, const char *smstate,
+ int n)
{
struct desc_struct desc;
int offset;
u16 selector;
- selector = GET_SMSTATE(u32, smbase, 0x7fa8 + n * 4);
+ selector = GET_SMSTATE(u32, smstate, 0x7fa8 + n * 4);
if (n < 3)
offset = 0x7f84 + n * 12;
else
offset = 0x7f2c + (n - 3) * 12;
- set_desc_base(&desc, GET_SMSTATE(u32, smbase, offset + 8));
- set_desc_limit(&desc, GET_SMSTATE(u32, smbase, offset + 4));
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, offset));
+ set_desc_base(&desc, GET_SMSTATE(u32, smstate, offset + 8));
+ set_desc_limit(&desc, GET_SMSTATE(u32, smstate, offset + 4));
+ rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, offset));
ctxt->ops->set_segment(ctxt, selector, &desc, 0, n);
return X86EMUL_CONTINUE;
}
-static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, u64 smbase, int n)
+#ifdef CONFIG_X86_64
+static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, const char *smstate,
+ int n)
{
struct desc_struct desc;
int offset;
offset = 0x7e00 + n * 16;
- selector = GET_SMSTATE(u16, smbase, offset);
- rsm_set_desc_flags(&desc, GET_SMSTATE(u16, smbase, offset + 2) << 8);
- set_desc_limit(&desc, GET_SMSTATE(u32, smbase, offset + 4));
- set_desc_base(&desc, GET_SMSTATE(u32, smbase, offset + 8));
- base3 = GET_SMSTATE(u32, smbase, offset + 12);
+ selector = GET_SMSTATE(u16, smstate, offset);
+ rsm_set_desc_flags(&desc, GET_SMSTATE(u16, smstate, offset + 2) << 8);
+ set_desc_limit(&desc, GET_SMSTATE(u32, smstate, offset + 4));
+ set_desc_base(&desc, GET_SMSTATE(u32, smstate, offset + 8));
+ base3 = GET_SMSTATE(u32, smstate, offset + 12);
ctxt->ops->set_segment(ctxt, selector, &desc, base3, n);
return X86EMUL_CONTINUE;
}
+#endif
static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt,
u64 cr0, u64 cr3, u64 cr4)
return X86EMUL_CONTINUE;
}
-static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, u64 smbase)
+static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt,
+ const char *smstate)
{
struct desc_struct desc;
struct desc_ptr dt;
u32 val, cr0, cr3, cr4;
int i;
- cr0 = GET_SMSTATE(u32, smbase, 0x7ffc);
- cr3 = GET_SMSTATE(u32, smbase, 0x7ff8);
- ctxt->eflags = GET_SMSTATE(u32, smbase, 0x7ff4) | X86_EFLAGS_FIXED;
- ctxt->_eip = GET_SMSTATE(u32, smbase, 0x7ff0);
+ cr0 = GET_SMSTATE(u32, smstate, 0x7ffc);
+ cr3 = GET_SMSTATE(u32, smstate, 0x7ff8);
+ ctxt->eflags = GET_SMSTATE(u32, smstate, 0x7ff4) | X86_EFLAGS_FIXED;
+ ctxt->_eip = GET_SMSTATE(u32, smstate, 0x7ff0);
for (i = 0; i < 8; i++)
- *reg_write(ctxt, i) = GET_SMSTATE(u32, smbase, 0x7fd0 + i * 4);
+ *reg_write(ctxt, i) = GET_SMSTATE(u32, smstate, 0x7fd0 + i * 4);
- val = GET_SMSTATE(u32, smbase, 0x7fcc);
+ val = GET_SMSTATE(u32, smstate, 0x7fcc);
ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1);
- val = GET_SMSTATE(u32, smbase, 0x7fc8);
+ val = GET_SMSTATE(u32, smstate, 0x7fc8);
ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1);
- selector = GET_SMSTATE(u32, smbase, 0x7fc4);
- set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7f64));
- set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7f60));
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7f5c));
+ selector = GET_SMSTATE(u32, smstate, 0x7fc4);
+ set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7f64));
+ set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7f60));
+ rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7f5c));
ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_TR);
- selector = GET_SMSTATE(u32, smbase, 0x7fc0);
- set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7f80));
- set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7f7c));
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7f78));
+ selector = GET_SMSTATE(u32, smstate, 0x7fc0);
+ set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7f80));
+ set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7f7c));
+ rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7f78));
ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_LDTR);
- dt.address = GET_SMSTATE(u32, smbase, 0x7f74);
- dt.size = GET_SMSTATE(u32, smbase, 0x7f70);
+ dt.address = GET_SMSTATE(u32, smstate, 0x7f74);
+ dt.size = GET_SMSTATE(u32, smstate, 0x7f70);
ctxt->ops->set_gdt(ctxt, &dt);
- dt.address = GET_SMSTATE(u32, smbase, 0x7f58);
- dt.size = GET_SMSTATE(u32, smbase, 0x7f54);
+ dt.address = GET_SMSTATE(u32, smstate, 0x7f58);
+ dt.size = GET_SMSTATE(u32, smstate, 0x7f54);
ctxt->ops->set_idt(ctxt, &dt);
for (i = 0; i < 6; i++) {
- int r = rsm_load_seg_32(ctxt, smbase, i);
+ int r = rsm_load_seg_32(ctxt, smstate, i);
if (r != X86EMUL_CONTINUE)
return r;
}
- cr4 = GET_SMSTATE(u32, smbase, 0x7f14);
+ cr4 = GET_SMSTATE(u32, smstate, 0x7f14);
- ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7ef8));
+ ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smstate, 0x7ef8));
return rsm_enter_protected_mode(ctxt, cr0, cr3, cr4);
}
-static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
+#ifdef CONFIG_X86_64
+static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt,
+ const char *smstate)
{
struct desc_struct desc;
struct desc_ptr dt;
int i, r;
for (i = 0; i < 16; i++)
- *reg_write(ctxt, i) = GET_SMSTATE(u64, smbase, 0x7ff8 - i * 8);
+ *reg_write(ctxt, i) = GET_SMSTATE(u64, smstate, 0x7ff8 - i * 8);
- ctxt->_eip = GET_SMSTATE(u64, smbase, 0x7f78);
- ctxt->eflags = GET_SMSTATE(u32, smbase, 0x7f70) | X86_EFLAGS_FIXED;
+ ctxt->_eip = GET_SMSTATE(u64, smstate, 0x7f78);
+ ctxt->eflags = GET_SMSTATE(u32, smstate, 0x7f70) | X86_EFLAGS_FIXED;
- val = GET_SMSTATE(u32, smbase, 0x7f68);
+ val = GET_SMSTATE(u32, smstate, 0x7f68);
ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1);
- val = GET_SMSTATE(u32, smbase, 0x7f60);
+ val = GET_SMSTATE(u32, smstate, 0x7f60);
ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1);
- cr0 = GET_SMSTATE(u64, smbase, 0x7f58);
- cr3 = GET_SMSTATE(u64, smbase, 0x7f50);
- cr4 = GET_SMSTATE(u64, smbase, 0x7f48);
- ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7f00));
- val = GET_SMSTATE(u64, smbase, 0x7ed0);
+ cr0 = GET_SMSTATE(u64, smstate, 0x7f58);
+ cr3 = GET_SMSTATE(u64, smstate, 0x7f50);
+ cr4 = GET_SMSTATE(u64, smstate, 0x7f48);
+ ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smstate, 0x7f00));
+ val = GET_SMSTATE(u64, smstate, 0x7ed0);
ctxt->ops->set_msr(ctxt, MSR_EFER, val & ~EFER_LMA);
- selector = GET_SMSTATE(u32, smbase, 0x7e90);
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7e92) << 8);
- set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7e94));
- set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7e98));
- base3 = GET_SMSTATE(u32, smbase, 0x7e9c);
+ selector = GET_SMSTATE(u32, smstate, 0x7e90);
+ rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7e92) << 8);
+ set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7e94));
+ set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7e98));
+ base3 = GET_SMSTATE(u32, smstate, 0x7e9c);
ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_TR);
- dt.size = GET_SMSTATE(u32, smbase, 0x7e84);
- dt.address = GET_SMSTATE(u64, smbase, 0x7e88);
+ dt.size = GET_SMSTATE(u32, smstate, 0x7e84);
+ dt.address = GET_SMSTATE(u64, smstate, 0x7e88);
ctxt->ops->set_idt(ctxt, &dt);
- selector = GET_SMSTATE(u32, smbase, 0x7e70);
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7e72) << 8);
- set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7e74));
- set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7e78));
- base3 = GET_SMSTATE(u32, smbase, 0x7e7c);
+ selector = GET_SMSTATE(u32, smstate, 0x7e70);
+ rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7e72) << 8);
+ set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7e74));
+ set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7e78));
+ base3 = GET_SMSTATE(u32, smstate, 0x7e7c);
ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_LDTR);
- dt.size = GET_SMSTATE(u32, smbase, 0x7e64);
- dt.address = GET_SMSTATE(u64, smbase, 0x7e68);
+ dt.size = GET_SMSTATE(u32, smstate, 0x7e64);
+ dt.address = GET_SMSTATE(u64, smstate, 0x7e68);
ctxt->ops->set_gdt(ctxt, &dt);
r = rsm_enter_protected_mode(ctxt, cr0, cr3, cr4);
return r;
for (i = 0; i < 6; i++) {
- r = rsm_load_seg_64(ctxt, smbase, i);
+ r = rsm_load_seg_64(ctxt, smstate, i);
if (r != X86EMUL_CONTINUE)
return r;
}
return X86EMUL_CONTINUE;
}
+#endif
static int em_rsm(struct x86_emulate_ctxt *ctxt)
{
unsigned long cr0, cr4, efer;
+ char buf[512];
u64 smbase;
int ret;
if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_MASK) == 0)
return emulate_ud(ctxt);
+ smbase = ctxt->ops->get_smbase(ctxt);
+
+ ret = ctxt->ops->read_phys(ctxt, smbase + 0xfe00, buf, sizeof(buf));
+ if (ret != X86EMUL_CONTINUE)
+ return X86EMUL_UNHANDLEABLE;
+
+ if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_INSIDE_NMI_MASK) == 0)
+ ctxt->ops->set_nmi_mask(ctxt, false);
+
+ ctxt->ops->set_hflags(ctxt, ctxt->ops->get_hflags(ctxt) &
+ ~(X86EMUL_SMM_INSIDE_NMI_MASK | X86EMUL_SMM_MASK));
+
/*
* Get back to real mode, to prepare a safe state in which to load
* CR0/CR3/CR4/EFER. It's all a bit more complicated if the vCPU
* supports long mode.
*/
- cr4 = ctxt->ops->get_cr(ctxt, 4);
if (emulator_has_longmode(ctxt)) {
struct desc_struct cs_desc;
/* Zero CR4.PCIDE before CR0.PG. */
- if (cr4 & X86_CR4_PCIDE) {
+ cr4 = ctxt->ops->get_cr(ctxt, 4);
+ if (cr4 & X86_CR4_PCIDE)
ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PCIDE);
- cr4 &= ~X86_CR4_PCIDE;
- }
/* A 32-bit code segment is required to clear EFER.LMA. */
memset(&cs_desc, 0, sizeof(cs_desc));
if (cr0 & X86_CR0_PE)
ctxt->ops->set_cr(ctxt, 0, cr0 & ~(X86_CR0_PG | X86_CR0_PE));
- /* Now clear CR4.PAE (which must be done before clearing EFER.LME). */
- if (cr4 & X86_CR4_PAE)
- ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PAE);
-
- /* And finally go back to 32-bit mode. */
- efer = 0;
- ctxt->ops->set_msr(ctxt, MSR_EFER, efer);
+ if (emulator_has_longmode(ctxt)) {
+ /* Clear CR4.PAE before clearing EFER.LME. */
+ cr4 = ctxt->ops->get_cr(ctxt, 4);
+ if (cr4 & X86_CR4_PAE)
+ ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PAE);
- smbase = ctxt->ops->get_smbase(ctxt);
+ /* And finally go back to 32-bit mode. */
+ efer = 0;
+ ctxt->ops->set_msr(ctxt, MSR_EFER, efer);
+ }
/*
* Give pre_leave_smm() a chance to make ISA-specific changes to the
* vCPU state (e.g. enter guest mode) before loading state from the SMM
* state-save area.
*/
- if (ctxt->ops->pre_leave_smm(ctxt, smbase))
+ if (ctxt->ops->pre_leave_smm(ctxt, buf))
return X86EMUL_UNHANDLEABLE;
+#ifdef CONFIG_X86_64
if (emulator_has_longmode(ctxt))
- ret = rsm_load_state_64(ctxt, smbase + 0x8000);
+ ret = rsm_load_state_64(ctxt, buf);
else
- ret = rsm_load_state_32(ctxt, smbase + 0x8000);
+#endif
+ ret = rsm_load_state_32(ctxt, buf);
if (ret != X86EMUL_CONTINUE) {
/* FIXME: should triple fault */
return X86EMUL_UNHANDLEABLE;
}
- if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_INSIDE_NMI_MASK) == 0)
- ctxt->ops->set_nmi_mask(ctxt, false);
+ ctxt->ops->post_leave_smm(ctxt);
- ctxt->ops->set_hflags(ctxt, ctxt->ops->get_hflags(ctxt) &
- ~(X86EMUL_SMM_INSIDE_NMI_MASK | X86EMUL_SMM_MASK));
return X86EMUL_CONTINUE;
}
new_config.enable = 0;
stimer->config.as_uint64 = new_config.as_uint64;
- stimer_mark_pending(stimer, false);
+ if (stimer->config.enable)
+ stimer_mark_pending(stimer, false);
+
return 0;
}
stimer->config.enable = 0;
else if (stimer->config.auto_enable)
stimer->config.enable = 1;
- stimer_mark_pending(stimer, false);
+
+ if (stimer->config.enable)
+ stimer_mark_pending(stimer, false);
+
return 0;
}
if (offset <= max_apic_id) {
u8 cluster_size = min(max_apic_id - offset + 1, 16U);
+ offset = array_index_nospec(offset, map->max_apic_id + 1);
*cluster = &map->phys_map[offset];
*mask = dest_id & (0xffff >> (16 - cluster_size));
} else {
if (irq->dest_id > map->max_apic_id) {
*bitmap = 0;
} else {
- *dst = &map->phys_map[irq->dest_id];
+ u32 dest_id = array_index_nospec(irq->dest_id, map->max_apic_id + 1);
+ *dst = &map->phys_map[dest_id];
*bitmap = 1;
}
return true;
static const union kvm_mmu_page_role mmu_base_role_mask = {
.cr0_wp = 1,
- .cr4_pae = 1,
+ .gpte_is_8_bytes = 1,
.nxe = 1,
.smep_andnot_wp = 1,
.smap_andnot_wp = 1,
* aggregate version in order to make the slab shrinker
* faster
*/
-static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, int nr)
+static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, unsigned long nr)
{
kvm->arch.n_used_mmu_pages += nr;
percpu_counter_add(&kvm_total_used_mmu_pages, nr);
static void kvm_mmu_commit_zap_page(struct kvm *kvm,
struct list_head *invalid_list);
+
#define for_each_valid_sp(_kvm, _sp, _gfn) \
hlist_for_each_entry(_sp, \
&(_kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(_gfn)], hash_link) \
for_each_valid_sp(_kvm, _sp, _gfn) \
if ((_sp)->gfn != (_gfn) || (_sp)->role.direct) {} else
+static inline bool is_ept_sp(struct kvm_mmu_page *sp)
+{
+ return sp->role.cr0_wp && sp->role.smap_andnot_wp;
+}
+
/* @sp->gfn should be write-protected at the call site */
static bool __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
struct list_head *invalid_list)
{
- if (sp->role.cr4_pae != !!is_pae(vcpu)
- || vcpu->arch.mmu->sync_page(vcpu, sp) == 0) {
+ if ((!is_ept_sp(sp) && sp->role.gpte_is_8_bytes != !!is_pae(vcpu)) ||
+ vcpu->arch.mmu->sync_page(vcpu, sp) == 0) {
kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list);
return false;
}
struct list_head *invalid_list,
bool remote_flush)
{
- if (!remote_flush && !list_empty(invalid_list))
+ if (!remote_flush && list_empty(invalid_list))
return false;
if (!list_empty(invalid_list))
role.level = level;
role.direct = direct;
if (role.direct)
- role.cr4_pae = 0;
+ role.gpte_is_8_bytes = true;
role.access = access;
if (!vcpu->arch.mmu->direct_map
&& vcpu->arch.mmu->root_level <= PT32_ROOT_LEVEL) {
* Changing the number of mmu pages allocated to the vm
* Note: if goal_nr_mmu_pages is too small, you will get dead lock
*/
-void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int goal_nr_mmu_pages)
+void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long goal_nr_mmu_pages)
{
LIST_HEAD(invalid_list);
role.base.access = ACC_ALL;
role.base.nxe = !!is_nx(vcpu);
- role.base.cr4_pae = !!is_pae(vcpu);
role.base.cr0_wp = is_write_protection(vcpu);
role.base.smm = is_smm(vcpu);
role.base.guest_mode = is_guest_mode(vcpu);
role.base.ad_disabled = (shadow_accessed_mask == 0);
role.base.level = kvm_x86_ops->get_tdp_level(vcpu);
role.base.direct = true;
+ role.base.gpte_is_8_bytes = true;
return role;
}
role.base.smap_andnot_wp = role.ext.cr4_smap &&
!is_write_protection(vcpu);
role.base.direct = !is_paging(vcpu);
+ role.base.gpte_is_8_bytes = !!is_pae(vcpu);
if (!is_long_mode(vcpu))
role.base.level = PT32E_ROOT_LEVEL;
kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty,
bool execonly)
{
- union kvm_mmu_role role;
+ union kvm_mmu_role role = {0};
- /* Base role is inherited from root_mmu */
- role.base.word = vcpu->arch.root_mmu.mmu_role.base.word;
- role.ext = kvm_calc_mmu_role_ext(vcpu);
+ /* SMM flag is inherited from root_mmu */
+ role.base.smm = vcpu->arch.root_mmu.mmu_role.base.smm;
role.base.level = PT64_ROOT_4LEVEL;
+ role.base.gpte_is_8_bytes = true;
role.base.direct = false;
role.base.ad_disabled = !accessed_dirty;
role.base.guest_mode = true;
role.base.access = ACC_ALL;
+ /*
+ * WP=1 and NOT_WP=1 is an impossible combination, use WP and the
+ * SMAP variation to denote shadow EPT entries.
+ */
+ role.base.cr0_wp = true;
+ role.base.smap_andnot_wp = true;
+
+ role.ext = kvm_calc_mmu_role_ext(vcpu);
role.ext.execonly = execonly;
return role;
gpa, bytes, sp->role.word);
offset = offset_in_page(gpa);
- pte_size = sp->role.cr4_pae ? 8 : 4;
+ pte_size = sp->role.gpte_is_8_bytes ? 8 : 4;
/*
* Sometimes, the OS only writes the last one bytes to update status
page_offset = offset_in_page(gpa);
level = sp->role.level;
*nspte = 1;
- if (!sp->role.cr4_pae) {
+ if (!sp->role.gpte_is_8_bytes) {
page_offset <<= 1; /* 32->64 */
/*
* A 32-bit pde maps 4MB while the shadow pdes map
* This can happen if a guest gets a page-fault on data access but the HW
* table walker is not able to read the instruction page (e.g instruction
* page is not present in memory). In those cases we simply restart the
- * guest.
+ * guest, with the exception of AMD Erratum 1096 which is unrecoverable.
*/
- if (unlikely(insn && !insn_len))
- return 1;
+ if (unlikely(insn && !insn_len)) {
+ if (!kvm_x86_ops->need_emulation_on_page_fault(vcpu))
+ return 1;
+ }
er = x86_emulate_instruction(vcpu, cr2, emulation_type, insn, insn_len);
if (need_resched() || spin_needbreak(&kvm->mmu_lock)) {
if (flush && lock_flush_tlb) {
- kvm_flush_remote_tlbs(kvm);
+ kvm_flush_remote_tlbs_with_address(kvm,
+ start_gfn,
+ iterator.gfn - start_gfn + 1);
flush = false;
}
cond_resched_lock(&kvm->mmu_lock);
}
if (flush && lock_flush_tlb) {
- kvm_flush_remote_tlbs(kvm);
+ kvm_flush_remote_tlbs_with_address(kvm, start_gfn,
+ end_gfn - start_gfn + 1);
flush = false;
}
/*
* Calculate mmu pages needed for kvm.
*/
-unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm)
+unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm)
{
- unsigned int nr_mmu_pages;
- unsigned int nr_pages = 0;
+ unsigned long nr_mmu_pages;
+ unsigned long nr_pages = 0;
struct kvm_memslots *slots;
struct kvm_memory_slot *memslot;
int i;
}
nr_mmu_pages = nr_pages * KVM_PERMILLE_MMU_PAGES / 1000;
- nr_mmu_pages = max(nr_mmu_pages,
- (unsigned int) KVM_MIN_ALLOC_MMU_PAGES);
+ nr_mmu_pages = max(nr_mmu_pages, KVM_MIN_ALLOC_MMU_PAGES);
return nr_mmu_pages;
}
int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code,
u64 fault_address, char *insn, int insn_len);
-static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm)
+static inline unsigned long kvm_mmu_available_pages(struct kvm *kvm)
{
if (kvm->arch.n_max_mmu_pages > kvm->arch.n_used_mmu_pages)
return kvm->arch.n_max_mmu_pages -
\
role.word = __entry->role; \
\
- trace_seq_printf(p, "sp gfn %llx l%u%s q%u%s %s%s" \
+ trace_seq_printf(p, "sp gfn %llx l%u %u-byte q%u%s %s%s" \
" %snxe %sad root %u %s%c", \
__entry->gfn, role.level, \
- role.cr4_pae ? " pae" : "", \
+ role.gpte_is_8_bytes ? 8 : 4, \
role.quadrant, \
role.direct ? " direct" : "", \
access_str[role.access], \
int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
{
bool fast_mode = idx & (1u << 31);
+ struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
struct kvm_pmc *pmc;
u64 ctr_val;
+ if (!pmu->version)
+ return 1;
+
if (is_vmware_backdoor_pmc(idx))
return kvm_pmu_rdpmc_vmware(vcpu, idx, data);
};
#define AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK (0xFF)
+#define AVIC_LOGICAL_ID_ENTRY_VALID_BIT 31
#define AVIC_LOGICAL_ID_ENTRY_VALID_MASK (1 << 31)
#define AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK (0xFFULL)
static int db_interception(struct vcpu_svm *svm)
{
struct kvm_run *kvm_run = svm->vcpu.run;
+ struct kvm_vcpu *vcpu = &svm->vcpu;
if (!(svm->vcpu.guest_debug &
(KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) &&
if (svm->nmi_singlestep) {
disable_nmi_singlestep(svm);
+ /* Make sure we check for pending NMIs upon entry */
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
}
if (svm->vcpu.guest_debug &
kvm_lapic_reg_write(apic, APIC_ICR, icrl);
break;
case AVIC_IPI_FAILURE_TARGET_NOT_RUNNING: {
+ int i;
+ struct kvm_vcpu *vcpu;
+ struct kvm *kvm = svm->vcpu.kvm;
struct kvm_lapic *apic = svm->vcpu.arch.apic;
/*
- * Update ICR high and low, then emulate sending IPI,
- * which is handled when writing APIC_ICR.
+ * At this point, we expect that the AVIC HW has already
+ * set the appropriate IRR bits on the valid target
+ * vcpus. So, we just need to kick the appropriate vcpu.
*/
- kvm_lapic_reg_write(apic, APIC_ICR2, icrh);
- kvm_lapic_reg_write(apic, APIC_ICR, icrl);
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ bool m = kvm_apic_match_dest(vcpu, apic,
+ icrl & KVM_APIC_SHORT_MASK,
+ GET_APIC_DEST_FIELD(icrh),
+ icrl & KVM_APIC_DEST_MASK);
+
+ if (m && !avic_vcpu_is_running(vcpu))
+ kvm_vcpu_wake_up(vcpu);
+ }
break;
}
case AVIC_IPI_FAILURE_INVALID_TARGET:
u32 *entry = avic_get_logical_id_entry(vcpu, svm->ldr_reg, flat);
if (entry)
- WRITE_ONCE(*entry, (u32) ~AVIC_LOGICAL_ID_ENTRY_VALID_MASK);
+ clear_bit(AVIC_LOGICAL_ID_ENTRY_VALID_BIT, (unsigned long *)entry);
}
static int avic_handle_ldr_update(struct kvm_vcpu *vcpu)
svm->vmcb->save.cr2 = vcpu->arch.cr2;
clgi();
+ kvm_load_guest_xcr0(vcpu);
/*
* If this vCPU has touched SPEC_CTRL, restore the guest's value if
if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI))
kvm_before_interrupt(&svm->vcpu);
+ kvm_put_guest_xcr0(vcpu);
stgi();
/* Any pending NMI will happen here */
return 0;
}
-static int svm_pre_leave_smm(struct kvm_vcpu *vcpu, u64 smbase)
+static int svm_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct vmcb *nested_vmcb;
struct page *page;
- struct {
- u64 guest;
- u64 vmcb;
- } svm_state_save;
- int ret;
+ u64 guest;
+ u64 vmcb;
- ret = kvm_vcpu_read_guest(vcpu, smbase + 0xfed8, &svm_state_save,
- sizeof(svm_state_save));
- if (ret)
- return ret;
+ guest = GET_SMSTATE(u64, smstate, 0x7ed8);
+ vmcb = GET_SMSTATE(u64, smstate, 0x7ee0);
- if (svm_state_save.guest) {
- vcpu->arch.hflags &= ~HF_SMM_MASK;
- nested_vmcb = nested_svm_map(svm, svm_state_save.vmcb, &page);
- if (nested_vmcb)
- enter_svm_guest_mode(svm, svm_state_save.vmcb, nested_vmcb, page);
- else
- ret = 1;
- vcpu->arch.hflags |= HF_SMM_MASK;
+ if (guest) {
+ nested_vmcb = nested_svm_map(svm, vmcb, &page);
+ if (!nested_vmcb)
+ return 1;
+ enter_svm_guest_mode(svm, vmcb, nested_vmcb, page);
}
- return ret;
+ return 0;
}
static int enable_smi_window(struct kvm_vcpu *vcpu)
return ret;
}
-static int get_num_contig_pages(int idx, struct page **inpages,
- unsigned long npages)
+static unsigned long get_num_contig_pages(unsigned long idx,
+ struct page **inpages, unsigned long npages)
{
unsigned long paddr, next_paddr;
- int i = idx + 1, pages = 1;
+ unsigned long i = idx + 1, pages = 1;
/* find the number of contiguous pages starting from idx */
paddr = __sme_page_pa(inpages[idx]);
static int sev_launch_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp)
{
- unsigned long vaddr, vaddr_end, next_vaddr, npages, size;
+ unsigned long vaddr, vaddr_end, next_vaddr, npages, pages, size, i;
struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
struct kvm_sev_launch_update_data params;
struct sev_data_launch_update_data *data;
struct page **inpages;
- int i, ret, pages;
+ int ret;
if (!sev_guest(kvm))
return -ENOTTY;
struct page **src_p, **dst_p;
struct kvm_sev_dbg debug;
unsigned long n;
- int ret, size;
+ unsigned int size;
+ int ret;
if (!sev_guest(kvm))
return -ENOTTY;
if (copy_from_user(&debug, (void __user *)(uintptr_t)argp->data, sizeof(debug)))
return -EFAULT;
+ if (!debug.len || debug.src_uaddr + debug.len < debug.src_uaddr)
+ return -EINVAL;
+ if (!debug.dst_uaddr)
+ return -EINVAL;
+
vaddr = debug.src_uaddr;
size = debug.len;
vaddr_end = vaddr + size;
dst_vaddr,
len, &argp->error);
- sev_unpin_memory(kvm, src_p, 1);
- sev_unpin_memory(kvm, dst_p, 1);
+ sev_unpin_memory(kvm, src_p, n);
+ sev_unpin_memory(kvm, dst_p, n);
if (ret)
goto err;
return -ENODEV;
}
+static bool svm_need_emulation_on_page_fault(struct kvm_vcpu *vcpu)
+{
+ bool is_user, smap;
+
+ is_user = svm_get_cpl(vcpu) == 3;
+ smap = !kvm_read_cr4_bits(vcpu, X86_CR4_SMAP);
+
+ /*
+ * Detect and workaround Errata 1096 Fam_17h_00_0Fh
+ *
+ * In non SEV guest, hypervisor will be able to read the guest
+ * memory to decode the instruction pointer when insn_len is zero
+ * so we return true to indicate that decoding is possible.
+ *
+ * But in the SEV guest, the guest memory is encrypted with the
+ * guest specific key and hypervisor will not be able to decode the
+ * instruction pointer so we will not able to workaround it. Lets
+ * print the error and request to kill the guest.
+ */
+ if (is_user && smap) {
+ if (!sev_guest(vcpu->kvm))
+ return true;
+
+ pr_err_ratelimited("KVM: Guest triggered AMD Erratum 1096\n");
+ kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
+ }
+
+ return false;
+}
+
static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
.cpu_has_kvm_support = has_svm,
.disabled_by_bios = is_disabled,
.nested_enable_evmcs = nested_enable_evmcs,
.nested_get_evmcs_version = nested_get_evmcs_version,
+
+ .need_emulation_on_page_fault = svm_need_emulation_on_page_fault,
};
static int __init svm_init(void)
);
TRACE_EVENT(kvm_apic_accept_irq,
- TP_PROTO(__u32 apicid, __u16 dm, __u8 tm, __u8 vec),
+ TP_PROTO(__u32 apicid, __u16 dm, __u16 tm, __u8 vec),
TP_ARGS(apicid, dm, tm, vec),
TP_STRUCT__entry(
__field( __u32, apicid )
__field( __u16, dm )
- __field( __u8, tm )
+ __field( __u16, tm )
__field( __u8, vec )
),
}
}
+static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap) {
+ int msr;
+
+ for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
+ unsigned word = msr / BITS_PER_LONG;
+
+ msr_bitmap[word] = ~0;
+ msr_bitmap[word + (0x800 / sizeof(long))] = ~0;
+ }
+}
+
/*
* Merge L0's and L1's MSR bitmap, return false to indicate that
* we do not use the hardware.
return false;
msr_bitmap_l1 = (unsigned long *)kmap(page);
- if (nested_cpu_has_apic_reg_virt(vmcs12)) {
- /*
- * L0 need not intercept reads for MSRs between 0x800 and 0x8ff, it
- * just lets the processor take the value from the virtual-APIC page;
- * take those 256 bits directly from the L1 bitmap.
- */
- for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
- unsigned word = msr / BITS_PER_LONG;
- msr_bitmap_l0[word] = msr_bitmap_l1[word];
- msr_bitmap_l0[word + (0x800 / sizeof(long))] = ~0;
- }
- } else {
- for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
- unsigned word = msr / BITS_PER_LONG;
- msr_bitmap_l0[word] = ~0;
- msr_bitmap_l0[word + (0x800 / sizeof(long))] = ~0;
- }
- }
- nested_vmx_disable_intercept_for_msr(
- msr_bitmap_l1, msr_bitmap_l0,
- X2APIC_MSR(APIC_TASKPRI),
- MSR_TYPE_W);
+ /*
+ * To keep the control flow simple, pay eight 8-byte writes (sixteen
+ * 4-byte writes on 32-bit systems) up front to enable intercepts for
+ * the x2APIC MSR range and selectively disable them below.
+ */
+ enable_x2apic_msr_intercepts(msr_bitmap_l0);
+
+ if (nested_cpu_has_virt_x2apic_mode(vmcs12)) {
+ if (nested_cpu_has_apic_reg_virt(vmcs12)) {
+ /*
+ * L0 need not intercept reads for MSRs between 0x800
+ * and 0x8ff, it just lets the processor take the value
+ * from the virtual-APIC page; take those 256 bits
+ * directly from the L1 bitmap.
+ */
+ for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
+ unsigned word = msr / BITS_PER_LONG;
+
+ msr_bitmap_l0[word] = msr_bitmap_l1[word];
+ }
+ }
- if (nested_cpu_has_vid(vmcs12)) {
- nested_vmx_disable_intercept_for_msr(
- msr_bitmap_l1, msr_bitmap_l0,
- X2APIC_MSR(APIC_EOI),
- MSR_TYPE_W);
nested_vmx_disable_intercept_for_msr(
msr_bitmap_l1, msr_bitmap_l0,
- X2APIC_MSR(APIC_SELF_IPI),
- MSR_TYPE_W);
+ X2APIC_MSR(APIC_TASKPRI),
+ MSR_TYPE_R | MSR_TYPE_W);
+
+ if (nested_cpu_has_vid(vmcs12)) {
+ nested_vmx_disable_intercept_for_msr(
+ msr_bitmap_l1, msr_bitmap_l0,
+ X2APIC_MSR(APIC_EOI),
+ MSR_TYPE_W);
+ nested_vmx_disable_intercept_for_msr(
+ msr_bitmap_l1, msr_bitmap_l0,
+ X2APIC_MSR(APIC_SELF_IPI),
+ MSR_TYPE_W);
+ }
}
if (spec_ctrl)
!nested_host_cr4_valid(vcpu, vmcs12->host_cr4) ||
!nested_cr3_valid(vcpu, vmcs12->host_cr3))
return -EINVAL;
+
+ if (is_noncanonical_address(vmcs12->host_ia32_sysenter_esp, vcpu) ||
+ is_noncanonical_address(vmcs12->host_ia32_sysenter_eip, vcpu))
+ return -EINVAL;
+
/*
* If the load IA32_EFER VM-exit control is 1, bits reserved in the
* IA32_EFER MSR must be 0 in the field for that register. In addition,
/*
* If translation failed, VM entry will fail because
* prepare_vmcs02 set VIRTUAL_APIC_PAGE_ADDR to -1ull.
- * Failing the vm entry is _not_ what the processor
- * does but it's basically the only possibility we
- * have. We could still enter the guest if CR8 load
- * exits are enabled, CR8 store exits are enabled, and
- * virtualize APIC access is disabled; in this case
- * the processor would never use the TPR shadow and we
- * could simply clear the bit from the execution
- * control. But such a configuration is useless, so
- * let's keep the code simple.
*/
if (!is_error_page(page)) {
vmx->nested.virtual_apic_page = page;
hpa = page_to_phys(vmx->nested.virtual_apic_page);
vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, hpa);
+ } else if (nested_cpu_has(vmcs12, CPU_BASED_CR8_LOAD_EXITING) &&
+ nested_cpu_has(vmcs12, CPU_BASED_CR8_STORE_EXITING) &&
+ !nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
+ /*
+ * The processor will never use the TPR shadow, simply
+ * clear the bit from the execution control. Such a
+ * configuration is useless, but it happens in tests.
+ * For any other configuration, failing the vm entry is
+ * _not_ what the processor does but it's basically the
+ * only possibility we have.
+ */
+ vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL,
+ CPU_BASED_TPR_SHADOW);
+ } else {
+ printk("bad virtual-APIC page address\n");
+ dump_vmcs();
}
}
vmx_set_cr4(vcpu, vmcs_readl(CR4_READ_SHADOW));
nested_ept_uninit_mmu_context(vcpu);
- vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
- __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
+
+ /*
+ * This is only valid if EPT is in use, otherwise the vmcs01 GUEST_CR3
+ * points to shadow pages! Fortunately we only get here after a WARN_ON
+ * if EPT is disabled, so a VMabort is perfectly fine.
+ */
+ if (enable_ept) {
+ vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
+ __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
+ } else {
+ nested_vmx_abort(vcpu, VMX_ABORT_VMCS_CORRUPTED);
+ }
/*
* Use ept_save_pdptrs(vcpu) to load the MMU's cached PDPTRs
{
int i;
+ /*
+ * Without EPT it is not possible to restore L1's CR3 and PDPTR on
+ * VMfail, because they are not available in vmcs01. Just always
+ * use hardware checks.
+ */
+ if (!enable_ept)
+ nested_early_check = 1;
+
if (!cpu_has_vmx_shadow_vmcs())
enable_shadow_vmcs = 0;
if (enable_shadow_vmcs) {
msr_info->data = to_vmx(vcpu)->spec_ctrl;
break;
- case MSR_IA32_ARCH_CAPABILITIES:
- if (!msr_info->host_initiated &&
- !guest_cpuid_has(vcpu, X86_FEATURE_ARCH_CAPABILITIES))
- return 1;
- msr_info->data = to_vmx(vcpu)->arch_capabilities;
- break;
case MSR_IA32_SYSENTER_CS:
msr_info->data = vmcs_read32(GUEST_SYSENTER_CS);
break;
vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, MSR_IA32_PRED_CMD,
MSR_TYPE_W);
break;
- case MSR_IA32_ARCH_CAPABILITIES:
- if (!msr_info->host_initiated)
- return 1;
- vmx->arch_capabilities = data;
- break;
case MSR_IA32_CR_PAT:
if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) {
if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data))
++vmx->nmsrs;
}
- vmx->arch_capabilities = kvm_get_arch_capabilities();
-
vm_exit_controls_init(vmx, vmx_vmexit_ctrl());
/* 22.2.1, 20.8.1 */
vmcs_readl(limit + GUEST_GDTR_BASE - GUEST_GDTR_LIMIT));
}
-static void dump_vmcs(void)
+void dump_vmcs(void)
{
u32 vmentry_ctl = vmcs_read32(VM_ENTRY_CONTROLS);
u32 vmexit_ctl = vmcs_read32(VM_EXIT_CONTROLS);
if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
vmx_set_interrupt_shadow(vcpu, 0);
+ kvm_load_guest_xcr0(vcpu);
+
if (static_cpu_has(X86_FEATURE_PKU) &&
kvm_read_cr4_bits(vcpu, X86_CR4_PKE) &&
vcpu->arch.pkru != vmx->host_pkru)
__write_pkru(vmx->host_pkru);
}
+ kvm_put_guest_xcr0(vcpu);
+
vmx->nested.nested_run_pending = 0;
vmx->idt_vectoring_info = 0;
}
}
+static bool guest_cpuid_has_pmu(struct kvm_vcpu *vcpu)
+{
+ struct kvm_cpuid_entry2 *entry;
+ union cpuid10_eax eax;
+
+ entry = kvm_find_cpuid_entry(vcpu, 0xa, 0);
+ if (!entry)
+ return false;
+
+ eax.full = entry->eax;
+ return (eax.split.version_id > 0);
+}
+
+static void nested_vmx_procbased_ctls_update(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ bool pmu_enabled = guest_cpuid_has_pmu(vcpu);
+
+ if (pmu_enabled)
+ vmx->nested.msrs.procbased_ctls_high |= CPU_BASED_RDPMC_EXITING;
+ else
+ vmx->nested.msrs.procbased_ctls_high &= ~CPU_BASED_RDPMC_EXITING;
+}
+
static void update_intel_pt_cfg(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
if (nested_vmx_allowed(vcpu)) {
nested_vmx_cr_fixed1_bits_update(vcpu);
nested_vmx_entry_exit_ctls_update(vcpu);
+ nested_vmx_procbased_ctls_update(vcpu);
}
if (boot_cpu_has(X86_FEATURE_INTEL_PT) &&
return 0;
}
-static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, u64 smbase)
+static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
int ret;
}
if (vmx->nested.smm.guest_mode) {
- vcpu->arch.hflags &= ~HF_SMM_MASK;
ret = nested_vmx_enter_non_root_mode(vcpu, false);
- vcpu->arch.hflags |= HF_SMM_MASK;
if (ret)
return ret;
return 0;
}
+static bool vmx_need_emulation_on_page_fault(struct kvm_vcpu *vcpu)
+{
+ return 0;
+}
+
static __init int hardware_setup(void)
{
unsigned long host_bndcfgs;
.set_nested_state = NULL,
.get_vmcs12_pages = NULL,
.nested_enable_evmcs = NULL,
+ .need_emulation_on_page_fault = vmx_need_emulation_on_page_fault,
};
static void vmx_cleanup_l1d_flush(void)
u64 msr_guest_kernel_gs_base;
#endif
- u64 arch_capabilities;
u64 spec_ctrl;
u32 vm_entry_controls_shadow;
vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio);
}
+void dump_vmcs(void);
+
#endif /* __KVM_X86_VMX_H */
}
EXPORT_SYMBOL_GPL(kvm_lmsw);
-static void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu)
+void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu)
{
if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) &&
!vcpu->guest_xcr0_loaded) {
vcpu->guest_xcr0_loaded = 1;
}
}
+EXPORT_SYMBOL_GPL(kvm_load_guest_xcr0);
-static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu)
+void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu)
{
if (vcpu->guest_xcr0_loaded) {
if (vcpu->arch.xcr0 != host_xcr0)
vcpu->guest_xcr0_loaded = 0;
}
}
+EXPORT_SYMBOL_GPL(kvm_put_guest_xcr0);
static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
{
#endif
MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA,
MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS, MSR_TSC_AUX,
- MSR_IA32_SPEC_CTRL, MSR_IA32_ARCH_CAPABILITIES,
+ MSR_IA32_SPEC_CTRL,
MSR_IA32_RTIT_CTL, MSR_IA32_RTIT_STATUS, MSR_IA32_RTIT_CR3_MATCH,
MSR_IA32_RTIT_OUTPUT_BASE, MSR_IA32_RTIT_OUTPUT_MASK,
MSR_IA32_RTIT_ADDR0_A, MSR_IA32_RTIT_ADDR0_B,
MSR_IA32_TSC_ADJUST,
MSR_IA32_TSCDEADLINE,
+ MSR_IA32_ARCH_CAPABILITIES,
MSR_IA32_MISC_ENABLE,
MSR_IA32_MCG_STATUS,
MSR_IA32_MCG_CTL,
if (msr_info->host_initiated)
vcpu->arch.microcode_version = data;
break;
+ case MSR_IA32_ARCH_CAPABILITIES:
+ if (!msr_info->host_initiated)
+ return 1;
+ vcpu->arch.arch_capabilities = data;
+ break;
case MSR_EFER:
return set_efer(vcpu, data);
case MSR_K7_HWCR:
case MSR_IA32_UCODE_REV:
msr_info->data = vcpu->arch.microcode_version;
break;
+ case MSR_IA32_ARCH_CAPABILITIES:
+ if (!msr_info->host_initiated &&
+ !guest_cpuid_has(vcpu, X86_FEATURE_ARCH_CAPABILITIES))
+ return 1;
+ msr_info->data = vcpu->arch.arch_capabilities;
+ break;
case MSR_IA32_TSC:
msr_info->data = kvm_scale_tsc(vcpu, rdtsc()) + vcpu->arch.tsc_offset;
break;
break;
case KVM_CAP_NESTED_STATE:
r = kvm_x86_ops->get_nested_state ?
- kvm_x86_ops->get_nested_state(NULL, 0, 0) : 0;
+ kvm_x86_ops->get_nested_state(NULL, NULL, 0) : 0;
break;
default:
break;
memset(&events->reserved, 0, sizeof(events->reserved));
}
-static void kvm_set_hflags(struct kvm_vcpu *vcpu, unsigned emul_flags);
+static void kvm_smm_changed(struct kvm_vcpu *vcpu);
static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
struct kvm_vcpu_events *events)
vcpu->arch.apic->sipi_vector = events->sipi_vector;
if (events->flags & KVM_VCPUEVENT_VALID_SMM) {
- u32 hflags = vcpu->arch.hflags;
- if (events->smi.smm)
- hflags |= HF_SMM_MASK;
- else
- hflags &= ~HF_SMM_MASK;
- kvm_set_hflags(vcpu, hflags);
+ if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) {
+ if (events->smi.smm)
+ vcpu->arch.hflags |= HF_SMM_MASK;
+ else
+ vcpu->arch.hflags &= ~HF_SMM_MASK;
+ kvm_smm_changed(vcpu);
+ }
vcpu->arch.smi_pending = events->smi.pending;
}
static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm,
- u32 kvm_nr_mmu_pages)
+ unsigned long kvm_nr_mmu_pages)
{
if (kvm_nr_mmu_pages < KVM_MIN_ALLOC_MMU_PAGES)
return -EINVAL;
return 0;
}
-static int kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm)
+static unsigned long kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm)
{
return kvm->arch.n_max_mmu_pages;
}
static void emulator_set_hflags(struct x86_emulate_ctxt *ctxt, unsigned emul_flags)
{
- kvm_set_hflags(emul_to_vcpu(ctxt), emul_flags);
+ emul_to_vcpu(ctxt)->arch.hflags = emul_flags;
+}
+
+static int emulator_pre_leave_smm(struct x86_emulate_ctxt *ctxt,
+ const char *smstate)
+{
+ return kvm_x86_ops->pre_leave_smm(emul_to_vcpu(ctxt), smstate);
}
-static int emulator_pre_leave_smm(struct x86_emulate_ctxt *ctxt, u64 smbase)
+static void emulator_post_leave_smm(struct x86_emulate_ctxt *ctxt)
{
- return kvm_x86_ops->pre_leave_smm(emul_to_vcpu(ctxt), smbase);
+ kvm_smm_changed(emul_to_vcpu(ctxt));
}
static const struct x86_emulate_ops emulate_ops = {
.get_hflags = emulator_get_hflags,
.set_hflags = emulator_set_hflags,
.pre_leave_smm = emulator_pre_leave_smm,
+ .post_leave_smm = emulator_post_leave_smm,
};
static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask)
kvm_mmu_reset_context(vcpu);
}
-static void kvm_set_hflags(struct kvm_vcpu *vcpu, unsigned emul_flags)
-{
- unsigned changed = vcpu->arch.hflags ^ emul_flags;
-
- vcpu->arch.hflags = emul_flags;
-
- if (changed & HF_SMM_MASK)
- kvm_smm_changed(vcpu);
-}
-
static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7,
unsigned long *db)
{
}
EXPORT_SYMBOL_GPL(kvm_emulate_instruction_from_buffer);
+static int complete_fast_pio_out(struct kvm_vcpu *vcpu)
+{
+ vcpu->arch.pio.count = 0;
+
+ if (unlikely(!kvm_is_linear_rip(vcpu, vcpu->arch.pio.linear_rip)))
+ return 1;
+
+ return kvm_skip_emulated_instruction(vcpu);
+}
+
static int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size,
unsigned short port)
{
unsigned long val = kvm_register_read(vcpu, VCPU_REGS_RAX);
int ret = emulator_pio_out_emulated(&vcpu->arch.emulate_ctxt,
size, port, &val, 1);
- /* do not return to emulator after return from userspace */
- vcpu->arch.pio.count = 0;
+
+ if (!ret) {
+ vcpu->arch.pio.linear_rip = kvm_get_linear_rip(vcpu);
+ vcpu->arch.complete_userspace_io = complete_fast_pio_out;
+ }
return ret;
}
/* We should only ever be called with arch.pio.count equal to 1 */
BUG_ON(vcpu->arch.pio.count != 1);
+ if (unlikely(!kvm_is_linear_rip(vcpu, vcpu->arch.pio.linear_rip))) {
+ vcpu->arch.pio.count = 0;
+ return 1;
+ }
+
/* For size less than 4 we merge, else we zero extend */
val = (vcpu->arch.pio.size < 4) ? kvm_register_read(vcpu, VCPU_REGS_RAX)
: 0;
vcpu->arch.pio.port, &val, 1);
kvm_register_write(vcpu, VCPU_REGS_RAX, val);
- return 1;
+ return kvm_skip_emulated_instruction(vcpu);
}
static int kvm_fast_pio_in(struct kvm_vcpu *vcpu, int size,
return ret;
}
+ vcpu->arch.pio.linear_rip = kvm_get_linear_rip(vcpu);
vcpu->arch.complete_userspace_io = complete_fast_pio_in;
return 0;
int kvm_fast_pio(struct kvm_vcpu *vcpu, int size, unsigned short port, int in)
{
- int ret = kvm_skip_emulated_instruction(vcpu);
+ int ret;
- /*
- * TODO: we might be squashing a KVM_GUESTDBG_SINGLESTEP-triggered
- * KVM_EXIT_DEBUG here.
- */
if (in)
- return kvm_fast_pio_in(vcpu, size, port) && ret;
+ ret = kvm_fast_pio_in(vcpu, size, port);
else
- return kvm_fast_pio_out(vcpu, size, port) && ret;
+ ret = kvm_fast_pio_out(vcpu, size, port);
+ return ret && kvm_skip_emulated_instruction(vcpu);
}
EXPORT_SYMBOL_GPL(kvm_fast_pio);
put_smstate(u32, buf, 0x7ef8, vcpu->arch.smbase);
}
+#ifdef CONFIG_X86_64
static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, char *buf)
{
-#ifdef CONFIG_X86_64
struct desc_ptr dt;
struct kvm_segment seg;
unsigned long val;
for (i = 0; i < 6; i++)
enter_smm_save_seg_64(vcpu, buf, i);
-#else
- WARN_ON_ONCE(1);
-#endif
}
+#endif
static void enter_smm(struct kvm_vcpu *vcpu)
{
trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, true);
memset(buf, 0, 512);
+#ifdef CONFIG_X86_64
if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
enter_smm_save_state_64(vcpu, buf);
else
+#endif
enter_smm_save_state_32(vcpu, buf);
/*
kvm_set_segment(vcpu, &ds, VCPU_SREG_GS);
kvm_set_segment(vcpu, &ds, VCPU_SREG_SS);
+#ifdef CONFIG_X86_64
if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
kvm_x86_ops->set_efer(vcpu, 0);
+#endif
kvm_update_cpuid(vcpu);
kvm_mmu_reset_context(vcpu);
goto cancel_injection;
}
- kvm_load_guest_xcr0(vcpu);
-
if (req_immediate_exit) {
kvm_make_request(KVM_REQ_EVENT, vcpu);
kvm_x86_ops->request_immediate_exit(vcpu);
vcpu->mode = OUTSIDE_GUEST_MODE;
smp_wmb();
- kvm_put_guest_xcr0(vcpu);
-
kvm_before_interrupt(vcpu);
kvm_x86_ops->handle_external_intr(vcpu);
kvm_after_interrupt(vcpu);
int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
{
+ vcpu->arch.arch_capabilities = kvm_get_arch_capabilities();
vcpu->arch.msr_platform_info = MSR_PLATFORM_INFO_CPUID_FAULT;
kvm_vcpu_mtrr_init(vcpu);
vcpu_load(vcpu);
const struct kvm_memory_slot *new,
enum kvm_mr_change change)
{
- int nr_mmu_pages = 0;
-
if (!kvm->arch.n_requested_mmu_pages)
- nr_mmu_pages = kvm_mmu_calculate_mmu_pages(kvm);
-
- if (nr_mmu_pages)
- kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages);
+ kvm_mmu_change_mmu_pages(kvm,
+ kvm_mmu_calculate_default_mmu_pages(kvm));
/*
* Dirty logging tracks sptes in 4k granularity, meaning that large
__this_cpu_write(current_vcpu, NULL);
}
+void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu);
+void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu);
#endif
/* Can we access it for direct reading/writing? Must be RAM: */
int valid_phys_addr_range(phys_addr_t addr, size_t count)
{
- return addr + count <= __pa(high_memory);
+ return addr + count - 1 <= __pa(high_memory - 1);
}
/* Can we access it through mmap? Must be a valid physical address: */
*/
rm_size = real_mode_size_needed();
if (rm_size && (start + rm_size) < (1<<20) && size >= rm_size) {
- set_real_mode_mem(start, rm_size);
+ set_real_mode_mem(start);
start += rm_size;
size -= rm_size;
}
/* Hold the pgd entry used on booting additional CPUs */
pgd_t trampoline_pgd_entry;
-void __init set_real_mode_mem(phys_addr_t mem, size_t size)
-{
- void *base = __va(mem);
-
- real_mode_header = (struct real_mode_header *) base;
- printk(KERN_DEBUG "Base memory trampoline at [%p] %llx size %zu\n",
- base, (unsigned long long)mem, size);
-}
-
void __init reserve_real_mode(void)
{
phys_addr_t mem;
}
memblock_reserve(mem, size);
- set_real_mode_mem(mem, size);
+ set_real_mode_mem(mem);
}
static void __init setup_real_mode(void)
generic-y += kdebug.h
generic-y += kmap_types.h
generic-y += kprobes.h
+generic-y += kvm_para.h
generic-y += local.h
generic-y += local64.h
generic-y += mcs_spinlock.h
/* Clearing a0 terminates the backtrace. */
#define start_thread(regs, new_pc, new_sp) \
- memset(regs, 0, sizeof(*regs)); \
- regs->pc = new_pc; \
- regs->ps = USER_PS_VALUE; \
- regs->areg[1] = new_sp; \
- regs->areg[0] = 0; \
- regs->wmask = 1; \
- regs->depc = 0; \
- regs->windowbase = 0; \
- regs->windowstart = 1;
+ do { \
+ memset((regs), 0, sizeof(*(regs))); \
+ (regs)->pc = (new_pc); \
+ (regs)->ps = USER_PS_VALUE; \
+ (regs)->areg[1] = (new_sp); \
+ (regs)->areg[0] = 0; \
+ (regs)->wmask = 1; \
+ (regs)->depc = 0; \
+ (regs)->windowbase = 0; \
+ (regs)->windowstart = 1; \
+ (regs)->syscall = NO_SYSCALL; \
+ } while (0)
/* Forward declaration */
struct task_struct;
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
static const unsigned int reg[] = XTENSA_SYSCALL_ARGUMENT_REGS;
- unsigned int j;
+ unsigned int i;
- if (n == 0)
- return;
-
- WARN_ON_ONCE(i + n > SYSCALL_MAX_ARGS);
-
- for (j = 0; j < n; ++j) {
- if (i + j < SYSCALL_MAX_ARGS)
- args[j] = regs->areg[reg[i + j]];
- else
- args[j] = 0;
- }
+ for (i = 0; i < 6; ++i)
+ args[i] = regs->areg[reg[i]];
}
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
static const unsigned int reg[] = XTENSA_SYSCALL_ARGUMENT_REGS;
- unsigned int j;
-
- if (n == 0)
- return;
-
- if (WARN_ON_ONCE(i + n > SYSCALL_MAX_ARGS)) {
- if (i < SYSCALL_MAX_ARGS)
- n = SYSCALL_MAX_ARGS - i;
- else
- return;
- }
+ unsigned int i;
- for (j = 0; j < n; ++j)
- regs->areg[reg[i + j]] = args[j];
+ for (i = 0; i < 6; ++i)
+ regs->areg[reg[i]] = args[i];
}
asmlinkage long xtensa_rt_sigreturn(struct pt_regs*);
generated-y += unistd_32.h
-generic-y += kvm_para.h
l32i a7, a2, PT_SYSCALL
1:
+ s32i a7, a1, 4
+
/* syscall = sys_call_table[syscall_nr] */
movi a4, sys_call_table
retw
1:
+ l32i a4, a1, 4
+ l32i a3, a2, PT_SYSCALL
+ s32i a4, a2, PT_SYSCALL
mov a6, a2
call4 do_syscall_trace_leave
+ s32i a3, a2, PT_SYSCALL
retw
ENDPROC(system_call)
return 1;
}
+/*
+ * level == 0 is for the return address from the caller of this function,
+ * not from this function itself.
+ */
unsigned long return_address(unsigned level)
{
struct return_addr_data r = {
- .skip = level + 1,
+ .skip = level,
};
walk_stackframe(stack_pointer(NULL), return_address_cb, &r);
return r.addr;
pte = memblock_alloc_low(n_pages * sizeof(pte_t), PAGE_SIZE);
if (!pte)
- panic("%s: Failed to allocate %zu bytes align=%lx\n",
+ panic("%s: Failed to allocate %lu bytes align=%lx\n",
__func__, n_pages * sizeof(pte_t), PAGE_SIZE);
for (i = 0; i < n_pages; ++i)
* at least two nodes.
*/
return !(varied_queue_weights || multiple_classes_busy
-#ifdef BFQ_GROUP_IOSCHED_ENABLED
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
|| bfqd->num_groups_with_pending_reqs > 0
#endif
);
bfq_remove_request(q, rq);
}
-static void __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+static bool __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq)
{
/*
* If this bfqq is shared between multiple processes, check
/*
* All in-service entities must have been properly deactivated
* or requeued before executing the next function, which
- * resets all in-service entites as no more in service.
+ * resets all in-service entities as no more in service. This
+ * may cause bfqq to be freed. If this happens, the next
+ * function returns true.
*/
- __bfq_bfqd_reset_in_service(bfqd);
+ return __bfq_bfqd_reset_in_service(bfqd);
}
/**
bool slow;
unsigned long delta = 0;
struct bfq_entity *entity = &bfqq->entity;
- int ref;
/*
* Check whether the process is slow (see bfq_bfqq_is_slow).
* reason.
*/
__bfq_bfqq_recalc_budget(bfqd, bfqq, reason);
- ref = bfqq->ref;
- __bfq_bfqq_expire(bfqd, bfqq);
-
- if (ref == 1) /* bfqq is gone, no more actions on it */
+ if (__bfq_bfqq_expire(bfqd, bfqq))
+ /* bfqq is gone, no more actions on it */
return;
bfqq->injected_service = 0;
bool ins_into_idle_tree);
bool next_queue_may_preempt(struct bfq_data *bfqd);
struct bfq_queue *bfq_get_next_queue(struct bfq_data *bfqd);
-void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd);
+bool __bfq_bfqd_reset_in_service(struct bfq_data *bfqd);
void bfq_deactivate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
bool ins_into_idle_tree, bool expiration);
void bfq_activate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq);
entity->on_st = true;
}
-#ifdef BFQ_GROUP_IOSCHED_ENABLED
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
if (!bfq_entity_to_bfqq(entity)) { /* bfq_group */
struct bfq_group *bfqg =
container_of(entity, struct bfq_group, entity);
return bfqq;
}
-void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd)
+/* returns true if the in-service queue gets freed */
+bool __bfq_bfqd_reset_in_service(struct bfq_data *bfqd)
{
struct bfq_queue *in_serv_bfqq = bfqd->in_service_queue;
struct bfq_entity *in_serv_entity = &in_serv_bfqq->entity;
* service tree either, then release the service reference to
* the queue it represents (taken with bfq_get_entity).
*/
- if (!in_serv_entity->on_st)
+ if (!in_serv_entity->on_st) {
+ /*
+ * If no process is referencing in_serv_bfqq any
+ * longer, then the service reference may be the only
+ * reference to the queue. If this is the case, then
+ * bfqq gets freed here.
+ */
+ int ref = in_serv_bfqq->ref;
bfq_put_queue(in_serv_bfqq);
+ if (ref == 1)
+ return true;
+ }
+
+ return false;
}
void bfq_deactivate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
}
}
- if (bio_add_pc_page(q, bio, page, bytes, offset) < bytes)
+ if (bio_add_pc_page(q, bio, page, bytes, offset) < bytes) {
+ if (!map_data)
+ __free_page(page);
break;
+ }
len -= bytes;
offset = 0;
*/
blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *rq)
{
- blk_qc_t unused;
-
if (blk_cloned_rq_check_limits(q, rq))
return BLK_STS_IOERR;
* bypass a potential scheduler on the bottom device for
* insert.
*/
- return blk_mq_try_issue_directly(rq->mq_hctx, rq, &unused, true, true);
+ return blk_mq_request_issue_directly(rq, true);
}
EXPORT_SYMBOL_GPL(blk_insert_cloned_request);
blk_mq_tag_set_rq(hctx, flush_rq->tag, fq->orig_rq);
flush_rq->tag = -1;
} else {
- blk_mq_put_driver_tag_hctx(hctx, flush_rq);
+ blk_mq_put_driver_tag(flush_rq);
flush_rq->internal_tag = -1;
}
if (q->elevator) {
WARN_ON(rq->tag < 0);
- blk_mq_put_driver_tag_hctx(hctx, rq);
+ blk_mq_put_driver_tag(rq);
}
/*
* busy in case of 'none' scheduler, and this way may save
* us one extra enqueue & dequeue to sw queue.
*/
- if (!hctx->dispatch_busy && !e && !run_queue_async)
+ if (!hctx->dispatch_busy && !e && !run_queue_async) {
blk_mq_try_issue_list_directly(hctx, list);
- else
- blk_mq_insert_requests(hctx, ctx, list);
+ if (list_empty(list))
+ return;
+ }
+ blk_mq_insert_requests(hctx, ctx, list);
}
blk_mq_run_hw_queue(hctx, run_queue_async);
}
/*
- * Check if any of the ctx's have pending work in this hardware queue
+ * Check if any of the ctx, dispatch list or elevator
+ * have pending work in this hardware queue.
*/
static bool blk_mq_hctx_has_pending(struct blk_mq_hw_ctx *hctx)
{
}
EXPORT_SYMBOL(blk_mq_complete_request);
+void blk_mq_complete_request_sync(struct request *rq)
+{
+ WRITE_ONCE(rq->state, MQ_RQ_COMPLETE);
+ rq->q->mq_ops->complete(rq);
+}
+EXPORT_SYMBOL_GPL(blk_mq_complete_request_sync);
+
int blk_mq_request_started(struct request *rq)
{
return blk_mq_rq_state(rq) != MQ_RQ_IDLE;
hctx = container_of(wait, struct blk_mq_hw_ctx, dispatch_wait);
spin_lock(&hctx->dispatch_wait_lock);
- list_del_init(&wait->entry);
+ if (!list_empty(&wait->entry)) {
+ struct sbitmap_queue *sbq;
+
+ list_del_init(&wait->entry);
+ sbq = &hctx->tags->bitmap_tags;
+ atomic_dec(&sbq->ws_active);
+ }
spin_unlock(&hctx->dispatch_wait_lock);
blk_mq_run_hw_queue(hctx, true);
static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx,
struct request *rq)
{
+ struct sbitmap_queue *sbq = &hctx->tags->bitmap_tags;
struct wait_queue_head *wq;
wait_queue_entry_t *wait;
bool ret;
if (!list_empty_careful(&wait->entry))
return false;
- wq = &bt_wait_ptr(&hctx->tags->bitmap_tags, hctx)->wait;
+ wq = &bt_wait_ptr(sbq, hctx)->wait;
spin_lock_irq(&wq->lock);
spin_lock(&hctx->dispatch_wait_lock);
return false;
}
+ atomic_inc(&sbq->ws_active);
wait->flags &= ~WQ_FLAG_EXCLUSIVE;
__add_wait_queue(wq, wait);
* someone else gets the wakeup.
*/
list_del_init(&wait->entry);
+ atomic_dec(&sbq->ws_active);
spin_unlock(&hctx->dispatch_wait_lock);
spin_unlock_irq(&wq->lock);
unsigned int depth;
list_splice_init(&plug->mq_list, &list);
- plug->rq_count = 0;
if (plug->rq_count > 2 && plug->multiple_queues)
list_sort(NULL, &list, plug_rq_cmp);
+ plug->rq_count = 0;
+
this_q = NULL;
this_hctx = NULL;
this_ctx = NULL;
return ret;
}
-blk_status_t blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
+static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
struct request *rq,
blk_qc_t *cookie,
- bool bypass, bool last)
+ bool bypass_insert, bool last)
{
struct request_queue *q = rq->q;
bool run_queue = true;
- blk_status_t ret = BLK_STS_RESOURCE;
- int srcu_idx;
- bool force = false;
- hctx_lock(hctx, &srcu_idx);
/*
- * hctx_lock is needed before checking quiesced flag.
+ * RCU or SRCU read lock is needed before checking quiesced flag.
*
- * When queue is stopped or quiesced, ignore 'bypass', insert
- * and return BLK_STS_OK to caller, and avoid driver to try to
- * dispatch again.
+ * When queue is stopped or quiesced, ignore 'bypass_insert' from
+ * blk_mq_request_issue_directly(), and return BLK_STS_OK to caller,
+ * and avoid driver to try to dispatch again.
*/
- if (unlikely(blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q))) {
+ if (blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q)) {
run_queue = false;
- bypass = false;
- goto out_unlock;
+ bypass_insert = false;
+ goto insert;
}
- if (unlikely(q->elevator && !bypass))
- goto out_unlock;
+ if (q->elevator && !bypass_insert)
+ goto insert;
if (!blk_mq_get_dispatch_budget(hctx))
- goto out_unlock;
+ goto insert;
if (!blk_mq_get_driver_tag(rq)) {
blk_mq_put_dispatch_budget(hctx);
- goto out_unlock;
+ goto insert;
}
- /*
- * Always add a request that has been through
- *.queue_rq() to the hardware dispatch list.
- */
- force = true;
- ret = __blk_mq_issue_directly(hctx, rq, cookie, last);
-out_unlock:
+ return __blk_mq_issue_directly(hctx, rq, cookie, last);
+insert:
+ if (bypass_insert)
+ return BLK_STS_RESOURCE;
+
+ blk_mq_request_bypass_insert(rq, run_queue);
+ return BLK_STS_OK;
+}
+
+static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
+ struct request *rq, blk_qc_t *cookie)
+{
+ blk_status_t ret;
+ int srcu_idx;
+
+ might_sleep_if(hctx->flags & BLK_MQ_F_BLOCKING);
+
+ hctx_lock(hctx, &srcu_idx);
+
+ ret = __blk_mq_try_issue_directly(hctx, rq, cookie, false, true);
+ if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE)
+ blk_mq_request_bypass_insert(rq, true);
+ else if (ret != BLK_STS_OK)
+ blk_mq_end_request(rq, ret);
+
+ hctx_unlock(hctx, srcu_idx);
+}
+
+blk_status_t blk_mq_request_issue_directly(struct request *rq, bool last)
+{
+ blk_status_t ret;
+ int srcu_idx;
+ blk_qc_t unused_cookie;
+ struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
+
+ hctx_lock(hctx, &srcu_idx);
+ ret = __blk_mq_try_issue_directly(hctx, rq, &unused_cookie, true, last);
hctx_unlock(hctx, srcu_idx);
- switch (ret) {
- case BLK_STS_OK:
- break;
- case BLK_STS_DEV_RESOURCE:
- case BLK_STS_RESOURCE:
- if (force) {
- blk_mq_request_bypass_insert(rq, run_queue);
- /*
- * We have to return BLK_STS_OK for the DM
- * to avoid livelock. Otherwise, we return
- * the real result to indicate whether the
- * request is direct-issued successfully.
- */
- ret = bypass ? BLK_STS_OK : ret;
- } else if (!bypass) {
- blk_mq_sched_insert_request(rq, false,
- run_queue, false);
- }
- break;
- default:
- if (!bypass)
- blk_mq_end_request(rq, ret);
- break;
- }
return ret;
}
void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
struct list_head *list)
{
- blk_qc_t unused;
- blk_status_t ret = BLK_STS_OK;
-
while (!list_empty(list)) {
+ blk_status_t ret;
struct request *rq = list_first_entry(list, struct request,
queuelist);
list_del_init(&rq->queuelist);
- if (ret == BLK_STS_OK)
- ret = blk_mq_try_issue_directly(hctx, rq, &unused,
- false,
+ ret = blk_mq_request_issue_directly(rq, list_empty(list));
+ if (ret != BLK_STS_OK) {
+ if (ret == BLK_STS_RESOURCE ||
+ ret == BLK_STS_DEV_RESOURCE) {
+ blk_mq_request_bypass_insert(rq,
list_empty(list));
- else
- blk_mq_sched_insert_request(rq, false, true, false);
+ break;
+ }
+ blk_mq_end_request(rq, ret);
+ }
}
/*
* the driver there was more coming, but that turned out to
* be a lie.
*/
- if (ret != BLK_STS_OK && hctx->queue->mq_ops->commit_rqs)
+ if (!list_empty(list) && hctx->queue->mq_ops->commit_rqs)
hctx->queue->mq_ops->commit_rqs(hctx);
}
plug->rq_count--;
}
blk_add_rq_to_plug(plug, rq);
+ trace_block_plug(q);
blk_mq_put_ctx(data.ctx);
if (same_queue_rq) {
data.hctx = same_queue_rq->mq_hctx;
+ trace_block_unplug(q, 1, true);
blk_mq_try_issue_directly(data.hctx, same_queue_rq,
- &cookie, false, true);
+ &cookie);
}
} else if ((q->nr_hw_queues > 1 && is_sync) || (!q->elevator &&
!data.hctx->dispatch_busy)) {
blk_mq_put_ctx(data.ctx);
blk_mq_bio_to_request(rq, bio);
- blk_mq_try_issue_directly(data.hctx, rq, &cookie, false, true);
+ blk_mq_try_issue_directly(data.hctx, rq, &cookie);
} else {
blk_mq_put_ctx(data.ctx);
blk_mq_bio_to_request(rq, bio);
return 0;
free_fq:
- kfree(hctx->fq);
+ blk_free_flush_queue(hctx->fq);
exit_hctx:
if (set->ops->exit_hctx)
set->ops->exit_hctx(hctx, hctx_idx);
void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
struct list_head *list);
-blk_status_t blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
- struct request *rq,
- blk_qc_t *cookie,
- bool bypass, bool last);
+/* Used by blk_insert_cloned_request() to issue request directly */
+blk_status_t blk_mq_request_issue_directly(struct request *rq, bool last);
void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
struct list_head *list);
}
}
-static inline void blk_mq_put_driver_tag_hctx(struct blk_mq_hw_ctx *hctx,
- struct request *rq)
-{
- if (rq->tag == -1 || rq->internal_tag == -1)
- return;
-
- __blk_mq_put_driver_tag(hctx, rq);
-}
-
static inline void blk_mq_put_driver_tag(struct request *rq)
{
if (rq->tag == -1 || rq->internal_tag == -1)
ACPI_FUNCTION_TRACE(ev_enable_gpe);
- /* Enable the requested GPE */
+ /* Clear the GPE status */
+ status = acpi_hw_clear_gpe(gpe_event_info);
+ if (ACPI_FAILURE(status))
+ return_ACPI_STATUS(status);
+ /* Enable the requested GPE */
status = acpi_hw_low_set_gpe(gpe_event_info, ACPI_GPE_ENABLE);
return_ACPI_STATUS(status);
}
}
}
+ if (obj_desc->common.type == ACPI_TYPE_REGION) {
+ acpi_ut_remove_address_range(obj_desc->region.space_id, node);
+ }
+
/* Clear the Node entry in all cases */
node->object = NULL;
acpi_permanent_mmap = true;
- /* Initialize debug output. Linux does not use ACPICA defaults */
- acpi_dbg_level = ACPI_LV_INFO | ACPI_LV_REPAIR;
-
#ifdef CONFIG_X86
/*
* If the machine falls into the DMI check table,
cpc_read(cpunum, nominal_reg, &nom);
perf_caps->nominal_perf = nom;
- cpc_read(cpunum, guaranteed_reg, &guaranteed);
- perf_caps->guaranteed_perf = guaranteed;
+ if (guaranteed_reg->type != ACPI_TYPE_BUFFER ||
+ IS_NULL_REG(&guaranteed_reg->cpc_entry.reg)) {
+ perf_caps->guaranteed_perf = 0;
+ } else {
+ cpc_read(cpunum, guaranteed_reg, &guaranteed);
+ perf_caps->guaranteed_perf = guaranteed;
+ }
cpc_read(cpunum, lowest_non_linear_reg, &min_nonlinear);
perf_caps->lowest_nonlinear_perf = min_nonlinear;
goto out;
}
+ dev_dbg(dev, "%s cmd: %s output length: %d\n", dimm_name,
+ cmd_name, out_obj->buffer.length);
+ print_hex_dump_debug(cmd_name, DUMP_PREFIX_OFFSET, 4, 4,
+ out_obj->buffer.pointer,
+ min_t(u32, 128, out_obj->buffer.length), true);
+
if (call_pkg) {
call_pkg->nd_fw_size = out_obj->buffer.length;
memcpy(call_pkg->nd_payload + call_pkg->nd_size_in,
return 0;
}
- dev_dbg(dev, "%s cmd: %s output length: %d\n", dimm_name,
- cmd_name, out_obj->buffer.length);
- print_hex_dump_debug(cmd_name, DUMP_PREFIX_OFFSET, 4, 4,
- out_obj->buffer.pointer,
- min_t(u32, 128, out_obj->buffer.length), true);
-
for (i = 0, offset = 0; i < desc->out_num; i++) {
u32 out_size = nd_cmd_out_size(nvdimm, cmd, desc, i, buf,
(u32 *) out_obj->buffer.pointer,
if (!test_bit(cmd, &nfit_mem->dsm_mask))
return -ENOTTY;
- if (old_data)
- memcpy(nd_cmd.cmd.old_pass, old_data->data,
- sizeof(nd_cmd.cmd.old_pass));
+ memcpy(nd_cmd.cmd.old_pass, old_data->data,
+ sizeof(nd_cmd.cmd.old_pass));
memcpy(nd_cmd.cmd.new_pass, new_data->data,
sizeof(nd_cmd.cmd.new_pass));
rc = nvdimm_ctl(nvdimm, ND_CMD_CALL, &nd_cmd, sizeof(nd_cmd), NULL);
/* flush all cache before we erase DIMM */
nvdimm_invalidate_cache();
- if (nkey)
- memcpy(nd_cmd.cmd.passphrase, nkey->data,
- sizeof(nd_cmd.cmd.passphrase));
+ memcpy(nd_cmd.cmd.passphrase, nkey->data,
+ sizeof(nd_cmd.cmd.passphrase));
rc = nvdimm_ctl(nvdimm, ND_CMD_CALL, &nd_cmd, sizeof(nd_cmd), NULL);
if (rc < 0)
return rc;
size_t object_size = 0;
read_size = min_t(size_t, sizeof(*object), buffer->data_size - offset);
- if (read_size < sizeof(*hdr) || !IS_ALIGNED(offset, sizeof(u32)))
+ if (offset > buffer->data_size || read_size < sizeof(*hdr) ||
+ !IS_ALIGNED(offset, sizeof(u32)))
return 0;
binder_alloc_copy_from_buffer(&proc->alloc, object, buffer,
offset, read_size);
index = page - alloc->pages;
page_addr = (uintptr_t)alloc->buffer + index * PAGE_SIZE;
+
+ mm = alloc->vma_vm_mm;
+ if (!mmget_not_zero(mm))
+ goto err_mmget;
+ if (!down_write_trylock(&mm->mmap_sem))
+ goto err_down_write_mmap_sem_failed;
vma = binder_alloc_get_vma(alloc);
- if (vma) {
- if (!mmget_not_zero(alloc->vma_vm_mm))
- goto err_mmget;
- mm = alloc->vma_vm_mm;
- if (!down_read_trylock(&mm->mmap_sem))
- goto err_down_write_mmap_sem_failed;
- }
list_lru_isolate(lru, item);
spin_unlock(lock);
zap_page_range(vma, page_addr, PAGE_SIZE);
trace_binder_unmap_user_end(alloc, index);
-
- up_read(&mm->mmap_sem);
- mmput(mm);
}
+ up_write(&mm->mmap_sem);
+ mmput(mm);
trace_binder_unmap_kernel_start(alloc, index);
/* Per the spec, only slot type and drawer type ODD can be supported */
static enum odd_mech_type zpodd_get_mech_type(struct ata_device *dev)
{
- char buf[16];
+ char *buf;
unsigned int ret;
- struct rm_feature_desc *desc = (void *)(buf + 8);
+ struct rm_feature_desc *desc;
struct ata_taskfile tf;
static const char cdb[] = { GPCMD_GET_CONFIGURATION,
2, /* only 1 feature descriptor requested */
0, 3, /* 3, removable medium feature */
0, 0, 0,/* reserved */
- 0, sizeof(buf),
+ 0, 16,
0, 0, 0,
};
+ buf = kzalloc(16, GFP_KERNEL);
+ if (!buf)
+ return ODD_MECH_TYPE_UNSUPPORTED;
+ desc = (void *)(buf + 8);
+
ata_tf_init(dev, &tf);
tf.flags = ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE;
tf.command = ATA_CMD_PACKET;
tf.protocol = ATAPI_PROT_PIO;
- tf.lbam = sizeof(buf);
+ tf.lbam = 16;
ret = ata_exec_internal(dev, &tf, cdb, DMA_FROM_DEVICE,
- buf, sizeof(buf), 0);
- if (ret)
+ buf, 16, 0);
+ if (ret) {
+ kfree(buf);
return ODD_MECH_TYPE_UNSUPPORTED;
+ }
- if (be16_to_cpu(desc->feature_code) != 3)
+ if (be16_to_cpu(desc->feature_code) != 3) {
+ kfree(buf);
return ODD_MECH_TYPE_UNSUPPORTED;
+ }
- if (desc->mech_type == 0 && desc->load == 0 && desc->eject == 1)
+ if (desc->mech_type == 0 && desc->load == 0 && desc->eject == 1) {
+ kfree(buf);
return ODD_MECH_TYPE_SLOT;
- else if (desc->mech_type == 1 && desc->load == 0 && desc->eject == 1)
+ } else if (desc->mech_type == 1 && desc->load == 0 &&
+ desc->eject == 1) {
+ kfree(buf);
return ODD_MECH_TYPE_DRAWER;
- else
+ } else {
+ kfree(buf);
return ODD_MECH_TYPE_UNSUPPORTED;
+ }
}
/* Test if ODD is zero power ready by sense code */
return -EINVAL;
}
+ if (g_home_node != NUMA_NO_NODE && g_home_node >= nr_online_nodes) {
+ pr_err("null_blk: invalid home_node value\n");
+ g_home_node = NUMA_NO_NODE;
+ }
+
if (g_queue_mode == NULL_Q_RQ) {
pr_err("null_blk: legacy IO path no longer available\n");
return -EINVAL;
disk->queue = blk_mq_init_sq_queue(&cd->tag_set, &pcd_mq_ops,
1, BLK_MQ_F_SHOULD_MERGE);
if (IS_ERR(disk->queue)) {
+ put_disk(disk);
disk->queue = NULL;
continue;
}
printk("%s: No CD-ROM drive found\n", name);
for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) {
+ if (!cd->disk)
+ continue;
blk_cleanup_queue(cd->disk->queue);
cd->disk->queue = NULL;
blk_mq_free_tag_set(&cd->tag_set);
pcd_probe_capabilities();
if (register_blkdev(major, name)) {
- for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++)
+ for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) {
+ if (!cd->disk)
+ continue;
+
+ blk_cleanup_queue(cd->disk->queue);
+ blk_mq_free_tag_set(&cd->tag_set);
put_disk(cd->disk);
+ }
return -EBUSY;
}
int unit;
for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) {
+ if (!cd->disk)
+ continue;
+
if (cd->present) {
del_gendisk(cd->disk);
pi_release(cd->pi);
printk("%s: No ATAPI disk detected\n", name);
for (pf = units, unit = 0; unit < PF_UNITS; pf++, unit++) {
+ if (!pf->disk)
+ continue;
blk_cleanup_queue(pf->disk->queue);
pf->disk->queue = NULL;
blk_mq_free_tag_set(&pf->tag_set);
pf_busy = 0;
if (register_blkdev(major, name)) {
- for (pf = units, unit = 0; unit < PF_UNITS; pf++, unit++)
+ for (pf = units, unit = 0; unit < PF_UNITS; pf++, unit++) {
+ if (!pf->disk)
+ continue;
+ blk_cleanup_queue(pf->disk->queue);
+ blk_mq_free_tag_set(&pf->tag_set);
put_disk(pf->disk);
+ }
return -EBUSY;
}
int unit;
unregister_blkdev(major, name);
for (pf = units, unit = 0; unit < PF_UNITS; pf++, unit++) {
+ if (!pf->disk)
+ continue;
+
if (pf->present)
del_gendisk(pf->disk);
if (err)
num_vqs = 1;
+ num_vqs = min_t(unsigned int, nr_cpu_ids, num_vqs);
+
vblk->vqs = kmalloc_array(num_vqs, sizeof(*vblk->vqs), GFP_KERNEL);
if (!vblk->vqs)
return -ENOMEM;
return 0;
err_read:
+ /* prevent double queue cleanup */
+ ace->gd->queue = NULL;
put_disk(ace->gd);
err_alloc_disk:
blk_cleanup_queue(ace->queue);
struct zram *zram = dev_to_zram(dev);
unsigned long nr_pages = zram->disksize >> PAGE_SHIFT;
int index;
- char mode_buf[8];
- ssize_t sz;
- sz = strscpy(mode_buf, buf, sizeof(mode_buf));
- if (sz <= 0)
- return -EINVAL;
-
- /* ignore trailing new line */
- if (mode_buf[sz - 1] == '\n')
- mode_buf[sz - 1] = 0x00;
-
- if (strcmp(mode_buf, "all"))
+ if (!sysfs_streq(buf, "all"))
return -EINVAL;
down_read(&zram->init_lock);
struct bio bio;
struct bio_vec bio_vec;
struct page *page;
- ssize_t ret, sz;
- char mode_buf[8];
- int mode = -1;
+ ssize_t ret;
+ int mode;
unsigned long blk_idx = 0;
- sz = strscpy(mode_buf, buf, sizeof(mode_buf));
- if (sz <= 0)
- return -EINVAL;
-
- /* ignore trailing newline */
- if (mode_buf[sz - 1] == '\n')
- mode_buf[sz - 1] = 0x00;
-
- if (!strcmp(mode_buf, "idle"))
+ if (sysfs_streq(buf, "idle"))
mode = IDLE_WRITEBACK;
- else if (!strcmp(mode_buf, "huge"))
+ else if (sysfs_streq(buf, "huge"))
mode = HUGE_WRITEBACK;
-
- if (mode == -1)
+ else
return -EINVAL;
down_read(&zram->init_lock);
return 0;
}
+ irq_set_status_flags(irq, IRQ_NOAUTOEN);
ret = devm_request_irq(&hdev->dev, irq, btusb_oob_wake_handler,
0, "OOB Wake-on-BT", data);
if (ret) {
}
data->oob_wake_irq = irq;
- disable_irq(irq);
bt_dev_info(hdev, "OOB Wake-on-BT configured at IRQ %u", irq);
return 0;
}
config R3964
tristate "Siemens R3964 line discipline"
- depends on TTY
+ depends on TTY && BROKEN
---help---
This driver allows synchronous communication with devices using the
Siemens R3964 packet protocol. Unless you are dealing with special
return;
}
- memset(&p, 0, sizeof(p));
p.addr = base_addr;
p.space = space;
p.regspacing = offset;
/* Does this interface receive IPMI events? */
bool gets_events;
+
+ /* Free must run in process context for RCU cleanup. */
+ struct work_struct remove_work;
};
static struct ipmi_user *acquire_ipmi_user(struct ipmi_user *user, int *index)
return rv;
}
+static void free_user_work(struct work_struct *work)
+{
+ struct ipmi_user *user = container_of(work, struct ipmi_user,
+ remove_work);
+
+ cleanup_srcu_struct(&user->release_barrier);
+ kfree(user);
+}
+
int ipmi_create_user(unsigned int if_num,
const struct ipmi_user_hndl *handler,
void *handler_data,
goto out_kfree;
found:
+ INIT_WORK(&new_user->remove_work, free_user_work);
+
rv = init_srcu_struct(&new_user->release_barrier);
if (rv)
goto out_kfree;
static void free_user(struct kref *ref)
{
struct ipmi_user *user = container_of(ref, struct ipmi_user, refcount);
- cleanup_srcu_struct(&user->release_barrier);
- kfree(user);
+
+ /* SRCU cleanup must happen in task context. */
+ schedule_work(&user->remove_work);
}
static void _ipmi_destroy_user(struct ipmi_user *user)
char *str;
char *si_type[SI_MAX_PARMS];
+ memset(si_type, 0, sizeof(si_type));
+
/* Parse out the si_type string into its components. */
str = si_type_str;
if (*str != '\0') {
*
* Returns size of the event. If it is an invalid event, returns 0.
*/
-static int calc_tpm2_event_size(struct tcg_pcr_event2_head *event,
- struct tcg_pcr_event *event_header)
+static size_t calc_tpm2_event_size(struct tcg_pcr_event2_head *event,
+ struct tcg_pcr_event *event_header)
{
struct tcg_efi_specid_event_head *efispecid;
struct tcg_event_field *event_field;
__poll_t mask = 0;
poll_wait(file, &priv->async_wait, wait);
+ mutex_lock(&priv->buffer_mutex);
- if (!priv->response_read || priv->response_length)
+ /*
+ * The response_length indicates if there is still response
+ * (or part of it) to be consumed. Partial reads decrease it
+ * by the number of bytes read, and write resets it the zero.
+ */
+ if (priv->response_length)
mask = EPOLLIN | EPOLLRDNORM;
else
mask = EPOLLOUT | EPOLLWRNORM;
+ mutex_unlock(&priv->buffer_mutex);
return mask;
}
if (chip->flags & TPM_CHIP_FLAG_ALWAYS_POWERED)
return 0;
- if (chip->flags & TPM_CHIP_FLAG_TPM2) {
- mutex_lock(&chip->tpm_mutex);
- if (!tpm_chip_start(chip)) {
+ if (!tpm_chip_start(chip)) {
+ if (chip->flags & TPM_CHIP_FLAG_TPM2)
tpm2_shutdown(chip, TPM2_SU_STATE);
- tpm_chip_stop(chip);
- }
- mutex_unlock(&chip->tpm_mutex);
- } else {
- rc = tpm1_pm_suspend(chip, tpm_suspend_pcr);
+ else
+ rc = tpm1_pm_suspend(chip, tpm_suspend_pcr);
+
+ tpm_chip_stop(chip);
}
return rc;
#define PROG_ID_MAX 7
#define PROG_STATUS_MASK(id) (1 << ((id) + 8))
-#define PROG_PRES_MASK 0x7
-#define PROG_PRES(layout, pckr) ((pckr >> layout->pres_shift) & PROG_PRES_MASK)
+#define PROG_PRES(layout, pckr) ((pckr >> layout->pres_shift) & layout->pres_mask)
#define PROG_MAX_RM9200_CSS 3
struct clk_programmable {
unsigned long parent_rate)
{
struct clk_programmable *prog = to_clk_programmable(hw);
+ const struct clk_programmable_layout *layout = prog->layout;
unsigned int pckr;
+ unsigned long rate;
regmap_read(prog->regmap, AT91_PMC_PCKR(prog->id), &pckr);
- return parent_rate >> PROG_PRES(prog->layout, pckr);
+ if (layout->is_pres_direct)
+ rate = parent_rate / (PROG_PRES(layout, pckr) + 1);
+ else
+ rate = parent_rate >> PROG_PRES(layout, pckr);
+
+ return rate;
}
static int clk_programmable_determine_rate(struct clk_hw *hw,
struct clk_rate_request *req)
{
+ struct clk_programmable *prog = to_clk_programmable(hw);
+ const struct clk_programmable_layout *layout = prog->layout;
struct clk_hw *parent;
long best_rate = -EINVAL;
unsigned long parent_rate;
- unsigned long tmp_rate;
+ unsigned long tmp_rate = 0;
int shift;
int i;
continue;
parent_rate = clk_hw_get_rate(parent);
- for (shift = 0; shift < PROG_PRES_MASK; shift++) {
- tmp_rate = parent_rate >> shift;
- if (tmp_rate <= req->rate)
- break;
+ if (layout->is_pres_direct) {
+ for (shift = 0; shift <= layout->pres_mask; shift++) {
+ tmp_rate = parent_rate / (shift + 1);
+ if (tmp_rate <= req->rate)
+ break;
+ }
+ } else {
+ for (shift = 0; shift < layout->pres_mask; shift++) {
+ tmp_rate = parent_rate >> shift;
+ if (tmp_rate <= req->rate)
+ break;
+ }
}
if (tmp_rate > req->rate)
if (!div)
return -EINVAL;
- shift = fls(div) - 1;
+ if (layout->is_pres_direct) {
+ shift = div - 1;
- if (div != (1 << shift))
- return -EINVAL;
+ if (shift > layout->pres_mask)
+ return -EINVAL;
+ } else {
+ shift = fls(div) - 1;
- if (shift >= PROG_PRES_MASK)
- return -EINVAL;
+ if (div != (1 << shift))
+ return -EINVAL;
+
+ if (shift >= layout->pres_mask)
+ return -EINVAL;
+ }
regmap_update_bits(prog->regmap, AT91_PMC_PCKR(prog->id),
- PROG_PRES_MASK << layout->pres_shift,
+ layout->pres_mask << layout->pres_shift,
shift << layout->pres_shift);
return 0;
}
const struct clk_programmable_layout at91rm9200_programmable_layout = {
+ .pres_mask = 0x7,
.pres_shift = 2,
.css_mask = 0x3,
.have_slck_mck = 0,
+ .is_pres_direct = 0,
};
const struct clk_programmable_layout at91sam9g45_programmable_layout = {
+ .pres_mask = 0x7,
.pres_shift = 2,
.css_mask = 0x3,
.have_slck_mck = 1,
+ .is_pres_direct = 0,
};
const struct clk_programmable_layout at91sam9x5_programmable_layout = {
+ .pres_mask = 0x7,
.pres_shift = 4,
.css_mask = 0x7,
.have_slck_mck = 0,
+ .is_pres_direct = 0,
};
};
struct clk_programmable_layout {
+ u8 pres_mask;
u8 pres_shift;
u8 css_mask;
u8 have_slck_mck;
+ u8 is_pres_direct;
};
extern const struct clk_programmable_layout at91rm9200_programmable_layout;
.pll = true },
};
+static const struct clk_programmable_layout sama5d2_programmable_layout = {
+ .pres_mask = 0xff,
+ .pres_shift = 4,
+ .css_mask = 0x7,
+ .have_slck_mck = 0,
+ .is_pres_direct = 1,
+};
+
static void __init sama5d2_pmc_setup(struct device_node *np)
{
struct clk_range range = CLK_RANGE(0, 0);
hw = at91_clk_register_programmable(regmap, name,
parent_names, 6, i,
- &at91sam9x5_programmable_layout);
+ &sama5d2_programmable_layout);
if (IS_ERR(hw))
goto err_free;
}
switch (pll_clk->type) {
case PLL_1416X:
- if (!pll->rate_table)
+ if (!pll_clk->rate_table)
init.ops = &clk_pll1416x_min_ops;
else
init.ops = &clk_pll1416x_ops;
return ERR_PTR(-ENOMEM);
init.name = name;
- init.flags = CLK_SET_RATE_PARENT;
+ init.flags = flags | CLK_SET_RATE_PARENT;
init.parent_names = parent_name ? &parent_name : NULL;
init.num_parents = parent_name ? 1 : 0;
init.ops = ops;
- init.flags = flags;
cg->regmap = regmap;
cg->set_ofs = set_ofs;
return true;
} else {
/* Round down */
- if (now < rate && best < now)
+ if (now <= rate && best < now)
return true;
}
/* VPU Clock */
static const char * const g12a_vpu_parent_names[] = {
- "fclk_div4", "fclk_div3", "fclk_div5", "fclk_div7",
+ "fclk_div3", "fclk_div4", "fclk_div5", "fclk_div7",
"mpll1", "vid_pll", "hifi_pll", "gp0_pll",
};
static struct clk_regmap g12a_vpu_0_sel = {
.data = &(struct clk_regmap_mux_data){
.offset = HHI_VPU_CLK_CNTL,
- .mask = 0x3,
+ .mask = 0x7,
.shift = 9,
},
.hw.init = &(struct clk_init_data){
static struct clk_regmap g12a_vpu_1_sel = {
.data = &(struct clk_regmap_mux_data){
.offset = HHI_VPU_CLK_CNTL,
- .mask = 0x3,
+ .mask = 0x7,
.shift = 25,
},
.hw.init = &(struct clk_init_data){
.offset = HHI_VDEC_CLK_CNTL,
.shift = 0,
.width = 7,
+ .flags = CLK_DIVIDER_ROUND_CLOSEST,
},
.hw.init = &(struct clk_init_data){
.name = "vdec_1_div",
.offset = HHI_VDEC2_CLK_CNTL,
.shift = 16,
.width = 7,
+ .flags = CLK_DIVIDER_ROUND_CLOSEST,
},
.hw.init = &(struct clk_init_data){
.name = "vdec_hevc_div",
div = _get_table_val(meson_parm_read(clk->map, &pll_div->val),
meson_parm_read(clk->map, &pll_div->sel));
if (!div || !div->divider) {
- pr_info("%s: Invalid config value for vid_pll_div\n", __func__);
- return parent_rate;
+ pr_debug("%s: Invalid config value for vid_pll_div\n", __func__);
+ return 0;
}
return DIV_ROUND_UP_ULL(parent_rate * div->multiplier, div->divider);
};
static struct clk_plt *plt_clk_register(struct platform_device *pdev, int id,
- void __iomem *base,
+ const struct pmc_clk_data *pmc_data,
const char **parent_names,
int num_parents)
{
init.num_parents = num_parents;
pclk->hw.init = &init;
- pclk->reg = base + PMC_CLK_CTL_OFFSET + id * PMC_CLK_CTL_SIZE;
+ pclk->reg = pmc_data->base + PMC_CLK_CTL_OFFSET + id * PMC_CLK_CTL_SIZE;
spin_lock_init(&pclk->lock);
+ /*
+ * On some systems, the pmc_plt_clocks already enabled by the
+ * firmware are being marked as critical to avoid them being
+ * gated by the clock framework.
+ */
+ if (pmc_data->critical && plt_clk_is_enabled(&pclk->hw))
+ init.flags |= CLK_IS_CRITICAL;
+
ret = devm_clk_hw_register(&pdev->dev, &pclk->hw);
if (ret) {
pclk = ERR_PTR(ret);
return PTR_ERR(parent_names);
for (i = 0; i < PMC_CLK_NUM; i++) {
- data->clks[i] = plt_clk_register(pdev, i, pmc_data->base,
+ data->clks[i] = plt_clk_register(pdev, i, pmc_data,
parent_names, data->nparents);
if (IS_ERR(data->clks[i])) {
err = PTR_ERR(data->clks[i]);
if (ret)
return ret;
- return cppc_perf.guaranteed_perf;
+ if (cppc_perf.guaranteed_perf)
+ return cppc_perf.guaranteed_perf;
+
+ return cppc_perf.nominal_perf;
}
#else /* CONFIG_ACPI_CPPC_LIB */
const struct x86_cpu_id *id;
int rc;
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+ return -ENODEV;
+
if (no_load)
return -ENODEV;
} else {
id = x86_match_cpu(intel_pstate_cpu_ids);
if (!id) {
- pr_info("CPU ID not supported\n");
+ pr_info("CPU model not supported\n");
return -ENODEV;
}
clk_put(priv->clk);
dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &policy->freq_table);
- kfree(priv);
dev_pm_opp_remove_all_dynamic(priv->cpu_dev);
+ kfree(priv);
return 0;
}
if (ret)
goto unmap_ctx;
- if (mapped_nents) {
+ if (mapped_nents)
sg_to_sec4_sg_last(req->src, mapped_nents,
edesc->sec4_sg + sec4_sg_src_index,
0);
- if (*next_buflen)
- scatterwalk_map_and_copy(next_buf, req->src,
- to_hash - *buflen,
- *next_buflen, 0);
- } else {
+ else
sg_to_sec4_set_last(edesc->sec4_sg + sec4_sg_src_index -
1);
- }
+ if (*next_buflen)
+ scatterwalk_map_and_copy(next_buf, req->src,
+ to_hash - *buflen,
+ *next_buflen, 0);
desc = edesc->hw_desc;
edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg,
dmadev->nr_channels = nr_channels;
dmadev->nr_requests = nr_requests;
- ret = device_property_read_u32_array(&pdev->dev, "st,ahb-addr-masks",
+ device_property_read_u32_array(&pdev->dev, "st,ahb-addr-masks",
dmadev->ahb_addr_masks,
count);
- if (ret)
- return ret;
dmadev->nr_ahb_addr_masks = count;
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
if (err < 0)
goto out;
- if (err & BIT(pos))
- err = -EACCES;
+ if (value & BIT(pos)) {
+ err = -EPERM;
+ goto out;
+ }
err = 0;
gpio->offset_timer =
devm_kzalloc(&pdev->dev, gpio->chip.ngpio, GFP_KERNEL);
+ if (!gpio->offset_timer)
+ return -ENOMEM;
return aspeed_gpio_setup_irqs(gpio, pdev);
}
mutex_init(&exar_gpio->lock);
index = ida_simple_get(&ida_index, 0, 0, GFP_KERNEL);
+ if (index < 0)
+ goto err_destroy;
sprintf(exar_gpio->name, "exar_gpio%d", index);
exar_gpio->gpio_chip.label = exar_gpio->name;
struct gpio_mockup_chip *chip;
struct seq_file *sfile;
struct gpio_chip *gc;
+ int val, cnt;
char buf[3];
- int val, rv;
if (*ppos != 0)
return 0;
gc = &chip->gc;
val = gpio_mockup_get(gc, priv->offset);
- snprintf(buf, sizeof(buf), "%d\n", val);
+ cnt = snprintf(buf, sizeof(buf), "%d\n", val);
- rv = copy_to_user(usr_buf, buf, sizeof(buf));
- if (rv)
- return rv;
-
- return sizeof(buf) - 1;
+ return simple_read_from_buffer(usr_buf, size, ppos, buf, cnt);
}
static ssize_t gpio_mockup_debugfs_write(struct file *file,
* to determine if the flags should have inverted semantics.
*/
if (IS_ENABLED(CONFIG_SPI_MASTER) &&
- of_property_read_bool(np, "cs-gpios")) {
+ of_property_read_bool(np, "cs-gpios") &&
+ !strcmp(propname, "cs-gpios")) {
struct device_node *child;
u32 cs;
int ret;
* conflict and the "spi-cs-high" flag will
* take precedence.
*/
- if (of_property_read_bool(np, "spi-cs-high")) {
+ if (of_property_read_bool(child, "spi-cs-high")) {
if (*flags & OF_GPIO_ACTIVE_LOW) {
pr_warn("%s GPIO handle specifies active low - ignored\n",
- of_node_full_name(np));
+ of_node_full_name(child));
*flags &= ~OF_GPIO_ACTIVE_LOW;
}
} else {
if (!(*flags & OF_GPIO_ACTIVE_LOW))
pr_info("%s enforce active low on chipselect handle\n",
- of_node_full_name(np));
+ of_node_full_name(child));
*flags |= OF_GPIO_ACTIVE_LOW;
}
break;
of_node_get(chip->of_node);
- return of_gpiochip_scan_gpios(chip);
+ status = of_gpiochip_scan_gpios(chip);
+ if (status) {
+ of_node_put(chip->of_node);
+ gpiochip_remove_pin_ranges(chip);
+ }
+
+ return status;
}
void of_gpiochip_remove(struct gpio_chip *chip)
}
config = pinconf_to_config_packed(PIN_CONFIG_INPUT_DEBOUNCE, debounce);
- return gpio_set_config(chip, gpio_chip_hwgpio(desc), config);
+ return chip->set_config(chip, gpio_chip_hwgpio(desc), config);
}
EXPORT_SYMBOL_GPL(gpiod_set_debounce);
packed = pinconf_to_config_packed(PIN_CONFIG_PERSIST_STATE,
!transitory);
gpio = gpio_chip_hwgpio(desc);
- rc = gpio_set_config(chip, gpio, packed);
+ rc = chip->set_config(chip, gpio, packed);
if (rc == -ENOTSUPP) {
dev_dbg(&desc->gdev->dev, "Persistence not supported for GPIO %d\n",
gpio);
break;
if (fence) {
- r = dma_fence_wait_timeout(fence, false, tmo);
+ tmo = dma_fence_wait_timeout(fence, false, tmo);
dma_fence_put(fence);
fence = next;
- if (r <= 0)
+ if (tmo == 0) {
+ r = -ETIMEDOUT;
break;
+ } else if (tmo < 0) {
+ r = tmo;
+ break;
+ }
} else {
fence = next;
}
tmo = dma_fence_wait_timeout(fence, false, tmo);
dma_fence_put(fence);
- if (r <= 0 || tmo <= 0) {
- DRM_ERROR("recover vram bo from shadow failed\n");
+ if (r < 0 || tmo <= 0) {
+ DRM_ERROR("recover vram bo from shadow failed, r is %ld, tmo is %ld\n", r, tmo);
return -EIO;
}
struct pci_dev *pdev = adev->pdev;
enum pci_bus_speed cur_speed;
enum pcie_link_width cur_width;
+ u32 ret = 1;
*speed = PCI_SPEED_UNKNOWN;
*width = PCIE_LNK_WIDTH_UNKNOWN;
while (pdev) {
cur_speed = pcie_get_speed_cap(pdev);
cur_width = pcie_get_width_cap(pdev);
+ ret = pcie_bandwidth_available(adev->pdev, NULL,
+ NULL, &cur_width);
+ if (!ret)
+ cur_width = PCIE_LNK_WIDTH_RESRV;
if (cur_speed != PCI_SPEED_UNKNOWN) {
if (*speed == PCI_SPEED_UNKNOWN)
#include "amdgpu_trace.h"
#define AMDGPU_IB_TEST_TIMEOUT msecs_to_jiffies(1000)
+#define AMDGPU_IB_TEST_GFX_XGMI_TIMEOUT msecs_to_jiffies(2000)
/*
* IB
* cost waiting for it coming back under RUNTIME only
*/
tmo_gfx = 8 * AMDGPU_IB_TEST_TIMEOUT;
+ } else if (adev->gmc.xgmi.hive_id) {
+ tmo_gfx = AMDGPU_IB_TEST_GFX_XGMI_TIMEOUT;
}
for (i = 0; i < adev->num_rings; ++i) {
/* disable CG */
WREG32_SOC15(GC, 0, mmRLC_CGCG_CGLS_CTRL, 0);
- adev->gfx.rlc.funcs->reset(adev);
-
gfx_v9_0_init_pg(adev);
if (adev->firmware.load_type != AMDGPU_FW_LOAD_PSP) {
{ 0x9876, &carrizo_device_info }, /* Carrizo */
{ 0x9877, &carrizo_device_info }, /* Carrizo */
{ 0x15DD, &raven_device_info }, /* Raven */
+ { 0x15D8, &raven_device_info }, /* Raven */
#endif
{ 0x67A0, &hawaii_device_info }, /* Hawaii */
{ 0x67A1, &hawaii_device_info }, /* Hawaii */
amdgpu_crtc->cursor_width = plane->state->crtc_w;
amdgpu_crtc->cursor_height = plane->state->crtc_h;
+ memset(&attributes, 0, sizeof(attributes));
attributes.address.high_part = upper_32_bits(address);
attributes.address.low_part = lower_32_bits(address);
attributes.width = plane->state->crtc_w;
struct amdgpu_dm_connector *aconnector =
to_amdgpu_dm_connector(new_con_state->base.connector);
struct drm_display_mode *mode = &new_crtc_state->base.mode;
+ int vrefresh = drm_mode_vrefresh(mode);
new_crtc_state->vrr_supported = new_con_state->freesync_capable &&
- aconnector->min_vfreq <= drm_mode_vrefresh(mode);
+ vrefresh >= aconnector->min_vfreq &&
+ vrefresh <= aconnector->max_vfreq;
if (new_crtc_state->vrr_supported) {
new_crtc_state->stream->ignore_msa_timing_param = true;
void core_link_disable_stream(struct pipe_ctx *pipe_ctx, int option)
{
struct dc *core_dc = pipe_ctx->stream->ctx->dc;
+ struct dc_stream_state *stream = pipe_ctx->stream;
core_dc->hwss.blank_stream(pipe_ctx);
if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST)
deallocate_mst_payload(pipe_ctx);
+ if (dc_is_hdmi_signal(pipe_ctx->stream->signal))
+ dal_ddc_service_write_scdc_data(
+ stream->link->ddc, 0,
+ stream->timing.flags.LTE_340MCSC_SCRAMBLE);
+
core_dc->hwss.disable_stream(pipe_ctx, option);
disable_link(pipe_ctx->stream->link, pipe_ctx->stream->signal);
REG_UPDATE(CURSOR_CONTROL,
CURSOR_ENABLE, cur_en);
- //account for cases where we see negative offset relative to overlay plane
- if (src_x_offset < 0 && src_y_offset < 0) {
- REG_SET_2(CURSOR_POSITION, 0,
- CURSOR_X_POSITION, 0,
- CURSOR_Y_POSITION, 0);
- x_hotspot -= src_x_offset;
- y_hotspot -= src_y_offset;
- } else if (src_x_offset < 0) {
- REG_SET_2(CURSOR_POSITION, 0,
- CURSOR_X_POSITION, 0,
- CURSOR_Y_POSITION, pos->y);
- x_hotspot -= src_x_offset;
- } else if (src_y_offset < 0) {
- REG_SET_2(CURSOR_POSITION, 0,
+ REG_SET_2(CURSOR_POSITION, 0,
CURSOR_X_POSITION, pos->x,
- CURSOR_Y_POSITION, 0);
- y_hotspot -= src_y_offset;
- } else {
- REG_SET_2(CURSOR_POSITION, 0,
- CURSOR_X_POSITION, pos->x,
- CURSOR_Y_POSITION, pos->y);
- }
+ CURSOR_Y_POSITION, pos->y);
REG_SET_2(CURSOR_HOT_SPOT, 0,
CURSOR_HOT_SPOT_X, x_hotspot,
* MP0CLK DS
*/
data->registry_data.disallowed_features = 0xE0041C00;
+ /* ECC feature should be disabled on old SMUs */
+ smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetSmuVersion);
+ hwmgr->smu_version = smum_get_argument(hwmgr);
+ if (hwmgr->smu_version < 0x282100)
+ data->registry_data.disallowed_features |= FEATURE_ECC_MASK;
+
data->registry_data.od_state_in_dc_support = 0;
data->registry_data.thermal_support = 1;
data->registry_data.skip_baco_hardware = 0;
data->smu_features[GNLD_DS_MP1CLK].smu_feature_id = FEATURE_DS_MP1CLK_BIT;
data->smu_features[GNLD_DS_MP0CLK].smu_feature_id = FEATURE_DS_MP0CLK_BIT;
data->smu_features[GNLD_XGMI].smu_feature_id = FEATURE_XGMI_BIT;
+ data->smu_features[GNLD_ECC].smu_feature_id = FEATURE_ECC_BIT;
for (i = 0; i < GNLD_FEATURES_MAX; i++) {
data->smu_features[i].smu_feature_bitmap =
"FCLK_DS",
"MP1CLK_DS",
"MP0CLK_DS",
- "XGMI"};
+ "XGMI",
+ "ECC"};
static const char *output_title[] = {
"FEATURES",
"BITMASK",
struct vega20_single_dpm_table *dpm_table;
bool vblank_too_short = false;
bool disable_mclk_switching;
+ bool disable_fclk_switching;
uint32_t i, latency;
disable_mclk_switching = ((1 < hwmgr->display_config->num_display) &&
if (hwmgr->display_config->nb_pstate_switch_disable)
dpm_table->dpm_state.hard_min_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+ if ((disable_mclk_switching &&
+ (dpm_table->dpm_state.hard_min_level == dpm_table->dpm_levels[dpm_table->count - 1].value)) ||
+ hwmgr->display_config->min_mem_set_clock / 100 >= dpm_table->dpm_levels[dpm_table->count - 1].value)
+ disable_fclk_switching = true;
+ else
+ disable_fclk_switching = false;
+
/* fclk */
dpm_table = &(data->dpm_table.fclk_table);
dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[0].value;
dpm_table->dpm_state.soft_max_level = VG20_CLOCK_MAX_DEFAULT;
dpm_table->dpm_state.hard_min_level = dpm_table->dpm_levels[0].value;
dpm_table->dpm_state.hard_max_level = VG20_CLOCK_MAX_DEFAULT;
- if (hwmgr->display_config->nb_pstate_switch_disable)
+ if (hwmgr->display_config->nb_pstate_switch_disable || disable_fclk_switching)
dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
/* vclk */
GNLD_DS_MP1CLK,
GNLD_DS_MP0CLK,
GNLD_XGMI,
+ GNLD_ECC,
GNLD_FEATURES_MAX
};
#define FEATURE_DS_MP1CLK_BIT 30
#define FEATURE_DS_MP0CLK_BIT 31
#define FEATURE_XGMI_BIT 32
-#define FEATURE_SPARE_33_BIT 33
+#define FEATURE_ECC_BIT 33
#define FEATURE_SPARE_34_BIT 34
#define FEATURE_SPARE_35_BIT 35
#define FEATURE_SPARE_36_BIT 36
#define FEATURE_DS_FCLK_MASK (1 << FEATURE_DS_FCLK_BIT )
#define FEATURE_DS_MP1CLK_MASK (1 << FEATURE_DS_MP1CLK_BIT )
#define FEATURE_DS_MP0CLK_MASK (1 << FEATURE_DS_MP0CLK_BIT )
-#define FEATURE_XGMI_MASK (1 << FEATURE_XGMI_BIT )
+#define FEATURE_XGMI_MASK (1ULL << FEATURE_XGMI_BIT )
+#define FEATURE_ECC_MASK (1ULL << FEATURE_ECC_BIT )
#define DPM_OVERRIDE_DISABLE_SOCCLK_PID 0x00000001
#define DPM_OVERRIDE_DISABLE_UCLK_PID 0x00000002
}
EXPORT_SYMBOL_GPL(dw_hdmi_phy_i2c_write);
+/* Filter out invalid setups to avoid configuring SCDC and scrambling */
+static bool dw_hdmi_support_scdc(struct dw_hdmi *hdmi)
+{
+ struct drm_display_info *display = &hdmi->connector.display_info;
+
+ /* Completely disable SCDC support for older controllers */
+ if (hdmi->version < 0x200a)
+ return false;
+
+ /* Disable if SCDC is not supported, or if an HF-VSDB block is absent */
+ if (!display->hdmi.scdc.supported ||
+ !display->hdmi.scdc.scrambling.supported)
+ return false;
+
+ /*
+ * Disable if display only support low TMDS rates and scrambling
+ * for low rates is not supported either
+ */
+ if (!display->hdmi.scdc.scrambling.low_rates &&
+ display->max_tmds_clock <= 340000)
+ return false;
+
+ return true;
+}
+
/*
* HDMI2.0 Specifies the following procedure for High TMDS Bit Rates:
* - The Source shall suspend transmission of the TMDS clock and data
unsigned long mtmdsclock = hdmi->hdmi_data.video_mode.mtmdsclock;
/* Control for TMDS Bit Period/TMDS Clock-Period Ratio */
- if (hdmi->connector.display_info.hdmi.scdc.supported) {
+ if (dw_hdmi_support_scdc(hdmi)) {
if (mtmdsclock > HDMI14_MAX_TMDSCLK)
drm_scdc_set_high_tmds_clock_ratio(hdmi->ddc, 1);
else
/* Set up HDMI_FC_INVIDCONF */
inv_val = (hdmi->hdmi_data.hdcp_enable ||
- vmode->mtmdsclock > HDMI14_MAX_TMDSCLK ||
- hdmi_info->scdc.scrambling.low_rates ?
+ (dw_hdmi_support_scdc(hdmi) &&
+ (vmode->mtmdsclock > HDMI14_MAX_TMDSCLK ||
+ hdmi_info->scdc.scrambling.low_rates)) ?
HDMI_FC_INVIDCONF_HDCP_KEEPOUT_ACTIVE :
HDMI_FC_INVIDCONF_HDCP_KEEPOUT_INACTIVE);
}
/* Scrambling Control */
- if (hdmi_info->scdc.supported) {
+ if (dw_hdmi_support_scdc(hdmi)) {
if (vmode->mtmdsclock > HDMI14_MAX_TMDSCLK ||
hdmi_info->scdc.scrambling.low_rates) {
/*
funcs->atomic_disable(crtc, old_crtc_state);
else if (funcs->disable)
funcs->disable(crtc);
- else
+ else if (funcs->dpms)
funcs->dpms(crtc, DRM_MODE_DPMS_OFF);
if (!(dev->irq_enabled && dev->num_crtcs))
if (new_crtc_state->enable) {
DRM_DEBUG_ATOMIC("enabling [CRTC:%d:%s]\n",
crtc->base.id, crtc->name);
-
if (funcs->atomic_enable)
funcs->atomic_enable(crtc, old_crtc_state);
- else
+ else if (funcs->commit)
funcs->commit(crtc);
}
}
synchronize_srcu(&drm_unplug_srcu);
drm_dev_unregister(dev);
-
- mutex_lock(&drm_global_mutex);
- if (dev->open_count == 0)
- drm_dev_put(dev);
- mutex_unlock(&drm_global_mutex);
+ drm_dev_put(dev);
}
EXPORT_SYMBOL(drm_dev_unplug);
best_depth = fmt->depth;
}
}
- if (sizes.surface_depth != best_depth) {
+ if (sizes.surface_depth != best_depth && best_depth) {
DRM_INFO("requested bpp %d, scaled depth down to %d",
sizes.surface_bpp, best_depth);
sizes.surface_depth = best_depth;
drm_close_helper(filp);
- if (!--dev->open_count) {
+ if (!--dev->open_count)
drm_lastclose(dev);
- if (drm_dev_is_unplugged(dev))
- drm_put_dev(dev);
- }
+
mutex_unlock(&drm_global_mutex);
drm_minor_release(minor);
}
if (index_mode) {
- if (guest_gma >= I915_GTT_PAGE_SIZE / sizeof(u64)) {
+ if (guest_gma >= I915_GTT_PAGE_SIZE) {
ret = -EFAULT;
goto err;
}
/**
* intel_vgpu_emulate_hotplug - trigger hotplug event for vGPU
* @vgpu: a vGPU
- * @conncted: link state
+ * @connected: link state
*
* This function is used to trigger hotplug interrupt for vGPU
*
struct drm_i915_private *dev_priv = to_i915(dev);
struct intel_vgpu_primary_plane_format p;
struct intel_vgpu_cursor_plane_format c;
- int ret;
+ int ret, tile_height = 1;
if (plane_id == DRM_PLANE_TYPE_PRIMARY) {
ret = intel_vgpu_decode_primary_plane(vgpu, &p);
break;
case PLANE_CTL_TILED_X:
info->drm_format_mod = I915_FORMAT_MOD_X_TILED;
+ tile_height = 8;
break;
case PLANE_CTL_TILED_Y:
info->drm_format_mod = I915_FORMAT_MOD_Y_TILED;
+ tile_height = 32;
break;
case PLANE_CTL_TILED_YF:
info->drm_format_mod = I915_FORMAT_MOD_Yf_TILED;
+ tile_height = 32;
break;
default:
gvt_vgpu_err("invalid tiling mode: %x\n", p.tiled);
}
-
- info->size = (((p.stride * p.height * p.bpp) / 8) +
- (PAGE_SIZE - 1)) >> PAGE_SHIFT;
} else if (plane_id == DRM_PLANE_TYPE_CURSOR) {
ret = intel_vgpu_decode_cursor_plane(vgpu, &c);
if (ret)
info->x_hot = UINT_MAX;
info->y_hot = UINT_MAX;
}
-
- info->size = (((info->stride * c.height * c.bpp) / 8)
- + (PAGE_SIZE - 1)) >> PAGE_SHIFT;
} else {
gvt_vgpu_err("invalid plane id:%d\n", plane_id);
return -EINVAL;
}
+ info->size = (info->stride * roundup(info->height, tile_height)
+ + PAGE_SIZE - 1) >> PAGE_SHIFT;
if (info->size == 0) {
gvt_vgpu_err("fb size is zero\n");
return -EINVAL;
static void ppgtt_free_all_spt(struct intel_vgpu *vgpu)
{
- struct intel_vgpu_ppgtt_spt *spt;
+ struct intel_vgpu_ppgtt_spt *spt, *spn;
struct radix_tree_iter iter;
- void **slot;
+ LIST_HEAD(all_spt);
+ void __rcu **slot;
+ rcu_read_lock();
radix_tree_for_each_slot(slot, &vgpu->gtt.spt_tree, &iter, 0) {
spt = radix_tree_deref_slot(slot);
- ppgtt_free_spt(spt);
+ list_move(&spt->post_shadow_list, &all_spt);
}
+ rcu_read_unlock();
+
+ list_for_each_entry_safe(spt, spn, &all_spt, post_shadow_list)
+ ppgtt_free_spt(spt);
}
static int ppgtt_handle_guest_write_page_table_bytes(
}
list_add_tail(&mm->ppgtt_mm.list, &vgpu->gtt.ppgtt_mm_list_head);
+
+ mutex_lock(&gvt->gtt.ppgtt_mm_lock);
list_add_tail(&mm->ppgtt_mm.lru_list, &gvt->gtt.ppgtt_mm_lru_list_head);
+ mutex_unlock(&gvt->gtt.ppgtt_mm_lock);
+
return mm;
}
*/
void intel_vgpu_unpin_mm(struct intel_vgpu_mm *mm)
{
- atomic_dec(&mm->pincount);
+ atomic_dec_if_positive(&mm->pincount);
}
/**
if (ret)
return ret;
+ mutex_lock(&mm->vgpu->gvt->gtt.ppgtt_mm_lock);
list_move_tail(&mm->ppgtt_mm.lru_list,
&mm->vgpu->gvt->gtt.ppgtt_mm_lru_list_head);
-
+ mutex_unlock(&mm->vgpu->gvt->gtt.ppgtt_mm_lock);
}
return 0;
struct intel_vgpu_mm *mm;
struct list_head *pos, *n;
+ mutex_lock(&gvt->gtt.ppgtt_mm_lock);
+
list_for_each_safe(pos, n, &gvt->gtt.ppgtt_mm_lru_list_head) {
mm = container_of(pos, struct intel_vgpu_mm, ppgtt_mm.lru_list);
continue;
list_del_init(&mm->ppgtt_mm.lru_list);
+ mutex_unlock(&gvt->gtt.ppgtt_mm_lock);
invalidate_ppgtt_mm(mm);
return 1;
}
+ mutex_unlock(&gvt->gtt.ppgtt_mm_lock);
return 0;
}
}
}
INIT_LIST_HEAD(&gvt->gtt.ppgtt_mm_lru_list_head);
+ mutex_init(&gvt->gtt.ppgtt_mm_lock);
return 0;
}
list_for_each_safe(pos, n, &vgpu->gtt.ppgtt_mm_list_head) {
mm = container_of(pos, struct intel_vgpu_mm, ppgtt_mm.list);
if (mm->type == INTEL_GVT_MM_PPGTT) {
+ mutex_lock(&vgpu->gvt->gtt.ppgtt_mm_lock);
list_del_init(&mm->ppgtt_mm.lru_list);
+ mutex_unlock(&vgpu->gvt->gtt.ppgtt_mm_lock);
if (mm->ppgtt_mm.shadowed)
invalidate_ppgtt_mm(mm);
}
void (*mm_free_page_table)(struct intel_vgpu_mm *mm);
struct list_head oos_page_use_list_head;
struct list_head oos_page_free_list_head;
+ struct mutex ppgtt_mm_lock;
struct list_head ppgtt_mm_lru_list_head;
struct page *scratch_page;
static int intel_vgpu_aperture_rw(struct intel_vgpu *vgpu, u64 off,
void *buf, unsigned long count, bool is_write)
{
- void *aperture_va;
+ void __iomem *aperture_va;
if (!intel_vgpu_in_aperture(vgpu, off) ||
!intel_vgpu_in_aperture(vgpu, off + count)) {
return -EIO;
if (is_write)
- memcpy(aperture_va + offset_in_page(off), buf, count);
+ memcpy_toio(aperture_va + offset_in_page(off), buf, count);
else
- memcpy(buf, aperture_va + offset_in_page(off), count);
+ memcpy_fromio(buf, aperture_va + offset_in_page(off), count);
io_mapping_unmap(aperture_va);
{RCS, GEN9_GAMT_ECO_REG_RW_IA, 0x0, false}, /* 0x4ab0 */
{RCS, GEN9_CSFE_CHICKEN1_RCS, 0xffff, false}, /* 0x20d4 */
+ {RCS, _MMIO(0x20D8), 0xffff, true}, /* 0x20d8 */
{RCS, GEN8_GARBCNTL, 0x0, false}, /* 0xb004 */
{RCS, GEN7_FF_THREAD_MODE, 0x0, false}, /* 0x20a0 */
int i = 0;
if (mm->type != INTEL_GVT_MM_PPGTT || !mm->ppgtt_mm.shadowed)
- return -1;
+ return -EINVAL;
if (mm->ppgtt_mm.root_entry_type == GTT_TYPE_PPGTT_ROOT_L4_ENTRY) {
px_dma(&ppgtt->pml4) = mm->ppgtt_mm.shadow_pdps[0];
if (workload->shadow)
return 0;
- ret = set_context_ppgtt_from_shadow(workload, shadow_ctx);
- if (ret < 0) {
- gvt_vgpu_err("workload shadow ppgtt isn't ready\n");
- return ret;
- }
-
/* pin shadow context by gvt even the shadow context will be pinned
* when i915 alloc request. That is because gvt will update the guest
* context from shadow context when workload is completed, and at that
{
struct intel_vgpu *vgpu = workload->vgpu;
struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
+ struct intel_vgpu_submission *s = &vgpu->submission;
+ struct i915_gem_context *shadow_ctx = s->shadow_ctx;
+ struct i915_request *rq;
int ring_id = workload->ring_id;
int ret;
mutex_lock(&vgpu->vgpu_lock);
mutex_lock(&dev_priv->drm.struct_mutex);
+ ret = set_context_ppgtt_from_shadow(workload, shadow_ctx);
+ if (ret < 0) {
+ gvt_vgpu_err("workload shadow ppgtt isn't ready\n");
+ goto err_req;
+ }
+
ret = intel_gvt_workload_req_alloc(workload);
if (ret)
goto err_req;
ret = prepare_workload(workload);
out:
+ if (ret) {
+ /* We might still need to add request with
+ * clean ctx to retire it properly..
+ */
+ rq = fetch_and_zero(&workload->req);
+ i915_request_put(rq);
+ }
+
if (!IS_ERR_OR_NULL(workload->req)) {
gvt_dbg_sched("ring id %d submit workload to i915 %p\n",
ring_id, workload->req);
goto out;
}
- if (list_empty(workload_q_head(scheduler->current_vgpu, ring_id)))
+ if (!scheduler->current_vgpu->active ||
+ list_empty(workload_q_head(scheduler->current_vgpu, ring_id)))
goto out;
/*
intel_runtime_pm_put_unchecked(dev_priv);
}
- if (ret && (vgpu_is_vm_unhealthy(ret))) {
- enter_failsafe_mode(vgpu, GVT_FAILSAFE_GUEST_ERR);
+ if (ret) {
+ if (vgpu_is_vm_unhealthy(ret))
+ enter_failsafe_mode(vgpu, GVT_FAILSAFE_GUEST_ERR);
intel_vgpu_destroy_workload(workload);
return ERR_PTR(ret);
}
ret = drm_modeset_lock(&dev->mode_config.connection_mutex,
&ctx);
if (ret) {
- ret = -EINTR;
+ if (ret == -EDEADLK && !drm_modeset_backoff(&ctx)) {
+ try_again = true;
+ continue;
+ }
break;
}
crtc = connector->state->crtc;
INTEL_DEVID(dev_priv) == 0x5915 || \
INTEL_DEVID(dev_priv) == 0x591E)
#define IS_AML_ULX(dev_priv) (INTEL_DEVID(dev_priv) == 0x591C || \
- INTEL_DEVID(dev_priv) == 0x87C0)
+ INTEL_DEVID(dev_priv) == 0x87C0 || \
+ INTEL_DEVID(dev_priv) == 0x87CA)
#define IS_SKL_GT2(dev_priv) (IS_SKYLAKE(dev_priv) && \
INTEL_INFO(dev_priv)->gt == 2)
#define IS_SKL_GT3(dev_priv) (IS_SKYLAKE(dev_priv) && \
#define GEN11_GT_VEBOX_VDBOX_DISABLE _MMIO(0x9140)
#define GEN11_GT_VDBOX_DISABLE_MASK 0xff
#define GEN11_GT_VEBOX_DISABLE_SHIFT 16
-#define GEN11_GT_VEBOX_DISABLE_MASK (0xff << GEN11_GT_VEBOX_DISABLE_SHIFT)
+#define GEN11_GT_VEBOX_DISABLE_MASK (0x0f << GEN11_GT_VEBOX_DISABLE_SHIFT)
#define GEN11_EU_DISABLE _MMIO(0x9134)
#define GEN11_EU_DIS_MASK 0xFF
#define TRANS_DDI_FUNC_CTL2(tran) _MMIO_TRANS2(tran, \
_TRANS_DDI_FUNC_CTL2_A)
#define PORT_SYNC_MODE_ENABLE (1 << 4)
-#define PORT_SYNC_MODE_MASTER_SELECT(x) ((x) < 0)
+#define PORT_SYNC_MODE_MASTER_SELECT(x) ((x) << 0)
#define PORT_SYNC_MODE_MASTER_SELECT_MASK (0x7 << 0)
#define PORT_SYNC_MODE_MASTER_SELECT_SHIFT 0
}
}
+static void get_dsi_io_power_domains(struct drm_i915_private *dev_priv,
+ struct intel_dsi *intel_dsi)
+{
+ enum port port;
+
+ for_each_dsi_port(port, intel_dsi->ports) {
+ WARN_ON(intel_dsi->io_wakeref[port]);
+ intel_dsi->io_wakeref[port] =
+ intel_display_power_get(dev_priv,
+ port == PORT_A ?
+ POWER_DOMAIN_PORT_DDI_A_IO :
+ POWER_DOMAIN_PORT_DDI_B_IO);
+ }
+}
+
static void gen11_dsi_enable_io_power(struct intel_encoder *encoder)
{
struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
I915_WRITE(ICL_DSI_IO_MODECTL(port), tmp);
}
- for_each_dsi_port(port, intel_dsi->ports) {
- intel_dsi->io_wakeref[port] =
- intel_display_power_get(dev_priv,
- port == PORT_A ?
- POWER_DOMAIN_PORT_DDI_A_IO :
- POWER_DOMAIN_PORT_DDI_B_IO);
- }
+ get_dsi_io_power_domains(dev_priv, intel_dsi);
}
static void gen11_dsi_power_up_lanes(struct intel_encoder *encoder)
val |= DPCLKA_CFGCR0_DDI_CLK_SEL(pll->info->id, port);
}
I915_WRITE(DPCLKA_CFGCR0_ICL, val);
+
+ for_each_dsi_port(port, intel_dsi->ports) {
+ val &= ~DPCLKA_CFGCR0_DDI_CLK_OFF(port);
+ }
+ I915_WRITE(DPCLKA_CFGCR0_ICL, val);
+
POSTING_READ(DPCLKA_CFGCR0_ICL);
mutex_unlock(&dev_priv->dpll_lock);
DRM_ERROR("DDI port:%c buffer not idle\n",
port_name(port));
}
- gen11_dsi_ungate_clocks(encoder);
+ gen11_dsi_gate_clocks(encoder);
}
static void gen11_dsi_disable_io_power(struct intel_encoder *encoder)
return 0;
}
-static u64 gen11_dsi_get_power_domains(struct intel_encoder *encoder,
- struct intel_crtc_state *crtc_state)
+static void gen11_dsi_get_power_domains(struct intel_encoder *encoder,
+ struct intel_crtc_state *crtc_state)
{
- struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
- u64 domains = 0;
- enum port port;
-
- for_each_dsi_port(port, intel_dsi->ports)
- if (port == PORT_A)
- domains |= BIT_ULL(POWER_DOMAIN_PORT_DDI_A_IO);
- else
- domains |= BIT_ULL(POWER_DOMAIN_PORT_DDI_B_IO);
-
- return domains;
+ get_dsi_io_power_domains(to_i915(encoder->base.dev),
+ enc_to_intel_dsi(&encoder->base));
}
static bool gen11_dsi_get_hw_state(struct intel_encoder *encoder,
intel_aux_power_domain(dig_port);
}
-static u64 intel_ddi_get_power_domains(struct intel_encoder *encoder,
- struct intel_crtc_state *crtc_state)
+static void intel_ddi_get_power_domains(struct intel_encoder *encoder,
+ struct intel_crtc_state *crtc_state)
{
struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
struct intel_digital_port *dig_port;
- u64 domains;
/*
* TODO: Add support for MST encoders. Atm, the following should never
* hook.
*/
if (WARN_ON(intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP_MST)))
- return 0;
+ return;
dig_port = enc_to_dig_port(&encoder->base);
- domains = BIT_ULL(dig_port->ddi_io_power_domain);
+ intel_display_power_get(dev_priv, dig_port->ddi_io_power_domain);
/*
* AUX power is only needed for (e)DP mode, and for HDMI mode on TC
*/
if (intel_crtc_has_dp_encoder(crtc_state) ||
intel_port_is_tc(dev_priv, encoder->port))
- domains |= BIT_ULL(intel_ddi_main_link_aux_domain(dig_port));
+ intel_display_power_get(dev_priv,
+ intel_ddi_main_link_aux_domain(dig_port));
/*
* VDSC power is needed when DSC is enabled
*/
if (crtc_state->dsc_params.compression_enable)
- domains |= BIT_ULL(intel_dsc_power_domain(crtc_state));
-
- return domains;
+ intel_display_power_get(dev_priv,
+ intel_dsc_power_domain(crtc_state));
}
void intel_ddi_enable_pipe_clock(const struct intel_crtc_state *crtc_state)
return;
}
/*
- * DSI ports should have their DDI clock ungated when disabled
- * and gated when enabled.
+ * For DSI we keep the ddi clocks gated
+ * except during enable/disable sequence.
*/
- ddi_clk_needed = !encoder->base.crtc;
+ ddi_clk_needed = false;
}
val = I915_READ(DPCLKA_CFGCR0_ICL);
struct intel_encoder *encoder;
for_each_intel_encoder(&dev_priv->drm, encoder) {
- u64 get_domains;
- enum intel_display_power_domain domain;
struct intel_crtc_state *crtc_state;
if (!encoder->get_power_domains)
continue;
crtc_state = to_intel_crtc_state(encoder->base.crtc->state);
- get_domains = encoder->get_power_domains(encoder, crtc_state);
- for_each_power_domain(domain, get_domains)
- intel_display_power_get(dev_priv, domain);
+ encoder->get_power_domains(encoder, crtc_state);
}
}
return -EINVAL;
}
-/* Optimize link config in order: max bpp, min lanes, min clock */
-static int
-intel_dp_compute_link_config_fast(struct intel_dp *intel_dp,
- struct intel_crtc_state *pipe_config,
- const struct link_config_limits *limits)
-{
- struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
- int bpp, clock, lane_count;
- int mode_rate, link_clock, link_avail;
-
- for (bpp = limits->max_bpp; bpp >= limits->min_bpp; bpp -= 2 * 3) {
- mode_rate = intel_dp_link_required(adjusted_mode->crtc_clock,
- bpp);
-
- for (lane_count = limits->min_lane_count;
- lane_count <= limits->max_lane_count;
- lane_count <<= 1) {
- for (clock = limits->min_clock; clock <= limits->max_clock; clock++) {
- link_clock = intel_dp->common_rates[clock];
- link_avail = intel_dp_max_data_rate(link_clock,
- lane_count);
-
- if (mode_rate <= link_avail) {
- pipe_config->lane_count = lane_count;
- pipe_config->pipe_bpp = bpp;
- pipe_config->port_clock = link_clock;
-
- return 0;
- }
- }
- }
- }
-
- return -EINVAL;
-}
-
static int intel_dp_dsc_compute_bpp(struct intel_dp *intel_dp, u8 dsc_max_bpc)
{
int i, num_bpc;
limits.min_bpp = 6 * 3;
limits.max_bpp = intel_dp_compute_bpp(intel_dp, pipe_config);
- if (intel_dp_is_edp(intel_dp) && intel_dp->edp_dpcd[0] < DP_EDP_14) {
+ if (intel_dp_is_edp(intel_dp)) {
/*
* Use the maximum clock and number of lanes the eDP panel
- * advertizes being capable of. The eDP 1.3 and earlier panels
- * are generally designed to support only a single clock and
- * lane configuration, and typically these values correspond to
- * the native resolution of the panel. With eDP 1.4 rate select
- * and DSC, this is decreasingly the case, and we need to be
- * able to select less than maximum link config.
+ * advertizes being capable of. The panels are generally
+ * designed to support only a single clock and lane
+ * configuration, and typically these values correspond to the
+ * native resolution of the panel.
*/
limits.min_lane_count = limits.max_lane_count;
limits.min_clock = limits.max_clock;
intel_dp->common_rates[limits.max_clock],
limits.max_bpp, adjusted_mode->crtc_clock);
- if (intel_dp_is_edp(intel_dp))
- /*
- * Optimize for fast and narrow. eDP 1.3 section 3.3 and eDP 1.4
- * section A.1: "It is recommended that the minimum number of
- * lanes be used, using the minimum link rate allowed for that
- * lane configuration."
- *
- * Note that we use the max clock and lane count for eDP 1.3 and
- * earlier, and fast vs. wide is irrelevant.
- */
- ret = intel_dp_compute_link_config_fast(intel_dp, pipe_config,
- &limits);
- else
- /* Optimize for slow and wide. */
- ret = intel_dp_compute_link_config_wide(intel_dp, pipe_config,
- &limits);
+ /*
+ * Optimize for slow and wide. This is the place to add alternative
+ * optimization policy.
+ */
+ ret = intel_dp_compute_link_config_wide(intel_dp, pipe_config, &limits);
/* enable compression if the mode doesn't fit available BW */
DRM_DEBUG_KMS("Force DSC en = %d\n", intel_dp->force_dsc_en);
* be set correctly before calling this function. */
void (*get_config)(struct intel_encoder *,
struct intel_crtc_state *pipe_config);
- /* Returns a mask of power domains that need to be referenced as part
- * of the hardware state readout code. */
- u64 (*get_power_domains)(struct intel_encoder *encoder,
- struct intel_crtc_state *crtc_state);
+ /*
+ * Acquires the power domains needed for an active encoder during
+ * hardware state readout.
+ */
+ void (*get_power_domains)(struct intel_encoder *encoder,
+ struct intel_crtc_state *crtc_state);
/*
* Called during system suspend after all pending requests for the
* encoder are flushed (for example for DP AUX transactions) and
struct i915_gem_context *ctx;
ctx = live_context(i915, file);
- if (!ctx)
+ if (IS_ERR(ctx))
break;
/* We will need some GGTT space for the rq's context */
mutex_unlock(&dev_priv->sb_lock);
}
+static int bdw_get_pipemisc_bpp(struct intel_crtc *crtc)
+{
+ struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+ u32 tmp;
+
+ tmp = I915_READ(PIPEMISC(crtc->pipe));
+
+ switch (tmp & PIPEMISC_DITHER_BPC_MASK) {
+ case PIPEMISC_DITHER_6_BPC:
+ return 18;
+ case PIPEMISC_DITHER_8_BPC:
+ return 24;
+ case PIPEMISC_DITHER_10_BPC:
+ return 30;
+ case PIPEMISC_DITHER_12_BPC:
+ return 36;
+ default:
+ MISSING_CASE(tmp);
+ return 0;
+ }
+}
+
static int intel_dsi_compute_config(struct intel_encoder *encoder,
struct intel_crtc_state *pipe_config,
struct drm_connector_state *conn_state)
bpp = mipi_dsi_pixel_format_to_bpp(
pixel_format_from_register_bits(fmt));
+ pipe_config->pipe_bpp = bdw_get_pipemisc_bpp(crtc);
+
/* Enable Frame time stamo based scanline reporting */
adjusted_mode->private_flags |=
I915_MODE_FLAG_GET_SCANLINE_FROM_TIMESTAMP;
static unsigned int mt2701_calculate_factor(int clock)
{
if (clock <= 64000)
- return 16;
- else if (clock <= 128000)
- return 8;
- else if (clock <= 256000)
return 4;
- else
+ else if (clock <= 128000)
return 2;
+ else
+ return 1;
}
static const struct mtk_dpi_conf mt8173_conf = {
#include <drm/drmP.h>
#include <drm/drm_atomic.h>
#include <drm/drm_atomic_helper.h>
+#include <drm/drm_fb_helper.h>
#include <drm/drm_gem.h>
#include <drm/drm_gem_cma_helper.h>
#include <drm/drm_of.h>
.gem_prime_get_sg_table = mtk_gem_prime_get_sg_table,
.gem_prime_import_sg_table = mtk_gem_prime_import_sg_table,
.gem_prime_mmap = mtk_drm_gem_mmap_buf,
+ .gem_prime_vmap = mtk_drm_gem_prime_vmap,
+ .gem_prime_vunmap = mtk_drm_gem_prime_vunmap,
.fops = &mtk_drm_fops,
.name = DRIVER_NAME,
if (ret < 0)
goto err_deinit;
+ ret = drm_fbdev_generic_setup(drm, 32);
+ if (ret)
+ DRM_ERROR("Failed to initialize fbdev: %d\n", ret);
+
return 0;
err_deinit:
kfree(mtk_gem);
return ERR_PTR(ret);
}
+
+void *mtk_drm_gem_prime_vmap(struct drm_gem_object *obj)
+{
+ struct mtk_drm_gem_obj *mtk_gem = to_mtk_gem_obj(obj);
+ struct sg_table *sgt;
+ struct sg_page_iter iter;
+ unsigned int npages;
+ unsigned int i = 0;
+
+ if (mtk_gem->kvaddr)
+ return mtk_gem->kvaddr;
+
+ sgt = mtk_gem_prime_get_sg_table(obj);
+ if (IS_ERR(sgt))
+ return NULL;
+
+ npages = obj->size >> PAGE_SHIFT;
+ mtk_gem->pages = kcalloc(npages, sizeof(*mtk_gem->pages), GFP_KERNEL);
+ if (!mtk_gem->pages)
+ goto out;
+
+ for_each_sg_page(sgt->sgl, &iter, sgt->orig_nents, 0) {
+ mtk_gem->pages[i++] = sg_page_iter_page(&iter);
+ if (i > npages)
+ break;
+ }
+ mtk_gem->kvaddr = vmap(mtk_gem->pages, npages, VM_MAP,
+ pgprot_writecombine(PAGE_KERNEL));
+
+out:
+ kfree((void *)sgt);
+
+ return mtk_gem->kvaddr;
+}
+
+void mtk_drm_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr)
+{
+ struct mtk_drm_gem_obj *mtk_gem = to_mtk_gem_obj(obj);
+
+ if (!mtk_gem->pages)
+ return;
+
+ vunmap(vaddr);
+ mtk_gem->kvaddr = 0;
+ kfree((void *)mtk_gem->pages);
+}
dma_addr_t dma_addr;
unsigned long dma_attrs;
struct sg_table *sg;
+ struct page **pages;
};
#define to_mtk_gem_obj(x) container_of(x, struct mtk_drm_gem_obj, base)
struct sg_table *mtk_gem_prime_get_sg_table(struct drm_gem_object *obj);
struct drm_gem_object *mtk_gem_prime_import_sg_table(struct drm_device *dev,
struct dma_buf_attachment *attach, struct sg_table *sg);
+void *mtk_drm_gem_prime_vmap(struct drm_gem_object *obj);
+void mtk_drm_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr);
#endif
if (IS_ERR(regmap))
ret = PTR_ERR(regmap);
if (ret) {
- ret = PTR_ERR(regmap);
dev_err(dev,
"Failed to get system configuration registers: %d\n",
ret);
of_node_put(remote);
hdmi->ddc_adpt = of_find_i2c_adapter_by_node(i2c_np);
+ of_node_put(i2c_np);
if (!hdmi->ddc_adpt) {
dev_err(dev, "Failed to get ddc i2c adapter by node\n");
return -EINVAL;
.owner = THIS_MODULE,
};
-long mtk_hdmi_pll_round_rate(struct clk_hw *hw, unsigned long rate,
- unsigned long *parent_rate)
-{
- struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw);
-
- hdmi_phy->pll_rate = rate;
- if (rate <= 74250000)
- *parent_rate = rate;
- else
- *parent_rate = rate / 2;
-
- return rate;
-}
-
-unsigned long mtk_hdmi_pll_recalc_rate(struct clk_hw *hw,
- unsigned long parent_rate)
-{
- struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw);
-
- return hdmi_phy->pll_rate;
-}
-
void mtk_hdmi_phy_clear_bits(struct mtk_hdmi_phy *hdmi_phy, u32 offset,
u32 bits)
{
return NULL;
}
-static void mtk_hdmi_phy_clk_get_ops(struct mtk_hdmi_phy *hdmi_phy,
- const struct clk_ops **ops)
+static void mtk_hdmi_phy_clk_get_data(struct mtk_hdmi_phy *hdmi_phy,
+ struct clk_init_data *clk_init)
{
- if (hdmi_phy && hdmi_phy->conf && hdmi_phy->conf->hdmi_phy_clk_ops)
- *ops = hdmi_phy->conf->hdmi_phy_clk_ops;
- else
- dev_err(hdmi_phy->dev, "Failed to get clk ops of phy\n");
+ clk_init->flags = hdmi_phy->conf->flags;
+ clk_init->ops = hdmi_phy->conf->hdmi_phy_clk_ops;
}
static int mtk_hdmi_phy_probe(struct platform_device *pdev)
struct clk_init_data clk_init = {
.num_parents = 1,
.parent_names = (const char * const *)&ref_clk_name,
- .flags = CLK_SET_RATE_PARENT | CLK_SET_RATE_GATE,
};
struct phy *phy;
hdmi_phy->dev = dev;
hdmi_phy->conf =
(struct mtk_hdmi_phy_conf *)of_device_get_match_data(dev);
- mtk_hdmi_phy_clk_get_ops(hdmi_phy, &clk_init.ops);
+ mtk_hdmi_phy_clk_get_data(hdmi_phy, &clk_init);
hdmi_phy->pll_hw.init = &clk_init;
hdmi_phy->pll = devm_clk_register(dev, &hdmi_phy->pll_hw);
if (IS_ERR(hdmi_phy->pll)) {
struct mtk_hdmi_phy_conf {
bool tz_disabled;
+ unsigned long flags;
const struct clk_ops *hdmi_phy_clk_ops;
void (*hdmi_phy_enable_tmds)(struct mtk_hdmi_phy *hdmi_phy);
void (*hdmi_phy_disable_tmds)(struct mtk_hdmi_phy *hdmi_phy);
void mtk_hdmi_phy_mask(struct mtk_hdmi_phy *hdmi_phy, u32 offset,
u32 val, u32 mask);
struct mtk_hdmi_phy *to_mtk_hdmi_phy(struct clk_hw *hw);
-long mtk_hdmi_pll_round_rate(struct clk_hw *hw, unsigned long rate,
- unsigned long *parent_rate);
-unsigned long mtk_hdmi_pll_recalc_rate(struct clk_hw *hw,
- unsigned long parent_rate);
extern struct platform_driver mtk_hdmi_phy_driver;
extern struct mtk_hdmi_phy_conf mtk_hdmi_phy_8173_conf;
mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_SLDO_MASK);
usleep_range(80, 100);
mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_MBIAS_LPF_EN);
- mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_EN_TX_POSDIV);
mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_SER_MASK);
mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_PRED_MASK);
mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_DRV_MASK);
mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_DRV_MASK);
mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_PRED_MASK);
mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_SER_MASK);
- mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_EN_TX_POSDIV);
mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_MBIAS_LPF_EN);
usleep_range(80, 100);
mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_SLDO_MASK);
usleep_range(80, 100);
}
+static long mtk_hdmi_pll_round_rate(struct clk_hw *hw, unsigned long rate,
+ unsigned long *parent_rate)
+{
+ return rate;
+}
+
static int mtk_hdmi_pll_set_rate(struct clk_hw *hw, unsigned long rate,
unsigned long parent_rate)
{
if (rate <= 64000000)
pos_div = 3;
- else if (rate <= 12800000)
- pos_div = 1;
+ else if (rate <= 128000000)
+ pos_div = 2;
else
pos_div = 1;
mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON6, RG_HTPLL_PREDIV_MASK);
mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON6, RG_HTPLL_POSDIV_MASK);
+ mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_EN_TX_POSDIV);
mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON6, (0x1 << RG_HTPLL_IC),
RG_HTPLL_IC_MASK);
mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON6, (0x1 << RG_HTPLL_IR),
return 0;
}
+static unsigned long mtk_hdmi_pll_recalc_rate(struct clk_hw *hw,
+ unsigned long parent_rate)
+{
+ struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw);
+ unsigned long out_rate, val;
+
+ val = (readl(hdmi_phy->regs + HDMI_CON6)
+ & RG_HTPLL_PREDIV_MASK) >> RG_HTPLL_PREDIV;
+ switch (val) {
+ case 0x00:
+ out_rate = parent_rate;
+ break;
+ case 0x01:
+ out_rate = parent_rate / 2;
+ break;
+ default:
+ out_rate = parent_rate / 4;
+ break;
+ }
+
+ val = (readl(hdmi_phy->regs + HDMI_CON6)
+ & RG_HTPLL_FBKDIV_MASK) >> RG_HTPLL_FBKDIV;
+ out_rate *= (val + 1) * 2;
+ val = (readl(hdmi_phy->regs + HDMI_CON2)
+ & RG_HDMITX_TX_POSDIV_MASK);
+ out_rate >>= (val >> RG_HDMITX_TX_POSDIV);
+
+ if (readl(hdmi_phy->regs + HDMI_CON2) & RG_HDMITX_EN_TX_POSDIV)
+ out_rate /= 5;
+
+ return out_rate;
+}
+
static const struct clk_ops mtk_hdmi_phy_pll_ops = {
.prepare = mtk_hdmi_pll_prepare,
.unprepare = mtk_hdmi_pll_unprepare,
mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_SLDO_MASK);
usleep_range(80, 100);
mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_MBIAS_LPF_EN);
- mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_EN_TX_POSDIV);
mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_SER_MASK);
mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_PRED_MASK);
mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_DRV_MASK);
mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_DRV_MASK);
mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_PRED_MASK);
mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_SER_MASK);
- mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_EN_TX_POSDIV);
mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_MBIAS_LPF_EN);
usleep_range(80, 100);
mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_SLDO_MASK);
struct mtk_hdmi_phy_conf mtk_hdmi_phy_2701_conf = {
.tz_disabled = true,
+ .flags = CLK_SET_RATE_GATE,
.hdmi_phy_clk_ops = &mtk_hdmi_phy_pll_ops,
.hdmi_phy_enable_tmds = mtk_hdmi_phy_enable_tmds,
.hdmi_phy_disable_tmds = mtk_hdmi_phy_disable_tmds,
usleep_range(100, 150);
}
+static long mtk_hdmi_pll_round_rate(struct clk_hw *hw, unsigned long rate,
+ unsigned long *parent_rate)
+{
+ struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw);
+
+ hdmi_phy->pll_rate = rate;
+ if (rate <= 74250000)
+ *parent_rate = rate;
+ else
+ *parent_rate = rate / 2;
+
+ return rate;
+}
+
static int mtk_hdmi_pll_set_rate(struct clk_hw *hw, unsigned long rate,
unsigned long parent_rate)
{
return 0;
}
+static unsigned long mtk_hdmi_pll_recalc_rate(struct clk_hw *hw,
+ unsigned long parent_rate)
+{
+ struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw);
+
+ return hdmi_phy->pll_rate;
+}
+
static const struct clk_ops mtk_hdmi_phy_pll_ops = {
.prepare = mtk_hdmi_pll_prepare,
.unprepare = mtk_hdmi_pll_unprepare,
}
struct mtk_hdmi_phy_conf mtk_hdmi_phy_8173_conf = {
+ .flags = CLK_SET_RATE_PARENT | CLK_SET_RATE_GATE,
.hdmi_phy_clk_ops = &mtk_hdmi_phy_pll_ops,
.hdmi_phy_enable_tmds = mtk_hdmi_phy_enable_tmds,
.hdmi_phy_disable_tmds = mtk_hdmi_phy_disable_tmds,
ret = drm_dev_register(drm, 0);
if (ret)
- goto free_drm;
+ goto uninstall_irq;
drm_fbdev_generic_setup(drm, 32);
return 0;
+uninstall_irq:
+ drm_irq_uninstall(drm);
free_drm:
drm_dev_put(drm);
static void meson_drv_unbind(struct device *dev)
{
- struct drm_device *drm = dev_get_drvdata(dev);
- struct meson_drm *priv = drm->dev_private;
+ struct meson_drm *priv = dev_get_drvdata(dev);
+ struct drm_device *drm = priv->drm;
if (priv->canvas) {
meson_canvas_free(priv->canvas, priv->canvas_id_osd1);
}
drm_dev_unregister(drm);
+ drm_irq_uninstall(drm);
drm_kms_helper_poll_fini(drm);
drm_mode_config_cleanup(drm);
drm_dev_put(drm);
DRM_DEBUG_DRIVER("Modeline " DRM_MODE_FMT "\n", DRM_MODE_ARG(mode));
/* If sink max TMDS clock, we reject the mode */
- if (mode->clock > connector->display_info.max_tmds_clock)
+ if (connector->display_info.max_tmds_clock &&
+ mode->clock > connector->display_info.max_tmds_clock)
return MODE_BAD;
/* Check against non-VIC supported modes */
REG_FLD_MOD(core->base, HDMI_CORE_SYS_INTR_UNMASK4, 0, 3, 3);
hdmi_wp_clear_irqenable(core->wp, HDMI_IRQ_CORE);
hdmi_wp_set_irqstatus(core->wp, HDMI_IRQ_CORE);
+ REG_FLD_MOD(core->wp->base, HDMI_WP_CLK, 0, 5, 0);
hdmi4_core_disable(core);
return 0;
}
if (err)
return err;
+ /*
+ * Initialize CEC clock divider: CEC needs 2MHz clock hence
+ * set the divider to 24 to get 48/24=2MHz clock
+ */
+ REG_FLD_MOD(core->wp->base, HDMI_WP_CLK, 0x18, 5, 0);
+
/* Clear TX FIFO */
if (!hdmi_cec_clear_tx_fifo(adap)) {
pr_err("cec-%s: could not clear TX FIFO\n", adap->name);
- return -EIO;
+ err = -EIO;
+ goto err_disable_clk;
}
/* Clear RX FIFO */
if (!hdmi_cec_clear_rx_fifo(adap)) {
pr_err("cec-%s: could not clear RX FIFO\n", adap->name);
- return -EIO;
+ err = -EIO;
+ goto err_disable_clk;
}
/* Clear CEC interrupts */
hdmi_write_reg(core->base, HDMI_CEC_INT_STATUS_1, temp);
}
return 0;
+
+err_disable_clk:
+ REG_FLD_MOD(core->wp->base, HDMI_WP_CLK, 0, 5, 0);
+ hdmi4_core_disable(core);
+
+ return err;
}
static int hdmi_cec_adap_log_addr(struct cec_adapter *adap, u8 log_addr)
return ret;
core->wp = wp;
- /*
- * Initialize CEC clock divider: CEC needs 2MHz clock hence
- * set the devider to 24 to get 48/24=2MHz clock
- */
- REG_FLD_MOD(core->wp->base, HDMI_WP_CLK, 0x18, 5, 0);
+ /* Disable clock initially, hdmi_cec_adap_enable() manages it */
+ REG_FLD_MOD(core->wp->base, HDMI_WP_CLK, 0, 5, 0);
ret = cec_register_adapter(core->adap, &pdev->dev);
if (ret < 0) {
else
acore.i2s_cfg.justification = HDMI_AUDIO_JUSTIFY_RIGHT;
/*
- * The I2S input word length is twice the lenght given in the IEC-60958
+ * The I2S input word length is twice the length given in the IEC-60958
* status word. If the word size is greater than
* 20 bits, increment by one.
*/
clk_disable(vop->hclk);
}
+static void vop_win_disable(struct vop *vop, const struct vop_win_data *win)
+{
+ if (win->phy->scl && win->phy->scl->ext) {
+ VOP_SCL_SET_EXT(vop, win, yrgb_hor_scl_mode, SCALE_NONE);
+ VOP_SCL_SET_EXT(vop, win, yrgb_ver_scl_mode, SCALE_NONE);
+ VOP_SCL_SET_EXT(vop, win, cbcr_hor_scl_mode, SCALE_NONE);
+ VOP_SCL_SET_EXT(vop, win, cbcr_ver_scl_mode, SCALE_NONE);
+ }
+
+ VOP_WIN_SET(vop, win, enable, 0);
+}
+
static int vop_enable(struct drm_crtc *crtc)
{
struct vop *vop = to_vop(crtc);
struct vop_win *vop_win = &vop->win[i];
const struct vop_win_data *win = vop_win->data;
- VOP_WIN_SET(vop, win, enable, 0);
+ vop_win_disable(vop, win);
}
spin_unlock(&vop->reg_lock);
spin_lock(&vop->reg_lock);
- VOP_WIN_SET(vop, win, enable, 0);
+ vop_win_disable(vop, win);
spin_unlock(&vop->reg_lock);
}
int channel = i * 2 + 1;
VOP_WIN_SET(vop, win, channel, (channel + 1) << 4 | channel);
- VOP_WIN_SET(vop, win, enable, 0);
+ vop_win_disable(vop, win);
VOP_WIN_SET(vop, win, gate, 1);
}
sun8i_dw_hdmi_mode_valid_h6(struct drm_connector *connector,
const struct drm_display_mode *mode)
{
- /* This is max for HDMI 2.0b (4K@60Hz) */
- if (mode->clock > 594000)
+ /*
+ * Controller support maximum of 594 MHz, which correlates to
+ * 4K@60Hz 4:4:4 or RGB. However, for frequencies greater than
+ * 340 MHz scrambling has to be enabled. Because scrambling is
+ * not yet implemented, just limit to 340 MHz for now.
+ */
+ if (mode->clock > 340000)
return MODE_CLOCK_HIGH;
return MODE_OK;
err_unregister_gates:
for (i = 0; i < CLK_NUM; i++)
- if (clk_data->hws[i])
+ if (!IS_ERR_OR_NULL(clk_data->hws[i]))
clk_hw_unregister_gate(clk_data->hws[i]);
clk_disable_unprepare(tcon_top->bus);
err_assert_reset:
of_clk_del_provider(dev->of_node);
for (i = 0; i < CLK_NUM; i++)
- clk_hw_unregister_gate(clk_data->hws[i]);
+ if (clk_data->hws[i])
+ clk_hw_unregister_gate(clk_data->hws[i]);
clk_disable_unprepare(tcon_top->bus);
reset_control_assert(tcon_top->rst);
static void tegra_shared_plane_atomic_disable(struct drm_plane *plane,
struct drm_plane_state *old_state)
{
- struct tegra_dc *dc = to_tegra_dc(old_state->crtc);
struct tegra_plane *p = to_tegra_plane(plane);
+ struct tegra_dc *dc;
u32 value;
/* rien ne va plus */
if (!old_state || !old_state->crtc)
return;
+ dc = to_tegra_dc(old_state->crtc);
+
/*
* XXX Legacy helpers seem to sometimes call ->atomic_disable() even
* on planes that are already disabled. Make sure we fallback to the
if (vic->booted)
return 0;
+#ifdef CONFIG_IOMMU_API
if (vic->config->supports_sid) {
struct iommu_fwspec *spec = dev_iommu_fwspec_get(vic->dev);
u32 value;
vic_writel(vic, value, VIC_THI_STREAMID1);
}
}
+#endif
/* setup clockgating registers */
vic_writel(vic, CG_IDLE_CG_DLY_CNT(4) |
#include "udl_connector.h"
#include "udl_drv.h"
-static bool udl_get_edid_block(struct udl_device *udl, int block_idx,
- u8 *buff)
+static int udl_get_edid_block(void *data, u8 *buf, unsigned int block,
+ size_t len)
{
int ret, i;
u8 *read_buff;
+ struct udl_device *udl = data;
read_buff = kmalloc(2, GFP_KERNEL);
if (!read_buff)
- return false;
+ return -1;
- for (i = 0; i < EDID_LENGTH; i++) {
- int bval = (i + block_idx * EDID_LENGTH) << 8;
+ for (i = 0; i < len; i++) {
+ int bval = (i + block * EDID_LENGTH) << 8;
ret = usb_control_msg(udl->udev,
usb_rcvctrlpipe(udl->udev, 0),
(0x02), (0x80 | (0x02 << 5)), bval,
if (ret < 1) {
DRM_ERROR("Read EDID byte %d failed err %x\n", i, ret);
kfree(read_buff);
- return false;
+ return -1;
}
- buff[i] = read_buff[1];
+ buf[i] = read_buff[1];
}
kfree(read_buff);
- return true;
-}
-
-static bool udl_get_edid(struct udl_device *udl, u8 **result_buff,
- int *result_buff_size)
-{
- int i, extensions;
- u8 *block_buff = NULL, *buff_ptr;
-
- block_buff = kmalloc(EDID_LENGTH, GFP_KERNEL);
- if (block_buff == NULL)
- return false;
-
- if (udl_get_edid_block(udl, 0, block_buff) &&
- memchr_inv(block_buff, 0, EDID_LENGTH)) {
- extensions = ((struct edid *)block_buff)->extensions;
- if (extensions > 0) {
- /* we have to read all extensions one by one */
- *result_buff_size = EDID_LENGTH * (extensions + 1);
- *result_buff = kmalloc(*result_buff_size, GFP_KERNEL);
- buff_ptr = *result_buff;
- if (buff_ptr == NULL) {
- kfree(block_buff);
- return false;
- }
- memcpy(buff_ptr, block_buff, EDID_LENGTH);
- kfree(block_buff);
- buff_ptr += EDID_LENGTH;
- for (i = 1; i < extensions; ++i) {
- if (udl_get_edid_block(udl, i, buff_ptr)) {
- buff_ptr += EDID_LENGTH;
- } else {
- kfree(*result_buff);
- *result_buff = NULL;
- return false;
- }
- }
- return true;
- }
- /* we have only base edid block */
- *result_buff = block_buff;
- *result_buff_size = EDID_LENGTH;
- return true;
- }
-
- kfree(block_buff);
-
- return false;
+ return 0;
}
static int udl_get_modes(struct drm_connector *connector)
static enum drm_connector_status
udl_detect(struct drm_connector *connector, bool force)
{
- u8 *edid_buff = NULL;
- int edid_buff_size = 0;
struct udl_device *udl = connector->dev->dev_private;
struct udl_drm_connector *udl_connector =
container_of(connector,
udl_connector->edid = NULL;
}
-
- if (!udl_get_edid(udl, &edid_buff, &edid_buff_size))
+ udl_connector->edid = drm_do_get_edid(connector, udl_get_edid_block, udl);
+ if (!udl_connector->edid)
return connector_status_disconnected;
- udl_connector->edid = (struct edid *)edid_buff;
-
return connector_status_connected;
}
.driver_features = DRIVER_MODESET | DRIVER_GEM | DRIVER_PRIME,
.load = udl_driver_load,
.unload = udl_driver_unload,
+ .release = udl_driver_release,
/* gem hooks */
.gem_free_object_unlocked = udl_gem_free_object,
int udl_driver_load(struct drm_device *dev, unsigned long flags);
void udl_driver_unload(struct drm_device *dev);
+void udl_driver_release(struct drm_device *dev);
int udl_fbdev_init(struct drm_device *dev);
void udl_fbdev_cleanup(struct drm_device *dev);
udl_free_urb_list(dev);
udl_fbdev_cleanup(dev);
- udl_modeset_cleanup(dev);
kfree(udl);
}
+
+void udl_driver_release(struct drm_device *dev)
+{
+ udl_modeset_cleanup(dev);
+ drm_dev_fini(dev);
+ kfree(dev);
+}
ret = drm_gem_handle_create(file, &obj->base, handle);
drm_gem_object_put_unlocked(&obj->base);
if (ret)
- goto err;
+ return ERR_PTR(ret);
return &obj->base;
-
-err:
- __vgem_gem_destroy(obj);
- return ERR_PTR(ret);
}
static int vgem_gem_dumb_create(struct drm_file *file, struct drm_device *dev,
ret = drm_gem_handle_create(file, &obj->gem, handle);
drm_gem_object_put_unlocked(&obj->gem);
- if (ret) {
- drm_gem_object_release(&obj->gem);
- kfree(obj);
+ if (ret)
return ERR_PTR(ret);
- }
return &obj->gem;
}
static void host1x_channel_set_streamid(struct host1x_channel *channel)
{
-#if HOST1X_HW >= 6
+#if IS_ENABLED(CONFIG_IOMMU_API) && HOST1X_HW >= 6
struct iommu_fwspec *spec = dev_iommu_fwspec_get(channel->dev->parent);
u32 sid = spec ? spec->ids[0] & 0xffff : 0x7f;
tristate "Asus"
depends on LEDS_CLASS
depends on ASUS_WMI || ASUS_WMI=n
+ select POWER_SUPPLY
---help---
Support for Asus notebook built-in keyboard and touchpad via i2c, and
the Asus Republic of Gamers laptop keyboard special keys.
u32 hid_field_extract(const struct hid_device *hid, u8 *report,
unsigned offset, unsigned n)
{
- if (n > 32) {
- hid_warn(hid, "hid_field_extract() called with n (%d) > 32! (%s)\n",
+ if (n > 256) {
+ hid_warn(hid, "hid_field_extract() called with n (%d) > 256! (%s)\n",
n, current->comm);
- n = 32;
+ n = 256;
}
return __extract(report, offset, n);
seq_printf(f, "\n\n");
/* dump parsed data and input mappings */
+ if (down_interruptible(&hdev->driver_input_lock))
+ return 0;
+
hid_dump_device(hdev, f);
seq_printf(f, "\n");
hid_dump_input_mapping(hdev, f);
+ up(&hdev->driver_input_lock);
+
return 0;
}
#define USB_DEVICE_ID_SYNAPTICS_HD 0x0ac3
#define USB_DEVICE_ID_SYNAPTICS_QUAD_HD 0x1ac3
#define USB_DEVICE_ID_SYNAPTICS_TP_V103 0x5710
+#define I2C_DEVICE_ID_SYNAPTICS_7E7E 0x7e7e
#define USB_VENDOR_ID_TEXAS_INSTRUMENTS 0x2047
#define USB_DEVICE_ID_TEXAS_INSTRUMENTS_LENOVO_YOGA 0x0855
case 0x1b8: map_key_clear(KEY_VIDEO); break;
case 0x1bc: map_key_clear(KEY_MESSENGER); break;
case 0x1bd: map_key_clear(KEY_INFO); break;
+ case 0x1cb: map_key_clear(KEY_ASSISTANT); break;
case 0x201: map_key_clear(KEY_NEW); break;
case 0x202: map_key_clear(KEY_OPEN); break;
case 0x203: map_key_clear(KEY_CLOSE); break;
kfree(data);
return -ENOMEM;
}
+ data->wq = create_singlethread_workqueue("hidpp-ff-sendqueue");
+ if (!data->wq) {
+ kfree(data->effect_ids);
+ kfree(data);
+ return -ENOMEM;
+ }
+
data->hidpp = hidpp;
data->feature_index = feature_index;
data->version = version;
/* ignore boost value at response.fap.params[2] */
/* init the hardware command queue */
- data->wq = create_singlethread_workqueue("hidpp-ff-sendqueue");
atomic_set(&data->workqueue_size, 0);
/* initialize with zero autocenter to get wheel in usable state */
input_report_rel(mydata->input, REL_Y, v);
v = hid_snto32(data[6], 8);
- hidpp_scroll_counter_handle_scroll(
- &hidpp->vertical_wheel_counter, v);
+ if (v != 0)
+ hidpp_scroll_counter_handle_scroll(
+ &hidpp->vertical_wheel_counter, v);
input_sync(mydata->input);
}
{ HID_USB_DEVICE(USB_VENDOR_ID_DEALEXTREAME, USB_DEVICE_ID_DEALEXTREAME_RADIO_SI4701) },
{ HID_USB_DEVICE(USB_VENDOR_ID_DELORME, USB_DEVICE_ID_DELORME_EARTHMATE) },
{ HID_USB_DEVICE(USB_VENDOR_ID_DELORME, USB_DEVICE_ID_DELORME_EM_LT20) },
- { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, 0x0400) },
{ HID_USB_DEVICE(USB_VENDOR_ID_ESSENTIAL_REALITY, USB_DEVICE_ID_ESSENTIAL_REALITY_P5) },
{ HID_USB_DEVICE(USB_VENDOR_ID_ETT, USB_DEVICE_ID_TC5UH) },
{ HID_USB_DEVICE(USB_VENDOR_ID_ETT, USB_DEVICE_ID_TC4UM) },
{ }
};
-/**
+/*
* hid_mouse_ignore_list - mouse devices which should not be handled by the hid layer
*
* There are composite devices for which we want to ignore only a certain
if (hdev->product == 0x0401 &&
strncmp(hdev->name, "ELAN0800", 8) != 0)
return true;
+ /* Same with product id 0x0400 */
+ if (hdev->product == 0x0400 &&
+ strncmp(hdev->name, "QTEC0001", 8) != 0)
+ return true;
break;
}
}
if (bl_entry != NULL)
- dbg_hid("Found dynamic quirk 0x%lx for HID device 0x%hx:0x%hx\n",
+ dbg_hid("Found dynamic quirk 0x%lx for HID device 0x%04x:0x%04x\n",
bl_entry->driver_data, bl_entry->vendor,
bl_entry->product);
quirks |= bl_entry->driver_data;
if (quirks)
- dbg_hid("Found squirk 0x%lx for HID device 0x%hx:0x%hx\n",
+ dbg_hid("Found squirk 0x%lx for HID device 0x%04x:0x%04x\n",
quirks, hdev->vendor, hdev->product);
return quirks;
}
static int steam_register(struct steam_device *steam)
{
int ret;
+ bool client_opened;
/*
* This function can be called several times in a row with the
* Unlikely, but getting the serial could fail, and it is not so
* important, so make up a serial number and go on.
*/
+ mutex_lock(&steam->mutex);
if (steam_get_serial(steam) < 0)
strlcpy(steam->serial_no, "XXXXXXXXXX",
sizeof(steam->serial_no));
+ mutex_unlock(&steam->mutex);
hid_info(steam->hdev, "Steam Controller '%s' connected",
steam->serial_no);
}
mutex_lock(&steam->mutex);
- if (!steam->client_opened) {
+ client_opened = steam->client_opened;
+ if (!client_opened)
steam_set_lizard_mode(steam, lizard_mode);
+ mutex_unlock(&steam->mutex);
+
+ if (!client_opened)
ret = steam_input_register(steam);
- } else {
+ else
ret = 0;
- }
- mutex_unlock(&steam->mutex);
return ret;
}
{
struct steam_device *steam = hdev->driver_data;
+ unsigned long flags;
+ bool connected;
+
+ spin_lock_irqsave(&steam->lock, flags);
+ connected = steam->connected;
+ spin_unlock_irqrestore(&steam->lock, flags);
+
mutex_lock(&steam->mutex);
steam->client_opened = false;
+ if (connected)
+ steam_set_lizard_mode(steam, lizard_mode);
mutex_unlock(&steam->mutex);
- if (steam->connected) {
- steam_set_lizard_mode(steam, lizard_mode);
+ if (connected)
steam_input_register(steam);
- }
}
static int steam_client_ll_raw_request(struct hid_device *hdev,
goto cleanup;
}
rc = usb_string(udev, 201, ver_ptr, ver_len);
- if (ver_ptr == NULL) {
- rc = -ENOMEM;
- goto cleanup;
- }
if (rc == -EPIPE) {
*ver_ptr = '\0';
} else if (rc < 0) {
I2C_HID_QUIRK_NO_RUNTIME_PM },
{ USB_VENDOR_ID_ELAN, HID_ANY_ID,
I2C_HID_QUIRK_BOGUS_IRQ },
+ { USB_VENDOR_ID_SYNAPTICS, I2C_DEVICE_ID_SYNAPTICS_7E7E,
+ I2C_HID_QUIRK_NO_RUNTIME_PM },
{ 0, 0 }
};
config SENSORS_W83773G
tristate "Nuvoton W83773G"
depends on I2C
+ select REGMAP_I2C
help
If you say yes here you get support for the Nuvoton W83773G hardware
monitoring chip.
};
static const u32 ntc_temp_config[] = {
- HWMON_T_INPUT, HWMON_T_TYPE,
+ HWMON_T_INPUT | HWMON_T_TYPE,
0
};
s++;
}
}
+
+ s = (sensors->power.num_sensors * 4) + 1;
} else {
for (i = 0; i < sensors->power.num_sensors; ++i) {
s = i + 1;
show_power, NULL, 3, i);
attr++;
}
- }
- if (sensors->caps.num_sensors >= 1) {
s = sensors->power.num_sensors + 1;
+ }
+ if (sensors->caps.num_sensors >= 1) {
snprintf(attr->name, sizeof(attr->name), "power%d_label", s);
attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_caps, NULL,
0, 0);
Cannon Lake (PCH)
Cedar Fork (PCH)
Ice Lake (PCH)
+ Comet Lake (PCH)
This driver can also be built as a module. If so, the module
will be called i2c-i801.
* Cannon Lake-LP (PCH) 0x9da3 32 hard yes yes yes
* Cedar Fork (PCH) 0x18df 32 hard yes yes yes
* Ice Lake-LP (PCH) 0x34a3 32 hard yes yes yes
+ * Comet Lake (PCH) 0x02a3 32 hard yes yes yes
*
* Features supported by this driver:
* Software PEC no
#define PCI_DEVICE_ID_INTEL_LEWISBURG_SSKU_SMBUS 0xa223
#define PCI_DEVICE_ID_INTEL_KABYLAKE_PCH_H_SMBUS 0xa2a3
#define PCI_DEVICE_ID_INTEL_CANNONLAKE_H_SMBUS 0xa323
+#define PCI_DEVICE_ID_INTEL_COMETLAKE_SMBUS 0x02a3
struct i801_mux_config {
char *gpio_chip;
{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CANNONLAKE_H_SMBUS) },
{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CANNONLAKE_LP_SMBUS) },
{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICELAKE_LP_SMBUS) },
+ { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_COMETLAKE_SMBUS) },
{ 0, }
};
case PCI_DEVICE_ID_INTEL_DNV_SMBUS:
case PCI_DEVICE_ID_INTEL_KABYLAKE_PCH_H_SMBUS:
case PCI_DEVICE_ID_INTEL_ICELAKE_LP_SMBUS:
+ case PCI_DEVICE_ID_INTEL_COMETLAKE_SMBUS:
priv->features |= FEATURE_I2C_BLOCK_READ;
priv->features |= FEATURE_IRQ;
priv->features |= FEATURE_SMBUS_PEC;
/* Init DMA config if supported */
ret = i2c_imx_dma_request(i2c_imx, phy_addr);
if (ret < 0)
- goto clk_notifier_unregister;
+ goto del_adapter;
dev_info(&i2c_imx->adapter.dev, "IMX I2C adapter registered\n");
return 0; /* Return OK */
+del_adapter:
+ i2c_del_adapter(&i2c_imx->adapter);
clk_notifier_unregister:
clk_notifier_unregister(i2c_imx->clk, &i2c_imx->clk_change_nb);
rpm_disable:
if (family == AF_INET) {
rt = container_of(dst, struct rtable, dst);
- return rt->rt_uses_gateway;
+ return rt->rt_gw_family == AF_INET;
}
rt6 = container_of(dst, struct rt6_info, dst);
int total_contexts;
int ret;
unsigned ngroups;
- int qos_rmt_count;
+ int rmt_count;
int user_rmt_reduced;
u32 n_usr_ctxts;
u32 send_contexts = chip_send_contexts(dd);
n_usr_ctxts = rcv_contexts - total_contexts;
}
- /* each user context requires an entry in the RMT */
- qos_rmt_count = qos_rmt_entries(dd, NULL, NULL);
- if (qos_rmt_count + n_usr_ctxts > NUM_MAP_ENTRIES) {
- user_rmt_reduced = NUM_MAP_ENTRIES - qos_rmt_count;
+ /*
+ * The RMT entries are currently allocated as shown below:
+ * 1. QOS (0 to 128 entries);
+ * 2. FECN for PSM (num_user_contexts + num_vnic_contexts);
+ * 3. VNIC (num_vnic_contexts).
+ * It should be noted that PSM FECN oversubscribe num_vnic_contexts
+ * entries of RMT because both VNIC and PSM could allocate any receive
+ * context between dd->first_dyn_alloc_text and dd->num_rcv_contexts,
+ * and PSM FECN must reserve an RMT entry for each possible PSM receive
+ * context.
+ */
+ rmt_count = qos_rmt_entries(dd, NULL, NULL) + (num_vnic_contexts * 2);
+ if (rmt_count + n_usr_ctxts > NUM_MAP_ENTRIES) {
+ user_rmt_reduced = NUM_MAP_ENTRIES - rmt_count;
dd_dev_err(dd,
"RMT size is reducing the number of user receive contexts from %u to %d\n",
n_usr_ctxts,
u64 reg;
int i, idx, regoff, regidx;
u8 offset;
+ u32 total_cnt;
/* there needs to be enough room in the map table */
- if (rmt->used + dd->num_user_contexts >= NUM_MAP_ENTRIES) {
+ total_cnt = dd->num_rcv_contexts - dd->first_dyn_alloc_ctxt;
+ if (rmt->used + total_cnt >= NUM_MAP_ENTRIES) {
dd_dev_err(dd, "User FECN handling disabled - too many user contexts allocated\n");
return;
}
/* add rule 1 */
add_rsm_rule(dd, RSM_INS_FECN, &rrd);
- rmt->used += dd->num_user_contexts;
+ rmt->used += total_cnt;
}
/* Initialize RSM for VNIC */
if (!list_empty(&priv->s_iowait.list) &&
!(qp->s_flags & RVT_S_BUSY) &&
!(priv->s_flags & RVT_S_BUSY)) {
- qp->s_flags &= ~RVT_S_ANY_WAIT_IO;
+ qp->s_flags &= ~HFI1_S_ANY_WAIT_IO;
+ iowait_clear_flag(&priv->s_iowait, IOWAIT_PENDING_IB);
+ iowait_clear_flag(&priv->s_iowait, IOWAIT_PENDING_TID);
list_del_init(&priv->s_iowait.list);
priv->s_iowait.lock = NULL;
rvt_put_qp(qp);
update_ack_queue(qp, next);
}
e = &qp->s_ack_queue[qp->r_head_ack_queue];
- if (e->opcode == OP(RDMA_READ_REQUEST) && e->rdma_sge.mr) {
+ if (e->rdma_sge.mr) {
rvt_put_mr(e->rdma_sge.mr);
e->rdma_sge.mr = NULL;
}
update_ack_queue(qp, next);
}
e = &qp->s_ack_queue[qp->r_head_ack_queue];
- if (e->opcode == OP(RDMA_READ_REQUEST) && e->rdma_sge.mr) {
+ if (e->rdma_sge.mr) {
rvt_put_mr(e->rdma_sge.mr);
e->rdma_sge.mr = NULL;
}
make_tid_rdma_ack(qp, ohdr, ps))
return 1;
- if (!(ib_rvt_state_ops[qp->state] & RVT_PROCESS_SEND_OK)) {
- if (!(ib_rvt_state_ops[qp->state] & RVT_FLUSH_SEND))
- goto bail;
- /* We are in the error state, flush the work request. */
- if (qp->s_last == READ_ONCE(qp->s_head))
- goto bail;
- /* If DMAs are in progress, we can't flush immediately. */
- if (iowait_sdma_pending(&priv->s_iowait)) {
- qp->s_flags |= RVT_S_WAIT_DMA;
- goto bail;
- }
- clear_ahg(qp);
- wqe = rvt_get_swqe_ptr(qp, qp->s_last);
- hfi1_trdma_send_complete(qp, wqe, qp->s_last != qp->s_acked ?
- IB_WC_SUCCESS : IB_WC_WR_FLUSH_ERR);
- /* will get called again */
- goto done_free_tx;
- }
+ /*
+ * Bail out if we can't send data.
+ * Be reminded that this check must been done after the call to
+ * make_tid_rdma_ack() because the responding QP could be in
+ * RTR state where it can send TID RDMA ACK, not TID RDMA WRITE DATA.
+ */
+ if (!(ib_rvt_state_ops[qp->state] & RVT_PROCESS_SEND_OK))
+ goto bail;
if (priv->s_flags & RVT_S_WAIT_ACK)
goto bail;
hfi1_make_ruc_header(qp, ohdr, (opcode << 24), bth1, bth2,
middle, ps);
return 1;
-done_free_tx:
- hfi1_put_txreq(ps->s_txreq);
- ps->s_txreq = NULL;
- return 1;
-
bail:
hfi1_put_txreq(ps->s_txreq);
bail_no_tx:
idx_offset = (obj & (table->num_obj - 1)) % obj_per_chunk;
dma_offset = offset = idx_offset * table->obj_size;
} else {
+ u32 seg_size = 64; /* 8 bytes per BA and 8 BA per segment */
+
hns_roce_calc_hem_mhop(hr_dev, table, &mhop_obj, &mhop);
/* mtt mhop */
i = mhop.l0_idx;
hem_idx = i;
hem = table->hem[hem_idx];
- dma_offset = offset = (obj & (table->num_obj - 1)) *
- table->obj_size % mhop.bt_chunk_size;
+ dma_offset = offset = (obj & (table->num_obj - 1)) * seg_size %
+ mhop.bt_chunk_size;
if (mhop.hop_num == 2)
dma_offset = offset = 0;
}
struct hns_roce_hem_table *table;
dma_addr_t dma_handle;
__le64 *mtts;
- u32 s = start_index * sizeof(u64);
u32 bt_page_size;
u32 i;
return -EINVAL;
mtts = hns_roce_table_find(hr_dev, table,
- mtt->first_seg + s / hr_dev->caps.mtt_entry_sz,
+ mtt->first_seg +
+ start_index / HNS_ROCE_MTT_ENTRY_PER_SEG,
&dma_handle);
if (!mtts)
return -ENOMEM;
wait_for_completion(&hr_qp->free);
if ((hr_qp->ibqp.qp_type) != IB_QPT_GSI) {
- if (hr_dev->caps.sccc_entry_sz)
- hns_roce_table_put(hr_dev, &qp_table->sccc_table,
- hr_qp->qpn);
if (hr_dev->caps.trrl_entry_sz)
hns_roce_table_put(hr_dev, &qp_table->trrl_table,
hr_qp->qpn);
return ret;
}
- *addr = pci_resource_start(dev->pdev, 0) +
+ *addr = dev->bar_addr +
MLX5_GET64(alloc_memic_out, out, memic_start_addr);
return 0;
u64 start_page_idx;
int err;
- addr -= pci_resource_start(dev->pdev, 0);
+ addr -= dev->bar_addr;
start_page_idx = (addr - hw_start_addr) >> PAGE_SHIFT;
MLX5_SET(dealloc_memic_in, in, opcode, MLX5_CMD_OP_DEALLOC_MEMIC);
fw_uars_per_page = MLX5_CAP_GEN(dev->mdev, uar_4k) ? MLX5_UARS_IN_PAGE : 1;
- return (pci_resource_start(dev->mdev->pdev, 0) >> PAGE_SHIFT) + uar_idx / fw_uars_per_page;
+ return (dev->mdev->bar_addr >> PAGE_SHIFT) + uar_idx / fw_uars_per_page;
}
static int get_command(unsigned long offset)
page_idx + npages)
return -EINVAL;
- pfn = ((pci_resource_start(dev->mdev->pdev, 0) +
+ pfn = ((dev->mdev->bar_addr +
MLX5_CAP64_DEV_MEM(dev->mdev, memic_bar_start_addr)) >>
PAGE_SHIFT) +
page_idx;
goto err_free;
start_offset = memic_addr & ~PAGE_MASK;
- page_idx = (memic_addr - pci_resource_start(memic->dev->pdev, 0) -
+ page_idx = (memic_addr - memic->dev->bar_addr -
MLX5_CAP64_DEV_MEM(memic->dev, memic_bar_start_addr)) >>
PAGE_SHIFT;
if (ret)
return ret;
- page_idx = (dm->dev_addr - pci_resource_start(memic->dev->pdev, 0) -
+ page_idx = (dm->dev_addr - memic->dev->bar_addr -
MLX5_CAP64_DEV_MEM(memic->dev, memic_bar_start_addr)) >>
PAGE_SHIFT;
bitmap_clear(to_mucontext(ibdm->uobject->context)->dm_pages,
MLX5_SET64(mkc, mkc, len, length);
MLX5_SET(mkc, mkc, pd, to_mpd(pd)->pdn);
MLX5_SET(mkc, mkc, qpn, 0xffffff);
- MLX5_SET64(mkc, mkc, start_addr,
- memic_addr - pci_resource_start(dev->mdev->pdev, 0));
+ MLX5_SET64(mkc, mkc, start_addr, memic_addr - dev->mdev->bar_addr);
err = mlx5_core_create_mkey(mdev, &mr->mmkey, in, inlen);
if (err)
struct ib_umem_odp *odp_mr = to_ib_umem_odp(mr->umem);
bool downgrade = flags & MLX5_PF_FLAGS_DOWNGRADE;
bool prefetch = flags & MLX5_PF_FLAGS_PREFETCH;
- u64 access_mask = ODP_READ_ALLOWED_BIT;
+ u64 access_mask;
u64 start_idx, page_mask;
struct ib_umem_odp *odp;
size_t size;
page_shift = mr->umem->page_shift;
page_mask = ~(BIT(page_shift) - 1);
start_idx = (io_virt - (mr->mmkey.iova & page_mask)) >> page_shift;
+ access_mask = ODP_READ_ALLOWED_BIT;
if (prefetch && !downgrade && !mr->umem->writable) {
/* prefetch with write-access must
wmb();
/* currently we support only regular doorbells */
- mlx5_write64((__be32 *)ctrl, bf->bfreg->map + bf->offset, NULL);
+ mlx5_write64((__be32 *)ctrl, bf->bfreg->map + bf->offset);
/* Make sure doorbells don't leak out of SQ spinlock
* and reach the HCA out of order.
*/
if (neigh->nud_state & NUD_VALID) {
nes_debug(NES_DBG_CM, "Neighbor MAC address for 0x%08X"
" is %pM, Gateway is 0x%08X \n", dst_ip,
- neigh->ha, ntohl(rt->rt_gateway));
+ neigh->ha, ntohl(rt->rt_gw4));
if (arpindex >= 0) {
if (ether_addr_equal(nesadapter->arp_table[arpindex].mac_addr, neigh->ha)) {
pvrdma_page_dir_cleanup(dev, &dev->cq_pdir);
pvrdma_page_dir_cleanup(dev, &dev->async_pdir);
pvrdma_free_slots(dev);
+ dma_free_coherent(&pdev->dev, sizeof(*dev->dsr), dev->dsr,
+ dev->dsrbase);
iounmap(dev->regs);
kfree(dev->sgid_tbl);
return;
list_for_each_entry(entry, &amd_iommu_unity_map, list) {
+ int type, prot = 0;
size_t length;
- int prot = 0;
if (devid < entry->devid_start || devid > entry->devid_end)
continue;
+ type = IOMMU_RESV_DIRECT;
length = entry->address_end - entry->address_start;
if (entry->prot & IOMMU_PROT_IR)
prot |= IOMMU_READ;
if (entry->prot & IOMMU_PROT_IW)
prot |= IOMMU_WRITE;
+ if (entry->prot & IOMMU_UNITY_MAP_FLAG_EXCL_RANGE)
+ /* Exclusion range */
+ type = IOMMU_RESV_RESERVED;
region = iommu_alloc_resv_region(entry->address_start,
- length, prot,
- IOMMU_RESV_DIRECT);
+ length, prot, type);
if (!region) {
dev_err(dev, "Out of memory allocating dm-regions\n");
return;
static void iommu_set_exclusion_range(struct amd_iommu *iommu)
{
u64 start = iommu->exclusion_start & PAGE_MASK;
- u64 limit = (start + iommu->exclusion_length) & PAGE_MASK;
+ u64 limit = (start + iommu->exclusion_length - 1) & PAGE_MASK;
u64 entry;
if (!iommu->exclusion_start)
if (e == NULL)
return -ENOMEM;
+ if (m->flags & IVMD_FLAG_EXCL_RANGE)
+ init_exclusion_range(m);
+
switch (m->type) {
default:
kfree(e);
while (p < end) {
m = (struct ivmd_header *)p;
- if (m->flags & IVMD_FLAG_EXCL_RANGE)
- init_exclusion_range(m);
- else if (m->flags & IVMD_FLAG_UNITY_MAP)
+ if (m->flags & (IVMD_FLAG_UNITY_MAP | IVMD_FLAG_EXCL_RANGE))
init_unity_map_range(m);
p += m->length;
#define IOMMU_PROT_IR 0x01
#define IOMMU_PROT_IW 0x02
+#define IOMMU_UNITY_MAP_FLAG_EXCL_RANGE (1 << 2)
+
/* IOMMU capabilities */
#define IOMMU_CAP_IOTLB 24
#define IOMMU_CAP_NPCACHE 26
#define ARM_V7S_TCR_PD1 BIT(5)
+#ifdef CONFIG_ZONE_DMA32
+#define ARM_V7S_TABLE_GFP_DMA GFP_DMA32
+#define ARM_V7S_TABLE_SLAB_FLAGS SLAB_CACHE_DMA32
+#else
+#define ARM_V7S_TABLE_GFP_DMA GFP_DMA
+#define ARM_V7S_TABLE_SLAB_FLAGS SLAB_CACHE_DMA
+#endif
+
typedef u32 arm_v7s_iopte;
static bool selftest_running;
void *table = NULL;
if (lvl == 1)
- table = (void *)__get_dma_pages(__GFP_ZERO, get_order(size));
+ table = (void *)__get_free_pages(
+ __GFP_ZERO | ARM_V7S_TABLE_GFP_DMA, get_order(size));
else if (lvl == 2)
- table = kmem_cache_zalloc(data->l2_tables, gfp | GFP_DMA);
+ table = kmem_cache_zalloc(data->l2_tables, gfp);
phys = virt_to_phys(table);
- if (phys != (arm_v7s_iopte)phys)
+ if (phys != (arm_v7s_iopte)phys) {
/* Doesn't fit in PTE */
+ dev_err(dev, "Page table does not fit in PTE: %pa", &phys);
goto out_free;
+ }
if (table && !(cfg->quirks & IO_PGTABLE_QUIRK_NO_DMA)) {
dma = dma_map_single(dev, table, size, DMA_TO_DEVICE);
if (dma_mapping_error(dev, dma))
data->l2_tables = kmem_cache_create("io-pgtable_armv7s_l2",
ARM_V7S_TABLE_SIZE(2),
ARM_V7S_TABLE_SIZE(2),
- SLAB_CACHE_DMA, NULL);
+ ARM_V7S_TABLE_SLAB_FLAGS, NULL);
if (!data->l2_tables)
goto out_free_data;
dom = __iommu_domain_alloc(dev->bus, iommu_def_domain_type);
if (!dom && iommu_def_domain_type != IOMMU_DOMAIN_DMA) {
- dev_warn(dev,
- "failed to allocate default IOMMU domain of type %u; falling back to IOMMU_DOMAIN_DMA",
- iommu_def_domain_type);
dom = __iommu_domain_alloc(dev->bus, IOMMU_DOMAIN_DMA);
+ if (dom) {
+ dev_warn(dev,
+ "failed to allocate default IOMMU domain of type %u; falling back to IOMMU_DOMAIN_DMA",
+ iommu_def_domain_type);
+ }
}
group->default_domain = dom;
NULL);
if (!priv->domain) {
pr_err("ls1x-irq: cannot add IRQ domain\n");
+ err = -ENOMEM;
goto out_iounmap;
}
struct sock *sk = sock->sk;
int err = 0;
- if (!maddr || maddr->family != AF_ISDN)
+ if (addr_len < sizeof(struct sockaddr_mISDN))
return -EINVAL;
- if (addr_len < sizeof(struct sockaddr_mISDN))
+ if (!maddr || maddr->family != AF_ISDN)
return -EINVAL;
lock_sock(sk);
const struct i2c_device_id *id)
{
int devid;
+ const struct of_device_id *of_id;
struct pca9532_data *data = i2c_get_clientdata(client);
struct pca9532_platform_data *pca9532_pdata =
dev_get_platdata(&client->dev);
dev_err(&client->dev, "no platform data\n");
return -EINVAL;
}
- devid = (int)(uintptr_t)of_match_device(
- of_pca9532_leds_match, &client->dev)->data;
+ of_id = of_match_device(of_pca9532_leds_match,
+ &client->dev);
+ if (unlikely(!of_id))
+ return -EINVAL;
+ devid = (int)(uintptr_t) of_id->data;
} else {
devid = id->driver_data;
}
trigger_data->net_dev = NULL;
}
- strncpy(trigger_data->device_name, buf, size);
+ memcpy(trigger_data->device_name, buf, size);
+ trigger_data->device_name[size] = 0;
if (size > 0 && trigger_data->device_name[size - 1] == '\n')
trigger_data->device_name[size - 1] = 0;
container_of(nb, struct led_netdev_data, notifier);
if (evt != NETDEV_UP && evt != NETDEV_DOWN && evt != NETDEV_CHANGE
- && evt != NETDEV_REGISTER && evt != NETDEV_UNREGISTER
- && evt != NETDEV_CHANGENAME)
+ && evt != NETDEV_REGISTER && evt != NETDEV_UNREGISTER)
return NOTIFY_DONE;
- if (strcmp(dev->name, trigger_data->device_name))
+ if (!(dev == trigger_data->net_dev ||
+ (evt == NETDEV_REGISTER && !strcmp(dev->name, trigger_data->device_name))))
return NOTIFY_DONE;
cancel_delayed_work_sync(&trigger_data->work);
dev_hold(dev);
trigger_data->net_dev = dev;
break;
- case NETDEV_CHANGENAME:
case NETDEV_UNREGISTER:
- if (trigger_data->net_dev) {
- dev_put(trigger_data->net_dev);
- trigger_data->net_dev = NULL;
- }
+ dev_put(trigger_data->net_dev);
+ trigger_data->net_dev = NULL;
break;
case NETDEV_UP:
case NETDEV_CHANGE:
struct pblk_sec_meta *meta;
struct bio *new_bio = rqd->bio;
struct bio *bio = pr_ctx->orig_bio;
- struct bio_vec src_bv, dst_bv;
void *meta_list = rqd->meta_list;
- int bio_init_idx = pr_ctx->bio_init_idx;
unsigned long *read_bitmap = pr_ctx->bitmap;
+ struct bvec_iter orig_iter = BVEC_ITER_ALL_INIT;
+ struct bvec_iter new_iter = BVEC_ITER_ALL_INIT;
int nr_secs = pr_ctx->orig_nr_secs;
int nr_holes = nr_secs - bitmap_weight(read_bitmap, nr_secs);
void *src_p, *dst_p;
- int hole, i;
+ int bit, i;
if (unlikely(nr_holes == 1)) {
struct ppa_addr ppa;
/* Fill the holes in the original bio */
i = 0;
- hole = find_first_zero_bit(read_bitmap, nr_secs);
- do {
- struct pblk_line *line;
+ for (bit = 0; bit < nr_secs; bit++) {
+ if (!test_bit(bit, read_bitmap)) {
+ struct bio_vec dst_bv, src_bv;
+ struct pblk_line *line;
- line = pblk_ppa_to_line(pblk, rqd->ppa_list[i]);
- kref_put(&line->ref, pblk_line_put);
+ line = pblk_ppa_to_line(pblk, rqd->ppa_list[i]);
+ kref_put(&line->ref, pblk_line_put);
- meta = pblk_get_meta(pblk, meta_list, hole);
- meta->lba = cpu_to_le64(pr_ctx->lba_list_media[i]);
+ meta = pblk_get_meta(pblk, meta_list, bit);
+ meta->lba = cpu_to_le64(pr_ctx->lba_list_media[i]);
- src_bv = new_bio->bi_io_vec[i++];
- dst_bv = bio->bi_io_vec[bio_init_idx + hole];
+ dst_bv = bio_iter_iovec(bio, orig_iter);
+ src_bv = bio_iter_iovec(new_bio, new_iter);
- src_p = kmap_atomic(src_bv.bv_page);
- dst_p = kmap_atomic(dst_bv.bv_page);
+ src_p = kmap_atomic(src_bv.bv_page);
+ dst_p = kmap_atomic(dst_bv.bv_page);
- memcpy(dst_p + dst_bv.bv_offset,
- src_p + src_bv.bv_offset,
- PBLK_EXPOSED_PAGE_SIZE);
+ memcpy(dst_p + dst_bv.bv_offset,
+ src_p + src_bv.bv_offset,
+ PBLK_EXPOSED_PAGE_SIZE);
- kunmap_atomic(src_p);
- kunmap_atomic(dst_p);
+ kunmap_atomic(src_p);
+ kunmap_atomic(dst_p);
- mempool_free(src_bv.bv_page, &pblk->page_bio_pool);
+ flush_dcache_page(dst_bv.bv_page);
+ mempool_free(src_bv.bv_page, &pblk->page_bio_pool);
- hole = find_next_zero_bit(read_bitmap, nr_secs, hole + 1);
- } while (hole < nr_secs);
+ bio_advance_iter(new_bio, &new_iter,
+ PBLK_EXPOSED_PAGE_SIZE);
+ i++;
+ }
+ bio_advance_iter(bio, &orig_iter, PBLK_EXPOSED_PAGE_SIZE);
+ }
bio_put(new_bio);
kfree(pr_ctx);
struct srcu_struct io_barrier;
};
+void disable_discard(struct mapped_device *md);
void disable_write_same(struct mapped_device *md);
void disable_write_zeroes(struct mapped_device *md);
struct list_head list;
};
-const char *dm_allowed_targets[] __initconst = {
+const char * const dm_allowed_targets[] __initconst = {
"crypt",
"delay",
"linear",
static bool ranges_overlap(struct dm_integrity_range *range1, struct dm_integrity_range *range2)
{
return range1->logical_sector < range2->logical_sector + range2->n_sectors &&
- range2->logical_sector + range2->n_sectors > range2->logical_sector;
+ range1->logical_sector + range1->n_sectors > range2->logical_sector;
}
static bool add_new_range(struct dm_integrity_c *ic, struct dm_integrity_range *new_range, bool check_waiting)
struct dm_integrity_range *last_range =
list_first_entry(&ic->wait_list, struct dm_integrity_range, wait_entry);
struct task_struct *last_range_task;
- if (!ranges_overlap(range, last_range))
- break;
last_range_task = last_range->task;
list_del(&last_range->wait_entry);
if (!add_new_range(ic, last_range, false)) {
journal_watermark = val;
else if (sscanf(opt_string, "commit_time:%u%c", &val, &dummy) == 1)
sync_msec = val;
- else if (!memcmp(opt_string, "meta_device:", strlen("meta_device:"))) {
+ else if (!strncmp(opt_string, "meta_device:", strlen("meta_device:"))) {
if (ic->meta_dev) {
dm_put_device(ti, ic->meta_dev);
ic->meta_dev = NULL;
goto bad;
}
ic->sectors_per_block = val >> SECTOR_SHIFT;
- } else if (!memcmp(opt_string, "internal_hash:", strlen("internal_hash:"))) {
+ } else if (!strncmp(opt_string, "internal_hash:", strlen("internal_hash:"))) {
r = get_alg_and_key(opt_string, &ic->internal_hash_alg, &ti->error,
"Invalid internal_hash argument");
if (r)
goto bad;
- } else if (!memcmp(opt_string, "journal_crypt:", strlen("journal_crypt:"))) {
+ } else if (!strncmp(opt_string, "journal_crypt:", strlen("journal_crypt:"))) {
r = get_alg_and_key(opt_string, &ic->journal_crypt_alg, &ti->error,
"Invalid journal_crypt argument");
if (r)
goto bad;
- } else if (!memcmp(opt_string, "journal_mac:", strlen("journal_mac:"))) {
+ } else if (!strncmp(opt_string, "journal_mac:", strlen("journal_mac:"))) {
r = get_alg_and_key(opt_string, &ic->journal_mac_alg, &ti->error,
"Invalid journal_mac argument");
if (r)
.io_hints = dm_integrity_io_hints,
};
-int __init dm_integrity_init(void)
+static int __init dm_integrity_init(void)
{
int r;
return r;
}
-void dm_integrity_exit(void)
+static void __exit dm_integrity_exit(void)
{
dm_unregister_target(&integrity_target);
kmem_cache_destroy(journal_io_cache);
}
if (unlikely(error == BLK_STS_TARGET)) {
- if (req_op(clone) == REQ_OP_WRITE_SAME &&
- !clone->q->limits.max_write_same_sectors)
+ if (req_op(clone) == REQ_OP_DISCARD &&
+ !clone->q->limits.max_discard_sectors)
+ disable_discard(tio->md);
+ else if (req_op(clone) == REQ_OP_WRITE_SAME &&
+ !clone->q->limits.max_write_same_sectors)
disable_write_same(tio->md);
- if (req_op(clone) == REQ_OP_WRITE_ZEROES &&
- !clone->q->limits.max_write_zeroes_sectors)
+ else if (req_op(clone) == REQ_OP_WRITE_ZEROES &&
+ !clone->q->limits.max_write_zeroes_sectors)
disable_write_zeroes(tio->md);
}
return true;
}
+static int device_requires_stable_pages(struct dm_target *ti,
+ struct dm_dev *dev, sector_t start,
+ sector_t len, void *data)
+{
+ struct request_queue *q = bdev_get_queue(dev->bdev);
+
+ return q && bdi_cap_stable_pages_required(q->backing_dev_info);
+}
+
+/*
+ * If any underlying device requires stable pages, a table must require
+ * them as well. Only targets that support iterate_devices are considered:
+ * don't want error, zero, etc to require stable pages.
+ */
+static bool dm_table_requires_stable_pages(struct dm_table *t)
+{
+ struct dm_target *ti;
+ unsigned i;
+
+ for (i = 0; i < dm_table_get_num_targets(t); i++) {
+ ti = dm_table_get_target(t, i);
+
+ if (ti->type->iterate_devices &&
+ ti->type->iterate_devices(ti, device_requires_stable_pages, NULL))
+ return true;
+ }
+
+ return false;
+}
+
void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
struct queue_limits *limits)
{
dm_table_verify_integrity(t);
+ /*
+ * Some devices don't use blk_integrity but still want stable pages
+ * because they do their own checksumming.
+ */
+ if (dm_table_requires_stable_pages(t))
+ q->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES;
+ else
+ q->backing_dev_info->capabilities &= ~BDI_CAP_STABLE_WRITES;
+
/*
* Determine whether or not this queue's I/O timings contribute
* to the entropy pool, Only request-based targets use this.
}
}
+void disable_discard(struct mapped_device *md)
+{
+ struct queue_limits *limits = dm_get_queue_limits(md);
+
+ /* device doesn't really support DISCARD, disable it */
+ limits->max_discard_sectors = 0;
+ blk_queue_flag_clear(QUEUE_FLAG_DISCARD, md->queue);
+}
+
void disable_write_same(struct mapped_device *md)
{
struct queue_limits *limits = dm_get_queue_limits(md);
dm_endio_fn endio = tio->ti->type->end_io;
if (unlikely(error == BLK_STS_TARGET) && md->type != DM_TYPE_NVME_BIO_BASED) {
- if (bio_op(bio) == REQ_OP_WRITE_SAME &&
- !bio->bi_disk->queue->limits.max_write_same_sectors)
+ if (bio_op(bio) == REQ_OP_DISCARD &&
+ !bio->bi_disk->queue->limits.max_discard_sectors)
+ disable_discard(md);
+ else if (bio_op(bio) == REQ_OP_WRITE_SAME &&
+ !bio->bi_disk->queue->limits.max_write_same_sectors)
disable_write_same(md);
- if (bio_op(bio) == REQ_OP_WRITE_ZEROES &&
- !bio->bi_disk->queue->limits.max_write_zeroes_sectors)
+ else if (bio_op(bio) == REQ_OP_WRITE_ZEROES &&
+ !bio->bi_disk->queue->limits.max_write_zeroes_sectors)
disable_write_zeroes(md);
}
return -EINVAL;
}
- /*
- * BIO based queue uses its own splitting. When multipage bvecs
- * is switched on, size of the incoming bio may be too big to
- * be handled in some targets, such as crypt.
- *
- * When these targets are ready for the big bio, we can remove
- * the limit.
- */
- ti->max_io_len = min_t(uint32_t, len, BIO_MAX_PAGES * PAGE_SIZE);
+ ti->max_io_len = (uint32_t) len;
return 0;
}
config MFD_SUN6I_PRCM
bool "Allwinner A31 PRCM controller"
- depends on ARCH_SUNXI
+ depends on ARCH_SUNXI || COMPILE_TEST
select MFD_CORE
help
Support for the PRCM (Power/Reset/Clock Management) unit available
static const struct mfd_cell sprd_pmic_devs[] = {
{
.name = "sc27xx-wdt",
- .of_compatible = "sprd,sc27xx-wdt",
+ .of_compatible = "sprd,sc2731-wdt",
}, {
.name = "sc27xx-rtc",
- .of_compatible = "sprd,sc27xx-rtc",
+ .of_compatible = "sprd,sc2731-rtc",
}, {
.name = "sc27xx-charger",
- .of_compatible = "sprd,sc27xx-charger",
+ .of_compatible = "sprd,sc2731-charger",
}, {
.name = "sc27xx-chg-timer",
- .of_compatible = "sprd,sc27xx-chg-timer",
+ .of_compatible = "sprd,sc2731-chg-timer",
}, {
.name = "sc27xx-fast-chg",
- .of_compatible = "sprd,sc27xx-fast-chg",
+ .of_compatible = "sprd,sc2731-fast-chg",
}, {
.name = "sc27xx-chg-wdt",
- .of_compatible = "sprd,sc27xx-chg-wdt",
+ .of_compatible = "sprd,sc2731-chg-wdt",
}, {
.name = "sc27xx-typec",
- .of_compatible = "sprd,sc27xx-typec",
+ .of_compatible = "sprd,sc2731-typec",
}, {
.name = "sc27xx-flash",
- .of_compatible = "sprd,sc27xx-flash",
+ .of_compatible = "sprd,sc2731-flash",
}, {
.name = "sc27xx-eic",
- .of_compatible = "sprd,sc27xx-eic",
+ .of_compatible = "sprd,sc2731-eic",
}, {
.name = "sc27xx-efuse",
- .of_compatible = "sprd,sc27xx-efuse",
+ .of_compatible = "sprd,sc2731-efuse",
}, {
.name = "sc27xx-thermal",
- .of_compatible = "sprd,sc27xx-thermal",
+ .of_compatible = "sprd,sc2731-thermal",
}, {
.name = "sc27xx-adc",
- .of_compatible = "sprd,sc27xx-adc",
+ .of_compatible = "sprd,sc2731-adc",
}, {
.name = "sc27xx-audio-codec",
- .of_compatible = "sprd,sc27xx-audio-codec",
+ .of_compatible = "sprd,sc2731-audio-codec",
}, {
.name = "sc27xx-regulator",
- .of_compatible = "sprd,sc27xx-regulator",
+ .of_compatible = "sprd,sc2731-regulator",
}, {
.name = "sc27xx-vibrator",
- .of_compatible = "sprd,sc27xx-vibrator",
+ .of_compatible = "sprd,sc2731-vibrator",
}, {
.name = "sc27xx-keypad-led",
- .of_compatible = "sprd,sc27xx-keypad-led",
+ .of_compatible = "sprd,sc2731-keypad-led",
}, {
.name = "sc27xx-bltc",
- .of_compatible = "sprd,sc27xx-bltc",
+ .of_compatible = "sprd,sc2731-bltc",
}, {
.name = "sc27xx-fgu",
- .of_compatible = "sprd,sc27xx-fgu",
+ .of_compatible = "sprd,sc2731-fgu",
}, {
.name = "sc27xx-7sreset",
- .of_compatible = "sprd,sc27xx-7sreset",
+ .of_compatible = "sprd,sc2731-7sreset",
}, {
.name = "sc27xx-poweroff",
- .of_compatible = "sprd,sc27xx-poweroff",
+ .of_compatible = "sprd,sc2731-poweroff",
}, {
.name = "sc27xx-syscon",
- .of_compatible = "sprd,sc27xx-syscon",
+ .of_compatible = "sprd,sc2731-syscon",
},
};
return status;
}
+static int __maybe_unused twl_suspend(struct device *dev)
+{
+ struct i2c_client *client = to_i2c_client(dev);
+
+ if (client->irq)
+ disable_irq(client->irq);
+
+ return 0;
+}
+
+static int __maybe_unused twl_resume(struct device *dev)
+{
+ struct i2c_client *client = to_i2c_client(dev);
+
+ if (client->irq)
+ enable_irq(client->irq);
+
+ return 0;
+}
+
+static SIMPLE_DEV_PM_OPS(twl_dev_pm_ops, twl_suspend, twl_resume);
+
static const struct i2c_device_id twl_ids[] = {
{ "twl4030", TWL4030_VAUX2 }, /* "Triton 2" */
{ "twl5030", 0 }, /* T2 updated */
/* One Client Driver , 4 Clients */
static struct i2c_driver twl_driver = {
.driver.name = DRIVER_NAME,
+ .driver.pm = &twl_dev_pm_ops,
.id_table = twl_ids,
.probe = twl_probe,
.remove = twl_remove,
/* We also need to update CI for internal queues */
if (cs->submitted) {
+ int cs_cnt = atomic_dec_return(&hdev->cs_active_cnt);
+
+ WARN_ONCE((cs_cnt < 0),
+ "hl%d: error in CS active cnt %d\n",
+ hdev->id, cs_cnt);
+
hl_int_hw_queue_update_ci(cs);
spin_lock(&hdev->hw_queues_mirror_lock);
struct hl_vm_phys_pg_pack *phys_pg_pack = NULL;
enum vm_type_t *vm_type;
bool once = true;
+ u64 j;
int i;
if (!dev_entry->hdev->mmu_enable)
} else {
phys_pg_pack = hnode->ptr;
seq_printf(s,
- " 0x%-14llx %-10u %-4u\n",
+ " 0x%-14llx %-10llu %-4u\n",
hnode->vaddr, phys_pg_pack->total_size,
phys_pg_pack->handle);
}
phys_pg_pack->page_size);
seq_puts(s, " physical address\n");
seq_puts(s, "---------------------\n");
- for (i = 0 ; i < phys_pg_pack->npages ; i++) {
+ for (j = 0 ; j < phys_pg_pack->npages ; j++) {
seq_printf(s, " 0x%-14llx\n",
- phys_pg_pack->pages[i]);
+ phys_pg_pack->pages[j]);
}
}
spin_unlock(&vm->idr_lock);
#include <linux/sched/signal.h>
#include <linux/hwmon.h>
+#define HL_PLDM_PENDING_RESET_PER_SEC (HL_PENDING_RESET_PER_SEC * 10)
+
bool hl_device_disabled_or_in_reset(struct hl_device *hdev)
{
if ((hdev->disabled) || (atomic_read(&hdev->in_reset)))
spin_lock_init(&hdev->hw_queues_mirror_lock);
atomic_set(&hdev->in_reset, 0);
atomic_set(&hdev->fd_open_cnt, 0);
+ atomic_set(&hdev->cs_active_cnt, 0);
return 0;
pci_save_state(hdev->pdev);
+ /* Block future CS/VM/JOB completion operations */
+ rc = atomic_cmpxchg(&hdev->in_reset, 0, 1);
+ if (rc) {
+ dev_err(hdev->dev, "Can't suspend while in reset\n");
+ return -EIO;
+ }
+
+ /* This blocks all other stuff that is not blocked by in_reset */
+ hdev->disabled = true;
+
+ /*
+ * Flush anyone that is inside the critical section of enqueue
+ * jobs to the H/W
+ */
+ hdev->asic_funcs->hw_queues_lock(hdev);
+ hdev->asic_funcs->hw_queues_unlock(hdev);
+
+ /* Flush processes that are sending message to CPU */
+ mutex_lock(&hdev->send_cpu_message_lock);
+ mutex_unlock(&hdev->send_cpu_message_lock);
+
rc = hdev->asic_funcs->suspend(hdev);
if (rc)
dev_err(hdev->dev,
pci_set_power_state(hdev->pdev, PCI_D0);
pci_restore_state(hdev->pdev);
- rc = pci_enable_device(hdev->pdev);
+ rc = pci_enable_device_mem(hdev->pdev);
if (rc) {
dev_err(hdev->dev,
"Failed to enable PCI device in resume\n");
return rc;
}
+ pci_set_master(hdev->pdev);
+
rc = hdev->asic_funcs->resume(hdev);
if (rc) {
- dev_err(hdev->dev,
- "Failed to enable PCI access from device CPU\n");
- return rc;
+ dev_err(hdev->dev, "Failed to resume device after suspend\n");
+ goto disable_device;
+ }
+
+
+ hdev->disabled = false;
+ atomic_set(&hdev->in_reset, 0);
+
+ rc = hl_device_reset(hdev, true, false);
+ if (rc) {
+ dev_err(hdev->dev, "Failed to reset device during resume\n");
+ goto disable_device;
}
return 0;
+
+disable_device:
+ pci_clear_master(hdev->pdev);
+ pci_disable_device(hdev->pdev);
+
+ return rc;
}
static void hl_device_hard_reset_pending(struct work_struct *work)
struct hl_device_reset_work *device_reset_work =
container_of(work, struct hl_device_reset_work, reset_work);
struct hl_device *hdev = device_reset_work->hdev;
- u16 pending_cnt = HL_PENDING_RESET_PER_SEC;
+ u16 pending_total, pending_cnt;
struct task_struct *task = NULL;
+ if (hdev->pldm)
+ pending_total = HL_PLDM_PENDING_RESET_PER_SEC;
+ else
+ pending_total = HL_PENDING_RESET_PER_SEC;
+
+ pending_cnt = pending_total;
+
/* Flush all processes that are inside hl_open */
mutex_lock(&hdev->fd_open_cnt_lock);
}
}
+ pending_cnt = pending_total;
+
+ while ((atomic_read(&hdev->fd_open_cnt)) && (pending_cnt)) {
+
+ pending_cnt--;
+
+ ssleep(1);
+ }
+
+ if (atomic_read(&hdev->fd_open_cnt))
+ dev_crit(hdev->dev,
+ "Going to hard reset with open user contexts\n");
+
mutex_unlock(&hdev->fd_open_cnt_lock);
hl_device_reset(hdev, true, true);
return retval;
}
-static void goya_resume_external_queues(struct hl_device *hdev)
-{
- WREG32(mmDMA_QM_0_GLBL_CFG1, 0);
- WREG32(mmDMA_QM_1_GLBL_CFG1, 0);
- WREG32(mmDMA_QM_2_GLBL_CFG1, 0);
- WREG32(mmDMA_QM_3_GLBL_CFG1, 0);
- WREG32(mmDMA_QM_4_GLBL_CFG1, 0);
-}
-
/*
* goya_init_cpu_queues - Initialize PQ/CQ/EQ of CPU
*
return retval;
}
-static void goya_resume_internal_queues(struct hl_device *hdev)
-{
- WREG32(mmMME_QM_GLBL_CFG1, 0);
- WREG32(mmMME_CMDQ_GLBL_CFG1, 0);
-
- WREG32(mmTPC0_QM_GLBL_CFG1, 0);
- WREG32(mmTPC0_CMDQ_GLBL_CFG1, 0);
-
- WREG32(mmTPC1_QM_GLBL_CFG1, 0);
- WREG32(mmTPC1_CMDQ_GLBL_CFG1, 0);
-
- WREG32(mmTPC2_QM_GLBL_CFG1, 0);
- WREG32(mmTPC2_CMDQ_GLBL_CFG1, 0);
-
- WREG32(mmTPC3_QM_GLBL_CFG1, 0);
- WREG32(mmTPC3_CMDQ_GLBL_CFG1, 0);
-
- WREG32(mmTPC4_QM_GLBL_CFG1, 0);
- WREG32(mmTPC4_CMDQ_GLBL_CFG1, 0);
-
- WREG32(mmTPC5_QM_GLBL_CFG1, 0);
- WREG32(mmTPC5_CMDQ_GLBL_CFG1, 0);
-
- WREG32(mmTPC6_QM_GLBL_CFG1, 0);
- WREG32(mmTPC6_CMDQ_GLBL_CFG1, 0);
-
- WREG32(mmTPC7_QM_GLBL_CFG1, 0);
- WREG32(mmTPC7_CMDQ_GLBL_CFG1, 0);
-}
-
static void goya_dma_stall(struct hl_device *hdev)
{
WREG32(mmDMA_QM_0_GLBL_CFG1, 1 << DMA_QM_0_GLBL_CFG1_DMA_STOP_SHIFT);
{
int rc;
- rc = goya_stop_internal_queues(hdev);
-
- if (rc) {
- dev_err(hdev->dev, "failed to stop internal queues\n");
- return rc;
- }
-
- rc = goya_stop_external_queues(hdev);
-
- if (rc) {
- dev_err(hdev->dev, "failed to stop external queues\n");
- return rc;
- }
-
rc = goya_send_pci_access_msg(hdev, ARMCP_PACKET_DISABLE_PCI_ACCESS);
if (rc)
dev_err(hdev->dev, "Failed to disable PCI access from CPU\n");
int goya_resume(struct hl_device *hdev)
{
- int rc;
-
- goya_resume_external_queues(hdev);
- goya_resume_internal_queues(hdev);
-
- rc = goya_send_pci_access_msg(hdev, ARMCP_PACKET_ENABLE_PCI_ACCESS);
- if (rc)
- dev_err(hdev->dev, "Failed to enable PCI access from CPU\n");
- return rc;
+ return goya_init_iatu(hdev);
}
static int goya_cb_mmap(struct hl_device *hdev, struct vm_area_struct *vma,
*dma_handle = hdev->asic_prop.sram_base_address;
- base = hdev->pcie_bar[SRAM_CFG_BAR_ID];
+ base = (void *) hdev->pcie_bar[SRAM_CFG_BAR_ID];
switch (queue_id) {
case GOYA_QUEUE_ID_MME:
* struct hl_vm_phys_pg_pack - physical page pack.
* @vm_type: describes the type of the virtual area descriptor.
* @pages: the physical page array.
+ * @npages: num physical pages in the pack.
+ * @total_size: total size of all the pages in this list.
* @mapping_cnt: number of shared mappings.
* @asid: the context related to this list.
- * @npages: num physical pages in the pack.
* @page_size: size of each page in the pack.
- * @total_size: total size of all the pages in this list.
* @flags: HL_MEM_* flags related to this list.
* @handle: the provided handle related to this list.
* @offset: offset from the first page.
struct hl_vm_phys_pg_pack {
enum vm_type_t vm_type; /* must be first */
u64 *pages;
+ u64 npages;
+ u64 total_size;
atomic_t mapping_cnt;
u32 asid;
- u32 npages;
u32 page_size;
- u32 total_size;
u32 flags;
u32 handle;
u32 offset;
* @cb_pool_lock: protects the CB pool.
* @user_ctx: current user context executing.
* @dram_used_mem: current DRAM memory consumption.
- * @in_reset: is device in reset flow.
- * @curr_pll_profile: current PLL profile.
- * @fd_open_cnt: number of open user processes.
* @timeout_jiffies: device CS timeout value.
* @max_power: the max power of the device, as configured by the sysadmin. This
* value is saved so in case of hard-reset, KMD will restore this
* value and update the F/W after the re-initialization
+ * @in_reset: is device in reset flow.
+ * @curr_pll_profile: current PLL profile.
+ * @fd_open_cnt: number of open user processes.
+ * @cs_active_cnt: number of active command submissions on this device (active
+ * means already in H/W queues)
* @major: habanalabs KMD major.
* @high_pll: high PLL profile frequency.
* @soft_reset_cnt: number of soft reset since KMD loading.
struct hl_ctx *user_ctx;
atomic64_t dram_used_mem;
+ u64 timeout_jiffies;
+ u64 max_power;
atomic_t in_reset;
atomic_t curr_pll_profile;
atomic_t fd_open_cnt;
- u64 timeout_jiffies;
- u64 max_power;
+ atomic_t cs_active_cnt;
u32 major;
u32 high_pll;
u32 soft_reset_cnt;
spin_unlock(&hdev->hw_queues_mirror_lock);
}
- list_for_each_entry_safe(job, tmp, &cs->job_list, cs_node) {
+ atomic_inc(&hdev->cs_active_cnt);
+
+ list_for_each_entry_safe(job, tmp, &cs->job_list, cs_node)
if (job->ext_queue)
ext_hw_queue_schedule_job(job);
else
int_hw_queue_schedule_job(job);
- }
cs->submitted = true;
struct hl_device *hdev = ctx->hdev;
struct hl_vm *vm = &hdev->vm;
struct hl_vm_phys_pg_pack *phys_pg_pack;
- u64 paddr = 0;
- u32 total_size, num_pgs, num_curr_pgs, page_size, page_shift;
- int handle, rc, i;
+ u64 paddr = 0, total_size, num_pgs, i;
+ u32 num_curr_pgs, page_size, page_shift;
+ int handle, rc;
bool contiguous;
num_curr_pgs = 0;
paddr = (u64) gen_pool_alloc(vm->dram_pg_pool, total_size);
if (!paddr) {
dev_err(hdev->dev,
- "failed to allocate %u huge contiguous pages\n",
+ "failed to allocate %llu huge contiguous pages\n",
num_pgs);
return -ENOMEM;
}
phys_pg_pack->flags = args->flags;
phys_pg_pack->contiguous = contiguous;
- phys_pg_pack->pages = kcalloc(num_pgs, sizeof(u64), GFP_KERNEL);
+ phys_pg_pack->pages = kvmalloc_array(num_pgs, sizeof(u64), GFP_KERNEL);
if (!phys_pg_pack->pages) {
rc = -ENOMEM;
goto pages_arr_err;
gen_pool_free(vm->dram_pg_pool, phys_pg_pack->pages[i],
page_size);
- kfree(phys_pg_pack->pages);
+ kvfree(phys_pg_pack->pages);
pages_arr_err:
kfree(phys_pg_pack);
pages_pack_err:
struct hl_vm_phys_pg_pack *phys_pg_pack)
{
struct hl_vm *vm = &hdev->vm;
- int i;
+ u64 i;
if (!phys_pg_pack->created_from_userptr) {
if (phys_pg_pack->contiguous) {
}
}
- kfree(phys_pg_pack->pages);
+ kvfree(phys_pg_pack->pages);
kfree(phys_pg_pack);
}
* - Return the start address of the virtual block
*/
static u64 get_va_block(struct hl_device *hdev,
- struct hl_va_range *va_range, u32 size, u64 hint_addr,
+ struct hl_va_range *va_range, u64 size, u64 hint_addr,
bool is_userptr)
{
struct hl_vm_va_block *va_block, *new_va_block = NULL;
}
if (!new_va_block) {
- dev_err(hdev->dev, "no available va block for size %u\n", size);
+ dev_err(hdev->dev, "no available va block for size %llu\n",
+ size);
goto out;
}
struct hl_vm_phys_pg_pack *phys_pg_pack;
struct scatterlist *sg;
dma_addr_t dma_addr;
- u64 page_mask;
- u32 npages, total_npages, page_size = PAGE_SIZE;
+ u64 page_mask, total_npages;
+ u32 npages, page_size = PAGE_SIZE;
bool first = true, is_huge_page_opt = true;
int rc, i, j;
page_mask = ~(((u64) page_size) - 1);
- phys_pg_pack->pages = kcalloc(total_npages, sizeof(u64), GFP_KERNEL);
+ phys_pg_pack->pages = kvmalloc_array(total_npages, sizeof(u64),
+ GFP_KERNEL);
if (!phys_pg_pack->pages) {
rc = -ENOMEM;
goto page_pack_arr_mem_err;
struct hl_vm_phys_pg_pack *phys_pg_pack)
{
struct hl_device *hdev = ctx->hdev;
- u64 next_vaddr = vaddr, paddr;
+ u64 next_vaddr = vaddr, paddr, mapped_pg_cnt = 0, i;
u32 page_size = phys_pg_pack->page_size;
- int i, rc = 0, mapped_pg_cnt = 0;
+ int rc = 0;
for (i = 0 ; i < phys_pg_pack->npages ; i++) {
paddr = phys_pg_pack->pages[i];
rc = hl_mmu_map(ctx, next_vaddr, paddr, page_size);
if (rc) {
dev_err(hdev->dev,
- "map failed for handle %u, npages: %d, mapped: %d",
+ "map failed for handle %u, npages: %llu, mapped: %llu",
phys_pg_pack->handle, phys_pg_pack->npages,
mapped_pg_cnt);
goto err;
struct hl_vm_hash_node *hnode = NULL;
struct hl_userptr *userptr = NULL;
enum vm_type_t *vm_type;
- u64 next_vaddr;
+ u64 next_vaddr, i;
u32 page_size;
bool is_userptr;
- int i, rc;
+ int rc;
/* protect from double entrance */
mutex_lock(&ctx->mem_hash_lock);
int hl_mmu_map(struct hl_ctx *ctx, u64 virt_addr, u64 phys_addr, u32 page_size)
{
struct hl_device *hdev = ctx->hdev;
- u64 real_virt_addr;
+ u64 real_virt_addr, real_phys_addr;
u32 real_page_size, npages;
int i, rc, mapped_cnt = 0;
npages = page_size / real_page_size;
real_virt_addr = virt_addr;
+ real_phys_addr = phys_addr;
for (i = 0 ; i < npages ; i++) {
- rc = _hl_mmu_map(ctx, real_virt_addr, phys_addr,
+ rc = _hl_mmu_map(ctx, real_virt_addr, real_phys_addr,
real_page_size);
if (rc)
goto err;
real_virt_addr += real_page_size;
+ real_phys_addr += real_page_size;
mapped_cnt++;
}
struct mmc_command *cmd;
struct mmc_data *data;
unsigned int dma_on:1;
- unsigned int early_data:1;
struct mutex cmd_mutex;
host->sg_count--;
}
-static void alcor_trigger_data_transfer(struct alcor_sdmmc_host *host,
- bool early)
+static void alcor_trigger_data_transfer(struct alcor_sdmmc_host *host)
{
struct alcor_pci_priv *priv = host->alcor_pci;
struct mmc_data *data = host->data;
ctrl |= AU6601_DATA_WRITE;
if (data->host_cookie == COOKIE_MAPPED) {
- if (host->early_data) {
- host->early_data = false;
- return;
- }
-
- host->early_data = early;
-
alcor_data_set_dma(host);
ctrl |= AU6601_DATA_DMA_MODE;
host->dma_on = 1;
static void alcor_prepare_data(struct alcor_sdmmc_host *host,
struct mmc_command *cmd)
{
+ struct alcor_pci_priv *priv = host->alcor_pci;
struct mmc_data *data = cmd->data;
if (!data)
if (data->host_cookie != COOKIE_MAPPED)
alcor_prepare_sg_miter(host);
- alcor_trigger_data_transfer(host, true);
+ alcor_write8(priv, 0, AU6601_DATA_XFER_CTRL);
}
static void alcor_send_cmd(struct alcor_sdmmc_host *host,
if (!host->data)
return false;
- alcor_trigger_data_transfer(host, false);
+ alcor_trigger_data_transfer(host);
host->cmd = NULL;
return true;
}
if (!host->data)
alcor_request_complete(host, 1);
else
- alcor_trigger_data_transfer(host, false);
+ alcor_trigger_data_transfer(host);
host->cmd = NULL;
}
break;
case AU6601_INT_READ_BUF_RDY:
alcor_trf_block_pio(host, true);
- if (!host->blocks)
- break;
- alcor_trigger_data_transfer(host, false);
return 1;
case AU6601_INT_WRITE_BUF_RDY:
alcor_trf_block_pio(host, false);
- if (!host->blocks)
- break;
- alcor_trigger_data_transfer(host, false);
return 1;
case AU6601_INT_DMA_END:
if (!host->sg_count)
break;
}
- if (intmask & AU6601_INT_DATA_END)
- return 0;
+ if (intmask & AU6601_INT_DATA_END) {
+ if (!host->dma_on && host->blocks) {
+ alcor_trigger_data_transfer(host);
+ return 1;
+ } else {
+ return 0;
+ }
+ }
return 1;
}
sdhci_reset(host, mask);
}
+#define CMD_ERR_MASK (SDHCI_INT_CRC | SDHCI_INT_END_BIT | SDHCI_INT_INDEX |\
+ SDHCI_INT_TIMEOUT)
+#define CMD_MASK (CMD_ERR_MASK | SDHCI_INT_RESPONSE)
+
+static u32 sdhci_omap_irq(struct sdhci_host *host, u32 intmask)
+{
+ struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+ struct sdhci_omap_host *omap_host = sdhci_pltfm_priv(pltfm_host);
+
+ if (omap_host->is_tuning && host->cmd && !host->data_early &&
+ (intmask & CMD_ERR_MASK)) {
+
+ /*
+ * Since we are not resetting data lines during tuning
+ * operation, data error or data complete interrupts
+ * might still arrive. Mark this request as a failure
+ * but still wait for the data interrupt
+ */
+ if (intmask & SDHCI_INT_TIMEOUT)
+ host->cmd->error = -ETIMEDOUT;
+ else
+ host->cmd->error = -EILSEQ;
+
+ host->cmd = NULL;
+
+ /*
+ * Sometimes command error interrupts and command complete
+ * interrupt will arrive together. Clear all command related
+ * interrupts here.
+ */
+ sdhci_writel(host, intmask & CMD_MASK, SDHCI_INT_STATUS);
+ intmask &= ~CMD_MASK;
+ }
+
+ return intmask;
+}
+
static struct sdhci_ops sdhci_omap_ops = {
.set_clock = sdhci_omap_set_clock,
.set_power = sdhci_omap_set_power,
.platform_send_init_74_clocks = sdhci_omap_init_74_clocks,
.reset = sdhci_omap_reset,
.set_uhs_signaling = sdhci_omap_set_uhs_signaling,
+ .irq = sdhci_omap_irq,
};
static int sdhci_omap_set_capabilities(struct sdhci_omap_host *omap_host)
continue;
}
- if (time_after(jiffies, timeo) && !chip_ready(map, adr))
+ /*
+ * We check "time_after" and "!chip_good" before checking "chip_good" to avoid
+ * the failure due to scheduling.
+ */
+ if (time_after(jiffies, timeo) && !chip_good(map, adr, datum))
break;
if (chip_good(map, adr, datum)) {
*/
static netdev_tx_t ipddp_xmit(struct sk_buff *skb, struct net_device *dev)
{
- __be32 paddr = skb_rtable(skb)->rt_gateway;
+ struct rtable *rtable = skb_rtable(skb);
+ __be32 paddr = 0;
struct ddpehdr *ddp;
struct ipddp_route *rt;
struct atalk_addr *our_addr;
+ if (rtable->rt_gw_family == AF_INET)
+ paddr = rtable->rt_gw4;
+
spin_lock(&ipddp_route_lock);
/*
return NOTIFY_DONE;
if (event_dev->flags & IFF_MASTER) {
+ int ret;
+
netdev_dbg(event_dev, "IFF_MASTER\n");
- return bond_master_netdev_event(event, event_dev);
+ ret = bond_master_netdev_event(event, event_dev);
+ if (ret != NOTIFY_DONE)
+ return ret;
}
if (event_dev->flags & IFF_SLAVE) {
static ssize_t perm_hwaddr_show(struct slave *slave, char *buf)
{
- return sprintf(buf, "%pM\n", slave->perm_hwaddr);
+ return sprintf(buf, "%*phC\n",
+ slave->dev->addr_len,
+ slave->perm_hwaddr);
}
static SLAVE_ATTR_RO(perm_hwaddr);
interface = PHY_INTERFACE_MODE_GMII;
if (gbit)
break;
+ /* fall through */
case 0:
interface = PHY_INTERFACE_MODE_MII;
break;
return 0;
lane = mv88e6390x_serdes_get_lane(chip, port);
- if (lane < 0)
+ if (lane < 0 && lane != -ENODEV)
return lane;
- if (chip->ports[port].serdes_irq) {
- err = mv88e6390_serdes_irq_disable(chip, port, lane);
+ if (lane >= 0) {
+ if (chip->ports[port].serdes_irq) {
+ err = mv88e6390_serdes_irq_disable(chip, port, lane);
+ if (err)
+ return err;
+ }
+
+ err = mv88e6390x_serdes_power(chip, port, false);
if (err)
return err;
}
- err = mv88e6390x_serdes_power(chip, port, false);
- if (err)
- return err;
+ chip->ports[port].cmode = 0;
if (cmode) {
err = mv88e6xxx_port_read(chip, port, MV88E6XXX_PORT_STS, ®);
if (err)
return err;
+ chip->ports[port].cmode = cmode;
+
+ lane = mv88e6390x_serdes_get_lane(chip, port);
+ if (lane < 0)
+ return lane;
+
err = mv88e6390x_serdes_power(chip, port, true);
if (err)
return err;
}
}
- chip->ports[port].cmode = cmode;
-
return 0;
}
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
+#include <linux/ethtool.h>
#include <linux/init.h>
#include <linux/moduleparam.h>
#include <linux/rtnetlink.h>
strlcpy(info->version, DRV_VERSION, sizeof(info->version));
}
-static int dummy_get_ts_info(struct net_device *dev,
- struct ethtool_ts_info *ts_info)
-{
- ts_info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
- SOF_TIMESTAMPING_RX_SOFTWARE |
- SOF_TIMESTAMPING_SOFTWARE;
-
- ts_info->phc_index = -1;
-
- return 0;
-};
-
static const struct ethtool_ops dummy_ethtool_ops = {
.get_drvinfo = dummy_get_drvinfo,
- .get_ts_info = dummy_get_ts_info,
+ .get_ts_info = ethtool_op_get_ts_info,
};
static void dummy_setup(struct net_device *dev)
}
}
- if (netif_xmit_stopped(txq) || !skb->xmit_more) {
+ if (netif_xmit_stopped(txq) || !netdev_xmit_more()) {
/* trigger the dma engine. ena_com_write_sq_doorbell()
* has a mb
*/
smp_wmb();
ring->cur = cur_index + 1;
- if (!packet->skb->xmit_more ||
+ if (!netdev_xmit_more() ||
netif_xmit_stopped(netdev_get_tx_queue(pdata->netdev,
channel->queue_index)))
xgbe_tx_start_xmit(channel, ring);
unsigned int dma_len;
unsigned int align;
unsigned int next;
+ bool xmit_more;
if (atomic_read(&priv->tx_free) <= NB8800_DESC_LOW) {
netif_stop_queue(dev);
return NETDEV_TX_OK;
}
+ xmit_more = netdev_xmit_more();
if (atomic_dec_return(&priv->tx_free) <= NB8800_DESC_LOW) {
netif_stop_queue(dev);
- skb->xmit_more = 0;
+ xmit_more = false;
}
next = priv->tx_next;
desc->n_addr = priv->tx_bufs[next].dma_desc;
desc->config = DESC_BTS(2) | DESC_DS | DESC_EOF | dma_len;
- if (!skb->xmit_more)
+ if (!xmit_more)
desc->config |= DESC_EOC;
txb->skb = skb;
priv->tx_next = next;
- if (!skb->xmit_more) {
+ if (!xmit_more) {
smp_wmb();
priv->tx_chain->ready = true;
priv->tx_chain = NULL;
return 0;
}
+#define BNX2X_P2P_DETECT_PARAM_MASK 0x5F5
+#define BNX2X_P2P_DETECT_RULE_MASK 0x3DBB
+#define BNX2X_PTP_TX_ON_PARAM_MASK (BNX2X_P2P_DETECT_PARAM_MASK & 0x6AA)
+#define BNX2X_PTP_TX_ON_RULE_MASK (BNX2X_P2P_DETECT_RULE_MASK & 0x3EEE)
+#define BNX2X_PTP_V1_L4_PARAM_MASK (BNX2X_P2P_DETECT_PARAM_MASK & 0x7EE)
+#define BNX2X_PTP_V1_L4_RULE_MASK (BNX2X_P2P_DETECT_RULE_MASK & 0x3FFE)
+#define BNX2X_PTP_V2_L4_PARAM_MASK (BNX2X_P2P_DETECT_PARAM_MASK & 0x7EA)
+#define BNX2X_PTP_V2_L4_RULE_MASK (BNX2X_P2P_DETECT_RULE_MASK & 0x3FEE)
+#define BNX2X_PTP_V2_L2_PARAM_MASK (BNX2X_P2P_DETECT_PARAM_MASK & 0x6BF)
+#define BNX2X_PTP_V2_L2_RULE_MASK (BNX2X_P2P_DETECT_RULE_MASK & 0x3EFF)
+#define BNX2X_PTP_V2_PARAM_MASK (BNX2X_P2P_DETECT_PARAM_MASK & 0x6AA)
+#define BNX2X_PTP_V2_RULE_MASK (BNX2X_P2P_DETECT_RULE_MASK & 0x3EEE)
+
int bnx2x_configure_ptp_filters(struct bnx2x *bp)
{
int port = BP_PORT(bp);
+ u32 param, rule;
int rc;
if (!bp->hwtstamp_ioctl_called)
return 0;
+ param = port ? NIG_REG_P1_TLLH_PTP_PARAM_MASK :
+ NIG_REG_P0_TLLH_PTP_PARAM_MASK;
+ rule = port ? NIG_REG_P1_TLLH_PTP_RULE_MASK :
+ NIG_REG_P0_TLLH_PTP_RULE_MASK;
switch (bp->tx_type) {
case HWTSTAMP_TX_ON:
bp->flags |= TX_TIMESTAMPING_EN;
- REG_WR(bp, port ? NIG_REG_P1_TLLH_PTP_PARAM_MASK :
- NIG_REG_P0_TLLH_PTP_PARAM_MASK, 0x6AA);
- REG_WR(bp, port ? NIG_REG_P1_TLLH_PTP_RULE_MASK :
- NIG_REG_P0_TLLH_PTP_RULE_MASK, 0x3EEE);
+ REG_WR(bp, param, BNX2X_PTP_TX_ON_PARAM_MASK);
+ REG_WR(bp, rule, BNX2X_PTP_TX_ON_RULE_MASK);
break;
case HWTSTAMP_TX_ONESTEP_SYNC:
BNX2X_ERR("One-step timestamping is not supported\n");
return -ERANGE;
}
+ param = port ? NIG_REG_P1_LLH_PTP_PARAM_MASK :
+ NIG_REG_P0_LLH_PTP_PARAM_MASK;
+ rule = port ? NIG_REG_P1_LLH_PTP_RULE_MASK :
+ NIG_REG_P0_LLH_PTP_RULE_MASK;
switch (bp->rx_filter) {
case HWTSTAMP_FILTER_NONE:
break;
case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
bp->rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
/* Initialize PTP detection for UDP/IPv4 events */
- REG_WR(bp, port ? NIG_REG_P1_LLH_PTP_PARAM_MASK :
- NIG_REG_P0_LLH_PTP_PARAM_MASK, 0x7EE);
- REG_WR(bp, port ? NIG_REG_P1_LLH_PTP_RULE_MASK :
- NIG_REG_P0_LLH_PTP_RULE_MASK, 0x3FFE);
+ REG_WR(bp, param, BNX2X_PTP_V1_L4_PARAM_MASK);
+ REG_WR(bp, rule, BNX2X_PTP_V1_L4_RULE_MASK);
break;
case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
bp->rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT;
/* Initialize PTP detection for UDP/IPv4 or UDP/IPv6 events */
- REG_WR(bp, port ? NIG_REG_P1_LLH_PTP_PARAM_MASK :
- NIG_REG_P0_LLH_PTP_PARAM_MASK, 0x7EA);
- REG_WR(bp, port ? NIG_REG_P1_LLH_PTP_RULE_MASK :
- NIG_REG_P0_LLH_PTP_RULE_MASK, 0x3FEE);
+ REG_WR(bp, param, BNX2X_PTP_V2_L4_PARAM_MASK);
+ REG_WR(bp, rule, BNX2X_PTP_V2_L4_RULE_MASK);
break;
case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
bp->rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT;
/* Initialize PTP detection L2 events */
- REG_WR(bp, port ? NIG_REG_P1_LLH_PTP_PARAM_MASK :
- NIG_REG_P0_LLH_PTP_PARAM_MASK, 0x6BF);
- REG_WR(bp, port ? NIG_REG_P1_LLH_PTP_RULE_MASK :
- NIG_REG_P0_LLH_PTP_RULE_MASK, 0x3EFF);
+ REG_WR(bp, param, BNX2X_PTP_V2_L2_PARAM_MASK);
+ REG_WR(bp, rule, BNX2X_PTP_V2_L2_RULE_MASK);
break;
case HWTSTAMP_FILTER_PTP_V2_EVENT:
case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
bp->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
/* Initialize PTP detection L2, UDP/IPv4 or UDP/IPv6 events */
- REG_WR(bp, port ? NIG_REG_P1_LLH_PTP_PARAM_MASK :
- NIG_REG_P0_LLH_PTP_PARAM_MASK, 0x6AA);
- REG_WR(bp, port ? NIG_REG_P1_LLH_PTP_RULE_MASK :
- NIG_REG_P0_LLH_PTP_RULE_MASK, 0x3EEE);
+ REG_WR(bp, param, BNX2X_PTP_V2_PARAM_MASK);
+ REG_WR(bp, rule, BNX2X_PTP_V2_RULE_MASK);
break;
}
bnx2x_sample_bulletin(bp);
if (bp->shadow_bulletin.content.valid_bitmap & 1 << VLAN_VALID) {
- BNX2X_ERR("Hypervisor will dicline the request, avoiding\n");
+ BNX2X_ERR("Hypervisor will decline the request, avoiding\n");
rc = -EINVAL;
goto out;
}
prod = NEXT_TX(prod);
txr->tx_prod = prod;
- if (!skb->xmit_more || netif_xmit_stopped(txq))
+ if (!netdev_xmit_more() || netif_xmit_stopped(txq))
bnxt_db_write(bp, &txr->tx_db, prod);
tx_done:
mmiowb();
if (unlikely(bnxt_tx_avail(bp, txr) <= MAX_SKB_FRAGS + 1)) {
- if (skb->xmit_more && !tx_buf->is_push)
+ if (netdev_xmit_more() && !tx_buf->is_push)
bnxt_db_write(bp, &txr->tx_db, prod);
netif_tx_stop_queue(txq);
tpa_info = &rxr->rx_tpa[agg_id];
if (unlikely(cons != rxr->rx_next_cons)) {
+ netdev_warn(bp->dev, "TPA cons %x != expected cons %x\n",
+ cons, rxr->rx_next_cons);
bnxt_sched_reset(bp, rxr);
return;
}
}
cons = rxcmp->rx_cmp_opaque;
- rx_buf = &rxr->rx_buf_ring[cons];
- data = rx_buf->data;
- data_ptr = rx_buf->data_ptr;
if (unlikely(cons != rxr->rx_next_cons)) {
int rc1 = bnxt_discard_rx(bp, cpr, raw_cons, rxcmp);
+ netdev_warn(bp->dev, "RX cons %x != expected cons %x\n",
+ cons, rxr->rx_next_cons);
bnxt_sched_reset(bp, rxr);
return rc1;
}
+ rx_buf = &rxr->rx_buf_ring[cons];
+ data = rx_buf->data;
+ data_ptr = rx_buf->data_ptr;
prefetch(data_ptr);
misc = le32_to_cpu(rxcmp->rx_cmp_misc_v1);
rx_buf->data = NULL;
if (rxcmp1->rx_cmp_cfa_code_errors_v2 & RX_CMP_L2_ERRORS) {
+ u32 rx_err = le32_to_cpu(rxcmp1->rx_cmp_cfa_code_errors_v2);
+
bnxt_reuse_rx_data(rxr, cons, data);
if (agg_bufs)
bnxt_reuse_rx_agg_bufs(cpr, cp_cons, agg_bufs);
rc = -EIO;
+ if (rx_err & RX_CMPL_ERRORS_BUFFER_ERROR_MASK) {
+ netdev_warn(bp->dev, "RX buffer error %x\n", rx_err);
+ bnxt_sched_reset(bp, rxr);
+ }
goto next_rx;
}
.ndo_bpf = bnxt_xdp,
.ndo_bridge_getlink = bnxt_bridge_getlink,
.ndo_bridge_setlink = bnxt_bridge_setlink,
- .ndo_get_port_parent_id = bnxt_get_port_parent_id,
.ndo_get_devlink_port = bnxt_get_devlink_port,
};
return rc;
}
+static int bnxt_pcie_dsn_get(struct bnxt *bp, u8 dsn[])
+{
+ struct pci_dev *pdev = bp->pdev;
+ int pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_DSN);
+ u32 dw;
+
+ if (!pos) {
+ netdev_info(bp->dev, "Unable do read adapter's DSN");
+ return -EOPNOTSUPP;
+ }
+
+ /* DSN (two dw) is at an offset of 4 from the cap pos */
+ pos += 4;
+ pci_read_config_dword(pdev, pos, &dw);
+ put_unaligned_le32(dw, &dsn[0]);
+ pci_read_config_dword(pdev, pos + 4, &dw);
+ put_unaligned_le32(dw, &dsn[4]);
+ return 0;
+}
+
static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
{
static int version_printed;
goto init_err_pci_clean;
}
+ /* Read the adapter's DSN to use as the eswitch switch_id */
+ rc = bnxt_pcie_dsn_get(bp, bp->switch_id);
+ if (rc)
+ goto init_err_pci_clean;
+
bnxt_hwrm_func_qcfg(bp);
bnxt_hwrm_vnic_qcaps(bp);
bnxt_hwrm_port_led_qcaps(bp);
}
devlink_port_attrs_set(&bp->dl_port, DEVLINK_PORT_FLAVOUR_PHYSICAL,
- bp->pf.port_id, false, 0);
+ bp->pf.port_id, false, 0,
+ bp->switch_id, sizeof(bp->switch_id));
rc = devlink_port_register(dl, &bp->dl_port, bp->pf.port_id);
if (rc) {
netdev_err(bp->dev, "devlink_port_register failed");
dev->min_mtu = ETH_ZLEN;
}
-static int bnxt_pcie_dsn_get(struct bnxt *bp, u8 dsn[])
-{
- struct pci_dev *pdev = bp->pdev;
- int pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_DSN);
- u32 dw;
-
- if (!pos) {
- netdev_info(bp->dev, "Unable do read adapter's DSN");
- return -EOPNOTSUPP;
- }
-
- /* DSN (two dw) is at an offset of 4 from the cap pos */
- pos += 4;
- pci_read_config_dword(pdev, pos, &dw);
- put_unaligned_le32(dw, &dsn[0]);
- pci_read_config_dword(pdev, pos + 4, &dw);
- put_unaligned_le32(dw, &dsn[4]);
- return 0;
-}
-
static int bnxt_vf_reps_create(struct bnxt *bp)
{
u16 *cfa_code_map = NULL, num_vfs = pci_num_vf(bp->pdev);
}
}
- /* Read the adapter's DSN to use as the eswitch switch_id */
- rc = bnxt_pcie_dsn_get(bp, bp->switch_id);
- if (rc)
- goto err;
-
/* publish cfa_code_map only after all VF-reps have been initialized */
bp->cfa_code_map = cfa_code_map;
bp->eswitch_mode = DEVLINK_ESWITCH_MODE_SWITCHDEV;
if (ring->free_bds <= (MAX_SKB_FRAGS + 1))
netif_tx_stop_queue(txq);
- if (!skb->xmit_more || netif_xmit_stopped(txq))
+ if (!netdev_xmit_more() || netif_xmit_stopped(txq))
/* Packets are ready, update producer index */
bcmgenet_tdma_ring_writel(priv, ring->index,
ring->prod_index, TDMA_PROD_INDEX);
pci_set_power_state(tp->pdev, PCI_D3hot);
}
-static void tg3_aux_stat_to_speed_duplex(struct tg3 *tp, u32 val, u16 *speed, u8 *duplex)
+static void tg3_aux_stat_to_speed_duplex(struct tg3 *tp, u32 val, u32 *speed, u8 *duplex)
{
switch (val & MII_TG3_AUX_STAT_SPDMASK) {
case MII_TG3_AUX_STAT_10HALF:
bool current_link_up;
u32 bmsr, val;
u32 lcl_adv, rmt_adv;
- u16 current_speed;
+ u32 current_speed;
u8 current_duplex;
int i, err;
static int tg3_setup_fiber_phy(struct tg3 *tp, bool force_reset)
{
u32 orig_pause_cfg;
- u16 orig_active_speed;
+ u32 orig_active_speed;
u8 orig_active_duplex;
u32 mac_status;
bool current_link_up;
{
int err = 0;
u32 bmsr, bmcr;
- u16 current_speed = SPEED_UNKNOWN;
+ u32 current_speed = SPEED_UNKNOWN;
u8 current_duplex = DUPLEX_UNKNOWN;
bool current_link_up = false;
u32 local_adv, remote_adv, sgsr;
netif_tx_wake_queue(txq);
}
- if (!skb->xmit_more || netif_xmit_stopped(txq)) {
+ if (!netdev_xmit_more() || netif_xmit_stopped(txq)) {
/* Packets are ready, update Tx producer idx on card. */
tw32_tx_mbox(tnapi->prodmbox, entry);
mmiowb();
{
struct tg3 *tp = netdev_priv(dev);
- if (!netif_running(tp->dev))
- return -EAGAIN;
-
switch (state) {
case ETHTOOL_ID_ACTIVE:
return 1; /* cycle on/off once per second */
struct tg3_link_config {
/* Describes what we're trying to get. */
u32 advertising;
- u16 speed;
+ u32 speed;
u8 duplex;
u8 autoneg;
u8 flowctrl;
u8 active_flowctrl;
u8 active_duplex;
- u16 active_speed;
+ u32 active_speed;
u32 rmt_adv;
};
/* First, update TX stats if needed */
if (skb) {
- if (gem_ptp_do_txstamp(queue, skb, desc) == 0) {
+ if (unlikely(skb_shinfo(skb)->tx_flags &
+ SKBTX_HW_TSTAMP) &&
+ gem_ptp_do_txstamp(queue, skb, desc) == 0) {
/* skb now belongs to timestamp buffer
* and will be removed later
*/
irh->vlan = skb_vlan_tag_get(skb) & 0xfff;
}
- xmit_more = skb->xmit_more;
+ xmit_more = netdev_xmit_more();
if (unlikely(cmdsetup.s.timestamp))
status = send_nic_timestamp_pkt(oct, &ndata, finfo, xmit_more);
irh->vlan = skb_vlan_tag_get(skb) & VLAN_VID_MASK;
}
- xmit_more = skb->xmit_more;
+ xmit_more = netdev_xmit_more();
if (unlikely(cmdsetup.s.timestamp))
status = send_nic_timestamp_pkt(oct, &ndata, finfo, xmit_more);
#define DRV_NAME "nicvf"
#define DRV_VERSION "1.0"
+/* NOTE: Packets bigger than 1530 are split across multiple pages and XDP needs
+ * the buffer to be contiguous. Allow XDP to be set up only if we don't exceed
+ * this value, keeping headroom for the 14 byte Ethernet header and two
+ * VLAN tags (for QinQ)
+ */
+#define MAX_XDP_MTU (1530 - ETH_HLEN - VLAN_HLEN * 2)
+
/* Supported devices */
static const struct pci_device_id nicvf_id_table[] = {
{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM,
struct nicvf_cq_poll *cq_poll = NULL;
union nic_mbx mbx = {};
- cancel_delayed_work_sync(&nic->link_change_work);
-
/* wait till all queued set_rx_mode tasks completes */
- drain_workqueue(nic->nicvf_rx_mode_wq);
+ if (nic->nicvf_rx_mode_wq) {
+ cancel_delayed_work_sync(&nic->link_change_work);
+ drain_workqueue(nic->nicvf_rx_mode_wq);
+ }
mbx.msg.msg = NIC_MBOX_MSG_SHUTDOWN;
nicvf_send_msg_to_pf(nic, &mbx);
struct nicvf_cq_poll *cq_poll = NULL;
/* wait till all queued set_rx_mode tasks completes if any */
- drain_workqueue(nic->nicvf_rx_mode_wq);
+ if (nic->nicvf_rx_mode_wq)
+ drain_workqueue(nic->nicvf_rx_mode_wq);
netif_carrier_off(netdev);
/* Send VF config done msg to PF */
nicvf_send_cfg_done(nic);
- INIT_DELAYED_WORK(&nic->link_change_work,
- nicvf_link_status_check_task);
- queue_delayed_work(nic->nicvf_rx_mode_wq,
- &nic->link_change_work, 0);
+ if (nic->nicvf_rx_mode_wq) {
+ INIT_DELAYED_WORK(&nic->link_change_work,
+ nicvf_link_status_check_task);
+ queue_delayed_work(nic->nicvf_rx_mode_wq,
+ &nic->link_change_work, 0);
+ }
return 0;
cleanup:
struct nicvf *nic = netdev_priv(netdev);
int orig_mtu = netdev->mtu;
+ /* For now just support only the usual MTU sized frames,
+ * plus some headroom for VLAN, QinQ.
+ */
+ if (nic->xdp_prog && new_mtu > MAX_XDP_MTU) {
+ netdev_warn(netdev, "Jumbo frames not yet supported with XDP, current MTU %d.\n",
+ netdev->mtu);
+ return -EINVAL;
+ }
+
netdev->mtu = new_mtu;
if (!netif_running(netdev))
bool bpf_attached = false;
int ret = 0;
- /* For now just support only the usual MTU sized frames */
- if (prog && (dev->mtu > 1500)) {
+ /* For now just support only the usual MTU sized frames,
+ * plus some headroom for VLAN, QinQ.
+ */
+ if (prog && dev->mtu > MAX_XDP_MTU) {
netdev_warn(dev, "Jumbo frames not yet supported with XDP, current MTU %d.\n",
dev->mtu);
return -EOPNOTSUPP;
/* Check if page can be recycled */
if (page) {
ref_count = page_ref_count(page);
- /* Check if this page has been used once i.e 'put_page'
- * called after packet transmission i.e internal ref_count
- * and page's ref_count are equal i.e page can be recycled.
+ /* This page can be recycled if internal ref_count and page's
+ * ref_count are equal, indicating that the page has been used
+ * once for packet transmission. For non-XDP mode, internal
+ * ref_count is always '1'.
*/
- if (rbdr->is_xdp && (ref_count == pgcache->ref_count))
- pgcache->ref_count--;
- else
- page = NULL;
-
- /* In non-XDP mode, page's ref_count needs to be '1' for it
- * to be recycled.
- */
- if (!rbdr->is_xdp && (ref_count != 1))
+ if (rbdr->is_xdp) {
+ if (ref_count == pgcache->ref_count)
+ pgcache->ref_count--;
+ else
+ page = NULL;
+ } else if (ref_count != 1) {
page = NULL;
+ }
}
if (!page) {
while (head < rbdr->pgcnt) {
pgcache = &rbdr->pgcache[head];
if (pgcache->page && page_ref_count(pgcache->page) != 0) {
- if (!rbdr->is_xdp) {
- put_page(pgcache->page);
- continue;
+ if (rbdr->is_xdp) {
+ page_ref_sub(pgcache->page,
+ pgcache->ref_count - 1);
}
- page_ref_sub(pgcache->page, pgcache->ref_count - 1);
put_page(pgcache->page);
}
head++;
lmac->last_duplex = (an_result >> 1) & 0x1;
switch (speed) {
case 0:
- lmac->last_speed = 10;
+ lmac->last_speed = SPEED_10;
break;
case 1:
- lmac->last_speed = 100;
+ lmac->last_speed = SPEED_100;
break;
case 2:
- lmac->last_speed = 1000;
+ lmac->last_speed = SPEED_1000;
break;
default:
lmac->link_up = false;
!(smu_link & SMU_RX_CTL_STATUS)) {
lmac->link_up = 1;
if (lmac->lmac_type == BGX_MODE_XLAUI)
- lmac->last_speed = 40000;
+ lmac->last_speed = SPEED_40000;
else
- lmac->last_speed = 10000;
- lmac->last_duplex = 1;
+ lmac->last_speed = SPEED_10000;
+ lmac->last_duplex = DUPLEX_FULL;
} else {
lmac->link_up = 0;
lmac->last_speed = SPEED_UNKNOWN;
} else {
/* Default to below link speed and duplex */
lmac->link_up = true;
- lmac->last_speed = 1000;
- lmac->last_duplex = 1;
+ lmac->last_speed = SPEED_1000;
+ lmac->last_duplex = DUPLEX_FULL;
bgx_sgmii_change_link_state(lmac);
return 0;
}
struct l2t_data *t3_init_l2t(unsigned int l2t_capacity)
{
struct l2t_data *d;
- int i, size = sizeof(*d) + l2t_capacity * sizeof(struct l2t_entry);
+ int i;
- d = kvzalloc(size, GFP_KERNEL);
+ d = kvzalloc(struct_size(d, l2tab, l2t_capacity), GFP_KERNEL);
if (!d)
return NULL;
struct l2t_entry *rover; /* starting point for next allocation */
atomic_t nfree; /* number of free entries */
rwlock_t lock;
- struct l2t_entry l2tab[0];
struct rcu_head rcu_head; /* to handle rcu cleanup */
+ struct l2t_entry l2tab[];
};
typedef void (*arp_failure_handler_func)(struct t3cdev * dev,
break;
default:
- dev_err(adap->pdev_dev, "%s: filter creation PROBLEM; status = %u\n",
- __func__, status);
+ if (status != CPL_ERR_TCAM_FULL)
+ dev_err(adap->pdev_dev, "%s: filter creation PROBLEM; status = %u\n",
+ __func__, status);
if (ctx) {
if (status == CPL_ERR_TCAM_FULL)
- ctx->result = -EAGAIN;
+ ctx->result = -ENOSPC;
else
ctx->result = -EINVAL;
}
ret = ctx.result;
/* Check if hw returned error for filter creation */
- if (ret) {
- netdev_err(dev, "%s: filter creation err %d\n",
- __func__, ret);
+ if (ret)
goto free_entry;
- }
ch_flower->tc_flower_cookie = cls->cookie;
ch_flower->filter_id = ctx.tid;
ppmax = max;
/* pool size must be multiple of unsigned long */
- bmap = BITS_TO_LONGS(ppmax);
+ bmap = ppmax / BITS_PER_TYPE(unsigned long);
+ if (!bmap)
+ return NULL;
+
ppmax = (bmap * sizeof(unsigned long)) << 3;
alloc_sz = sizeof(*pools) + sizeof(unsigned long) * bmap;
if (reserve_factor) {
ppmax_pool = ppmax / reserve_factor;
pool = ppm_alloc_cpu_pool(&ppmax_pool, &pool_index_max);
+ if (!pool) {
+ ppmax_pool = 0;
+ reserve_factor = 0;
+ }
pr_debug("%s: ppmax %u, cpu total %u, per cpu %u.\n",
ndev->name, ppmax, ppmax_pool, pool_index_max);
if (vnic_wq_desc_avail(wq) < MAX_SKB_FRAGS + ENIC_DESC_MAX_SPLITS)
netif_tx_stop_queue(txq);
skb_tx_timestamp(skb);
- if (!skb->xmit_more || netif_xmit_stopped(txq))
+ if (!netdev_xmit_more() || netif_xmit_stopped(txq))
vnic_wq_doorbell(wq);
spin_unlock(&enic->wq_lock[txq_map]);
u16 q_idx = skb_get_queue_mapping(skb);
struct be_tx_obj *txo = &adapter->tx_obj[q_idx];
struct be_wrb_params wrb_params = { 0 };
- bool flush = !skb->xmit_more;
+ bool flush = !netdev_xmit_more();
u16 wrb_cnt;
skb = be_xmit_workarounds(adapter, skb, &wrb_params);
.rxnfc_field = RXH_L2DA,
.cls_prot = NET_PROT_ETH,
.cls_field = NH_FLD_ETH_DA,
+ .id = DPAA2_ETH_DIST_ETHDST,
.size = 6,
}, {
.cls_prot = NET_PROT_ETH,
.cls_field = NH_FLD_ETH_SA,
+ .id = DPAA2_ETH_DIST_ETHSRC,
.size = 6,
}, {
/* This is the last ethertype field parsed:
*/
.cls_prot = NET_PROT_ETH,
.cls_field = NH_FLD_ETH_TYPE,
+ .id = DPAA2_ETH_DIST_ETHTYPE,
.size = 2,
}, {
/* VLAN header */
.rxnfc_field = RXH_VLAN,
.cls_prot = NET_PROT_VLAN,
.cls_field = NH_FLD_VLAN_TCI,
+ .id = DPAA2_ETH_DIST_VLAN,
.size = 2,
}, {
/* IP header */
.rxnfc_field = RXH_IP_SRC,
.cls_prot = NET_PROT_IP,
.cls_field = NH_FLD_IP_SRC,
+ .id = DPAA2_ETH_DIST_IPSRC,
.size = 4,
}, {
.rxnfc_field = RXH_IP_DST,
.cls_prot = NET_PROT_IP,
.cls_field = NH_FLD_IP_DST,
+ .id = DPAA2_ETH_DIST_IPDST,
.size = 4,
}, {
.rxnfc_field = RXH_L3_PROTO,
.cls_prot = NET_PROT_IP,
.cls_field = NH_FLD_IP_PROTO,
+ .id = DPAA2_ETH_DIST_IPPROTO,
.size = 1,
}, {
/* Using UDP ports, this is functionally equivalent to raw
.rxnfc_field = RXH_L4_B_0_1,
.cls_prot = NET_PROT_UDP,
.cls_field = NH_FLD_UDP_PORT_SRC,
+ .id = DPAA2_ETH_DIST_L4SRC,
.size = 2,
}, {
.rxnfc_field = RXH_L4_B_2_3,
.cls_prot = NET_PROT_UDP,
.cls_field = NH_FLD_UDP_PORT_DST,
+ .id = DPAA2_ETH_DIST_L4DST,
.size = 2,
},
};
}
/* Size of the Rx flow classification key */
-int dpaa2_eth_cls_key_size(void)
+int dpaa2_eth_cls_key_size(u64 fields)
{
int i, size = 0;
- for (i = 0; i < ARRAY_SIZE(dist_fields); i++)
+ for (i = 0; i < ARRAY_SIZE(dist_fields); i++) {
+ if (!(fields & dist_fields[i].id))
+ continue;
size += dist_fields[i].size;
+ }
return size;
}
return 0;
}
+/* Prune unused fields from the classification rule.
+ * Used when masking is not supported
+ */
+void dpaa2_eth_cls_trim_rule(void *key_mem, u64 fields)
+{
+ int off = 0, new_off = 0;
+ int i, size;
+
+ for (i = 0; i < ARRAY_SIZE(dist_fields); i++) {
+ size = dist_fields[i].size;
+ if (dist_fields[i].id & fields) {
+ memcpy(key_mem + new_off, key_mem + off, size);
+ new_off += size;
+ }
+ off += size;
+ }
+}
+
/* Set Rx distribution (hash or flow classification) key
* flags is a combination of RXH_ bits
*/
struct dpkg_extract *key =
&cls_cfg.extracts[cls_cfg.num_extracts];
- /* For Rx hashing key we set only the selected fields.
- * For Rx flow classification key we set all supported fields
+ /* For both Rx hashing and classification keys
+ * we set only the selected fields.
*/
- if (type == DPAA2_ETH_RX_DIST_HASH) {
- if (!(flags & dist_fields[i].rxnfc_field))
- continue;
+ if (!(flags & dist_fields[i].id))
+ continue;
+ if (type == DPAA2_ETH_RX_DIST_HASH)
rx_hash_fields |= dist_fields[i].rxnfc_field;
- }
if (cls_cfg.num_extracts >= DPKG_MAX_NUM_OF_EXTRACTS) {
dev_err(dev, "error adding key extraction rule, too many rules?\n");
int dpaa2_eth_set_hash(struct net_device *net_dev, u64 flags)
{
struct dpaa2_eth_priv *priv = netdev_priv(net_dev);
+ u64 key = 0;
+ int i;
if (!dpaa2_eth_hash_enabled(priv))
return -EOPNOTSUPP;
- return dpaa2_eth_set_dist_key(net_dev, DPAA2_ETH_RX_DIST_HASH, flags);
+ for (i = 0; i < ARRAY_SIZE(dist_fields); i++)
+ if (dist_fields[i].rxnfc_field & flags)
+ key |= dist_fields[i].id;
+
+ return dpaa2_eth_set_dist_key(net_dev, DPAA2_ETH_RX_DIST_HASH, key);
}
-static int dpaa2_eth_set_cls(struct dpaa2_eth_priv *priv)
+int dpaa2_eth_set_cls(struct net_device *net_dev, u64 flags)
+{
+ return dpaa2_eth_set_dist_key(net_dev, DPAA2_ETH_RX_DIST_CLS, flags);
+}
+
+static int dpaa2_eth_set_default_cls(struct dpaa2_eth_priv *priv)
{
struct device *dev = priv->net_dev->dev.parent;
+ int err;
/* Check if we actually support Rx flow classification */
if (dpaa2_eth_has_legacy_dist(priv)) {
return -EOPNOTSUPP;
}
- if (priv->dpni_attrs.options & DPNI_OPT_NO_FS ||
- !(priv->dpni_attrs.options & DPNI_OPT_HAS_KEY_MASKING)) {
+ if (!dpaa2_eth_fs_enabled(priv)) {
dev_dbg(dev, "Rx cls disabled in DPNI options\n");
return -EOPNOTSUPP;
}
return -EOPNOTSUPP;
}
+ /* If there is no support for masking in the classification table,
+ * we don't set a default key, as it will depend on the rules
+ * added by the user at runtime.
+ */
+ if (!dpaa2_eth_fs_mask_enabled(priv))
+ goto out;
+
+ err = dpaa2_eth_set_cls(priv->net_dev, DPAA2_ETH_DIST_ALL);
+ if (err)
+ return err;
+
+out:
priv->rx_cls_enabled = 1;
- return dpaa2_eth_set_dist_key(priv->net_dev, DPAA2_ETH_RX_DIST_CLS, 0);
+ return 0;
}
/* Bind the DPNI to its needed objects and resources: buffer pool, DPIOs,
/* Configure the flow classification key; it includes all
* supported header fields and cannot be modified at runtime
*/
- err = dpaa2_eth_set_cls(priv);
+ err = dpaa2_eth_set_default_cls(priv);
if (err && err != -EOPNOTSUPP)
dev_err(dev, "Failed to configure Rx classification key\n");
enum net_prot cls_prot;
int cls_field;
int size;
+ u64 id;
};
struct dpaa2_eth_cls_rule {
/* enabled ethtool hashing bits */
u64 rx_hash_fields;
+ u64 rx_cls_fields;
struct dpaa2_eth_cls_rule *cls_rules;
u8 rx_cls_enabled;
struct bpf_prog *xdp_prog;
(dpaa2_eth_cmp_dpni_ver((priv), DPNI_RX_DIST_KEY_VER_MAJOR, \
DPNI_RX_DIST_KEY_VER_MINOR) < 0)
+#define dpaa2_eth_fs_enabled(priv) \
+ (!((priv)->dpni_attrs.options & DPNI_OPT_NO_FS))
+
+#define dpaa2_eth_fs_mask_enabled(priv) \
+ ((priv)->dpni_attrs.options & DPNI_OPT_HAS_KEY_MASKING)
+
#define dpaa2_eth_fs_count(priv) \
((priv)->dpni_attrs.fs_entries)
DPAA2_ETH_RX_DIST_CLS
};
+/* Unique IDs for the supported Rx classification header fields */
+#define DPAA2_ETH_DIST_ETHDST BIT(0)
+#define DPAA2_ETH_DIST_ETHSRC BIT(1)
+#define DPAA2_ETH_DIST_ETHTYPE BIT(2)
+#define DPAA2_ETH_DIST_VLAN BIT(3)
+#define DPAA2_ETH_DIST_IPSRC BIT(4)
+#define DPAA2_ETH_DIST_IPDST BIT(5)
+#define DPAA2_ETH_DIST_IPPROTO BIT(6)
+#define DPAA2_ETH_DIST_L4SRC BIT(7)
+#define DPAA2_ETH_DIST_L4DST BIT(8)
+#define DPAA2_ETH_DIST_ALL (~0U)
+
static inline
unsigned int dpaa2_eth_needed_headroom(struct dpaa2_eth_priv *priv,
struct sk_buff *skb)
}
int dpaa2_eth_set_hash(struct net_device *net_dev, u64 flags);
-int dpaa2_eth_cls_key_size(void);
+int dpaa2_eth_set_cls(struct net_device *net_dev, u64 key);
+int dpaa2_eth_cls_key_size(u64 key);
int dpaa2_eth_cls_fld_off(int prot, int field);
+void dpaa2_eth_cls_trim_rule(void *key_mem, u64 fields);
#endif /* __DPAA2_H */
}
static int prep_eth_rule(struct ethhdr *eth_value, struct ethhdr *eth_mask,
- void *key, void *mask)
+ void *key, void *mask, u64 *fields)
{
int off;
off = dpaa2_eth_cls_fld_off(NET_PROT_ETH, NH_FLD_ETH_TYPE);
*(__be16 *)(key + off) = eth_value->h_proto;
*(__be16 *)(mask + off) = eth_mask->h_proto;
+ *fields |= DPAA2_ETH_DIST_ETHTYPE;
}
if (!is_zero_ether_addr(eth_mask->h_source)) {
off = dpaa2_eth_cls_fld_off(NET_PROT_ETH, NH_FLD_ETH_SA);
ether_addr_copy(key + off, eth_value->h_source);
ether_addr_copy(mask + off, eth_mask->h_source);
+ *fields |= DPAA2_ETH_DIST_ETHSRC;
}
if (!is_zero_ether_addr(eth_mask->h_dest)) {
off = dpaa2_eth_cls_fld_off(NET_PROT_ETH, NH_FLD_ETH_DA);
ether_addr_copy(key + off, eth_value->h_dest);
ether_addr_copy(mask + off, eth_mask->h_dest);
+ *fields |= DPAA2_ETH_DIST_ETHDST;
}
return 0;
static int prep_uip_rule(struct ethtool_usrip4_spec *uip_value,
struct ethtool_usrip4_spec *uip_mask,
- void *key, void *mask)
+ void *key, void *mask, u64 *fields)
{
int off;
u32 tmp_value, tmp_mask;
off = dpaa2_eth_cls_fld_off(NET_PROT_IP, NH_FLD_IP_SRC);
*(__be32 *)(key + off) = uip_value->ip4src;
*(__be32 *)(mask + off) = uip_mask->ip4src;
+ *fields |= DPAA2_ETH_DIST_IPSRC;
}
if (uip_mask->ip4dst) {
off = dpaa2_eth_cls_fld_off(NET_PROT_IP, NH_FLD_IP_DST);
*(__be32 *)(key + off) = uip_value->ip4dst;
*(__be32 *)(mask + off) = uip_mask->ip4dst;
+ *fields |= DPAA2_ETH_DIST_IPDST;
}
if (uip_mask->proto) {
off = dpaa2_eth_cls_fld_off(NET_PROT_IP, NH_FLD_IP_PROTO);
*(u8 *)(key + off) = uip_value->proto;
*(u8 *)(mask + off) = uip_mask->proto;
+ *fields |= DPAA2_ETH_DIST_IPPROTO;
}
if (uip_mask->l4_4_bytes) {
off = dpaa2_eth_cls_fld_off(NET_PROT_UDP, NH_FLD_UDP_PORT_SRC);
*(__be16 *)(key + off) = htons(tmp_value >> 16);
*(__be16 *)(mask + off) = htons(tmp_mask >> 16);
+ *fields |= DPAA2_ETH_DIST_L4SRC;
off = dpaa2_eth_cls_fld_off(NET_PROT_UDP, NH_FLD_UDP_PORT_DST);
*(__be16 *)(key + off) = htons(tmp_value & 0xFFFF);
*(__be16 *)(mask + off) = htons(tmp_mask & 0xFFFF);
+ *fields |= DPAA2_ETH_DIST_L4DST;
}
/* Only apply the rule for IPv4 frames */
off = dpaa2_eth_cls_fld_off(NET_PROT_ETH, NH_FLD_ETH_TYPE);
*(__be16 *)(key + off) = htons(ETH_P_IP);
*(__be16 *)(mask + off) = htons(0xFFFF);
+ *fields |= DPAA2_ETH_DIST_ETHTYPE;
return 0;
}
static int prep_l4_rule(struct ethtool_tcpip4_spec *l4_value,
struct ethtool_tcpip4_spec *l4_mask,
- void *key, void *mask, u8 l4_proto)
+ void *key, void *mask, u8 l4_proto, u64 *fields)
{
int off;
off = dpaa2_eth_cls_fld_off(NET_PROT_IP, NH_FLD_IP_SRC);
*(__be32 *)(key + off) = l4_value->ip4src;
*(__be32 *)(mask + off) = l4_mask->ip4src;
+ *fields |= DPAA2_ETH_DIST_IPSRC;
}
if (l4_mask->ip4dst) {
off = dpaa2_eth_cls_fld_off(NET_PROT_IP, NH_FLD_IP_DST);
*(__be32 *)(key + off) = l4_value->ip4dst;
*(__be32 *)(mask + off) = l4_mask->ip4dst;
+ *fields |= DPAA2_ETH_DIST_IPDST;
}
if (l4_mask->psrc) {
off = dpaa2_eth_cls_fld_off(NET_PROT_UDP, NH_FLD_UDP_PORT_SRC);
*(__be16 *)(key + off) = l4_value->psrc;
*(__be16 *)(mask + off) = l4_mask->psrc;
+ *fields |= DPAA2_ETH_DIST_L4SRC;
}
if (l4_mask->pdst) {
off = dpaa2_eth_cls_fld_off(NET_PROT_UDP, NH_FLD_UDP_PORT_DST);
*(__be16 *)(key + off) = l4_value->pdst;
*(__be16 *)(mask + off) = l4_mask->pdst;
+ *fields |= DPAA2_ETH_DIST_L4DST;
}
/* Only apply the rule for IPv4 frames with the specified L4 proto */
off = dpaa2_eth_cls_fld_off(NET_PROT_ETH, NH_FLD_ETH_TYPE);
*(__be16 *)(key + off) = htons(ETH_P_IP);
*(__be16 *)(mask + off) = htons(0xFFFF);
+ *fields |= DPAA2_ETH_DIST_ETHTYPE;
off = dpaa2_eth_cls_fld_off(NET_PROT_IP, NH_FLD_IP_PROTO);
*(u8 *)(key + off) = l4_proto;
*(u8 *)(mask + off) = 0xFF;
+ *fields |= DPAA2_ETH_DIST_IPPROTO;
return 0;
}
static int prep_ext_rule(struct ethtool_flow_ext *ext_value,
struct ethtool_flow_ext *ext_mask,
- void *key, void *mask)
+ void *key, void *mask, u64 *fields)
{
int off;
off = dpaa2_eth_cls_fld_off(NET_PROT_VLAN, NH_FLD_VLAN_TCI);
*(__be16 *)(key + off) = ext_value->vlan_tci;
*(__be16 *)(mask + off) = ext_mask->vlan_tci;
+ *fields |= DPAA2_ETH_DIST_VLAN;
}
return 0;
static int prep_mac_ext_rule(struct ethtool_flow_ext *ext_value,
struct ethtool_flow_ext *ext_mask,
- void *key, void *mask)
+ void *key, void *mask, u64 *fields)
{
int off;
off = dpaa2_eth_cls_fld_off(NET_PROT_ETH, NH_FLD_ETH_DA);
ether_addr_copy(key + off, ext_value->h_dest);
ether_addr_copy(mask + off, ext_mask->h_dest);
+ *fields |= DPAA2_ETH_DIST_ETHDST;
}
return 0;
}
-static int prep_cls_rule(struct ethtool_rx_flow_spec *fs, void *key, void *mask)
+static int prep_cls_rule(struct ethtool_rx_flow_spec *fs, void *key, void *mask,
+ u64 *fields)
{
int err;
switch (fs->flow_type & 0xFF) {
case ETHER_FLOW:
err = prep_eth_rule(&fs->h_u.ether_spec, &fs->m_u.ether_spec,
- key, mask);
+ key, mask, fields);
break;
case IP_USER_FLOW:
err = prep_uip_rule(&fs->h_u.usr_ip4_spec,
- &fs->m_u.usr_ip4_spec, key, mask);
+ &fs->m_u.usr_ip4_spec, key, mask, fields);
break;
case TCP_V4_FLOW:
err = prep_l4_rule(&fs->h_u.tcp_ip4_spec, &fs->m_u.tcp_ip4_spec,
- key, mask, IPPROTO_TCP);
+ key, mask, IPPROTO_TCP, fields);
break;
case UDP_V4_FLOW:
err = prep_l4_rule(&fs->h_u.udp_ip4_spec, &fs->m_u.udp_ip4_spec,
- key, mask, IPPROTO_UDP);
+ key, mask, IPPROTO_UDP, fields);
break;
case SCTP_V4_FLOW:
err = prep_l4_rule(&fs->h_u.sctp_ip4_spec,
&fs->m_u.sctp_ip4_spec, key, mask,
- IPPROTO_SCTP);
+ IPPROTO_SCTP, fields);
break;
default:
return -EOPNOTSUPP;
return err;
if (fs->flow_type & FLOW_EXT) {
- err = prep_ext_rule(&fs->h_ext, &fs->m_ext, key, mask);
+ err = prep_ext_rule(&fs->h_ext, &fs->m_ext, key, mask, fields);
if (err)
return err;
}
if (fs->flow_type & FLOW_MAC_EXT) {
- err = prep_mac_ext_rule(&fs->h_ext, &fs->m_ext, key, mask);
+ err = prep_mac_ext_rule(&fs->h_ext, &fs->m_ext, key, mask,
+ fields);
if (err)
return err;
}
struct dpni_rule_cfg rule_cfg = { 0 };
struct dpni_fs_action_cfg fs_act = { 0 };
dma_addr_t key_iova;
+ u64 fields = 0;
void *key_buf;
int err;
fs->ring_cookie >= dpaa2_eth_queue_count(priv))
return -EINVAL;
- rule_cfg.key_size = dpaa2_eth_cls_key_size();
+ rule_cfg.key_size = dpaa2_eth_cls_key_size(DPAA2_ETH_DIST_ALL);
/* allocate twice the key size, for the actual key and for mask */
key_buf = kzalloc(rule_cfg.key_size * 2, GFP_KERNEL);
return -ENOMEM;
/* Fill the key and mask memory areas */
- err = prep_cls_rule(fs, key_buf, key_buf + rule_cfg.key_size);
+ err = prep_cls_rule(fs, key_buf, key_buf + rule_cfg.key_size, &fields);
if (err)
goto free_mem;
+ if (!dpaa2_eth_fs_mask_enabled(priv)) {
+ /* Masking allows us to configure a maximal key during init and
+ * use it for all flow steering rules. Without it, we include
+ * in the key only the fields actually used, so we need to
+ * extract the others from the final key buffer.
+ *
+ * Program the FS key if needed, or return error if previously
+ * set key can't be used for the current rule. User needs to
+ * delete existing rules in this case to allow for the new one.
+ */
+ if (!priv->rx_cls_fields) {
+ err = dpaa2_eth_set_cls(net_dev, fields);
+ if (err)
+ goto free_mem;
+
+ priv->rx_cls_fields = fields;
+ } else if (priv->rx_cls_fields != fields) {
+ netdev_err(net_dev, "No support for multiple FS keys, need to delete existing rules\n");
+ err = -EOPNOTSUPP;
+ goto free_mem;
+ }
+
+ dpaa2_eth_cls_trim_rule(key_buf, fields);
+ rule_cfg.key_size = dpaa2_eth_cls_key_size(fields);
+ }
+
key_iova = dma_map_single(dev, key_buf, rule_cfg.key_size * 2,
DMA_TO_DEVICE);
if (dma_mapping_error(dev, key_iova)) {
}
rule_cfg.key_iova = key_iova;
- rule_cfg.mask_iova = key_iova + rule_cfg.key_size;
+ if (dpaa2_eth_fs_mask_enabled(priv))
+ rule_cfg.mask_iova = key_iova + rule_cfg.key_size;
if (add) {
if (fs->ring_cookie == RX_CLS_FLOW_DISC)
return err;
}
+static int num_rules(struct dpaa2_eth_priv *priv)
+{
+ int i, rules = 0;
+
+ for (i = 0; i < dpaa2_eth_fs_count(priv); i++)
+ if (priv->cls_rules[i].in_use)
+ rules++;
+
+ return rules;
+}
+
static int update_cls_rule(struct net_device *net_dev,
struct ethtool_rx_flow_spec *new_fs,
int location)
return err;
rule->in_use = 0;
+
+ if (!dpaa2_eth_fs_mask_enabled(priv) && !num_rules(priv))
+ priv->rx_cls_fields = 0;
}
/* If no new entry to add, return here */
break;
case ETHTOOL_GRXCLSRLCNT:
rxnfc->rule_cnt = 0;
- for (i = 0; i < max_rules; i++)
- if (priv->cls_rules[i].in_use)
- rxnfc->rule_cnt++;
+ rxnfc->rule_cnt = num_rules(priv);
rxnfc->data = max_rules;
break;
case ETHTOOL_GRXCLSRULE:
int ret;
if (enable) {
- ret = clk_prepare_enable(fep->clk_ahb);
- if (ret)
- return ret;
-
ret = clk_prepare_enable(fep->clk_enet_out);
if (ret)
- goto failed_clk_enet_out;
+ return ret;
if (fep->clk_ptp) {
mutex_lock(&fep->ptp_clk_mutex);
phy_reset_after_clk_enable(ndev->phydev);
} else {
- clk_disable_unprepare(fep->clk_ahb);
clk_disable_unprepare(fep->clk_enet_out);
if (fep->clk_ptp) {
mutex_lock(&fep->ptp_clk_mutex);
failed_clk_ptp:
if (fep->clk_enet_out)
clk_disable_unprepare(fep->clk_enet_out);
-failed_clk_enet_out:
- clk_disable_unprepare(fep->clk_ahb);
return ret;
}
ret = clk_prepare_enable(fep->clk_ipg);
if (ret)
goto failed_clk_ipg;
+ ret = clk_prepare_enable(fep->clk_ahb);
+ if (ret)
+ goto failed_clk_ahb;
fep->reg_phy = devm_regulator_get_optional(&pdev->dev, "phy");
if (!IS_ERR(fep->reg_phy)) {
pm_runtime_put(&pdev->dev);
pm_runtime_disable(&pdev->dev);
failed_regulator:
+ clk_disable_unprepare(fep->clk_ahb);
+failed_clk_ahb:
+ clk_disable_unprepare(fep->clk_ipg);
failed_clk_ipg:
fec_enet_clk_enable(ndev, false);
failed_clk:
struct net_device *ndev = dev_get_drvdata(dev);
struct fec_enet_private *fep = netdev_priv(ndev);
+ clk_disable_unprepare(fep->clk_ahb);
clk_disable_unprepare(fep->clk_ipg);
return 0;
{
struct net_device *ndev = dev_get_drvdata(dev);
struct fec_enet_private *fep = netdev_priv(ndev);
+ int ret;
- return clk_prepare_enable(fep->clk_ipg);
+ ret = clk_prepare_enable(fep->clk_ahb);
+ if (ret)
+ return ret;
+ ret = clk_prepare_enable(fep->clk_ipg);
+ if (ret)
+ goto failed_clk_ipg;
+
+ return 0;
+
+failed_clk_ipg:
+ clk_disable_unprepare(fep->clk_ahb);
+ return ret;
}
static const struct dev_pm_ops fec_pm_ops = {
/* free desc along with its attached buffer */
static void hnae_free_desc(struct hnae_ring *ring)
{
- hnae_free_buffers(ring);
dma_unmap_single(ring_to_dev(ring), ring->desc_dma_addr,
ring->desc_num * sizeof(ring->desc[0]),
ring_to_dma_dir(ring));
/* fini ring, also free the buffer for the ring */
static void hnae_fini_ring(struct hnae_ring *ring)
{
+ if (is_rx_ring(ring))
+ hnae_free_buffers(ring);
+
hnae_free_desc(ring);
kfree(ring->desc_cb);
ring->desc_cb = NULL;
};
struct hnae_queue {
- void __iomem *io_base;
+ u8 __iomem *io_base;
phys_addr_t phy_base;
struct hnae_ae_dev *dev; /* the device who use this queue */
struct hnae_ring rx_ring ____cacheline_internodealigned_in_smp;
static void hns_mac_param_get(struct mac_params *param,
struct hns_mac_cb *mac_cb)
{
- param->vaddr = (void *)mac_cb->vaddr;
+ param->vaddr = mac_cb->vaddr;
param->mac_mode = hns_get_enet_interface(mac_cb);
ether_addr_copy(param->addr, mac_cb->addr_entry_idx[0].addr);
param->mac_id = mac_cb->mac_id;
/*mac para struct ,mac get param from nic or dsaf when initialize*/
struct mac_params {
char addr[ETH_ALEN];
- void *vaddr; /*virtual address*/
+ u8 __iomem *vaddr; /*virtual address*/
struct device *dev;
u8 mac_id;
/**< Ethernet operation mode (MAC-PHY interface and speed) */
enum mac_mode mac_mode;
u8 mac_id;
struct hns_mac_cb *mac_cb;
- void __iomem *io_base;
+ u8 __iomem *io_base;
unsigned int mac_en_flg;/*you'd better don't enable mac twice*/
unsigned int virt_dev_num;
struct device *dev;
DSAF_TBL_TCAM_KEY_VLAN_S, vlan_id);
dsaf_set_field(mac_key->low.bits.port_vlan, DSAF_TBL_TCAM_KEY_PORT_M,
DSAF_TBL_TCAM_KEY_PORT_S, port);
-
- mac_key->low.bits.port_vlan = le16_to_cpu(mac_key->low.bits.port_vlan);
}
/**
/* default config dvc to 0 */
mac_data.tbl_ucast_dvc = 0;
mac_data.tbl_ucast_out_port = mac_entry->port_num;
- tcam_data.tbl_tcam_data_high = cpu_to_le32(mac_key.high.val);
- tcam_data.tbl_tcam_data_low = cpu_to_le32(mac_key.low.val);
+ tcam_data.tbl_tcam_data_high = mac_key.high.val;
+ tcam_data.tbl_tcam_data_low = mac_key.low.val;
hns_dsaf_tcam_uc_cfg(dsaf_dev, entry_index, &tcam_data, &mac_data);
0xff,
mc_mask);
- mask_key.high.val = le32_to_cpu(mask_key.high.val);
- mask_key.low.val = le32_to_cpu(mask_key.low.val);
-
pmask_key = (struct dsaf_tbl_tcam_data *)(&mask_key);
}
dsaf_dev->ae_dev.name, mac_key.high.val,
mac_key.low.val, entry_index);
- tcam_data.tbl_tcam_data_high = cpu_to_le32(mac_key.high.val);
- tcam_data.tbl_tcam_data_low = cpu_to_le32(mac_key.low.val);
+ tcam_data.tbl_tcam_data_high = mac_key.high.val;
+ tcam_data.tbl_tcam_data_low = mac_key.low.val;
/* config mc entry with mask */
hns_dsaf_tcam_mc_cfg(dsaf_dev, entry_index, &tcam_data,
/* config key mask */
hns_dsaf_set_mac_key(dsaf_dev, &mask_key, 0x00, 0xff, mc_mask);
- mask_key.high.val = le32_to_cpu(mask_key.high.val);
- mask_key.low.val = le32_to_cpu(mask_key.low.val);
-
pmask_key = (struct dsaf_tbl_tcam_data *)(&mask_key);
}
soft_mac_entry += entry_index;
soft_mac_entry->index = DSAF_INVALID_ENTRY_IDX;
} else { /* not zero, just del port, update */
- tcam_data.tbl_tcam_data_high = cpu_to_le32(mac_key.high.val);
- tcam_data.tbl_tcam_data_low = cpu_to_le32(mac_key.low.val);
+ tcam_data.tbl_tcam_data_high = mac_key.high.val;
+ tcam_data.tbl_tcam_data_low = mac_key.low.val;
hns_dsaf_tcam_mc_cfg(dsaf_dev, entry_index,
&tcam_data,
return DSAF_DUMP_REGS_NUM;
}
+static int hns_dsaf_get_port_id(u8 port)
+{
+ if (port < DSAF_SERVICE_NW_NUM)
+ return port;
+
+ if (port >= DSAF_BASE_INNER_PORT_NUM)
+ return port - DSAF_BASE_INNER_PORT_NUM + DSAF_SERVICE_NW_NUM;
+
+ return -EINVAL;
+}
+
static void set_promisc_tcam_enable(struct dsaf_device *dsaf_dev, u32 port)
{
struct dsaf_tbl_tcam_ucast_cfg tbl_tcam_ucast = {0, 1, 0, 0, 0x80};
struct hns_mac_cb *mac_cb;
u8 addr[ETH_ALEN] = {0};
u8 port_num;
- u16 mskid;
+ int mskid;
/* promisc use vague table match with vlanid = 0 & macaddr = 0 */
hns_dsaf_set_mac_key(dsaf_dev, &mac_key, 0x00, port, addr);
memset(&temp_key, 0x0, sizeof(temp_key));
mask_entry.addr[0] = 0x01;
hns_dsaf_set_mac_key(dsaf_dev, &mask_key, mask_entry.in_vlan_id,
- port, mask_entry.addr);
+ 0xf, mask_entry.addr);
tbl_tcam_mcast.tbl_mcast_item_vld = 1;
tbl_tcam_mcast.tbl_mcast_old_en = 0;
- if (port < DSAF_SERVICE_NW_NUM) {
- mskid = port;
- } else if (port >= DSAF_BASE_INNER_PORT_NUM) {
- mskid = port - DSAF_BASE_INNER_PORT_NUM + DSAF_SERVICE_NW_NUM;
- } else {
+ /* set MAC port to handle multicast */
+ mskid = hns_dsaf_get_port_id(port);
+ if (mskid == -EINVAL) {
dev_err(dsaf_dev->dev, "%s,pnum(%d)error,key(%#x:%#x)\n",
dsaf_dev->ae_dev.name, port,
mask_key.high.val, mask_key.low.val);
return;
}
+ dsaf_set_bit(tbl_tcam_mcast.tbl_mcast_port_msk[mskid / 32],
+ mskid % 32, 1);
+ /* set pool bit map to handle multicast */
+ mskid = hns_dsaf_get_port_id(port_num);
+ if (mskid == -EINVAL) {
+ dev_err(dsaf_dev->dev,
+ "%s, pool bit map pnum(%d)error,key(%#x:%#x)\n",
+ dsaf_dev->ae_dev.name, port_num,
+ mask_key.high.val, mask_key.low.val);
+ return;
+ }
dsaf_set_bit(tbl_tcam_mcast.tbl_mcast_port_msk[mskid / 32],
mskid % 32, 1);
+
memcpy(&temp_key, &mask_key, sizeof(mask_key));
hns_dsaf_tcam_mc_cfg_vague(dsaf_dev, entry_index, &tbl_tcam_data_mc,
(struct dsaf_tbl_tcam_data *)(&mask_key),
u8 mac_id, u8 port_num);
int hns_dsaf_wait_pkt_clean(struct dsaf_device *dsaf_dev, int port);
+int hns_dsaf_roce_reset(struct fwnode_handle *dsaf_fwnode, bool dereset);
+
#endif /* __HNS_DSAF_MAIN_H__ */
dsaf_set_field(origin, 1ull << 10, 10, en);
dsaf_write_syscon(mac_cb->serdes_ctrl, reg_offset, origin);
} else {
- u8 *base_addr = (u8 *)mac_cb->serdes_vaddr +
+ u8 __iomem *base_addr = mac_cb->serdes_vaddr +
(mac_cb->mac_id <= 3 ? 0x00280000 : 0x00200000);
dsaf_set_reg_field(base_addr, reg_offset, 1ull << 10, 10, en);
}
}
}
-static void __iomem *
+static u8 __iomem *
hns_ppe_common_get_ioaddr(struct ppe_common_cb *ppe_common)
{
return ppe_common->dsaf_dev->ppe_base + PPE_COMMON_REG_OFFSET;
dsaf_dev->ppe_common[comm_index] = NULL;
}
-static void __iomem *hns_ppe_get_iobase(struct ppe_common_cb *ppe_common,
- int ppe_idx)
+static u8 __iomem *hns_ppe_get_iobase(struct ppe_common_cb *ppe_common,
+ int ppe_idx)
{
return ppe_common->dsaf_dev->ppe_base + ppe_idx * PPE_REG_OFFSET;
}
struct hns_ppe_hw_stats hw_stats;
u8 index; /* index in a ppe common device */
- void __iomem *io_base;
+ u8 __iomem *io_base;
int virq;
u32 rss_indir_table[HNS_PPEV2_RSS_IND_TBL_SIZE]; /*shadow indir tab */
u32 rss_key[HNS_PPEV2_RSS_KEY_NUM]; /* rss hash key */
struct ppe_common_cb {
struct device *dev;
struct dsaf_device *dsaf_dev;
- void __iomem *io_base;
+ u8 __iomem *io_base;
enum ppe_common_mode ppe_mode;
mdnum_ppkt = HNS_RCB_RING_MAX_BD_PER_PKT;
} else {
ring = &q->tx_ring;
- ring->io_base = (u8 __iomem *)ring_pair_cb->q.io_base +
+ ring->io_base = ring_pair_cb->q.io_base +
HNS_RCB_TX_REG_OFFSET;
irq_idx = HNS_RCB_IRQ_IDX_TX;
mdnum_ppkt = is_ver1 ? HNS_RCB_RING_MAX_TXBD_PER_PKT :
}
}
-static void __iomem *hns_rcb_common_get_vaddr(struct rcb_common_cb *rcb_common)
+static u8 __iomem *hns_rcb_common_get_vaddr(struct rcb_common_cb *rcb_common)
{
struct dsaf_device *dsaf_dev = rcb_common->dsaf_dev;
#define XGMAC_PAUSE_CTL_RSP_MODE_B 2
#define XGMAC_PAUSE_CTL_TX_XOFF_B 3
-static inline void dsaf_write_reg(void __iomem *base, u32 reg, u32 value)
+static inline void dsaf_write_reg(u8 __iomem *base, u32 reg, u32 value)
{
writel(value, base + reg);
}
#define dsaf_set_bit(origin, shift, val) \
dsaf_set_field((origin), (1ull << (shift)), (shift), (val))
-static inline void dsaf_set_reg_field(void __iomem *base, u32 reg, u32 mask,
+static inline void dsaf_set_reg_field(u8 __iomem *base, u32 reg, u32 mask,
u32 shift, u32 val)
{
u32 origin = dsaf_read_reg(base, reg);
#define dsaf_get_bit(origin, shift) \
dsaf_get_field((origin), (1ull << (shift)), (shift))
-static inline u32 dsaf_get_reg_field(void __iomem *base, u32 reg, u32 mask,
+static inline u32 dsaf_get_reg_field(u8 __iomem *base, u32 reg, u32 mask,
u32 shift)
{
u32 origin;
dsaf_get_reg_field((dev)->io_base, (reg), (1ull << (bit)), (bit))
#define dsaf_write_b(addr, data)\
- writeb((data), (__iomem unsigned char *)(addr))
+ writeb((data), (__iomem u8 *)(addr))
#define dsaf_read_b(addr)\
- readb((__iomem unsigned char *)(addr))
+ readb((__iomem u8 *)(addr))
#define hns_mac_reg_read64(drv, offset) \
- readq((__iomem void *)(((u8 *)(drv)->io_base + 0xc00 + (offset))))
+ readq((__iomem void *)(((drv)->io_base + 0xc00 + (offset))))
#endif /* _DSAF_REG_H */
dsaf_set_bit(val, XGMAC_UNIDIR_EN_B, 0);
dsaf_set_bit(val, XGMAC_RF_TX_EN_B, 1);
dsaf_set_field(val, XGMAC_LF_RF_INSERT_M, XGMAC_LF_RF_INSERT_S, 0);
- dsaf_write_reg(mac_drv, XGMAC_MAC_TX_LF_RF_CONTROL_REG, val);
+ dsaf_write_dev(mac_drv, XGMAC_MAC_TX_LF_RF_CONTROL_REG, val);
}
/**
#define SERVICE_TIMER_HZ (1 * HZ)
-#define NIC_TX_CLEAN_MAX_NUM 256
-#define NIC_RX_CLEAN_MAX_NUM 64
-
#define RCB_IRQ_NOT_INITED 0
#define RCB_IRQ_INITED 1
#define HNS_BUFFER_SIZE_2048 2048
wmb(); /* commit all data before submit */
assert(skb->queue_mapping < priv->ae_handle->q_num);
hnae_queue_xmit(priv->ae_handle->qs[skb->queue_mapping], buf_num);
- ring->stats.tx_pkts++;
- ring->stats.tx_bytes += skb->len;
return NETDEV_TX_OK;
/* issue prefetch for next Tx descriptor */
prefetch(&ring->desc_cb[ring->next_to_clean]);
}
+ /* update tx ring statistics. */
+ ring->stats.tx_pkts += pkts;
+ ring->stats.tx_bytes += bytes;
NETIF_TX_UNLOCK(ring);
hns_nic_tx_fini_pro_v2;
netif_napi_add(priv->netdev, &rd->napi,
- hns_nic_common_poll, NIC_TX_CLEAN_MAX_NUM);
+ hns_nic_common_poll, NAPI_POLL_WEIGHT);
rd->ring->irq_init_flag = RCB_IRQ_NOT_INITED;
}
for (i = h->q_num; i < h->q_num * 2; i++) {
hns_nic_rx_fini_pro_v2;
netif_napi_add(priv->netdev, &rd->napi,
- hns_nic_common_poll, NIC_RX_CLEAN_MAX_NUM);
+ hns_nic_common_poll, NAPI_POLL_WEIGHT);
rd->ring->irq_init_flag = RCB_IRQ_NOT_INITED;
}
HCLGE_MBX_GET_QID_IN_PF, /* (VF -> PF) get queue id in pf */
HCLGE_MBX_LINK_STAT_MODE, /* (PF -> VF) link mode has changed */
HCLGE_MBX_GET_LINK_MODE, /* (VF -> PF) get the link mode of pf */
+ HLCGE_MBX_PUSH_VLAN_INFO, /* (PF -> VF) push port base vlan */
+ HCLGE_MBX_GET_MEDIA_TYPE, /* (VF -> PF) get media type */
HCLGE_MBX_GET_VF_FLR_STATUS = 200, /* (M7 -> PF) get vf reset status */
};
HCLGE_MBX_VLAN_FILTER = 0, /* set vlan filter */
HCLGE_MBX_VLAN_TX_OFF_CFG, /* set tx side vlan offload */
HCLGE_MBX_VLAN_RX_OFF_CFG, /* set rx side vlan offload */
+ HCLGE_MBX_PORT_BASE_VLAN_CFG, /* set port based vlan configuration */
+ HCLGE_MBX_GET_PORT_BASE_VLAN_STATE, /* get port based vlan state */
};
#define HCLGE_MBX_MAX_MSG_SIZE 16
return inited;
}
-static int hnae3_match_n_instantiate(struct hnae3_client *client,
- struct hnae3_ae_dev *ae_dev, bool is_reg)
+static int hnae3_init_client_instance(struct hnae3_client *client,
+ struct hnae3_ae_dev *ae_dev)
{
int ret;
return 0;
}
- /* now, (un-)instantiate client by calling lower layer */
- if (is_reg) {
- ret = ae_dev->ops->init_client_instance(client, ae_dev);
- if (ret)
- dev_err(&ae_dev->pdev->dev,
- "fail to instantiate client, ret = %d\n", ret);
+ ret = ae_dev->ops->init_client_instance(client, ae_dev);
+ if (ret)
+ dev_err(&ae_dev->pdev->dev,
+ "fail to instantiate client, ret = %d\n", ret);
- return ret;
- }
+ return ret;
+}
+
+static void hnae3_uninit_client_instance(struct hnae3_client *client,
+ struct hnae3_ae_dev *ae_dev)
+{
+ /* check if this client matches the type of ae_dev */
+ if (!(hnae3_client_match(client->type, ae_dev->dev_type) &&
+ hnae3_get_bit(ae_dev->flag, HNAE3_DEV_INITED_B)))
+ return;
if (hnae3_get_client_init_flag(client, ae_dev)) {
ae_dev->ops->uninit_client_instance(client, ae_dev);
hnae3_set_client_init_flag(client, ae_dev, 0);
}
-
- return 0;
}
int hnae3_register_client(struct hnae3_client *client)
/* if the client could not be initialized on current port, for
* any error reasons, move on to next available port
*/
- ret = hnae3_match_n_instantiate(client, ae_dev, true);
+ ret = hnae3_init_client_instance(client, ae_dev);
if (ret)
dev_err(&ae_dev->pdev->dev,
"match and instantiation failed for port, ret = %d\n",
mutex_lock(&hnae3_common_lock);
/* un-initialize the client on every matched port */
list_for_each_entry(ae_dev, &hnae3_ae_dev_list, node) {
- hnae3_match_n_instantiate(client, ae_dev, false);
+ hnae3_uninit_client_instance(client, ae_dev);
}
list_del(&client->node);
* initialize the figure out client instance
*/
list_for_each_entry(client, &hnae3_client_list, node) {
- ret = hnae3_match_n_instantiate(client, ae_dev, true);
+ ret = hnae3_init_client_instance(client, ae_dev);
if (ret)
dev_err(&ae_dev->pdev->dev,
"match and instantiation failed, ret = %d\n",
* un-initialize the figure out client instance
*/
list_for_each_entry(client, &hnae3_client_list, node)
- hnae3_match_n_instantiate(client, ae_dev, false);
+ hnae3_uninit_client_instance(client, ae_dev);
ae_algo->ops->uninit_ae_dev(ae_dev);
hnae3_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 0);
* initialize the figure out client instance
*/
list_for_each_entry(client, &hnae3_client_list, node) {
- ret = hnae3_match_n_instantiate(client, ae_dev, true);
+ ret = hnae3_init_client_instance(client, ae_dev);
if (ret)
dev_err(&ae_dev->pdev->dev,
"match and instantiation failed, ret = %d\n",
continue;
list_for_each_entry(client, &hnae3_client_list, node)
- hnae3_match_n_instantiate(client, ae_dev, false);
+ hnae3_uninit_client_instance(client, ae_dev);
ae_algo->ops->uninit_ae_dev(ae_dev);
hnae3_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 0);
HNAE3_FLR_DONE,
};
+enum hnae3_port_base_vlan_state {
+ HNAE3_PORT_BASE_VLAN_DISABLE,
+ HNAE3_PORT_BASE_VLAN_ENABLE,
+ HNAE3_PORT_BASE_VLAN_MODIFY,
+ HNAE3_PORT_BASE_VLAN_NOCHANGE,
+};
+
struct hnae3_vector_info {
u8 __iomem *io_addr;
int vector;
u32 numa_node_mask; /* for multi-chip support */
+ enum hnae3_port_base_vlan_state port_base_vlan_state;
+
u8 netdev_flags;
struct dentry *hnae3_dbgfs;
};
{
#define HNS3_TX_VLAN_PRIO_SHIFT 13
+ struct hnae3_handle *handle = tx_ring->tqp->handle;
+
+ /* Since HW limitation, if port based insert VLAN enabled, only one VLAN
+ * header is allowed in skb, otherwise it will cause RAS error.
+ */
+ if (unlikely(skb_vlan_tagged_multi(skb) &&
+ handle->port_base_vlan_state ==
+ HNAE3_PORT_BASE_VLAN_ENABLE))
+ return -EINVAL;
+
if (skb->protocol == htons(ETH_P_8021Q) &&
!(tx_ring->tqp->handle->kinfo.netdev->features &
NETIF_F_HW_VLAN_CTAG_TX)) {
* and use inner_vtag in one tag case.
*/
if (skb->protocol == htons(ETH_P_8021Q)) {
- hns3_set_field(*out_vlan_flag, HNS3_TXD_OVLAN_B, 1);
- *out_vtag = vlan_tag;
+ if (handle->port_base_vlan_state ==
+ HNAE3_PORT_BASE_VLAN_DISABLE){
+ hns3_set_field(*out_vlan_flag,
+ HNS3_TXD_OVLAN_B, 1);
+ *out_vtag = vlan_tag;
+ } else {
+ hns3_set_field(*inner_vlan_flag,
+ HNS3_TXD_VLAN_B, 1);
+ *inner_vtag = vlan_tag;
+ }
} else {
hns3_set_field(*inner_vlan_flag, HNS3_TXD_VLAN_B, 1);
*inner_vtag = vlan_tag;
struct hns3_desc_cb *desc_cb = &ring->desc_cb[ring->next_to_use];
struct hns3_desc *desc = &ring->desc[ring->next_to_use];
struct device *dev = ring_to_dev(ring);
- u16 bdtp_fe_sc_vld_ra_ri = 0;
struct skb_frag_struct *frag;
unsigned int frag_buf_num;
int k, sizeoflast;
desc_cb->length = size;
+ if (likely(size <= HNS3_MAX_BD_SIZE)) {
+ u16 bdtp_fe_sc_vld_ra_ri = 0;
+
+ desc_cb->priv = priv;
+ desc_cb->dma = dma;
+ desc_cb->type = type;
+ desc->addr = cpu_to_le64(dma);
+ desc->tx.send_size = cpu_to_le16(size);
+ hns3_set_txbd_baseinfo(&bdtp_fe_sc_vld_ra_ri, frag_end);
+ desc->tx.bdtp_fe_sc_vld_ra_ri =
+ cpu_to_le16(bdtp_fe_sc_vld_ra_ri);
+
+ ring_ptr_move_fw(ring, next_to_use);
+ return 0;
+ }
+
frag_buf_num = hns3_tx_bd_count(size);
sizeoflast = size & HNS3_TX_LAST_SIZE_M;
sizeoflast = sizeoflast ? sizeoflast : HNS3_MAX_BD_SIZE;
/* When frag size is bigger than hardware limit, split this frag */
for (k = 0; k < frag_buf_num; k++) {
+ u16 bdtp_fe_sc_vld_ra_ri = 0;
+
/* The txbd's baseinfo of DESC_TYPE_PAGE & DESC_TYPE_SKB */
desc_cb->priv = priv;
desc_cb->dma = dma + HNS3_MAX_BD_SIZE * k;
struct hnae3_handle *h = hns3_get_handle(netdev);
int ret;
+ if (hns3_nic_resetting(netdev))
+ return -EBUSY;
+
if (!h->ae_algo->ops->set_mtu)
return -EOPNOTSUPP;
}
}
+static int hns3_gro_complete(struct sk_buff *skb)
+{
+ __be16 type = skb->protocol;
+ struct tcphdr *th;
+ int depth = 0;
+
+ while (type == htons(ETH_P_8021Q)) {
+ struct vlan_hdr *vh;
+
+ if ((depth + VLAN_HLEN) > skb_headlen(skb))
+ return -EFAULT;
+
+ vh = (struct vlan_hdr *)(skb->data + depth);
+ type = vh->h_vlan_encapsulated_proto;
+ depth += VLAN_HLEN;
+ }
+
+ if (type == htons(ETH_P_IP)) {
+ depth += sizeof(struct iphdr);
+ } else if (type == htons(ETH_P_IPV6)) {
+ depth += sizeof(struct ipv6hdr);
+ } else {
+ netdev_err(skb->dev,
+ "Error: FW GRO supports only IPv4/IPv6, not 0x%04x, depth: %d\n",
+ be16_to_cpu(type), depth);
+ return -EFAULT;
+ }
+
+ th = (struct tcphdr *)(skb->data + depth);
+ skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count;
+ if (th->cwr)
+ skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN;
+
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+ return 0;
+}
+
static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb,
- struct hns3_desc *desc)
+ u32 l234info, u32 bd_base_info)
{
struct net_device *netdev = ring->tqp->handle->kinfo.netdev;
int l3_type, l4_type;
- u32 bd_base_info;
int ol4_type;
- u32 l234info;
-
- bd_base_info = le32_to_cpu(desc->rx.bd_base_info);
- l234info = le32_to_cpu(desc->rx.l234_info);
skb->ip_summed = CHECKSUM_NONE;
if (!(netdev->features & NETIF_F_RXCSUM))
return;
- /* We MUST enable hardware checksum before enabling hardware GRO */
- if (skb_shinfo(skb)->gso_size) {
- skb->ip_summed = CHECKSUM_UNNECESSARY;
- return;
- }
-
/* check if hardware has done checksum */
if (!(bd_base_info & BIT(HNS3_RXD_L3L4P_B)))
return;
struct hns3_desc *desc, u32 l234info,
u16 *vlan_tag)
{
+ struct hnae3_handle *handle = ring->tqp->handle;
struct pci_dev *pdev = ring->tqp->handle->pdev;
if (pdev->revision == 0x20) {
#define HNS3_STRP_OUTER_VLAN 0x1
#define HNS3_STRP_INNER_VLAN 0x2
+#define HNS3_STRP_BOTH 0x3
+ /* Hardware always insert VLAN tag into RX descriptor when
+ * remove the tag from packet, driver needs to determine
+ * reporting which tag to stack.
+ */
switch (hnae3_get_field(l234info, HNS3_RXD_STRP_TAGP_M,
HNS3_RXD_STRP_TAGP_S)) {
case HNS3_STRP_OUTER_VLAN:
+ if (handle->port_base_vlan_state !=
+ HNAE3_PORT_BASE_VLAN_DISABLE)
+ return false;
+
*vlan_tag = le16_to_cpu(desc->rx.ot_vlan_tag);
return true;
case HNS3_STRP_INNER_VLAN:
+ if (handle->port_base_vlan_state !=
+ HNAE3_PORT_BASE_VLAN_DISABLE)
+ return false;
+
*vlan_tag = le16_to_cpu(desc->rx.vlan_tag);
+ return true;
+ case HNS3_STRP_BOTH:
+ if (handle->port_base_vlan_state ==
+ HNAE3_PORT_BASE_VLAN_DISABLE)
+ *vlan_tag = le16_to_cpu(desc->rx.ot_vlan_tag);
+ else
+ *vlan_tag = le16_to_cpu(desc->rx.vlan_tag);
+
return true;
default:
return false;
return 0;
}
-static void hns3_set_gro_param(struct sk_buff *skb, u32 l234info,
- u32 bd_base_info)
+static int hns3_set_gro_and_checksum(struct hns3_enet_ring *ring,
+ struct sk_buff *skb, u32 l234info,
+ u32 bd_base_info)
{
u16 gro_count;
u32 l3_type;
gro_count = hnae3_get_field(l234info, HNS3_RXD_GRO_COUNT_M,
HNS3_RXD_GRO_COUNT_S);
/* if there is no HW GRO, do not set gro params */
- if (!gro_count)
- return;
+ if (!gro_count) {
+ hns3_rx_checksum(ring, skb, l234info, bd_base_info);
+ return 0;
+ }
- /* tcp_gro_complete() will copy NAPI_GRO_CB(skb)->count
- * to skb_shinfo(skb)->gso_segs
- */
NAPI_GRO_CB(skb)->count = gro_count;
l3_type = hnae3_get_field(l234info, HNS3_RXD_L3ID_M,
else if (l3_type == HNS3_L3_TYPE_IPV6)
skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
else
- return;
+ return -EFAULT;
skb_shinfo(skb)->gso_size = hnae3_get_field(bd_base_info,
HNS3_RXD_GRO_SIZE_M,
HNS3_RXD_GRO_SIZE_S);
- if (skb_shinfo(skb)->gso_size)
- tcp_gro_complete(skb);
+
+ return hns3_gro_complete(skb);
}
static void hns3_set_rx_skb_rss_type(struct hns3_enet_ring *ring,
skb_set_hash(skb, le32_to_cpu(desc->rx.rss_hash), rss_type);
}
-static int hns3_handle_rx_bd(struct hns3_enet_ring *ring,
- struct sk_buff **out_skb)
+static int hns3_handle_bdinfo(struct hns3_enet_ring *ring, struct sk_buff *skb,
+ struct hns3_desc *desc)
{
struct net_device *netdev = ring->tqp->handle->kinfo.netdev;
+ u32 bd_base_info = le32_to_cpu(desc->rx.bd_base_info);
+ u32 l234info = le32_to_cpu(desc->rx.l234_info);
enum hns3_pkt_l2t_type l2_frame_type;
+ unsigned int len;
+ int ret;
+
+ /* Based on hw strategy, the tag offloaded will be stored at
+ * ot_vlan_tag in two layer tag case, and stored at vlan_tag
+ * in one layer tag case.
+ */
+ if (netdev->features & NETIF_F_HW_VLAN_CTAG_RX) {
+ u16 vlan_tag;
+
+ if (hns3_parse_vlan_tag(ring, desc, l234info, &vlan_tag))
+ __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
+ vlan_tag);
+ }
+
+ if (unlikely(!(bd_base_info & BIT(HNS3_RXD_VLD_B)))) {
+ u64_stats_update_begin(&ring->syncp);
+ ring->stats.non_vld_descs++;
+ u64_stats_update_end(&ring->syncp);
+
+ return -EINVAL;
+ }
+
+ if (unlikely(!desc->rx.pkt_len || (l234info & (BIT(HNS3_RXD_TRUNCAT_B) |
+ BIT(HNS3_RXD_L2E_B))))) {
+ u64_stats_update_begin(&ring->syncp);
+ if (l234info & BIT(HNS3_RXD_L2E_B))
+ ring->stats.l2_err++;
+ else
+ ring->stats.err_pkt_len++;
+ u64_stats_update_end(&ring->syncp);
+
+ return -EFAULT;
+ }
+
+ len = skb->len;
+
+ /* Do update ip stack process */
+ skb->protocol = eth_type_trans(skb, netdev);
+
+ /* This is needed in order to enable forwarding support */
+ ret = hns3_set_gro_and_checksum(ring, skb, l234info, bd_base_info);
+ if (unlikely(ret)) {
+ u64_stats_update_begin(&ring->syncp);
+ ring->stats.rx_err_cnt++;
+ u64_stats_update_end(&ring->syncp);
+ return ret;
+ }
+
+ l2_frame_type = hnae3_get_field(l234info, HNS3_RXD_DMAC_M,
+ HNS3_RXD_DMAC_S);
+
+ u64_stats_update_begin(&ring->syncp);
+ ring->stats.rx_pkts++;
+ ring->stats.rx_bytes += len;
+
+ if (l2_frame_type == HNS3_L2_TYPE_MULTICAST)
+ ring->stats.rx_multicast++;
+
+ u64_stats_update_end(&ring->syncp);
+
+ ring->tqp_vector->rx_group.total_bytes += len;
+ return 0;
+}
+
+static int hns3_handle_rx_bd(struct hns3_enet_ring *ring,
+ struct sk_buff **out_skb)
+{
struct sk_buff *skb = ring->skb;
struct hns3_desc_cb *desc_cb;
struct hns3_desc *desc;
u32 bd_base_info;
- u32 l234info;
int length;
int ret;
ALIGN(ring->pull_len, sizeof(long)));
}
- l234info = le32_to_cpu(desc->rx.l234_info);
- bd_base_info = le32_to_cpu(desc->rx.bd_base_info);
-
- /* Based on hw strategy, the tag offloaded will be stored at
- * ot_vlan_tag in two layer tag case, and stored at vlan_tag
- * in one layer tag case.
- */
- if (netdev->features & NETIF_F_HW_VLAN_CTAG_RX) {
- u16 vlan_tag;
-
- if (hns3_parse_vlan_tag(ring, desc, l234info, &vlan_tag))
- __vlan_hwaccel_put_tag(skb,
- htons(ETH_P_8021Q),
- vlan_tag);
- }
-
- if (unlikely(!(bd_base_info & BIT(HNS3_RXD_VLD_B)))) {
- u64_stats_update_begin(&ring->syncp);
- ring->stats.non_vld_descs++;
- u64_stats_update_end(&ring->syncp);
-
+ ret = hns3_handle_bdinfo(ring, skb, desc);
+ if (unlikely(ret)) {
dev_kfree_skb_any(skb);
- return -EINVAL;
- }
-
- if (unlikely((!desc->rx.pkt_len) ||
- (l234info & (BIT(HNS3_RXD_TRUNCAT_B) |
- BIT(HNS3_RXD_L2E_B))))) {
- u64_stats_update_begin(&ring->syncp);
- if (l234info & BIT(HNS3_RXD_L2E_B))
- ring->stats.l2_err++;
- else
- ring->stats.err_pkt_len++;
- u64_stats_update_end(&ring->syncp);
-
- dev_kfree_skb_any(skb);
- return -EFAULT;
+ return ret;
}
-
- l2_frame_type = hnae3_get_field(l234info, HNS3_RXD_DMAC_M,
- HNS3_RXD_DMAC_S);
- u64_stats_update_begin(&ring->syncp);
- if (l2_frame_type == HNS3_L2_TYPE_MULTICAST)
- ring->stats.rx_multicast++;
-
- ring->stats.rx_pkts++;
- ring->stats.rx_bytes += skb->len;
- u64_stats_update_end(&ring->syncp);
-
- ring->tqp_vector->rx_group.total_bytes += skb->len;
-
- /* This is needed in order to enable forwarding support */
- hns3_set_gro_param(skb, l234info, bd_base_info);
-
- hns3_rx_checksum(ring, skb, desc);
*out_skb = skb;
hns3_set_rx_skb_rss_type(ring, skb);
void (*rx_fn)(struct hns3_enet_ring *, struct sk_buff *))
{
#define RCB_NOF_ALLOC_RX_BUFF_ONCE 16
- struct net_device *netdev = ring->tqp->handle->kinfo.netdev;
int recv_pkts, recv_bds, clean_count, err;
int unused_count = hns3_desc_unused(ring) - ring->pending_buf;
struct sk_buff *skb = ring->skb;
continue;
}
- /* Do update ip stack process */
- skb->protocol = eth_type_trans(skb, netdev);
rx_fn(ring, skb);
recv_bds += ring->pending_buf;
clean_count += ring->pending_buf;
struct hns3_enet_tqp_vector *tqp_vector =
container_of(napi, struct hns3_enet_tqp_vector, napi);
bool clean_complete = true;
- int rx_budget;
+ int rx_budget = budget;
if (unlikely(test_bit(HNS3_NIC_STATE_DOWN, &priv->state))) {
napi_complete(napi);
hns3_clean_tx_ring(ring);
/* make sure rx ring budget not smaller than 1 */
- rx_budget = max(budget / tqp_vector->num_tqps, 1);
+ if (tqp_vector->num_tqps > 1)
+ rx_budget = max(budget / tqp_vector->num_tqps, 1);
hns3_for_each_ring(ring, tqp_vector->rx_group) {
int rx_cleaned = hns3_clean_rx_ring(ring, rx_budget,
struct hns3_nic_priv *priv = netdev_priv(netdev);
int ret;
- hns3_client_stop(handle);
-
hns3_remove_hw_addr(netdev);
if (netdev->reg_state != NETREG_UNINITIALIZED)
unregister_netdev(netdev);
+ hns3_client_stop(handle);
+
if (!test_and_clear_bit(HNS3_NIC_STATE_INITED, &priv->state)) {
netdev_warn(netdev, "already uninitialized\n");
goto out_netdev_free;
struct netdev_hw_addr *ha, *tmp;
int ret = 0;
+ netif_addr_lock_bh(ndev);
/* go through and sync uc_addr entries to the device */
list = &ndev->uc;
list_for_each_entry_safe(ha, tmp, &list->list, list) {
ret = hns3_nic_uc_sync(ndev, ha->addr);
if (ret)
- return ret;
+ goto out;
}
/* go through and sync mc_addr entries to the device */
list_for_each_entry_safe(ha, tmp, &list->list, list) {
ret = hns3_nic_mc_sync(ndev, ha->addr);
if (ret)
- return ret;
+ goto out;
}
+out:
+ netif_addr_unlock_bh(ndev);
return ret;
}
hns3_nic_uc_unsync(netdev, netdev->dev_addr);
+ netif_addr_lock_bh(netdev);
/* go through and unsync uc_addr entries to the device */
list = &netdev->uc;
list_for_each_entry_safe(ha, tmp, &list->list, list)
list_for_each_entry_safe(ha, tmp, &list->list, list)
if (ha->refcount > 1)
hns3_nic_mc_unsync(netdev, ha->addr);
+
+ netif_addr_unlock_bh(netdev);
}
static void hns3_clear_tx_ring(struct hns3_enet_ring *ring)
ring_ptr_move_fw(ring, next_to_use);
}
+ /* Free the pending skb in rx ring */
+ if (ring->skb) {
+ dev_kfree_skb_any(ring->skb);
+ ring->skb = NULL;
+ ring->pending_buf = 0;
+ }
+
return 0;
}
if (ret)
goto err_uninit_vector;
+ ret = hns3_client_start(handle);
+ if (ret) {
+ dev_err(priv->dev, "hns3_client_start fail! ret=%d\n", ret);
+ goto err_uninit_ring;
+ }
+
set_bit(HNS3_NIC_STATE_INITED, &priv->state);
return ret;
+err_uninit_ring:
+ hns3_uninit_all_ring(priv);
err_uninit_vector:
hns3_nic_uninit_vector_data(priv);
priv->ring_data = NULL;
struct hns3_nic_priv *priv = netdev_priv(netdev);
int ret;
- if (!test_bit(HNS3_NIC_STATE_INITED, &priv->state)) {
+ if (!test_and_clear_bit(HNS3_NIC_STATE_INITED, &priv->state)) {
netdev_warn(netdev, "already uninitialized\n");
return 0;
}
hns3_put_ring_config(priv);
priv->ring_data = NULL;
- clear_bit(HNS3_NIC_STATE_INITED, &priv->state);
-
return ret;
}
unsigned char *hdr;
};
-/* the distance between [begin, end) in a ring buffer
- * note: there is a unuse slot between the begin and the end
- */
-static inline int ring_dist(struct hns3_enet_ring *ring, int begin, int end)
-{
- return (end - begin + ring->desc_num) % ring->desc_num;
-}
-
static inline int ring_space(struct hns3_enet_ring *ring)
{
- return ring->desc_num -
- ring_dist(ring, ring->next_to_clean, ring->next_to_use) - 1;
+ int begin = ring->next_to_clean;
+ int end = ring->next_to_use;
+
+ return ((end >= begin) ? (ring->desc_num - end + begin) :
+ (begin - end)) - 1;
}
static inline int is_ring_empty(struct hns3_enet_ring *ring)
struct hnae3_handle *h = hns3_get_handle(netdev);
u64 *p = data;
+ if (hns3_nic_resetting(netdev)) {
+ netdev_err(netdev, "dev resetting, could not get stats\n");
+ return;
+ }
+
if (!h->ae_algo->ops->get_stats || !h->ae_algo->ops->update_stats) {
netdev_err(netdev, "could not get any statistics\n");
return;
static int hns3_set_link_ksettings(struct net_device *netdev,
const struct ethtool_link_ksettings *cmd)
{
+ /* Chip doesn't support this mode. */
+ if (cmd->base.speed == SPEED_1000 && cmd->base.duplex == DUPLEX_HALF)
+ return -EINVAL;
+
/* Only support ksettings_set for netdev with phy attached for now */
if (netdev->phydev)
return phy_ethtool_ksettings_set(netdev->phydev, cmd);
# Makefile for the HISILICON network device drivers.
#
-ccflags-y := -Idrivers/net/ethernet/hisilicon/hns3
+ccflags-y := -I $(srctree)/drivers/net/ethernet/hisilicon/hns3
obj-$(CONFIG_HNS3_HCLGE) += hclge.o
hclge-objs = hclge_main.o hclge_cmd.o hclge_mdio.o hclge_tm.o hclge_mbx.o hclge_err.o hclge_debugfs.o
int ret;
spin_lock_bh(&hdev->hw.cmq.csq.lock);
- spin_lock_bh(&hdev->hw.cmq.crq.lock);
+ spin_lock(&hdev->hw.cmq.crq.lock);
hdev->hw.cmq.csq.next_to_clean = 0;
hdev->hw.cmq.csq.next_to_use = 0;
hclge_cmd_init_regs(&hdev->hw);
- spin_unlock_bh(&hdev->hw.cmq.crq.lock);
+ spin_unlock(&hdev->hw.cmq.crq.lock);
spin_unlock_bh(&hdev->hw.cmq.csq.lock);
clear_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
* reset may happen when lower level reset is being processed.
*/
if ((hclge_is_reset_pending(hdev))) {
- set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
- return -EBUSY;
+ ret = -EBUSY;
+ goto err_cmd_init;
}
ret = hclge_cmd_query_firmware_version(&hdev->hw, &version);
if (ret) {
dev_err(&hdev->pdev->dev,
"firmware version query failed %d\n", ret);
- return ret;
+ goto err_cmd_init;
}
hdev->fw_version = version;
dev_info(&hdev->pdev->dev, "The firmware version is %08x\n", version);
return 0;
+
+err_cmd_init:
+ set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
+
+ return ret;
}
static void hclge_cmd_uninit_regs(struct hclge_hw *hw)
#include "hclge_err.h"
static const struct hclge_hw_error hclge_imp_tcm_ecc_int[] = {
- { .int_msk = BIT(1), .msg = "imp_itcm0_ecc_mbit_err" },
- { .int_msk = BIT(3), .msg = "imp_itcm1_ecc_mbit_err" },
- { .int_msk = BIT(5), .msg = "imp_itcm2_ecc_mbit_err" },
- { .int_msk = BIT(7), .msg = "imp_itcm3_ecc_mbit_err" },
- { .int_msk = BIT(9), .msg = "imp_dtcm0_mem0_ecc_mbit_err" },
- { .int_msk = BIT(11), .msg = "imp_dtcm0_mem1_ecc_mbit_err" },
- { .int_msk = BIT(13), .msg = "imp_dtcm1_mem0_ecc_mbit_err" },
- { .int_msk = BIT(15), .msg = "imp_dtcm1_mem1_ecc_mbit_err" },
- { .int_msk = BIT(17), .msg = "imp_itcm4_ecc_mbit_err" },
+ { .int_msk = BIT(1), .msg = "imp_itcm0_ecc_mbit_err",
+ .reset_level = HNAE3_NONE_RESET },
+ { .int_msk = BIT(3), .msg = "imp_itcm1_ecc_mbit_err",
+ .reset_level = HNAE3_NONE_RESET },
+ { .int_msk = BIT(5), .msg = "imp_itcm2_ecc_mbit_err",
+ .reset_level = HNAE3_NONE_RESET },
+ { .int_msk = BIT(7), .msg = "imp_itcm3_ecc_mbit_err",
+ .reset_level = HNAE3_NONE_RESET },
+ { .int_msk = BIT(9), .msg = "imp_dtcm0_mem0_ecc_mbit_err",
+ .reset_level = HNAE3_NONE_RESET },
+ { .int_msk = BIT(11), .msg = "imp_dtcm0_mem1_ecc_mbit_err",
+ .reset_level = HNAE3_NONE_RESET },
+ { .int_msk = BIT(13), .msg = "imp_dtcm1_mem0_ecc_mbit_err",
+ .reset_level = HNAE3_NONE_RESET },
+ { .int_msk = BIT(15), .msg = "imp_dtcm1_mem1_ecc_mbit_err",
+ .reset_level = HNAE3_NONE_RESET },
+ { .int_msk = BIT(17), .msg = "imp_itcm4_ecc_mbit_err",
+ .reset_level = HNAE3_NONE_RESET },
{ /* sentinel */ }
};
static const struct hclge_hw_error hclge_cmdq_nic_mem_ecc_int[] = {
- { .int_msk = BIT(1), .msg = "cmdq_nic_rx_depth_ecc_mbit_err" },
- { .int_msk = BIT(3), .msg = "cmdq_nic_tx_depth_ecc_mbit_err" },
- { .int_msk = BIT(5), .msg = "cmdq_nic_rx_tail_ecc_mbit_err" },
- { .int_msk = BIT(7), .msg = "cmdq_nic_tx_tail_ecc_mbit_err" },
- { .int_msk = BIT(9), .msg = "cmdq_nic_rx_head_ecc_mbit_err" },
- { .int_msk = BIT(11), .msg = "cmdq_nic_tx_head_ecc_mbit_err" },
- { .int_msk = BIT(13), .msg = "cmdq_nic_rx_addr_ecc_mbit_err" },
- { .int_msk = BIT(15), .msg = "cmdq_nic_tx_addr_ecc_mbit_err" },
- { .int_msk = BIT(17), .msg = "cmdq_rocee_rx_depth_ecc_mbit_err" },
- { .int_msk = BIT(19), .msg = "cmdq_rocee_tx_depth_ecc_mbit_err" },
- { .int_msk = BIT(21), .msg = "cmdq_rocee_rx_tail_ecc_mbit_err" },
- { .int_msk = BIT(23), .msg = "cmdq_rocee_tx_tail_ecc_mbit_err" },
- { .int_msk = BIT(25), .msg = "cmdq_rocee_rx_head_ecc_mbit_err" },
- { .int_msk = BIT(27), .msg = "cmdq_rocee_tx_head_ecc_mbit_err" },
- { .int_msk = BIT(29), .msg = "cmdq_rocee_rx_addr_ecc_mbit_err" },
- { .int_msk = BIT(31), .msg = "cmdq_rocee_tx_addr_ecc_mbit_err" },
+ { .int_msk = BIT(1), .msg = "cmdq_nic_rx_depth_ecc_mbit_err",
+ .reset_level = HNAE3_NONE_RESET },
+ { .int_msk = BIT(3), .msg = "cmdq_nic_tx_depth_ecc_mbit_err",
+ .reset_level = HNAE3_NONE_RESET },
+ { .int_msk = BIT(5), .msg = "cmdq_nic_rx_tail_ecc_mbit_err",
+ .reset_level = HNAE3_NONE_RESET },
+ { .int_msk = BIT(7), .msg = "cmdq_nic_tx_tail_ecc_mbit_err",
+ .reset_level = HNAE3_NONE_RESET },
+ { .int_msk = BIT(9), .msg = "cmdq_nic_rx_head_ecc_mbit_err",
+ .reset_level = HNAE3_NONE_RESET },
+ { .int_msk = BIT(11), .msg = "cmdq_nic_tx_head_ecc_mbit_err",
+ .reset_level = HNAE3_NONE_RESET },
+ { .int_msk = BIT(13), .msg = "cmdq_nic_rx_addr_ecc_mbit_err",
+ .reset_level = HNAE3_NONE_RESET },
+ { .int_msk = BIT(15), .msg = "cmdq_nic_tx_addr_ecc_mbit_err",
+ .reset_level = HNAE3_NONE_RESET },
+ { .int_msk = BIT(17), .msg = "cmdq_rocee_rx_depth_ecc_mbit_err",
+ .reset_level = HNAE3_NONE_RESET },
+ { .int_msk = BIT(19), .msg = "cmdq_rocee_tx_depth_ecc_mbit_err",
+ .reset_level = HNAE3_NONE_RESET },
+ { .int_msk = BIT(21), .msg = "cmdq_rocee_rx_tail_ecc_mbit_err",
+ .reset_level = HNAE3_NONE_RESET },
+ { .int_msk = BIT(23), .msg = "cmdq_rocee_tx_tail_ecc_mbit_err",
+ .reset_level = HNAE3_NONE_RESET },
+ { .int_msk = BIT(25), .msg = "cmdq_rocee_rx_head_ecc_mbit_err",
+ .reset_level = HNAE3_NONE_RESET },
+ { .int_msk = BIT(27), .msg = "cmdq_rocee_tx_head_ecc_mbit_err",
+ .reset_level = HNAE3_NONE_RESET },
+ { .int_msk = BIT(29), .msg = "cmdq_rocee_rx_addr_ecc_mbit_err",
+ .reset_level = HNAE3_NONE_RESET },
+ { .int_msk = BIT(31), .msg = "cmdq_rocee_tx_addr_ecc_mbit_err",
+ .reset_level = HNAE3_NONE_RESET },
{ /* sentinel */ }
};
static const struct hclge_hw_error hclge_tqp_int_ecc_int[] = {
- { .int_msk = BIT(6), .msg = "tqp_int_cfg_even_ecc_mbit_err" },
- { .int_msk = BIT(7), .msg = "tqp_int_cfg_odd_ecc_mbit_err" },
- { .int_msk = BIT(8), .msg = "tqp_int_ctrl_even_ecc_mbit_err" },
- { .int_msk = BIT(9), .msg = "tqp_int_ctrl_odd_ecc_mbit_err" },
- { .int_msk = BIT(10), .msg = "tx_que_scan_int_ecc_mbit_err" },
- { .int_msk = BIT(11), .msg = "rx_que_scan_int_ecc_mbit_err" },
+ { .int_msk = BIT(6), .msg = "tqp_int_cfg_even_ecc_mbit_err",
+ .reset_level = HNAE3_NONE_RESET },
+ { .int_msk = BIT(7), .msg = "tqp_int_cfg_odd_ecc_mbit_err",
+ .reset_level = HNAE3_NONE_RESET },
+ { .int_msk = BIT(8), .msg = "tqp_int_ctrl_even_ecc_mbit_err",
+ .reset_level = HNAE3_NONE_RESET },
+ { .int_msk = BIT(9), .msg = "tqp_int_ctrl_odd_ecc_mbit_err",
+ .reset_level = HNAE3_NONE_RESET },
+ { .int_msk = BIT(10), .msg = "tx_que_scan_int_ecc_mbit_err",
+ .reset_level = HNAE3_NONE_RESET },
+ { .int_msk = BIT(11), .msg = "rx_que_scan_int_ecc_mbit_err",
+ .reset_level = HNAE3_NONE_RESET },
{ /* sentinel */ }
};
static const struct hclge_hw_error hclge_msix_sram_ecc_int[] = {
- { .int_msk = BIT(1), .msg = "msix_nic_ecc_mbit_err" },
- { .int_msk = BIT(3), .msg = "msix_rocee_ecc_mbit_err" },
+ { .int_msk = BIT(1), .msg = "msix_nic_ecc_mbit_err",
+ .reset_level = HNAE3_NONE_RESET },
+ { .int_msk = BIT(3), .msg = "msix_rocee_ecc_mbit_err",
+ .reset_level = HNAE3_NONE_RESET },
{ /* sentinel */ }
};
static const struct hclge_hw_error hclge_igu_int[] = {
- { .int_msk = BIT(0), .msg = "igu_rx_buf0_ecc_mbit_err" },
- { .int_msk = BIT(2), .msg = "igu_rx_buf1_ecc_mbit_err" },
+ { .int_msk = BIT(0), .msg = "igu_rx_buf0_ecc_mbit_err",
+ .reset_level = HNAE3_CORE_RESET },
+ { .int_msk = BIT(2), .msg = "igu_rx_buf1_ecc_mbit_err",
+ .reset_level = HNAE3_CORE_RESET },
{ /* sentinel */ }
};
static const struct hclge_hw_error hclge_igu_egu_tnl_int[] = {
- { .int_msk = BIT(0), .msg = "rx_buf_overflow" },
- { .int_msk = BIT(1), .msg = "rx_stp_fifo_overflow" },
- { .int_msk = BIT(2), .msg = "rx_stp_fifo_undeflow" },
- { .int_msk = BIT(3), .msg = "tx_buf_overflow" },
- { .int_msk = BIT(4), .msg = "tx_buf_underrun" },
- { .int_msk = BIT(5), .msg = "rx_stp_buf_overflow" },
+ { .int_msk = BIT(0), .msg = "rx_buf_overflow",
+ .reset_level = HNAE3_CORE_RESET },
+ { .int_msk = BIT(1), .msg = "rx_stp_fifo_overflow",
+ .reset_level = HNAE3_CORE_RESET },
+ { .int_msk = BIT(2), .msg = "rx_stp_fifo_undeflow",
+ .reset_level = HNAE3_CORE_RESET },
+ { .int_msk = BIT(3), .msg = "tx_buf_overflow",
+ .reset_level = HNAE3_CORE_RESET },
+ { .int_msk = BIT(4), .msg = "tx_buf_underrun",
+ .reset_level = HNAE3_CORE_RESET },
+ { .int_msk = BIT(5), .msg = "rx_stp_buf_overflow",
+ .reset_level = HNAE3_CORE_RESET },
{ /* sentinel */ }
};
static const struct hclge_hw_error hclge_ncsi_err_int[] = {
- { .int_msk = BIT(1), .msg = "ncsi_tx_ecc_mbit_err" },
+ { .int_msk = BIT(1), .msg = "ncsi_tx_ecc_mbit_err",
+ .reset_level = HNAE3_NONE_RESET },
{ /* sentinel */ }
};
static const struct hclge_hw_error hclge_ppp_mpf_abnormal_int_st1[] = {
- { .int_msk = BIT(0), .msg = "vf_vlan_ad_mem_ecc_mbit_err" },
- { .int_msk = BIT(1), .msg = "umv_mcast_group_mem_ecc_mbit_err" },
- { .int_msk = BIT(2), .msg = "umv_key_mem0_ecc_mbit_err" },
- { .int_msk = BIT(3), .msg = "umv_key_mem1_ecc_mbit_err" },
- { .int_msk = BIT(4), .msg = "umv_key_mem2_ecc_mbit_err" },
- { .int_msk = BIT(5), .msg = "umv_key_mem3_ecc_mbit_err" },
- { .int_msk = BIT(6), .msg = "umv_ad_mem_ecc_mbit_err" },
- { .int_msk = BIT(7), .msg = "rss_tc_mode_mem_ecc_mbit_err" },
- { .int_msk = BIT(8), .msg = "rss_idt_mem0_ecc_mbit_err" },
- { .int_msk = BIT(9), .msg = "rss_idt_mem1_ecc_mbit_err" },
- { .int_msk = BIT(10), .msg = "rss_idt_mem2_ecc_mbit_err" },
- { .int_msk = BIT(11), .msg = "rss_idt_mem3_ecc_mbit_err" },
- { .int_msk = BIT(12), .msg = "rss_idt_mem4_ecc_mbit_err" },
- { .int_msk = BIT(13), .msg = "rss_idt_mem5_ecc_mbit_err" },
- { .int_msk = BIT(14), .msg = "rss_idt_mem6_ecc_mbit_err" },
- { .int_msk = BIT(15), .msg = "rss_idt_mem7_ecc_mbit_err" },
- { .int_msk = BIT(16), .msg = "rss_idt_mem8_ecc_mbit_err" },
- { .int_msk = BIT(17), .msg = "rss_idt_mem9_ecc_mbit_err" },
- { .int_msk = BIT(18), .msg = "rss_idt_mem10_ecc_m1bit_err" },
- { .int_msk = BIT(19), .msg = "rss_idt_mem11_ecc_mbit_err" },
- { .int_msk = BIT(20), .msg = "rss_idt_mem12_ecc_mbit_err" },
- { .int_msk = BIT(21), .msg = "rss_idt_mem13_ecc_mbit_err" },
- { .int_msk = BIT(22), .msg = "rss_idt_mem14_ecc_mbit_err" },
- { .int_msk = BIT(23), .msg = "rss_idt_mem15_ecc_mbit_err" },
- { .int_msk = BIT(24), .msg = "port_vlan_mem_ecc_mbit_err" },
- { .int_msk = BIT(25), .msg = "mcast_linear_table_mem_ecc_mbit_err" },
- { .int_msk = BIT(26), .msg = "mcast_result_mem_ecc_mbit_err" },
- { .int_msk = BIT(27),
- .msg = "flow_director_ad_mem0_ecc_mbit_err" },
- { .int_msk = BIT(28),
- .msg = "flow_director_ad_mem1_ecc_mbit_err" },
- { .int_msk = BIT(29),
- .msg = "rx_vlan_tag_memory_ecc_mbit_err" },
- { .int_msk = BIT(30),
- .msg = "Tx_UP_mapping_config_mem_ecc_mbit_err" },
+ { .int_msk = BIT(0), .msg = "vf_vlan_ad_mem_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(1), .msg = "umv_mcast_group_mem_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(2), .msg = "umv_key_mem0_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(3), .msg = "umv_key_mem1_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(4), .msg = "umv_key_mem2_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(5), .msg = "umv_key_mem3_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(6), .msg = "umv_ad_mem_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(7), .msg = "rss_tc_mode_mem_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(8), .msg = "rss_idt_mem0_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(9), .msg = "rss_idt_mem1_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(10), .msg = "rss_idt_mem2_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(11), .msg = "rss_idt_mem3_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(12), .msg = "rss_idt_mem4_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(13), .msg = "rss_idt_mem5_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(14), .msg = "rss_idt_mem6_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(15), .msg = "rss_idt_mem7_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(16), .msg = "rss_idt_mem8_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(17), .msg = "rss_idt_mem9_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(18), .msg = "rss_idt_mem10_ecc_m1bit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(19), .msg = "rss_idt_mem11_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(20), .msg = "rss_idt_mem12_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(21), .msg = "rss_idt_mem13_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(22), .msg = "rss_idt_mem14_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(23), .msg = "rss_idt_mem15_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(24), .msg = "port_vlan_mem_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(25), .msg = "mcast_linear_table_mem_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(26), .msg = "mcast_result_mem_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(27), .msg = "flow_director_ad_mem0_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(28), .msg = "flow_director_ad_mem1_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(29), .msg = "rx_vlan_tag_memory_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(30), .msg = "Tx_UP_mapping_config_mem_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
{ /* sentinel */ }
};
static const struct hclge_hw_error hclge_ppp_pf_abnormal_int[] = {
- { .int_msk = BIT(0), .msg = "tx_vlan_tag_err" },
- { .int_msk = BIT(1), .msg = "rss_list_tc_unassigned_queue_err" },
+ { .int_msk = BIT(0), .msg = "tx_vlan_tag_err",
+ .reset_level = HNAE3_NONE_RESET },
+ { .int_msk = BIT(1), .msg = "rss_list_tc_unassigned_queue_err",
+ .reset_level = HNAE3_NONE_RESET },
{ /* sentinel */ }
};
static const struct hclge_hw_error hclge_ppp_mpf_abnormal_int_st3[] = {
- { .int_msk = BIT(0), .msg = "hfs_fifo_mem_ecc_mbit_err" },
- { .int_msk = BIT(1), .msg = "rslt_descr_fifo_mem_ecc_mbit_err" },
- { .int_msk = BIT(2), .msg = "tx_vlan_tag_mem_ecc_mbit_err" },
- { .int_msk = BIT(3), .msg = "FD_CN0_memory_ecc_mbit_err" },
- { .int_msk = BIT(4), .msg = "FD_CN1_memory_ecc_mbit_err" },
- { .int_msk = BIT(5), .msg = "GRO_AD_memory_ecc_mbit_err" },
+ { .int_msk = BIT(0), .msg = "hfs_fifo_mem_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(1), .msg = "rslt_descr_fifo_mem_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(2), .msg = "tx_vlan_tag_mem_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(3), .msg = "FD_CN0_memory_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(4), .msg = "FD_CN1_memory_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(5), .msg = "GRO_AD_memory_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
{ /* sentinel */ }
};
static const struct hclge_hw_error hclge_tm_sch_rint[] = {
- { .int_msk = BIT(1), .msg = "tm_sch_ecc_mbit_err" },
- { .int_msk = BIT(2), .msg = "tm_sch_port_shap_sub_fifo_wr_err" },
- { .int_msk = BIT(3), .msg = "tm_sch_port_shap_sub_fifo_rd_err" },
- { .int_msk = BIT(4), .msg = "tm_sch_pg_pshap_sub_fifo_wr_err" },
- { .int_msk = BIT(5), .msg = "tm_sch_pg_pshap_sub_fifo_rd_err" },
- { .int_msk = BIT(6), .msg = "tm_sch_pg_cshap_sub_fifo_wr_err" },
- { .int_msk = BIT(7), .msg = "tm_sch_pg_cshap_sub_fifo_rd_err" },
- { .int_msk = BIT(8), .msg = "tm_sch_pri_pshap_sub_fifo_wr_err" },
- { .int_msk = BIT(9), .msg = "tm_sch_pri_pshap_sub_fifo_rd_err" },
- { .int_msk = BIT(10), .msg = "tm_sch_pri_cshap_sub_fifo_wr_err" },
- { .int_msk = BIT(11), .msg = "tm_sch_pri_cshap_sub_fifo_rd_err" },
- { .int_msk = BIT(12),
- .msg = "tm_sch_port_shap_offset_fifo_wr_err" },
- { .int_msk = BIT(13),
- .msg = "tm_sch_port_shap_offset_fifo_rd_err" },
- { .int_msk = BIT(14),
- .msg = "tm_sch_pg_pshap_offset_fifo_wr_err" },
- { .int_msk = BIT(15),
- .msg = "tm_sch_pg_pshap_offset_fifo_rd_err" },
- { .int_msk = BIT(16),
- .msg = "tm_sch_pg_cshap_offset_fifo_wr_err" },
- { .int_msk = BIT(17),
- .msg = "tm_sch_pg_cshap_offset_fifo_rd_err" },
- { .int_msk = BIT(18),
- .msg = "tm_sch_pri_pshap_offset_fifo_wr_err" },
- { .int_msk = BIT(19),
- .msg = "tm_sch_pri_pshap_offset_fifo_rd_err" },
- { .int_msk = BIT(20),
- .msg = "tm_sch_pri_cshap_offset_fifo_wr_err" },
- { .int_msk = BIT(21),
- .msg = "tm_sch_pri_cshap_offset_fifo_rd_err" },
- { .int_msk = BIT(22), .msg = "tm_sch_rq_fifo_wr_err" },
- { .int_msk = BIT(23), .msg = "tm_sch_rq_fifo_rd_err" },
- { .int_msk = BIT(24), .msg = "tm_sch_nq_fifo_wr_err" },
- { .int_msk = BIT(25), .msg = "tm_sch_nq_fifo_rd_err" },
- { .int_msk = BIT(26), .msg = "tm_sch_roce_up_fifo_wr_err" },
- { .int_msk = BIT(27), .msg = "tm_sch_roce_up_fifo_rd_err" },
- { .int_msk = BIT(28), .msg = "tm_sch_rcb_byte_fifo_wr_err" },
- { .int_msk = BIT(29), .msg = "tm_sch_rcb_byte_fifo_rd_err" },
- { .int_msk = BIT(30), .msg = "tm_sch_ssu_byte_fifo_wr_err" },
- { .int_msk = BIT(31), .msg = "tm_sch_ssu_byte_fifo_rd_err" },
+ { .int_msk = BIT(1), .msg = "tm_sch_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(2), .msg = "tm_sch_port_shap_sub_fifo_wr_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(3), .msg = "tm_sch_port_shap_sub_fifo_rd_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(4), .msg = "tm_sch_pg_pshap_sub_fifo_wr_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(5), .msg = "tm_sch_pg_pshap_sub_fifo_rd_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(6), .msg = "tm_sch_pg_cshap_sub_fifo_wr_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(7), .msg = "tm_sch_pg_cshap_sub_fifo_rd_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(8), .msg = "tm_sch_pri_pshap_sub_fifo_wr_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(9), .msg = "tm_sch_pri_pshap_sub_fifo_rd_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(10), .msg = "tm_sch_pri_cshap_sub_fifo_wr_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(11), .msg = "tm_sch_pri_cshap_sub_fifo_rd_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(12), .msg = "tm_sch_port_shap_offset_fifo_wr_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(13), .msg = "tm_sch_port_shap_offset_fifo_rd_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(14), .msg = "tm_sch_pg_pshap_offset_fifo_wr_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(15), .msg = "tm_sch_pg_pshap_offset_fifo_rd_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(16), .msg = "tm_sch_pg_cshap_offset_fifo_wr_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(17), .msg = "tm_sch_pg_cshap_offset_fifo_rd_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(18), .msg = "tm_sch_pri_pshap_offset_fifo_wr_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(19), .msg = "tm_sch_pri_pshap_offset_fifo_rd_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(20), .msg = "tm_sch_pri_cshap_offset_fifo_wr_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(21), .msg = "tm_sch_pri_cshap_offset_fifo_rd_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(22), .msg = "tm_sch_rq_fifo_wr_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(23), .msg = "tm_sch_rq_fifo_rd_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(24), .msg = "tm_sch_nq_fifo_wr_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(25), .msg = "tm_sch_nq_fifo_rd_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(26), .msg = "tm_sch_roce_up_fifo_wr_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(27), .msg = "tm_sch_roce_up_fifo_rd_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(28), .msg = "tm_sch_rcb_byte_fifo_wr_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(29), .msg = "tm_sch_rcb_byte_fifo_rd_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(30), .msg = "tm_sch_ssu_byte_fifo_wr_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(31), .msg = "tm_sch_ssu_byte_fifo_rd_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
{ /* sentinel */ }
};
static const struct hclge_hw_error hclge_qcn_fifo_rint[] = {
- { .int_msk = BIT(0), .msg = "qcn_shap_gp0_sch_fifo_rd_err" },
- { .int_msk = BIT(1), .msg = "qcn_shap_gp0_sch_fifo_wr_err" },
- { .int_msk = BIT(2), .msg = "qcn_shap_gp1_sch_fifo_rd_err" },
- { .int_msk = BIT(3), .msg = "qcn_shap_gp1_sch_fifo_wr_err" },
- { .int_msk = BIT(4), .msg = "qcn_shap_gp2_sch_fifo_rd_err" },
- { .int_msk = BIT(5), .msg = "qcn_shap_gp2_sch_fifo_wr_err" },
- { .int_msk = BIT(6), .msg = "qcn_shap_gp3_sch_fifo_rd_err" },
- { .int_msk = BIT(7), .msg = "qcn_shap_gp3_sch_fifo_wr_err" },
- { .int_msk = BIT(8), .msg = "qcn_shap_gp0_offset_fifo_rd_err" },
- { .int_msk = BIT(9), .msg = "qcn_shap_gp0_offset_fifo_wr_err" },
- { .int_msk = BIT(10), .msg = "qcn_shap_gp1_offset_fifo_rd_err" },
- { .int_msk = BIT(11), .msg = "qcn_shap_gp1_offset_fifo_wr_err" },
- { .int_msk = BIT(12), .msg = "qcn_shap_gp2_offset_fifo_rd_err" },
- { .int_msk = BIT(13), .msg = "qcn_shap_gp2_offset_fifo_wr_err" },
- { .int_msk = BIT(14), .msg = "qcn_shap_gp3_offset_fifo_rd_err" },
- { .int_msk = BIT(15), .msg = "qcn_shap_gp3_offset_fifo_wr_err" },
- { .int_msk = BIT(16), .msg = "qcn_byte_info_fifo_rd_err" },
- { .int_msk = BIT(17), .msg = "qcn_byte_info_fifo_wr_err" },
+ { .int_msk = BIT(0), .msg = "qcn_shap_gp0_sch_fifo_rd_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(1), .msg = "qcn_shap_gp0_sch_fifo_wr_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(2), .msg = "qcn_shap_gp1_sch_fifo_rd_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(3), .msg = "qcn_shap_gp1_sch_fifo_wr_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(4), .msg = "qcn_shap_gp2_sch_fifo_rd_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(5), .msg = "qcn_shap_gp2_sch_fifo_wr_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(6), .msg = "qcn_shap_gp3_sch_fifo_rd_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(7), .msg = "qcn_shap_gp3_sch_fifo_wr_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(8), .msg = "qcn_shap_gp0_offset_fifo_rd_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(9), .msg = "qcn_shap_gp0_offset_fifo_wr_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(10), .msg = "qcn_shap_gp1_offset_fifo_rd_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(11), .msg = "qcn_shap_gp1_offset_fifo_wr_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(12), .msg = "qcn_shap_gp2_offset_fifo_rd_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(13), .msg = "qcn_shap_gp2_offset_fifo_wr_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(14), .msg = "qcn_shap_gp3_offset_fifo_rd_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(15), .msg = "qcn_shap_gp3_offset_fifo_wr_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(16), .msg = "qcn_byte_info_fifo_rd_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(17), .msg = "qcn_byte_info_fifo_wr_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
{ /* sentinel */ }
};
static const struct hclge_hw_error hclge_qcn_ecc_rint[] = {
- { .int_msk = BIT(1), .msg = "qcn_byte_mem_ecc_mbit_err" },
- { .int_msk = BIT(3), .msg = "qcn_time_mem_ecc_mbit_err" },
- { .int_msk = BIT(5), .msg = "qcn_fb_mem_ecc_mbit_err" },
- { .int_msk = BIT(7), .msg = "qcn_link_mem_ecc_mbit_err" },
- { .int_msk = BIT(9), .msg = "qcn_rate_mem_ecc_mbit_err" },
- { .int_msk = BIT(11), .msg = "qcn_tmplt_mem_ecc_mbit_err" },
- { .int_msk = BIT(13), .msg = "qcn_shap_cfg_mem_ecc_mbit_err" },
- { .int_msk = BIT(15), .msg = "qcn_gp0_barrel_mem_ecc_mbit_err" },
- { .int_msk = BIT(17), .msg = "qcn_gp1_barrel_mem_ecc_mbit_err" },
- { .int_msk = BIT(19), .msg = "qcn_gp2_barrel_mem_ecc_mbit_err" },
- { .int_msk = BIT(21), .msg = "qcn_gp3_barral_mem_ecc_mbit_err" },
+ { .int_msk = BIT(1), .msg = "qcn_byte_mem_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(3), .msg = "qcn_time_mem_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(5), .msg = "qcn_fb_mem_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(7), .msg = "qcn_link_mem_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(9), .msg = "qcn_rate_mem_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(11), .msg = "qcn_tmplt_mem_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(13), .msg = "qcn_shap_cfg_mem_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(15), .msg = "qcn_gp0_barrel_mem_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(17), .msg = "qcn_gp1_barrel_mem_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(19), .msg = "qcn_gp2_barrel_mem_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(21), .msg = "qcn_gp3_barral_mem_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
{ /* sentinel */ }
};
static const struct hclge_hw_error hclge_mac_afifo_tnl_int[] = {
- { .int_msk = BIT(0), .msg = "egu_cge_afifo_ecc_1bit_err" },
- { .int_msk = BIT(1), .msg = "egu_cge_afifo_ecc_mbit_err" },
- { .int_msk = BIT(2), .msg = "egu_lge_afifo_ecc_1bit_err" },
- { .int_msk = BIT(3), .msg = "egu_lge_afifo_ecc_mbit_err" },
- { .int_msk = BIT(4), .msg = "cge_igu_afifo_ecc_1bit_err" },
- { .int_msk = BIT(5), .msg = "cge_igu_afifo_ecc_mbit_err" },
- { .int_msk = BIT(6), .msg = "lge_igu_afifo_ecc_1bit_err" },
- { .int_msk = BIT(7), .msg = "lge_igu_afifo_ecc_mbit_err" },
- { .int_msk = BIT(8), .msg = "cge_igu_afifo_overflow_err" },
- { .int_msk = BIT(9), .msg = "lge_igu_afifo_overflow_err" },
- { .int_msk = BIT(10), .msg = "egu_cge_afifo_underrun_err" },
- { .int_msk = BIT(11), .msg = "egu_lge_afifo_underrun_err" },
- { .int_msk = BIT(12), .msg = "egu_ge_afifo_underrun_err" },
- { .int_msk = BIT(13), .msg = "ge_igu_afifo_overflow_err" },
+ { .int_msk = BIT(0), .msg = "egu_cge_afifo_ecc_1bit_err",
+ .reset_level = HNAE3_NONE_RESET },
+ { .int_msk = BIT(1), .msg = "egu_cge_afifo_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(2), .msg = "egu_lge_afifo_ecc_1bit_err",
+ .reset_level = HNAE3_NONE_RESET },
+ { .int_msk = BIT(3), .msg = "egu_lge_afifo_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(4), .msg = "cge_igu_afifo_ecc_1bit_err",
+ .reset_level = HNAE3_NONE_RESET },
+ { .int_msk = BIT(5), .msg = "cge_igu_afifo_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(6), .msg = "lge_igu_afifo_ecc_1bit_err",
+ .reset_level = HNAE3_NONE_RESET },
+ { .int_msk = BIT(7), .msg = "lge_igu_afifo_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(8), .msg = "cge_igu_afifo_overflow_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(9), .msg = "lge_igu_afifo_overflow_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(10), .msg = "egu_cge_afifo_underrun_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(11), .msg = "egu_lge_afifo_underrun_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(12), .msg = "egu_ge_afifo_underrun_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(13), .msg = "ge_igu_afifo_overflow_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
{ /* sentinel */ }
};
static const struct hclge_hw_error hclge_ppu_mpf_abnormal_int_st2[] = {
- { .int_msk = BIT(13), .msg = "rpu_rx_pkt_bit32_ecc_mbit_err" },
- { .int_msk = BIT(14), .msg = "rpu_rx_pkt_bit33_ecc_mbit_err" },
- { .int_msk = BIT(15), .msg = "rpu_rx_pkt_bit34_ecc_mbit_err" },
- { .int_msk = BIT(16), .msg = "rpu_rx_pkt_bit35_ecc_mbit_err" },
- { .int_msk = BIT(17), .msg = "rcb_tx_ring_ecc_mbit_err" },
- { .int_msk = BIT(18), .msg = "rcb_rx_ring_ecc_mbit_err" },
- { .int_msk = BIT(19), .msg = "rcb_tx_fbd_ecc_mbit_err" },
- { .int_msk = BIT(20), .msg = "rcb_rx_ebd_ecc_mbit_err" },
- { .int_msk = BIT(21), .msg = "rcb_tso_info_ecc_mbit_err" },
- { .int_msk = BIT(22), .msg = "rcb_tx_int_info_ecc_mbit_err" },
- { .int_msk = BIT(23), .msg = "rcb_rx_int_info_ecc_mbit_err" },
- { .int_msk = BIT(24), .msg = "tpu_tx_pkt_0_ecc_mbit_err" },
- { .int_msk = BIT(25), .msg = "tpu_tx_pkt_1_ecc_mbit_err" },
- { .int_msk = BIT(26), .msg = "rd_bus_err" },
- { .int_msk = BIT(27), .msg = "wr_bus_err" },
- { .int_msk = BIT(28), .msg = "reg_search_miss" },
- { .int_msk = BIT(29), .msg = "rx_q_search_miss" },
- { .int_msk = BIT(30), .msg = "ooo_ecc_err_detect" },
- { .int_msk = BIT(31), .msg = "ooo_ecc_err_multpl" },
+ { .int_msk = BIT(13), .msg = "rpu_rx_pkt_bit32_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(14), .msg = "rpu_rx_pkt_bit33_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(15), .msg = "rpu_rx_pkt_bit34_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(16), .msg = "rpu_rx_pkt_bit35_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(17), .msg = "rcb_tx_ring_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(18), .msg = "rcb_rx_ring_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(19), .msg = "rcb_tx_fbd_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(20), .msg = "rcb_rx_ebd_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(21), .msg = "rcb_tso_info_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(22), .msg = "rcb_tx_int_info_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(23), .msg = "rcb_rx_int_info_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(24), .msg = "tpu_tx_pkt_0_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(25), .msg = "tpu_tx_pkt_1_ecc_mbit_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(26), .msg = "rd_bus_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(27), .msg = "wr_bus_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(28), .msg = "reg_search_miss",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(29), .msg = "rx_q_search_miss",
+ .reset_level = HNAE3_NONE_RESET },
+ { .int_msk = BIT(30), .msg = "ooo_ecc_err_detect",
+ .reset_level = HNAE3_NONE_RESET },
+ { .int_msk = BIT(31), .msg = "ooo_ecc_err_multpl",
+ .reset_level = HNAE3_GLOBAL_RESET },
{ /* sentinel */ }
};
static const struct hclge_hw_error hclge_ppu_mpf_abnormal_int_st3[] = {
- { .int_msk = BIT(4), .msg = "gro_bd_ecc_mbit_err" },
- { .int_msk = BIT(5), .msg = "gro_context_ecc_mbit_err" },
- { .int_msk = BIT(6), .msg = "rx_stash_cfg_ecc_mbit_err" },
- { .int_msk = BIT(7), .msg = "axi_rd_fbd_ecc_mbit_err" },
+ { .int_msk = BIT(4), .msg = "gro_bd_ecc_mbit_err",
+ .reset_level = HNAE3_CORE_RESET },
+ { .int_msk = BIT(5), .msg = "gro_context_ecc_mbit_err",
+ .reset_level = HNAE3_CORE_RESET },
+ { .int_msk = BIT(6), .msg = "rx_stash_cfg_ecc_mbit_err",
+ .reset_level = HNAE3_CORE_RESET },
+ { .int_msk = BIT(7), .msg = "axi_rd_fbd_ecc_mbit_err",
+ .reset_level = HNAE3_CORE_RESET },
{ /* sentinel */ }
};
static const struct hclge_hw_error hclge_ppu_pf_abnormal_int[] = {
- { .int_msk = BIT(0), .msg = "over_8bd_no_fe" },
- { .int_msk = BIT(1), .msg = "tso_mss_cmp_min_err" },
- { .int_msk = BIT(2), .msg = "tso_mss_cmp_max_err" },
- { .int_msk = BIT(3), .msg = "tx_rd_fbd_poison" },
- { .int_msk = BIT(4), .msg = "rx_rd_ebd_poison" },
- { .int_msk = BIT(5), .msg = "buf_wait_timeout" },
+ { .int_msk = BIT(0), .msg = "over_8bd_no_fe",
+ .reset_level = HNAE3_FUNC_RESET },
+ { .int_msk = BIT(1), .msg = "tso_mss_cmp_min_err",
+ .reset_level = HNAE3_NONE_RESET },
+ { .int_msk = BIT(2), .msg = "tso_mss_cmp_max_err",
+ .reset_level = HNAE3_NONE_RESET },
+ { .int_msk = BIT(3), .msg = "tx_rd_fbd_poison",
+ .reset_level = HNAE3_FUNC_RESET },
+ { .int_msk = BIT(4), .msg = "rx_rd_ebd_poison",
+ .reset_level = HNAE3_FUNC_RESET },
+ { .int_msk = BIT(5), .msg = "buf_wait_timeout",
+ .reset_level = HNAE3_NONE_RESET },
{ /* sentinel */ }
};
static const struct hclge_hw_error hclge_ssu_com_err_int[] = {
- { .int_msk = BIT(0), .msg = "buf_sum_err" },
- { .int_msk = BIT(1), .msg = "ppp_mb_num_err" },
- { .int_msk = BIT(2), .msg = "ppp_mbid_err" },
- { .int_msk = BIT(3), .msg = "ppp_rlt_mac_err" },
- { .int_msk = BIT(4), .msg = "ppp_rlt_host_err" },
- { .int_msk = BIT(5), .msg = "cks_edit_position_err" },
- { .int_msk = BIT(6), .msg = "cks_edit_condition_err" },
- { .int_msk = BIT(7), .msg = "vlan_edit_condition_err" },
- { .int_msk = BIT(8), .msg = "vlan_num_ot_err" },
- { .int_msk = BIT(9), .msg = "vlan_num_in_err" },
+ { .int_msk = BIT(0), .msg = "buf_sum_err",
+ .reset_level = HNAE3_NONE_RESET },
+ { .int_msk = BIT(1), .msg = "ppp_mb_num_err",
+ .reset_level = HNAE3_NONE_RESET },
+ { .int_msk = BIT(2), .msg = "ppp_mbid_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(3), .msg = "ppp_rlt_mac_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(4), .msg = "ppp_rlt_host_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(5), .msg = "cks_edit_position_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(6), .msg = "cks_edit_condition_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(7), .msg = "vlan_edit_condition_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(8), .msg = "vlan_num_ot_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(9), .msg = "vlan_num_in_err",
+ .reset_level = HNAE3_GLOBAL_RESET },
{ /* sentinel */ }
};
#define HCLGE_SSU_MEM_ECC_ERR(x) \
- { .int_msk = BIT(x), .msg = "ssu_mem" #x "_ecc_mbit_err" }
+ { .int_msk = BIT(x), .msg = "ssu_mem" #x "_ecc_mbit_err", \
+ .reset_level = HNAE3_GLOBAL_RESET }
static const struct hclge_hw_error hclge_ssu_mem_ecc_err_int[] = {
HCLGE_SSU_MEM_ECC_ERR(0),
};
static const struct hclge_hw_error hclge_ssu_port_based_err_int[] = {
- { .int_msk = BIT(0), .msg = "roc_pkt_without_key_port" },
- { .int_msk = BIT(1), .msg = "tpu_pkt_without_key_port" },
- { .int_msk = BIT(2), .msg = "igu_pkt_without_key_port" },
- { .int_msk = BIT(3), .msg = "roc_eof_mis_match_port" },
- { .int_msk = BIT(4), .msg = "tpu_eof_mis_match_port" },
- { .int_msk = BIT(5), .msg = "igu_eof_mis_match_port" },
- { .int_msk = BIT(6), .msg = "roc_sof_mis_match_port" },
- { .int_msk = BIT(7), .msg = "tpu_sof_mis_match_port" },
- { .int_msk = BIT(8), .msg = "igu_sof_mis_match_port" },
- { .int_msk = BIT(11), .msg = "ets_rd_int_rx_port" },
- { .int_msk = BIT(12), .msg = "ets_wr_int_rx_port" },
- { .int_msk = BIT(13), .msg = "ets_rd_int_tx_port" },
- { .int_msk = BIT(14), .msg = "ets_wr_int_tx_port" },
+ { .int_msk = BIT(0), .msg = "roc_pkt_without_key_port",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(1), .msg = "tpu_pkt_without_key_port",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(2), .msg = "igu_pkt_without_key_port",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(3), .msg = "roc_eof_mis_match_port",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(4), .msg = "tpu_eof_mis_match_port",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(5), .msg = "igu_eof_mis_match_port",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(6), .msg = "roc_sof_mis_match_port",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(7), .msg = "tpu_sof_mis_match_port",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(8), .msg = "igu_sof_mis_match_port",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(11), .msg = "ets_rd_int_rx_port",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(12), .msg = "ets_wr_int_rx_port",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(13), .msg = "ets_rd_int_tx_port",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(14), .msg = "ets_wr_int_tx_port",
+ .reset_level = HNAE3_GLOBAL_RESET },
{ /* sentinel */ }
};
static const struct hclge_hw_error hclge_ssu_fifo_overflow_int[] = {
- { .int_msk = BIT(0), .msg = "ig_mac_inf_int" },
- { .int_msk = BIT(1), .msg = "ig_host_inf_int" },
- { .int_msk = BIT(2), .msg = "ig_roc_buf_int" },
- { .int_msk = BIT(3), .msg = "ig_host_data_fifo_int" },
- { .int_msk = BIT(4), .msg = "ig_host_key_fifo_int" },
- { .int_msk = BIT(5), .msg = "tx_qcn_fifo_int" },
- { .int_msk = BIT(6), .msg = "rx_qcn_fifo_int" },
- { .int_msk = BIT(7), .msg = "tx_pf_rd_fifo_int" },
- { .int_msk = BIT(8), .msg = "rx_pf_rd_fifo_int" },
- { .int_msk = BIT(9), .msg = "qm_eof_fifo_int" },
- { .int_msk = BIT(10), .msg = "mb_rlt_fifo_int" },
- { .int_msk = BIT(11), .msg = "dup_uncopy_fifo_int" },
- { .int_msk = BIT(12), .msg = "dup_cnt_rd_fifo_int" },
- { .int_msk = BIT(13), .msg = "dup_cnt_drop_fifo_int" },
- { .int_msk = BIT(14), .msg = "dup_cnt_wrb_fifo_int" },
- { .int_msk = BIT(15), .msg = "host_cmd_fifo_int" },
- { .int_msk = BIT(16), .msg = "mac_cmd_fifo_int" },
- { .int_msk = BIT(17), .msg = "host_cmd_bitmap_empty_int" },
- { .int_msk = BIT(18), .msg = "mac_cmd_bitmap_empty_int" },
- { .int_msk = BIT(19), .msg = "dup_bitmap_empty_int" },
- { .int_msk = BIT(20), .msg = "out_queue_bitmap_empty_int" },
- { .int_msk = BIT(21), .msg = "bank2_bitmap_empty_int" },
- { .int_msk = BIT(22), .msg = "bank1_bitmap_empty_int" },
- { .int_msk = BIT(23), .msg = "bank0_bitmap_empty_int" },
+ { .int_msk = BIT(0), .msg = "ig_mac_inf_int",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(1), .msg = "ig_host_inf_int",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(2), .msg = "ig_roc_buf_int",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(3), .msg = "ig_host_data_fifo_int",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(4), .msg = "ig_host_key_fifo_int",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(5), .msg = "tx_qcn_fifo_int",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(6), .msg = "rx_qcn_fifo_int",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(7), .msg = "tx_pf_rd_fifo_int",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(8), .msg = "rx_pf_rd_fifo_int",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(9), .msg = "qm_eof_fifo_int",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(10), .msg = "mb_rlt_fifo_int",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(11), .msg = "dup_uncopy_fifo_int",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(12), .msg = "dup_cnt_rd_fifo_int",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(13), .msg = "dup_cnt_drop_fifo_int",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(14), .msg = "dup_cnt_wrb_fifo_int",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(15), .msg = "host_cmd_fifo_int",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(16), .msg = "mac_cmd_fifo_int",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(17), .msg = "host_cmd_bitmap_empty_int",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(18), .msg = "mac_cmd_bitmap_empty_int",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(19), .msg = "dup_bitmap_empty_int",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(20), .msg = "out_queue_bitmap_empty_int",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(21), .msg = "bank2_bitmap_empty_int",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(22), .msg = "bank1_bitmap_empty_int",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(23), .msg = "bank0_bitmap_empty_int",
+ .reset_level = HNAE3_GLOBAL_RESET },
{ /* sentinel */ }
};
static const struct hclge_hw_error hclge_ssu_ets_tcg_int[] = {
- { .int_msk = BIT(0), .msg = "ets_rd_int_rx_tcg" },
- { .int_msk = BIT(1), .msg = "ets_wr_int_rx_tcg" },
- { .int_msk = BIT(2), .msg = "ets_rd_int_tx_tcg" },
- { .int_msk = BIT(3), .msg = "ets_wr_int_tx_tcg" },
+ { .int_msk = BIT(0), .msg = "ets_rd_int_rx_tcg",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(1), .msg = "ets_wr_int_rx_tcg",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(2), .msg = "ets_rd_int_tx_tcg",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(3), .msg = "ets_wr_int_tx_tcg",
+ .reset_level = HNAE3_GLOBAL_RESET },
{ /* sentinel */ }
};
static const struct hclge_hw_error hclge_ssu_port_based_pf_int[] = {
- { .int_msk = BIT(0), .msg = "roc_pkt_without_key_port" },
- { .int_msk = BIT(9), .msg = "low_water_line_err_port" },
- { .int_msk = BIT(10), .msg = "hi_water_line_err_port" },
+ { .int_msk = BIT(0), .msg = "roc_pkt_without_key_port",
+ .reset_level = HNAE3_GLOBAL_RESET },
+ { .int_msk = BIT(9), .msg = "low_water_line_err_port",
+ .reset_level = HNAE3_NONE_RESET },
+ { .int_msk = BIT(10), .msg = "hi_water_line_err_port",
+ .reset_level = HNAE3_GLOBAL_RESET },
{ /* sentinel */ }
};
{ /* sentinel */ }
};
-static void hclge_log_error(struct device *dev, char *reg,
- const struct hclge_hw_error *err,
- u32 err_sts)
+static enum hnae3_reset_type hclge_log_error(struct device *dev, char *reg,
+ const struct hclge_hw_error *err,
+ u32 err_sts)
{
+ enum hnae3_reset_type reset_level = HNAE3_FUNC_RESET;
+ bool need_reset = false;
+
while (err->msg) {
- if (err->int_msk & err_sts)
+ if (err->int_msk & err_sts) {
dev_warn(dev, "%s %s found [error status=0x%x]\n",
reg, err->msg, err_sts);
+ if (err->reset_level != HNAE3_NONE_RESET &&
+ err->reset_level >= reset_level) {
+ reset_level = err->reset_level;
+ need_reset = true;
+ }
+ }
err++;
}
+ if (need_reset)
+ return reset_level;
+ else
+ return HNAE3_NONE_RESET;
}
/* hclge_cmd_query_error: read the error information
int num)
{
struct hnae3_ae_dev *ae_dev = hdev->ae_dev;
+ enum hnae3_reset_type reset_level;
struct device *dev = &hdev->pdev->dev;
__le32 *desc_data;
u32 status;
/* log HNS common errors */
status = le32_to_cpu(desc[0].data[0]);
if (status) {
- hclge_log_error(dev, "IMP_TCM_ECC_INT_STS",
- &hclge_imp_tcm_ecc_int[0], status);
- HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_GLOBAL_RESET);
+ reset_level = hclge_log_error(dev, "IMP_TCM_ECC_INT_STS",
+ &hclge_imp_tcm_ecc_int[0],
+ status);
+ HCLGE_SET_DEFAULT_RESET_REQUEST(reset_level);
}
status = le32_to_cpu(desc[0].data[1]);
if (status) {
- hclge_log_error(dev, "CMDQ_MEM_ECC_INT_STS",
- &hclge_cmdq_nic_mem_ecc_int[0], status);
- HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_GLOBAL_RESET);
+ reset_level = hclge_log_error(dev, "CMDQ_MEM_ECC_INT_STS",
+ &hclge_cmdq_nic_mem_ecc_int[0],
+ status);
+ HCLGE_SET_DEFAULT_RESET_REQUEST(reset_level);
}
if ((le32_to_cpu(desc[0].data[2])) & BIT(0)) {
dev_warn(dev, "imp_rd_data_poison_err found\n");
- HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_GLOBAL_RESET);
+ HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_NONE_RESET);
}
status = le32_to_cpu(desc[0].data[3]);
if (status) {
- hclge_log_error(dev, "TQP_INT_ECC_INT_STS",
- &hclge_tqp_int_ecc_int[0], status);
- HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
+ reset_level = hclge_log_error(dev, "TQP_INT_ECC_INT_STS",
+ &hclge_tqp_int_ecc_int[0],
+ status);
+ HCLGE_SET_DEFAULT_RESET_REQUEST(reset_level);
}
status = le32_to_cpu(desc[0].data[4]);
if (status) {
- hclge_log_error(dev, "MSIX_ECC_INT_STS",
- &hclge_msix_sram_ecc_int[0], status);
- HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
+ reset_level = hclge_log_error(dev, "MSIX_ECC_INT_STS",
+ &hclge_msix_sram_ecc_int[0],
+ status);
+ HCLGE_SET_DEFAULT_RESET_REQUEST(reset_level);
}
/* log SSU(Storage Switch Unit) errors */
desc_data = (__le32 *)&desc[2];
status = le32_to_cpu(*(desc_data + 2));
if (status) {
- hclge_log_error(dev, "SSU_ECC_MULTI_BIT_INT_0",
- &hclge_ssu_mem_ecc_err_int[0], status);
- HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
+ reset_level = hclge_log_error(dev, "SSU_ECC_MULTI_BIT_INT_0",
+ &hclge_ssu_mem_ecc_err_int[0],
+ status);
+ HCLGE_SET_DEFAULT_RESET_REQUEST(reset_level);
}
status = le32_to_cpu(*(desc_data + 3)) & BIT(0);
if (status) {
dev_warn(dev, "SSU_ECC_MULTI_BIT_INT_1 ssu_mem32_ecc_mbit_err found [error status=0x%x]\n",
status);
- HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
+ HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_GLOBAL_RESET);
}
status = le32_to_cpu(*(desc_data + 4)) & HCLGE_SSU_COMMON_ERR_INT_MASK;
if (status) {
- hclge_log_error(dev, "SSU_COMMON_ERR_INT",
- &hclge_ssu_com_err_int[0], status);
- HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_GLOBAL_RESET);
+ reset_level = hclge_log_error(dev, "SSU_COMMON_ERR_INT",
+ &hclge_ssu_com_err_int[0],
+ status);
+ HCLGE_SET_DEFAULT_RESET_REQUEST(reset_level);
}
/* log IGU(Ingress Unit) errors */
desc_data = (__le32 *)&desc[3];
status = le32_to_cpu(*desc_data) & HCLGE_IGU_INT_MASK;
- if (status)
- hclge_log_error(dev, "IGU_INT_STS",
- &hclge_igu_int[0], status);
+ if (status) {
+ reset_level = hclge_log_error(dev, "IGU_INT_STS",
+ &hclge_igu_int[0], status);
+ HCLGE_SET_DEFAULT_RESET_REQUEST(reset_level);
+ }
/* log PPP(Programmable Packet Process) errors */
desc_data = (__le32 *)&desc[4];
status = le32_to_cpu(*(desc_data + 1));
- if (status)
- hclge_log_error(dev, "PPP_MPF_ABNORMAL_INT_ST1",
- &hclge_ppp_mpf_abnormal_int_st1[0], status);
+ if (status) {
+ reset_level =
+ hclge_log_error(dev, "PPP_MPF_ABNORMAL_INT_ST1",
+ &hclge_ppp_mpf_abnormal_int_st1[0],
+ status);
+ HCLGE_SET_DEFAULT_RESET_REQUEST(reset_level);
+ }
status = le32_to_cpu(*(desc_data + 3)) & HCLGE_PPP_MPF_INT_ST3_MASK;
- if (status)
- hclge_log_error(dev, "PPP_MPF_ABNORMAL_INT_ST3",
- &hclge_ppp_mpf_abnormal_int_st3[0], status);
+ if (status) {
+ reset_level =
+ hclge_log_error(dev, "PPP_MPF_ABNORMAL_INT_ST3",
+ &hclge_ppp_mpf_abnormal_int_st3[0],
+ status);
+ HCLGE_SET_DEFAULT_RESET_REQUEST(reset_level);
+ }
/* log PPU(RCB) errors */
desc_data = (__le32 *)&desc[5];
if (status) {
dev_warn(dev, "PPU_MPF_ABNORMAL_INT_ST1 %s found\n",
"rpu_rx_pkt_ecc_mbit_err");
- HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
+ HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_GLOBAL_RESET);
}
status = le32_to_cpu(*(desc_data + 2));
if (status) {
- hclge_log_error(dev, "PPU_MPF_ABNORMAL_INT_ST2",
- &hclge_ppu_mpf_abnormal_int_st2[0], status);
- HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
+ reset_level =
+ hclge_log_error(dev, "PPU_MPF_ABNORMAL_INT_ST2",
+ &hclge_ppu_mpf_abnormal_int_st2[0],
+ status);
+ HCLGE_SET_DEFAULT_RESET_REQUEST(reset_level);
}
status = le32_to_cpu(*(desc_data + 3)) & HCLGE_PPU_MPF_INT_ST3_MASK;
if (status) {
- hclge_log_error(dev, "PPU_MPF_ABNORMAL_INT_ST3",
- &hclge_ppu_mpf_abnormal_int_st3[0], status);
- HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
+ reset_level =
+ hclge_log_error(dev, "PPU_MPF_ABNORMAL_INT_ST3",
+ &hclge_ppu_mpf_abnormal_int_st3[0],
+ status);
+ HCLGE_SET_DEFAULT_RESET_REQUEST(reset_level);
}
/* log TM(Traffic Manager) errors */
desc_data = (__le32 *)&desc[6];
status = le32_to_cpu(*desc_data);
if (status) {
- hclge_log_error(dev, "TM_SCH_RINT",
- &hclge_tm_sch_rint[0], status);
- HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
+ reset_level = hclge_log_error(dev, "TM_SCH_RINT",
+ &hclge_tm_sch_rint[0], status);
+ HCLGE_SET_DEFAULT_RESET_REQUEST(reset_level);
}
/* log QCN(Quantized Congestion Control) errors */
desc_data = (__le32 *)&desc[7];
status = le32_to_cpu(*desc_data) & HCLGE_QCN_FIFO_INT_MASK;
if (status) {
- hclge_log_error(dev, "QCN_FIFO_RINT",
- &hclge_qcn_fifo_rint[0], status);
- HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
+ reset_level = hclge_log_error(dev, "QCN_FIFO_RINT",
+ &hclge_qcn_fifo_rint[0], status);
+ HCLGE_SET_DEFAULT_RESET_REQUEST(reset_level);
}
status = le32_to_cpu(*(desc_data + 1)) & HCLGE_QCN_ECC_INT_MASK;
if (status) {
- hclge_log_error(dev, "QCN_ECC_RINT",
- &hclge_qcn_ecc_rint[0], status);
- HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
+ reset_level = hclge_log_error(dev, "QCN_ECC_RINT",
+ &hclge_qcn_ecc_rint[0],
+ status);
+ HCLGE_SET_DEFAULT_RESET_REQUEST(reset_level);
}
/* log NCSI errors */
desc_data = (__le32 *)&desc[9];
status = le32_to_cpu(*desc_data) & HCLGE_NCSI_ECC_INT_MASK;
if (status) {
- hclge_log_error(dev, "NCSI_ECC_INT_RPT",
- &hclge_ncsi_err_int[0], status);
- HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
+ reset_level = hclge_log_error(dev, "NCSI_ECC_INT_RPT",
+ &hclge_ncsi_err_int[0], status);
+ HCLGE_SET_DEFAULT_RESET_REQUEST(reset_level);
}
/* clear all main PF RAS errors */
{
struct hnae3_ae_dev *ae_dev = hdev->ae_dev;
struct device *dev = &hdev->pdev->dev;
+ enum hnae3_reset_type reset_level;
__le32 *desc_data;
u32 status;
int ret;
/* log SSU(Storage Switch Unit) errors */
status = le32_to_cpu(desc[0].data[0]);
if (status) {
- hclge_log_error(dev, "SSU_PORT_BASED_ERR_INT",
- &hclge_ssu_port_based_err_int[0], status);
- HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_GLOBAL_RESET);
+ reset_level = hclge_log_error(dev, "SSU_PORT_BASED_ERR_INT",
+ &hclge_ssu_port_based_err_int[0],
+ status);
+ HCLGE_SET_DEFAULT_RESET_REQUEST(reset_level);
}
status = le32_to_cpu(desc[0].data[1]);
if (status) {
- hclge_log_error(dev, "SSU_FIFO_OVERFLOW_INT",
- &hclge_ssu_fifo_overflow_int[0], status);
- HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_GLOBAL_RESET);
+ reset_level = hclge_log_error(dev, "SSU_FIFO_OVERFLOW_INT",
+ &hclge_ssu_fifo_overflow_int[0],
+ status);
+ HCLGE_SET_DEFAULT_RESET_REQUEST(reset_level);
}
status = le32_to_cpu(desc[0].data[2]);
if (status) {
- hclge_log_error(dev, "SSU_ETS_TCG_INT",
- &hclge_ssu_ets_tcg_int[0], status);
- HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_GLOBAL_RESET);
+ reset_level = hclge_log_error(dev, "SSU_ETS_TCG_INT",
+ &hclge_ssu_ets_tcg_int[0],
+ status);
+ HCLGE_SET_DEFAULT_RESET_REQUEST(reset_level);
}
/* log IGU(Ingress Unit) EGU(Egress Unit) TNL errors */
desc_data = (__le32 *)&desc[1];
status = le32_to_cpu(*desc_data) & HCLGE_IGU_EGU_TNL_INT_MASK;
- if (status)
- hclge_log_error(dev, "IGU_EGU_TNL_INT_STS",
- &hclge_igu_egu_tnl_int[0], status);
+ if (status) {
+ reset_level = hclge_log_error(dev, "IGU_EGU_TNL_INT_STS",
+ &hclge_igu_egu_tnl_int[0],
+ status);
+ HCLGE_SET_DEFAULT_RESET_REQUEST(reset_level);
+ }
/* log PPU(RCB) errors */
desc_data = (__le32 *)&desc[3];
status = le32_to_cpu(*desc_data) & HCLGE_PPU_PF_INT_RAS_MASK;
- if (status)
- hclge_log_error(dev, "PPU_PF_ABNORMAL_INT_ST0",
- &hclge_ppu_pf_abnormal_int[0], status);
+ if (status) {
+ reset_level = hclge_log_error(dev, "PPU_PF_ABNORMAL_INT_ST0",
+ &hclge_ppu_pf_abnormal_int[0],
+ status);
+ HCLGE_SET_DEFAULT_RESET_REQUEST(reset_level);
+ }
/* clear all PF RAS errors */
hclge_cmd_reuse_desc(&desc[0], false);
{
struct device *dev = &hdev->pdev->dev;
u32 mpf_bd_num, pf_bd_num, bd_num;
+ enum hnae3_reset_type reset_level;
struct hclge_desc desc_bd;
struct hclge_desc *desc;
__le32 *desc_data;
- int ret = 0;
u32 status;
-
- /* set default handling */
- set_bit(HNAE3_FUNC_RESET, reset_requests);
+ int ret;
/* query the number of bds for the MSIx int status */
hclge_cmd_setup_basic_desc(&desc_bd, HCLGE_QUERY_MSIX_INT_STS_BD_NUM,
desc_data = (__le32 *)&desc[1];
status = le32_to_cpu(*desc_data);
if (status) {
- hclge_log_error(dev, "MAC_AFIFO_TNL_INT_R",
- &hclge_mac_afifo_tnl_int[0], status);
- set_bit(HNAE3_GLOBAL_RESET, reset_requests);
+ reset_level = hclge_log_error(dev, "MAC_AFIFO_TNL_INT_R",
+ &hclge_mac_afifo_tnl_int[0],
+ status);
+ set_bit(reset_level, reset_requests);
}
/* log PPU(RCB) MPF errors */
status = le32_to_cpu(*(desc_data + 2)) &
HCLGE_PPU_MPF_INT_ST2_MSIX_MASK;
if (status) {
- hclge_log_error(dev, "PPU_MPF_ABNORMAL_INT_ST2",
- &hclge_ppu_mpf_abnormal_int_st2[0], status);
- set_bit(HNAE3_CORE_RESET, reset_requests);
+ reset_level =
+ hclge_log_error(dev, "PPU_MPF_ABNORMAL_INT_ST2",
+ &hclge_ppu_mpf_abnormal_int_st2[0],
+ status);
+ set_bit(reset_level, reset_requests);
}
/* clear all main PF MSIx errors */
/* log SSU PF errors */
status = le32_to_cpu(desc[0].data[0]) & HCLGE_SSU_PORT_INT_MSIX_MASK;
if (status) {
- hclge_log_error(dev, "SSU_PORT_BASED_ERR_INT",
- &hclge_ssu_port_based_pf_int[0], status);
- set_bit(HNAE3_GLOBAL_RESET, reset_requests);
+ reset_level = hclge_log_error(dev, "SSU_PORT_BASED_ERR_INT",
+ &hclge_ssu_port_based_pf_int[0],
+ status);
+ set_bit(reset_level, reset_requests);
}
/* read and log PPP PF errors */
desc_data = (__le32 *)&desc[2];
status = le32_to_cpu(*desc_data);
- if (status)
- hclge_log_error(dev, "PPP_PF_ABNORMAL_INT_ST0",
- &hclge_ppp_pf_abnormal_int[0], status);
+ if (status) {
+ reset_level = hclge_log_error(dev, "PPP_PF_ABNORMAL_INT_ST0",
+ &hclge_ppp_pf_abnormal_int[0],
+ status);
+ set_bit(reset_level, reset_requests);
+ }
/* log PPU(RCB) PF errors */
desc_data = (__le32 *)&desc[3];
status = le32_to_cpu(*desc_data) & HCLGE_PPU_PF_INT_MSIX_MASK;
- if (status)
- hclge_log_error(dev, "PPU_PF_ABNORMAL_INT_ST",
- &hclge_ppu_pf_abnormal_int[0], status);
+ if (status) {
+ reset_level = hclge_log_error(dev, "PPU_PF_ABNORMAL_INT_ST",
+ &hclge_ppu_pf_abnormal_int[0],
+ status);
+ set_bit(reset_level, reset_requests);
+ }
/* clear all PF MSIx errors */
hclge_cmd_reuse_desc(&desc[0], false);
struct hclge_hw_error {
u32 int_msk;
const char *msg;
+ enum hnae3_reset_type reset_level;
};
int hclge_hw_error_set_state(struct hclge_dev *hdev, bool state);
#include <linux/pci.h>
#include <linux/platform_device.h>
#include <linux/if_vlan.h>
+#include <linux/crash_dump.h>
#include <net/rtnetlink.h>
#include "hclge_cmd.h"
#include "hclge_dcb.h"
static int hclge_set_mac_mtu(struct hclge_dev *hdev, int new_mps);
static int hclge_init_vlan_config(struct hclge_dev *hdev);
static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev);
+static bool hclge_get_hw_reset_stat(struct hnae3_handle *handle);
static int hclge_set_umv_space(struct hclge_dev *hdev, u16 space_size,
u16 *allocated_size, bool is_alloc);
return ret;
}
+static void hclge_init_kdump_kernel_config(struct hclge_dev *hdev)
+{
+#define HCLGE_MIN_TX_DESC 64
+#define HCLGE_MIN_RX_DESC 64
+
+ if (!is_kdump_kernel())
+ return;
+
+ dev_info(&hdev->pdev->dev,
+ "Running kdump kernel. Using minimal resources\n");
+
+ /* minimal queue pairs equals to the number of vports */
+ hdev->num_tqps = hdev->num_vmdq_vport + hdev->num_req_vfs + 1;
+ hdev->num_tx_desc = HCLGE_MIN_TX_DESC;
+ hdev->num_rx_desc = HCLGE_MIN_RX_DESC;
+}
+
static int hclge_configure(struct hclge_dev *hdev)
{
struct hclge_cfg cfg;
hdev->tx_sch_mode = HCLGE_FLAG_TC_BASE_SCH_MODE;
+ hclge_init_kdump_kernel_config(hdev);
+
return ret;
}
vport->back = hdev;
vport->vport_id = i;
vport->mps = HCLGE_MAC_DEFAULT_FRAME;
+ vport->port_base_vlan_cfg.state = HNAE3_PORT_BASE_VLAN_DISABLE;
+ vport->rxvlan_cfg.rx_vlan_offload_en = true;
INIT_LIST_HEAD(&vport->vlan_list);
INIT_LIST_HEAD(&vport->uc_mac_list);
INIT_LIST_HEAD(&vport->mc_mac_list);
return ret;
}
-static int hclge_get_tc_num(struct hclge_dev *hdev)
+static u32 hclge_get_tc_num(struct hclge_dev *hdev)
{
int i, cnt = 0;
return cnt;
}
-static int hclge_get_pfc_enalbe_num(struct hclge_dev *hdev)
-{
- int i, cnt = 0;
-
- for (i = 0; i < HCLGE_MAX_TC_NUM; i++)
- if (hdev->hw_tc_map & BIT(i) &&
- hdev->tm_info.hw_pfc_map & BIT(i))
- cnt++;
- return cnt;
-}
-
/* Get the number of pfc enabled TCs, which have private buffer */
static int hclge_get_pfc_priv_num(struct hclge_dev *hdev,
struct hclge_pkt_buf_alloc *buf_alloc)
struct hclge_pkt_buf_alloc *buf_alloc,
u32 rx_all)
{
- u32 shared_buf_min, shared_buf_tc, shared_std;
- int tc_num, pfc_enable_num;
+ u32 shared_buf_min, shared_buf_tc, shared_std, hi_thrd, lo_thrd;
+ u32 tc_num = hclge_get_tc_num(hdev);
u32 shared_buf, aligned_mps;
u32 rx_priv;
int i;
- tc_num = hclge_get_tc_num(hdev);
- pfc_enable_num = hclge_get_pfc_enalbe_num(hdev);
aligned_mps = roundup(hdev->mps, HCLGE_BUF_SIZE_UNIT);
if (hnae3_dev_dcb_supported(hdev))
shared_buf_min = aligned_mps + HCLGE_NON_DCB_ADDITIONAL_BUF
+ hdev->dv_buf_size;
- shared_buf_tc = pfc_enable_num * aligned_mps +
- (tc_num - pfc_enable_num) * aligned_mps / 2 +
- aligned_mps;
+ shared_buf_tc = tc_num * aligned_mps + aligned_mps;
shared_std = roundup(max_t(u32, shared_buf_min, shared_buf_tc),
HCLGE_BUF_SIZE_UNIT);
} else {
buf_alloc->s_buf.self.high = aligned_mps +
HCLGE_NON_DCB_ADDITIONAL_BUF;
- buf_alloc->s_buf.self.low =
- roundup(aligned_mps / 2, HCLGE_BUF_SIZE_UNIT);
+ buf_alloc->s_buf.self.low = aligned_mps;
+ }
+
+ if (hnae3_dev_dcb_supported(hdev)) {
+ if (tc_num)
+ hi_thrd = (shared_buf - hdev->dv_buf_size) / tc_num;
+ else
+ hi_thrd = shared_buf - hdev->dv_buf_size;
+
+ hi_thrd = max_t(u32, hi_thrd, 2 * aligned_mps);
+ hi_thrd = rounddown(hi_thrd, HCLGE_BUF_SIZE_UNIT);
+ lo_thrd = hi_thrd - aligned_mps / 2;
+ } else {
+ hi_thrd = aligned_mps + HCLGE_NON_DCB_ADDITIONAL_BUF;
+ lo_thrd = aligned_mps;
}
for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
- if ((hdev->hw_tc_map & BIT(i)) &&
- (hdev->tm_info.hw_pfc_map & BIT(i))) {
- buf_alloc->s_buf.tc_thrd[i].low = aligned_mps;
- buf_alloc->s_buf.tc_thrd[i].high = 2 * aligned_mps;
- } else {
- buf_alloc->s_buf.tc_thrd[i].low = 0;
- buf_alloc->s_buf.tc_thrd[i].high = aligned_mps;
- }
+ buf_alloc->s_buf.tc_thrd[i].low = lo_thrd;
+ buf_alloc->s_buf.tc_thrd[i].high = hi_thrd;
}
return true;
static void hclge_mbx_task_schedule(struct hclge_dev *hdev)
{
- if (!test_and_set_bit(HCLGE_STATE_MBX_SERVICE_SCHED, &hdev->state))
+ if (!test_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state) &&
+ !test_and_set_bit(HCLGE_STATE_MBX_SERVICE_SCHED, &hdev->state))
schedule_work(&hdev->mbx_service_task);
}
return ret;
}
- if (!reset)
+ if (!reset || !test_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state))
continue;
/* Inform VF to process the reset.
static void hclge_do_reset(struct hclge_dev *hdev)
{
+ struct hnae3_handle *handle = &hdev->vport[0].nic;
struct pci_dev *pdev = hdev->pdev;
u32 val;
+ if (hclge_get_hw_reset_stat(handle)) {
+ dev_info(&pdev->dev, "Hardware reset not finish\n");
+ dev_info(&pdev->dev, "func_rst_reg:0x%x, global_rst_reg:0x%x\n",
+ hclge_read_dev(&hdev->hw, HCLGE_FUN_RST_ING),
+ hclge_read_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG));
+ return;
+ }
+
switch (hdev->reset_type) {
case HNAE3_GLOBAL_RESET:
val = hclge_read_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG);
clear_bit(HNAE3_FLR_RESET, addr);
}
+ if (hdev->reset_type != HNAE3_NONE_RESET &&
+ rst_level < hdev->reset_type)
+ return HNAE3_NONE_RESET;
+
return rst_level;
}
hdev->last_reset_time = jiffies;
hdev->reset_fail_cnt = 0;
ae_dev->reset_type = HNAE3_NONE_RESET;
+ del_timer(&hdev->reset_timer);
return;
}
/* check if we just hit the duplicate */
- if (!ret)
- ret = -EINVAL;
+ if (!ret) {
+ dev_warn(&hdev->pdev->dev, "VF %d mac(%pM) exists\n",
+ vport->vport_id, addr);
+ return 0;
+ }
dev_err(&hdev->pdev->dev,
"PF failed to add unicast entry(%pM) in the MAC table\n",
return -EINVAL;
}
- if (!is_first && hclge_rm_uc_addr(handle, hdev->hw.mac.mac_addr))
+ if ((!is_first || is_kdump_kernel()) &&
+ hclge_rm_uc_addr(handle, hdev->hw.mac.mac_addr))
dev_warn(&hdev->pdev->dev,
"remove old uc mac address fail.\n");
return ret;
}
-int hclge_set_vlan_filter(struct hnae3_handle *handle, __be16 proto,
- u16 vlan_id, bool is_kill)
-{
- struct hclge_vport *vport = hclge_get_vport(handle);
- struct hclge_dev *hdev = vport->back;
-
- return hclge_set_vlan_filter_hw(hdev, proto, vport->vport_id, vlan_id,
- 0, is_kill);
-}
-
-static int hclge_set_vf_vlan_filter(struct hnae3_handle *handle, int vfid,
- u16 vlan, u8 qos, __be16 proto)
-{
- struct hclge_vport *vport = hclge_get_vport(handle);
- struct hclge_dev *hdev = vport->back;
-
- if ((vfid >= hdev->num_alloc_vfs) || (vlan > 4095) || (qos > 7))
- return -EINVAL;
- if (proto != htons(ETH_P_8021Q))
- return -EPROTONOSUPPORT;
-
- return hclge_set_vlan_filter_hw(hdev, proto, vfid, vlan, qos, false);
-}
-
static int hclge_set_vlan_tx_offload_cfg(struct hclge_vport *vport)
{
struct hclge_tx_vtag_cfg *vcfg = &vport->txvlan_cfg;
return status;
}
+static int hclge_vlan_offload_cfg(struct hclge_vport *vport,
+ u16 port_base_vlan_state,
+ u16 vlan_tag)
+{
+ int ret;
+
+ if (port_base_vlan_state == HNAE3_PORT_BASE_VLAN_DISABLE) {
+ vport->txvlan_cfg.accept_tag1 = true;
+ vport->txvlan_cfg.insert_tag1_en = false;
+ vport->txvlan_cfg.default_tag1 = 0;
+ } else {
+ vport->txvlan_cfg.accept_tag1 = false;
+ vport->txvlan_cfg.insert_tag1_en = true;
+ vport->txvlan_cfg.default_tag1 = vlan_tag;
+ }
+
+ vport->txvlan_cfg.accept_untag1 = true;
+
+ /* accept_tag2 and accept_untag2 are not supported on
+ * pdev revision(0x20), new revision support them,
+ * this two fields can not be configured by user.
+ */
+ vport->txvlan_cfg.accept_tag2 = true;
+ vport->txvlan_cfg.accept_untag2 = true;
+ vport->txvlan_cfg.insert_tag2_en = false;
+ vport->txvlan_cfg.default_tag2 = 0;
+
+ if (port_base_vlan_state == HNAE3_PORT_BASE_VLAN_DISABLE) {
+ vport->rxvlan_cfg.strip_tag1_en = false;
+ vport->rxvlan_cfg.strip_tag2_en =
+ vport->rxvlan_cfg.rx_vlan_offload_en;
+ } else {
+ vport->rxvlan_cfg.strip_tag1_en =
+ vport->rxvlan_cfg.rx_vlan_offload_en;
+ vport->rxvlan_cfg.strip_tag2_en = true;
+ }
+ vport->rxvlan_cfg.vlan1_vlan_prionly = false;
+ vport->rxvlan_cfg.vlan2_vlan_prionly = false;
+
+ ret = hclge_set_vlan_tx_offload_cfg(vport);
+ if (ret)
+ return ret;
+
+ return hclge_set_vlan_rx_offload_cfg(vport);
+}
+
static int hclge_set_vlan_protocol_type(struct hclge_dev *hdev)
{
struct hclge_rx_vlan_type_cfg_cmd *rx_req;
return ret;
for (i = 0; i < hdev->num_alloc_vport; i++) {
- vport = &hdev->vport[i];
- vport->txvlan_cfg.accept_tag1 = true;
- vport->txvlan_cfg.accept_untag1 = true;
+ u16 vlan_tag;
- /* accept_tag2 and accept_untag2 are not supported on
- * pdev revision(0x20), new revision support them. The
- * value of this two fields will not return error when driver
- * send command to fireware in revision(0x20).
- * This two fields can not configured by user.
- */
- vport->txvlan_cfg.accept_tag2 = true;
- vport->txvlan_cfg.accept_untag2 = true;
-
- vport->txvlan_cfg.insert_tag1_en = false;
- vport->txvlan_cfg.insert_tag2_en = false;
- vport->txvlan_cfg.default_tag1 = 0;
- vport->txvlan_cfg.default_tag2 = 0;
-
- ret = hclge_set_vlan_tx_offload_cfg(vport);
- if (ret)
- return ret;
-
- vport->rxvlan_cfg.strip_tag1_en = false;
- vport->rxvlan_cfg.strip_tag2_en = true;
- vport->rxvlan_cfg.vlan1_vlan_prionly = false;
- vport->rxvlan_cfg.vlan2_vlan_prionly = false;
+ vport = &hdev->vport[i];
+ vlan_tag = vport->port_base_vlan_cfg.vlan_info.vlan_tag;
- ret = hclge_set_vlan_rx_offload_cfg(vport);
+ ret = hclge_vlan_offload_cfg(vport,
+ vport->port_base_vlan_cfg.state,
+ vlan_tag);
if (ret)
return ret;
}
return hclge_set_vlan_filter(handle, htons(ETH_P_8021Q), 0, false);
}
-void hclge_add_vport_vlan_table(struct hclge_vport *vport, u16 vlan_id)
+static void hclge_add_vport_vlan_table(struct hclge_vport *vport, u16 vlan_id,
+ bool writen_to_tbl)
{
struct hclge_vport_vlan_cfg *vlan;
if (!vlan)
return;
- vlan->hd_tbl_status = true;
+ vlan->hd_tbl_status = writen_to_tbl;
vlan->vlan_id = vlan_id;
list_add_tail(&vlan->node, &vport->vlan_list);
}
-void hclge_rm_vport_vlan_table(struct hclge_vport *vport, u16 vlan_id,
- bool is_write_tbl)
+static int hclge_add_vport_all_vlan_table(struct hclge_vport *vport)
+{
+ struct hclge_vport_vlan_cfg *vlan, *tmp;
+ struct hclge_dev *hdev = vport->back;
+ int ret;
+
+ list_for_each_entry_safe(vlan, tmp, &vport->vlan_list, node) {
+ if (!vlan->hd_tbl_status) {
+ ret = hclge_set_vlan_filter_hw(hdev, htons(ETH_P_8021Q),
+ vport->vport_id,
+ vlan->vlan_id, 0, false);
+ if (ret) {
+ dev_err(&hdev->pdev->dev,
+ "restore vport vlan list failed, ret=%d\n",
+ ret);
+ return ret;
+ }
+ }
+ vlan->hd_tbl_status = true;
+ }
+
+ return 0;
+}
+
+static void hclge_rm_vport_vlan_table(struct hclge_vport *vport, u16 vlan_id,
+ bool is_write_tbl)
{
struct hclge_vport_vlan_cfg *vlan, *tmp;
struct hclge_dev *hdev = vport->back;
{
struct hclge_vport *vport = hclge_get_vport(handle);
- vport->rxvlan_cfg.strip_tag1_en = false;
- vport->rxvlan_cfg.strip_tag2_en = enable;
+ if (vport->port_base_vlan_cfg.state == HNAE3_PORT_BASE_VLAN_DISABLE) {
+ vport->rxvlan_cfg.strip_tag1_en = false;
+ vport->rxvlan_cfg.strip_tag2_en = enable;
+ } else {
+ vport->rxvlan_cfg.strip_tag1_en = enable;
+ vport->rxvlan_cfg.strip_tag2_en = true;
+ }
vport->rxvlan_cfg.vlan1_vlan_prionly = false;
vport->rxvlan_cfg.vlan2_vlan_prionly = false;
+ vport->rxvlan_cfg.rx_vlan_offload_en = enable;
return hclge_set_vlan_rx_offload_cfg(vport);
}
+static int hclge_update_vlan_filter_entries(struct hclge_vport *vport,
+ u16 port_base_vlan_state,
+ struct hclge_vlan_info *new_info,
+ struct hclge_vlan_info *old_info)
+{
+ struct hclge_dev *hdev = vport->back;
+ int ret;
+
+ if (port_base_vlan_state == HNAE3_PORT_BASE_VLAN_ENABLE) {
+ hclge_rm_vport_all_vlan_table(vport, false);
+ return hclge_set_vlan_filter_hw(hdev,
+ htons(new_info->vlan_proto),
+ vport->vport_id,
+ new_info->vlan_tag,
+ new_info->qos, false);
+ }
+
+ ret = hclge_set_vlan_filter_hw(hdev, htons(old_info->vlan_proto),
+ vport->vport_id, old_info->vlan_tag,
+ old_info->qos, true);
+ if (ret)
+ return ret;
+
+ return hclge_add_vport_all_vlan_table(vport);
+}
+
+int hclge_update_port_base_vlan_cfg(struct hclge_vport *vport, u16 state,
+ struct hclge_vlan_info *vlan_info)
+{
+ struct hnae3_handle *nic = &vport->nic;
+ struct hclge_vlan_info *old_vlan_info;
+ struct hclge_dev *hdev = vport->back;
+ int ret;
+
+ old_vlan_info = &vport->port_base_vlan_cfg.vlan_info;
+
+ ret = hclge_vlan_offload_cfg(vport, state, vlan_info->vlan_tag);
+ if (ret)
+ return ret;
+
+ if (state == HNAE3_PORT_BASE_VLAN_MODIFY) {
+ /* add new VLAN tag */
+ ret = hclge_set_vlan_filter_hw(hdev,
+ htons(vlan_info->vlan_proto),
+ vport->vport_id,
+ vlan_info->vlan_tag,
+ vlan_info->qos, false);
+ if (ret)
+ return ret;
+
+ /* remove old VLAN tag */
+ ret = hclge_set_vlan_filter_hw(hdev,
+ htons(old_vlan_info->vlan_proto),
+ vport->vport_id,
+ old_vlan_info->vlan_tag,
+ old_vlan_info->qos, true);
+ if (ret)
+ return ret;
+
+ goto update;
+ }
+
+ ret = hclge_update_vlan_filter_entries(vport, state, vlan_info,
+ old_vlan_info);
+ if (ret)
+ return ret;
+
+ /* update state only when disable/enable port based VLAN */
+ vport->port_base_vlan_cfg.state = state;
+ if (state == HNAE3_PORT_BASE_VLAN_DISABLE)
+ nic->port_base_vlan_state = HNAE3_PORT_BASE_VLAN_DISABLE;
+ else
+ nic->port_base_vlan_state = HNAE3_PORT_BASE_VLAN_ENABLE;
+
+update:
+ vport->port_base_vlan_cfg.vlan_info.vlan_tag = vlan_info->vlan_tag;
+ vport->port_base_vlan_cfg.vlan_info.qos = vlan_info->qos;
+ vport->port_base_vlan_cfg.vlan_info.vlan_proto = vlan_info->vlan_proto;
+
+ return 0;
+}
+
+static u16 hclge_get_port_base_vlan_state(struct hclge_vport *vport,
+ enum hnae3_port_base_vlan_state state,
+ u16 vlan)
+{
+ if (state == HNAE3_PORT_BASE_VLAN_DISABLE) {
+ if (!vlan)
+ return HNAE3_PORT_BASE_VLAN_NOCHANGE;
+ else
+ return HNAE3_PORT_BASE_VLAN_ENABLE;
+ } else {
+ if (!vlan)
+ return HNAE3_PORT_BASE_VLAN_DISABLE;
+ else if (vport->port_base_vlan_cfg.vlan_info.vlan_tag == vlan)
+ return HNAE3_PORT_BASE_VLAN_NOCHANGE;
+ else
+ return HNAE3_PORT_BASE_VLAN_MODIFY;
+ }
+}
+
+static int hclge_set_vf_vlan_filter(struct hnae3_handle *handle, int vfid,
+ u16 vlan, u8 qos, __be16 proto)
+{
+ struct hclge_vport *vport = hclge_get_vport(handle);
+ struct hclge_dev *hdev = vport->back;
+ struct hclge_vlan_info vlan_info;
+ u16 state;
+ int ret;
+
+ if (hdev->pdev->revision == 0x20)
+ return -EOPNOTSUPP;
+
+ /* qos is a 3 bits value, so can not be bigger than 7 */
+ if (vfid >= hdev->num_alloc_vfs || vlan > VLAN_N_VID - 1 || qos > 7)
+ return -EINVAL;
+ if (proto != htons(ETH_P_8021Q))
+ return -EPROTONOSUPPORT;
+
+ vport = &hdev->vport[vfid];
+ state = hclge_get_port_base_vlan_state(vport,
+ vport->port_base_vlan_cfg.state,
+ vlan);
+ if (state == HNAE3_PORT_BASE_VLAN_NOCHANGE)
+ return 0;
+
+ vlan_info.vlan_tag = vlan;
+ vlan_info.qos = qos;
+ vlan_info.vlan_proto = ntohs(proto);
+
+ /* update port based VLAN for PF */
+ if (!vfid) {
+ hclge_notify_client(hdev, HNAE3_DOWN_CLIENT);
+ ret = hclge_update_port_base_vlan_cfg(vport, state, &vlan_info);
+ hclge_notify_client(hdev, HNAE3_UP_CLIENT);
+
+ return ret;
+ }
+
+ if (!test_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state)) {
+ return hclge_update_port_base_vlan_cfg(vport, state,
+ &vlan_info);
+ } else {
+ ret = hclge_push_vf_port_base_vlan_info(&hdev->vport[0],
+ (u8)vfid, state,
+ vlan, qos,
+ ntohs(proto));
+ return ret;
+ }
+}
+
+int hclge_set_vlan_filter(struct hnae3_handle *handle, __be16 proto,
+ u16 vlan_id, bool is_kill)
+{
+ struct hclge_vport *vport = hclge_get_vport(handle);
+ struct hclge_dev *hdev = vport->back;
+ bool writen_to_tbl = false;
+ int ret = 0;
+
+ /* when port based VLAN enabled, we use port based VLAN as the VLAN
+ * filter entry. In this case, we don't update VLAN filter table
+ * when user add new VLAN or remove exist VLAN, just update the vport
+ * VLAN list. The VLAN id in VLAN list won't be writen in VLAN filter
+ * table until port based VLAN disabled
+ */
+ if (handle->port_base_vlan_state == HNAE3_PORT_BASE_VLAN_DISABLE) {
+ ret = hclge_set_vlan_filter_hw(hdev, proto, vport->vport_id,
+ vlan_id, 0, is_kill);
+ writen_to_tbl = true;
+ }
+
+ if (ret)
+ return ret;
+
+ if (is_kill)
+ hclge_rm_vport_vlan_table(vport, vlan_id, false);
+ else
+ hclge_add_vport_vlan_table(vport, vlan_id,
+ writen_to_tbl);
+
+ return 0;
+}
+
static int hclge_set_mac_mtu(struct hclge_dev *hdev, int new_mps)
{
struct hclge_config_max_frm_size_cmd *req;
int i;
for (i = 0; i < hdev->num_alloc_vport; i++) {
- hclge_vport_start(vport);
+ hclge_vport_stop(vport);
vport++;
}
}
/* VPort level vlan tag configuration for RX direction */
struct hclge_rx_vtag_cfg {
- bool strip_tag1_en; /* Whether strip inner vlan tag */
- bool strip_tag2_en; /* Whether strip outer vlan tag */
- bool vlan1_vlan_prionly;/* Inner VLAN Tag up to descriptor Enable */
- bool vlan2_vlan_prionly;/* Outer VLAN Tag up to descriptor Enable */
+ u8 rx_vlan_offload_en; /* Whether enable rx vlan offload */
+ u8 strip_tag1_en; /* Whether strip inner vlan tag */
+ u8 strip_tag2_en; /* Whether strip outer vlan tag */
+ u8 vlan1_vlan_prionly; /* Inner VLAN Tag up to descriptor Enable */
+ u8 vlan2_vlan_prionly; /* Outer VLAN Tag up to descriptor Enable */
};
struct hclge_rss_tuple_cfg {
HCLGE_VPORT_STATE_MAX
};
+struct hclge_vlan_info {
+ u16 vlan_proto; /* so far support 802.1Q only */
+ u16 qos;
+ u16 vlan_tag;
+};
+
+struct hclge_port_base_vlan_config {
+ u16 state;
+ struct hclge_vlan_info vlan_info;
+};
+
struct hclge_vport {
u16 alloc_tqps; /* Allocated Tx/Rx queues */
u16 alloc_rss_size;
u16 qs_offset;
- u16 bw_limit; /* VSI BW Limit (0 = disabled) */
+ u32 bw_limit; /* VSI BW Limit (0 = disabled) */
u8 dwrr;
+ struct hclge_port_base_vlan_config port_base_vlan_cfg;
struct hclge_tx_vtag_cfg txvlan_cfg;
struct hclge_rx_vtag_cfg rxvlan_cfg;
void hclge_rm_vport_all_mac_table(struct hclge_vport *vport, bool is_del_list,
enum HCLGE_MAC_ADDR_TYPE mac_type);
void hclge_uninit_vport_mac_table(struct hclge_dev *hdev);
-void hclge_add_vport_vlan_table(struct hclge_vport *vport, u16 vlan_id);
-void hclge_rm_vport_vlan_table(struct hclge_vport *vport, u16 vlan_id,
- bool is_write_tbl);
void hclge_rm_vport_all_vlan_table(struct hclge_vport *vport, bool is_del_list);
void hclge_uninit_vport_vlan_table(struct hclge_dev *hdev);
+int hclge_update_port_base_vlan_cfg(struct hclge_vport *vport, u16 state,
+ struct hclge_vlan_info *vlan_info);
+int hclge_push_vf_port_base_vlan_info(struct hclge_vport *vport, u8 vfid,
+ u16 state, u16 vlan_tag, u16 qos,
+ u16 vlan_proto);
#endif
return 0;
}
+int hclge_push_vf_port_base_vlan_info(struct hclge_vport *vport, u8 vfid,
+ u16 state, u16 vlan_tag, u16 qos,
+ u16 vlan_proto)
+{
+#define MSG_DATA_SIZE 8
+
+ u8 msg_data[MSG_DATA_SIZE];
+
+ memcpy(&msg_data[0], &state, sizeof(u16));
+ memcpy(&msg_data[2], &vlan_proto, sizeof(u16));
+ memcpy(&msg_data[4], &qos, sizeof(u16));
+ memcpy(&msg_data[6], &vlan_tag, sizeof(u16));
+
+ return hclge_send_mbx_msg(vport, msg_data, sizeof(msg_data),
+ HLCGE_MBX_PUSH_VLAN_INFO, vfid);
+}
+
static int hclge_set_vf_vlan_cfg(struct hclge_vport *vport,
- struct hclge_mbx_vf_to_pf_cmd *mbx_req,
- bool gen_resp)
+ struct hclge_mbx_vf_to_pf_cmd *mbx_req)
{
int status = 0;
memcpy(&proto, &mbx_req->msg[5], sizeof(proto));
status = hclge_set_vlan_filter(handle, cpu_to_be16(proto),
vlan, is_kill);
- if (!status)
- is_kill ? hclge_rm_vport_vlan_table(vport, vlan, false)
- : hclge_add_vport_vlan_table(vport, vlan);
} else if (mbx_req->msg[1] == HCLGE_MBX_VLAN_RX_OFF_CFG) {
struct hnae3_handle *handle = &vport->nic;
bool en = mbx_req->msg[2] ? true : false;
status = hclge_en_hw_strip_rxvtag(handle, en);
+ } else if (mbx_req->msg[1] == HCLGE_MBX_PORT_BASE_VLAN_CFG) {
+ struct hclge_vlan_info *vlan_info;
+ u16 *state;
+
+ state = (u16 *)&mbx_req->msg[2];
+ vlan_info = (struct hclge_vlan_info *)&mbx_req->msg[4];
+ status = hclge_update_port_base_vlan_cfg(vport, *state,
+ vlan_info);
+ } else if (mbx_req->msg[1] == HCLGE_MBX_GET_PORT_BASE_VLAN_STATE) {
+ u8 state;
+
+ state = vport->port_base_vlan_cfg.state;
+ status = hclge_gen_resp_to_vf(vport, mbx_req, 0, &state,
+ sizeof(u8));
}
- if (gen_resp)
- status = hclge_gen_resp_to_vf(vport, mbx_req, status, NULL, 0);
-
return status;
}
HCLGE_TQPS_DEPTH_INFO_LEN);
}
+static int hclge_get_vf_media_type(struct hclge_vport *vport,
+ struct hclge_mbx_vf_to_pf_cmd *mbx_req)
+{
+ struct hclge_dev *hdev = vport->back;
+ u8 resp_data;
+
+ resp_data = hdev->hw.mac.media_type;
+ return hclge_gen_resp_to_vf(vport, mbx_req, 0, &resp_data,
+ sizeof(resp_data));
+}
+
static int hclge_get_link_info(struct hclge_vport *vport,
struct hclge_mbx_vf_to_pf_cmd *mbx_req)
{
struct hclge_dev *hdev = vport->back;
u16 link_status;
- u8 msg_data[10];
- u16 media_type;
+ u8 msg_data[8];
u8 dest_vfid;
u16 duplex;
/* mac.link can only be 0 or 1 */
link_status = (u16)hdev->hw.mac.link;
duplex = hdev->hw.mac.duplex;
- media_type = hdev->hw.mac.media_type;
memcpy(&msg_data[0], &link_status, sizeof(u16));
memcpy(&msg_data[2], &hdev->hw.mac.speed, sizeof(u32));
memcpy(&msg_data[6], &duplex, sizeof(u16));
- memcpy(&msg_data[8], &media_type, sizeof(u16));
dest_vfid = mbx_req->mbx_src_vfid;
/* send this requested info to VF */
ret);
break;
case HCLGE_MBX_SET_VLAN:
- ret = hclge_set_vf_vlan_cfg(vport, req, false);
+ ret = hclge_set_vf_vlan_cfg(vport, req);
if (ret)
dev_err(&hdev->pdev->dev,
"PF failed(%d) to config VF's VLAN\n",
hclge_rm_vport_all_vlan_table(vport, true);
mutex_unlock(&hdev->vport_cfg_mutex);
break;
+ case HCLGE_MBX_GET_MEDIA_TYPE:
+ ret = hclge_get_vf_media_type(vport, req);
+ if (ret)
+ dev_err(&hdev->pdev->dev,
+ "PF fail(%d) to media type for VF\n",
+ ret);
+ break;
default:
dev_err(&hdev->pdev->dev,
"un-supported mailbox message, code = %d\n",
int hclge_mac_mdio_config(struct hclge_dev *hdev)
{
+#define PHY_INEXISTENT 255
+
struct hclge_mac *mac = &hdev->hw.mac;
struct phy_device *phydev;
struct mii_bus *mdio_bus;
int ret;
- if (hdev->hw.mac.phy_addr >= PHY_MAX_ADDR) {
+ if (hdev->hw.mac.phy_addr == PHY_INEXISTENT) {
+ dev_info(&hdev->pdev->dev,
+ "no phy device is connected to mdio bus\n");
+ return 0;
+ } else if (hdev->hw.mac.phy_addr >= PHY_MAX_ADDR) {
dev_err(&hdev->pdev->dev, "phy_addr(%d) is too large.\n",
hdev->hw.mac.phy_addr);
return -EINVAL;
# Makefile for the HISILICON network device drivers.
#
-ccflags-y := -Idrivers/net/ethernet/hisilicon/hns3
+ccflags-y := -I $(srctree)/drivers/net/ethernet/hisilicon/hns3
obj-$(CONFIG_HNS3_HCLGEVF) += hclgevf.o
hclgevf-objs = hclgevf_main.o hclgevf_cmd.o hclgevf_mbx.o
\ No newline at end of file
return ring->desc_num - used - 1;
}
+static int hclgevf_is_valid_csq_clean_head(struct hclgevf_cmq_ring *ring,
+ int head)
+{
+ int ntu = ring->next_to_use;
+ int ntc = ring->next_to_clean;
+
+ if (ntu > ntc)
+ return head >= ntc && head <= ntu;
+
+ return head >= ntc || head <= ntu;
+}
+
static int hclgevf_cmd_csq_clean(struct hclgevf_hw *hw)
{
+ struct hclgevf_dev *hdev = container_of(hw, struct hclgevf_dev, hw);
struct hclgevf_cmq_ring *csq = &hw->cmq.csq;
- u16 ntc = csq->next_to_clean;
- struct hclgevf_desc *desc;
int clean = 0;
u32 head;
- desc = &csq->desc[ntc];
head = hclgevf_read_dev(hw, HCLGEVF_NIC_CSQ_HEAD_REG);
- while (head != ntc) {
- memset(desc, 0, sizeof(*desc));
- ntc++;
- if (ntc == csq->desc_num)
- ntc = 0;
- desc = &csq->desc[ntc];
- clean++;
+ rmb(); /* Make sure head is ready before touch any data */
+
+ if (!hclgevf_is_valid_csq_clean_head(csq, head)) {
+ dev_warn(&hdev->pdev->dev, "wrong cmd head (%d, %d-%d)\n", head,
+ csq->next_to_use, csq->next_to_clean);
+ dev_warn(&hdev->pdev->dev,
+ "Disabling any further commands to IMP firmware\n");
+ set_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state);
+ return -EIO;
}
- csq->next_to_clean = ntc;
+ clean = (head - csq->next_to_clean + csq->desc_num) % csq->desc_num;
+ csq->next_to_clean = head;
return clean;
}
int ret;
spin_lock_bh(&hdev->hw.cmq.csq.lock);
- spin_lock_bh(&hdev->hw.cmq.crq.lock);
+ spin_lock(&hdev->hw.cmq.crq.lock);
/* initialize the pointers of async rx queue of mailbox */
hdev->arq.hdev = hdev;
hclgevf_cmd_init_regs(&hdev->hw);
- spin_unlock_bh(&hdev->hw.cmq.crq.lock);
+ spin_unlock(&hdev->hw.cmq.crq.lock);
spin_unlock_bh(&hdev->hw.cmq.csq.lock);
clear_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state);
* reset may happen when lower level reset is being processed.
*/
if (hclgevf_is_reset_pending(hdev)) {
- set_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state);
- return -EBUSY;
+ ret = -EBUSY;
+ goto err_cmd_init;
}
/* get firmware version */
if (ret) {
dev_err(&hdev->pdev->dev,
"failed(%d) to query firmware version\n", ret);
- return ret;
+ goto err_cmd_init;
}
hdev->fw_version = version;
dev_info(&hdev->pdev->dev, "The firmware version is %08x\n", version);
return 0;
+
+err_cmd_init:
+ set_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state);
+
+ return ret;
}
static void hclgevf_cmd_uninit_regs(struct hclgevf_hw *hw)
return 0;
}
+static int hclgevf_get_port_base_vlan_filter_state(struct hclgevf_dev *hdev)
+{
+ struct hnae3_handle *nic = &hdev->nic;
+ u8 resp_msg;
+ int ret;
+
+ ret = hclgevf_send_mbx_msg(hdev, HCLGE_MBX_SET_VLAN,
+ HCLGE_MBX_GET_PORT_BASE_VLAN_STATE,
+ NULL, 0, true, &resp_msg, sizeof(u8));
+ if (ret) {
+ dev_err(&hdev->pdev->dev,
+ "VF request to get port based vlan state failed %d",
+ ret);
+ return ret;
+ }
+
+ nic->port_base_vlan_state = resp_msg;
+
+ return 0;
+}
+
static int hclgevf_get_queue_info(struct hclgevf_dev *hdev)
{
#define HCLGEVF_TQPS_RSS_INFO_LEN 6
return qid_in_pf;
}
+static int hclgevf_get_pf_media_type(struct hclgevf_dev *hdev)
+{
+ u8 resp_msg;
+ int ret;
+
+ ret = hclgevf_send_mbx_msg(hdev, HCLGE_MBX_GET_MEDIA_TYPE, 0, NULL, 0,
+ true, &resp_msg, sizeof(resp_msg));
+ if (ret) {
+ dev_err(&hdev->pdev->dev,
+ "VF request to get the pf port media type failed %d",
+ ret);
+ return ret;
+ }
+
+ hdev->hw.mac.media_type = resp_msg;
+
+ return 0;
+}
+
static int hclgevf_alloc_tqps(struct hclgevf_dev *hdev)
{
struct hclgevf_tqp *tqp;
*/
hclgevf_cmd_init(hdev);
dev_err(&hdev->pdev->dev, "failed to reset VF\n");
+ if (hclgevf_is_reset_pending(hdev))
+ hclgevf_reset_task_schedule(hdev);
return ret;
}
void hclgevf_reset_task_schedule(struct hclgevf_dev *hdev)
{
- if (!test_bit(HCLGEVF_STATE_RST_SERVICE_SCHED, &hdev->state) &&
- !test_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state)) {
+ if (!test_bit(HCLGEVF_STATE_RST_SERVICE_SCHED, &hdev->state)) {
set_bit(HCLGEVF_STATE_RST_SERVICE_SCHED, &hdev->state);
schedule_work(&hdev->rst_service_task);
}
{
int ret;
+ /* get current port based vlan state from PF */
+ ret = hclgevf_get_port_base_vlan_filter_state(hdev);
+ if (ret)
+ return ret;
+
/* get queue configuration from PF */
ret = hclgevf_get_queue_info(hdev);
if (ret)
if (ret)
return ret;
+ ret = hclgevf_get_pf_media_type(hdev);
+ if (ret)
+ return ret;
+
/* get tc configuration from PF */
return hclgevf_get_tc_info(hdev);
}
static int hclgevf_client_start(struct hnae3_handle *handle)
{
struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+ int ret;
+
+ ret = hclgevf_set_alive(handle, true);
+ if (ret)
+ return ret;
mod_timer(&hdev->keep_alive_timer, jiffies + 2 * HZ);
- return hclgevf_set_alive(handle, true);
+
+ return 0;
}
static void hclgevf_client_stop(struct hnae3_handle *handle)
{
set_bit(HCLGEVF_STATE_DOWN, &hdev->state);
+ if (hdev->keep_alive_timer.function)
+ del_timer_sync(&hdev->keep_alive_timer);
+ if (hdev->keep_alive_task.func)
+ cancel_work_sync(&hdev->keep_alive_task);
if (hdev->service_timer.function)
del_timer_sync(&hdev->service_timer);
if (hdev->service_task.func)
}
}
+void hclgevf_update_port_base_vlan_info(struct hclgevf_dev *hdev, u16 state,
+ u8 *port_base_vlan_info, u8 data_size)
+{
+ struct hnae3_handle *nic = &hdev->nic;
+
+ rtnl_lock();
+ hclgevf_notify_client(hdev, HNAE3_DOWN_CLIENT);
+ rtnl_unlock();
+
+ /* send msg to PF and wait update port based vlan info */
+ hclgevf_send_mbx_msg(hdev, HCLGE_MBX_SET_VLAN,
+ HCLGE_MBX_PORT_BASE_VLAN_CFG,
+ port_base_vlan_info, data_size,
+ false, NULL, 0);
+
+ if (state == HNAE3_PORT_BASE_VLAN_DISABLE)
+ nic->port_base_vlan_state = HNAE3_PORT_BASE_VLAN_DISABLE;
+ else
+ nic->port_base_vlan_state = HNAE3_PORT_BASE_VLAN_ENABLE;
+
+ rtnl_lock();
+ hclgevf_notify_client(hdev, HNAE3_UP_CLIENT);
+ rtnl_unlock();
+}
+
static const struct hnae3_ae_ops hclgevf_ops = {
.init_ae_dev = hclgevf_init_ae_dev,
.uninit_ae_dev = hclgevf_uninit_ae_dev,
u8 duplex);
void hclgevf_reset_task_schedule(struct hclgevf_dev *hdev);
void hclgevf_mbx_task_schedule(struct hclgevf_dev *hdev);
+void hclgevf_update_port_base_vlan_info(struct hclgevf_dev *hdev, u16 state,
+ u8 *port_base_vlan_info, u8 data_size);
#endif
case HCLGE_MBX_LINK_STAT_CHANGE:
case HCLGE_MBX_ASSERTING_RESET:
case HCLGE_MBX_LINK_STAT_MODE:
+ case HLCGE_MBX_PUSH_VLAN_INFO:
/* set this mbx event as pending. This is required as we
* might loose interrupt event when mbx task is busy
* handling. This shall be cleared when mbx task just
void hclgevf_mbx_async_handler(struct hclgevf_dev *hdev)
{
enum hnae3_reset_type reset_type;
- u16 link_status;
- u16 *msg_q;
+ u16 link_status, state;
+ u16 *msg_q, *vlan_info;
u8 duplex;
u32 speed;
u32 tail;
link_status = le16_to_cpu(msg_q[1]);
memcpy(&speed, &msg_q[2], sizeof(speed));
duplex = (u8)le16_to_cpu(msg_q[4]);
- hdev->hw.mac.media_type = (u8)le16_to_cpu(msg_q[5]);
/* update upper layer with new link link status */
hclgevf_update_link_status(hdev, link_status);
hclgevf_reset_task_schedule(hdev);
break;
+ case HLCGE_MBX_PUSH_VLAN_INFO:
+ state = le16_to_cpu(msg_q[1]);
+ vlan_info = &msg_q[1];
+ hclgevf_update_port_base_vlan_info(hdev, state,
+ (u8 *)vlan_info, 8);
+ break;
default:
dev_err(&hdev->pdev->dev,
"fetched unsupported(%d) message from arq\n",
};
struct hns_mdio_device {
- void *vbase; /* mdio reg base address */
+ u8 __iomem *vbase; /* mdio reg base address */
struct regmap *subctrl_vbase;
struct hns_mdio_sc_reg sc_reg;
};
#define MDIO_SC_CLK_ST 0x531C
#define MDIO_SC_RESET_ST 0x5A1C
-static void mdio_write_reg(void *base, u32 reg, u32 value)
+static void mdio_write_reg(u8 __iomem *base, u32 reg, u32 value)
{
- u8 __iomem *reg_addr = (u8 __iomem *)base;
-
- writel_relaxed(value, reg_addr + reg);
+ writel_relaxed(value, base + reg);
}
#define MDIO_WRITE_REG(a, reg, value) \
mdio_write_reg((a)->vbase, (reg), (value))
-static u32 mdio_read_reg(void *base, u32 reg)
+static u32 mdio_read_reg(u8 __iomem *base, u32 reg)
{
- u8 __iomem *reg_addr = (u8 __iomem *)base;
-
- return readl_relaxed(reg_addr + reg);
+ return readl_relaxed(base + reg);
}
#define mdio_set_field(origin, mask, shift, val) \
#define mdio_get_field(origin, mask, shift) (((origin) >> (shift)) & (mask))
-static void mdio_set_reg_field(void *base, u32 reg, u32 mask, u32 shift,
+static void mdio_set_reg_field(u8 __iomem *base, u32 reg, u32 mask, u32 shift,
u32 val)
{
u32 origin = mdio_read_reg(base, reg);
#define MDIO_SET_REG_FIELD(dev, reg, mask, shift, val) \
mdio_set_reg_field((dev)->vbase, (reg), (mask), (shift), (val))
-static u32 mdio_get_reg_field(void *base, u32 reg, u32 mask, u32 shift)
+static u32 mdio_get_reg_field(u8 __iomem *base, u32 reg, u32 mask, u32 shift)
{
u32 origin;
flush_skbs:
netdev_txq = netdev_get_tx_queue(netdev, q_id);
- if ((!skb->xmit_more) || (netif_xmit_stopped(netdev_txq)))
+ if ((!netdev_xmit_more()) || (netif_xmit_stopped(netdev_txq)))
hinic_sq_write_db(txq->sq, prod_idx, wqe_size, 0);
return err;
memset(pr, 0, sizeof(struct ehea_port_res));
- pr->tx_bytes = rx_bytes;
+ pr->tx_bytes = tx_bytes;
pr->tx_packets = tx_packets;
pr->rx_bytes = rx_bytes;
pr->rx_packets = rx_packets;
int nr_of_cqe, u64 eq_handle, u32 cq_token)
{
struct ehea_cq *cq;
- struct h_epa epa;
- u64 *cq_handle_ref, hret, rpage;
+ u64 hret, rpage;
u32 counter;
int ret;
void *vpage;
cq->adapter = adapter;
- cq_handle_ref = &cq->fw_handle;
-
hret = ehea_h_alloc_resource_cq(adapter->handle, &cq->attr,
&cq->fw_handle, &cq->epas);
if (hret != H_SUCCESS) {
}
hw_qeit_reset(&cq->hw_queue);
- epa = cq->epas.kernel;
ehea_reset_cq_ep(cq);
ehea_reset_cq_n1(cq);
*/
adapter->state = VNIC_PROBED;
+ reinit_completion(&adapter->init_done);
rc = init_crq_queue(adapter);
if (rc) {
netdev_err(adapter->netdev,
{
struct ibmvnic_rwi *rwi;
struct ibmvnic_adapter *adapter;
- struct net_device *netdev;
bool we_lock_rtnl = false;
u32 reset_state;
int rc = 0;
adapter = container_of(work, struct ibmvnic_adapter, ibmvnic_reset);
- netdev = adapter->netdev;
/* netif_set_real_num_xx_queues needs to take rtnl lock here
* unless wait_for_reset is set, in which case the rtnl lock
{
struct device *dev = &adapter->vdev->dev;
struct ibmvnic_query_ip_offload_buffer *buf = &adapter->ip_offload_buf;
+ netdev_features_t old_hw_features = 0;
union ibmvnic_crq crq;
int i;
adapter->ip_offload_ctrl.large_rx_ipv4 = 0;
adapter->ip_offload_ctrl.large_rx_ipv6 = 0;
- adapter->netdev->features = NETIF_F_SG | NETIF_F_GSO;
+ if (adapter->state != VNIC_PROBING) {
+ old_hw_features = adapter->netdev->hw_features;
+ adapter->netdev->hw_features = 0;
+ }
+
+ adapter->netdev->hw_features = NETIF_F_SG | NETIF_F_GSO | NETIF_F_GRO;
if (buf->tcp_ipv4_chksum || buf->udp_ipv4_chksum)
- adapter->netdev->features |= NETIF_F_IP_CSUM;
+ adapter->netdev->hw_features |= NETIF_F_IP_CSUM;
if (buf->tcp_ipv6_chksum || buf->udp_ipv6_chksum)
- adapter->netdev->features |= NETIF_F_IPV6_CSUM;
+ adapter->netdev->hw_features |= NETIF_F_IPV6_CSUM;
if ((adapter->netdev->features &
(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)))
- adapter->netdev->features |= NETIF_F_RXCSUM;
+ adapter->netdev->hw_features |= NETIF_F_RXCSUM;
if (buf->large_tx_ipv4)
- adapter->netdev->features |= NETIF_F_TSO;
+ adapter->netdev->hw_features |= NETIF_F_TSO;
if (buf->large_tx_ipv6)
- adapter->netdev->features |= NETIF_F_TSO6;
+ adapter->netdev->hw_features |= NETIF_F_TSO6;
- adapter->netdev->hw_features |= adapter->netdev->features;
+ if (adapter->state == VNIC_PROBING) {
+ adapter->netdev->features |= adapter->netdev->hw_features;
+ } else if (old_hw_features != adapter->netdev->hw_features) {
+ netdev_features_t tmp = 0;
+
+ /* disable features no longer supported */
+ adapter->netdev->features &= adapter->netdev->hw_features;
+ /* turn on features now supported if previously enabled */
+ tmp = (old_hw_features ^ adapter->netdev->hw_features) &
+ adapter->netdev->hw_features;
+ adapter->netdev->features |=
+ tmp & adapter->netdev->wanted_features;
+ }
memset(&crq, 0, sizeof(crq));
crq.control_ip_offload.first = IBMVNIC_CRQ_CMD;
old_num_rx_queues = adapter->req_rx_queues;
old_num_tx_queues = adapter->req_tx_queues;
- init_completion(&adapter->init_done);
+ reinit_completion(&adapter->init_done);
adapter->init_done_rc = 0;
ibmvnic_send_crq_init(adapter);
if (!wait_for_completion_timeout(&adapter->init_done, timeout)) {
adapter->from_passive_init = false;
- init_completion(&adapter->init_done);
adapter->init_done_rc = 0;
ibmvnic_send_crq_init(adapter);
if (!wait_for_completion_timeout(&adapter->init_done, timeout)) {
INIT_WORK(&adapter->ibmvnic_reset, __ibmvnic_reset);
INIT_LIST_HEAD(&adapter->rwi_list);
spin_lock_init(&adapter->rwi_lock);
+ init_completion(&adapter->init_done);
adapter->resetting = false;
adapter->mac_change_pending = false;
/* Make sure there is space in the ring for the next send. */
e1000_maybe_stop_tx(netdev, tx_ring, desc_needed);
- if (!skb->xmit_more ||
+ if (!netdev_xmit_more() ||
netif_xmit_stopped(netdev_get_tx_queue(netdev, 0))) {
writel(tx_ring->next_to_use, hw->hw_addr + tx_ring->tdt);
/* we need this if more than one processor can write to
DIV_ROUND_UP(PAGE_SIZE,
adapter->tx_fifo_limit) + 2));
- if (!skb->xmit_more ||
+ if (!netdev_xmit_more() ||
netif_xmit_stopped(netdev_get_tx_queue(netdev, 0))) {
if (adapter->flags2 & FLAG2_PCIM2PCI_ARBITER_WA)
e1000e_update_tdt_wa(tx_ring,
/* create driver workqueue */
fm10k_workqueue = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0,
fm10k_driver_name);
+ if (!fm10k_workqueue)
+ return -ENOMEM;
fm10k_dbg_init();
fm10k_maybe_stop_tx(tx_ring, DESC_NEEDED);
/* notify HW of packet */
- if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
+ if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) {
writel(i, tx_ring->tail);
/* we need this if more than one processor can write to our tail
i40e_diag.o \
i40e_txrx.o \
i40e_ptp.o \
+ i40e_ddp.o \
i40e_client.o \
i40e_virtchnl_pf.o \
i40e_xsk.o
u8 filter_index;
};
+#define I40_DDP_FLASH_REGION 100
+#define I40E_PROFILE_INFO_SIZE 48
+#define I40E_MAX_PROFILE_NUM 16
+#define I40E_PROFILE_LIST_SIZE \
+ (I40E_PROFILE_INFO_SIZE * I40E_MAX_PROFILE_NUM + 4)
+#define I40E_DDP_PROFILE_PATH "intel/i40e/ddp/"
+#define I40E_DDP_PROFILE_NAME_MAX 64
+
+int i40e_ddp_load(struct net_device *netdev, const u8 *data, size_t size,
+ bool is_add);
+int i40e_ddp_flash(struct net_device *netdev, struct ethtool_flash *flash);
+
+struct i40e_ddp_profile_list {
+ u32 p_count;
+ struct i40e_profile_info p_info[0];
+};
+
+struct i40e_ddp_old_profile_list {
+ struct list_head list;
+ size_t old_ddp_size;
+ u8 old_ddp_buf[0];
+};
+
/* macros related to FLX_PIT */
#define I40E_FLEX_SET_FSIZE(fsize) (((fsize) << \
I40E_PRTQF_FLX_PIT_FSIZE_SHIFT) & \
struct sk_buff *ptp_tx_skb;
unsigned long ptp_tx_start;
struct hwtstamp_config tstamp_config;
+ struct timespec64 ptp_prev_hw_time;
+ ktime_t ptp_reset_start;
struct mutex tmreg_lock; /* Used to protect the SYSTIME registers. */
u32 ptp_adj_mult;
u32 tx_hwtstamp_timeouts;
u16 override_q_count;
u16 last_sw_conf_flags;
u16 last_sw_conf_valid_flags;
+ /* List to keep previous DDP profiles to be rolled back in the future */
+ struct list_head ddp_old_prof;
};
/**
/* VSI specific handlers */
irqreturn_t (*irq_handler)(int irq, void *data);
+
+ unsigned long *af_xdp_zc_qps; /* tracks AF_XDP ZC enabled qps */
} ____cacheline_internodealigned_in_smp;
struct i40e_netdev_priv {
void i40e_ptp_set_increment(struct i40e_pf *pf);
int i40e_ptp_set_ts_config(struct i40e_pf *pf, struct ifreq *ifr);
int i40e_ptp_get_ts_config(struct i40e_pf *pf, struct ifreq *ifr);
+void i40e_ptp_save_hw_time(struct i40e_pf *pf);
+void i40e_ptp_restore_hw_time(struct i40e_pf *pf);
void i40e_ptp_init(struct i40e_pf *pf);
void i40e_ptp_stop(struct i40e_pf *pf);
int i40e_is_vsi_uplink_mode_veb(struct i40e_vsi *vsi);
return !!vsi->xdp_prog;
}
-static inline struct xdp_umem *i40e_xsk_umem(struct i40e_ring *ring)
-{
- bool xdp_on = i40e_enabled_xdp_vsi(ring->vsi);
- int qid = ring->queue_index;
-
- if (ring_is_xdp(ring))
- qid -= ring->vsi->alloc_queue_pairs;
-
- if (!xdp_on)
- return NULL;
-
- return xdp_get_umem_from_qid(ring->vsi->netdev, qid);
-}
-
int i40e_create_queue_channel(struct i40e_vsi *vsi, struct i40e_channel *ch);
int i40e_set_bw_limit(struct i40e_vsi *vsi, u16 seid, u64 max_tx_rate);
int i40e_add_del_cloud_filter(struct i40e_vsi *vsi,
if (val >= hw->aq.num_asq_entries) {
i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
"AQTX: head overrun at %d\n", val);
- status = I40E_ERR_QUEUE_EMPTY;
+ status = I40E_ERR_ADMIN_QUEUE_FULL;
goto asq_send_command_error;
}
*/
#define I40E_FW_API_VERSION_MAJOR 0x0001
-#define I40E_FW_API_VERSION_MINOR_X722 0x0006
-#define I40E_FW_API_VERSION_MINOR_X710 0x0007
+#define I40E_FW_API_VERSION_MINOR_X722 0x0008
+#define I40E_FW_API_VERSION_MINOR_X710 0x0008
#define I40E_FW_MINOR_VERSION(_h) ((_h)->mac.type == I40E_MAC_XL710 ? \
I40E_FW_API_VERSION_MINOR_X710 : \
**/
u32 i40e_led_get(struct i40e_hw *hw)
{
- u32 current_mode = 0;
u32 mode = 0;
int i;
if (!gpio_val)
continue;
- /* ignore gpio LED src mode entries related to the activity
- * LEDs
- */
- current_mode = ((gpio_val & I40E_GLGEN_GPIO_CTL_LED_MODE_MASK)
- >> I40E_GLGEN_GPIO_CTL_LED_MODE_SHIFT);
- switch (current_mode) {
- case I40E_COMBINED_ACTIVITY:
- case I40E_FILTER_ACTIVITY:
- case I40E_MAC_ACTIVITY:
- case I40E_LINK_ACTIVITY:
- continue;
- default:
- break;
- }
-
mode = (gpio_val & I40E_GLGEN_GPIO_CTL_LED_MODE_MASK) >>
I40E_GLGEN_GPIO_CTL_LED_MODE_SHIFT;
break;
**/
void i40e_led_set(struct i40e_hw *hw, u32 mode, bool blink)
{
- u32 current_mode = 0;
int i;
if (mode & 0xfffffff0)
if (!gpio_val)
continue;
-
- /* ignore gpio LED src mode entries related to the activity
- * LEDs
- */
- current_mode = ((gpio_val & I40E_GLGEN_GPIO_CTL_LED_MODE_MASK)
- >> I40E_GLGEN_GPIO_CTL_LED_MODE_SHIFT);
- switch (current_mode) {
- case I40E_COMBINED_ACTIVITY:
- case I40E_FILTER_ACTIVITY:
- case I40E_MAC_ACTIVITY:
- case I40E_LINK_ACTIVITY:
- continue;
- default:
- break;
- }
-
gpio_val &= ~I40E_GLGEN_GPIO_CTL_LED_MODE_MASK;
/* this & is a bit of paranoia, but serves as a range check */
gpio_val |= ((mode << I40E_GLGEN_GPIO_CTL_LED_MODE_SHIFT) &
return NULL;
}
+/* Get section table in profile */
+#define I40E_SECTION_TABLE(profile, sec_tbl) \
+ do { \
+ struct i40e_profile_segment *p = (profile); \
+ u32 count; \
+ u32 *nvm; \
+ count = p->device_table_count; \
+ nvm = (u32 *)&p->device_table[count]; \
+ sec_tbl = (struct i40e_section_table *)&nvm[nvm[0] + 1]; \
+ } while (0)
+
+/* Get section header in profile */
+#define I40E_SECTION_HEADER(profile, offset) \
+ (struct i40e_profile_section_header *)((u8 *)(profile) + (offset))
+
+/**
+ * i40e_find_section_in_profile
+ * @section_type: the section type to search for (i.e., SECTION_TYPE_NOTE)
+ * @profile: pointer to the i40e segment header to be searched
+ *
+ * This function searches i40e segment for a particular section type. On
+ * success it returns a pointer to the section header, otherwise it will
+ * return NULL.
+ **/
+struct i40e_profile_section_header *
+i40e_find_section_in_profile(u32 section_type,
+ struct i40e_profile_segment *profile)
+{
+ struct i40e_profile_section_header *sec;
+ struct i40e_section_table *sec_tbl;
+ u32 sec_off;
+ u32 i;
+
+ if (profile->header.type != SEGMENT_TYPE_I40E)
+ return NULL;
+
+ I40E_SECTION_TABLE(profile, sec_tbl);
+
+ for (i = 0; i < sec_tbl->section_count; i++) {
+ sec_off = sec_tbl->section_offset[i];
+ sec = I40E_SECTION_HEADER(profile, sec_off);
+ if (sec->section.type == section_type)
+ return sec;
+ }
+
+ return NULL;
+}
+
+/**
+ * i40e_ddp_exec_aq_section - Execute generic AQ for DDP
+ * @hw: pointer to the hw struct
+ * @aq: command buffer containing all data to execute AQ
+ **/
+static enum
+i40e_status_code i40e_ddp_exec_aq_section(struct i40e_hw *hw,
+ struct i40e_profile_aq_section *aq)
+{
+ i40e_status status;
+ struct i40e_aq_desc desc;
+ u8 *msg = NULL;
+ u16 msglen;
+
+ i40e_fill_default_direct_cmd_desc(&desc, aq->opcode);
+ desc.flags |= cpu_to_le16(aq->flags);
+ memcpy(desc.params.raw, aq->param, sizeof(desc.params.raw));
+
+ msglen = aq->datalen;
+ if (msglen) {
+ desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF |
+ I40E_AQ_FLAG_RD));
+ if (msglen > I40E_AQ_LARGE_BUF)
+ desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+ desc.datalen = cpu_to_le16(msglen);
+ msg = &aq->data[0];
+ }
+
+ status = i40e_asq_send_command(hw, &desc, msg, msglen, NULL);
+
+ if (status) {
+ i40e_debug(hw, I40E_DEBUG_PACKAGE,
+ "unable to exec DDP AQ opcode %u, error %d\n",
+ aq->opcode, status);
+ return status;
+ }
+
+ /* copy returned desc to aq_buf */
+ memcpy(aq->param, desc.params.raw, sizeof(desc.params.raw));
+
+ return 0;
+}
+
+/**
+ * i40e_validate_profile
+ * @hw: pointer to the hardware structure
+ * @profile: pointer to the profile segment of the package to be validated
+ * @track_id: package tracking id
+ * @rollback: flag if the profile is for rollback.
+ *
+ * Validates supported devices and profile's sections.
+ */
+static enum i40e_status_code
+i40e_validate_profile(struct i40e_hw *hw, struct i40e_profile_segment *profile,
+ u32 track_id, bool rollback)
+{
+ struct i40e_profile_section_header *sec = NULL;
+ i40e_status status = 0;
+ struct i40e_section_table *sec_tbl;
+ u32 vendor_dev_id;
+ u32 dev_cnt;
+ u32 sec_off;
+ u32 i;
+
+ if (track_id == I40E_DDP_TRACKID_INVALID) {
+ i40e_debug(hw, I40E_DEBUG_PACKAGE, "Invalid track_id\n");
+ return I40E_NOT_SUPPORTED;
+ }
+
+ dev_cnt = profile->device_table_count;
+ for (i = 0; i < dev_cnt; i++) {
+ vendor_dev_id = profile->device_table[i].vendor_dev_id;
+ if ((vendor_dev_id >> 16) == PCI_VENDOR_ID_INTEL &&
+ hw->device_id == (vendor_dev_id & 0xFFFF))
+ break;
+ }
+ if (dev_cnt && i == dev_cnt) {
+ i40e_debug(hw, I40E_DEBUG_PACKAGE,
+ "Device doesn't support DDP\n");
+ return I40E_ERR_DEVICE_NOT_SUPPORTED;
+ }
+
+ I40E_SECTION_TABLE(profile, sec_tbl);
+
+ /* Validate sections types */
+ for (i = 0; i < sec_tbl->section_count; i++) {
+ sec_off = sec_tbl->section_offset[i];
+ sec = I40E_SECTION_HEADER(profile, sec_off);
+ if (rollback) {
+ if (sec->section.type == SECTION_TYPE_MMIO ||
+ sec->section.type == SECTION_TYPE_AQ ||
+ sec->section.type == SECTION_TYPE_RB_AQ) {
+ i40e_debug(hw, I40E_DEBUG_PACKAGE,
+ "Not a roll-back package\n");
+ return I40E_NOT_SUPPORTED;
+ }
+ } else {
+ if (sec->section.type == SECTION_TYPE_RB_AQ ||
+ sec->section.type == SECTION_TYPE_RB_MMIO) {
+ i40e_debug(hw, I40E_DEBUG_PACKAGE,
+ "Not an original package\n");
+ return I40E_NOT_SUPPORTED;
+ }
+ }
+ }
+
+ return status;
+}
+
/**
* i40e_write_profile
* @hw: pointer to the hardware structure
i40e_status status = 0;
struct i40e_section_table *sec_tbl;
struct i40e_profile_section_header *sec = NULL;
- u32 dev_cnt;
- u32 vendor_dev_id;
- u32 *nvm;
+ struct i40e_profile_aq_section *ddp_aq;
u32 section_size = 0;
u32 offset = 0, info = 0;
+ u32 sec_off;
u32 i;
- dev_cnt = profile->device_table_count;
+ status = i40e_validate_profile(hw, profile, track_id, false);
+ if (status)
+ return status;
- for (i = 0; i < dev_cnt; i++) {
- vendor_dev_id = profile->device_table[i].vendor_dev_id;
- if ((vendor_dev_id >> 16) == PCI_VENDOR_ID_INTEL)
- if (hw->device_id == (vendor_dev_id & 0xFFFF))
+ I40E_SECTION_TABLE(profile, sec_tbl);
+
+ for (i = 0; i < sec_tbl->section_count; i++) {
+ sec_off = sec_tbl->section_offset[i];
+ sec = I40E_SECTION_HEADER(profile, sec_off);
+ /* Process generic admin command */
+ if (sec->section.type == SECTION_TYPE_AQ) {
+ ddp_aq = (struct i40e_profile_aq_section *)&sec[1];
+ status = i40e_ddp_exec_aq_section(hw, ddp_aq);
+ if (status) {
+ i40e_debug(hw, I40E_DEBUG_PACKAGE,
+ "Failed to execute aq: section %d, opcode %u\n",
+ i, ddp_aq->opcode);
break;
+ }
+ sec->section.type = SECTION_TYPE_RB_AQ;
+ }
+
+ /* Skip any non-mmio sections */
+ if (sec->section.type != SECTION_TYPE_MMIO)
+ continue;
+
+ section_size = sec->section.size +
+ sizeof(struct i40e_profile_section_header);
+
+ /* Write MMIO section */
+ status = i40e_aq_write_ddp(hw, (void *)sec, (u16)section_size,
+ track_id, &offset, &info, NULL);
+ if (status) {
+ i40e_debug(hw, I40E_DEBUG_PACKAGE,
+ "Failed to write profile: section %d, offset %d, info %d\n",
+ i, offset, info);
+ break;
+ }
}
- if (i == dev_cnt) {
- i40e_debug(hw, I40E_DEBUG_PACKAGE, "Device doesn't support DDP");
- return I40E_ERR_DEVICE_NOT_SUPPORTED;
- }
+ return status;
+}
+
+/**
+ * i40e_rollback_profile
+ * @hw: pointer to the hardware structure
+ * @profile: pointer to the profile segment of the package to be removed
+ * @track_id: package tracking id
+ *
+ * Rolls back previously loaded package.
+ */
+enum i40e_status_code
+i40e_rollback_profile(struct i40e_hw *hw, struct i40e_profile_segment *profile,
+ u32 track_id)
+{
+ struct i40e_profile_section_header *sec = NULL;
+ i40e_status status = 0;
+ struct i40e_section_table *sec_tbl;
+ u32 offset = 0, info = 0;
+ u32 section_size = 0;
+ u32 sec_off;
+ int i;
+
+ status = i40e_validate_profile(hw, profile, track_id, true);
+ if (status)
+ return status;
- nvm = (u32 *)&profile->device_table[dev_cnt];
- sec_tbl = (struct i40e_section_table *)&nvm[nvm[0] + 1];
+ I40E_SECTION_TABLE(profile, sec_tbl);
- for (i = 0; i < sec_tbl->section_count; i++) {
- sec = (struct i40e_profile_section_header *)((u8 *)profile +
- sec_tbl->section_offset[i]);
+ /* For rollback write sections in reverse */
+ for (i = sec_tbl->section_count - 1; i >= 0; i--) {
+ sec_off = sec_tbl->section_offset[i];
+ sec = I40E_SECTION_HEADER(profile, sec_off);
- /* Skip 'AQ', 'note' and 'name' sections */
- if (sec->section.type != SECTION_TYPE_MMIO)
+ /* Skip any non-rollback sections */
+ if (sec->section.type != SECTION_TYPE_RB_MMIO)
continue;
section_size = sec->section.size +
sizeof(struct i40e_profile_section_header);
- /* Write profile */
+ /* Write roll-back MMIO section */
status = i40e_aq_write_ddp(hw, (void *)sec, (u16)section_size,
track_id, &offset, &info, NULL);
if (status) {
i40e_debug(hw, I40E_DEBUG_PACKAGE,
- "Failed to write profile: offset %d, info %d",
- offset, info);
+ "Failed to write profile: section %d, offset %d, info %d\n",
+ i, offset, info);
break;
}
}
/**
* i40e_init_dcb
* @hw: pointer to the hw struct
+ * @enable_mib_change: enable mib change event
*
* Update DCB configuration from the Firmware
**/
-i40e_status i40e_init_dcb(struct i40e_hw *hw)
+i40e_status i40e_init_dcb(struct i40e_hw *hw, bool enable_mib_change)
{
i40e_status ret = 0;
struct i40e_lldp_variables lldp_cfg;
u8 adminstatus = 0;
if (!hw->func_caps.dcb)
- return ret;
+ return I40E_NOT_SUPPORTED;
/* Read LLDP NVM area */
ret = i40e_read_lldp_cfg(hw, &lldp_cfg);
if (ret)
- return ret;
+ return I40E_ERR_NOT_READY;
/* Get the LLDP AdminStatus for the current port */
adminstatus = lldp_cfg.adminstatus >> (hw->port * 4);
/* LLDP agent disabled */
if (!adminstatus) {
hw->dcbx_status = I40E_DCBX_STATUS_DISABLED;
- return ret;
+ return I40E_ERR_NOT_READY;
}
/* Get DCBX status */
return ret;
/* Check the DCBX Status */
- switch (hw->dcbx_status) {
- case I40E_DCBX_STATUS_DONE:
- case I40E_DCBX_STATUS_IN_PROGRESS:
+ if (hw->dcbx_status == I40E_DCBX_STATUS_DONE ||
+ hw->dcbx_status == I40E_DCBX_STATUS_IN_PROGRESS) {
/* Get current DCBX configuration */
ret = i40e_get_dcb_config(hw);
if (ret)
return ret;
- break;
- case I40E_DCBX_STATUS_DISABLED:
- return ret;
- case I40E_DCBX_STATUS_NOT_STARTED:
- case I40E_DCBX_STATUS_MULTIPLE_PEERS:
- default:
- break;
+ } else if (hw->dcbx_status == I40E_DCBX_STATUS_DISABLED) {
+ return I40E_ERR_NOT_READY;
}
/* Configure the LLDP MIB change event */
- ret = i40e_aq_cfg_lldp_mib_change_event(hw, true, NULL);
- if (ret)
- return ret;
+ if (enable_mib_change)
+ ret = i40e_aq_cfg_lldp_mib_change_event(hw, true, NULL);
return ret;
}
u8 bridgetype,
struct i40e_dcbx_config *dcbcfg);
i40e_status i40e_get_dcb_config(struct i40e_hw *hw);
-i40e_status i40e_init_dcb(struct i40e_hw *hw);
+i40e_status i40e_init_dcb(struct i40e_hw *hw, bool enable_mib_change);
#endif /* _I40E_DCB_H_ */
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
+
+#include "i40e.h"
+
+#include <linux/firmware.h>
+
+/**
+ * i40e_ddp_profiles_eq - checks if DDP profiles are the equivalent
+ * @a: new profile info
+ * @b: old profile info
+ *
+ * checks if DDP profiles are the equivalent.
+ * Returns true if profiles are the same.
+ **/
+static bool i40e_ddp_profiles_eq(struct i40e_profile_info *a,
+ struct i40e_profile_info *b)
+{
+ return a->track_id == b->track_id &&
+ !memcmp(&a->version, &b->version, sizeof(a->version)) &&
+ !memcmp(&a->name, &b->name, I40E_DDP_NAME_SIZE);
+}
+
+/**
+ * i40e_ddp_does_profile_exist - checks if DDP profile loaded already
+ * @hw: HW data structure
+ * @pinfo: DDP profile information structure
+ *
+ * checks if DDP profile loaded already.
+ * Returns >0 if the profile exists.
+ * Returns 0 if the profile is absent.
+ * Returns <0 if error.
+ **/
+static int i40e_ddp_does_profile_exist(struct i40e_hw *hw,
+ struct i40e_profile_info *pinfo)
+{
+ struct i40e_ddp_profile_list *profile_list;
+ u8 buff[I40E_PROFILE_LIST_SIZE];
+ i40e_status status;
+ int i;
+
+ status = i40e_aq_get_ddp_list(hw, buff, I40E_PROFILE_LIST_SIZE, 0,
+ NULL);
+ if (status)
+ return -1;
+
+ profile_list = (struct i40e_ddp_profile_list *)buff;
+ for (i = 0; i < profile_list->p_count; i++) {
+ if (i40e_ddp_profiles_eq(pinfo, &profile_list->p_info[i]))
+ return 1;
+ }
+ return 0;
+}
+
+/**
+ * i40e_ddp_profiles_overlap - checks if DDP profiles overlap.
+ * @new: new profile info
+ * @old: old profile info
+ *
+ * checks if DDP profiles overlap.
+ * Returns true if profiles are overlap.
+ **/
+static bool i40e_ddp_profiles_overlap(struct i40e_profile_info *new,
+ struct i40e_profile_info *old)
+{
+ unsigned int group_id_old = (u8)((old->track_id & 0x00FF0000) >> 16);
+ unsigned int group_id_new = (u8)((new->track_id & 0x00FF0000) >> 16);
+
+ /* 0x00 group must be only the first */
+ if (group_id_new == 0)
+ return true;
+ /* 0xFF group is compatible with anything else */
+ if (group_id_new == 0xFF || group_id_old == 0xFF)
+ return false;
+ /* otherwise only profiles from the same group are compatible*/
+ return group_id_old != group_id_new;
+}
+
+/**
+ * i40e_ddp_does_profiles_ - checks if DDP overlaps with existing one.
+ * @hw: HW data structure
+ * @pinfo: DDP profile information structure
+ *
+ * checks if DDP profile overlaps with existing one.
+ * Returns >0 if the profile overlaps.
+ * Returns 0 if the profile is ok.
+ * Returns <0 if error.
+ **/
+static int i40e_ddp_does_profile_overlap(struct i40e_hw *hw,
+ struct i40e_profile_info *pinfo)
+{
+ struct i40e_ddp_profile_list *profile_list;
+ u8 buff[I40E_PROFILE_LIST_SIZE];
+ i40e_status status;
+ int i;
+
+ status = i40e_aq_get_ddp_list(hw, buff, I40E_PROFILE_LIST_SIZE, 0,
+ NULL);
+ if (status)
+ return -EIO;
+
+ profile_list = (struct i40e_ddp_profile_list *)buff;
+ for (i = 0; i < profile_list->p_count; i++) {
+ if (i40e_ddp_profiles_overlap(pinfo,
+ &profile_list->p_info[i]))
+ return 1;
+ }
+ return 0;
+}
+
+/**
+ * i40e_add_pinfo
+ * @hw: pointer to the hardware structure
+ * @profile: pointer to the profile segment of the package
+ * @profile_info_sec: buffer for information section
+ * @track_id: package tracking id
+ *
+ * Register a profile to the list of loaded profiles.
+ */
+static enum i40e_status_code
+i40e_add_pinfo(struct i40e_hw *hw, struct i40e_profile_segment *profile,
+ u8 *profile_info_sec, u32 track_id)
+{
+ struct i40e_profile_section_header *sec;
+ struct i40e_profile_info *pinfo;
+ i40e_status status;
+ u32 offset = 0, info = 0;
+
+ sec = (struct i40e_profile_section_header *)profile_info_sec;
+ sec->tbl_size = 1;
+ sec->data_end = sizeof(struct i40e_profile_section_header) +
+ sizeof(struct i40e_profile_info);
+ sec->section.type = SECTION_TYPE_INFO;
+ sec->section.offset = sizeof(struct i40e_profile_section_header);
+ sec->section.size = sizeof(struct i40e_profile_info);
+ pinfo = (struct i40e_profile_info *)(profile_info_sec +
+ sec->section.offset);
+ pinfo->track_id = track_id;
+ pinfo->version = profile->version;
+ pinfo->op = I40E_DDP_ADD_TRACKID;
+
+ /* Clear reserved field */
+ memset(pinfo->reserved, 0, sizeof(pinfo->reserved));
+ memcpy(pinfo->name, profile->name, I40E_DDP_NAME_SIZE);
+
+ status = i40e_aq_write_ddp(hw, (void *)sec, sec->data_end,
+ track_id, &offset, &info, NULL);
+ return status;
+}
+
+/**
+ * i40e_del_pinfo - delete DDP profile info from NIC
+ * @hw: HW data structure
+ * @profile: DDP profile segment to be deleted
+ * @profile_info_sec: DDP profile section header
+ * @track_id: track ID of the profile for deletion
+ *
+ * Removes DDP profile from the NIC.
+ **/
+static enum i40e_status_code
+i40e_del_pinfo(struct i40e_hw *hw, struct i40e_profile_segment *profile,
+ u8 *profile_info_sec, u32 track_id)
+{
+ struct i40e_profile_section_header *sec;
+ struct i40e_profile_info *pinfo;
+ i40e_status status;
+ u32 offset = 0, info = 0;
+
+ sec = (struct i40e_profile_section_header *)profile_info_sec;
+ sec->tbl_size = 1;
+ sec->data_end = sizeof(struct i40e_profile_section_header) +
+ sizeof(struct i40e_profile_info);
+ sec->section.type = SECTION_TYPE_INFO;
+ sec->section.offset = sizeof(struct i40e_profile_section_header);
+ sec->section.size = sizeof(struct i40e_profile_info);
+ pinfo = (struct i40e_profile_info *)(profile_info_sec +
+ sec->section.offset);
+ pinfo->track_id = track_id;
+ pinfo->version = profile->version;
+ pinfo->op = I40E_DDP_REMOVE_TRACKID;
+
+ /* Clear reserved field */
+ memset(pinfo->reserved, 0, sizeof(pinfo->reserved));
+ memcpy(pinfo->name, profile->name, I40E_DDP_NAME_SIZE);
+
+ status = i40e_aq_write_ddp(hw, (void *)sec, sec->data_end,
+ track_id, &offset, &info, NULL);
+ return status;
+}
+
+/**
+ * i40e_ddp_is_pkg_hdr_valid - performs basic pkg header integrity checks
+ * @netdev: net device structure (for logging purposes)
+ * @pkg_hdr: pointer to package header
+ * @size_huge: size of the whole DDP profile package in size_t
+ *
+ * Checks correctness of pkg header: Version, size too big/small, and
+ * all segment offsets alignment and boundaries. This function lets
+ * reject non DDP profile file to be loaded by administrator mistake.
+ **/
+static bool i40e_ddp_is_pkg_hdr_valid(struct net_device *netdev,
+ struct i40e_package_header *pkg_hdr,
+ size_t size_huge)
+{
+ u32 size = 0xFFFFFFFFU & size_huge;
+ u32 pkg_hdr_size;
+ u32 segment;
+
+ if (!pkg_hdr)
+ return false;
+
+ if (pkg_hdr->version.major > 0) {
+ struct i40e_ddp_version ver = pkg_hdr->version;
+
+ netdev_err(netdev, "Unsupported DDP profile version %u.%u.%u.%u",
+ ver.major, ver.minor, ver.update, ver.draft);
+ return false;
+ }
+ if (size_huge > size) {
+ netdev_err(netdev, "Invalid DDP profile - size is bigger than 4G");
+ return false;
+ }
+ if (size < (sizeof(struct i40e_package_header) +
+ sizeof(struct i40e_metadata_segment) + sizeof(u32) * 2)) {
+ netdev_err(netdev, "Invalid DDP profile - size is too small.");
+ return false;
+ }
+
+ pkg_hdr_size = sizeof(u32) * (pkg_hdr->segment_count + 2U);
+ if (size < pkg_hdr_size) {
+ netdev_err(netdev, "Invalid DDP profile - too many segments");
+ return false;
+ }
+ for (segment = 0; segment < pkg_hdr->segment_count; ++segment) {
+ u32 offset = pkg_hdr->segment_offset[segment];
+
+ if (0xFU & offset) {
+ netdev_err(netdev,
+ "Invalid DDP profile %u segment alignment",
+ segment);
+ return false;
+ }
+ if (pkg_hdr_size > offset || offset >= size) {
+ netdev_err(netdev,
+ "Invalid DDP profile %u segment offset",
+ segment);
+ return false;
+ }
+ }
+
+ return true;
+}
+
+/**
+ * i40e_ddp_load - performs DDP loading
+ * @netdev: net device structure
+ * @data: buffer containing recipe file
+ * @size: size of the buffer
+ * @is_add: true when loading profile, false when rolling back the previous one
+ *
+ * Checks correctness and loads DDP profile to the NIC. The function is
+ * also used for rolling back previously loaded profile.
+ **/
+int i40e_ddp_load(struct net_device *netdev, const u8 *data, size_t size,
+ bool is_add)
+{
+ u8 profile_info_sec[sizeof(struct i40e_profile_section_header) +
+ sizeof(struct i40e_profile_info)];
+ struct i40e_metadata_segment *metadata_hdr;
+ struct i40e_profile_segment *profile_hdr;
+ struct i40e_profile_info pinfo;
+ struct i40e_package_header *pkg_hdr;
+ i40e_status status;
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_vsi *vsi = np->vsi;
+ struct i40e_pf *pf = vsi->back;
+ u32 track_id;
+ int istatus;
+
+ pkg_hdr = (struct i40e_package_header *)data;
+ if (!i40e_ddp_is_pkg_hdr_valid(netdev, pkg_hdr, size))
+ return -EINVAL;
+
+ if (size < (sizeof(struct i40e_package_header) +
+ sizeof(struct i40e_metadata_segment) + sizeof(u32) * 2)) {
+ netdev_err(netdev, "Invalid DDP recipe size.");
+ return -EINVAL;
+ }
+
+ /* Find beginning of segment data in buffer */
+ metadata_hdr = (struct i40e_metadata_segment *)
+ i40e_find_segment_in_package(SEGMENT_TYPE_METADATA, pkg_hdr);
+ if (!metadata_hdr) {
+ netdev_err(netdev, "Failed to find metadata segment in DDP recipe.");
+ return -EINVAL;
+ }
+
+ track_id = metadata_hdr->track_id;
+ profile_hdr = (struct i40e_profile_segment *)
+ i40e_find_segment_in_package(SEGMENT_TYPE_I40E, pkg_hdr);
+ if (!profile_hdr) {
+ netdev_err(netdev, "Failed to find profile segment in DDP recipe.");
+ return -EINVAL;
+ }
+
+ pinfo.track_id = track_id;
+ pinfo.version = profile_hdr->version;
+ if (is_add)
+ pinfo.op = I40E_DDP_ADD_TRACKID;
+ else
+ pinfo.op = I40E_DDP_REMOVE_TRACKID;
+
+ memcpy(pinfo.name, profile_hdr->name, I40E_DDP_NAME_SIZE);
+
+ /* Check if profile data already exists*/
+ istatus = i40e_ddp_does_profile_exist(&pf->hw, &pinfo);
+ if (istatus < 0) {
+ netdev_err(netdev, "Failed to fetch loaded profiles.");
+ return istatus;
+ }
+ if (is_add) {
+ if (istatus > 0) {
+ netdev_err(netdev, "DDP profile already loaded.");
+ return -EINVAL;
+ }
+ istatus = i40e_ddp_does_profile_overlap(&pf->hw, &pinfo);
+ if (istatus < 0) {
+ netdev_err(netdev, "Failed to fetch loaded profiles.");
+ return istatus;
+ }
+ if (istatus > 0) {
+ netdev_err(netdev, "DDP profile overlaps with existing one.");
+ return -EINVAL;
+ }
+ } else {
+ if (istatus == 0) {
+ netdev_err(netdev,
+ "DDP profile for deletion does not exist.");
+ return -EINVAL;
+ }
+ }
+
+ /* Load profile data */
+ if (is_add) {
+ status = i40e_write_profile(&pf->hw, profile_hdr, track_id);
+ if (status) {
+ if (status == I40E_ERR_DEVICE_NOT_SUPPORTED) {
+ netdev_err(netdev,
+ "Profile is not supported by the device.");
+ return -EPERM;
+ }
+ netdev_err(netdev, "Failed to write DDP profile.");
+ return -EIO;
+ }
+ } else {
+ status = i40e_rollback_profile(&pf->hw, profile_hdr, track_id);
+ if (status) {
+ netdev_err(netdev, "Failed to remove DDP profile.");
+ return -EIO;
+ }
+ }
+
+ /* Add/remove profile to/from profile list in FW */
+ if (is_add) {
+ status = i40e_add_pinfo(&pf->hw, profile_hdr, profile_info_sec,
+ track_id);
+ if (status) {
+ netdev_err(netdev, "Failed to add DDP profile info.");
+ return -EIO;
+ }
+ } else {
+ status = i40e_del_pinfo(&pf->hw, profile_hdr, profile_info_sec,
+ track_id);
+ if (status) {
+ netdev_err(netdev, "Failed to restore DDP profile info.");
+ return -EIO;
+ }
+ }
+
+ return 0;
+}
+
+/**
+ * i40e_ddp_restore - restore previously loaded profile and remove from list
+ * @pf: PF data struct
+ *
+ * Restores previously loaded profile stored on the list in driver memory.
+ * After rolling back removes entry from the list.
+ **/
+static int i40e_ddp_restore(struct i40e_pf *pf)
+{
+ struct i40e_ddp_old_profile_list *entry;
+ struct net_device *netdev = pf->vsi[pf->lan_vsi]->netdev;
+ int status = 0;
+
+ if (!list_empty(&pf->ddp_old_prof)) {
+ entry = list_first_entry(&pf->ddp_old_prof,
+ struct i40e_ddp_old_profile_list,
+ list);
+ status = i40e_ddp_load(netdev, entry->old_ddp_buf,
+ entry->old_ddp_size, false);
+ list_del(&entry->list);
+ kfree(entry);
+ }
+ return status;
+}
+
+/**
+ * i40e_ddp_flash - callback function for ethtool flash feature
+ * @netdev: net device structure
+ * @flash: kernel flash structure
+ *
+ * Ethtool callback function used for loading and unloading DDP profiles.
+ **/
+int i40e_ddp_flash(struct net_device *netdev, struct ethtool_flash *flash)
+{
+ const struct firmware *ddp_config;
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_vsi *vsi = np->vsi;
+ struct i40e_pf *pf = vsi->back;
+ int status = 0;
+
+ /* Check for valid region first */
+ if (flash->region != I40_DDP_FLASH_REGION) {
+ netdev_err(netdev, "Requested firmware region is not recognized by this driver.");
+ return -EINVAL;
+ }
+ if (pf->hw.bus.func != 0) {
+ netdev_err(netdev, "Any DDP operation is allowed only on Phy0 NIC interface");
+ return -EINVAL;
+ }
+
+ /* If the user supplied "-" instead of file name rollback previously
+ * stored profile.
+ */
+ if (strncmp(flash->data, "-", 2) != 0) {
+ struct i40e_ddp_old_profile_list *list_entry;
+ char profile_name[sizeof(I40E_DDP_PROFILE_PATH)
+ + I40E_DDP_PROFILE_NAME_MAX];
+
+ profile_name[sizeof(profile_name) - 1] = 0;
+ strncpy(profile_name, I40E_DDP_PROFILE_PATH,
+ sizeof(profile_name) - 1);
+ strncat(profile_name, flash->data, I40E_DDP_PROFILE_NAME_MAX);
+ /* Load DDP recipe. */
+ status = request_firmware(&ddp_config, profile_name,
+ &netdev->dev);
+ if (status) {
+ netdev_err(netdev, "DDP recipe file request failed.");
+ return status;
+ }
+
+ status = i40e_ddp_load(netdev, ddp_config->data,
+ ddp_config->size, true);
+
+ if (!status) {
+ list_entry =
+ kzalloc(sizeof(struct i40e_ddp_old_profile_list) +
+ ddp_config->size, GFP_KERNEL);
+ if (!list_entry) {
+ netdev_info(netdev, "Failed to allocate memory for previous DDP profile data.");
+ netdev_info(netdev, "New profile loaded but roll-back will be impossible.");
+ } else {
+ memcpy(list_entry->old_ddp_buf,
+ ddp_config->data, ddp_config->size);
+ list_entry->old_ddp_size = ddp_config->size;
+ list_add(&list_entry->list, &pf->ddp_old_prof);
+ }
+ }
+
+ release_firmware(ddp_config);
+ } else {
+ if (!list_empty(&pf->ddp_old_prof)) {
+ status = i40e_ddp_restore(pf);
+ } else {
+ netdev_warn(netdev, "There is no DDP profile to restore.");
+ status = -ENOENT;
+ }
+ }
+ return status;
+}
ethtool_link_ksettings_add_link_mode(ks, advertising,
1000baseT_Full);
}
- if (phy_types & I40E_CAP_PHY_TYPE_40GBASE_SR4)
+ if (phy_types & I40E_CAP_PHY_TYPE_40GBASE_SR4) {
ethtool_link_ksettings_add_link_mode(ks, supported,
40000baseSR4_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 40000baseSR4_Full);
+ }
if (phy_types & I40E_CAP_PHY_TYPE_40GBASE_LR4)
ethtool_link_ksettings_add_link_mode(ks, supported,
40000baseLR4_Full);
case I40E_PHY_TYPE_40GBASE_SR4:
ethtool_link_ksettings_add_link_mode(ks, supported,
40000baseSR4_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 40000baseSR4_Full);
break;
case I40E_PHY_TYPE_40GBASE_LR4:
ethtool_link_ksettings_add_link_mode(ks, supported,
return -EOPNOTSUPP;
/* only magic packet is supported */
- if (wol->wolopts && (wol->wolopts != WAKE_MAGIC)
- | (wol->wolopts != WAKE_FILTER))
+ if (wol->wolopts & ~WAKE_MAGIC)
return -EOPNOTSUPP;
/* is this a new value? */
.set_link_ksettings = i40e_set_link_ksettings,
.get_fecparam = i40e_get_fec_param,
.set_fecparam = i40e_set_fec_param,
+ .flash_device = i40e_ddp_flash,
};
void i40e_set_ethtool_ops(struct net_device *netdev)
fcnt = i40e_update_filter_state(num_add, list, add_head);
if (fcnt != num_add) {
- set_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state);
- dev_warn(&vsi->back->pdev->dev,
- "Error %s adding RX filters on %s, promiscuous mode forced on\n",
- i40e_aq_str(hw, aq_err),
- vsi_name);
+ if (vsi->type == I40E_VSI_MAIN) {
+ set_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state);
+ dev_warn(&vsi->back->pdev->dev,
+ "Error %s adding RX filters on %s, promiscuous mode forced on\n",
+ i40e_aq_str(hw, aq_err), vsi_name);
+ } else if (vsi->type == I40E_VSI_SRIOV ||
+ vsi->type == I40E_VSI_VMDQ1 ||
+ vsi->type == I40E_VSI_VMDQ2) {
+ dev_warn(&vsi->back->pdev->dev,
+ "Error %s adding RX filters on %s, please set promiscuous on manually for %s\n",
+ i40e_aq_str(hw, aq_err), vsi_name, vsi_name);
+ } else {
+ dev_warn(&vsi->back->pdev->dev,
+ "Error %s adding RX filters on %s, incorrect VSI type: %i.\n",
+ i40e_aq_str(hw, aq_err), vsi_name, vsi->type);
+ }
}
}
struct i40e_vsi_context ctxt;
i40e_status ret;
+ /* Don't modify stripping options if a port VLAN is active */
+ if (vsi->info.pvid)
+ return;
+
if ((vsi->info.valid_sections &
cpu_to_le16(I40E_AQ_VSI_PROP_VLAN_VALID)) &&
((vsi->info.port_vlan_flags & I40E_AQ_VSI_PVLAN_MODE_MASK) == 0))
struct i40e_vsi_context ctxt;
i40e_status ret;
+ /* Don't modify stripping options if a port VLAN is active */
+ if (vsi->info.pvid)
+ return;
+
if ((vsi->info.valid_sections &
cpu_to_le16(I40E_AQ_VSI_PROP_VLAN_VALID)) &&
((vsi->info.port_vlan_flags & I40E_AQ_VSI_PVLAN_EMOD_MASK) ==
ring->queue_index);
}
+/**
+ * i40e_xsk_umem - Retrieve the AF_XDP ZC if XDP and ZC is enabled
+ * @ring: The Tx or Rx ring
+ *
+ * Returns the UMEM or NULL.
+ **/
+static struct xdp_umem *i40e_xsk_umem(struct i40e_ring *ring)
+{
+ bool xdp_on = i40e_enabled_xdp_vsi(ring->vsi);
+ int qid = ring->queue_index;
+
+ if (ring_is_xdp(ring))
+ qid -= ring->vsi->alloc_queue_pairs;
+
+ if (!xdp_on || !test_bit(qid, ring->vsi->af_xdp_zc_qps))
+ return NULL;
+
+ return xdp_get_umem_from_qid(ring->vsi->netdev, qid);
+}
+
/**
* i40e_configure_tx_ring - Configure a transmit ring context and rest
* @ring: The Tx ring to configure
goto out;
/* Get the initial DCB configuration */
- err = i40e_init_dcb(hw);
+ err = i40e_init_dcb(hw, true);
if (!err) {
/* Device/Function is not DCBX capable */
if ((!hw->func_caps.dcb) ||
struct i40e_pf *pf = vsi->back;
u8 enabled_tc = 0, num_tc, hw;
bool need_reset = false;
+ int old_queue_pairs;
int ret = -EINVAL;
u16 mode;
int i;
+ old_queue_pairs = vsi->num_queue_pairs;
num_tc = mqprio_qopt->qopt.num_tc;
hw = mqprio_qopt->qopt.hw;
mode = mqprio_qopt->mode;
}
ret = i40e_configure_queue_channels(vsi);
if (ret) {
+ vsi->num_queue_pairs = old_queue_pairs;
netdev_info(netdev,
"Failed configuring queue channels\n");
need_reset = true;
dev_warn(&pf->pdev->dev,
"shutdown_lan_hmc failed: %d\n", ret);
}
+
+ /* Save the current PTP time so that we can restore the time after the
+ * reset completes.
+ */
+ i40e_ptp_save_hw_time(pf);
}
/**
hash_init(vsi->mac_filter_hash);
vsi->irqs_ready = false;
+ if (type == I40E_VSI_MAIN) {
+ vsi->af_xdp_zc_qps = bitmap_zalloc(pf->num_lan_qps, GFP_KERNEL);
+ if (!vsi->af_xdp_zc_qps)
+ goto err_rings;
+ }
+
ret = i40e_set_num_rings_in_vsi(vsi);
if (ret)
goto err_rings;
goto unlock_pf;
err_rings:
+ bitmap_free(vsi->af_xdp_zc_qps);
pf->next_vsi = i - 1;
kfree(vsi);
unlock_pf:
i40e_put_lump(pf->qp_pile, vsi->base_queue, vsi->idx);
i40e_put_lump(pf->irq_pile, vsi->base_vector, vsi->idx);
+ bitmap_free(vsi->af_xdp_zc_qps);
i40e_vsi_free_arrays(vsi, true);
i40e_clear_rss_config_user(vsi);
INIT_LIST_HEAD(&pf->l3_flex_pit_list);
INIT_LIST_HEAD(&pf->l4_flex_pit_list);
+ INIT_LIST_HEAD(&pf->ddp_old_prof);
/* set up the locks for the AQ, do this only once in probe
* and destroy them only once in remove
if (err) {
if (err == I40E_ERR_FIRMWARE_API_VERSION)
dev_info(&pdev->dev,
- "The driver for the device stopped because the NVM image is newer than expected. You must install the most recent version of the network driver.\n");
+ "The driver for the device stopped because the NVM image v%u.%u is newer than expected v%u.%u. You must install the most recent version of the network driver.\n",
+ hw->aq.api_maj_ver,
+ hw->aq.api_min_ver,
+ I40E_FW_API_VERSION_MAJOR,
+ I40E_FW_MINOR_VERSION(hw));
else
dev_info(&pdev->dev,
"The driver for the device stopped because the device firmware failed to init. Try updating your NVM image.\n");
if (hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR &&
hw->aq.api_min_ver > I40E_FW_MINOR_VERSION(hw))
dev_info(&pdev->dev,
- "The driver for the device detected a newer version of the NVM image than expected. Please install the most recent version of the network driver.\n");
+ "The driver for the device detected a newer version of the NVM image v%u.%u than expected v%u.%u. Please install the most recent version of the network driver.\n",
+ hw->aq.api_maj_ver,
+ hw->aq.api_min_ver,
+ I40E_FW_API_VERSION_MAJOR,
+ I40E_FW_MINOR_VERSION(hw));
else if (hw->aq.api_maj_ver == 1 && hw->aq.api_min_ver < 4)
dev_info(&pdev->dev,
- "The driver for the device detected an older version of the NVM image than expected. Please update the NVM image.\n");
+ "The driver for the device detected an older version of the NVM image v%u.%u than expected v%u.%u. Please update the NVM image.\n",
+ hw->aq.api_maj_ver,
+ hw->aq.api_min_ver,
+ I40E_FW_API_VERSION_MAJOR,
+ I40E_FW_MINOR_VERSION(hw));
i40e_verify_eeprom(pf);
struct i40e_generic_seg_header *
i40e_find_segment_in_package(u32 segment_type,
struct i40e_package_header *pkg_header);
+struct i40e_profile_section_header *
+i40e_find_section_in_profile(u32 section_type,
+ struct i40e_profile_segment *profile);
enum i40e_status_code
i40e_write_profile(struct i40e_hw *hw, struct i40e_profile_segment *i40e_seg,
u32 track_id);
enum i40e_status_code
+i40e_rollback_profile(struct i40e_hw *hw, struct i40e_profile_segment *i40e_seg,
+ u32 track_id);
+enum i40e_status_code
i40e_add_pinfo_to_list(struct i40e_hw *hw,
struct i40e_profile_segment *profile,
u8 *profile_info_sec, u32 track_id);
static int i40e_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
{
struct i40e_pf *pf = container_of(ptp, struct i40e_pf, ptp_caps);
- struct timespec64 now;
+ struct timespec64 now, then;
+ then = ns_to_timespec64(delta);
mutex_lock(&pf->tmreg_lock);
i40e_ptp_read(pf, &now, NULL);
- timespec64_add_ns(&now, delta);
+ now = timespec64_add(now, then);
i40e_ptp_write(pf, (const struct timespec64 *)&now);
mutex_unlock(&pf->tmreg_lock);
pf->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;
pf->tstamp_config.tx_type = HWTSTAMP_TX_OFF;
+ /* Set the previous "reset" time to the current Kernel clock time */
+ pf->ptp_prev_hw_time = ktime_to_timespec64(ktime_get_real());
+ pf->ptp_reset_start = ktime_get();
+
return 0;
}
+/**
+ * i40e_ptp_save_hw_time - Save the current PTP time as ptp_prev_hw_time
+ * @pf: Board private structure
+ *
+ * Read the current PTP time and save it into pf->ptp_prev_hw_time. This should
+ * be called at the end of preparing to reset, just before hardware reset
+ * occurs, in order to preserve the PTP time as close as possible across
+ * resets.
+ */
+void i40e_ptp_save_hw_time(struct i40e_pf *pf)
+{
+ /* don't try to access the PTP clock if it's not enabled */
+ if (!(pf->flags & I40E_FLAG_PTP))
+ return;
+
+ i40e_ptp_gettimex(&pf->ptp_caps, &pf->ptp_prev_hw_time, NULL);
+ /* Get a monotonic starting time for this reset */
+ pf->ptp_reset_start = ktime_get();
+}
+
+/**
+ * i40e_ptp_restore_hw_time - Restore the ptp_prev_hw_time + delta to PTP regs
+ * @pf: Board private structure
+ *
+ * Restore the PTP hardware clock registers. We previously cached the PTP
+ * hardware time as pf->ptp_prev_hw_time. To be as accurate as possible,
+ * update this value based on the time delta since the time was saved, using
+ * CLOCK_MONOTONIC (via ktime_get()) to calculate the time difference.
+ *
+ * This ensures that the hardware clock is restored to nearly what it should
+ * have been if a reset had not occurred.
+ */
+void i40e_ptp_restore_hw_time(struct i40e_pf *pf)
+{
+ ktime_t delta = ktime_sub(ktime_get(), pf->ptp_reset_start);
+
+ /* Update the previous HW time with the ktime delta */
+ timespec64_add_ns(&pf->ptp_prev_hw_time, ktime_to_ns(delta));
+
+ /* Restore the hardware clock registers */
+ i40e_ptp_settime(&pf->ptp_caps, &pf->ptp_prev_hw_time);
+}
+
/**
* i40e_ptp_init - Initialize the 1588 support after device probe or reset
* @pf: Board private structure
* This function sets device up for 1588 support. The first time it is run, it
* will create a PHC clock device. It does not create a clock device if one
* already exists. It also reconfigures the device after a reset.
+ *
+ * The first time a clock is created, i40e_ptp_create_clock will set
+ * pf->ptp_prev_hw_time to the current system time. During resets, it is
+ * expected that this timespec will be set to the last known PTP clock time,
+ * in order to preserve the clock time as close as possible across a reset.
**/
void i40e_ptp_init(struct i40e_pf *pf)
{
dev_err(&pf->pdev->dev, "%s: ptp_clock_register failed\n",
__func__);
} else if (pf->ptp_clock) {
- struct timespec64 ts;
u32 regval;
if (pf->hw.debug_mask & I40E_DEBUG_LAN)
/* reset timestamping mode */
i40e_ptp_set_timestamp_mode(pf, &pf->tstamp_config);
- /* Set the clock value. */
- ts = ktime_to_timespec64(ktime_get_real());
- i40e_ptp_settime(&pf->ptp_caps, &ts);
+ /* Restore the clock time based on last known value */
+ i40e_ptp_restore_hw_time(pf);
}
}
first->next_to_watch = tx_desc;
/* notify HW of packet */
- if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
+ if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) {
writel(i, tx_ring->tail);
/* we need this if more than one processor can write to our tail
struct i40e_metadata_segment {
struct i40e_generic_seg_header header;
struct i40e_ddp_version version;
+#define I40E_DDP_TRACKID_RDONLY 0
+#define I40E_DDP_TRACKID_INVALID 0xFFFFFFFF
u32 track_id;
char name[I40E_DDP_NAME_SIZE];
};
struct {
#define SECTION_TYPE_INFO 0x00000010
#define SECTION_TYPE_MMIO 0x00000800
+#define SECTION_TYPE_RB_MMIO 0x00001800
#define SECTION_TYPE_AQ 0x00000801
+#define SECTION_TYPE_RB_AQ 0x00001801
#define SECTION_TYPE_NOTE 0x80000000
#define SECTION_TYPE_NAME 0x80000001
+#define SECTION_TYPE_PROTO 0x80000002
+#define SECTION_TYPE_PCTYPE 0x80000003
+#define SECTION_TYPE_PTYPE 0x80000004
u32 type;
u32 offset;
u32 size;
} section;
};
+struct i40e_profile_tlv_section_record {
+ u8 rtype;
+ u8 type;
+ u16 len;
+ u8 data[12];
+};
+
+/* Generic AQ section in proflie */
+struct i40e_profile_aq_section {
+ u16 opcode;
+ u16 flags;
+ u8 param[16];
+ u16 datalen;
+ u8 data[1];
+};
+
struct i40e_profile_info {
u32 track_id;
struct i40e_ddp_version version;
(u8 *)&stats, sizeof(stats));
}
-/* If the VF is not trusted restrict the number of MAC/VLAN it can program */
-#define I40E_VC_MAX_MAC_ADDR_PER_VF 12
+/* If the VF is not trusted restrict the number of MAC/VLAN it can program
+ * MAC filters: 16 for multicast, 1 for MAC, 1 for broadcast
+ */
+#define I40E_VC_MAX_MAC_ADDR_PER_VF (16 + 1 + 1)
#define I40E_VC_MAX_VLAN_PER_VF 8
/**
if (err)
return err;
+ set_bit(qid, vsi->af_xdp_zc_qps);
+
if_running = netif_running(vsi->netdev) && i40e_enabled_xdp_vsi(vsi);
if (if_running) {
return err;
}
+ clear_bit(qid, vsi->af_xdp_zc_qps);
i40e_xsk_umem_dma_unmap(vsi, umem);
if (if_running) {
#define I40E_FW_API_VERSION_MAJOR 0x0001
#define I40E_FW_API_VERSION_MINOR_X722 0x0005
-#define I40E_FW_API_VERSION_MINOR_X710 0x0007
+#define I40E_FW_API_VERSION_MINOR_X710 0x0008
#define I40E_FW_MINOR_VERSION(_h) ((_h)->mac.type == I40E_MAC_XL710 ? \
I40E_FW_API_VERSION_MINOR_X710 : \
first->next_to_watch = tx_desc;
/* notify HW of packet */
- if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
+ if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) {
writel(i, tx_ring->tail);
/* we need this if more than one processor can write to our tail
ice_maybe_stop_tx(tx_ring, DESC_NEEDED);
/* notify HW of packet */
- if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
+ if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) {
writel(i, tx_ring->tail);
/* we need this if more than one processor can write to our tail
/* enable link status from external LINK_0 and LINK_1 pins */
#define E1000_CTRL_SWDPIN0 0x00040000 /* SWDPIN 0 value */
#define E1000_CTRL_SWDPIN1 0x00080000 /* SWDPIN 1 value */
+#define E1000_CTRL_ADVD3WUC 0x00100000 /* D3 WUC */
+#define E1000_CTRL_EN_PHY_PWR_MGMT 0x00200000 /* PHY PM enable */
#define E1000_CTRL_SDP0_DIR 0x00400000 /* SDP0 Data direction */
#define E1000_CTRL_SDP1_DIR 0x00800000 /* SDP1 Data direction */
#define E1000_CTRL_RST 0x04000000 /* Global reset */
/* Make sure there is space in the ring for the next send. */
igb_maybe_stop_tx(tx_ring, DESC_NEEDED);
- if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
+ if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) {
writel(i, tx_ring->tail);
/* we need this if more than one processor can write to our tail
struct e1000_hw *hw = &adapter->hw;
u32 ctrl, rctl, status;
u32 wufc = runtime ? E1000_WUFC_LNKC : adapter->wol;
-#ifdef CONFIG_PM
- int retval = 0;
-#endif
+ bool wake;
rtnl_lock();
netif_device_detach(netdev);
igb_clear_interrupt_scheme(adapter);
rtnl_unlock();
-#ifdef CONFIG_PM
- if (!runtime) {
- retval = pci_save_state(pdev);
- if (retval)
- return retval;
- }
-#endif
-
status = rd32(E1000_STATUS);
if (status & E1000_STATUS_LU)
wufc &= ~E1000_WUFC_LNKC;
}
ctrl = rd32(E1000_CTRL);
- /* advertise wake from D3Cold */
- #define E1000_CTRL_ADVD3WUC 0x00100000
- /* phy power management enable */
- #define E1000_CTRL_EN_PHY_PWR_MGMT 0x00200000
ctrl |= E1000_CTRL_ADVD3WUC;
wr32(E1000_CTRL, ctrl);
wr32(E1000_WUFC, 0);
}
- *enable_wake = wufc || adapter->en_mng_pt;
- if (!*enable_wake)
+ wake = wufc || adapter->en_mng_pt;
+ if (!wake)
igb_power_down_link(adapter);
else
igb_power_up_link(adapter);
+ if (enable_wake)
+ *enable_wake = wake;
+
/* Release control of h/w to f/w. If f/w is AMT enabled, this
* would have already happened in close and is redundant.
*/
static int __maybe_unused igb_suspend(struct device *dev)
{
- int retval;
- bool wake;
- struct pci_dev *pdev = to_pci_dev(dev);
-
- retval = __igb_shutdown(pdev, &wake, 0);
- if (retval)
- return retval;
-
- if (wake) {
- pci_prepare_to_sleep(pdev);
- } else {
- pci_wake_from_d3(pdev, false);
- pci_set_power_state(pdev, PCI_D3hot);
- }
-
- return 0;
+ return __igb_shutdown(to_pci_dev(dev), NULL, 0);
}
static int __maybe_unused igb_resume(struct device *dev)
static int __maybe_unused igb_runtime_suspend(struct device *dev)
{
- struct pci_dev *pdev = to_pci_dev(dev);
- int retval;
- bool wake;
-
- retval = __igb_shutdown(pdev, &wake, 1);
- if (retval)
- return retval;
-
- if (wake) {
- pci_prepare_to_sleep(pdev);
- } else {
- pci_wake_from_d3(pdev, false);
- pci_set_power_state(pdev, PCI_D3hot);
- }
-
- return 0;
+ return __igb_shutdown(to_pci_dev(dev), NULL, 1);
}
static int __maybe_unused igb_runtime_resume(struct device *dev)
/* Make sure there is space in the ring for the next send. */
igc_maybe_stop_tx(tx_ring, DESC_NEEDED);
- if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
+ if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) {
writel(i, tx_ring->tail);
/* we need this if more than one processor can write to our tail
ixgbe_maybe_stop_tx(tx_ring, DESC_NEEDED);
- if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
+ if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) {
writel(i, tx_ring->tail);
/* we need this if more than one processor can write to our tail
struct pci_dev *pdev = adapter->pdev;
struct device *dev = &adapter->netdev->dev;
struct mii_bus *bus;
+ int err = -ENODEV;
- adapter->mii_bus = devm_mdiobus_alloc(dev);
- if (!adapter->mii_bus)
+ bus = devm_mdiobus_alloc(dev);
+ if (!bus)
return -ENOMEM;
- bus = adapter->mii_bus;
-
switch (hw->device_id) {
/* C3000 SoCs */
case IXGBE_DEV_ID_X550EM_A_KR:
*/
hw->phy.mdio.mode_support = MDIO_SUPPORTS_C45 | MDIO_SUPPORTS_C22;
- return mdiobus_register(bus);
+ err = mdiobus_register(bus);
+ if (!err) {
+ adapter->mii_bus = bus;
+ return 0;
+ }
ixgbe_no_mii_bus:
devm_mdiobus_free(dev, bus);
- adapter->mii_bus = NULL;
- return -ENODEV;
+ return err;
}
/**
if (txq->count >= txq->tx_stop_threshold)
netif_tx_stop_queue(nq);
- if (!skb->xmit_more || netif_xmit_stopped(nq) ||
+ if (!netdev_xmit_more() || netif_xmit_stopped(nq) ||
txq->pending + frags > MVNETA_TXQ_DEC_SENT_MASK)
mvneta_txq_pend_desc_add(pp, txq, frags);
else
*/
wmb();
- if (netif_xmit_stopped(netdev_get_tx_queue(dev, 0)) || !skb->xmit_more)
+ if (netif_xmit_stopped(netdev_get_tx_queue(dev, 0)) ||
+ !netdev_xmit_more())
mtk_w32(eth, txd->txd2, MTK_QTX_CTX_PTR);
return 0;
send_doorbell = __netdev_tx_sent_queue(ring->tx_queue,
tx_info->nr_bytes,
- skb->xmit_more);
+ netdev_xmit_more());
real_size = (real_size / 16) & 0x3f;
struct mlx5_cmd *cmd = &dev->cmd;
snprintf(cmd->wq_name, sizeof(cmd->wq_name), "mlx5_cmd_%s",
- dev_name(&dev->pdev->dev));
+ dev->priv.name);
}
static void clean_debug_files(struct mlx5_core_dev *dev)
memset(cmd, 0, sizeof(*cmd));
cmd_if_rev = cmdif_rev(dev);
if (cmd_if_rev != CMD_IF_REV) {
- dev_err(&dev->pdev->dev,
- "Driver cmdif rev(%d) differs from firmware's(%d)\n",
- CMD_IF_REV, cmd_if_rev);
+ mlx5_core_err(dev,
+ "Driver cmdif rev(%d) differs from firmware's(%d)\n",
+ CMD_IF_REV, cmd_if_rev);
return -EINVAL;
}
cmd->log_sz = cmd_l >> 4 & 0xf;
cmd->log_stride = cmd_l & 0xf;
if (1 << cmd->log_sz > MLX5_MAX_COMMANDS) {
- dev_err(&dev->pdev->dev, "firmware reports too many outstanding commands %d\n",
- 1 << cmd->log_sz);
+ mlx5_core_err(dev, "firmware reports too many outstanding commands %d\n",
+ 1 << cmd->log_sz);
err = -EINVAL;
goto err_free_page;
}
if (cmd->log_sz + cmd->log_stride > MLX5_ADAPTER_PAGE_SHIFT) {
- dev_err(&dev->pdev->dev, "command queue size overflow\n");
+ mlx5_core_err(dev, "command queue size overflow\n");
err = -EINVAL;
goto err_free_page;
}
cmd->cmdif_rev = ioread32be(&dev->iseg->cmdif_rev_fw_sub) >> 16;
if (cmd->cmdif_rev > CMD_IF_REV) {
- dev_err(&dev->pdev->dev, "driver does not support command interface version. driver %d, firmware %d\n",
- CMD_IF_REV, cmd->cmdif_rev);
+ mlx5_core_err(dev, "driver does not support command interface version. driver %d, firmware %d\n",
+ CMD_IF_REV, cmd->cmdif_rev);
err = -EOPNOTSUPP;
goto err_free_page;
}
cmd_h = (u32)((u64)(cmd->dma) >> 32);
cmd_l = (u32)(cmd->dma);
if (cmd_l & 0xfff) {
- dev_err(&dev->pdev->dev, "invalid command queue address\n");
+ mlx5_core_err(dev, "invalid command queue address\n");
err = -ENOMEM;
goto err_free_page;
}
set_wqname(dev);
cmd->wq = create_singlethread_workqueue(cmd->wq_name);
if (!cmd->wq) {
- dev_err(&dev->pdev->dev, "failed to create command workqueue\n");
+ mlx5_core_err(dev, "failed to create command workqueue\n");
err = -ENOMEM;
goto err_cache;
}
TP_ARGS(tracer, trace_timestamp, lost, event_id, msg),
TP_STRUCT__entry(
- __string(dev_name, dev_name(&tracer->dev->pdev->dev))
+ __string(dev_name, tracer->dev->priv.name)
__field(u64, trace_timestamp)
__field(bool, lost)
__field(u8, event_id)
),
TP_fast_assign(
- __assign_str(dev_name, dev_name(&tracer->dev->pdev->dev));
+ __assign_str(dev_name, tracer->dev->priv.name);
__entry->trace_timestamp = trace_timestamp;
__entry->lost = lost;
__entry->event_id = event_id;
struct net_dim_cq_moder rx_cq_moderation;
struct net_dim_cq_moder tx_cq_moderation;
bool lro_en;
- u32 lro_wqe_sz;
u8 tx_min_inline_mode;
bool vlan_strip_disable;
bool scatter_fcs_en;
struct net_device *sb_dev);
netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev);
netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
- struct mlx5e_tx_wqe *wqe, u16 pi);
+ struct mlx5e_tx_wqe *wqe, u16 pi, bool xmit_more);
void mlx5e_completion_event(struct mlx5_core_cq *mcq);
void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event);
* switching channels
*/
typedef int (*mlx5e_fp_hw_modify)(struct mlx5e_priv *priv);
+int mlx5e_safe_reopen_channels(struct mlx5e_priv *priv);
int mlx5e_safe_switch_channels(struct mlx5e_priv *priv,
struct mlx5e_channels *new_chs,
mlx5e_fp_hw_modify hw_modify);
*/
wmb();
- mlx5_write64((__be32 *)ctrl, uar_map, NULL);
+ mlx5_write64((__be32 *)ctrl, uar_map);
}
static inline void mlx5e_cq_arm(struct mlx5e_cq *cq)
int mlx5e_attach_netdev(struct mlx5e_priv *priv);
void mlx5e_detach_netdev(struct mlx5e_priv *priv);
void mlx5e_destroy_netdev(struct mlx5e_priv *priv);
+void mlx5e_set_netdev_mtu_boundaries(struct mlx5e_priv *priv);
void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
struct mlx5e_rss_params *rss_params,
struct mlx5e_params *params,
if (!eproto)
return -EINVAL;
- if (ext != MLX5_CAP_PCAM_FEATURE(dev, ptys_extended_ethernet))
- return -EOPNOTSUPP;
-
err = mlx5_query_port_ptys(dev, out, sizeof(out), MLX5_PTYS_EN, port);
if (err)
return err;
return err;
}
-/* xoff = ((301+2.16 * len [m]) * speed [Gbps] + 2.72 MTU [B]) */
+/* xoff = ((301+2.16 * len [m]) * speed [Gbps] + 2.72 MTU [B])
+ * minimum speed value is 40Gbps
+ */
static u32 calculate_xoff(struct mlx5e_priv *priv, unsigned int mtu)
{
u32 speed;
int err;
err = mlx5e_port_linkspeed(priv->mdev, &speed);
- if (err) {
- mlx5_core_warn(priv->mdev, "cannot get port speed\n");
- return 0;
- }
+ if (err)
+ speed = SPEED_40000;
+ speed = max_t(u32, speed, SPEED_40000);
xoff = (301 + 216 * priv->dcbx.cable_len / 100) * speed / 1000 + 272 * mtu / 100;
}
static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer,
- u32 xoff, unsigned int mtu)
+ u32 xoff, unsigned int max_mtu)
{
int i;
}
if (port_buffer->buffer[i].size <
- (xoff + mtu + (1 << MLX5E_BUFFER_CELL_SHIFT)))
+ (xoff + max_mtu + (1 << MLX5E_BUFFER_CELL_SHIFT)))
return -ENOMEM;
port_buffer->buffer[i].xoff = port_buffer->buffer[i].size - xoff;
- port_buffer->buffer[i].xon = port_buffer->buffer[i].xoff - mtu;
+ port_buffer->buffer[i].xon =
+ port_buffer->buffer[i].xoff - max_mtu;
}
return 0;
/**
* update_buffer_lossy - Update buffer configuration based on pfc
- * @mtu: device's MTU
+ * @max_mtu: netdev's max_mtu
* @pfc_en: <input> current pfc configuration
* @buffer: <input> current prio to buffer mapping
* @xoff: <input> xoff value
* @return: 0 if no error,
* sets change to true if buffer configuration was modified.
*/
-static int update_buffer_lossy(unsigned int mtu,
+static int update_buffer_lossy(unsigned int max_mtu,
u8 pfc_en, u8 *buffer, u32 xoff,
struct mlx5e_port_buffer *port_buffer,
bool *change)
}
if (changed) {
- err = update_xoff_threshold(port_buffer, xoff, mtu);
+ err = update_xoff_threshold(port_buffer, xoff, max_mtu);
if (err)
return err;
return 0;
}
+#define MINIMUM_MAX_MTU 9216
int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
u32 change, unsigned int mtu,
struct ieee_pfc *pfc,
bool update_prio2buffer = false;
u8 buffer[MLX5E_MAX_PRIORITY];
bool update_buffer = false;
+ unsigned int max_mtu;
u32 total_used = 0;
u8 curr_pfc_en;
int err;
int i;
mlx5e_dbg(HW, priv, "%s: change=%x\n", __func__, change);
+ max_mtu = max_t(unsigned int, priv->netdev->max_mtu, MINIMUM_MAX_MTU);
err = mlx5e_port_query_buffer(priv, &port_buffer);
if (err)
if (change & MLX5E_PORT_BUFFER_CABLE_LEN) {
update_buffer = true;
- err = update_xoff_threshold(&port_buffer, xoff, mtu);
+ err = update_xoff_threshold(&port_buffer, xoff, max_mtu);
if (err)
return err;
}
if (err)
return err;
- err = update_buffer_lossy(mtu, pfc->pfc_en, buffer, xoff,
+ err = update_buffer_lossy(max_mtu, pfc->pfc_en, buffer, xoff,
&port_buffer, &update_buffer);
if (err)
return err;
if (err)
return err;
- err = update_buffer_lossy(mtu, curr_pfc_en, prio2buffer, xoff,
- &port_buffer, &update_buffer);
+ err = update_buffer_lossy(max_mtu, curr_pfc_en, prio2buffer,
+ xoff, &port_buffer, &update_buffer);
if (err)
return err;
}
return -EINVAL;
update_buffer = true;
- err = update_xoff_threshold(&port_buffer, xoff, mtu);
+ err = update_xoff_threshold(&port_buffer, xoff, max_mtu);
if (err)
return err;
}
/* Need to update buffer configuration if xoff value is changed */
if (!update_buffer && xoff != priv->dcbx.xoff) {
update_buffer = true;
- err = update_xoff_threshold(&port_buffer, xoff, mtu);
+ err = update_xoff_threshold(&port_buffer, xoff, max_mtu);
if (err)
return err;
}
static int mlx5e_tx_reporter_recover_all(struct mlx5e_priv *priv)
{
- int err;
+ int err = 0;
rtnl_lock();
mutex_lock(&priv->state_lock);
- mlx5e_close_locked(priv->netdev);
- err = mlx5e_open_locked(priv->netdev);
+
+ if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+ goto out;
+
+ err = mlx5e_safe_reopen_channels(priv);
+
+out:
mutex_unlock(&priv->state_lock);
rtnl_unlock();
return -EOPNOTSUPP;
}
+ if (!(mlx5e_eswitch_rep(*out_dev) &&
+ mlx5e_is_uplink_rep(netdev_priv(*out_dev))))
+ return -EOPNOTSUPP;
+
return 0;
}
if (ret)
return ret;
- if (mlx5_lag_is_multipath(mdev) && !rt->rt_gateway)
+ if (mlx5_lag_is_multipath(mdev) && rt->rt_gw_family != AF_INET)
return -ENETUNREACH;
#else
return -EOPNOTSUPP;
if (dev->rtnl_link_ops)
return dev->rtnl_link_ops->kind;
else
- return "";
+ return "unknown";
}
static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
headers_c, headers_v);
} else {
netdev_warn(priv->netdev,
- "decapsulation offload is not supported for %s net device (%d)\n",
- mlx5e_netdev_kind(filter_dev), tunnel_type);
+ "decapsulation offload is not supported for %s (kind: \"%s\")\n",
+ netdev_name(filter_dev),
+ mlx5e_netdev_kind(filter_dev));
+
return -EOPNOTSUPP;
}
return err;
*/
nskb->ip_summed = CHECKSUM_PARTIAL;
- nskb->xmit_more = 1;
nskb->queue_mapping = skb->queue_mapping;
}
sq->stats->tls_resync_bytes += nskb->len;
mlx5e_tls_complete_sync_skb(skb, nskb, tcp_seq, headln,
cpu_to_be64(info.rcd_sn));
- mlx5e_sq_xmit(sq, nskb, *wqe, *pi);
+ mlx5e_sq_xmit(sq, nskb, *wqe, *pi, true);
mlx5e_sq_fetch_wqe(sq, wqe, pi);
return skb;
if (err)
return err;
+ mutex_lock(&mdev->mlx5e_res.td.list_lock);
list_add(&tir->list, &mdev->mlx5e_res.td.tirs_list);
+ mutex_unlock(&mdev->mlx5e_res.td.list_lock);
return 0;
}
void mlx5e_destroy_tir(struct mlx5_core_dev *mdev,
struct mlx5e_tir *tir)
{
+ mutex_lock(&mdev->mlx5e_res.td.list_lock);
mlx5_core_destroy_tir(mdev, tir->tirn);
list_del(&tir->list);
+ mutex_unlock(&mdev->mlx5e_res.td.list_lock);
}
static int mlx5e_create_mkey(struct mlx5_core_dev *mdev, u32 pdn,
}
INIT_LIST_HEAD(&mdev->mlx5e_res.td.tirs_list);
+ mutex_init(&mdev->mlx5e_res.td.list_lock);
return 0;
{
struct mlx5_core_dev *mdev = priv->mdev;
struct mlx5e_tir *tir;
- int err = -ENOMEM;
+ int err = 0;
u32 tirn = 0;
int inlen;
void *in;
inlen = MLX5_ST_SZ_BYTES(modify_tir_in);
in = kvzalloc(inlen, GFP_KERNEL);
- if (!in)
+ if (!in) {
+ err = -ENOMEM;
goto out;
+ }
if (enable_uc_lb)
MLX5_SET(modify_tir_in, in, ctx.self_lb_block,
MLX5_SET(modify_tir_in, in, bitmask.self_lb_en, 1);
+ mutex_lock(&mdev->mlx5e_res.td.list_lock);
list_for_each_entry(tir, &mdev->mlx5e_res.td.tirs_list, list) {
tirn = tir->tirn;
err = mlx5_core_modify_tir(mdev, tirn, in, inlen);
kvfree(in);
if (err)
netdev_err(priv->netdev, "refresh tir(0x%x) failed, %d\n", tirn, err);
+ mutex_unlock(&mdev->mlx5e_res.td.list_lock);
return err;
}
__ETHTOOL_LINK_MODE_MASK_NBITS);
}
-static void ptys2ethtool_adver_link(struct mlx5_core_dev *mdev,
- unsigned long *advertising_modes,
- u32 eth_proto_cap)
+static void ptys2ethtool_adver_link(unsigned long *advertising_modes,
+ u32 eth_proto_cap, bool ext)
{
unsigned long proto_cap = eth_proto_cap;
struct ptys2ethtool_config *table;
u32 max_size;
int proto;
- mlx5e_ethtool_get_speed_arr(mdev, &table, &max_size);
+ table = ext ? ptys2ext_ethtool_table : ptys2legacy_ethtool_table;
+ max_size = ext ? ARRAY_SIZE(ptys2ext_ethtool_table) :
+ ARRAY_SIZE(ptys2legacy_ethtool_table);
+
for_each_set_bit(proto, &proto_cap, max_size)
bitmap_or(advertising_modes, advertising_modes,
table[proto].advertised,
ethtool_link_ksettings_add_link_mode(link_ksettings, supported, Pause);
}
-static void get_advertising(struct mlx5_core_dev *mdev, u32 eth_proto_cap,
- u8 tx_pause, u8 rx_pause,
- struct ethtool_link_ksettings *link_ksettings)
+static void get_advertising(u32 eth_proto_cap, u8 tx_pause, u8 rx_pause,
+ struct ethtool_link_ksettings *link_ksettings,
+ bool ext)
{
unsigned long *advertising = link_ksettings->link_modes.advertising;
- ptys2ethtool_adver_link(mdev, advertising, eth_proto_cap);
+ ptys2ethtool_adver_link(advertising, eth_proto_cap, ext);
if (rx_pause)
ethtool_link_ksettings_add_link_mode(link_ksettings, advertising, Pause);
struct ethtool_link_ksettings *link_ksettings)
{
unsigned long *lp_advertising = link_ksettings->link_modes.lp_advertising;
+ bool ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
- ptys2ethtool_adver_link(mdev, lp_advertising, eth_proto_lp);
+ ptys2ethtool_adver_link(lp_advertising, eth_proto_lp, ext);
}
int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv,
u8 an_disable_admin;
u8 an_status;
u8 connector_type;
+ bool admin_ext;
bool ext;
int err;
eth_proto_capability);
eth_proto_admin = MLX5_GET_ETH_PROTO(ptys_reg, out, ext,
eth_proto_admin);
+ /* Fields: eth_proto_admin and ext_eth_proto_admin are
+ * mutually exclusive. Hence try reading legacy advertising
+ * when extended advertising is zero.
+ * admin_ext indicates how eth_proto_admin should be
+ * interpreted
+ */
+ admin_ext = ext;
+ if (ext && !eth_proto_admin) {
+ eth_proto_admin = MLX5_GET_ETH_PROTO(ptys_reg, out, false,
+ eth_proto_admin);
+ admin_ext = false;
+ }
+
eth_proto_oper = MLX5_GET_ETH_PROTO(ptys_reg, out, ext,
eth_proto_oper);
eth_proto_lp = MLX5_GET(ptys_reg, out, eth_proto_lp_advertise);
ethtool_link_ksettings_zero_link_mode(link_ksettings, advertising);
get_supported(mdev, eth_proto_cap, link_ksettings);
- get_advertising(mdev, eth_proto_admin, tx_pause, rx_pause, link_ksettings);
+ get_advertising(eth_proto_admin, tx_pause, rx_pause, link_ksettings,
+ admin_ext);
get_speed_duplex(priv->netdev, eth_proto_oper, link_ksettings);
eth_proto_oper = eth_proto_oper ? eth_proto_oper : eth_proto_cap;
#define MLX5E_PTYS_EXT ((1ULL << ETHTOOL_LINK_MODE_50000baseKR_Full_BIT) - 1)
- ext_requested = (link_ksettings->link_modes.advertising[0] >
- MLX5E_PTYS_EXT);
+ ext_requested = !!(link_ksettings->link_modes.advertising[0] >
+ MLX5E_PTYS_EXT ||
+ link_ksettings->link_modes.advertising[1]);
ext_supported = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
-
- /*when ptys_extended_ethernet is set legacy link modes are deprecated */
- if (ext_requested != ext_supported)
- return -EPROTONOSUPPORT;
+ ext_requested &= ext_supported;
speed = link_ksettings->base.speed;
ethtool2ptys_adver_func = ext_requested ?
mlx5e_ethtool2ptys_ext_adver_link :
mlx5e_ethtool2ptys_adver_link;
- err = mlx5_port_query_eth_proto(mdev, 1, ext_supported, &eproto);
+ err = mlx5_port_query_eth_proto(mdev, 1, ext_requested, &eproto);
if (err) {
netdev_err(priv->netdev, "%s: query port eth proto failed: %d\n",
__func__, err);
if (!an_changes && link_modes == eproto.admin)
goto out;
- mlx5_port_set_eth_ptys(mdev, an_disable, link_modes, ext_supported);
+ mlx5_port_set_eth_ptys(mdev, an_disable, link_modes, ext_requested);
mlx5_toggle_port_link(mdev);
out:
struct mlx5e_channel *c;
int i;
- if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+ if (!test_bit(MLX5E_STATE_OPENED, &priv->state) ||
+ priv->channels.params.xdp_prog)
return 0;
for (i = 0; i < channels->num; i++) {
void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev,
struct mlx5e_params *params)
{
- params->lro_wqe_sz = MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ;
params->log_rq_mtu_frames = is_kdump_kernel() ?
MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE :
MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE;
if (params->rx_dim_enabled)
__set_bit(MLX5E_RQ_STATE_AM, &c->rq.state);
- if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_NO_CSUM_COMPLETE))
+ /* We disable csum_complete when XDP is enabled since
+ * XDP programs might manipulate packets which will render
+ * skb->checksum incorrect.
+ */
+ if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_NO_CSUM_COMPLETE) || c->xdp)
__set_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &c->rq.state);
return 0;
MLX5_TIRC_LRO_ENABLE_MASK_IPV4_LRO |
MLX5_TIRC_LRO_ENABLE_MASK_IPV6_LRO);
MLX5_SET(tirc, tirc, lro_max_ip_payload_size,
- (params->lro_wqe_sz - ROUGH_MAX_L2_L3_HDR_SZ) >> 8);
+ (MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ - ROUGH_MAX_L2_L3_HDR_SZ) >> 8);
MLX5_SET(tirc, tirc, lro_timeout_period_usecs, params->lro_timeout);
}
return 0;
}
+void mlx5e_set_netdev_mtu_boundaries(struct mlx5e_priv *priv)
+{
+ struct mlx5e_params *params = &priv->channels.params;
+ struct net_device *netdev = priv->netdev;
+ struct mlx5_core_dev *mdev = priv->mdev;
+ u16 max_mtu;
+
+ /* MTU range: 68 - hw-specific max */
+ netdev->min_mtu = ETH_MIN_MTU;
+
+ mlx5_query_port_max_mtu(mdev, &max_mtu, 1);
+ netdev->max_mtu = min_t(unsigned int, MLX5E_HW2SW_MTU(params, max_mtu),
+ ETH_MAX_MTU);
+}
+
static void mlx5e_netdev_set_tcs(struct net_device *netdev)
{
struct mlx5e_priv *priv = netdev_priv(netdev);
return 0;
}
+int mlx5e_safe_reopen_channels(struct mlx5e_priv *priv)
+{
+ struct mlx5e_channels new_channels = {};
+
+ new_channels.params = priv->channels.params;
+ return mlx5e_safe_switch_channels(priv, &new_channels, NULL);
+}
+
void mlx5e_timestamp_init(struct mlx5e_priv *priv)
{
priv->tstamp.tx_type = HWTSTAMP_TX_OFF;
if (!report_failed)
goto unlock;
- mlx5e_close_locked(priv->netdev);
- err = mlx5e_open_locked(priv->netdev);
+ err = mlx5e_safe_reopen_channels(priv);
if (err)
netdev_err(priv->netdev,
- "mlx5e_open_locked failed recovering from a tx_timeout, err(%d).\n",
+ "mlx5e_safe_reopen_channels failed recovering from a tx_timeout, err(%d).\n",
err);
unlock:
{
enum mlx5e_traffic_types tt;
- rss_params->hfunc = ETH_RSS_HASH_XOR;
+ rss_params->hfunc = ETH_RSS_HASH_TOP;
netdev_rss_key_fill(rss_params->toeplitz_hash_key,
sizeof(rss_params->toeplitz_hash_key));
mlx5e_build_default_indir_rqt(rss_params->indirection_rqt,
{
struct net_device *netdev = priv->netdev;
struct mlx5_core_dev *mdev = priv->mdev;
- u16 max_mtu;
mlx5e_init_l2_addr(priv);
if (!netif_running(netdev))
mlx5_set_port_admin_status(mdev, MLX5_PORT_DOWN);
- /* MTU range: 68 - hw-specific max */
- netdev->min_mtu = ETH_MIN_MTU;
- mlx5_query_port_max_mtu(priv->mdev, &max_mtu, 1);
- netdev->max_mtu = MLX5E_HW2SW_MTU(&priv->channels.params, max_mtu);
+ mlx5e_set_netdev_mtu_boundaries(priv);
mlx5e_set_dev_port_mtu(priv);
mlx5_lag_add(mdev, netdev);
struct mlx5e_priv *priv = netdev_priv(rpriv->netdev);
struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
- if (!mlx5e_tc_tun_device_to_offload(priv, netdev))
+ if (!mlx5e_tc_tun_device_to_offload(priv, netdev) &&
+ !is_vlan_dev(netdev))
return NOTIFY_OK;
switch (event) {
static void mlx5e_vf_rep_enable(struct mlx5e_priv *priv)
{
- struct net_device *netdev = priv->netdev;
- struct mlx5_core_dev *mdev = priv->mdev;
- u16 max_mtu;
-
- netdev->min_mtu = ETH_MIN_MTU;
- mlx5_query_port_max_mtu(mdev, &max_mtu, 1);
- netdev->max_mtu = MLX5E_HW2SW_MTU(&priv->channels.params, max_mtu);
+ mlx5e_set_netdev_mtu_boundaries(priv);
}
static int uplink_rep_async_event(struct notifier_block *nb, unsigned long event, void *data)
{
*proto = ((struct ethhdr *)skb->data)->h_proto;
*proto = __vlan_get_protocol(skb, *proto, network_depth);
- return (*proto == htons(ETH_P_IP) || *proto == htons(ETH_P_IPV6));
+
+ if (*proto == htons(ETH_P_IP))
+ return pskb_may_pull(skb, *network_depth + sizeof(struct iphdr));
+
+ if (*proto == htons(ETH_P_IPV6))
+ return pskb_may_pull(skb, *network_depth + sizeof(struct ipv6hdr));
+
+ return false;
}
static inline void mlx5e_enable_ecn(struct mlx5e_rq *rq, struct sk_buff *skb)
rq->stats->ecn_mark += !!rc;
}
-static u32 mlx5e_get_fcs(const struct sk_buff *skb)
-{
- const void *fcs_bytes;
- u32 _fcs_bytes;
-
- fcs_bytes = skb_header_pointer(skb, skb->len - ETH_FCS_LEN,
- ETH_FCS_LEN, &_fcs_bytes);
-
- return __get_unaligned_cpu32(fcs_bytes);
-}
-
static u8 get_ip_proto(struct sk_buff *skb, int network_depth, __be16 proto)
{
void *ip_p = skb->data + network_depth;
#define short_frame(size) ((size) <= ETH_ZLEN + ETH_FCS_LEN)
+#define MAX_PADDING 8
+
+static void
+tail_padding_csum_slow(struct sk_buff *skb, int offset, int len,
+ struct mlx5e_rq_stats *stats)
+{
+ stats->csum_complete_tail_slow++;
+ skb->csum = csum_block_add(skb->csum,
+ skb_checksum(skb, offset, len, 0),
+ offset);
+}
+
+static void
+tail_padding_csum(struct sk_buff *skb, int offset,
+ struct mlx5e_rq_stats *stats)
+{
+ u8 tail_padding[MAX_PADDING];
+ int len = skb->len - offset;
+ void *tail;
+
+ if (unlikely(len > MAX_PADDING)) {
+ tail_padding_csum_slow(skb, offset, len, stats);
+ return;
+ }
+
+ tail = skb_header_pointer(skb, offset, len, tail_padding);
+ if (unlikely(!tail)) {
+ tail_padding_csum_slow(skb, offset, len, stats);
+ return;
+ }
+
+ stats->csum_complete_tail++;
+ skb->csum = csum_block_add(skb->csum, csum_partial(tail, len, 0), offset);
+}
+
+static void
+mlx5e_skb_padding_csum(struct sk_buff *skb, int network_depth, __be16 proto,
+ struct mlx5e_rq_stats *stats)
+{
+ struct ipv6hdr *ip6;
+ struct iphdr *ip4;
+ int pkt_len;
+
+ switch (proto) {
+ case htons(ETH_P_IP):
+ ip4 = (struct iphdr *)(skb->data + network_depth);
+ pkt_len = network_depth + ntohs(ip4->tot_len);
+ break;
+ case htons(ETH_P_IPV6):
+ ip6 = (struct ipv6hdr *)(skb->data + network_depth);
+ pkt_len = network_depth + sizeof(*ip6) + ntohs(ip6->payload_len);
+ break;
+ default:
+ return;
+ }
+
+ if (likely(pkt_len >= skb->len))
+ return;
+
+ tail_padding_csum(skb, pkt_len, stats);
+}
+
static inline void mlx5e_handle_csum(struct net_device *netdev,
struct mlx5_cqe64 *cqe,
struct mlx5e_rq *rq,
return;
}
- if (unlikely(test_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &rq->state)))
+ /* True when explicitly set via priv flag, or XDP prog is loaded */
+ if (test_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &rq->state))
goto csum_unnecessary;
/* CQE csum doesn't cover padding octets in short ethernet
skb->csum = csum_partial(skb->data + ETH_HLEN,
network_depth - ETH_HLEN,
skb->csum);
- if (unlikely(netdev->features & NETIF_F_RXFCS))
- skb->csum = csum_block_add(skb->csum,
- (__force __wsum)mlx5e_get_fcs(skb),
- skb->len - ETH_FCS_LEN);
+
+ mlx5e_skb_padding_csum(skb, network_depth, proto, stats);
stats->csum_complete++;
return;
}
csum_unnecessary:
if (likely((cqe->hds_ip_ext & CQE_L3_OK) &&
- ((cqe->hds_ip_ext & CQE_L4_OK) ||
- (get_cqe_l4_hdr_type(cqe) == CQE_L4_HDR_TYPE_NONE)))) {
+ (cqe->hds_ip_ext & CQE_L4_OK))) {
skb->ip_summed = CHECKSUM_UNNECESSARY;
if (cqe_is_tunneled(cqe)) {
skb->csum_level = 1;
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_none) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_complete) },
+ { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_complete_tail) },
+ { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_complete_tail_slow) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary_inner) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_drop) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_redirect) },
s->rx_removed_vlan_packets += rq_stats->removed_vlan_packets;
s->rx_csum_none += rq_stats->csum_none;
s->rx_csum_complete += rq_stats->csum_complete;
+ s->rx_csum_complete_tail += rq_stats->csum_complete_tail;
+ s->rx_csum_complete_tail_slow += rq_stats->csum_complete_tail_slow;
s->rx_csum_unnecessary += rq_stats->csum_unnecessary;
s->rx_csum_unnecessary_inner += rq_stats->csum_unnecessary_inner;
s->rx_xdp_drop += rq_stats->xdp_drop;
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, packets) },
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, bytes) },
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_complete) },
+ { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_complete_tail) },
+ { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_complete_tail_slow) },
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_unnecessary) },
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_unnecessary_inner) },
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_none) },
u64 rx_csum_unnecessary;
u64 rx_csum_none;
u64 rx_csum_complete;
+ u64 rx_csum_complete_tail;
+ u64 rx_csum_complete_tail_slow;
u64 rx_csum_unnecessary_inner;
u64 rx_xdp_drop;
u64 rx_xdp_redirect;
u64 packets;
u64 bytes;
u64 csum_complete;
+ u64 csum_complete_tail;
+ u64 csum_complete_tail_slow;
u64 csum_unnecessary;
u64 csum_unnecessary_inner;
u64 csum_none;
return 0;
}
+static void *get_match_headers_criteria(u32 flags,
+ struct mlx5_flow_spec *spec)
+{
+ return (flags & MLX5_FLOW_CONTEXT_ACTION_DECAP) ?
+ MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+ inner_headers) :
+ MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+ outer_headers);
+}
+
+static void *get_match_headers_value(u32 flags,
+ struct mlx5_flow_spec *spec)
+{
+ return (flags & MLX5_FLOW_CONTEXT_ACTION_DECAP) ?
+ MLX5_ADDR_OF(fte_match_param, spec->match_value,
+ inner_headers) :
+ MLX5_ADDR_OF(fte_match_param, spec->match_value,
+ outer_headers);
+}
+
static int __parse_cls_flower(struct mlx5e_priv *priv,
struct mlx5_flow_spec *spec,
struct tc_cls_flower_offload *f,
/* In decap flow, header pointers should point to the inner
* headers, outer header were already set by parse_tunnel_attr
*/
- headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
- inner_headers);
- headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
- inner_headers);
+ headers_c = get_match_headers_criteria(MLX5_FLOW_CONTEXT_ACTION_DECAP,
+ spec);
+ headers_v = get_match_headers_value(MLX5_FLOW_CONTEXT_ACTION_DECAP,
+ spec);
}
if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
if (match.mask->n_proto)
*match_level = MLX5_MATCH_L2;
}
-
- if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) {
+ if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN) ||
+ is_vlan_dev(filter_dev)) {
+ struct flow_dissector_key_vlan filter_dev_mask;
+ struct flow_dissector_key_vlan filter_dev_key;
struct flow_match_vlan match;
- flow_rule_match_vlan(rule, &match);
+ if (is_vlan_dev(filter_dev)) {
+ match.key = &filter_dev_key;
+ match.key->vlan_id = vlan_dev_vlan_id(filter_dev);
+ match.key->vlan_tpid = vlan_dev_vlan_proto(filter_dev);
+ match.key->vlan_priority = 0;
+ match.mask = &filter_dev_mask;
+ memset(match.mask, 0xff, sizeof(*match.mask));
+ match.mask->vlan_priority = 0;
+ } else {
+ flow_rule_match_vlan(rule, &match);
+ }
if (match.mask->vlan_id ||
match.mask->vlan_priority ||
match.mask->vlan_tpid) {
u8 field;
u8 size;
u32 offset;
+ u32 match_offset;
};
-#define OFFLOAD(fw_field, size, field, off) \
- {MLX5_ACTION_IN_FIELD_OUT_ ## fw_field, size, offsetof(struct pedit_headers, field) + (off)}
+#define OFFLOAD(fw_field, size, field, off, match_field) \
+ {MLX5_ACTION_IN_FIELD_OUT_ ## fw_field, size, \
+ offsetof(struct pedit_headers, field) + (off), \
+ MLX5_BYTE_OFF(fte_match_set_lyr_2_4, match_field)}
+
+static bool cmp_val_mask(void *valp, void *maskp, void *matchvalp,
+ void *matchmaskp, int size)
+{
+ bool same = false;
+
+ switch (size) {
+ case sizeof(u8):
+ same = ((*(u8 *)valp) & (*(u8 *)maskp)) ==
+ ((*(u8 *)matchvalp) & (*(u8 *)matchmaskp));
+ break;
+ case sizeof(u16):
+ same = ((*(u16 *)valp) & (*(u16 *)maskp)) ==
+ ((*(u16 *)matchvalp) & (*(u16 *)matchmaskp));
+ break;
+ case sizeof(u32):
+ same = ((*(u32 *)valp) & (*(u32 *)maskp)) ==
+ ((*(u32 *)matchvalp) & (*(u32 *)matchmaskp));
+ break;
+ }
+
+ return same;
+}
static struct mlx5_fields fields[] = {
- OFFLOAD(DMAC_47_16, 4, eth.h_dest[0], 0),
- OFFLOAD(DMAC_15_0, 2, eth.h_dest[4], 0),
- OFFLOAD(SMAC_47_16, 4, eth.h_source[0], 0),
- OFFLOAD(SMAC_15_0, 2, eth.h_source[4], 0),
- OFFLOAD(ETHERTYPE, 2, eth.h_proto, 0),
- OFFLOAD(FIRST_VID, 2, vlan.h_vlan_TCI, 0),
-
- OFFLOAD(IP_TTL, 1, ip4.ttl, 0),
- OFFLOAD(SIPV4, 4, ip4.saddr, 0),
- OFFLOAD(DIPV4, 4, ip4.daddr, 0),
-
- OFFLOAD(SIPV6_127_96, 4, ip6.saddr.s6_addr32[0], 0),
- OFFLOAD(SIPV6_95_64, 4, ip6.saddr.s6_addr32[1], 0),
- OFFLOAD(SIPV6_63_32, 4, ip6.saddr.s6_addr32[2], 0),
- OFFLOAD(SIPV6_31_0, 4, ip6.saddr.s6_addr32[3], 0),
- OFFLOAD(DIPV6_127_96, 4, ip6.daddr.s6_addr32[0], 0),
- OFFLOAD(DIPV6_95_64, 4, ip6.daddr.s6_addr32[1], 0),
- OFFLOAD(DIPV6_63_32, 4, ip6.daddr.s6_addr32[2], 0),
- OFFLOAD(DIPV6_31_0, 4, ip6.daddr.s6_addr32[3], 0),
- OFFLOAD(IPV6_HOPLIMIT, 1, ip6.hop_limit, 0),
-
- OFFLOAD(TCP_SPORT, 2, tcp.source, 0),
- OFFLOAD(TCP_DPORT, 2, tcp.dest, 0),
- OFFLOAD(TCP_FLAGS, 1, tcp.ack_seq, 5),
-
- OFFLOAD(UDP_SPORT, 2, udp.source, 0),
- OFFLOAD(UDP_DPORT, 2, udp.dest, 0),
+ OFFLOAD(DMAC_47_16, 4, eth.h_dest[0], 0, dmac_47_16),
+ OFFLOAD(DMAC_15_0, 2, eth.h_dest[4], 0, dmac_15_0),
+ OFFLOAD(SMAC_47_16, 4, eth.h_source[0], 0, smac_47_16),
+ OFFLOAD(SMAC_15_0, 2, eth.h_source[4], 0, smac_15_0),
+ OFFLOAD(ETHERTYPE, 2, eth.h_proto, 0, ethertype),
+ OFFLOAD(FIRST_VID, 2, vlan.h_vlan_TCI, 0, first_vid),
+
+ OFFLOAD(IP_TTL, 1, ip4.ttl, 0, ttl_hoplimit),
+ OFFLOAD(SIPV4, 4, ip4.saddr, 0, src_ipv4_src_ipv6.ipv4_layout.ipv4),
+ OFFLOAD(DIPV4, 4, ip4.daddr, 0, dst_ipv4_dst_ipv6.ipv4_layout.ipv4),
+
+ OFFLOAD(SIPV6_127_96, 4, ip6.saddr.s6_addr32[0], 0,
+ src_ipv4_src_ipv6.ipv6_layout.ipv6[0]),
+ OFFLOAD(SIPV6_95_64, 4, ip6.saddr.s6_addr32[1], 0,
+ src_ipv4_src_ipv6.ipv6_layout.ipv6[4]),
+ OFFLOAD(SIPV6_63_32, 4, ip6.saddr.s6_addr32[2], 0,
+ src_ipv4_src_ipv6.ipv6_layout.ipv6[8]),
+ OFFLOAD(SIPV6_31_0, 4, ip6.saddr.s6_addr32[3], 0,
+ src_ipv4_src_ipv6.ipv6_layout.ipv6[12]),
+ OFFLOAD(DIPV6_127_96, 4, ip6.daddr.s6_addr32[0], 0,
+ dst_ipv4_dst_ipv6.ipv6_layout.ipv6[0]),
+ OFFLOAD(DIPV6_95_64, 4, ip6.daddr.s6_addr32[1], 0,
+ dst_ipv4_dst_ipv6.ipv6_layout.ipv6[4]),
+ OFFLOAD(DIPV6_63_32, 4, ip6.daddr.s6_addr32[2], 0,
+ dst_ipv4_dst_ipv6.ipv6_layout.ipv6[8]),
+ OFFLOAD(DIPV6_31_0, 4, ip6.daddr.s6_addr32[3], 0,
+ dst_ipv4_dst_ipv6.ipv6_layout.ipv6[12]),
+ OFFLOAD(IPV6_HOPLIMIT, 1, ip6.hop_limit, 0, ttl_hoplimit),
+
+ OFFLOAD(TCP_SPORT, 2, tcp.source, 0, tcp_sport),
+ OFFLOAD(TCP_DPORT, 2, tcp.dest, 0, tcp_dport),
+ OFFLOAD(TCP_FLAGS, 1, tcp.ack_seq, 5, tcp_flags),
+
+ OFFLOAD(UDP_SPORT, 2, udp.source, 0, udp_sport),
+ OFFLOAD(UDP_DPORT, 2, udp.dest, 0, udp_dport),
};
/* On input attr->max_mod_hdr_actions tells how many HW actions can be parsed at
*/
static int offload_pedit_fields(struct pedit_headers_action *hdrs,
struct mlx5e_tc_flow_parse_attr *parse_attr,
+ u32 *action_flags,
struct netlink_ext_ack *extack)
{
struct pedit_headers *set_masks, *add_masks, *set_vals, *add_vals;
+ void *headers_c = get_match_headers_criteria(*action_flags,
+ &parse_attr->spec);
+ void *headers_v = get_match_headers_value(*action_flags,
+ &parse_attr->spec);
int i, action_size, nactions, max_actions, first, last, next_z;
void *s_masks_p, *a_masks_p, *vals_p;
struct mlx5_fields *f;
nactions = parse_attr->num_mod_hdr_actions;
for (i = 0; i < ARRAY_SIZE(fields); i++) {
+ bool skip;
+
f = &fields[i];
/* avoid seeing bits set from previous iterations */
s_mask = 0;
return -EOPNOTSUPP;
}
+ skip = false;
if (s_mask) {
+ void *match_mask = headers_c + f->match_offset;
+ void *match_val = headers_v + f->match_offset;
+
cmd = MLX5_ACTION_TYPE_SET;
mask = s_mask;
vals_p = (void *)set_vals + f->offset;
+ /* don't rewrite if we have a match on the same value */
+ if (cmp_val_mask(vals_p, s_masks_p, match_val,
+ match_mask, f->size))
+ skip = true;
/* clear to denote we consumed this field */
memset(s_masks_p, 0, f->size);
} else {
+ u32 zero = 0;
+
cmd = MLX5_ACTION_TYPE_ADD;
mask = a_mask;
vals_p = (void *)add_vals + f->offset;
+ /* add 0 is no change */
+ if (!memcmp(vals_p, &zero, f->size))
+ skip = true;
/* clear to denote we consumed this field */
memset(a_masks_p, 0, f->size);
}
+ if (skip)
+ continue;
field_bsize = f->size * BITS_PER_BYTE;
return 0;
}
+static int mlx5e_flow_namespace_max_modify_action(struct mlx5_core_dev *mdev,
+ int namespace)
+{
+ if (namespace == MLX5_FLOW_NAMESPACE_FDB) /* FDB offloading */
+ return MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, max_modify_header_actions);
+ else /* namespace is MLX5_FLOW_NAMESPACE_KERNEL - NIC offloading */
+ return MLX5_CAP_FLOWTABLE_NIC_RX(mdev, max_modify_header_actions);
+}
+
static int alloc_mod_hdr_actions(struct mlx5e_priv *priv,
struct pedit_headers_action *hdrs,
int namespace,
hdrs[TCA_PEDIT_KEY_EX_CMD_ADD].pedits;
action_size = MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto);
- if (namespace == MLX5_FLOW_NAMESPACE_FDB) /* FDB offloading */
- max_actions = MLX5_CAP_ESW_FLOWTABLE_FDB(priv->mdev, max_modify_header_actions);
- else /* namespace is MLX5_FLOW_NAMESPACE_KERNEL - NIC offloading */
- max_actions = MLX5_CAP_FLOWTABLE_NIC_RX(priv->mdev, max_modify_header_actions);
-
+ max_actions = mlx5e_flow_namespace_max_modify_action(priv->mdev, namespace);
/* can get up to crazingly 16 HW actions in 32 bits pedit SW key */
max_actions = min(max_actions, nkeys * 16);
goto out_err;
}
+ if (!mlx5e_flow_namespace_max_modify_action(priv->mdev, namespace)) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "The pedit offload action is not supported");
+ goto out_err;
+ }
+
mask = act->mangle.mask;
val = act->mangle.val;
offset = act->mangle.offset;
static int alloc_tc_pedit_action(struct mlx5e_priv *priv, int namespace,
struct mlx5e_tc_flow_parse_attr *parse_attr,
struct pedit_headers_action *hdrs,
+ u32 *action_flags,
struct netlink_ext_ack *extack)
{
struct pedit_headers *cmd_masks;
goto out_err;
}
- err = offload_pedit_fields(hdrs, parse_attr, extack);
+ err = offload_pedit_fields(hdrs, parse_attr, action_flags, extack);
if (err < 0)
goto out_dealloc_parsed_actions;
return true;
}
+struct ip_ttl_word {
+ __u8 ttl;
+ __u8 protocol;
+ __sum16 check;
+};
+
+struct ipv6_hoplimit_word {
+ __be16 payload_len;
+ __u8 nexthdr;
+ __u8 hop_limit;
+};
+
+static bool is_action_keys_supported(const struct flow_action_entry *act)
+{
+ u32 mask, offset;
+ u8 htype;
+
+ htype = act->mangle.htype;
+ offset = act->mangle.offset;
+ mask = ~act->mangle.mask;
+ /* For IPv4 & IPv6 header check 4 byte word,
+ * to determine that modified fields
+ * are NOT ttl & hop_limit only.
+ */
+ if (htype == FLOW_ACT_MANGLE_HDR_TYPE_IP4) {
+ struct ip_ttl_word *ttl_word =
+ (struct ip_ttl_word *)&mask;
+
+ if (offset != offsetof(struct iphdr, ttl) ||
+ ttl_word->protocol ||
+ ttl_word->check) {
+ return true;
+ }
+ } else if (htype == FLOW_ACT_MANGLE_HDR_TYPE_IP6) {
+ struct ipv6_hoplimit_word *hoplimit_word =
+ (struct ipv6_hoplimit_word *)&mask;
+
+ if (offset != offsetof(struct ipv6hdr, payload_len) ||
+ hoplimit_word->payload_len ||
+ hoplimit_word->nexthdr) {
+ return true;
+ }
+ }
+ return false;
+}
+
static bool modify_header_match_supported(struct mlx5_flow_spec *spec,
struct flow_action *flow_action,
u32 actions,
{
const struct flow_action_entry *act;
bool modify_ip_header;
- u8 htype, ip_proto;
void *headers_v;
u16 ethertype;
+ u8 ip_proto;
int i;
- if (actions & MLX5_FLOW_CONTEXT_ACTION_DECAP)
- headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, inner_headers);
- else
- headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, outer_headers);
-
+ headers_v = get_match_headers_value(actions, spec);
ethertype = MLX5_GET(fte_match_set_lyr_2_4, headers_v, ethertype);
/* for non-IP we only re-write MACs, so we're okay */
act->id != FLOW_ACTION_ADD)
continue;
- htype = act->mangle.htype;
- if (htype == FLOW_ACT_MANGLE_HDR_TYPE_IP4 ||
- htype == FLOW_ACT_MANGLE_HDR_TYPE_IP6) {
+ if (is_action_keys_supported(act)) {
modify_ip_header = true;
break;
}
actions = flow->nic_attr->action;
if (flow->flags & MLX5E_TC_FLOW_EGRESS &&
- !(actions & MLX5_FLOW_CONTEXT_ACTION_DECAP))
+ !((actions & MLX5_FLOW_CONTEXT_ACTION_DECAP) ||
+ (actions & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP)))
return false;
if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
.mangle.mask = ~(u32)be16_to_cpu(*(__be16 *)&mask16),
.mangle.val = (u32)be16_to_cpu(*(__be16 *)&val16),
};
+ u8 match_prio_mask, match_prio_val;
+ void *headers_c, *headers_v;
int err;
- if (act->vlan.prio) {
- NL_SET_ERR_MSG_MOD(extack, "Setting VLAN prio is not supported");
+ headers_c = get_match_headers_criteria(*action, &parse_attr->spec);
+ headers_v = get_match_headers_value(*action, &parse_attr->spec);
+
+ if (!(MLX5_GET(fte_match_set_lyr_2_4, headers_c, cvlan_tag) &&
+ MLX5_GET(fte_match_set_lyr_2_4, headers_v, cvlan_tag))) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "VLAN rewrite action must have VLAN protocol match");
+ return -EOPNOTSUPP;
+ }
+
+ match_prio_mask = MLX5_GET(fte_match_set_lyr_2_4, headers_c, first_prio);
+ match_prio_val = MLX5_GET(fte_match_set_lyr_2_4, headers_v, first_prio);
+ if (act->vlan.prio != (match_prio_val & match_prio_mask)) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Changing VLAN prio is not supported");
return -EOPNOTSUPP;
}
}
break;
default:
- return -EINVAL;
+ NL_SET_ERR_MSG_MOD(extack, "The offload action is not supported");
+ return -EOPNOTSUPP;
}
}
if (hdrs[TCA_PEDIT_KEY_EX_CMD_SET].pedits ||
hdrs[TCA_PEDIT_KEY_EX_CMD_ADD].pedits) {
err = alloc_tc_pedit_action(priv, MLX5_FLOW_NAMESPACE_KERNEL,
- parse_attr, hdrs, extack);
+ parse_attr, hdrs, &action, extack);
if (err)
return err;
+ /* in case all pedit actions are skipped, remove the MOD_HDR
+ * flag.
+ */
+ if (parse_attr->num_mod_hdr_actions == 0)
+ action &= ~MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
}
attr->action = action;
return 0;
}
-static inline int cmp_encap_info(struct ip_tunnel_key *a,
- struct ip_tunnel_key *b)
+struct encap_key {
+ struct ip_tunnel_key *ip_tun_key;
+ int tunnel_type;
+};
+
+static inline int cmp_encap_info(struct encap_key *a,
+ struct encap_key *b)
{
- return memcmp(a, b, sizeof(*a));
+ return memcmp(a->ip_tun_key, b->ip_tun_key, sizeof(*a->ip_tun_key)) ||
+ a->tunnel_type != b->tunnel_type;
}
-static inline int hash_encap_info(struct ip_tunnel_key *key)
+static inline int hash_encap_info(struct encap_key *key)
{
- return jhash(key, sizeof(*key), 0);
+ return jhash(key->ip_tun_key, sizeof(*key->ip_tun_key),
+ key->tunnel_type);
}
struct mlx5_esw_flow_attr *attr = flow->esw_attr;
struct mlx5e_tc_flow_parse_attr *parse_attr;
struct ip_tunnel_info *tun_info;
- struct ip_tunnel_key *key;
+ struct encap_key key, e_key;
struct mlx5e_encap_entry *e;
unsigned short family;
uintptr_t hash_key;
parse_attr = attr->parse_attr;
tun_info = &parse_attr->tun_info[out_index];
family = ip_tunnel_info_af(tun_info);
- key = &tun_info->key;
+ key.ip_tun_key = &tun_info->key;
+ key.tunnel_type = mlx5e_tc_tun_get_type(mirred_dev);
- hash_key = hash_encap_info(key);
+ hash_key = hash_encap_info(&key);
hash_for_each_possible_rcu(esw->offloads.encap_tbl, e,
encap_hlist, hash_key) {
- if (!cmp_encap_info(&e->tun_info.key, key)) {
+ e_key.ip_tun_key = &e->tun_info.key;
+ e_key.tunnel_type = e->tunnel_type;
+ if (!cmp_encap_info(&e_key, &key)) {
found = true;
break;
}
return 0;
}
+static int add_vlan_push_action(struct mlx5e_priv *priv,
+ struct mlx5_esw_flow_attr *attr,
+ struct net_device **out_dev,
+ u32 *action)
+{
+ struct net_device *vlan_dev = *out_dev;
+ struct flow_action_entry vlan_act = {
+ .id = FLOW_ACTION_VLAN_PUSH,
+ .vlan.vid = vlan_dev_vlan_id(vlan_dev),
+ .vlan.proto = vlan_dev_vlan_proto(vlan_dev),
+ .vlan.prio = 0,
+ };
+ int err;
+
+ err = parse_tc_vlan_action(priv, &vlan_act, attr, action);
+ if (err)
+ return err;
+
+ *out_dev = dev_get_by_index_rcu(dev_net(vlan_dev),
+ dev_get_iflink(vlan_dev));
+ if (is_vlan_dev(*out_dev))
+ err = add_vlan_push_action(priv, attr, out_dev, action);
+
+ return err;
+}
+
+static int add_vlan_pop_action(struct mlx5e_priv *priv,
+ struct mlx5_esw_flow_attr *attr,
+ u32 *action)
+{
+ int nest_level = vlan_get_encap_level(attr->parse_attr->filter_dev);
+ struct flow_action_entry vlan_act = {
+ .id = FLOW_ACTION_VLAN_POP,
+ };
+ int err = 0;
+
+ while (nest_level--) {
+ err = parse_tc_vlan_action(priv, &vlan_act, attr, action);
+ if (err)
+ return err;
+ }
+
+ return err;
+}
+
static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
struct flow_action *flow_action,
- struct mlx5e_tc_flow_parse_attr *parse_attr,
struct mlx5e_tc_flow *flow,
struct netlink_ext_ack *extack)
{
struct pedit_headers_action hdrs[2] = {};
struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
struct mlx5_esw_flow_attr *attr = flow->esw_attr;
+ struct mlx5e_tc_flow_parse_attr *parse_attr = attr->parse_attr;
struct mlx5e_rep_priv *rpriv = priv->ppriv;
const struct ip_tunnel_info *info = NULL;
const struct flow_action_entry *act;
uplink_upper == out_dev)
out_dev = uplink_dev;
+ if (is_vlan_dev(out_dev)) {
+ err = add_vlan_push_action(priv, attr,
+ &out_dev,
+ &action);
+ if (err)
+ return err;
+ }
+ if (is_vlan_dev(parse_attr->filter_dev)) {
+ err = add_vlan_pop_action(priv, attr,
+ &action);
+ if (err)
+ return err;
+ }
+
if (!mlx5e_eswitch_rep(out_dev))
return -EOPNOTSUPP;
out_dev->ifindex;
parse_attr->tun_info[attr->out_count] = *info;
encap = false;
- attr->parse_attr = parse_attr;
attr->dests[attr->out_count].flags |=
MLX5_ESW_DEST_ENCAP;
attr->out_count++;
break;
}
default:
- return -EINVAL;
+ NL_SET_ERR_MSG_MOD(extack, "The offload action is not supported");
+ return -EOPNOTSUPP;
}
}
if (hdrs[TCA_PEDIT_KEY_EX_CMD_SET].pedits ||
hdrs[TCA_PEDIT_KEY_EX_CMD_ADD].pedits) {
- err = alloc_tc_pedit_action(priv, MLX5_FLOW_NAMESPACE_KERNEL,
- parse_attr, hdrs, extack);
+ err = alloc_tc_pedit_action(priv, MLX5_FLOW_NAMESPACE_FDB,
+ parse_attr, hdrs, &action, extack);
if (err)
return err;
+ /* in case all pedit actions are skipped, remove the MOD_HDR
+ * flag. we might have set split_count either by pedit or
+ * pop/push. if there is no pop/push either, reset it too.
+ */
+ if (parse_attr->num_mod_hdr_actions == 0) {
+ action &= ~MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
+ if (!((action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP) ||
+ (action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH)))
+ attr->split_count = 0;
+ }
}
attr->action = action;
if (err)
goto err_free;
- err = parse_tc_fdb_actions(priv, &rule->action, parse_attr, flow, extack);
+ err = parse_tc_fdb_actions(priv, &rule->action, flow, extack);
if (err)
goto err_free;
static inline void
mlx5e_txwqe_complete(struct mlx5e_txqsq *sq, struct sk_buff *skb,
u8 opcode, u16 ds_cnt, u8 num_wqebbs, u32 num_bytes, u8 num_dma,
- struct mlx5e_tx_wqe_info *wi, struct mlx5_wqe_ctrl_seg *cseg)
+ struct mlx5e_tx_wqe_info *wi, struct mlx5_wqe_ctrl_seg *cseg,
+ bool xmit_more)
{
struct mlx5_wq_cyc *wq = &sq->wq;
sq->stats->stopped++;
}
- if (!skb->xmit_more || netif_xmit_stopped(sq->txq))
+ if (!xmit_more || netif_xmit_stopped(sq->txq))
mlx5e_notify_hw(wq, sq->pc, sq->uar_map, cseg);
}
#define INL_HDR_START_SZ (sizeof(((struct mlx5_wqe_eth_seg *)NULL)->inline_hdr.start))
netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
- struct mlx5e_tx_wqe *wqe, u16 pi)
+ struct mlx5e_tx_wqe *wqe, u16 pi, bool xmit_more)
{
struct mlx5_wq_cyc *wq = &sq->wq;
struct mlx5_wqe_ctrl_seg *cseg;
}
stats->bytes += num_bytes;
- stats->xmit_more += skb->xmit_more;
+ stats->xmit_more += netdev_xmit_more();
headlen = skb->len - ihs - skb->data_len;
ds_cnt += !!headlen;
goto err_drop;
mlx5e_txwqe_complete(sq, skb, opcode, ds_cnt, num_wqebbs, num_bytes,
- num_dma, wi, cseg);
+ num_dma, wi, cseg, xmit_more);
return NETDEV_TX_OK;
if (unlikely(!skb))
return NETDEV_TX_OK;
- return mlx5e_sq_xmit(sq, skb, wqe, pi);
+ return mlx5e_sq_xmit(sq, skb, wqe, pi, netdev_xmit_more());
}
static void mlx5e_dump_error_cqe(struct mlx5e_txqsq *sq,
}
stats->bytes += num_bytes;
- stats->xmit_more += skb->xmit_more;
+ stats->xmit_more += netdev_xmit_more();
headlen = skb->len - ihs - skb->data_len;
ds_cnt += !!headlen;
goto err_drop;
mlx5e_txwqe_complete(sq, skb, opcode, ds_cnt, num_wqebbs, num_bytes,
- num_dma, wi, cseg);
+ num_dma, wi, cseg, false);
return NETDEV_TX_OK;
__raw_writel((__force u32)cpu_to_be32(val), addr);
/* We still want ordering, just not swabbing, so add a barrier */
- mb();
+ wmb();
}
EXPORT_SYMBOL(mlx5_eq_update_ci);
opcode, MLX5_CMD_OP_MODIFY_NIC_VPORT_CONTEXT);
MLX5_SET(modify_nic_vport_context_in, in, field_select.change_event, 1);
MLX5_SET(modify_nic_vport_context_in, in, vport_number, vport);
- if (vport)
- MLX5_SET(modify_nic_vport_context_in, in, other_vport, 1);
+ MLX5_SET(modify_nic_vport_context_in, in, other_vport, 1);
nic_vport_ctx = MLX5_ADDR_OF(modify_nic_vport_context_in,
in, nic_vport_context);
MLX5_SET(modify_esw_vport_context_in, in, opcode,
MLX5_CMD_OP_MODIFY_ESW_VPORT_CONTEXT);
MLX5_SET(modify_esw_vport_context_in, in, vport_number, vport);
- if (vport)
- MLX5_SET(modify_esw_vport_context_in, in, other_vport, 1);
+ MLX5_SET(modify_esw_vport_context_in, in, other_vport, 1);
return mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
}
{
int err;
+ memset(&esw->fdb_table.legacy, 0, sizeof(struct legacy_fdb));
+
err = esw_create_legacy_vepa_table(esw);
if (err)
return err;
/* Star rule to forward all traffic to uplink vport */
memset(spec, 0, sizeof(*spec));
+ memset(&dest, 0, sizeof(dest));
dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
dest.vport.num = MLX5_VPORT_UPLINK;
flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
{
int err;
+ memset(&esw->fdb_table.offloads, 0, sizeof(struct offloads_fdb));
mutex_init(&esw->fdb_table.offloads.fdb_prio_lock);
err = esw_create_offloads_fdb_tables(esw, nvports);
{
int err;
- mutex_init(&esw->fdb_table.offloads.fdb_prio_lock);
-
err = esw_offloads_steering_init(esw, total_nvports);
if (err)
return err;
static int any_notifier(struct notifier_block *, unsigned long, void *);
static int temp_warn(struct notifier_block *, unsigned long, void *);
static int port_module(struct notifier_block *, unsigned long, void *);
+static int pcie_core(struct notifier_block *, unsigned long, void *);
/* handler which forwards the event to events->nh, driver notifiers */
static int forward_event(struct notifier_block *, unsigned long, void *);
{.nb.notifier_call = any_notifier, .event_type = MLX5_EVENT_TYPE_NOTIFY_ANY },
{.nb.notifier_call = temp_warn, .event_type = MLX5_EVENT_TYPE_TEMP_WARN_EVENT },
{.nb.notifier_call = port_module, .event_type = MLX5_EVENT_TYPE_PORT_MODULE_EVENT },
+ {.nb.notifier_call = pcie_core, .event_type = MLX5_EVENT_TYPE_GENERAL_EVENT },
/* Events to be forwarded (as is) to mlx5 core interfaces (mlx5e/mlx5_ib) */
{.nb.notifier_call = forward_event, .event_type = MLX5_EVENT_TYPE_PORT_CHANGE },
struct mlx5_events {
struct mlx5_core_dev *dev;
+ struct workqueue_struct *wq;
struct mlx5_event_nb notifiers[ARRAY_SIZE(events_nbs_ref)];
/* driver notifier chain */
struct atomic_notifier_head nh;
/* port module events stats */
struct mlx5_pme_stats pme_stats;
+ /*pcie_core*/
+ struct work_struct pcie_core_work;
};
static const char *eqe_type_str(u8 type)
return NOTIFY_OK;
}
+enum {
+ MLX5_PCI_POWER_COULD_NOT_BE_READ = 0x0,
+ MLX5_PCI_POWER_SUFFICIENT_REPORTED = 0x1,
+ MLX5_PCI_POWER_INSUFFICIENT_REPORTED = 0x2,
+};
+
+static void mlx5_pcie_event(struct work_struct *work)
+{
+ u32 out[MLX5_ST_SZ_DW(mpein_reg)] = {0};
+ u32 in[MLX5_ST_SZ_DW(mpein_reg)] = {0};
+ struct mlx5_events *events;
+ struct mlx5_core_dev *dev;
+ u8 power_status;
+ u16 pci_power;
+
+ events = container_of(work, struct mlx5_events, pcie_core_work);
+ dev = events->dev;
+
+ if (!MLX5_CAP_MCAM_FEATURE(dev, pci_status_and_power))
+ return;
+
+ mlx5_core_access_reg(dev, in, sizeof(in), out, sizeof(out),
+ MLX5_REG_MPEIN, 0, 0);
+ power_status = MLX5_GET(mpein_reg, out, pwr_status);
+ pci_power = MLX5_GET(mpein_reg, out, pci_power);
+
+ switch (power_status) {
+ case MLX5_PCI_POWER_COULD_NOT_BE_READ:
+ mlx5_core_info_rl(dev,
+ "PCIe slot power capability was not advertised.\n");
+ break;
+ case MLX5_PCI_POWER_INSUFFICIENT_REPORTED:
+ mlx5_core_warn_rl(dev,
+ "Detected insufficient power on the PCIe slot (%uW).\n",
+ pci_power);
+ break;
+ case MLX5_PCI_POWER_SUFFICIENT_REPORTED:
+ mlx5_core_info_rl(dev,
+ "PCIe slot advertised sufficient power (%uW).\n",
+ pci_power);
+ break;
+ }
+}
+
+static int pcie_core(struct notifier_block *nb, unsigned long type, void *data)
+{
+ struct mlx5_event_nb *event_nb = mlx5_nb_cof(nb,
+ struct mlx5_event_nb,
+ nb);
+ struct mlx5_events *events = event_nb->ctx;
+ struct mlx5_eqe *eqe = data;
+
+ switch (eqe->sub_type) {
+ case MLX5_GENERAL_SUBTYPE_PCI_POWER_CHANGE_EVENT:
+ queue_work(events->wq, &events->pcie_core_work);
+ break;
+ default:
+ return NOTIFY_DONE;
+ }
+
+ return NOTIFY_OK;
+}
+
void mlx5_get_pme_stats(struct mlx5_core_dev *dev, struct mlx5_pme_stats *stats)
{
*stats = dev->priv.events->pme_stats;
ATOMIC_INIT_NOTIFIER_HEAD(&events->nh);
events->dev = dev;
dev->priv.events = events;
+ events->wq = create_singlethread_workqueue("mlx5_events");
+ if (!events->wq)
+ return -ENOMEM;
+ INIT_WORK(&events->pcie_core_work, mlx5_pcie_event);
+
return 0;
}
void mlx5_events_cleanup(struct mlx5_core_dev *dev)
{
+ destroy_workqueue(dev->priv.events->wq);
kvfree(dev->priv.events);
}
for (i = ARRAY_SIZE(events_nbs_ref) - 1; i >= 0 ; i--)
mlx5_eq_notifier_unregister(dev, &events->notifiers[i].nb);
+ flush_workqueue(events->wq);
}
int mlx5_notifier_register(struct mlx5_core_dev *dev, struct notifier_block *nb)
*conn->qp.wq.sq.db = cpu_to_be32(conn->qp.sq.pc);
/* Make sure that doorbell record is visible before ringing */
wmb();
- mlx5_write64(wqe, conn->fdev->conn_res.uar->map + MLX5_BF_OFFSET, NULL);
+ mlx5_write64(wqe, conn->fdev->conn_res.uar->map + MLX5_BF_OFFSET);
}
static void mlx5_fpga_conn_post_send(struct mlx5_fpga_conn *conn,
#include <linux/mlx5/eq.h>
+#include "mlx5_core.h"
#include "lib/eq.h"
#include "fpga/cmd.h"
};
#define mlx5_fpga_dbg(__adev, format, ...) \
- dev_dbg(&(__adev)->mdev->pdev->dev, "FPGA: %s:%d:(pid %d): " format, \
- __func__, __LINE__, current->pid, ##__VA_ARGS__)
+ mlx5_core_dbg((__adev)->mdev, "FPGA: %s:%d:(pid %d): " format, \
+ __func__, __LINE__, current->pid, ##__VA_ARGS__)
#define mlx5_fpga_err(__adev, format, ...) \
- dev_err(&(__adev)->mdev->pdev->dev, "FPGA: %s:%d:(pid %d): " format, \
- __func__, __LINE__, current->pid, ##__VA_ARGS__)
+ mlx5_core_err((__adev)->mdev, "FPGA: %s:%d:(pid %d): " format, \
+ __func__, __LINE__, current->pid, ##__VA_ARGS__)
#define mlx5_fpga_warn(__adev, format, ...) \
- dev_warn(&(__adev)->mdev->pdev->dev, "FPGA: %s:%d:(pid %d): " format, \
- __func__, __LINE__, current->pid, ##__VA_ARGS__)
+ mlx5_core_warn((__adev)->mdev, "FPGA: %s:%d:(pid %d): " format, \
+ __func__, __LINE__, current->pid, ##__VA_ARGS__)
#define mlx5_fpga_warn_ratelimited(__adev, format, ...) \
- dev_warn_ratelimited(&(__adev)->mdev->pdev->dev, "FPGA: %s:%d: " \
- format, __func__, __LINE__, ##__VA_ARGS__)
+ mlx5_core_err_rl((__adev)->mdev, "FPGA: %s:%d: " \
+ format, __func__, __LINE__, ##__VA_ARGS__)
#define mlx5_fpga_notice(__adev, format, ...) \
- dev_notice(&(__adev)->mdev->pdev->dev, "FPGA: " format, ##__VA_ARGS__)
+ mlx5_core_info((__adev)->mdev, "FPGA: " format, ##__VA_ARGS__)
#define mlx5_fpga_info(__adev, format, ...) \
- dev_info(&(__adev)->mdev->pdev->dev, "FPGA: " format, ##__VA_ARGS__)
+ mlx5_core_info((__adev)->mdev, "FPGA: " format, ##__VA_ARGS__)
int mlx5_fpga_init(struct mlx5_core_dev *mdev);
void mlx5_fpga_cleanup(struct mlx5_core_dev *mdev);
return ret;
}
-static void mlx5_fpga_tls_release_swid(struct idr *idr,
- spinlock_t *idr_spinlock, u32 swid)
+static void *mlx5_fpga_tls_release_swid(struct idr *idr,
+ spinlock_t *idr_spinlock, u32 swid)
{
unsigned long flags;
+ void *ptr;
spin_lock_irqsave(idr_spinlock, flags);
- idr_remove(idr, swid);
+ ptr = idr_remove(idr, swid);
spin_unlock_irqrestore(idr_spinlock, flags);
+ return ptr;
}
static void mlx_tls_kfree_complete(struct mlx5_fpga_conn *conn,
kfree(buf);
}
-struct mlx5_teardown_stream_context {
- struct mlx5_fpga_tls_command_context cmd;
- u32 swid;
-};
-
static void
mlx5_fpga_tls_teardown_completion(struct mlx5_fpga_conn *conn,
struct mlx5_fpga_device *fdev,
struct mlx5_fpga_tls_command_context *cmd,
struct mlx5_fpga_dma_buf *resp)
{
- struct mlx5_teardown_stream_context *ctx =
- container_of(cmd, struct mlx5_teardown_stream_context, cmd);
-
if (resp) {
u32 syndrome = MLX5_GET(tls_resp, resp->sg[0].data, syndrome);
mlx5_fpga_err(fdev,
"Teardown stream failed with syndrome = %d",
syndrome);
- else if (MLX5_GET(tls_cmd, cmd->buf.sg[0].data, direction_sx))
- mlx5_fpga_tls_release_swid(&fdev->tls->tx_idr,
- &fdev->tls->tx_idr_spinlock,
- ctx->swid);
- else
- mlx5_fpga_tls_release_swid(&fdev->tls->rx_idr,
- &fdev->tls->rx_idr_spinlock,
- ctx->swid);
}
mlx5_fpga_tls_put_command_ctx(cmd);
}
rcu_read_lock();
flow = idr_find(&mdev->fpga->tls->rx_idr, ntohl(handle));
- rcu_read_unlock();
+ if (unlikely(!flow)) {
+ rcu_read_unlock();
+ WARN_ONCE(1, "Received NULL pointer for handle\n");
+ kfree(buf);
+ return -EINVAL;
+ }
mlx5_fpga_tls_flow_to_cmd(flow, cmd);
+ rcu_read_unlock();
MLX5_SET(tls_cmd, cmd, swid, ntohl(handle));
MLX5_SET64(tls_cmd, cmd, tls_rcd_sn, be64_to_cpu(rcd_sn));
buf->complete = mlx_tls_kfree_complete;
ret = mlx5_fpga_sbu_conn_sendmsg(mdev->fpga->tls->conn, buf);
+ if (ret < 0)
+ kfree(buf);
return ret;
}
static void mlx5_fpga_tls_send_teardown_cmd(struct mlx5_core_dev *mdev,
void *flow, u32 swid, gfp_t flags)
{
- struct mlx5_teardown_stream_context *ctx;
+ struct mlx5_fpga_tls_command_context *ctx;
struct mlx5_fpga_dma_buf *buf;
void *cmd;
if (!ctx)
return;
- buf = &ctx->cmd.buf;
+ buf = &ctx->buf;
cmd = (ctx + 1);
MLX5_SET(tls_cmd, cmd, command_type, CMD_TEARDOWN_STREAM);
MLX5_SET(tls_cmd, cmd, swid, swid);
buf->sg[0].data = cmd;
buf->sg[0].size = MLX5_TLS_COMMAND_SIZE;
- ctx->swid = swid;
- mlx5_fpga_tls_cmd_send(mdev->fpga, &ctx->cmd,
+ mlx5_fpga_tls_cmd_send(mdev->fpga, ctx,
mlx5_fpga_tls_teardown_completion);
}
struct mlx5_fpga_tls *tls = mdev->fpga->tls;
void *flow;
- rcu_read_lock();
if (direction_sx)
- flow = idr_find(&tls->tx_idr, swid);
+ flow = mlx5_fpga_tls_release_swid(&tls->tx_idr,
+ &tls->tx_idr_spinlock,
+ swid);
else
- flow = idr_find(&tls->rx_idr, swid);
-
- rcu_read_unlock();
+ flow = mlx5_fpga_tls_release_swid(&tls->rx_idr,
+ &tls->rx_idr_spinlock,
+ swid);
if (!flow) {
mlx5_fpga_err(mdev->fpga, "No flow information for swid %u\n",
return;
}
+ synchronize_rcu(); /* before kfree(flow) */
mlx5_fpga_tls_send_teardown_cmd(mdev, flow, swid, flags);
}
struct mlx5_flow_root_namespace *root = find_root(&prio->node);
struct mlx5_ft_underlay_qp *uqp;
int min_level = INT_MAX;
- int err;
+ int err = 0;
u32 qpn;
if (root->root_ft)
nic_state = mlx5_get_nic_state(dev);
if (nic_state == MLX5_NIC_IFC_INVALID) {
- dev_err(&dev->pdev->dev, "health recovery flow aborted since the nic state is invalid\n");
+ mlx5_core_err(dev, "health recovery flow aborted since the nic state is invalid\n");
return;
}
- dev_err(&dev->pdev->dev, "starting health recovery flow\n");
+ mlx5_core_err(dev, "starting health recovery flow\n");
mlx5_recover_device(dev);
}
if (!test_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags))
schedule_delayed_work(&health->recover_work, recover_delay);
else
- dev_err(&dev->pdev->dev,
- "new health works are not permitted at this stage\n");
+ mlx5_core_err(dev,
+ "new health works are not permitted at this stage\n");
spin_unlock_irqrestore(&health->wq_lock, flags);
}
return;
for (i = 0; i < ARRAY_SIZE(h->assert_var); i++)
- dev_err(&dev->pdev->dev, "assert_var[%d] 0x%08x\n", i, ioread32be(h->assert_var + i));
+ mlx5_core_err(dev, "assert_var[%d] 0x%08x\n", i,
+ ioread32be(h->assert_var + i));
- dev_err(&dev->pdev->dev, "assert_exit_ptr 0x%08x\n", ioread32be(&h->assert_exit_ptr));
- dev_err(&dev->pdev->dev, "assert_callra 0x%08x\n", ioread32be(&h->assert_callra));
+ mlx5_core_err(dev, "assert_exit_ptr 0x%08x\n",
+ ioread32be(&h->assert_exit_ptr));
+ mlx5_core_err(dev, "assert_callra 0x%08x\n",
+ ioread32be(&h->assert_callra));
sprintf(fw_str, "%d.%d.%d", fw_rev_maj(dev), fw_rev_min(dev), fw_rev_sub(dev));
- dev_err(&dev->pdev->dev, "fw_ver %s\n", fw_str);
- dev_err(&dev->pdev->dev, "hw_id 0x%08x\n", ioread32be(&h->hw_id));
- dev_err(&dev->pdev->dev, "irisc_index %d\n", ioread8(&h->irisc_index));
- dev_err(&dev->pdev->dev, "synd 0x%x: %s\n", ioread8(&h->synd), hsynd_str(ioread8(&h->synd)));
- dev_err(&dev->pdev->dev, "ext_synd 0x%04x\n", ioread16be(&h->ext_synd));
+ mlx5_core_err(dev, "fw_ver %s\n", fw_str);
+ mlx5_core_err(dev, "hw_id 0x%08x\n", ioread32be(&h->hw_id));
+ mlx5_core_err(dev, "irisc_index %d\n", ioread8(&h->irisc_index));
+ mlx5_core_err(dev, "synd 0x%x: %s\n", ioread8(&h->synd),
+ hsynd_str(ioread8(&h->synd)));
+ mlx5_core_err(dev, "ext_synd 0x%04x\n", ioread16be(&h->ext_synd));
fw = ioread32be(&h->fw_ver);
- dev_err(&dev->pdev->dev, "raw fw_ver 0x%08x\n", fw);
+ mlx5_core_err(dev, "raw fw_ver 0x%08x\n", fw);
}
static unsigned long get_next_poll_jiffies(void)
if (!test_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags))
queue_work(health->wq, &health->work);
else
- dev_err(&dev->pdev->dev,
- "new health works are not permitted at this stage\n");
+ mlx5_core_err(dev, "new health works are not permitted at this stage\n");
spin_unlock_irqrestore(&health->wq_lock, flags);
}
health->prev = count;
if (health->miss_counter == MAX_MISSES) {
- dev_err(&dev->pdev->dev, "device's health compromised - reached miss count\n");
+ mlx5_core_err(dev, "device's health compromised - reached miss count\n");
print_health_info(dev);
}
cancel_delayed_work_sync(&dev->priv.health.recover_work);
}
+void mlx5_health_flush(struct mlx5_core_dev *dev)
+{
+ struct mlx5_core_health *health = &dev->priv.health;
+
+ flush_workqueue(health->wq);
+}
+
void mlx5_health_cleanup(struct mlx5_core_dev *dev)
{
struct mlx5_core_health *health = &dev->priv.health;
return -ENOMEM;
strcpy(name, "mlx5_health");
- strcat(name, dev_name(&dev->pdev->dev));
+ strcat(name, dev->priv.name);
health->wq = create_singlethread_workqueue(name);
kfree(name);
if (!health->wq)
void *ppriv)
{
struct mlx5e_priv *priv = mlx5i_epriv(netdev);
- u16 max_mtu;
int err;
err = mlx5e_netdev_init(netdev, priv, mdev, profile, ppriv);
if (err)
return err;
- mlx5_query_port_max_mtu(mdev, &max_mtu, 1);
- netdev->mtu = max_mtu;
+ mlx5e_set_netdev_mtu_boundaries(priv);
+ netdev->mtu = netdev->max_mtu;
mlx5e_build_nic_params(mdev, &priv->rss_params, &priv->channels.params,
mlx5e_get_netdev_max_channels(netdev),
.size = 8,
.limit = 4
},
- .mr_cache[16] = {
- .size = 8,
- .limit = 4
- },
- .mr_cache[17] = {
- .size = 8,
- .limit = 4
- },
- .mr_cache[18] = {
- .size = 8,
- .limit = 4
- },
- .mr_cache[19] = {
- .size = 4,
- .limit = 2
- },
- .mr_cache[20] = {
- .size = 4,
- .limit = 2
- },
},
};
static int set_hca_cap(struct mlx5_core_dev *dev)
{
- struct pci_dev *pdev = dev->pdev;
int err;
err = handle_hca_cap(dev);
if (err) {
- dev_err(&pdev->dev, "handle_hca_cap failed\n");
+ mlx5_core_err(dev, "handle_hca_cap failed\n");
goto out;
}
err = handle_hca_cap_atomic(dev);
if (err) {
- dev_err(&pdev->dev, "handle_hca_cap_atomic failed\n");
+ mlx5_core_err(dev, "handle_hca_cap_atomic failed\n");
goto out;
}
err = handle_hca_cap_odp(dev);
if (err) {
- dev_err(&pdev->dev, "handle_hca_cap_odp failed\n");
+ mlx5_core_err(dev, "handle_hca_cap_odp failed\n");
goto out;
}
return -EOPNOTSUPP;
}
-static int mlx5_pci_init(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
+static int mlx5_pci_init(struct mlx5_core_dev *dev, struct pci_dev *pdev,
+ const struct pci_device_id *id)
{
- struct pci_dev *pdev = dev->pdev;
+ struct mlx5_priv *priv = &dev->priv;
int err = 0;
- pci_set_drvdata(dev->pdev, dev);
- strncpy(priv->name, dev_name(&pdev->dev), MLX5_MAX_NAME_LEN);
- priv->name[MLX5_MAX_NAME_LEN - 1] = 0;
-
- mutex_init(&priv->pgdir_mutex);
- INIT_LIST_HEAD(&priv->pgdir_list);
- spin_lock_init(&priv->mkey_lock);
+ dev->pdev = pdev;
+ priv->pci_dev_data = id->driver_data;
- mutex_init(&priv->alloc_mutex);
+ pci_set_drvdata(dev->pdev, dev);
+ dev->bar_addr = pci_resource_start(pdev, 0);
priv->numa_node = dev_to_node(&dev->pdev->dev);
- if (mlx5_debugfs_root)
- priv->dbg_root =
- debugfs_create_dir(pci_name(pdev), mlx5_debugfs_root);
-
err = mlx5_pci_enable_device(dev);
if (err) {
- dev_err(&pdev->dev, "Cannot enable PCI device, aborting\n");
- goto err_dbg;
+ mlx5_core_err(dev, "Cannot enable PCI device, aborting\n");
+ return err;
}
err = request_bar(pdev);
if (err) {
- dev_err(&pdev->dev, "error requesting BARs, aborting\n");
+ mlx5_core_err(dev, "error requesting BARs, aborting\n");
goto err_disable;
}
err = set_dma_caps(pdev);
if (err) {
- dev_err(&pdev->dev, "Failed setting DMA capabilities mask, aborting\n");
+ mlx5_core_err(dev, "Failed setting DMA capabilities mask, aborting\n");
goto err_clr_master;
}
pci_enable_atomic_ops_to_root(pdev, PCI_EXP_DEVCAP2_ATOMIC_COMP128))
mlx5_core_dbg(dev, "Enabling pci atomics failed\n");
- dev->iseg_base = pci_resource_start(dev->pdev, 0);
+ dev->iseg_base = dev->bar_addr;
dev->iseg = ioremap(dev->iseg_base, sizeof(*dev->iseg));
if (!dev->iseg) {
err = -ENOMEM;
- dev_err(&pdev->dev, "Failed mapping initialization segment, aborting\n");
+ mlx5_core_err(dev, "Failed mapping initialization segment, aborting\n");
goto err_clr_master;
}
release_bar(dev->pdev);
err_disable:
mlx5_pci_disable_device(dev);
-
-err_dbg:
- debugfs_remove(priv->dbg_root);
return err;
}
-static void mlx5_pci_close(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
+static void mlx5_pci_close(struct mlx5_core_dev *dev)
{
iounmap(dev->iseg);
pci_clear_master(dev->pdev);
release_bar(dev->pdev);
mlx5_pci_disable_device(dev);
- debugfs_remove_recursive(priv->dbg_root);
}
-static int mlx5_init_once(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
+static int mlx5_init_once(struct mlx5_core_dev *dev)
{
- struct pci_dev *pdev = dev->pdev;
int err;
- priv->devcom = mlx5_devcom_register_device(dev);
- if (IS_ERR(priv->devcom))
- dev_err(&pdev->dev, "failed to register with devcom (0x%p)\n",
- priv->devcom);
+ dev->priv.devcom = mlx5_devcom_register_device(dev);
+ if (IS_ERR(dev->priv.devcom))
+ mlx5_core_err(dev, "failed to register with devcom (0x%p)\n",
+ dev->priv.devcom);
err = mlx5_query_board_id(dev);
if (err) {
- dev_err(&pdev->dev, "query board id failed\n");
+ mlx5_core_err(dev, "query board id failed\n");
goto err_devcom;
}
err = mlx5_eq_table_init(dev);
if (err) {
- dev_err(&pdev->dev, "failed to initialize eq\n");
+ mlx5_core_err(dev, "failed to initialize eq\n");
goto err_devcom;
}
err = mlx5_events_init(dev);
if (err) {
- dev_err(&pdev->dev, "failed to initialize events\n");
+ mlx5_core_err(dev, "failed to initialize events\n");
goto err_eq_cleanup;
}
err = mlx5_cq_debugfs_init(dev);
if (err) {
- dev_err(&pdev->dev, "failed to initialize cq debugfs\n");
+ mlx5_core_err(dev, "failed to initialize cq debugfs\n");
goto err_events_cleanup;
}
err = mlx5_init_rl_table(dev);
if (err) {
- dev_err(&pdev->dev, "Failed to init rate limiting\n");
+ mlx5_core_err(dev, "Failed to init rate limiting\n");
goto err_tables_cleanup;
}
err = mlx5_mpfs_init(dev);
if (err) {
- dev_err(&pdev->dev, "Failed to init l2 table %d\n", err);
+ mlx5_core_err(dev, "Failed to init l2 table %d\n", err);
goto err_rl_cleanup;
}
err = mlx5_eswitch_init(dev);
if (err) {
- dev_err(&pdev->dev, "Failed to init eswitch %d\n", err);
+ mlx5_core_err(dev, "Failed to init eswitch %d\n", err);
goto err_mpfs_cleanup;
}
err = mlx5_sriov_init(dev);
if (err) {
- dev_err(&pdev->dev, "Failed to init sriov %d\n", err);
+ mlx5_core_err(dev, "Failed to init sriov %d\n", err);
goto err_eswitch_cleanup;
}
err = mlx5_fpga_init(dev);
if (err) {
- dev_err(&pdev->dev, "Failed to init fpga device %d\n", err);
+ mlx5_core_err(dev, "Failed to init fpga device %d\n", err);
goto err_sriov_cleanup;
}
mlx5_devcom_unregister_device(dev->priv.devcom);
}
-static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
- bool boot)
+static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot)
{
- struct pci_dev *pdev = dev->pdev;
int err;
- dev->caps.embedded_cpu = mlx5_read_embedded_cpu(dev);
- mutex_lock(&dev->intf_state_mutex);
- if (test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) {
- dev_warn(&dev->pdev->dev, "%s: interface is up, NOP\n",
- __func__);
- goto out;
- }
-
- dev_info(&pdev->dev, "firmware version: %d.%d.%d\n", fw_rev_maj(dev),
- fw_rev_min(dev), fw_rev_sub(dev));
+ mlx5_core_info(dev, "firmware version: %d.%d.%d\n", fw_rev_maj(dev),
+ fw_rev_min(dev), fw_rev_sub(dev));
/* Only PFs hold the relevant PCIe information for this query */
if (mlx5_core_is_pf(dev))
pcie_print_link_status(dev->pdev);
- /* on load removing any previous indication of internal error, device is
- * up
- */
- dev->state = MLX5_DEVICE_STATE_UP;
-
/* wait for firmware to accept initialization segments configurations
*/
err = wait_fw_init(dev, FW_PRE_INIT_TIMEOUT_MILI);
if (err) {
- dev_err(&dev->pdev->dev, "Firmware over %d MS in pre-initializing state, aborting\n",
- FW_PRE_INIT_TIMEOUT_MILI);
- goto out_err;
+ mlx5_core_err(dev, "Firmware over %d MS in pre-initializing state, aborting\n",
+ FW_PRE_INIT_TIMEOUT_MILI);
+ return err;
}
err = mlx5_cmd_init(dev);
if (err) {
- dev_err(&pdev->dev, "Failed initializing command interface, aborting\n");
- goto out_err;
+ mlx5_core_err(dev, "Failed initializing command interface, aborting\n");
+ return err;
}
err = wait_fw_init(dev, FW_INIT_TIMEOUT_MILI);
if (err) {
- dev_err(&dev->pdev->dev, "Firmware over %d MS in initializing state, aborting\n",
- FW_INIT_TIMEOUT_MILI);
+ mlx5_core_err(dev, "Firmware over %d MS in initializing state, aborting\n",
+ FW_INIT_TIMEOUT_MILI);
goto err_cmd_cleanup;
}
err = mlx5_core_enable_hca(dev, 0);
if (err) {
- dev_err(&pdev->dev, "enable hca failed\n");
+ mlx5_core_err(dev, "enable hca failed\n");
goto err_cmd_cleanup;
}
err = mlx5_core_set_issi(dev);
if (err) {
- dev_err(&pdev->dev, "failed to set issi\n");
+ mlx5_core_err(dev, "failed to set issi\n");
goto err_disable_hca;
}
err = mlx5_satisfy_startup_pages(dev, 1);
if (err) {
- dev_err(&pdev->dev, "failed to allocate boot pages\n");
+ mlx5_core_err(dev, "failed to allocate boot pages\n");
goto err_disable_hca;
}
err = set_hca_ctrl(dev);
if (err) {
- dev_err(&pdev->dev, "set_hca_ctrl failed\n");
+ mlx5_core_err(dev, "set_hca_ctrl failed\n");
goto reclaim_boot_pages;
}
err = set_hca_cap(dev);
if (err) {
- dev_err(&pdev->dev, "set_hca_cap failed\n");
+ mlx5_core_err(dev, "set_hca_cap failed\n");
goto reclaim_boot_pages;
}
err = mlx5_satisfy_startup_pages(dev, 0);
if (err) {
- dev_err(&pdev->dev, "failed to allocate init pages\n");
+ mlx5_core_err(dev, "failed to allocate init pages\n");
goto reclaim_boot_pages;
}
err = mlx5_cmd_init_hca(dev, sw_owner_id);
if (err) {
- dev_err(&pdev->dev, "init hca failed\n");
+ mlx5_core_err(dev, "init hca failed\n");
goto reclaim_boot_pages;
}
err = mlx5_query_hca_caps(dev);
if (err) {
- dev_err(&pdev->dev, "query hca failed\n");
- goto err_stop_poll;
+ mlx5_core_err(dev, "query hca failed\n");
+ goto stop_health;
}
- if (boot) {
- err = mlx5_init_once(dev, priv);
- if (err) {
- dev_err(&pdev->dev, "sw objs init failed\n");
- goto err_stop_poll;
- }
+ return 0;
+
+stop_health:
+ mlx5_stop_health_poll(dev, boot);
+reclaim_boot_pages:
+ mlx5_reclaim_startup_pages(dev);
+err_disable_hca:
+ mlx5_core_disable_hca(dev, 0);
+err_cmd_cleanup:
+ mlx5_cmd_cleanup(dev);
+
+ return err;
+}
+
+static int mlx5_function_teardown(struct mlx5_core_dev *dev, bool boot)
+{
+ int err;
+
+ mlx5_stop_health_poll(dev, boot);
+ err = mlx5_cmd_teardown_hca(dev);
+ if (err) {
+ mlx5_core_err(dev, "tear_down_hca failed, skip cleanup\n");
+ return err;
}
+ mlx5_reclaim_startup_pages(dev);
+ mlx5_core_disable_hca(dev, 0);
+ mlx5_cmd_cleanup(dev);
+
+ return 0;
+}
+
+static int mlx5_load(struct mlx5_core_dev *dev)
+{
+ int err;
dev->priv.uar = mlx5_get_uars_page(dev);
if (IS_ERR(dev->priv.uar)) {
- dev_err(&pdev->dev, "Failed allocating uar, aborting\n");
+ mlx5_core_err(dev, "Failed allocating uar, aborting\n");
err = PTR_ERR(dev->priv.uar);
- goto err_get_uars;
+ return err;
}
mlx5_events_start(dev);
err = mlx5_eq_table_create(dev);
if (err) {
- dev_err(&pdev->dev, "Failed to create EQs\n");
+ mlx5_core_err(dev, "Failed to create EQs\n");
goto err_eq_table;
}
err = mlx5_fw_tracer_init(dev->tracer);
if (err) {
- dev_err(&pdev->dev, "Failed to init FW tracer\n");
+ mlx5_core_err(dev, "Failed to init FW tracer\n");
goto err_fw_tracer;
}
err = mlx5_fpga_device_start(dev);
if (err) {
- dev_err(&pdev->dev, "fpga device start failed %d\n", err);
+ mlx5_core_err(dev, "fpga device start failed %d\n", err);
goto err_fpga_start;
}
err = mlx5_accel_ipsec_init(dev);
if (err) {
- dev_err(&pdev->dev, "IPSec device start failed %d\n", err);
+ mlx5_core_err(dev, "IPSec device start failed %d\n", err);
goto err_ipsec_start;
}
err = mlx5_accel_tls_init(dev);
if (err) {
- dev_err(&pdev->dev, "TLS device start failed %d\n", err);
+ mlx5_core_err(dev, "TLS device start failed %d\n", err);
goto err_tls_start;
}
err = mlx5_init_fs(dev);
if (err) {
- dev_err(&pdev->dev, "Failed to init flow steering\n");
+ mlx5_core_err(dev, "Failed to init flow steering\n");
goto err_fs;
}
err = mlx5_core_set_hca_defaults(dev);
if (err) {
- dev_err(&pdev->dev, "Failed to set hca defaults\n");
+ mlx5_core_err(dev, "Failed to set hca defaults\n");
goto err_fs;
}
err = mlx5_sriov_attach(dev);
if (err) {
- dev_err(&pdev->dev, "sriov init failed %d\n", err);
+ mlx5_core_err(dev, "sriov init failed %d\n", err);
goto err_sriov;
}
err = mlx5_ec_init(dev);
if (err) {
- dev_err(&pdev->dev, "Failed to init embedded CPU\n");
+ mlx5_core_err(dev, "Failed to init embedded CPU\n");
goto err_ec;
}
- if (mlx5_device_registered(dev)) {
- mlx5_attach_device(dev);
- } else {
- err = mlx5_register_device(dev);
- if (err) {
- dev_err(&pdev->dev, "mlx5_register_device failed %d\n", err);
- goto err_reg_dev;
- }
- }
-
- set_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state);
-out:
- mutex_unlock(&dev->intf_state_mutex);
-
return 0;
-err_reg_dev:
- mlx5_ec_cleanup(dev);
-
err_ec:
mlx5_sriov_detach(dev);
-
err_sriov:
mlx5_cleanup_fs(dev);
-
err_fs:
mlx5_accel_tls_cleanup(dev);
-
err_tls_start:
mlx5_accel_ipsec_cleanup(dev);
-
err_ipsec_start:
mlx5_fpga_device_stop(dev);
-
err_fpga_start:
mlx5_fw_tracer_cleanup(dev->tracer);
-
err_fw_tracer:
mlx5_eq_table_destroy(dev);
-
err_eq_table:
mlx5_pagealloc_stop(dev);
mlx5_events_stop(dev);
- mlx5_put_uars_page(dev, priv->uar);
+ mlx5_put_uars_page(dev, dev->priv.uar);
+ return err;
+}
-err_get_uars:
- if (boot)
- mlx5_cleanup_once(dev);
+static void mlx5_unload(struct mlx5_core_dev *dev)
+{
+ mlx5_ec_cleanup(dev);
+ mlx5_sriov_detach(dev);
+ mlx5_cleanup_fs(dev);
+ mlx5_accel_ipsec_cleanup(dev);
+ mlx5_accel_tls_cleanup(dev);
+ mlx5_fpga_device_stop(dev);
+ mlx5_fw_tracer_cleanup(dev->tracer);
+ mlx5_eq_table_destroy(dev);
+ mlx5_pagealloc_stop(dev);
+ mlx5_events_stop(dev);
+ mlx5_put_uars_page(dev, dev->priv.uar);
+}
-err_stop_poll:
- mlx5_stop_health_poll(dev, boot);
- if (mlx5_cmd_teardown_hca(dev)) {
- dev_err(&dev->pdev->dev, "tear_down_hca failed, skip cleanup\n");
- goto out_err;
+static int mlx5_load_one(struct mlx5_core_dev *dev, bool boot)
+{
+ int err = 0;
+
+ dev->caps.embedded_cpu = mlx5_read_embedded_cpu(dev);
+ mutex_lock(&dev->intf_state_mutex);
+ if (test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) {
+ mlx5_core_warn(dev, "interface is up, NOP\n");
+ goto out;
}
+ /* remove any previous indication of internal error */
+ dev->state = MLX5_DEVICE_STATE_UP;
-reclaim_boot_pages:
- mlx5_reclaim_startup_pages(dev);
+ err = mlx5_function_setup(dev, boot);
+ if (err)
+ goto out;
-err_disable_hca:
- mlx5_core_disable_hca(dev, 0);
+ if (boot) {
+ err = mlx5_init_once(dev);
+ if (err) {
+ mlx5_core_err(dev, "sw objs init failed\n");
+ goto function_teardown;
+ }
+ }
-err_cmd_cleanup:
- mlx5_cmd_cleanup(dev);
+ err = mlx5_load(dev);
+ if (err)
+ goto err_load;
+
+ if (mlx5_device_registered(dev)) {
+ mlx5_attach_device(dev);
+ } else {
+ err = mlx5_register_device(dev);
+ if (err) {
+ mlx5_core_err(dev, "register device failed %d\n", err);
+ goto err_reg_dev;
+ }
+ }
+
+ set_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state);
+out:
+ mutex_unlock(&dev->intf_state_mutex);
+
+ return err;
-out_err:
+err_reg_dev:
+ mlx5_unload(dev);
+err_load:
+ if (boot)
+ mlx5_cleanup_once(dev);
+function_teardown:
+ mlx5_function_teardown(dev, boot);
dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
mutex_unlock(&dev->intf_state_mutex);
return err;
}
-static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
- bool cleanup)
+static int mlx5_unload_one(struct mlx5_core_dev *dev, bool cleanup)
{
int err = 0;
mutex_lock(&dev->intf_state_mutex);
if (!test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) {
- dev_warn(&dev->pdev->dev, "%s: interface is down, NOP\n",
- __func__);
+ mlx5_core_warn(dev, "%s: interface is down, NOP\n",
+ __func__);
if (cleanup)
mlx5_cleanup_once(dev);
goto out;
if (mlx5_device_registered(dev))
mlx5_detach_device(dev);
- mlx5_ec_cleanup(dev);
- mlx5_sriov_detach(dev);
- mlx5_cleanup_fs(dev);
- mlx5_accel_ipsec_cleanup(dev);
- mlx5_accel_tls_cleanup(dev);
- mlx5_fpga_device_stop(dev);
- mlx5_fw_tracer_cleanup(dev->tracer);
- mlx5_eq_table_destroy(dev);
- mlx5_pagealloc_stop(dev);
- mlx5_events_stop(dev);
- mlx5_put_uars_page(dev, priv->uar);
+ mlx5_unload(dev);
+
if (cleanup)
mlx5_cleanup_once(dev);
- mlx5_stop_health_poll(dev, cleanup);
-
- err = mlx5_cmd_teardown_hca(dev);
- if (err) {
- dev_err(&dev->pdev->dev, "tear_down_hca failed, skip cleanup\n");
- goto out;
- }
- mlx5_reclaim_startup_pages(dev);
- mlx5_core_disable_hca(dev, 0);
- mlx5_cmd_cleanup(dev);
+ mlx5_function_teardown(dev, cleanup);
out:
mutex_unlock(&dev->intf_state_mutex);
return err;
#endif
};
-#define MLX5_IB_MOD "mlx5_ib"
-static int init_one(struct pci_dev *pdev,
- const struct pci_device_id *id)
+static int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx, const char *name)
{
- struct mlx5_core_dev *dev;
- struct devlink *devlink;
- struct mlx5_priv *priv;
+ struct mlx5_priv *priv = &dev->priv;
int err;
- devlink = devlink_alloc(&mlx5_devlink_ops, sizeof(*dev));
- if (!devlink) {
- dev_err(&pdev->dev, "kzalloc failed\n");
- return -ENOMEM;
- }
-
- dev = devlink_priv(devlink);
- priv = &dev->priv;
- priv->pci_dev_data = id->driver_data;
-
- pci_set_drvdata(pdev, dev);
+ strncpy(priv->name, name, MLX5_MAX_NAME_LEN);
+ priv->name[MLX5_MAX_NAME_LEN - 1] = 0;
- dev->pdev = pdev;
- dev->profile = &profile[prof_sel];
+ dev->profile = &profile[profile_idx];
INIT_LIST_HEAD(&priv->ctx_list);
spin_lock_init(&priv->ctx_lock);
INIT_LIST_HEAD(&priv->bfregs.reg_head.list);
INIT_LIST_HEAD(&priv->bfregs.wc_head.list);
- err = mlx5_pci_init(dev, priv);
- if (err) {
- dev_err(&pdev->dev, "mlx5_pci_init failed with error code %d\n", err);
- goto clean_dev;
+ mutex_init(&priv->alloc_mutex);
+ mutex_init(&priv->pgdir_mutex);
+ INIT_LIST_HEAD(&priv->pgdir_list);
+ spin_lock_init(&priv->mkey_lock);
+
+ priv->dbg_root = debugfs_create_dir(name, mlx5_debugfs_root);
+ if (!priv->dbg_root) {
+ pr_err("mlx5_core: %s error, Cannot create debugfs dir, aborting\n", name);
+ return -ENOMEM;
}
err = mlx5_health_init(dev);
- if (err) {
- dev_err(&pdev->dev, "mlx5_health_init failed with error code %d\n", err);
- goto close_pci;
- }
+ if (err)
+ goto err_health_init;
err = mlx5_pagealloc_init(dev);
if (err)
goto err_pagealloc_init;
- err = mlx5_load_one(dev, priv, true);
+ return 0;
+
+err_pagealloc_init:
+ mlx5_health_cleanup(dev);
+err_health_init:
+ debugfs_remove(dev->priv.dbg_root);
+
+ return err;
+}
+
+static void mlx5_mdev_uninit(struct mlx5_core_dev *dev)
+{
+ mlx5_pagealloc_cleanup(dev);
+ mlx5_health_cleanup(dev);
+ debugfs_remove_recursive(dev->priv.dbg_root);
+}
+
+#define MLX5_IB_MOD "mlx5_ib"
+static int init_one(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+ struct mlx5_core_dev *dev;
+ struct devlink *devlink;
+ int err;
+
+ devlink = devlink_alloc(&mlx5_devlink_ops, sizeof(*dev));
+ if (!devlink) {
+ dev_err(&pdev->dev, "kzalloc failed\n");
+ return -ENOMEM;
+ }
+
+ dev = devlink_priv(devlink);
+
+ err = mlx5_mdev_init(dev, prof_sel, dev_name(&pdev->dev));
+ if (err)
+ goto mdev_init_err;
+
+ err = mlx5_pci_init(dev, pdev, id);
+ if (err) {
+ mlx5_core_err(dev, "mlx5_pci_init failed with error code %d\n",
+ err);
+ goto pci_init_err;
+ }
+
+ err = mlx5_load_one(dev, true);
if (err) {
- dev_err(&pdev->dev, "mlx5_load_one failed with error code %d\n", err);
+ mlx5_core_err(dev, "mlx5_load_one failed with error code %d\n",
+ err);
goto err_load_one;
}
return 0;
clean_load:
- mlx5_unload_one(dev, priv, true);
+ mlx5_unload_one(dev, true);
+
err_load_one:
- mlx5_pagealloc_cleanup(dev);
-err_pagealloc_init:
- mlx5_health_cleanup(dev);
-close_pci:
- mlx5_pci_close(dev, priv);
-clean_dev:
+ mlx5_pci_close(dev);
+pci_init_err:
+ mlx5_mdev_uninit(dev);
+mdev_init_err:
devlink_free(devlink);
return err;
{
struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
struct devlink *devlink = priv_to_devlink(dev);
- struct mlx5_priv *priv = &dev->priv;
devlink_unregister(devlink);
mlx5_unregister_device(dev);
- if (mlx5_unload_one(dev, priv, true)) {
- dev_err(&dev->pdev->dev, "mlx5_unload_one failed\n");
- mlx5_health_cleanup(dev);
+ if (mlx5_unload_one(dev, true)) {
+ mlx5_core_err(dev, "mlx5_unload_one failed\n");
+ mlx5_health_flush(dev);
return;
}
- mlx5_pagealloc_cleanup(dev);
- mlx5_health_cleanup(dev);
- mlx5_pci_close(dev, priv);
+ mlx5_pci_close(dev);
+ mlx5_mdev_uninit(dev);
devlink_free(devlink);
}
pci_channel_state_t state)
{
struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
- struct mlx5_priv *priv = &dev->priv;
- dev_info(&pdev->dev, "%s was called\n", __func__);
+ mlx5_core_info(dev, "%s was called\n", __func__);
mlx5_enter_error_state(dev, false);
- mlx5_unload_one(dev, priv, false);
+ mlx5_unload_one(dev, false);
/* In case of kernel call drain the health wq */
if (state) {
mlx5_drain_health_wq(dev);
count = ioread32be(health->health_counter);
if (count && count != 0xffffffff) {
if (last_count && last_count != count) {
- dev_info(&pdev->dev, "Counter value 0x%x after %d iterations\n", count, i);
+ mlx5_core_info(dev,
+ "wait vital counter value 0x%x after %d iterations\n",
+ count, i);
return 0;
}
last_count = count;
struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
int err;
- dev_info(&pdev->dev, "%s was called\n", __func__);
+ mlx5_core_info(dev, "%s was called\n", __func__);
err = mlx5_pci_enable_device(dev);
if (err) {
- dev_err(&pdev->dev, "%s: mlx5_pci_enable_device failed with error code: %d\n"
- , __func__, err);
+ mlx5_core_err(dev, "%s: mlx5_pci_enable_device failed with error code: %d\n",
+ __func__, err);
return PCI_ERS_RESULT_DISCONNECT;
}
pci_save_state(pdev);
if (wait_vital(pdev)) {
- dev_err(&pdev->dev, "%s: wait_vital timed out\n", __func__);
+ mlx5_core_err(dev, "%s: wait_vital timed out\n", __func__);
return PCI_ERS_RESULT_DISCONNECT;
}
static void mlx5_pci_resume(struct pci_dev *pdev)
{
struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
- struct mlx5_priv *priv = &dev->priv;
int err;
- dev_info(&pdev->dev, "%s was called\n", __func__);
+ mlx5_core_info(dev, "%s was called\n", __func__);
- err = mlx5_load_one(dev, priv, false);
+ err = mlx5_load_one(dev, false);
if (err)
- dev_err(&pdev->dev, "%s: mlx5_load_one failed with error code: %d\n"
- , __func__, err);
+ mlx5_core_err(dev, "%s: mlx5_load_one failed with error code: %d\n",
+ __func__, err);
else
- dev_info(&pdev->dev, "%s: device recovered\n", __func__);
+ mlx5_core_info(dev, "%s: device recovered\n", __func__);
}
static const struct pci_error_handlers mlx5_err_handler = {
static void shutdown(struct pci_dev *pdev)
{
struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
- struct mlx5_priv *priv = &dev->priv;
int err;
- dev_info(&pdev->dev, "Shutdown was called\n");
+ mlx5_core_info(dev, "Shutdown was called\n");
err = mlx5_try_fast_unload(dev);
if (err)
- mlx5_unload_one(dev, priv, false);
+ mlx5_unload_one(dev, false);
mlx5_pci_disable_device(dev);
}
extern uint mlx5_core_debug_mask;
#define mlx5_core_dbg(__dev, format, ...) \
- dev_dbg(&(__dev)->pdev->dev, "%s:%d:(pid %d): " format, \
+ pr_debug("%s:%s:%d:(pid %d): " format, (__dev)->priv.name, \
__func__, __LINE__, current->pid, \
##__VA_ARGS__)
#define mlx5_core_dbg_once(__dev, format, ...) \
- dev_dbg_once(&(__dev)->pdev->dev, "%s:%d:(pid %d): " format, \
+ pr_debug_once("%s:%s:%d:(pid %d): " format, (__dev)->priv.name, \
__func__, __LINE__, current->pid, \
##__VA_ARGS__)
} while (0)
#define mlx5_core_err(__dev, format, ...) \
- dev_err(&(__dev)->pdev->dev, "%s:%d:(pid %d): " format, \
+ pr_err("%s:%s:%d:(pid %d): " format, (__dev)->priv.name, \
__func__, __LINE__, current->pid, \
##__VA_ARGS__)
-#define mlx5_core_err_rl(__dev, format, ...) \
- dev_err_ratelimited(&(__dev)->pdev->dev, \
- "%s:%d:(pid %d): " format, \
- __func__, __LINE__, current->pid, \
+#define mlx5_core_err_rl(__dev, format, ...) \
+ pr_err_ratelimited("%s:%s:%d:(pid %d): " format, (__dev)->priv.name, \
+ __func__, __LINE__, current->pid, \
##__VA_ARGS__)
#define mlx5_core_warn(__dev, format, ...) \
- dev_warn(&(__dev)->pdev->dev, "%s:%d:(pid %d): " format, \
+ pr_warn("%s:%s:%d:(pid %d): " format, (__dev)->priv.name, \
__func__, __LINE__, current->pid, \
##__VA_ARGS__)
#define mlx5_core_warn_once(__dev, format, ...) \
- dev_warn_once(&(__dev)->pdev->dev, "%s:%d:(pid %d): " format, \
+ pr_warn_once("%s:%s:%d:(pid %d): " format, (__dev)->priv.name, \
__func__, __LINE__, current->pid, \
##__VA_ARGS__)
+#define mlx5_core_warn_rl(__dev, format, ...) \
+ pr_warn_ratelimited("%s:%s:%d:(pid %d): " format, (__dev)->priv.name, \
+ __func__, __LINE__, current->pid, \
+ ##__VA_ARGS__)
+
#define mlx5_core_info(__dev, format, ...) \
- dev_info(&(__dev)->pdev->dev, format, ##__VA_ARGS__)
+ pr_info("%s " format, (__dev)->priv.name, ##__VA_ARGS__)
+
+#define mlx5_core_info_rl(__dev, format, ...) \
+ pr_info_ratelimited("%s:%s:%d:(pid %d): " format, (__dev)->priv.name, \
+ __func__, __LINE__, current->pid, \
+ ##__VA_ARGS__)
enum {
MLX5_CMD_DATA, /* print command payload only */
else
system_page_index = index;
- return (pci_resource_start(mdev->pdev, 0) >> PAGE_SHIFT) + system_page_index;
+ return (mdev->bar_addr >> PAGE_SHIFT) + system_page_index;
}
static void up_rel_func(struct kref *kref)
if (!(mlxsw_core->bus->features & MLXSW_BUS_F_TXRX))
return 0;
- emad_wq = alloc_workqueue("mlxsw_core_emad", WQ_MEM_RECLAIM, 0);
+ emad_wq = alloc_workqueue("mlxsw_core_emad", 0, 0);
if (!emad_wq)
return -ENOMEM;
mlxsw_core->emad_wq = emad_wq;
pool_type, p_cur, p_max);
}
+static int
+mlxsw_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req,
+ struct netlink_ext_ack *extack)
+{
+ struct mlxsw_core *mlxsw_core = devlink_priv(devlink);
+ char fw_info_psid[MLXSW_REG_MGIR_FW_INFO_PSID_SIZE];
+ u32 hw_rev, fw_major, fw_minor, fw_sub_minor;
+ char mgir_pl[MLXSW_REG_MGIR_LEN];
+ char buf[32];
+ int err;
+
+ err = devlink_info_driver_name_put(req,
+ mlxsw_core->bus_info->device_kind);
+ if (err)
+ return err;
+
+ mlxsw_reg_mgir_pack(mgir_pl);
+ err = mlxsw_reg_query(mlxsw_core, MLXSW_REG(mgir), mgir_pl);
+ if (err)
+ return err;
+ mlxsw_reg_mgir_unpack(mgir_pl, &hw_rev, fw_info_psid, &fw_major,
+ &fw_minor, &fw_sub_minor);
+
+ sprintf(buf, "%X", hw_rev);
+ err = devlink_info_version_fixed_put(req, "hw.revision", buf);
+ if (err)
+ return err;
+
+ err = devlink_info_version_fixed_put(req, "fw.psid", fw_info_psid);
+ if (err)
+ return err;
+
+ sprintf(buf, "%d.%d.%d", fw_major, fw_minor, fw_sub_minor);
+ err = devlink_info_version_running_put(req, "fw.version", buf);
+ if (err)
+ return err;
+
+ return 0;
+}
+
static int mlxsw_devlink_core_bus_device_reload(struct devlink *devlink,
struct netlink_ext_ack *extack)
{
.sb_occ_max_clear = mlxsw_devlink_sb_occ_max_clear,
.sb_occ_port_pool_get = mlxsw_devlink_sb_occ_port_pool_get,
.sb_occ_tc_port_bind_get = mlxsw_devlink_sb_occ_tc_port_bind_get,
+ .info_get = mlxsw_devlink_info_get,
};
static int
int mlxsw_core_port_init(struct mlxsw_core *mlxsw_core, u8 local_port,
u32 port_number, bool split,
- u32 split_port_subnumber)
+ u32 split_port_subnumber,
+ const unsigned char *switch_id,
+ unsigned char switch_id_len)
{
struct devlink *devlink = priv_to_devlink(mlxsw_core);
struct mlxsw_core_port *mlxsw_core_port =
mlxsw_core_port->local_port = local_port;
devlink_port_attrs_set(devlink_port, DEVLINK_PORT_FLAVOUR_PHYSICAL,
- port_number, split, split_port_subnumber);
+ port_number, split, split_port_subnumber,
+ switch_id, switch_id_len);
err = devlink_port_register(devlink, devlink_port, local_port);
if (err)
memset(mlxsw_core_port, 0, sizeof(*mlxsw_core_port));
{
int err;
- mlxsw_wq = alloc_workqueue(mlxsw_core_driver_name, WQ_MEM_RECLAIM, 0);
+ mlxsw_wq = alloc_workqueue(mlxsw_core_driver_name, 0, 0);
if (!mlxsw_wq)
return -ENOMEM;
- mlxsw_owq = alloc_ordered_workqueue("%s_ordered", WQ_MEM_RECLAIM,
+ mlxsw_owq = alloc_ordered_workqueue("%s_ordered", 0,
mlxsw_core_driver_name);
if (!mlxsw_owq) {
err = -ENOMEM;
void *mlxsw_core_port_driver_priv(struct mlxsw_core_port *mlxsw_core_port);
int mlxsw_core_port_init(struct mlxsw_core *mlxsw_core, u8 local_port,
u32 port_number, bool split,
- u32 split_port_subnumber);
+ u32 split_port_subnumber,
+ const unsigned char *switch_id,
+ unsigned char switch_id_len);
void mlxsw_core_port_fini(struct mlxsw_core *mlxsw_core, u8 local_port);
void mlxsw_core_port_eth_set(struct mlxsw_core *mlxsw_core, u8 local_port,
void *port_driver_priv, struct net_device *dev);
return 0;
}
-static int mlxsw_m_port_get_port_parent_id(struct net_device *dev,
- struct netdev_phys_item_id *ppid)
-{
- struct mlxsw_m_port *mlxsw_m_port = netdev_priv(dev);
- struct mlxsw_m *mlxsw_m = mlxsw_m_port->mlxsw_m;
-
- ppid->id_len = sizeof(mlxsw_m->base_mac);
- memcpy(&ppid->id, &mlxsw_m->base_mac, ppid->id_len);
-
- return 0;
-}
-
static struct devlink_port *
mlxsw_m_port_get_devlink_port(struct net_device *dev)
{
static const struct net_device_ops mlxsw_m_port_netdev_ops = {
.ndo_open = mlxsw_m_port_dummy_open_stop,
.ndo_stop = mlxsw_m_port_dummy_open_stop,
- .ndo_get_port_parent_id = mlxsw_m_port_get_port_parent_id,
.ndo_get_devlink_port = mlxsw_m_port_get_devlink_port,
};
int err;
err = mlxsw_core_port_init(mlxsw_m->core, local_port,
- module + 1, false, 0);
+ module + 1, false, 0,
+ mlxsw_m->base_mac,
+ sizeof(mlxsw_m->base_mac));
if (err) {
dev_err(mlxsw_m->bus_info->dev, "Port %d: Failed to init core port\n",
local_port);
mlxsw_reg_mpar_pa_id_set(payload, pa_id);
}
+/* MGIR - Management General Information Register
+ * ----------------------------------------------
+ * MGIR register allows software to query the hardware and firmware general
+ * information.
+ */
+#define MLXSW_REG_MGIR_ID 0x9020
+#define MLXSW_REG_MGIR_LEN 0x9C
+
+MLXSW_REG_DEFINE(mgir, MLXSW_REG_MGIR_ID, MLXSW_REG_MGIR_LEN);
+
+/* reg_mgir_hw_info_device_hw_revision
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, mgir, hw_info_device_hw_revision, 0x0, 16, 16);
+
+#define MLXSW_REG_MGIR_FW_INFO_PSID_SIZE 16
+
+/* reg_mgir_fw_info_psid
+ * PSID (ASCII string).
+ * Access: RO
+ */
+MLXSW_ITEM_BUF(reg, mgir, fw_info_psid, 0x30, MLXSW_REG_MGIR_FW_INFO_PSID_SIZE);
+
+/* reg_mgir_fw_info_extended_major
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, mgir, fw_info_extended_major, 0x44, 0, 32);
+
+/* reg_mgir_fw_info_extended_minor
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, mgir, fw_info_extended_minor, 0x48, 0, 32);
+
+/* reg_mgir_fw_info_extended_sub_minor
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, mgir, fw_info_extended_sub_minor, 0x4C, 0, 32);
+
+static inline void mlxsw_reg_mgir_pack(char *payload)
+{
+ MLXSW_REG_ZERO(mgir, payload);
+}
+
+static inline void
+mlxsw_reg_mgir_unpack(char *payload, u32 *hw_rev, char *fw_info_psid,
+ u32 *fw_major, u32 *fw_minor, u32 *fw_sub_minor)
+{
+ *hw_rev = mlxsw_reg_mgir_hw_info_device_hw_revision_get(payload);
+ mlxsw_reg_mgir_fw_info_psid_memcpy_from(payload, fw_info_psid);
+ *fw_major = mlxsw_reg_mgir_fw_info_extended_major_get(payload);
+ *fw_minor = mlxsw_reg_mgir_fw_info_extended_minor_get(payload);
+ *fw_sub_minor = mlxsw_reg_mgir_fw_info_extended_sub_minor_get(payload);
+}
+
/* MRSR - Management Reset and Shutdown Register
* ---------------------------------------------
* MRSR register is used to reset or shutdown the switch or
MLXSW_REG(mcia),
MLXSW_REG(mpat),
MLXSW_REG(mpar),
+ MLXSW_REG(mgir),
MLXSW_REG(mrsr),
MLXSW_REG(mlcr),
MLXSW_REG(mpsc),
mlxsw_sp_feature_hw_tc);
}
-static int mlxsw_sp_port_get_port_parent_id(struct net_device *dev,
- struct netdev_phys_item_id *ppid)
-{
- struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
- struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
-
- ppid->id_len = sizeof(mlxsw_sp->base_mac);
- memcpy(&ppid->id, &mlxsw_sp->base_mac, ppid->id_len);
-
- return 0;
-}
-
static struct devlink_port *
mlxsw_sp_port_get_devlink_port(struct net_device *dev)
{
.ndo_vlan_rx_add_vid = mlxsw_sp_port_add_vid,
.ndo_vlan_rx_kill_vid = mlxsw_sp_port_kill_vid,
.ndo_set_features = mlxsw_sp_set_features,
- .ndo_get_port_parent_id = mlxsw_sp_port_get_port_parent_id,
.ndo_get_devlink_port = mlxsw_sp_port_get_devlink_port,
};
int err;
err = mlxsw_core_port_init(mlxsw_sp->core, local_port,
- module + 1, split, lane / width);
+ module + 1, split, lane / width,
+ mlxsw_sp->base_mac,
+ sizeof(mlxsw_sp->base_mac));
if (err) {
dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to init core port\n",
local_port);
struct mlxsw_sp_acl_tcam_rehash_ctx ctx;
} rehash;
struct mlxsw_sp *mlxsw_sp;
- bool failed_rollback; /* Indicates failed rollback during migration */
unsigned int ref_count;
};
struct mlxsw_sp_acl_tcam_chunk *new_chunk;
new_chunk = mlxsw_sp_acl_tcam_chunk_create(mlxsw_sp, vchunk, region);
- if (IS_ERR(new_chunk)) {
- if (ctx->this_is_rollback)
- vchunk->vregion->failed_rollback = true;
+ if (IS_ERR(new_chunk))
return PTR_ERR(new_chunk);
- }
vchunk->chunk2 = vchunk->chunk;
vchunk->chunk = new_chunk;
ctx->current_vchunk = vchunk;
err = mlxsw_sp_acl_tcam_ventry_migrate(mlxsw_sp, ventry,
vchunk->chunk, credits);
if (err) {
- if (ctx->this_is_rollback)
+ if (ctx->this_is_rollback) {
+ /* Save the ventry which we ended with and try
+ * to continue later on.
+ */
+ ctx->start_ventry = ventry;
return err;
+ }
/* Swap the chunk and chunk2 pointers so the follow-up
* rollback call will see the original chunk pointer
* in vchunk->chunk.
ctx->this_is_rollback = true;
err2 = mlxsw_sp_acl_tcam_vchunk_migrate_all(mlxsw_sp, vregion,
ctx, credits);
- if (err2)
- vregion->failed_rollback = true;
+ if (err2) {
+ trace_mlxsw_sp_acl_tcam_vregion_rehash_rollback_failed(mlxsw_sp,
+ vregion);
+ dev_err(mlxsw_sp->bus_info->dev, "Failed to rollback during vregion migration fail\n");
+ /* Let the rollback to be continued later on. */
+ }
}
mutex_unlock(&vregion->lock);
trace_mlxsw_sp_acl_tcam_vregion_migrate_end(mlxsw_sp, vregion);
int err;
trace_mlxsw_sp_acl_tcam_vregion_rehash(mlxsw_sp, vregion);
- if (vregion->failed_rollback)
- return -EBUSY;
hints_priv = ops->region_rehash_hints_get(vregion->region->priv);
if (IS_ERR(hints_priv))
struct mlxsw_sp_acl_tcam_region *unused_region = vregion->region2;
const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
- if (!vregion->failed_rollback) {
- vregion->region2 = NULL;
- mlxsw_sp_acl_tcam_group_region_detach(mlxsw_sp, unused_region);
- mlxsw_sp_acl_tcam_region_destroy(mlxsw_sp, unused_region);
- }
+ vregion->region2 = NULL;
+ mlxsw_sp_acl_tcam_group_region_detach(mlxsw_sp, unused_region);
+ mlxsw_sp_acl_tcam_region_destroy(mlxsw_sp, unused_region);
ops->region_rehash_hints_put(ctx->hints_priv);
ctx->hints_priv = NULL;
}
ctx, credits);
if (err) {
dev_err(mlxsw_sp->bus_info->dev, "Failed to migrate vregion\n");
- if (vregion->failed_rollback) {
- trace_mlxsw_sp_acl_tcam_vregion_rehash_dis(mlxsw_sp,
- vregion);
- dev_err(mlxsw_sp->bus_info->dev, "Failed to rollback during vregion migration fail\n");
- }
}
if (*credits >= 0)
{MLXSW_REG_SBXX_DIR_EGRESS, 1},
{MLXSW_REG_SBXX_DIR_EGRESS, 2},
{MLXSW_REG_SBXX_DIR_EGRESS, 3},
+ {MLXSW_REG_SBXX_DIR_EGRESS, 15},
};
#define MLXSW_SP_SB_ING_TC_COUNT 8
MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, 0),
MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, 0),
MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, 0),
+ MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, MLXSW_SP_SB_INFI),
};
static int mlxsw_sp_sb_prs_init(struct mlxsw_sp *mlxsw_sp,
MLXSW_SP_SB_CM(0, 7, 4),
MLXSW_SP_SB_CM(0, 7, 4),
MLXSW_SP_SB_CM(0, 7, 4),
- MLXSW_SP_SB_CM(0, 7, 4),
- MLXSW_SP_SB_CM(0, 7, 4),
- MLXSW_SP_SB_CM(0, 7, 4),
- MLXSW_SP_SB_CM(0, 7, 4),
- MLXSW_SP_SB_CM(0, 7, 4),
- MLXSW_SP_SB_CM(0, 7, 4),
- MLXSW_SP_SB_CM(0, 7, 4),
- MLXSW_SP_SB_CM(0, 7, 4),
+ MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8),
+ MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8),
+ MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8),
+ MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8),
+ MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8),
+ MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8),
+ MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8),
+ MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8),
MLXSW_SP_SB_CM(1, 0xff, 4),
};
MLXSW_SP_SB_PM(0, 0),
MLXSW_SP_SB_PM(0, 0),
MLXSW_SP_SB_PM(0, 0),
+ MLXSW_SP_SB_PM(10000, 90000),
};
static int mlxsw_sp_port_sb_pms_init(struct mlxsw_sp_port *mlxsw_sp_port)
MLXSW_REG_RAUHT_OP_WRITE_DELETE;
}
-static void
+static int
mlxsw_sp_router_neigh_entry_op4(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_neigh_entry *neigh_entry,
enum mlxsw_reg_rauht_op op)
if (neigh_entry->counter_valid)
mlxsw_reg_rauht_pack_counter(rauht_pl,
neigh_entry->counter_index);
- mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rauht), rauht_pl);
+ return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rauht), rauht_pl);
}
-static void
+static int
mlxsw_sp_router_neigh_entry_op6(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_neigh_entry *neigh_entry,
enum mlxsw_reg_rauht_op op)
if (neigh_entry->counter_valid)
mlxsw_reg_rauht_pack_counter(rauht_pl,
neigh_entry->counter_index);
- mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rauht), rauht_pl);
+ return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rauht), rauht_pl);
}
bool mlxsw_sp_neigh_ipv6_ignore(struct mlxsw_sp_neigh_entry *neigh_entry)
struct mlxsw_sp_neigh_entry *neigh_entry,
bool adding)
{
+ enum mlxsw_reg_rauht_op op = mlxsw_sp_rauht_op(adding);
+ int err;
+
if (!adding && !neigh_entry->connected)
return;
neigh_entry->connected = adding;
if (neigh_entry->key.n->tbl->family == AF_INET) {
- mlxsw_sp_router_neigh_entry_op4(mlxsw_sp, neigh_entry,
- mlxsw_sp_rauht_op(adding));
+ err = mlxsw_sp_router_neigh_entry_op4(mlxsw_sp, neigh_entry,
+ op);
+ if (err)
+ return;
} else if (neigh_entry->key.n->tbl->family == AF_INET6) {
if (mlxsw_sp_neigh_ipv6_ignore(neigh_entry))
return;
- mlxsw_sp_router_neigh_entry_op6(mlxsw_sp, neigh_entry,
- mlxsw_sp_rauht_op(adding));
+ err = mlxsw_sp_router_neigh_entry_op6(mlxsw_sp, neigh_entry,
+ op);
+ if (err)
+ return;
} else {
WARN_ON_ONCE(1);
+ return;
}
+
+ if (adding)
+ neigh_entry->key.n->flags |= NTF_OFFLOADED;
+ else
+ neigh_entry->key.n->flags &= ~NTF_OFFLOADED;
}
void
static bool mlxsw_sp_fib6_rt_can_mp(const struct fib6_info *rt)
{
/* RTF_CACHE routes are ignored */
- return !(rt->fib6_flags & RTF_ADDRCONF) && rt->fib6_nh.fib_nh_has_gw;
+ return !(rt->fib6_flags & RTF_ADDRCONF) && rt->fib6_nh.fib_nh_gw_family;
}
static struct fib6_info *
static bool mlxsw_sp_rt6_is_gateway(const struct mlxsw_sp *mlxsw_sp,
const struct fib6_info *rt)
{
- return rt->fib6_nh.fib_nh_has_gw ||
+ return rt->fib6_nh.fib_nh_gw_family ||
mlxsw_sp_nexthop6_ipip_type(mlxsw_sp, rt, NULL);
}
NL_SET_ERR_MSG_MOD(info->extack, "FIB offload was aborted. Not configuring route");
return notifier_from_errno(-EINVAL);
}
+ if (info->family == AF_INET) {
+ struct fib_entry_notifier_info *fen_info = ptr;
+
+ if (fen_info->fi->fib_nh_is_v6) {
+ NL_SET_ERR_MSG_MOD(info->extack, "IPv6 gateway with IPv4 route is not supported");
+ return notifier_from_errno(-EINVAL);
+ }
+ }
break;
}
/* A RIF is not created for macvlan netdevs. Their MAC is used to
* populate the FDB
*/
- if (netif_is_macvlan(dev))
+ if (netif_is_macvlan(dev) || netif_is_l3_master(dev))
return 0;
for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) {
dev = rt->dst.dev;
*saddrp = fl4.saddr;
- *daddrp = rt->rt_gateway;
+ if (rt->rt_gw_family == AF_INET)
+ *daddrp = rt->rt_gw4;
+ /* can not offload if route has an IPv6 gateway */
+ else if (rt->rt_gw_family == AF_INET6)
+ dev = NULL;
out:
ip_rt_put(rt);
u16 fid_index;
int err = 0;
- if (switchdev_trans_ph_prepare(trans))
+ if (switchdev_trans_ph_commit(trans))
return 0;
bridge_port = mlxsw_sp_bridge_port_find(mlxsw_sp->bridge, orig_dev);
struct mlxsw_sib_port **ports;
struct mlxsw_core *core;
const struct mlxsw_bus_info *bus_info;
+ u8 hw_id[ETH_ALEN];
};
struct mlxsw_sib_port {
mlxsw_tx_v1_hdr_type_set(txhdr, MLXSW_TXHDR_TYPE_CONTROL);
}
+static int mlxsw_sib_hw_id_get(struct mlxsw_sib *mlxsw_sib)
+{
+ char spad_pl[MLXSW_REG_SPAD_LEN] = {0};
+ int err;
+
+ err = mlxsw_reg_query(mlxsw_sib->core, MLXSW_REG(spad), spad_pl);
+ if (err)
+ return err;
+ mlxsw_reg_spad_base_mac_memcpy_from(spad_pl, mlxsw_sib->hw_id);
+ return 0;
+}
+
static int
mlxsw_sib_port_admin_status_set(struct mlxsw_sib_port *mlxsw_sib_port,
bool is_up)
int err;
err = mlxsw_core_port_init(mlxsw_sib->core, local_port,
- module + 1, false, 0);
+ module + 1, false, 0,
+ mlxsw_sib->hw_id, sizeof(mlxsw_sib->hw_id));
if (err) {
dev_err(mlxsw_sib->bus_info->dev, "Port %d: Failed to init core port\n",
local_port);
mlxsw_sib->core = mlxsw_core;
mlxsw_sib->bus_info = mlxsw_bus_info;
+ err = mlxsw_sib_hw_id_get(mlxsw_sib);
+ if (err) {
+ dev_err(mlxsw_sib->bus_info->dev, "Failed to get switch HW ID\n");
+ return err;
+ }
+
err = mlxsw_sib_ports_create(mlxsw_sib);
if (err) {
dev_err(mlxsw_sib->bus_info->dev, "Failed to create ports\n");
stats->tx_dropped = tx_dropped;
}
-static int mlxsw_sx_port_get_port_parent_id(struct net_device *dev,
- struct netdev_phys_item_id *ppid)
-{
- struct mlxsw_sx_port *mlxsw_sx_port = netdev_priv(dev);
- struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx;
-
- ppid->id_len = sizeof(mlxsw_sx->hw_id);
- memcpy(&ppid->id, &mlxsw_sx->hw_id, ppid->id_len);
-
- return 0;
-}
-
static struct devlink_port *
mlxsw_sx_port_get_devlink_port(struct net_device *dev)
{
.ndo_start_xmit = mlxsw_sx_port_xmit,
.ndo_change_mtu = mlxsw_sx_port_change_mtu,
.ndo_get_stats64 = mlxsw_sx_port_get_stats64,
- .ndo_get_port_parent_id = mlxsw_sx_port_get_port_parent_id,
.ndo_get_devlink_port = mlxsw_sx_port_get_devlink_port,
};
int err;
err = mlxsw_core_port_init(mlxsw_sx->core, local_port,
- module + 1, false, 0);
+ module + 1, false, 0,
+ mlxsw_sx->hw_id, sizeof(mlxsw_sx->hw_id));
if (err) {
dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to init core port\n",
local_port);
struct netdev_hw_addr *hw_addr)
{
struct ocelot *ocelot = port->ocelot;
- struct netdev_hw_addr *ha = kzalloc(sizeof(*ha), GFP_KERNEL);
+ struct netdev_hw_addr *ha = kzalloc(sizeof(*ha), GFP_ATOMIC);
if (!ha)
return -ENOMEM;
ETH_GSTRING_LEN);
}
-static void ocelot_check_stats(struct work_struct *work)
+static void ocelot_update_stats(struct ocelot *ocelot)
{
- struct delayed_work *del_work = to_delayed_work(work);
- struct ocelot *ocelot = container_of(del_work, struct ocelot, stats_work);
int i, j;
mutex_lock(&ocelot->stats_lock);
}
}
- cancel_delayed_work(&ocelot->stats_work);
+ mutex_unlock(&ocelot->stats_lock);
+}
+
+static void ocelot_check_stats_work(struct work_struct *work)
+{
+ struct delayed_work *del_work = to_delayed_work(work);
+ struct ocelot *ocelot = container_of(del_work, struct ocelot,
+ stats_work);
+
+ ocelot_update_stats(ocelot);
+
queue_delayed_work(ocelot->stats_queue, &ocelot->stats_work,
OCELOT_STATS_CHECK_DELAY);
-
- mutex_unlock(&ocelot->stats_lock);
}
static void ocelot_get_ethtool_stats(struct net_device *dev,
int i;
/* check and update now */
- ocelot_check_stats(&ocelot->stats_work.work);
+ ocelot_update_stats(ocelot);
/* Copy all counters */
for (i = 0; i < ocelot->num_stats; i++)
ANA_CPUQ_8021_CFG_CPUQ_BPDU_VAL(6),
ANA_CPUQ_8021_CFG, i);
- INIT_DELAYED_WORK(&ocelot->stats_work, ocelot_check_stats);
+ INIT_DELAYED_WORK(&ocelot->stats_work, ocelot_check_stats_work);
queue_delayed_work(ocelot->stats_queue, &ocelot->stats_work,
OCELOT_STATS_CHECK_DELAY);
return 0;
dma_object->addr))) {
vxge_os_dma_free(devh->pdev, memblock,
&dma_object->acc_handle);
+ memblock = NULL;
goto exit;
}
nfpcore/nfp_resource.o \
nfpcore/nfp_rtsym.o \
nfpcore/nfp_target.o \
+ ccm.o \
nfp_asm.o \
nfp_app.o \
nfp_app_nic.o \
int nfp_abm_ctrl_prio_map_update(struct nfp_abm_link *alink, u32 *packed)
{
+ const u32 cmd = NFP_NET_CFG_MBOX_CMD_PCI_DSCP_PRIOMAP_SET;
struct nfp_net *nn = alink->vnic;
unsigned int i;
int err;
+ err = nfp_net_mbox_lock(nn, alink->abm->prio_map_len);
+ if (err)
+ return err;
+
/* Write data_len and wipe reserved */
nn_writeq(nn, nn->tlv_caps.mbox_off + NFP_NET_ABM_MBOX_DATALEN,
alink->abm->prio_map_len);
nn_writel(nn, nn->tlv_caps.mbox_off + NFP_NET_ABM_MBOX_DATA + i,
packed[i / sizeof(u32)]);
- err = nfp_net_reconfig_mbox(nn,
- NFP_NET_CFG_MBOX_CMD_PCI_DSCP_PRIOMAP_SET);
+ err = nfp_net_mbox_reconfig_and_unlock(nn, cmd);
if (err)
nfp_err(alink->abm->app->cpp,
"setting DSCP -> VQ map failed with error %d\n", err);
}
}
-static struct net_device *nfp_abm_repr_get(struct nfp_app *app, u32 port_id)
+static struct net_device *
+nfp_abm_repr_get(struct nfp_app *app, u32 port_id, bool *redir_egress)
{
enum nfp_repr_type rtype;
struct nfp_reprs *reprs;
.eswitch_mode_get = nfp_abm_eswitch_mode_get,
.eswitch_mode_set = nfp_abm_eswitch_mode_set,
- .repr_get = nfp_abm_repr_get,
+ .dev_get = nfp_abm_repr_get,
};
#include <linux/bug.h>
#include <linux/jiffies.h>
#include <linux/skbuff.h>
-#include <linux/wait.h>
+#include "../ccm.h"
#include "../nfp_app.h"
#include "../nfp_net.h"
#include "fw.h"
#include "main.h"
-#define NFP_BPF_TAG_ALLOC_SPAN (U16_MAX / 4)
-
-static bool nfp_bpf_all_tags_busy(struct nfp_app_bpf *bpf)
-{
- u16 used_tags;
-
- used_tags = bpf->tag_alloc_next - bpf->tag_alloc_last;
-
- return used_tags > NFP_BPF_TAG_ALLOC_SPAN;
-}
-
-static int nfp_bpf_alloc_tag(struct nfp_app_bpf *bpf)
-{
- /* All FW communication for BPF is request-reply. To make sure we
- * don't reuse the message ID too early after timeout - limit the
- * number of requests in flight.
- */
- if (nfp_bpf_all_tags_busy(bpf)) {
- cmsg_warn(bpf, "all FW request contexts busy!\n");
- return -EAGAIN;
- }
-
- WARN_ON(__test_and_set_bit(bpf->tag_alloc_next, bpf->tag_allocator));
- return bpf->tag_alloc_next++;
-}
-
-static void nfp_bpf_free_tag(struct nfp_app_bpf *bpf, u16 tag)
-{
- WARN_ON(!__test_and_clear_bit(tag, bpf->tag_allocator));
-
- while (!test_bit(bpf->tag_alloc_last, bpf->tag_allocator) &&
- bpf->tag_alloc_last != bpf->tag_alloc_next)
- bpf->tag_alloc_last++;
-}
-
static struct sk_buff *
nfp_bpf_cmsg_alloc(struct nfp_app_bpf *bpf, unsigned int size)
{
return size;
}
-static u8 nfp_bpf_cmsg_get_type(struct sk_buff *skb)
-{
- struct cmsg_hdr *hdr;
-
- hdr = (struct cmsg_hdr *)skb->data;
-
- return hdr->type;
-}
-
-static unsigned int nfp_bpf_cmsg_get_tag(struct sk_buff *skb)
-{
- struct cmsg_hdr *hdr;
-
- hdr = (struct cmsg_hdr *)skb->data;
-
- return be16_to_cpu(hdr->tag);
-}
-
-static struct sk_buff *__nfp_bpf_reply(struct nfp_app_bpf *bpf, u16 tag)
-{
- unsigned int msg_tag;
- struct sk_buff *skb;
-
- skb_queue_walk(&bpf->cmsg_replies, skb) {
- msg_tag = nfp_bpf_cmsg_get_tag(skb);
- if (msg_tag == tag) {
- nfp_bpf_free_tag(bpf, tag);
- __skb_unlink(skb, &bpf->cmsg_replies);
- return skb;
- }
- }
-
- return NULL;
-}
-
-static struct sk_buff *nfp_bpf_reply(struct nfp_app_bpf *bpf, u16 tag)
-{
- struct sk_buff *skb;
-
- nfp_ctrl_lock(bpf->app->ctrl);
- skb = __nfp_bpf_reply(bpf, tag);
- nfp_ctrl_unlock(bpf->app->ctrl);
-
- return skb;
-}
-
-static struct sk_buff *nfp_bpf_reply_drop_tag(struct nfp_app_bpf *bpf, u16 tag)
-{
- struct sk_buff *skb;
-
- nfp_ctrl_lock(bpf->app->ctrl);
- skb = __nfp_bpf_reply(bpf, tag);
- if (!skb)
- nfp_bpf_free_tag(bpf, tag);
- nfp_ctrl_unlock(bpf->app->ctrl);
-
- return skb;
-}
-
-static struct sk_buff *
-nfp_bpf_cmsg_wait_reply(struct nfp_app_bpf *bpf, enum nfp_bpf_cmsg_type type,
- int tag)
-{
- struct sk_buff *skb;
- int i, err;
-
- for (i = 0; i < 50; i++) {
- udelay(4);
- skb = nfp_bpf_reply(bpf, tag);
- if (skb)
- return skb;
- }
-
- err = wait_event_interruptible_timeout(bpf->cmsg_wq,
- skb = nfp_bpf_reply(bpf, tag),
- msecs_to_jiffies(5000));
- /* We didn't get a response - try last time and atomically drop
- * the tag even if no response is matched.
- */
- if (!skb)
- skb = nfp_bpf_reply_drop_tag(bpf, tag);
- if (err < 0) {
- cmsg_warn(bpf, "%s waiting for response to 0x%02x: %d\n",
- err == ERESTARTSYS ? "interrupted" : "error",
- type, err);
- return ERR_PTR(err);
- }
- if (!skb) {
- cmsg_warn(bpf, "timeout waiting for response to 0x%02x\n",
- type);
- return ERR_PTR(-ETIMEDOUT);
- }
-
- return skb;
-}
-
-static struct sk_buff *
-nfp_bpf_cmsg_communicate(struct nfp_app_bpf *bpf, struct sk_buff *skb,
- enum nfp_bpf_cmsg_type type, unsigned int reply_size)
-{
- struct cmsg_hdr *hdr;
- int tag;
-
- nfp_ctrl_lock(bpf->app->ctrl);
- tag = nfp_bpf_alloc_tag(bpf);
- if (tag < 0) {
- nfp_ctrl_unlock(bpf->app->ctrl);
- dev_kfree_skb_any(skb);
- return ERR_PTR(tag);
- }
-
- hdr = (void *)skb->data;
- hdr->ver = CMSG_MAP_ABI_VERSION;
- hdr->type = type;
- hdr->tag = cpu_to_be16(tag);
-
- __nfp_app_ctrl_tx(bpf->app, skb);
-
- nfp_ctrl_unlock(bpf->app->ctrl);
-
- skb = nfp_bpf_cmsg_wait_reply(bpf, type, tag);
- if (IS_ERR(skb))
- return skb;
-
- hdr = (struct cmsg_hdr *)skb->data;
- if (hdr->type != __CMSG_REPLY(type)) {
- cmsg_warn(bpf, "cmsg drop - wrong type 0x%02x != 0x%02lx!\n",
- hdr->type, __CMSG_REPLY(type));
- goto err_free;
- }
- /* 0 reply_size means caller will do the validation */
- if (reply_size && skb->len != reply_size) {
- cmsg_warn(bpf, "cmsg drop - type 0x%02x wrong size %d != %d!\n",
- type, skb->len, reply_size);
- goto err_free;
- }
-
- return skb;
-err_free:
- dev_kfree_skb_any(skb);
- return ERR_PTR(-EIO);
-}
-
static int
nfp_bpf_ctrl_rc_to_errno(struct nfp_app_bpf *bpf,
struct cmsg_reply_map_simple *reply)
req->map_type = cpu_to_be32(map->map_type);
req->map_flags = 0;
- skb = nfp_bpf_cmsg_communicate(bpf, skb, CMSG_TYPE_MAP_ALLOC,
- sizeof(*reply));
+ skb = nfp_ccm_communicate(&bpf->ccm, skb, NFP_CCM_TYPE_BPF_MAP_ALLOC,
+ sizeof(*reply));
if (IS_ERR(skb))
return PTR_ERR(skb);
req = (void *)skb->data;
req->tid = cpu_to_be32(nfp_map->tid);
- skb = nfp_bpf_cmsg_communicate(bpf, skb, CMSG_TYPE_MAP_FREE,
- sizeof(*reply));
+ skb = nfp_ccm_communicate(&bpf->ccm, skb, NFP_CCM_TYPE_BPF_MAP_FREE,
+ sizeof(*reply));
if (IS_ERR(skb)) {
cmsg_warn(bpf, "leaking map - I/O error\n");
return;
}
static int
-nfp_bpf_ctrl_entry_op(struct bpf_offloaded_map *offmap,
- enum nfp_bpf_cmsg_type op,
+nfp_bpf_ctrl_entry_op(struct bpf_offloaded_map *offmap, enum nfp_ccm_type op,
u8 *key, u8 *value, u64 flags, u8 *out_key, u8 *out_value)
{
struct nfp_bpf_map *nfp_map = offmap->dev_priv;
memcpy(nfp_bpf_ctrl_req_val(bpf, req, 0), value,
map->value_size);
- skb = nfp_bpf_cmsg_communicate(bpf, skb, op,
- nfp_bpf_cmsg_map_reply_size(bpf, 1));
+ skb = nfp_ccm_communicate(&bpf->ccm, skb, op,
+ nfp_bpf_cmsg_map_reply_size(bpf, 1));
if (IS_ERR(skb))
return PTR_ERR(skb);
int nfp_bpf_ctrl_update_entry(struct bpf_offloaded_map *offmap,
void *key, void *value, u64 flags)
{
- return nfp_bpf_ctrl_entry_op(offmap, CMSG_TYPE_MAP_UPDATE,
+ return nfp_bpf_ctrl_entry_op(offmap, NFP_CCM_TYPE_BPF_MAP_UPDATE,
key, value, flags, NULL, NULL);
}
int nfp_bpf_ctrl_del_entry(struct bpf_offloaded_map *offmap, void *key)
{
- return nfp_bpf_ctrl_entry_op(offmap, CMSG_TYPE_MAP_DELETE,
+ return nfp_bpf_ctrl_entry_op(offmap, NFP_CCM_TYPE_BPF_MAP_DELETE,
key, NULL, 0, NULL, NULL);
}
int nfp_bpf_ctrl_lookup_entry(struct bpf_offloaded_map *offmap,
void *key, void *value)
{
- return nfp_bpf_ctrl_entry_op(offmap, CMSG_TYPE_MAP_LOOKUP,
+ return nfp_bpf_ctrl_entry_op(offmap, NFP_CCM_TYPE_BPF_MAP_LOOKUP,
key, NULL, 0, NULL, value);
}
int nfp_bpf_ctrl_getfirst_entry(struct bpf_offloaded_map *offmap,
void *next_key)
{
- return nfp_bpf_ctrl_entry_op(offmap, CMSG_TYPE_MAP_GETFIRST,
+ return nfp_bpf_ctrl_entry_op(offmap, NFP_CCM_TYPE_BPF_MAP_GETFIRST,
NULL, NULL, 0, next_key, NULL);
}
int nfp_bpf_ctrl_getnext_entry(struct bpf_offloaded_map *offmap,
void *key, void *next_key)
{
- return nfp_bpf_ctrl_entry_op(offmap, CMSG_TYPE_MAP_GETNEXT,
+ return nfp_bpf_ctrl_entry_op(offmap, NFP_CCM_TYPE_BPF_MAP_GETNEXT,
key, NULL, 0, next_key, NULL);
}
void nfp_bpf_ctrl_msg_rx(struct nfp_app *app, struct sk_buff *skb)
{
struct nfp_app_bpf *bpf = app->priv;
- unsigned int tag;
if (unlikely(skb->len < sizeof(struct cmsg_reply_map_simple))) {
cmsg_warn(bpf, "cmsg drop - too short %d!\n", skb->len);
- goto err_free;
+ dev_kfree_skb_any(skb);
+ return;
}
- if (nfp_bpf_cmsg_get_type(skb) == CMSG_TYPE_BPF_EVENT) {
+ if (nfp_ccm_get_type(skb) == NFP_CCM_TYPE_BPF_BPF_EVENT) {
if (!nfp_bpf_event_output(bpf, skb->data, skb->len))
dev_consume_skb_any(skb);
else
dev_kfree_skb_any(skb);
- return;
}
- nfp_ctrl_lock(bpf->app->ctrl);
-
- tag = nfp_bpf_cmsg_get_tag(skb);
- if (unlikely(!test_bit(tag, bpf->tag_allocator))) {
- cmsg_warn(bpf, "cmsg drop - no one is waiting for tag %u!\n",
- tag);
- goto err_unlock;
- }
-
- __skb_queue_tail(&bpf->cmsg_replies, skb);
- wake_up_interruptible_all(&bpf->cmsg_wq);
-
- nfp_ctrl_unlock(bpf->app->ctrl);
-
- return;
-err_unlock:
- nfp_ctrl_unlock(bpf->app->ctrl);
-err_free:
- dev_kfree_skb_any(skb);
+ nfp_ccm_rx(&bpf->ccm, skb);
}
void
nfp_bpf_ctrl_msg_rx_raw(struct nfp_app *app, const void *data, unsigned int len)
{
+ const struct nfp_ccm_hdr *hdr = data;
struct nfp_app_bpf *bpf = app->priv;
- const struct cmsg_hdr *hdr = data;
if (unlikely(len < sizeof(struct cmsg_reply_map_simple))) {
cmsg_warn(bpf, "cmsg drop - too short %d!\n", len);
return;
}
- if (hdr->type == CMSG_TYPE_BPF_EVENT)
+ if (hdr->type == NFP_CCM_TYPE_BPF_BPF_EVENT)
nfp_bpf_event_output(bpf, data, len);
else
cmsg_warn(bpf, "cmsg drop - msg type %d with raw buffer!\n",
#include <linux/bitops.h>
#include <linux/types.h>
+#include "../ccm.h"
/* Kernel's enum bpf_reg_type is not uABI so people may change it breaking
* our FW ABI. In that case we will do translation in the driver.
/*
* Types defined for map related control messages
*/
-#define CMSG_MAP_ABI_VERSION 1
-
-enum nfp_bpf_cmsg_type {
- CMSG_TYPE_MAP_ALLOC = 1,
- CMSG_TYPE_MAP_FREE = 2,
- CMSG_TYPE_MAP_LOOKUP = 3,
- CMSG_TYPE_MAP_UPDATE = 4,
- CMSG_TYPE_MAP_DELETE = 5,
- CMSG_TYPE_MAP_GETNEXT = 6,
- CMSG_TYPE_MAP_GETFIRST = 7,
- CMSG_TYPE_BPF_EVENT = 8,
- __CMSG_TYPE_MAP_MAX,
-};
-
-#define CMSG_TYPE_MAP_REPLY_BIT 7
-#define __CMSG_REPLY(req) (BIT(CMSG_TYPE_MAP_REPLY_BIT) | (req))
/* BPF ABIv2 fixed-length control message fields */
#define CMSG_MAP_KEY_LW 16
CMSG_RC_ERR_MAP_E2BIG = 7,
};
-struct cmsg_hdr {
- u8 type;
- u8 ver;
- __be16 tag;
-};
-
struct cmsg_reply_map_simple {
- struct cmsg_hdr hdr;
+ struct nfp_ccm_hdr hdr;
__be32 rc;
};
struct cmsg_req_map_alloc_tbl {
- struct cmsg_hdr hdr;
+ struct nfp_ccm_hdr hdr;
__be32 key_size; /* in bytes */
__be32 value_size; /* in bytes */
__be32 max_entries;
};
struct cmsg_req_map_free_tbl {
- struct cmsg_hdr hdr;
+ struct nfp_ccm_hdr hdr;
__be32 tid;
};
};
struct cmsg_req_map_op {
- struct cmsg_hdr hdr;
+ struct nfp_ccm_hdr hdr;
__be32 tid;
__be32 count;
__be32 flags;
};
struct cmsg_bpf_event {
- struct cmsg_hdr hdr;
+ struct nfp_ccm_hdr hdr;
__be32 cpu_id;
__be64 map_ptr;
__be32 data_size;
bpf->app = app;
app->priv = bpf;
- skb_queue_head_init(&bpf->cmsg_replies);
- init_waitqueue_head(&bpf->cmsg_wq);
INIT_LIST_HEAD(&bpf->map_list);
- err = rhashtable_init(&bpf->maps_neutral, &nfp_bpf_maps_neutral_params);
+ err = nfp_ccm_init(&bpf->ccm, app);
if (err)
goto err_free_bpf;
+ err = rhashtable_init(&bpf->maps_neutral, &nfp_bpf_maps_neutral_params);
+ if (err)
+ goto err_clean_ccm;
+
nfp_bpf_init_capabilities(bpf);
err = nfp_bpf_parse_capabilities(app);
err_free_neutral_maps:
rhashtable_destroy(&bpf->maps_neutral);
+err_clean_ccm:
+ nfp_ccm_clean(&bpf->ccm);
err_free_bpf:
kfree(bpf);
return err;
struct nfp_app_bpf *bpf = app->priv;
bpf_offload_dev_destroy(bpf->bpf_dev);
- WARN_ON(!skb_queue_empty(&bpf->cmsg_replies));
+ nfp_ccm_clean(&bpf->ccm);
WARN_ON(!list_empty(&bpf->map_list));
WARN_ON(bpf->maps_in_use || bpf->map_elems_in_use);
rhashtable_free_and_destroy(&bpf->maps_neutral,
#include <linux/types.h>
#include <linux/wait.h>
+#include "../ccm.h"
#include "../nfp_asm.h"
#include "fw.h"
/**
* struct nfp_app_bpf - bpf app priv structure
* @app: backpointer to the app
+ * @ccm: common control message handler data
*
* @bpf_dev: BPF offload device handle
*
- * @tag_allocator: bitmap of control message tags in use
- * @tag_alloc_next: next tag bit to allocate
- * @tag_alloc_last: next tag bit to be freed
- *
- * @cmsg_replies: received cmsg replies waiting to be consumed
- * @cmsg_wq: work queue for waiting for cmsg replies
- *
* @cmsg_key_sz: size of key in cmsg element array
* @cmsg_val_sz: size of value in cmsg element array
*
*/
struct nfp_app_bpf {
struct nfp_app *app;
+ struct nfp_ccm ccm;
struct bpf_offload_dev *bpf_dev;
- DECLARE_BITMAP(tag_allocator, U16_MAX + 1);
- u16 tag_alloc_next;
- u16 tag_alloc_last;
-
- struct sk_buff_head cmsg_replies;
- struct wait_queue_head cmsg_wq;
-
unsigned int cmsg_key_sz;
unsigned int cmsg_val_sz;
#include <net/tc_act/tc_mirred.h>
#include "main.h"
+#include "../ccm.h"
#include "../nfp_app.h"
#include "../nfp_net_ctrl.h"
#include "../nfp_net.h"
if (len < sizeof(struct cmsg_bpf_event) + pkt_size + data_size)
return -EINVAL;
- if (cbe->hdr.ver != CMSG_MAP_ABI_VERSION)
+ if (cbe->hdr.ver != NFP_CCM_ABI_VERSION)
return -EINVAL;
rcu_read_lock();
--- /dev/null
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/* Copyright (C) 2016-2019 Netronome Systems, Inc. */
+
+#include <linux/bitops.h>
+
+#include "ccm.h"
+#include "nfp_app.h"
+#include "nfp_net.h"
+
+#define NFP_CCM_TYPE_REPLY_BIT 7
+#define __NFP_CCM_REPLY(req) (BIT(NFP_CCM_TYPE_REPLY_BIT) | (req))
+
+#define ccm_warn(app, msg...) nn_dp_warn(&(app)->ctrl->dp, msg)
+
+#define NFP_CCM_TAG_ALLOC_SPAN (U16_MAX / 4)
+
+static bool nfp_ccm_all_tags_busy(struct nfp_ccm *ccm)
+{
+ u16 used_tags;
+
+ used_tags = ccm->tag_alloc_next - ccm->tag_alloc_last;
+
+ return used_tags > NFP_CCM_TAG_ALLOC_SPAN;
+}
+
+static int nfp_ccm_alloc_tag(struct nfp_ccm *ccm)
+{
+ /* CCM is for FW communication which is request-reply. To make sure
+ * we don't reuse the message ID too early after timeout - limit the
+ * number of requests in flight.
+ */
+ if (unlikely(nfp_ccm_all_tags_busy(ccm))) {
+ ccm_warn(ccm->app, "all FW request contexts busy!\n");
+ return -EAGAIN;
+ }
+
+ WARN_ON(__test_and_set_bit(ccm->tag_alloc_next, ccm->tag_allocator));
+ return ccm->tag_alloc_next++;
+}
+
+static void nfp_ccm_free_tag(struct nfp_ccm *ccm, u16 tag)
+{
+ WARN_ON(!__test_and_clear_bit(tag, ccm->tag_allocator));
+
+ while (!test_bit(ccm->tag_alloc_last, ccm->tag_allocator) &&
+ ccm->tag_alloc_last != ccm->tag_alloc_next)
+ ccm->tag_alloc_last++;
+}
+
+static struct sk_buff *__nfp_ccm_reply(struct nfp_ccm *ccm, u16 tag)
+{
+ unsigned int msg_tag;
+ struct sk_buff *skb;
+
+ skb_queue_walk(&ccm->replies, skb) {
+ msg_tag = nfp_ccm_get_tag(skb);
+ if (msg_tag == tag) {
+ nfp_ccm_free_tag(ccm, tag);
+ __skb_unlink(skb, &ccm->replies);
+ return skb;
+ }
+ }
+
+ return NULL;
+}
+
+static struct sk_buff *
+nfp_ccm_reply(struct nfp_ccm *ccm, struct nfp_app *app, u16 tag)
+{
+ struct sk_buff *skb;
+
+ nfp_ctrl_lock(app->ctrl);
+ skb = __nfp_ccm_reply(ccm, tag);
+ nfp_ctrl_unlock(app->ctrl);
+
+ return skb;
+}
+
+static struct sk_buff *
+nfp_ccm_reply_drop_tag(struct nfp_ccm *ccm, struct nfp_app *app, u16 tag)
+{
+ struct sk_buff *skb;
+
+ nfp_ctrl_lock(app->ctrl);
+ skb = __nfp_ccm_reply(ccm, tag);
+ if (!skb)
+ nfp_ccm_free_tag(ccm, tag);
+ nfp_ctrl_unlock(app->ctrl);
+
+ return skb;
+}
+
+static struct sk_buff *
+nfp_ccm_wait_reply(struct nfp_ccm *ccm, struct nfp_app *app,
+ enum nfp_ccm_type type, int tag)
+{
+ struct sk_buff *skb;
+ int i, err;
+
+ for (i = 0; i < 50; i++) {
+ udelay(4);
+ skb = nfp_ccm_reply(ccm, app, tag);
+ if (skb)
+ return skb;
+ }
+
+ err = wait_event_interruptible_timeout(ccm->wq,
+ skb = nfp_ccm_reply(ccm, app,
+ tag),
+ msecs_to_jiffies(5000));
+ /* We didn't get a response - try last time and atomically drop
+ * the tag even if no response is matched.
+ */
+ if (!skb)
+ skb = nfp_ccm_reply_drop_tag(ccm, app, tag);
+ if (err < 0) {
+ ccm_warn(app, "%s waiting for response to 0x%02x: %d\n",
+ err == ERESTARTSYS ? "interrupted" : "error",
+ type, err);
+ return ERR_PTR(err);
+ }
+ if (!skb) {
+ ccm_warn(app, "timeout waiting for response to 0x%02x\n", type);
+ return ERR_PTR(-ETIMEDOUT);
+ }
+
+ return skb;
+}
+
+struct sk_buff *
+nfp_ccm_communicate(struct nfp_ccm *ccm, struct sk_buff *skb,
+ enum nfp_ccm_type type, unsigned int reply_size)
+{
+ struct nfp_app *app = ccm->app;
+ struct nfp_ccm_hdr *hdr;
+ int reply_type, tag;
+
+ nfp_ctrl_lock(app->ctrl);
+ tag = nfp_ccm_alloc_tag(ccm);
+ if (tag < 0) {
+ nfp_ctrl_unlock(app->ctrl);
+ dev_kfree_skb_any(skb);
+ return ERR_PTR(tag);
+ }
+
+ hdr = (void *)skb->data;
+ hdr->ver = NFP_CCM_ABI_VERSION;
+ hdr->type = type;
+ hdr->tag = cpu_to_be16(tag);
+
+ __nfp_app_ctrl_tx(app, skb);
+
+ nfp_ctrl_unlock(app->ctrl);
+
+ skb = nfp_ccm_wait_reply(ccm, app, type, tag);
+ if (IS_ERR(skb))
+ return skb;
+
+ reply_type = nfp_ccm_get_type(skb);
+ if (reply_type != __NFP_CCM_REPLY(type)) {
+ ccm_warn(app, "cmsg drop - wrong type 0x%02x != 0x%02lx!\n",
+ reply_type, __NFP_CCM_REPLY(type));
+ goto err_free;
+ }
+ /* 0 reply_size means caller will do the validation */
+ if (reply_size && skb->len != reply_size) {
+ ccm_warn(app, "cmsg drop - type 0x%02x wrong size %d != %d!\n",
+ type, skb->len, reply_size);
+ goto err_free;
+ }
+
+ return skb;
+err_free:
+ dev_kfree_skb_any(skb);
+ return ERR_PTR(-EIO);
+}
+
+void nfp_ccm_rx(struct nfp_ccm *ccm, struct sk_buff *skb)
+{
+ struct nfp_app *app = ccm->app;
+ unsigned int tag;
+
+ if (unlikely(skb->len < sizeof(struct nfp_ccm_hdr))) {
+ ccm_warn(app, "cmsg drop - too short %d!\n", skb->len);
+ goto err_free;
+ }
+
+ nfp_ctrl_lock(app->ctrl);
+
+ tag = nfp_ccm_get_tag(skb);
+ if (unlikely(!test_bit(tag, ccm->tag_allocator))) {
+ ccm_warn(app, "cmsg drop - no one is waiting for tag %u!\n",
+ tag);
+ goto err_unlock;
+ }
+
+ __skb_queue_tail(&ccm->replies, skb);
+ wake_up_interruptible_all(&ccm->wq);
+
+ nfp_ctrl_unlock(app->ctrl);
+ return;
+
+err_unlock:
+ nfp_ctrl_unlock(app->ctrl);
+err_free:
+ dev_kfree_skb_any(skb);
+}
+
+int nfp_ccm_init(struct nfp_ccm *ccm, struct nfp_app *app)
+{
+ ccm->app = app;
+ skb_queue_head_init(&ccm->replies);
+ init_waitqueue_head(&ccm->wq);
+ return 0;
+}
+
+void nfp_ccm_clean(struct nfp_ccm *ccm)
+{
+ WARN_ON(!skb_queue_empty(&ccm->replies));
+}
--- /dev/null
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/* Copyright (C) 2016-2019 Netronome Systems, Inc. */
+
+#ifndef NFP_CCM_H
+#define NFP_CCM_H 1
+
+#include <linux/bitmap.h>
+#include <linux/skbuff.h>
+#include <linux/wait.h>
+
+struct nfp_app;
+
+/* Firmware ABI */
+
+enum nfp_ccm_type {
+ NFP_CCM_TYPE_BPF_MAP_ALLOC = 1,
+ NFP_CCM_TYPE_BPF_MAP_FREE = 2,
+ NFP_CCM_TYPE_BPF_MAP_LOOKUP = 3,
+ NFP_CCM_TYPE_BPF_MAP_UPDATE = 4,
+ NFP_CCM_TYPE_BPF_MAP_DELETE = 5,
+ NFP_CCM_TYPE_BPF_MAP_GETNEXT = 6,
+ NFP_CCM_TYPE_BPF_MAP_GETFIRST = 7,
+ NFP_CCM_TYPE_BPF_BPF_EVENT = 8,
+ __NFP_CCM_TYPE_MAX,
+};
+
+#define NFP_CCM_ABI_VERSION 1
+
+struct nfp_ccm_hdr {
+ u8 type;
+ u8 ver;
+ __be16 tag;
+};
+
+static inline u8 nfp_ccm_get_type(struct sk_buff *skb)
+{
+ struct nfp_ccm_hdr *hdr;
+
+ hdr = (struct nfp_ccm_hdr *)skb->data;
+
+ return hdr->type;
+}
+
+static inline unsigned int nfp_ccm_get_tag(struct sk_buff *skb)
+{
+ struct nfp_ccm_hdr *hdr;
+
+ hdr = (struct nfp_ccm_hdr *)skb->data;
+
+ return be16_to_cpu(hdr->tag);
+}
+
+/* Implementation */
+
+/**
+ * struct nfp_ccm - common control message handling
+ * @tag_allocator: bitmap of control message tags in use
+ * @tag_alloc_next: next tag bit to allocate
+ * @tag_alloc_last: next tag bit to be freed
+ *
+ * @replies: received cmsg replies waiting to be consumed
+ * @wq: work queue for waiting for cmsg replies
+ */
+struct nfp_ccm {
+ struct nfp_app *app;
+
+ DECLARE_BITMAP(tag_allocator, U16_MAX + 1);
+ u16 tag_alloc_next;
+ u16 tag_alloc_last;
+
+ struct sk_buff_head replies;
+ struct wait_queue_head wq;
+};
+
+int nfp_ccm_init(struct nfp_ccm *ccm, struct nfp_app *app);
+void nfp_ccm_clean(struct nfp_ccm *ccm);
+void nfp_ccm_rx(struct nfp_ccm *ccm, struct sk_buff *skb);
+struct sk_buff *
+nfp_ccm_communicate(struct nfp_ccm *ccm, struct sk_buff *skb,
+ enum nfp_ccm_type type, unsigned int reply_size);
+#endif
tmp_push_vlan_tci =
FIELD_PREP(NFP_FL_PUSH_VLAN_PRIO, act->vlan.prio) |
- FIELD_PREP(NFP_FL_PUSH_VLAN_VID, act->vlan.vid) |
- NFP_FL_PUSH_VLAN_CFI;
+ FIELD_PREP(NFP_FL_PUSH_VLAN_VID, act->vlan.vid);
push_vlan->vlan_tci = cpu_to_be16(tmp_push_vlan_tci);
}
}
}
-static int
-nfp_fl_pedit(const struct flow_action_entry *act,
- struct tc_cls_flower_offload *flow,
- char *nfp_action, int *a_len, u32 *csum_updated)
-{
- struct flow_rule *rule = tc_cls_flower_offload_flow_rule(flow);
+struct nfp_flower_pedit_acts {
struct nfp_fl_set_ipv6_addr set_ip6_dst, set_ip6_src;
struct nfp_fl_set_ipv6_tc_hl_fl set_ip6_tc_hl_fl;
struct nfp_fl_set_ip4_ttl_tos set_ip_ttl_tos;
struct nfp_fl_set_ip4_addrs set_ip_addr;
- enum flow_action_mangle_base htype;
struct nfp_fl_set_tport set_tport;
struct nfp_fl_set_eth set_eth;
+};
+
+static int
+nfp_fl_commit_mangle(struct tc_cls_flower_offload *flow, char *nfp_action,
+ int *a_len, struct nfp_flower_pedit_acts *set_act,
+ u32 *csum_updated)
+{
+ struct flow_rule *rule = tc_cls_flower_offload_flow_rule(flow);
size_t act_size = 0;
u8 ip_proto = 0;
- u32 offset;
- int err;
-
- memset(&set_ip6_tc_hl_fl, 0, sizeof(set_ip6_tc_hl_fl));
- memset(&set_ip_ttl_tos, 0, sizeof(set_ip_ttl_tos));
- memset(&set_ip6_dst, 0, sizeof(set_ip6_dst));
- memset(&set_ip6_src, 0, sizeof(set_ip6_src));
- memset(&set_ip_addr, 0, sizeof(set_ip_addr));
- memset(&set_tport, 0, sizeof(set_tport));
- memset(&set_eth, 0, sizeof(set_eth));
-
- htype = act->mangle.htype;
- offset = act->mangle.offset;
-
- switch (htype) {
- case TCA_PEDIT_KEY_EX_HDR_TYPE_ETH:
- err = nfp_fl_set_eth(act, offset, &set_eth);
- break;
- case TCA_PEDIT_KEY_EX_HDR_TYPE_IP4:
- err = nfp_fl_set_ip4(act, offset, &set_ip_addr,
- &set_ip_ttl_tos);
- break;
- case TCA_PEDIT_KEY_EX_HDR_TYPE_IP6:
- err = nfp_fl_set_ip6(act, offset, &set_ip6_dst,
- &set_ip6_src, &set_ip6_tc_hl_fl);
- break;
- case TCA_PEDIT_KEY_EX_HDR_TYPE_TCP:
- err = nfp_fl_set_tport(act, offset, &set_tport,
- NFP_FL_ACTION_OPCODE_SET_TCP);
- break;
- case TCA_PEDIT_KEY_EX_HDR_TYPE_UDP:
- err = nfp_fl_set_tport(act, offset, &set_tport,
- NFP_FL_ACTION_OPCODE_SET_UDP);
- break;
- default:
- return -EOPNOTSUPP;
- }
- if (err)
- return err;
if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
struct flow_match_basic match;
ip_proto = match.key->ip_proto;
}
- if (set_eth.head.len_lw) {
- act_size = sizeof(set_eth);
- memcpy(nfp_action, &set_eth, act_size);
+ if (set_act->set_eth.head.len_lw) {
+ act_size = sizeof(set_act->set_eth);
+ memcpy(nfp_action, &set_act->set_eth, act_size);
*a_len += act_size;
}
- if (set_ip_ttl_tos.head.len_lw) {
+
+ if (set_act->set_ip_ttl_tos.head.len_lw) {
nfp_action += act_size;
- act_size = sizeof(set_ip_ttl_tos);
- memcpy(nfp_action, &set_ip_ttl_tos, act_size);
+ act_size = sizeof(set_act->set_ip_ttl_tos);
+ memcpy(nfp_action, &set_act->set_ip_ttl_tos, act_size);
*a_len += act_size;
/* Hardware will automatically fix IPv4 and TCP/UDP checksum. */
*csum_updated |= TCA_CSUM_UPDATE_FLAG_IPV4HDR |
nfp_fl_csum_l4_to_flag(ip_proto);
}
- if (set_ip_addr.head.len_lw) {
+
+ if (set_act->set_ip_addr.head.len_lw) {
nfp_action += act_size;
- act_size = sizeof(set_ip_addr);
- memcpy(nfp_action, &set_ip_addr, act_size);
+ act_size = sizeof(set_act->set_ip_addr);
+ memcpy(nfp_action, &set_act->set_ip_addr, act_size);
*a_len += act_size;
/* Hardware will automatically fix IPv4 and TCP/UDP checksum. */
*csum_updated |= TCA_CSUM_UPDATE_FLAG_IPV4HDR |
nfp_fl_csum_l4_to_flag(ip_proto);
}
- if (set_ip6_tc_hl_fl.head.len_lw) {
+
+ if (set_act->set_ip6_tc_hl_fl.head.len_lw) {
nfp_action += act_size;
- act_size = sizeof(set_ip6_tc_hl_fl);
- memcpy(nfp_action, &set_ip6_tc_hl_fl, act_size);
+ act_size = sizeof(set_act->set_ip6_tc_hl_fl);
+ memcpy(nfp_action, &set_act->set_ip6_tc_hl_fl, act_size);
*a_len += act_size;
/* Hardware will automatically fix TCP/UDP checksum. */
*csum_updated |= nfp_fl_csum_l4_to_flag(ip_proto);
}
- if (set_ip6_dst.head.len_lw && set_ip6_src.head.len_lw) {
+
+ if (set_act->set_ip6_dst.head.len_lw &&
+ set_act->set_ip6_src.head.len_lw) {
/* TC compiles set src and dst IPv6 address as a single action,
* the hardware requires this to be 2 separate actions.
*/
nfp_action += act_size;
- act_size = sizeof(set_ip6_src);
- memcpy(nfp_action, &set_ip6_src, act_size);
+ act_size = sizeof(set_act->set_ip6_src);
+ memcpy(nfp_action, &set_act->set_ip6_src, act_size);
*a_len += act_size;
- act_size = sizeof(set_ip6_dst);
- memcpy(&nfp_action[sizeof(set_ip6_src)], &set_ip6_dst,
- act_size);
+ act_size = sizeof(set_act->set_ip6_dst);
+ memcpy(&nfp_action[sizeof(set_act->set_ip6_src)],
+ &set_act->set_ip6_dst, act_size);
*a_len += act_size;
/* Hardware will automatically fix TCP/UDP checksum. */
*csum_updated |= nfp_fl_csum_l4_to_flag(ip_proto);
- } else if (set_ip6_dst.head.len_lw) {
+ } else if (set_act->set_ip6_dst.head.len_lw) {
nfp_action += act_size;
- act_size = sizeof(set_ip6_dst);
- memcpy(nfp_action, &set_ip6_dst, act_size);
+ act_size = sizeof(set_act->set_ip6_dst);
+ memcpy(nfp_action, &set_act->set_ip6_dst, act_size);
*a_len += act_size;
/* Hardware will automatically fix TCP/UDP checksum. */
*csum_updated |= nfp_fl_csum_l4_to_flag(ip_proto);
- } else if (set_ip6_src.head.len_lw) {
+ } else if (set_act->set_ip6_src.head.len_lw) {
nfp_action += act_size;
- act_size = sizeof(set_ip6_src);
- memcpy(nfp_action, &set_ip6_src, act_size);
+ act_size = sizeof(set_act->set_ip6_src);
+ memcpy(nfp_action, &set_act->set_ip6_src, act_size);
*a_len += act_size;
/* Hardware will automatically fix TCP/UDP checksum. */
*csum_updated |= nfp_fl_csum_l4_to_flag(ip_proto);
}
- if (set_tport.head.len_lw) {
+ if (set_act->set_tport.head.len_lw) {
nfp_action += act_size;
- act_size = sizeof(set_tport);
- memcpy(nfp_action, &set_tport, act_size);
+ act_size = sizeof(set_act->set_tport);
+ memcpy(nfp_action, &set_act->set_tport, act_size);
*a_len += act_size;
/* Hardware will automatically fix TCP/UDP checksum. */
}
static int
-nfp_flower_output_action(struct nfp_app *app, const struct flow_action_entry *act,
+nfp_fl_pedit(const struct flow_action_entry *act,
+ struct tc_cls_flower_offload *flow, char *nfp_action, int *a_len,
+ u32 *csum_updated, struct nfp_flower_pedit_acts *set_act)
+{
+ enum flow_action_mangle_base htype;
+ u32 offset;
+
+ htype = act->mangle.htype;
+ offset = act->mangle.offset;
+
+ switch (htype) {
+ case TCA_PEDIT_KEY_EX_HDR_TYPE_ETH:
+ return nfp_fl_set_eth(act, offset, &set_act->set_eth);
+ case TCA_PEDIT_KEY_EX_HDR_TYPE_IP4:
+ return nfp_fl_set_ip4(act, offset, &set_act->set_ip_addr,
+ &set_act->set_ip_ttl_tos);
+ case TCA_PEDIT_KEY_EX_HDR_TYPE_IP6:
+ return nfp_fl_set_ip6(act, offset, &set_act->set_ip6_dst,
+ &set_act->set_ip6_src,
+ &set_act->set_ip6_tc_hl_fl);
+ case TCA_PEDIT_KEY_EX_HDR_TYPE_TCP:
+ return nfp_fl_set_tport(act, offset, &set_act->set_tport,
+ NFP_FL_ACTION_OPCODE_SET_TCP);
+ case TCA_PEDIT_KEY_EX_HDR_TYPE_UDP:
+ return nfp_fl_set_tport(act, offset, &set_act->set_tport,
+ NFP_FL_ACTION_OPCODE_SET_UDP);
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
+static int
+nfp_flower_output_action(struct nfp_app *app,
+ const struct flow_action_entry *act,
struct nfp_fl_payload *nfp_fl, int *a_len,
struct net_device *netdev, bool last,
enum nfp_flower_tun_type *tun_type, int *tun_out_cnt,
struct nfp_fl_payload *nfp_fl, int *a_len,
struct net_device *netdev,
enum nfp_flower_tun_type *tun_type, int *tun_out_cnt,
- int *out_cnt, u32 *csum_updated)
+ int *out_cnt, u32 *csum_updated,
+ struct nfp_flower_pedit_acts *set_act)
{
struct nfp_fl_set_ipv4_udp_tun *set_tun;
struct nfp_fl_pre_tunnel *pre_tun;
return 0;
case FLOW_ACTION_MANGLE:
if (nfp_fl_pedit(act, flow, &nfp_fl->action_data[*a_len],
- a_len, csum_updated))
+ a_len, csum_updated, set_act))
return -EOPNOTSUPP;
break;
case FLOW_ACTION_CSUM:
return 0;
}
+static bool nfp_fl_check_mangle_start(struct flow_action *flow_act,
+ int current_act_idx)
+{
+ struct flow_action_entry current_act;
+ struct flow_action_entry prev_act;
+
+ current_act = flow_act->entries[current_act_idx];
+ if (current_act.id != FLOW_ACTION_MANGLE)
+ return false;
+
+ if (current_act_idx == 0)
+ return true;
+
+ prev_act = flow_act->entries[current_act_idx - 1];
+
+ return prev_act.id != FLOW_ACTION_MANGLE;
+}
+
+static bool nfp_fl_check_mangle_end(struct flow_action *flow_act,
+ int current_act_idx)
+{
+ struct flow_action_entry current_act;
+ struct flow_action_entry next_act;
+
+ current_act = flow_act->entries[current_act_idx];
+ if (current_act.id != FLOW_ACTION_MANGLE)
+ return false;
+
+ if (current_act_idx == flow_act->num_entries)
+ return true;
+
+ next_act = flow_act->entries[current_act_idx + 1];
+
+ return next_act.id != FLOW_ACTION_MANGLE;
+}
+
int nfp_flower_compile_action(struct nfp_app *app,
struct tc_cls_flower_offload *flow,
struct net_device *netdev,
struct nfp_fl_payload *nfp_flow)
{
int act_len, act_cnt, err, tun_out_cnt, out_cnt, i;
+ struct nfp_flower_pedit_acts set_act;
enum nfp_flower_tun_type tun_type;
struct flow_action_entry *act;
u32 csum_updated = 0;
out_cnt = 0;
flow_action_for_each(i, act, &flow->rule->action) {
+ if (nfp_fl_check_mangle_start(&flow->rule->action, i))
+ memset(&set_act, 0, sizeof(set_act));
err = nfp_flower_loop_action(app, act, flow, nfp_flow, &act_len,
netdev, &tun_type, &tun_out_cnt,
- &out_cnt, &csum_updated);
+ &out_cnt, &csum_updated, &set_act);
if (err)
return err;
act_cnt++;
+ if (nfp_fl_check_mangle_end(&flow->rule->action, i))
+ nfp_fl_commit_mangle(flow,
+ &nfp_flow->action_data[act_len],
+ &act_len, &set_act, &csum_updated);
}
/* We optimise when the action list is small, this can unfortunately
rtnl_lock();
rcu_read_lock();
- netdev = nfp_app_repr_get(app, be32_to_cpu(msg->portnum));
+ netdev = nfp_app_dev_get(app, be32_to_cpu(msg->portnum), NULL);
rcu_read_unlock();
if (!netdev) {
nfp_flower_cmsg_warn(app, "ctrl msg for unknown port 0x%08x\n",
msg = nfp_flower_cmsg_get_data(skb);
rcu_read_lock();
- exists = !!nfp_app_repr_get(app, be32_to_cpu(msg->portnum));
+ exists = !!nfp_app_dev_get(app, be32_to_cpu(msg->portnum), NULL);
rcu_read_unlock();
if (!exists) {
nfp_flower_cmsg_warn(app, "ctrl msg for unknown port 0x%08x\n",
wake_up(&priv->reify_wait_queue);
}
+static void
+nfp_flower_cmsg_merge_hint_rx(struct nfp_app *app, struct sk_buff *skb)
+{
+ unsigned int msg_len = nfp_flower_cmsg_get_data_len(skb);
+ struct nfp_flower_cmsg_merge_hint *msg;
+ struct nfp_fl_payload *sub_flows[2];
+ int err, i, flow_cnt;
+
+ msg = nfp_flower_cmsg_get_data(skb);
+ /* msg->count starts at 0 and always assumes at least 1 entry. */
+ flow_cnt = msg->count + 1;
+
+ if (msg_len < struct_size(msg, flow, flow_cnt)) {
+ nfp_flower_cmsg_warn(app, "Merge hint ctrl msg too short - %d bytes but expect %ld\n",
+ msg_len, struct_size(msg, flow, flow_cnt));
+ return;
+ }
+
+ if (flow_cnt != 2) {
+ nfp_flower_cmsg_warn(app, "Merge hint contains %d flows - two are expected\n",
+ flow_cnt);
+ return;
+ }
+
+ rtnl_lock();
+ for (i = 0; i < flow_cnt; i++) {
+ u32 ctx = be32_to_cpu(msg->flow[i].host_ctx);
+
+ sub_flows[i] = nfp_flower_get_fl_payload_from_ctx(app, ctx);
+ if (!sub_flows[i]) {
+ nfp_flower_cmsg_warn(app, "Invalid flow in merge hint\n");
+ goto err_rtnl_unlock;
+ }
+ }
+
+ err = nfp_flower_merge_offloaded_flows(app, sub_flows[0], sub_flows[1]);
+ /* Only warn on memory fail. Hint veto will not break functionality. */
+ if (err == -ENOMEM)
+ nfp_flower_cmsg_warn(app, "Flow merge memory fail.\n");
+
+err_rtnl_unlock:
+ rtnl_unlock();
+}
+
static void
nfp_flower_cmsg_process_one_rx(struct nfp_app *app, struct sk_buff *skb)
{
case NFP_FLOWER_CMSG_TYPE_PORT_MOD:
nfp_flower_cmsg_portmod_rx(app, skb);
break;
+ case NFP_FLOWER_CMSG_TYPE_MERGE_HINT:
+ if (app_priv->flower_ext_feats & NFP_FL_FEATS_FLOW_MERGE) {
+ nfp_flower_cmsg_merge_hint_rx(app, skb);
+ break;
+ }
+ goto err_default;
case NFP_FLOWER_CMSG_TYPE_NO_NEIGH:
nfp_tunnel_request_route(app, skb);
break;
}
/* fall through */
default:
+err_default:
nfp_flower_cmsg_warn(app, "Cannot handle invalid repr control type %u\n",
type);
goto out;
#define NFP_FLOWER_LAYER2_GENEVE_OP BIT(6)
#define NFP_FLOWER_MASK_VLAN_PRIO GENMASK(15, 13)
-#define NFP_FLOWER_MASK_VLAN_CFI BIT(12)
+#define NFP_FLOWER_MASK_VLAN_PRESENT BIT(12)
#define NFP_FLOWER_MASK_VLAN_VID GENMASK(11, 0)
#define NFP_FLOWER_MASK_MPLS_LB GENMASK(31, 12)
#define NFP_FL_OUT_FLAGS_TYPE_IDX GENMASK(2, 0)
#define NFP_FL_PUSH_VLAN_PRIO GENMASK(15, 13)
-#define NFP_FL_PUSH_VLAN_CFI BIT(12)
#define NFP_FL_PUSH_VLAN_VID GENMASK(11, 0)
#define IPV6_FLOW_LABEL_MASK cpu_to_be32(0x000fffff)
/* Types defined for port related control messages */
enum nfp_flower_cmsg_type_port {
NFP_FLOWER_CMSG_TYPE_FLOW_ADD = 0,
+ NFP_FLOWER_CMSG_TYPE_FLOW_MOD = 1,
NFP_FLOWER_CMSG_TYPE_FLOW_DEL = 2,
NFP_FLOWER_CMSG_TYPE_LAG_CONFIG = 4,
NFP_FLOWER_CMSG_TYPE_PORT_REIFY = 6,
NFP_FLOWER_CMSG_TYPE_MAC_REPR = 7,
NFP_FLOWER_CMSG_TYPE_PORT_MOD = 8,
+ NFP_FLOWER_CMSG_TYPE_MERGE_HINT = 9,
NFP_FLOWER_CMSG_TYPE_NO_NEIGH = 10,
NFP_FLOWER_CMSG_TYPE_TUN_MAC = 11,
NFP_FLOWER_CMSG_TYPE_ACTIVE_TUNS = 12,
#define NFP_FLOWER_CMSG_PORTREIFY_INFO_EXIST BIT(0)
+/* NFP_FLOWER_CMSG_TYPE_FLOW_MERGE_HINT */
+struct nfp_flower_cmsg_merge_hint {
+ u8 reserved[3];
+ u8 count;
+ struct {
+ __be32 host_ctx;
+ __be64 host_cookie;
+ } __packed flow[0];
+};
+
enum nfp_flower_cmsg_port_type {
NFP_FLOWER_CMSG_PORT_TYPE_UNSPEC = 0x0,
NFP_FLOWER_CMSG_PORT_TYPE_PHYS_PORT = 0x1,
#define NFP_FLOWER_CMSG_PORT_PCIE_Q GENMASK(5, 0)
#define NFP_FLOWER_CMSG_PORT_PHYS_PORT_NUM GENMASK(7, 0)
+static inline u32 nfp_flower_internal_port_get_port_id(u8 internal_port)
+{
+ return FIELD_PREP(NFP_FLOWER_CMSG_PORT_PHYS_PORT_NUM, internal_port) |
+ FIELD_PREP(NFP_FLOWER_CMSG_PORT_TYPE,
+ NFP_FLOWER_CMSG_PORT_TYPE_OTHER_PORT);
+}
+
static inline u32 nfp_flower_cmsg_phys_port(u8 phys_port)
{
return FIELD_PREP(NFP_FLOWER_CMSG_PORT_PHYS_PORT_NUM, phys_port) |
#define NFP_FLOWER_ALLOWED_VER 0x0001000000010000UL
+#define NFP_MIN_INT_PORT_ID 1
+#define NFP_MAX_INT_PORT_ID 256
+
static const char *nfp_flower_extra_cap(struct nfp_app *app, struct nfp_net *nn)
{
return "FLOWER";
return DEVLINK_ESWITCH_MODE_SWITCHDEV;
}
+static int
+nfp_flower_lookup_internal_port_id(struct nfp_flower_priv *priv,
+ struct net_device *netdev)
+{
+ struct net_device *entry;
+ int i, id = 0;
+
+ rcu_read_lock();
+ idr_for_each_entry(&priv->internal_ports.port_ids, entry, i)
+ if (entry == netdev) {
+ id = i;
+ break;
+ }
+ rcu_read_unlock();
+
+ return id;
+}
+
+static int
+nfp_flower_get_internal_port_id(struct nfp_app *app, struct net_device *netdev)
+{
+ struct nfp_flower_priv *priv = app->priv;
+ int id;
+
+ id = nfp_flower_lookup_internal_port_id(priv, netdev);
+ if (id > 0)
+ return id;
+
+ idr_preload(GFP_ATOMIC);
+ spin_lock_bh(&priv->internal_ports.lock);
+ id = idr_alloc(&priv->internal_ports.port_ids, netdev,
+ NFP_MIN_INT_PORT_ID, NFP_MAX_INT_PORT_ID, GFP_ATOMIC);
+ spin_unlock_bh(&priv->internal_ports.lock);
+ idr_preload_end();
+
+ return id;
+}
+
+u32 nfp_flower_get_port_id_from_netdev(struct nfp_app *app,
+ struct net_device *netdev)
+{
+ int ext_port;
+
+ if (nfp_netdev_is_nfp_repr(netdev)) {
+ return nfp_repr_get_port_id(netdev);
+ } else if (nfp_flower_internal_port_can_offload(app, netdev)) {
+ ext_port = nfp_flower_get_internal_port_id(app, netdev);
+ if (ext_port < 0)
+ return 0;
+
+ return nfp_flower_internal_port_get_port_id(ext_port);
+ }
+
+ return 0;
+}
+
+static struct net_device *
+nfp_flower_get_netdev_from_internal_port_id(struct nfp_app *app, int port_id)
+{
+ struct nfp_flower_priv *priv = app->priv;
+ struct net_device *netdev;
+
+ rcu_read_lock();
+ netdev = idr_find(&priv->internal_ports.port_ids, port_id);
+ rcu_read_unlock();
+
+ return netdev;
+}
+
+static void
+nfp_flower_free_internal_port_id(struct nfp_app *app, struct net_device *netdev)
+{
+ struct nfp_flower_priv *priv = app->priv;
+ int id;
+
+ id = nfp_flower_lookup_internal_port_id(priv, netdev);
+ if (!id)
+ return;
+
+ spin_lock_bh(&priv->internal_ports.lock);
+ idr_remove(&priv->internal_ports.port_ids, id);
+ spin_unlock_bh(&priv->internal_ports.lock);
+}
+
+static int
+nfp_flower_internal_port_event_handler(struct nfp_app *app,
+ struct net_device *netdev,
+ unsigned long event)
+{
+ if (event == NETDEV_UNREGISTER &&
+ nfp_flower_internal_port_can_offload(app, netdev))
+ nfp_flower_free_internal_port_id(app, netdev);
+
+ return NOTIFY_OK;
+}
+
+static void nfp_flower_internal_port_init(struct nfp_flower_priv *priv)
+{
+ spin_lock_init(&priv->internal_ports.lock);
+ idr_init(&priv->internal_ports.port_ids);
+}
+
+static void nfp_flower_internal_port_cleanup(struct nfp_flower_priv *priv)
+{
+ idr_destroy(&priv->internal_ports.port_ids);
+}
+
static struct nfp_flower_non_repr_priv *
nfp_flower_non_repr_priv_lookup(struct nfp_app *app, struct net_device *netdev)
{
}
static struct net_device *
-nfp_flower_repr_get(struct nfp_app *app, u32 port_id)
+nfp_flower_dev_get(struct nfp_app *app, u32 port_id, bool *redir_egress)
{
enum nfp_repr_type repr_type;
struct nfp_reprs *reprs;
u8 port = 0;
+ /* Check if the port is internal. */
+ if (FIELD_GET(NFP_FLOWER_CMSG_PORT_TYPE, port_id) ==
+ NFP_FLOWER_CMSG_PORT_TYPE_OTHER_PORT) {
+ if (redir_egress)
+ *redir_egress = true;
+ port = FIELD_GET(NFP_FLOWER_CMSG_PORT_PHYS_PORT_NUM, port_id);
+ return nfp_flower_get_netdev_from_internal_port_id(app, port);
+ }
+
repr_type = nfp_flower_repr_get_type_and_port(app, port_id, &port);
if (repr_type > NFP_REPR_TYPE_MAX)
return NULL;
goto err_cleanup_metadata;
}
+ if (app_priv->flower_ext_feats & NFP_FL_FEATS_FLOW_MOD) {
+ /* Tell the firmware that the driver supports flow merging. */
+ err = nfp_rtsym_write_le(app->pf->rtbl,
+ "_abi_flower_merge_hint_enable", 1);
+ if (!err) {
+ app_priv->flower_ext_feats |= NFP_FL_FEATS_FLOW_MERGE;
+ nfp_flower_internal_port_init(app_priv);
+ } else if (err == -ENOENT) {
+ nfp_warn(app->cpp, "Flow merge not supported by FW.\n");
+ } else {
+ goto err_lag_clean;
+ }
+ } else {
+ nfp_warn(app->cpp, "Flow mod/merge not supported by FW.\n");
+ }
+
INIT_LIST_HEAD(&app_priv->indr_block_cb_priv);
INIT_LIST_HEAD(&app_priv->non_repr_priv);
return 0;
+err_lag_clean:
+ if (app_priv->flower_ext_feats & NFP_FL_FEATS_LAG)
+ nfp_flower_lag_cleanup(&app_priv->nfp_lag);
err_cleanup_metadata:
nfp_flower_metadata_cleanup(app);
err_free_app_priv:
if (app_priv->flower_ext_feats & NFP_FL_FEATS_LAG)
nfp_flower_lag_cleanup(&app_priv->nfp_lag);
+ if (app_priv->flower_ext_feats & NFP_FL_FEATS_FLOW_MERGE)
+ nfp_flower_internal_port_cleanup(app_priv);
+
nfp_flower_metadata_cleanup(app);
vfree(app->priv);
app->priv = NULL;
if (ret & NOTIFY_STOP_MASK)
return ret;
+ ret = nfp_flower_internal_port_event_handler(app, netdev, event);
+ if (ret & NOTIFY_STOP_MASK)
+ return ret;
+
return nfp_tunnel_mac_event_handler(app, netdev, event, ptr);
}
.sriov_disable = nfp_flower_sriov_disable,
.eswitch_mode_get = eswitch_mode_get,
- .repr_get = nfp_flower_repr_get,
+ .dev_get = nfp_flower_dev_get,
.setup_tc = nfp_flower_setup_tc,
};
#define NFP_FL_NBI_MTU_SETTING BIT(1)
#define NFP_FL_FEATS_GENEVE_OPT BIT(2)
#define NFP_FL_FEATS_VLAN_PCP BIT(3)
+#define NFP_FL_FEATS_FLOW_MOD BIT(5)
+#define NFP_FL_FEATS_FLOW_MERGE BIT(30)
#define NFP_FL_FEATS_LAG BIT(31)
struct nfp_fl_mask_id {
struct sk_buff_head retrans_skbs;
};
+/**
+ * struct nfp_fl_internal_ports - Flower APP priv data for additional ports
+ * @port_ids: Assignment of ids to any additional ports
+ * @lock: Lock for extra ports list
+ */
+struct nfp_fl_internal_ports {
+ struct idr port_ids;
+ spinlock_t lock;
+};
+
/**
* struct nfp_flower_priv - Flower APP per-vNIC priv data
* @app: Back pointer to app
* @flow_table: Hash table used to store flower rules
* @stats: Stored stats updates for flower rules
* @stats_lock: Lock for flower rule stats updates
+ * @stats_ctx_table: Hash table to map stats contexts to its flow rule
* @cmsg_work: Workqueue for control messages processing
* @cmsg_skbs_high: List of higher priority skbs for control message
* processing
* @non_repr_priv: List of offloaded non-repr ports and their priv data
* @active_mem_unit: Current active memory unit for flower rules
* @total_mem_units: Total number of available memory units for flower rules
+ * @internal_ports: Internal port ids used in offloaded rules
*/
struct nfp_flower_priv {
struct nfp_app *app;
struct rhashtable flow_table;
struct nfp_fl_stats *stats;
spinlock_t stats_lock; /* lock stats */
+ struct rhashtable stats_ctx_table;
struct work_struct cmsg_work;
struct sk_buff_head cmsg_skbs_high;
struct sk_buff_head cmsg_skbs_low;
struct list_head non_repr_priv;
unsigned int active_mem_unit;
unsigned int total_mem_units;
+ struct nfp_fl_internal_ports internal_ports;
};
/**
char *unmasked_data;
char *mask_data;
char *action_data;
+ struct list_head linked_flows;
+ bool in_hw;
+};
+
+struct nfp_fl_payload_link {
+ /* A link contains a pointer to a merge flow and an associated sub_flow.
+ * Each merge flow will feature in 2 links to its underlying sub_flows.
+ * A sub_flow will have at least 1 link to a merge flow or more if it
+ * has been used to create multiple merge flows.
+ *
+ * For a merge flow, 'linked_flows' in its nfp_fl_payload struct lists
+ * all links to sub_flows (sub_flow.flow) via merge.list.
+ * For a sub_flow, 'linked_flows' gives all links to merge flows it has
+ * formed (merge_flow.flow) via sub_flow.list.
+ */
+ struct {
+ struct list_head list;
+ struct nfp_fl_payload *flow;
+ } merge_flow, sub_flow;
};
extern const struct rhashtable_params nfp_flower_table_params;
__be64 stats_cookie;
};
+static inline bool
+nfp_flower_internal_port_can_offload(struct nfp_app *app,
+ struct net_device *netdev)
+{
+ struct nfp_flower_priv *app_priv = app->priv;
+
+ if (!(app_priv->flower_ext_feats & NFP_FL_FEATS_FLOW_MERGE))
+ return false;
+ if (!netdev->rtnl_link_ops)
+ return false;
+ if (!strcmp(netdev->rtnl_link_ops->kind, "openvswitch"))
+ return true;
+
+ return false;
+}
+
+/* The address of the merged flow acts as its cookie.
+ * Cookies supplied to us by TC flower are also addresses to allocated
+ * memory and thus this scheme should not generate any collisions.
+ */
+static inline bool nfp_flower_is_merge_flow(struct nfp_fl_payload *flow_pay)
+{
+ return flow_pay->tc_flower_cookie == (unsigned long)flow_pay;
+}
+
int nfp_flower_metadata_init(struct nfp_app *app, u64 host_ctx_count,
unsigned int host_ctx_split);
void nfp_flower_metadata_cleanup(struct nfp_app *app);
int nfp_flower_setup_tc(struct nfp_app *app, struct net_device *netdev,
enum tc_setup_type type, void *type_data);
+int nfp_flower_merge_offloaded_flows(struct nfp_app *app,
+ struct nfp_fl_payload *sub_flow1,
+ struct nfp_fl_payload *sub_flow2);
int nfp_flower_compile_flow_match(struct nfp_app *app,
struct tc_cls_flower_offload *flow,
struct nfp_fl_key_ls *key_ls,
struct tc_cls_flower_offload *flow,
struct nfp_fl_payload *nfp_flow,
struct net_device *netdev);
+void __nfp_modify_flow_metadata(struct nfp_flower_priv *priv,
+ struct nfp_fl_payload *nfp_flow);
int nfp_modify_flow_metadata(struct nfp_app *app,
struct nfp_fl_payload *nfp_flow);
nfp_flower_search_fl_table(struct nfp_app *app, unsigned long tc_flower_cookie,
struct net_device *netdev);
struct nfp_fl_payload *
+nfp_flower_get_fl_payload_from_ctx(struct nfp_app *app, u32 ctx_id);
+struct nfp_fl_payload *
nfp_flower_remove_fl_table(struct nfp_app *app, unsigned long tc_flower_cookie);
void nfp_flower_rx_flow_stats(struct nfp_app *app, struct sk_buff *skb);
__nfp_flower_non_repr_priv_put(struct nfp_flower_non_repr_priv *non_repr_priv);
void
nfp_flower_non_repr_priv_put(struct nfp_app *app, struct net_device *netdev);
+u32 nfp_flower_get_port_id_from_netdev(struct nfp_app *app,
+ struct net_device *netdev);
#endif
flow_rule_match_vlan(rule, &match);
/* Populate the tci field. */
- if (match.key->vlan_id || match.key->vlan_priority) {
- tmp_tci = FIELD_PREP(NFP_FLOWER_MASK_VLAN_PRIO,
- match.key->vlan_priority) |
- FIELD_PREP(NFP_FLOWER_MASK_VLAN_VID,
- match.key->vlan_id) |
- NFP_FLOWER_MASK_VLAN_CFI;
- ext->tci = cpu_to_be16(tmp_tci);
- tmp_tci = FIELD_PREP(NFP_FLOWER_MASK_VLAN_PRIO,
- match.mask->vlan_priority) |
- FIELD_PREP(NFP_FLOWER_MASK_VLAN_VID,
- match.mask->vlan_id) |
- NFP_FLOWER_MASK_VLAN_CFI;
- msk->tci = cpu_to_be16(tmp_tci);
- }
+ tmp_tci = NFP_FLOWER_MASK_VLAN_PRESENT;
+ tmp_tci |= FIELD_PREP(NFP_FLOWER_MASK_VLAN_PRIO,
+ match.key->vlan_priority) |
+ FIELD_PREP(NFP_FLOWER_MASK_VLAN_VID,
+ match.key->vlan_id);
+ ext->tci = cpu_to_be16(tmp_tci);
+
+ tmp_tci = NFP_FLOWER_MASK_VLAN_PRESENT;
+ tmp_tci |= FIELD_PREP(NFP_FLOWER_MASK_VLAN_PRIO,
+ match.mask->vlan_priority) |
+ FIELD_PREP(NFP_FLOWER_MASK_VLAN_VID,
+ match.mask->vlan_id);
+ msk->tci = cpu_to_be16(tmp_tci);
}
}
struct nfp_fl_payload *nfp_flow,
enum nfp_flower_tun_type tun_type)
{
- u32 cmsg_port = 0;
+ u32 port_id;
int err;
u8 *ext;
u8 *msk;
- if (nfp_netdev_is_nfp_repr(netdev))
- cmsg_port = nfp_repr_get_port_id(netdev);
+ port_id = nfp_flower_get_port_id_from_netdev(app, netdev);
memset(nfp_flow->unmasked_data, 0, key_ls->key_size);
memset(nfp_flow->mask_data, 0, key_ls->key_size);
/* Populate Exact Port data. */
err = nfp_flower_compile_port((struct nfp_flower_in_port *)ext,
- cmsg_port, false, tun_type);
+ port_id, false, tun_type);
if (err)
return err;
/* Populate Mask Port Data. */
err = nfp_flower_compile_port((struct nfp_flower_in_port *)msk,
- cmsg_port, true, tun_type);
+ port_id, true, tun_type);
if (err)
return err;
unsigned long cookie;
};
+struct nfp_fl_stats_ctx_to_flow {
+ struct rhash_head ht_node;
+ u32 stats_cxt;
+ struct nfp_fl_payload *flow;
+};
+
+static const struct rhashtable_params stats_ctx_table_params = {
+ .key_offset = offsetof(struct nfp_fl_stats_ctx_to_flow, stats_cxt),
+ .head_offset = offsetof(struct nfp_fl_stats_ctx_to_flow, ht_node),
+ .key_len = sizeof(u32),
+};
+
static int nfp_release_stats_entry(struct nfp_app *app, u32 stats_context_id)
{
struct nfp_flower_priv *priv = app->priv;
if (!mask_entry)
return false;
- if (meta_flags)
- *meta_flags &= ~NFP_FL_META_FLAG_MANAGE_MASK;
-
*mask_id = mask_entry->mask_id;
mask_entry->ref_cnt--;
if (!mask_entry->ref_cnt) {
struct nfp_fl_payload *nfp_flow,
struct net_device *netdev)
{
+ struct nfp_fl_stats_ctx_to_flow *ctx_entry;
struct nfp_flower_priv *priv = app->priv;
struct nfp_fl_payload *check_entry;
u8 new_mask_id;
u32 stats_cxt;
+ int err;
- if (nfp_get_stats_entry(app, &stats_cxt))
- return -ENOENT;
+ err = nfp_get_stats_entry(app, &stats_cxt);
+ if (err)
+ return err;
nfp_flow->meta.host_ctx_id = cpu_to_be32(stats_cxt);
nfp_flow->meta.host_cookie = cpu_to_be64(flow->cookie);
nfp_flow->ingress_dev = netdev;
+ ctx_entry = kzalloc(sizeof(*ctx_entry), GFP_KERNEL);
+ if (!ctx_entry) {
+ err = -ENOMEM;
+ goto err_release_stats;
+ }
+
+ ctx_entry->stats_cxt = stats_cxt;
+ ctx_entry->flow = nfp_flow;
+
+ if (rhashtable_insert_fast(&priv->stats_ctx_table, &ctx_entry->ht_node,
+ stats_ctx_table_params)) {
+ err = -ENOMEM;
+ goto err_free_ctx_entry;
+ }
+
new_mask_id = 0;
if (!nfp_check_mask_add(app, nfp_flow->mask_data,
nfp_flow->meta.mask_len,
&nfp_flow->meta.flags, &new_mask_id)) {
- if (nfp_release_stats_entry(app, stats_cxt))
- return -EINVAL;
- return -ENOENT;
+ err = -ENOENT;
+ goto err_remove_rhash;
}
nfp_flow->meta.flow_version = cpu_to_be64(priv->flower_version);
check_entry = nfp_flower_search_fl_table(app, flow->cookie, netdev);
if (check_entry) {
- if (nfp_release_stats_entry(app, stats_cxt))
- return -EINVAL;
-
- if (!nfp_check_mask_remove(app, nfp_flow->mask_data,
- nfp_flow->meta.mask_len,
- NULL, &new_mask_id))
- return -EINVAL;
-
- return -EEXIST;
+ err = -EEXIST;
+ goto err_remove_mask;
}
return 0;
+
+err_remove_mask:
+ nfp_check_mask_remove(app, nfp_flow->mask_data, nfp_flow->meta.mask_len,
+ NULL, &new_mask_id);
+err_remove_rhash:
+ WARN_ON_ONCE(rhashtable_remove_fast(&priv->stats_ctx_table,
+ &ctx_entry->ht_node,
+ stats_ctx_table_params));
+err_free_ctx_entry:
+ kfree(ctx_entry);
+err_release_stats:
+ nfp_release_stats_entry(app, stats_cxt);
+
+ return err;
+}
+
+void __nfp_modify_flow_metadata(struct nfp_flower_priv *priv,
+ struct nfp_fl_payload *nfp_flow)
+{
+ nfp_flow->meta.flags &= ~NFP_FL_META_FLAG_MANAGE_MASK;
+ nfp_flow->meta.flow_version = cpu_to_be64(priv->flower_version);
+ priv->flower_version++;
}
int nfp_modify_flow_metadata(struct nfp_app *app,
struct nfp_fl_payload *nfp_flow)
{
+ struct nfp_fl_stats_ctx_to_flow *ctx_entry;
struct nfp_flower_priv *priv = app->priv;
u8 new_mask_id = 0;
u32 temp_ctx_id;
+ __nfp_modify_flow_metadata(priv, nfp_flow);
+
nfp_check_mask_remove(app, nfp_flow->mask_data,
nfp_flow->meta.mask_len, &nfp_flow->meta.flags,
&new_mask_id);
- nfp_flow->meta.flow_version = cpu_to_be64(priv->flower_version);
- priv->flower_version++;
-
/* Update flow payload with mask ids. */
nfp_flow->unmasked_data[NFP_FL_MASK_ID_LOCATION] = new_mask_id;
- /* Release the stats ctx id. */
+ /* Release the stats ctx id and ctx to flow table entry. */
temp_ctx_id = be32_to_cpu(nfp_flow->meta.host_ctx_id);
+ ctx_entry = rhashtable_lookup_fast(&priv->stats_ctx_table, &temp_ctx_id,
+ stats_ctx_table_params);
+ if (!ctx_entry)
+ return -ENOENT;
+
+ WARN_ON_ONCE(rhashtable_remove_fast(&priv->stats_ctx_table,
+ &ctx_entry->ht_node,
+ stats_ctx_table_params));
+ kfree(ctx_entry);
+
return nfp_release_stats_entry(app, temp_ctx_id);
}
+struct nfp_fl_payload *
+nfp_flower_get_fl_payload_from_ctx(struct nfp_app *app, u32 ctx_id)
+{
+ struct nfp_fl_stats_ctx_to_flow *ctx_entry;
+ struct nfp_flower_priv *priv = app->priv;
+
+ ctx_entry = rhashtable_lookup_fast(&priv->stats_ctx_table, &ctx_id,
+ stats_ctx_table_params);
+ if (!ctx_entry)
+ return NULL;
+
+ return ctx_entry->flow;
+}
+
static int nfp_fl_obj_cmpfn(struct rhashtable_compare_arg *arg,
const void *obj)
{
if (err)
return err;
+ err = rhashtable_init(&priv->stats_ctx_table, &stats_ctx_table_params);
+ if (err)
+ goto err_free_flow_table;
+
get_random_bytes(&priv->mask_id_seed, sizeof(priv->mask_id_seed));
/* Init ring buffer and unallocated mask_ids. */
kmalloc_array(NFP_FLOWER_MASK_ENTRY_RS,
NFP_FLOWER_MASK_ELEMENT_RS, GFP_KERNEL);
if (!priv->mask_ids.mask_id_free_list.buf)
- goto err_free_flow_table;
+ goto err_free_stats_ctx_table;
priv->mask_ids.init_unallocated = NFP_FLOWER_MASK_ENTRY_RS - 1;
kfree(priv->mask_ids.last_used);
err_free_mask_id:
kfree(priv->mask_ids.mask_id_free_list.buf);
+err_free_stats_ctx_table:
+ rhashtable_destroy(&priv->stats_ctx_table);
err_free_flow_table:
rhashtable_destroy(&priv->flow_table);
return -ENOMEM;
rhashtable_free_and_destroy(&priv->flow_table,
nfp_check_rhashtable_empty, NULL);
+ rhashtable_free_and_destroy(&priv->stats_ctx_table,
+ nfp_check_rhashtable_empty, NULL);
kvfree(priv->stats);
kfree(priv->mask_ids.mask_id_free_list.buf);
kfree(priv->mask_ids.last_used);
BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | \
BIT(FLOW_DISSECTOR_KEY_ENC_PORTS))
+#define NFP_FLOWER_MERGE_FIELDS \
+ (NFP_FLOWER_LAYER_PORT | \
+ NFP_FLOWER_LAYER_MAC | \
+ NFP_FLOWER_LAYER_TP | \
+ NFP_FLOWER_LAYER_IPV4 | \
+ NFP_FLOWER_LAYER_IPV6)
+
+struct nfp_flower_merge_check {
+ union {
+ struct {
+ __be16 tci;
+ struct nfp_flower_mac_mpls l2;
+ struct nfp_flower_tp_ports l4;
+ union {
+ struct nfp_flower_ipv4 ipv4;
+ struct nfp_flower_ipv6 ipv6;
+ };
+ };
+ unsigned long vals[8];
+ };
+};
+
static int
nfp_flower_xmit_flow(struct nfp_app *app, struct nfp_fl_payload *nfp_flow,
u8 mtype)
break;
case cpu_to_be16(ETH_P_IPV6):
- key_layer |= NFP_FLOWER_LAYER_IPV6;
+ key_layer |= NFP_FLOWER_LAYER_IPV6;
key_size += sizeof(struct nfp_flower_ipv6);
break;
flow_pay->nfp_tun_ipv4_addr = 0;
flow_pay->meta.flags = 0;
+ INIT_LIST_HEAD(&flow_pay->linked_flows);
+ flow_pay->in_hw = false;
return flow_pay;
return NULL;
}
+static int
+nfp_flower_update_merge_with_actions(struct nfp_fl_payload *flow,
+ struct nfp_flower_merge_check *merge,
+ u8 *last_act_id, int *act_out)
+{
+ struct nfp_fl_set_ipv6_tc_hl_fl *ipv6_tc_hl_fl;
+ struct nfp_fl_set_ip4_ttl_tos *ipv4_ttl_tos;
+ struct nfp_fl_set_ip4_addrs *ipv4_add;
+ struct nfp_fl_set_ipv6_addr *ipv6_add;
+ struct nfp_fl_push_vlan *push_vlan;
+ struct nfp_fl_set_tport *tport;
+ struct nfp_fl_set_eth *eth;
+ struct nfp_fl_act_head *a;
+ unsigned int act_off = 0;
+ u8 act_id = 0;
+ u8 *ports;
+ int i;
+
+ while (act_off < flow->meta.act_len) {
+ a = (struct nfp_fl_act_head *)&flow->action_data[act_off];
+ act_id = a->jump_id;
+
+ switch (act_id) {
+ case NFP_FL_ACTION_OPCODE_OUTPUT:
+ if (act_out)
+ (*act_out)++;
+ break;
+ case NFP_FL_ACTION_OPCODE_PUSH_VLAN:
+ push_vlan = (struct nfp_fl_push_vlan *)a;
+ if (push_vlan->vlan_tci)
+ merge->tci = cpu_to_be16(0xffff);
+ break;
+ case NFP_FL_ACTION_OPCODE_POP_VLAN:
+ merge->tci = cpu_to_be16(0);
+ break;
+ case NFP_FL_ACTION_OPCODE_SET_IPV4_TUNNEL:
+ /* New tunnel header means l2 to l4 can be matched. */
+ eth_broadcast_addr(&merge->l2.mac_dst[0]);
+ eth_broadcast_addr(&merge->l2.mac_src[0]);
+ memset(&merge->l4, 0xff,
+ sizeof(struct nfp_flower_tp_ports));
+ memset(&merge->ipv4, 0xff,
+ sizeof(struct nfp_flower_ipv4));
+ break;
+ case NFP_FL_ACTION_OPCODE_SET_ETHERNET:
+ eth = (struct nfp_fl_set_eth *)a;
+ for (i = 0; i < ETH_ALEN; i++)
+ merge->l2.mac_dst[i] |= eth->eth_addr_mask[i];
+ for (i = 0; i < ETH_ALEN; i++)
+ merge->l2.mac_src[i] |=
+ eth->eth_addr_mask[ETH_ALEN + i];
+ break;
+ case NFP_FL_ACTION_OPCODE_SET_IPV4_ADDRS:
+ ipv4_add = (struct nfp_fl_set_ip4_addrs *)a;
+ merge->ipv4.ipv4_src |= ipv4_add->ipv4_src_mask;
+ merge->ipv4.ipv4_dst |= ipv4_add->ipv4_dst_mask;
+ break;
+ case NFP_FL_ACTION_OPCODE_SET_IPV4_TTL_TOS:
+ ipv4_ttl_tos = (struct nfp_fl_set_ip4_ttl_tos *)a;
+ merge->ipv4.ip_ext.ttl |= ipv4_ttl_tos->ipv4_ttl_mask;
+ merge->ipv4.ip_ext.tos |= ipv4_ttl_tos->ipv4_tos_mask;
+ break;
+ case NFP_FL_ACTION_OPCODE_SET_IPV6_SRC:
+ ipv6_add = (struct nfp_fl_set_ipv6_addr *)a;
+ for (i = 0; i < 4; i++)
+ merge->ipv6.ipv6_src.in6_u.u6_addr32[i] |=
+ ipv6_add->ipv6[i].mask;
+ break;
+ case NFP_FL_ACTION_OPCODE_SET_IPV6_DST:
+ ipv6_add = (struct nfp_fl_set_ipv6_addr *)a;
+ for (i = 0; i < 4; i++)
+ merge->ipv6.ipv6_dst.in6_u.u6_addr32[i] |=
+ ipv6_add->ipv6[i].mask;
+ break;
+ case NFP_FL_ACTION_OPCODE_SET_IPV6_TC_HL_FL:
+ ipv6_tc_hl_fl = (struct nfp_fl_set_ipv6_tc_hl_fl *)a;
+ merge->ipv6.ip_ext.ttl |=
+ ipv6_tc_hl_fl->ipv6_hop_limit_mask;
+ merge->ipv6.ip_ext.tos |= ipv6_tc_hl_fl->ipv6_tc_mask;
+ merge->ipv6.ipv6_flow_label_exthdr |=
+ ipv6_tc_hl_fl->ipv6_label_mask;
+ break;
+ case NFP_FL_ACTION_OPCODE_SET_UDP:
+ case NFP_FL_ACTION_OPCODE_SET_TCP:
+ tport = (struct nfp_fl_set_tport *)a;
+ ports = (u8 *)&merge->l4.port_src;
+ for (i = 0; i < 4; i++)
+ ports[i] |= tport->tp_port_mask[i];
+ break;
+ case NFP_FL_ACTION_OPCODE_PRE_TUNNEL:
+ case NFP_FL_ACTION_OPCODE_PRE_LAG:
+ case NFP_FL_ACTION_OPCODE_PUSH_GENEVE:
+ break;
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ act_off += a->len_lw << NFP_FL_LW_SIZ;
+ }
+
+ if (last_act_id)
+ *last_act_id = act_id;
+
+ return 0;
+}
+
+static int
+nfp_flower_populate_merge_match(struct nfp_fl_payload *flow,
+ struct nfp_flower_merge_check *merge,
+ bool extra_fields)
+{
+ struct nfp_flower_meta_tci *meta_tci;
+ u8 *mask = flow->mask_data;
+ u8 key_layer, match_size;
+
+ memset(merge, 0, sizeof(struct nfp_flower_merge_check));
+
+ meta_tci = (struct nfp_flower_meta_tci *)mask;
+ key_layer = meta_tci->nfp_flow_key_layer;
+
+ if (key_layer & ~NFP_FLOWER_MERGE_FIELDS && !extra_fields)
+ return -EOPNOTSUPP;
+
+ merge->tci = meta_tci->tci;
+ mask += sizeof(struct nfp_flower_meta_tci);
+
+ if (key_layer & NFP_FLOWER_LAYER_EXT_META)
+ mask += sizeof(struct nfp_flower_ext_meta);
+
+ mask += sizeof(struct nfp_flower_in_port);
+
+ if (key_layer & NFP_FLOWER_LAYER_MAC) {
+ match_size = sizeof(struct nfp_flower_mac_mpls);
+ memcpy(&merge->l2, mask, match_size);
+ mask += match_size;
+ }
+
+ if (key_layer & NFP_FLOWER_LAYER_TP) {
+ match_size = sizeof(struct nfp_flower_tp_ports);
+ memcpy(&merge->l4, mask, match_size);
+ mask += match_size;
+ }
+
+ if (key_layer & NFP_FLOWER_LAYER_IPV4) {
+ match_size = sizeof(struct nfp_flower_ipv4);
+ memcpy(&merge->ipv4, mask, match_size);
+ }
+
+ if (key_layer & NFP_FLOWER_LAYER_IPV6) {
+ match_size = sizeof(struct nfp_flower_ipv6);
+ memcpy(&merge->ipv6, mask, match_size);
+ }
+
+ return 0;
+}
+
+static int
+nfp_flower_can_merge(struct nfp_fl_payload *sub_flow1,
+ struct nfp_fl_payload *sub_flow2)
+{
+ /* Two flows can be merged if sub_flow2 only matches on bits that are
+ * either matched by sub_flow1 or set by a sub_flow1 action. This
+ * ensures that every packet that hits sub_flow1 and recirculates is
+ * guaranteed to hit sub_flow2.
+ */
+ struct nfp_flower_merge_check sub_flow1_merge, sub_flow2_merge;
+ int err, act_out = 0;
+ u8 last_act_id = 0;
+
+ err = nfp_flower_populate_merge_match(sub_flow1, &sub_flow1_merge,
+ true);
+ if (err)
+ return err;
+
+ err = nfp_flower_populate_merge_match(sub_flow2, &sub_flow2_merge,
+ false);
+ if (err)
+ return err;
+
+ err = nfp_flower_update_merge_with_actions(sub_flow1, &sub_flow1_merge,
+ &last_act_id, &act_out);
+ if (err)
+ return err;
+
+ /* Must only be 1 output action and it must be the last in sequence. */
+ if (act_out != 1 || last_act_id != NFP_FL_ACTION_OPCODE_OUTPUT)
+ return -EOPNOTSUPP;
+
+ /* Reject merge if sub_flow2 matches on something that is not matched
+ * on or set in an action by sub_flow1.
+ */
+ err = bitmap_andnot(sub_flow2_merge.vals, sub_flow2_merge.vals,
+ sub_flow1_merge.vals,
+ sizeof(struct nfp_flower_merge_check) * 8);
+ if (err)
+ return -EINVAL;
+
+ return 0;
+}
+
+static unsigned int
+nfp_flower_copy_pre_actions(char *act_dst, char *act_src, int len,
+ bool *tunnel_act)
+{
+ unsigned int act_off = 0, act_len;
+ struct nfp_fl_act_head *a;
+ u8 act_id = 0;
+
+ while (act_off < len) {
+ a = (struct nfp_fl_act_head *)&act_src[act_off];
+ act_len = a->len_lw << NFP_FL_LW_SIZ;
+ act_id = a->jump_id;
+
+ switch (act_id) {
+ case NFP_FL_ACTION_OPCODE_PRE_TUNNEL:
+ if (tunnel_act)
+ *tunnel_act = true;
+ /* fall through */
+ case NFP_FL_ACTION_OPCODE_PRE_LAG:
+ memcpy(act_dst + act_off, act_src + act_off, act_len);
+ break;
+ default:
+ return act_off;
+ }
+
+ act_off += act_len;
+ }
+
+ return act_off;
+}
+
+static int nfp_fl_verify_post_tun_acts(char *acts, int len)
+{
+ struct nfp_fl_act_head *a;
+ unsigned int act_off = 0;
+
+ while (act_off < len) {
+ a = (struct nfp_fl_act_head *)&acts[act_off];
+ if (a->jump_id != NFP_FL_ACTION_OPCODE_OUTPUT)
+ return -EOPNOTSUPP;
+
+ act_off += a->len_lw << NFP_FL_LW_SIZ;
+ }
+
+ return 0;
+}
+
+static int
+nfp_flower_merge_action(struct nfp_fl_payload *sub_flow1,
+ struct nfp_fl_payload *sub_flow2,
+ struct nfp_fl_payload *merge_flow)
+{
+ unsigned int sub1_act_len, sub2_act_len, pre_off1, pre_off2;
+ bool tunnel_act = false;
+ char *merge_act;
+ int err;
+
+ /* The last action of sub_flow1 must be output - do not merge this. */
+ sub1_act_len = sub_flow1->meta.act_len - sizeof(struct nfp_fl_output);
+ sub2_act_len = sub_flow2->meta.act_len;
+
+ if (!sub2_act_len)
+ return -EINVAL;
+
+ if (sub1_act_len + sub2_act_len > NFP_FL_MAX_A_SIZ)
+ return -EINVAL;
+
+ /* A shortcut can only be applied if there is a single action. */
+ if (sub1_act_len)
+ merge_flow->meta.shortcut = cpu_to_be32(NFP_FL_SC_ACT_NULL);
+ else
+ merge_flow->meta.shortcut = sub_flow2->meta.shortcut;
+
+ merge_flow->meta.act_len = sub1_act_len + sub2_act_len;
+ merge_act = merge_flow->action_data;
+
+ /* Copy any pre-actions to the start of merge flow action list. */
+ pre_off1 = nfp_flower_copy_pre_actions(merge_act,
+ sub_flow1->action_data,
+ sub1_act_len, &tunnel_act);
+ merge_act += pre_off1;
+ sub1_act_len -= pre_off1;
+ pre_off2 = nfp_flower_copy_pre_actions(merge_act,
+ sub_flow2->action_data,
+ sub2_act_len, NULL);
+ merge_act += pre_off2;
+ sub2_act_len -= pre_off2;
+
+ /* FW does a tunnel push when egressing, therefore, if sub_flow 1 pushes
+ * a tunnel, sub_flow 2 can only have output actions for a valid merge.
+ */
+ if (tunnel_act) {
+ char *post_tun_acts = &sub_flow2->action_data[pre_off2];
+
+ err = nfp_fl_verify_post_tun_acts(post_tun_acts, sub2_act_len);
+ if (err)
+ return err;
+ }
+
+ /* Copy remaining actions from sub_flows 1 and 2. */
+ memcpy(merge_act, sub_flow1->action_data + pre_off1, sub1_act_len);
+ merge_act += sub1_act_len;
+ memcpy(merge_act, sub_flow2->action_data + pre_off2, sub2_act_len);
+
+ return 0;
+}
+
+/* Flow link code should only be accessed under RTNL. */
+static void nfp_flower_unlink_flow(struct nfp_fl_payload_link *link)
+{
+ list_del(&link->merge_flow.list);
+ list_del(&link->sub_flow.list);
+ kfree(link);
+}
+
+static void nfp_flower_unlink_flows(struct nfp_fl_payload *merge_flow,
+ struct nfp_fl_payload *sub_flow)
+{
+ struct nfp_fl_payload_link *link;
+
+ list_for_each_entry(link, &merge_flow->linked_flows, merge_flow.list)
+ if (link->sub_flow.flow == sub_flow) {
+ nfp_flower_unlink_flow(link);
+ return;
+ }
+}
+
+static int nfp_flower_link_flows(struct nfp_fl_payload *merge_flow,
+ struct nfp_fl_payload *sub_flow)
+{
+ struct nfp_fl_payload_link *link;
+
+ link = kmalloc(sizeof(*link), GFP_KERNEL);
+ if (!link)
+ return -ENOMEM;
+
+ link->merge_flow.flow = merge_flow;
+ list_add_tail(&link->merge_flow.list, &merge_flow->linked_flows);
+ link->sub_flow.flow = sub_flow;
+ list_add_tail(&link->sub_flow.list, &sub_flow->linked_flows);
+
+ return 0;
+}
+
+/**
+ * nfp_flower_merge_offloaded_flows() - Merge 2 existing flows to single flow.
+ * @app: Pointer to the APP handle
+ * @sub_flow1: Initial flow matched to produce merge hint
+ * @sub_flow2: Post recirculation flow matched in merge hint
+ *
+ * Combines 2 flows (if valid) to a single flow, removing the initial from hw
+ * and offloading the new, merged flow.
+ *
+ * Return: negative value on error, 0 in success.
+ */
+int nfp_flower_merge_offloaded_flows(struct nfp_app *app,
+ struct nfp_fl_payload *sub_flow1,
+ struct nfp_fl_payload *sub_flow2)
+{
+ struct tc_cls_flower_offload merge_tc_off;
+ struct nfp_flower_priv *priv = app->priv;
+ struct nfp_fl_payload *merge_flow;
+ struct nfp_fl_key_ls merge_key_ls;
+ int err;
+
+ ASSERT_RTNL();
+
+ if (sub_flow1 == sub_flow2 ||
+ nfp_flower_is_merge_flow(sub_flow1) ||
+ nfp_flower_is_merge_flow(sub_flow2))
+ return -EINVAL;
+
+ err = nfp_flower_can_merge(sub_flow1, sub_flow2);
+ if (err)
+ return err;
+
+ merge_key_ls.key_size = sub_flow1->meta.key_len;
+
+ merge_flow = nfp_flower_allocate_new(&merge_key_ls);
+ if (!merge_flow)
+ return -ENOMEM;
+
+ merge_flow->tc_flower_cookie = (unsigned long)merge_flow;
+ merge_flow->ingress_dev = sub_flow1->ingress_dev;
+
+ memcpy(merge_flow->unmasked_data, sub_flow1->unmasked_data,
+ sub_flow1->meta.key_len);
+ memcpy(merge_flow->mask_data, sub_flow1->mask_data,
+ sub_flow1->meta.mask_len);
+
+ err = nfp_flower_merge_action(sub_flow1, sub_flow2, merge_flow);
+ if (err)
+ goto err_destroy_merge_flow;
+
+ err = nfp_flower_link_flows(merge_flow, sub_flow1);
+ if (err)
+ goto err_destroy_merge_flow;
+
+ err = nfp_flower_link_flows(merge_flow, sub_flow2);
+ if (err)
+ goto err_unlink_sub_flow1;
+
+ merge_tc_off.cookie = merge_flow->tc_flower_cookie;
+ err = nfp_compile_flow_metadata(app, &merge_tc_off, merge_flow,
+ merge_flow->ingress_dev);
+ if (err)
+ goto err_unlink_sub_flow2;
+
+ err = rhashtable_insert_fast(&priv->flow_table, &merge_flow->fl_node,
+ nfp_flower_table_params);
+ if (err)
+ goto err_release_metadata;
+
+ err = nfp_flower_xmit_flow(app, merge_flow,
+ NFP_FLOWER_CMSG_TYPE_FLOW_MOD);
+ if (err)
+ goto err_remove_rhash;
+
+ merge_flow->in_hw = true;
+ sub_flow1->in_hw = false;
+
+ return 0;
+
+err_remove_rhash:
+ WARN_ON_ONCE(rhashtable_remove_fast(&priv->flow_table,
+ &merge_flow->fl_node,
+ nfp_flower_table_params));
+err_release_metadata:
+ nfp_modify_flow_metadata(app, merge_flow);
+err_unlink_sub_flow2:
+ nfp_flower_unlink_flows(merge_flow, sub_flow2);
+err_unlink_sub_flow1:
+ nfp_flower_unlink_flows(merge_flow, sub_flow1);
+err_destroy_merge_flow:
+ kfree(merge_flow->action_data);
+ kfree(merge_flow->mask_data);
+ kfree(merge_flow->unmasked_data);
+ kfree(merge_flow);
+ return err;
+}
+
/**
* nfp_flower_add_offload() - Adds a new flow to hardware.
* @app: Pointer to the APP handle
if (port)
port->tc_offload_cnt++;
+ flow_pay->in_hw = true;
+
/* Deallocate flow payload when flower rule has been destroyed. */
kfree(key_layer);
return err;
}
+static void
+nfp_flower_remove_merge_flow(struct nfp_app *app,
+ struct nfp_fl_payload *del_sub_flow,
+ struct nfp_fl_payload *merge_flow)
+{
+ struct nfp_flower_priv *priv = app->priv;
+ struct nfp_fl_payload_link *link, *temp;
+ struct nfp_fl_payload *origin;
+ bool mod = false;
+ int err;
+
+ link = list_first_entry(&merge_flow->linked_flows,
+ struct nfp_fl_payload_link, merge_flow.list);
+ origin = link->sub_flow.flow;
+
+ /* Re-add rule the merge had overwritten if it has not been deleted. */
+ if (origin != del_sub_flow)
+ mod = true;
+
+ err = nfp_modify_flow_metadata(app, merge_flow);
+ if (err) {
+ nfp_flower_cmsg_warn(app, "Metadata fail for merge flow delete.\n");
+ goto err_free_links;
+ }
+
+ if (!mod) {
+ err = nfp_flower_xmit_flow(app, merge_flow,
+ NFP_FLOWER_CMSG_TYPE_FLOW_DEL);
+ if (err) {
+ nfp_flower_cmsg_warn(app, "Failed to delete merged flow.\n");
+ goto err_free_links;
+ }
+ } else {
+ __nfp_modify_flow_metadata(priv, origin);
+ err = nfp_flower_xmit_flow(app, origin,
+ NFP_FLOWER_CMSG_TYPE_FLOW_MOD);
+ if (err)
+ nfp_flower_cmsg_warn(app, "Failed to revert merge flow.\n");
+ origin->in_hw = true;
+ }
+
+err_free_links:
+ /* Clean any links connected with the merged flow. */
+ list_for_each_entry_safe(link, temp, &merge_flow->linked_flows,
+ merge_flow.list)
+ nfp_flower_unlink_flow(link);
+
+ kfree(merge_flow->action_data);
+ kfree(merge_flow->mask_data);
+ kfree(merge_flow->unmasked_data);
+ WARN_ON_ONCE(rhashtable_remove_fast(&priv->flow_table,
+ &merge_flow->fl_node,
+ nfp_flower_table_params));
+ kfree_rcu(merge_flow, rcu);
+}
+
+static void
+nfp_flower_del_linked_merge_flows(struct nfp_app *app,
+ struct nfp_fl_payload *sub_flow)
+{
+ struct nfp_fl_payload_link *link, *temp;
+
+ /* Remove any merge flow formed from the deleted sub_flow. */
+ list_for_each_entry_safe(link, temp, &sub_flow->linked_flows,
+ sub_flow.list)
+ nfp_flower_remove_merge_flow(app, sub_flow,
+ link->merge_flow.flow);
+}
+
/**
* nfp_flower_del_offload() - Removes a flow from hardware.
* @app: Pointer to the APP handle
* @flow: TC flower classifier offload structure
*
* Removes a flow from the repeated hash structure and clears the
- * action payload.
+ * action payload. Any flows merged from this are also deleted.
*
* Return: negative value on error, 0 if removed successfully.
*/
err = nfp_modify_flow_metadata(app, nfp_flow);
if (err)
- goto err_free_flow;
+ goto err_free_merge_flow;
if (nfp_flow->nfp_tun_ipv4_addr)
nfp_tunnel_del_ipv4_off(app, nfp_flow->nfp_tun_ipv4_addr);
+ if (!nfp_flow->in_hw) {
+ err = 0;
+ goto err_free_merge_flow;
+ }
+
err = nfp_flower_xmit_flow(app, nfp_flow,
NFP_FLOWER_CMSG_TYPE_FLOW_DEL);
- if (err)
- goto err_free_flow;
+ /* Fall through on error. */
-err_free_flow:
+err_free_merge_flow:
+ nfp_flower_del_linked_merge_flows(app, nfp_flow);
if (port)
port->tc_offload_cnt--;
kfree(nfp_flow->action_data);
return err;
}
+static void
+__nfp_flower_update_merge_stats(struct nfp_app *app,
+ struct nfp_fl_payload *merge_flow)
+{
+ struct nfp_flower_priv *priv = app->priv;
+ struct nfp_fl_payload_link *link;
+ struct nfp_fl_payload *sub_flow;
+ u64 pkts, bytes, used;
+ u32 ctx_id;
+
+ ctx_id = be32_to_cpu(merge_flow->meta.host_ctx_id);
+ pkts = priv->stats[ctx_id].pkts;
+ /* Do not cycle subflows if no stats to distribute. */
+ if (!pkts)
+ return;
+ bytes = priv->stats[ctx_id].bytes;
+ used = priv->stats[ctx_id].used;
+
+ /* Reset stats for the merge flow. */
+ priv->stats[ctx_id].pkts = 0;
+ priv->stats[ctx_id].bytes = 0;
+
+ /* The merge flow has received stats updates from firmware.
+ * Distribute these stats to all subflows that form the merge.
+ * The stats will collected from TC via the subflows.
+ */
+ list_for_each_entry(link, &merge_flow->linked_flows, merge_flow.list) {
+ sub_flow = link->sub_flow.flow;
+ ctx_id = be32_to_cpu(sub_flow->meta.host_ctx_id);
+ priv->stats[ctx_id].pkts += pkts;
+ priv->stats[ctx_id].bytes += bytes;
+ max_t(u64, priv->stats[ctx_id].used, used);
+ }
+}
+
+static void
+nfp_flower_update_merge_stats(struct nfp_app *app,
+ struct nfp_fl_payload *sub_flow)
+{
+ struct nfp_fl_payload_link *link;
+
+ /* Get merge flows that the subflow forms to distribute their stats. */
+ list_for_each_entry(link, &sub_flow->linked_flows, sub_flow.list)
+ __nfp_flower_update_merge_stats(app, link->merge_flow.flow);
+}
+
/**
* nfp_flower_get_stats() - Populates flow stats obtained from hardware.
* @app: Pointer to the APP handle
ctx_id = be32_to_cpu(nfp_flow->meta.host_ctx_id);
spin_lock_bh(&priv->stats_lock);
+ /* If request is for a sub_flow, update stats from merged flows. */
+ if (!list_empty(&nfp_flow->linked_flows))
+ nfp_flower_update_merge_stats(app, nfp_flow);
+
flow_stats_update(&flow->stats, priv->stats[ctx_id].bytes,
priv->stats[ctx_id].pkts, priv->stats[ctx_id].used);
struct nfp_flower_priv *priv = app->priv;
int err;
- if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+ if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS &&
+ !(f->binder_type == TCF_BLOCK_BINDER_TYPE_CLSACT_EGRESS &&
+ nfp_flower_internal_port_can_offload(app, netdev)))
return -EOPNOTSUPP;
switch (f->command) {
for (i = 0; i < count; i++) {
ipv4_addr = payload->tun_info[i].ipv4;
port = be32_to_cpu(payload->tun_info[i].egress_port);
- netdev = nfp_app_repr_get(app, port);
+ netdev = nfp_app_dev_get(app, port, NULL);
if (!netdev)
continue;
struct flowi4 *flow, struct neighbour *neigh, gfp_t flag)
{
struct nfp_tun_neigh payload;
+ u32 port_id;
- /* Only offload representor IPv4s for now. */
- if (!nfp_netdev_is_nfp_repr(netdev))
+ port_id = nfp_flower_get_port_id_from_netdev(app, netdev);
+ if (!port_id)
return;
memset(&payload, 0, sizeof(struct nfp_tun_neigh));
payload.src_ipv4 = flow->saddr;
ether_addr_copy(payload.src_addr, netdev->dev_addr);
neigh_ha_snapshot(payload.dst_addr, neigh, netdev);
- payload.port_id = cpu_to_be32(nfp_repr_get_port_id(netdev));
+ payload.port_id = cpu_to_be32(port_id);
/* Add destination of new route to NFP cache. */
nfp_tun_add_route_to_cache(app, payload.dst_ipv4);
payload = nfp_flower_cmsg_get_data(skb);
- netdev = nfp_app_repr_get(app, be32_to_cpu(payload->ingress_port));
+ netdev = nfp_app_dev_get(app, be32_to_cpu(payload->ingress_port), NULL);
if (!netdev)
goto route_fail_warning;
* @eswitch_mode_set: set SR-IOV eswitch mode (under pf->lock)
* @sriov_enable: app-specific sriov initialisation
* @sriov_disable: app-specific sriov clean-up
- * @repr_get: get representor netdev
+ * @dev_get: get representor or internal port representing netdev
*/
struct nfp_app_type {
enum nfp_app_id id;
enum devlink_eswitch_mode (*eswitch_mode_get)(struct nfp_app *app);
int (*eswitch_mode_set)(struct nfp_app *app, u16 mode);
- struct net_device *(*repr_get)(struct nfp_app *app, u32 id);
+ struct net_device *(*dev_get)(struct nfp_app *app, u32 id,
+ bool *redir_egress);
};
/**
app->type->sriov_disable(app);
}
-static inline struct net_device *nfp_app_repr_get(struct nfp_app *app, u32 id)
+static inline
+struct net_device *nfp_app_dev_get(struct nfp_app *app, u32 id,
+ bool *redir_egress)
{
- if (unlikely(!app || !app->type->repr_get))
+ if (unlikely(!app || !app->type->dev_get))
return NULL;
- return app->type->repr_get(app, id);
+ return app->type->dev_get(app, id, redir_egress);
}
struct nfp_app *nfp_app_from_netdev(struct net_device *netdev);
{
struct nfp_eth_table_port eth_port;
struct devlink *devlink;
+ const u8 *serial;
+ int serial_len;
int ret;
rtnl_lock();
if (ret)
return ret;
+ serial_len = nfp_cpp_serial(port->app->cpp, &serial);
devlink_port_attrs_set(&port->dl_port, DEVLINK_PORT_FLAVOUR_PHYSICAL,
eth_port.label_port, eth_port.is_split,
- eth_port.label_subport);
+ eth_port.label_subport, serial, serial_len);
devlink = priv_to_devlink(app->pf);
* @shared_handler: Handler for shared interrupts
* @shared_name: Name for shared interrupt
* @me_freq_mhz: ME clock_freq (MHz)
- * @reconfig_lock: Protects HW reconfiguration request regs/machinery
+ * @reconfig_lock: Protects @reconfig_posted, @reconfig_timer_active,
+ * @reconfig_sync_present and HW reconfiguration request
+ * regs/machinery from async requests (sync must take
+ * @bar_lock)
* @reconfig_posted: Pending reconfig bits coming from async sources
* @reconfig_timer_active: Timer for reading reconfiguration results is pending
* @reconfig_sync_present: Some thread is performing synchronous reconfig
* @reconfig_timer: Timer for async reading of reconfig results
* @reconfig_in_progress_update: Update FW is processing now (debug only)
+ * @bar_lock: vNIC config BAR access lock, protects: update,
+ * mailbox area
* @link_up: Is the link up?
* @link_status_lock: Protects @link_* and ensures atomicity with BAR reading
* @rx_coalesce_usecs: RX interrupt moderation usecs delay parameter
struct timer_list reconfig_timer;
u32 reconfig_in_progress_update;
+ struct mutex bar_lock;
+
u32 rx_coalesce_usecs;
u32 rx_coalesce_max_frames;
u32 tx_coalesce_usecs;
spin_unlock_bh(&nn->r_vecs[0].lock);
}
+static inline void nn_ctrl_bar_lock(struct nfp_net *nn)
+{
+ mutex_lock(&nn->bar_lock);
+}
+
+static inline void nn_ctrl_bar_unlock(struct nfp_net *nn)
+{
+ mutex_unlock(&nn->bar_lock);
+}
+
/* Globals */
extern const char nfp_driver_version[];
void nfp_net_rss_write_itbl(struct nfp_net *nn);
void nfp_net_rss_write_key(struct nfp_net *nn);
void nfp_net_coalesce_write_cfg(struct nfp_net *nn);
-int nfp_net_reconfig_mbox(struct nfp_net *nn, u32 mbox_cmd);
+int nfp_net_mbox_lock(struct nfp_net *nn, unsigned int data_size);
+int nfp_net_mbox_reconfig(struct nfp_net *nn, u32 mbox_cmd);
+int nfp_net_mbox_reconfig_and_unlock(struct nfp_net *nn, u32 mbox_cmd);
unsigned int
nfp_net_irqs_alloc(struct pci_dev *pdev, struct msix_entry *irq_entries,
#include <linux/interrupt.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
+#include <linux/lockdep.h>
#include <linux/mm.h>
#include <linux/overflow.h>
#include <linux/page_ref.h>
return false;
}
-static int nfp_net_reconfig_wait(struct nfp_net *nn, unsigned long deadline)
+static bool __nfp_net_reconfig_wait(struct nfp_net *nn, unsigned long deadline)
{
bool timed_out = false;
+ int i;
+
+ /* Poll update field, waiting for NFP to ack the config.
+ * Do an opportunistic wait-busy loop, afterward sleep.
+ */
+ for (i = 0; i < 50; i++) {
+ if (nfp_net_reconfig_check_done(nn, false))
+ return false;
+ udelay(4);
+ }
- /* Poll update field, waiting for NFP to ack the config */
while (!nfp_net_reconfig_check_done(nn, timed_out)) {
- msleep(1);
+ usleep_range(250, 500);
timed_out = time_is_before_eq_jiffies(deadline);
}
+ return timed_out;
+}
+
+static int nfp_net_reconfig_wait(struct nfp_net *nn, unsigned long deadline)
+{
+ if (__nfp_net_reconfig_wait(nn, deadline))
+ return -EIO;
+
if (nn_readl(nn, NFP_NET_CFG_UPDATE) & NFP_NET_CFG_UPDATE_ERR)
return -EIO;
- return timed_out ? -EIO : 0;
+ return 0;
}
static void nfp_net_reconfig_timer(struct timer_list *t)
}
/**
- * nfp_net_reconfig() - Reconfigure the firmware
+ * __nfp_net_reconfig() - Reconfigure the firmware
* @nn: NFP Net device to reconfigure
* @update: The value for the update field in the BAR config
*
*
* Return: Negative errno on error, 0 on success
*/
-int nfp_net_reconfig(struct nfp_net *nn, u32 update)
+static int __nfp_net_reconfig(struct nfp_net *nn, u32 update)
{
int ret;
+ lockdep_assert_held(&nn->bar_lock);
+
nfp_net_reconfig_sync_enter(nn);
nfp_net_reconfig_start(nn, update);
return ret;
}
+int nfp_net_reconfig(struct nfp_net *nn, u32 update)
+{
+ int ret;
+
+ nn_ctrl_bar_lock(nn);
+ ret = __nfp_net_reconfig(nn, update);
+ nn_ctrl_bar_unlock(nn);
+
+ return ret;
+}
+
+int nfp_net_mbox_lock(struct nfp_net *nn, unsigned int data_size)
+{
+ if (nn->tlv_caps.mbox_len < NFP_NET_CFG_MBOX_SIMPLE_VAL + data_size) {
+ nn_err(nn, "mailbox too small for %u of data (%u)\n",
+ data_size, nn->tlv_caps.mbox_len);
+ return -EIO;
+ }
+
+ nn_ctrl_bar_lock(nn);
+ return 0;
+}
+
/**
- * nfp_net_reconfig_mbox() - Reconfigure the firmware via the mailbox
+ * nfp_net_mbox_reconfig() - Reconfigure the firmware via the mailbox
* @nn: NFP Net device to reconfigure
* @mbox_cmd: The value for the mailbox command
*
*
* Return: Negative errno on error, 0 on success
*/
-int nfp_net_reconfig_mbox(struct nfp_net *nn, u32 mbox_cmd)
+int nfp_net_mbox_reconfig(struct nfp_net *nn, u32 mbox_cmd)
{
u32 mbox = nn->tlv_caps.mbox_off;
int ret;
- if (!nfp_net_has_mbox(&nn->tlv_caps)) {
- nn_err(nn, "no mailbox present, command: %u\n", mbox_cmd);
- return -EIO;
- }
-
+ lockdep_assert_held(&nn->bar_lock);
nn_writeq(nn, mbox + NFP_NET_CFG_MBOX_SIMPLE_CMD, mbox_cmd);
- ret = nfp_net_reconfig(nn, NFP_NET_CFG_UPDATE_MBOX);
+ ret = __nfp_net_reconfig(nn, NFP_NET_CFG_UPDATE_MBOX);
if (ret) {
nn_err(nn, "Mailbox update error\n");
return ret;
return -nn_readl(nn, mbox + NFP_NET_CFG_MBOX_SIMPLE_RET);
}
+int nfp_net_mbox_reconfig_and_unlock(struct nfp_net *nn, u32 mbox_cmd)
+{
+ int ret;
+
+ ret = nfp_net_mbox_reconfig(nn, mbox_cmd);
+ nn_ctrl_bar_unlock(nn);
+ return ret;
+}
+
/* Interrupt configuration and handling
*/
nfp_net_tx_ring_stop(nd_q, tx_ring);
tx_ring->wr_ptr_add += nr_frags + 1;
- if (__netdev_tx_sent_queue(nd_q, txbuf->real_len, skb->xmit_more))
+ if (__netdev_tx_sent_queue(nd_q, txbuf->real_len, netdev_xmit_more()))
nfp_net_tx_xmit_more_flush(tx_ring);
return NETDEV_TX_OK;
struct nfp_net_rx_buf *rxbuf;
struct nfp_net_rx_desc *rxd;
struct nfp_meta_parsed meta;
+ bool redir_egress = false;
struct net_device *netdev;
dma_addr_t new_dma_addr;
u32 meta_len_xdp = 0;
struct nfp_net *nn;
nn = netdev_priv(dp->netdev);
- netdev = nfp_app_repr_get(nn->app, meta.portid);
+ netdev = nfp_app_dev_get(nn->app, meta.portid,
+ &redir_egress);
if (unlikely(!netdev)) {
nfp_net_rx_drop(dp, r_vec, rx_ring, rxbuf,
NULL);
continue;
}
- nfp_repr_inc_rx_stats(netdev, pkt_len);
+
+ if (nfp_netdev_is_nfp_repr(netdev))
+ nfp_repr_inc_rx_stats(netdev, pkt_len);
}
skb = build_skb(rxbuf->frag, true_bufsz);
if (meta_len_xdp)
skb_metadata_set(skb, meta_len_xdp);
- napi_gro_receive(&rx_ring->r_vec->napi, skb);
+ if (likely(!redir_egress)) {
+ napi_gro_receive(&rx_ring->r_vec->napi, skb);
+ } else {
+ skb->dev = netdev;
+ __skb_push(skb, ETH_HLEN);
+ dev_queue_xmit(skb);
+ }
}
if (xdp_prog) {
static int
nfp_net_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid)
{
+ const u32 cmd = NFP_NET_CFG_MBOX_CMD_CTAG_FILTER_ADD;
struct nfp_net *nn = netdev_priv(netdev);
+ int err;
/* Priority tagged packets with vlan id 0 are processed by the
* NFP as untagged packets
if (!vid)
return 0;
+ err = nfp_net_mbox_lock(nn, NFP_NET_CFG_VLAN_FILTER_SZ);
+ if (err)
+ return err;
+
nn_writew(nn, nn->tlv_caps.mbox_off + NFP_NET_CFG_VLAN_FILTER_VID, vid);
nn_writew(nn, nn->tlv_caps.mbox_off + NFP_NET_CFG_VLAN_FILTER_PROTO,
ETH_P_8021Q);
- return nfp_net_reconfig_mbox(nn, NFP_NET_CFG_MBOX_CMD_CTAG_FILTER_ADD);
+ return nfp_net_mbox_reconfig_and_unlock(nn, cmd);
}
static int
nfp_net_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid)
{
+ const u32 cmd = NFP_NET_CFG_MBOX_CMD_CTAG_FILTER_KILL;
struct nfp_net *nn = netdev_priv(netdev);
+ int err;
/* Priority tagged packets with vlan id 0 are processed by the
* NFP as untagged packets
if (!vid)
return 0;
+ err = nfp_net_mbox_lock(nn, NFP_NET_CFG_VLAN_FILTER_SZ);
+ if (err)
+ return err;
+
nn_writew(nn, nn->tlv_caps.mbox_off + NFP_NET_CFG_VLAN_FILTER_VID, vid);
nn_writew(nn, nn->tlv_caps.mbox_off + NFP_NET_CFG_VLAN_FILTER_PROTO,
ETH_P_8021Q);
- return nfp_net_reconfig_mbox(nn, NFP_NET_CFG_MBOX_CMD_CTAG_FILTER_KILL);
+ return nfp_net_mbox_reconfig_and_unlock(nn, cmd);
}
static void nfp_net_stat64(struct net_device *netdev,
.ndo_udp_tunnel_add = nfp_net_add_vxlan_port,
.ndo_udp_tunnel_del = nfp_net_del_vxlan_port,
.ndo_bpf = nfp_net_xdp,
- .ndo_get_port_parent_id = nfp_port_get_port_parent_id,
.ndo_get_devlink_port = nfp_devlink_get_devlink_port,
};
nn->dp.txd_cnt = NFP_NET_TX_DESCS_DEFAULT;
nn->dp.rxd_cnt = NFP_NET_RX_DESCS_DEFAULT;
+ mutex_init(&nn->bar_lock);
+
spin_lock_init(&nn->reconfig_lock);
spin_lock_init(&nn->link_status_lock);
void nfp_net_free(struct nfp_net *nn)
{
WARN_ON(timer_pending(&nn->reconfig_timer) || nn->reconfig_posted);
+
+ mutex_destroy(&nn->bar_lock);
+
if (nn->dp.netdev)
free_netdev(nn->dp.netdev);
else
nn->dp.ctrl |= NFP_NET_CFG_CTRL_IRQMOD;
}
- if (nn->dp.netdev)
- nfp_net_netdev_init(nn);
-
/* Stash the re-configuration queue away. First odd queue in TX Bar */
nn->qcp_cfg = nn->tx_bar + NFP_QCP_QUEUE_ADDR_SZ;
if (err)
return err;
+ if (nn->dp.netdev)
+ nfp_net_netdev_init(nn);
+
nfp_net_vecs_init(nn);
if (!nn->dp.netdev)
#define NFP_NET_CFG_MBOX_SIMPLE_CMD 0x0
#define NFP_NET_CFG_MBOX_SIMPLE_RET 0x4
#define NFP_NET_CFG_MBOX_SIMPLE_VAL 0x8
-#define NFP_NET_CFG_MBOX_SIMPLE_LEN 12
#define NFP_NET_CFG_MBOX_CMD_CTAG_FILTER_ADD 1
#define NFP_NET_CFG_MBOX_CMD_CTAG_FILTER_KILL 2
int nfp_net_tlv_caps_parse(struct device *dev, u8 __iomem *ctrl_mem,
struct nfp_net_tlv_caps *caps);
-
-static inline bool nfp_net_has_mbox(struct nfp_net_tlv_caps *caps)
-{
- return caps->mbox_len >= NFP_NET_CFG_MBOX_SIMPLE_LEN;
-}
-
#endif /* _NFP_NET_CTRL_H_ */
#include <linux/pci.h>
#include <linux/ethtool.h>
#include <linux/firmware.h>
+#include <linux/sfp.h>
#include "nfpcore/nfp.h"
#include "nfpcore/nfp_nsp.h"
#define NN_RVEC_GATHER_STATS 9
#define NN_RVEC_PER_Q_STATS 3
+#define SFP_SFF_REV_COMPLIANCE 1
+
static void nfp_net_get_nspinfo(struct nfp_app *app, char *version)
{
struct nfp_nsp *nsp;
buffer);
}
+static int
+nfp_port_get_module_info(struct net_device *netdev,
+ struct ethtool_modinfo *modinfo)
+{
+ struct nfp_eth_table_port *eth_port;
+ struct nfp_port *port;
+ unsigned int read_len;
+ struct nfp_nsp *nsp;
+ int err = 0;
+ u8 data;
+
+ port = nfp_port_from_netdev(netdev);
+ eth_port = nfp_port_get_eth_port(port);
+ if (!eth_port)
+ return -EOPNOTSUPP;
+
+ nsp = nfp_nsp_open(port->app->cpp);
+ if (IS_ERR(nsp)) {
+ err = PTR_ERR(nsp);
+ netdev_err(netdev, "Failed to access the NSP: %d\n", err);
+ return err;
+ }
+
+ if (!nfp_nsp_has_read_module_eeprom(nsp)) {
+ netdev_info(netdev, "reading module EEPROM not supported. Please update flash\n");
+ err = -EOPNOTSUPP;
+ goto exit_close_nsp;
+ }
+
+ switch (eth_port->interface) {
+ case NFP_INTERFACE_SFP:
+ case NFP_INTERFACE_SFP28:
+ err = nfp_nsp_read_module_eeprom(nsp, eth_port->eth_index,
+ SFP_SFF8472_COMPLIANCE, &data,
+ 1, &read_len);
+ if (err < 0)
+ goto exit_close_nsp;
+
+ if (!data) {
+ modinfo->type = ETH_MODULE_SFF_8079;
+ modinfo->eeprom_len = ETH_MODULE_SFF_8079_LEN;
+ } else {
+ modinfo->type = ETH_MODULE_SFF_8472;
+ modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN;
+ }
+ break;
+ case NFP_INTERFACE_QSFP:
+ err = nfp_nsp_read_module_eeprom(nsp, eth_port->eth_index,
+ SFP_SFF_REV_COMPLIANCE, &data,
+ 1, &read_len);
+ if (err < 0)
+ goto exit_close_nsp;
+
+ if (data < 0x3) {
+ modinfo->type = ETH_MODULE_SFF_8436;
+ modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN;
+ } else {
+ modinfo->type = ETH_MODULE_SFF_8636;
+ modinfo->eeprom_len = ETH_MODULE_SFF_8636_LEN;
+ }
+ break;
+ case NFP_INTERFACE_QSFP28:
+ modinfo->type = ETH_MODULE_SFF_8636;
+ modinfo->eeprom_len = ETH_MODULE_SFF_8636_LEN;
+ break;
+ default:
+ netdev_err(netdev, "Unsupported module 0x%x detected\n",
+ eth_port->interface);
+ err = -EINVAL;
+ }
+
+exit_close_nsp:
+ nfp_nsp_close(nsp);
+ return err;
+}
+
+static int
+nfp_port_get_module_eeprom(struct net_device *netdev,
+ struct ethtool_eeprom *eeprom, u8 *data)
+{
+ struct nfp_eth_table_port *eth_port;
+ struct nfp_port *port;
+ struct nfp_nsp *nsp;
+ int err;
+
+ port = nfp_port_from_netdev(netdev);
+ eth_port = __nfp_port_get_eth_port(port);
+ if (!eth_port)
+ return -EOPNOTSUPP;
+
+ nsp = nfp_nsp_open(port->app->cpp);
+ if (IS_ERR(nsp)) {
+ err = PTR_ERR(nsp);
+ netdev_err(netdev, "Failed to access the NSP: %d\n", err);
+ return err;
+ }
+
+ if (!nfp_nsp_has_read_module_eeprom(nsp)) {
+ netdev_info(netdev, "reading module EEPROM not supported. Please update flash\n");
+ err = -EOPNOTSUPP;
+ goto exit_close_nsp;
+ }
+
+ err = nfp_nsp_read_module_eeprom(nsp, eth_port->eth_index,
+ eeprom->offset, data, eeprom->len,
+ &eeprom->len);
+ if (err < 0) {
+ if (eeprom->len) {
+ netdev_warn(netdev,
+ "Incomplete read from module EEPROM: %d\n",
+ err);
+ err = 0;
+ } else {
+ netdev_err(netdev,
+ "Reading from module EEPROM failed: %d\n",
+ err);
+ }
+ }
+
+exit_close_nsp:
+ nfp_nsp_close(nsp);
+ return err;
+}
+
static int nfp_net_set_coalesce(struct net_device *netdev,
struct ethtool_coalesce *ec)
{
.set_dump = nfp_app_set_dump,
.get_dump_flag = nfp_app_get_dump_flag,
.get_dump_data = nfp_app_get_dump_data,
+ .get_module_info = nfp_port_get_module_info,
+ .get_module_eeprom = nfp_port_get_module_eeprom,
.get_coalesce = nfp_net_get_coalesce,
.set_coalesce = nfp_net_set_coalesce,
.get_channels = nfp_net_get_channels,
.set_dump = nfp_app_set_dump,
.get_dump_flag = nfp_app_get_dump_flag,
.get_dump_data = nfp_app_get_dump_data,
+ .get_module_info = nfp_port_get_module_info,
+ .get_module_eeprom = nfp_port_get_module_eeprom,
.get_link_ksettings = nfp_net_get_link_ksettings,
.set_link_ksettings = nfp_net_set_link_ksettings,
.get_fecparam = nfp_port_get_fecparam,
ret = dev_queue_xmit(skb);
nfp_repr_inc_tx_stats(netdev, len, ret);
- return ret;
+ return NETDEV_TX_OK;
}
static int nfp_repr_stop(struct net_device *netdev)
.ndo_fix_features = nfp_repr_fix_features,
.ndo_set_features = nfp_port_set_features,
.ndo_set_mac_address = eth_mac_addr,
- .ndo_get_port_parent_id = nfp_port_get_port_parent_id,
.ndo_get_devlink_port = nfp_devlink_get_devlink_port,
};
netdev->features &= ~(NETIF_F_TSO | NETIF_F_TSO6);
netdev->gso_max_segs = NFP_NET_LSO_MAX_SEGS;
- netdev->priv_flags |= IFF_NO_QUEUE;
+ netdev->priv_flags |= IFF_NO_QUEUE | IFF_DISABLE_NETPOLL;
netdev->features |= NETIF_F_LLTX;
if (nfp_app_has_tc(app)) {
return NULL;
}
-int nfp_port_get_port_parent_id(struct net_device *netdev,
- struct netdev_phys_item_id *ppid)
-{
- struct nfp_port *port;
- const u8 *serial;
-
- port = nfp_port_from_netdev(netdev);
- if (!port)
- return -EOPNOTSUPP;
-
- ppid->id_len = nfp_cpp_serial(port->app->cpp, &serial);
- memcpy(&ppid->id, serial, ppid->id_len);
-
- return 0;
-}
-
int nfp_port_setup_tc(struct net_device *netdev, enum tc_setup_type type,
void *type_data)
{
#define NFP_VERSIONS_NCSI_OFF 22
#define NFP_VERSIONS_CFGR_OFF 26
+#define NSP_SFF_EEPROM_BLOCK_LEN 8
+
enum nfp_nsp_cmd {
SPCODE_NOOP = 0, /* No operation */
SPCODE_SOFT_RESET = 1, /* Soft reset the NFP */
SPCODE_FW_STORED = 16, /* If no FW loaded, load flash app FW */
SPCODE_HWINFO_LOOKUP = 17, /* Lookup HWinfo with overwrites etc. */
SPCODE_VERSIONS = 21, /* Report FW versions */
+ SPCODE_READ_SFF_EEPROM = 22, /* Read module EEPROM */
};
struct nfp_nsp_dma_buf {
return (const char *)&buf[buf_off];
}
+
+static int
+__nfp_nsp_module_eeprom(struct nfp_nsp *state, void *buf, unsigned int size)
+{
+ struct nfp_nsp_command_buf_arg module_eeprom = {
+ {
+ .code = SPCODE_READ_SFF_EEPROM,
+ .option = size,
+ },
+ .in_buf = buf,
+ .in_size = size,
+ .out_buf = buf,
+ .out_size = size,
+ };
+
+ return nfp_nsp_command_buf(state, &module_eeprom);
+}
+
+int nfp_nsp_read_module_eeprom(struct nfp_nsp *state, int eth_index,
+ unsigned int offset, void *data,
+ unsigned int len, unsigned int *read_len)
+{
+ struct eeprom_buf {
+ u8 metalen;
+ __le16 length;
+ __le16 offset;
+ __le16 readlen;
+ u8 eth_index;
+ u8 data[0];
+ } __packed *buf;
+ int bufsz, ret;
+
+ BUILD_BUG_ON(offsetof(struct eeprom_buf, data) % 8);
+
+ /* Buffer must be large enough and rounded to the next block size. */
+ bufsz = struct_size(buf, data, round_up(len, NSP_SFF_EEPROM_BLOCK_LEN));
+ buf = kzalloc(bufsz, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
+ buf->metalen =
+ offsetof(struct eeprom_buf, data) / NSP_SFF_EEPROM_BLOCK_LEN;
+ buf->length = cpu_to_le16(len);
+ buf->offset = cpu_to_le16(offset);
+ buf->eth_index = eth_index;
+
+ ret = __nfp_nsp_module_eeprom(state, buf, bufsz);
+
+ *read_len = min_t(unsigned int, len, le16_to_cpu(buf->readlen));
+ if (*read_len)
+ memcpy(data, buf->data, *read_len);
+
+ if (!ret && *read_len < len)
+ ret = -EIO;
+
+ kfree(buf);
+
+ return ret;
+}
int nfp_nsp_mac_reinit(struct nfp_nsp *state);
int nfp_nsp_load_stored_fw(struct nfp_nsp *state);
int nfp_nsp_hwinfo_lookup(struct nfp_nsp *state, void *buf, unsigned int size);
+int nfp_nsp_read_module_eeprom(struct nfp_nsp *state, int eth_index,
+ unsigned int offset, void *data,
+ unsigned int len, unsigned int *read_len);
static inline bool nfp_nsp_has_mac_reinit(struct nfp_nsp *state)
{
return nfp_nsp_get_abi_ver_minor(state) > 27;
}
+static inline bool nfp_nsp_has_read_module_eeprom(struct nfp_nsp *state)
+{
+ return nfp_nsp_get_abi_ver_minor(state) > 28;
+}
+
enum nfp_eth_interface {
NFP_INTERFACE_NONE = 0,
NFP_INTERFACE_SFP = 1,
const int nh_off = skb_network_offset(skb);
const int nh_len = skb_network_header_len(skb);
const int nfrags = skb_shinfo(skb)->nr_frags;
- int cs_size, i, fill, hdr, cpyhdr, evt;
+ int cs_size, i, fill, hdr, evt;
dma_addr_t csdma;
fund = XCT_FUN_ST | XCT_FUN_RR_8BRES |
fill++;
/* Copy the result into the TCP packet */
- cpyhdr = fill;
CS_DESC(csring, fill++) = XCT_FUN_O | XCT_FUN_FUN(csring->fun) |
XCT_FUN_LLEN(2) | XCT_FUN_SE;
CS_DESC(csring, fill++) = XCT_PTR_LEN(2) | XCT_PTR_ADDR(cs_dest) | XCT_PTR_T;
u8 num_pf_rls;
};
+#define QED_OVERFLOW_BIT 1
+
struct qed_db_recovery_info {
struct list_head list;
/* Lock to protect the doorbell recovery mechanism list */
spinlock_t lock;
+ bool dorq_attn;
u32 db_recovery_counter;
+ unsigned long overflow;
};
struct storm_stats {
/* doorbell recovery mechanism */
void qed_db_recovery_dp(struct qed_hwfn *p_hwfn);
-void qed_db_recovery_execute(struct qed_hwfn *p_hwfn,
- enum qed_db_rec_exec db_exec);
+void qed_db_recovery_execute(struct qed_hwfn *p_hwfn);
bool qed_edpm_enabled(struct qed_hwfn *p_hwfn);
/* Other Linux specific common definitions */
/* Doorbell address sanity (address within doorbell bar range) */
static bool qed_db_rec_sanity(struct qed_dev *cdev,
- void __iomem *db_addr, void *db_data)
+ void __iomem *db_addr,
+ enum qed_db_rec_width db_width,
+ void *db_data)
{
+ u32 width = (db_width == DB_REC_WIDTH_32B) ? 32 : 64;
+
/* Make sure doorbell address is within the doorbell bar */
if (db_addr < cdev->doorbells ||
- (u8 __iomem *)db_addr >
+ (u8 __iomem *)db_addr + width >
(u8 __iomem *)cdev->doorbells + cdev->db_size) {
WARN(true,
"Illegal doorbell address: %p. Legal range for doorbell addresses is [%p..%p]\n",
}
/* Sanitize doorbell address */
- if (!qed_db_rec_sanity(cdev, db_addr, db_data))
+ if (!qed_db_rec_sanity(cdev, db_addr, db_width, db_data))
return -EINVAL;
/* Obtain hwfn from doorbell address */
return 0;
}
- /* Sanitize doorbell address */
- if (!qed_db_rec_sanity(cdev, db_addr, db_data))
- return -EINVAL;
-
/* Obtain hwfn from doorbell address */
p_hwfn = qed_db_rec_find_hwfn(cdev, db_addr);
/* Ring the doorbell of a single doorbell recovery entry */
static void qed_db_recovery_ring(struct qed_hwfn *p_hwfn,
- struct qed_db_recovery_entry *db_entry,
- enum qed_db_rec_exec db_exec)
-{
- if (db_exec != DB_REC_ONCE) {
- /* Print according to width */
- if (db_entry->db_width == DB_REC_WIDTH_32B) {
- DP_VERBOSE(p_hwfn, QED_MSG_SPQ,
- "%s doorbell address %p data %x\n",
- db_exec == DB_REC_DRY_RUN ?
- "would have rung" : "ringing",
- db_entry->db_addr,
- *(u32 *)db_entry->db_data);
- } else {
- DP_VERBOSE(p_hwfn, QED_MSG_SPQ,
- "%s doorbell address %p data %llx\n",
- db_exec == DB_REC_DRY_RUN ?
- "would have rung" : "ringing",
- db_entry->db_addr,
- *(u64 *)(db_entry->db_data));
- }
+ struct qed_db_recovery_entry *db_entry)
+{
+ /* Print according to width */
+ if (db_entry->db_width == DB_REC_WIDTH_32B) {
+ DP_VERBOSE(p_hwfn, QED_MSG_SPQ,
+ "ringing doorbell address %p data %x\n",
+ db_entry->db_addr,
+ *(u32 *)db_entry->db_data);
+ } else {
+ DP_VERBOSE(p_hwfn, QED_MSG_SPQ,
+ "ringing doorbell address %p data %llx\n",
+ db_entry->db_addr,
+ *(u64 *)(db_entry->db_data));
}
/* Sanity */
if (!qed_db_rec_sanity(p_hwfn->cdev, db_entry->db_addr,
- db_entry->db_data))
+ db_entry->db_width, db_entry->db_data))
return;
/* Flush the write combined buffer. Since there are multiple doorbelling
wmb();
/* Ring the doorbell */
- if (db_exec == DB_REC_REAL_DEAL || db_exec == DB_REC_ONCE) {
- if (db_entry->db_width == DB_REC_WIDTH_32B)
- DIRECT_REG_WR(db_entry->db_addr,
- *(u32 *)(db_entry->db_data));
- else
- DIRECT_REG_WR64(db_entry->db_addr,
- *(u64 *)(db_entry->db_data));
- }
+ if (db_entry->db_width == DB_REC_WIDTH_32B)
+ DIRECT_REG_WR(db_entry->db_addr,
+ *(u32 *)(db_entry->db_data));
+ else
+ DIRECT_REG_WR64(db_entry->db_addr,
+ *(u64 *)(db_entry->db_data));
/* Flush the write combined buffer. Next doorbell may come from a
* different entity to the same address...
}
/* Traverse the doorbell recovery entry list and ring all the doorbells */
-void qed_db_recovery_execute(struct qed_hwfn *p_hwfn,
- enum qed_db_rec_exec db_exec)
+void qed_db_recovery_execute(struct qed_hwfn *p_hwfn)
{
struct qed_db_recovery_entry *db_entry = NULL;
- if (db_exec != DB_REC_ONCE) {
- DP_NOTICE(p_hwfn,
- "Executing doorbell recovery. Counter was %d\n",
- p_hwfn->db_recovery_info.db_recovery_counter);
+ DP_NOTICE(p_hwfn, "Executing doorbell recovery. Counter was %d\n",
+ p_hwfn->db_recovery_info.db_recovery_counter);
- /* Track amount of times recovery was executed */
- p_hwfn->db_recovery_info.db_recovery_counter++;
- }
+ /* Track amount of times recovery was executed */
+ p_hwfn->db_recovery_info.db_recovery_counter++;
/* Protect the list */
spin_lock_bh(&p_hwfn->db_recovery_info.lock);
list_for_each_entry(db_entry,
- &p_hwfn->db_recovery_info.list, list_entry) {
- qed_db_recovery_ring(p_hwfn, db_entry, db_exec);
- if (db_exec == DB_REC_ONCE)
- break;
- }
-
+ &p_hwfn->db_recovery_info.list, list_entry)
+ qed_db_recovery_ring(p_hwfn, db_entry);
spin_unlock_bh(&p_hwfn->db_recovery_info.lock);
}
u32 count = QED_DB_REC_COUNT;
u32 usage = 1;
+ /* Flush any pending (e)dpms as they may never arrive */
+ qed_wr(p_hwfn, p_ptt, DORQ_REG_DPM_FORCE_ABORT, 0x1);
+
/* wait for usage to zero or count to run out. This is necessary since
* EDPM doorbell transactions can take multiple 64b cycles, and as such
* can "split" over the pci. Possibly, the doorbell drop can happen with
int qed_db_rec_handler(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
{
- u32 overflow;
+ u32 attn_ovfl, cur_ovfl;
int rc;
- overflow = qed_rd(p_hwfn, p_ptt, DORQ_REG_PF_OVFL_STICKY);
- DP_NOTICE(p_hwfn, "PF Overflow sticky 0x%x\n", overflow);
- if (!overflow) {
- qed_db_recovery_execute(p_hwfn, DB_REC_ONCE);
+ attn_ovfl = test_and_clear_bit(QED_OVERFLOW_BIT,
+ &p_hwfn->db_recovery_info.overflow);
+ cur_ovfl = qed_rd(p_hwfn, p_ptt, DORQ_REG_PF_OVFL_STICKY);
+ if (!cur_ovfl && !attn_ovfl)
return 0;
- }
- if (qed_edpm_enabled(p_hwfn)) {
+ DP_NOTICE(p_hwfn, "PF Overflow sticky: attn %u current %u\n",
+ attn_ovfl, cur_ovfl);
+
+ if (cur_ovfl && !p_hwfn->db_bar_no_edpm) {
rc = qed_db_rec_flush_queue(p_hwfn, p_ptt);
if (rc)
return rc;
}
- /* Flush any pending (e)dpm as they may never arrive */
- qed_wr(p_hwfn, p_ptt, DORQ_REG_DPM_FORCE_ABORT, 0x1);
-
/* Release overflow sticky indication (stop silently dropping everything) */
qed_wr(p_hwfn, p_ptt, DORQ_REG_PF_OVFL_STICKY, 0x0);
/* Repeat all last doorbells (doorbell drop recovery) */
- qed_db_recovery_execute(p_hwfn, DB_REC_REAL_DEAL);
+ qed_db_recovery_execute(p_hwfn);
return 0;
}
-static int qed_dorq_attn_cb(struct qed_hwfn *p_hwfn)
+static void qed_dorq_attn_overflow(struct qed_hwfn *p_hwfn)
{
- u32 int_sts, first_drop_reason, details, address, all_drops_reason;
struct qed_ptt *p_ptt = p_hwfn->p_dpc_ptt;
+ u32 overflow;
int rc;
- int_sts = qed_rd(p_hwfn, p_ptt, DORQ_REG_INT_STS);
- DP_NOTICE(p_hwfn->cdev, "DORQ attention. int_sts was %x\n", int_sts);
+ overflow = qed_rd(p_hwfn, p_ptt, DORQ_REG_PF_OVFL_STICKY);
+ if (!overflow)
+ goto out;
+
+ /* Run PF doorbell recovery in next periodic handler */
+ set_bit(QED_OVERFLOW_BIT, &p_hwfn->db_recovery_info.overflow);
+
+ if (!p_hwfn->db_bar_no_edpm) {
+ rc = qed_db_rec_flush_queue(p_hwfn, p_ptt);
+ if (rc)
+ goto out;
+ }
+
+ qed_wr(p_hwfn, p_ptt, DORQ_REG_PF_OVFL_STICKY, 0x0);
+out:
+ /* Schedule the handler even if overflow was not detected */
+ qed_periodic_db_rec_start(p_hwfn);
+}
+
+static int qed_dorq_attn_int_sts(struct qed_hwfn *p_hwfn)
+{
+ u32 int_sts, first_drop_reason, details, address, all_drops_reason;
+ struct qed_ptt *p_ptt = p_hwfn->p_dpc_ptt;
/* int_sts may be zero since all PFs were interrupted for doorbell
* overflow but another one already handled it. Can abort here. If
* This PF also requires overflow recovery we will be interrupted again.
* The masked almost full indication may also be set. Ignoring.
*/
+ int_sts = qed_rd(p_hwfn, p_ptt, DORQ_REG_INT_STS);
if (!(int_sts & ~DORQ_REG_INT_STS_DORQ_FIFO_AFULL))
return 0;
+ DP_NOTICE(p_hwfn->cdev, "DORQ attention. int_sts was %x\n", int_sts);
+
/* check if db_drop or overflow happened */
if (int_sts & (DORQ_REG_INT_STS_DB_DROP |
DORQ_REG_INT_STS_DORQ_FIFO_OVFL_ERR)) {
GET_FIELD(details, QED_DORQ_ATTENTION_SIZE) * 4,
first_drop_reason, all_drops_reason);
- rc = qed_db_rec_handler(p_hwfn, p_ptt);
- qed_periodic_db_rec_start(p_hwfn);
- if (rc)
- return rc;
-
/* Clear the doorbell drop details and prepare for next drop */
qed_wr(p_hwfn, p_ptt, DORQ_REG_DB_DROP_DETAILS_REL, 0);
return -EINVAL;
}
+static int qed_dorq_attn_cb(struct qed_hwfn *p_hwfn)
+{
+ p_hwfn->db_recovery_info.dorq_attn = true;
+ qed_dorq_attn_overflow(p_hwfn);
+
+ return qed_dorq_attn_int_sts(p_hwfn);
+}
+
+static void qed_dorq_attn_handler(struct qed_hwfn *p_hwfn)
+{
+ if (p_hwfn->db_recovery_info.dorq_attn)
+ goto out;
+
+ /* Call DORQ callback if the attention was missed */
+ qed_dorq_attn_cb(p_hwfn);
+out:
+ p_hwfn->db_recovery_info.dorq_attn = false;
+}
+
/* Instead of major changes to the data-structure, we have a some 'special'
* identifiers for sources that changed meaning between adapters.
*/
}
}
+ /* Handle missed DORQ attention */
+ qed_dorq_attn_handler(p_hwfn);
+
/* Clear IGU indication for the deasserted bits */
DIRECT_REG_WR((u8 __iomem *)p_hwfn->regview +
GTT_BAR0_MAP_REG_IGU_CMD +
/**
* @brief - Doorbell Recovery handler.
- * Run DB_REAL_DEAL doorbell recovery in case of PF overflow
- * (and flush DORQ if needed), otherwise run DB_REC_ONCE.
+ * Run doorbell recovery in case of PF overflow (and flush DORQ if
+ * needed).
*
* @param p_hwfn
* @param p_ptt
}
}
-#define QED_PERIODIC_DB_REC_COUNT 100
+#define QED_PERIODIC_DB_REC_COUNT 10
#define QED_PERIODIC_DB_REC_INTERVAL_MS 100
#define QED_PERIODIC_DB_REC_INTERVAL \
msecs_to_jiffies(QED_PERIODIC_DB_REC_INTERVAL_MS)
p_vfdev->eth_fp_hsi_minor = ETH_HSI_VER_NO_PKT_LEN_TUNN;
} else {
DP_INFO(p_hwfn,
- "VF[%d] needs fastpath HSI %02x.%02x, which is incompatible with loaded FW's faspath HSI %02x.%02x\n",
+ "VF[%d] needs fastpath HSI %02x.%02x, which is incompatible with loaded FW's fastpath HSI %02x.%02x\n",
vf->abs_vf_id,
req->vfdev_info.eth_fp_hsi_major,
req->vfdev_info.eth_fp_hsi_minor,
txq->tx_db.data.bd_prod =
cpu_to_le16(qed_chain_get_prod_idx(&txq->tx_pbl));
- if (!skb->xmit_more || netif_xmit_stopped(netdev_txq))
+ if (!netdev_xmit_more() || netif_xmit_stopped(netdev_txq))
qede_update_tx_producer(txq);
if (unlikely(qed_chain_get_elem_left(&txq->tx_pbl)
< (MAX_SKB_FRAGS + 1))) {
- if (skb->xmit_more)
+ if (netdev_xmit_more())
qede_update_tx_producer(txq);
netif_tx_stop_queue(netdev_txq);
ptp->clock = ptp_clock_register(&ptp->clock_info, &edev->pdev->dev);
if (IS_ERR(ptp->clock)) {
- rc = -EINVAL;
DP_ERR(edev, "PTP clock registration failed\n");
+ qede_ptp_disable(edev);
+ rc = -EINVAL;
goto err2;
}
return 0;
-err2:
- qede_ptp_disable(edev);
- ptp->clock = NULL;
err1:
kfree(ptp);
+err2:
edev->ptp = NULL;
return rc;
u16 board_type;
u16 supported_type;
- u16 link_speed;
+ u32 link_speed;
u16 link_duplex;
u16 link_autoneg;
u16 module_type;
skb_tx_timestamp(skb);
/* Trigger the MAC to check the TX descriptor */
- if (!skb->xmit_more || netif_queue_stopped(dev))
+ if (!netdev_xmit_more() || netif_queue_stopped(dev))
iowrite16(TM2TX, ioaddr + MTPR);
lp->tx_insert_ptr = descptr->vndescp;
#include <linux/pm_runtime.h>
#include <linux/firmware.h>
#include <linux/prefetch.h>
+#include <linux/pci-aspm.h>
#include <linux/ipv6.h>
#include <net/ip6_checksum.h>
PCIDAC = (1 << 4),
PCIMulRW = (1 << 3),
#define INTT_MASK GENMASK(1, 0)
- INTT_0 = 0x0000, // 8168
- INTT_1 = 0x0001, // 8168
- INTT_2 = 0x0002, // 8168
- INTT_3 = 0x0003, // 8168
/* rtl8169_PHYstatus */
TBI_Enable = 0x80,
u32 ocp_base;
};
+typedef void (*rtl_generic_fct)(struct rtl8169_private *tp);
+
MODULE_AUTHOR("Realtek and the Linux r8169 crew <netdev@vger.kernel.org>");
MODULE_DESCRIPTION("RealTek RTL-8169 Gigabit Ethernet driver");
module_param_named(debug, debug.msg_enable, int, 0);
static void rtl_hw_phy_config(struct net_device *dev)
{
+ static const rtl_generic_fct phy_configs[] = {
+ /* PCI devices. */
+ [RTL_GIGA_MAC_VER_01] = NULL,
+ [RTL_GIGA_MAC_VER_02] = rtl8169s_hw_phy_config,
+ [RTL_GIGA_MAC_VER_03] = rtl8169s_hw_phy_config,
+ [RTL_GIGA_MAC_VER_04] = rtl8169sb_hw_phy_config,
+ [RTL_GIGA_MAC_VER_05] = rtl8169scd_hw_phy_config,
+ [RTL_GIGA_MAC_VER_06] = rtl8169sce_hw_phy_config,
+ /* PCI-E devices. */
+ [RTL_GIGA_MAC_VER_07] = rtl8102e_hw_phy_config,
+ [RTL_GIGA_MAC_VER_08] = rtl8102e_hw_phy_config,
+ [RTL_GIGA_MAC_VER_09] = rtl8102e_hw_phy_config,
+ [RTL_GIGA_MAC_VER_10] = NULL,
+ [RTL_GIGA_MAC_VER_11] = rtl8168bb_hw_phy_config,
+ [RTL_GIGA_MAC_VER_12] = rtl8168bef_hw_phy_config,
+ [RTL_GIGA_MAC_VER_13] = NULL,
+ [RTL_GIGA_MAC_VER_14] = NULL,
+ [RTL_GIGA_MAC_VER_15] = NULL,
+ [RTL_GIGA_MAC_VER_16] = NULL,
+ [RTL_GIGA_MAC_VER_17] = rtl8168bef_hw_phy_config,
+ [RTL_GIGA_MAC_VER_18] = rtl8168cp_1_hw_phy_config,
+ [RTL_GIGA_MAC_VER_19] = rtl8168c_1_hw_phy_config,
+ [RTL_GIGA_MAC_VER_20] = rtl8168c_2_hw_phy_config,
+ [RTL_GIGA_MAC_VER_21] = rtl8168c_3_hw_phy_config,
+ [RTL_GIGA_MAC_VER_22] = rtl8168c_4_hw_phy_config,
+ [RTL_GIGA_MAC_VER_23] = rtl8168cp_2_hw_phy_config,
+ [RTL_GIGA_MAC_VER_24] = rtl8168cp_2_hw_phy_config,
+ [RTL_GIGA_MAC_VER_25] = rtl8168d_1_hw_phy_config,
+ [RTL_GIGA_MAC_VER_26] = rtl8168d_2_hw_phy_config,
+ [RTL_GIGA_MAC_VER_27] = rtl8168d_3_hw_phy_config,
+ [RTL_GIGA_MAC_VER_28] = rtl8168d_4_hw_phy_config,
+ [RTL_GIGA_MAC_VER_29] = rtl8105e_hw_phy_config,
+ [RTL_GIGA_MAC_VER_30] = rtl8105e_hw_phy_config,
+ [RTL_GIGA_MAC_VER_31] = NULL,
+ [RTL_GIGA_MAC_VER_32] = rtl8168e_1_hw_phy_config,
+ [RTL_GIGA_MAC_VER_33] = rtl8168e_1_hw_phy_config,
+ [RTL_GIGA_MAC_VER_34] = rtl8168e_2_hw_phy_config,
+ [RTL_GIGA_MAC_VER_35] = rtl8168f_1_hw_phy_config,
+ [RTL_GIGA_MAC_VER_36] = rtl8168f_2_hw_phy_config,
+ [RTL_GIGA_MAC_VER_37] = rtl8402_hw_phy_config,
+ [RTL_GIGA_MAC_VER_38] = rtl8411_hw_phy_config,
+ [RTL_GIGA_MAC_VER_39] = rtl8106e_hw_phy_config,
+ [RTL_GIGA_MAC_VER_40] = rtl8168g_1_hw_phy_config,
+ [RTL_GIGA_MAC_VER_41] = NULL,
+ [RTL_GIGA_MAC_VER_42] = rtl8168g_2_hw_phy_config,
+ [RTL_GIGA_MAC_VER_43] = rtl8168g_2_hw_phy_config,
+ [RTL_GIGA_MAC_VER_44] = rtl8168g_2_hw_phy_config,
+ [RTL_GIGA_MAC_VER_45] = rtl8168h_1_hw_phy_config,
+ [RTL_GIGA_MAC_VER_46] = rtl8168h_2_hw_phy_config,
+ [RTL_GIGA_MAC_VER_47] = rtl8168h_1_hw_phy_config,
+ [RTL_GIGA_MAC_VER_48] = rtl8168h_2_hw_phy_config,
+ [RTL_GIGA_MAC_VER_49] = rtl8168ep_1_hw_phy_config,
+ [RTL_GIGA_MAC_VER_50] = rtl8168ep_2_hw_phy_config,
+ [RTL_GIGA_MAC_VER_51] = rtl8168ep_2_hw_phy_config,
+ };
struct rtl8169_private *tp = netdev_priv(dev);
- switch (tp->mac_version) {
- case RTL_GIGA_MAC_VER_01:
- break;
- case RTL_GIGA_MAC_VER_02:
- case RTL_GIGA_MAC_VER_03:
- rtl8169s_hw_phy_config(tp);
- break;
- case RTL_GIGA_MAC_VER_04:
- rtl8169sb_hw_phy_config(tp);
- break;
- case RTL_GIGA_MAC_VER_05:
- rtl8169scd_hw_phy_config(tp);
- break;
- case RTL_GIGA_MAC_VER_06:
- rtl8169sce_hw_phy_config(tp);
- break;
- case RTL_GIGA_MAC_VER_07:
- case RTL_GIGA_MAC_VER_08:
- case RTL_GIGA_MAC_VER_09:
- rtl8102e_hw_phy_config(tp);
- break;
- case RTL_GIGA_MAC_VER_11:
- rtl8168bb_hw_phy_config(tp);
- break;
- case RTL_GIGA_MAC_VER_12:
- rtl8168bef_hw_phy_config(tp);
- break;
- case RTL_GIGA_MAC_VER_17:
- rtl8168bef_hw_phy_config(tp);
- break;
- case RTL_GIGA_MAC_VER_18:
- rtl8168cp_1_hw_phy_config(tp);
- break;
- case RTL_GIGA_MAC_VER_19:
- rtl8168c_1_hw_phy_config(tp);
- break;
- case RTL_GIGA_MAC_VER_20:
- rtl8168c_2_hw_phy_config(tp);
- break;
- case RTL_GIGA_MAC_VER_21:
- rtl8168c_3_hw_phy_config(tp);
- break;
- case RTL_GIGA_MAC_VER_22:
- rtl8168c_4_hw_phy_config(tp);
- break;
- case RTL_GIGA_MAC_VER_23:
- case RTL_GIGA_MAC_VER_24:
- rtl8168cp_2_hw_phy_config(tp);
- break;
- case RTL_GIGA_MAC_VER_25:
- rtl8168d_1_hw_phy_config(tp);
- break;
- case RTL_GIGA_MAC_VER_26:
- rtl8168d_2_hw_phy_config(tp);
- break;
- case RTL_GIGA_MAC_VER_27:
- rtl8168d_3_hw_phy_config(tp);
- break;
- case RTL_GIGA_MAC_VER_28:
- rtl8168d_4_hw_phy_config(tp);
- break;
- case RTL_GIGA_MAC_VER_29:
- case RTL_GIGA_MAC_VER_30:
- rtl8105e_hw_phy_config(tp);
- break;
- case RTL_GIGA_MAC_VER_31:
- /* None. */
- break;
- case RTL_GIGA_MAC_VER_32:
- case RTL_GIGA_MAC_VER_33:
- rtl8168e_1_hw_phy_config(tp);
- break;
- case RTL_GIGA_MAC_VER_34:
- rtl8168e_2_hw_phy_config(tp);
- break;
- case RTL_GIGA_MAC_VER_35:
- rtl8168f_1_hw_phy_config(tp);
- break;
- case RTL_GIGA_MAC_VER_36:
- rtl8168f_2_hw_phy_config(tp);
- break;
-
- case RTL_GIGA_MAC_VER_37:
- rtl8402_hw_phy_config(tp);
- break;
-
- case RTL_GIGA_MAC_VER_38:
- rtl8411_hw_phy_config(tp);
- break;
-
- case RTL_GIGA_MAC_VER_39:
- rtl8106e_hw_phy_config(tp);
- break;
-
- case RTL_GIGA_MAC_VER_40:
- rtl8168g_1_hw_phy_config(tp);
- break;
- case RTL_GIGA_MAC_VER_42:
- case RTL_GIGA_MAC_VER_43:
- case RTL_GIGA_MAC_VER_44:
- rtl8168g_2_hw_phy_config(tp);
- break;
- case RTL_GIGA_MAC_VER_45:
- case RTL_GIGA_MAC_VER_47:
- rtl8168h_1_hw_phy_config(tp);
- break;
- case RTL_GIGA_MAC_VER_46:
- case RTL_GIGA_MAC_VER_48:
- rtl8168h_2_hw_phy_config(tp);
- break;
-
- case RTL_GIGA_MAC_VER_49:
- rtl8168ep_1_hw_phy_config(tp);
- break;
- case RTL_GIGA_MAC_VER_50:
- case RTL_GIGA_MAC_VER_51:
- rtl8168ep_2_hw_phy_config(tp);
- break;
-
- case RTL_GIGA_MAC_VER_41:
- default:
- break;
- }
+ if (phy_configs[tp->mac_version])
+ phy_configs[tp->mac_version](tp);
}
static void rtl_schedule_task(struct rtl8169_private *tp, enum rtl_flag flag)
rtl_set_rx_tx_desc_registers(tp);
rtl_lock_config_regs(tp);
+ /* disable interrupt coalescing */
+ RTL_W16(tp, IntrMitigate, 0x0000);
/* Initially a 10 us delay. Turned it into a PCI commit. - FR */
RTL_R8(tp, IntrMask);
RTL_W8(tp, ChipCmd, CmdTxEnb | CmdRxEnb);
rtl8169_set_magic_reg(tp, tp->mac_version);
- /*
- * Undocumented corner. Supposedly:
- * (TxTimer << 12) | (TxPackets << 8) | (RxTimer << 4) | RxPackets
- */
- RTL_W16(tp, IntrMitigate, 0x0000);
-
RTL_W32(tp, RxMissed, 0);
}
rtl_hw_aspm_clkreq_enable(tp, true);
}
-static void rtl_hw_start_8168(struct rtl8169_private *tp)
-{
- RTL_W8(tp, MaxTxPacketSize, TxPacketMax);
-
- tp->cp_cmd &= ~INTT_MASK;
- tp->cp_cmd |= PktCntrDisable | INTT_1;
- RTL_W16(tp, CPlusCmd, tp->cp_cmd);
-
- RTL_W16(tp, IntrMitigate, 0x5151);
-
- /* Work around for RxFIFO overflow. */
- if (tp->mac_version == RTL_GIGA_MAC_VER_11) {
- tp->irq_mask |= RxFIFOOver;
- tp->irq_mask &= ~RxOverflow;
- }
-
- switch (tp->mac_version) {
- case RTL_GIGA_MAC_VER_11:
- rtl_hw_start_8168bb(tp);
- break;
-
- case RTL_GIGA_MAC_VER_12:
- case RTL_GIGA_MAC_VER_17:
- rtl_hw_start_8168bef(tp);
- break;
-
- case RTL_GIGA_MAC_VER_18:
- rtl_hw_start_8168cp_1(tp);
- break;
-
- case RTL_GIGA_MAC_VER_19:
- rtl_hw_start_8168c_1(tp);
- break;
-
- case RTL_GIGA_MAC_VER_20:
- rtl_hw_start_8168c_2(tp);
- break;
-
- case RTL_GIGA_MAC_VER_21:
- rtl_hw_start_8168c_3(tp);
- break;
-
- case RTL_GIGA_MAC_VER_22:
- rtl_hw_start_8168c_4(tp);
- break;
-
- case RTL_GIGA_MAC_VER_23:
- rtl_hw_start_8168cp_2(tp);
- break;
-
- case RTL_GIGA_MAC_VER_24:
- rtl_hw_start_8168cp_3(tp);
- break;
-
- case RTL_GIGA_MAC_VER_25:
- case RTL_GIGA_MAC_VER_26:
- case RTL_GIGA_MAC_VER_27:
- rtl_hw_start_8168d(tp);
- break;
-
- case RTL_GIGA_MAC_VER_28:
- rtl_hw_start_8168d_4(tp);
- break;
-
- case RTL_GIGA_MAC_VER_31:
- rtl_hw_start_8168dp(tp);
- break;
-
- case RTL_GIGA_MAC_VER_32:
- case RTL_GIGA_MAC_VER_33:
- rtl_hw_start_8168e_1(tp);
- break;
- case RTL_GIGA_MAC_VER_34:
- rtl_hw_start_8168e_2(tp);
- break;
-
- case RTL_GIGA_MAC_VER_35:
- case RTL_GIGA_MAC_VER_36:
- rtl_hw_start_8168f_1(tp);
- break;
-
- case RTL_GIGA_MAC_VER_38:
- rtl_hw_start_8411(tp);
- break;
-
- case RTL_GIGA_MAC_VER_40:
- case RTL_GIGA_MAC_VER_41:
- rtl_hw_start_8168g_1(tp);
- break;
- case RTL_GIGA_MAC_VER_42:
- rtl_hw_start_8168g_2(tp);
- break;
-
- case RTL_GIGA_MAC_VER_44:
- rtl_hw_start_8411_2(tp);
- break;
-
- case RTL_GIGA_MAC_VER_45:
- case RTL_GIGA_MAC_VER_46:
- rtl_hw_start_8168h_1(tp);
- break;
-
- case RTL_GIGA_MAC_VER_49:
- rtl_hw_start_8168ep_1(tp);
- break;
-
- case RTL_GIGA_MAC_VER_50:
- rtl_hw_start_8168ep_2(tp);
- break;
-
- case RTL_GIGA_MAC_VER_51:
- rtl_hw_start_8168ep_3(tp);
- break;
-
- default:
- netif_err(tp, drv, tp->dev,
- "unknown chipset (mac_version = %d)\n",
- tp->mac_version);
- break;
- }
-}
-
static void rtl_hw_start_8102e_1(struct rtl8169_private *tp)
{
static const struct ephy_info e_info_8102e_1[] = {
rtl_hw_aspm_clkreq_enable(tp, true);
}
+static void rtl_hw_config(struct rtl8169_private *tp)
+{
+ static const rtl_generic_fct hw_configs[] = {
+ [RTL_GIGA_MAC_VER_07] = rtl_hw_start_8102e_1,
+ [RTL_GIGA_MAC_VER_08] = rtl_hw_start_8102e_3,
+ [RTL_GIGA_MAC_VER_09] = rtl_hw_start_8102e_2,
+ [RTL_GIGA_MAC_VER_10] = NULL,
+ [RTL_GIGA_MAC_VER_11] = rtl_hw_start_8168bb,
+ [RTL_GIGA_MAC_VER_12] = rtl_hw_start_8168bef,
+ [RTL_GIGA_MAC_VER_13] = NULL,
+ [RTL_GIGA_MAC_VER_14] = NULL,
+ [RTL_GIGA_MAC_VER_15] = NULL,
+ [RTL_GIGA_MAC_VER_16] = NULL,
+ [RTL_GIGA_MAC_VER_17] = rtl_hw_start_8168bef,
+ [RTL_GIGA_MAC_VER_18] = rtl_hw_start_8168cp_1,
+ [RTL_GIGA_MAC_VER_19] = rtl_hw_start_8168c_1,
+ [RTL_GIGA_MAC_VER_20] = rtl_hw_start_8168c_2,
+ [RTL_GIGA_MAC_VER_21] = rtl_hw_start_8168c_3,
+ [RTL_GIGA_MAC_VER_22] = rtl_hw_start_8168c_4,
+ [RTL_GIGA_MAC_VER_23] = rtl_hw_start_8168cp_2,
+ [RTL_GIGA_MAC_VER_24] = rtl_hw_start_8168cp_3,
+ [RTL_GIGA_MAC_VER_25] = rtl_hw_start_8168d,
+ [RTL_GIGA_MAC_VER_26] = rtl_hw_start_8168d,
+ [RTL_GIGA_MAC_VER_27] = rtl_hw_start_8168d,
+ [RTL_GIGA_MAC_VER_28] = rtl_hw_start_8168d_4,
+ [RTL_GIGA_MAC_VER_29] = rtl_hw_start_8105e_1,
+ [RTL_GIGA_MAC_VER_30] = rtl_hw_start_8105e_2,
+ [RTL_GIGA_MAC_VER_31] = rtl_hw_start_8168dp,
+ [RTL_GIGA_MAC_VER_32] = rtl_hw_start_8168e_1,
+ [RTL_GIGA_MAC_VER_33] = rtl_hw_start_8168e_1,
+ [RTL_GIGA_MAC_VER_34] = rtl_hw_start_8168e_2,
+ [RTL_GIGA_MAC_VER_35] = rtl_hw_start_8168f_1,
+ [RTL_GIGA_MAC_VER_36] = rtl_hw_start_8168f_1,
+ [RTL_GIGA_MAC_VER_37] = rtl_hw_start_8402,
+ [RTL_GIGA_MAC_VER_38] = rtl_hw_start_8411,
+ [RTL_GIGA_MAC_VER_39] = rtl_hw_start_8106,
+ [RTL_GIGA_MAC_VER_40] = rtl_hw_start_8168g_1,
+ [RTL_GIGA_MAC_VER_41] = rtl_hw_start_8168g_1,
+ [RTL_GIGA_MAC_VER_42] = rtl_hw_start_8168g_2,
+ [RTL_GIGA_MAC_VER_43] = rtl_hw_start_8168g_2,
+ [RTL_GIGA_MAC_VER_44] = rtl_hw_start_8411_2,
+ [RTL_GIGA_MAC_VER_45] = rtl_hw_start_8168h_1,
+ [RTL_GIGA_MAC_VER_46] = rtl_hw_start_8168h_1,
+ [RTL_GIGA_MAC_VER_47] = rtl_hw_start_8168h_1,
+ [RTL_GIGA_MAC_VER_48] = rtl_hw_start_8168h_1,
+ [RTL_GIGA_MAC_VER_49] = rtl_hw_start_8168ep_1,
+ [RTL_GIGA_MAC_VER_50] = rtl_hw_start_8168ep_2,
+ [RTL_GIGA_MAC_VER_51] = rtl_hw_start_8168ep_3,
+ };
+
+ if (hw_configs[tp->mac_version])
+ hw_configs[tp->mac_version](tp);
+}
+
+static void rtl_hw_start_8168(struct rtl8169_private *tp)
+{
+ RTL_W8(tp, MaxTxPacketSize, TxPacketMax);
+
+ /* Workaround for RxFIFO overflow. */
+ if (tp->mac_version == RTL_GIGA_MAC_VER_11) {
+ tp->irq_mask |= RxFIFOOver;
+ tp->irq_mask &= ~RxOverflow;
+ }
+
+ rtl_hw_config(tp);
+}
+
static void rtl_hw_start_8101(struct rtl8169_private *tp)
{
if (tp->mac_version >= RTL_GIGA_MAC_VER_30)
tp->cp_cmd &= CPCMD_QUIRK_MASK;
RTL_W16(tp, CPlusCmd, tp->cp_cmd);
- switch (tp->mac_version) {
- case RTL_GIGA_MAC_VER_07:
- rtl_hw_start_8102e_1(tp);
- break;
-
- case RTL_GIGA_MAC_VER_08:
- rtl_hw_start_8102e_3(tp);
- break;
-
- case RTL_GIGA_MAC_VER_09:
- rtl_hw_start_8102e_2(tp);
- break;
-
- case RTL_GIGA_MAC_VER_29:
- rtl_hw_start_8105e_1(tp);
- break;
- case RTL_GIGA_MAC_VER_30:
- rtl_hw_start_8105e_2(tp);
- break;
-
- case RTL_GIGA_MAC_VER_37:
- rtl_hw_start_8402(tp);
- break;
-
- case RTL_GIGA_MAC_VER_39:
- rtl_hw_start_8106(tp);
- break;
- case RTL_GIGA_MAC_VER_43:
- rtl_hw_start_8168g_2(tp);
- break;
- case RTL_GIGA_MAC_VER_47:
- case RTL_GIGA_MAC_VER_48:
- rtl_hw_start_8168h_1(tp);
- break;
- }
-
- RTL_W16(tp, IntrMitigate, 0x0000);
+ rtl_hw_config(tp);
}
static int rtl8169_change_mtu(struct net_device *dev, int new_mtu)
set_bit(RTL_FLAG_TASK_RESET_PENDING, tp->wk.flags);
}
- if (status & (RTL_EVENT_NAPI | LinkChg)) {
- rtl_irq_disable(tp);
- napi_schedule_irqoff(&tp->napi);
- }
+ rtl_irq_disable(tp);
+ napi_schedule_irqoff(&tp->napi);
out:
rtl_ack_events(tp, status);
if (rc)
return rc;
+ /* Disable ASPM completely as that cause random device stop working
+ * problems as well as full system hangs for some PCIe devices users.
+ */
+ pci_disable_link_state(pdev, PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1);
+
/* enable device (incl. PCI PM wakeup and hotplug setup) */
rc = pcim_enable_device(pdev);
if (rc < 0) {
switch (event) {
case FIB_EVENT_ENTRY_ADD: /* fall through */
case FIB_EVENT_ENTRY_DEL:
+ if (info->family == AF_INET) {
+ struct fib_entry_notifier_info *fen_info = ptr;
+
+ if (fen_info->fi->fib_nh_is_v6) {
+ NL_SET_ERR_MSG_MOD(info->extack, "IPv6 gateway with IPv4 route is not supported");
+ return notifier_from_errno(-EINVAL);
+ }
+ }
+
memcpy(&fib_work->fen_info, ptr, sizeof(fib_work->fen_info));
/* Take referece on fib_info to prevent it from being
* freed while work is queued. Release it afterwards.
netdev_tx_sent_queue(tx_queue->core_txq, skb_len);
/* Pass off to hardware */
- if (!skb->xmit_more || netif_xmit_stopped(tx_queue->core_txq)) {
+ if (!netdev_xmit_more() || netif_xmit_stopped(tx_queue->core_txq)) {
struct ef4_tx_queue *txq2 = ef4_tx_queue_partner(tx_queue);
/* There could be packets left on the partner queue if those
ef4_nic_push_buffers(tx_queue);
} else {
- tx_queue->xmit_more_available = skb->xmit_more;
+ tx_queue->xmit_more_available = netdev_xmit_more();
}
tx_queue->tx_packets++;
next = skb->next;
skb->next = NULL;
- if (next)
- skb->xmit_more = true;
efx_enqueue_skb(tx_queue, skb);
skb = next;
}
netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
{
unsigned int old_insert_count = tx_queue->insert_count;
- bool xmit_more = skb->xmit_more;
+ bool xmit_more = netdev_xmit_more();
bool data_mapped = false;
unsigned int segments;
unsigned int skb_len;
if (rc)
goto err;
#ifdef EFX_USE_PIO
- } else if (skb_len <= efx_piobuf_size && !skb->xmit_more &&
+ } else if (skb_len <= efx_piobuf_size && !xmit_more &&
efx_nic_may_tx_pio(tx_queue)) {
/* Use PIO for short packets with an empty queue. */
if (efx_enqueue_skb_pio(tx_queue, skb))
if (__netdev_tx_sent_queue(tx_queue->core_txq, skb_len, xmit_more)) {
struct efx_tx_queue *txq2 = efx_tx_queue_partner(tx_queue);
- /* There could be packets left on the partner queue if those
- * SKBs had skb->xmit_more set. If we do not push those they
+ /* There could be packets left on the partner queue if
+ * xmit_more was set. If we do not push those they
* could be left for a long time and cause a netdev watchdog.
*/
if (txq2->xmit_more_available)
efx_nic_push_buffers(tx_queue);
} else {
- tx_queue->xmit_more_available = skb->xmit_more;
+ tx_queue->xmit_more_available = xmit_more;
}
if (segments) {
/* Specific functions used for Ring mode */
/* Enhanced descriptors */
-static inline void ehn_desc_rx_set_on_ring(struct dma_desc *p, int end)
+static inline void ehn_desc_rx_set_on_ring(struct dma_desc *p, int end,
+ int bfsize)
{
- p->des1 |= cpu_to_le32((BUF_SIZE_8KiB
- << ERDES1_BUFFER2_SIZE_SHIFT)
- & ERDES1_BUFFER2_SIZE_MASK);
+ if (bfsize == BUF_SIZE_16KiB)
+ p->des1 |= cpu_to_le32((BUF_SIZE_8KiB
+ << ERDES1_BUFFER2_SIZE_SHIFT)
+ & ERDES1_BUFFER2_SIZE_MASK);
if (end)
p->des1 |= cpu_to_le32(ERDES1_END_RING);
}
/* Normal descriptors */
-static inline void ndesc_rx_set_on_ring(struct dma_desc *p, int end)
+static inline void ndesc_rx_set_on_ring(struct dma_desc *p, int end, int bfsize)
{
- p->des1 |= cpu_to_le32(((BUF_SIZE_2KiB - 1)
- << RDES1_BUFFER2_SIZE_SHIFT)
- & RDES1_BUFFER2_SIZE_MASK);
+ if (bfsize >= BUF_SIZE_2KiB) {
+ int bfsize2;
+
+ bfsize2 = min(bfsize - BUF_SIZE_2KiB + 1, BUF_SIZE_2KiB - 1);
+ p->des1 |= cpu_to_le32((bfsize2 << RDES1_BUFFER2_SIZE_SHIFT)
+ & RDES1_BUFFER2_SIZE_MASK);
+ }
if (end)
p->des1 |= cpu_to_le32(RDES1_END_RING);
}
static void dwmac4_rd_init_rx_desc(struct dma_desc *p, int disable_rx_ic,
- int mode, int end)
+ int mode, int end, int bfsize)
{
dwmac4_set_rx_owner(p, disable_rx_ic);
}
#define XGMAC_RSF BIT(5)
#define XGMAC_RTC GENMASK(1, 0)
#define XGMAC_RTC_SHIFT 0
+#define XGMAC_MTL_RXQ_FLOW_CONTROL(x) (0x00001150 + (0x80 * (x)))
+#define XGMAC_RFD GENMASK(31, 17)
+#define XGMAC_RFD_SHIFT 17
+#define XGMAC_RFA GENMASK(15, 1)
+#define XGMAC_RFA_SHIFT 1
#define XGMAC_MTL_QINTEN(x) (0x00001170 + (0x80 * (x)))
#define XGMAC_RXOIE BIT(16)
#define XGMAC_MTL_QINT_STATUS(x) (0x00001174 + (0x80 * (x)))
}
static void dwxgmac2_init_rx_desc(struct dma_desc *p, int disable_rx_ic,
- int mode, int end)
+ int mode, int end, int bfsize)
{
dwxgmac2_set_rx_owner(p, disable_rx_ic);
}
value &= ~XGMAC_RQS;
value |= (rqs << XGMAC_RQS_SHIFT) & XGMAC_RQS;
+ if ((fifosz >= 4096) && (qmode != MTL_QUEUE_AVB)) {
+ u32 flow = readl(ioaddr + XGMAC_MTL_RXQ_FLOW_CONTROL(channel));
+ unsigned int rfd, rfa;
+
+ value |= XGMAC_EHFC;
+
+ /* Set Threshold for Activating Flow Control to min 2 frames,
+ * i.e. 1500 * 2 = 3000 bytes.
+ *
+ * Set Threshold for Deactivating Flow Control to min 1 frame,
+ * i.e. 1500 bytes.
+ */
+ switch (fifosz) {
+ case 4096:
+ /* This violates the above formula because of FIFO size
+ * limit therefore overflow may occur in spite of this.
+ */
+ rfd = 0x03; /* Full-2.5K */
+ rfa = 0x01; /* Full-1.5K */
+ break;
+
+ case 8192:
+ rfd = 0x06; /* Full-4K */
+ rfa = 0x0a; /* Full-6K */
+ break;
+
+ case 16384:
+ rfd = 0x06; /* Full-4K */
+ rfa = 0x12; /* Full-10K */
+ break;
+
+ default:
+ rfd = 0x06; /* Full-4K */
+ rfa = 0x1e; /* Full-16K */
+ break;
+ }
+
+ flow &= ~XGMAC_RFD;
+ flow |= rfd << XGMAC_RFD_SHIFT;
+
+ flow &= ~XGMAC_RFA;
+ flow |= rfa << XGMAC_RFA_SHIFT;
+
+ writel(flow, ioaddr + XGMAC_MTL_RXQ_FLOW_CONTROL(channel));
+ }
+
writel(value, ioaddr + XGMAC_MTL_RXQ_OPMODE(channel));
/* Enable MTL RX overflow */
if (unlikely(rdes0 & RDES0_OWN))
return dma_own;
+ if (unlikely(!(rdes0 & RDES0_LAST_DESCRIPTOR))) {
+ stats->rx_length_errors++;
+ return discard_frame;
+ }
+
if (unlikely(rdes0 & RDES0_ERROR_SUMMARY)) {
if (unlikely(rdes0 & RDES0_DESCRIPTOR_ERROR)) {
x->rx_desc++;
* It doesn't match with the information reported into the databook.
* At any rate, we need to understand if the CSUM hw computation is ok
* and report this info to the upper layers. */
- ret = enh_desc_coe_rdes0(!!(rdes0 & RDES0_IPC_CSUM_ERROR),
- !!(rdes0 & RDES0_FRAME_TYPE),
- !!(rdes0 & ERDES0_RX_MAC_ADDR));
+ if (likely(ret == good_frame))
+ ret = enh_desc_coe_rdes0(!!(rdes0 & RDES0_IPC_CSUM_ERROR),
+ !!(rdes0 & RDES0_FRAME_TYPE),
+ !!(rdes0 & ERDES0_RX_MAC_ADDR));
if (unlikely(rdes0 & RDES0_DRIBBLING))
x->dribbling_bit++;
}
static void enh_desc_init_rx_desc(struct dma_desc *p, int disable_rx_ic,
- int mode, int end)
+ int mode, int end, int bfsize)
{
+ int bfsize1;
+
p->des0 |= cpu_to_le32(RDES0_OWN);
- p->des1 |= cpu_to_le32(BUF_SIZE_8KiB & ERDES1_BUFFER1_SIZE_MASK);
+
+ bfsize1 = min(bfsize, BUF_SIZE_8KiB);
+ p->des1 |= cpu_to_le32(bfsize1 & ERDES1_BUFFER1_SIZE_MASK);
if (mode == STMMAC_CHAIN_MODE)
ehn_desc_rx_set_on_chain(p);
else
- ehn_desc_rx_set_on_ring(p, end);
+ ehn_desc_rx_set_on_ring(p, end, bfsize);
if (disable_rx_ic)
p->des1 |= cpu_to_le32(ERDES1_DISABLE_IC);
struct stmmac_desc_ops {
/* DMA RX descriptor ring initialization */
void (*init_rx_desc)(struct dma_desc *p, int disable_rx_ic, int mode,
- int end);
+ int end, int bfsize);
/* DMA TX descriptor ring initialization */
void (*init_tx_desc)(struct dma_desc *p, int mode, int end);
/* Invoked by the xmit function to prepare the tx descriptor */
return dma_own;
if (unlikely(!(rdes0 & RDES0_LAST_DESCRIPTOR))) {
- pr_warn("%s: Oversized frame spanned multiple buffers\n",
- __func__);
stats->rx_length_errors++;
return discard_frame;
}
}
static void ndesc_init_rx_desc(struct dma_desc *p, int disable_rx_ic, int mode,
- int end)
+ int end, int bfsize)
{
+ int bfsize1;
+
p->des0 |= cpu_to_le32(RDES0_OWN);
- p->des1 |= cpu_to_le32((BUF_SIZE_2KiB - 1) & RDES1_BUFFER1_SIZE_MASK);
+
+ bfsize1 = min(bfsize, BUF_SIZE_2KiB - 1);
+ p->des1 |= cpu_to_le32(bfsize & RDES1_BUFFER1_SIZE_MASK);
if (mode == STMMAC_CHAIN_MODE)
ndesc_rx_set_on_chain(p, end);
else
- ndesc_rx_set_on_ring(p, end);
+ ndesc_rx_set_on_ring(p, end, bfsize);
if (disable_rx_ic)
p->des1 |= cpu_to_le32(RDES1_DISABLE_IC);
#define STMMAC_TX_THRESH (DMA_TX_SIZE / 4)
#define STMMAC_RX_THRESH (DMA_RX_SIZE / 4)
-static int flow_ctrl = FLOW_OFF;
+static int flow_ctrl = FLOW_AUTO;
module_param(flow_ctrl, int, 0644);
MODULE_PARM_DESC(flow_ctrl, "Flow control ability [on/off]");
if (priv->extend_desc)
stmmac_init_rx_desc(priv, &rx_q->dma_erx[i].basic,
priv->use_riwt, priv->mode,
- (i == DMA_RX_SIZE - 1));
+ (i == DMA_RX_SIZE - 1),
+ priv->dma_buf_sz);
else
stmmac_init_rx_desc(priv, &rx_q->dma_rx[i],
priv->use_riwt, priv->mode,
- (i == DMA_RX_SIZE - 1));
+ (i == DMA_RX_SIZE - 1),
+ priv->dma_buf_sz);
}
/**
{
struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
struct stmmac_channel *ch = &priv->channel[queue];
- unsigned int entry = rx_q->cur_rx;
+ unsigned int next_entry = rx_q->cur_rx;
int coe = priv->hw->rx_csum;
- unsigned int next_entry;
unsigned int count = 0;
bool xmac;
stmmac_display_ring(priv, rx_head, DMA_RX_SIZE, true);
}
while (count < limit) {
- int status;
+ int entry, status;
struct dma_desc *p;
struct dma_desc *np;
+ entry = next_entry;
+
if (priv->extend_desc)
p = (struct dma_desc *)(rx_q->dma_erx + entry);
else
* ignored
*/
if (frame_len > priv->dma_buf_sz) {
- netdev_err(priv->dev,
- "len %d larger than size (%d)\n",
- frame_len, priv->dma_buf_sz);
+ if (net_ratelimit())
+ netdev_err(priv->dev,
+ "len %d larger than size (%d)\n",
+ frame_len, priv->dma_buf_sz);
priv->dev->stats.rx_length_errors++;
- break;
+ continue;
}
/* ACS is set; GMAC core strips PAD/FCS for IEEE 802.3
dev_warn(priv->device,
"packet dropped\n");
priv->dev->stats.rx_dropped++;
- break;
+ continue;
}
dma_sync_single_for_cpu(priv->device,
} else {
skb = rx_q->rx_skbuff[entry];
if (unlikely(!skb)) {
- netdev_err(priv->dev,
- "%s: Inconsistent Rx chain\n",
- priv->dev->name);
+ if (net_ratelimit())
+ netdev_err(priv->dev,
+ "%s: Inconsistent Rx chain\n",
+ priv->dev->name);
priv->dev->stats.rx_dropped++;
- break;
+ continue;
}
prefetch(skb->data - NET_IP_ALIGN);
rx_q->rx_skbuff[entry] = NULL;
priv->dev->stats.rx_packets++;
priv->dev->stats.rx_bytes += frame_len;
}
- entry = next_entry;
}
stmmac_rx_refill(priv, queue);
smp_wmb();
ring->cur = cur_index + 1;
- if (!pkt_info->skb->xmit_more ||
+ if (!netdev_xmit_more() ||
netif_xmit_stopped(netdev_get_tx_queue(pdata->netdev,
channel->queue_index)))
xlgmac_tx_start_xmit(channel, ring);
static void davinci_mdio_enable(struct davinci_mdio_data *data)
{
/* set enable and clock divider */
- __raw_writel(data->clk_div | CONTROL_ENABLE, &data->regs->control);
+ writel(data->clk_div | CONTROL_ENABLE, &data->regs->control);
}
static int davinci_mdio_reset(struct mii_bus *bus)
msleep(PHY_MAX_ADDR * data->access_time);
/* dump hardware version info */
- ver = __raw_readl(&data->regs->version);
+ ver = readl(&data->regs->version);
dev_info(data->dev,
"davinci mdio revision %d.%d, bus freq %ld\n",
(ver >> 8) & 0xff, ver & 0xff,
goto done;
/* get phy mask from the alive register */
- phy_mask = __raw_readl(&data->regs->alive);
+ phy_mask = readl(&data->regs->alive);
if (phy_mask) {
/* restrict mdio bus to live phys only */
dev_info(data->dev, "detected phy mask %x\n", ~phy_mask);
u32 reg;
while (time_after(timeout, jiffies)) {
- reg = __raw_readl(®s->user[0].access);
+ reg = readl(®s->user[0].access);
if ((reg & USERACCESS_GO) == 0)
return 0;
- reg = __raw_readl(®s->control);
+ reg = readl(®s->control);
if ((reg & CONTROL_IDLE) == 0) {
usleep_range(100, 200);
continue;
return -EAGAIN;
}
- reg = __raw_readl(®s->user[0].access);
+ reg = readl(®s->user[0].access);
if ((reg & USERACCESS_GO) == 0)
return 0;
if (ret < 0)
break;
- __raw_writel(reg, &data->regs->user[0].access);
+ writel(reg, &data->regs->user[0].access);
ret = wait_for_user_access(data);
if (ret == -EAGAIN)
if (ret < 0)
break;
- reg = __raw_readl(&data->regs->user[0].access);
+ reg = readl(&data->regs->user[0].access);
ret = (reg & USERACCESS_ACK) ? (reg & USERACCESS_DATA) : -EIO;
break;
}
if (ret < 0)
break;
- __raw_writel(reg, &data->regs->user[0].access);
+ writel(reg, &data->regs->user[0].access);
ret = wait_for_user_access(data);
if (ret == -EAGAIN)
u32 ctrl;
/* shutdown the scan state machine */
- ctrl = __raw_readl(&data->regs->control);
+ ctrl = readl(&data->regs->control);
ctrl &= ~CONTROL_ENABLE;
- __raw_writel(ctrl, &data->regs->control);
+ writel(ctrl, &data->regs->control);
wait_for_idle(data);
return 0;
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/skbuff.h>
+#include <linux/ethtool.h>
#include <linux/io.h>
#include <linux/slab.h>
#include <linux/of_address.h>
return (bool)*p;
}
+/**
+ * xemaclite_ethtools_get_drvinfo - Get various Axi Emac Lite driver info
+ * @ndev: Pointer to net_device structure
+ * @ed: Pointer to ethtool_drvinfo structure
+ *
+ * This implements ethtool command for getting the driver information.
+ * Issue "ethtool -i ethX" under linux prompt to execute this function.
+ */
+static void xemaclite_ethtools_get_drvinfo(struct net_device *ndev,
+ struct ethtool_drvinfo *ed)
+{
+ strlcpy(ed->driver, DRIVER_NAME, sizeof(ed->driver));
+}
+
+static const struct ethtool_ops xemaclite_ethtool_ops = {
+ .get_drvinfo = xemaclite_ethtools_get_drvinfo,
+ .get_link = ethtool_op_get_link,
+ .get_link_ksettings = phy_ethtool_get_link_ksettings,
+ .set_link_ksettings = phy_ethtool_set_link_ksettings,
+};
+
static const struct net_device_ops xemaclite_netdev_ops;
/**
dev_info(dev, "MAC address is now %pM\n", ndev->dev_addr);
ndev->netdev_ops = &xemaclite_netdev_ops;
+ ndev->ethtool_ops = &xemaclite_ethtool_ops;
ndev->flags &= ~IFF_MULTICAST;
ndev->watchdog_timeo = TX_TIMEOUT;
}
#endif
+/* Ioctl MII Interface */
+static int xemaclite_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
+{
+ if (!dev->phydev || !netif_running(dev))
+ return -EINVAL;
+
+ switch (cmd) {
+ case SIOCGMIIPHY:
+ case SIOCGMIIREG:
+ case SIOCSMIIREG:
+ return phy_mii_ioctl(dev->phydev, rq, cmd);
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
static const struct net_device_ops xemaclite_netdev_ops = {
.ndo_open = xemaclite_open,
.ndo_stop = xemaclite_close,
.ndo_start_xmit = xemaclite_send,
.ndo_set_mac_address = xemaclite_set_mac_address,
.ndo_tx_timeout = xemaclite_tx_timeout,
+ .ndo_do_ioctl = xemaclite_ioctl,
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_poll_controller = xemaclite_poll_controller,
#endif
wait_queue_head_t wait_drain;
bool destroy;
+ bool tx_disable; /* if true, do not wake up queue again */
/* Receive buffer allocated by us but manages by NetVSP */
void *recv_buf;
init_waitqueue_head(&net_device->wait_drain);
net_device->destroy = false;
+ net_device->tx_disable = false;
net_device->max_pkt = RNDIS_MAX_PKT_DEFAULT;
net_device->pkt_align = RNDIS_PKT_ALIGN_DEFAULT;
} else {
struct netdev_queue *txq = netdev_get_tx_queue(ndev, q_idx);
- if (netif_tx_queue_stopped(txq) &&
+ if (netif_tx_queue_stopped(txq) && !net_device->tx_disable &&
(hv_get_avail_to_write_percent(&channel->outbound) >
RING_AVAIL_PERCENT_HIWATER || queue_sends < 1)) {
netif_tx_wake_queue(txq);
} else if (ret == -EAGAIN) {
netif_tx_stop_queue(txq);
ndev_ctx->eth_stats.stop_queue++;
- if (atomic_read(&nvchan->queue_sends) < 1) {
+ if (atomic_read(&nvchan->queue_sends) < 1 &&
+ !net_device->tx_disable) {
netif_tx_wake_queue(txq);
ndev_ctx->eth_stats.wake_queue++;
ret = -ENOSPC;
/* Keep aggregating only if stack says more data is coming
* and not doing mixed modes send and not flow blocked
*/
- xmit_more = skb->xmit_more &&
+ xmit_more = netdev_xmit_more() &&
!packet->cp_partial &&
!netif_xmit_stopped(netdev_get_tx_queue(ndev, packet->q_idx));
rcu_read_unlock();
}
+static void netvsc_tx_enable(struct netvsc_device *nvscdev,
+ struct net_device *ndev)
+{
+ nvscdev->tx_disable = false;
+ virt_wmb(); /* ensure queue wake up mechanism is on */
+
+ netif_tx_wake_all_queues(ndev);
+}
+
static int netvsc_open(struct net_device *net)
{
struct net_device_context *ndev_ctx = netdev_priv(net);
rdev = nvdev->extension;
if (!rdev->link_state) {
netif_carrier_on(net);
- netif_tx_wake_all_queues(net);
+ netvsc_tx_enable(nvdev, net);
}
if (vf_netdev) {
}
}
+static void netvsc_tx_disable(struct netvsc_device *nvscdev,
+ struct net_device *ndev)
+{
+ if (nvscdev) {
+ nvscdev->tx_disable = true;
+ virt_wmb(); /* ensure txq will not wake up after stop */
+ }
+
+ netif_tx_disable(ndev);
+}
+
static int netvsc_close(struct net_device *net)
{
struct net_device_context *net_device_ctx = netdev_priv(net);
struct netvsc_device *nvdev = rtnl_dereference(net_device_ctx->nvdev);
int ret;
- netif_tx_disable(net);
+ netvsc_tx_disable(nvdev, net);
/* No need to close rndis filter if it is removed already */
if (!nvdev)
/* If device was up (receiving) then shutdown */
if (netif_running(ndev)) {
- netif_tx_disable(ndev);
+ netvsc_tx_disable(nvdev, ndev);
ret = rndis_filter_close(nvdev);
if (ret) {
if (rdev->link_state) {
rdev->link_state = false;
netif_carrier_on(net);
- netif_tx_wake_all_queues(net);
+ netvsc_tx_enable(net_device, net);
} else {
notify = true;
}
if (!rdev->link_state) {
rdev->link_state = true;
netif_carrier_off(net);
- netif_tx_stop_all_queues(net);
+ netvsc_tx_disable(net_device, net);
}
kfree(event);
break;
if (!rdev->link_state) {
rdev->link_state = true;
netif_carrier_off(net);
- netif_tx_stop_all_queues(net);
+ netvsc_tx_disable(net_device, net);
event->event = RNDIS_STATUS_MEDIA_CONNECT;
spin_lock_irqsave(&ndev_ctx->lock, flags);
list_add(&event->list, &ndev_ctx->reconfig_events);
return 1;
}
-static int loopback_get_ts_info(struct net_device *netdev,
- struct ethtool_ts_info *ts_info)
-{
- ts_info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
- SOF_TIMESTAMPING_RX_SOFTWARE |
- SOF_TIMESTAMPING_SOFTWARE;
-
- ts_info->phc_index = -1;
-
- return 0;
-};
-
static const struct ethtool_ops loopback_ethtool_ops = {
.get_link = always_on,
- .get_ts_info = loopback_get_ts_info,
+ .get_ts_info = ethtool_op_get_ts_info,
};
static int loopback_dev_init(struct net_device *dev)
return 0;
}
-static int copy_rx_sa_stats(struct sk_buff *skb,
- struct macsec_rx_sa_stats __percpu *pstats)
+static noinline_for_stack int
+copy_rx_sa_stats(struct sk_buff *skb,
+ struct macsec_rx_sa_stats __percpu *pstats)
{
struct macsec_rx_sa_stats sum = {0, };
int cpu;
return 0;
}
-static int copy_rx_sc_stats(struct sk_buff *skb,
- struct pcpu_rx_sc_stats __percpu *pstats)
+static noinline_for_stack int
+copy_rx_sc_stats(struct sk_buff *skb, struct pcpu_rx_sc_stats __percpu *pstats)
{
struct macsec_rx_sc_stats sum = {0, };
int cpu;
return 0;
}
-static int copy_tx_sc_stats(struct sk_buff *skb,
- struct pcpu_tx_sc_stats __percpu *pstats)
+static noinline_for_stack int
+copy_tx_sc_stats(struct sk_buff *skb, struct pcpu_tx_sc_stats __percpu *pstats)
{
struct macsec_tx_sc_stats sum = {0, };
int cpu;
return 0;
}
-static int copy_secy_stats(struct sk_buff *skb,
- struct pcpu_secy_stats __percpu *pstats)
+static noinline_for_stack int
+copy_secy_stats(struct sk_buff *skb, struct pcpu_secy_stats __percpu *pstats)
{
struct macsec_dev_stats sum = {0, };
int cpu;
return 1;
}
-static int dump_secy(struct macsec_secy *secy, struct net_device *dev,
- struct sk_buff *skb, struct netlink_callback *cb)
+static noinline_for_stack int
+dump_secy(struct macsec_secy *secy, struct net_device *dev,
+ struct sk_buff *skb, struct netlink_callback *cb)
{
struct macsec_rx_sc *rx_sc;
struct macsec_tx_sc *tx_sc = &secy->tx_sc;
obj-$(CONFIG_NETDEVSIM) += netdevsim.o
netdevsim-objs := \
- netdev.o \
+ netdev.o devlink.o fib.o sdev.o \
ifeq ($(CONFIG_BPF_SYSCALL),y)
netdevsim-objs += \
bpf.o
endif
-ifneq ($(CONFIG_NET_DEVLINK),)
-netdevsim-objs += devlink.o fib.o
-endif
-
ifneq ($(CONFIG_XFRM_OFFLOAD),)
netdevsim-objs += ipsec.o
endif
bpf_verifier_log_write(env, "[netdevsim] " fmt, ##__VA_ARGS__)
struct nsim_bpf_bound_prog {
- struct netdevsim *ns;
+ struct netdevsim_shared_dev *sdev;
struct bpf_prog *prog;
struct dentry *ddir;
const char *state;
struct nsim_bpf_bound_prog *state;
state = env->prog->aux->offload->dev_priv;
- if (state->ns->bpf_bind_verifier_delay && !insn_idx)
- msleep(state->ns->bpf_bind_verifier_delay);
+ if (state->sdev->bpf_bind_verifier_delay && !insn_idx)
+ msleep(state->sdev->bpf_bind_verifier_delay);
if (insn_idx == env->prog->len - 1)
pr_vlog(env, "Hello from netdevsim!\n");
return 0;
}
-static int nsim_bpf_create_prog(struct netdevsim *ns, struct bpf_prog *prog)
+static int nsim_bpf_create_prog(struct netdevsim_shared_dev *sdev,
+ struct bpf_prog *prog)
{
struct nsim_bpf_bound_prog *state;
char name[16];
if (!state)
return -ENOMEM;
- state->ns = ns;
+ state->sdev = sdev;
state->prog = prog;
state->state = "verify";
/* Program id is not populated yet when we create the state. */
- sprintf(name, "%u", ns->sdev->prog_id_gen++);
- state->ddir = debugfs_create_dir(name, ns->sdev->ddir_bpf_bound_progs);
+ sprintf(name, "%u", sdev->prog_id_gen++);
+ state->ddir = debugfs_create_dir(name, sdev->ddir_bpf_bound_progs);
if (IS_ERR_OR_NULL(state->ddir)) {
kfree(state);
return -ENOMEM;
&state->state, &nsim_bpf_string_fops);
debugfs_create_bool("loaded", 0400, state->ddir, &state->is_loaded);
- list_add_tail(&state->l, &ns->sdev->bpf_bound_progs);
+ list_add_tail(&state->l, &sdev->bpf_bound_progs);
prog->aux->offload->dev_priv = state;
static int nsim_bpf_verifier_prep(struct bpf_prog *prog)
{
- struct netdevsim *ns = bpf_offload_dev_priv(prog->aux->offload->offdev);
+ struct netdevsim_shared_dev *sdev =
+ bpf_offload_dev_priv(prog->aux->offload->offdev);
- if (!ns->bpf_bind_accept)
+ if (!sdev->bpf_bind_accept)
return -EOPNOTSUPP;
- return nsim_bpf_create_prog(ns, prog);
+ return nsim_bpf_create_prog(sdev, prog);
}
static int nsim_bpf_translate(struct bpf_prog *prog)
}
}
-int nsim_bpf_init(struct netdevsim *ns)
+static int nsim_bpf_sdev_init(struct netdevsim_shared_dev *sdev)
{
int err;
- if (ns->sdev->refcnt == 1) {
- INIT_LIST_HEAD(&ns->sdev->bpf_bound_progs);
- INIT_LIST_HEAD(&ns->sdev->bpf_bound_maps);
+ INIT_LIST_HEAD(&sdev->bpf_bound_progs);
+ INIT_LIST_HEAD(&sdev->bpf_bound_maps);
- ns->sdev->ddir_bpf_bound_progs =
- debugfs_create_dir("bpf_bound_progs", ns->sdev->ddir);
- if (IS_ERR_OR_NULL(ns->sdev->ddir_bpf_bound_progs))
- return -ENOMEM;
+ sdev->ddir_bpf_bound_progs =
+ debugfs_create_dir("bpf_bound_progs", sdev->ddir);
+ if (IS_ERR_OR_NULL(sdev->ddir_bpf_bound_progs))
+ return -ENOMEM;
+
+ sdev->bpf_dev = bpf_offload_dev_create(&nsim_bpf_dev_ops, sdev);
+ err = PTR_ERR_OR_ZERO(sdev->bpf_dev);
+ if (err)
+ return err;
- ns->sdev->bpf_dev = bpf_offload_dev_create(&nsim_bpf_dev_ops,
- ns);
- err = PTR_ERR_OR_ZERO(ns->sdev->bpf_dev);
+ sdev->bpf_bind_accept = true;
+ debugfs_create_bool("bpf_bind_accept", 0600, sdev->ddir,
+ &sdev->bpf_bind_accept);
+ debugfs_create_u32("bpf_bind_verifier_delay", 0600, sdev->ddir,
+ &sdev->bpf_bind_verifier_delay);
+ return 0;
+}
+
+static void nsim_bpf_sdev_uninit(struct netdevsim_shared_dev *sdev)
+{
+ WARN_ON(!list_empty(&sdev->bpf_bound_progs));
+ WARN_ON(!list_empty(&sdev->bpf_bound_maps));
+ bpf_offload_dev_destroy(sdev->bpf_dev);
+}
+
+int nsim_bpf_init(struct netdevsim *ns)
+{
+ int err;
+
+ if (ns->sdev->refcnt == 1) {
+ err = nsim_bpf_sdev_init(ns->sdev);
if (err)
return err;
}
err = bpf_offload_dev_netdev_register(ns->sdev->bpf_dev, ns->netdev);
if (err)
- goto err_destroy_bdev;
+ goto err_bpf_sdev_uninit;
debugfs_create_u32("bpf_offloaded_id", 0400, ns->ddir,
&ns->bpf_offloaded_id);
- ns->bpf_bind_accept = true;
- debugfs_create_bool("bpf_bind_accept", 0600, ns->ddir,
- &ns->bpf_bind_accept);
- debugfs_create_u32("bpf_bind_verifier_delay", 0600, ns->ddir,
- &ns->bpf_bind_verifier_delay);
-
ns->bpf_tc_accept = true;
debugfs_create_bool("bpf_tc_accept", 0600, ns->ddir,
&ns->bpf_tc_accept);
return 0;
-err_destroy_bdev:
+err_bpf_sdev_uninit:
if (ns->sdev->refcnt == 1)
- bpf_offload_dev_destroy(ns->sdev->bpf_dev);
+ nsim_bpf_sdev_uninit(ns->sdev);
return err;
}
WARN_ON(ns->bpf_offloaded);
bpf_offload_dev_netdev_unregister(ns->sdev->bpf_dev, ns->netdev);
- if (ns->sdev->refcnt == 1) {
- WARN_ON(!list_empty(&ns->sdev->bpf_bound_progs));
- WARN_ON(!list_empty(&ns->sdev->bpf_bound_maps));
- bpf_offload_dev_destroy(ns->sdev->bpf_dev);
- }
+ if (ns->sdev->refcnt == 1)
+ nsim_bpf_sdev_uninit(ns->sdev);
}
#include "netdevsim.h"
+static u32 nsim_dev_id;
+
struct nsim_vf_config {
int link_state;
u16 min_tx_rate;
bool rss_query_enabled;
};
-static u32 nsim_dev_id;
-
static struct dentry *nsim_ddir;
-static struct dentry *nsim_sdev_ddir;
static int nsim_num_vf(struct device *dev)
{
struct netdevsim *ns = to_nsim(dev);
nsim_vfs_disable(ns);
- free_netdev(ns->netdev);
}
static struct device_type nsim_dev_type = {
static int nsim_init(struct net_device *dev)
{
- char sdev_ddir_name[10], sdev_link_name[32];
struct netdevsim *ns = netdev_priv(dev);
+ char sdev_link_name[32];
int err;
ns->netdev = dev;
if (IS_ERR_OR_NULL(ns->ddir))
return -ENOMEM;
- if (!ns->sdev) {
- ns->sdev = kzalloc(sizeof(*ns->sdev), GFP_KERNEL);
- if (!ns->sdev) {
- err = -ENOMEM;
- goto err_debugfs_destroy;
- }
- ns->sdev->refcnt = 1;
- ns->sdev->switch_id = nsim_dev_id;
- sprintf(sdev_ddir_name, "%u", ns->sdev->switch_id);
- ns->sdev->ddir = debugfs_create_dir(sdev_ddir_name,
- nsim_sdev_ddir);
- if (IS_ERR_OR_NULL(ns->sdev->ddir)) {
- err = PTR_ERR_OR_ZERO(ns->sdev->ddir) ?: -EINVAL;
- goto err_sdev_free;
- }
- } else {
- sprintf(sdev_ddir_name, "%u", ns->sdev->switch_id);
- ns->sdev->refcnt++;
- }
-
- sprintf(sdev_link_name, "../../" DRV_NAME "_sdev/%s", sdev_ddir_name);
+ sprintf(sdev_link_name, "../../" DRV_NAME "_sdev/%u",
+ ns->sdev->switch_id);
debugfs_create_symlink("sdev", ns->ddir, sdev_link_name);
err = nsim_bpf_init(ns);
if (err)
- goto err_sdev_destroy;
+ goto err_debugfs_destroy;
ns->dev.id = nsim_dev_id++;
ns->dev.bus = &nsim_bus;
device_unregister(&ns->dev);
err_bpf_uninit:
nsim_bpf_uninit(ns);
-err_sdev_destroy:
- if (!--ns->sdev->refcnt) {
- debugfs_remove_recursive(ns->sdev->ddir);
-err_sdev_free:
- kfree(ns->sdev);
- }
err_debugfs_destroy:
debugfs_remove_recursive(ns->ddir);
return err;
nsim_devlink_teardown(ns);
debugfs_remove_recursive(ns->ddir);
nsim_bpf_uninit(ns);
- if (!--ns->sdev->refcnt) {
- debugfs_remove_recursive(ns->sdev->ddir);
- kfree(ns->sdev);
- }
}
static void nsim_free(struct net_device *dev)
device_unregister(&ns->dev);
/* netdev and vf state will be freed out of device_release() */
+ nsim_sdev_put(ns->sdev);
}
static netdev_tx_t nsim_start_xmit(struct sk_buff *skb, struct net_device *dev)
eth_hw_addr_random(dev);
dev->netdev_ops = &nsim_netdev_ops;
+ dev->needs_free_netdev = true;
dev->priv_destructor = nsim_free;
dev->tx_queue_len = 0;
struct netlink_ext_ack *extack)
{
struct netdevsim *ns = netdev_priv(dev);
+ struct netdevsim *joinns = NULL;
+ int err;
if (tb[IFLA_LINK]) {
struct net_device *joindev;
- struct netdevsim *joinns;
joindev = __dev_get_by_index(src_net,
nla_get_u32(tb[IFLA_LINK]));
return -EINVAL;
joinns = netdev_priv(joindev);
- if (!joinns->sdev || !joinns->sdev->refcnt)
- return -EINVAL;
- ns->sdev = joinns->sdev;
}
- return register_netdevice(dev);
-}
+ ns->sdev = nsim_sdev_get(joinns);
+ if (IS_ERR(ns->sdev))
+ return PTR_ERR(ns->sdev);
-static void nsim_dellink(struct net_device *dev, struct list_head *head)
-{
- unregister_netdevice_queue(dev, head);
+ err = register_netdevice(dev);
+ if (err)
+ goto err_sdev_put;
+ return 0;
+
+err_sdev_put:
+ nsim_sdev_put(ns->sdev);
+ return err;
}
static struct rtnl_link_ops nsim_link_ops __read_mostly = {
.setup = nsim_setup,
.validate = nsim_validate,
.newlink = nsim_newlink,
- .dellink = nsim_dellink,
};
static int __init nsim_module_init(void)
if (IS_ERR_OR_NULL(nsim_ddir))
return -ENOMEM;
- nsim_sdev_ddir = debugfs_create_dir(DRV_NAME "_sdev", NULL);
- if (IS_ERR_OR_NULL(nsim_sdev_ddir)) {
- err = -ENOMEM;
+ err = nsim_sdev_init();
+ if (err)
goto err_debugfs_destroy;
- }
err = bus_register(&nsim_bus);
if (err)
- goto err_sdir_destroy;
+ goto err_sdev_exit;
err = nsim_devlink_init();
if (err)
nsim_devlink_exit();
err_unreg_bus:
bus_unregister(&nsim_bus);
-err_sdir_destroy:
- debugfs_remove_recursive(nsim_sdev_ddir);
+err_sdev_exit:
+ nsim_sdev_exit();
err_debugfs_destroy:
debugfs_remove_recursive(nsim_ddir);
return err;
rtnl_link_unregister(&nsim_link_ops);
nsim_devlink_exit();
bus_unregister(&nsim_bus);
- debugfs_remove_recursive(nsim_sdev_ddir);
+ nsim_sdev_exit();
debugfs_remove_recursive(nsim_ddir);
}
struct bpf_offload_dev *bpf_dev;
+ bool bpf_bind_accept;
+ u32 bpf_bind_verifier_delay;
+
struct dentry *ddir_bpf_bound_progs;
u32 prog_id_gen;
struct list_head bpf_bound_maps;
};
+struct netdevsim;
+
+struct netdevsim_shared_dev *nsim_sdev_get(struct netdevsim *joinns);
+void nsim_sdev_put(struct netdevsim_shared_dev *sdev);
+int nsim_sdev_init(void);
+void nsim_sdev_exit(void);
+
#define NSIM_IPSEC_MAX_SA_COUNT 33
#define NSIM_IPSEC_VALID BIT(31)
struct xdp_attachment_info xdp;
struct xdp_attachment_info xdp_hw;
- bool bpf_bind_accept;
- u32 bpf_bind_verifier_delay;
-
bool bpf_tc_accept;
bool bpf_tc_non_bound_accept;
bool bpf_xdpdrv_accept;
bool bpf_xdpoffload_accept;
bool bpf_map_accept;
-#if IS_ENABLED(CONFIG_NET_DEVLINK)
struct devlink *devlink;
-#endif
struct nsim_ipsec ipsec;
};
}
#endif
-#if IS_ENABLED(CONFIG_NET_DEVLINK)
enum nsim_resource_id {
NSIM_RESOURCE_NONE, /* DEVLINK_RESOURCE_ID_PARENT_TOP */
NSIM_RESOURCE_IPV4,
u64 nsim_fib_get_val(struct net *net, enum nsim_resource_id res_id, bool max);
int nsim_fib_set_max(struct net *net, enum nsim_resource_id res_id, u64 val,
struct netlink_ext_ack *extack);
-#else
-static inline int nsim_devlink_setup(struct netdevsim *ns)
-{
- return 0;
-}
-
-static inline void nsim_devlink_teardown(struct netdevsim *ns)
-{
-}
-
-static inline int nsim_devlink_init(void)
-{
- return 0;
-}
-
-static inline void nsim_devlink_exit(void)
-{
-}
-#endif
#if IS_ENABLED(CONFIG_XFRM_OFFLOAD)
void nsim_ipsec_init(struct netdevsim *ns);
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Mellanox Technologies. All rights reserved */
+
+#include <linux/debugfs.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+
+#include "netdevsim.h"
+
+static struct dentry *nsim_sdev_ddir;
+
+static u32 nsim_sdev_id;
+
+struct netdevsim_shared_dev *nsim_sdev_get(struct netdevsim *joinns)
+{
+ struct netdevsim_shared_dev *sdev;
+ char sdev_ddir_name[10];
+ int err;
+
+ if (joinns) {
+ if (WARN_ON(!joinns->sdev))
+ return ERR_PTR(-EINVAL);
+ sdev = joinns->sdev;
+ sdev->refcnt++;
+ return sdev;
+ }
+
+ sdev = kzalloc(sizeof(*sdev), GFP_KERNEL);
+ if (!sdev)
+ return ERR_PTR(-ENOMEM);
+ sdev->refcnt = 1;
+ sdev->switch_id = nsim_sdev_id++;
+
+ sprintf(sdev_ddir_name, "%u", sdev->switch_id);
+ sdev->ddir = debugfs_create_dir(sdev_ddir_name, nsim_sdev_ddir);
+ if (IS_ERR_OR_NULL(sdev->ddir)) {
+ err = PTR_ERR_OR_ZERO(sdev->ddir) ?: -EINVAL;
+ goto err_sdev_free;
+ }
+
+ return sdev;
+
+err_sdev_free:
+ nsim_sdev_id--;
+ kfree(sdev);
+ return ERR_PTR(err);
+}
+
+void nsim_sdev_put(struct netdevsim_shared_dev *sdev)
+{
+ if (--sdev->refcnt)
+ return;
+ debugfs_remove_recursive(sdev->ddir);
+ kfree(sdev);
+}
+
+int nsim_sdev_init(void)
+{
+ nsim_sdev_ddir = debugfs_create_dir(DRV_NAME "_sdev", NULL);
+ if (IS_ERR_OR_NULL(nsim_sdev_ddir))
+ return -ENOMEM;
+ return 0;
+}
+
+void nsim_sdev_exit(void)
+{
+ debugfs_remove_recursive(nsim_sdev_ddir);
+}
several child MDIO busses to a parent bus. Child bus
selection is under the control of GPIO lines.
+config MDIO_BUS_MUX_MESON_G12A
+ tristate "Amlogic G12a based MDIO bus multiplexer"
+ depends on ARCH_MESON || COMPILE_TEST
+ depends on OF_MDIO && HAS_IOMEM && COMMON_CLK
+ select MDIO_BUS_MUX
+ default m if ARCH_MESON
+ help
+ This module provides a driver for the MDIO multiplexer/glue of
+ the amlogic g12a SoC. The multiplexers connects either the external
+ or the internal MDIO bus to the parent bus.
+
config MDIO_BUS_MUX_MMIOREG
tristate "MMIO device-controlled MDIO bus multiplexers"
depends on OF_MDIO && HAS_IOMEM
obj-$(CONFIG_MDIO_BUS_MUX) += mdio-mux.o
obj-$(CONFIG_MDIO_BUS_MUX_BCM_IPROC) += mdio-mux-bcm-iproc.o
obj-$(CONFIG_MDIO_BUS_MUX_GPIO) += mdio-mux-gpio.o
+obj-$(CONFIG_MDIO_BUS_MUX_MESON_G12A) += mdio-mux-meson-g12a.o
obj-$(CONFIG_MDIO_BUS_MUX_MMIOREG) += mdio-mux-mmioreg.o
obj-$(CONFIG_MDIO_BUS_MUX_MULTIPLEXER) += mdio-mux-multiplexer.o
obj-$(CONFIG_MDIO_CAVIUM) += mdio-cavium.o
.phy_id = PHY_ID_AM79C874,
.name = "AM79C874",
.phy_id_mask = 0xfffffff0,
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.config_init = am79c_config_init,
.ack_interrupt = am79c_ack_interrupt,
.config_intr = am79c_config_intr,
#define MDIO_AN_RX_VEND_STAT3 0xe832
#define MDIO_AN_RX_VEND_STAT3_AFR BIT(0)
+/* MDIO_MMD_C22EXT */
+#define MDIO_C22EXT_STAT_SGMII_RX_GOOD_FRAMES 0xd292
+#define MDIO_C22EXT_STAT_SGMII_RX_BAD_FRAMES 0xd294
+#define MDIO_C22EXT_STAT_SGMII_RX_FALSE_CARRIER 0xd297
+#define MDIO_C22EXT_STAT_SGMII_TX_GOOD_FRAMES 0xd313
+#define MDIO_C22EXT_STAT_SGMII_TX_BAD_FRAMES 0xd315
+#define MDIO_C22EXT_STAT_SGMII_TX_FALSE_CARRIER 0xd317
+#define MDIO_C22EXT_STAT_SGMII_TX_COLLISIONS 0xd318
+#define MDIO_C22EXT_STAT_SGMII_TX_LINE_COLLISIONS 0xd319
+#define MDIO_C22EXT_STAT_SGMII_TX_FRAME_ALIGN_ERR 0xd31a
+#define MDIO_C22EXT_STAT_SGMII_TX_RUNT_FRAMES 0xd31b
+
/* Vendor specific 1, MDIO_MMD_VEND1 */
#define VEND1_GLOBAL_FW_ID 0x0020
#define VEND1_GLOBAL_FW_ID_MAJOR GENMASK(15, 8)
#define VEND1_GLOBAL_INT_VEND_MASK_GLOBAL2 BIT(1)
#define VEND1_GLOBAL_INT_VEND_MASK_GLOBAL3 BIT(0)
+struct aqr107_hw_stat {
+ const char *name;
+ int reg;
+ int size;
+};
+
+#define SGMII_STAT(n, r, s) { n, MDIO_C22EXT_STAT_SGMII_ ## r, s }
+static const struct aqr107_hw_stat aqr107_hw_stats[] = {
+ SGMII_STAT("sgmii_rx_good_frames", RX_GOOD_FRAMES, 26),
+ SGMII_STAT("sgmii_rx_bad_frames", RX_BAD_FRAMES, 26),
+ SGMII_STAT("sgmii_rx_false_carrier_events", RX_FALSE_CARRIER, 8),
+ SGMII_STAT("sgmii_tx_good_frames", TX_GOOD_FRAMES, 26),
+ SGMII_STAT("sgmii_tx_bad_frames", TX_BAD_FRAMES, 26),
+ SGMII_STAT("sgmii_tx_false_carrier_events", TX_FALSE_CARRIER, 8),
+ SGMII_STAT("sgmii_tx_collisions", TX_COLLISIONS, 8),
+ SGMII_STAT("sgmii_tx_line_collisions", TX_LINE_COLLISIONS, 8),
+ SGMII_STAT("sgmii_tx_frame_alignment_err", TX_FRAME_ALIGN_ERR, 16),
+ SGMII_STAT("sgmii_tx_runt_frames", TX_RUNT_FRAMES, 22),
+};
+#define AQR107_SGMII_STAT_SZ ARRAY_SIZE(aqr107_hw_stats)
+
+struct aqr107_priv {
+ u64 sgmii_stats[AQR107_SGMII_STAT_SZ];
+};
+
+static int aqr107_get_sset_count(struct phy_device *phydev)
+{
+ return AQR107_SGMII_STAT_SZ;
+}
+
+static void aqr107_get_strings(struct phy_device *phydev, u8 *data)
+{
+ int i;
+
+ for (i = 0; i < AQR107_SGMII_STAT_SZ; i++)
+ strscpy(data + i * ETH_GSTRING_LEN, aqr107_hw_stats[i].name,
+ ETH_GSTRING_LEN);
+}
+
+static u64 aqr107_get_stat(struct phy_device *phydev, int index)
+{
+ const struct aqr107_hw_stat *stat = aqr107_hw_stats + index;
+ int len_l = min(stat->size, 16);
+ int len_h = stat->size - len_l;
+ u64 ret;
+ int val;
+
+ val = phy_read_mmd(phydev, MDIO_MMD_C22EXT, stat->reg);
+ if (val < 0)
+ return U64_MAX;
+
+ ret = val & GENMASK(len_l - 1, 0);
+ if (len_h) {
+ val = phy_read_mmd(phydev, MDIO_MMD_C22EXT, stat->reg + 1);
+ if (val < 0)
+ return U64_MAX;
+
+ ret += (val & GENMASK(len_h - 1, 0)) << 16;
+ }
+
+ return ret;
+}
+
+static void aqr107_get_stats(struct phy_device *phydev,
+ struct ethtool_stats *stats, u64 *data)
+{
+ struct aqr107_priv *priv = phydev->priv;
+ u64 val;
+ int i;
+
+ for (i = 0; i < AQR107_SGMII_STAT_SZ; i++) {
+ val = aqr107_get_stat(phydev, i);
+ if (val == U64_MAX)
+ phydev_err(phydev, "Reading HW Statistics failed for %s\n",
+ aqr107_hw_stats[i].name);
+ else
+ priv->sgmii_stats[i] += val;
+
+ data[i] = priv->sgmii_stats[i];
+ }
+}
+
static int aqr_config_aneg(struct phy_device *phydev)
{
bool changed = false;
phydev_info(phydev, "Aquantia 1000Base-T2 mode active\n");
}
+static int aqr107_suspend(struct phy_device *phydev)
+{
+ return phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, MDIO_CTRL1,
+ MDIO_CTRL1_LPOWER);
+}
+
+static int aqr107_resume(struct phy_device *phydev)
+{
+ return phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, MDIO_CTRL1,
+ MDIO_CTRL1_LPOWER);
+}
+
+static int aqr107_probe(struct phy_device *phydev)
+{
+ phydev->priv = devm_kzalloc(&phydev->mdio.dev,
+ sizeof(struct aqr107_priv), GFP_KERNEL);
+ if (!phydev->priv)
+ return -ENOMEM;
+
+ return aqr_hwmon_probe(phydev);
+}
+
static struct phy_driver aqr_driver[] = {
{
PHY_ID_MATCH_MODEL(PHY_ID_AQ1202),
.name = "Aquantia AQ1202",
- .aneg_done = genphy_c45_aneg_done,
- .get_features = genphy_c45_pma_read_abilities,
.config_aneg = aqr_config_aneg,
.config_intr = aqr_config_intr,
.ack_interrupt = aqr_ack_interrupt,
{
PHY_ID_MATCH_MODEL(PHY_ID_AQ2104),
.name = "Aquantia AQ2104",
- .aneg_done = genphy_c45_aneg_done,
- .get_features = genphy_c45_pma_read_abilities,
.config_aneg = aqr_config_aneg,
.config_intr = aqr_config_intr,
.ack_interrupt = aqr_ack_interrupt,
{
PHY_ID_MATCH_MODEL(PHY_ID_AQR105),
.name = "Aquantia AQR105",
- .aneg_done = genphy_c45_aneg_done,
- .get_features = genphy_c45_pma_read_abilities,
.config_aneg = aqr_config_aneg,
.config_intr = aqr_config_intr,
.ack_interrupt = aqr_ack_interrupt,
{
PHY_ID_MATCH_MODEL(PHY_ID_AQR106),
.name = "Aquantia AQR106",
- .aneg_done = genphy_c45_aneg_done,
- .get_features = genphy_c45_pma_read_abilities,
.config_aneg = aqr_config_aneg,
.config_intr = aqr_config_intr,
.ack_interrupt = aqr_ack_interrupt,
{
PHY_ID_MATCH_MODEL(PHY_ID_AQR107),
.name = "Aquantia AQR107",
- .aneg_done = genphy_c45_aneg_done,
- .get_features = genphy_c45_pma_read_abilities,
- .probe = aqr_hwmon_probe,
+ .probe = aqr107_probe,
.config_init = aqr107_config_init,
.config_aneg = aqr_config_aneg,
.config_intr = aqr_config_intr,
.read_status = aqr107_read_status,
.get_tunable = aqr107_get_tunable,
.set_tunable = aqr107_set_tunable,
+ .suspend = aqr107_suspend,
+ .resume = aqr107_resume,
+ .get_sset_count = aqr107_get_sset_count,
+ .get_strings = aqr107_get_strings,
+ .get_stats = aqr107_get_stats,
.link_change_notify = aqr107_link_change_notify,
},
{
PHY_ID_MATCH_MODEL(PHY_ID_AQCS109),
.name = "Aquantia AQCS109",
- .aneg_done = genphy_c45_aneg_done,
- .get_features = genphy_c45_pma_read_abilities,
- .probe = aqr_hwmon_probe,
+ .probe = aqr107_probe,
.config_init = aqcs109_config_init,
.config_aneg = aqr_config_aneg,
.config_intr = aqr_config_intr,
.read_status = aqr107_read_status,
.get_tunable = aqr107_get_tunable,
.set_tunable = aqr107_set_tunable,
+ .suspend = aqr107_suspend,
+ .resume = aqr107_resume,
+ .get_sset_count = aqr107_get_sset_count,
+ .get_strings = aqr107_get_strings,
+ .get_stats = aqr107_get_stats,
.link_change_notify = aqr107_link_change_notify,
},
{
PHY_ID_MATCH_MODEL(PHY_ID_AQR405),
.name = "Aquantia AQR405",
- .aneg_done = genphy_c45_aneg_done,
- .get_features = genphy_c45_pma_read_abilities,
.config_aneg = aqr_config_aneg,
.config_intr = aqr_config_intr,
.ack_interrupt = aqr_ack_interrupt,
.phy_id = PHY_ID_ASIX_AX88796B,
.name = "Asix Electronics AX88796B",
.phy_id_mask = 0xfffffff0,
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.soft_reset = asix_soft_reset,
} };
.get_wol = at803x_get_wol,
.suspend = at803x_suspend,
.resume = at803x_resume,
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.ack_interrupt = at803x_ack_interrupt,
.config_intr = at803x_config_intr,
}, {
.get_wol = at803x_get_wol,
.suspend = at803x_suspend,
.resume = at803x_resume,
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.ack_interrupt = at803x_ack_interrupt,
.config_intr = at803x_config_intr,
}, {
.get_wol = at803x_get_wol,
.suspend = at803x_suspend,
.resume = at803x_resume,
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.aneg_done = at803x_aneg_done,
.ack_interrupt = &at803x_ack_interrupt,
.config_intr = &at803x_config_intr,
.phy_id = PHY_ID_BCM_CYGNUS,
.phy_id_mask = 0xfffffff0,
.name = "Broadcom Cygnus PHY",
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.config_init = bcm_cygnus_config_init,
.ack_interrupt = bcm_phy_ack_intr,
.config_intr = bcm_phy_config_intr,
.phy_id = PHY_ID_BCM_OMEGA,
.phy_id_mask = 0xfffffff0,
.name = "Broadcom Omega Combo GPHY",
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.flags = PHY_IS_INTERNAL,
.config_init = bcm_omega_config_init,
.suspend = genphy_suspend,
.phy_id = 0x00406000,
.phy_id_mask = 0xfffffc00,
.name = "Broadcom BCM63XX (1)",
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.flags = PHY_IS_INTERNAL,
.config_init = bcm63xx_config_init,
.ack_interrupt = bcm_phy_ack_intr,
/* same phy as above, with just a different OUI */
.phy_id = 0x002bdc00,
.phy_id_mask = 0xfffffc00,
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.flags = PHY_IS_INTERNAL,
.config_init = bcm63xx_config_init,
.ack_interrupt = bcm_phy_ack_intr,
.phy_id = (_oui), \
.phy_id_mask = 0xfffffff0, \
.name = _name, \
- .features = PHY_GBIT_FEATURES, \
+ /* PHY_GBIT_FEATURES */ \
.flags = PHY_IS_INTERNAL, \
.config_init = bcm7xxx_28nm_config_init, \
.resume = bcm7xxx_28nm_resume, \
.phy_id = (_oui), \
.phy_id_mask = 0xfffffff0, \
.name = _name, \
- .features = PHY_BASIC_FEATURES, \
+ /* PHY_BASIC_FEATURES */ \
.flags = PHY_IS_INTERNAL, \
.config_init = bcm7xxx_28nm_ephy_config_init, \
.resume = bcm7xxx_28nm_ephy_resume, \
.phy_id = (_oui), \
.phy_id_mask = 0xfffffff0, \
.name = _name, \
- .features = PHY_BASIC_FEATURES, \
+ /* PHY_BASIC_FEATURES */ \
.flags = PHY_IS_INTERNAL, \
.config_init = bcm7xxx_config_init, \
.suspend = bcm7xxx_suspend, \
.phy_id = PHY_ID_BCM5411,
.phy_id_mask = 0xfffffff0,
.name = "Broadcom BCM5411",
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.config_init = bcm54xx_config_init,
.ack_interrupt = bcm_phy_ack_intr,
.config_intr = bcm_phy_config_intr,
.phy_id = PHY_ID_BCM5421,
.phy_id_mask = 0xfffffff0,
.name = "Broadcom BCM5421",
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.config_init = bcm54xx_config_init,
.ack_interrupt = bcm_phy_ack_intr,
.config_intr = bcm_phy_config_intr,
.phy_id = PHY_ID_BCM54210E,
.phy_id_mask = 0xfffffff0,
.name = "Broadcom BCM54210E",
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.config_init = bcm54xx_config_init,
.ack_interrupt = bcm_phy_ack_intr,
.config_intr = bcm_phy_config_intr,
.phy_id = PHY_ID_BCM5461,
.phy_id_mask = 0xfffffff0,
.name = "Broadcom BCM5461",
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.config_init = bcm54xx_config_init,
.ack_interrupt = bcm_phy_ack_intr,
.config_intr = bcm_phy_config_intr,
.phy_id = PHY_ID_BCM54612E,
.phy_id_mask = 0xfffffff0,
.name = "Broadcom BCM54612E",
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.config_init = bcm54xx_config_init,
.ack_interrupt = bcm_phy_ack_intr,
.config_intr = bcm_phy_config_intr,
.phy_id = PHY_ID_BCM54616S,
.phy_id_mask = 0xfffffff0,
.name = "Broadcom BCM54616S",
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.config_init = bcm54xx_config_init,
.config_aneg = bcm54616s_config_aneg,
.ack_interrupt = bcm_phy_ack_intr,
.phy_id = PHY_ID_BCM5464,
.phy_id_mask = 0xfffffff0,
.name = "Broadcom BCM5464",
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.config_init = bcm54xx_config_init,
.ack_interrupt = bcm_phy_ack_intr,
.config_intr = bcm_phy_config_intr,
.phy_id = PHY_ID_BCM5481,
.phy_id_mask = 0xfffffff0,
.name = "Broadcom BCM5481",
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.config_init = bcm54xx_config_init,
.config_aneg = bcm5481_config_aneg,
.ack_interrupt = bcm_phy_ack_intr,
.phy_id = PHY_ID_BCM54810,
.phy_id_mask = 0xfffffff0,
.name = "Broadcom BCM54810",
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.config_init = bcm54xx_config_init,
.config_aneg = bcm5481_config_aneg,
.ack_interrupt = bcm_phy_ack_intr,
.phy_id = PHY_ID_BCM5482,
.phy_id_mask = 0xfffffff0,
.name = "Broadcom BCM5482",
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.config_init = bcm5482_config_init,
.read_status = bcm5482_read_status,
.ack_interrupt = bcm_phy_ack_intr,
.phy_id = PHY_ID_BCM50610,
.phy_id_mask = 0xfffffff0,
.name = "Broadcom BCM50610",
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.config_init = bcm54xx_config_init,
.ack_interrupt = bcm_phy_ack_intr,
.config_intr = bcm_phy_config_intr,
.phy_id = PHY_ID_BCM50610M,
.phy_id_mask = 0xfffffff0,
.name = "Broadcom BCM50610M",
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.config_init = bcm54xx_config_init,
.ack_interrupt = bcm_phy_ack_intr,
.config_intr = bcm_phy_config_intr,
.phy_id = PHY_ID_BCM57780,
.phy_id_mask = 0xfffffff0,
.name = "Broadcom BCM57780",
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.config_init = bcm54xx_config_init,
.ack_interrupt = bcm_phy_ack_intr,
.config_intr = bcm_phy_config_intr,
.phy_id = PHY_ID_BCMAC131,
.phy_id_mask = 0xfffffff0,
.name = "Broadcom BCMAC131",
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.config_init = brcm_fet_config_init,
.ack_interrupt = brcm_fet_ack_interrupt,
.config_intr = brcm_fet_config_intr,
.phy_id = PHY_ID_BCM5241,
.phy_id_mask = 0xfffffff0,
.name = "Broadcom BCM5241",
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.config_init = brcm_fet_config_init,
.ack_interrupt = brcm_fet_ack_interrupt,
.config_intr = brcm_fet_config_intr,
.phy_id_mask = 0xfffffff0,
.name = "Broadcom BCM5395",
.flags = PHY_IS_INTERNAL,
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.get_sset_count = bcm_phy_get_sset_count,
.get_strings = bcm_phy_get_strings,
.get_stats = bcm53xx_phy_get_stats,
.phy_id = PHY_ID_BCM89610,
.phy_id_mask = 0xfffffff0,
.name = "Broadcom BCM89610",
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.config_init = bcm54xx_config_init,
.ack_interrupt = bcm_phy_ack_intr,
.config_intr = bcm_phy_config_intr,
.phy_id = 0x000fc410,
.name = "Cicada Cis8201",
.phy_id_mask = 0x000ffff0,
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.config_init = &cis820x_config_init,
.ack_interrupt = &cis820x_ack_interrupt,
.config_intr = &cis820x_config_intr,
.phy_id = 0x000fc440,
.name = "Cicada Cis8204",
.phy_id_mask = 0x000fffc0,
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.config_init = &cis820x_config_init,
.ack_interrupt = &cis820x_ack_interrupt,
.config_intr = &cis820x_config_intr,
.phy_id = 0x0181b880,
.name = "Davicom DM9161E",
.phy_id_mask = 0x0ffffff0,
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.config_init = dm9161_config_init,
.config_aneg = dm9161_config_aneg,
.ack_interrupt = dm9161_ack_interrupt,
.phy_id = 0x0181b8b0,
.name = "Davicom DM9161B/C",
.phy_id_mask = 0x0ffffff0,
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.config_init = dm9161_config_init,
.config_aneg = dm9161_config_aneg,
.ack_interrupt = dm9161_ack_interrupt,
.phy_id = 0x0181b8a0,
.name = "Davicom DM9161A",
.phy_id_mask = 0x0ffffff0,
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.config_init = dm9161_config_init,
.config_aneg = dm9161_config_aneg,
.ack_interrupt = dm9161_ack_interrupt,
.phy_id = 0x00181b80,
.name = "Davicom DM9131",
.phy_id_mask = 0x0ffffff0,
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.ack_interrupt = dm9161_ack_interrupt,
.config_intr = dm9161_config_intr,
} };
.phy_id = DP83640_PHY_ID,
.phy_id_mask = 0xfffffff0,
.name = "NatSemi DP83640",
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.probe = dp83640_probe,
.remove = dp83640_remove,
.soft_reset = dp83640_soft_reset,
{ \
PHY_ID_MATCH_MODEL(_id), \
.name = (_name), \
- .features = PHY_BASIC_FEATURES, \
+ /* PHY_BASIC_FEATURES */ \
.soft_reset = dp83822_phy_reset, \
.config_init = dp83822_config_init, \
.get_wol = dp83822_get_wol, \
.phy_id = _id, \
.phy_id_mask = 0xfffffff0, \
.name = _name, \
- .features = PHY_BASIC_FEATURES, \
+ /* PHY_BASIC_FEATURES */ \
\
.soft_reset = genphy_soft_reset, \
.config_init = _config_init, \
.phy_id = DP83867_PHY_ID,
.phy_id_mask = 0xfffffff0,
.name = "TI DP83867",
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.config_init = dp83867_config_init,
.soft_reset = dp83867_phy_reset,
.phy_id = DP83TC811_PHY_ID,
.phy_id_mask = 0xfffffff0,
.name = "TI DP83TC811",
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.config_init = dp83811_config_init,
.config_aneg = dp83811_config_aneg,
.soft_reset = dp83811_phy_reset,
.phy_id = 0x0282f014,
.name = "ET1011C",
.phy_id_mask = 0xfffffff0,
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.config_aneg = et1011c_config_aneg,
.read_status = et1011c_read_status,
} };
.phy_id = 0x02430d80,
.name = "ICPlus IP175C",
.phy_id_mask = 0x0ffffff0,
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.config_init = &ip175c_config_init,
.config_aneg = &ip175c_config_aneg,
.read_status = &ip175c_read_status,
.phy_id = 0x02430d90,
.name = "ICPlus IP1001",
.phy_id_mask = 0x0ffffff0,
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.config_init = &ip1001_config_init,
.suspend = genphy_suspend,
.resume = genphy_resume,
.phy_id = 0x02430c54,
.name = "ICPlus IP101A/G",
.phy_id_mask = 0x0ffffff0,
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.probe = ip101a_g_probe,
.config_intr = ip101a_g_config_intr,
.did_interrupt = ip101a_g_did_interrupt,
.phy_id = PHY_ID_PHY11G_1_3,
.phy_id_mask = 0xffffffff,
.name = "Intel XWAY PHY11G (PEF 7071/PEF 7072) v1.3",
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.config_init = xway_gphy_config_init,
.config_aneg = xway_gphy14_config_aneg,
.ack_interrupt = xway_gphy_ack_interrupt,
.phy_id = PHY_ID_PHY22F_1_3,
.phy_id_mask = 0xffffffff,
.name = "Intel XWAY PHY22F (PEF 7061) v1.3",
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.config_init = xway_gphy_config_init,
.config_aneg = xway_gphy14_config_aneg,
.ack_interrupt = xway_gphy_ack_interrupt,
.phy_id = PHY_ID_PHY11G_1_4,
.phy_id_mask = 0xffffffff,
.name = "Intel XWAY PHY11G (PEF 7071/PEF 7072) v1.4",
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.config_init = xway_gphy_config_init,
.config_aneg = xway_gphy14_config_aneg,
.ack_interrupt = xway_gphy_ack_interrupt,
.phy_id = PHY_ID_PHY22F_1_4,
.phy_id_mask = 0xffffffff,
.name = "Intel XWAY PHY22F (PEF 7061) v1.4",
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.config_init = xway_gphy_config_init,
.config_aneg = xway_gphy14_config_aneg,
.ack_interrupt = xway_gphy_ack_interrupt,
.phy_id = PHY_ID_PHY11G_1_5,
.phy_id_mask = 0xffffffff,
.name = "Intel XWAY PHY11G (PEF 7071/PEF 7072) v1.5 / v1.6",
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.config_init = xway_gphy_config_init,
.ack_interrupt = xway_gphy_ack_interrupt,
.did_interrupt = xway_gphy_did_interrupt,
.phy_id = PHY_ID_PHY22F_1_5,
.phy_id_mask = 0xffffffff,
.name = "Intel XWAY PHY22F (PEF 7061) v1.5 / v1.6",
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.config_init = xway_gphy_config_init,
.ack_interrupt = xway_gphy_ack_interrupt,
.did_interrupt = xway_gphy_did_interrupt,
.phy_id = PHY_ID_PHY11G_VR9_1_1,
.phy_id_mask = 0xffffffff,
.name = "Intel XWAY PHY11G (xRX v1.1 integrated)",
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.config_init = xway_gphy_config_init,
.ack_interrupt = xway_gphy_ack_interrupt,
.did_interrupt = xway_gphy_did_interrupt,
.phy_id = PHY_ID_PHY22F_VR9_1_1,
.phy_id_mask = 0xffffffff,
.name = "Intel XWAY PHY22F (xRX v1.1 integrated)",
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.config_init = xway_gphy_config_init,
.ack_interrupt = xway_gphy_ack_interrupt,
.did_interrupt = xway_gphy_did_interrupt,
.phy_id = PHY_ID_PHY11G_VR9_1_2,
.phy_id_mask = 0xffffffff,
.name = "Intel XWAY PHY11G (xRX v1.2 integrated)",
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.config_init = xway_gphy_config_init,
.ack_interrupt = xway_gphy_ack_interrupt,
.did_interrupt = xway_gphy_did_interrupt,
.phy_id = PHY_ID_PHY22F_VR9_1_2,
.phy_id_mask = 0xffffffff,
.name = "Intel XWAY PHY22F (xRX v1.2 integrated)",
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.config_init = xway_gphy_config_init,
.ack_interrupt = xway_gphy_ack_interrupt,
.did_interrupt = xway_gphy_did_interrupt,
.phy_id = 0x78100000,
.name = "LXT970",
.phy_id_mask = 0xfffffff0,
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.config_init = lxt970_config_init,
.ack_interrupt = lxt970_ack_interrupt,
.config_intr = lxt970_config_intr,
.phy_id = 0x001378e0,
.name = "LXT971",
.phy_id_mask = 0xfffffff0,
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.ack_interrupt = lxt971_ack_interrupt,
.config_intr = lxt971_config_intr,
}, {
.phy_id = 0x00137a10,
.name = "LXT973-A2",
.phy_id_mask = 0xffffffff,
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.flags = 0,
.probe = lxt973_probe,
.config_aneg = lxt973_config_aneg,
.phy_id = 0x00137a10,
.name = "LXT973",
.phy_id_mask = 0xfffffff0,
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.flags = 0,
.probe = lxt973_probe,
.config_aneg = lxt973_config_aneg,
.phy_id = MARVELL_PHY_ID_88E1101,
.phy_id_mask = MARVELL_PHY_ID_MASK,
.name = "Marvell 88E1101",
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.probe = marvell_probe,
.config_init = &marvell_config_init,
.config_aneg = &m88e1101_config_aneg,
.phy_id = MARVELL_PHY_ID_88E1112,
.phy_id_mask = MARVELL_PHY_ID_MASK,
.name = "Marvell 88E1112",
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.probe = marvell_probe,
.config_init = &m88e1111_config_init,
.config_aneg = &marvell_config_aneg,
.phy_id = MARVELL_PHY_ID_88E1111,
.phy_id_mask = MARVELL_PHY_ID_MASK,
.name = "Marvell 88E1111",
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.probe = marvell_probe,
.config_init = &m88e1111_config_init,
.config_aneg = &marvell_config_aneg,
.phy_id = MARVELL_PHY_ID_88E1118,
.phy_id_mask = MARVELL_PHY_ID_MASK,
.name = "Marvell 88E1118",
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.probe = marvell_probe,
.config_init = &m88e1118_config_init,
.config_aneg = &m88e1118_config_aneg,
.phy_id = MARVELL_PHY_ID_88E1121R,
.phy_id_mask = MARVELL_PHY_ID_MASK,
.name = "Marvell 88E1121R",
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.probe = &m88e1121_probe,
.config_init = &marvell_config_init,
.config_aneg = &m88e1121_config_aneg,
.phy_id = MARVELL_PHY_ID_88E1318S,
.phy_id_mask = MARVELL_PHY_ID_MASK,
.name = "Marvell 88E1318S",
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.probe = marvell_probe,
.config_init = &m88e1318_config_init,
.config_aneg = &m88e1318_config_aneg,
.phy_id = MARVELL_PHY_ID_88E1145,
.phy_id_mask = MARVELL_PHY_ID_MASK,
.name = "Marvell 88E1145",
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.probe = marvell_probe,
.config_init = &m88e1145_config_init,
.config_aneg = &m88e1101_config_aneg,
.phy_id = MARVELL_PHY_ID_88E1149R,
.phy_id_mask = MARVELL_PHY_ID_MASK,
.name = "Marvell 88E1149R",
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.probe = marvell_probe,
.config_init = &m88e1149_config_init,
.config_aneg = &m88e1118_config_aneg,
.phy_id = MARVELL_PHY_ID_88E1240,
.phy_id_mask = MARVELL_PHY_ID_MASK,
.name = "Marvell 88E1240",
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.probe = marvell_probe,
.config_init = &m88e1111_config_init,
.config_aneg = &marvell_config_aneg,
.phy_id = MARVELL_PHY_ID_88E1116R,
.phy_id_mask = MARVELL_PHY_ID_MASK,
.name = "Marvell 88E1116R",
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.probe = marvell_probe,
.config_init = &m88e1116r_config_init,
.ack_interrupt = &marvell_ack_interrupt,
.phy_id = MARVELL_PHY_ID_88E1540,
.phy_id_mask = MARVELL_PHY_ID_MASK,
.name = "Marvell 88E1540",
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.probe = m88e1510_probe,
.config_init = &marvell_config_init,
.config_aneg = &m88e1510_config_aneg,
.phy_id_mask = MARVELL_PHY_ID_MASK,
.name = "Marvell 88E1545",
.probe = m88e1510_probe,
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.config_init = &marvell_config_init,
.config_aneg = &m88e1510_config_aneg,
.read_status = &marvell_read_status,
.phy_id = MARVELL_PHY_ID_88E3016,
.phy_id_mask = MARVELL_PHY_ID_MASK,
.name = "Marvell 88E3016",
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.probe = marvell_probe,
.config_init = &m88e3016_config_init,
.aneg_done = &marvell_aneg_done,
.phy_id = MARVELL_PHY_ID_88E6390,
.phy_id_mask = MARVELL_PHY_ID_MASK,
.name = "Marvell 88E6390",
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.probe = m88e6390_probe,
.config_init = &marvell_config_init,
.config_aneg = &m88e6390_config_aneg,
MV_AN_STAT1000 = 0x8001, /* 1000base-T status register */
/* Vendor2 MMD registers */
+ MV_V2_PORT_CTRL = 0xf001,
+ MV_V2_PORT_CTRL_PWRDOWN = 0x0800,
MV_V2_TEMP_CTRL = 0xf08a,
MV_V2_TEMP_CTRL_MASK = 0xc000,
MV_V2_TEMP_CTRL_SAMPLE = 0x0000,
static int mv3310_suspend(struct phy_device *phydev)
{
- return 0;
+ return phy_set_bits_mmd(phydev, MDIO_MMD_VEND2, MV_V2_PORT_CTRL,
+ MV_V2_PORT_CTRL_PWRDOWN);
}
static int mv3310_resume(struct phy_device *phydev)
{
+ int ret;
+
+ ret = phy_clear_bits_mmd(phydev, MDIO_MMD_VEND2, MV_V2_PORT_CTRL,
+ MV_V2_PORT_CTRL_PWRDOWN);
+ if (ret)
+ return ret;
+
return mv3310_hwmon_config(phydev, true);
}
.phy_id = MARVELL_PHY_ID_88E2110,
.phy_id_mask = MARVELL_PHY_ID_MASK,
.name = "mv88x2110",
- .get_features = genphy_c45_pma_read_abilities,
.probe = mv3310_probe,
+ .suspend = mv3310_suspend,
+ .resume = mv3310_resume,
.soft_reset = genphy_no_soft_reset,
.config_init = mv3310_config_init,
.config_aneg = mv3310_config_aneg,
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Baylibre, SAS.
+ * Author: Jerome Brunet <jbrunet@baylibre.com>
+ */
+
+#include <linux/bitfield.h>
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/mdio-mux.h>
+#include <linux/module.h>
+#include <linux/phy.h>
+#include <linux/platform_device.h>
+
+#define ETH_PLL_STS 0x40
+#define ETH_PLL_CTL0 0x44
+#define PLL_CTL0_LOCK_DIG BIT(30)
+#define PLL_CTL0_RST BIT(29)
+#define PLL_CTL0_EN BIT(28)
+#define PLL_CTL0_SEL BIT(23)
+#define PLL_CTL0_N GENMASK(14, 10)
+#define PLL_CTL0_M GENMASK(8, 0)
+#define PLL_LOCK_TIMEOUT 1000000
+#define PLL_MUX_NUM_PARENT 2
+#define ETH_PLL_CTL1 0x48
+#define ETH_PLL_CTL2 0x4c
+#define ETH_PLL_CTL3 0x50
+#define ETH_PLL_CTL4 0x54
+#define ETH_PLL_CTL5 0x58
+#define ETH_PLL_CTL6 0x5c
+#define ETH_PLL_CTL7 0x60
+
+#define ETH_PHY_CNTL0 0x80
+#define EPHY_G12A_ID 0x33000180
+#define ETH_PHY_CNTL1 0x84
+#define PHY_CNTL1_ST_MODE GENMASK(2, 0)
+#define PHY_CNTL1_ST_PHYADD GENMASK(7, 3)
+#define EPHY_DFLT_ADD 8
+#define PHY_CNTL1_MII_MODE GENMASK(15, 14)
+#define EPHY_MODE_RMII 0x1
+#define PHY_CNTL1_CLK_EN BIT(16)
+#define PHY_CNTL1_CLKFREQ BIT(17)
+#define PHY_CNTL1_PHY_ENB BIT(18)
+#define ETH_PHY_CNTL2 0x88
+#define PHY_CNTL2_USE_INTERNAL BIT(5)
+#define PHY_CNTL2_SMI_SRC_MAC BIT(6)
+#define PHY_CNTL2_RX_CLK_EPHY BIT(9)
+
+#define MESON_G12A_MDIO_EXTERNAL_ID 0
+#define MESON_G12A_MDIO_INTERNAL_ID 1
+
+struct g12a_mdio_mux {
+ bool pll_is_enabled;
+ void __iomem *regs;
+ void *mux_handle;
+ struct clk *pclk;
+ struct clk *pll;
+};
+
+struct g12a_ephy_pll {
+ void __iomem *base;
+ struct clk_hw hw;
+};
+
+#define g12a_ephy_pll_to_dev(_hw) \
+ container_of(_hw, struct g12a_ephy_pll, hw)
+
+static unsigned long g12a_ephy_pll_recalc_rate(struct clk_hw *hw,
+ unsigned long parent_rate)
+{
+ struct g12a_ephy_pll *pll = g12a_ephy_pll_to_dev(hw);
+ u32 val, m, n;
+
+ val = readl(pll->base + ETH_PLL_CTL0);
+ m = FIELD_GET(PLL_CTL0_M, val);
+ n = FIELD_GET(PLL_CTL0_N, val);
+
+ return parent_rate * m / n;
+}
+
+static int g12a_ephy_pll_enable(struct clk_hw *hw)
+{
+ struct g12a_ephy_pll *pll = g12a_ephy_pll_to_dev(hw);
+ u32 val = readl(pll->base + ETH_PLL_CTL0);
+
+ /* Apply both enable an reset */
+ val |= PLL_CTL0_RST | PLL_CTL0_EN;
+ writel(val, pll->base + ETH_PLL_CTL0);
+
+ /* Clear the reset to let PLL lock */
+ val &= ~PLL_CTL0_RST;
+ writel(val, pll->base + ETH_PLL_CTL0);
+
+ /* Poll on the digital lock instead of the usual analog lock
+ * This is done because bit 31 is unreliable on some SoC. Bit
+ * 31 may indicate that the PLL is not lock eventhough the clock
+ * is actually running
+ */
+ return readl_poll_timeout(pll->base + ETH_PLL_CTL0, val,
+ val & PLL_CTL0_LOCK_DIG, 0, PLL_LOCK_TIMEOUT);
+}
+
+static void g12a_ephy_pll_disable(struct clk_hw *hw)
+{
+ struct g12a_ephy_pll *pll = g12a_ephy_pll_to_dev(hw);
+ u32 val;
+
+ val = readl(pll->base + ETH_PLL_CTL0);
+ val &= ~PLL_CTL0_EN;
+ val |= PLL_CTL0_RST;
+ writel(val, pll->base + ETH_PLL_CTL0);
+}
+
+static int g12a_ephy_pll_is_enabled(struct clk_hw *hw)
+{
+ struct g12a_ephy_pll *pll = g12a_ephy_pll_to_dev(hw);
+ unsigned int val;
+
+ val = readl(pll->base + ETH_PLL_CTL0);
+
+ return (val & PLL_CTL0_LOCK_DIG) ? 1 : 0;
+}
+
+static void g12a_ephy_pll_init(struct clk_hw *hw)
+{
+ struct g12a_ephy_pll *pll = g12a_ephy_pll_to_dev(hw);
+
+ /* Apply PLL HW settings */
+ writel(0x29c0040a, pll->base + ETH_PLL_CTL0);
+ writel(0x927e0000, pll->base + ETH_PLL_CTL1);
+ writel(0xac5f49e5, pll->base + ETH_PLL_CTL2);
+ writel(0x00000000, pll->base + ETH_PLL_CTL3);
+ writel(0x00000000, pll->base + ETH_PLL_CTL4);
+ writel(0x20200000, pll->base + ETH_PLL_CTL5);
+ writel(0x0000c002, pll->base + ETH_PLL_CTL6);
+ writel(0x00000023, pll->base + ETH_PLL_CTL7);
+}
+
+static const struct clk_ops g12a_ephy_pll_ops = {
+ .recalc_rate = g12a_ephy_pll_recalc_rate,
+ .is_enabled = g12a_ephy_pll_is_enabled,
+ .enable = g12a_ephy_pll_enable,
+ .disable = g12a_ephy_pll_disable,
+ .init = g12a_ephy_pll_init,
+};
+
+static int g12a_enable_internal_mdio(struct g12a_mdio_mux *priv)
+{
+ int ret;
+
+ /* Enable the phy clock */
+ if (!priv->pll_is_enabled) {
+ ret = clk_prepare_enable(priv->pll);
+ if (ret)
+ return ret;
+ }
+
+ priv->pll_is_enabled = true;
+
+ /* Initialize ephy control */
+ writel(EPHY_G12A_ID, priv->regs + ETH_PHY_CNTL0);
+ writel(FIELD_PREP(PHY_CNTL1_ST_MODE, 3) |
+ FIELD_PREP(PHY_CNTL1_ST_PHYADD, EPHY_DFLT_ADD) |
+ FIELD_PREP(PHY_CNTL1_MII_MODE, EPHY_MODE_RMII) |
+ PHY_CNTL1_CLK_EN |
+ PHY_CNTL1_CLKFREQ |
+ PHY_CNTL1_PHY_ENB,
+ priv->regs + ETH_PHY_CNTL1);
+ writel(PHY_CNTL2_USE_INTERNAL |
+ PHY_CNTL2_SMI_SRC_MAC |
+ PHY_CNTL2_RX_CLK_EPHY,
+ priv->regs + ETH_PHY_CNTL2);
+
+ return 0;
+}
+
+static int g12a_enable_external_mdio(struct g12a_mdio_mux *priv)
+{
+ /* Reset the mdio bus mux */
+ writel_relaxed(0x0, priv->regs + ETH_PHY_CNTL2);
+
+ /* Disable the phy clock if enabled */
+ if (priv->pll_is_enabled) {
+ clk_disable_unprepare(priv->pll);
+ priv->pll_is_enabled = false;
+ }
+
+ return 0;
+}
+
+static int g12a_mdio_switch_fn(int current_child, int desired_child,
+ void *data)
+{
+ struct g12a_mdio_mux *priv = dev_get_drvdata(data);
+
+ if (current_child == desired_child)
+ return 0;
+
+ switch (desired_child) {
+ case MESON_G12A_MDIO_EXTERNAL_ID:
+ return g12a_enable_external_mdio(priv);
+ case MESON_G12A_MDIO_INTERNAL_ID:
+ return g12a_enable_internal_mdio(priv);
+ default:
+ return -EINVAL;
+ }
+}
+
+static const struct of_device_id g12a_mdio_mux_match[] = {
+ { .compatible = "amlogic,g12a-mdio-mux", },
+ {},
+};
+MODULE_DEVICE_TABLE(of, g12a_mdio_mux_match);
+
+static int g12a_ephy_glue_clk_register(struct device *dev)
+{
+ struct g12a_mdio_mux *priv = dev_get_drvdata(dev);
+ const char *parent_names[PLL_MUX_NUM_PARENT];
+ struct clk_init_data init;
+ struct g12a_ephy_pll *pll;
+ struct clk_mux *mux;
+ struct clk *clk;
+ char *name;
+ int i;
+
+ /* get the mux parents */
+ for (i = 0; i < PLL_MUX_NUM_PARENT; i++) {
+ char in_name[8];
+
+ snprintf(in_name, sizeof(in_name), "clkin%d", i);
+ clk = devm_clk_get(dev, in_name);
+ if (IS_ERR(clk)) {
+ if (PTR_ERR(clk) != -EPROBE_DEFER)
+ dev_err(dev, "Missing clock %s\n", in_name);
+ return PTR_ERR(clk);
+ }
+
+ parent_names[i] = __clk_get_name(clk);
+ }
+
+ /* create the input mux */
+ mux = devm_kzalloc(dev, sizeof(*mux), GFP_KERNEL);
+ if (!mux)
+ return -ENOMEM;
+
+ name = kasprintf(GFP_KERNEL, "%s#mux", dev_name(dev));
+ if (!name)
+ return -ENOMEM;
+
+ init.name = name;
+ init.ops = &clk_mux_ro_ops;
+ init.flags = 0;
+ init.parent_names = parent_names;
+ init.num_parents = PLL_MUX_NUM_PARENT;
+
+ mux->reg = priv->regs + ETH_PLL_CTL0;
+ mux->shift = __ffs(PLL_CTL0_SEL);
+ mux->mask = PLL_CTL0_SEL >> mux->shift;
+ mux->hw.init = &init;
+
+ clk = devm_clk_register(dev, &mux->hw);
+ kfree(name);
+ if (IS_ERR(clk)) {
+ dev_err(dev, "failed to register input mux\n");
+ return PTR_ERR(clk);
+ }
+
+ /* create the pll */
+ pll = devm_kzalloc(dev, sizeof(*pll), GFP_KERNEL);
+ if (!pll)
+ return -ENOMEM;
+
+ name = kasprintf(GFP_KERNEL, "%s#pll", dev_name(dev));
+ if (!name)
+ return -ENOMEM;
+
+ init.name = name;
+ init.ops = &g12a_ephy_pll_ops;
+ init.flags = 0;
+ parent_names[0] = __clk_get_name(clk);
+ init.parent_names = parent_names;
+ init.num_parents = 1;
+
+ pll->base = priv->regs;
+ pll->hw.init = &init;
+
+ clk = devm_clk_register(dev, &pll->hw);
+ kfree(name);
+ if (IS_ERR(clk)) {
+ dev_err(dev, "failed to register input mux\n");
+ return PTR_ERR(clk);
+ }
+
+ priv->pll = clk;
+
+ return 0;
+}
+
+static int g12a_mdio_mux_probe(struct platform_device *pdev)
+{
+ struct device *dev = &pdev->dev;
+ struct g12a_mdio_mux *priv;
+ struct resource *res;
+ int ret;
+
+ priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+ if (!priv)
+ return -ENOMEM;
+
+ platform_set_drvdata(pdev, priv);
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ priv->regs = devm_ioremap_resource(dev, res);
+ if (IS_ERR(priv->regs))
+ return PTR_ERR(priv->regs);
+
+ priv->pclk = devm_clk_get(dev, "pclk");
+ if (IS_ERR(priv->pclk)) {
+ ret = PTR_ERR(priv->pclk);
+ if (ret != -EPROBE_DEFER)
+ dev_err(dev, "failed to get peripheral clock\n");
+ return ret;
+ }
+
+ /* Make sure the device registers are clocked */
+ ret = clk_prepare_enable(priv->pclk);
+ if (ret) {
+ dev_err(dev, "failed to enable peripheral clock");
+ return ret;
+ }
+
+ /* Register PLL in CCF */
+ ret = g12a_ephy_glue_clk_register(dev);
+ if (ret)
+ goto err;
+
+ ret = mdio_mux_init(dev, dev->of_node, g12a_mdio_switch_fn,
+ &priv->mux_handle, dev, NULL);
+ if (ret) {
+ if (ret != -EPROBE_DEFER)
+ dev_err(dev, "mdio multiplexer init failed: %d", ret);
+ goto err;
+ }
+
+ return 0;
+
+err:
+ clk_disable_unprepare(priv->pclk);
+ return ret;
+}
+
+static int g12a_mdio_mux_remove(struct platform_device *pdev)
+{
+ struct g12a_mdio_mux *priv = platform_get_drvdata(pdev);
+
+ mdio_mux_uninit(priv->mux_handle);
+
+ if (priv->pll_is_enabled)
+ clk_disable_unprepare(priv->pll);
+
+ clk_disable_unprepare(priv->pclk);
+
+ return 0;
+}
+
+static struct platform_driver g12a_mdio_mux_driver = {
+ .probe = g12a_mdio_mux_probe,
+ .remove = g12a_mdio_mux_remove,
+ .driver = {
+ .name = "g12a-mdio_mux",
+ .of_match_table = g12a_mdio_mux_match,
+ },
+};
+module_platform_driver(g12a_mdio_mux_driver);
+
+MODULE_DESCRIPTION("Amlogic G12a MDIO multiplexer driver");
+MODULE_AUTHOR("Jerome Brunet <jbrunet@baylibre.com>");
+MODULE_LICENSE("GPL v2");
static struct phy_driver meson_gxl_phy[] = {
{
- .phy_id = 0x01814400,
- .phy_id_mask = 0xfffffff0,
+ PHY_ID_MATCH_EXACT(0x01814400),
.name = "Meson GXL Internal PHY",
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.flags = PHY_IS_INTERNAL,
.soft_reset = genphy_soft_reset,
.config_init = meson_gxl_config_init,
- .aneg_done = genphy_aneg_done,
.read_status = meson_gxl_read_status,
.ack_interrupt = meson_gxl_ack_interrupt,
.config_intr = meson_gxl_config_intr,
.suspend = genphy_suspend,
.resume = genphy_resume,
+ }, {
+ PHY_ID_MATCH_EXACT(0x01803301),
+ .name = "Meson G12A Internal PHY",
+ /* PHY_BASIC_FEATURES */
+ .flags = PHY_IS_INTERNAL,
+ .soft_reset = genphy_soft_reset,
+ .ack_interrupt = meson_gxl_ack_interrupt,
+ .config_intr = meson_gxl_config_intr,
+ .suspend = genphy_suspend,
+ .resume = genphy_resume,
},
};
static struct mdio_device_id __maybe_unused meson_gxl_tbl[] = {
- { 0x01814400, 0xfffffff0 },
+ { PHY_ID_MATCH_VENDOR(0x01814400) },
+ { PHY_ID_MATCH_VENDOR(0x01803301) },
{ }
};
return 0;
}
+static int ksz9031_get_features(struct phy_device *phydev)
+{
+ int ret;
+
+ ret = genphy_read_abilities(phydev);
+ if (ret < 0)
+ return ret;
+
+ /* Silicon Errata Sheet (DS80000691D or DS80000692D):
+ * Whenever the device's Asymmetric Pause capability is set to 1,
+ * link-up may fail after a link-up to link-down transition.
+ *
+ * Workaround:
+ * Do not enable the Asymmetric Pause capability bit.
+ */
+ linkmode_clear_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, phydev->supported);
+
+ /* We force setting the Pause capability as the core will force the
+ * Asymmetric Pause capability to 1 otherwise.
+ */
+ linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, phydev->supported);
+
+ return 0;
+}
+
static int ksz9031_read_status(struct phy_device *phydev)
{
int err;
.phy_id = PHY_ID_KS8737,
.phy_id_mask = MICREL_PHY_ID_MASK,
.name = "Micrel KS8737",
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.driver_data = &ks8737_type,
.config_init = kszphy_config_init,
.ack_interrupt = kszphy_ack_interrupt,
.phy_id = PHY_ID_KSZ8021,
.phy_id_mask = 0x00ffffff,
.name = "Micrel KSZ8021 or KSZ8031",
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.driver_data = &ksz8021_type,
.probe = kszphy_probe,
.config_init = kszphy_config_init,
.phy_id = PHY_ID_KSZ8031,
.phy_id_mask = 0x00ffffff,
.name = "Micrel KSZ8031",
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.driver_data = &ksz8021_type,
.probe = kszphy_probe,
.config_init = kszphy_config_init,
.phy_id = PHY_ID_KSZ8041,
.phy_id_mask = MICREL_PHY_ID_MASK,
.name = "Micrel KSZ8041",
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.driver_data = &ksz8041_type,
.probe = kszphy_probe,
.config_init = ksz8041_config_init,
.phy_id = PHY_ID_KSZ8041RNLI,
.phy_id_mask = MICREL_PHY_ID_MASK,
.name = "Micrel KSZ8041RNLI",
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.driver_data = &ksz8041_type,
.probe = kszphy_probe,
.config_init = kszphy_config_init,
.phy_id = PHY_ID_KSZ8051,
.phy_id_mask = MICREL_PHY_ID_MASK,
.name = "Micrel KSZ8051",
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.driver_data = &ksz8051_type,
.probe = kszphy_probe,
.config_init = kszphy_config_init,
.phy_id = PHY_ID_KSZ8001,
.name = "Micrel KSZ8001 or KS8721",
.phy_id_mask = 0x00fffffc,
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.driver_data = &ksz8041_type,
.probe = kszphy_probe,
.config_init = kszphy_config_init,
.phy_id = PHY_ID_KSZ8081,
.name = "Micrel KSZ8081 or KSZ8091",
.phy_id_mask = MICREL_PHY_ID_MASK,
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.driver_data = &ksz8081_type,
.probe = kszphy_probe,
.config_init = kszphy_config_init,
.phy_id = PHY_ID_KSZ8061,
.name = "Micrel KSZ8061",
.phy_id_mask = MICREL_PHY_ID_MASK,
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.config_init = ksz8061_config_init,
.ack_interrupt = kszphy_ack_interrupt,
.config_intr = kszphy_config_intr,
.phy_id = PHY_ID_KSZ9021,
.phy_id_mask = 0x000ffffe,
.name = "Micrel KSZ9021 Gigabit PHY",
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.driver_data = &ksz9021_type,
.probe = kszphy_probe,
.config_init = ksz9021_config_init,
.phy_id = PHY_ID_KSZ9031,
.phy_id_mask = MICREL_PHY_ID_MASK,
.name = "Micrel KSZ9031 Gigabit PHY",
- .features = PHY_GBIT_FEATURES,
.driver_data = &ksz9021_type,
.probe = kszphy_probe,
+ .get_features = ksz9031_get_features,
.config_init = ksz9031_config_init,
.soft_reset = genphy_soft_reset,
.read_status = ksz9031_read_status,
.phy_id = PHY_ID_KSZ9131,
.phy_id_mask = MICREL_PHY_ID_MASK,
.name = "Microchip KSZ9131 Gigabit PHY",
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.driver_data = &ksz9021_type,
.probe = kszphy_probe,
.config_init = ksz9131_config_init,
.phy_id = PHY_ID_KSZ8873MLL,
.phy_id_mask = MICREL_PHY_ID_MASK,
.name = "Micrel KSZ8873MLL Switch",
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.config_init = kszphy_config_init,
.config_aneg = ksz8873mll_config_aneg,
.read_status = ksz8873mll_read_status,
.phy_id = PHY_ID_KSZ886X,
.phy_id_mask = MICREL_PHY_ID_MASK,
.name = "Micrel KSZ886X Switch",
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.config_init = kszphy_config_init,
.suspend = genphy_suspend,
.resume = genphy_resume,
.phy_id = PHY_ID_KSZ8795,
.phy_id_mask = MICREL_PHY_ID_MASK,
.name = "Micrel KSZ8795",
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.config_init = kszphy_config_init,
.config_aneg = ksz8873mll_config_aneg,
.read_status = ksz8873mll_read_status,
.phy_id = PHY_ID_KSZ9477,
.phy_id_mask = MICREL_PHY_ID_MASK,
.name = "Microchip KSZ9477",
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.config_init = kszphy_config_init,
.suspend = genphy_suspend,
.resume = genphy_resume,
.phy_id_mask = 0xfffffff0,
.name = "Microchip LAN88xx",
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.probe = lan88xx_probe,
.remove = lan88xx_remove,
.phy_id = PHY_ID_VSC8530,
.name = "Microsemi FE VSC8530",
.phy_id_mask = 0xfffffff0,
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.soft_reset = &genphy_soft_reset,
.config_init = &vsc85xx_config_init,
.config_aneg = &vsc85xx_config_aneg,
.phy_id = PHY_ID_VSC8531,
.name = "Microsemi VSC8531",
.phy_id_mask = 0xfffffff0,
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.soft_reset = &genphy_soft_reset,
.config_init = &vsc85xx_config_init,
.config_aneg = &vsc85xx_config_aneg,
.phy_id = PHY_ID_VSC8540,
.name = "Microsemi FE VSC8540 SyncE",
.phy_id_mask = 0xfffffff0,
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.soft_reset = &genphy_soft_reset,
.config_init = &vsc85xx_config_init,
.config_aneg = &vsc85xx_config_aneg,
.phy_id = PHY_ID_VSC8541,
.name = "Microsemi VSC8541 SyncE",
.phy_id_mask = 0xfffffff0,
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.soft_reset = &genphy_soft_reset,
.config_init = &vsc85xx_config_init,
.config_aneg = &vsc85xx_config_aneg,
.phy_id = PHY_ID_VSC8574,
.name = "Microsemi GE VSC8574 SyncE",
.phy_id_mask = 0xfffffff0,
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.soft_reset = &genphy_soft_reset,
.config_init = &vsc8584_config_init,
.config_aneg = &vsc85xx_config_aneg,
.phy_id = PHY_ID_VSC8584,
.name = "Microsemi GE VSC8584 SyncE",
.phy_id_mask = 0xfffffff0,
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.soft_reset = &genphy_soft_reset,
.config_init = &vsc8584_config_init,
.config_aneg = &vsc85xx_config_aneg,
.phy_id = DP83865_PHY_ID,
.phy_id_mask = 0xfffffff0,
.name = "NatSemi DP83865",
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.config_init = ns_config_init,
.ack_interrupt = ns_ack_interrupt,
.config_intr = ns_config_intr,
{
int val;
+ val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_STAT1);
+ if (val < 0)
+ return val;
+
+ if (!(val & MDIO_AN_STAT1_COMPLETE)) {
+ linkmode_clear_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
+ phydev->lp_advertising);
+ mii_10gbt_stat_mod_linkmode_lpa_t(phydev->lp_advertising, 0);
+ mii_adv_mod_linkmode_adv_t(phydev->lp_advertising, 0);
+ phydev->pause = 0;
+ phydev->asym_pause = 0;
+
+ return 0;
+ }
+
+ linkmode_mod_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, phydev->lp_advertising,
+ val & MDIO_AN_STAT1_LPABLE);
+
/* Read the link partner's base page advertisement */
val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_LPA);
if (val < 0)
return val;
- mii_lpa_mod_linkmode_lpa_t(phydev->lp_advertising, val);
+ mii_adv_mod_linkmode_adv_t(phydev->lp_advertising, val);
phydev->pause = val & LPA_PAUSE_CAP ? 1 : 0;
phydev->asym_pause = val & LPA_PAUSE_ASYM ? 1 : 0;
}
EXPORT_SYMBOL_GPL(gen10g_config_aneg);
-static int gen10g_read_status(struct phy_device *phydev)
-{
- /* For now just lie and say it's 10G all the time */
- phydev->speed = SPEED_10000;
- phydev->duplex = DUPLEX_FULL;
-
- return genphy_c45_read_link(phydev);
-}
-
-struct phy_driver genphy_10g_driver = {
+struct phy_driver genphy_c45_driver = {
.phy_id = 0xffffffff,
.phy_id_mask = 0xffffffff,
- .name = "Generic 10G PHY",
+ .name = "Generic Clause 45 PHY",
.soft_reset = genphy_no_soft_reset,
- .features = PHY_10GBIT_FEATURES,
- .config_aneg = gen10g_config_aneg,
- .read_status = gen10g_read_status,
+ .read_status = genphy_c45_read_status,
};
const char *phy_speed_to_str(int speed)
{
+ BUILD_BUG_ON_MSG(__ETHTOOL_LINK_MODE_MASK_NBITS != 67,
+ "Enum ethtool_link_mode_bit_indices and phylib are out of sync. "
+ "If a speed or mode has been added please update phy_speed_to_str "
+ "and the PHY settings array.\n");
+
switch (speed) {
case SPEED_10:
return "10Mbps";
return "56Gbps";
case SPEED_100000:
return "100Gbps";
+ case SPEED_200000:
+ return "200Gbps";
case SPEED_UNKNOWN:
return "Unknown";
default:
/* A mapping of all SUPPORTED settings to speed/duplex. This table
* must be grouped by speed and sorted in descending match priority
* - iow, descending speed. */
+
+#define PHY_SETTING(s, d, b) { .speed = SPEED_ ## s, .duplex = DUPLEX_ ## d, \
+ .bit = ETHTOOL_LINK_MODE_ ## b ## _BIT}
+
static const struct phy_setting settings[] = {
+ /* 200G */
+ PHY_SETTING( 200000, FULL, 200000baseCR4_Full ),
+ PHY_SETTING( 200000, FULL, 200000baseKR4_Full ),
+ PHY_SETTING( 200000, FULL, 200000baseLR4_ER4_FR4_Full ),
+ PHY_SETTING( 200000, FULL, 200000baseDR4_Full ),
+ PHY_SETTING( 200000, FULL, 200000baseSR4_Full ),
/* 100G */
- {
- .speed = SPEED_100000,
- .duplex = DUPLEX_FULL,
- .bit = ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT,
- },
- {
- .speed = SPEED_100000,
- .duplex = DUPLEX_FULL,
- .bit = ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT,
- },
- {
- .speed = SPEED_100000,
- .duplex = DUPLEX_FULL,
- .bit = ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT,
- },
- {
- .speed = SPEED_100000,
- .duplex = DUPLEX_FULL,
- .bit = ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT,
- },
+ PHY_SETTING( 100000, FULL, 100000baseCR4_Full ),
+ PHY_SETTING( 100000, FULL, 100000baseKR4_Full ),
+ PHY_SETTING( 100000, FULL, 100000baseLR4_ER4_Full ),
+ PHY_SETTING( 100000, FULL, 100000baseSR4_Full ),
+ PHY_SETTING( 100000, FULL, 100000baseCR2_Full ),
+ PHY_SETTING( 100000, FULL, 100000baseKR2_Full ),
+ PHY_SETTING( 100000, FULL, 100000baseLR2_ER2_FR2_Full ),
+ PHY_SETTING( 100000, FULL, 100000baseDR2_Full ),
+ PHY_SETTING( 100000, FULL, 100000baseSR2_Full ),
/* 56G */
- {
- .speed = SPEED_56000,
- .duplex = DUPLEX_FULL,
- .bit = ETHTOOL_LINK_MODE_56000baseCR4_Full_BIT,
- },
- {
- .speed = SPEED_56000,
- .duplex = DUPLEX_FULL,
- .bit = ETHTOOL_LINK_MODE_56000baseKR4_Full_BIT,
- },
- {
- .speed = SPEED_56000,
- .duplex = DUPLEX_FULL,
- .bit = ETHTOOL_LINK_MODE_56000baseLR4_Full_BIT,
- },
- {
- .speed = SPEED_56000,
- .duplex = DUPLEX_FULL,
- .bit = ETHTOOL_LINK_MODE_56000baseSR4_Full_BIT,
- },
+ PHY_SETTING( 56000, FULL, 56000baseCR4_Full ),
+ PHY_SETTING( 56000, FULL, 56000baseKR4_Full ),
+ PHY_SETTING( 56000, FULL, 56000baseLR4_Full ),
+ PHY_SETTING( 56000, FULL, 56000baseSR4_Full ),
/* 50G */
- {
- .speed = SPEED_50000,
- .duplex = DUPLEX_FULL,
- .bit = ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT,
- },
- {
- .speed = SPEED_50000,
- .duplex = DUPLEX_FULL,
- .bit = ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT,
- },
- {
- .speed = SPEED_50000,
- .duplex = DUPLEX_FULL,
- .bit = ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT,
- },
+ PHY_SETTING( 50000, FULL, 50000baseCR2_Full ),
+ PHY_SETTING( 50000, FULL, 50000baseKR2_Full ),
+ PHY_SETTING( 50000, FULL, 50000baseSR2_Full ),
+ PHY_SETTING( 50000, FULL, 50000baseCR_Full ),
+ PHY_SETTING( 50000, FULL, 50000baseKR_Full ),
+ PHY_SETTING( 50000, FULL, 50000baseLR_ER_FR_Full ),
+ PHY_SETTING( 50000, FULL, 50000baseDR_Full ),
+ PHY_SETTING( 50000, FULL, 50000baseSR_Full ),
/* 40G */
- {
- .speed = SPEED_40000,
- .duplex = DUPLEX_FULL,
- .bit = ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT,
- },
- {
- .speed = SPEED_40000,
- .duplex = DUPLEX_FULL,
- .bit = ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT,
- },
- {
- .speed = SPEED_40000,
- .duplex = DUPLEX_FULL,
- .bit = ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT,
- },
- {
- .speed = SPEED_40000,
- .duplex = DUPLEX_FULL,
- .bit = ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT,
- },
+ PHY_SETTING( 40000, FULL, 40000baseCR4_Full ),
+ PHY_SETTING( 40000, FULL, 40000baseKR4_Full ),
+ PHY_SETTING( 40000, FULL, 40000baseLR4_Full ),
+ PHY_SETTING( 40000, FULL, 40000baseSR4_Full ),
/* 25G */
- {
- .speed = SPEED_25000,
- .duplex = DUPLEX_FULL,
- .bit = ETHTOOL_LINK_MODE_25000baseCR_Full_BIT,
- },
- {
- .speed = SPEED_25000,
- .duplex = DUPLEX_FULL,
- .bit = ETHTOOL_LINK_MODE_25000baseKR_Full_BIT,
- },
- {
- .speed = SPEED_25000,
- .duplex = DUPLEX_FULL,
- .bit = ETHTOOL_LINK_MODE_25000baseSR_Full_BIT,
- },
-
+ PHY_SETTING( 25000, FULL, 25000baseCR_Full ),
+ PHY_SETTING( 25000, FULL, 25000baseKR_Full ),
+ PHY_SETTING( 25000, FULL, 25000baseSR_Full ),
/* 20G */
- {
- .speed = SPEED_20000,
- .duplex = DUPLEX_FULL,
- .bit = ETHTOOL_LINK_MODE_20000baseKR2_Full_BIT,
- },
- {
- .speed = SPEED_20000,
- .duplex = DUPLEX_FULL,
- .bit = ETHTOOL_LINK_MODE_20000baseMLD2_Full_BIT,
- },
+ PHY_SETTING( 20000, FULL, 20000baseKR2_Full ),
+ PHY_SETTING( 20000, FULL, 20000baseMLD2_Full ),
/* 10G */
- {
- .speed = SPEED_10000,
- .duplex = DUPLEX_FULL,
- .bit = ETHTOOL_LINK_MODE_10000baseCR_Full_BIT,
- },
- {
- .speed = SPEED_10000,
- .duplex = DUPLEX_FULL,
- .bit = ETHTOOL_LINK_MODE_10000baseER_Full_BIT,
- },
- {
- .speed = SPEED_10000,
- .duplex = DUPLEX_FULL,
- .bit = ETHTOOL_LINK_MODE_10000baseKR_Full_BIT,
- },
- {
- .speed = SPEED_10000,
- .duplex = DUPLEX_FULL,
- .bit = ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT,
- },
- {
- .speed = SPEED_10000,
- .duplex = DUPLEX_FULL,
- .bit = ETHTOOL_LINK_MODE_10000baseLR_Full_BIT,
- },
- {
- .speed = SPEED_10000,
- .duplex = DUPLEX_FULL,
- .bit = ETHTOOL_LINK_MODE_10000baseLRM_Full_BIT,
- },
- {
- .speed = SPEED_10000,
- .duplex = DUPLEX_FULL,
- .bit = ETHTOOL_LINK_MODE_10000baseR_FEC_BIT,
- },
- {
- .speed = SPEED_10000,
- .duplex = DUPLEX_FULL,
- .bit = ETHTOOL_LINK_MODE_10000baseSR_Full_BIT,
- },
- {
- .speed = SPEED_10000,
- .duplex = DUPLEX_FULL,
- .bit = ETHTOOL_LINK_MODE_10000baseT_Full_BIT,
- },
+ PHY_SETTING( 10000, FULL, 10000baseCR_Full ),
+ PHY_SETTING( 10000, FULL, 10000baseER_Full ),
+ PHY_SETTING( 10000, FULL, 10000baseKR_Full ),
+ PHY_SETTING( 10000, FULL, 10000baseKX4_Full ),
+ PHY_SETTING( 10000, FULL, 10000baseLR_Full ),
+ PHY_SETTING( 10000, FULL, 10000baseLRM_Full ),
+ PHY_SETTING( 10000, FULL, 10000baseR_FEC ),
+ PHY_SETTING( 10000, FULL, 10000baseSR_Full ),
+ PHY_SETTING( 10000, FULL, 10000baseT_Full ),
/* 5G */
- {
- .speed = SPEED_5000,
- .duplex = DUPLEX_FULL,
- .bit = ETHTOOL_LINK_MODE_5000baseT_Full_BIT,
- },
-
+ PHY_SETTING( 5000, FULL, 5000baseT_Full ),
/* 2.5G */
- {
- .speed = SPEED_2500,
- .duplex = DUPLEX_FULL,
- .bit = ETHTOOL_LINK_MODE_2500baseT_Full_BIT,
- },
- {
- .speed = SPEED_2500,
- .duplex = DUPLEX_FULL,
- .bit = ETHTOOL_LINK_MODE_2500baseX_Full_BIT,
- },
+ PHY_SETTING( 2500, FULL, 2500baseT_Full ),
+ PHY_SETTING( 2500, FULL, 2500baseX_Full ),
/* 1G */
- {
- .speed = SPEED_1000,
- .duplex = DUPLEX_FULL,
- .bit = ETHTOOL_LINK_MODE_1000baseKX_Full_BIT,
- },
- {
- .speed = SPEED_1000,
- .duplex = DUPLEX_FULL,
- .bit = ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
- },
- {
- .speed = SPEED_1000,
- .duplex = DUPLEX_HALF,
- .bit = ETHTOOL_LINK_MODE_1000baseT_Half_BIT,
- },
- {
- .speed = SPEED_1000,
- .duplex = DUPLEX_FULL,
- .bit = ETHTOOL_LINK_MODE_1000baseX_Full_BIT,
- },
+ PHY_SETTING( 1000, FULL, 1000baseKX_Full ),
+ PHY_SETTING( 1000, FULL, 1000baseT_Full ),
+ PHY_SETTING( 1000, HALF, 1000baseT_Half ),
+ PHY_SETTING( 1000, FULL, 1000baseX_Full ),
/* 100M */
- {
- .speed = SPEED_100,
- .duplex = DUPLEX_FULL,
- .bit = ETHTOOL_LINK_MODE_100baseT_Full_BIT,
- },
- {
- .speed = SPEED_100,
- .duplex = DUPLEX_HALF,
- .bit = ETHTOOL_LINK_MODE_100baseT_Half_BIT,
- },
+ PHY_SETTING( 100, FULL, 100baseT_Full ),
+ PHY_SETTING( 100, HALF, 100baseT_Half ),
/* 10M */
- {
- .speed = SPEED_10,
- .duplex = DUPLEX_FULL,
- .bit = ETHTOOL_LINK_MODE_10baseT_Full_BIT,
- },
- {
- .speed = SPEED_10,
- .duplex = DUPLEX_HALF,
- .bit = ETHTOOL_LINK_MODE_10baseT_Half_BIT,
- },
+ PHY_SETTING( 10, FULL, 10baseT_Full ),
+ PHY_SETTING( 10, HALF, 10baseT_Half ),
};
+#undef PHY_SETTING
/**
* phy_lookup_setting - lookup a PHY setting
}
static struct phy_driver genphy_driver;
-extern struct phy_driver genphy_10g_driver;
+extern struct phy_driver genphy_c45_driver;
static LIST_HEAD(phy_fixup_list);
static DEFINE_MUTEX(phy_fixup_lock);
*/
if (!d->driver) {
if (phydev->is_c45)
- d->driver = &genphy_10g_driver.mdiodrv.driver;
+ d->driver = &genphy_c45_driver.mdiodrv.driver;
else
d->driver = &genphy_driver.mdiodrv.driver;
bool phy_driver_is_genphy_10g(struct phy_device *phydev)
{
return phy_driver_is_genphy_kind(phydev,
- &genphy_10g_driver.mdiodrv.driver);
+ &genphy_c45_driver.mdiodrv.driver);
}
EXPORT_SYMBOL_GPL(phy_driver_is_genphy_10g);
*/
if (!phy_polling_mode(phydev)) {
status = phy_read(phydev, MII_BMSR);
- if (status < 0) {
+ if (status < 0)
return status;
- } else if (status & BMSR_LSTATUS) {
- phydev->link = 1;
- return 0;
- }
+ else if (status & BMSR_LSTATUS)
+ goto done;
}
/* Read link and autonegotiation status */
status = phy_read(phydev, MII_BMSR);
if (status < 0)
return status;
-
- if ((status & BMSR_LSTATUS) == 0)
- phydev->link = 0;
- else
- phydev->link = 1;
+done:
+ phydev->link = status & BMSR_LSTATUS ? 1 : 0;
+ phydev->autoneg_complete = status & BMSR_ANEGCOMPLETE ? 1 : 0;
return 0;
}
*/
int genphy_read_status(struct phy_device *phydev)
{
- int adv;
- int err;
- int lpa;
- int lpagb = 0;
+ int adv, lpa, lpagb, err;
/* Update the link, but return if there was an error */
err = genphy_update_link(phydev);
if (err)
return err;
+ phydev->speed = SPEED_UNKNOWN;
+ phydev->duplex = DUPLEX_UNKNOWN;
+ phydev->pause = 0;
+ phydev->asym_pause = 0;
+
linkmode_zero(phydev->lp_advertising);
- if (AUTONEG_ENABLE == phydev->autoneg) {
- if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT,
- phydev->supported) ||
- linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
- phydev->supported)) {
+ if (phydev->autoneg == AUTONEG_ENABLE && phydev->autoneg_complete) {
+ if (phydev->is_gigabit_capable) {
lpagb = phy_read(phydev, MII_STAT1000);
if (lpagb < 0)
return lpagb;
return lpa;
mii_lpa_mod_linkmode_lpa_t(phydev->lp_advertising, lpa);
-
- phydev->speed = SPEED_UNKNOWN;
- phydev->duplex = DUPLEX_UNKNOWN;
- phydev->pause = 0;
- phydev->asym_pause = 0;
-
phy_resolve_aneg_linkmode(phydev);
- } else {
+ } else if (phydev->autoneg == AUTONEG_DISABLE) {
int bmcr = phy_read(phydev, MII_BMCR);
if (bmcr < 0)
phydev->speed = SPEED_100;
else
phydev->speed = SPEED_10;
-
- phydev->pause = 0;
- phydev->asym_pause = 0;
}
return 0;
}
EXPORT_SYMBOL(genphy_config_init);
+/**
+ * genphy_read_abilities - read PHY abilities from Clause 22 registers
+ * @phydev: target phy_device struct
+ *
+ * Description: Reads the PHY's abilities and populates
+ * phydev->supported accordingly.
+ *
+ * Returns: 0 on success, < 0 on failure
+ */
+int genphy_read_abilities(struct phy_device *phydev)
+{
+ int val;
+
+ linkmode_set_bit_array(phy_basic_ports_array,
+ ARRAY_SIZE(phy_basic_ports_array),
+ phydev->supported);
+
+ val = phy_read(phydev, MII_BMSR);
+ if (val < 0)
+ return val;
+
+ linkmode_mod_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, phydev->supported,
+ val & BMSR_ANEGCAPABLE);
+
+ linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, phydev->supported,
+ val & BMSR_100FULL);
+ linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, phydev->supported,
+ val & BMSR_100HALF);
+ linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, phydev->supported,
+ val & BMSR_10FULL);
+ linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, phydev->supported,
+ val & BMSR_10HALF);
+
+ if (val & BMSR_ESTATEN) {
+ val = phy_read(phydev, MII_ESTATUS);
+ if (val < 0)
+ return val;
+
+ linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
+ phydev->supported, val & ESTATUS_1000_TFULL);
+ linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT,
+ phydev->supported, val & ESTATUS_1000_THALF);
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL(genphy_read_abilities);
+
/* This is used for the phy device which doesn't support the MMD extended
* register access, but it does have side effect when we are trying to access
* the MMD register via indirect method.
*/
if (phydrv->features) {
linkmode_copy(phydev->supported, phydrv->features);
- } else {
+ } else if (phydrv->get_features) {
err = phydrv->get_features(phydev);
- if (err)
- goto out;
+ } else if (phydev->is_c45) {
+ err = genphy_c45_pma_read_abilities(phydev);
+ } else {
+ err = genphy_read_abilities(phydev);
}
+ if (err)
+ goto out;
+
+ if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT,
+ phydev->supported))
+ phydev->is_gigabit_capable = 1;
+ if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
+ phydev->supported))
+ phydev->is_gigabit_capable = 1;
+
of_set_phy_supported(phydev);
linkmode_copy(phydev->advertising, phydev->supported);
int retval;
/* Either the features are hard coded, or dynamically
- * determine. It cannot be both or neither
+ * determined. It cannot be both.
*/
- if (WARN_ON((!new_driver->features && !new_driver->get_features) ||
- (new_driver->features && new_driver->get_features))) {
- pr_err("%s: Driver features are missing\n", new_driver->name);
+ if (WARN_ON(new_driver->features && new_driver->get_features)) {
+ pr_err("%s: features and get_features must not both be set\n",
+ new_driver->name);
return -EINVAL;
}
.phy_id_mask = 0xffffffff,
.name = "Generic PHY",
.soft_reset = genphy_no_soft_reset,
- .config_init = genphy_config_init,
- .features = PHY_GBIT_ALL_PORTS_FEATURES,
+ .get_features = genphy_read_abilities,
.aneg_done = genphy_aneg_done,
.suspend = genphy_suspend,
.resume = genphy_resume,
features_init();
- rc = phy_driver_register(&genphy_10g_driver, THIS_MODULE);
+ rc = phy_driver_register(&genphy_c45_driver, THIS_MODULE);
if (rc)
- goto err_10g;
+ goto err_c45;
rc = phy_driver_register(&genphy_driver, THIS_MODULE);
if (rc) {
- phy_driver_unregister(&genphy_10g_driver);
-err_10g:
+ phy_driver_unregister(&genphy_c45_driver);
+err_c45:
mdio_bus_exit();
}
static void __exit phy_exit(void)
{
- phy_driver_unregister(&genphy_10g_driver);
+ phy_driver_unregister(&genphy_c45_driver);
phy_driver_unregister(&genphy_driver);
mdio_bus_exit();
}
.phy_id = 0x00181440,
.name = "QS6612",
.phy_id_mask = 0xfffffff0,
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.config_init = qs6612_config_init,
.ack_interrupt = qs6612_ack_interrupt,
.config_intr = qs6612_config_intr,
static int rtl8211c_config_init(struct phy_device *phydev)
{
/* RTL8211C has an issue when operating in Gigabit slave mode */
- phy_set_bits(phydev, MII_CTRL1000,
- CTL1000_ENABLE_MASTER | CTL1000_AS_MASTER);
-
- return genphy_config_init(phydev);
+ return phy_set_bits(phydev, MII_CTRL1000,
+ CTL1000_ENABLE_MASTER | CTL1000_AS_MASTER);
}
static int rtl8211f_config_init(struct phy_device *phydev)
{
- int ret;
u16 val = 0;
- ret = genphy_config_init(phydev);
- if (ret < 0)
- return ret;
-
/* enable TX-delay for rgmii-id and rgmii-txid, otherwise disable it */
if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID ||
phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID)
{
int ret;
- ret = genphy_config_init(phydev);
- if (ret < 0)
- return ret;
-
ret = phy_set_bits(phydev, RTL8366RB_POWER_SAVE,
RTL8366RB_POWER_SAVE_ON);
if (ret) {
{
PHY_ID_MATCH_EXACT(0x00008201),
.name = "RTL8201CP Ethernet",
- .features = PHY_BASIC_FEATURES,
}, {
PHY_ID_MATCH_EXACT(0x001cc816),
.name = "RTL8201F Fast Ethernet",
- .features = PHY_BASIC_FEATURES,
.ack_interrupt = &rtl8201_ack_interrupt,
.config_intr = &rtl8201_config_intr,
.suspend = genphy_suspend,
}, {
PHY_ID_MATCH_EXACT(0x001cc910),
.name = "RTL8211 Gigabit Ethernet",
- .features = PHY_GBIT_FEATURES,
.config_aneg = rtl8211_config_aneg,
.read_mmd = &genphy_read_mmd_unsupported,
.write_mmd = &genphy_write_mmd_unsupported,
}, {
PHY_ID_MATCH_EXACT(0x001cc912),
.name = "RTL8211B Gigabit Ethernet",
- .features = PHY_GBIT_FEATURES,
.ack_interrupt = &rtl821x_ack_interrupt,
.config_intr = &rtl8211b_config_intr,
.read_mmd = &genphy_read_mmd_unsupported,
}, {
PHY_ID_MATCH_EXACT(0x001cc913),
.name = "RTL8211C Gigabit Ethernet",
- .features = PHY_GBIT_FEATURES,
.config_init = rtl8211c_config_init,
.read_mmd = &genphy_read_mmd_unsupported,
.write_mmd = &genphy_write_mmd_unsupported,
}, {
PHY_ID_MATCH_EXACT(0x001cc914),
.name = "RTL8211DN Gigabit Ethernet",
- .features = PHY_GBIT_FEATURES,
.ack_interrupt = rtl821x_ack_interrupt,
.config_intr = rtl8211e_config_intr,
.suspend = genphy_suspend,
}, {
PHY_ID_MATCH_EXACT(0x001cc915),
.name = "RTL8211E Gigabit Ethernet",
- .features = PHY_GBIT_FEATURES,
.ack_interrupt = &rtl821x_ack_interrupt,
.config_intr = &rtl8211e_config_intr,
.suspend = genphy_suspend,
}, {
PHY_ID_MATCH_EXACT(0x001cc916),
.name = "RTL8211F Gigabit Ethernet",
- .features = PHY_GBIT_FEATURES,
.config_init = &rtl8211f_config_init,
.ack_interrupt = &rtl8211f_ack_interrupt,
.config_intr = &rtl8211f_config_intr,
}, {
PHY_ID_MATCH_EXACT(0x001cc800),
.name = "Generic Realtek PHY",
- .features = PHY_GBIT_FEATURES,
- .config_init = genphy_config_init,
.suspend = genphy_suspend,
.resume = genphy_resume,
.read_page = rtl821x_read_page,
}, {
PHY_ID_MATCH_EXACT(0x001cc961),
.name = "RTL8366RB Gigabit Ethernet",
- .features = PHY_GBIT_FEATURES,
.config_init = &rtl8366rb_config_init,
/* These interrupts are handled by the irq controller
* embedded inside the RTL8366RB, they get unmasked when the
.phy_id = INTERNAL_EPHY_ID,
.phy_id_mask = 0xfffffff0,
.name = "Rockchip integrated EPHY",
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.flags = 0,
.link_change_notify = rockchip_link_change_notify,
.soft_reset = genphy_soft_reset,
.phy_id_mask = 0xfffffff0,
.name = "SMSC LAN83C185",
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.probe = smsc_phy_probe,
.phy_id_mask = 0xfffffff0,
.name = "SMSC LAN8187",
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.probe = smsc_phy_probe,
.phy_id_mask = 0xfffffff0,
.name = "SMSC LAN8700",
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.probe = smsc_phy_probe,
.phy_id_mask = 0xfffffff0,
.name = "SMSC LAN911x Internal PHY",
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.probe = smsc_phy_probe,
.phy_id_mask = 0xfffffff0,
.name = "SMSC LAN8710/LAN8720",
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.flags = PHY_RST_AFTER_CLK_EN,
.probe = smsc_phy_probe,
.phy_id_mask = 0xfffffff0,
.name = "SMSC LAN8740",
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.probe = smsc_phy_probe,
.phy_id = STE101P_PHY_ID,
.phy_id_mask = 0xfffffff0,
.name = "STe101p",
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.config_init = ste10Xp_config_init,
.ack_interrupt = ste10Xp_ack_interrupt,
.config_intr = ste10Xp_config_intr,
.phy_id = STE100P_PHY_ID,
.phy_id_mask = 0xffffffff,
.name = "STe100p",
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.config_init = ste10Xp_config_init,
.ack_interrupt = ste10Xp_ack_interrupt,
.config_intr = ste10Xp_config_intr,
.phy_id = UPD60620_PHY_ID,
.phy_id_mask = 0xfffffffe,
.name = "Renesas uPD60620",
- .features = PHY_BASIC_FEATURES,
+ /* PHY_BASIC_FEATURES */
.flags = 0,
.config_init = upd60620_config_init,
.read_status = upd60620_read_status,
.phy_id = PHY_ID_VSC8234,
.name = "Vitesse VSC8234",
.phy_id_mask = 0x000ffff0,
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.config_init = &vsc824x_config_init,
.config_aneg = &vsc82x4_config_aneg,
.ack_interrupt = &vsc824x_ack_interrupt,
.phy_id = PHY_ID_VSC8244,
.name = "Vitesse VSC8244",
.phy_id_mask = 0x000fffc0,
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.config_init = &vsc824x_config_init,
.config_aneg = &vsc82x4_config_aneg,
.ack_interrupt = &vsc824x_ack_interrupt,
.phy_id = PHY_ID_VSC8572,
.name = "Vitesse VSC8572",
.phy_id_mask = 0x000ffff0,
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.config_init = &vsc824x_config_init,
.config_aneg = &vsc82x4_config_aneg,
.ack_interrupt = &vsc824x_ack_interrupt,
.phy_id = PHY_ID_VSC8601,
.name = "Vitesse VSC8601",
.phy_id_mask = 0x000ffff0,
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.config_init = &vsc8601_config_init,
.ack_interrupt = &vsc824x_ack_interrupt,
.config_intr = &vsc82xx_config_intr,
.phy_id = PHY_ID_VSC7385,
.name = "Vitesse VSC7385",
.phy_id_mask = 0x000ffff0,
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.config_init = vsc738x_config_init,
.config_aneg = vsc73xx_config_aneg,
.read_page = vsc73xx_read_page,
.phy_id = PHY_ID_VSC7388,
.name = "Vitesse VSC7388",
.phy_id_mask = 0x000ffff0,
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.config_init = vsc738x_config_init,
.config_aneg = vsc73xx_config_aneg,
.read_page = vsc73xx_read_page,
.phy_id = PHY_ID_VSC7395,
.name = "Vitesse VSC7395",
.phy_id_mask = 0x000ffff0,
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.config_init = vsc739x_config_init,
.config_aneg = vsc73xx_config_aneg,
.read_page = vsc73xx_read_page,
.phy_id = PHY_ID_VSC7398,
.name = "Vitesse VSC7398",
.phy_id_mask = 0x000ffff0,
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.config_init = vsc739x_config_init,
.config_aneg = vsc73xx_config_aneg,
.read_page = vsc73xx_read_page,
.phy_id = PHY_ID_VSC8662,
.name = "Vitesse VSC8662",
.phy_id_mask = 0x000ffff0,
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.config_init = &vsc824x_config_init,
.config_aneg = &vsc82x4_config_aneg,
.ack_interrupt = &vsc824x_ack_interrupt,
.phy_id = PHY_ID_VSC8221,
.phy_id_mask = 0x000ffff0,
.name = "Vitesse VSC8221",
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.config_init = &vsc8221_config_init,
.ack_interrupt = &vsc824x_ack_interrupt,
.config_intr = &vsc82xx_config_intr,
.phy_id = PHY_ID_VSC8211,
.phy_id_mask = 0x000ffff0,
.name = "Vitesse VSC8211",
- .features = PHY_GBIT_FEATURES,
+ /* PHY_GBIT_FEATURES */
.config_init = &vsc8221_config_init,
.ack_interrupt = &vsc824x_ack_interrupt,
.config_intr = &vsc82xx_config_intr,
goto err_option_port_add;
}
+ /* set promiscuity level to new slave */
+ if (dev->flags & IFF_PROMISC) {
+ err = dev_set_promiscuity(port_dev, 1);
+ if (err)
+ goto err_set_slave_promisc;
+ }
+
+ /* set allmulti level to new slave */
+ if (dev->flags & IFF_ALLMULTI) {
+ err = dev_set_allmulti(port_dev, 1);
+ if (err) {
+ if (dev->flags & IFF_PROMISC)
+ dev_set_promiscuity(port_dev, -1);
+ goto err_set_slave_promisc;
+ }
+ }
+
netif_addr_lock_bh(dev);
dev_uc_sync_multiple(port_dev, dev);
dev_mc_sync_multiple(port_dev, dev);
return 0;
+err_set_slave_promisc:
+ __team_option_inst_del_port(team, port);
+
err_option_port_add:
team_upper_dev_unlink(team, port);
team_port_disable(team, port);
list_del_rcu(&port->list);
+
+ if (dev->flags & IFF_PROMISC)
+ dev_set_promiscuity(port_dev, -1);
+ if (dev->flags & IFF_ALLMULTI)
+ dev_set_allmulti(port_dev, -1);
+
team_upper_dev_unlink(team, port);
netdev_rx_handler_unregister(port_dev);
team_port_disable_netpoll(port);
enum qmi_wwan_quirks {
QMI_WWAN_QUIRK_DTR = 1 << 0, /* needs "set DTR" request */
+ QMI_WWAN_QUIRK_QUECTEL_DYNCFG = 1 << 1, /* check num. endpoints */
};
struct qmimux_hdr {
.data = QMI_WWAN_QUIRK_DTR,
};
+static const struct driver_info qmi_wwan_info_quirk_quectel_dyncfg = {
+ .description = "WWAN/QMI device",
+ .flags = FLAG_WWAN | FLAG_SEND_ZLP,
+ .bind = qmi_wwan_bind,
+ .unbind = qmi_wwan_unbind,
+ .manage_power = qmi_wwan_manage_power,
+ .rx_fixup = qmi_wwan_rx_fixup,
+ .data = QMI_WWAN_QUIRK_DTR | QMI_WWAN_QUIRK_QUECTEL_DYNCFG,
+};
+
#define HUAWEI_VENDOR_ID 0x12D1
/* map QMI/wwan function by a fixed interface number */
#define QMI_GOBI_DEVICE(vend, prod) \
QMI_FIXED_INTF(vend, prod, 0)
+/* Quectel does not use fixed interface numbers on at least some of their
+ * devices. We need to check the number of endpoints to ensure that we bind to
+ * the correct interface.
+ */
+#define QMI_QUIRK_QUECTEL_DYNCFG(vend, prod) \
+ USB_DEVICE_AND_INTERFACE_INFO(vend, prod, USB_CLASS_VENDOR_SPEC, \
+ USB_SUBCLASS_VENDOR_SPEC, 0xff), \
+ .driver_info = (unsigned long)&qmi_wwan_info_quirk_quectel_dyncfg
+
static const struct usb_device_id products[] = {
/* 1. CDC ECM like devices match on the control interface */
{ /* Huawei E392, E398 and possibly others sharing both device id and more... */
USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0x581d, USB_CLASS_VENDOR_SPEC, 1, 7),
.driver_info = (unsigned long)&qmi_wwan_info,
},
- { /* Quectel EP06/EG06/EM06 */
- USB_DEVICE_AND_INTERFACE_INFO(0x2c7c, 0x0306,
- USB_CLASS_VENDOR_SPEC,
- USB_SUBCLASS_VENDOR_SPEC,
- 0xff),
- .driver_info = (unsigned long)&qmi_wwan_info_quirk_dtr,
- },
- { /* Quectel EG12/EM12 */
- USB_DEVICE_AND_INTERFACE_INFO(0x2c7c, 0x0512,
- USB_CLASS_VENDOR_SPEC,
- USB_SUBCLASS_VENDOR_SPEC,
- 0xff),
- .driver_info = (unsigned long)&qmi_wwan_info_quirk_dtr,
- },
+ {QMI_QUIRK_QUECTEL_DYNCFG(0x2c7c, 0x0125)}, /* Quectel EC25, EC20 R2.0 Mini PCIe */
+ {QMI_QUIRK_QUECTEL_DYNCFG(0x2c7c, 0x0306)}, /* Quectel EP06/EG06/EM06 */
+ {QMI_QUIRK_QUECTEL_DYNCFG(0x2c7c, 0x0512)}, /* Quectel EG12/EM12 */
/* 3. Combined interface devices matching on interface number */
{QMI_FIXED_INTF(0x0408, 0xea42, 4)}, /* Yota / Megafon M100-1 */
{QMI_FIXED_INTF(0x19d2, 0x2002, 4)}, /* ZTE (Vodafone) K3765-Z */
{QMI_FIXED_INTF(0x2001, 0x7e19, 4)}, /* D-Link DWM-221 B1 */
{QMI_FIXED_INTF(0x2001, 0x7e35, 4)}, /* D-Link DWM-222 */
+ {QMI_FIXED_INTF(0x2020, 0x2031, 4)}, /* Olicard 600 */
{QMI_FIXED_INTF(0x2020, 0x2033, 4)}, /* BroadMobi BM806U */
{QMI_FIXED_INTF(0x0f3d, 0x68a2, 8)}, /* Sierra Wireless MC7700 */
{QMI_FIXED_INTF(0x114f, 0x68a2, 8)}, /* Sierra Wireless MC7750 */
{QMI_FIXED_INTF(0x03f0, 0x9d1d, 1)}, /* HP lt4120 Snapdragon X5 LTE */
{QMI_FIXED_INTF(0x22de, 0x9061, 3)}, /* WeTelecom WPD-600N */
{QMI_QUIRK_SET_DTR(0x1e0e, 0x9001, 5)}, /* SIMCom 7100E, 7230E, 7600E ++ */
- {QMI_QUIRK_SET_DTR(0x2c7c, 0x0125, 4)}, /* Quectel EC25, EC20 R2.0 Mini PCIe */
{QMI_QUIRK_SET_DTR(0x2c7c, 0x0121, 4)}, /* Quectel EC21 Mini PCIe */
{QMI_QUIRK_SET_DTR(0x2c7c, 0x0191, 4)}, /* Quectel EG91 */
{QMI_FIXED_INTF(0x2c7c, 0x0296, 4)}, /* Quectel BG96 */
return false;
}
-static bool quectel_diag_detected(struct usb_interface *intf)
-{
- struct usb_device *dev = interface_to_usbdev(intf);
- struct usb_interface_descriptor intf_desc = intf->cur_altsetting->desc;
- u16 id_vendor = le16_to_cpu(dev->descriptor.idVendor);
- u16 id_product = le16_to_cpu(dev->descriptor.idProduct);
-
- if (id_vendor != 0x2c7c || intf_desc.bNumEndpoints != 2)
- return false;
-
- if (id_product == 0x0306 || id_product == 0x0512)
- return true;
- else
- return false;
-}
-
static int qmi_wwan_probe(struct usb_interface *intf,
const struct usb_device_id *prod)
{
struct usb_device_id *id = (struct usb_device_id *)prod;
struct usb_interface_descriptor *desc = &intf->cur_altsetting->desc;
+ const struct driver_info *info;
/* Workaround to enable dynamic IDs. This disables usbnet
* blacklisting functionality. Which, if required, can be
* we need to match on class/subclass/protocol. These values are
* identical for the diagnostic- and QMI-interface, but bNumEndpoints is
* different. Ignore the current interface if the number of endpoints
- * the number for the diag interface (two).
+ * equals the number for the diag interface (two).
*/
- if (quectel_diag_detected(intf))
- return -ENODEV;
+ info = (void *)&id->driver_info;
+
+ if (info->data & QMI_WWAN_QUIRK_QUECTEL_DYNCFG) {
+ if (desc->bNumEndpoints == 2)
+ return -ENODEV;
+ }
return usbnet_probe(intf, id);
}
goto amacout;
}
memcpy(sa->sa_data, buf, 6);
- ether_addr_copy(tp->netdev->dev_addr, sa->sa_data);
netif_info(tp, probe, tp->netdev,
"Using pass-thru MAC addr %pM\n", sa->sa_data);
return ret;
}
-static int set_ethernet_addr(struct r8152 *tp)
+static int determine_ethernet_addr(struct r8152 *tp, struct sockaddr *sa)
{
struct net_device *dev = tp->netdev;
- struct sockaddr sa;
int ret;
if (tp->version == RTL_VER_01) {
- ret = pla_ocp_read(tp, PLA_IDR, 8, sa.sa_data);
+ ret = pla_ocp_read(tp, PLA_IDR, 8, sa->sa_data);
} else {
/* if device doesn't support MAC pass through this will
* be expected to be non-zero
*/
- ret = vendor_mac_passthru_addr_read(tp, &sa);
+ ret = vendor_mac_passthru_addr_read(tp, sa);
if (ret < 0)
- ret = pla_ocp_read(tp, PLA_BACKUP, 8, sa.sa_data);
+ ret = pla_ocp_read(tp, PLA_BACKUP, 8, sa->sa_data);
}
if (ret < 0) {
netif_err(tp, probe, dev, "Get ether addr fail\n");
- } else if (!is_valid_ether_addr(sa.sa_data)) {
+ } else if (!is_valid_ether_addr(sa->sa_data)) {
netif_err(tp, probe, dev, "Invalid ether addr %pM\n",
- sa.sa_data);
+ sa->sa_data);
eth_hw_addr_random(dev);
- ether_addr_copy(sa.sa_data, dev->dev_addr);
- ret = rtl8152_set_mac_address(dev, &sa);
+ ether_addr_copy(sa->sa_data, dev->dev_addr);
netif_info(tp, probe, dev, "Random ether addr %pM\n",
- sa.sa_data);
- } else {
- if (tp->version == RTL_VER_01)
- ether_addr_copy(dev->dev_addr, sa.sa_data);
- else
- ret = rtl8152_set_mac_address(dev, &sa);
+ sa->sa_data);
+ return 0;
}
return ret;
}
+static int set_ethernet_addr(struct r8152 *tp)
+{
+ struct net_device *dev = tp->netdev;
+ struct sockaddr sa;
+ int ret;
+
+ ret = determine_ethernet_addr(tp, &sa);
+ if (ret < 0)
+ return ret;
+
+ if (tp->version == RTL_VER_01)
+ ether_addr_copy(dev->dev_addr, sa.sa_data);
+ else
+ ret = rtl8152_set_mac_address(dev, &sa);
+
+ return ret;
+}
+
static void read_bulk_callback(struct urb *urb)
{
struct net_device *netdev;
{
struct r8152 *tp = usb_get_intfdata(intf);
struct net_device *netdev;
+ struct sockaddr sa;
if (!tp)
return 0;
+ /* reset the MAC adddress in case of policy change */
+ if (determine_ethernet_addr(tp, &sa) >= 0) {
+ rtnl_lock();
+ dev_set_mac_address (tp->netdev, &sa, NULL);
+ rtnl_unlock();
+ }
+
netdev = tp->netdev;
if (!netif_running(netdev))
return 0;
}
}
-static int veth_get_ts_info(struct net_device *dev,
- struct ethtool_ts_info *info)
-{
- info->so_timestamping =
- SOF_TIMESTAMPING_TX_SOFTWARE |
- SOF_TIMESTAMPING_RX_SOFTWARE |
- SOF_TIMESTAMPING_SOFTWARE;
- info->phc_index = -1;
-
- return 0;
-}
-
static const struct ethtool_ops veth_ethtool_ops = {
.get_drvinfo = veth_get_drvinfo,
.get_link = ethtool_op_get_link,
.get_sset_count = veth_get_sset_count,
.get_ethtool_stats = veth_get_ethtool_stats,
.get_link_ksettings = veth_get_link_ksettings,
- .get_ts_info = veth_get_ts_info,
+ .get_ts_info = ethtool_op_get_ts_info,
};
/* general routines */
#include <linux/average.h>
#include <linux/filter.h>
#include <linux/kernel.h>
-#include <linux/pci.h>
#include <net/route.h>
#include <net/xdp.h>
#include <net/net_failover.h>
struct send_queue *sq = &vi->sq[qnum];
int err;
struct netdev_queue *txq = netdev_get_tx_queue(dev, qnum);
- bool kick = !skb->xmit_more;
+ bool kick = !netdev_xmit_more();
bool use_napi = sq->napi.weight;
/* Free up any pending old buffers before queueing new ones. */
dev->stats.tx_fifo_errors++;
if (net_ratelimit())
dev_warn(&dev->dev,
- "Unexpected TXQ (%d) queue failure: %d\n", qnum, err);
+ "Unexpected TXQ (%d) queue failure: %d\n",
+ qnum, err);
dev->stats.tx_dropped++;
dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_GUEST_OFFLOADS,
VIRTIO_NET_CTRL_GUEST_OFFLOADS_SET, &sg)) {
- dev_warn(&vi->dev->dev, "Fail to set guest offload. \n");
+ dev_warn(&vi->dev->dev, "Fail to set guest offload.\n");
return -EINVAL;
}
/* Should never trigger: MTU was previously validated
* in virtnet_validate.
*/
- dev_err(&vdev->dev, "device MTU appears to have changed "
- "it is now %d < %d", mtu, dev->min_mtu);
+ dev_err(&vdev->dev,
+ "device MTU appears to have changed it is now %d < %d",
+ mtu, dev->min_mtu);
goto free;
}
neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false);
if (!IS_ERR(neigh)) {
sock_confirm_neigh(skb, neigh);
- ret = neigh_output(neigh, skb);
+ ret = neigh_output(neigh, skb, false);
rcu_read_unlock_bh();
return ret;
}
struct net_device *dev = dst->dev;
unsigned int hh_len = LL_RESERVED_SPACE(dev);
struct neighbour *neigh;
- u32 nexthop;
+ bool is_v6gw = false;
int ret = -EINVAL;
nf_reset(skb);
rcu_read_lock_bh();
- nexthop = (__force u32)rt_nexthop(rt, ip_hdr(skb)->daddr);
- neigh = __ipv4_neigh_lookup_noref(dev, nexthop);
- if (unlikely(!neigh))
- neigh = __neigh_create(&arp_tbl, &nexthop, dev, false);
+ neigh = ip_neigh_for_gw(rt, skb, &is_v6gw);
if (!IS_ERR(neigh)) {
sock_confirm_neigh(skb, neigh);
- ret = neigh_output(neigh, skb);
+ /* if crossing protocols, can not use the cached header */
+ ret = neigh_output(neigh, skb, is_v6gw);
rcu_read_unlock_bh();
return ret;
}
/* default to no qdisc; user can add if desired */
dev->priv_flags |= IFF_NO_QUEUE;
+ dev->priv_flags |= IFF_NO_RX_HANDLER;
- dev->min_mtu = 0;
- dev->max_mtu = 0;
+ /* VRF devices do not care about MTU, but if the MTU is set
+ * too low then the ipv4 and ipv6 protocols are disabled
+ * which breaks networking.
+ */
+ dev->min_mtu = IPV6_MIN_MTU;
+ dev->max_mtu = ETH_MAX_MTU;
}
static int vrf_validate(struct nlattr *tb[], struct nlattr *data[],
num_msdus++;
num_bytes += ret;
}
- ieee80211_return_txq(hw, txq);
+ ieee80211_return_txq(hw, txq, false);
ieee80211_txq_schedule_end(hw, txq->ac);
record->num_msdus = cpu_to_le16(num_msdus);
if (ret < 0)
break;
}
- ieee80211_return_txq(hw, txq);
+ ieee80211_return_txq(hw, txq, false);
ath10k_htt_tx_txq_update(hw, txq);
if (ret == -EBUSY)
break;
if (ret < 0)
break;
}
- ieee80211_return_txq(hw, txq);
+ ieee80211_return_txq(hw, txq, false);
ath10k_htt_tx_txq_update(hw, txq);
out:
ieee80211_txq_schedule_end(hw, ac);
goto out;
while ((queue = ieee80211_next_txq(hw, txq->mac80211_qnum))) {
+ bool force;
+
tid = (struct ath_atx_tid *)queue->drv_priv;
ret = ath_tx_sched_aggr(sc, txq, tid);
ath_dbg(common, QUEUE, "ath_tx_sched_aggr returned %d\n", ret);
- ieee80211_return_txq(hw, queue);
+ force = !skb_queue_empty(&tid->retry_q);
+ ieee80211_return_txq(hw, queue, force);
}
out:
#define IWL_22000_HR_A0_FW_PRE "iwlwifi-QuQnj-a0-hr-a0-"
#define IWL_22000_SU_Z0_FW_PRE "iwlwifi-su-z0-"
#define IWL_QU_B_JF_B_FW_PRE "iwlwifi-Qu-b0-jf-b0-"
+#define IWL_QUZ_A_HR_B_FW_PRE "iwlwifi-QuZ-a0-hr-b0-"
#define IWL_QNJ_B_JF_B_FW_PRE "iwlwifi-QuQnj-b0-jf-b0-"
#define IWL_CC_A_FW_PRE "iwlwifi-cc-a0-"
#define IWL_22000_SO_A_JF_B_FW_PRE "iwlwifi-so-a0-jf-b0-"
IWL_22000_HR_A0_FW_PRE __stringify(api) ".ucode"
#define IWL_22000_SU_Z0_MODULE_FIRMWARE(api) \
IWL_22000_SU_Z0_FW_PRE __stringify(api) ".ucode"
-#define IWL_QU_B_JF_B_MODULE_FIRMWARE(api) \
- IWL_QU_B_JF_B_FW_PRE __stringify(api) ".ucode"
+#define IWL_QUZ_A_HR_B_MODULE_FIRMWARE(api) \
+ IWL_QUZ_A_HR_B_FW_PRE __stringify(api) ".ucode"
#define IWL_QU_B_JF_B_MODULE_FIRMWARE(api) \
IWL_QU_B_JF_B_FW_PRE __stringify(api) ".ucode"
#define IWL_QNJ_B_JF_B_MODULE_FIRMWARE(api) \
.max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
};
-const struct iwl_cfg iwl22260_2ax_cfg = {
- .name = "Intel(R) Wireless-AX 22260",
+const struct iwl_cfg iwl_ax101_cfg_quz_hr = {
+ .name = "Intel(R) Wi-Fi 6 AX101",
+ .fw_name_pre = IWL_QUZ_A_HR_B_FW_PRE,
+ IWL_DEVICE_22500,
+ /*
+ * This device doesn't support receiving BlockAck with a large bitmap
+ * so we need to restrict the size of transmitted aggregation to the
+ * HT size; mac80211 would otherwise pick the HE max (256) by default.
+ */
+ .max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
+};
+
+const struct iwl_cfg iwl_ax200_cfg_cc = {
+ .name = "Intel(R) Wi-Fi 6 AX200 160MHz",
.fw_name_pre = IWL_CC_A_FW_PRE,
IWL_DEVICE_22500,
/*
};
const struct iwl_cfg killer1650x_2ax_cfg = {
- .name = "Killer(R) Wireless-AX 1650x Wireless Network Adapter (200NGW)",
+ .name = "Killer(R) Wi-Fi 6 AX1650x 160MHz Wireless Network Adapter (200NGW)",
.fw_name_pre = IWL_CC_A_FW_PRE,
IWL_DEVICE_22500,
/*
};
const struct iwl_cfg killer1650w_2ax_cfg = {
- .name = "Killer(R) Wireless-AX 1650w Wireless Network Adapter (200D2W)",
+ .name = "Killer(R) Wi-Fi 6 AX1650w 160MHz Wireless Network Adapter (200D2W)",
.fw_name_pre = IWL_CC_A_FW_PRE,
IWL_DEVICE_22500,
/*
};
const struct iwl_cfg killer1650s_2ax_cfg_qu_b0_hr_b0 = {
- .name = "Killer(R) Wireless-AX 1650i Wireless Network Adapter (22560NGW)",
+ .name = "Killer(R) Wi-Fi 6 AX1650i 160MHz Wireless Network Adapter (201NGW)",
.fw_name_pre = IWL_22000_QU_B_HR_B_FW_PRE,
IWL_DEVICE_22500,
/*
};
const struct iwl_cfg killer1650i_2ax_cfg_qu_b0_hr_b0 = {
- .name = "Killer(R) Wireless-AX 1650s Wireless Network Adapter (22560D2W)",
+ .name = "Killer(R) Wi-Fi 6 AX1650s 160MHz Wireless Network Adapter (201D2W)",
.fw_name_pre = IWL_22000_QU_B_HR_B_FW_PRE,
IWL_DEVICE_22500,
/*
MODULE_FIRMWARE(IWL_22000_HR_A0_QNJ_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
MODULE_FIRMWARE(IWL_22000_SU_Z0_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
MODULE_FIRMWARE(IWL_QU_B_JF_B_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
+MODULE_FIRMWARE(IWL_QUZ_A_HR_B_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
MODULE_FIRMWARE(IWL_QNJ_B_JF_B_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
MODULE_FIRMWARE(IWL_CC_A_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
MODULE_FIRMWARE(IWL_22000_SO_A_JF_B_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
if (!range) {
IWL_ERR(fwrt, "Failed to fill region header: id=%d, type=%d\n",
le32_to_cpu(reg->region_id), type);
+ memset(*data, 0, le32_to_cpu((*data)->len));
return;
}
if (range_size < 0) {
IWL_ERR(fwrt, "Failed to dump region: id=%d, type=%d\n",
le32_to_cpu(reg->region_id), type);
+ memset(*data, 0, le32_to_cpu((*data)->len));
return;
}
range = range + range_size;
trigger = fwrt->dump.active_trigs[id].trig;
- size = sizeof(*dump_file);
- size += iwl_fw_ini_get_trigger_len(fwrt, trigger);
-
+ size = iwl_fw_ini_get_trigger_len(fwrt, trigger);
if (!size)
return NULL;
+ size += sizeof(*dump_file);
+
dump_file = vzalloc(size);
if (!dump_file)
return NULL;
iwl_dump_error_desc->len = 0;
ret = iwl_fw_dbg_collect_desc(fwrt, iwl_dump_error_desc, false, 0);
- if (ret) {
+ if (ret)
kfree(iwl_dump_error_desc);
- } else {
- set_bit(STATUS_FW_WAIT_DUMP, &fwrt->trans->status);
-
- /* trigger nmi to halt the fw */
- iwl_force_nmi(fwrt->trans);
- }
+ else
+ iwl_trans_sync_nmi(fwrt->trans);
return ret;
}
void iwl_fwrt_stop_device(struct iwl_fw_runtime *fwrt)
{
- /* if the wait event timeout elapses instead of wake up then
- * the driver did not receive NMI interrupt and can not assume the FW
- * is halted
- */
- int ret = wait_event_timeout(fwrt->trans->fw_halt_waitq,
- !test_bit(STATUS_FW_WAIT_DUMP,
- &fwrt->trans->status),
- msecs_to_jiffies(2000));
- if (!ret) {
- /* failed to receive NMI interrupt, assuming the FW is stuck */
- set_bit(STATUS_FW_ERROR, &fwrt->trans->status);
-
- clear_bit(STATUS_FW_WAIT_DUMP, &fwrt->trans->status);
- }
-
- /* Assuming the op mode mutex is held at this point */
iwl_fw_dbg_collect_sync(fwrt);
iwl_trans_stop_device(fwrt->trans);
fwrt->ops_ctx = ops_ctx;
INIT_DELAYED_WORK(&fwrt->dump.wk, iwl_fw_error_dump_wk);
iwl_fwrt_dbgfs_register(fwrt, dbgfs_dir);
- init_waitqueue_head(&fwrt->trans->fw_halt_waitq);
}
IWL_EXPORT_SYMBOL(iwl_fw_runtime_init);
extern const struct iwl_cfg iwl22000_2ac_cfg_hr_cdb;
extern const struct iwl_cfg iwl22000_2ac_cfg_jf;
extern const struct iwl_cfg iwl_ax101_cfg_qu_hr;
+extern const struct iwl_cfg iwl_ax101_cfg_quz_hr;
extern const struct iwl_cfg iwl22000_2ax_cfg_hr;
-extern const struct iwl_cfg iwl22260_2ax_cfg;
+extern const struct iwl_cfg iwl_ax200_cfg_cc;
extern const struct iwl_cfg killer1650s_2ax_cfg_qu_b0_hr_b0;
extern const struct iwl_cfg killer1650i_2ax_cfg_qu_b0_hr_b0;
extern const struct iwl_cfg killer1650x_2ax_cfg;
#define CSR_HW_REV_TYPE_NONE (0x00001F0)
#define CSR_HW_REV_TYPE_QNJ (0x0000360)
#define CSR_HW_REV_TYPE_QNJ_B0 (0x0000364)
+#define CSR_HW_REV_TYPE_QUZ (0x0000354)
#define CSR_HW_REV_TYPE_HR_CDB (0x0000340)
#define CSR_HW_REV_TYPE_SO (0x0000370)
#define CSR_HW_REV_TYPE_TY (0x0000420)
* are sent
* @STATUS_TRANS_IDLE: the trans is idle - general commands are not to be sent
* @STATUS_TRANS_DEAD: trans is dead - avoid any read/write operation
- * @STATUS_FW_WAIT_DUMP: if set, wait until cleared before collecting dump
*/
enum iwl_trans_status {
STATUS_SYNC_HCMD_ACTIVE,
STATUS_TRANS_GOING_IDLE,
STATUS_TRANS_IDLE,
STATUS_TRANS_DEAD,
- STATUS_FW_WAIT_DUMP,
};
static inline int
struct iwl_trans_dump_data *(*dump_data)(struct iwl_trans *trans,
u32 dump_mask);
void (*debugfs_cleanup)(struct iwl_trans *trans);
+ void (*sync_nmi)(struct iwl_trans *trans);
};
/**
u32 lmac_error_event_table[2];
u32 umac_error_event_table;
unsigned int error_event_table_tlv_status;
- wait_queue_head_t fw_halt_waitq;
bool hw_error;
/* pointer to trans specific struct */
/* prevent double restarts due to the same erroneous FW */
if (!test_and_set_bit(STATUS_FW_ERROR, &trans->status))
iwl_op_mode_nic_error(trans->op_mode);
+}
- if (test_and_clear_bit(STATUS_FW_WAIT_DUMP, &trans->status))
- wake_up(&trans->fw_halt_waitq);
-
+static inline void iwl_trans_sync_nmi(struct iwl_trans *trans)
+{
+ if (trans->ops->sync_nmi)
+ trans->ops->sync_nmi(trans);
}
/*****************************************************
iwl_mvm_mac_ctxt_remove(mvm, vif);
- kfree(mvmvif->ap_wep_key);
- mvmvif->ap_wep_key = NULL;
-
mutex_unlock(&mvm->mutex);
}
ret = iwl_mvm_update_sta(mvm, vif, sta);
} else if (old_state == IEEE80211_STA_ASSOC &&
new_state == IEEE80211_STA_AUTHORIZED) {
- /* if wep is used, need to set the key for the station now */
- if (vif->type == NL80211_IFTYPE_AP && mvmvif->ap_wep_key) {
- mvm_sta->wep_key =
- kmemdup(mvmvif->ap_wep_key,
- sizeof(*mvmvif->ap_wep_key) +
- mvmvif->ap_wep_key->keylen,
- GFP_KERNEL);
- if (!mvm_sta->wep_key) {
- ret = -ENOMEM;
- goto out_unlock;
- }
-
- ret = iwl_mvm_set_sta_key(mvm, vif, sta,
- mvm_sta->wep_key,
- STA_KEY_IDX_INVALID);
- } else {
- ret = 0;
- }
+ ret = 0;
/* we don't support TDLS during DCM */
if (iwl_mvm_phy_ctx_count(mvm) > 1)
NL80211_TDLS_DISABLE_LINK);
}
- /* Remove STA key if this is an AP using WEP */
- if (vif->type == NL80211_IFTYPE_AP && mvmvif->ap_wep_key) {
- int rm_ret = iwl_mvm_remove_sta_key(mvm, vif, sta,
- mvm_sta->wep_key);
-
- if (!ret)
- ret = rm_ret;
- kfree(mvm_sta->wep_key);
- mvm_sta->wep_key = NULL;
- }
-
if (unlikely(ret &&
test_bit(IWL_MVM_STATUS_HW_RESTART_REQUESTED,
&mvm->status)))
struct ieee80211_sta *sta, u32 changed)
{
struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
+ struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
+
+ if (changed & (IEEE80211_RC_BW_CHANGED |
+ IEEE80211_RC_SUPP_RATES_CHANGED |
+ IEEE80211_RC_NSS_CHANGED))
+ iwl_mvm_rs_rate_init(mvm, sta, mvmvif->phy_ctxt->channel->band,
+ true);
if (vif->type == NL80211_IFTYPE_STATION &&
changed & IEEE80211_RC_NSS_CHANGED)
break;
case WLAN_CIPHER_SUITE_WEP40:
case WLAN_CIPHER_SUITE_WEP104:
- if (vif->type == NL80211_IFTYPE_AP) {
- struct iwl_mvm_vif *mvmvif =
- iwl_mvm_vif_from_mac80211(vif);
-
- mvmvif->ap_wep_key = kmemdup(key,
- sizeof(*key) + key->keylen,
- GFP_KERNEL);
- if (!mvmvif->ap_wep_key)
- return -ENOMEM;
- }
-
- if (vif->type != NL80211_IFTYPE_STATION)
- return 0;
- break;
+ if (vif->type == NL80211_IFTYPE_STATION)
+ break;
+ if (iwl_mvm_has_new_tx_api(mvm))
+ return -EOPNOTSUPP;
+ /* support HW crypto on TX */
+ return 0;
default:
/* currently FW supports only one optional cipher scheme */
if (hw->n_cipher_schemes &&
ret = iwl_mvm_set_sta_key(mvm, vif, sta, key, key_offset);
if (ret) {
IWL_WARN(mvm, "set key failed\n");
+ key->hw_key_idx = STA_KEY_IDX_INVALID;
/*
* can't add key for RX, but we don't need it
- * in the device for TX so still return 0
+ * in the device for TX so still return 0,
+ * unless we have new TX API where we cannot
+ * put key material into the TX_CMD
*/
- key->hw_key_idx = STA_KEY_IDX_INVALID;
- ret = 0;
+ if (iwl_mvm_has_new_tx_api(mvm))
+ ret = -EOPNOTSUPP;
+ else
+ ret = 0;
}
break;
netdev_features_t features;
struct iwl_probe_resp_data __rcu *probe_resp_data;
- struct ieee80211_key_conf *ap_wep_key;
};
static inline struct iwl_mvm_vif *
* Copyright(c) 2012 - 2015 Intel Corporation. All rights reserved.
* Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
* Copyright(c) 2016 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2018 Intel Corporation
+ * Copyright(c) 2018 - 2019 Intel Corporation
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of version 2 of the GNU General Public License as
* Copyright(c) 2012 - 2015 Intel Corporation. All rights reserved.
* Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
* Copyright(c) 2016 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2018 Intel Corporation
+ * Copyright(c) 2018 - 2019 Intel Corporation
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
iwl_mvm_sta_alloc_queue(mvm, txq->sta, txq->ac, tid);
list_del_init(&mvmtxq->list);
+ local_bh_disable();
iwl_mvm_mac_itxq_xmit(mvm->hw, txq);
+ local_bh_enable();
}
mutex_unlock(&mvm->mutex);
iwl_mvm_enable_txq(mvm, NULL, mvmvif->cab_queue, 0, &cfg,
timeout);
- if (mvmvif->ap_wep_key) {
- u8 key_offset = iwl_mvm_set_fw_key_idx(mvm);
-
- __set_bit(key_offset, mvm->fw_key_table);
-
- if (key_offset == STA_KEY_IDX_INVALID)
- return -ENOSPC;
-
- ret = iwl_mvm_send_sta_key(mvm, mvmvif->mcast_sta.sta_id,
- mvmvif->ap_wep_key, true, 0, NULL, 0,
- key_offset, 0);
- if (ret)
- return ret;
- }
-
return 0;
}
iwl_mvm_disable_txq(mvm, NULL, mvmvif->cab_queue, 0, 0);
- if (mvmvif->ap_wep_key) {
- int i;
-
- if (!__test_and_clear_bit(mvmvif->ap_wep_key->hw_key_idx,
- mvm->fw_key_table)) {
- IWL_ERR(mvm, "offset %d not used in fw key table.\n",
- mvmvif->ap_wep_key->hw_key_idx);
- return -ENOENT;
- }
-
- /* track which key was deleted last */
- for (i = 0; i < STA_KEY_MAX_NUM; i++) {
- if (mvm->fw_key_deleted[i] < U8_MAX)
- mvm->fw_key_deleted[i]++;
- }
- mvm->fw_key_deleted[mvmvif->ap_wep_key->hw_key_idx] = 0;
- ret = __iwl_mvm_remove_sta_key(mvm, mvmvif->mcast_sta.sta_id,
- mvmvif->ap_wep_key, true);
- if (ret)
- return ret;
- }
-
ret = iwl_mvm_rm_sta_common(mvm, mvmvif->mcast_sta.sta_id);
if (ret)
IWL_WARN(mvm, "Failed sending remove station\n");
* Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
* Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
* Copyright(c) 2015 - 2016 Intel Deutschland GmbH
- * Copyright(c) 2018 Intel Corporation
+ * Copyright(c) 2018 - 2019 Intel Corporation
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of version 2 of the GNU General Public License as
* Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
* Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
* Copyright(c) 2015 - 2016 Intel Deutschland GmbH
- * Copyright(c) 2018 Intel Corporation
+ * Copyright(c) 2018 - 2019 Intel Corporation
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* the BA window. To be used for UAPSD only.
* @ptk_pn: per-queue PTK PN data structures
* @dup_data: per queue duplicate packet detection data
- * @wep_key: used in AP mode. Is a duplicate of the WEP key.
* @deferred_traffic_tid_map: indication bitmap of deferred traffic per-TID
* @tx_ant: the index of the antenna to use for data tx to this station. Only
* used during connection establishment (e.g. for the 4 way handshake
struct iwl_mvm_key_pn __rcu *ptk_pn[4];
struct iwl_mvm_rxq_dup_data *dup_data;
- struct ieee80211_key_conf *wep_key;
-
u8 reserved_queue;
/* Temporary, until the new TLC will control the Tx protection */
{IWL_PCI_DEVICE(0xA0F0, 0x1652, killer1650i_2ax_cfg_qu_b0_hr_b0)},
{IWL_PCI_DEVICE(0xA0F0, 0x4070, iwl_ax101_cfg_qu_hr)},
- {IWL_PCI_DEVICE(0x2723, 0x0080, iwl22260_2ax_cfg)},
- {IWL_PCI_DEVICE(0x2723, 0x0084, iwl22260_2ax_cfg)},
- {IWL_PCI_DEVICE(0x2723, 0x0088, iwl22260_2ax_cfg)},
- {IWL_PCI_DEVICE(0x2723, 0x008C, iwl22260_2ax_cfg)},
+ {IWL_PCI_DEVICE(0x2723, 0x0080, iwl_ax200_cfg_cc)},
+ {IWL_PCI_DEVICE(0x2723, 0x0084, iwl_ax200_cfg_cc)},
+ {IWL_PCI_DEVICE(0x2723, 0x0088, iwl_ax200_cfg_cc)},
+ {IWL_PCI_DEVICE(0x2723, 0x008C, iwl_ax200_cfg_cc)},
{IWL_PCI_DEVICE(0x2723, 0x1653, killer1650w_2ax_cfg)},
{IWL_PCI_DEVICE(0x2723, 0x1654, killer1650x_2ax_cfg)},
- {IWL_PCI_DEVICE(0x2723, 0x2080, iwl22260_2ax_cfg)},
- {IWL_PCI_DEVICE(0x2723, 0x4080, iwl22260_2ax_cfg)},
- {IWL_PCI_DEVICE(0x2723, 0x4088, iwl22260_2ax_cfg)},
+ {IWL_PCI_DEVICE(0x2723, 0x2080, iwl_ax200_cfg_cc)},
+ {IWL_PCI_DEVICE(0x2723, 0x4080, iwl_ax200_cfg_cc)},
+ {IWL_PCI_DEVICE(0x2723, 0x4088, iwl_ax200_cfg_cc)},
+
{IWL_PCI_DEVICE(0x2725, 0x0090, iwlax210_2ax_cfg_so_hr_a0)},
{IWL_PCI_DEVICE(0x7A70, 0x0090, iwlax210_2ax_cfg_so_hr_a0)},
{IWL_PCI_DEVICE(0x7A70, 0x0310, iwlax210_2ax_cfg_so_hr_a0)},
void iwl_trans_pcie_rf_kill(struct iwl_trans *trans, bool state);
void iwl_trans_pcie_dump_regs(struct iwl_trans *trans);
-void iwl_trans_sync_nmi(struct iwl_trans *trans);
+void iwl_trans_pcie_sync_nmi(struct iwl_trans *trans);
#ifdef CONFIG_IWLWIFI_DEBUGFS
void iwl_trans_pcie_dbgfs_register(struct iwl_trans *trans);
.unref = iwl_trans_pcie_unref, \
.dump_data = iwl_trans_pcie_dump_data, \
.d3_suspend = iwl_trans_pcie_d3_suspend, \
- .d3_resume = iwl_trans_pcie_d3_resume
+ .d3_resume = iwl_trans_pcie_d3_resume, \
+ .sync_nmi = iwl_trans_pcie_sync_nmi
#ifdef CONFIG_PM_SLEEP
#define IWL_TRANS_PM_OPS \
}
} else if (cfg == &iwl_ax101_cfg_qu_hr) {
if (CSR_HW_RF_ID_TYPE_CHIP_ID(trans->hw_rf_id) ==
+ CSR_HW_RF_ID_TYPE_CHIP_ID(CSR_HW_RF_ID_TYPE_HR) &&
+ trans->hw_rev == CSR_HW_REV_TYPE_QNJ_B0) {
+ trans->cfg = &iwl22000_2ax_cfg_qnj_hr_b0;
+ } else if (CSR_HW_RF_ID_TYPE_CHIP_ID(trans->hw_rf_id) ==
CSR_HW_RF_ID_TYPE_CHIP_ID(CSR_HW_RF_ID_TYPE_HR)) {
trans->cfg = &iwl_ax101_cfg_qu_hr;
} else if (CSR_HW_RF_ID_TYPE_CHIP_ID(trans->hw_rf_id) ==
}
} else if (CSR_HW_RF_ID_TYPE_CHIP_ID(trans->hw_rf_id) ==
CSR_HW_RF_ID_TYPE_CHIP_ID(CSR_HW_RF_ID_TYPE_HR) &&
- (trans->cfg != &iwl22260_2ax_cfg ||
+ (trans->cfg != &iwl_ax200_cfg_cc ||
trans->hw_rev == CSR_HW_REV_TYPE_QNJ_B0)) {
u32 hw_status;
return ERR_PTR(ret);
}
-void iwl_trans_sync_nmi(struct iwl_trans *trans)
+void iwl_trans_pcie_sync_nmi(struct iwl_trans *trans)
{
unsigned long timeout = jiffies + IWL_TRANS_NMI_TIMEOUT;
cmd_str);
ret = -ETIMEDOUT;
- iwl_trans_sync_nmi(trans);
+ iwl_trans_pcie_sync_nmi(trans);
goto cancel;
}
iwl_get_cmd_string(trans, cmd->id));
ret = -ETIMEDOUT;
- iwl_trans_sync_nmi(trans);
+ iwl_trans_pcie_sync_nmi(trans);
goto cancel;
}
enum nl80211_band band;
const struct ieee80211_ops *ops = &mac80211_hwsim_ops;
struct net *net;
- int idx;
+ int idx, i;
int n_limits = 0;
if (WARN_ON(param->channels > 1 && !param->use_chanctx))
goto failed_hw;
}
+ data->if_combination.max_interfaces = 0;
+ for (i = 0; i < n_limits; i++)
+ data->if_combination.max_interfaces +=
+ data->if_limits[i].max;
+
data->if_combination.n_limits = n_limits;
- data->if_combination.max_interfaces = 2048;
data->if_combination.limits = data->if_limits;
- hw->wiphy->iface_combinations = &data->if_combination;
- hw->wiphy->n_iface_combinations = 1;
+ /*
+ * If we actually were asked to support combinations,
+ * advertise them - if there's only a single thing like
+ * only IBSS then don't advertise it as combinations.
+ */
+ if (data->if_combination.max_interfaces > 1) {
+ hw->wiphy->iface_combinations = &data->if_combination;
+ hw->wiphy->n_iface_combinations = 1;
+ }
if (param->ciphers) {
memcpy(data->ciphers, param->ciphers,
bus_ops->rmw = mt7603_rmw;
dev->mt76.bus = bus_ops;
+ spin_lock_init(&dev->ps_lock);
+
INIT_DELAYED_WORK(&dev->mac_work, mt7603_mac_work);
tasklet_init(&dev->pre_tbtt_tasklet, mt7603_pre_tbtt_tasklet,
(unsigned long)dev);
MT_BA_CONTROL_1_RESET));
}
-void mt7603_mac_tx_ba_reset(struct mt7603_dev *dev, int wcid, int tid, int ssn,
+void mt7603_mac_tx_ba_reset(struct mt7603_dev *dev, int wcid, int tid,
int ba_size)
{
u32 addr = mt7603_wtbl2_addr(wcid);
mt76_clear(dev, addr + (15 * 4), tid_mask);
return;
}
- mt76_poll(dev, MT_WTBL_UPDATE, MT_WTBL_UPDATE_BUSY, 0, 5000);
-
- mt7603_mac_stop(dev);
- switch (tid) {
- case 0:
- mt76_rmw_field(dev, addr + (2 * 4), MT_WTBL2_W2_TID0_SN, ssn);
- break;
- case 1:
- mt76_rmw_field(dev, addr + (2 * 4), MT_WTBL2_W2_TID1_SN, ssn);
- break;
- case 2:
- mt76_rmw_field(dev, addr + (2 * 4), MT_WTBL2_W2_TID2_SN_LO,
- ssn);
- mt76_rmw_field(dev, addr + (3 * 4), MT_WTBL2_W3_TID2_SN_HI,
- ssn >> 8);
- break;
- case 3:
- mt76_rmw_field(dev, addr + (3 * 4), MT_WTBL2_W3_TID3_SN, ssn);
- break;
- case 4:
- mt76_rmw_field(dev, addr + (3 * 4), MT_WTBL2_W3_TID4_SN, ssn);
- break;
- case 5:
- mt76_rmw_field(dev, addr + (3 * 4), MT_WTBL2_W3_TID5_SN_LO,
- ssn);
- mt76_rmw_field(dev, addr + (4 * 4), MT_WTBL2_W4_TID5_SN_HI,
- ssn >> 4);
- break;
- case 6:
- mt76_rmw_field(dev, addr + (4 * 4), MT_WTBL2_W4_TID6_SN, ssn);
- break;
- case 7:
- mt76_rmw_field(dev, addr + (4 * 4), MT_WTBL2_W4_TID7_SN, ssn);
- break;
- }
- mt7603_wtbl_update(dev, wcid, MT_WTBL_UPDATE_WTBL2);
- mt7603_mac_start(dev);
for (i = 7; i > 0; i--) {
if (ba_size >= MT_AGG_SIZE_LIMIT(i))
struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
struct ieee80211_tx_rate *rate = &info->control.rates[0];
struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
+ struct ieee80211_bar *bar = (struct ieee80211_bar *)skb->data;
struct ieee80211_vif *vif = info->control.vif;
struct mt7603_vif *mvif;
int wlan_idx;
int tx_count = 8;
u8 frame_type, frame_subtype;
u16 fc = le16_to_cpu(hdr->frame_control);
+ u16 seqno = 0;
u8 vif_idx = 0;
u32 val;
u8 bw;
tx_count = 0x1f;
val = FIELD_PREP(MT_TXD3_REM_TX_COUNT, tx_count) |
- FIELD_PREP(MT_TXD3_SEQ, le16_to_cpu(hdr->seq_ctrl));
+ MT_TXD3_SN_VALID;
+
+ if (ieee80211_is_data_qos(hdr->frame_control))
+ seqno = le16_to_cpu(hdr->seq_ctrl);
+ else if (ieee80211_is_back_req(hdr->frame_control))
+ seqno = le16_to_cpu(bar->start_seq_num);
+ else
+ val &= ~MT_TXD3_SN_VALID;
+
+ val |= FIELD_PREP(MT_TXD3_SEQ, seqno >> 4);
+
txwi[3] = cpu_to_le32(val);
if (key) {
struct mt7603_sta *msta = (struct mt7603_sta *)sta->drv_priv;
struct sk_buff_head list;
- mt76_stop_tx_queues(&dev->mt76, sta, false);
+ mt76_stop_tx_queues(&dev->mt76, sta, true);
mt7603_wtbl_set_ps(dev, msta, ps);
if (ps)
return;
case IEEE80211_AMPDU_TX_OPERATIONAL:
mtxq->aggr = true;
mtxq->send_bar = false;
- mt7603_mac_tx_ba_reset(dev, msta->wcid.idx, tid, *ssn, ba_size);
+ mt7603_mac_tx_ba_reset(dev, msta->wcid.idx, tid, ba_size);
break;
case IEEE80211_AMPDU_TX_STOP_FLUSH:
case IEEE80211_AMPDU_TX_STOP_FLUSH_CONT:
mtxq->aggr = false;
ieee80211_send_bar(vif, sta->addr, tid, mtxq->agg_ssn);
- mt7603_mac_tx_ba_reset(dev, msta->wcid.idx, tid, *ssn, -1);
+ mt7603_mac_tx_ba_reset(dev, msta->wcid.idx, tid, -1);
break;
case IEEE80211_AMPDU_TX_START:
mtxq->agg_ssn = *ssn << 4;
break;
case IEEE80211_AMPDU_TX_STOP_CONT:
mtxq->aggr = false;
- mt7603_mac_tx_ba_reset(dev, msta->wcid.idx, tid, *ssn, -1);
+ mt7603_mac_tx_ba_reset(dev, msta->wcid.idx, tid, -1);
ieee80211_stop_tx_ba_cb_irqsafe(vif, sta->addr, tid);
break;
}
int mt7603_mac_fill_rx(struct mt7603_dev *dev, struct sk_buff *skb);
void mt7603_mac_add_txs(struct mt7603_dev *dev, void *data);
void mt7603_mac_rx_ba_reset(struct mt7603_dev *dev, void *addr, u8 tid);
-void mt7603_mac_tx_ba_reset(struct mt7603_dev *dev, int wcid, int tid, int ssn,
+void mt7603_mac_tx_ba_reset(struct mt7603_dev *dev, int wcid, int tid,
int ba_size);
void mt7603_pse_client_reset(struct mt7603_dev *dev);
return;
rcu_read_lock();
- mt76_tx_status_lock(mdev, &list);
if (stat->wcid < ARRAY_SIZE(dev->mt76.wcid))
wcid = rcu_dereference(dev->mt76.wcid[stat->wcid]);
drv_priv);
}
+ mt76_tx_status_lock(mdev, &list);
+
if (wcid) {
if (stat->pktid >= MT_PACKET_ID_FIRST)
status.skb = mt76_tx_status_skb_get(mdev, wcid,
if (*update == 0 && stat_val == stat_cache &&
stat->wcid == msta->status.wcid && msta->n_frames < 32) {
msta->n_frames++;
- goto out;
+ mt76_tx_status_unlock(mdev, &list);
+ rcu_read_unlock();
+ return;
}
mt76x02_mac_fill_tx_status(dev, status.info, &msta->status,
if (status.skb)
mt76_tx_status_skb_done(mdev, status.skb, &list);
- else
- ieee80211_tx_status_ext(mt76_hw(dev), &status);
-
-out:
mt76_tx_status_unlock(mdev, &list);
+
+ if (!status.skb)
+ ieee80211_tx_status_ext(mt76_hw(dev), &status);
rcu_read_unlock();
}
CONFIG_CHANNEL_HT40,
CONFIG_POWERSAVING,
CONFIG_HT_DISABLED,
- CONFIG_QOS_DISABLED,
CONFIG_MONITORING,
/*
rt2x00dev->intf_associated--;
rt2x00leds_led_assoc(rt2x00dev, !!rt2x00dev->intf_associated);
-
- clear_bit(CONFIG_QOS_DISABLED, &rt2x00dev->flags);
}
- /*
- * Check for access point which do not support 802.11e . We have to
- * generate data frames sequence number in S/W for such AP, because
- * of H/W bug.
- */
- if (changes & BSS_CHANGED_QOS && !bss_conf->qos)
- set_bit(CONFIG_QOS_DISABLED, &rt2x00dev->flags);
-
/*
* When the erp information has changed, we should perform
* additional configuration steps. For all other changes we are done.
if (!rt2x00_has_cap_flag(rt2x00dev, REQUIRE_SW_SEQNO)) {
/*
* rt2800 has a H/W (or F/W) bug, device incorrectly increase
- * seqno on retransmited data (non-QOS) frames. To workaround
- * the problem let's generate seqno in software if QOS is
- * disabled.
+ * seqno on retransmitted data (non-QOS) and management frames.
+ * To workaround the problem let's generate seqno in software.
+ * Except for beacons which are transmitted periodically by H/W
+ * hence hardware has to assign seqno for them.
*/
- if (test_bit(CONFIG_QOS_DISABLED, &rt2x00dev->flags))
- __clear_bit(ENTRY_TXD_GENERATE_SEQ, &txdesc->flags);
- else
+ if (ieee80211_is_beacon(hdr->frame_control)) {
+ __set_bit(ENTRY_TXD_GENERATE_SEQ, &txdesc->flags);
/* H/W will generate sequence number */
return;
+ }
+
+ __clear_bit(ENTRY_TXD_GENERATE_SEQ, &txdesc->flags);
}
/*
struct xenvif_hash_cache cache;
};
+struct backend_info {
+ struct xenbus_device *dev;
+ struct xenvif *vif;
+
+ /* This is the state that will be reflected in xenstore when any
+ * active hotplug script completes.
+ */
+ enum xenbus_state state;
+
+ enum xenbus_state frontend_state;
+ struct xenbus_watch hotplug_status_watch;
+ u8 have_hotplug_status_watch:1;
+
+ const char *hotplug_script;
+};
+
struct xenvif {
/* Unique identifier for this interface. */
domid_t domid;
struct xenbus_watch credit_watch;
struct xenbus_watch mcast_ctrl_watch;
+ struct backend_info *be;
+
spinlock_t lock;
#ifdef CONFIG_DEBUG_FS
#include <linux/vmalloc.h>
#include <linux/rtnetlink.h>
-struct backend_info {
- struct xenbus_device *dev;
- struct xenvif *vif;
-
- /* This is the state that will be reflected in xenstore when any
- * active hotplug script completes.
- */
- enum xenbus_state state;
-
- enum xenbus_state frontend_state;
- struct xenbus_watch hotplug_status_watch;
- u8 have_hotplug_status_watch:1;
-
- const char *hotplug_script;
-};
-
static int connect_data_rings(struct backend_info *be,
struct xenvif_queue *queue);
static void connect(struct backend_info *be);
return err;
}
be->vif = vif;
+ vif->be = be;
kobject_uevent(&dev->dev.kobj, KOBJ_ONLINE);
return 0;
case XenbusStateClosed:
if (dev->state == XenbusStateClosed)
break;
- /* Missed the backend's CLOSING state -- fallthrough */
+ /* Fall through - Missed the backend's CLOSING state. */
case XenbusStateClosing:
xenbus_frontend_closed(dev);
break;
return NULL;
nd_btt->id = ida_simple_get(&nd_region->btt_ida, 0, 0, GFP_KERNEL);
- if (nd_btt->id < 0) {
- kfree(nd_btt);
- return NULL;
- }
+ if (nd_btt->id < 0)
+ goto out_nd_btt;
nd_btt->lbasize = lbasize;
- if (uuid)
+ if (uuid) {
uuid = kmemdup(uuid, 16, GFP_KERNEL);
+ if (!uuid)
+ goto out_put_id;
+ }
nd_btt->uuid = uuid;
dev = &nd_btt->dev;
dev_set_name(dev, "btt%d.%d", nd_region->id, nd_btt->id);
return NULL;
}
return dev;
+
+out_put_id:
+ ida_simple_remove(&nd_region->btt_ida, nd_btt->id);
+
+out_nd_btt:
+ kfree(nd_btt);
+ return NULL;
}
struct device *nd_btt_create(struct nd_region *nd_region)
if (!nsblk->uuid)
goto blk_err;
memcpy(name, nd_label->name, NSLABEL_NAME_LEN);
- if (name[0])
+ if (name[0]) {
nsblk->alt_name = kmemdup(name, NSLABEL_NAME_LEN,
GFP_KERNEL);
+ if (!nsblk->alt_name)
+ goto blk_err;
+ }
res = nsblk_add_resource(nd_region, ndd, nsblk,
__le64_to_cpu(nd_label->dpa));
if (!res)
while (len) {
mem = kmap_atomic(page);
- chunk = min_t(unsigned int, len, PAGE_SIZE);
+ chunk = min_t(unsigned int, len, PAGE_SIZE - off);
memcpy_flushcache(pmem_addr, mem + off, chunk);
kunmap_atomic(mem);
len -= chunk;
off = 0;
page++;
- pmem_addr += PAGE_SIZE;
+ pmem_addr += chunk;
}
}
while (len) {
mem = kmap_atomic(page);
- chunk = min_t(unsigned int, len, PAGE_SIZE);
+ chunk = min_t(unsigned int, len, PAGE_SIZE - off);
rem = memcpy_mcsafe(mem + off, pmem_addr, chunk);
kunmap_atomic(mem);
if (rem)
len -= chunk;
off = 0;
page++;
- pmem_addr += PAGE_SIZE;
+ pmem_addr += chunk;
}
return BLK_STS_OK;
}
module_param(key_revalidate, bool, 0444);
MODULE_PARM_DESC(key_revalidate, "Require key validation at init.");
+static const char zero_key[NVDIMM_PASSPHRASE_LEN];
+
static void *key_data(struct key *key)
{
struct encrypted_key_payload *epayload = dereference_key_locked(key);
return key;
}
+static const void *nvdimm_get_key_payload(struct nvdimm *nvdimm,
+ struct key **key)
+{
+ *key = nvdimm_request_key(nvdimm);
+ if (!*key)
+ return zero_key;
+
+ return key_data(*key);
+}
+
static struct key *nvdimm_lookup_user_key(struct nvdimm *nvdimm,
key_serial_t id, int subclass)
{
return key;
}
-static struct key *nvdimm_key_revalidate(struct nvdimm *nvdimm)
+static const void *nvdimm_get_user_key_payload(struct nvdimm *nvdimm,
+ key_serial_t id, int subclass, struct key **key)
+{
+ *key = NULL;
+ if (id == 0) {
+ if (subclass == NVDIMM_BASE_KEY)
+ return zero_key;
+ else
+ return NULL;
+ }
+
+ *key = nvdimm_lookup_user_key(nvdimm, id, subclass);
+ if (!*key)
+ return NULL;
+
+ return key_data(*key);
+}
+
+
+static int nvdimm_key_revalidate(struct nvdimm *nvdimm)
{
struct key *key;
int rc;
+ const void *data;
if (!nvdimm->sec.ops->change_key)
- return NULL;
+ return -EOPNOTSUPP;
- key = nvdimm_request_key(nvdimm);
- if (!key)
- return NULL;
+ data = nvdimm_get_key_payload(nvdimm, &key);
/*
* Send the same key to the hardware as new and old key to
* verify that the key is good.
*/
- rc = nvdimm->sec.ops->change_key(nvdimm, key_data(key),
- key_data(key), NVDIMM_USER);
+ rc = nvdimm->sec.ops->change_key(nvdimm, data, data, NVDIMM_USER);
if (rc < 0) {
nvdimm_put_key(key);
- key = NULL;
+ return rc;
}
- return key;
+
+ nvdimm_put_key(key);
+ nvdimm->sec.state = nvdimm_security_state(nvdimm, NVDIMM_USER);
+ return 0;
}
static int __nvdimm_security_unlock(struct nvdimm *nvdimm)
{
struct device *dev = &nvdimm->dev;
struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev);
- struct key *key = NULL;
+ struct key *key;
+ const void *data;
int rc;
/* The bus lock should be held at the top level of the call stack */
if (!key_revalidate)
return 0;
- key = nvdimm_key_revalidate(nvdimm);
- if (!key)
- return nvdimm_security_freeze(nvdimm);
+ return nvdimm_key_revalidate(nvdimm);
} else
- key = nvdimm_request_key(nvdimm);
+ data = nvdimm_get_key_payload(nvdimm, &key);
- if (!key)
- return -ENOKEY;
-
- rc = nvdimm->sec.ops->unlock(nvdimm, key_data(key));
+ rc = nvdimm->sec.ops->unlock(nvdimm, data);
dev_dbg(dev, "key: %d unlock: %s\n", key_serial(key),
rc == 0 ? "success" : "fail");
struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev);
struct key *key;
int rc;
+ const void *data;
/* The bus lock should be held at the top level of the call stack */
lockdep_assert_held(&nvdimm_bus->reconfig_mutex);
return -EBUSY;
}
- key = nvdimm_lookup_user_key(nvdimm, keyid, NVDIMM_BASE_KEY);
- if (!key)
+ data = nvdimm_get_user_key_payload(nvdimm, keyid,
+ NVDIMM_BASE_KEY, &key);
+ if (!data)
return -ENOKEY;
- rc = nvdimm->sec.ops->disable(nvdimm, key_data(key));
+ rc = nvdimm->sec.ops->disable(nvdimm, data);
dev_dbg(dev, "key: %d disable: %s\n", key_serial(key),
rc == 0 ? "success" : "fail");
struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev);
struct key *key, *newkey;
int rc;
+ const void *data, *newdata;
/* The bus lock should be held at the top level of the call stack */
lockdep_assert_held(&nvdimm_bus->reconfig_mutex);
return -EIO;
}
- if (keyid == 0)
- key = NULL;
- else {
- key = nvdimm_lookup_user_key(nvdimm, keyid, NVDIMM_BASE_KEY);
- if (!key)
- return -ENOKEY;
- }
+ data = nvdimm_get_user_key_payload(nvdimm, keyid,
+ NVDIMM_BASE_KEY, &key);
+ if (!data)
+ return -ENOKEY;
- newkey = nvdimm_lookup_user_key(nvdimm, new_keyid, NVDIMM_NEW_KEY);
- if (!newkey) {
+ newdata = nvdimm_get_user_key_payload(nvdimm, new_keyid,
+ NVDIMM_NEW_KEY, &newkey);
+ if (!newdata) {
nvdimm_put_key(key);
return -ENOKEY;
}
- rc = nvdimm->sec.ops->change_key(nvdimm, key ? key_data(key) : NULL,
- key_data(newkey), pass_type);
+ rc = nvdimm->sec.ops->change_key(nvdimm, data, newdata, pass_type);
dev_dbg(dev, "key: %d %d update%s: %s\n",
key_serial(key), key_serial(newkey),
pass_type == NVDIMM_MASTER ? "(master)" : "(user)",
{
struct device *dev = &nvdimm->dev;
struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev);
- struct key *key;
+ struct key *key = NULL;
int rc;
+ const void *data;
/* The bus lock should be held at the top level of the call stack */
lockdep_assert_held(&nvdimm_bus->reconfig_mutex);
return -EOPNOTSUPP;
}
- key = nvdimm_lookup_user_key(nvdimm, keyid, NVDIMM_BASE_KEY);
- if (!key)
+ data = nvdimm_get_user_key_payload(nvdimm, keyid,
+ NVDIMM_BASE_KEY, &key);
+ if (!data)
return -ENOKEY;
- rc = nvdimm->sec.ops->erase(nvdimm, key_data(key), pass_type);
+ rc = nvdimm->sec.ops->erase(nvdimm, data, pass_type);
dev_dbg(dev, "key: %d erase%s: %s\n", key_serial(key),
pass_type == NVDIMM_MASTER ? "(master)" : "(user)",
rc == 0 ? "success" : "fail");
{
struct device *dev = &nvdimm->dev;
struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev);
- struct key *key;
+ struct key *key = NULL;
int rc;
+ const void *data;
/* The bus lock should be held at the top level of the call stack */
lockdep_assert_held(&nvdimm_bus->reconfig_mutex);
return -EBUSY;
}
- if (keyid == 0)
- key = NULL;
- else {
- key = nvdimm_lookup_user_key(nvdimm, keyid, NVDIMM_BASE_KEY);
- if (!key)
- return -ENOKEY;
- }
+ data = nvdimm_get_user_key_payload(nvdimm, keyid,
+ NVDIMM_BASE_KEY, &key);
+ if (!data)
+ return -ENOKEY;
- rc = nvdimm->sec.ops->overwrite(nvdimm, key ? key_data(key) : NULL);
+ rc = nvdimm->sec.ops->overwrite(nvdimm, data);
dev_dbg(dev, "key: %d overwrite submission: %s\n", key_serial(key),
rc == 0 ? "success" : "fail");
"Cancelling I/O %d", req->tag);
nvme_req(req)->status = NVME_SC_ABORT_REQ;
- blk_mq_complete_request(req);
+ blk_mq_complete_request_sync(req);
return true;
}
EXPORT_SYMBOL_GPL(nvme_cancel_request);
memset(queue, 0, sizeof(*queue));
queue->ctrl = ctrl;
queue->qnum = idx;
- atomic_set(&queue->csn, 1);
+ atomic_set(&queue->csn, 0);
queue->dev = ctrl->dev;
if (idx > 0)
*/
queue->connection_id = 0;
- atomic_set(&queue->csn, 1);
+ atomic_set(&queue->csn, 0);
}
static void
{
struct nvme_fc_cmd_iu *cmdiu = &op->cmd_iu;
struct nvme_command *sqe = &cmdiu->sqe;
- u32 csn;
int ret, opstate;
/*
/* format the FC-NVME CMD IU and fcp_req */
cmdiu->connection_id = cpu_to_be64(queue->connection_id);
- csn = atomic_inc_return(&queue->csn);
- cmdiu->csn = cpu_to_be32(csn);
cmdiu->data_len = cpu_to_be32(data_len);
switch (io_dir) {
case NVMEFC_FCP_WRITE:
if (!(op->flags & FCOP_FLAGS_AEN))
blk_mq_start_request(op->rq);
+ cmdiu->csn = cpu_to_be32(atomic_inc_return(&queue->csn));
ret = ctrl->lport->ops->fcp_io(&ctrl->lport->localport,
&ctrl->rport->remoteport,
queue->lldd_handle, &op->fcp_req);
if (ret) {
+ /*
+ * If the lld fails to send the command is there an issue with
+ * the csn value? If the command that fails is the Connect,
+ * no - as the connection won't be live. If it is a command
+ * post-connect, it's possible a gap in csn may be created.
+ * Does this matter? As Linux initiators don't send fused
+ * commands, no. The gap would exist, but as there's nothing
+ * that depends on csn order to be delivered on the target
+ * side, it shouldn't hurt. It would be difficult for a
+ * target to even detect the csn gap as it has no idea when the
+ * cmd with the csn was supposed to arrive.
+ */
opstate = atomic_xchg(&op->state, FCPOP_STATE_COMPLETE);
__nvme_fc_fcpop_chk_teardowns(ctrl, op, opstate);
static void nvme_update_ns_ana_state(struct nvme_ana_group_desc *desc,
struct nvme_ns *ns)
{
- enum nvme_ana_state old;
-
mutex_lock(&ns->head->lock);
- old = ns->ana_state;
ns->ana_grpid = le32_to_cpu(desc->grpid);
ns->ana_state = desc->state;
clear_bit(NVME_NS_ANA_PENDING, &ns->flags);
- if (nvme_state_is_live(ns->ana_state) && !nvme_state_is_live(old))
+ if (nvme_state_is_live(ns->ana_state))
nvme_mpath_set_live(ns);
mutex_unlock(&ns->head->lock);
}
return ret;
}
-static inline void nvme_tcp_end_request(struct request *rq, __le16 status)
+static inline void nvme_tcp_end_request(struct request *rq, u16 status)
{
union nvme_result res = {};
return len;
}
+u64 nvmet_get_log_page_offset(struct nvme_command *cmd)
+{
+ return le64_to_cpu(cmd->get_log_page.lpo);
+}
+
static void nvmet_execute_get_log_page_noop(struct nvmet_req *req)
{
nvmet_req_complete(req, nvmet_zero_sgl(req, 0, req->data_len));
ret = nvmet_p2pmem_ns_enable(ns);
if (ret)
- goto out_unlock;
+ goto out_dev_disable;
list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry)
nvmet_p2pmem_ns_add_p2p(ctrl, ns);
out_dev_put:
list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry)
pci_dev_put(radix_tree_delete(&ctrl->p2p_ns_map, ns->nsid));
-
+out_dev_disable:
nvmet_ns_dev_disable(ns);
goto out_unlock;
}
memcpy(traddr, port->disc_addr.traddr, NVMF_TRADDR_SIZE);
}
+static size_t discovery_log_entries(struct nvmet_req *req)
+{
+ struct nvmet_ctrl *ctrl = req->sq->ctrl;
+ struct nvmet_subsys_link *p;
+ struct nvmet_port *r;
+ size_t entries = 0;
+
+ list_for_each_entry(p, &req->port->subsystems, entry) {
+ if (!nvmet_host_allowed(p->subsys, ctrl->hostnqn))
+ continue;
+ entries++;
+ }
+ list_for_each_entry(r, &req->port->referrals, entry)
+ entries++;
+ return entries;
+}
+
static void nvmet_execute_get_disc_log_page(struct nvmet_req *req)
{
const int entry_size = sizeof(struct nvmf_disc_rsp_page_entry);
struct nvmet_ctrl *ctrl = req->sq->ctrl;
struct nvmf_disc_rsp_page_hdr *hdr;
+ u64 offset = nvmet_get_log_page_offset(req->cmd);
size_t data_len = nvmet_get_log_page_len(req->cmd);
- size_t alloc_len = max(data_len, sizeof(*hdr));
- int residual_len = data_len - sizeof(*hdr);
+ size_t alloc_len;
struct nvmet_subsys_link *p;
struct nvmet_port *r;
u32 numrec = 0;
u16 status = 0;
+ void *buffer;
+
+ /* Spec requires dword aligned offsets */
+ if (offset & 0x3) {
+ status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ goto out;
+ }
/*
* Make sure we're passing at least a buffer of response header size.
* If host provided data len is less than the header size, only the
* number of bytes requested by host will be sent to host.
*/
- hdr = kzalloc(alloc_len, GFP_KERNEL);
- if (!hdr) {
+ down_read(&nvmet_config_sem);
+ alloc_len = sizeof(*hdr) + entry_size * discovery_log_entries(req);
+ buffer = kzalloc(alloc_len, GFP_KERNEL);
+ if (!buffer) {
+ up_read(&nvmet_config_sem);
status = NVME_SC_INTERNAL;
goto out;
}
- down_read(&nvmet_config_sem);
+ hdr = buffer;
list_for_each_entry(p, &req->port->subsystems, entry) {
+ char traddr[NVMF_TRADDR_SIZE];
+
if (!nvmet_host_allowed(p->subsys, ctrl->hostnqn))
continue;
- if (residual_len >= entry_size) {
- char traddr[NVMF_TRADDR_SIZE];
-
- nvmet_set_disc_traddr(req, req->port, traddr);
- nvmet_format_discovery_entry(hdr, req->port,
- p->subsys->subsysnqn, traddr,
- NVME_NQN_NVME, numrec);
- residual_len -= entry_size;
- }
+
+ nvmet_set_disc_traddr(req, req->port, traddr);
+ nvmet_format_discovery_entry(hdr, req->port,
+ p->subsys->subsysnqn, traddr,
+ NVME_NQN_NVME, numrec);
numrec++;
}
list_for_each_entry(r, &req->port->referrals, entry) {
- if (residual_len >= entry_size) {
- nvmet_format_discovery_entry(hdr, r,
- NVME_DISC_SUBSYS_NAME,
- r->disc_addr.traddr,
- NVME_NQN_DISC, numrec);
- residual_len -= entry_size;
- }
+ nvmet_format_discovery_entry(hdr, r,
+ NVME_DISC_SUBSYS_NAME,
+ r->disc_addr.traddr,
+ NVME_NQN_DISC, numrec);
numrec++;
}
up_read(&nvmet_config_sem);
- status = nvmet_copy_to_sgl(req, 0, hdr, data_len);
- kfree(hdr);
+ status = nvmet_copy_to_sgl(req, 0, buffer + offset, data_len);
+ kfree(buffer);
out:
nvmet_req_complete(req, status);
}
return ret;
}
-static void nvmet_file_init_bvec(struct bio_vec *bv, struct sg_page_iter *iter)
+static void nvmet_file_init_bvec(struct bio_vec *bv, struct scatterlist *sg)
{
- bv->bv_page = sg_page_iter_page(iter);
- bv->bv_offset = iter->sg->offset;
- bv->bv_len = PAGE_SIZE - iter->sg->offset;
+ bv->bv_page = sg_page(sg);
+ bv->bv_offset = sg->offset;
+ bv->bv_len = sg->length;
}
static ssize_t nvmet_file_submit_bvec(struct nvmet_req *req, loff_t pos,
static bool nvmet_file_execute_io(struct nvmet_req *req, int ki_flags)
{
- ssize_t nr_bvec = DIV_ROUND_UP(req->data_len, PAGE_SIZE);
- struct sg_page_iter sg_pg_iter;
+ ssize_t nr_bvec = req->sg_cnt;
unsigned long bv_cnt = 0;
bool is_sync = false;
size_t len = 0, total_len = 0;
ssize_t ret = 0;
loff_t pos;
-
+ int i;
+ struct scatterlist *sg;
if (req->f.mpool_alloc && nr_bvec > NVMET_MAX_MPOOL_BVEC)
is_sync = true;
}
memset(&req->f.iocb, 0, sizeof(struct kiocb));
- for_each_sg_page(req->sg, &sg_pg_iter, req->sg_cnt, 0) {
- nvmet_file_init_bvec(&req->f.bvec[bv_cnt], &sg_pg_iter);
+ for_each_sg(req->sg, sg, req->sg_cnt, i) {
+ nvmet_file_init_bvec(&req->f.bvec[bv_cnt], sg);
len += req->f.bvec[bv_cnt].bv_len;
total_len += req->f.bvec[bv_cnt].bv_len;
bv_cnt++;
static void nvmet_file_execute_rw(struct nvmet_req *req)
{
- ssize_t nr_bvec = DIV_ROUND_UP(req->data_len, PAGE_SIZE);
+ ssize_t nr_bvec = req->sg_cnt;
if (!req->sg_cnt || !nr_bvec) {
nvmet_req_complete(req, 0);
u16 nvmet_zero_sgl(struct nvmet_req *req, off_t off, size_t len);
u32 nvmet_get_log_page_len(struct nvme_command *cmd);
+u64 nvmet_get_log_page_offset(struct nvme_command *cmd);
extern struct list_head *nvmet_ports;
void nvmet_port_disc_changed(struct nvmet_port *port,
#define DBG_IRT(x...)
#endif
+#ifdef CONFIG_64BIT
+#define COMPARE_IRTE_ADDR(irte, hpa) ((irte)->dest_iosapic_addr == (hpa))
+#else
#define COMPARE_IRTE_ADDR(irte, hpa) \
- ((irte)->dest_iosapic_addr == F_EXTEND(hpa))
+ ((irte)->dest_iosapic_addr == ((hpa) | 0xffffffff00000000ULL))
+#endif
#define IOSAPIC_REG_SELECT 0x00
#define IOSAPIC_REG_WINDOW 0x10
* removed from the slot/adapter.
*/
msleep(1000);
+
+ /* Ignore link or presence changes caused by power off */
+ atomic_and(~(PCI_EXP_SLTSTA_DLLSC | PCI_EXP_SLTSTA_PDC),
+ &ctrl->pending_events);
}
/* turn off Green LED */
u32 pcie_bandwidth_capable(struct pci_dev *dev, enum pci_bus_speed *speed,
enum pcie_link_width *width);
void __pcie_print_link_status(struct pci_dev *dev, bool verbose);
+void pcie_report_downtraining(struct pci_dev *dev);
/* Single Root I/O Virtualization */
struct pci_sriov {
{
u16 lnk_ctl;
+ pcie_capability_write_word(dev, PCI_EXP_LNKSTA, PCI_EXP_LNKSTA_LBMS);
+
pcie_capability_read_word(dev, PCI_EXP_LNKCTL, &lnk_ctl);
lnk_ctl |= PCI_EXP_LNKCTL_LBMIE;
pcie_capability_write_word(dev, PCI_EXP_LNKCTL, lnk_ctl);
pcie_capability_write_word(dev, PCI_EXP_LNKCTL, lnk_ctl);
}
-static irqreturn_t pcie_bw_notification_handler(int irq, void *context)
+static irqreturn_t pcie_bw_notification_irq(int irq, void *context)
{
struct pcie_device *srv = context;
struct pci_dev *port = srv->port;
- struct pci_dev *dev;
u16 link_status, events;
int ret;
if (ret != PCIBIOS_SUCCESSFUL || !events)
return IRQ_NONE;
+ pcie_capability_write_word(port, PCI_EXP_LNKSTA, events);
+ pcie_update_link_speed(port->subordinate, link_status);
+ return IRQ_WAKE_THREAD;
+}
+
+static irqreturn_t pcie_bw_notification_handler(int irq, void *context)
+{
+ struct pcie_device *srv = context;
+ struct pci_dev *port = srv->port;
+ struct pci_dev *dev;
+
/*
* Print status from downstream devices, not this root port or
* downstream switch port.
*/
down_read(&pci_bus_sem);
list_for_each_entry(dev, &port->subordinate->devices, bus_list)
- __pcie_print_link_status(dev, false);
+ pcie_report_downtraining(dev);
up_read(&pci_bus_sem);
- pcie_update_link_speed(port->subordinate, link_status);
- pcie_capability_write_word(port, PCI_EXP_LNKSTA, events);
return IRQ_HANDLED;
}
if (!pcie_link_bandwidth_notification_supported(srv->port))
return -ENODEV;
- ret = request_threaded_irq(srv->irq, NULL, pcie_bw_notification_handler,
+ ret = request_threaded_irq(srv->irq, pcie_bw_notification_irq,
+ pcie_bw_notification_handler,
IRQF_SHARED, "PCIe BW notif", srv);
if (ret)
return ret;
return dev;
}
-static void pcie_report_downtraining(struct pci_dev *dev)
+void pcie_report_downtraining(struct pci_dev *dev)
{
if (!pci_is_pcie(dev))
return;
/* https://bugzilla.kernel.org/show_bug.cgi?id=42679#c14 */
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9130,
quirk_dma_func1_alias);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9170,
+ quirk_dma_func1_alias);
/* https://bugzilla.kernel.org/show_bug.cgi?id=42679#c47 + c57 */
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9172,
quirk_dma_func1_alias);
struct sun4i_usb_phy_data *data = to_sun4i_usb_phy_data(phy);
int new_mode;
- if (phy->index != 0)
+ if (phy->index != 0) {
+ if (mode == PHY_MODE_USB_HOST)
+ return 0;
return -EINVAL;
+ }
switch (mode) {
case PHY_MODE_USB_HOST:
#include <linux/debugfs.h>
#include <linux/device.h>
+#include <linux/dmi.h>
#include <linux/init.h>
#include <linux/io.h>
#include <linux/platform_data/x86/clk-pmc-atom.h>
}
#endif /* CONFIG_DEBUG_FS */
+/*
+ * Some systems need one or more of their pmc_plt_clks to be
+ * marked as critical.
+ */
+static const struct dmi_system_id critclk_systems[] = {
+ {
+ .ident = "MPL CEC1x",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "MPL AG"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "CEC10 Family"),
+ },
+ },
+ { /*sentinel*/ }
+};
+
static int pmc_setup_clks(struct pci_dev *pdev, void __iomem *pmc_regmap,
const struct pmc_data *pmc_data)
{
struct platform_device *clkdev;
struct pmc_clk_data *clk_data;
+ const struct dmi_system_id *d = dmi_first_match(critclk_systems);
clk_data = kzalloc(sizeof(*clk_data), GFP_KERNEL);
if (!clk_data)
clk_data->base = pmc_regmap; /* offset is added by client */
clk_data->clks = pmc_data->clks;
+ if (d) {
+ clk_data->critical = true;
+ pr_info("%s critclks quirk enabled\n", d->ident);
+ }
clkdev = platform_device_register_data(&pdev->dev, "clk-pmc-atom",
PLATFORM_DEVID_NONE,
arb->rstc.nr_resets = ARRAY_SIZE(axg_audio_arb_reset_bits);
arb->rstc.ops = &meson_audio_arb_rstc_ops;
arb->rstc.of_node = dev->of_node;
+ arb->rstc.owner = THIS_MODULE;
/*
* Enable general :
will be called rtc-s5m.
config RTC_DRV_SD3078
- tristate "ZXW Crystal SD3078"
+ tristate "ZXW Shenzhen whwave SD3078"
help
- If you say yes here you get support for the ZXW Crystal
+ If you say yes here you get support for the ZXW Shenzhen whwave
SD3078 RTC chips.
This driver can also be built as a module. If so, the module
struct cros_ec_rtc *cros_ec_rtc = dev_get_drvdata(&pdev->dev);
if (device_may_wakeup(dev))
- enable_irq_wake(cros_ec_rtc->cros_ec->irq);
+ return enable_irq_wake(cros_ec_rtc->cros_ec->irq);
return 0;
}
struct cros_ec_rtc *cros_ec_rtc = dev_get_drvdata(&pdev->dev);
if (device_may_wakeup(dev))
- disable_irq_wake(cros_ec_rtc->cros_ec->irq);
+ return disable_irq_wake(cros_ec_rtc->cros_ec->irq);
return 0;
}
da9063_data_to_tm(data, &rtc->alarm_time, rtc);
rtc->rtc_sync = false;
+ /*
+ * TODO: some models have alarms on a minute boundary but still support
+ * real hardware interrupts. Add this once the core supports it.
+ */
+ if (config->rtc_data_start != RTC_SEC)
+ rtc->rtc_dev->uie_unsupported = 1;
+
irq_alarm = platform_get_irq_byname(pdev, "ALARM");
ret = devm_request_threaded_irq(&pdev->dev, irq_alarm, NULL,
da9063_alarm_event,
static inline int sh_rtc_read_alarm_value(struct sh_rtc *rtc, int reg_off)
{
unsigned int byte;
- int value = 0xff; /* return 0xff for ignored values */
+ int value = -1; /* return -1 for ignored values */
byte = readb(rtc->regbase + reg_off);
if (byte & AR_ENB) {
#include <asm/crw.h>
#include <asm/isc.h>
#include <asm/ebcdic.h>
+#include <asm/ap.h>
#include "css.h"
#include "cio.h"
" failed (rc=%d).\n", ret);
}
+static void chsc_process_sei_ap_cfg_chg(struct chsc_sei_nt0_area *sei_area)
+{
+ CIO_CRW_EVENT(3, "chsc: ap config changed\n");
+ if (sei_area->rs != 5)
+ return;
+
+ ap_bus_cfg_chg();
+}
+
static void chsc_process_sei_nt2(struct chsc_sei_nt2_area *sei_area)
{
switch (sei_area->cc) {
case 2: /* i/o resource accessibility */
chsc_process_sei_res_acc(sei_area);
break;
+ case 3: /* ap config changed */
+ chsc_process_sei_ap_cfg_chg(sei_area);
+ break;
case 7: /* channel-path-availability information */
chsc_process_sei_chp_avail(sei_area);
break;
{
struct vfio_ccw_private *private;
struct irb *irb;
+ bool is_final;
private = container_of(work, struct vfio_ccw_private, io_work);
irb = &private->irb;
+ is_final = !(scsw_actl(&irb->scsw) &
+ (SCSW_ACTL_DEVACT | SCSW_ACTL_SCHACT));
if (scsw_is_solicited(&irb->scsw)) {
cp_update_scsw(&private->cp, &irb->scsw);
- cp_free(&private->cp);
+ if (is_final)
+ cp_free(&private->cp);
}
memcpy(private->io_region->irb_area, irb, sizeof(*irb));
if (private->io_trigger)
eventfd_signal(private->io_trigger, 1);
- if (private->mdev)
+ if (private->mdev && is_final)
private->state = VFIO_CCW_STATE_IDLE;
}
struct ap_device *ap_dev = to_ap_dev(dev);
struct ap_driver *ap_drv = ap_dev->drv;
+ /* prepare ap queue device removal */
if (is_queue_dev(dev))
- ap_queue_remove(to_ap_queue(dev));
+ ap_queue_prepare_remove(to_ap_queue(dev));
+
+ /* driver's chance to clean up gracefully */
if (ap_drv->remove)
ap_drv->remove(ap_dev);
+ /* now do the ap queue device remove */
+ if (is_queue_dev(dev))
+ ap_queue_remove(to_ap_queue(dev));
+
/* Remove queue/card from list of active queues/cards */
spin_lock_bh(&ap_list_lock);
if (is_card_dev(dev))
}
EXPORT_SYMBOL(ap_bus_force_rescan);
+/*
+* A config change has happened, force an ap bus rescan.
+*/
+void ap_bus_cfg_chg(void)
+{
+ AP_DBF(DBF_INFO, "%s config change, forcing bus rescan\n", __func__);
+
+ ap_bus_force_rescan();
+}
+
/*
* hex2bitmap() - parse hex mask string and set bitmap.
* Valid strings are "0x012345678" with at least one valid hex number.
AP_STATE_WORKING,
AP_STATE_QUEUE_FULL,
AP_STATE_SUSPEND_WAIT,
+ AP_STATE_REMOVE, /* about to be removed from driver */
AP_STATE_UNBOUND, /* momentary not bound to a driver */
AP_STATE_BORKED, /* broken */
NR_AP_STATES
void ap_queue_init_reply(struct ap_queue *aq, struct ap_message *ap_msg);
struct ap_queue *ap_queue_create(ap_qid_t qid, int device_type);
+void ap_queue_prepare_remove(struct ap_queue *aq);
void ap_queue_remove(struct ap_queue *aq);
void ap_queue_suspend(struct ap_device *ap_dev);
void ap_queue_resume(struct ap_device *ap_dev);
[AP_EVENT_POLL] = ap_sm_suspend_read,
[AP_EVENT_TIMEOUT] = ap_sm_nop,
},
+ [AP_STATE_REMOVE] = {
+ [AP_EVENT_POLL] = ap_sm_nop,
+ [AP_EVENT_TIMEOUT] = ap_sm_nop,
+ },
[AP_STATE_UNBOUND] = {
[AP_EVENT_POLL] = ap_sm_nop,
[AP_EVENT_TIMEOUT] = ap_sm_nop,
}
EXPORT_SYMBOL(ap_flush_queue);
-void ap_queue_remove(struct ap_queue *aq)
+void ap_queue_prepare_remove(struct ap_queue *aq)
{
- ap_flush_queue(aq);
+ spin_lock_bh(&aq->lock);
+ /* flush queue */
+ __ap_flush_queue(aq);
+ /* set REMOVE state to prevent new messages are queued in */
+ aq->state = AP_STATE_REMOVE;
del_timer_sync(&aq->timeout);
+ spin_unlock_bh(&aq->lock);
+}
- /* reset with zero, also clears irq registration */
+void ap_queue_remove(struct ap_queue *aq)
+{
+ /*
+ * all messages have been flushed and the state is
+ * AP_STATE_REMOVE. Now reset with zero which also
+ * clears the irq registration and move the state
+ * to AP_STATE_UNBOUND to signal that this queue
+ * is not used by any driver currently.
+ */
spin_lock_bh(&aq->lock);
ap_zapq(aq->qid);
aq->state = AP_STATE_UNBOUND;
spin_unlock_bh(&aq->lock);
}
-EXPORT_SYMBOL(ap_queue_remove);
void ap_queue_reinit_state(struct ap_queue *aq)
{
ap_wait(ap_sm_event(aq, AP_EVENT_POLL));
spin_unlock_bh(&aq->lock);
}
-EXPORT_SYMBOL(ap_queue_reinit_state);
static inline struct zcrypt_queue *zcrypt_pick_queue(struct zcrypt_card *zc,
struct zcrypt_queue *zq,
+ struct module **pmod,
unsigned int weight)
{
if (!zq || !try_module_get(zq->queue->ap_dev.drv->driver.owner))
atomic_add(weight, &zc->load);
atomic_add(weight, &zq->load);
zq->request_count++;
+ *pmod = zq->queue->ap_dev.drv->driver.owner;
return zq;
}
static inline void zcrypt_drop_queue(struct zcrypt_card *zc,
struct zcrypt_queue *zq,
+ struct module *mod,
unsigned int weight)
{
- struct module *mod = zq->queue->ap_dev.drv->driver.owner;
-
zq->request_count--;
atomic_sub(weight, &zc->load);
atomic_sub(weight, &zq->load);
unsigned int weight, pref_weight;
unsigned int func_code;
int qid = 0, rc = -ENODEV;
+ struct module *mod;
trace_s390_zcrypt_req(mex, TP_ICARSAMODEXPO);
pref_weight = weight;
}
}
- pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, weight);
+ pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, &mod, weight);
spin_unlock(&zcrypt_list_lock);
if (!pref_zq) {
rc = pref_zq->ops->rsa_modexpo(pref_zq, mex);
spin_lock(&zcrypt_list_lock);
- zcrypt_drop_queue(pref_zc, pref_zq, weight);
+ zcrypt_drop_queue(pref_zc, pref_zq, mod, weight);
spin_unlock(&zcrypt_list_lock);
out:
unsigned int weight, pref_weight;
unsigned int func_code;
int qid = 0, rc = -ENODEV;
+ struct module *mod;
trace_s390_zcrypt_req(crt, TP_ICARSACRT);
pref_weight = weight;
}
}
- pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, weight);
+ pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, &mod, weight);
spin_unlock(&zcrypt_list_lock);
if (!pref_zq) {
rc = pref_zq->ops->rsa_modexpo_crt(pref_zq, crt);
spin_lock(&zcrypt_list_lock);
- zcrypt_drop_queue(pref_zc, pref_zq, weight);
+ zcrypt_drop_queue(pref_zc, pref_zq, mod, weight);
spin_unlock(&zcrypt_list_lock);
out:
unsigned int func_code;
unsigned short *domain;
int qid = 0, rc = -ENODEV;
+ struct module *mod;
trace_s390_zcrypt_req(xcRB, TB_ZSECSENDCPRB);
pref_weight = weight;
}
}
- pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, weight);
+ pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, &mod, weight);
spin_unlock(&zcrypt_list_lock);
if (!pref_zq) {
rc = pref_zq->ops->send_cprb(pref_zq, xcRB, &ap_msg);
spin_lock(&zcrypt_list_lock);
- zcrypt_drop_queue(pref_zc, pref_zq, weight);
+ zcrypt_drop_queue(pref_zc, pref_zq, mod, weight);
spin_unlock(&zcrypt_list_lock);
out:
unsigned int func_code;
struct ap_message ap_msg;
int qid = 0, rc = -ENODEV;
+ struct module *mod;
trace_s390_zcrypt_req(xcrb, TP_ZSENDEP11CPRB);
pref_weight = weight;
}
}
- pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, weight);
+ pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, &mod, weight);
spin_unlock(&zcrypt_list_lock);
if (!pref_zq) {
rc = pref_zq->ops->send_ep11_cprb(pref_zq, xcrb, &ap_msg);
spin_lock(&zcrypt_list_lock);
- zcrypt_drop_queue(pref_zc, pref_zq, weight);
+ zcrypt_drop_queue(pref_zc, pref_zq, mod, weight);
spin_unlock(&zcrypt_list_lock);
out_free:
struct ap_message ap_msg;
unsigned int domain;
int qid = 0, rc = -ENODEV;
+ struct module *mod;
trace_s390_zcrypt_req(buffer, TP_HWRNGCPRB);
pref_weight = weight;
}
}
- pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, weight);
+ pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, &mod, weight);
spin_unlock(&zcrypt_list_lock);
if (!pref_zq) {
rc = pref_zq->ops->rng(pref_zq, buffer, &ap_msg);
spin_lock(&zcrypt_list_lock);
- zcrypt_drop_queue(pref_zc, pref_zq, weight);
+ zcrypt_drop_queue(pref_zc, pref_zq, mod, weight);
spin_unlock(&zcrypt_list_lock);
out:
/* QDIO queue and buffer handling */
/*****************************************************************************/
#define QETH_MAX_QUEUES 4
+#define QETH_IQD_MIN_TXQ 2 /* One for ucast, one for mcast. */
+#define QETH_IQD_MCAST_TXQ 0
+#define QETH_IQD_MIN_UCAST_TXQ 1
#define QETH_IN_BUF_SIZE_DEFAULT 65536
#define QETH_IN_BUF_COUNT_DEFAULT 64
#define QETH_IN_BUF_COUNT_HSDEFAULT 128
u64 rx_errors;
u64 rx_dropped;
u64 rx_multicast;
- u64 tx_errors;
};
struct qeth_out_q_stats {
u64 skbs_linearized_fail;
u64 tso_bytes;
u64 packing_mode_switch;
+ u64 stopped;
/* rtnl_link_stats64 */
u64 tx_packets;
atomic_t set_pci_flags_count;
};
+static inline bool qeth_out_queue_is_full(struct qeth_qdio_out_q *queue)
+{
+ return atomic_read(&queue->used_buffers) >= QDIO_MAX_BUFFERS_PER_Q;
+}
+
struct qeth_qdio_info {
atomic_t state;
/* input */
return dev->netdev_ops != NULL;
}
+static inline u16 qeth_iqd_translate_txq(struct net_device *dev, u16 txq)
+{
+ if (txq == QETH_IQD_MCAST_TXQ)
+ return dev->num_tx_queues - 1;
+ if (txq == dev->num_tx_queues - 1)
+ return QETH_IQD_MCAST_TXQ;
+ return txq;
+}
+
static inline void qeth_scrub_qdio_buffer(struct qdio_buffer *buf,
unsigned int elements)
{
data, QETH_PROT_IPV6);
}
-int qeth_get_priority_queue(struct qeth_card *card, struct sk_buff *skb,
- int ipv);
-static inline struct qeth_qdio_out_q *qeth_get_tx_queue(struct qeth_card *card,
- struct sk_buff *skb,
- int ipv, int cast_type)
-{
- if (IS_IQD(card) && cast_type != RTN_UNICAST)
- return card->qdio.out_qs[card->qdio.no_out_queues - 1];
- if (!card->qdio.do_prio_queueing)
- return card->qdio.out_qs[card->qdio.default_out_queue];
- return card->qdio.out_qs[qeth_get_priority_queue(card, skb, ipv)];
-}
+int qeth_get_priority_queue(struct qeth_card *card, struct sk_buff *skb);
extern struct qeth_discipline qeth_l2_discipline;
extern struct qeth_discipline qeth_l3_discipline;
int qeth_qdio_clear_card(struct qeth_card *, int);
void qeth_clear_working_pool_list(struct qeth_card *);
void qeth_clear_cmd_buffers(struct qeth_channel *);
-void qeth_clear_qdio_buffers(struct qeth_card *);
+void qeth_drain_output_queues(struct qeth_card *card);
void qeth_setadp_promisc_mode(struct qeth_card *);
int qeth_setadpparms_change_macaddr(struct qeth_card *);
void qeth_tx_timeout(struct net_device *);
struct net_device *dev,
netdev_features_t features);
void qeth_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats);
+u16 qeth_iqd_select_queue(struct net_device *dev, struct sk_buff *skb,
+ u8 cast_type, struct net_device *sb_dev);
int qeth_open(struct net_device *dev);
int qeth_stop(struct net_device *dev);
static struct qeth_cmd_buffer *qeth_get_buffer(struct qeth_channel *);
static void qeth_free_buffer_pool(struct qeth_card *);
static int qeth_qdio_establish(struct qeth_card *);
-static void qeth_free_qdio_buffers(struct qeth_card *);
+static void qeth_free_qdio_queues(struct qeth_card *card);
static void qeth_notify_skbs(struct qeth_qdio_out_q *queue,
struct qeth_qdio_out_buffer *buf,
enum iucv_tx_notify notification);
atomic_set(&buf->state, QETH_QDIO_BUF_EMPTY);
}
-static void qeth_clear_outq_buffers(struct qeth_qdio_out_q *q, int free)
+static void qeth_drain_output_queue(struct qeth_qdio_out_q *q, bool free)
{
int j;
}
}
-void qeth_clear_qdio_buffers(struct qeth_card *card)
+void qeth_drain_output_queues(struct qeth_card *card)
{
int i;
QETH_CARD_TEXT(card, 2, "clearqdbf");
/* clear outbound buffers to free skbs */
for (i = 0; i < card->qdio.no_out_queues; ++i) {
- if (card->qdio.out_qs[i]) {
- qeth_clear_outq_buffers(card->qdio.out_qs[i], 0);
- }
+ if (card->qdio.out_qs[i])
+ qeth_drain_output_queue(card->qdio.out_qs[i], false);
}
}
-EXPORT_SYMBOL_GPL(qeth_clear_qdio_buffers);
+EXPORT_SYMBOL_GPL(qeth_drain_output_queues);
static void qeth_free_buffer_pool(struct qeth_card *card)
{
return 0;
}
-static void qeth_set_single_write_queues(struct qeth_card *card)
+static void qeth_osa_set_output_queues(struct qeth_card *card, bool single)
{
- if ((atomic_read(&card->qdio.state) != QETH_QDIO_UNINITIALIZED) &&
- (card->qdio.no_out_queues == 4))
- qeth_free_qdio_buffers(card);
+ unsigned int count = single ? 1 : card->dev->num_tx_queues;
- card->qdio.no_out_queues = 1;
- if (card->qdio.default_out_queue != 0)
- dev_info(&card->gdev->dev, "Priority Queueing not supported\n");
+ rtnl_lock();
+ netif_set_real_num_tx_queues(card->dev, count);
+ rtnl_unlock();
- card->qdio.default_out_queue = 0;
-}
+ if (card->qdio.no_out_queues == count)
+ return;
-static void qeth_set_multiple_write_queues(struct qeth_card *card)
-{
- if ((atomic_read(&card->qdio.state) != QETH_QDIO_UNINITIALIZED) &&
- (card->qdio.no_out_queues == 1)) {
- qeth_free_qdio_buffers(card);
- card->qdio.default_out_queue = 2;
- }
- card->qdio.no_out_queues = 4;
+ if (atomic_read(&card->qdio.state) != QETH_QDIO_UNINITIALIZED)
+ qeth_free_qdio_queues(card);
+
+ if (count == 1)
+ dev_info(&card->gdev->dev, "Priority Queueing not supported\n");
+
+ card->qdio.default_out_queue = single ? 0 : QETH_DEFAULT_QUEUE;
+ card->qdio.no_out_queues = count;
}
-static void qeth_update_from_chp_desc(struct qeth_card *card)
+static int qeth_update_from_chp_desc(struct qeth_card *card)
{
struct ccw_device *ccwdev;
struct channel_path_desc_fmt0 *chp_dsc;
ccwdev = card->data.ccwdev;
chp_dsc = ccw_device_get_chp_desc(ccwdev, 0);
if (!chp_dsc)
- goto out;
+ return -ENOMEM;
card->info.func_level = 0x4100 + chp_dsc->desc;
- if (card->info.type == QETH_CARD_TYPE_IQD)
- goto out;
- /* CHPP field bit 6 == 1 -> single queue */
- if ((chp_dsc->chpp & 0x02) == 0x02)
- qeth_set_single_write_queues(card);
- else
- qeth_set_multiple_write_queues(card);
-out:
+ if (IS_OSD(card) || IS_OSX(card))
+ /* CHPP field bit 6 == 1 -> single queue */
+ qeth_osa_set_output_queues(card, chp_dsc->chpp & 0x02);
+
kfree(chp_dsc);
QETH_DBF_TEXT_(SETUP, 2, "nr:%x", card->qdio.no_out_queues);
QETH_DBF_TEXT_(SETUP, 2, "lvl:%02x", card->info.func_level);
+ return 0;
}
static void qeth_init_qdio_info(struct qeth_card *card)
atomic_set(&card->qdio.state, QETH_QDIO_UNINITIALIZED);
card->qdio.do_prio_queueing = QETH_PRIOQ_DEFAULT;
card->qdio.default_out_queue = QETH_DEFAULT_QUEUE;
- card->qdio.no_out_queues = QETH_MAX_QUEUES;
/* inbound */
card->qdio.no_in_queues = 1;
/* adjust RX buffer size to new max MTU: */
card->qdio.in_buf_size = max_mtu + 2 * PAGE_SIZE;
if (dev->max_mtu && dev->max_mtu != max_mtu)
- qeth_free_qdio_buffers(card);
+ qeth_free_qdio_queues(card);
} else {
if (dev->mtu)
new_mtu = dev->mtu;
if (!q)
return;
- qeth_clear_outq_buffers(q, 1);
+ qeth_drain_output_queue(q, true);
qdio_free_buffers(q->qdio_bufs, QDIO_MAX_BUFFERS_PER_Q);
kfree(q);
}
-static struct qeth_qdio_out_q *qeth_alloc_qdio_out_buf(void)
+static struct qeth_qdio_out_q *qeth_alloc_output_queue(void)
{
struct qeth_qdio_out_q *q = kzalloc(sizeof(*q), GFP_KERNEL);
return q;
}
-static int qeth_alloc_qdio_buffers(struct qeth_card *card)
+static int qeth_alloc_qdio_queues(struct qeth_card *card)
{
int i, j;
/* outbound */
for (i = 0; i < card->qdio.no_out_queues; ++i) {
- card->qdio.out_qs[i] = qeth_alloc_qdio_out_buf();
+ card->qdio.out_qs[i] = qeth_alloc_output_queue();
if (!card->qdio.out_qs[i])
goto out_freeoutq;
QETH_DBF_TEXT_(SETUP, 2, "outq %i", i);
return -ENOMEM;
}
-static void qeth_free_qdio_buffers(struct qeth_card *card)
+static void qeth_free_qdio_queues(struct qeth_card *card)
{
int i, j;
QETH_DBF_TEXT_(SETUP, 2, "5err%d", rc);
goto out_qdio;
}
- rc = qeth_alloc_qdio_buffers(card);
+ rc = qeth_alloc_qdio_queues(card);
if (rc) {
QETH_DBF_TEXT_(SETUP, 2, "5err%d", rc);
goto out_qdio;
rc = qeth_qdio_establish(card);
if (rc) {
QETH_DBF_TEXT_(SETUP, 2, "6err%d", rc);
- qeth_free_qdio_buffers(card);
+ qeth_free_qdio_queues(card);
goto out_qdio;
}
rc = qeth_qdio_activate(card);
}
QETH_TXQ_STAT_ADD(queue, bufs, count);
- netif_trans_update(queue->card->dev);
qdio_flags = QDIO_FLAG_SYNC_OUTPUT;
if (atomic_read(&queue->set_pci_flags_count))
qdio_flags |= QDIO_FLAG_PCI_OUT;
- atomic_add(count, &queue->used_buffers);
rc = do_QDIO(CARD_DDEV(queue->card), qdio_flags,
queue->queue_no, index, count);
if (rc) {
* do_send_packet. So, we check if there is a
* packing buffer to be flushed here.
*/
- netif_stop_queue(queue->card->dev);
index = queue->next_buf_to_fill;
q_was_packing = queue->do_pack;
/* queue->do_pack may change */
goto out;
}
- qeth_free_qdio_buffers(card);
+ qeth_free_qdio_queues(card);
card->options.cq = cq;
rc = 0;
}
QETH_CARD_TEXT_(card, 5, "qcqherr%d", qdio_err);
if (qdio_err) {
- netif_stop_queue(card->dev);
+ netif_tx_stop_all_queues(card->dev);
qeth_schedule_recovery(card);
return;
}
struct qeth_card *card = (struct qeth_card *) card_ptr;
struct qeth_qdio_out_q *queue = card->qdio.out_qs[__queue];
struct qeth_qdio_out_buffer *buffer;
+ struct net_device *dev = card->dev;
+ struct netdev_queue *txq;
int i;
QETH_CARD_TEXT(card, 6, "qdouhdl");
if (qdio_error & QDIO_ERROR_FATAL) {
QETH_CARD_TEXT(card, 2, "achkcond");
- netif_stop_queue(card->dev);
+ netif_tx_stop_all_queues(dev);
qeth_schedule_recovery(card);
return;
}
if (card->info.type != QETH_CARD_TYPE_IQD)
qeth_check_outbound_queue(queue);
- netif_wake_queue(queue->card->dev);
-}
-
-/* We cannot use outbound queue 3 for unicast packets on HiperSockets */
-static inline int qeth_cut_iqd_prio(struct qeth_card *card, int queue_num)
-{
- if ((card->info.type == QETH_CARD_TYPE_IQD) && (queue_num == 3))
- return 2;
- return queue_num;
+ if (IS_IQD(card))
+ __queue = qeth_iqd_translate_txq(dev, __queue);
+ txq = netdev_get_tx_queue(dev, __queue);
+ /* xmit may have observed the full-condition, but not yet stopped the
+ * txq. In which case the code below won't trigger. So before returning,
+ * xmit will re-check the txq's fill level and wake it up if needed.
+ */
+ if (netif_tx_queue_stopped(txq) && !qeth_out_queue_is_full(queue))
+ netif_tx_wake_queue(txq);
}
/**
* Note: Function assumes that we have 4 outbound queues.
*/
-int qeth_get_priority_queue(struct qeth_card *card, struct sk_buff *skb,
- int ipv)
+int qeth_get_priority_queue(struct qeth_card *card, struct sk_buff *skb)
{
- __be16 *tci;
+ struct vlan_ethhdr *veth = vlan_eth_hdr(skb);
u8 tos;
switch (card->qdio.do_prio_queueing) {
case QETH_PRIO_Q_ING_TOS:
case QETH_PRIO_Q_ING_PREC:
- switch (ipv) {
+ switch (qeth_get_ip_version(skb)) {
case 4:
tos = ipv4_get_dsfield(ip_hdr(skb));
break;
return card->qdio.default_out_queue;
}
if (card->qdio.do_prio_queueing == QETH_PRIO_Q_ING_PREC)
- return qeth_cut_iqd_prio(card, ~tos >> 6 & 3);
+ return ~tos >> 6 & 3;
if (tos & IPTOS_MINCOST)
- return qeth_cut_iqd_prio(card, 3);
+ return 3;
if (tos & IPTOS_RELIABILITY)
return 2;
if (tos & IPTOS_THROUGHPUT)
case QETH_PRIO_Q_ING_SKB:
if (skb->priority > 5)
return 0;
- return qeth_cut_iqd_prio(card, ~skb->priority >> 1 & 3);
+ return ~skb->priority >> 1 & 3;
case QETH_PRIO_Q_ING_VLAN:
- tci = &((struct ethhdr *)skb->data)->h_proto;
- if (be16_to_cpu(*tci) == ETH_P_8021Q)
- return qeth_cut_iqd_prio(card,
- ~be16_to_cpu(*(tci + 1)) >> (VLAN_PRIO_SHIFT + 1) & 3);
+ if (veth->h_vlan_proto == htons(ETH_P_8021Q))
+ return ~ntohs(veth->h_vlan_TCI) >>
+ (VLAN_PRIO_SHIFT + 1) & 3;
break;
default:
break;
* from qeth_core_header_cache.
* @offset: when mapping the skb, start at skb->data + offset
* @hd_len: if > 0, build a dedicated header element of this size
+ * flush: Prepare the buffer to be flushed, regardless of its fill level.
*/
static int qeth_fill_buffer(struct qeth_qdio_out_q *queue,
struct qeth_qdio_out_buffer *buf,
struct sk_buff *skb, struct qeth_hdr *hdr,
- unsigned int offset, unsigned int hd_len)
+ unsigned int offset, unsigned int hd_len,
+ bool flush)
{
struct qdio_buffer *buffer = buf->buffer;
bool is_first_elem = true;
QETH_TXQ_STAT_INC(queue, skbs_pack);
/* If the buffer still has free elements, keep using it. */
- if (buf->next_element_to_fill <
- QETH_MAX_BUFFER_ELEMENTS(queue->card))
+ if (!flush && buf->next_element_to_fill <
+ QETH_MAX_BUFFER_ELEMENTS(queue->card))
return 0;
}
{
int index = queue->next_buf_to_fill;
struct qeth_qdio_out_buffer *buffer = queue->bufs[index];
+ struct netdev_queue *txq;
+ bool stopped = false;
- /*
- * check if buffer is empty to make sure that we do not 'overtake'
- * ourselves and try to fill a buffer that is already primed
+ /* Just a sanity check, the wake/stop logic should ensure that we always
+ * get a free buffer.
*/
if (atomic_read(&buffer->state) != QETH_QDIO_BUF_EMPTY)
return -EBUSY;
- qeth_fill_buffer(queue, buffer, skb, hdr, offset, hd_len);
+
+ txq = netdev_get_tx_queue(queue->card->dev, skb_get_queue_mapping(skb));
+
+ if (atomic_inc_return(&queue->used_buffers) >= QDIO_MAX_BUFFERS_PER_Q) {
+ /* If a TX completion happens right _here_ and misses to wake
+ * the txq, then our re-check below will catch the race.
+ */
+ QETH_TXQ_STAT_INC(queue, stopped);
+ netif_tx_stop_queue(txq);
+ stopped = true;
+ }
+
+ qeth_fill_buffer(queue, buffer, skb, hdr, offset, hd_len, stopped);
qeth_flush_buffers(queue, index, 1);
+
+ if (stopped && !qeth_out_queue_is_full(queue))
+ netif_tx_start_queue(txq);
return 0;
}
int elements_needed)
{
struct qeth_qdio_out_buffer *buffer;
+ struct netdev_queue *txq;
+ bool stopped = false;
int start_index;
int flush_count = 0;
int do_pack = 0;
QETH_OUT_Q_LOCKED) != QETH_OUT_Q_UNLOCKED);
start_index = queue->next_buf_to_fill;
buffer = queue->bufs[queue->next_buf_to_fill];
- /*
- * check if buffer is empty to make sure that we do not 'overtake'
- * ourselves and try to fill a buffer that is already primed
+
+ /* Just a sanity check, the wake/stop logic should ensure that we always
+ * get a free buffer.
*/
if (atomic_read(&buffer->state) != QETH_QDIO_BUF_EMPTY) {
atomic_set(&queue->state, QETH_OUT_Q_UNLOCKED);
return -EBUSY;
}
+
+ txq = netdev_get_tx_queue(card->dev, skb_get_queue_mapping(skb));
+
/* check if we need to switch packing state of this queue */
qeth_switch_to_packing_if_needed(queue);
if (queue->do_pack) {
(queue->next_buf_to_fill + 1) %
QDIO_MAX_BUFFERS_PER_Q;
buffer = queue->bufs[queue->next_buf_to_fill];
- /* we did a step forward, so check buffer state
- * again */
+
+ /* We stepped forward, so sanity-check again: */
if (atomic_read(&buffer->state) !=
QETH_QDIO_BUF_EMPTY) {
qeth_flush_buffers(queue, start_index,
}
}
- flush_count += qeth_fill_buffer(queue, buffer, skb, hdr, offset,
- hd_len);
+ if (buffer->next_element_to_fill == 0 &&
+ atomic_inc_return(&queue->used_buffers) >= QDIO_MAX_BUFFERS_PER_Q) {
+ /* If a TX completion happens right _here_ and misses to wake
+ * the txq, then our re-check below will catch the race.
+ */
+ QETH_TXQ_STAT_INC(queue, stopped);
+ netif_tx_stop_queue(txq);
+ stopped = true;
+ }
+
+ flush_count += qeth_fill_buffer(queue, buffer, skb, hdr, offset, hd_len,
+ stopped);
if (flush_count)
qeth_flush_buffers(queue, start_index, flush_count);
else if (!atomic_read(&queue->set_pci_flags_count))
if (do_pack)
QETH_TXQ_STAT_ADD(queue, bufs_pack, flush_count);
+ if (stopped && !qeth_out_queue_is_full(queue))
+ netif_tx_start_queue(txq);
return rc;
}
EXPORT_SYMBOL_GPL(qeth_do_send_packet);
} else {
if (!push_len)
kmem_cache_free(qeth_core_header_cache, hdr);
- if (rc == -EBUSY)
- /* roll back to ETH header */
- skb_pull(skb, push_len);
}
return rc;
}
card = dev->ml_priv;
QETH_CARD_TEXT(card, 4, "txtimeo");
- QETH_CARD_STAT_INC(card, tx_errors);
qeth_schedule_recovery(card);
}
EXPORT_SYMBOL_GPL(qeth_tx_timeout);
qeth_clean_channel(&card->write);
qeth_clean_channel(&card->data);
destroy_workqueue(card->event_wq);
- qeth_free_qdio_buffers(card);
+ qeth_free_qdio_queues(card);
unregister_service_level(&card->qeth_service_level);
dev_set_drvdata(&card->gdev->dev, NULL);
kfree(card);
QETH_DBF_TEXT(SETUP, 2, "hrdsetup");
atomic_set(&card->force_alloc_skb, 0);
- qeth_update_from_chp_desc(card);
+ rc = qeth_update_from_chp_desc(card);
+ if (rc)
+ return rc;
retry:
if (retries < 3)
QETH_DBF_MESSAGE(2, "Retrying to do IDX activates on device %x.\n",
switch (card->info.type) {
case QETH_CARD_TYPE_IQD:
- dev = alloc_netdev(0, "hsi%d", NET_NAME_UNKNOWN, ether_setup);
+ dev = alloc_netdev_mqs(0, "hsi%d", NET_NAME_UNKNOWN,
+ ether_setup, QETH_MAX_QUEUES, 1);
+ break;
+ case QETH_CARD_TYPE_OSM:
+ dev = alloc_etherdev(0);
break;
case QETH_CARD_TYPE_OSN:
dev = alloc_netdev(0, "osn%d", NET_NAME_UNKNOWN, ether_setup);
break;
default:
- dev = alloc_etherdev(0);
+ dev = alloc_etherdev_mqs(0, QETH_MAX_QUEUES, 1);
}
if (!dev)
dev->priv_flags &= ~IFF_TX_SKB_SHARING;
dev->hw_features |= NETIF_F_SG;
dev->vlan_features |= NETIF_F_SG;
- if (IS_IQD(card))
+ if (IS_IQD(card)) {
+ netif_set_real_num_tx_queues(dev, QETH_IQD_MIN_TXQ);
dev->features |= NETIF_F_SG;
+ }
}
return dev;
}
qeth_setup_card(card);
- qeth_update_from_chp_desc(card);
-
card->dev = qeth_alloc_netdev(card);
if (!card->dev) {
rc = -ENOMEM;
goto err_card;
}
+ card->qdio.no_out_queues = card->dev->num_tx_queues;
+ rc = qeth_update_from_chp_desc(card);
+ if (rc)
+ goto err_chp_desc;
qeth_determine_capabilities(card);
enforced_disc = qeth_enforce_discipline(card);
switch (enforced_disc) {
err_disc:
qeth_core_free_discipline(card);
err_load:
+err_chp_desc:
free_netdev(card->dev);
err_card:
qeth_core_free_card(card);
if ((gdev->state == CCWGROUP_ONLINE) && card->info.hwtrap)
qeth_hw_trap(card, QETH_DIAGS_TRAP_DISARM);
qeth_qdio_clear_card(card, 0);
- qeth_clear_qdio_buffers(card);
+ qeth_drain_output_queues(card);
qdio_free(CARD_DDEV(card));
}
stats->rx_errors = card->stats.rx_errors;
stats->rx_dropped = card->stats.rx_dropped;
stats->multicast = card->stats.rx_multicast;
- stats->tx_errors = card->stats.tx_errors;
for (i = 0; i < card->qdio.no_out_queues; i++) {
queue = card->qdio.out_qs[i];
}
EXPORT_SYMBOL_GPL(qeth_get_stats64);
+u16 qeth_iqd_select_queue(struct net_device *dev, struct sk_buff *skb,
+ u8 cast_type, struct net_device *sb_dev)
+{
+ if (cast_type != RTN_UNICAST)
+ return QETH_IQD_MCAST_TXQ;
+ return QETH_IQD_MIN_UCAST_TXQ;
+}
+EXPORT_SYMBOL_GPL(qeth_iqd_select_queue);
+
int qeth_open(struct net_device *dev)
{
struct qeth_card *card = dev->ml_priv;
return -EIO;
card->data.state = CH_STATE_UP;
- netif_start_queue(dev);
+ netif_tx_start_all_queues(dev);
napi_enable(&card->napi);
local_bh_disable();
if (!card)
return -EINVAL;
+ if (IS_IQD(card))
+ return -EOPNOTSUPP;
+
mutex_lock(&card->conf_mutex);
if (card->state != CARD_STATE_DOWN) {
rc = -EPERM;
card->qdio.do_prio_queueing = QETH_NO_PRIO_QUEUEING;
card->qdio.default_out_queue = 2;
} else if (sysfs_streq(buf, "no_prio_queueing:3")) {
- if (card->info.type == QETH_CARD_TYPE_IQD) {
- rc = -EPERM;
- goto out;
- }
card->qdio.do_prio_queueing = QETH_NO_PRIO_QUEUEING;
card->qdio.default_out_queue = 3;
} else if (sysfs_streq(buf, "no_prio_queueing")) {
QETH_TXQ_STAT("linearized+error skbs", skbs_linearized_fail),
QETH_TXQ_STAT("TSO bytes", tso_bytes),
QETH_TXQ_STAT("Packing mode switches", packing_mode_switch),
+ QETH_TXQ_STAT("Queue stopped", stopped),
};
static const struct qeth_stats card_stats[] = {
CARD_RDEV_ID(card), CARD_WDEV_ID(card), CARD_DDEV_ID(card));
}
+static void qeth_get_channels(struct net_device *dev,
+ struct ethtool_channels *channels)
+{
+ struct qeth_card *card = dev->ml_priv;
+
+ channels->max_rx = dev->num_rx_queues;
+ channels->max_tx = card->qdio.no_out_queues;
+ channels->max_other = 0;
+ channels->max_combined = 0;
+ channels->rx_count = dev->real_num_rx_queues;
+ channels->tx_count = dev->real_num_tx_queues;
+ channels->other_count = 0;
+ channels->combined_count = 0;
+}
+
/* Helper function to fill 'advertising' and 'supported' which are the same. */
/* Autoneg and full-duplex are supported and advertised unconditionally. */
/* Always advertise and support all speeds up to specified, and only one */
.get_ethtool_stats = qeth_get_ethtool_stats,
.get_sset_count = qeth_get_sset_count,
.get_drvinfo = qeth_get_drvinfo,
+ .get_channels = qeth_get_channels,
.get_link_ksettings = qeth_get_link_ksettings,
};
}
}
-static int qeth_l2_get_cast_type(struct qeth_card *card, struct sk_buff *skb)
+static int qeth_l2_get_cast_type(struct sk_buff *skb)
{
- if (card->info.type == QETH_CARD_TYPE_OSN)
- return RTN_UNICAST;
if (is_broadcast_ether_addr(skb->data))
return RTN_BROADCAST;
if (is_multicast_ether_addr(skb->data))
}
if (card->state == CARD_STATE_HARDSETUP) {
qeth_qdio_clear_card(card, 0);
- qeth_clear_qdio_buffers(card);
+ qeth_drain_output_queues(card);
qeth_clear_working_pool_list(card);
card->state = CARD_STATE_DOWN;
}
struct net_device *dev)
{
struct qeth_card *card = dev->ml_priv;
- int cast_type = qeth_l2_get_cast_type(card, skb);
- int ipv = qeth_get_ip_version(skb);
+ u16 txq = skb_get_queue_mapping(skb);
struct qeth_qdio_out_q *queue;
int tx_bytes = skb->len;
int rc;
- queue = qeth_get_tx_queue(card, skb, ipv, cast_type);
-
- netif_stop_queue(dev);
+ if (IS_IQD(card))
+ txq = qeth_iqd_translate_txq(dev, txq);
+ queue = card->qdio.out_qs[txq];
if (IS_OSN(card))
rc = qeth_l2_xmit_osn(card, skb, queue);
else
- rc = qeth_xmit(card, skb, queue, ipv, cast_type,
- qeth_l2_fill_header);
+ rc = qeth_xmit(card, skb, queue, qeth_get_ip_version(skb),
+ qeth_l2_get_cast_type(skb), qeth_l2_fill_header);
if (!rc) {
QETH_TXQ_STAT_INC(queue, tx_packets);
QETH_TXQ_STAT_ADD(queue, tx_bytes, tx_bytes);
- netif_wake_queue(dev);
return NETDEV_TX_OK;
- } else if (rc == -EBUSY) {
- return NETDEV_TX_BUSY;
- } /* else fall through */
+ }
QETH_TXQ_STAT_INC(queue, tx_dropped);
kfree_skb(skb);
- netif_wake_queue(dev);
return NETDEV_TX_OK;
}
+static u16 qeth_l2_select_queue(struct net_device *dev, struct sk_buff *skb,
+ struct net_device *sb_dev)
+{
+ struct qeth_card *card = dev->ml_priv;
+
+ if (IS_IQD(card))
+ return qeth_iqd_select_queue(dev, skb,
+ qeth_l2_get_cast_type(skb),
+ sb_dev);
+ return qeth_get_priority_queue(card, skb);
+}
+
static const struct device_type qeth_l2_devtype = {
.name = "qeth_layer2",
.groups = qeth_l2_attr_groups,
.ndo_get_stats64 = qeth_get_stats64,
.ndo_start_xmit = qeth_l2_hard_start_xmit,
.ndo_features_check = qeth_features_check,
+ .ndo_select_queue = qeth_l2_select_queue,
.ndo_validate_addr = qeth_l2_validate_addr,
.ndo_set_rx_mode = qeth_l2_set_rx_mode,
.ndo_do_ioctl = qeth_do_ioctl,
}
if (card->state == CARD_STATE_HARDSETUP) {
qeth_qdio_clear_card(card, 0);
- qeth_clear_qdio_buffers(card);
+ qeth_drain_output_queues(card);
qeth_clear_working_pool_list(card);
card->state = CARD_STATE_DOWN;
}
static int qeth_l3_xmit(struct qeth_card *card, struct sk_buff *skb,
struct qeth_qdio_out_q *queue, int ipv, int cast_type)
{
- unsigned char eth_hdr[ETH_HLEN];
unsigned int hw_hdr_len;
int rc;
rc = skb_cow_head(skb, hw_hdr_len - ETH_HLEN);
if (rc)
return rc;
- skb_copy_from_linear_data(skb, eth_hdr, ETH_HLEN);
skb_pull(skb, ETH_HLEN);
qeth_l3_fixup_headers(skb);
- rc = qeth_xmit(card, skb, queue, ipv, cast_type, qeth_l3_fill_header);
- if (rc == -EBUSY) {
- /* roll back to ETH header */
- skb_push(skb, ETH_HLEN);
- skb_copy_to_linear_data(skb, eth_hdr, ETH_HLEN);
- }
- return rc;
+ return qeth_xmit(card, skb, queue, ipv, cast_type, qeth_l3_fill_header);
}
static netdev_tx_t qeth_l3_hard_start_xmit(struct sk_buff *skb,
struct net_device *dev)
{
- int cast_type = qeth_l3_get_cast_type(skb);
struct qeth_card *card = dev->ml_priv;
+ u16 txq = skb_get_queue_mapping(skb);
int ipv = qeth_get_ip_version(skb);
struct qeth_qdio_out_q *queue;
int tx_bytes = skb->len;
- int rc;
-
- queue = qeth_get_tx_queue(card, skb, ipv, cast_type);
+ int cast_type, rc;
if (IS_IQD(card)) {
+ queue = card->qdio.out_qs[qeth_iqd_translate_txq(dev, txq)];
+
if (card->options.sniffer)
goto tx_drop;
if ((card->options.cq != QETH_CQ_ENABLED && !ipv) ||
(card->options.cq == QETH_CQ_ENABLED &&
skb->protocol != htons(ETH_P_AF_IUCV)))
goto tx_drop;
+
+ if (txq == QETH_IQD_MCAST_TXQ)
+ cast_type = qeth_l3_get_cast_type(skb);
+ else
+ cast_type = RTN_UNICAST;
+ } else {
+ queue = card->qdio.out_qs[txq];
+ cast_type = qeth_l3_get_cast_type(skb);
}
if (cast_type == RTN_BROADCAST && !card->info.broadcast_capable)
goto tx_drop;
- netif_stop_queue(dev);
-
if (ipv == 4 || IS_IQD(card))
rc = qeth_l3_xmit(card, skb, queue, ipv, cast_type);
else
if (!rc) {
QETH_TXQ_STAT_INC(queue, tx_packets);
QETH_TXQ_STAT_ADD(queue, tx_bytes, tx_bytes);
- netif_wake_queue(dev);
return NETDEV_TX_OK;
- } else if (rc == -EBUSY) {
- return NETDEV_TX_BUSY;
- } /* else fall through */
+ }
tx_drop:
QETH_TXQ_STAT_INC(queue, tx_dropped);
kfree_skb(skb);
- netif_wake_queue(dev);
return NETDEV_TX_OK;
}
return qeth_features_check(skb, dev, features);
}
+static u16 qeth_l3_iqd_select_queue(struct net_device *dev, struct sk_buff *skb,
+ struct net_device *sb_dev)
+{
+ return qeth_iqd_select_queue(dev, skb, qeth_l3_get_cast_type(skb),
+ sb_dev);
+}
+
+static u16 qeth_l3_osa_select_queue(struct net_device *dev, struct sk_buff *skb,
+ struct net_device *sb_dev)
+{
+ struct qeth_card *card = dev->ml_priv;
+
+ return qeth_get_priority_queue(card, skb);
+}
+
static const struct net_device_ops qeth_l3_netdev_ops = {
.ndo_open = qeth_open,
.ndo_stop = qeth_stop,
.ndo_get_stats64 = qeth_get_stats64,
.ndo_start_xmit = qeth_l3_hard_start_xmit,
+ .ndo_select_queue = qeth_l3_iqd_select_queue,
.ndo_validate_addr = eth_validate_addr,
.ndo_set_rx_mode = qeth_l3_set_rx_mode,
.ndo_do_ioctl = qeth_do_ioctl,
.ndo_get_stats64 = qeth_get_stats64,
.ndo_start_xmit = qeth_l3_hard_start_xmit,
.ndo_features_check = qeth_l3_osa_features_check,
+ .ndo_select_queue = qeth_l3_osa_select_queue,
.ndo_validate_addr = eth_validate_addr,
.ndo_set_rx_mode = qeth_l3_set_rx_mode,
.ndo_do_ioctl = qeth_do_ioctl,
add_timer(&erp_action->timer);
}
+void zfcp_erp_port_forced_reopen_all(struct zfcp_adapter *adapter,
+ int clear, char *dbftag)
+{
+ unsigned long flags;
+ struct zfcp_port *port;
+
+ write_lock_irqsave(&adapter->erp_lock, flags);
+ read_lock(&adapter->port_list_lock);
+ list_for_each_entry(port, &adapter->port_list, list)
+ _zfcp_erp_port_forced_reopen(port, clear, dbftag);
+ read_unlock(&adapter->port_list_lock);
+ write_unlock_irqrestore(&adapter->erp_lock, flags);
+}
+
static void _zfcp_erp_port_reopen_all(struct zfcp_adapter *adapter,
int clear, char *dbftag)
{
struct zfcp_scsi_dev *zsdev = sdev_to_zfcp(sdev);
int lun_status;
+ if (sdev->sdev_state == SDEV_DEL ||
+ sdev->sdev_state == SDEV_CANCEL)
+ continue;
if (zsdev->port != port)
continue;
/* LUN under port of interest */
char *dbftag);
extern void zfcp_erp_port_shutdown(struct zfcp_port *, int, char *);
extern void zfcp_erp_port_forced_reopen(struct zfcp_port *, int, char *);
+extern void zfcp_erp_port_forced_reopen_all(struct zfcp_adapter *adapter,
+ int clear, char *dbftag);
extern void zfcp_erp_set_lun_status(struct scsi_device *, u32);
extern void zfcp_erp_clear_lun_status(struct scsi_device *, u32);
extern void zfcp_erp_lun_reopen(struct scsi_device *, int, char *);
list_for_each_entry(port, &adapter->port_list, list) {
if ((port->d_id & range) == (ntoh24(page->rscn_fid) & range))
zfcp_fc_test_link(port);
- if (!port->d_id)
- zfcp_erp_port_reopen(port,
- ZFCP_STATUS_COMMON_ERP_FAILED,
- "fcrscn1");
}
read_unlock_irqrestore(&adapter->port_list_lock, flags);
}
static void zfcp_fc_incoming_rscn(struct zfcp_fsf_req *fsf_req)
{
struct fsf_status_read_buffer *status_buffer = (void *)fsf_req->data;
+ struct zfcp_adapter *adapter = fsf_req->adapter;
struct fc_els_rscn *head;
struct fc_els_rscn_page *page;
u16 i;
no_entries = be16_to_cpu(head->rscn_plen) /
sizeof(struct fc_els_rscn_page);
+ if (no_entries > 1) {
+ /* handle failed ports */
+ unsigned long flags;
+ struct zfcp_port *port;
+
+ read_lock_irqsave(&adapter->port_list_lock, flags);
+ list_for_each_entry(port, &adapter->port_list, list) {
+ if (port->d_id)
+ continue;
+ zfcp_erp_port_reopen(port,
+ ZFCP_STATUS_COMMON_ERP_FAILED,
+ "fcrscn1");
+ }
+ read_unlock_irqrestore(&adapter->port_list_lock, flags);
+ }
+
for (i = 1; i < no_entries; i++) {
/* skip head and start with 1st element */
page++;
struct zfcp_adapter *adapter = zfcp_sdev->port->adapter;
int ret = SUCCESS, fc_ret;
+ if (!(adapter->connection_features & FSF_FEATURE_NPIV_MODE)) {
+ zfcp_erp_port_forced_reopen_all(adapter, 0, "schrh_p");
+ zfcp_erp_wait(adapter);
+ }
zfcp_erp_adapter_reopen(adapter, 0, "schrh_1");
zfcp_erp_wait(adapter);
fc_ret = fc_block_scsi_eh(scpnt);
return capacity;
}
+static inline int aac_pci_offline(struct aac_dev *dev)
+{
+ return pci_channel_offline(dev->pdev) || dev->handle_pci_error;
+}
+
static inline int aac_adapter_check_health(struct aac_dev *dev)
{
- if (unlikely(pci_channel_offline(dev->pdev)))
+ if (unlikely(aac_pci_offline(dev)))
return -1;
return (dev)->a_ops.adapter_check_health(dev);
return -ETIMEDOUT;
}
- if (unlikely(pci_channel_offline(dev->pdev)))
+ if (unlikely(aac_pci_offline(dev)))
return -EFAULT;
if ((blink = aac_adapter_check_health(dev)) > 0) {
spin_unlock_irqrestore(&fibptr->event_lock, flags);
- if (unlikely(pci_channel_offline(dev->pdev)))
+ if (unlikely(aac_pci_offline(dev)))
return -EFAULT;
fibptr->flags |= FIB_CONTEXT_FLAG_WAIT;
}
out:
- if (req->nsge > 0)
+ if (req->nsge > 0) {
scsi_dma_unmap(cmnd);
+ if (req->dcopy && (host_status == DID_OK))
+ host_status = csio_scsi_copy_to_sgl(hw, req);
+ }
cmnd->result = (((host_status) << 16) | scsi_status);
cmnd->scsi_done(cmnd);
{ IBMVFC_FC_FAILURE, IBMVFC_VENDOR_SPECIFIC, DID_ERROR, 1, 1, "vendor specific" },
{ IBMVFC_FC_SCSI_ERROR, 0, DID_OK, 1, 0, "SCSI error" },
+ { IBMVFC_FC_SCSI_ERROR, IBMVFC_COMMAND_FAILED, DID_ERROR, 0, 1, "PRLI to device failed." },
};
static void ibmvfc_npiv_login(struct ibmvfc_host *);
if (rsp->flags & FCP_RSP_LEN_VALID)
rsp_code = rsp->data.info.rsp_code;
- scmd_printk(KERN_ERR, cmnd, "Command (%02X) failed: %s (%x:%x) "
+ scmd_printk(KERN_ERR, cmnd, "Command (%02X) : %s (%x:%x) "
"flags: %x fcp_rsp: %x, resid=%d, scsi_status: %x\n",
- cmnd->cmnd[0], err, vfc_cmd->status, vfc_cmd->error,
+ cmnd->cmnd[0], err, be16_to_cpu(vfc_cmd->status), be16_to_cpu(vfc_cmd->error),
rsp->flags, rsp_code, scsi_get_resid(cmnd), rsp->scsi_status);
}
sdev_printk(KERN_ERR, sdev, "%s reset failed: %s (%x:%x) "
"flags: %x fcp_rsp: %x, scsi_status: %x\n", desc,
ibmvfc_get_cmd_error(be16_to_cpu(rsp_iu.cmd.status), be16_to_cpu(rsp_iu.cmd.error)),
- rsp_iu.cmd.status, rsp_iu.cmd.error, fc_rsp->flags, rsp_code,
+ be16_to_cpu(rsp_iu.cmd.status), be16_to_cpu(rsp_iu.cmd.error), fc_rsp->flags, rsp_code,
fc_rsp->scsi_status);
rsp_rc = -EIO;
} else
sdev_printk(KERN_ERR, sdev, "Abort failed: %s (%x:%x) "
"flags: %x fcp_rsp: %x, scsi_status: %x\n",
ibmvfc_get_cmd_error(be16_to_cpu(rsp_iu.cmd.status), be16_to_cpu(rsp_iu.cmd.error)),
- rsp_iu.cmd.status, rsp_iu.cmd.error, fc_rsp->flags, rsp_code,
+ be16_to_cpu(rsp_iu.cmd.status), be16_to_cpu(rsp_iu.cmd.error), fc_rsp->flags, rsp_code,
fc_rsp->scsi_status);
rsp_rc = -EIO;
} else
ibmvfc_set_host_action(vhost, IBMVFC_HOST_ACTION_NONE);
if (crq->format == IBMVFC_PARTITION_MIGRATED) {
/* We need to re-setup the interpartition connection */
- dev_info(vhost->dev, "Re-enabling adapter\n");
+ dev_info(vhost->dev, "Partition migrated, Re-enabling adapter\n");
vhost->client_migrated = 1;
ibmvfc_purge_requests(vhost, DID_REQUEUE);
ibmvfc_link_down(vhost, IBMVFC_LINK_DOWN);
ibmvfc_set_host_action(vhost, IBMVFC_HOST_ACTION_REENABLE);
- } else {
- dev_err(vhost->dev, "Virtual adapter failed (rc=%d)\n", crq->format);
+ } else if (crq->format == IBMVFC_PARTNER_FAILED || crq->format == IBMVFC_PARTNER_DEREGISTER) {
+ dev_err(vhost->dev, "Host partner adapter deregistered or failed (rc=%d)\n", crq->format);
ibmvfc_purge_requests(vhost, DID_ERROR);
ibmvfc_link_down(vhost, IBMVFC_LINK_DOWN);
ibmvfc_set_host_action(vhost, IBMVFC_HOST_ACTION_RESET);
+ } else {
+ dev_err(vhost->dev, "Received unknown transport event from partner (rc=%d)\n", crq->format);
}
return;
case IBMVFC_CRQ_CMD_RSP:
tgt_log(tgt, level, "Process Login failed: %s (%x:%x) rc=0x%02X\n",
ibmvfc_get_cmd_error(be16_to_cpu(rsp->status), be16_to_cpu(rsp->error)),
- rsp->status, rsp->error, status);
+ be16_to_cpu(rsp->status), be16_to_cpu(rsp->error), status);
break;
}
ibmvfc_set_tgt_action(tgt, IBMVFC_TGT_ACTION_DEL_RPORT);
tgt_log(tgt, level, "Port Login failed: %s (%x:%x) %s (%x) %s (%x) rc=0x%02X\n",
- ibmvfc_get_cmd_error(be16_to_cpu(rsp->status), be16_to_cpu(rsp->error)), rsp->status, rsp->error,
- ibmvfc_get_fc_type(be16_to_cpu(rsp->fc_type)), rsp->fc_type,
- ibmvfc_get_ls_explain(be16_to_cpu(rsp->fc_explain)), rsp->fc_explain, status);
+ ibmvfc_get_cmd_error(be16_to_cpu(rsp->status), be16_to_cpu(rsp->error)),
+ be16_to_cpu(rsp->status), be16_to_cpu(rsp->error),
+ ibmvfc_get_fc_type(be16_to_cpu(rsp->fc_type)), be16_to_cpu(rsp->fc_type),
+ ibmvfc_get_ls_explain(be16_to_cpu(rsp->fc_explain)), be16_to_cpu(rsp->fc_explain), status);
break;
}
fc_explain = (be32_to_cpu(mad->fc_iu.response[1]) & 0x0000ff00) >> 8;
tgt_info(tgt, "ADISC failed: %s (%x:%x) %s (%x) %s (%x) rc=0x%02X\n",
ibmvfc_get_cmd_error(be16_to_cpu(mad->iu.status), be16_to_cpu(mad->iu.error)),
- mad->iu.status, mad->iu.error,
+ be16_to_cpu(mad->iu.status), be16_to_cpu(mad->iu.error),
ibmvfc_get_fc_type(fc_reason), fc_reason,
ibmvfc_get_ls_explain(fc_explain), fc_explain, status);
break;
tgt_log(tgt, level, "Query Target failed: %s (%x:%x) %s (%x) %s (%x) rc=0x%02X\n",
ibmvfc_get_cmd_error(be16_to_cpu(rsp->status), be16_to_cpu(rsp->error)),
- rsp->status, rsp->error, ibmvfc_get_fc_type(be16_to_cpu(rsp->fc_type)),
- rsp->fc_type, ibmvfc_get_gs_explain(be16_to_cpu(rsp->fc_explain)),
- rsp->fc_explain, status);
+ be16_to_cpu(rsp->status), be16_to_cpu(rsp->error),
+ ibmvfc_get_fc_type(be16_to_cpu(rsp->fc_type)), be16_to_cpu(rsp->fc_type),
+ ibmvfc_get_gs_explain(be16_to_cpu(rsp->fc_explain)), be16_to_cpu(rsp->fc_explain),
+ status);
break;
}
level += ibmvfc_retry_host_init(vhost);
ibmvfc_log(vhost, level, "Discover Targets failed: %s (%x:%x)\n",
ibmvfc_get_cmd_error(be16_to_cpu(rsp->status), be16_to_cpu(rsp->error)),
- rsp->status, rsp->error);
+ be16_to_cpu(rsp->status), be16_to_cpu(rsp->error));
break;
case IBMVFC_MAD_DRIVER_FAILED:
break;
ibmvfc_link_down(vhost, IBMVFC_LINK_DEAD);
ibmvfc_log(vhost, level, "NPIV Login failed: %s (%x:%x)\n",
ibmvfc_get_cmd_error(be16_to_cpu(rsp->status), be16_to_cpu(rsp->error)),
- rsp->status, rsp->error);
+ be16_to_cpu(rsp->status), be16_to_cpu(rsp->error));
ibmvfc_free_event(evt);
return;
case IBMVFC_MAD_CRQ_ERROR:
IBMVFC_CRQ_XPORT_EVENT = 0xFF,
};
-enum ibmvfc_crq_format {
+enum ibmvfc_crq_init_msg {
IBMVFC_CRQ_INIT = 0x01,
IBMVFC_CRQ_INIT_COMPLETE = 0x02,
+};
+
+enum ibmvfc_crq_xport_evts {
+ IBMVFC_PARTNER_FAILED = 0x01,
+ IBMVFC_PARTNER_DEREGISTER = 0x02,
IBMVFC_PARTITION_MIGRATED = 0x06,
};
* wake up the thread.
*/
spin_lock(&lpfc_cmd->buf_lock);
- if (unlikely(lpfc_cmd->cur_iocbq.iocb_flag & LPFC_DRIVER_ABORTED)) {
- lpfc_cmd->cur_iocbq.iocb_flag &= ~LPFC_DRIVER_ABORTED;
- if (lpfc_cmd->waitq)
- wake_up(lpfc_cmd->waitq);
+ lpfc_cmd->cur_iocbq.iocb_flag &= ~LPFC_DRIVER_ABORTED;
+ if (lpfc_cmd->waitq) {
+ wake_up(lpfc_cmd->waitq);
lpfc_cmd->waitq = NULL;
}
spin_unlock(&lpfc_cmd->buf_lock);
if (smid < ioc->hi_priority_smid) {
struct scsiio_tracker *st;
+ void *request;
st = _get_st_from_smid(ioc, smid);
if (!st) {
_base_recovery_check(ioc);
return;
}
+
+ /* Clear MPI request frame */
+ request = mpt3sas_base_get_msg_frame(ioc, smid);
+ memset(request, 0, ioc->request_sz);
+
mpt3sas_base_clear_st(ioc, st);
_base_recovery_check(ioc);
return;
{
struct scsi_cmnd *scmd = NULL;
struct scsiio_tracker *st;
+ Mpi25SCSIIORequest_t *mpi_request;
if (smid > 0 &&
smid <= ioc->scsiio_depth - INTERNAL_SCSIIO_CMDS_COUNT) {
u32 unique_tag = smid - 1;
+ mpi_request = mpt3sas_base_get_msg_frame(ioc, smid);
+
+ /*
+ * If SCSI IO request is outstanding at driver level then
+ * DevHandle filed must be non-zero. If DevHandle is zero
+ * then it means that this smid is free at driver level,
+ * so return NULL.
+ */
+ if (!mpi_request->DevHandle)
+ return scmd;
+
scmd = scsi_host_find_tag(ioc->shost, unique_tag);
if (scmd) {
st = scsi_cmd_priv(scmd);
static int qedi_alloc_nvm_iscsi_cfg(struct qedi_ctx *qedi)
{
- struct qedi_nvm_iscsi_image nvm_image;
-
qedi->iscsi_image = dma_alloc_coherent(&qedi->pdev->dev,
- sizeof(nvm_image),
+ sizeof(struct qedi_nvm_iscsi_image),
&qedi->nvm_buf_dma, GFP_KERNEL);
if (!qedi->iscsi_image) {
QEDI_ERR(&qedi->dbg_ctx, "Could not allocate NVM BUF.\n");
static int qedi_get_boot_info(struct qedi_ctx *qedi)
{
int ret = 1;
- struct qedi_nvm_iscsi_image nvm_image;
QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO,
"Get NVM iSCSI CFG image\n");
ret = qedi_ops->common->nvm_get_image(qedi->cdev,
QED_NVM_IMAGE_ISCSI_CFG,
(char *)qedi->iscsi_image,
- sizeof(nvm_image));
+ sizeof(struct qedi_nvm_iscsi_image));
if (ret)
QEDI_ERR(&qedi->dbg_ctx,
"Could not get NVM image. ret = %d\n", ret);
if (iscsi_conn_bind(cls_session, cls_conn, is_leading))
return -EINVAL;
ep = iscsi_lookup_endpoint(transport_fd);
+ if (!ep)
+ return -EINVAL;
conn = cls_conn->dd_data;
qla_conn = conn->dd_data;
qla_conn->qla_ep = ep->dd_data;
{"NETAPP", "Universal Xport", "*", BLIST_NO_ULD_ATTACH},
{"LSI", "Universal Xport", "*", BLIST_NO_ULD_ATTACH},
{"ENGENIO", "Universal Xport", "*", BLIST_NO_ULD_ATTACH},
+ {"LENOVO", "Universal Xport", "*", BLIST_NO_ULD_ATTACH},
{"SMSC", "USB 2 HS-CF", NULL, BLIST_SPARSELUN | BLIST_INQUIRY_36},
{"SONY", "CD-ROM CDU-8001", NULL, BLIST_BORKEN},
{"SONY", "TSL", NULL, BLIST_FORCELUN}, /* DDS3 & DDS4 autoloaders */
{"NETAPP", "INF-01-00", "rdac", },
{"LSI", "INF-01-00", "rdac", },
{"ENGENIO", "INF-01-00", "rdac", },
+ {"LENOVO", "DE_Series", "rdac", },
{NULL, NULL, NULL },
};
mutex_lock(&sdev->state_mutex);
ret = scsi_device_set_state(sdev, state);
+ /*
+ * If the device state changes to SDEV_RUNNING, we need to run
+ * the queue to avoid I/O hang.
+ */
+ if (ret == 0 && state == SDEV_RUNNING)
+ blk_mq_run_hw_queues(sdev->request_queue, true);
mutex_unlock(&sdev->state_mutex);
return ret == 0 ? count : -EINVAL;
scsi_set_medium_removal(sdev, SCSI_REMOVAL_ALLOW);
}
- /*
- * XXX and what if there are packets in flight and this close()
- * XXX is followed by a "rmmod sd_mod"?
- */
-
scsi_disk_put(sdkp);
}
unsigned int opt_xfer_bytes =
logical_to_bytes(sdp, sdkp->opt_xfer_blocks);
+ if (sdkp->opt_xfer_blocks == 0)
+ return false;
+
if (sdkp->opt_xfer_blocks > dev_max) {
sd_first_printk(KERN_WARNING, sdkp,
"Optimal transfer size %u logical blocks " \
{
struct scsi_disk *sdkp = to_scsi_disk(dev);
struct gendisk *disk = sdkp->disk;
-
+ struct request_queue *q = disk->queue;
+
ida_free(&sd_index_ida, sdkp->index);
+ /*
+ * Wait until all requests that are in progress have completed.
+ * This is necessary to avoid that e.g. scsi_end_request() crashes
+ * due to clearing the disk->private_data pointer. Wait from inside
+ * scsi_disk_release() instead of from sd_release() to avoid that
+ * freezing and unfreezing the request queue affects user space I/O
+ * in case multiple processes open a /dev/sd... node concurrently.
+ */
+ blk_mq_freeze_queue(q);
+ blk_mq_unfreeze_queue(q);
+
disk->private_data = NULL;
put_disk(disk);
put_device(&sdkp->device->sdev_gendev);
* This is the end of Protocol specific defines.
*/
-static int storvsc_ringbuffer_size = (256 * PAGE_SIZE);
+static int storvsc_ringbuffer_size = (128 * 1024);
static u32 max_outstanding_req_per_channel;
static int storvsc_vcpus_per_sub_channel = 4;
{
struct device *dev = &device->device;
struct storvsc_device *stor_device;
- int num_cpus = num_online_cpus();
int num_sc;
struct storvsc_cmd_request *request;
struct vstor_packet *vstor_packet;
int ret, t;
- num_sc = ((max_chns > num_cpus) ? num_cpus : max_chns);
+ /*
+ * If the number of CPUs is artificially restricted, such as
+ * with maxcpus=1 on the kernel boot line, Hyper-V could offer
+ * sub-channels >= the number of CPUs. These sub-channels
+ * should not be created. The primary channel is already created
+ * and assigned to one CPU, so check against # CPUs - 1.
+ */
+ num_sc = min((int)(num_online_cpus() - 1), max_chns);
+ if (!num_sc)
+ return;
+
stor_device = get_out_stor_device(device);
if (!stor_device)
return;
/* We need to know how many queues before we allocate. */
num_queues = virtscsi_config_get(vdev, num_queues) ? : 1;
+ num_queues = min_t(unsigned int, nr_cpu_ids, num_queues);
num_targets = virtscsi_config_get(vdev, max_target) + 1;
static int bcm2835_asb_enable(struct bcm2835_power *power, u32 reg)
{
- u64 start = ktime_get_ns();
+ u64 start;
+
+ if (!reg)
+ return 0;
+
+ start = ktime_get_ns();
/* Enable the module's async AXI bridges. */
ASB_WRITE(reg, ASB_READ(reg) & ~ASB_REQ_STOP);
static int bcm2835_asb_disable(struct bcm2835_power *power, u32 reg)
{
- u64 start = ktime_get_ns();
+ u64 start;
+
+ if (!reg)
+ return 0;
+
+ start = ktime_get_ns();
/* Enable the module's async AXI bridges. */
ASB_WRITE(reg, ASB_READ(reg) | ASB_REQ_STOP);
}
}
-static void
+static int
bcm2835_init_power_domain(struct bcm2835_power *power,
int pd_xlate_index, const char *name)
{
struct bcm2835_power_domain *dom = &power->domains[pd_xlate_index];
dom->clk = devm_clk_get(dev->parent, name);
+ if (IS_ERR(dom->clk)) {
+ int ret = PTR_ERR(dom->clk);
+
+ if (ret == -EPROBE_DEFER)
+ return ret;
+
+ /* Some domains don't have a clk, so make sure that we
+ * don't deref an error pointer later.
+ */
+ dom->clk = NULL;
+ }
dom->base.name = name;
dom->base.power_on = bcm2835_power_pd_power_on;
pm_genpd_init(&dom->base, NULL, true);
power->pd_xlate.domains[pd_xlate_index] = &dom->base;
+
+ return 0;
}
/** bcm2835_reset_reset - Resets a block that has a reset line in the
{ BCM2835_POWER_DOMAIN_IMAGE_PERI, BCM2835_POWER_DOMAIN_CAM0 },
{ BCM2835_POWER_DOMAIN_IMAGE_PERI, BCM2835_POWER_DOMAIN_CAM1 },
};
- int ret, i;
+ int ret = 0, i;
u32 id;
power = devm_kzalloc(dev, sizeof(*power), GFP_KERNEL);
power->pd_xlate.num_domains = ARRAY_SIZE(power_domain_names);
- for (i = 0; i < ARRAY_SIZE(power_domain_names); i++)
- bcm2835_init_power_domain(power, i, power_domain_names[i]);
+ for (i = 0; i < ARRAY_SIZE(power_domain_names); i++) {
+ ret = bcm2835_init_power_domain(power, i, power_domain_names[i]);
+ if (ret)
+ goto fail;
+ }
for (i = 0; i < ARRAY_SIZE(domain_deps); i++) {
pm_genpd_add_subdomain(&power->domains[domain_deps[i].parent].base,
ret = devm_reset_controller_register(dev, &power->reset);
if (ret)
- return ret;
+ goto fail;
of_genpd_add_provider_onecell(dev->parent->of_node, &power->pd_xlate);
dev_info(dev, "Broadcom BCM2835 power domains driver");
return 0;
+
+fail:
+ for (i = 0; i < ARRAY_SIZE(power_domain_names); i++) {
+ struct generic_pm_domain *dom = &power->domains[i].base;
+
+ if (dom->name)
+ pm_genpd_remove(dom);
+ }
+ return ret;
}
static int bcm2835_power_remove(struct platform_device *pdev)
source "drivers/staging/mt7621-mmc/Kconfig"
-source "drivers/staging/mt7621-eth/Kconfig"
-
source "drivers/staging/mt7621-dts/Kconfig"
source "drivers/staging/gasket/Kconfig"
obj-$(CONFIG_SOC_MT7621) += mt7621-dma/
obj-$(CONFIG_DMA_RALINK) += ralink-gdma/
obj-$(CONFIG_MTK_MMC) += mt7621-mmc/
-obj-$(CONFIG_NET_MEDIATEK_SOC_STAGING) += mt7621-eth/
obj-$(CONFIG_SOC_MT7621) += mt7621-dts/
obj-$(CONFIG_STAGING_GASKET_FRAMEWORK) += gasket/
obj-$(CONFIG_XIL_AXIS_FIFO) += axis-fifo/
#
config XIL_AXIS_FIFO
tristate "Xilinx AXI-Stream FIFO IP core driver"
+ depends on OF
default n
help
This adds support for the Xilinx AXI-Stream
unsigned int mask);
unsigned int comedi_dio_update_state(struct comedi_subdevice *s,
unsigned int *data);
+unsigned int comedi_bytes_per_scan_cmd(struct comedi_subdevice *s,
+ struct comedi_cmd *cmd);
unsigned int comedi_bytes_per_scan(struct comedi_subdevice *s);
unsigned int comedi_nscans_left(struct comedi_subdevice *s,
unsigned int nscans);
EXPORT_SYMBOL_GPL(comedi_dio_update_state);
/**
- * comedi_bytes_per_scan() - Get length of asynchronous command "scan" in bytes
+ * comedi_bytes_per_scan_cmd() - Get length of asynchronous command "scan" in
+ * bytes
* @s: COMEDI subdevice.
+ * @cmd: COMEDI command.
*
* Determines the overall scan length according to the subdevice type and the
- * number of channels in the scan.
+ * number of channels in the scan for the specified command.
*
* For digital input, output or input/output subdevices, samples for
* multiple channels are assumed to be packed into one or more unsigned
*
* Returns the overall scan length in bytes.
*/
-unsigned int comedi_bytes_per_scan(struct comedi_subdevice *s)
+unsigned int comedi_bytes_per_scan_cmd(struct comedi_subdevice *s,
+ struct comedi_cmd *cmd)
{
- struct comedi_cmd *cmd = &s->async->cmd;
unsigned int num_samples;
unsigned int bits_per_sample;
}
return comedi_samples_to_bytes(s, num_samples);
}
+EXPORT_SYMBOL_GPL(comedi_bytes_per_scan_cmd);
+
+/**
+ * comedi_bytes_per_scan() - Get length of asynchronous command "scan" in bytes
+ * @s: COMEDI subdevice.
+ *
+ * Determines the overall scan length according to the subdevice type and the
+ * number of channels in the scan for the current command.
+ *
+ * For digital input, output or input/output subdevices, samples for
+ * multiple channels are assumed to be packed into one or more unsigned
+ * short or unsigned int values according to the subdevice's %SDF_LSAMPL
+ * flag. For other types of subdevice, samples are assumed to occupy a
+ * whole unsigned short or unsigned int according to the %SDF_LSAMPL flag.
+ *
+ * Returns the overall scan length in bytes.
+ */
+unsigned int comedi_bytes_per_scan(struct comedi_subdevice *s)
+{
+ struct comedi_cmd *cmd = &s->async->cmd;
+
+ return comedi_bytes_per_scan_cmd(s, cmd);
+}
EXPORT_SYMBOL_GPL(comedi_bytes_per_scan);
static unsigned int __comedi_nscans_left(struct comedi_subdevice *s,
struct comedi_subdevice *s, struct comedi_cmd *cmd)
{
struct ni_private *devpriv = dev->private;
+ unsigned int bytes_per_scan;
int err = 0;
/* Step 1 : check if triggers are trivially valid */
err |= comedi_check_trigger_arg_is(&cmd->convert_arg, 0);
err |= comedi_check_trigger_arg_is(&cmd->scan_end_arg,
cmd->chanlist_len);
- err |= comedi_check_trigger_arg_max(&cmd->stop_arg,
- s->async->prealloc_bufsz /
- comedi_bytes_per_scan(s));
+ bytes_per_scan = comedi_bytes_per_scan_cmd(s, cmd);
+ if (bytes_per_scan) {
+ err |= comedi_check_trigger_arg_max(&cmd->stop_arg,
+ s->async->prealloc_bufsz /
+ bytes_per_scan);
+ }
if (err)
return 3;
[EROFS_FT_SYMLINK] = DT_LNK,
};
+static void debug_one_dentry(unsigned char d_type, const char *de_name,
+ unsigned int de_namelen)
+{
+#ifdef CONFIG_EROFS_FS_DEBUG
+ /* since the on-disk name could not have the trailing '\0' */
+ unsigned char dbg_namebuf[EROFS_NAME_LEN + 1];
+
+ memcpy(dbg_namebuf, de_name, de_namelen);
+ dbg_namebuf[de_namelen] = '\0';
+
+ debugln("found dirent %s de_len %u d_type %d", dbg_namebuf,
+ de_namelen, d_type);
+#endif
+}
+
static int erofs_fill_dentries(struct dir_context *ctx,
void *dentry_blk, unsigned int *ofs,
unsigned int nameoff, unsigned int maxsize)
de = dentry_blk + *ofs;
while (de < end) {
const char *de_name;
- int de_namelen;
+ unsigned int de_namelen;
unsigned char d_type;
-#ifdef CONFIG_EROFS_FS_DEBUG
- unsigned int dbg_namelen;
- unsigned char dbg_namebuf[EROFS_NAME_LEN];
-#endif
- if (unlikely(de->file_type < EROFS_FT_MAX))
+ if (de->file_type < EROFS_FT_MAX)
d_type = erofs_filetype_table[de->file_type];
else
d_type = DT_UNKNOWN;
nameoff = le16_to_cpu(de->nameoff);
de_name = (char *)dentry_blk + nameoff;
- de_namelen = unlikely(de + 1 >= end) ?
- /* last directory entry */
- strnlen(de_name, maxsize - nameoff) :
- le16_to_cpu(de[1].nameoff) - nameoff;
+ /* the last dirent in the block? */
+ if (de + 1 >= end)
+ de_namelen = strnlen(de_name, maxsize - nameoff);
+ else
+ de_namelen = le16_to_cpu(de[1].nameoff) - nameoff;
/* a corrupted entry is found */
- if (unlikely(de_namelen < 0)) {
+ if (unlikely(nameoff + de_namelen > maxsize ||
+ de_namelen > EROFS_NAME_LEN)) {
DBG_BUGON(1);
return -EIO;
}
-#ifdef CONFIG_EROFS_FS_DEBUG
- dbg_namelen = min(EROFS_NAME_LEN - 1, de_namelen);
- memcpy(dbg_namebuf, de_name, dbg_namelen);
- dbg_namebuf[dbg_namelen] = '\0';
-
- debugln("%s, found de_name %s de_len %d d_type %d", __func__,
- dbg_namebuf, de_namelen, d_type);
-#endif
-
+ debug_one_dentry(d_type, de_name, de_namelen);
if (!dir_emit(ctx, de_name, de_namelen,
le64_to_cpu(de->nid), d_type))
/* stopped by some reason */
overlapped = false;
compressed_pages = grp->compressed_pages;
+ err = 0;
for (i = 0; i < clusterpages; ++i) {
unsigned int pagenr;
DBG_BUGON(!page);
DBG_BUGON(!page->mapping);
- if (z_erofs_is_stagingpage(page))
- continue;
+ if (!z_erofs_is_stagingpage(page)) {
#ifdef EROFS_FS_HAS_MANAGED_CACHE
- if (page->mapping == MNGD_MAPPING(sbi)) {
- DBG_BUGON(!PageUptodate(page));
- continue;
- }
+ if (page->mapping == MNGD_MAPPING(sbi)) {
+ if (unlikely(!PageUptodate(page)))
+ err = -EIO;
+ continue;
+ }
#endif
- /* only non-head page could be reused as a compressed page */
- pagenr = z_erofs_onlinepage_index(page);
+ /*
+ * only if non-head page can be selected
+ * for inplace decompression
+ */
+ pagenr = z_erofs_onlinepage_index(page);
- DBG_BUGON(pagenr >= nr_pages);
- DBG_BUGON(pages[pagenr]);
- ++sparsemem_pages;
- pages[pagenr] = page;
+ DBG_BUGON(pagenr >= nr_pages);
+ DBG_BUGON(pages[pagenr]);
+ ++sparsemem_pages;
+ pages[pagenr] = page;
- overlapped = true;
+ overlapped = true;
+ }
+
+ /* PG_error needs checking for inplaced and staging pages */
+ if (unlikely(PageError(page))) {
+ DBG_BUGON(PageUptodate(page));
+ err = -EIO;
+ }
}
+ if (unlikely(err))
+ goto out;
+
llen = (nr_pages << PAGE_SHIFT) - work->pageofs;
if (z_erofs_vle_workgrp_fmt(grp) == Z_EROFS_VLE_WORKGRP_FMT_PLAIN) {
skip_allocpage:
vout = erofs_vmap(pages, nr_pages);
+ if (!vout) {
+ err = -ENOMEM;
+ goto out;
+ }
err = z_erofs_vle_unzip_vmap(compressed_pages,
clusterpages, vout, llen, work->pageofs, overlapped);
if (page->mapping == mc) {
WRITE_ONCE(grp->compressed_pages[nr], page);
+ ClearPageError(page);
if (!PagePrivate(page)) {
/*
* impossible to be !PagePrivate(page) for
nr_pages = DIV_ROUND_UP(outlen + pageofs, PAGE_SIZE);
- if (clusterpages == 1)
+ if (clusterpages == 1) {
vin = kmap_atomic(compressed_pages[0]);
- else
+ } else {
vin = erofs_vmap(compressed_pages, clusterpages);
+ if (!vin)
+ return -ENOMEM;
+ }
preempt_disable();
vout = erofs_pcpubuf[smp_processor_id()].data;
status = "okay";
};
-ðernet {
- //mtd-mac-address = <&factory 0xe000>;
- gmac1: mac@0 {
- compatible = "mediatek,eth-mac";
- reg = <0>;
- phy-handle = <&phy1>;
- };
-
- mdio-bus {
- phy1: ethernet-phy@1 {
- reg = <1>;
- phy-mode = "rgmii";
- };
- };
-};
-
&pinctrl {
state_default: pinctrl0 {
gpio {
};
};
};
+
+&switch0 {
+ ports {
+ port@0 {
+ label = "ethblack";
+ status = "ok";
+ };
+ port@4 {
+ label = "ethblue";
+ status = "ok";
+ };
+ };
+};
mediatek,ethsys = <ðsys>;
- mediatek,switch = <&gsw>;
+ gmac0: mac@0 {
+ compatible = "mediatek,eth-mac";
+ reg = <0>;
+ phy-mode = "rgmii";
+ fixed-link {
+ speed = <1000>;
+ full-duplex;
+ pause;
+ };
+ };
+ gmac1: mac@1 {
+ compatible = "mediatek,eth-mac";
+ reg = <1>;
+ status = "off";
+ phy-mode = "rgmii";
+ phy-handle = <&phy5>;
+ };
mdio-bus {
#address-cells = <1>;
#size-cells = <0>;
- phy1f: ethernet-phy@1f {
- reg = <0x1f>;
+ phy5: ethernet-phy@5 {
+ reg = <5>;
phy-mode = "rgmii";
};
+
+ switch0: switch0@0 {
+ compatible = "mediatek,mt7621";
+ #address-cells = <1>;
+ #size-cells = <0>;
+ reg = <0>;
+ mediatek,mcm;
+ resets = <&rstctrl 2>;
+ reset-names = "mcm";
+
+ ports {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ reg = <0>;
+ port@0 {
+ status = "off";
+ reg = <0>;
+ label = "lan0";
+ };
+ port@1 {
+ status = "off";
+ reg = <1>;
+ label = "lan1";
+ };
+ port@2 {
+ status = "off";
+ reg = <2>;
+ label = "lan2";
+ };
+ port@3 {
+ status = "off";
+ reg = <3>;
+ label = "lan3";
+ };
+ port@4 {
+ status = "off";
+ reg = <4>;
+ label = "lan4";
+ };
+ port@6 {
+ reg = <6>;
+ label = "cpu";
+ ethernet = <&gmac0>;
+ phy-mode = "trgmii";
+ fixed-link {
+ speed = <1000>;
+ full-duplex;
+ };
+ };
+ };
+ };
};
};
+++ /dev/null
-Mediatek Gigabit Switch
-=======================
-
-The mediatek gigabit switch can be found on Mediatek SoCs.
-
-Required properties:
-- compatible: Should be "mediatek,mt7620-gsw", "mediatek,mt7621-gsw",
- "mediatek,mt7623-gsw"
-- reg: Address and length of the register set for the device
-- interrupts: Should contain the gigabit switches interrupt
-
-
-Additional required properties for ARM based SoCs:
-- mediatek,reset-pin: phandle describing the reset GPIO
-- clocks: the clocks used by the switch
-- clock-names: the names of the clocks listed in the clocks property
- these should be "trgpll", "esw", "gp2", "gp1"
-- mt7530-supply: the phandle of the regulator used to power the switch
-- mediatek,pctl-regmap: phandle to the port control regmap. this is used to
- setup the drive current
-
-
-Optional properties:
-- interrupt-parent: Should be the phandle for the interrupt controller
- that services interrupts for this device
-
-Example:
-
-gsw: switch@1b100000 {
- compatible = "mediatek,mt7623-gsw";
- reg = <0 0x1b110000 0 0x300000>;
-
- interrupt-parent = <&pio>;
- interrupts = <168 IRQ_TYPE_EDGE_RISING>;
-
- clocks = <&apmixedsys CLK_APMIXED_TRGPLL>,
- <ðsys CLK_ETHSYS_ESW>,
- <ðsys CLK_ETHSYS_GP2>,
- <ðsys CLK_ETHSYS_GP1>;
- clock-names = "trgpll", "esw", "gp2", "gp1";
-
- mt7530-supply = <&mt6323_vpa_reg>;
-
- mediatek,pctl-regmap = <&syscfg_pctl_a>;
- mediatek,reset-pin = <&pio 15 0>;
-
- status = "okay";
-};
+++ /dev/null
-config NET_VENDOR_MEDIATEK_STAGING
- bool "MediaTek ethernet driver - staging version"
- depends on RALINK
- ---help---
- If you have an MT7621 Mediatek SoC with ethernet, say Y.
-
-if NET_VENDOR_MEDIATEK_STAGING
-choice
- prompt "MAC type"
-
-config NET_MEDIATEK_MT7621
- bool "MT7621"
- depends on MIPS && SOC_MT7621
-
-endchoice
-
-config NET_MEDIATEK_SOC_STAGING
- tristate "MediaTek SoC Gigabit Ethernet support"
- depends on NET_VENDOR_MEDIATEK_STAGING
- select PHYLIB
- ---help---
- This driver supports the gigabit ethernet MACs in the
- MediaTek SoC family.
-
-config NET_MEDIATEK_MDIO
- def_bool NET_MEDIATEK_SOC_STAGING
- depends on NET_MEDIATEK_MT7621
- select PHYLIB
-
-config NET_MEDIATEK_MDIO_MT7620
- def_bool NET_MEDIATEK_SOC_STAGING
- depends on NET_MEDIATEK_MT7621
- select NET_MEDIATEK_MDIO
-
-config NET_MEDIATEK_GSW_MT7621
- def_tristate NET_MEDIATEK_SOC_STAGING
- depends on NET_MEDIATEK_MT7621
-
-endif #NET_VENDOR_MEDIATEK_STAGING
+++ /dev/null
-#
-# Makefile for the Ralink SoCs built-in ethernet macs
-#
-
-mtk-eth-soc-y += mtk_eth_soc.o ethtool.o
-
-mtk-eth-soc-$(CONFIG_NET_MEDIATEK_MDIO) += mdio.o
-mtk-eth-soc-$(CONFIG_NET_MEDIATEK_MDIO_MT7620) += mdio_mt7620.o
-
-mtk-eth-soc-$(CONFIG_NET_MEDIATEK_MT7621) += soc_mt7621.o
-
-obj-$(CONFIG_NET_MEDIATEK_GSW_MT7621) += gsw_mt7621.o
-
-obj-$(CONFIG_NET_MEDIATEK_SOC_STAGING) += mtk-eth-soc.o
+++ /dev/null
-
-- verify devicetree documentation is consistent with code
-- fix ethtool - currently doesn't return valid data.
-- general code review and clean up
-- add support for second MAC on mt7621
-- convert gsw code to use switchdev interfaces
-- md7620_mmi_write etc should probably be wrapped
- in a regmap abstraction.
-- Get soc_mt7621 to work with QDMA TX if possible.
-- Ensure phys are correctly configured when a cable
- is plugged in.
-
-Cc: NeilBrown <neil@brown.name>
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0
-/* This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * Copyright (C) 2009-2016 John Crispin <blogic@openwrt.org>
- * Copyright (C) 2009-2016 Felix Fietkau <nbd@openwrt.org>
- * Copyright (C) 2013-2016 Michael Lee <igvtee@gmail.com>
- */
-
-#include "mtk_eth_soc.h"
-#include "ethtool.h"
-
-struct mtk_stat {
- char name[ETH_GSTRING_LEN];
- unsigned int idx;
-};
-
-#define MTK_HW_STAT(stat) { \
- .name = #stat, \
- .idx = offsetof(struct mtk_hw_stats, stat) / sizeof(u64) \
-}
-
-static const struct mtk_stat mtk_ethtool_hw_stats[] = {
- MTK_HW_STAT(tx_bytes),
- MTK_HW_STAT(tx_packets),
- MTK_HW_STAT(tx_skip),
- MTK_HW_STAT(tx_collisions),
- MTK_HW_STAT(rx_bytes),
- MTK_HW_STAT(rx_packets),
- MTK_HW_STAT(rx_overflow),
- MTK_HW_STAT(rx_fcs_errors),
- MTK_HW_STAT(rx_short_errors),
- MTK_HW_STAT(rx_long_errors),
- MTK_HW_STAT(rx_checksum_errors),
- MTK_HW_STAT(rx_flow_control_packets),
-};
-
-#define MTK_HW_STATS_LEN ARRAY_SIZE(mtk_ethtool_hw_stats)
-
-static int mtk_get_link_ksettings(struct net_device *dev,
- struct ethtool_link_ksettings *cmd)
-{
- struct mtk_mac *mac = netdev_priv(dev);
- int err;
-
- if (!mac->phy_dev)
- return -ENODEV;
-
- if (mac->phy_flags == MTK_PHY_FLAG_ATTACH) {
- err = phy_read_status(mac->phy_dev);
- if (err)
- return -ENODEV;
- }
-
- phy_ethtool_ksettings_get(mac->phy_dev, cmd);
- return 0;
-}
-
-static int mtk_set_link_ksettings(struct net_device *dev,
- const struct ethtool_link_ksettings *cmd)
-{
- struct mtk_mac *mac = netdev_priv(dev);
-
- if (!mac->phy_dev)
- return -ENODEV;
-
- if (cmd->base.phy_address != mac->phy_dev->mdio.addr) {
- if (mac->hw->phy->phy_node[cmd->base.phy_address]) {
- mac->phy_dev = mac->hw->phy->phy[cmd->base.phy_address];
- mac->phy_flags = MTK_PHY_FLAG_PORT;
- } else if (mac->hw->mii_bus) {
- mac->phy_dev = mdiobus_get_phy(mac->hw->mii_bus,
- cmd->base.phy_address);
- if (!mac->phy_dev)
- return -ENODEV;
- mac->phy_flags = MTK_PHY_FLAG_ATTACH;
- } else {
- return -ENODEV;
- }
- }
-
- return phy_ethtool_ksettings_set(mac->phy_dev, cmd);
-}
-
-static void mtk_get_drvinfo(struct net_device *dev,
- struct ethtool_drvinfo *info)
-{
- struct mtk_mac *mac = netdev_priv(dev);
- struct mtk_soc_data *soc = mac->hw->soc;
-
- strlcpy(info->driver, mac->hw->dev->driver->name, sizeof(info->driver));
- strlcpy(info->bus_info, dev_name(mac->hw->dev), sizeof(info->bus_info));
-
- if (soc->reg_table[MTK_REG_MTK_COUNTER_BASE])
- info->n_stats = MTK_HW_STATS_LEN;
-}
-
-static u32 mtk_get_msglevel(struct net_device *dev)
-{
- struct mtk_mac *mac = netdev_priv(dev);
-
- return mac->hw->msg_enable;
-}
-
-static void mtk_set_msglevel(struct net_device *dev, u32 value)
-{
- struct mtk_mac *mac = netdev_priv(dev);
-
- mac->hw->msg_enable = value;
-}
-
-static int mtk_nway_reset(struct net_device *dev)
-{
- struct mtk_mac *mac = netdev_priv(dev);
-
- if (!mac->phy_dev)
- return -EOPNOTSUPP;
-
- return genphy_restart_aneg(mac->phy_dev);
-}
-
-static u32 mtk_get_link(struct net_device *dev)
-{
- struct mtk_mac *mac = netdev_priv(dev);
- int err;
-
- if (!mac->phy_dev)
- goto out_get_link;
-
- if (mac->phy_flags == MTK_PHY_FLAG_ATTACH) {
- err = genphy_update_link(mac->phy_dev);
- if (err)
- goto out_get_link;
- }
-
- return mac->phy_dev->link;
-
-out_get_link:
- return ethtool_op_get_link(dev);
-}
-
-static int mtk_set_ringparam(struct net_device *dev,
- struct ethtool_ringparam *ring)
-{
- struct mtk_mac *mac = netdev_priv(dev);
-
- if ((ring->tx_pending < 2) ||
- (ring->rx_pending < 2) ||
- (ring->rx_pending > mac->hw->soc->dma_ring_size) ||
- (ring->tx_pending > mac->hw->soc->dma_ring_size))
- return -EINVAL;
-
- dev->netdev_ops->ndo_stop(dev);
-
- mac->hw->tx_ring.tx_ring_size = BIT(fls(ring->tx_pending) - 1);
- mac->hw->rx_ring[0].rx_ring_size = BIT(fls(ring->rx_pending) - 1);
-
- return dev->netdev_ops->ndo_open(dev);
-}
-
-static void mtk_get_ringparam(struct net_device *dev,
- struct ethtool_ringparam *ring)
-{
- struct mtk_mac *mac = netdev_priv(dev);
-
- ring->rx_max_pending = mac->hw->soc->dma_ring_size;
- ring->tx_max_pending = mac->hw->soc->dma_ring_size;
- ring->rx_pending = mac->hw->rx_ring[0].rx_ring_size;
- ring->tx_pending = mac->hw->tx_ring.tx_ring_size;
-}
-
-static void mtk_get_strings(struct net_device *dev, u32 stringset, u8 *data)
-{
- int i;
-
- switch (stringset) {
- case ETH_SS_STATS:
- for (i = 0; i < MTK_HW_STATS_LEN; i++) {
- memcpy(data, mtk_ethtool_hw_stats[i].name,
- ETH_GSTRING_LEN);
- data += ETH_GSTRING_LEN;
- }
- break;
- }
-}
-
-static int mtk_get_sset_count(struct net_device *dev, int sset)
-{
- switch (sset) {
- case ETH_SS_STATS:
- return MTK_HW_STATS_LEN;
- default:
- return -EOPNOTSUPP;
- }
-}
-
-static void mtk_get_ethtool_stats(struct net_device *dev,
- struct ethtool_stats *stats, u64 *data)
-{
- struct mtk_mac *mac = netdev_priv(dev);
- struct mtk_hw_stats *hwstats = mac->hw_stats;
- unsigned int start;
- int i;
-
- if (netif_running(dev) && netif_device_present(dev)) {
- if (spin_trylock(&hwstats->stats_lock)) {
- mtk_stats_update_mac(mac);
- spin_unlock(&hwstats->stats_lock);
- }
- }
-
- do {
- start = u64_stats_fetch_begin_irq(&hwstats->syncp);
- for (i = 0; i < MTK_HW_STATS_LEN; i++)
- data[i] = ((u64 *)hwstats)[mtk_ethtool_hw_stats[i].idx];
-
- } while (u64_stats_fetch_retry_irq(&hwstats->syncp, start));
-}
-
-static struct ethtool_ops mtk_ethtool_ops = {
- .get_link_ksettings = mtk_get_link_ksettings,
- .set_link_ksettings = mtk_set_link_ksettings,
- .get_drvinfo = mtk_get_drvinfo,
- .get_msglevel = mtk_get_msglevel,
- .set_msglevel = mtk_set_msglevel,
- .nway_reset = mtk_nway_reset,
- .get_link = mtk_get_link,
- .set_ringparam = mtk_set_ringparam,
- .get_ringparam = mtk_get_ringparam,
-};
-
-void mtk_set_ethtool_ops(struct net_device *netdev)
-{
- struct mtk_mac *mac = netdev_priv(netdev);
- struct mtk_soc_data *soc = mac->hw->soc;
-
- if (soc->reg_table[MTK_REG_MTK_COUNTER_BASE]) {
- mtk_ethtool_ops.get_strings = mtk_get_strings;
- mtk_ethtool_ops.get_sset_count = mtk_get_sset_count;
- mtk_ethtool_ops.get_ethtool_stats = mtk_get_ethtool_stats;
- }
-
- netdev->ethtool_ops = &mtk_ethtool_ops;
-}
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright (C) 2009-2016 John Crispin <blogic@openwrt.org>
- * Copyright (C) 2009-2016 Felix Fietkau <nbd@openwrt.org>
- * Copyright (C) 2013-2016 Michael Lee <igvtee@gmail.com>
- */
-
-#ifndef MTK_ETHTOOL_H
-#define MTK_ETHTOOL_H
-
-#include <linux/ethtool.h>
-
-void mtk_set_ethtool_ops(struct net_device *netdev);
-
-#endif /* MTK_ETHTOOL_H */
+++ /dev/null
-/* This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * Copyright (C) 2009-2016 John Crispin <blogic@openwrt.org>
- * Copyright (C) 2009-2016 Felix Fietkau <nbd@openwrt.org>
- * Copyright (C) 2013-2016 Michael Lee <igvtee@gmail.com>
- */
-
-#ifndef _RALINK_GSW_MT7620_H__
-#define _RALINK_GSW_MT7620_H__
-
-#define GSW_REG_PHY_TIMEOUT (5 * HZ)
-
-#define MT7620_GSW_REG_PIAC 0x0004
-
-#define GSW_NUM_VLANS 16
-#define GSW_NUM_VIDS 4096
-#define GSW_NUM_PORTS 7
-#define GSW_PORT6 6
-
-#define GSW_MDIO_ACCESS BIT(31)
-#define GSW_MDIO_READ BIT(19)
-#define GSW_MDIO_WRITE BIT(18)
-#define GSW_MDIO_START BIT(16)
-#define GSW_MDIO_ADDR_SHIFT 20
-#define GSW_MDIO_REG_SHIFT 25
-
-#define GSW_REG_PORT_PMCR(x) (0x3000 + (x * 0x100))
-#define GSW_REG_PORT_STATUS(x) (0x3008 + (x * 0x100))
-#define GSW_REG_SMACCR0 0x3fE4
-#define GSW_REG_SMACCR1 0x3fE8
-#define GSW_REG_CKGCR 0x3ff0
-
-#define GSW_REG_IMR 0x7008
-#define GSW_REG_ISR 0x700c
-#define GSW_REG_GPC1 0x7014
-
-#define SYSC_REG_CHIP_REV_ID 0x0c
-#define SYSC_REG_CFG 0x10
-#define SYSC_REG_CFG1 0x14
-#define RST_CTRL_MCM BIT(2)
-#define SYSC_PAD_RGMII2_MDIO 0x58
-#define SYSC_GPIO_MODE 0x60
-
-#define PORT_IRQ_ST_CHG 0x7f
-
-#define MT7621_ESW_PHY_POLLING 0x0000
-#define MT7620_ESW_PHY_POLLING 0x7000
-
-#define PMCR_IPG BIT(18)
-#define PMCR_MAC_MODE BIT(16)
-#define PMCR_FORCE BIT(15)
-#define PMCR_TX_EN BIT(14)
-#define PMCR_RX_EN BIT(13)
-#define PMCR_BACKOFF BIT(9)
-#define PMCR_BACKPRES BIT(8)
-#define PMCR_RX_FC BIT(5)
-#define PMCR_TX_FC BIT(4)
-#define PMCR_SPEED(_x) (_x << 2)
-#define PMCR_DUPLEX BIT(1)
-#define PMCR_LINK BIT(0)
-
-#define PHY_AN_EN BIT(31)
-#define PHY_PRE_EN BIT(30)
-#define PMY_MDC_CONF(_x) ((_x & 0x3f) << 24)
-
-/* ethernet subsystem config register */
-#define ETHSYS_SYSCFG0 0x14
-/* ethernet subsystem clock register */
-#define ETHSYS_CLKCFG0 0x2c
-#define ETHSYS_TRGMII_CLK_SEL362_5 BIT(11)
-
-/* p5 RGMII wrapper TX clock control register */
-#define MT7530_P5RGMIITXCR 0x7b04
-/* p5 RGMII wrapper RX clock control register */
-#define MT7530_P5RGMIIRXCR 0x7b00
-/* TRGMII TDX ODT registers */
-#define MT7530_TRGMII_TD0_ODT 0x7a54
-#define MT7530_TRGMII_TD1_ODT 0x7a5c
-#define MT7530_TRGMII_TD2_ODT 0x7a64
-#define MT7530_TRGMII_TD3_ODT 0x7a6c
-#define MT7530_TRGMII_TD4_ODT 0x7a74
-#define MT7530_TRGMII_TD5_ODT 0x7a7c
-/* TRGMII TCK ctrl register */
-#define MT7530_TRGMII_TCK_CTRL 0x7a78
-/* TRGMII Tx ctrl register */
-#define MT7530_TRGMII_TXCTRL 0x7a40
-/* port 6 extended control register */
-#define MT7530_P6ECR 0x7830
-/* IO driver control register */
-#define MT7530_IO_DRV_CR 0x7810
-/* top signal control register */
-#define MT7530_TOP_SIG_CTRL 0x7808
-/* modified hwtrap register */
-#define MT7530_MHWTRAP 0x7804
-/* hwtrap status register */
-#define MT7530_HWTRAP 0x7800
-/* status interrupt register */
-#define MT7530_SYS_INT_STS 0x700c
-/* system nterrupt register */
-#define MT7530_SYS_INT_EN 0x7008
-/* system control register */
-#define MT7530_SYS_CTRL 0x7000
-/* port MAC status register */
-#define MT7530_PMSR_P(x) (0x3008 + (x * 0x100))
-/* port MAC control register */
-#define MT7530_PMCR_P(x) (0x3000 + (x * 0x100))
-
-#define MT7621_XTAL_SHIFT 6
-#define MT7621_XTAL_MASK 0x7
-#define MT7621_XTAL_25 6
-#define MT7621_XTAL_40 3
-#define MT7621_MDIO_DRV_MASK (3 << 4)
-#define MT7621_GE1_MODE_MASK (3 << 12)
-
-#define TRGMII_TXCTRL_TXC_INV BIT(30)
-#define P6ECR_INTF_MODE_RGMII BIT(1)
-#define P5RGMIIRXCR_C_ALIGN BIT(8)
-#define P5RGMIIRXCR_DELAY_2 BIT(1)
-#define P5RGMIITXCR_DELAY_2 (BIT(8) | BIT(2))
-
-/* TOP_SIG_CTRL bits */
-#define TOP_SIG_CTRL_NORMAL (BIT(17) | BIT(16))
-
-/* MHWTRAP bits */
-#define MHWTRAP_MANUAL BIT(16)
-#define MHWTRAP_P5_MAC_SEL BIT(13)
-#define MHWTRAP_P6_DIS BIT(8)
-#define MHWTRAP_P5_RGMII_MODE BIT(7)
-#define MHWTRAP_P5_DIS BIT(6)
-#define MHWTRAP_PHY_ACCESS BIT(5)
-
-/* HWTRAP bits */
-#define HWTRAP_XTAL_SHIFT 9
-#define HWTRAP_XTAL_MASK 0x3
-
-/* SYS_CTRL bits */
-#define SYS_CTRL_SW_RST BIT(1)
-#define SYS_CTRL_REG_RST BIT(0)
-
-/* PMCR bits */
-#define PMCR_IFG_XMIT_96 BIT(18)
-#define PMCR_MAC_MODE BIT(16)
-#define PMCR_FORCE_MODE BIT(15)
-#define PMCR_TX_EN BIT(14)
-#define PMCR_RX_EN BIT(13)
-#define PMCR_BACK_PRES_EN BIT(9)
-#define PMCR_BACKOFF_EN BIT(8)
-#define PMCR_TX_FC_EN BIT(5)
-#define PMCR_RX_FC_EN BIT(4)
-#define PMCR_FORCE_SPEED_1000 BIT(3)
-#define PMCR_FORCE_FDX BIT(1)
-#define PMCR_FORCE_LNK BIT(0)
-#define PMCR_FIXED_LINK (PMCR_IFG_XMIT_96 | PMCR_MAC_MODE | \
- PMCR_FORCE_MODE | PMCR_TX_EN | PMCR_RX_EN | \
- PMCR_BACK_PRES_EN | PMCR_BACKOFF_EN | \
- PMCR_FORCE_SPEED_1000 | PMCR_FORCE_FDX | \
- PMCR_FORCE_LNK)
-
-#define PMCR_FIXED_LINK_FC (PMCR_FIXED_LINK | \
- PMCR_TX_FC_EN | PMCR_RX_FC_EN)
-
-/* TRGMII control registers */
-#define GSW_INTF_MODE 0x390
-#define GSW_TRGMII_TD0_ODT 0x354
-#define GSW_TRGMII_TD1_ODT 0x35c
-#define GSW_TRGMII_TD2_ODT 0x364
-#define GSW_TRGMII_TD3_ODT 0x36c
-#define GSW_TRGMII_TXCTL_ODT 0x374
-#define GSW_TRGMII_TCK_ODT 0x37c
-#define GSW_TRGMII_RCK_CTRL 0x300
-
-#define INTF_MODE_TRGMII BIT(1)
-#define TRGMII_RCK_CTRL_RX_RST BIT(31)
-
-/* Mac control registers */
-#define MTK_MAC_P2_MCR 0x200
-#define MTK_MAC_P1_MCR 0x100
-
-#define MAC_MCR_MAX_RX_2K BIT(29)
-#define MAC_MCR_IPG_CFG (BIT(18) | BIT(16))
-#define MAC_MCR_FORCE_MODE BIT(15)
-#define MAC_MCR_TX_EN BIT(14)
-#define MAC_MCR_RX_EN BIT(13)
-#define MAC_MCR_BACKOFF_EN BIT(9)
-#define MAC_MCR_BACKPR_EN BIT(8)
-#define MAC_MCR_FORCE_RX_FC BIT(5)
-#define MAC_MCR_FORCE_TX_FC BIT(4)
-#define MAC_MCR_SPEED_1000 BIT(3)
-#define MAC_MCR_FORCE_DPX BIT(1)
-#define MAC_MCR_FORCE_LINK BIT(0)
-#define MAC_MCR_FIXED_LINK (MAC_MCR_MAX_RX_2K | MAC_MCR_IPG_CFG | \
- MAC_MCR_FORCE_MODE | MAC_MCR_TX_EN | \
- MAC_MCR_RX_EN | MAC_MCR_BACKOFF_EN | \
- MAC_MCR_BACKPR_EN | MAC_MCR_FORCE_RX_FC | \
- MAC_MCR_FORCE_TX_FC | MAC_MCR_SPEED_1000 | \
- MAC_MCR_FORCE_DPX | MAC_MCR_FORCE_LINK)
-#define MAC_MCR_FIXED_LINK_FC (MAC_MCR_MAX_RX_2K | MAC_MCR_IPG_CFG | \
- MAC_MCR_FIXED_LINK)
-
-/* possible XTAL speed */
-#define MT7623_XTAL_40 0
-#define MT7623_XTAL_20 1
-#define MT7623_XTAL_25 3
-
-/* GPIO port control registers */
-#define GPIO_OD33_CTRL8 0x4c0
-#define GPIO_BIAS_CTRL 0xed0
-#define GPIO_DRV_SEL10 0xf00
-
-/* on MT7620 the functio of port 4 can be software configured */
-enum {
- PORT4_EPHY = 0,
- PORT4_EXT,
-};
-
-/* struct mt7620_gsw - the structure that holds the SoC specific data
- * @dev: The Device struct
- * @base: The base address
- * @piac_offset: The PIAC base may change depending on SoC
- * @irq: The IRQ we are using
- * @port4: The port4 mode on MT7620
- * @autopoll: Is MDIO autopolling enabled
- * @ethsys: The ethsys register map
- * @pctl: The pin control register map
- * @clk_gsw: The switch clock
- * @clk_gp1: The gmac1 clock
- * @clk_gp2: The gmac2 clock
- * @clk_trgpll: The trgmii pll clock
- */
-struct mt7620_gsw {
- struct device *dev;
- void __iomem *base;
- u32 piac_offset;
- int irq;
- int port4;
- unsigned long int autopoll;
-
- struct regmap *ethsys;
- struct regmap *pctl;
-
- struct clk *clk_gsw;
- struct clk *clk_gp1;
- struct clk *clk_gp2;
- struct clk *clk_trgpll;
-};
-
-/* switch register I/O wrappers */
-void mtk_switch_w32(struct mt7620_gsw *gsw, u32 val, unsigned int reg);
-u32 mtk_switch_r32(struct mt7620_gsw *gsw, unsigned int reg);
-
-/* the callback used by the driver core to bringup the switch */
-int mtk_gsw_init(struct mtk_eth *eth);
-
-/* MDIO access wrappers */
-int mt7620_mdio_write(struct mii_bus *bus, int phy_addr, int phy_reg, u16 val);
-int mt7620_mdio_read(struct mii_bus *bus, int phy_addr, int phy_reg);
-void mt7620_mdio_link_adjust(struct mtk_eth *eth, int port);
-int mt7620_has_carrier(struct mtk_eth *eth);
-void mt7620_print_link_state(struct mtk_eth *eth, int port, int link,
- int speed, int duplex);
-void mt7530_mdio_w32(struct mt7620_gsw *gsw, u32 reg, u32 val);
-u32 mt7530_mdio_r32(struct mt7620_gsw *gsw, u32 reg);
-void mt7530_mdio_m32(struct mt7620_gsw *gsw, u32 mask, u32 set, u32 reg);
-
-u32 _mt7620_mii_write(struct mt7620_gsw *gsw, u32 phy_addr,
- u32 phy_register, u32 write_data);
-u32 _mt7620_mii_read(struct mt7620_gsw *gsw, int phy_addr, int phy_reg);
-void mt7620_handle_carrier(struct mtk_eth *eth);
-
-#endif
+++ /dev/null
-/* This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * Copyright (C) 2009-2016 John Crispin <blogic@openwrt.org>
- * Copyright (C) 2009-2016 Felix Fietkau <nbd@openwrt.org>
- * Copyright (C) 2013-2016 Michael Lee <igvtee@gmail.com>
- */
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/platform_device.h>
-#include <linux/of_device.h>
-#include <linux/of_irq.h>
-
-#include <ralink_regs.h>
-
-#include "mtk_eth_soc.h"
-#include "gsw_mt7620.h"
-
-void mtk_switch_w32(struct mt7620_gsw *gsw, u32 val, unsigned int reg)
-{
- iowrite32(val, gsw->base + reg);
-}
-EXPORT_SYMBOL_GPL(mtk_switch_w32);
-
-u32 mtk_switch_r32(struct mt7620_gsw *gsw, unsigned int reg)
-{
- return ioread32(gsw->base + reg);
-}
-EXPORT_SYMBOL_GPL(mtk_switch_r32);
-
-static irqreturn_t gsw_interrupt_mt7621(int irq, void *_eth)
-{
- struct mtk_eth *eth = (struct mtk_eth *)_eth;
- struct mt7620_gsw *gsw = (struct mt7620_gsw *)eth->sw_priv;
- u32 reg, i;
-
- reg = mt7530_mdio_r32(gsw, MT7530_SYS_INT_STS);
-
- for (i = 0; i < 5; i++) {
- unsigned int link;
-
- if ((reg & BIT(i)) == 0)
- continue;
-
- link = mt7530_mdio_r32(gsw, MT7530_PMSR_P(i)) & 0x1;
-
- if (link == eth->link[i])
- continue;
-
- eth->link[i] = link;
- if (link)
- netdev_info(*eth->netdev,
- "port %d link up\n", i);
- else
- netdev_info(*eth->netdev,
- "port %d link down\n", i);
- }
-
- mt7530_mdio_w32(gsw, MT7530_SYS_INT_STS, 0x1f);
-
- return IRQ_HANDLED;
-}
-
-static void mt7621_hw_init(struct mtk_eth *eth, struct mt7620_gsw *gsw,
- struct device_node *np)
-{
- u32 i;
- u32 val;
-
- /* hardware reset the switch */
- mtk_reset(eth, RST_CTRL_MCM);
- mdelay(10);
-
- /* reduce RGMII2 PAD driving strength */
- rt_sysc_m32(MT7621_MDIO_DRV_MASK, 0, SYSC_PAD_RGMII2_MDIO);
-
- /* gpio mux - RGMII1=Normal mode */
- rt_sysc_m32(BIT(14), 0, SYSC_GPIO_MODE);
-
- /* set GMAC1 RGMII mode */
- rt_sysc_m32(MT7621_GE1_MODE_MASK, 0, SYSC_REG_CFG1);
-
- /* enable MDIO to control MT7530 */
- rt_sysc_m32(3 << 12, 0, SYSC_GPIO_MODE);
-
- /* turn off all PHYs */
- for (i = 0; i <= 4; i++) {
- val = _mt7620_mii_read(gsw, i, 0x0);
- val |= BIT(11);
- _mt7620_mii_write(gsw, i, 0x0, val);
- }
-
- /* reset the switch */
- mt7530_mdio_w32(gsw, MT7530_SYS_CTRL,
- SYS_CTRL_SW_RST | SYS_CTRL_REG_RST);
- usleep_range(10, 20);
-
- if ((rt_sysc_r32(SYSC_REG_CHIP_REV_ID) & 0xFFFF) == 0x0101) {
- /* GE1, Force 1000M/FD, FC ON, MAX_RX_LENGTH 1536 */
- mtk_switch_w32(gsw, MAC_MCR_FIXED_LINK, MTK_MAC_P2_MCR);
- mt7530_mdio_w32(gsw, MT7530_PMCR_P(6), PMCR_FIXED_LINK);
- } else {
- /* GE1, Force 1000M/FD, FC ON, MAX_RX_LENGTH 1536 */
- mtk_switch_w32(gsw, MAC_MCR_FIXED_LINK_FC, MTK_MAC_P1_MCR);
- mt7530_mdio_w32(gsw, MT7530_PMCR_P(6), PMCR_FIXED_LINK_FC);
- }
-
- /* GE2, Link down */
- mtk_switch_w32(gsw, MAC_MCR_FORCE_MODE, MTK_MAC_P2_MCR);
-
- /* Enable Port 6, P5 as GMAC5, P5 disable */
- val = mt7530_mdio_r32(gsw, MT7530_MHWTRAP);
- /* Enable Port 6 */
- val &= ~MHWTRAP_P6_DIS;
- /* Disable Port 5 */
- val |= MHWTRAP_P5_DIS;
- /* manual override of HW-Trap */
- val |= MHWTRAP_MANUAL;
- mt7530_mdio_w32(gsw, MT7530_MHWTRAP, val);
-
- val = rt_sysc_r32(SYSC_REG_CFG);
- val = (val >> MT7621_XTAL_SHIFT) & MT7621_XTAL_MASK;
- if (val < MT7621_XTAL_25 && val >= MT7621_XTAL_40) {
- /* 40Mhz */
-
- /* disable MT7530 core clock */
- _mt7620_mii_write(gsw, 0, 13, 0x1f);
- _mt7620_mii_write(gsw, 0, 14, 0x410);
- _mt7620_mii_write(gsw, 0, 13, 0x401f);
- _mt7620_mii_write(gsw, 0, 14, 0x0);
-
- /* disable MT7530 PLL */
- _mt7620_mii_write(gsw, 0, 13, 0x1f);
- _mt7620_mii_write(gsw, 0, 14, 0x40d);
- _mt7620_mii_write(gsw, 0, 13, 0x401f);
- _mt7620_mii_write(gsw, 0, 14, 0x2020);
-
- /* for MT7530 core clock = 500Mhz */
- _mt7620_mii_write(gsw, 0, 13, 0x1f);
- _mt7620_mii_write(gsw, 0, 14, 0x40e);
- _mt7620_mii_write(gsw, 0, 13, 0x401f);
- _mt7620_mii_write(gsw, 0, 14, 0x119);
-
- /* enable MT7530 PLL */
- _mt7620_mii_write(gsw, 0, 13, 0x1f);
- _mt7620_mii_write(gsw, 0, 14, 0x40d);
- _mt7620_mii_write(gsw, 0, 13, 0x401f);
- _mt7620_mii_write(gsw, 0, 14, 0x2820);
-
- usleep_range(20, 40);
-
- /* enable MT7530 core clock */
- _mt7620_mii_write(gsw, 0, 13, 0x1f);
- _mt7620_mii_write(gsw, 0, 14, 0x410);
- _mt7620_mii_write(gsw, 0, 13, 0x401f);
- }
-
- /* RGMII */
- _mt7620_mii_write(gsw, 0, 14, 0x1);
-
- /* set MT7530 central align */
- mt7530_mdio_m32(gsw, BIT(0), P6ECR_INTF_MODE_RGMII, MT7530_P6ECR);
- mt7530_mdio_m32(gsw, TRGMII_TXCTRL_TXC_INV, 0,
- MT7530_TRGMII_TXCTRL);
- mt7530_mdio_w32(gsw, MT7530_TRGMII_TCK_CTRL, 0x855);
-
- /* delay setting for 10/1000M */
- mt7530_mdio_w32(gsw, MT7530_P5RGMIIRXCR,
- P5RGMIIRXCR_C_ALIGN | P5RGMIIRXCR_DELAY_2);
- mt7530_mdio_w32(gsw, MT7530_P5RGMIITXCR, 0x14);
-
- /* lower Tx Driving*/
- mt7530_mdio_w32(gsw, MT7530_TRGMII_TD0_ODT, 0x44);
- mt7530_mdio_w32(gsw, MT7530_TRGMII_TD1_ODT, 0x44);
- mt7530_mdio_w32(gsw, MT7530_TRGMII_TD2_ODT, 0x44);
- mt7530_mdio_w32(gsw, MT7530_TRGMII_TD3_ODT, 0x44);
- mt7530_mdio_w32(gsw, MT7530_TRGMII_TD4_ODT, 0x44);
- mt7530_mdio_w32(gsw, MT7530_TRGMII_TD5_ODT, 0x44);
-
- /* turn on all PHYs */
- for (i = 0; i <= 4; i++) {
- val = _mt7620_mii_read(gsw, i, 0);
- val &= ~BIT(11);
- _mt7620_mii_write(gsw, i, 0, val);
- }
-
-#define MT7530_NUM_PORTS 8
-#define REG_ESW_PORT_PCR(x) (0x2004 | ((x) << 8))
-#define REG_ESW_PORT_PVC(x) (0x2010 | ((x) << 8))
-#define REG_ESW_PORT_PPBV1(x) (0x2014 | ((x) << 8))
-#define MT7530_CPU_PORT 6
-
- /* This is copied from mt7530_apply_config in libreCMC driver */
- {
- int i;
-
- for (i = 0; i < MT7530_NUM_PORTS; i++)
- mt7530_mdio_w32(gsw, REG_ESW_PORT_PCR(i), 0x00400000);
-
- mt7530_mdio_w32(gsw, REG_ESW_PORT_PCR(MT7530_CPU_PORT),
- 0x00ff0000);
-
- for (i = 0; i < MT7530_NUM_PORTS; i++)
- mt7530_mdio_w32(gsw, REG_ESW_PORT_PVC(i), 0x810000c0);
- }
-
- /* enable irq */
- mt7530_mdio_m32(gsw, 0, 3 << 16, MT7530_TOP_SIG_CTRL);
- mt7530_mdio_w32(gsw, MT7530_SYS_INT_EN, 0x1f);
-}
-
-static const struct of_device_id mediatek_gsw_match[] = {
- { .compatible = "mediatek,mt7621-gsw" },
- {},
-};
-MODULE_DEVICE_TABLE(of, mediatek_gsw_match);
-
-int mtk_gsw_init(struct mtk_eth *eth)
-{
- struct device_node *np = eth->switch_np;
- struct platform_device *pdev = of_find_device_by_node(np);
- struct mt7620_gsw *gsw;
-
- if (!pdev)
- return -ENODEV;
-
- if (!of_device_is_compatible(np, mediatek_gsw_match->compatible))
- return -EINVAL;
-
- gsw = platform_get_drvdata(pdev);
- eth->sw_priv = gsw;
-
- if (!gsw->irq)
- return -EINVAL;
-
- request_irq(gsw->irq, gsw_interrupt_mt7621, 0,
- "gsw", eth);
- disable_irq(gsw->irq);
-
- mt7621_hw_init(eth, gsw, np);
-
- enable_irq(gsw->irq);
-
- return 0;
-}
-EXPORT_SYMBOL_GPL(mtk_gsw_init);
-
-static int mt7621_gsw_probe(struct platform_device *pdev)
-{
- struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- struct mt7620_gsw *gsw;
-
- gsw = devm_kzalloc(&pdev->dev, sizeof(struct mt7620_gsw), GFP_KERNEL);
- if (!gsw)
- return -ENOMEM;
-
- gsw->base = devm_ioremap_resource(&pdev->dev, res);
- if (IS_ERR(gsw->base))
- return PTR_ERR(gsw->base);
-
- gsw->dev = &pdev->dev;
- gsw->irq = irq_of_parse_and_map(pdev->dev.of_node, 0);
-
- platform_set_drvdata(pdev, gsw);
-
- return 0;
-}
-
-static int mt7621_gsw_remove(struct platform_device *pdev)
-{
- platform_set_drvdata(pdev, NULL);
-
- return 0;
-}
-
-static struct platform_driver gsw_driver = {
- .probe = mt7621_gsw_probe,
- .remove = mt7621_gsw_remove,
- .driver = {
- .name = "mt7621-gsw",
- .of_match_table = mediatek_gsw_match,
- },
-};
-
-module_platform_driver(gsw_driver);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("John Crispin <blogic@openwrt.org>");
-MODULE_DESCRIPTION("GBit switch driver for Mediatek MT7621 SoC");
+++ /dev/null
-/* This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License
- *
- * Copyright (C) 2009-2016 John Crispin <blogic@openwrt.org>
- * Copyright (C) 2009-2016 Felix Fietkau <nbd@openwrt.org>
- * Copyright (C) 2013-2016 Michael Lee <igvtee@gmail.com>
- */
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/phy.h>
-#include <linux/of_net.h>
-#include <linux/of_mdio.h>
-
-#include "mtk_eth_soc.h"
-#include "mdio.h"
-
-static int mtk_mdio_reset(struct mii_bus *bus)
-{
- /* TODO */
- return 0;
-}
-
-static void mtk_phy_link_adjust(struct net_device *dev)
-{
- struct mtk_eth *eth = netdev_priv(dev);
- unsigned long flags;
- int i;
-
- spin_lock_irqsave(ð->phy->lock, flags);
- for (i = 0; i < 8; i++) {
- if (eth->phy->phy_node[i]) {
- struct phy_device *phydev = eth->phy->phy[i];
- int status_change = 0;
-
- if (phydev->link)
- if (eth->phy->duplex[i] != phydev->duplex ||
- eth->phy->speed[i] != phydev->speed)
- status_change = 1;
-
- if (phydev->link != eth->link[i])
- status_change = 1;
-
- switch (phydev->speed) {
- case SPEED_1000:
- case SPEED_100:
- case SPEED_10:
- eth->link[i] = phydev->link;
- eth->phy->duplex[i] = phydev->duplex;
- eth->phy->speed[i] = phydev->speed;
-
- if (status_change &&
- eth->soc->mdio_adjust_link)
- eth->soc->mdio_adjust_link(eth, i);
- break;
- }
- }
- }
- spin_unlock_irqrestore(ð->phy->lock, flags);
-}
-
-int mtk_connect_phy_node(struct mtk_eth *eth, struct mtk_mac *mac,
- struct device_node *phy_node)
-{
- const __be32 *_port = NULL;
- struct phy_device *phydev;
- int phy_mode, port;
-
- _port = of_get_property(phy_node, "reg", NULL);
-
- if (!_port || (be32_to_cpu(*_port) >= 0x20)) {
- pr_err("%pOFn: invalid port id\n", phy_node);
- return -EINVAL;
- }
- port = be32_to_cpu(*_port);
- phy_mode = of_get_phy_mode(phy_node);
- if (phy_mode < 0) {
- dev_err(eth->dev, "incorrect phy-mode %d\n", phy_mode);
- eth->phy->phy_node[port] = NULL;
- return -EINVAL;
- }
-
- phydev = of_phy_connect(eth->netdev[mac->id], phy_node,
- mtk_phy_link_adjust, 0, phy_mode);
- if (!phydev) {
- dev_err(eth->dev, "could not connect to PHY\n");
- eth->phy->phy_node[port] = NULL;
- return -ENODEV;
- }
-
- phydev->supported &= PHY_1000BT_FEATURES;
- phydev->advertising = phydev->supported;
-
- dev_info(eth->dev,
- "connected port %d to PHY at %s [uid=%08x, driver=%s]\n",
- port, phydev_name(phydev), phydev->phy_id,
- phydev->drv->name);
-
- eth->phy->phy[port] = phydev;
- eth->link[port] = 0;
-
- return 0;
-}
-
-static void phy_init(struct mtk_eth *eth, struct mtk_mac *mac,
- struct phy_device *phy)
-{
- phy_attach(eth->netdev[mac->id], phydev_name(phy),
- PHY_INTERFACE_MODE_MII);
-
- phy->autoneg = AUTONEG_ENABLE;
- phy->speed = 0;
- phy->duplex = 0;
- phy_set_max_speed(phy, SPEED_100);
- phy->advertising = phy->supported | ADVERTISED_Autoneg;
-
- phy_start_aneg(phy);
-}
-
-static int mtk_phy_connect(struct mtk_mac *mac)
-{
- struct mtk_eth *eth = mac->hw;
- int i;
-
- for (i = 0; i < 8; i++) {
- if (eth->phy->phy_node[i]) {
- if (!mac->phy_dev) {
- mac->phy_dev = eth->phy->phy[i];
- mac->phy_flags = MTK_PHY_FLAG_PORT;
- }
- } else if (eth->mii_bus) {
- struct phy_device *phy;
-
- phy = mdiobus_get_phy(eth->mii_bus, i);
- if (phy) {
- phy_init(eth, mac, phy);
- if (!mac->phy_dev) {
- mac->phy_dev = phy;
- mac->phy_flags = MTK_PHY_FLAG_ATTACH;
- }
- }
- }
- }
-
- return 0;
-}
-
-static void mtk_phy_disconnect(struct mtk_mac *mac)
-{
- struct mtk_eth *eth = mac->hw;
- unsigned long flags;
- int i;
-
- for (i = 0; i < 8; i++)
- if (eth->phy->phy_fixed[i]) {
- spin_lock_irqsave(ð->phy->lock, flags);
- eth->link[i] = 0;
- if (eth->soc->mdio_adjust_link)
- eth->soc->mdio_adjust_link(eth, i);
- spin_unlock_irqrestore(ð->phy->lock, flags);
- } else if (eth->phy->phy[i]) {
- phy_disconnect(eth->phy->phy[i]);
- } else if (eth->mii_bus) {
- struct phy_device *phy =
- mdiobus_get_phy(eth->mii_bus, i);
-
- if (phy)
- phy_detach(phy);
- }
-}
-
-static void mtk_phy_start(struct mtk_mac *mac)
-{
- struct mtk_eth *eth = mac->hw;
- unsigned long flags;
- int i;
-
- for (i = 0; i < 8; i++) {
- if (eth->phy->phy_fixed[i]) {
- spin_lock_irqsave(ð->phy->lock, flags);
- eth->link[i] = 1;
- if (eth->soc->mdio_adjust_link)
- eth->soc->mdio_adjust_link(eth, i);
- spin_unlock_irqrestore(ð->phy->lock, flags);
- } else if (eth->phy->phy[i]) {
- phy_start(eth->phy->phy[i]);
- }
- }
-}
-
-static void mtk_phy_stop(struct mtk_mac *mac)
-{
- struct mtk_eth *eth = mac->hw;
- unsigned long flags;
- int i;
-
- for (i = 0; i < 8; i++)
- if (eth->phy->phy_fixed[i]) {
- spin_lock_irqsave(ð->phy->lock, flags);
- eth->link[i] = 0;
- if (eth->soc->mdio_adjust_link)
- eth->soc->mdio_adjust_link(eth, i);
- spin_unlock_irqrestore(ð->phy->lock, flags);
- } else if (eth->phy->phy[i]) {
- phy_stop(eth->phy->phy[i]);
- }
-}
-
-static struct mtk_phy phy_ralink = {
- .connect = mtk_phy_connect,
- .disconnect = mtk_phy_disconnect,
- .start = mtk_phy_start,
- .stop = mtk_phy_stop,
-};
-
-int mtk_mdio_init(struct mtk_eth *eth)
-{
- struct device_node *mii_np;
- int err;
-
- if (!eth->soc->mdio_read || !eth->soc->mdio_write)
- return 0;
-
- spin_lock_init(&phy_ralink.lock);
- eth->phy = &phy_ralink;
-
- mii_np = of_get_child_by_name(eth->dev->of_node, "mdio-bus");
- if (!mii_np) {
- dev_err(eth->dev, "no %s child node found", "mdio-bus");
- return -ENODEV;
- }
-
- if (!of_device_is_available(mii_np)) {
- err = 0;
- goto err_put_node;
- }
-
- eth->mii_bus = mdiobus_alloc();
- if (!eth->mii_bus) {
- err = -ENOMEM;
- goto err_put_node;
- }
-
- eth->mii_bus->name = "mdio";
- eth->mii_bus->read = eth->soc->mdio_read;
- eth->mii_bus->write = eth->soc->mdio_write;
- eth->mii_bus->reset = mtk_mdio_reset;
- eth->mii_bus->priv = eth;
- eth->mii_bus->parent = eth->dev;
-
- snprintf(eth->mii_bus->id, MII_BUS_ID_SIZE, "%pOFn", mii_np);
- err = of_mdiobus_register(eth->mii_bus, mii_np);
- if (err)
- goto err_free_bus;
-
- return 0;
-
-err_free_bus:
- kfree(eth->mii_bus);
-err_put_node:
- of_node_put(mii_np);
- eth->mii_bus = NULL;
- return err;
-}
-
-void mtk_mdio_cleanup(struct mtk_eth *eth)
-{
- if (!eth->mii_bus)
- return;
-
- mdiobus_unregister(eth->mii_bus);
- of_node_put(eth->mii_bus->dev.of_node);
- kfree(eth->mii_bus);
-}
+++ /dev/null
-/* This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * Copyright (C) 2009-2016 John Crispin <blogic@openwrt.org>
- * Copyright (C) 2009-2016 Felix Fietkau <nbd@openwrt.org>
- * Copyright (C) 2013-2016 Michael Lee <igvtee@gmail.com>
- */
-
-#ifndef _RALINK_MDIO_H__
-#define _RALINK_MDIO_H__
-
-#ifdef CONFIG_NET_MEDIATEK_MDIO
-int mtk_mdio_init(struct mtk_eth *eth);
-void mtk_mdio_cleanup(struct mtk_eth *eth);
-int mtk_connect_phy_node(struct mtk_eth *eth, struct mtk_mac *mac,
- struct device_node *phy_node);
-#else
-static inline int mtk_mdio_init(struct mtk_eth *eth) { return 0; }
-static inline void mtk_mdio_cleanup(struct mtk_eth *eth) {}
-#endif
-#endif
+++ /dev/null
-/* This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * Copyright (C) 2009-2016 John Crispin <blogic@openwrt.org>
- * Copyright (C) 2009-2016 Felix Fietkau <nbd@openwrt.org>
- * Copyright (C) 2013-2016 Michael Lee <igvtee@gmail.com>
- */
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/types.h>
-
-#include "mtk_eth_soc.h"
-#include "gsw_mt7620.h"
-#include "mdio.h"
-
-static int mt7620_mii_busy_wait(struct mt7620_gsw *gsw)
-{
- unsigned long t_start = jiffies;
-
- while (1) {
- if (!(mtk_switch_r32(gsw,
- gsw->piac_offset + MT7620_GSW_REG_PIAC) &
- GSW_MDIO_ACCESS))
- return 0;
- if (time_after(jiffies, t_start + GSW_REG_PHY_TIMEOUT))
- break;
- }
-
- dev_err(gsw->dev, "mdio: MDIO timeout\n");
- return -1;
-}
-
-u32 _mt7620_mii_write(struct mt7620_gsw *gsw, u32 phy_addr,
- u32 phy_register, u32 write_data)
-{
- if (mt7620_mii_busy_wait(gsw))
- return -1;
-
- write_data &= 0xffff;
-
- mtk_switch_w32(gsw, GSW_MDIO_ACCESS | GSW_MDIO_START | GSW_MDIO_WRITE |
- (phy_register << GSW_MDIO_REG_SHIFT) |
- (phy_addr << GSW_MDIO_ADDR_SHIFT) | write_data,
- MT7620_GSW_REG_PIAC);
-
- if (mt7620_mii_busy_wait(gsw))
- return -1;
-
- return 0;
-}
-EXPORT_SYMBOL_GPL(_mt7620_mii_write);
-
-u32 _mt7620_mii_read(struct mt7620_gsw *gsw, int phy_addr, int phy_reg)
-{
- u32 d;
-
- if (mt7620_mii_busy_wait(gsw))
- return 0xffff;
-
- mtk_switch_w32(gsw, GSW_MDIO_ACCESS | GSW_MDIO_START | GSW_MDIO_READ |
- (phy_reg << GSW_MDIO_REG_SHIFT) |
- (phy_addr << GSW_MDIO_ADDR_SHIFT),
- MT7620_GSW_REG_PIAC);
-
- if (mt7620_mii_busy_wait(gsw))
- return 0xffff;
-
- d = mtk_switch_r32(gsw, MT7620_GSW_REG_PIAC) & 0xffff;
-
- return d;
-}
-EXPORT_SYMBOL_GPL(_mt7620_mii_read);
-
-int mt7620_mdio_write(struct mii_bus *bus, int phy_addr, int phy_reg, u16 val)
-{
- struct mtk_eth *eth = bus->priv;
- struct mt7620_gsw *gsw = (struct mt7620_gsw *)eth->sw_priv;
-
- return _mt7620_mii_write(gsw, phy_addr, phy_reg, val);
-}
-
-int mt7620_mdio_read(struct mii_bus *bus, int phy_addr, int phy_reg)
-{
- struct mtk_eth *eth = bus->priv;
- struct mt7620_gsw *gsw = (struct mt7620_gsw *)eth->sw_priv;
-
- return _mt7620_mii_read(gsw, phy_addr, phy_reg);
-}
-
-void mt7530_mdio_w32(struct mt7620_gsw *gsw, u32 reg, u32 val)
-{
- _mt7620_mii_write(gsw, 0x1f, 0x1f, (reg >> 6) & 0x3ff);
- _mt7620_mii_write(gsw, 0x1f, (reg >> 2) & 0xf, val & 0xffff);
- _mt7620_mii_write(gsw, 0x1f, 0x10, val >> 16);
-}
-EXPORT_SYMBOL_GPL(mt7530_mdio_w32);
-
-u32 mt7530_mdio_r32(struct mt7620_gsw *gsw, u32 reg)
-{
- u16 high, low;
-
- _mt7620_mii_write(gsw, 0x1f, 0x1f, (reg >> 6) & 0x3ff);
- low = _mt7620_mii_read(gsw, 0x1f, (reg >> 2) & 0xf);
- high = _mt7620_mii_read(gsw, 0x1f, 0x10);
-
- return (high << 16) | (low & 0xffff);
-}
-EXPORT_SYMBOL_GPL(mt7530_mdio_r32);
-
-void mt7530_mdio_m32(struct mt7620_gsw *gsw, u32 mask, u32 set, u32 reg)
-{
- u32 val = mt7530_mdio_r32(gsw, reg);
-
- val &= ~mask;
- val |= set;
- mt7530_mdio_w32(gsw, reg, val);
-}
-EXPORT_SYMBOL_GPL(mt7530_mdio_m32);
-
-static unsigned char *mtk_speed_str(int speed)
-{
- switch (speed) {
- case 2:
- case SPEED_1000:
- return "1000";
- case 1:
- case SPEED_100:
- return "100";
- case 0:
- case SPEED_10:
- return "10";
- }
-
- return "? ";
-}
-
-int mt7620_has_carrier(struct mtk_eth *eth)
-{
- struct mt7620_gsw *gsw = (struct mt7620_gsw *)eth->sw_priv;
- int i;
-
- for (i = 0; i < GSW_PORT6; i++)
- if (mt7530_mdio_r32(gsw, GSW_REG_PORT_STATUS(i)) & 0x1)
- return 1;
- return 0;
-}
-
-void mt7620_print_link_state(struct mtk_eth *eth, int port, int link,
- int speed, int duplex)
-{
- struct mt7620_gsw *gsw = eth->sw_priv;
-
- if (link)
- dev_info(gsw->dev, "port %d link up (%sMbps/%s duplex)\n",
- port, mtk_speed_str(speed),
- (duplex) ? "Full" : "Half");
- else
- dev_info(gsw->dev, "port %d link down\n", port);
-}
-
-void mt7620_mdio_link_adjust(struct mtk_eth *eth, int port)
-{
- mt7620_print_link_state(eth, port, eth->link[port],
- eth->phy->speed[port],
- (eth->phy->duplex[port] == DUPLEX_FULL));
-}
+++ /dev/null
-/* This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * Copyright (C) 2009-2016 John Crispin <blogic@openwrt.org>
- * Copyright (C) 2009-2016 Felix Fietkau <nbd@openwrt.org>
- * Copyright (C) 2013-2016 Michael Lee <igvtee@gmail.com>
- */
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/dma-mapping.h>
-#include <linux/init.h>
-#include <linux/skbuff.h>
-#include <linux/etherdevice.h>
-#include <linux/ethtool.h>
-#include <linux/platform_device.h>
-#include <linux/of_device.h>
-#include <linux/mfd/syscon.h>
-#include <linux/clk.h>
-#include <linux/of_net.h>
-#include <linux/of_mdio.h>
-#include <linux/if_vlan.h>
-#include <linux/reset.h>
-#include <linux/tcp.h>
-#include <linux/io.h>
-#include <linux/bug.h>
-#include <linux/regmap.h>
-
-#include "mtk_eth_soc.h"
-#include "mdio.h"
-#include "ethtool.h"
-
-#define MAX_RX_LENGTH 1536
-#define MTK_RX_ETH_HLEN (VLAN_ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN)
-#define MTK_RX_HLEN (NET_SKB_PAD + MTK_RX_ETH_HLEN + NET_IP_ALIGN)
-#define DMA_DUMMY_DESC 0xffffffff
-#define MTK_DEFAULT_MSG_ENABLE \
- (NETIF_MSG_DRV | \
- NETIF_MSG_PROBE | \
- NETIF_MSG_LINK | \
- NETIF_MSG_TIMER | \
- NETIF_MSG_IFDOWN | \
- NETIF_MSG_IFUP | \
- NETIF_MSG_RX_ERR | \
- NETIF_MSG_TX_ERR)
-
-#define TX_DMA_DESP2_DEF (TX_DMA_LS0 | TX_DMA_DONE)
-#define NEXT_TX_DESP_IDX(X) (((X) + 1) & (ring->tx_ring_size - 1))
-#define NEXT_RX_DESP_IDX(X) (((X) + 1) & (ring->rx_ring_size - 1))
-
-#define SYSC_REG_RSTCTRL 0x34
-
-static int mtk_msg_level = -1;
-module_param_named(msg_level, mtk_msg_level, int, 0);
-MODULE_PARM_DESC(msg_level, "Message level (-1=defaults,0=none,...,16=all)");
-
-static const u16 mtk_reg_table_default[MTK_REG_COUNT] = {
- [MTK_REG_PDMA_GLO_CFG] = MTK_PDMA_GLO_CFG,
- [MTK_REG_PDMA_RST_CFG] = MTK_PDMA_RST_CFG,
- [MTK_REG_DLY_INT_CFG] = MTK_DLY_INT_CFG,
- [MTK_REG_TX_BASE_PTR0] = MTK_TX_BASE_PTR0,
- [MTK_REG_TX_MAX_CNT0] = MTK_TX_MAX_CNT0,
- [MTK_REG_TX_CTX_IDX0] = MTK_TX_CTX_IDX0,
- [MTK_REG_TX_DTX_IDX0] = MTK_TX_DTX_IDX0,
- [MTK_REG_RX_BASE_PTR0] = MTK_RX_BASE_PTR0,
- [MTK_REG_RX_MAX_CNT0] = MTK_RX_MAX_CNT0,
- [MTK_REG_RX_CALC_IDX0] = MTK_RX_CALC_IDX0,
- [MTK_REG_RX_DRX_IDX0] = MTK_RX_DRX_IDX0,
- [MTK_REG_MTK_INT_ENABLE] = MTK_INT_ENABLE,
- [MTK_REG_MTK_INT_STATUS] = MTK_INT_STATUS,
- [MTK_REG_MTK_DMA_VID_BASE] = MTK_DMA_VID0,
- [MTK_REG_MTK_COUNTER_BASE] = MTK_GDMA1_TX_GBCNT,
- [MTK_REG_MTK_RST_GL] = MTK_RST_GL,
-};
-
-static const u16 *mtk_reg_table = mtk_reg_table_default;
-
-void mtk_w32(struct mtk_eth *eth, u32 val, unsigned int reg)
-{
- __raw_writel(val, eth->base + reg);
-}
-
-u32 mtk_r32(struct mtk_eth *eth, unsigned int reg)
-{
- return __raw_readl(eth->base + reg);
-}
-
-static void mtk_reg_w32(struct mtk_eth *eth, u32 val, enum mtk_reg reg)
-{
- mtk_w32(eth, val, mtk_reg_table[reg]);
-}
-
-static u32 mtk_reg_r32(struct mtk_eth *eth, enum mtk_reg reg)
-{
- return mtk_r32(eth, mtk_reg_table[reg]);
-}
-
-/* these bits are also exposed via the reset-controller API. however the switch
- * and FE need to be brought out of reset in the exakt same moemtn and the
- * reset-controller api does not provide this feature yet. Do the reset manually
- * until we fixed the reset-controller api to be able to do this
- */
-void mtk_reset(struct mtk_eth *eth, u32 reset_bits)
-{
- u32 val;
-
- regmap_read(eth->ethsys, SYSC_REG_RSTCTRL, &val);
- val |= reset_bits;
- regmap_write(eth->ethsys, SYSC_REG_RSTCTRL, val);
- usleep_range(10, 20);
- val &= ~reset_bits;
- regmap_write(eth->ethsys, SYSC_REG_RSTCTRL, val);
- usleep_range(10, 20);
-}
-EXPORT_SYMBOL(mtk_reset);
-
-static inline void mtk_irq_ack(struct mtk_eth *eth, u32 mask)
-{
- if (eth->soc->dma_type & MTK_PDMA)
- mtk_reg_w32(eth, mask, MTK_REG_MTK_INT_STATUS);
- if (eth->soc->dma_type & MTK_QDMA)
- mtk_w32(eth, mask, MTK_QMTK_INT_STATUS);
-}
-
-static inline u32 mtk_irq_pending(struct mtk_eth *eth)
-{
- u32 status = 0;
-
- if (eth->soc->dma_type & MTK_PDMA)
- status |= mtk_reg_r32(eth, MTK_REG_MTK_INT_STATUS);
- if (eth->soc->dma_type & MTK_QDMA)
- status |= mtk_r32(eth, MTK_QMTK_INT_STATUS);
-
- return status;
-}
-
-static void mtk_irq_ack_status(struct mtk_eth *eth, u32 mask)
-{
- u32 status_reg = MTK_REG_MTK_INT_STATUS;
-
- if (mtk_reg_table[MTK_REG_MTK_INT_STATUS2])
- status_reg = MTK_REG_MTK_INT_STATUS2;
-
- mtk_reg_w32(eth, mask, status_reg);
-}
-
-static u32 mtk_irq_pending_status(struct mtk_eth *eth)
-{
- u32 status_reg = MTK_REG_MTK_INT_STATUS;
-
- if (mtk_reg_table[MTK_REG_MTK_INT_STATUS2])
- status_reg = MTK_REG_MTK_INT_STATUS2;
-
- return mtk_reg_r32(eth, status_reg);
-}
-
-static inline void mtk_irq_disable(struct mtk_eth *eth, u32 mask)
-{
- u32 val;
-
- if (eth->soc->dma_type & MTK_PDMA) {
- val = mtk_reg_r32(eth, MTK_REG_MTK_INT_ENABLE);
- mtk_reg_w32(eth, val & ~mask, MTK_REG_MTK_INT_ENABLE);
- /* flush write */
- mtk_reg_r32(eth, MTK_REG_MTK_INT_ENABLE);
- }
- if (eth->soc->dma_type & MTK_QDMA) {
- val = mtk_r32(eth, MTK_QMTK_INT_ENABLE);
- mtk_w32(eth, val & ~mask, MTK_QMTK_INT_ENABLE);
- /* flush write */
- mtk_r32(eth, MTK_QMTK_INT_ENABLE);
- }
-}
-
-static inline void mtk_irq_enable(struct mtk_eth *eth, u32 mask)
-{
- u32 val;
-
- if (eth->soc->dma_type & MTK_PDMA) {
- val = mtk_reg_r32(eth, MTK_REG_MTK_INT_ENABLE);
- mtk_reg_w32(eth, val | mask, MTK_REG_MTK_INT_ENABLE);
- /* flush write */
- mtk_reg_r32(eth, MTK_REG_MTK_INT_ENABLE);
- }
- if (eth->soc->dma_type & MTK_QDMA) {
- val = mtk_r32(eth, MTK_QMTK_INT_ENABLE);
- mtk_w32(eth, val | mask, MTK_QMTK_INT_ENABLE);
- /* flush write */
- mtk_r32(eth, MTK_QMTK_INT_ENABLE);
- }
-}
-
-static inline u32 mtk_irq_enabled(struct mtk_eth *eth)
-{
- u32 enabled = 0;
-
- if (eth->soc->dma_type & MTK_PDMA)
- enabled |= mtk_reg_r32(eth, MTK_REG_MTK_INT_ENABLE);
- if (eth->soc->dma_type & MTK_QDMA)
- enabled |= mtk_r32(eth, MTK_QMTK_INT_ENABLE);
-
- return enabled;
-}
-
-static inline void mtk_hw_set_macaddr(struct mtk_mac *mac,
- unsigned char *macaddr)
-{
- unsigned long flags;
-
- spin_lock_irqsave(&mac->hw->page_lock, flags);
- mtk_w32(mac->hw, (macaddr[0] << 8) | macaddr[1], MTK_GDMA1_MAC_ADRH);
- mtk_w32(mac->hw, (macaddr[2] << 24) | (macaddr[3] << 16) |
- (macaddr[4] << 8) | macaddr[5],
- MTK_GDMA1_MAC_ADRL);
- spin_unlock_irqrestore(&mac->hw->page_lock, flags);
-}
-
-static int mtk_set_mac_address(struct net_device *dev, void *p)
-{
- int ret = eth_mac_addr(dev, p);
- struct mtk_mac *mac = netdev_priv(dev);
- struct mtk_eth *eth = mac->hw;
-
- if (ret)
- return ret;
-
- if (eth->soc->set_mac)
- eth->soc->set_mac(mac, dev->dev_addr);
- else
- mtk_hw_set_macaddr(mac, p);
-
- return 0;
-}
-
-static inline int mtk_max_frag_size(int mtu)
-{
- /* make sure buf_size will be at least MAX_RX_LENGTH */
- if (mtu + MTK_RX_ETH_HLEN < MAX_RX_LENGTH)
- mtu = MAX_RX_LENGTH - MTK_RX_ETH_HLEN;
-
- return SKB_DATA_ALIGN(MTK_RX_HLEN + mtu) +
- SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
-}
-
-static inline int mtk_max_buf_size(int frag_size)
-{
- int buf_size = frag_size - NET_SKB_PAD - NET_IP_ALIGN -
- SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
-
- WARN_ON(buf_size < MAX_RX_LENGTH);
-
- return buf_size;
-}
-
-static inline void mtk_get_rxd(struct mtk_rx_dma *rxd,
- struct mtk_rx_dma *dma_rxd)
-{
- rxd->rxd1 = READ_ONCE(dma_rxd->rxd1);
- rxd->rxd2 = READ_ONCE(dma_rxd->rxd2);
- rxd->rxd3 = READ_ONCE(dma_rxd->rxd3);
- rxd->rxd4 = READ_ONCE(dma_rxd->rxd4);
-}
-
-static inline void mtk_set_txd_pdma(struct mtk_tx_dma *txd,
- struct mtk_tx_dma *dma_txd)
-{
- WRITE_ONCE(dma_txd->txd1, txd->txd1);
- WRITE_ONCE(dma_txd->txd3, txd->txd3);
- WRITE_ONCE(dma_txd->txd4, txd->txd4);
- /* clean dma done flag last */
- WRITE_ONCE(dma_txd->txd2, txd->txd2);
-}
-
-static void mtk_clean_rx(struct mtk_eth *eth, struct mtk_rx_ring *ring)
-{
- int i;
-
- if (ring->rx_data && ring->rx_dma) {
- for (i = 0; i < ring->rx_ring_size; i++) {
- if (!ring->rx_data[i])
- continue;
- if (!ring->rx_dma[i].rxd1)
- continue;
- dma_unmap_single(eth->dev,
- ring->rx_dma[i].rxd1,
- ring->rx_buf_size,
- DMA_FROM_DEVICE);
- skb_free_frag(ring->rx_data[i]);
- }
- kfree(ring->rx_data);
- ring->rx_data = NULL;
- }
-
- if (ring->rx_dma) {
- dma_free_coherent(eth->dev,
- ring->rx_ring_size * sizeof(*ring->rx_dma),
- ring->rx_dma,
- ring->rx_phys);
- ring->rx_dma = NULL;
- }
-}
-
-static int mtk_dma_rx_alloc(struct mtk_eth *eth, struct mtk_rx_ring *ring)
-{
- int i, pad = 0;
-
- ring->frag_size = mtk_max_frag_size(ETH_DATA_LEN);
- ring->rx_buf_size = mtk_max_buf_size(ring->frag_size);
- ring->rx_ring_size = eth->soc->dma_ring_size;
- ring->rx_data = kcalloc(ring->rx_ring_size, sizeof(*ring->rx_data),
- GFP_KERNEL);
- if (!ring->rx_data)
- goto no_rx_mem;
-
- for (i = 0; i < ring->rx_ring_size; i++) {
- ring->rx_data[i] = netdev_alloc_frag(ring->frag_size);
- if (!ring->rx_data[i])
- goto no_rx_mem;
- }
-
- ring->rx_dma =
- dma_alloc_coherent(eth->dev,
- ring->rx_ring_size * sizeof(*ring->rx_dma),
- &ring->rx_phys, GFP_ATOMIC | __GFP_ZERO);
- if (!ring->rx_dma)
- goto no_rx_mem;
-
- if (!eth->soc->rx_2b_offset)
- pad = NET_IP_ALIGN;
-
- for (i = 0; i < ring->rx_ring_size; i++) {
- dma_addr_t dma_addr = dma_map_single(eth->dev,
- ring->rx_data[i] + NET_SKB_PAD + pad,
- ring->rx_buf_size,
- DMA_FROM_DEVICE);
- if (unlikely(dma_mapping_error(eth->dev, dma_addr)))
- goto no_rx_mem;
- ring->rx_dma[i].rxd1 = (unsigned int)dma_addr;
-
- if (eth->soc->rx_sg_dma)
- ring->rx_dma[i].rxd2 = RX_DMA_PLEN0(ring->rx_buf_size);
- else
- ring->rx_dma[i].rxd2 = RX_DMA_LSO;
- }
- ring->rx_calc_idx = ring->rx_ring_size - 1;
- /* make sure that all changes to the dma ring are flushed before we
- * continue
- */
- wmb();
-
- return 0;
-
-no_rx_mem:
- return -ENOMEM;
-}
-
-static void mtk_txd_unmap(struct device *dev, struct mtk_tx_buf *tx_buf)
-{
- if (tx_buf->flags & MTK_TX_FLAGS_SINGLE0) {
- dma_unmap_single(dev,
- dma_unmap_addr(tx_buf, dma_addr0),
- dma_unmap_len(tx_buf, dma_len0),
- DMA_TO_DEVICE);
- } else if (tx_buf->flags & MTK_TX_FLAGS_PAGE0) {
- dma_unmap_page(dev,
- dma_unmap_addr(tx_buf, dma_addr0),
- dma_unmap_len(tx_buf, dma_len0),
- DMA_TO_DEVICE);
- }
- if (tx_buf->flags & MTK_TX_FLAGS_PAGE1)
- dma_unmap_page(dev,
- dma_unmap_addr(tx_buf, dma_addr1),
- dma_unmap_len(tx_buf, dma_len1),
- DMA_TO_DEVICE);
-
- tx_buf->flags = 0;
- if (tx_buf->skb && (tx_buf->skb != (struct sk_buff *)DMA_DUMMY_DESC))
- dev_kfree_skb_any(tx_buf->skb);
- tx_buf->skb = NULL;
-}
-
-static void mtk_pdma_tx_clean(struct mtk_eth *eth)
-{
- struct mtk_tx_ring *ring = ð->tx_ring;
- int i;
-
- if (ring->tx_buf) {
- for (i = 0; i < ring->tx_ring_size; i++)
- mtk_txd_unmap(eth->dev, &ring->tx_buf[i]);
- kfree(ring->tx_buf);
- ring->tx_buf = NULL;
- }
-
- if (ring->tx_dma) {
- dma_free_coherent(eth->dev,
- ring->tx_ring_size * sizeof(*ring->tx_dma),
- ring->tx_dma,
- ring->tx_phys);
- ring->tx_dma = NULL;
- }
-}
-
-static void mtk_qdma_tx_clean(struct mtk_eth *eth)
-{
- struct mtk_tx_ring *ring = ð->tx_ring;
- int i;
-
- if (ring->tx_buf) {
- for (i = 0; i < ring->tx_ring_size; i++)
- mtk_txd_unmap(eth->dev, &ring->tx_buf[i]);
- kfree(ring->tx_buf);
- ring->tx_buf = NULL;
- }
-
- if (ring->tx_dma) {
- dma_free_coherent(eth->dev,
- ring->tx_ring_size * sizeof(*ring->tx_dma),
- ring->tx_dma,
- ring->tx_phys);
- ring->tx_dma = NULL;
- }
-}
-
-void mtk_stats_update_mac(struct mtk_mac *mac)
-{
- struct mtk_hw_stats *hw_stats = mac->hw_stats;
- unsigned int base = mtk_reg_table[MTK_REG_MTK_COUNTER_BASE];
- u64 stats;
-
- base += hw_stats->reg_offset;
-
- u64_stats_update_begin(&hw_stats->syncp);
-
- if (mac->hw->soc->new_stats) {
- hw_stats->rx_bytes += mtk_r32(mac->hw, base);
- stats = mtk_r32(mac->hw, base + 0x04);
- if (stats)
- hw_stats->rx_bytes += (stats << 32);
- hw_stats->rx_packets += mtk_r32(mac->hw, base + 0x08);
- hw_stats->rx_overflow += mtk_r32(mac->hw, base + 0x10);
- hw_stats->rx_fcs_errors += mtk_r32(mac->hw, base + 0x14);
- hw_stats->rx_short_errors += mtk_r32(mac->hw, base + 0x18);
- hw_stats->rx_long_errors += mtk_r32(mac->hw, base + 0x1c);
- hw_stats->rx_checksum_errors += mtk_r32(mac->hw, base + 0x20);
- hw_stats->rx_flow_control_packets +=
- mtk_r32(mac->hw, base + 0x24);
- hw_stats->tx_skip += mtk_r32(mac->hw, base + 0x28);
- hw_stats->tx_collisions += mtk_r32(mac->hw, base + 0x2c);
- hw_stats->tx_bytes += mtk_r32(mac->hw, base + 0x30);
- stats = mtk_r32(mac->hw, base + 0x34);
- if (stats)
- hw_stats->tx_bytes += (stats << 32);
- hw_stats->tx_packets += mtk_r32(mac->hw, base + 0x38);
- } else {
- hw_stats->tx_bytes += mtk_r32(mac->hw, base);
- hw_stats->tx_packets += mtk_r32(mac->hw, base + 0x04);
- hw_stats->tx_skip += mtk_r32(mac->hw, base + 0x08);
- hw_stats->tx_collisions += mtk_r32(mac->hw, base + 0x0c);
- hw_stats->rx_bytes += mtk_r32(mac->hw, base + 0x20);
- hw_stats->rx_packets += mtk_r32(mac->hw, base + 0x24);
- hw_stats->rx_overflow += mtk_r32(mac->hw, base + 0x28);
- hw_stats->rx_fcs_errors += mtk_r32(mac->hw, base + 0x2c);
- hw_stats->rx_short_errors += mtk_r32(mac->hw, base + 0x30);
- hw_stats->rx_long_errors += mtk_r32(mac->hw, base + 0x34);
- hw_stats->rx_checksum_errors += mtk_r32(mac->hw, base + 0x38);
- hw_stats->rx_flow_control_packets +=
- mtk_r32(mac->hw, base + 0x3c);
- }
-
- u64_stats_update_end(&hw_stats->syncp);
-}
-
-static void mtk_get_stats64(struct net_device *dev,
- struct rtnl_link_stats64 *storage)
-{
- struct mtk_mac *mac = netdev_priv(dev);
- struct mtk_hw_stats *hw_stats = mac->hw_stats;
- unsigned int base = mtk_reg_table[MTK_REG_MTK_COUNTER_BASE];
- unsigned int start;
-
- if (!base) {
- netdev_stats_to_stats64(storage, &dev->stats);
- return;
- }
-
- if (netif_running(dev) && netif_device_present(dev)) {
- if (spin_trylock(&hw_stats->stats_lock)) {
- mtk_stats_update_mac(mac);
- spin_unlock(&hw_stats->stats_lock);
- }
- }
-
- do {
- start = u64_stats_fetch_begin_irq(&hw_stats->syncp);
- storage->rx_packets = hw_stats->rx_packets;
- storage->tx_packets = hw_stats->tx_packets;
- storage->rx_bytes = hw_stats->rx_bytes;
- storage->tx_bytes = hw_stats->tx_bytes;
- storage->collisions = hw_stats->tx_collisions;
- storage->rx_length_errors = hw_stats->rx_short_errors +
- hw_stats->rx_long_errors;
- storage->rx_over_errors = hw_stats->rx_overflow;
- storage->rx_crc_errors = hw_stats->rx_fcs_errors;
- storage->rx_errors = hw_stats->rx_checksum_errors;
- storage->tx_aborted_errors = hw_stats->tx_skip;
- } while (u64_stats_fetch_retry_irq(&hw_stats->syncp, start));
-
- storage->tx_errors = dev->stats.tx_errors;
- storage->rx_dropped = dev->stats.rx_dropped;
- storage->tx_dropped = dev->stats.tx_dropped;
-}
-
-static int mtk_vlan_rx_add_vid(struct net_device *dev,
- __be16 proto, u16 vid)
-{
- struct mtk_mac *mac = netdev_priv(dev);
- struct mtk_eth *eth = mac->hw;
- u32 idx = (vid & 0xf);
- u32 vlan_cfg;
-
- if (!((mtk_reg_table[MTK_REG_MTK_DMA_VID_BASE]) &&
- (dev->features & NETIF_F_HW_VLAN_CTAG_TX)))
- return 0;
-
- if (test_bit(idx, ð->vlan_map)) {
- netdev_warn(dev, "disable tx vlan offload\n");
- dev->wanted_features &= ~NETIF_F_HW_VLAN_CTAG_TX;
- netdev_update_features(dev);
- } else {
- vlan_cfg = mtk_r32(eth,
- mtk_reg_table[MTK_REG_MTK_DMA_VID_BASE] +
- ((idx >> 1) << 2));
- if (idx & 0x1) {
- vlan_cfg &= 0xffff;
- vlan_cfg |= (vid << 16);
- } else {
- vlan_cfg &= 0xffff0000;
- vlan_cfg |= vid;
- }
- mtk_w32(eth,
- vlan_cfg, mtk_reg_table[MTK_REG_MTK_DMA_VID_BASE] +
- ((idx >> 1) << 2));
- set_bit(idx, ð->vlan_map);
- }
-
- return 0;
-}
-
-static int mtk_vlan_rx_kill_vid(struct net_device *dev,
- __be16 proto, u16 vid)
-{
- struct mtk_mac *mac = netdev_priv(dev);
- struct mtk_eth *eth = mac->hw;
- u32 idx = (vid & 0xf);
-
- if (!((mtk_reg_table[MTK_REG_MTK_DMA_VID_BASE]) &&
- (dev->features & NETIF_F_HW_VLAN_CTAG_TX)))
- return 0;
-
- clear_bit(idx, ð->vlan_map);
-
- return 0;
-}
-
-static inline u32 mtk_pdma_empty_txd(struct mtk_tx_ring *ring)
-{
- barrier();
- return (u32)(ring->tx_ring_size -
- ((ring->tx_next_idx - ring->tx_free_idx) &
- (ring->tx_ring_size - 1)));
-}
-
-static int mtk_skb_padto(struct sk_buff *skb, struct mtk_eth *eth)
-{
- unsigned int len;
- int ret;
-
- if (unlikely(skb->len >= VLAN_ETH_ZLEN))
- return 0;
-
- if (eth->soc->padding_64b && !eth->soc->padding_bug)
- return 0;
-
- if (skb_vlan_tag_present(skb))
- len = ETH_ZLEN;
- else if (skb->protocol == cpu_to_be16(ETH_P_8021Q))
- len = VLAN_ETH_ZLEN;
- else if (!eth->soc->padding_64b)
- len = ETH_ZLEN;
- else
- return 0;
-
- if (skb->len >= len)
- return 0;
-
- ret = skb_pad(skb, len - skb->len);
- if (ret < 0)
- return ret;
- skb->len = len;
- skb_set_tail_pointer(skb, len);
-
- return ret;
-}
-
-static int mtk_pdma_tx_map(struct sk_buff *skb, struct net_device *dev,
- int tx_num, struct mtk_tx_ring *ring, bool gso)
-{
- struct mtk_mac *mac = netdev_priv(dev);
- struct mtk_eth *eth = mac->hw;
- struct skb_frag_struct *frag;
- struct mtk_tx_dma txd, *ptxd;
- struct mtk_tx_buf *tx_buf;
- int i, j, k, frag_size, frag_map_size, offset;
- dma_addr_t mapped_addr;
- unsigned int nr_frags;
- u32 def_txd4;
-
- if (mtk_skb_padto(skb, eth)) {
- netif_warn(eth, tx_err, dev, "tx padding failed!\n");
- return -1;
- }
-
- tx_buf = &ring->tx_buf[ring->tx_next_idx];
- memset(tx_buf, 0, sizeof(*tx_buf));
- memset(&txd, 0, sizeof(txd));
- nr_frags = skb_shinfo(skb)->nr_frags;
-
- /* init tx descriptor */
- def_txd4 = eth->soc->txd4;
- txd.txd4 = def_txd4;
-
- if (eth->soc->mac_count > 1)
- txd.txd4 |= (mac->id + 1) << TX_DMA_FPORT_SHIFT;
-
- if (gso)
- txd.txd4 |= TX_DMA_TSO;
-
- /* TX Checksum offload */
- if (skb->ip_summed == CHECKSUM_PARTIAL)
- txd.txd4 |= TX_DMA_CHKSUM;
-
- /* VLAN header offload */
- if (skb_vlan_tag_present(skb)) {
- u16 tag = skb_vlan_tag_get(skb);
-
- txd.txd4 |= TX_DMA_INS_VLAN |
- ((tag >> VLAN_PRIO_SHIFT) << 4) |
- (tag & 0xF);
- }
-
- mapped_addr = dma_map_single(&dev->dev, skb->data,
- skb_headlen(skb), DMA_TO_DEVICE);
- if (unlikely(dma_mapping_error(&dev->dev, mapped_addr)))
- return -1;
-
- txd.txd1 = mapped_addr;
- txd.txd2 = TX_DMA_PLEN0(skb_headlen(skb));
-
- tx_buf->flags |= MTK_TX_FLAGS_SINGLE0;
- dma_unmap_addr_set(tx_buf, dma_addr0, mapped_addr);
- dma_unmap_len_set(tx_buf, dma_len0, skb_headlen(skb));
-
- /* TX SG offload */
- j = ring->tx_next_idx;
- k = 0;
- for (i = 0; i < nr_frags; i++) {
- offset = 0;
- frag = &skb_shinfo(skb)->frags[i];
- frag_size = skb_frag_size(frag);
-
- while (frag_size > 0) {
- frag_map_size = min(frag_size, TX_DMA_BUF_LEN);
- mapped_addr = skb_frag_dma_map(&dev->dev, frag, offset,
- frag_map_size,
- DMA_TO_DEVICE);
- if (unlikely(dma_mapping_error(&dev->dev, mapped_addr)))
- goto err_dma;
-
- if (k & 0x1) {
- j = NEXT_TX_DESP_IDX(j);
- txd.txd1 = mapped_addr;
- txd.txd2 = TX_DMA_PLEN0(frag_map_size);
- txd.txd4 = def_txd4;
-
- tx_buf = &ring->tx_buf[j];
- memset(tx_buf, 0, sizeof(*tx_buf));
-
- tx_buf->flags |= MTK_TX_FLAGS_PAGE0;
- dma_unmap_addr_set(tx_buf, dma_addr0,
- mapped_addr);
- dma_unmap_len_set(tx_buf, dma_len0,
- frag_map_size);
- } else {
- txd.txd3 = mapped_addr;
- txd.txd2 |= TX_DMA_PLEN1(frag_map_size);
-
- tx_buf->skb = (struct sk_buff *)DMA_DUMMY_DESC;
- tx_buf->flags |= MTK_TX_FLAGS_PAGE1;
- dma_unmap_addr_set(tx_buf, dma_addr1,
- mapped_addr);
- dma_unmap_len_set(tx_buf, dma_len1,
- frag_map_size);
-
- if (!((i == (nr_frags - 1)) &&
- (frag_map_size == frag_size))) {
- mtk_set_txd_pdma(&txd,
- &ring->tx_dma[j]);
- memset(&txd, 0, sizeof(txd));
- }
- }
- frag_size -= frag_map_size;
- offset += frag_map_size;
- k++;
- }
- }
-
- /* set last segment */
- if (k & 0x1)
- txd.txd2 |= TX_DMA_LS1;
- else
- txd.txd2 |= TX_DMA_LS0;
- mtk_set_txd_pdma(&txd, &ring->tx_dma[j]);
-
- /* store skb to cleanup */
- tx_buf->skb = skb;
-
- netdev_sent_queue(dev, skb->len);
- skb_tx_timestamp(skb);
-
- ring->tx_next_idx = NEXT_TX_DESP_IDX(j);
- /* make sure that all changes to the dma ring are flushed before we
- * continue
- */
- wmb();
- atomic_set(&ring->tx_free_count, mtk_pdma_empty_txd(ring));
-
- if (netif_xmit_stopped(netdev_get_tx_queue(dev, 0)) || !skb->xmit_more)
- mtk_reg_w32(eth, ring->tx_next_idx, MTK_REG_TX_CTX_IDX0);
-
- return 0;
-
-err_dma:
- j = ring->tx_next_idx;
- for (i = 0; i < tx_num; i++) {
- ptxd = &ring->tx_dma[j];
- tx_buf = &ring->tx_buf[j];
-
- /* unmap dma */
- mtk_txd_unmap(&dev->dev, tx_buf);
-
- ptxd->txd2 = TX_DMA_DESP2_DEF;
- j = NEXT_TX_DESP_IDX(j);
- }
- /* make sure that all changes to the dma ring are flushed before we
- * continue
- */
- wmb();
- return -1;
-}
-
-/* the qdma core needs scratch memory to be setup */
-static int mtk_init_fq_dma(struct mtk_eth *eth)
-{
- dma_addr_t dma_addr, phy_ring_head, phy_ring_tail;
- int cnt = eth->soc->dma_ring_size;
- int i;
-
- eth->scratch_ring = dma_alloc_coherent(eth->dev,
- cnt * sizeof(struct mtk_tx_dma),
- &phy_ring_head,
- GFP_ATOMIC | __GFP_ZERO);
- if (unlikely(!eth->scratch_ring))
- return -ENOMEM;
-
- eth->scratch_head = kcalloc(cnt, QDMA_PAGE_SIZE,
- GFP_KERNEL);
- dma_addr = dma_map_single(eth->dev,
- eth->scratch_head, cnt * QDMA_PAGE_SIZE,
- DMA_FROM_DEVICE);
- if (unlikely(dma_mapping_error(eth->dev, dma_addr)))
- return -ENOMEM;
-
- memset(eth->scratch_ring, 0x0, sizeof(struct mtk_tx_dma) * cnt);
- phy_ring_tail = phy_ring_head + (sizeof(struct mtk_tx_dma) * (cnt - 1));
-
- for (i = 0; i < cnt; i++) {
- eth->scratch_ring[i].txd1 = (dma_addr + (i * QDMA_PAGE_SIZE));
- if (i < cnt - 1)
- eth->scratch_ring[i].txd2 = (phy_ring_head +
- ((i + 1) * sizeof(struct mtk_tx_dma)));
- eth->scratch_ring[i].txd3 = TX_QDMA_SDL(QDMA_PAGE_SIZE);
- }
-
- mtk_w32(eth, phy_ring_head, MTK_QDMA_FQ_HEAD);
- mtk_w32(eth, phy_ring_tail, MTK_QDMA_FQ_TAIL);
- mtk_w32(eth, (cnt << 16) | cnt, MTK_QDMA_FQ_CNT);
- mtk_w32(eth, QDMA_PAGE_SIZE << 16, MTK_QDMA_FQ_BLEN);
-
- return 0;
-}
-
-static void *mtk_qdma_phys_to_virt(struct mtk_tx_ring *ring, u32 desc)
-{
- void *ret = ring->tx_dma;
-
- return ret + (desc - ring->tx_phys);
-}
-
-static struct mtk_tx_dma *mtk_tx_next_qdma(struct mtk_tx_ring *ring,
- struct mtk_tx_dma *txd)
-{
- return mtk_qdma_phys_to_virt(ring, txd->txd2);
-}
-
-static struct mtk_tx_buf *mtk_desc_to_tx_buf(struct mtk_tx_ring *ring,
- struct mtk_tx_dma *txd)
-{
- int idx = txd - ring->tx_dma;
-
- return &ring->tx_buf[idx];
-}
-
-static int mtk_qdma_tx_map(struct sk_buff *skb, struct net_device *dev,
- int tx_num, struct mtk_tx_ring *ring, bool gso)
-{
- struct mtk_mac *mac = netdev_priv(dev);
- struct mtk_eth *eth = mac->hw;
- struct mtk_tx_dma *itxd, *txd;
- struct mtk_tx_buf *tx_buf;
- dma_addr_t mapped_addr;
- unsigned int nr_frags;
- int i, n_desc = 1;
- u32 txd4 = eth->soc->txd4;
-
- itxd = ring->tx_next_free;
- if (itxd == ring->tx_last_free)
- return -ENOMEM;
-
- if (eth->soc->mac_count > 1)
- txd4 |= (mac->id + 1) << TX_DMA_FPORT_SHIFT;
-
- tx_buf = mtk_desc_to_tx_buf(ring, itxd);
- memset(tx_buf, 0, sizeof(*tx_buf));
-
- if (gso)
- txd4 |= TX_DMA_TSO;
-
- /* TX Checksum offload */
- if (skb->ip_summed == CHECKSUM_PARTIAL)
- txd4 |= TX_DMA_CHKSUM;
-
- /* VLAN header offload */
- if (skb_vlan_tag_present(skb))
- txd4 |= TX_DMA_INS_VLAN_MT7621 | skb_vlan_tag_get(skb);
-
- mapped_addr = dma_map_single(&dev->dev, skb->data,
- skb_headlen(skb), DMA_TO_DEVICE);
- if (unlikely(dma_mapping_error(&dev->dev, mapped_addr)))
- return -ENOMEM;
-
- WRITE_ONCE(itxd->txd1, mapped_addr);
- tx_buf->flags |= MTK_TX_FLAGS_SINGLE0;
- dma_unmap_addr_set(tx_buf, dma_addr0, mapped_addr);
- dma_unmap_len_set(tx_buf, dma_len0, skb_headlen(skb));
-
- /* TX SG offload */
- txd = itxd;
- nr_frags = skb_shinfo(skb)->nr_frags;
- for (i = 0; i < nr_frags; i++) {
- struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i];
- unsigned int offset = 0;
- int frag_size = skb_frag_size(frag);
-
- while (frag_size) {
- bool last_frag = false;
- unsigned int frag_map_size;
-
- txd = mtk_tx_next_qdma(ring, txd);
- if (txd == ring->tx_last_free)
- goto err_dma;
-
- n_desc++;
- frag_map_size = min(frag_size, TX_DMA_BUF_LEN);
- mapped_addr = skb_frag_dma_map(&dev->dev, frag, offset,
- frag_map_size,
- DMA_TO_DEVICE);
- if (unlikely(dma_mapping_error(&dev->dev, mapped_addr)))
- goto err_dma;
-
- if (i == nr_frags - 1 &&
- (frag_size - frag_map_size) == 0)
- last_frag = true;
-
- WRITE_ONCE(txd->txd1, mapped_addr);
- WRITE_ONCE(txd->txd3, (QDMA_TX_SWC |
- TX_DMA_PLEN0(frag_map_size) |
- last_frag * TX_DMA_LS0) |
- mac->id);
- WRITE_ONCE(txd->txd4, 0);
-
- tx_buf->skb = (struct sk_buff *)DMA_DUMMY_DESC;
- tx_buf = mtk_desc_to_tx_buf(ring, txd);
- memset(tx_buf, 0, sizeof(*tx_buf));
-
- tx_buf->flags |= MTK_TX_FLAGS_PAGE0;
- dma_unmap_addr_set(tx_buf, dma_addr0, mapped_addr);
- dma_unmap_len_set(tx_buf, dma_len0, frag_map_size);
- frag_size -= frag_map_size;
- offset += frag_map_size;
- }
- }
-
- /* store skb to cleanup */
- tx_buf->skb = skb;
-
- WRITE_ONCE(itxd->txd4, txd4);
- WRITE_ONCE(itxd->txd3, (QDMA_TX_SWC | TX_DMA_PLEN0(skb_headlen(skb)) |
- (!nr_frags * TX_DMA_LS0)));
-
- netdev_sent_queue(dev, skb->len);
- skb_tx_timestamp(skb);
-
- ring->tx_next_free = mtk_tx_next_qdma(ring, txd);
- atomic_sub(n_desc, &ring->tx_free_count);
-
- /* make sure that all changes to the dma ring are flushed before we
- * continue
- */
- wmb();
-
- if (netif_xmit_stopped(netdev_get_tx_queue(dev, 0)) || !skb->xmit_more)
- mtk_w32(eth, txd->txd2, MTK_QTX_CTX_PTR);
-
- return 0;
-
-err_dma:
- do {
- tx_buf = mtk_desc_to_tx_buf(ring, txd);
-
- /* unmap dma */
- mtk_txd_unmap(&dev->dev, tx_buf);
-
- itxd->txd3 = TX_DMA_DESP2_DEF;
- itxd = mtk_tx_next_qdma(ring, itxd);
- } while (itxd != txd);
-
- return -ENOMEM;
-}
-
-static inline int mtk_cal_txd_req(struct sk_buff *skb)
-{
- int i, nfrags;
- struct skb_frag_struct *frag;
-
- nfrags = 1;
- if (skb_is_gso(skb)) {
- for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
- frag = &skb_shinfo(skb)->frags[i];
- nfrags += DIV_ROUND_UP(frag->size, TX_DMA_BUF_LEN);
- }
- } else {
- nfrags += skb_shinfo(skb)->nr_frags;
- }
-
- return DIV_ROUND_UP(nfrags, 2);
-}
-
-static int mtk_start_xmit(struct sk_buff *skb, struct net_device *dev)
-{
- struct mtk_mac *mac = netdev_priv(dev);
- struct mtk_eth *eth = mac->hw;
- struct mtk_tx_ring *ring = ð->tx_ring;
- struct net_device_stats *stats = &dev->stats;
- int tx_num;
- int len = skb->len;
- bool gso = false;
-
- tx_num = mtk_cal_txd_req(skb);
- if (unlikely(atomic_read(&ring->tx_free_count) <= tx_num)) {
- netif_stop_queue(dev);
- netif_err(eth, tx_queued, dev,
- "Tx Ring full when queue awake!\n");
- return NETDEV_TX_BUSY;
- }
-
- /* TSO: fill MSS info in tcp checksum field */
- if (skb_is_gso(skb)) {
- if (skb_cow_head(skb, 0)) {
- netif_warn(eth, tx_err, dev,
- "GSO expand head fail.\n");
- goto drop;
- }
-
- if (skb_shinfo(skb)->gso_type &
- (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)) {
- gso = true;
- tcp_hdr(skb)->check = htons(skb_shinfo(skb)->gso_size);
- }
- }
-
- if (ring->tx_map(skb, dev, tx_num, ring, gso) < 0)
- goto drop;
-
- stats->tx_packets++;
- stats->tx_bytes += len;
-
- if (unlikely(atomic_read(&ring->tx_free_count) <= ring->tx_thresh)) {
- netif_stop_queue(dev);
- smp_mb();
- if (unlikely(atomic_read(&ring->tx_free_count) >
- ring->tx_thresh))
- netif_wake_queue(dev);
- }
-
- return NETDEV_TX_OK;
-
-drop:
- stats->tx_dropped++;
- dev_kfree_skb(skb);
- return NETDEV_TX_OK;
-}
-
-static int mtk_poll_rx(struct napi_struct *napi, int budget,
- struct mtk_eth *eth, u32 rx_intr)
-{
- struct mtk_soc_data *soc = eth->soc;
- struct mtk_rx_ring *ring = ð->rx_ring[0];
- int idx = ring->rx_calc_idx;
- u32 checksum_bit;
- struct sk_buff *skb;
- u8 *data, *new_data;
- struct mtk_rx_dma *rxd, trxd;
- int done = 0, pad;
-
- if (eth->soc->hw_features & NETIF_F_RXCSUM)
- checksum_bit = soc->checksum_bit;
- else
- checksum_bit = 0;
-
- if (eth->soc->rx_2b_offset)
- pad = 0;
- else
- pad = NET_IP_ALIGN;
-
- while (done < budget) {
- struct net_device *netdev;
- unsigned int pktlen;
- dma_addr_t dma_addr;
- int mac = 0;
-
- idx = NEXT_RX_DESP_IDX(idx);
- rxd = &ring->rx_dma[idx];
- data = ring->rx_data[idx];
-
- mtk_get_rxd(&trxd, rxd);
- if (!(trxd.rxd2 & RX_DMA_DONE))
- break;
-
- /* find out which mac the packet come from. values start at 1 */
- if (eth->soc->mac_count > 1) {
- mac = (trxd.rxd4 >> RX_DMA_FPORT_SHIFT) &
- RX_DMA_FPORT_MASK;
- mac--;
- if (mac < 0 || mac >= eth->soc->mac_count)
- goto release_desc;
- }
-
- netdev = eth->netdev[mac];
-
- /* alloc new buffer */
- new_data = napi_alloc_frag(ring->frag_size);
- if (unlikely(!new_data || !netdev)) {
- netdev->stats.rx_dropped++;
- goto release_desc;
- }
- dma_addr = dma_map_single(&netdev->dev,
- new_data + NET_SKB_PAD + pad,
- ring->rx_buf_size,
- DMA_FROM_DEVICE);
- if (unlikely(dma_mapping_error(&netdev->dev, dma_addr))) {
- skb_free_frag(new_data);
- goto release_desc;
- }
-
- /* receive data */
- skb = build_skb(data, ring->frag_size);
- if (unlikely(!skb)) {
- put_page(virt_to_head_page(new_data));
- goto release_desc;
- }
- skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
-
- dma_unmap_single(&netdev->dev, trxd.rxd1,
- ring->rx_buf_size, DMA_FROM_DEVICE);
- pktlen = RX_DMA_GET_PLEN0(trxd.rxd2);
- skb->dev = netdev;
- skb_put(skb, pktlen);
- if (trxd.rxd4 & checksum_bit)
- skb->ip_summed = CHECKSUM_UNNECESSARY;
- else
- skb_checksum_none_assert(skb);
- skb->protocol = eth_type_trans(skb, netdev);
-
- netdev->stats.rx_packets++;
- netdev->stats.rx_bytes += pktlen;
-
- if (netdev->features & NETIF_F_HW_VLAN_CTAG_RX &&
- RX_DMA_VID(trxd.rxd3))
- __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
- RX_DMA_VID(trxd.rxd3));
- napi_gro_receive(napi, skb);
-
- ring->rx_data[idx] = new_data;
- rxd->rxd1 = (unsigned int)dma_addr;
-
-release_desc:
- if (eth->soc->rx_sg_dma)
- rxd->rxd2 = RX_DMA_PLEN0(ring->rx_buf_size);
- else
- rxd->rxd2 = RX_DMA_LSO;
-
- ring->rx_calc_idx = idx;
- /* make sure that all changes to the dma ring are flushed before
- * we continue
- */
- wmb();
- if (eth->soc->dma_type == MTK_QDMA)
- mtk_w32(eth, ring->rx_calc_idx, MTK_QRX_CRX_IDX0);
- else
- mtk_reg_w32(eth, ring->rx_calc_idx,
- MTK_REG_RX_CALC_IDX0);
- done++;
- }
-
- if (done < budget)
- mtk_irq_ack(eth, rx_intr);
-
- return done;
-}
-
-static int mtk_pdma_tx_poll(struct mtk_eth *eth, int budget, bool *tx_again)
-{
- struct sk_buff *skb;
- struct mtk_tx_buf *tx_buf;
- int done = 0;
- u32 idx, hwidx;
- struct mtk_tx_ring *ring = ð->tx_ring;
- unsigned int bytes = 0;
-
- idx = ring->tx_free_idx;
- hwidx = mtk_reg_r32(eth, MTK_REG_TX_DTX_IDX0);
-
- while ((idx != hwidx) && budget) {
- tx_buf = &ring->tx_buf[idx];
- skb = tx_buf->skb;
-
- if (!skb)
- break;
-
- if (skb != (struct sk_buff *)DMA_DUMMY_DESC) {
- bytes += skb->len;
- done++;
- budget--;
- }
- mtk_txd_unmap(eth->dev, tx_buf);
- idx = NEXT_TX_DESP_IDX(idx);
- }
- ring->tx_free_idx = idx;
- atomic_set(&ring->tx_free_count, mtk_pdma_empty_txd(ring));
-
- /* read hw index again make sure no new tx packet */
- if (idx != hwidx || idx != mtk_reg_r32(eth, MTK_REG_TX_DTX_IDX0))
- *tx_again = 1;
-
- if (done)
- netdev_completed_queue(*eth->netdev, done, bytes);
-
- return done;
-}
-
-static int mtk_qdma_tx_poll(struct mtk_eth *eth, int budget, bool *tx_again)
-{
- struct mtk_tx_ring *ring = ð->tx_ring;
- struct mtk_tx_dma *desc;
- struct sk_buff *skb;
- struct mtk_tx_buf *tx_buf;
- int total = 0, done[MTK_MAX_DEVS];
- unsigned int bytes[MTK_MAX_DEVS];
- u32 cpu, dma;
- int i;
-
- memset(done, 0, sizeof(done));
- memset(bytes, 0, sizeof(bytes));
-
- cpu = mtk_r32(eth, MTK_QTX_CRX_PTR);
- dma = mtk_r32(eth, MTK_QTX_DRX_PTR);
-
- desc = mtk_qdma_phys_to_virt(ring, cpu);
-
- while ((cpu != dma) && budget) {
- u32 next_cpu = desc->txd2;
- int mac;
-
- desc = mtk_tx_next_qdma(ring, desc);
- if ((desc->txd3 & QDMA_TX_OWNER_CPU) == 0)
- break;
-
- mac = (desc->txd4 >> TX_DMA_FPORT_SHIFT) &
- TX_DMA_FPORT_MASK;
- mac--;
-
- tx_buf = mtk_desc_to_tx_buf(ring, desc);
- skb = tx_buf->skb;
- if (!skb)
- break;
-
- if (skb != (struct sk_buff *)DMA_DUMMY_DESC) {
- bytes[mac] += skb->len;
- done[mac]++;
- budget--;
- }
- mtk_txd_unmap(eth->dev, tx_buf);
-
- ring->tx_last_free->txd2 = next_cpu;
- ring->tx_last_free = desc;
- atomic_inc(&ring->tx_free_count);
-
- cpu = next_cpu;
- }
-
- mtk_w32(eth, cpu, MTK_QTX_CRX_PTR);
-
- /* read hw index again make sure no new tx packet */
- if (cpu != dma || cpu != mtk_r32(eth, MTK_QTX_DRX_PTR))
- *tx_again = true;
-
- for (i = 0; i < eth->soc->mac_count; i++) {
- if (!done[i])
- continue;
- netdev_completed_queue(eth->netdev[i], done[i], bytes[i]);
- total += done[i];
- }
-
- return total;
-}
-
-static int mtk_poll_tx(struct mtk_eth *eth, int budget, u32 tx_intr,
- bool *tx_again)
-{
- struct mtk_tx_ring *ring = ð->tx_ring;
- struct net_device *netdev = eth->netdev[0];
- int done;
-
- done = eth->tx_ring.tx_poll(eth, budget, tx_again);
- if (!*tx_again)
- mtk_irq_ack(eth, tx_intr);
-
- if (!done)
- return 0;
-
- smp_mb();
- if (unlikely(!netif_queue_stopped(netdev)))
- return done;
-
- if (atomic_read(&ring->tx_free_count) > ring->tx_thresh)
- netif_wake_queue(netdev);
-
- return done;
-}
-
-static void mtk_stats_update(struct mtk_eth *eth)
-{
- int i;
-
- for (i = 0; i < eth->soc->mac_count; i++) {
- if (!eth->mac[i] || !eth->mac[i]->hw_stats)
- continue;
- if (spin_trylock(ð->mac[i]->hw_stats->stats_lock)) {
- mtk_stats_update_mac(eth->mac[i]);
- spin_unlock(ð->mac[i]->hw_stats->stats_lock);
- }
- }
-}
-
-static int mtk_poll(struct napi_struct *napi, int budget)
-{
- struct mtk_eth *eth = container_of(napi, struct mtk_eth, rx_napi);
- u32 status, mtk_status, mask, tx_intr, rx_intr, status_intr;
- int tx_done, rx_done;
- bool tx_again = false;
-
- status = mtk_irq_pending(eth);
- mtk_status = mtk_irq_pending_status(eth);
- tx_intr = eth->soc->tx_int;
- rx_intr = eth->soc->rx_int;
- status_intr = eth->soc->status_int;
- tx_done = 0;
- rx_done = 0;
- tx_again = 0;
-
- if (status & tx_intr)
- tx_done = mtk_poll_tx(eth, budget, tx_intr, &tx_again);
-
- if (status & rx_intr)
- rx_done = mtk_poll_rx(napi, budget, eth, rx_intr);
-
- if (unlikely(mtk_status & status_intr)) {
- mtk_stats_update(eth);
- mtk_irq_ack_status(eth, status_intr);
- }
-
- if (unlikely(netif_msg_intr(eth))) {
- mask = mtk_irq_enabled(eth);
- netdev_info(eth->netdev[0],
- "done tx %d, rx %d, intr 0x%08x/0x%x\n",
- tx_done, rx_done, status, mask);
- }
-
- if (tx_again || rx_done == budget)
- return budget;
-
- status = mtk_irq_pending(eth);
- if (status & (tx_intr | rx_intr))
- return budget;
-
- napi_complete(napi);
- mtk_irq_enable(eth, tx_intr | rx_intr);
-
- return rx_done;
-}
-
-static int mtk_pdma_tx_alloc(struct mtk_eth *eth)
-{
- int i;
- struct mtk_tx_ring *ring = ð->tx_ring;
-
- ring->tx_ring_size = eth->soc->dma_ring_size;
- ring->tx_free_idx = 0;
- ring->tx_next_idx = 0;
- ring->tx_thresh = max((unsigned long)ring->tx_ring_size >> 2,
- MAX_SKB_FRAGS);
-
- ring->tx_buf = kcalloc(ring->tx_ring_size, sizeof(*ring->tx_buf),
- GFP_KERNEL);
- if (!ring->tx_buf)
- goto no_tx_mem;
-
- ring->tx_dma =
- dma_alloc_coherent(eth->dev,
- ring->tx_ring_size * sizeof(*ring->tx_dma),
- &ring->tx_phys, GFP_ATOMIC | __GFP_ZERO);
- if (!ring->tx_dma)
- goto no_tx_mem;
-
- for (i = 0; i < ring->tx_ring_size; i++) {
- ring->tx_dma[i].txd2 = TX_DMA_DESP2_DEF;
- ring->tx_dma[i].txd4 = eth->soc->txd4;
- }
-
- atomic_set(&ring->tx_free_count, mtk_pdma_empty_txd(ring));
- ring->tx_map = mtk_pdma_tx_map;
- ring->tx_poll = mtk_pdma_tx_poll;
- ring->tx_clean = mtk_pdma_tx_clean;
-
- /* make sure that all changes to the dma ring are flushed before we
- * continue
- */
- wmb();
-
- mtk_reg_w32(eth, ring->tx_phys, MTK_REG_TX_BASE_PTR0);
- mtk_reg_w32(eth, ring->tx_ring_size, MTK_REG_TX_MAX_CNT0);
- mtk_reg_w32(eth, 0, MTK_REG_TX_CTX_IDX0);
- mtk_reg_w32(eth, MTK_PST_DTX_IDX0, MTK_REG_PDMA_RST_CFG);
-
- return 0;
-
-no_tx_mem:
- return -ENOMEM;
-}
-
-static int mtk_qdma_tx_alloc_tx(struct mtk_eth *eth)
-{
- struct mtk_tx_ring *ring = ð->tx_ring;
- int i, sz = sizeof(*ring->tx_dma);
-
- ring->tx_ring_size = eth->soc->dma_ring_size;
- ring->tx_buf = kcalloc(ring->tx_ring_size, sizeof(*ring->tx_buf),
- GFP_KERNEL);
- if (!ring->tx_buf)
- goto no_tx_mem;
-
- ring->tx_dma = dma_alloc_coherent(eth->dev, ring->tx_ring_size * sz,
- &ring->tx_phys,
- GFP_ATOMIC | __GFP_ZERO);
- if (!ring->tx_dma)
- goto no_tx_mem;
-
- for (i = 0; i < ring->tx_ring_size; i++) {
- int next = (i + 1) % ring->tx_ring_size;
- u32 next_ptr = ring->tx_phys + next * sz;
-
- ring->tx_dma[i].txd2 = next_ptr;
- ring->tx_dma[i].txd3 = TX_DMA_DESP2_DEF;
- }
-
- atomic_set(&ring->tx_free_count, ring->tx_ring_size - 2);
- ring->tx_next_free = &ring->tx_dma[0];
- ring->tx_last_free = &ring->tx_dma[ring->tx_ring_size - 2];
- ring->tx_thresh = max((unsigned long)ring->tx_ring_size >> 2,
- MAX_SKB_FRAGS);
-
- ring->tx_map = mtk_qdma_tx_map;
- ring->tx_poll = mtk_qdma_tx_poll;
- ring->tx_clean = mtk_qdma_tx_clean;
-
- /* make sure that all changes to the dma ring are flushed before we
- * continue
- */
- wmb();
-
- mtk_w32(eth, ring->tx_phys, MTK_QTX_CTX_PTR);
- mtk_w32(eth, ring->tx_phys, MTK_QTX_DTX_PTR);
- mtk_w32(eth,
- ring->tx_phys + ((ring->tx_ring_size - 1) * sz),
- MTK_QTX_CRX_PTR);
- mtk_w32(eth,
- ring->tx_phys + ((ring->tx_ring_size - 1) * sz),
- MTK_QTX_DRX_PTR);
-
- return 0;
-
-no_tx_mem:
- return -ENOMEM;
-}
-
-static int mtk_qdma_init(struct mtk_eth *eth, int ring)
-{
- int err;
-
- err = mtk_init_fq_dma(eth);
- if (err)
- return err;
-
- err = mtk_qdma_tx_alloc_tx(eth);
- if (err)
- return err;
-
- err = mtk_dma_rx_alloc(eth, ð->rx_ring[ring]);
- if (err)
- return err;
-
- mtk_w32(eth, eth->rx_ring[ring].rx_phys, MTK_QRX_BASE_PTR0);
- mtk_w32(eth, eth->rx_ring[ring].rx_ring_size, MTK_QRX_MAX_CNT0);
- mtk_w32(eth, eth->rx_ring[ring].rx_calc_idx, MTK_QRX_CRX_IDX0);
- mtk_w32(eth, MTK_PST_DRX_IDX0, MTK_QDMA_RST_IDX);
- mtk_w32(eth, (QDMA_RES_THRES << 8) | QDMA_RES_THRES, MTK_QTX_CFG(0));
-
- /* Enable random early drop and set drop threshold automatically */
- mtk_w32(eth, 0x174444, MTK_QDMA_FC_THRES);
- mtk_w32(eth, 0x0, MTK_QDMA_HRED2);
-
- return 0;
-}
-
-static int mtk_pdma_qdma_init(struct mtk_eth *eth)
-{
- int err = mtk_qdma_init(eth, 1);
-
- if (err)
- return err;
-
- err = mtk_dma_rx_alloc(eth, ð->rx_ring[0]);
- if (err)
- return err;
-
- mtk_reg_w32(eth, eth->rx_ring[0].rx_phys, MTK_REG_RX_BASE_PTR0);
- mtk_reg_w32(eth, eth->rx_ring[0].rx_ring_size, MTK_REG_RX_MAX_CNT0);
- mtk_reg_w32(eth, eth->rx_ring[0].rx_calc_idx, MTK_REG_RX_CALC_IDX0);
- mtk_reg_w32(eth, MTK_PST_DRX_IDX0, MTK_REG_PDMA_RST_CFG);
-
- return 0;
-}
-
-static int mtk_pdma_init(struct mtk_eth *eth)
-{
- struct mtk_rx_ring *ring = ð->rx_ring[0];
- int err;
-
- err = mtk_pdma_tx_alloc(eth);
- if (err)
- return err;
-
- err = mtk_dma_rx_alloc(eth, ring);
- if (err)
- return err;
-
- mtk_reg_w32(eth, ring->rx_phys, MTK_REG_RX_BASE_PTR0);
- mtk_reg_w32(eth, ring->rx_ring_size, MTK_REG_RX_MAX_CNT0);
- mtk_reg_w32(eth, ring->rx_calc_idx, MTK_REG_RX_CALC_IDX0);
- mtk_reg_w32(eth, MTK_PST_DRX_IDX0, MTK_REG_PDMA_RST_CFG);
-
- return 0;
-}
-
-static void mtk_dma_free(struct mtk_eth *eth)
-{
- int i;
-
- for (i = 0; i < eth->soc->mac_count; i++)
- if (eth->netdev[i])
- netdev_reset_queue(eth->netdev[i]);
- eth->tx_ring.tx_clean(eth);
- mtk_clean_rx(eth, ð->rx_ring[0]);
- mtk_clean_rx(eth, ð->rx_ring[1]);
- kfree(eth->scratch_head);
-}
-
-static void mtk_tx_timeout(struct net_device *dev)
-{
- struct mtk_mac *mac = netdev_priv(dev);
- struct mtk_eth *eth = mac->hw;
- struct mtk_tx_ring *ring = ð->tx_ring;
-
- eth->netdev[mac->id]->stats.tx_errors++;
- netif_err(eth, tx_err, dev,
- "transmit timed out\n");
- if (eth->soc->dma_type & MTK_PDMA) {
- netif_info(eth, drv, dev, "pdma_cfg:%08x\n",
- mtk_reg_r32(eth, MTK_REG_PDMA_GLO_CFG));
- netif_info(eth, drv, dev,
- "tx_ring=%d, base=%08x, max=%u, ctx=%u, dtx=%u, fdx=%hu, next=%hu\n",
- 0, mtk_reg_r32(eth, MTK_REG_TX_BASE_PTR0),
- mtk_reg_r32(eth, MTK_REG_TX_MAX_CNT0),
- mtk_reg_r32(eth, MTK_REG_TX_CTX_IDX0),
- mtk_reg_r32(eth, MTK_REG_TX_DTX_IDX0),
- ring->tx_free_idx,
- ring->tx_next_idx);
- }
- if (eth->soc->dma_type & MTK_QDMA) {
- netif_info(eth, drv, dev, "qdma_cfg:%08x\n",
- mtk_r32(eth, MTK_QDMA_GLO_CFG));
- netif_info(eth, drv, dev,
- "tx_ring=%d, ctx=%08x, dtx=%08x, crx=%08x, drx=%08x, free=%hu\n",
- 0, mtk_r32(eth, MTK_QTX_CTX_PTR),
- mtk_r32(eth, MTK_QTX_DTX_PTR),
- mtk_r32(eth, MTK_QTX_CRX_PTR),
- mtk_r32(eth, MTK_QTX_DRX_PTR),
- atomic_read(&ring->tx_free_count));
- }
- netif_info(eth, drv, dev,
- "rx_ring=%d, base=%08x, max=%u, calc=%u, drx=%u\n",
- 0, mtk_reg_r32(eth, MTK_REG_RX_BASE_PTR0),
- mtk_reg_r32(eth, MTK_REG_RX_MAX_CNT0),
- mtk_reg_r32(eth, MTK_REG_RX_CALC_IDX0),
- mtk_reg_r32(eth, MTK_REG_RX_DRX_IDX0));
-
- schedule_work(&mac->pending_work);
-}
-
-static irqreturn_t mtk_handle_irq(int irq, void *_eth)
-{
- struct mtk_eth *eth = _eth;
- u32 status, int_mask;
-
- status = mtk_irq_pending(eth);
- if (unlikely(!status))
- return IRQ_NONE;
-
- int_mask = (eth->soc->rx_int | eth->soc->tx_int);
- if (likely(status & int_mask)) {
- if (likely(napi_schedule_prep(ð->rx_napi)))
- __napi_schedule(ð->rx_napi);
- } else {
- mtk_irq_ack(eth, status);
- }
- mtk_irq_disable(eth, int_mask);
-
- return IRQ_HANDLED;
-}
-
-#ifdef CONFIG_NET_POLL_CONTROLLER
-static void mtk_poll_controller(struct net_device *dev)
-{
- struct mtk_mac *mac = netdev_priv(dev);
- struct mtk_eth *eth = mac->hw;
- u32 int_mask = eth->soc->tx_int | eth->soc->rx_int;
-
- mtk_irq_disable(eth, int_mask);
- mtk_handle_irq(dev->irq, dev);
- mtk_irq_enable(eth, int_mask);
-}
-#endif
-
-int mtk_set_clock_cycle(struct mtk_eth *eth)
-{
- unsigned long sysclk = eth->sysclk;
-
- sysclk /= MTK_US_CYC_CNT_DIVISOR;
- sysclk <<= MTK_US_CYC_CNT_SHIFT;
-
- mtk_w32(eth, (mtk_r32(eth, MTK_GLO_CFG) &
- ~(MTK_US_CYC_CNT_MASK << MTK_US_CYC_CNT_SHIFT)) |
- sysclk,
- MTK_GLO_CFG);
- return 0;
-}
-
-void mtk_fwd_config(struct mtk_eth *eth)
-{
- u32 fwd_cfg;
-
- fwd_cfg = mtk_r32(eth, MTK_GDMA1_FWD_CFG);
-
- /* disable jumbo frame */
- if (eth->soc->jumbo_frame)
- fwd_cfg &= ~MTK_GDM1_JMB_EN;
-
- /* set unicast/multicast/broadcast frame to cpu */
- fwd_cfg &= ~0xffff;
-
- mtk_w32(eth, fwd_cfg, MTK_GDMA1_FWD_CFG);
-}
-
-void mtk_csum_config(struct mtk_eth *eth)
-{
- if (eth->soc->hw_features & NETIF_F_RXCSUM)
- mtk_w32(eth, mtk_r32(eth, MTK_GDMA1_FWD_CFG) |
- (MTK_GDM1_ICS_EN | MTK_GDM1_TCS_EN | MTK_GDM1_UCS_EN),
- MTK_GDMA1_FWD_CFG);
- else
- mtk_w32(eth, mtk_r32(eth, MTK_GDMA1_FWD_CFG) &
- ~(MTK_GDM1_ICS_EN | MTK_GDM1_TCS_EN | MTK_GDM1_UCS_EN),
- MTK_GDMA1_FWD_CFG);
- if (eth->soc->hw_features & NETIF_F_IP_CSUM)
- mtk_w32(eth, mtk_r32(eth, MTK_CDMA_CSG_CFG) |
- (MTK_ICS_GEN_EN | MTK_TCS_GEN_EN | MTK_UCS_GEN_EN),
- MTK_CDMA_CSG_CFG);
- else
- mtk_w32(eth, mtk_r32(eth, MTK_CDMA_CSG_CFG) &
- ~(MTK_ICS_GEN_EN | MTK_TCS_GEN_EN | MTK_UCS_GEN_EN),
- MTK_CDMA_CSG_CFG);
-}
-
-static int mtk_start_dma(struct mtk_eth *eth)
-{
- unsigned long flags;
- u32 val;
- int err;
-
- if (eth->soc->dma_type == MTK_PDMA)
- err = mtk_pdma_init(eth);
- else if (eth->soc->dma_type == MTK_QDMA)
- err = mtk_qdma_init(eth, 0);
- else
- err = mtk_pdma_qdma_init(eth);
- if (err) {
- mtk_dma_free(eth);
- return err;
- }
-
- spin_lock_irqsave(ð->page_lock, flags);
-
- val = MTK_TX_WB_DDONE | MTK_RX_DMA_EN | MTK_TX_DMA_EN;
- if (eth->soc->rx_2b_offset)
- val |= MTK_RX_2B_OFFSET;
- val |= eth->soc->pdma_glo_cfg;
-
- if (eth->soc->dma_type & MTK_PDMA)
- mtk_reg_w32(eth, val, MTK_REG_PDMA_GLO_CFG);
-
- if (eth->soc->dma_type & MTK_QDMA)
- mtk_w32(eth, val, MTK_QDMA_GLO_CFG);
-
- spin_unlock_irqrestore(ð->page_lock, flags);
-
- return 0;
-}
-
-static int mtk_open(struct net_device *dev)
-{
- struct mtk_mac *mac = netdev_priv(dev);
- struct mtk_eth *eth = mac->hw;
-
- dma_coerce_mask_and_coherent(&dev->dev, DMA_BIT_MASK(32));
-
- if (!atomic_read(ð->dma_refcnt)) {
- int err = mtk_start_dma(eth);
-
- if (err)
- return err;
-
- napi_enable(ð->rx_napi);
- mtk_irq_enable(eth, eth->soc->tx_int | eth->soc->rx_int);
- }
- atomic_inc(ð->dma_refcnt);
-
- if (eth->phy)
- eth->phy->start(mac);
-
- if (eth->soc->has_carrier && eth->soc->has_carrier(eth))
- netif_carrier_on(dev);
-
- netif_start_queue(dev);
- eth->soc->fwd_config(eth);
-
- return 0;
-}
-
-static void mtk_stop_dma(struct mtk_eth *eth, u32 glo_cfg)
-{
- unsigned long flags;
- u32 val;
- int i;
-
- /* stop the dma enfine */
- spin_lock_irqsave(ð->page_lock, flags);
- val = mtk_r32(eth, glo_cfg);
- mtk_w32(eth, val & ~(MTK_TX_WB_DDONE | MTK_RX_DMA_EN | MTK_TX_DMA_EN),
- glo_cfg);
- spin_unlock_irqrestore(ð->page_lock, flags);
-
- /* wait for dma stop */
- for (i = 0; i < 10; i++) {
- val = mtk_r32(eth, glo_cfg);
- if (val & (MTK_TX_DMA_BUSY | MTK_RX_DMA_BUSY)) {
- msleep(20);
- continue;
- }
- break;
- }
-}
-
-static int mtk_stop(struct net_device *dev)
-{
- struct mtk_mac *mac = netdev_priv(dev);
- struct mtk_eth *eth = mac->hw;
-
- netif_tx_disable(dev);
- if (eth->phy)
- eth->phy->stop(mac);
-
- if (!atomic_dec_and_test(ð->dma_refcnt))
- return 0;
-
- mtk_irq_disable(eth, eth->soc->tx_int | eth->soc->rx_int);
- napi_disable(ð->rx_napi);
-
- if (eth->soc->dma_type & MTK_PDMA)
- mtk_stop_dma(eth, mtk_reg_table[MTK_REG_PDMA_GLO_CFG]);
-
- if (eth->soc->dma_type & MTK_QDMA)
- mtk_stop_dma(eth, MTK_QDMA_GLO_CFG);
-
- mtk_dma_free(eth);
-
- return 0;
-}
-
-static int __init mtk_init_hw(struct mtk_eth *eth)
-{
- int i, err;
-
- eth->soc->reset_fe(eth);
-
- if (eth->soc->switch_init)
- if (eth->soc->switch_init(eth)) {
- dev_err(eth->dev, "failed to initialize switch core\n");
- return -ENODEV;
- }
-
- err = devm_request_irq(eth->dev, eth->irq, mtk_handle_irq, 0,
- dev_name(eth->dev), eth);
- if (err)
- return err;
-
- err = mtk_mdio_init(eth);
- if (err)
- return err;
-
- /* disable delay and normal interrupt */
- mtk_reg_w32(eth, 0, MTK_REG_DLY_INT_CFG);
- if (eth->soc->dma_type & MTK_QDMA)
- mtk_w32(eth, 0, MTK_QDMA_DELAY_INT);
- mtk_irq_disable(eth, eth->soc->tx_int | eth->soc->rx_int);
-
- /* frame engine will push VLAN tag regarding to VIDX field in Tx desc */
- if (mtk_reg_table[MTK_REG_MTK_DMA_VID_BASE])
- for (i = 0; i < 16; i += 2)
- mtk_w32(eth, ((i + 1) << 16) + i,
- mtk_reg_table[MTK_REG_MTK_DMA_VID_BASE] +
- (i * 2));
-
- if (eth->soc->fwd_config(eth))
- dev_err(eth->dev, "unable to get clock\n");
-
- if (mtk_reg_table[MTK_REG_MTK_RST_GL]) {
- mtk_reg_w32(eth, 1, MTK_REG_MTK_RST_GL);
- mtk_reg_w32(eth, 0, MTK_REG_MTK_RST_GL);
- }
-
- return 0;
-}
-
-static int __init mtk_init(struct net_device *dev)
-{
- struct mtk_mac *mac = netdev_priv(dev);
- struct mtk_eth *eth = mac->hw;
- struct device_node *port;
- const char *mac_addr;
- int err;
-
- mac_addr = of_get_mac_address(mac->of_node);
- if (mac_addr)
- ether_addr_copy(dev->dev_addr, mac_addr);
-
- /* If the mac address is invalid, use random mac address */
- if (!is_valid_ether_addr(dev->dev_addr)) {
- eth_hw_addr_random(dev);
- dev_err(eth->dev, "generated random MAC address %pM\n",
- dev->dev_addr);
- }
- mac->hw->soc->set_mac(mac, dev->dev_addr);
-
- if (eth->soc->port_init)
- for_each_child_of_node(mac->of_node, port)
- if (of_device_is_compatible(port,
- "mediatek,eth-port") &&
- of_device_is_available(port))
- eth->soc->port_init(eth, mac, port);
-
- if (eth->phy) {
- err = eth->phy->connect(mac);
- if (err)
- return err;
- }
-
- return 0;
-}
-
-static void mtk_uninit(struct net_device *dev)
-{
- struct mtk_mac *mac = netdev_priv(dev);
- struct mtk_eth *eth = mac->hw;
-
- if (eth->phy)
- eth->phy->disconnect(mac);
- mtk_mdio_cleanup(eth);
-
- mtk_irq_disable(eth, ~0);
- free_irq(dev->irq, dev);
-}
-
-static int mtk_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
-{
- struct mtk_mac *mac = netdev_priv(dev);
-
- if (!mac->phy_dev)
- return -ENODEV;
-
- switch (cmd) {
- case SIOCGMIIPHY:
- case SIOCGMIIREG:
- case SIOCSMIIREG:
- return phy_mii_ioctl(mac->phy_dev, ifr, cmd);
- default:
- break;
- }
-
- return -EOPNOTSUPP;
-}
-
-static int mtk_change_mtu(struct net_device *dev, int new_mtu)
-{
- struct mtk_mac *mac = netdev_priv(dev);
- struct mtk_eth *eth = mac->hw;
- int frag_size, old_mtu;
- u32 fwd_cfg;
-
- if (!eth->soc->jumbo_frame)
- return eth_change_mtu(dev, new_mtu);
-
- frag_size = mtk_max_frag_size(new_mtu);
- if (new_mtu < 68 || frag_size > PAGE_SIZE)
- return -EINVAL;
-
- old_mtu = dev->mtu;
- dev->mtu = new_mtu;
-
- /* return early if the buffer sizes will not change */
- if (old_mtu <= ETH_DATA_LEN && new_mtu <= ETH_DATA_LEN)
- return 0;
- if (old_mtu > ETH_DATA_LEN && new_mtu > ETH_DATA_LEN)
- return 0;
-
- if (new_mtu <= ETH_DATA_LEN)
- eth->rx_ring[0].frag_size = mtk_max_frag_size(ETH_DATA_LEN);
- else
- eth->rx_ring[0].frag_size = PAGE_SIZE;
- eth->rx_ring[0].rx_buf_size =
- mtk_max_buf_size(eth->rx_ring[0].frag_size);
-
- if (!netif_running(dev))
- return 0;
-
- mtk_stop(dev);
- fwd_cfg = mtk_r32(eth, MTK_GDMA1_FWD_CFG);
- if (new_mtu <= ETH_DATA_LEN) {
- fwd_cfg &= ~MTK_GDM1_JMB_EN;
- } else {
- fwd_cfg &= ~(MTK_GDM1_JMB_LEN_MASK << MTK_GDM1_JMB_LEN_SHIFT);
- fwd_cfg |= (DIV_ROUND_UP(frag_size, 1024) <<
- MTK_GDM1_JMB_LEN_SHIFT) | MTK_GDM1_JMB_EN;
- }
- mtk_w32(eth, fwd_cfg, MTK_GDMA1_FWD_CFG);
-
- return mtk_open(dev);
-}
-
-static void mtk_pending_work(struct work_struct *work)
-{
- struct mtk_mac *mac = container_of(work, struct mtk_mac, pending_work);
- struct mtk_eth *eth = mac->hw;
- struct net_device *dev = eth->netdev[mac->id];
- int err;
-
- rtnl_lock();
- mtk_stop(dev);
-
- err = mtk_open(dev);
- if (err) {
- netif_alert(eth, ifup, dev,
- "Driver up/down cycle failed, closing device.\n");
- dev_close(dev);
- }
- rtnl_unlock();
-}
-
-static int mtk_cleanup(struct mtk_eth *eth)
-{
- int i;
-
- for (i = 0; i < eth->soc->mac_count; i++) {
- struct mtk_mac *mac = netdev_priv(eth->netdev[i]);
-
- if (!eth->netdev[i])
- continue;
-
- unregister_netdev(eth->netdev[i]);
- free_netdev(eth->netdev[i]);
- cancel_work_sync(&mac->pending_work);
- }
-
- return 0;
-}
-
-static const struct net_device_ops mtk_netdev_ops = {
- .ndo_init = mtk_init,
- .ndo_uninit = mtk_uninit,
- .ndo_open = mtk_open,
- .ndo_stop = mtk_stop,
- .ndo_start_xmit = mtk_start_xmit,
- .ndo_set_mac_address = mtk_set_mac_address,
- .ndo_validate_addr = eth_validate_addr,
- .ndo_do_ioctl = mtk_do_ioctl,
- .ndo_change_mtu = mtk_change_mtu,
- .ndo_tx_timeout = mtk_tx_timeout,
- .ndo_get_stats64 = mtk_get_stats64,
- .ndo_vlan_rx_add_vid = mtk_vlan_rx_add_vid,
- .ndo_vlan_rx_kill_vid = mtk_vlan_rx_kill_vid,
-#ifdef CONFIG_NET_POLL_CONTROLLER
- .ndo_poll_controller = mtk_poll_controller,
-#endif
-};
-
-static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np)
-{
- struct mtk_mac *mac;
- const __be32 *_id = of_get_property(np, "reg", NULL);
- int id, err;
-
- if (!_id) {
- dev_err(eth->dev, "missing mac id\n");
- return -EINVAL;
- }
- id = be32_to_cpup(_id);
- if (id >= eth->soc->mac_count || eth->netdev[id]) {
- dev_err(eth->dev, "%d is not a valid mac id\n", id);
- return -EINVAL;
- }
-
- eth->netdev[id] = alloc_etherdev(sizeof(*mac));
- if (!eth->netdev[id]) {
- dev_err(eth->dev, "alloc_etherdev failed\n");
- return -ENOMEM;
- }
- mac = netdev_priv(eth->netdev[id]);
- eth->mac[id] = mac;
- mac->id = id;
- mac->hw = eth;
- mac->of_node = np;
- INIT_WORK(&mac->pending_work, mtk_pending_work);
-
- if (mtk_reg_table[MTK_REG_MTK_COUNTER_BASE]) {
- mac->hw_stats = devm_kzalloc(eth->dev,
- sizeof(*mac->hw_stats),
- GFP_KERNEL);
- if (!mac->hw_stats) {
- err = -ENOMEM;
- goto free_netdev;
- }
- spin_lock_init(&mac->hw_stats->stats_lock);
- mac->hw_stats->reg_offset = id * MTK_STAT_OFFSET;
- }
-
- SET_NETDEV_DEV(eth->netdev[id], eth->dev);
- eth->netdev[id]->netdev_ops = &mtk_netdev_ops;
- eth->netdev[id]->base_addr = (unsigned long)eth->base;
-
- if (eth->soc->init_data)
- eth->soc->init_data(eth->soc, eth->netdev[id]);
-
- eth->netdev[id]->vlan_features = eth->soc->hw_features &
- ~(NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX);
- eth->netdev[id]->features |= eth->soc->hw_features;
-
- if (mtk_reg_table[MTK_REG_MTK_DMA_VID_BASE])
- eth->netdev[id]->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
-
- mtk_set_ethtool_ops(eth->netdev[id]);
-
- err = register_netdev(eth->netdev[id]);
- if (err) {
- dev_err(eth->dev, "error bringing up device\n");
- err = -ENOMEM;
- goto free_netdev;
- }
- eth->netdev[id]->irq = eth->irq;
- netif_info(eth, probe, eth->netdev[id],
- "mediatek frame engine at 0x%08lx, irq %d\n",
- eth->netdev[id]->base_addr, eth->netdev[id]->irq);
-
- return 0;
-
-free_netdev:
- free_netdev(eth->netdev[id]);
- return err;
-}
-
-static int mtk_probe(struct platform_device *pdev)
-{
- struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- const struct of_device_id *match;
- struct device_node *mac_np;
- struct mtk_soc_data *soc;
- struct mtk_eth *eth;
- struct clk *sysclk;
- int err;
-
- device_reset(&pdev->dev);
-
- match = of_match_device(of_mtk_match, &pdev->dev);
- soc = (struct mtk_soc_data *)match->data;
-
- if (soc->reg_table)
- mtk_reg_table = soc->reg_table;
-
- eth = devm_kzalloc(&pdev->dev, sizeof(*eth), GFP_KERNEL);
- if (!eth)
- return -ENOMEM;
-
- eth->base = devm_ioremap_resource(&pdev->dev, res);
- if (IS_ERR(eth->base))
- return PTR_ERR(eth->base);
-
- spin_lock_init(ð->page_lock);
-
- eth->ethsys = syscon_regmap_lookup_by_phandle(pdev->dev.of_node,
- "mediatek,ethsys");
- if (IS_ERR(eth->ethsys))
- return PTR_ERR(eth->ethsys);
-
- eth->irq = platform_get_irq(pdev, 0);
- if (eth->irq < 0) {
- dev_err(&pdev->dev, "no IRQ resource found\n");
- return -ENXIO;
- }
-
- sysclk = devm_clk_get(&pdev->dev, NULL);
- if (IS_ERR(sysclk)) {
- dev_err(&pdev->dev,
- "the clock is not defined in the devicetree\n");
- return -ENXIO;
- }
- eth->sysclk = clk_get_rate(sysclk);
-
- eth->switch_np = of_parse_phandle(pdev->dev.of_node,
- "mediatek,switch", 0);
- if (soc->has_switch && !eth->switch_np) {
- dev_err(&pdev->dev, "failed to read switch phandle\n");
- return -ENODEV;
- }
-
- eth->dev = &pdev->dev;
- eth->soc = soc;
- eth->msg_enable = netif_msg_init(mtk_msg_level, MTK_DEFAULT_MSG_ENABLE);
-
- err = mtk_init_hw(eth);
- if (err)
- return err;
-
- if (eth->soc->mac_count > 1) {
- for_each_child_of_node(pdev->dev.of_node, mac_np) {
- if (!of_device_is_compatible(mac_np,
- "mediatek,eth-mac"))
- continue;
-
- if (!of_device_is_available(mac_np))
- continue;
-
- err = mtk_add_mac(eth, mac_np);
- if (err)
- goto err_free_dev;
- }
-
- init_dummy_netdev(ð->dummy_dev);
- netif_napi_add(ð->dummy_dev, ð->rx_napi, mtk_poll,
- soc->napi_weight);
- } else {
- err = mtk_add_mac(eth, pdev->dev.of_node);
- if (err)
- goto err_free_dev;
- netif_napi_add(eth->netdev[0], ð->rx_napi, mtk_poll,
- soc->napi_weight);
- }
-
- platform_set_drvdata(pdev, eth);
-
- return 0;
-
-err_free_dev:
- mtk_cleanup(eth);
- return err;
-}
-
-static int mtk_remove(struct platform_device *pdev)
-{
- struct mtk_eth *eth = platform_get_drvdata(pdev);
-
- netif_napi_del(ð->rx_napi);
- mtk_cleanup(eth);
- platform_set_drvdata(pdev, NULL);
-
- return 0;
-}
-
-static struct platform_driver mtk_driver = {
- .probe = mtk_probe,
- .remove = mtk_remove,
- .driver = {
- .name = "mtk_soc_eth",
- .of_match_table = of_mtk_match,
- },
-};
-
-module_platform_driver(mtk_driver);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("John Crispin <blogic@openwrt.org>");
-MODULE_DESCRIPTION("Ethernet driver for MediaTek SoC");
+++ /dev/null
-/* This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * Copyright (C) 2009-2016 John Crispin <blogic@openwrt.org>
- * Copyright (C) 2009-2016 Felix Fietkau <nbd@openwrt.org>
- * Copyright (C) 2013-2016 Michael Lee <igvtee@gmail.com>
- */
-
-#ifndef MTK_ETH_H
-#define MTK_ETH_H
-
-#include <linux/mii.h>
-#include <linux/interrupt.h>
-#include <linux/netdevice.h>
-#include <linux/dma-mapping.h>
-#include <linux/phy.h>
-#include <linux/ethtool.h>
-#include <linux/version.h>
-#include <linux/atomic.h>
-
-/* these registers have different offsets depending on the SoC. we use a lookup
- * table for these
- */
-enum mtk_reg {
- MTK_REG_PDMA_GLO_CFG = 0,
- MTK_REG_PDMA_RST_CFG,
- MTK_REG_DLY_INT_CFG,
- MTK_REG_TX_BASE_PTR0,
- MTK_REG_TX_MAX_CNT0,
- MTK_REG_TX_CTX_IDX0,
- MTK_REG_TX_DTX_IDX0,
- MTK_REG_RX_BASE_PTR0,
- MTK_REG_RX_MAX_CNT0,
- MTK_REG_RX_CALC_IDX0,
- MTK_REG_RX_DRX_IDX0,
- MTK_REG_MTK_INT_ENABLE,
- MTK_REG_MTK_INT_STATUS,
- MTK_REG_MTK_DMA_VID_BASE,
- MTK_REG_MTK_COUNTER_BASE,
- MTK_REG_MTK_RST_GL,
- MTK_REG_MTK_INT_STATUS2,
- MTK_REG_COUNT
-};
-
-/* delayed interrupt bits */
-#define MTK_DELAY_EN_INT 0x80
-#define MTK_DELAY_MAX_INT 0x04
-#define MTK_DELAY_MAX_TOUT 0x04
-#define MTK_DELAY_TIME 20
-#define MTK_DELAY_CHAN (((MTK_DELAY_EN_INT | MTK_DELAY_MAX_INT) << 8) \
- | MTK_DELAY_MAX_TOUT)
-#define MTK_DELAY_INIT ((MTK_DELAY_CHAN << 16) | MTK_DELAY_CHAN)
-#define MTK_PSE_FQFC_CFG_INIT 0x80504000
-#define MTK_PSE_FQFC_CFG_256Q 0xff908000
-
-/* interrupt bits */
-#define MTK_CNT_PPE_AF BIT(31)
-#define MTK_CNT_GDM_AF BIT(29)
-#define MTK_PSE_P2_FC BIT(26)
-#define MTK_PSE_BUF_DROP BIT(24)
-#define MTK_GDM_OTHER_DROP BIT(23)
-#define MTK_PSE_P1_FC BIT(22)
-#define MTK_PSE_P0_FC BIT(21)
-#define MTK_PSE_FQ_EMPTY BIT(20)
-#define MTK_GE1_STA_CHG BIT(18)
-#define MTK_TX_COHERENT BIT(17)
-#define MTK_RX_COHERENT BIT(16)
-#define MTK_TX_DONE_INT3 BIT(11)
-#define MTK_TX_DONE_INT2 BIT(10)
-#define MTK_TX_DONE_INT1 BIT(9)
-#define MTK_TX_DONE_INT0 BIT(8)
-#define MTK_RX_DONE_INT0 BIT(2)
-#define MTK_TX_DLY_INT BIT(1)
-#define MTK_RX_DLY_INT BIT(0)
-
-#define MTK_RX_DONE_INT MTK_RX_DONE_INT0
-#define MTK_TX_DONE_INT (MTK_TX_DONE_INT0 | MTK_TX_DONE_INT1 | \
- MTK_TX_DONE_INT2 | MTK_TX_DONE_INT3)
-
-#define RT5350_RX_DLY_INT BIT(30)
-#define RT5350_TX_DLY_INT BIT(28)
-#define RT5350_RX_DONE_INT1 BIT(17)
-#define RT5350_RX_DONE_INT0 BIT(16)
-#define RT5350_TX_DONE_INT3 BIT(3)
-#define RT5350_TX_DONE_INT2 BIT(2)
-#define RT5350_TX_DONE_INT1 BIT(1)
-#define RT5350_TX_DONE_INT0 BIT(0)
-
-#define RT5350_RX_DONE_INT (RT5350_RX_DONE_INT0 | RT5350_RX_DONE_INT1)
-#define RT5350_TX_DONE_INT (RT5350_TX_DONE_INT0 | RT5350_TX_DONE_INT1 | \
- RT5350_TX_DONE_INT2 | RT5350_TX_DONE_INT3)
-
-/* registers */
-#define MTK_GDMA_OFFSET 0x0020
-#define MTK_PSE_OFFSET 0x0040
-#define MTK_GDMA2_OFFSET 0x0060
-#define MTK_CDMA_OFFSET 0x0080
-#define MTK_DMA_VID0 0x00a8
-#define MTK_PDMA_OFFSET 0x0100
-#define MTK_PPE_OFFSET 0x0200
-#define MTK_CMTABLE_OFFSET 0x0400
-#define MTK_POLICYTABLE_OFFSET 0x1000
-
-#define MT7621_GDMA_OFFSET 0x0500
-#define MT7620_GDMA_OFFSET 0x0600
-
-#define RT5350_PDMA_OFFSET 0x0800
-#define RT5350_SDM_OFFSET 0x0c00
-
-#define MTK_MDIO_ACCESS 0x00
-#define MTK_MDIO_CFG 0x04
-#define MTK_GLO_CFG 0x08
-#define MTK_RST_GL 0x0C
-#define MTK_INT_STATUS 0x10
-#define MTK_INT_ENABLE 0x14
-#define MTK_MDIO_CFG2 0x18
-#define MTK_FOC_TS_T 0x1C
-
-#define MTK_GDMA1_FWD_CFG (MTK_GDMA_OFFSET + 0x00)
-#define MTK_GDMA1_SCH_CFG (MTK_GDMA_OFFSET + 0x04)
-#define MTK_GDMA1_SHPR_CFG (MTK_GDMA_OFFSET + 0x08)
-#define MTK_GDMA1_MAC_ADRL (MTK_GDMA_OFFSET + 0x0C)
-#define MTK_GDMA1_MAC_ADRH (MTK_GDMA_OFFSET + 0x10)
-
-#define MTK_GDMA2_FWD_CFG (MTK_GDMA2_OFFSET + 0x00)
-#define MTK_GDMA2_SCH_CFG (MTK_GDMA2_OFFSET + 0x04)
-#define MTK_GDMA2_SHPR_CFG (MTK_GDMA2_OFFSET + 0x08)
-#define MTK_GDMA2_MAC_ADRL (MTK_GDMA2_OFFSET + 0x0C)
-#define MTK_GDMA2_MAC_ADRH (MTK_GDMA2_OFFSET + 0x10)
-
-#define MTK_PSE_FQ_CFG (MTK_PSE_OFFSET + 0x00)
-#define MTK_CDMA_FC_CFG (MTK_PSE_OFFSET + 0x04)
-#define MTK_GDMA1_FC_CFG (MTK_PSE_OFFSET + 0x08)
-#define MTK_GDMA2_FC_CFG (MTK_PSE_OFFSET + 0x0C)
-
-#define MTK_CDMA_CSG_CFG (MTK_CDMA_OFFSET + 0x00)
-#define MTK_CDMA_SCH_CFG (MTK_CDMA_OFFSET + 0x04)
-
-#define MT7621_GDMA_FWD_CFG(x) (MT7621_GDMA_OFFSET + (x * 0x1000))
-
-/* FIXME this might be different for different SOCs */
-#define MT7620_GDMA1_FWD_CFG (MT7621_GDMA_OFFSET + 0x00)
-
-#define RT5350_TX_BASE_PTR0 (RT5350_PDMA_OFFSET + 0x00)
-#define RT5350_TX_MAX_CNT0 (RT5350_PDMA_OFFSET + 0x04)
-#define RT5350_TX_CTX_IDX0 (RT5350_PDMA_OFFSET + 0x08)
-#define RT5350_TX_DTX_IDX0 (RT5350_PDMA_OFFSET + 0x0C)
-#define RT5350_TX_BASE_PTR1 (RT5350_PDMA_OFFSET + 0x10)
-#define RT5350_TX_MAX_CNT1 (RT5350_PDMA_OFFSET + 0x14)
-#define RT5350_TX_CTX_IDX1 (RT5350_PDMA_OFFSET + 0x18)
-#define RT5350_TX_DTX_IDX1 (RT5350_PDMA_OFFSET + 0x1C)
-#define RT5350_TX_BASE_PTR2 (RT5350_PDMA_OFFSET + 0x20)
-#define RT5350_TX_MAX_CNT2 (RT5350_PDMA_OFFSET + 0x24)
-#define RT5350_TX_CTX_IDX2 (RT5350_PDMA_OFFSET + 0x28)
-#define RT5350_TX_DTX_IDX2 (RT5350_PDMA_OFFSET + 0x2C)
-#define RT5350_TX_BASE_PTR3 (RT5350_PDMA_OFFSET + 0x30)
-#define RT5350_TX_MAX_CNT3 (RT5350_PDMA_OFFSET + 0x34)
-#define RT5350_TX_CTX_IDX3 (RT5350_PDMA_OFFSET + 0x38)
-#define RT5350_TX_DTX_IDX3 (RT5350_PDMA_OFFSET + 0x3C)
-#define RT5350_RX_BASE_PTR0 (RT5350_PDMA_OFFSET + 0x100)
-#define RT5350_RX_MAX_CNT0 (RT5350_PDMA_OFFSET + 0x104)
-#define RT5350_RX_CALC_IDX0 (RT5350_PDMA_OFFSET + 0x108)
-#define RT5350_RX_DRX_IDX0 (RT5350_PDMA_OFFSET + 0x10C)
-#define RT5350_RX_BASE_PTR1 (RT5350_PDMA_OFFSET + 0x110)
-#define RT5350_RX_MAX_CNT1 (RT5350_PDMA_OFFSET + 0x114)
-#define RT5350_RX_CALC_IDX1 (RT5350_PDMA_OFFSET + 0x118)
-#define RT5350_RX_DRX_IDX1 (RT5350_PDMA_OFFSET + 0x11C)
-#define RT5350_PDMA_GLO_CFG (RT5350_PDMA_OFFSET + 0x204)
-#define RT5350_PDMA_RST_CFG (RT5350_PDMA_OFFSET + 0x208)
-#define RT5350_DLY_INT_CFG (RT5350_PDMA_OFFSET + 0x20c)
-#define RT5350_MTK_INT_STATUS (RT5350_PDMA_OFFSET + 0x220)
-#define RT5350_MTK_INT_ENABLE (RT5350_PDMA_OFFSET + 0x228)
-#define RT5350_PDMA_SCH_CFG (RT5350_PDMA_OFFSET + 0x280)
-
-#define MTK_PDMA_GLO_CFG (MTK_PDMA_OFFSET + 0x00)
-#define MTK_PDMA_RST_CFG (MTK_PDMA_OFFSET + 0x04)
-#define MTK_PDMA_SCH_CFG (MTK_PDMA_OFFSET + 0x08)
-#define MTK_DLY_INT_CFG (MTK_PDMA_OFFSET + 0x0C)
-#define MTK_TX_BASE_PTR0 (MTK_PDMA_OFFSET + 0x10)
-#define MTK_TX_MAX_CNT0 (MTK_PDMA_OFFSET + 0x14)
-#define MTK_TX_CTX_IDX0 (MTK_PDMA_OFFSET + 0x18)
-#define MTK_TX_DTX_IDX0 (MTK_PDMA_OFFSET + 0x1C)
-#define MTK_TX_BASE_PTR1 (MTK_PDMA_OFFSET + 0x20)
-#define MTK_TX_MAX_CNT1 (MTK_PDMA_OFFSET + 0x24)
-#define MTK_TX_CTX_IDX1 (MTK_PDMA_OFFSET + 0x28)
-#define MTK_TX_DTX_IDX1 (MTK_PDMA_OFFSET + 0x2C)
-#define MTK_RX_BASE_PTR0 (MTK_PDMA_OFFSET + 0x30)
-#define MTK_RX_MAX_CNT0 (MTK_PDMA_OFFSET + 0x34)
-#define MTK_RX_CALC_IDX0 (MTK_PDMA_OFFSET + 0x38)
-#define MTK_RX_DRX_IDX0 (MTK_PDMA_OFFSET + 0x3C)
-#define MTK_TX_BASE_PTR2 (MTK_PDMA_OFFSET + 0x40)
-#define MTK_TX_MAX_CNT2 (MTK_PDMA_OFFSET + 0x44)
-#define MTK_TX_CTX_IDX2 (MTK_PDMA_OFFSET + 0x48)
-#define MTK_TX_DTX_IDX2 (MTK_PDMA_OFFSET + 0x4C)
-#define MTK_TX_BASE_PTR3 (MTK_PDMA_OFFSET + 0x50)
-#define MTK_TX_MAX_CNT3 (MTK_PDMA_OFFSET + 0x54)
-#define MTK_TX_CTX_IDX3 (MTK_PDMA_OFFSET + 0x58)
-#define MTK_TX_DTX_IDX3 (MTK_PDMA_OFFSET + 0x5C)
-#define MTK_RX_BASE_PTR1 (MTK_PDMA_OFFSET + 0x60)
-#define MTK_RX_MAX_CNT1 (MTK_PDMA_OFFSET + 0x64)
-#define MTK_RX_CALC_IDX1 (MTK_PDMA_OFFSET + 0x68)
-#define MTK_RX_DRX_IDX1 (MTK_PDMA_OFFSET + 0x6C)
-
-/* Switch DMA configuration */
-#define RT5350_SDM_CFG (RT5350_SDM_OFFSET + 0x00)
-#define RT5350_SDM_RRING (RT5350_SDM_OFFSET + 0x04)
-#define RT5350_SDM_TRING (RT5350_SDM_OFFSET + 0x08)
-#define RT5350_SDM_MAC_ADRL (RT5350_SDM_OFFSET + 0x0C)
-#define RT5350_SDM_MAC_ADRH (RT5350_SDM_OFFSET + 0x10)
-#define RT5350_SDM_TPCNT (RT5350_SDM_OFFSET + 0x100)
-#define RT5350_SDM_TBCNT (RT5350_SDM_OFFSET + 0x104)
-#define RT5350_SDM_RPCNT (RT5350_SDM_OFFSET + 0x108)
-#define RT5350_SDM_RBCNT (RT5350_SDM_OFFSET + 0x10C)
-#define RT5350_SDM_CS_ERR (RT5350_SDM_OFFSET + 0x110)
-
-#define RT5350_SDM_ICS_EN BIT(16)
-#define RT5350_SDM_TCS_EN BIT(17)
-#define RT5350_SDM_UCS_EN BIT(18)
-
-/* QDMA registers */
-#define MTK_QTX_CFG(x) (0x1800 + (x * 0x10))
-#define MTK_QTX_SCH(x) (0x1804 + (x * 0x10))
-#define MTK_QRX_BASE_PTR0 0x1900
-#define MTK_QRX_MAX_CNT0 0x1904
-#define MTK_QRX_CRX_IDX0 0x1908
-#define MTK_QRX_DRX_IDX0 0x190C
-#define MTK_QDMA_GLO_CFG 0x1A04
-#define MTK_QDMA_RST_IDX 0x1A08
-#define MTK_QDMA_DELAY_INT 0x1A0C
-#define MTK_QDMA_FC_THRES 0x1A10
-#define MTK_QMTK_INT_STATUS 0x1A18
-#define MTK_QMTK_INT_ENABLE 0x1A1C
-#define MTK_QDMA_HRED2 0x1A44
-
-#define MTK_QTX_CTX_PTR 0x1B00
-#define MTK_QTX_DTX_PTR 0x1B04
-
-#define MTK_QTX_CRX_PTR 0x1B10
-#define MTK_QTX_DRX_PTR 0x1B14
-
-#define MTK_QDMA_FQ_HEAD 0x1B20
-#define MTK_QDMA_FQ_TAIL 0x1B24
-#define MTK_QDMA_FQ_CNT 0x1B28
-#define MTK_QDMA_FQ_BLEN 0x1B2C
-
-#define QDMA_PAGE_SIZE 2048
-#define QDMA_TX_OWNER_CPU BIT(31)
-#define QDMA_TX_SWC BIT(14)
-#define TX_QDMA_SDL(_x) (((_x) & 0x3fff) << 16)
-#define QDMA_RES_THRES 4
-
-/* MDIO_CFG register bits */
-#define MTK_MDIO_CFG_AUTO_POLL_EN BIT(29)
-#define MTK_MDIO_CFG_GP1_BP_EN BIT(16)
-#define MTK_MDIO_CFG_GP1_FRC_EN BIT(15)
-#define MTK_MDIO_CFG_GP1_SPEED_10 (0 << 13)
-#define MTK_MDIO_CFG_GP1_SPEED_100 (1 << 13)
-#define MTK_MDIO_CFG_GP1_SPEED_1000 (2 << 13)
-#define MTK_MDIO_CFG_GP1_DUPLEX BIT(12)
-#define MTK_MDIO_CFG_GP1_FC_TX BIT(11)
-#define MTK_MDIO_CFG_GP1_FC_RX BIT(10)
-#define MTK_MDIO_CFG_GP1_LNK_DWN BIT(9)
-#define MTK_MDIO_CFG_GP1_AN_FAIL BIT(8)
-#define MTK_MDIO_CFG_MDC_CLK_DIV_1 (0 << 6)
-#define MTK_MDIO_CFG_MDC_CLK_DIV_2 (1 << 6)
-#define MTK_MDIO_CFG_MDC_CLK_DIV_4 (2 << 6)
-#define MTK_MDIO_CFG_MDC_CLK_DIV_8 (3 << 6)
-#define MTK_MDIO_CFG_TURBO_MII_FREQ BIT(5)
-#define MTK_MDIO_CFG_TURBO_MII_MODE BIT(4)
-#define MTK_MDIO_CFG_RX_CLK_SKEW_0 (0 << 2)
-#define MTK_MDIO_CFG_RX_CLK_SKEW_200 (1 << 2)
-#define MTK_MDIO_CFG_RX_CLK_SKEW_400 (2 << 2)
-#define MTK_MDIO_CFG_RX_CLK_SKEW_INV (3 << 2)
-#define MTK_MDIO_CFG_TX_CLK_SKEW_0 0
-#define MTK_MDIO_CFG_TX_CLK_SKEW_200 1
-#define MTK_MDIO_CFG_TX_CLK_SKEW_400 2
-#define MTK_MDIO_CFG_TX_CLK_SKEW_INV 3
-
-/* uni-cast port */
-#define MTK_GDM1_JMB_LEN_MASK 0xf
-#define MTK_GDM1_JMB_LEN_SHIFT 28
-#define MTK_GDM1_ICS_EN BIT(22)
-#define MTK_GDM1_TCS_EN BIT(21)
-#define MTK_GDM1_UCS_EN BIT(20)
-#define MTK_GDM1_JMB_EN BIT(19)
-#define MTK_GDM1_STRPCRC BIT(16)
-#define MTK_GDM1_UFRC_P_CPU (0 << 12)
-#define MTK_GDM1_UFRC_P_GDMA1 (1 << 12)
-#define MTK_GDM1_UFRC_P_PPE (6 << 12)
-
-/* checksums */
-#define MTK_ICS_GEN_EN BIT(2)
-#define MTK_UCS_GEN_EN BIT(1)
-#define MTK_TCS_GEN_EN BIT(0)
-
-/* dma mode */
-#define MTK_PDMA BIT(0)
-#define MTK_QDMA BIT(1)
-#define MTK_PDMA_RX_QDMA_TX (MTK_PDMA | MTK_QDMA)
-
-/* dma ring */
-#define MTK_PST_DRX_IDX0 BIT(16)
-#define MTK_PST_DTX_IDX3 BIT(3)
-#define MTK_PST_DTX_IDX2 BIT(2)
-#define MTK_PST_DTX_IDX1 BIT(1)
-#define MTK_PST_DTX_IDX0 BIT(0)
-
-#define MTK_RX_2B_OFFSET BIT(31)
-#define MTK_TX_WB_DDONE BIT(6)
-#define MTK_RX_DMA_BUSY BIT(3)
-#define MTK_TX_DMA_BUSY BIT(1)
-#define MTK_RX_DMA_EN BIT(2)
-#define MTK_TX_DMA_EN BIT(0)
-
-#define MTK_PDMA_SIZE_4DWORDS (0 << 4)
-#define MTK_PDMA_SIZE_8DWORDS (1 << 4)
-#define MTK_PDMA_SIZE_16DWORDS (2 << 4)
-
-#define MTK_US_CYC_CNT_MASK 0xff
-#define MTK_US_CYC_CNT_SHIFT 0x8
-#define MTK_US_CYC_CNT_DIVISOR 1000000
-
-/* PDMA descriptor rxd2 */
-#define RX_DMA_DONE BIT(31)
-#define RX_DMA_LSO BIT(30)
-#define RX_DMA_PLEN0(_x) (((_x) & 0x3fff) << 16)
-#define RX_DMA_GET_PLEN0(_x) (((_x) >> 16) & 0x3fff)
-#define RX_DMA_TAG BIT(15)
-
-/* PDMA descriptor rxd3 */
-#define RX_DMA_TPID(_x) (((_x) >> 16) & 0xffff)
-#define RX_DMA_VID(_x) ((_x) & 0xfff)
-
-/* PDMA descriptor rxd4 */
-#define RX_DMA_L4VALID BIT(30)
-#define RX_DMA_FPORT_SHIFT 19
-#define RX_DMA_FPORT_MASK 0x7
-
-struct mtk_rx_dma {
- unsigned int rxd1;
- unsigned int rxd2;
- unsigned int rxd3;
- unsigned int rxd4;
-} __packed __aligned(4);
-
-/* PDMA tx descriptor bits */
-#define TX_DMA_BUF_LEN 0x3fff
-#define TX_DMA_PLEN0_MASK (TX_DMA_BUF_LEN << 16)
-#define TX_DMA_PLEN0(_x) (((_x) & TX_DMA_BUF_LEN) << 16)
-#define TX_DMA_PLEN1(_x) ((_x) & TX_DMA_BUF_LEN)
-#define TX_DMA_GET_PLEN0(_x) (((_x) >> 16) & TX_DMA_BUF_LEN)
-#define TX_DMA_GET_PLEN1(_x) ((_x) & TX_DMA_BUF_LEN)
-#define TX_DMA_LS1 BIT(14)
-#define TX_DMA_LS0 BIT(30)
-#define TX_DMA_DONE BIT(31)
-#define TX_DMA_FPORT_SHIFT 25
-#define TX_DMA_FPORT_MASK 0x7
-#define TX_DMA_INS_VLAN_MT7621 BIT(16)
-#define TX_DMA_INS_VLAN BIT(7)
-#define TX_DMA_INS_PPPOE BIT(12)
-#define TX_DMA_TAG BIT(15)
-#define TX_DMA_TAG_MASK BIT(15)
-#define TX_DMA_QN(_x) ((_x) << 16)
-#define TX_DMA_PN(_x) ((_x) << 24)
-#define TX_DMA_QN_MASK TX_DMA_QN(0x7)
-#define TX_DMA_PN_MASK TX_DMA_PN(0x7)
-#define TX_DMA_UDF BIT(20)
-#define TX_DMA_CHKSUM (0x7 << 29)
-#define TX_DMA_TSO BIT(28)
-#define TX_DMA_DESP4_DEF (TX_DMA_QN(3) | TX_DMA_PN(1))
-
-/* frame engine counters */
-#define MTK_PPE_AC_BCNT0 (MTK_CMTABLE_OFFSET + 0x00)
-#define MTK_GDMA1_TX_GBCNT (MTK_CMTABLE_OFFSET + 0x300)
-#define MTK_GDMA2_TX_GBCNT (MTK_GDMA1_TX_GBCNT + 0x40)
-
-/* phy device flags */
-#define MTK_PHY_FLAG_PORT BIT(0)
-#define MTK_PHY_FLAG_ATTACH BIT(1)
-
-struct mtk_tx_dma {
- unsigned int txd1;
- unsigned int txd2;
- unsigned int txd3;
- unsigned int txd4;
-} __packed __aligned(4);
-
-struct mtk_eth;
-struct mtk_mac;
-
-/* manage the attached phys */
-struct mtk_phy {
- spinlock_t lock;
-
- struct phy_device *phy[8];
- struct device_node *phy_node[8];
- const __be32 *phy_fixed[8];
- int duplex[8];
- int speed[8];
- int tx_fc[8];
- int rx_fc[8];
- int (*connect)(struct mtk_mac *mac);
- void (*disconnect)(struct mtk_mac *mac);
- void (*start)(struct mtk_mac *mac);
- void (*stop)(struct mtk_mac *mac);
-};
-
-/* struct mtk_soc_data - the structure that holds the SoC specific data
- * @reg_table: Some of the legacy registers changed their location
- * over time. Their offsets are stored in this table
- *
- * @init_data: Some features depend on the silicon revision. This
- * callback allows runtime modification of the content of
- * this struct
- * @reset_fe: This callback is used to trigger the reset of the frame
- * engine
- * @set_mac: This callback is used to set the unicast mac address
- * filter
- * @fwd_config: This callback is used to setup the forward config
- * register of the MAC
- * @switch_init: This callback is used to bring up the switch core
- * @port_init: Some SoCs have ports that can be router to a switch port
- * or an external PHY. This callback is used to setup these
- * ports.
- * @has_carrier: This callback allows driver to check if there is a cable
- * attached.
- * @mdio_init: This callbck is used to setup the MDIO bus if one is
- * present
- * @mdio_cleanup: This callback is used to cleanup the MDIO state.
- * @mdio_write: This callback is used to write data to the MDIO bus.
- * @mdio_read: This callback is used to write data to the MDIO bus.
- * @mdio_adjust_link: This callback is used to apply the PHY settings.
- * @piac_offset: the PIAC register has a different different base offset
- * @hw_features: feature set depends on the SoC type
- * @dma_ring_size: allow GBit SoCs to set bigger rings than FE SoCs
- * @napi_weight: allow GBit SoCs to set bigger napi weight than FE SoCs
- * @dma_type: SoCs is PDMA, QDMA or a mix of the 2
- * @pdma_glo_cfg: the default DMA configuration
- * @rx_int: the TX interrupt bits used by the SoC
- * @tx_int: the TX interrupt bits used by the SoC
- * @status_int: the Status interrupt bits used by the SoC
- * @checksum_bit: the bits used to turn on HW checksumming
- * @txd4: default value of the TXD4 descriptor
- * @mac_count: the number of MACs that the SoC has
- * @new_stats: there is a old and new way to read hardware stats
- * registers
- * @jumbo_frame: does the SoC support jumbo frames ?
- * @rx_2b_offset: tell the rx dma to offset the data by 2 bytes
- * @rx_sg_dma: scatter gather support
- * @padding_64b enable 64 bit padding
- * @padding_bug: rt2880 has a padding bug
- * @has_switch: does the SoC have a built-in switch
- *
- * Although all of the supported SoCs share the same basic functionality, there
- * are several SoC specific functions and features that we need to support. This
- * struct holds the SoC specific data so that the common core can figure out
- * how to setup and use these differences.
- */
-struct mtk_soc_data {
- const u16 *reg_table;
-
- void (*init_data)(struct mtk_soc_data *data, struct net_device *netdev);
- void (*reset_fe)(struct mtk_eth *eth);
- void (*set_mac)(struct mtk_mac *mac, unsigned char *macaddr);
- int (*fwd_config)(struct mtk_eth *eth);
- int (*switch_init)(struct mtk_eth *eth);
- void (*port_init)(struct mtk_eth *eth, struct mtk_mac *mac,
- struct device_node *port);
- int (*has_carrier)(struct mtk_eth *eth);
- int (*mdio_init)(struct mtk_eth *eth);
- void (*mdio_cleanup)(struct mtk_eth *eth);
- int (*mdio_write)(struct mii_bus *bus, int phy_addr, int phy_reg,
- u16 val);
- int (*mdio_read)(struct mii_bus *bus, int phy_addr, int phy_reg);
- void (*mdio_adjust_link)(struct mtk_eth *eth, int port);
- u32 piac_offset;
- netdev_features_t hw_features;
- u32 dma_ring_size;
- u32 napi_weight;
- u32 dma_type;
- u32 pdma_glo_cfg;
- u32 rx_int;
- u32 tx_int;
- u32 status_int;
- u32 checksum_bit;
- u32 txd4;
- u32 mac_count;
-
- u32 new_stats:1;
- u32 jumbo_frame:1;
- u32 rx_2b_offset:1;
- u32 rx_sg_dma:1;
- u32 padding_64b:1;
- u32 padding_bug:1;
- u32 has_switch:1;
-};
-
-#define MTK_STAT_OFFSET 0x40
-
-/* struct mtk_hw_stats - the structure that holds the traffic statistics.
- * @stats_lock: make sure that stats operations are atomic
- * @reg_offset: the status register offset of the SoC
- * @syncp: the refcount
- *
- * All of the supported SoCs have hardware counters for traffic statstics.
- * Whenever the status IRQ triggers we can read the latest stats from these
- * counters and store them in this struct.
- */
-struct mtk_hw_stats {
- spinlock_t stats_lock;
- u32 reg_offset;
- struct u64_stats_sync syncp;
-
- u64 tx_bytes;
- u64 tx_packets;
- u64 tx_skip;
- u64 tx_collisions;
- u64 rx_bytes;
- u64 rx_packets;
- u64 rx_overflow;
- u64 rx_fcs_errors;
- u64 rx_short_errors;
- u64 rx_long_errors;
- u64 rx_checksum_errors;
- u64 rx_flow_control_packets;
-};
-
-/* PDMA descriptor can point at 1-2 segments. This enum allows us to track how
- * memory was allocated so that it can be freed properly
- */
-enum mtk_tx_flags {
- MTK_TX_FLAGS_SINGLE0 = 0x01,
- MTK_TX_FLAGS_PAGE0 = 0x02,
- MTK_TX_FLAGS_PAGE1 = 0x04,
-};
-
-/* struct mtk_tx_buf - This struct holds the pointers to the memory pointed at
- * by the TX descriptor s
- * @skb: The SKB pointer of the packet being sent
- * @dma_addr0: The base addr of the first segment
- * @dma_len0: The length of the first segment
- * @dma_addr1: The base addr of the second segment
- * @dma_len1: The length of the second segment
- */
-struct mtk_tx_buf {
- struct sk_buff *skb;
- u32 flags;
- DEFINE_DMA_UNMAP_ADDR(dma_addr0);
- DEFINE_DMA_UNMAP_LEN(dma_len0);
- DEFINE_DMA_UNMAP_ADDR(dma_addr1);
- DEFINE_DMA_UNMAP_LEN(dma_len1);
-};
-
-/* struct mtk_tx_ring - This struct holds info describing a TX ring
- * @tx_dma: The descriptor ring
- * @tx_buf: The memory pointed at by the ring
- * @tx_phys: The physical addr of tx_buf
- * @tx_next_free: Pointer to the next free descriptor
- * @tx_last_free: Pointer to the last free descriptor
- * @tx_thresh: The threshold of minimum amount of free descriptors
- * @tx_map: Callback to map a new packet into the ring
- * @tx_poll: Callback for the housekeeping function
- * @tx_clean: Callback for the cleanup function
- * @tx_ring_size: How many descriptors are in the ring
- * @tx_free_idx: The index of th next free descriptor
- * @tx_next_idx: QDMA uses a linked list. This element points to the next
- * free descriptor in the list
- * @tx_free_count: QDMA uses a linked list. Track how many free descriptors
- * are present
- */
-struct mtk_tx_ring {
- struct mtk_tx_dma *tx_dma;
- struct mtk_tx_buf *tx_buf;
- dma_addr_t tx_phys;
- struct mtk_tx_dma *tx_next_free;
- struct mtk_tx_dma *tx_last_free;
- u16 tx_thresh;
- int (*tx_map)(struct sk_buff *skb, struct net_device *dev, int tx_num,
- struct mtk_tx_ring *ring, bool gso);
- int (*tx_poll)(struct mtk_eth *eth, int budget, bool *tx_again);
- void (*tx_clean)(struct mtk_eth *eth);
-
- /* PDMA only */
- u16 tx_ring_size;
- u16 tx_free_idx;
-
- /* QDMA only */
- u16 tx_next_idx;
- atomic_t tx_free_count;
-};
-
-/* struct mtk_rx_ring - This struct holds info describing a RX ring
- * @rx_dma: The descriptor ring
- * @rx_data: The memory pointed at by the ring
- * @trx_phys: The physical addr of rx_buf
- * @rx_ring_size: How many descriptors are in the ring
- * @rx_buf_size: The size of each packet buffer
- * @rx_calc_idx: The current head of ring
- */
-struct mtk_rx_ring {
- struct mtk_rx_dma *rx_dma;
- u8 **rx_data;
- dma_addr_t rx_phys;
- u16 rx_ring_size;
- u16 frag_size;
- u16 rx_buf_size;
- u16 rx_calc_idx;
-};
-
-/* currently no SoC has more than 2 macs */
-#define MTK_MAX_DEVS 2
-
-/* struct mtk_eth - This is the main datasructure for holding the state
- * of the driver
- * @dev: The device pointer
- * @base: The mapped register i/o base
- * @page_lock: Make sure that register operations are atomic
- * @soc: pointer to our SoC specific data
- * @dummy_dev: we run 2 netdevs on 1 physical DMA ring and need a
- * dummy for NAPI to work
- * @netdev: The netdev instances
- * @mac: Each netdev is linked to a physical MAC
- * @switch_np: The phandle for the switch
- * @irq: The IRQ that we are using
- * @msg_enable: Ethtool msg level
- * @ysclk: The sysclk rate - neeed for calibration
- * @ethsys: The register map pointing at the range used to setup
- * MII modes
- * @dma_refcnt: track how many netdevs are using the DMA engine
- * @tx_ring: Pointer to the memore holding info about the TX ring
- * @rx_ring: Pointer to the memore holding info about the RX ring
- * @rx_napi: The NAPI struct
- * @scratch_ring: Newer SoCs need memory for a second HW managed TX ring
- * @scratch_head: The scratch memory that scratch_ring points to.
- * @phy: Info about the attached PHYs
- * @mii_bus: If there is a bus we need to create an instance for it
- * @link: Track if the ports have a physical link
- * @sw_priv: Pointer to the switches private data
- * @vlan_map: RX VID tracking
- */
-
-struct mtk_eth {
- struct device *dev;
- void __iomem *base;
- spinlock_t page_lock;
- struct mtk_soc_data *soc;
- struct net_device dummy_dev;
- struct net_device *netdev[MTK_MAX_DEVS];
- struct mtk_mac *mac[MTK_MAX_DEVS];
- struct device_node *switch_np;
- int irq;
- u32 msg_enable;
- unsigned long sysclk;
- struct regmap *ethsys;
- atomic_t dma_refcnt;
- struct mtk_tx_ring tx_ring;
- struct mtk_rx_ring rx_ring[2];
- struct napi_struct rx_napi;
- struct mtk_tx_dma *scratch_ring;
- void *scratch_head;
- struct mtk_phy *phy;
- struct mii_bus *mii_bus;
- int link[8];
- void *sw_priv;
- unsigned long vlan_map;
-};
-
-/* struct mtk_mac - the structure that holds the info about the MACs of the
- * SoC
- * @id: The number of the MAC
- * @of_node: Our devicetree node
- * @hw: Backpointer to our main datastruture
- * @hw_stats: Packet statistics counter
- * @phy_dev: The attached PHY if available
- * @phy_flags: The PHYs flags
- * @pending_work: The workqueue used to reset the dma ring
- */
-struct mtk_mac {
- int id;
- struct device_node *of_node;
- struct mtk_eth *hw;
- struct mtk_hw_stats *hw_stats;
- struct phy_device *phy_dev;
- u32 phy_flags;
- struct work_struct pending_work;
-};
-
-/* the struct describing the SoC. these are declared in the soc_xyz.c files */
-extern const struct of_device_id of_mtk_match[];
-
-/* read the hardware status register */
-void mtk_stats_update_mac(struct mtk_mac *mac);
-
-/* default checksum setup handler */
-void mtk_reset(struct mtk_eth *eth, u32 reset_bits);
-
-/* register i/o wrappers */
-void mtk_w32(struct mtk_eth *eth, u32 val, unsigned int reg);
-u32 mtk_r32(struct mtk_eth *eth, unsigned int reg);
-
-/* default clock calibration handler */
-int mtk_set_clock_cycle(struct mtk_eth *eth);
-
-/* default checksum setup handler */
-void mtk_csum_config(struct mtk_eth *eth);
-
-/* default forward config handler */
-void mtk_fwd_config(struct mtk_eth *eth);
-
-#endif /* MTK_ETH_H */
+++ /dev/null
-/* This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * Copyright (C) 2009-2016 John Crispin <blogic@openwrt.org>
- * Copyright (C) 2009-2016 Felix Fietkau <nbd@openwrt.org>
- * Copyright (C) 2013-2016 Michael Lee <igvtee@gmail.com>
- */
-
-#include <linux/module.h>
-#include <linux/platform_device.h>
-#include <linux/if_vlan.h>
-#include <linux/of_net.h>
-
-#include <asm/mach-ralink/ralink_regs.h>
-
-#include "mtk_eth_soc.h"
-#include "gsw_mt7620.h"
-#include "mdio.h"
-
-#define MT7620_CDMA_CSG_CFG 0x400
-#define MT7621_CDMP_IG_CTRL (MT7620_CDMA_CSG_CFG + 0x00)
-#define MT7621_CDMP_EG_CTRL (MT7620_CDMA_CSG_CFG + 0x04)
-#define MT7621_RESET_FE BIT(6)
-#define MT7621_L4_VALID BIT(24)
-
-#define MT7621_TX_DMA_UDF BIT(19)
-
-#define CDMA_ICS_EN BIT(2)
-#define CDMA_UCS_EN BIT(1)
-#define CDMA_TCS_EN BIT(0)
-
-#define GDMA_ICS_EN BIT(22)
-#define GDMA_TCS_EN BIT(21)
-#define GDMA_UCS_EN BIT(20)
-
-/* frame engine counters */
-#define MT7621_REG_MIB_OFFSET 0x2000
-#define MT7621_PPE_AC_BCNT0 (MT7621_REG_MIB_OFFSET + 0x00)
-#define MT7621_GDM1_TX_GBCNT (MT7621_REG_MIB_OFFSET + 0x400)
-#define MT7621_GDM2_TX_GBCNT (MT7621_GDM1_TX_GBCNT + 0x40)
-
-#define GSW_REG_GDMA1_MAC_ADRL 0x508
-#define GSW_REG_GDMA1_MAC_ADRH 0x50C
-#define GSW_REG_GDMA2_MAC_ADRL 0x1508
-#define GSW_REG_GDMA2_MAC_ADRH 0x150C
-
-#define MT7621_MTK_RST_GL 0x04
-#define MT7620_MTK_INT_STATUS2 0x08
-
-/* MTK_INT_STATUS reg on mt7620 define CNT_GDM1_AF at BIT(29)
- * but after test it should be BIT(13).
- */
-#define MT7621_MTK_GDM1_AF BIT(28)
-#define MT7621_MTK_GDM2_AF BIT(29)
-
-static const u16 mt7621_reg_table[MTK_REG_COUNT] = {
- [MTK_REG_PDMA_GLO_CFG] = RT5350_PDMA_GLO_CFG,
- [MTK_REG_PDMA_RST_CFG] = RT5350_PDMA_RST_CFG,
- [MTK_REG_DLY_INT_CFG] = RT5350_DLY_INT_CFG,
- [MTK_REG_TX_BASE_PTR0] = RT5350_TX_BASE_PTR0,
- [MTK_REG_TX_MAX_CNT0] = RT5350_TX_MAX_CNT0,
- [MTK_REG_TX_CTX_IDX0] = RT5350_TX_CTX_IDX0,
- [MTK_REG_TX_DTX_IDX0] = RT5350_TX_DTX_IDX0,
- [MTK_REG_RX_BASE_PTR0] = RT5350_RX_BASE_PTR0,
- [MTK_REG_RX_MAX_CNT0] = RT5350_RX_MAX_CNT0,
- [MTK_REG_RX_CALC_IDX0] = RT5350_RX_CALC_IDX0,
- [MTK_REG_RX_DRX_IDX0] = RT5350_RX_DRX_IDX0,
- [MTK_REG_MTK_INT_ENABLE] = RT5350_MTK_INT_ENABLE,
- [MTK_REG_MTK_INT_STATUS] = RT5350_MTK_INT_STATUS,
- [MTK_REG_MTK_DMA_VID_BASE] = 0,
- [MTK_REG_MTK_COUNTER_BASE] = MT7621_GDM1_TX_GBCNT,
- [MTK_REG_MTK_RST_GL] = MT7621_MTK_RST_GL,
- [MTK_REG_MTK_INT_STATUS2] = MT7620_MTK_INT_STATUS2,
-};
-
-static void mt7621_mtk_reset(struct mtk_eth *eth)
-{
- mtk_reset(eth, MT7621_RESET_FE);
-}
-
-static int mt7621_fwd_config(struct mtk_eth *eth)
-{
- /* Setup GMAC1 only, there is no support for GMAC2 yet */
- mtk_w32(eth, mtk_r32(eth, MT7620_GDMA1_FWD_CFG) & ~0xffff,
- MT7620_GDMA1_FWD_CFG);
-
- /* Enable RX checksum */
- mtk_w32(eth, mtk_r32(eth, MT7620_GDMA1_FWD_CFG) | (GDMA_ICS_EN |
- GDMA_TCS_EN | GDMA_UCS_EN),
- MT7620_GDMA1_FWD_CFG);
-
- /* Enable RX VLan Offloading */
- mtk_w32(eth, 0, MT7621_CDMP_EG_CTRL);
-
- return 0;
-}
-
-static void mt7621_set_mac(struct mtk_mac *mac, unsigned char *hwaddr)
-{
- unsigned long flags;
-
- spin_lock_irqsave(&mac->hw->page_lock, flags);
- if (mac->id == 0) {
- mtk_w32(mac->hw, (hwaddr[0] << 8) | hwaddr[1],
- GSW_REG_GDMA1_MAC_ADRH);
- mtk_w32(mac->hw, (hwaddr[2] << 24) | (hwaddr[3] << 16) |
- (hwaddr[4] << 8) | hwaddr[5],
- GSW_REG_GDMA1_MAC_ADRL);
- }
- if (mac->id == 1) {
- mtk_w32(mac->hw, (hwaddr[0] << 8) | hwaddr[1],
- GSW_REG_GDMA2_MAC_ADRH);
- mtk_w32(mac->hw, (hwaddr[2] << 24) | (hwaddr[3] << 16) |
- (hwaddr[4] << 8) | hwaddr[5],
- GSW_REG_GDMA2_MAC_ADRL);
- }
- spin_unlock_irqrestore(&mac->hw->page_lock, flags);
-}
-
-static struct mtk_soc_data mt7621_data = {
- .hw_features = NETIF_F_IP_CSUM | NETIF_F_RXCSUM |
- NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX |
- NETIF_F_SG | NETIF_F_TSO | NETIF_F_TSO6 |
- NETIF_F_IPV6_CSUM,
- .dma_type = MTK_PDMA,
- .dma_ring_size = 256,
- .napi_weight = 64,
- .new_stats = 1,
- .padding_64b = 1,
- .rx_2b_offset = 1,
- .rx_sg_dma = 1,
- .has_switch = 1,
- .mac_count = 2,
- .reset_fe = mt7621_mtk_reset,
- .set_mac = mt7621_set_mac,
- .fwd_config = mt7621_fwd_config,
- .switch_init = mtk_gsw_init,
- .reg_table = mt7621_reg_table,
- .pdma_glo_cfg = MTK_PDMA_SIZE_16DWORDS,
- .rx_int = RT5350_RX_DONE_INT,
- .tx_int = RT5350_TX_DONE_INT,
- .status_int = MT7621_MTK_GDM1_AF | MT7621_MTK_GDM2_AF,
- .checksum_bit = MT7621_L4_VALID,
- .has_carrier = mt7620_has_carrier,
- .mdio_read = mt7620_mdio_read,
- .mdio_write = mt7620_mdio_write,
- .mdio_adjust_link = mt7620_mdio_link_adjust,
-};
-
-const struct of_device_id of_mtk_match[] = {
- { .compatible = "mediatek,mt7621-eth", .data = &mt7621_data },
- {},
-};
-
-MODULE_DEVICE_TABLE(of, of_mtk_match);
config PCI_MT7621
tristate "MediaTek MT7621 PCI Controller"
depends on RALINK
+ depends on PCI
select PCI_DRIVERS_GENERIC
help
This selects a driver for the MediaTek MT7621 PCI Controller.
goto no_phy;
phydev = of_phy_connect(dev, phy_node, cvm_oct_adjust_link, 0,
- PHY_INTERFACE_MODE_GMII);
+ priv->phy_mode);
of_node_put(phy_node);
if (!phydev)
return np;
}
-static void cvm_set_rgmii_delay(struct device_node *np, int iface, int port)
+static void cvm_set_rgmii_delay(struct octeon_ethernet *priv, int iface,
+ int port)
{
+ struct device_node *np = priv->of_node;
u32 delay_value;
+ bool rx_delay;
+ bool tx_delay;
- if (!of_property_read_u32(np, "rx-delay", &delay_value))
+ /* By default, both RX/TX delay is enabled in
+ * __cvmx_helper_rgmii_enable().
+ */
+ rx_delay = true;
+ tx_delay = true;
+
+ if (!of_property_read_u32(np, "rx-delay", &delay_value)) {
cvmx_write_csr(CVMX_ASXX_RX_CLK_SETX(port, iface), delay_value);
- if (!of_property_read_u32(np, "tx-delay", &delay_value))
+ rx_delay = delay_value > 0;
+ }
+ if (!of_property_read_u32(np, "tx-delay", &delay_value)) {
cvmx_write_csr(CVMX_ASXX_TX_CLK_SETX(port, iface), delay_value);
+ tx_delay = delay_value > 0;
+ }
+
+ if (!rx_delay && !tx_delay)
+ priv->phy_mode = PHY_INTERFACE_MODE_RGMII_ID;
+ else if (!rx_delay)
+ priv->phy_mode = PHY_INTERFACE_MODE_RGMII_RXID;
+ else if (!tx_delay)
+ priv->phy_mode = PHY_INTERFACE_MODE_RGMII_TXID;
+ else
+ priv->phy_mode = PHY_INTERFACE_MODE_RGMII;
}
static int cvm_oct_probe(struct platform_device *pdev)
priv->port = port;
priv->queue = cvmx_pko_get_base_queue(priv->port);
priv->fau = fau - cvmx_pko_get_num_queues(port) * 4;
+ priv->phy_mode = PHY_INTERFACE_MODE_NA;
for (qos = 0; qos < 16; qos++)
skb_queue_head_init(&priv->tx_free_list[qos]);
for (qos = 0; qos < cvmx_pko_get_num_queues(port);
break;
case CVMX_HELPER_INTERFACE_MODE_SGMII:
+ priv->phy_mode = PHY_INTERFACE_MODE_SGMII;
dev->netdev_ops = &cvm_oct_sgmii_netdev_ops;
strcpy(dev->name, "eth%d");
break;
strcpy(dev->name, "spi%d");
break;
- case CVMX_HELPER_INTERFACE_MODE_RGMII:
case CVMX_HELPER_INTERFACE_MODE_GMII:
+ priv->phy_mode = PHY_INTERFACE_MODE_GMII;
+ dev->netdev_ops = &cvm_oct_rgmii_netdev_ops;
+ strcpy(dev->name, "eth%d");
+ break;
+
+ case CVMX_HELPER_INTERFACE_MODE_RGMII:
dev->netdev_ops = &cvm_oct_rgmii_netdev_ops;
strcpy(dev->name, "eth%d");
- cvm_set_rgmii_delay(priv->of_node, interface,
+ cvm_set_rgmii_delay(priv, interface,
port_index);
break;
}
#define OCTEON_ETHERNET_H
#include <linux/of.h>
-
+#include <linux/phy.h>
#include <asm/octeon/cvmx-helper-board.h>
/**
* cvmx_helper_interface_mode_t
*/
int imode;
+ /* PHY mode */
+ phy_interface_t phy_mode;
/* List of outstanding tx buffers per queue */
struct sk_buff_head tx_free_list[16];
unsigned int last_speed;
{
unsigned char lob;
int ret, i;
- struct dcon_gpio *pin = &gpios_asis[0];
+ const struct dcon_gpio *pin = &gpios_asis[0];
for (i = 0; i < ARRAY_SIZE(gpios_asis); i++) {
gpios[i] = devm_gpiod_get(&dcon->client->dev, pin[i].name,
pxmitpriv->free_xmit_extbuf_cnt = num_xmit_extbuf;
- rtw_alloc_hwxmits(padapter);
+ res = rtw_alloc_hwxmits(padapter);
+ if (res == _FAIL)
+ goto exit;
rtw_init_hwxmits(pxmitpriv->hwxmits, pxmitpriv->hwxmit_entry);
for (i = 0; i < 4; i++)
return res;
}
-void rtw_alloc_hwxmits(struct adapter *padapter)
+s32 rtw_alloc_hwxmits(struct adapter *padapter)
{
struct hw_xmit *hwxmits;
struct xmit_priv *pxmitpriv = &padapter->xmitpriv;
pxmitpriv->hwxmits = kcalloc(pxmitpriv->hwxmit_entry,
sizeof(struct hw_xmit), GFP_KERNEL);
+ if (!pxmitpriv->hwxmits)
+ return _FAIL;
hwxmits = pxmitpriv->hwxmits;
hwxmits[1] .sta_queue = &pxmitpriv->vi_pending;
hwxmits[2] .sta_queue = &pxmitpriv->be_pending;
hwxmits[3] .sta_queue = &pxmitpriv->bk_pending;
+ return _SUCCESS;
}
void rtw_free_hwxmits(struct adapter *padapter)
void rtw_init_hwxmits(struct hw_xmit *phwxmit, int entry);
s32 _rtw_init_xmit_priv(struct xmit_priv *pxmitpriv, struct adapter *padapter);
void _rtw_free_xmit_priv(struct xmit_priv *pxmitpriv);
-void rtw_alloc_hwxmits(struct adapter *padapter);
+s32 rtw_alloc_hwxmits(struct adapter *padapter);
void rtw_free_hwxmits(struct adapter *padapter);
s32 rtw_xmit(struct adapter *padapter, struct sk_buff **pkt);
static u8 read_bbreg_hdl(struct _adapter *padapter, u8 *pbuf)
{
- u32 val;
- void (*pcmd_callback)(struct _adapter *dev, struct cmd_obj *pcmd);
struct cmd_obj *pcmd = (struct cmd_obj *)pbuf;
- if (pcmd->rsp && pcmd->rspsz > 0)
- memcpy(pcmd->rsp, (u8 *)&val, pcmd->rspsz);
- pcmd_callback = cmd_callback[pcmd->cmdcode].callback;
- if (!pcmd_callback)
- r8712_free_cmd_obj(pcmd);
- else
- pcmd_callback(padapter, pcmd);
+ r8712_free_cmd_obj(pcmd);
return H2C_SUCCESS;
}
static struct _cmd_callback cmd_callback[] = {
{GEN_CMD_CODE(_Read_MACREG), NULL}, /*0*/
{GEN_CMD_CODE(_Write_MACREG), NULL},
- {GEN_CMD_CODE(_Read_BBREG), &r8712_getbbrfreg_cmdrsp_callback},
+ {GEN_CMD_CODE(_Read_BBREG), NULL},
{GEN_CMD_CODE(_Write_BBREG), NULL},
{GEN_CMD_CODE(_Read_RFREG), &r8712_getbbrfreg_cmdrsp_callback},
{GEN_CMD_CODE(_Write_RFREG), NULL}, /*5*/
}
}
- rtw_alloc_hwxmits(padapter);
+ res = rtw_alloc_hwxmits(padapter);
+ if (res == _FAIL)
+ goto exit;
rtw_init_hwxmits(pxmitpriv->hwxmits, pxmitpriv->hwxmit_entry);
for (i = 0; i < 4; i++) {
return res;
}
-void rtw_alloc_hwxmits(struct adapter *padapter)
+s32 rtw_alloc_hwxmits(struct adapter *padapter)
{
struct hw_xmit *hwxmits;
struct xmit_priv *pxmitpriv = &padapter->xmitpriv;
pxmitpriv->hwxmits = rtw_zmalloc(sizeof(struct hw_xmit) * pxmitpriv->hwxmit_entry);
- if (pxmitpriv->hwxmits == NULL) {
- DBG_871X("alloc hwxmits fail!...\n");
- return;
- }
+ if (!pxmitpriv->hwxmits)
+ return _FAIL;
hwxmits = pxmitpriv->hwxmits;
}
-
+ return _SUCCESS;
}
void rtw_free_hwxmits(struct adapter *padapter)
void _rtw_free_xmit_priv (struct xmit_priv *pxmitpriv);
-void rtw_alloc_hwxmits(struct adapter *padapter);
+s32 rtw_alloc_hwxmits(struct adapter *padapter);
void rtw_free_hwxmits(struct adapter *padapter);
rtlpriv->phydm.internal =
kzalloc(sizeof(struct phy_dm_struct), GFP_KERNEL);
+ if (!rtlpriv->phydm.internal)
+ return 0;
_rtl_phydm_init_com_info(rtlpriv, ic, params);
u1_rsvd_page_loc, 3);
skb = dev_alloc_skb(totalpacketlen);
+ if (!skb)
+ return;
memcpy((u8 *)skb_put(skb, totalpacketlen), &reserved_page_packet,
totalpacketlen);
return -EINVAL;
spin_lock_irqsave(&speakup_info.spinlock, flags);
+ synth_soft.alive = 1;
while (1) {
prepare_to_wait(&speakup_event, &wait, TASK_INTERRUPTIBLE);
- if (!unicode)
- synth_buffer_skip_nonlatin1();
- if (!synth_buffer_empty() || speakup_info.flushing)
- break;
+ if (synth_current() == &synth_soft) {
+ if (!unicode)
+ synth_buffer_skip_nonlatin1();
+ if (!synth_buffer_empty() || speakup_info.flushing)
+ break;
+ }
spin_unlock_irqrestore(&speakup_info.spinlock, flags);
if (fp->f_flags & O_NONBLOCK) {
finish_wait(&speakup_event, &wait);
/* Keep 3 bytes available for a 16bit UTF-8-encoded character */
while (chars_sent <= count - bytes_per_ch) {
+ if (synth_current() != &synth_soft)
+ break;
if (speakup_info.flushing) {
speakup_info.flushing = 0;
ch = '\x18';
poll_wait(fp, &speakup_event, wait);
spin_lock_irqsave(&speakup_info.spinlock, flags);
- if (!synth_buffer_empty() || speakup_info.flushing)
+ if (synth_current() == &synth_soft &&
+ (!synth_buffer_empty() || speakup_info.flushing))
ret = EPOLLIN | EPOLLRDNORM;
spin_unlock_irqrestore(&speakup_info.spinlock, flags);
return ret;
int synth_release_region(unsigned long start, unsigned long n);
int synth_add(struct spk_synth *in_synth);
void synth_remove(struct spk_synth *in_synth);
+struct spk_synth *synth_current(void);
extern struct speakup_info_t speakup_info;
}
EXPORT_SYMBOL_GPL(synth_remove);
+struct spk_synth *synth_current(void)
+{
+ return synth;
+}
+EXPORT_SYMBOL_GPL(synth_current);
+
short spk_punc_masks[] = { 0, SOME, MOST, PUNC, PUNC | B_SYM };
struct device_node *fw_node;
const struct of_device_id *of_id;
struct vchiq_drvdata *drvdata;
+ struct device *vchiq_dev;
int err;
of_id = of_match_node(vchiq_of_match, pdev->dev.of_node);
goto failed_platform_init;
}
- if (IS_ERR(device_create(vchiq_class, &pdev->dev, vchiq_devid,
- NULL, "vchiq")))
+ vchiq_dev = device_create(vchiq_class, &pdev->dev, vchiq_devid, NULL,
+ "vchiq");
+ if (IS_ERR(vchiq_dev)) {
+ err = PTR_ERR(vchiq_dev);
goto failed_device_create;
+ }
vchiq_debugfs_init();
return;
}
- MACvIntDisable(priv->PortOffset);
-
spin_lock_irqsave(&priv->lock, flags);
/* Read low level stats */
}
spin_unlock_irqrestore(&priv->lock, flags);
-
- MACvIntEnable(priv->PortOffset, IMR_MASK_VALUE);
}
static void vnt_interrupt_work(struct work_struct *work)
if (priv->vif)
vnt_interrupt_process(priv);
+
+ MACvIntEnable(priv->PortOffset, IMR_MASK_VALUE);
}
static irqreturn_t vnt_interrupt(int irq, void *arg)
{
struct vnt_private *priv = arg;
- if (priv->vif)
- schedule_work(&priv->interrupt_work);
+ schedule_work(&priv->interrupt_work);
+
+ MACvIntDisable(priv->PortOffset);
return IRQ_HANDLED;
}
struct clk *clk;
};
-static inline bool ar933x_uart_console_enabled(void)
-{
- return IS_ENABLED(CONFIG_SERIAL_AR933X_CONSOLE);
-}
-
static inline unsigned int ar933x_uart_read(struct ar933x_uart_port *up,
int offset)
{
.verify_port = ar933x_uart_verify_port,
};
+#ifdef CONFIG_SERIAL_AR933X_CONSOLE
static struct ar933x_uart_port *
ar933x_console_ports[CONFIG_SERIAL_AR933X_NR_UARTS];
.index = -1,
.data = &ar933x_uart_driver,
};
-
-static void ar933x_uart_add_console_port(struct ar933x_uart_port *up)
-{
- if (!ar933x_uart_console_enabled())
- return;
-
- ar933x_console_ports[up->port.line] = up;
-}
+#endif /* CONFIG_SERIAL_AR933X_CONSOLE */
static struct uart_driver ar933x_uart_driver = {
.owner = THIS_MODULE,
baud = ar933x_uart_get_baud(port->uartclk, 0, AR933X_UART_MAX_STEP);
up->max_baud = min_t(unsigned int, baud, AR933X_UART_MAX_BAUD);
- ar933x_uart_add_console_port(up);
+#ifdef CONFIG_SERIAL_AR933X_CONSOLE
+ ar933x_console_ports[up->port.line] = up;
+#endif
ret = uart_add_one_port(&ar933x_uart_driver, &up->port);
if (ret)
{
int ret;
- if (ar933x_uart_console_enabled())
- ar933x_uart_driver.cons = &ar933x_uart_console;
+#ifdef CONFIG_SERIAL_AR933X_CONSOLE
+ ar933x_uart_driver.cons = &ar933x_uart_console;
+#endif
ret = uart_register_driver(&ar933x_uart_driver);
if (ret)
unsigned int pending_status;
spinlock_t lock_suspended;
+ bool hd_start_rx; /* can start RX during half-duplex operation */
+
/* ISO7816 */
unsigned int fidi_min;
unsigned int fidi_max;
__raw_writeb(value, port->membase + ATMEL_US_THR);
}
+static inline int atmel_uart_is_half_duplex(struct uart_port *port)
+{
+ return ((port->rs485.flags & SER_RS485_ENABLED) &&
+ !(port->rs485.flags & SER_RS485_RX_DURING_TX)) ||
+ (port->iso7816.flags & SER_ISO7816_ENABLED);
+}
+
#ifdef CONFIG_SERIAL_ATMEL_PDC
static bool atmel_use_pdc_rx(struct uart_port *port)
{
/* Disable interrupts */
atmel_uart_writel(port, ATMEL_US_IDR, atmel_port->tx_done_mask);
- if (((port->rs485.flags & SER_RS485_ENABLED) &&
- !(port->rs485.flags & SER_RS485_RX_DURING_TX)) ||
- port->iso7816.flags & SER_ISO7816_ENABLED)
+ if (atmel_uart_is_half_duplex(port))
atmel_start_rx(port);
+
}
/*
return;
if (atmel_use_pdc_tx(port) || atmel_use_dma_tx(port))
- if (((port->rs485.flags & SER_RS485_ENABLED) &&
- !(port->rs485.flags & SER_RS485_RX_DURING_TX)) ||
- port->iso7816.flags & SER_ISO7816_ENABLED)
+ if (atmel_uart_is_half_duplex(port))
atmel_stop_rx(port);
if (atmel_use_pdc_tx(port))
*/
if (!uart_circ_empty(xmit))
atmel_tasklet_schedule(atmel_port, &atmel_port->tasklet_tx);
- else if (((port->rs485.flags & SER_RS485_ENABLED) &&
- !(port->rs485.flags & SER_RS485_RX_DURING_TX)) ||
- port->iso7816.flags & SER_ISO7816_ENABLED) {
- /* DMA done, stop TX, start RX for RS485 */
- atmel_start_rx(port);
+ else if (atmel_uart_is_half_duplex(port)) {
+ /*
+ * DMA done, re-enable TXEMPTY and signal that we can stop
+ * TX and start RX for RS485
+ */
+ atmel_port->hd_start_rx = true;
+ atmel_uart_writel(port, ATMEL_US_IER,
+ atmel_port->tx_done_mask);
}
spin_unlock_irqrestore(&port->lock, flags);
sg_dma_len(&atmel_port->sg_rx)/2,
DMA_DEV_TO_MEM,
DMA_PREP_INTERRUPT);
+ if (!desc) {
+ dev_err(port->dev, "Preparing DMA cyclic failed\n");
+ goto chan_err;
+ }
desc->callback = atmel_complete_rx_dma;
desc->callback_param = port;
atmel_port->desc_rx = desc;
struct atmel_uart_port *atmel_port = to_atmel_uart_port(port);
if (pending & atmel_port->tx_done_mask) {
- /* Either PDC or interrupt transmission */
atmel_uart_writel(port, ATMEL_US_IDR,
atmel_port->tx_done_mask);
+
+ /* Start RX if flag was set and FIFO is empty */
+ if (atmel_port->hd_start_rx) {
+ if (!(atmel_uart_readl(port, ATMEL_US_CSR)
+ & ATMEL_US_TXEMPTY))
+ dev_warn(port->dev, "Should start RX, but TX fifo is not empty\n");
+
+ atmel_port->hd_start_rx = false;
+ atmel_start_rx(port);
+ return;
+ }
+
atmel_tasklet_schedule(atmel_port, &atmel_port->tasklet_tx);
}
}
atmel_uart_writel(port, ATMEL_US_IER,
atmel_port->tx_done_mask);
} else {
- if (((port->rs485.flags & SER_RS485_ENABLED) &&
- !(port->rs485.flags & SER_RS485_RX_DURING_TX)) ||
- port->iso7816.flags & SER_ISO7816_ENABLED) {
+ if (atmel_uart_is_half_duplex(port)) {
/* DMA done, stop TX, start RX for RS485 */
atmel_start_rx(port);
}
char *cptr = config;
struct console *cons;
- if (!strlen(config) || isspace(config[0]))
+ if (!strlen(config) || isspace(config[0])) {
+ err = 0;
goto noconfig;
+ }
kgdboc_io_ops.is_console = 0;
kgdb_tty_driver = NULL;
if (spi->dev.of_node) {
const struct of_device_id *of_id =
of_match_device(max310x_dt_ids, &spi->dev);
+ if (!of_id)
+ return -ENODEV;
devtype = (struct max310x_devtype *)of_id->data;
} else {
return -EINVAL;
}
+ if (!match)
+ return -ENODEV;
+
/* Assume that all UART ports have a DT alias or none has */
id = of_alias_get_id(pdev->dev.of_node, "serial");
if (!pdev->dev.of_node || id < 0)
s->port.mapbase = r->start;
s->port.membase = ioremap(r->start, resource_size(r));
+ if (!s->port.membase) {
+ ret = -ENOMEM;
+ goto out_disable_clks;
+ }
s->port.ops = &mxs_auart_ops;
s->port.iotype = UPIO_MEM;
s->port.fifosize = MXS_AUART_FIFO_SIZE;
{
struct uart_port *uport;
struct qcom_geni_serial_port *port;
- int baud;
+ int baud = 9600;
int bits = 8;
int parity = 'n';
int flow = 'n';
ret = i2c_add_driver(&sc16is7xx_i2c_uart_driver);
if (ret < 0) {
pr_err("failed to init sc16is7xx i2c --> %d\n", ret);
- return ret;
+ goto err_i2c;
}
#endif
ret = spi_register_driver(&sc16is7xx_spi_uart_driver);
if (ret < 0) {
pr_err("failed to init sc16is7xx spi --> %d\n", ret);
- return ret;
+ goto err_spi;
}
#endif
return ret;
+
+err_spi:
+#ifdef CONFIG_SERIAL_SC16IS7XX_I2C
+ i2c_del_driver(&sc16is7xx_i2c_uart_driver);
+#endif
+err_i2c:
+ uart_unregister_driver(&sc16is7xx_uart);
+ return ret;
}
module_init(sc16is7xx_init);
if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS)
uart_write_wakeup(port);
- if (uart_circ_empty(xmit)) {
+ if (uart_circ_empty(xmit))
sci_stop_tx(port);
- } else {
- ctrl = serial_port_in(port, SCSCR);
-
- if (port->type != PORT_SCI) {
- serial_port_in(port, SCxSR); /* Dummy read */
- sci_clear_SCxSR(port, SCxSR_TDxE_CLEAR(port));
- }
- ctrl |= SCSCR_TIE;
- serial_port_out(port, SCSCR, ctrl);
- }
}
/* On SH3, SCIF may read end-of-break as a space->mark char */
if (tty && C_HUPCL(tty))
tty_port_lower_dtr_rts(port);
- if (port->ops->shutdown)
+ if (port->ops && port->ops->shutdown)
port->ops->shutdown(port);
}
out:
*/
int tty_port_carrier_raised(struct tty_port *port)
{
- if (port->ops->carrier_raised == NULL)
+ if (!port->ops || !port->ops->carrier_raised)
return 1;
return port->ops->carrier_raised(port);
}
*/
void tty_port_raise_dtr_rts(struct tty_port *port)
{
- if (port->ops->dtr_rts)
+ if (port->ops && port->ops->dtr_rts)
port->ops->dtr_rts(port, 1);
}
EXPORT_SYMBOL(tty_port_raise_dtr_rts);
*/
void tty_port_lower_dtr_rts(struct tty_port *port)
{
- if (port->ops->dtr_rts)
+ if (port->ops && port->ops->dtr_rts)
port->ops->dtr_rts(port, 0);
}
EXPORT_SYMBOL(tty_port_lower_dtr_rts);
if (!tty_port_initialized(port)) {
clear_bit(TTY_IO_ERROR, &tty->flags);
- if (port->ops->activate) {
+ if (port->ops && port->ops->activate) {
int retval = port->ops->activate(port, tty);
if (retval) {
mutex_unlock(&port->mutex);
clear_bit(EVENT_RX_STALL, &acm->flags);
}
- if (test_bit(EVENT_TTY_WAKEUP, &acm->flags)) {
+ if (test_and_clear_bit(EVENT_TTY_WAKEUP, &acm->flags))
tty_port_tty_wakeup(&acm->port);
- clear_bit(EVENT_TTY_WAKEUP, &acm->flags);
- }
}
/*
do {
controller = of_find_node_with_property(controller, "phys");
+ if (!of_device_is_available(controller))
+ continue;
index = 0;
do {
if (arg0 == -1) {
retval = usb_phy_roothub_set_mode(hcd->phy_roothub,
PHY_MODE_USB_HOST_SS);
+ if (retval)
+ retval = usb_phy_roothub_set_mode(hcd->phy_roothub,
+ PHY_MODE_USB_HOST);
if (retval)
goto err_usb_phy_roothub_power_on;
#define PCI_DEVICE_ID_INTEL_BXT_M 0x1aaa
#define PCI_DEVICE_ID_INTEL_APL 0x5aaa
#define PCI_DEVICE_ID_INTEL_KBP 0xa2b0
+#define PCI_DEVICE_ID_INTEL_CMLH 0x02ee
#define PCI_DEVICE_ID_INTEL_GLK 0x31aa
#define PCI_DEVICE_ID_INTEL_CNPLP 0x9dee
#define PCI_DEVICE_ID_INTEL_CNPH 0xa36e
{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_MRFLD),
(kernel_ulong_t) &dwc3_pci_mrfld_properties, },
+ { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_CMLH),
+ (kernel_ulong_t) &dwc3_pci_intel_properties, },
+
{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_SPTLP),
(kernel_ulong_t) &dwc3_pci_intel_properties, },
req->complete = f_hidg_req_complete;
req->context = hidg;
+ spin_unlock_irqrestore(&hidg->write_spinlock, flags);
+
status = usb_ep_queue(hidg->in_ep, req, GFP_ATOMIC);
if (status < 0) {
ERROR(hidg->func.config->cdev,
"usb_ep_queue error on int endpoint %zd\n", status);
- goto release_write_pending_unlocked;
+ goto release_write_pending;
} else {
status = count;
}
- spin_unlock_irqrestore(&hidg->write_spinlock, flags);
return status;
release_write_pending:
spin_lock_irqsave(&hidg->write_spinlock, flags);
-release_write_pending_unlocked:
hidg->write_pending = 0;
spin_unlock_irqrestore(&hidg->write_spinlock, flags);
break;
}
if (&req->req != _req) {
+ ep->stopped = stopped;
spin_unlock_irqrestore(&ep->dev->lock, flags);
return -EINVAL;
}
(void) readl(&ep->dev->pci->pcimstctl);
writel(BIT(DMA_START), &dma->dmastat);
-
- if (!ep->is_in)
- stop_out_naking(ep);
}
static void start_dma(struct net2280_ep *ep, struct net2280_request *req)
writel(BIT(DMA_START), &dma->dmastat);
return;
}
+ stop_out_naking(ep);
}
tmp = dmactl_default;
break;
}
if (&req->req != _req) {
+ ep->stopped = stopped;
spin_unlock_irqrestore(&ep->dev->lock, flags);
- dev_err(&ep->dev->pdev->dev, "%s: Request mismatch\n",
- __func__);
+ ep_dbg(ep->dev, "%s: Request mismatch\n", __func__);
return -EINVAL;
}
printk(KERN_INFO "driver %s\n", hcd_name);
workqueue = create_singlethread_workqueue("u132");
retval = platform_driver_register(&u132_platform_driver);
+ if (retval)
+ destroy_workqueue(workqueue);
+
return retval;
}
return -1;
writel(0, &dbc->regs->control);
- xhci_dbc_mem_cleanup(xhci);
dbc->state = DS_DISABLED;
return 0;
ret = xhci_do_dbc_stop(xhci);
spin_unlock_irqrestore(&dbc->lock, flags);
- if (!ret)
+ if (!ret) {
+ xhci_dbc_mem_cleanup(xhci);
pm_runtime_put_sync(xhci_to_hcd(xhci)->self.controller);
+ }
}
static void
port_index = max_ports;
while (port_index--) {
u32 t1, t2;
-
+ int retries = 10;
+retry:
t1 = readl(ports[port_index]->addr);
t2 = xhci_port_state_to_neutral(t1);
portsc_buf[port_index] = 0;
- /* Bail out if a USB3 port has a new device in link training */
- if ((hcd->speed >= HCD_USB3) &&
+ /*
+ * Give a USB3 port in link training time to finish, but don't
+ * prevent suspend as port might be stuck
+ */
+ if ((hcd->speed >= HCD_USB3) && retries-- &&
(t1 & PORT_PLS_MASK) == XDEV_POLLING) {
- bus_state->bus_suspended = 0;
spin_unlock_irqrestore(&xhci->lock, flags);
- xhci_dbg(xhci, "Bus suspend bailout, port in polling\n");
- return -EBUSY;
+ msleep(XHCI_PORT_POLLING_LFPS_TIME);
+ spin_lock_irqsave(&xhci->lock, flags);
+ xhci_dbg(xhci, "port %d polling in bus suspend, waiting\n",
+ port_index);
+ goto retry;
}
-
/* suspend ports in U0, or bail out for new connect changes */
if ((t1 & PORT_PE) && (t1 & PORT_PLS_MASK) == XDEV_U0) {
if ((t1 & PORT_CSC) && wake_enabled) {
if (!xhci_rcar_wait_for_pll_active(hcd))
return -ETIMEDOUT;
+ xhci->quirks |= XHCI_TRUST_TX_LENGTH;
return xhci_rcar_download_firmware(hcd);
}
}
}
- if ((portsc & PORT_PLC) && (portsc & PORT_PLS_MASK) == XDEV_U0 &&
- DEV_SUPERSPEED_ANY(portsc)) {
+ if ((portsc & PORT_PLC) &&
+ DEV_SUPERSPEED_ANY(portsc) &&
+ ((portsc & PORT_PLS_MASK) == XDEV_U0 ||
+ (portsc & PORT_PLS_MASK) == XDEV_U1 ||
+ (portsc & PORT_PLS_MASK) == XDEV_U2)) {
xhci_dbg(xhci, "resume SS port %d finished\n", port_id);
- /* We've just brought the device into U0 through either the
+ /* We've just brought the device into U0/1/2 through either the
* Resume state after a device remote wakeup, or through the
* U3Exit state after a host-initiated resume. If it's a device
* initiated remote wake, don't pass up the link state change,
*/
#define XHCI_DEFAULT_BESL 4
+/*
+ * USB3 specification define a 360ms tPollingLFPSTiemout for USB3 ports
+ * to complete link training. usually link trainig completes much faster
+ * so check status 10 times with 36ms sleep in places we need to wait for
+ * polling to complete.
+ */
+#define XHCI_PORT_POLLING_LFPS_TIME 36
+
/**
* struct xhci_intr_reg - Interrupt Register Set
* @irq_pending: IMAN - Interrupt Management Register. Used to enable
*/
hub->port_swap = USB251XB_DEF_PORT_SWAP;
of_property_for_each_u32(np, "swap-dx-lanes", prop, p, port) {
- if ((port >= 0) && (port <= data->port_cnt))
+ if (port <= data->port_cnt)
hub->port_swap |= BIT(port);
}
dev);
int err;
- if (np) {
+ if (np && of_id) {
err = usb251xb_get_ofdata(hub,
(struct usb251xb_data *)of_id->data);
if (err) {
tristate "MediaTek USB3 Dual Role controller"
depends on USB || USB_GADGET
depends on ARCH_MEDIATEK || COMPILE_TEST
+ depends on EXTCON || !EXTCON
select USB_XHCI_MTK if USB_SUPPORT && USB_XHCI_HCD
help
Say Y or M here if your system runs on MediaTek SoCs with
{ USB_DEVICE(0x10C4, 0x804E) }, /* Software Bisque Paramount ME build-in converter */
{ USB_DEVICE(0x10C4, 0x8053) }, /* Enfora EDG1228 */
{ USB_DEVICE(0x10C4, 0x8054) }, /* Enfora GSM2228 */
+ { USB_DEVICE(0x10C4, 0x8056) }, /* Lorenz Messtechnik devices */
{ USB_DEVICE(0x10C4, 0x8066) }, /* Argussoft In-System Programmer */
{ USB_DEVICE(0x10C4, 0x806F) }, /* IMS USB to RS422 Converter Cable */
{ USB_DEVICE(0x10C4, 0x807A) }, /* Crumb128 board */
.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
{ USB_DEVICE(FTDI_VID, FTDI_NT_ORIONLXM_PID),
.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
+ { USB_DEVICE(FTDI_VID, FTDI_NT_ORIONLX_PLUS_PID) },
+ { USB_DEVICE(FTDI_VID, FTDI_NT_ORION_IO_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_SYNAPSE_SS200_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_CUSTOMWARE_MINIPLEX_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_CUSTOMWARE_MINIPLEX2_PID) },
/*
* NovaTech product ids (FTDI_VID)
*/
-#define FTDI_NT_ORIONLXM_PID 0x7c90 /* OrionLXm Substation Automation Platform */
+#define FTDI_NT_ORIONLXM_PID 0x7c90 /* OrionLXm Substation Automation Platform */
+#define FTDI_NT_ORIONLX_PLUS_PID 0x7c91 /* OrionLX+ Substation Automation Platform */
+#define FTDI_NT_ORION_IO_PID 0x7c92 /* Orion I/O */
/*
* Synapse Wireless product ids (FTDI_VID)
if (!urbtrack)
return -ENOMEM;
- kref_get(&mos_parport->ref_count);
- urbtrack->mos_parport = mos_parport;
urbtrack->urb = usb_alloc_urb(0, GFP_ATOMIC);
if (!urbtrack->urb) {
kfree(urbtrack);
usb_sndctrlpipe(usbdev, 0),
(unsigned char *)urbtrack->setup,
NULL, 0, async_complete, urbtrack);
+ kref_get(&mos_parport->ref_count);
+ urbtrack->mos_parport = mos_parport;
kref_init(&urbtrack->ref_count);
INIT_LIST_HEAD(&urbtrack->urblist_entry);
#define QUECTEL_PRODUCT_EC25 0x0125
#define QUECTEL_PRODUCT_BG96 0x0296
#define QUECTEL_PRODUCT_EP06 0x0306
+#define QUECTEL_PRODUCT_EM12 0x0512
#define CMOTECH_VENDOR_ID 0x16d8
#define CMOTECH_PRODUCT_6001 0x6001
.driver_info = RSVD(3) },
{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x6613)}, /* Onda H600/ZTE MF330 */
{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x0023)}, /* ONYX 3G device */
- { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x9000)}, /* SIMCom SIM5218 */
+ { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x9000), /* SIMCom SIM5218 */
+ .driver_info = NCTRL(0) | NCTRL(1) | NCTRL(2) | NCTRL(3) | RSVD(4) },
/* Quectel products using Qualcomm vendor ID */
{ USB_DEVICE(QUALCOMM_VENDOR_ID, QUECTEL_PRODUCT_UC15)},
{ USB_DEVICE(QUALCOMM_VENDOR_ID, QUECTEL_PRODUCT_UC20),
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0xff, 0xff),
.driver_info = RSVD(1) | RSVD(2) | RSVD(3) | RSVD(4) | NUMEP2 },
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0, 0) },
+ { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM12, 0xff, 0xff, 0xff),
+ .driver_info = RSVD(1) | RSVD(2) | RSVD(3) | RSVD(4) | NUMEP2 },
+ { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM12, 0xff, 0, 0) },
{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6001) },
{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CMU_300) },
{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6003),
.driver_info = RSVD(4) },
{ USB_DEVICE_INTERFACE_CLASS(0x2001, 0x7e35, 0xff), /* D-Link DWM-222 */
.driver_info = RSVD(4) },
- { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e01, 0xff, 0xff, 0xff) }, /* D-Link DWM-152/C1 */
- { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e02, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/C1 */
- { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x7e11, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/A3 */
- { USB_DEVICE_INTERFACE_CLASS(0x2020, 0x4000, 0xff) }, /* OLICARD300 - MT6225 */
+ { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e01, 0xff, 0xff, 0xff) }, /* D-Link DWM-152/C1 */
+ { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e02, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/C1 */
+ { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x7e11, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/A3 */
+ { USB_DEVICE_INTERFACE_CLASS(0x2020, 0x2031, 0xff), /* Olicard 600 */
+ .driver_info = RSVD(4) },
+ { USB_DEVICE_INTERFACE_CLASS(0x2020, 0x4000, 0xff) }, /* OLICARD300 - MT6225 */
{ USB_DEVICE(INOVIA_VENDOR_ID, INOVIA_SEW858) },
{ USB_DEVICE(VIATELECOM_VENDOR_ID, VIATELECOM_PRODUCT_CDS7) },
{ USB_DEVICE_AND_INTERFACE_INFO(WETELECOM_VENDOR_ID, WETELECOM_PRODUCT_WMD200, 0xff, 0xff, 0xff) },
S(SRC_ATTACHED), \
S(SRC_STARTUP), \
S(SRC_SEND_CAPABILITIES), \
+ S(SRC_SEND_CAPABILITIES_TIMEOUT), \
S(SRC_NEGOTIATE_CAPABILITIES), \
S(SRC_TRANSITION_SUPPLY), \
S(SRC_READY), \
/* port->hard_reset_count = 0; */
port->caps_count = 0;
port->pd_capable = true;
- tcpm_set_state_cond(port, hard_reset_state(port),
+ tcpm_set_state_cond(port, SRC_SEND_CAPABILITIES_TIMEOUT,
PD_T_SEND_SOURCE_CAP);
}
break;
+ case SRC_SEND_CAPABILITIES_TIMEOUT:
+ /*
+ * Error recovery for a PD_DATA_SOURCE_CAP reply timeout.
+ *
+ * PD 2.0 sinks are supposed to accept src-capabilities with a
+ * 3.0 header and simply ignore any src PDOs which the sink does
+ * not understand such as PPS but some 2.0 sinks instead ignore
+ * the entire PD_DATA_SOURCE_CAP message, causing contract
+ * negotiation to fail.
+ *
+ * After PD_N_HARD_RESET_COUNT hard-reset attempts, we try
+ * sending src-capabilities with a lower PD revision to
+ * make these broken sinks work.
+ */
+ if (port->hard_reset_count < PD_N_HARD_RESET_COUNT) {
+ tcpm_set_state(port, HARD_RESET_SEND, 0);
+ } else if (port->negotiated_rev > PD_REV20) {
+ port->negotiated_rev--;
+ port->hard_reset_count = 0;
+ tcpm_set_state(port, SRC_SEND_CAPABILITIES, 0);
+ } else {
+ tcpm_set_state(port, hard_reset_state(port), 0);
+ }
+ break;
case SRC_NEGOTIATE_CAPABILITIES:
ret = tcpm_pd_check_request(port);
if (ret < 0) {
wcove->dev = &pdev->dev;
wcove->regmap = pmic->regmap;
- irq = regmap_irq_get_virq(pmic->irq_chip_data_chgr,
- platform_get_irq(pdev, 0));
+ irq = platform_get_irq(pdev, 0);
+ if (irq < 0) {
+ dev_err(&pdev->dev, "Failed to get IRQ: %d\n", irq);
+ return irq;
+ }
+
+ irq = regmap_irq_get_virq(pmic->irq_chip_data_chgr, irq);
if (irq < 0)
return irq;
rc = pci_add_dynid(&vfio_pci_driver, vendor, device,
subvendor, subdevice, class, class_mask, 0);
if (rc)
- pr_warn("failed to add dynamic id [%04hx:%04hx[%04hx:%04hx]] class %#08x/%08x (%d)\n",
+ pr_warn("failed to add dynamic id [%04x:%04x[%04x:%04x]] class %#08x/%08x (%d)\n",
vendor, device, subvendor, subdevice,
class, class_mask, rc);
else
- pr_info("add [%04hx:%04hx[%04hx:%04hx]] class %#08x/%08x\n",
+ pr_info("add [%04x:%04x[%04x:%04x]] class %#08x/%08x\n",
vendor, device, subvendor, subdevice,
class, class_mask);
}
mutex_unlock(&container->lock);
}
-const struct vfio_iommu_driver_ops tce_iommu_driver_ops = {
+static const struct vfio_iommu_driver_ops tce_iommu_driver_ops = {
.name = "iommu-vfio-powerpc",
.owner = THIS_MODULE,
.open = tce_iommu_open,
MODULE_PARM_DESC(disable_hugepages,
"Disable VFIO IOMMU support for IOMMU hugepages.");
+static unsigned int dma_entry_limit __read_mostly = U16_MAX;
+module_param_named(dma_entry_limit, dma_entry_limit, uint, 0644);
+MODULE_PARM_DESC(dma_entry_limit,
+ "Maximum number of user DMA mappings per container (65535).");
+
struct vfio_iommu {
struct list_head domain_list;
struct vfio_domain *external_domain; /* domain for external user */
struct mutex lock;
struct rb_root dma_list;
struct blocking_notifier_head notifier;
+ unsigned int dma_avail;
bool v2;
bool nesting;
};
vfio_unlink_dma(iommu, dma);
put_task_struct(dma->task);
kfree(dma);
+ iommu->dma_avail++;
}
static unsigned long vfio_pgsize_bitmap(struct vfio_iommu *iommu)
goto out_unlock;
}
+ if (!iommu->dma_avail) {
+ ret = -ENOSPC;
+ goto out_unlock;
+ }
+
dma = kzalloc(sizeof(*dma), GFP_KERNEL);
if (!dma) {
ret = -ENOMEM;
goto out_unlock;
}
+ iommu->dma_avail--;
dma->iova = iova;
dma->vaddr = vaddr;
dma->prot = prot;
INIT_LIST_HEAD(&iommu->domain_list);
iommu->dma_list = RB_ROOT;
+ iommu->dma_avail = dma_entry_limit;
mutex_init(&iommu->lock);
BLOCKING_INIT_NOTIFIER_HEAD(&iommu->notifier);
u64 start, u64 size, u64 end,
u64 userspace_addr, int perm)
{
- struct vhost_umem_node *tmp, *node = kmalloc(sizeof(*node), GFP_ATOMIC);
+ struct vhost_umem_node *tmp, *node;
+ if (!size)
+ return -EFAULT;
+
+ node = kmalloc(sizeof(*node), GFP_ATOMIC);
if (!node)
return -ENOMEM;
#define GUEST_MAPPINGS_TRIES 5
+#define VBG_KERNEL_REQUEST \
+ (VMMDEV_REQUESTOR_KERNEL | VMMDEV_REQUESTOR_USR_DRV | \
+ VMMDEV_REQUESTOR_CON_DONT_KNOW | VMMDEV_REQUESTOR_TRUST_NOT_GIVEN)
+
/**
* Reserves memory in which the VMM can relocate any guest mappings
* that are floating around.
int i, rc;
/* Query the required space. */
- req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_GET_HYPERVISOR_INFO);
+ req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_GET_HYPERVISOR_INFO,
+ VBG_KERNEL_REQUEST);
if (!req)
return;
* Tell the host that we're going to free the memory we reserved for
* it, the free it up. (Leak the memory if anything goes wrong here.)
*/
- req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_SET_HYPERVISOR_INFO);
+ req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_SET_HYPERVISOR_INFO,
+ VBG_KERNEL_REQUEST);
if (!req)
return;
struct vmmdev_guest_info2 *req2 = NULL;
int rc, ret = -ENOMEM;
- req1 = vbg_req_alloc(sizeof(*req1), VMMDEVREQ_REPORT_GUEST_INFO);
- req2 = vbg_req_alloc(sizeof(*req2), VMMDEVREQ_REPORT_GUEST_INFO2);
+ req1 = vbg_req_alloc(sizeof(*req1), VMMDEVREQ_REPORT_GUEST_INFO,
+ VBG_KERNEL_REQUEST);
+ req2 = vbg_req_alloc(sizeof(*req2), VMMDEVREQ_REPORT_GUEST_INFO2,
+ VBG_KERNEL_REQUEST);
if (!req1 || !req2)
goto out_free;
req2->additions_minor = VBG_VERSION_MINOR;
req2->additions_build = VBG_VERSION_BUILD;
req2->additions_revision = VBG_SVN_REV;
- /* (no features defined yet) */
- req2->additions_features = 0;
+ req2->additions_features =
+ VMMDEV_GUEST_INFO2_ADDITIONS_FEATURES_REQUESTOR_INFO;
strlcpy(req2->name, VBG_VERSION_STRING,
sizeof(req2->name));
struct vmmdev_guest_status *req;
int rc;
- req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_REPORT_GUEST_STATUS);
+ req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_REPORT_GUEST_STATUS,
+ VBG_KERNEL_REQUEST);
if (!req)
return -ENOMEM;
struct vmmdev_heartbeat *req;
int rc;
- req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_HEARTBEAT_CONFIGURE);
+ req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_HEARTBEAT_CONFIGURE,
+ VBG_KERNEL_REQUEST);
if (!req)
return -ENOMEM;
gdev->guest_heartbeat_req = vbg_req_alloc(
sizeof(*gdev->guest_heartbeat_req),
- VMMDEVREQ_GUEST_HEARTBEAT);
+ VMMDEVREQ_GUEST_HEARTBEAT,
+ VBG_KERNEL_REQUEST);
if (!gdev->guest_heartbeat_req)
return -ENOMEM;
struct vmmdev_mask *req;
int rc;
- req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_CTL_GUEST_FILTER_MASK);
+ req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_CTL_GUEST_FILTER_MASK,
+ VBG_KERNEL_REQUEST);
if (!req)
return -ENOMEM;
u32 changed, previous;
int rc, ret = 0;
- /* Allocate a request buffer before taking the spinlock */
- req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_CTL_GUEST_FILTER_MASK);
+ /*
+ * Allocate a request buffer before taking the spinlock, when
+ * the session is being terminated the requestor is the kernel,
+ * as we're cleaning up.
+ */
+ req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_CTL_GUEST_FILTER_MASK,
+ session_termination ? VBG_KERNEL_REQUEST :
+ session->requestor);
if (!req) {
if (!session_termination)
return -ENOMEM;
struct vmmdev_mask *req;
int rc;
- req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_SET_GUEST_CAPABILITIES);
+ req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_SET_GUEST_CAPABILITIES,
+ VBG_KERNEL_REQUEST);
if (!req)
return -ENOMEM;
u32 changed, previous;
int rc, ret = 0;
- /* Allocate a request buffer before taking the spinlock */
- req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_SET_GUEST_CAPABILITIES);
+ /*
+ * Allocate a request buffer before taking the spinlock, when
+ * the session is being terminated the requestor is the kernel,
+ * as we're cleaning up.
+ */
+ req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_SET_GUEST_CAPABILITIES,
+ session_termination ? VBG_KERNEL_REQUEST :
+ session->requestor);
if (!req) {
if (!session_termination)
return -ENOMEM;
struct vmmdev_host_version *req;
int rc, ret;
- req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_GET_HOST_VERSION);
+ req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_GET_HOST_VERSION,
+ VBG_KERNEL_REQUEST);
if (!req)
return -ENOMEM;
gdev->mem_balloon.get_req =
vbg_req_alloc(sizeof(*gdev->mem_balloon.get_req),
- VMMDEVREQ_GET_MEMBALLOON_CHANGE_REQ);
+ VMMDEVREQ_GET_MEMBALLOON_CHANGE_REQ,
+ VBG_KERNEL_REQUEST);
gdev->mem_balloon.change_req =
vbg_req_alloc(sizeof(*gdev->mem_balloon.change_req),
- VMMDEVREQ_CHANGE_MEMBALLOON);
+ VMMDEVREQ_CHANGE_MEMBALLOON,
+ VBG_KERNEL_REQUEST);
gdev->cancel_req =
vbg_req_alloc(sizeof(*(gdev->cancel_req)),
- VMMDEVREQ_HGCM_CANCEL2);
+ VMMDEVREQ_HGCM_CANCEL2,
+ VBG_KERNEL_REQUEST);
gdev->ack_events_req =
vbg_req_alloc(sizeof(*gdev->ack_events_req),
- VMMDEVREQ_ACKNOWLEDGE_EVENTS);
+ VMMDEVREQ_ACKNOWLEDGE_EVENTS,
+ VBG_KERNEL_REQUEST);
gdev->mouse_status_req =
vbg_req_alloc(sizeof(*gdev->mouse_status_req),
- VMMDEVREQ_GET_MOUSE_STATUS);
+ VMMDEVREQ_GET_MOUSE_STATUS,
+ VBG_KERNEL_REQUEST);
if (!gdev->mem_balloon.get_req || !gdev->mem_balloon.change_req ||
!gdev->cancel_req || !gdev->ack_events_req ||
* vboxguest_linux.c calls this when userspace opens the char-device.
* Return: A pointer to the new session or an ERR_PTR on error.
* @gdev: The Guest extension device.
- * @user: Set if this is a session for the vboxuser device.
+ * @requestor: VMMDEV_REQUESTOR_* flags
*/
-struct vbg_session *vbg_core_open_session(struct vbg_dev *gdev, bool user)
+struct vbg_session *vbg_core_open_session(struct vbg_dev *gdev, u32 requestor)
{
struct vbg_session *session;
return ERR_PTR(-ENOMEM);
session->gdev = gdev;
- session->user_session = user;
+ session->requestor = requestor;
return session;
}
if (!session->hgcm_client_ids[i])
continue;
- vbg_hgcm_disconnect(gdev, session->hgcm_client_ids[i], &rc);
+ /* requestor is kernel here, as we're cleaning up. */
+ vbg_hgcm_disconnect(gdev, VBG_KERNEL_REQUEST,
+ session->hgcm_client_ids[i], &rc);
}
kfree(session);
return -EPERM;
}
- if (trusted_apps_only && session->user_session) {
+ if (trusted_apps_only &&
+ (session->requestor & VMMDEV_REQUESTOR_USER_DEVICE)) {
vbg_err("Denying userspace vmm call type %#08x through vboxuser device node\n",
req->request_type);
return -EPERM;
if (i >= ARRAY_SIZE(session->hgcm_client_ids))
return -EMFILE;
- ret = vbg_hgcm_connect(gdev, &conn->u.in.loc, &client_id,
- &conn->hdr.rc);
+ ret = vbg_hgcm_connect(gdev, session->requestor, &conn->u.in.loc,
+ &client_id, &conn->hdr.rc);
mutex_lock(&gdev->session_mutex);
if (ret == 0 && conn->hdr.rc >= 0) {
if (i >= ARRAY_SIZE(session->hgcm_client_ids))
return -EINVAL;
- ret = vbg_hgcm_disconnect(gdev, client_id, &disconn->hdr.rc);
+ ret = vbg_hgcm_disconnect(gdev, session->requestor, client_id,
+ &disconn->hdr.rc);
mutex_lock(&gdev->session_mutex);
if (ret == 0 && disconn->hdr.rc >= 0)
}
if (IS_ENABLED(CONFIG_COMPAT) && f32bit)
- ret = vbg_hgcm_call32(gdev, client_id,
+ ret = vbg_hgcm_call32(gdev, session->requestor, client_id,
call->function, call->timeout_ms,
VBG_IOCTL_HGCM_CALL_PARMS32(call),
call->parm_count, &call->hdr.rc);
else
- ret = vbg_hgcm_call(gdev, client_id,
+ ret = vbg_hgcm_call(gdev, session->requestor, client_id,
call->function, call->timeout_ms,
VBG_IOCTL_HGCM_CALL_PARMS(call),
call->parm_count, &call->hdr.rc);
}
static int vbg_ioctl_write_core_dump(struct vbg_dev *gdev,
+ struct vbg_session *session,
struct vbg_ioctl_write_coredump *dump)
{
struct vmmdev_write_core_dump *req;
if (vbg_ioctl_chk(&dump->hdr, sizeof(dump->u.in), 0))
return -EINVAL;
- req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_WRITE_COREDUMP);
+ req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_WRITE_COREDUMP,
+ session->requestor);
if (!req)
return -ENOMEM;
case VBG_IOCTL_CHECK_BALLOON:
return vbg_ioctl_check_balloon(gdev, data);
case VBG_IOCTL_WRITE_CORE_DUMP:
- return vbg_ioctl_write_core_dump(gdev, data);
+ return vbg_ioctl_write_core_dump(gdev, session, data);
}
/* Variable sized requests. */
struct vmmdev_mouse_status *req;
int rc;
- req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_SET_MOUSE_STATUS);
+ req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_SET_MOUSE_STATUS,
+ VBG_KERNEL_REQUEST);
if (!req)
return -ENOMEM;
* host. Protected by vbg_gdev.session_mutex.
*/
u32 guest_caps;
- /** Does this session belong to a root process or a user one? */
- bool user_session;
+ /** VMMDEV_REQUESTOR_* flags */
+ u32 requestor;
/** Set on CANCEL_ALL_WAITEVENTS, protected by vbg_devevent_spinlock. */
bool cancel_waiters;
};
int vbg_core_init(struct vbg_dev *gdev, u32 fixed_events);
void vbg_core_exit(struct vbg_dev *gdev);
-struct vbg_session *vbg_core_open_session(struct vbg_dev *gdev, bool user);
+struct vbg_session *vbg_core_open_session(struct vbg_dev *gdev, u32 requestor);
void vbg_core_close_session(struct vbg_session *session);
int vbg_core_ioctl(struct vbg_session *session, unsigned int req, void *data);
int vbg_core_set_mouse_status(struct vbg_dev *gdev, u32 features);
void vbg_linux_mouse_event(struct vbg_dev *gdev);
/* Private (non exported) functions form vboxguest_utils.c */
-void *vbg_req_alloc(size_t len, enum vmmdev_request_type req_type);
+void *vbg_req_alloc(size_t len, enum vmmdev_request_type req_type,
+ u32 requestor);
void vbg_req_free(void *req, size_t len);
int vbg_req_perform(struct vbg_dev *gdev, void *req);
int vbg_hgcm_call32(
- struct vbg_dev *gdev, u32 client_id, u32 function, u32 timeout_ms,
- struct vmmdev_hgcm_function_parameter32 *parm32, u32 parm_count,
- int *vbox_status);
+ struct vbg_dev *gdev, u32 requestor, u32 client_id, u32 function,
+ u32 timeout_ms, struct vmmdev_hgcm_function_parameter32 *parm32,
+ u32 parm_count, int *vbox_status);
#endif
* Copyright (C) 2006-2016 Oracle Corporation
*/
+#include <linux/cred.h>
#include <linux/input.h>
#include <linux/kernel.h>
#include <linux/miscdevice.h>
/** Global vbg_gdev pointer used by vbg_get/put_gdev. */
static struct vbg_dev *vbg_gdev;
+static u32 vbg_misc_device_requestor(struct inode *inode)
+{
+ u32 requestor = VMMDEV_REQUESTOR_USERMODE |
+ VMMDEV_REQUESTOR_CON_DONT_KNOW |
+ VMMDEV_REQUESTOR_TRUST_NOT_GIVEN;
+
+ if (from_kuid(current_user_ns(), current->cred->uid) == 0)
+ requestor |= VMMDEV_REQUESTOR_USR_ROOT;
+ else
+ requestor |= VMMDEV_REQUESTOR_USR_USER;
+
+ if (in_egroup_p(inode->i_gid))
+ requestor |= VMMDEV_REQUESTOR_GRP_VBOX;
+
+ return requestor;
+}
+
static int vbg_misc_device_open(struct inode *inode, struct file *filp)
{
struct vbg_session *session;
/* misc_open sets filp->private_data to our misc device */
gdev = container_of(filp->private_data, struct vbg_dev, misc_device);
- session = vbg_core_open_session(gdev, false);
+ session = vbg_core_open_session(gdev, vbg_misc_device_requestor(inode));
if (IS_ERR(session))
return PTR_ERR(session);
gdev = container_of(filp->private_data, struct vbg_dev,
misc_device_user);
- session = vbg_core_open_session(gdev, false);
+ session = vbg_core_open_session(gdev, vbg_misc_device_requestor(inode) |
+ VMMDEV_REQUESTOR_USER_DEVICE);
if (IS_ERR(session))
return PTR_ERR(session);
req == VBG_IOCTL_VMMDEV_REQUEST_BIG;
if (is_vmmdev_req)
- buf = vbg_req_alloc(size, VBG_IOCTL_HDR_TYPE_DEFAULT);
+ buf = vbg_req_alloc(size, VBG_IOCTL_HDR_TYPE_DEFAULT,
+ session->requestor);
else
buf = kmalloc(size, GFP_KERNEL);
if (!buf)
VBG_LOG(vbg_debug, pr_debug);
#endif
-void *vbg_req_alloc(size_t len, enum vmmdev_request_type req_type)
+void *vbg_req_alloc(size_t len, enum vmmdev_request_type req_type,
+ u32 requestor)
{
struct vmmdev_request_header *req;
int order = get_order(PAGE_ALIGN(len));
req->request_type = req_type;
req->rc = VERR_GENERAL_FAILURE;
req->reserved1 = 0;
- req->reserved2 = 0;
+ req->requestor = requestor;
return req;
}
return done;
}
-int vbg_hgcm_connect(struct vbg_dev *gdev,
+int vbg_hgcm_connect(struct vbg_dev *gdev, u32 requestor,
struct vmmdev_hgcm_service_location *loc,
u32 *client_id, int *vbox_status)
{
int rc;
hgcm_connect = vbg_req_alloc(sizeof(*hgcm_connect),
- VMMDEVREQ_HGCM_CONNECT);
+ VMMDEVREQ_HGCM_CONNECT, requestor);
if (!hgcm_connect)
return -ENOMEM;
}
EXPORT_SYMBOL(vbg_hgcm_connect);
-int vbg_hgcm_disconnect(struct vbg_dev *gdev, u32 client_id, int *vbox_status)
+int vbg_hgcm_disconnect(struct vbg_dev *gdev, u32 requestor,
+ u32 client_id, int *vbox_status)
{
struct vmmdev_hgcm_disconnect *hgcm_disconnect = NULL;
int rc;
hgcm_disconnect = vbg_req_alloc(sizeof(*hgcm_disconnect),
- VMMDEVREQ_HGCM_DISCONNECT);
+ VMMDEVREQ_HGCM_DISCONNECT,
+ requestor);
if (!hgcm_disconnect)
return -ENOMEM;
return 0;
}
-int vbg_hgcm_call(struct vbg_dev *gdev, u32 client_id, u32 function,
- u32 timeout_ms, struct vmmdev_hgcm_function_parameter *parms,
- u32 parm_count, int *vbox_status)
+int vbg_hgcm_call(struct vbg_dev *gdev, u32 requestor, u32 client_id,
+ u32 function, u32 timeout_ms,
+ struct vmmdev_hgcm_function_parameter *parms, u32 parm_count,
+ int *vbox_status)
{
struct vmmdev_hgcm_call *call;
void **bounce_bufs = NULL;
goto free_bounce_bufs;
}
- call = vbg_req_alloc(size, VMMDEVREQ_HGCM_CALL);
+ call = vbg_req_alloc(size, VMMDEVREQ_HGCM_CALL, requestor);
if (!call) {
ret = -ENOMEM;
goto free_bounce_bufs;
#ifdef CONFIG_COMPAT
int vbg_hgcm_call32(
- struct vbg_dev *gdev, u32 client_id, u32 function, u32 timeout_ms,
- struct vmmdev_hgcm_function_parameter32 *parm32, u32 parm_count,
- int *vbox_status)
+ struct vbg_dev *gdev, u32 requestor, u32 client_id, u32 function,
+ u32 timeout_ms, struct vmmdev_hgcm_function_parameter32 *parm32,
+ u32 parm_count, int *vbox_status)
{
struct vmmdev_hgcm_function_parameter *parm64 = NULL;
u32 i, size;
goto out_free;
}
- ret = vbg_hgcm_call(gdev, client_id, function, timeout_ms,
+ ret = vbg_hgcm_call(gdev, requestor, client_id, function, timeout_ms,
parm64, parm_count, vbox_status);
if (ret < 0)
goto out_free;
#ifndef __VBOX_VERSION_H__
#define __VBOX_VERSION_H__
-/* Last synced October 4th 2017 */
-#define VBG_VERSION_MAJOR 5
-#define VBG_VERSION_MINOR 2
+#define VBG_VERSION_MAJOR 6
+#define VBG_VERSION_MINOR 0
#define VBG_VERSION_BUILD 0
-#define VBG_SVN_REV 68940
-#define VBG_VERSION_STRING "5.2.0"
+#define VBG_SVN_REV 127566
+#define VBG_VERSION_STRING "6.0.0"
#endif
s32 rc;
/** Reserved field no.1. MBZ. */
u32 reserved1;
- /** Reserved field no.2. MBZ. */
- u32 reserved2;
+ /** IN: Requestor information (VMMDEV_REQUESTOR_*) */
+ u32 requestor;
};
VMMDEV_ASSERT_SIZE(vmmdev_request_header, 24);
};
VMMDEV_ASSERT_SIZE(vmmdev_guest_info, 24 + 8);
+#define VMMDEV_GUEST_INFO2_ADDITIONS_FEATURES_REQUESTOR_INFO BIT(0)
+
/** struct vmmdev_guestinfo2 - Guest information report, version 2. */
struct vmmdev_guest_info2 {
/** Header. */
u32 additions_build;
/** SVN revision. */
u32 additions_revision;
- /** Feature mask, currently unused. */
+ /** Feature mask. */
u32 additions_features;
/**
* The intentional meaning of this field was:
for (i = 0; i < vp_dev->msix_used_vectors; ++i)
free_irq(pci_irq_vector(vp_dev->pci_dev, i), vp_dev);
- for (i = 0; i < vp_dev->msix_vectors; i++)
- if (vp_dev->msix_affinity_masks[i])
- free_cpumask_var(vp_dev->msix_affinity_masks[i]);
+ if (vp_dev->msix_affinity_masks) {
+ for (i = 0; i < vp_dev->msix_vectors; i++)
+ if (vp_dev->msix_affinity_masks[i])
+ free_cpumask_var(vp_dev->msix_affinity_masks[i]);
+ }
if (vp_dev->msix_enabled) {
/* Disable the vector used for configuration */
GFP_KERNEL|__GFP_NOWARN|__GFP_ZERO);
if (queue)
break;
+ if (!may_reduce_num)
+ return NULL;
}
if (!num)
if (!(vma->vm_flags & VM_SHARED))
return -EINVAL;
- vma_priv = kzalloc(sizeof(*vma_priv) + count * sizeof(void *),
- GFP_KERNEL);
+ vma_priv = kzalloc(struct_size(vma_priv, pages, count), GFP_KERNEL);
if (!vma_priv)
return -ENOMEM;
if (xen_store_evtchn == 0)
return -ENOENT;
- nonseekable_open(inode, filp);
-
- filp->f_mode &= ~FMODE_ATOMIC_POS; /* cdev-style semantics */
+ stream_open(inode, filp);
u = kzalloc(sizeof(*u), GFP_KERNEL);
if (u == NULL)
xdr_encode_AFS_StoreStatus(&bp, attr);
- *bp++ = 0; /* position of start of write */
- *bp++ = 0;
+ *bp++ = htonl(attr->ia_size >> 32); /* position of start of write */
+ *bp++ = htonl((u32) attr->ia_size);
*bp++ = 0; /* size of write */
*bp++ = 0;
*bp++ = htonl(attr->ia_size >> 32); /* new file length */
xdr_encode_AFS_StoreStatus(&bp, attr);
- *bp++ = 0; /* position of start of write */
+ *bp++ = htonl(attr->ia_size); /* position of start of write */
*bp++ = 0; /* size of write */
*bp++ = htonl(attr->ia_size); /* new file length */
bool stalled = false;
u64 rtt;
u32 life, last_life;
+ bool rxrpc_complete = false;
DECLARE_WAITQUEUE(myself, current);
rtt2 = 2;
timeout = rtt2;
- last_life = rxrpc_kernel_check_life(call->net->socket, call->rxcall);
+ rxrpc_kernel_check_life(call->net->socket, call->rxcall, &last_life);
add_wait_queue(&call->waitq, &myself);
for (;;) {
if (afs_check_call_state(call, AFS_CALL_COMPLETE))
break;
- life = rxrpc_kernel_check_life(call->net->socket, call->rxcall);
+ if (!rxrpc_kernel_check_life(call->net->socket, call->rxcall, &life)) {
+ /* rxrpc terminated the call. */
+ rxrpc_complete = true;
+ break;
+ }
+
if (timeout == 0 &&
life == last_life && signal_pending(current)) {
if (stalled)
remove_wait_queue(&call->waitq, &myself);
__set_current_state(TASK_RUNNING);
- /* Kill off the call if it's still live. */
if (!afs_check_call_state(call, AFS_CALL_COMPLETE)) {
- _debug("call interrupted");
- if (rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
- RX_USER_ABORT, -EINTR, "KWI"))
- afs_set_call_complete(call, -EINTR, 0);
+ if (rxrpc_complete) {
+ afs_set_call_complete(call, call->error, call->abort_code);
+ } else {
+ /* Kill off the call if it's still live. */
+ _debug("call interrupted");
+ if (rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
+ RX_USER_ABORT, -EINTR, "KWI"))
+ afs_set_call_complete(call, -EINTR, 0);
+ }
}
spin_lock_bh(&call->state_lock);
bp = xdr_encode_u32(bp, 0); /* RPC flags */
bp = xdr_encode_YFSFid(bp, &vnode->fid);
bp = xdr_encode_YFS_StoreStatus(bp, attr);
- bp = xdr_encode_u64(bp, 0); /* position of start of write */
+ bp = xdr_encode_u64(bp, attr->ia_size); /* position of start of write */
bp = xdr_encode_u64(bp, 0); /* size of write */
bp = xdr_encode_u64(bp, attr->ia_size); /* new file length */
yfs_check_req(call, bp);
struct file *file;
struct wait_queue_head *head;
__poll_t events;
- bool woken;
+ bool done;
bool cancelled;
struct wait_queue_entry wait;
struct work_struct work;
struct kioctx *ki_ctx;
kiocb_cancel_fn *ki_cancel;
- struct iocb __user *ki_user_iocb; /* user's aiocb */
- __u64 ki_user_data; /* user's data for completion */
+ struct io_event ki_res;
struct list_head ki_list; /* the aio core uses this
* for cancellation */
/* aio_get_req
* Allocate a slot for an aio request.
* Returns NULL if no requests are free.
+ *
+ * The refcount is initialized to 2 - one for the async op completion,
+ * one for the synchronous code that does this.
*/
static inline struct aio_kiocb *aio_get_req(struct kioctx *ctx)
{
if (unlikely(!req))
return NULL;
+ if (unlikely(!get_reqs_available(ctx))) {
+ kmem_cache_free(kiocb_cachep, req);
+ return NULL;
+ }
+
percpu_ref_get(&ctx->reqs);
req->ki_ctx = ctx;
INIT_LIST_HEAD(&req->ki_list);
- refcount_set(&req->ki_refcnt, 0);
+ refcount_set(&req->ki_refcnt, 2);
req->ki_eventfd = NULL;
return req;
}
return ret;
}
-static inline void iocb_put(struct aio_kiocb *iocb)
-{
- if (refcount_read(&iocb->ki_refcnt) == 0 ||
- refcount_dec_and_test(&iocb->ki_refcnt)) {
- if (iocb->ki_filp)
- fput(iocb->ki_filp);
- percpu_ref_put(&iocb->ki_ctx->reqs);
- kmem_cache_free(kiocb_cachep, iocb);
- }
-}
-
-static void aio_fill_event(struct io_event *ev, struct aio_kiocb *iocb,
- long res, long res2)
+static inline void iocb_destroy(struct aio_kiocb *iocb)
{
- ev->obj = (u64)(unsigned long)iocb->ki_user_iocb;
- ev->data = iocb->ki_user_data;
- ev->res = res;
- ev->res2 = res2;
+ if (iocb->ki_eventfd)
+ eventfd_ctx_put(iocb->ki_eventfd);
+ if (iocb->ki_filp)
+ fput(iocb->ki_filp);
+ percpu_ref_put(&iocb->ki_ctx->reqs);
+ kmem_cache_free(kiocb_cachep, iocb);
}
/* aio_complete
* Called when the io request on the given iocb is complete.
*/
-static void aio_complete(struct aio_kiocb *iocb, long res, long res2)
+static void aio_complete(struct aio_kiocb *iocb)
{
struct kioctx *ctx = iocb->ki_ctx;
struct aio_ring *ring;
ev_page = kmap_atomic(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]);
event = ev_page + pos % AIO_EVENTS_PER_PAGE;
- aio_fill_event(event, iocb, res, res2);
+ *event = iocb->ki_res;
kunmap_atomic(ev_page);
flush_dcache_page(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]);
- pr_debug("%p[%u]: %p: %p %Lx %lx %lx\n",
- ctx, tail, iocb, iocb->ki_user_iocb, iocb->ki_user_data,
- res, res2);
+ pr_debug("%p[%u]: %p: %p %Lx %Lx %Lx\n", ctx, tail, iocb,
+ (void __user *)(unsigned long)iocb->ki_res.obj,
+ iocb->ki_res.data, iocb->ki_res.res, iocb->ki_res.res2);
/* after flagging the request as done, we
* must never even look at it again
* eventfd. The eventfd_signal() function is safe to be called
* from IRQ context.
*/
- if (iocb->ki_eventfd) {
+ if (iocb->ki_eventfd)
eventfd_signal(iocb->ki_eventfd, 1);
- eventfd_ctx_put(iocb->ki_eventfd);
- }
/*
* We have to order our ring_info tail store above and test
if (waitqueue_active(&ctx->wait))
wake_up(&ctx->wait);
- iocb_put(iocb);
+}
+
+static inline void iocb_put(struct aio_kiocb *iocb)
+{
+ if (refcount_dec_and_test(&iocb->ki_refcnt)) {
+ aio_complete(iocb);
+ iocb_destroy(iocb);
+ }
}
/* aio_read_events_ring
file_end_write(kiocb->ki_filp);
}
- aio_complete(iocb, res, res2);
+ iocb->ki_res.res = res;
+ iocb->ki_res.res2 = res2;
+ iocb_put(iocb);
}
static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb)
}
}
-static ssize_t aio_read(struct kiocb *req, const struct iocb *iocb,
+static int aio_read(struct kiocb *req, const struct iocb *iocb,
bool vectored, bool compat)
{
struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
struct iov_iter iter;
struct file *file;
- ssize_t ret;
+ int ret;
ret = aio_prep_rw(req, iocb);
if (ret)
return ret;
}
-static ssize_t aio_write(struct kiocb *req, const struct iocb *iocb,
+static int aio_write(struct kiocb *req, const struct iocb *iocb,
bool vectored, bool compat)
{
struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
struct iov_iter iter;
struct file *file;
- ssize_t ret;
+ int ret;
ret = aio_prep_rw(req, iocb);
if (ret)
static void aio_fsync_work(struct work_struct *work)
{
- struct fsync_iocb *req = container_of(work, struct fsync_iocb, work);
- int ret;
+ struct aio_kiocb *iocb = container_of(work, struct aio_kiocb, fsync.work);
- ret = vfs_fsync(req->file, req->datasync);
- aio_complete(container_of(req, struct aio_kiocb, fsync), ret, 0);
+ iocb->ki_res.res = vfs_fsync(iocb->fsync.file, iocb->fsync.datasync);
+ iocb_put(iocb);
}
static int aio_fsync(struct fsync_iocb *req, const struct iocb *iocb,
return 0;
}
-static inline void aio_poll_complete(struct aio_kiocb *iocb, __poll_t mask)
-{
- aio_complete(iocb, mangle_poll(mask), 0);
-}
-
static void aio_poll_complete_work(struct work_struct *work)
{
struct poll_iocb *req = container_of(work, struct poll_iocb, work);
return;
}
list_del_init(&iocb->ki_list);
+ iocb->ki_res.res = mangle_poll(mask);
+ req->done = true;
spin_unlock_irq(&ctx->ctx_lock);
- aio_poll_complete(iocb, mask);
+ iocb_put(iocb);
}
/* assumes we are called with irqs disabled */
__poll_t mask = key_to_poll(key);
unsigned long flags;
- req->woken = true;
-
/* for instances that support it check for an event match first: */
- if (mask) {
- if (!(mask & req->events))
- return 0;
+ if (mask && !(mask & req->events))
+ return 0;
+
+ list_del_init(&req->wait.entry);
+ if (mask && spin_trylock_irqsave(&iocb->ki_ctx->ctx_lock, flags)) {
/*
* Try to complete the iocb inline if we can. Use
* irqsave/irqrestore because not all filesystems (e.g. fuse)
* call this function with IRQs disabled and because IRQs
* have to be disabled before ctx_lock is obtained.
*/
- if (spin_trylock_irqsave(&iocb->ki_ctx->ctx_lock, flags)) {
- list_del(&iocb->ki_list);
- spin_unlock_irqrestore(&iocb->ki_ctx->ctx_lock, flags);
-
- list_del_init(&req->wait.entry);
- aio_poll_complete(iocb, mask);
- return 1;
- }
+ list_del(&iocb->ki_list);
+ iocb->ki_res.res = mangle_poll(mask);
+ req->done = true;
+ spin_unlock_irqrestore(&iocb->ki_ctx->ctx_lock, flags);
+ iocb_put(iocb);
+ } else {
+ schedule_work(&req->work);
}
-
- list_del_init(&req->wait.entry);
- schedule_work(&req->work);
return 1;
}
add_wait_queue(head, &pt->iocb->poll.wait);
}
-static ssize_t aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb)
+static int aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb)
{
struct kioctx *ctx = aiocb->ki_ctx;
struct poll_iocb *req = &aiocb->poll;
struct aio_poll_table apt;
+ bool cancel = false;
__poll_t mask;
/* reject any unknown events outside the normal event mask. */
req->events = demangle_poll(iocb->aio_buf) | EPOLLERR | EPOLLHUP;
req->head = NULL;
- req->woken = false;
+ req->done = false;
req->cancelled = false;
apt.pt._qproc = aio_poll_queue_proc;
INIT_LIST_HEAD(&req->wait.entry);
init_waitqueue_func_entry(&req->wait, aio_poll_wake);
- /* one for removal from waitqueue, one for this function */
- refcount_set(&aiocb->ki_refcnt, 2);
-
mask = vfs_poll(req->file, &apt.pt) & req->events;
- if (unlikely(!req->head)) {
- /* we did not manage to set up a waitqueue, done */
- goto out;
- }
-
spin_lock_irq(&ctx->ctx_lock);
- spin_lock(&req->head->lock);
- if (req->woken) {
- /* wake_up context handles the rest */
- mask = 0;
+ if (likely(req->head)) {
+ spin_lock(&req->head->lock);
+ if (unlikely(list_empty(&req->wait.entry))) {
+ if (apt.error)
+ cancel = true;
+ apt.error = 0;
+ mask = 0;
+ }
+ if (mask || apt.error) {
+ list_del_init(&req->wait.entry);
+ } else if (cancel) {
+ WRITE_ONCE(req->cancelled, true);
+ } else if (!req->done) { /* actually waiting for an event */
+ list_add_tail(&aiocb->ki_list, &ctx->active_reqs);
+ aiocb->ki_cancel = aio_poll_cancel;
+ }
+ spin_unlock(&req->head->lock);
+ }
+ if (mask) { /* no async, we'd stolen it */
+ aiocb->ki_res.res = mangle_poll(mask);
apt.error = 0;
- } else if (mask || apt.error) {
- /* if we get an error or a mask we are done */
- WARN_ON_ONCE(list_empty(&req->wait.entry));
- list_del_init(&req->wait.entry);
- } else {
- /* actually waiting for an event */
- list_add_tail(&aiocb->ki_list, &ctx->active_reqs);
- aiocb->ki_cancel = aio_poll_cancel;
}
- spin_unlock(&req->head->lock);
spin_unlock_irq(&ctx->ctx_lock);
-
-out:
- if (unlikely(apt.error))
- return apt.error;
-
if (mask)
- aio_poll_complete(aiocb, mask);
- iocb_put(aiocb);
- return 0;
+ iocb_put(aiocb);
+ return apt.error;
}
static int __io_submit_one(struct kioctx *ctx, const struct iocb *iocb,
- struct iocb __user *user_iocb, bool compat)
+ struct iocb __user *user_iocb, struct aio_kiocb *req,
+ bool compat)
{
- struct aio_kiocb *req;
- ssize_t ret;
-
- /* enforce forwards compatibility on users */
- if (unlikely(iocb->aio_reserved2)) {
- pr_debug("EINVAL: reserve field set\n");
- return -EINVAL;
- }
-
- /* prevent overflows */
- if (unlikely(
- (iocb->aio_buf != (unsigned long)iocb->aio_buf) ||
- (iocb->aio_nbytes != (size_t)iocb->aio_nbytes) ||
- ((ssize_t)iocb->aio_nbytes < 0)
- )) {
- pr_debug("EINVAL: overflow check\n");
- return -EINVAL;
- }
-
- if (!get_reqs_available(ctx))
- return -EAGAIN;
-
- ret = -EAGAIN;
- req = aio_get_req(ctx);
- if (unlikely(!req))
- goto out_put_reqs_available;
-
req->ki_filp = fget(iocb->aio_fildes);
- ret = -EBADF;
if (unlikely(!req->ki_filp))
- goto out_put_req;
+ return -EBADF;
if (iocb->aio_flags & IOCB_FLAG_RESFD) {
+ struct eventfd_ctx *eventfd;
/*
* If the IOCB_FLAG_RESFD flag of aio_flags is set, get an
* instance of the file* now. The file descriptor must be
* an eventfd() fd, and will be signaled for each completed
* event using the eventfd_signal() function.
*/
- req->ki_eventfd = eventfd_ctx_fdget((int) iocb->aio_resfd);
- if (IS_ERR(req->ki_eventfd)) {
- ret = PTR_ERR(req->ki_eventfd);
- req->ki_eventfd = NULL;
- goto out_put_req;
- }
+ eventfd = eventfd_ctx_fdget(iocb->aio_resfd);
+ if (IS_ERR(eventfd))
+ return PTR_ERR(eventfd);
+
+ req->ki_eventfd = eventfd;
}
- ret = put_user(KIOCB_KEY, &user_iocb->aio_key);
- if (unlikely(ret)) {
+ if (unlikely(put_user(KIOCB_KEY, &user_iocb->aio_key))) {
pr_debug("EFAULT: aio_key\n");
- goto out_put_req;
+ return -EFAULT;
}
- req->ki_user_iocb = user_iocb;
- req->ki_user_data = iocb->aio_data;
+ req->ki_res.obj = (u64)(unsigned long)user_iocb;
+ req->ki_res.data = iocb->aio_data;
+ req->ki_res.res = 0;
+ req->ki_res.res2 = 0;
switch (iocb->aio_lio_opcode) {
case IOCB_CMD_PREAD:
- ret = aio_read(&req->rw, iocb, false, compat);
- break;
+ return aio_read(&req->rw, iocb, false, compat);
case IOCB_CMD_PWRITE:
- ret = aio_write(&req->rw, iocb, false, compat);
- break;
+ return aio_write(&req->rw, iocb, false, compat);
case IOCB_CMD_PREADV:
- ret = aio_read(&req->rw, iocb, true, compat);
- break;
+ return aio_read(&req->rw, iocb, true, compat);
case IOCB_CMD_PWRITEV:
- ret = aio_write(&req->rw, iocb, true, compat);
- break;
+ return aio_write(&req->rw, iocb, true, compat);
case IOCB_CMD_FSYNC:
- ret = aio_fsync(&req->fsync, iocb, false);
- break;
+ return aio_fsync(&req->fsync, iocb, false);
case IOCB_CMD_FDSYNC:
- ret = aio_fsync(&req->fsync, iocb, true);
- break;
+ return aio_fsync(&req->fsync, iocb, true);
case IOCB_CMD_POLL:
- ret = aio_poll(req, iocb);
- break;
+ return aio_poll(req, iocb);
default:
pr_debug("invalid aio operation %d\n", iocb->aio_lio_opcode);
- ret = -EINVAL;
- break;
+ return -EINVAL;
}
-
- /*
- * If ret is 0, we'd either done aio_complete() ourselves or have
- * arranged for that to be done asynchronously. Anything non-zero
- * means that we need to destroy req ourselves.
- */
- if (ret)
- goto out_put_req;
- return 0;
-out_put_req:
- if (req->ki_eventfd)
- eventfd_ctx_put(req->ki_eventfd);
- iocb_put(req);
-out_put_reqs_available:
- put_reqs_available(ctx, 1);
- return ret;
}
static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
bool compat)
{
+ struct aio_kiocb *req;
struct iocb iocb;
+ int err;
if (unlikely(copy_from_user(&iocb, user_iocb, sizeof(iocb))))
return -EFAULT;
- return __io_submit_one(ctx, &iocb, user_iocb, compat);
+ /* enforce forwards compatibility on users */
+ if (unlikely(iocb.aio_reserved2)) {
+ pr_debug("EINVAL: reserve field set\n");
+ return -EINVAL;
+ }
+
+ /* prevent overflows */
+ if (unlikely(
+ (iocb.aio_buf != (unsigned long)iocb.aio_buf) ||
+ (iocb.aio_nbytes != (size_t)iocb.aio_nbytes) ||
+ ((ssize_t)iocb.aio_nbytes < 0)
+ )) {
+ pr_debug("EINVAL: overflow check\n");
+ return -EINVAL;
+ }
+
+ req = aio_get_req(ctx);
+ if (unlikely(!req))
+ return -EAGAIN;
+
+ err = __io_submit_one(ctx, &iocb, user_iocb, req, compat);
+
+ /* Done with the synchronous reference */
+ iocb_put(req);
+
+ /*
+ * If err is 0, we'd either done aio_complete() ourselves or have
+ * arranged for that to be done asynchronously. Anything non-zero
+ * means that we need to destroy req ourselves.
+ */
+ if (unlikely(err)) {
+ iocb_destroy(req);
+ put_reqs_available(ctx, 1);
+ }
+ return err;
}
/* sys_io_submit:
}
#endif
-/* lookup_kiocb
- * Finds a given iocb for cancellation.
- */
-static struct aio_kiocb *
-lookup_kiocb(struct kioctx *ctx, struct iocb __user *iocb)
-{
- struct aio_kiocb *kiocb;
-
- assert_spin_locked(&ctx->ctx_lock);
-
- /* TODO: use a hash or array, this sucks. */
- list_for_each_entry(kiocb, &ctx->active_reqs, ki_list) {
- if (kiocb->ki_user_iocb == iocb)
- return kiocb;
- }
- return NULL;
-}
-
/* sys_io_cancel:
* Attempts to cancel an iocb previously passed to io_submit. If
* the operation is successfully cancelled, the resulting event is
struct aio_kiocb *kiocb;
int ret = -EINVAL;
u32 key;
+ u64 obj = (u64)(unsigned long)iocb;
if (unlikely(get_user(key, &iocb->aio_key)))
return -EFAULT;
return -EINVAL;
spin_lock_irq(&ctx->ctx_lock);
- kiocb = lookup_kiocb(ctx, iocb);
- if (kiocb) {
- ret = kiocb->ki_cancel(&kiocb->rw);
- list_del_init(&kiocb->ki_list);
+ /* TODO: use a hash or array, this sucks. */
+ list_for_each_entry(kiocb, &ctx->active_reqs, ki_list) {
+ if (kiocb->ki_res.obj == obj) {
+ ret = kiocb->ki_cancel(&kiocb->rw);
+ list_del_init(&kiocb->ki_list);
+ break;
+ }
}
spin_unlock_irq(&ctx->ctx_lock);
struct blkdev_dio *dio = bio->bi_private;
bool should_dirty = dio->should_dirty;
- if (dio->multi_bio && !atomic_dec_and_test(&dio->ref)) {
- if (bio->bi_status && !dio->bio.bi_status)
- dio->bio.bi_status = bio->bi_status;
- } else {
+ if (bio->bi_status && !dio->bio.bi_status)
+ dio->bio.bi_status = bio->bi_status;
+
+ if (!dio->multi_bio || atomic_dec_and_test(&dio->ref)) {
if (!dio->is_sync) {
struct kiocb *iocb = dio->iocb;
ssize_t ret;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
+ /*
+ * If the fs is mounted with nologreplay, which requires it to be
+ * mounted in RO mode as well, we can not allow discard on free space
+ * inside block groups, because log trees refer to extents that are not
+ * pinned in a block group's free space cache (pinning the extents is
+ * precisely the first phase of replaying a log tree).
+ */
+ if (btrfs_test_opt(fs_info, NOLOGREPLAY))
+ return -EROFS;
+
rcu_read_lock();
list_for_each_entry_rcu(device, &fs_info->fs_devices->devices,
dev_list) {
static int prop_compression_validate(const char *value, size_t len)
{
- if (!strncmp("lzo", value, len))
+ if (!strncmp("lzo", value, 3))
return 0;
- else if (!strncmp("zlib", value, len))
+ else if (!strncmp("zlib", value, 4))
return 0;
- else if (!strncmp("zstd", value, len))
+ else if (!strncmp("zstd", value, 4))
return 0;
return -EINVAL;
btrfs_set_fs_incompat(fs_info, COMPRESS_LZO);
} else if (!strncmp("zlib", value, 4)) {
type = BTRFS_COMPRESS_ZLIB;
- } else if (!strncmp("zstd", value, len)) {
+ } else if (!strncmp("zstd", value, 4)) {
type = BTRFS_COMPRESS_ZSTD;
btrfs_set_fs_incompat(fs_info, COMPRESS_ZSTD);
} else {
struct inode *inode = container_of(head, struct inode, i_rcu);
struct ceph_inode_info *ci = ceph_inode(inode);
+ kfree(ci->i_symlink);
kmem_cache_free(ceph_inode_cachep, ci);
}
}
}
- kfree(ci->i_symlink);
while ((n = rb_first(&ci->i_fragtree)) != NULL) {
frag = rb_entry(n, struct ceph_inode_frag, node);
rb_erase(n, &ci->i_fragtree);
tcon->ses->server->echo_interval / HZ);
if (tcon->snapshot_time)
seq_printf(s, ",snapshot=%llu", tcon->snapshot_time);
+ if (tcon->handle_timeout)
+ seq_printf(s, ",handletimeout=%u", tcon->handle_timeout);
/* convert actimeo and display it in seconds */
seq_printf(s, ",actimeo=%lu", cifs_sb->actimeo / HZ);
*/
#define CIFS_MAX_ACTIMEO (1 << 30)
+/*
+ * Max persistent and resilient handle timeout (milliseconds).
+ * Windows durable max was 960000 (16 minutes)
+ */
+#define SMB3_MAX_HANDLE_TIMEOUT 960000
+
/*
* MAX_REQ is the maximum number of requests that WE will send
* on one socket concurrently.
struct nls_table *local_nls;
unsigned int echo_interval; /* echo interval in secs */
__u64 snapshot_time; /* needed for timewarp tokens */
+ __u32 handle_timeout; /* persistent and durable handle timeout in ms */
unsigned int max_credits; /* smb3 max_credits 10 < credits < 60000 */
};
__u32 vol_serial_number;
__le64 vol_create_time;
__u64 snapshot_time; /* for timewarp tokens - timestamp of snapshot */
+ __u32 handle_timeout; /* persistent and durable handle timeout in ms */
__u32 ss_flags; /* sector size flags */
__u32 perf_sector_size; /* best sector size for perf */
__u32 max_chunks;
Opt_cruid, Opt_gid, Opt_file_mode,
Opt_dirmode, Opt_port,
Opt_blocksize, Opt_rsize, Opt_wsize, Opt_actimeo,
- Opt_echo_interval, Opt_max_credits,
+ Opt_echo_interval, Opt_max_credits, Opt_handletimeout,
Opt_snapshot,
/* Mount options which take string value */
{ Opt_rsize, "rsize=%s" },
{ Opt_wsize, "wsize=%s" },
{ Opt_actimeo, "actimeo=%s" },
+ { Opt_handletimeout, "handletimeout=%s" },
{ Opt_echo_interval, "echo_interval=%s" },
{ Opt_max_credits, "max_credits=%s" },
{ Opt_snapshot, "snapshot=%s" },
vol->actimeo = CIFS_DEF_ACTIMEO;
+ /* Most clients set timeout to 0, allows server to use its default */
+ vol->handle_timeout = 0; /* See MS-SMB2 spec section 2.2.14.2.12 */
+
/* offer SMB2.1 and later (SMB3 etc). Secure and widely accepted */
vol->ops = &smb30_operations;
vol->vals = &smbdefault_values;
goto cifs_parse_mount_err;
}
break;
+ case Opt_handletimeout:
+ if (get_option_ul(args, &option)) {
+ cifs_dbg(VFS, "%s: Invalid handletimeout value\n",
+ __func__);
+ goto cifs_parse_mount_err;
+ }
+ vol->handle_timeout = option;
+ if (vol->handle_timeout > SMB3_MAX_HANDLE_TIMEOUT) {
+ cifs_dbg(VFS, "Invalid handle cache timeout, longer than 16 minutes\n");
+ goto cifs_parse_mount_err;
+ }
+ break;
case Opt_echo_interval:
if (get_option_ul(args, &option)) {
cifs_dbg(VFS, "%s: Invalid echo interval value\n",
return 0;
if (tcon->snapshot_time != volume_info->snapshot_time)
return 0;
+ if (tcon->handle_timeout != volume_info->handle_timeout)
+ return 0;
return 1;
}
tcon->snapshot_time = volume_info->snapshot_time;
}
+ if (volume_info->handle_timeout) {
+ if (ses->server->vals->protocol_id == 0) {
+ cifs_dbg(VFS,
+ "Use SMB2.1 or later for handle timeout option\n");
+ rc = -EOPNOTSUPP;
+ goto out_fail;
+ } else
+ tcon->handle_timeout = volume_info->handle_timeout;
+ }
+
tcon->ses = ses;
if (volume_info->password) {
tcon->password = kstrdup(volume_info->password, GFP_KERNEL);
if (oparms->tcon->use_resilient) {
- nr_ioctl_req.Timeout = 0; /* use server default (120 seconds) */
+ /* default timeout is 0, servers pick default (120 seconds) */
+ nr_ioctl_req.Timeout =
+ cpu_to_le32(oparms->tcon->handle_timeout);
nr_ioctl_req.Reserved = 0;
rc = SMB2_ioctl(xid, oparms->tcon, fid->persistent_fid,
fid->volatile_fid, FSCTL_LMR_REQUEST_RESILIENCY,
true /* is_fsctl */,
(char *)&nr_ioctl_req, sizeof(nr_ioctl_req),
- NULL, NULL /* no return info */);
+ CIFSMaxBufSize, NULL, NULL /* no return info */);
if (rc == -EOPNOTSUPP) {
cifs_dbg(VFS,
"resiliency not supported by server, disabling\n");
rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID,
FSCTL_QUERY_NETWORK_INTERFACE_INFO, true /* is_fsctl */,
NULL /* no data input */, 0 /* no data input */,
- (char **)&out_buf, &ret_data_len);
+ CIFSMaxBufSize, (char **)&out_buf, &ret_data_len);
if (rc == -EOPNOTSUPP) {
cifs_dbg(FYI,
"server does not support query network interfaces\n");
oparms.fid->mid = le64_to_cpu(o_rsp->sync_hdr.MessageId);
#endif /* CIFS_DEBUG2 */
- if (o_rsp->OplockLevel == SMB2_OPLOCK_LEVEL_LEASE)
- oplock = smb2_parse_lease_state(server, o_rsp,
- &oparms.fid->epoch,
- oparms.fid->lease_key);
- else
- goto oshr_exit;
-
-
memcpy(tcon->crfid.fid, pfid, sizeof(struct cifs_fid));
tcon->crfid.tcon = tcon;
tcon->crfid.is_valid = true;
kref_init(&tcon->crfid.refcount);
- kref_get(&tcon->crfid.refcount);
+ if (o_rsp->OplockLevel == SMB2_OPLOCK_LEVEL_LEASE) {
+ kref_get(&tcon->crfid.refcount);
+ oplock = smb2_parse_lease_state(server, o_rsp,
+ &oparms.fid->epoch,
+ oparms.fid->lease_key);
+ } else
+ goto oshr_exit;
qi_rsp = (struct smb2_query_info_rsp *)rsp_iov[1].iov_base;
if (le32_to_cpu(qi_rsp->OutputBufferLength) < sizeof(struct smb2_file_all_info))
goto oshr_exit;
- rc = smb2_validate_and_copy_iov(
+ if (!smb2_validate_and_copy_iov(
le16_to_cpu(qi_rsp->OutputBufferOffset),
sizeof(struct smb2_file_all_info),
&rsp_iov[1], sizeof(struct smb2_file_all_info),
- (char *)&tcon->crfid.file_all_info);
- if (rc)
- goto oshr_exit;
- tcon->crfid.file_all_info_is_valid = 1;
+ (char *)&tcon->crfid.file_all_info))
+ tcon->crfid.file_all_info_is_valid = 1;
oshr_exit:
mutex_unlock(&tcon->crfid.fid_mutex);
rc = SMB2_ioctl(xid, tcon, persistent_fid, volatile_fid,
FSCTL_SRV_REQUEST_RESUME_KEY, true /* is_fsctl */,
- NULL, 0 /* no input */,
+ NULL, 0 /* no input */, CIFSMaxBufSize,
(char **)&res_key, &ret_data_len);
if (rc) {
rc = SMB2_ioctl_init(tcon, &rqst[1],
COMPOUND_FID, COMPOUND_FID,
qi.info_type, true, NULL,
- 0);
+ 0, CIFSMaxBufSize);
}
} else if (qi.flags == PASSTHRU_QUERY_INFO) {
memset(&qi_iov, 0, sizeof(qi_iov));
rc = SMB2_ioctl(xid, tcon, trgtfile->fid.persistent_fid,
trgtfile->fid.volatile_fid, FSCTL_SRV_COPYCHUNK_WRITE,
true /* is_fsctl */, (char *)pcchunk,
- sizeof(struct copychunk_ioctl), (char **)&retbuf,
- &ret_data_len);
+ sizeof(struct copychunk_ioctl), CIFSMaxBufSize,
+ (char **)&retbuf, &ret_data_len);
if (rc == 0) {
if (ret_data_len !=
sizeof(struct copychunk_ioctl_rsp)) {
rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid,
cfile->fid.volatile_fid, FSCTL_SET_SPARSE,
true /* is_fctl */,
- &setsparse, 1, NULL, NULL);
+ &setsparse, 1, CIFSMaxBufSize, NULL, NULL);
if (rc) {
tcon->broken_sparse_sup = true;
cifs_dbg(FYI, "set sparse rc = %d\n", rc);
true /* is_fsctl */,
(char *)&dup_ext_buf,
sizeof(struct duplicate_extents_to_file),
- NULL,
+ CIFSMaxBufSize, NULL,
&ret_data_len);
if (ret_data_len > 0)
true /* is_fsctl */,
(char *)&integr_info,
sizeof(struct fsctl_set_integrity_information_req),
- NULL,
+ CIFSMaxBufSize, NULL,
&ret_data_len);
}
/* GMT Token is @GMT-YYYY.MM.DD-HH.MM.SS Unicode which is 48 bytes + null */
#define GMT_TOKEN_SIZE 50
+#define MIN_SNAPSHOT_ARRAY_SIZE 16 /* See MS-SMB2 section 3.3.5.15.1 */
+
/*
* Input buffer contains (empty) struct smb_snapshot array with size filled in
* For output see struct SRV_SNAPSHOT_ARRAY in MS-SMB2 section 2.2.32.2
char *retbuf = NULL;
unsigned int ret_data_len = 0;
int rc;
+ u32 max_response_size;
struct smb_snapshot_array snapshot_in;
+ if (get_user(ret_data_len, (unsigned int __user *)ioc_buf))
+ return -EFAULT;
+
+ /*
+ * Note that for snapshot queries that servers like Azure expect that
+ * the first query be minimal size (and just used to get the number/size
+ * of previous versions) so response size must be specified as EXACTLY
+ * sizeof(struct snapshot_array) which is 16 when rounded up to multiple
+ * of eight bytes.
+ */
+ if (ret_data_len == 0)
+ max_response_size = MIN_SNAPSHOT_ARRAY_SIZE;
+ else
+ max_response_size = CIFSMaxBufSize;
+
rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid,
cfile->fid.volatile_fid,
FSCTL_SRV_ENUMERATE_SNAPSHOTS,
true /* is_fsctl */,
- NULL, 0 /* no input data */,
+ NULL, 0 /* no input data */, max_response_size,
(char **)&retbuf,
&ret_data_len);
cifs_dbg(FYI, "enum snaphots ioctl returned %d and ret buflen is %d\n",
rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID,
FSCTL_DFS_GET_REFERRALS,
true /* is_fsctl */,
- (char *)dfs_req, dfs_req_size,
+ (char *)dfs_req, dfs_req_size, CIFSMaxBufSize,
(char **)&dfs_rsp, &dfs_rsp_size);
} while (rc == -EAGAIN);
rc = SMB2_ioctl_init(tcon, &rqst[num++], cfile->fid.persistent_fid,
cfile->fid.volatile_fid, FSCTL_SET_ZERO_DATA,
true /* is_fctl */, (char *)&fsctl_buf,
- sizeof(struct file_zero_data_information));
+ sizeof(struct file_zero_data_information),
+ CIFSMaxBufSize);
if (rc)
goto zero_range_exit;
rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid,
cfile->fid.volatile_fid, FSCTL_SET_ZERO_DATA,
true /* is_fctl */, (char *)&fsctl_buf,
- sizeof(struct file_zero_data_information), NULL, NULL);
+ sizeof(struct file_zero_data_information),
+ CIFSMaxBufSize, NULL, NULL);
free_xid(xid);
return rc;
}
rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID,
FSCTL_VALIDATE_NEGOTIATE_INFO, true /* is_fsctl */,
- (char *)pneg_inbuf, inbuflen, (char **)&pneg_rsp, &rsplen);
+ (char *)pneg_inbuf, inbuflen, CIFSMaxBufSize,
+ (char **)&pneg_rsp, &rsplen);
if (rc == -EOPNOTSUPP) {
/*
* Old Windows versions or Netapp SMB server can return
}
static struct create_durable_v2 *
-create_durable_v2_buf(struct cifs_fid *pfid)
+create_durable_v2_buf(struct cifs_open_parms *oparms)
{
+ struct cifs_fid *pfid = oparms->fid;
struct create_durable_v2 *buf;
buf = kzalloc(sizeof(struct create_durable_v2), GFP_KERNEL);
(struct create_durable_v2, Name));
buf->ccontext.NameLength = cpu_to_le16(4);
- buf->dcontext.Timeout = 0; /* Should this be configurable by workload */
+ /*
+ * NB: Handle timeout defaults to 0, which allows server to choose
+ * (most servers default to 120 seconds) and most clients default to 0.
+ * This can be overridden at mount ("handletimeout=") if the user wants
+ * a different persistent (or resilient) handle timeout for all opens
+ * opens on a particular SMB3 mount.
+ */
+ buf->dcontext.Timeout = cpu_to_le32(oparms->tcon->handle_timeout);
buf->dcontext.Flags = cpu_to_le32(SMB2_DHANDLE_FLAG_PERSISTENT);
generate_random_uuid(buf->dcontext.CreateGuid);
memcpy(pfid->create_guid, buf->dcontext.CreateGuid, 16);
struct smb2_create_req *req = iov[0].iov_base;
unsigned int num = *num_iovec;
- iov[num].iov_base = create_durable_v2_buf(oparms->fid);
+ iov[num].iov_base = create_durable_v2_buf(oparms);
if (iov[num].iov_base == NULL)
return -ENOMEM;
iov[num].iov_len = sizeof(struct create_durable_v2);
int
SMB2_ioctl_init(struct cifs_tcon *tcon, struct smb_rqst *rqst,
u64 persistent_fid, u64 volatile_fid, u32 opcode,
- bool is_fsctl, char *in_data, u32 indatalen)
+ bool is_fsctl, char *in_data, u32 indatalen,
+ __u32 max_response_size)
{
struct smb2_ioctl_req *req;
struct kvec *iov = rqst->rq_iov;
req->OutputCount = 0; /* MBZ */
/*
- * Could increase MaxOutputResponse, but that would require more
- * than one credit. Windows typically sets this smaller, but for some
+ * In most cases max_response_size is set to 16K (CIFSMaxBufSize)
+ * We Could increase default MaxOutputResponse, but that could require
+ * more credits. Windows typically sets this smaller, but for some
* ioctls it may be useful to allow server to send more. No point
* limiting what the server can send as long as fits in one credit
- * Unfortunately - we can not handle more than CIFS_MAX_MSG_SIZE
- * (by default, note that it can be overridden to make max larger)
- * in responses (except for read responses which can be bigger.
- * We may want to bump this limit up
+ * We can not handle more than CIFS_MAX_BUF_SIZE yet but may want
+ * to increase this limit up in the future.
+ * Note that for snapshot queries that servers like Azure expect that
+ * the first query be minimal size (and just used to get the number/size
+ * of previous versions) so response size must be specified as EXACTLY
+ * sizeof(struct snapshot_array) which is 16 when rounded up to multiple
+ * of eight bytes. Currently that is the only case where we set max
+ * response size smaller.
*/
- req->MaxOutputResponse = cpu_to_le32(CIFSMaxBufSize);
+ req->MaxOutputResponse = cpu_to_le32(max_response_size);
if (is_fsctl)
req->Flags = cpu_to_le32(SMB2_0_IOCTL_IS_FSCTL);
cifs_small_buf_release(rqst->rq_iov[0].iov_base); /* request */
}
+
/*
* SMB2 IOCTL is used for both IOCTLs and FSCTLs
*/
int
SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
u64 volatile_fid, u32 opcode, bool is_fsctl,
- char *in_data, u32 indatalen,
+ char *in_data, u32 indatalen, u32 max_out_data_len,
char **out_data, u32 *plen /* returned data len */)
{
struct smb_rqst rqst;
rqst.rq_iov = iov;
rqst.rq_nvec = SMB2_IOCTL_IOV_SIZE;
- rc = SMB2_ioctl_init(tcon, &rqst, persistent_fid, volatile_fid,
- opcode, is_fsctl, in_data, indatalen);
+ rc = SMB2_ioctl_init(tcon, &rqst, persistent_fid, volatile_fid, opcode,
+ is_fsctl, in_data, indatalen, max_out_data_len);
if (rc)
goto ioctl_exit;
rc = SMB2_ioctl(xid, tcon, persistent_fid, volatile_fid,
FSCTL_SET_COMPRESSION, true /* is_fsctl */,
(char *)&fsctl_input /* data input */,
- 2 /* in data len */, &ret_data /* out data */, NULL);
+ 2 /* in data len */, CIFSMaxBufSize /* max out data */,
+ &ret_data /* out data */, NULL);
cifs_dbg(FYI, "set compression rc %d\n", rc);
extern void SMB2_open_free(struct smb_rqst *rqst);
extern int SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon,
u64 persistent_fid, u64 volatile_fid, u32 opcode,
- bool is_fsctl, char *in_data, u32 indatalen,
+ bool is_fsctl, char *in_data, u32 indatalen, u32 maxoutlen,
char **out_data, u32 *plen /* returned data len */);
extern int SMB2_ioctl_init(struct cifs_tcon *tcon, struct smb_rqst *rqst,
u64 persistent_fid, u64 volatile_fid, u32 opcode,
- bool is_fsctl, char *in_data, u32 indatalen);
+ bool is_fsctl, char *in_data, u32 indatalen,
+ __u32 max_response_size);
extern void SMB2_ioctl_free(struct smb_rqst *rqst);
extern int SMB2_close(const unsigned int xid, struct cifs_tcon *tcon,
u64 persistent_file_id, u64 volatile_file_id);
#include <linux/sizes.h>
#include <linux/mmu_notifier.h>
#include <linux/iomap.h>
+#include <asm/pgalloc.h>
#include "internal.h"
#define CREATE_TRACE_POINTS
{
struct address_space *mapping = vmf->vma->vm_file->f_mapping;
unsigned long pmd_addr = vmf->address & PMD_MASK;
+ struct vm_area_struct *vma = vmf->vma;
struct inode *inode = mapping->host;
+ pgtable_t pgtable = NULL;
struct page *zero_page;
spinlock_t *ptl;
pmd_t pmd_entry;
*entry = dax_insert_entry(xas, mapping, vmf, *entry, pfn,
DAX_PMD | DAX_ZERO_PAGE, false);
+ if (arch_needs_pgtable_deposit()) {
+ pgtable = pte_alloc_one(vma->vm_mm);
+ if (!pgtable)
+ return VM_FAULT_OOM;
+ }
+
ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd);
if (!pmd_none(*(vmf->pmd))) {
spin_unlock(ptl);
goto fallback;
}
+ if (pgtable) {
+ pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable);
+ mm_inc_nr_ptes(vma->vm_mm);
+ }
pmd_entry = mk_pmd(zero_page, vmf->vma->vm_page_prot);
pmd_entry = pmd_mkhuge(pmd_entry);
set_pmd_at(vmf->vma->vm_mm, pmd_addr, vmf->pmd, pmd_entry);
return VM_FAULT_NOPAGE;
fallback:
+ if (pgtable)
+ pte_free(vma->vm_mm, pgtable);
trace_dax_pmd_load_hole_fallback(inode, vmf, zero_page, *entry);
return VM_FAULT_FALLBACK;
}
return 0;
}
-static void debugfs_evict_inode(struct inode *inode)
+static void debugfs_i_callback(struct rcu_head *head)
{
- truncate_inode_pages_final(&inode->i_data);
- clear_inode(inode);
+ struct inode *inode = container_of(head, struct inode, i_rcu);
if (S_ISLNK(inode->i_mode))
kfree(inode->i_link);
+ free_inode_nonrcu(inode);
+}
+
+static void debugfs_destroy_inode(struct inode *inode)
+{
+ call_rcu(&inode->i_rcu, debugfs_i_callback);
}
static const struct super_operations debugfs_super_operations = {
.statfs = simple_statfs,
.remount_fs = debugfs_remount,
.show_options = debugfs_show_options,
- .evict_inode = debugfs_evict_inode,
+ .destroy_inode = debugfs_destroy_inode,
};
static void debugfs_release_dentry(struct dentry *dentry)
for (param = desc->specs; param->name; param++) {
if (param->opt == e->opt &&
param->type != fs_param_is_enum) {
- pr_err("VALIDATE %s: e[%lu] enum val for %s\n",
+ pr_err("VALIDATE %s: e[%tu] enum val for %s\n",
name, e - desc->enums, param->name);
good = false;
}
rem += pipe->bufs[(pipe->curbuf + idx) & (pipe->buffers - 1)].len;
ret = -EINVAL;
- if (rem < len) {
- pipe_unlock(pipe);
- goto out;
- }
+ if (rem < len)
+ goto out_free;
rem = len;
while (rem) {
pipe->curbuf = (pipe->curbuf + 1) & (pipe->buffers - 1);
pipe->nrbufs--;
} else {
- pipe_buf_get(pipe, ibuf);
+ if (!pipe_buf_get(pipe, ibuf))
+ goto out_free;
+
*obuf = *ibuf;
obuf->flags &= ~PIPE_BUF_FLAG_GIFT;
obuf->len = rem;
ret = fuse_dev_do_write(fud, &cs, len);
pipe_lock(pipe);
+out_free:
for (idx = 0; idx < nbuf; idx++)
pipe_buf_release(pipe, &bufs[idx]);
pipe_unlock(pipe);
-out:
kvfree(bufs);
return ret;
}
umode_t mode, dev_t dev)
{
struct inode *inode;
- struct resv_map *resv_map;
+ struct resv_map *resv_map = NULL;
- resv_map = resv_map_alloc();
- if (!resv_map)
- return NULL;
+ /*
+ * Reserve maps are only needed for inodes that can have associated
+ * page allocations.
+ */
+ if (S_ISREG(mode) || S_ISLNK(mode)) {
+ resv_map = resv_map_alloc();
+ if (!resv_map)
+ return NULL;
+ }
inode = new_inode(sb);
if (inode) {
break;
}
lockdep_annotate_inode_mutex_key(inode);
- } else
- kref_put(&resv_map->refs, resv_map_release);
+ } else {
+ if (resv_map)
+ kref_put(&resv_map->refs, resv_map_release);
+ }
return inode;
}
ret = rw_verify_area(WRITE, file, &kiocb->ki_pos, iov_count);
if (!ret) {
+ ssize_t ret2;
+
/*
* Open-code file_start_write here to grab freeze protection,
* which will be released by another thread in
SB_FREEZE_WRITE);
}
kiocb->ki_flags |= IOCB_WRITE;
- io_rw_done(kiocb, call_write_iter(file, kiocb, &iter));
+
+ ret2 = call_write_iter(file, kiocb, &iter);
+ if (!force_nonblock || ret2 != -EAGAIN) {
+ io_rw_done(kiocb, ret2);
+ } else {
+ /*
+ * If ->needs_lock is true, we're already in async
+ * context.
+ */
+ if (!s->needs_lock)
+ io_async_list_note(WRITE, req, iov_count);
+ ret = -EAGAIN;
+ }
}
out_free:
kfree(iovec);
return 0;
if (sig) {
- ret = set_user_sigmask(sig, &ksigmask, &sigsaved, sigsz);
+#ifdef CONFIG_COMPAT
+ if (in_compat_syscall())
+ ret = set_compat_user_sigmask((const compat_sigset_t __user *)sig,
+ &ksigmask, &sigsaved, sigsz);
+ else
+#endif
+ ret = set_user_sigmask(sig, &ksigmask,
+ &sigsaved, sigsz);
+
if (ret)
return ret;
}
fput(ctx->user_files[i]);
kfree(ctx->user_files);
+ ctx->user_files = NULL;
ctx->nr_user_files = 0;
return ret;
}
goto err;
if (ctx->flags & IORING_SETUP_SQPOLL) {
+ ret = -EPERM;
+ if (!capable(CAP_SYS_ADMIN))
+ goto err;
+
if (p->flags & IORING_SETUP_SQ_AFF) {
int cpu;
jffs2_kill_fragtree(&f->fragtree, deleted?c:NULL);
- if (f->target) {
- kfree(f->target);
- f->target = NULL;
- }
-
fds = f->dents;
while(fds) {
fd = fds;
static void jffs2_i_callback(struct rcu_head *head)
{
struct inode *inode = container_of(head, struct inode, i_rcu);
- kmem_cache_free(jffs2_inode_cachep, JFFS2_INODE_INFO(inode));
+ struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode);
+
+ kfree(f->target);
+ kmem_cache_free(jffs2_inode_cachep, f);
}
static void jffs2_destroy_inode(struct inode *inode)
};
ssize_t err, err2;
- if (!nfs_server_capable(file_inode(dst), NFS_CAP_COPY))
- return -EOPNOTSUPP;
-
src_lock = nfs_get_lock_context(nfs_file_open_context(src));
if (IS_ERR(src_lock))
return PTR_ERR(src_lock);
struct file *file_out, loff_t pos_out,
size_t count, unsigned int flags)
{
+ if (!nfs_server_capable(file_inode(file_out), NFS_CAP_COPY))
+ return -EOPNOTSUPP;
if (file_inode(file_in) == file_inode(file_out))
- return -EINVAL;
+ return -EOPNOTSUPP;
return nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count);
}
ARRAY_SIZE(nfs4_acl_bitmap), &hdr);
rpc_prepare_reply_pages(req, args->acl_pages, 0,
- args->acl_len, replen);
+ args->acl_len, replen + 1);
encode_nops(&hdr);
}
}
rpc_prepare_reply_pages(req, (struct page **)&args->page, 0,
- PAGE_SIZE, replen);
+ PAGE_SIZE, replen + 1);
encode_nops(&hdr);
}
memcpy(sap, &data->addr, sizeof(data->addr));
args->nfs_server.addrlen = sizeof(data->addr);
args->nfs_server.port = ntohs(data->addr.sin_port);
- if (!nfs_verify_server_address(sap))
+ if (sap->sa_family != AF_INET ||
+ !nfs_verify_server_address(sap))
goto out_no_address;
if (!(data->flags & NFS_MOUNT_TCP))
/* Lock an inode and grab a bh pointing to the inode. */
int ocfs2_reflink_inodes_lock(struct inode *s_inode,
- struct buffer_head **bh1,
+ struct buffer_head **bh_s,
struct inode *t_inode,
- struct buffer_head **bh2)
+ struct buffer_head **bh_t)
{
- struct inode *inode1;
- struct inode *inode2;
+ struct inode *inode1 = s_inode;
+ struct inode *inode2 = t_inode;
struct ocfs2_inode_info *oi1;
struct ocfs2_inode_info *oi2;
+ struct buffer_head *bh1 = NULL;
+ struct buffer_head *bh2 = NULL;
bool same_inode = (s_inode == t_inode);
+ bool need_swap = (inode1->i_ino > inode2->i_ino);
int status;
/* First grab the VFS and rw locks. */
lock_two_nondirectories(s_inode, t_inode);
- inode1 = s_inode;
- inode2 = t_inode;
- if (inode1->i_ino > inode2->i_ino)
+ if (need_swap)
swap(inode1, inode2);
status = ocfs2_rw_lock(inode1, 1);
trace_ocfs2_double_lock((unsigned long long)oi1->ip_blkno,
(unsigned long long)oi2->ip_blkno);
- if (*bh1)
- *bh1 = NULL;
- if (*bh2)
- *bh2 = NULL;
-
/* We always want to lock the one with the lower lockid first. */
if (oi1->ip_blkno > oi2->ip_blkno)
mlog_errno(-ENOLCK);
/* lock id1 */
- status = ocfs2_inode_lock_nested(inode1, bh1, 1, OI_LS_REFLINK_TARGET);
+ status = ocfs2_inode_lock_nested(inode1, &bh1, 1,
+ OI_LS_REFLINK_TARGET);
if (status < 0) {
if (status != -ENOENT)
mlog_errno(status);
/* lock id2 */
if (!same_inode) {
- status = ocfs2_inode_lock_nested(inode2, bh2, 1,
+ status = ocfs2_inode_lock_nested(inode2, &bh2, 1,
OI_LS_REFLINK_TARGET);
if (status < 0) {
if (status != -ENOENT)
mlog_errno(status);
goto out_cl1;
}
- } else
- *bh2 = *bh1;
+ } else {
+ bh2 = bh1;
+ }
+
+ /*
+ * If we swapped inode order above, we have to swap the buffer heads
+ * before passing them back to the caller.
+ */
+ if (need_swap)
+ swap(bh1, bh2);
+ *bh_s = bh1;
+ *bh_t = bh2;
trace_ocfs2_double_lock_end(
(unsigned long long)oi1->ip_blkno,
out_cl1:
ocfs2_inode_unlock(inode1, 1);
- brelse(*bh1);
- *bh1 = NULL;
+ brelse(bh1);
out_rw2:
ocfs2_rw_unlock(inode2, 1);
out_i2:
return 0;
}
+ /* Any file opened for execve()/uselib() has to be a regular file. */
+ if (unlikely(f->f_flags & FMODE_EXEC && !S_ISREG(inode->i_mode))) {
+ error = -EACCES;
+ goto cleanup_file;
+ }
+
if (f->f_mode & FMODE_WRITE && !special_file(inode->i_mode)) {
error = get_write_access(inode);
if (unlikely(error))
}
EXPORT_SYMBOL(nonseekable_open);
+
+/*
+ * stream_open is used by subsystems that want stream-like file descriptors.
+ * Such file descriptors are not seekable and don't have notion of position
+ * (file.f_pos is always 0). Contrary to file descriptors of other regular
+ * files, .read() and .write() can run simultaneously.
+ *
+ * stream_open never fails and is marked to return int so that it could be
+ * directly used as file_operations.open .
+ */
+int stream_open(struct inode *inode, struct file *filp)
+{
+ filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE | FMODE_ATOMIC_POS);
+ filp->f_mode |= FMODE_STREAM;
+ return 0;
+}
+
+EXPORT_SYMBOL(stream_open);
* in the tee() system call, when we duplicate the buffers in one
* pipe into another.
*/
-void generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf)
+bool generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf)
{
- get_page(buf->page);
+ return try_get_page(buf->page);
}
EXPORT_SYMBOL(generic_pipe_buf_get);
static int proc_pid_syscall(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *task)
{
- long nr;
- unsigned long args[6], sp, pc;
+ struct syscall_info info;
+ u64 *args = &info.data.args[0];
int res;
res = lock_trace(task);
if (res)
return res;
- if (task_current_syscall(task, &nr, args, 6, &sp, &pc))
+ if (task_current_syscall(task, &info))
seq_puts(m, "running\n");
- else if (nr < 0)
- seq_printf(m, "%ld 0x%lx 0x%lx\n", nr, sp, pc);
+ else if (info.data.nr < 0)
+ seq_printf(m, "%d 0x%llx 0x%llx\n",
+ info.data.nr, info.sp, info.data.instruction_pointer);
else
seq_printf(m,
- "%ld 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx\n",
- nr,
+ "%d 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx\n",
+ info.data.nr,
args[0], args[1], args[2], args[3], args[4], args[5],
- sp, pc);
+ info.sp, info.data.instruction_pointer);
unlock_trace(task);
return 0;
/*
* MODULES_VADDR has no intersection with VMALLOC_ADDR.
*/
-struct kcore_list kcore_modules;
+static struct kcore_list kcore_modules;
static void __init add_modules_range(void)
{
if (MODULES_VADDR != VMALLOC_START && MODULES_END != VMALLOC_END) {
if (--header->nreg)
return;
- put_links(header);
+ if (parent)
+ put_links(header);
start_unregistering(header);
if (!--header->count)
kfree_rcu(header, rcu);
static inline loff_t file_pos_read(struct file *file)
{
- return file->f_pos;
+ return file->f_mode & FMODE_STREAM ? 0 : file->f_pos;
}
static inline void file_pos_write(struct file *file, loff_t pos)
{
- file->f_pos = pos;
+ if ((file->f_mode & FMODE_STREAM) == 0)
+ file->f_pos = pos;
}
ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count)
* Get a reference to this pipe buffer,
* so we can copy the contents over.
*/
- pipe_buf_get(ipipe, ibuf);
+ if (!pipe_buf_get(ipipe, ibuf)) {
+ if (ret == 0)
+ ret = -EFAULT;
+ break;
+ }
*obuf = *ibuf;
/*
* Get a reference to this pipe buffer,
* so we can copy the contents over.
*/
- pipe_buf_get(ipipe, ibuf);
+ if (!pipe_buf_get(ipipe, ibuf)) {
+ if (ret == 0)
+ ret = -EFAULT;
+ break;
+ }
obuf = opipe->bufs + nbuf;
*obuf = *ibuf;
{
struct inode *inode = container_of(head, struct inode, i_rcu);
struct ubifs_inode *ui = ubifs_inode(inode);
+ kfree(ui->data);
kmem_cache_free(ubifs_inode_slab, ui);
}
static void ubifs_destroy_inode(struct inode *inode)
{
- struct ubifs_inode *ui = ubifs_inode(inode);
-
- kfree(ui->data);
call_rcu(&inode->i_rcu, ubifs_i_callback);
}
* Root level must use BMAP_BROOT_PTR_ADDR macro to get ptr out.
*/
level = be16_to_cpu(block->bb_level);
- ASSERT(level > 0);
+ if (unlikely(level == 0)) {
+ XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp);
+ return -EFSCORRUPTED;
+ }
pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, 1, ifp->if_broot_bytes);
bno = be64_to_cpu(*pp);
struct xfs_bmbt_irec *mval, /* output: map values */
int *nmap) /* i/o: mval size/count */
{
+ struct xfs_bmalloca bma = {
+ .tp = tp,
+ .ip = ip,
+ .total = total,
+ };
struct xfs_mount *mp = ip->i_mount;
struct xfs_ifork *ifp;
- struct xfs_bmalloca bma = { NULL }; /* args for xfs_bmap_alloc */
xfs_fileoff_t end; /* end of mapped file region */
bool eof = false; /* after the end of extents */
int error; /* error return */
eof = true;
if (!xfs_iext_peek_prev_extent(ifp, &bma.icur, &bma.prev))
bma.prev.br_startoff = NULLFILEOFF;
- bma.tp = tp;
- bma.ip = ip;
- bma.total = total;
- bma.datatype = 0;
bma.minleft = xfs_bmapi_minleft(tp, ip, whichfork);
n = 0;
struct xfs_btree_cur *cur = bs->cur;
struct check_owner *co;
- if ((cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) && bp == NULL)
+ /*
+ * In theory, xfs_btree_get_block should only give us a null buffer
+ * pointer for the root of a root-in-inode btree type, but we need
+ * to check defensively here in case the cursor state is also screwed
+ * up.
+ */
+ if (bp == NULL) {
+ if (!(cur->bc_flags & XFS_BTREE_ROOT_IN_INODE))
+ xchk_btree_set_corrupt(bs->sc, bs->cur, level);
return 0;
+ }
/*
* We want to cross-reference each btree block with the bnobt
/* Drill another level deeper. */
blkno = be32_to_cpu(key->before);
level++;
+ if (level >= XFS_DA_NODE_MAXDEPTH) {
+ /* Too deep! */
+ xchk_da_set_corrupt(&ds, level - 1);
+ break;
+ }
ds.tree_level--;
error = xchk_da_btree_block(&ds, level, blkno);
if (error)
return -EPERM;
if (!blk_queue_discard(q))
return -EOPNOTSUPP;
+
+ /*
+ * We haven't recovered the log, so we cannot use our bnobt-guided
+ * storage zapping commands.
+ */
+ if (mp->m_flags & XFS_MOUNT_NORECOVERY)
+ return -EROFS;
+
if (copy_from_user(&range, urange, sizeof(range)))
return -EFAULT;
count = iov_iter_count(from);
/*
- * If we are doing unaligned IO, wait for all other IO to drain,
- * otherwise demote the lock if we had to take the exclusive lock
- * for other reasons in xfs_file_aio_write_checks.
+ * If we are doing unaligned IO, we can't allow any other overlapping IO
+ * in-flight at the same time or we risk data corruption. Wait for all
+ * other IO to drain before we submit. If the IO is aligned, demote the
+ * iolock if we had to take the exclusive lock in
+ * xfs_file_aio_write_checks() for other reasons.
*/
if (unaligned_io) {
- /* If we are going to wait for other DIO to finish, bail */
- if (iocb->ki_flags & IOCB_NOWAIT) {
- if (atomic_read(&inode->i_dio_count))
- return -EAGAIN;
- } else {
- inode_dio_wait(inode);
- }
+ /* unaligned dio always waits, bail */
+ if (iocb->ki_flags & IOCB_NOWAIT)
+ return -EAGAIN;
+ inode_dio_wait(inode);
} else if (iolock == XFS_IOLOCK_EXCL) {
xfs_ilock_demote(ip, XFS_IOLOCK_EXCL);
iolock = XFS_IOLOCK_SHARED;
trace_xfs_file_direct_write(ip, count, iocb->ki_pos);
ret = iomap_dio_rw(iocb, from, &xfs_iomap_ops, xfs_dio_write_end_io);
+
+ /*
+ * If unaligned, this is the only IO in-flight. If it has not yet
+ * completed, wait on it before we release the iolock to prevent
+ * subsequent overlapping IO.
+ */
+ if (ret == -EIOCBQUEUED && unaligned_io)
+ inode_dio_wait(inode);
out:
xfs_iunlock(ip, iolock);
/* Defaults for debug_level, debug and normal */
+#ifndef ACPI_DEBUG_DEFAULT
#define ACPI_DEBUG_DEFAULT (ACPI_LV_INIT | ACPI_LV_DEBUG_OBJECT | ACPI_LV_EVALUATION | ACPI_LV_REPAIR)
+#endif
+
#define ACPI_NORMAL_DEFAULT (ACPI_LV_INIT | ACPI_LV_DEBUG_OBJECT | ACPI_LV_REPAIR)
#define ACPI_DEBUG_ALL (ACPI_LV_AML_DISASSEMBLE | ACPI_LV_ALL_EXCEPTIONS | ACPI_LV_ALL)
#define ACPI_NO_ERROR_MESSAGES
#undef ACPI_DEBUG_OUTPUT
+/* Use a specific bugging default separate from ACPICA */
+
+#undef ACPI_DEBUG_DEFAULT
+#define ACPI_DEBUG_DEFAULT (ACPI_LV_INFO | ACPI_LV_REPAIR)
+
/* External interface for __KERNEL__, stub is needed */
#define ACPI_EXTERNAL_RETURN_STATUS(prototype) \
* syscall_get_arguments - extract system call parameter values
* @task: task of interest, must be blocked
* @regs: task_pt_regs() of @task
- * @i: argument index [0,5]
- * @n: number of arguments; n+i must be [1,6].
* @args: array filled with argument values
*
- * Fetches @n arguments to the system call starting with the @i'th argument
- * (from 0 through 5). Argument @i is stored in @args[0], and so on.
- * An arch inline version is probably optimal when @i and @n are constants.
+ * Fetches 6 arguments to the system call. First argument is stored in
+* @args[0], and so on.
*
* It's only valid to call this when @task is stopped for tracing on
* entry to a system call, due to %TIF_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
- * It's invalid to call this with @i + @n > 6; we only support system calls
- * taking up to 6 arguments.
*/
void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
- unsigned int i, unsigned int n, unsigned long *args);
+ unsigned long *args);
/**
* syscall_set_arguments - change system call parameter value
* @task: task of interest, must be in system call entry tracing
* @regs: task_pt_regs() of @task
- * @i: argument index [0,5]
- * @n: number of arguments; n+i must be [1,6].
* @args: array of argument values to store
*
- * Changes @n arguments to the system call starting with the @i'th argument.
- * Argument @i gets value @args[0], and so on.
- * An arch inline version is probably optimal when @i and @n are constants.
+ * Changes 6 arguments to the system call.
+ * The first argument gets value @args[0], and so on.
*
* It's only valid to call this when @task is stopped for tracing on
* entry to a system call, due to %TIF_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
- * It's invalid to call this with @i + @n > 6; we only support system calls
- * taking up to 6 arguments.
*/
void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args);
/**
* Drivers can use the @old_crtc_state input parameter if the operations
* needed to enable the CRTC don't depend solely on the new state but
* also on the transition between the old state and the new state.
+ *
+ * This function is optional.
*/
void (*atomic_enable)(struct drm_crtc *crtc,
struct drm_crtc_state *old_crtc_state);
* parameter @old_crtc_state which could be used to access the old
* state. Atomic drivers should consider to use this one instead
* of @disable.
+ *
+ * This function is optional.
*/
void (*atomic_disable)(struct drm_crtc *crtc,
struct drm_crtc_state *old_crtc_state);
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2018-2019 SiFive, Inc.
+ * Wesley Terpstra
+ * Paul Walmsley
+ */
+
+#ifndef __DT_BINDINGS_CLOCK_SIFIVE_FU540_PRCI_H
+#define __DT_BINDINGS_CLOCK_SIFIVE_FU540_PRCI_H
+
+/* Clock indexes for use by Device Tree data and the PRCI driver */
+
+#define PRCI_CLK_COREPLL 0
+#define PRCI_CLK_DDRPLL 1
+#define PRCI_CLK_GEMGXLPLL 2
+#define PRCI_CLK_TLCLK 3
+
+#endif
#define RESET_SD_EMMC_A 44
#define RESET_SD_EMMC_B 45
#define RESET_SD_EMMC_C 46
-/* 47-60 */
+/* 47 */
+#define RESET_USB_PHY20 48
+#define RESET_USB_PHY21 49
+/* 50-60 */
#define RESET_AUDIO_CODEC 61
/* 62-63 */
/* RESET2 */
int TSS_authhmac(unsigned char *digest, const unsigned char *key,
unsigned int keylen, unsigned char *h1,
- unsigned char *h2, unsigned char h3, ...);
+ unsigned char *h2, unsigned int h3, ...);
int TSS_checkhmac1(unsigned char *buffer,
const uint32_t command,
const unsigned char *ononce,
return bio->bi_vcnt >= bio->bi_max_vecs;
}
-#define mp_bvec_for_each_segment(bv, bvl, i, iter_all) \
- for (bv = bvec_init_iter_all(&iter_all); \
- (iter_all.done < (bvl)->bv_len) && \
- (mp_bvec_next_segment((bvl), &iter_all), 1); \
- iter_all.done += bv->bv_len, i += 1)
+static inline bool bio_next_segment(const struct bio *bio,
+ struct bvec_iter_all *iter)
+{
+ if (iter->idx >= bio->bi_vcnt)
+ return false;
+
+ bvec_advance(&bio->bi_io_vec[iter->idx], iter);
+ return true;
+}
/*
* drivers should _never_ use the all version - the bio may have been split
* before it got to the driver and the driver won't own all of it
*/
-#define bio_for_each_segment_all(bvl, bio, i, iter_all) \
- for (i = 0, iter_all.idx = 0; iter_all.idx < (bio)->bi_vcnt; iter_all.idx++) \
- mp_bvec_for_each_segment(bvl, &((bio)->bi_io_vec[iter_all.idx]), i, iter_all)
+#define bio_for_each_segment_all(bvl, bio, i, iter) \
+ for (i = 0, bvl = bvec_init_iter_all(&iter); \
+ bio_next_segment((bio), &iter); i++)
static inline void bio_advance_iter(struct bio *bio, struct bvec_iter *iter,
unsigned bytes)
#define __constant_bitrev32(x) \
({ \
- u32 __x = x; \
- __x = (__x >> 16) | (__x << 16); \
- __x = ((__x & (u32)0xFF00FF00UL) >> 8) | ((__x & (u32)0x00FF00FFUL) << 8); \
- __x = ((__x & (u32)0xF0F0F0F0UL) >> 4) | ((__x & (u32)0x0F0F0F0FUL) << 4); \
- __x = ((__x & (u32)0xCCCCCCCCUL) >> 2) | ((__x & (u32)0x33333333UL) << 2); \
- __x = ((__x & (u32)0xAAAAAAAAUL) >> 1) | ((__x & (u32)0x55555555UL) << 1); \
- __x; \
+ u32 ___x = x; \
+ ___x = (___x >> 16) | (___x << 16); \
+ ___x = ((___x & (u32)0xFF00FF00UL) >> 8) | ((___x & (u32)0x00FF00FFUL) << 8); \
+ ___x = ((___x & (u32)0xF0F0F0F0UL) >> 4) | ((___x & (u32)0x0F0F0F0FUL) << 4); \
+ ___x = ((___x & (u32)0xCCCCCCCCUL) >> 2) | ((___x & (u32)0x33333333UL) << 2); \
+ ___x = ((___x & (u32)0xAAAAAAAAUL) >> 1) | ((___x & (u32)0x55555555UL) << 1); \
+ ___x; \
})
#define __constant_bitrev16(x) \
({ \
- u16 __x = x; \
- __x = (__x >> 8) | (__x << 8); \
- __x = ((__x & (u16)0xF0F0U) >> 4) | ((__x & (u16)0x0F0FU) << 4); \
- __x = ((__x & (u16)0xCCCCU) >> 2) | ((__x & (u16)0x3333U) << 2); \
- __x = ((__x & (u16)0xAAAAU) >> 1) | ((__x & (u16)0x5555U) << 1); \
- __x; \
+ u16 ___x = x; \
+ ___x = (___x >> 8) | (___x << 8); \
+ ___x = ((___x & (u16)0xF0F0U) >> 4) | ((___x & (u16)0x0F0FU) << 4); \
+ ___x = ((___x & (u16)0xCCCCU) >> 2) | ((___x & (u16)0x3333U) << 2); \
+ ___x = ((___x & (u16)0xAAAAU) >> 1) | ((___x & (u16)0x5555U) << 1); \
+ ___x; \
})
#define __constant_bitrev8x4(x) \
({ \
- u32 __x = x; \
- __x = ((__x & (u32)0xF0F0F0F0UL) >> 4) | ((__x & (u32)0x0F0F0F0FUL) << 4); \
- __x = ((__x & (u32)0xCCCCCCCCUL) >> 2) | ((__x & (u32)0x33333333UL) << 2); \
- __x = ((__x & (u32)0xAAAAAAAAUL) >> 1) | ((__x & (u32)0x55555555UL) << 1); \
- __x; \
+ u32 ___x = x; \
+ ___x = ((___x & (u32)0xF0F0F0F0UL) >> 4) | ((___x & (u32)0x0F0F0F0FUL) << 4); \
+ ___x = ((___x & (u32)0xCCCCCCCCUL) >> 2) | ((___x & (u32)0x33333333UL) << 2); \
+ ___x = ((___x & (u32)0xAAAAAAAAUL) >> 1) | ((___x & (u32)0x55555555UL) << 1); \
+ ___x; \
})
#define __constant_bitrev8(x) \
({ \
- u8 __x = x; \
- __x = (__x >> 4) | (__x << 4); \
- __x = ((__x & (u8)0xCCU) >> 2) | ((__x & (u8)0x33U) << 2); \
- __x = ((__x & (u8)0xAAU) >> 1) | ((__x & (u8)0x55U) << 1); \
- __x; \
+ u8 ___x = x; \
+ ___x = (___x >> 4) | (___x << 4); \
+ ___x = ((___x & (u8)0xCCU) >> 2) | ((___x & (u8)0x33U) << 2); \
+ ___x = ((___x & (u8)0xAAU) >> 1) | ((___x & (u8)0x55U) << 1); \
+ ___x; \
})
#define bitrev32(x) \
void blk_mq_kick_requeue_list(struct request_queue *q);
void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs);
bool blk_mq_complete_request(struct request *rq);
+void blk_mq_complete_request_sync(struct request *rq);
bool blk_mq_bio_list_merge(struct request_queue *q, struct list_head *list,
struct bio *bio);
bool blk_mq_queue_stopped(struct request_queue *q);
const struct btf *btf,
const struct btf_type *key_type,
const struct btf_type *value_type);
+
+ /* Direct value access helpers. */
+ int (*map_direct_value_addr)(const struct bpf_map *map,
+ u64 *imm, u32 off);
+ int (*map_direct_value_meta)(const struct bpf_map *map,
+ u64 imm, u32 *off);
};
struct bpf_map {
struct btf *btf;
u32 pages;
bool unpriv_array;
- /* 51 bytes hole */
+ bool frozen; /* write-once */
+ /* 48 bytes hole */
/* The 3rd and 4th cacheline with misc members to avoid false sharing
* particularly with refcounting.
};
};
+#define BPF_COMPLEXITY_LIMIT_INSNS 1000000 /* yes. 1M insns */
#define MAX_TAIL_CALL_CNT 32
+#define BPF_F_ACCESS_MASK (BPF_F_RDONLY | \
+ BPF_F_RDONLY_PROG | \
+ BPF_F_WRONLY | \
+ BPF_F_WRONLY_PROG)
+
+#define BPF_MAP_CAN_READ BIT(0)
+#define BPF_MAP_CAN_WRITE BIT(1)
+
+static inline u32 bpf_map_flags_to_cap(struct bpf_map *map)
+{
+ u32 access_flags = map->map_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG);
+
+ /* Combination of BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG is
+ * not possible.
+ */
+ if (access_flags & BPF_F_RDONLY_PROG)
+ return BPF_MAP_CAN_READ;
+ else if (access_flags & BPF_F_WRONLY_PROG)
+ return BPF_MAP_CAN_WRITE;
+ else
+ return BPF_MAP_CAN_READ | BPF_MAP_CAN_WRITE;
+}
+
+static inline bool bpf_map_flags_access_ok(u32 access_flags)
+{
+ return (access_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG)) !=
+ (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG);
+}
+
struct bpf_event_entry {
struct perf_event *event;
struct file *perf_file;
u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy);
-int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
- union bpf_attr __user *uattr);
-int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
- union bpf_attr __user *uattr);
-int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
- const union bpf_attr *kattr,
- union bpf_attr __user *uattr);
-
/* an array of programs to be executed under rcu_lock.
*
* Typical usage:
struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type);
int array_map_alloc_check(union bpf_attr *attr);
+int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
+ union bpf_attr __user *uattr);
+int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
+ union bpf_attr __user *uattr);
+int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
+ const union bpf_attr *kattr,
+ union bpf_attr __user *uattr);
#else /* !CONFIG_BPF_SYSCALL */
static inline struct bpf_prog *bpf_prog_get(u32 ufd)
{
{
return ERR_PTR(-EOPNOTSUPP);
}
+
+static inline int bpf_prog_test_run_xdp(struct bpf_prog *prog,
+ const union bpf_attr *kattr,
+ union bpf_attr __user *uattr)
+{
+ return -ENOTSUPP;
+}
+
+static inline int bpf_prog_test_run_skb(struct bpf_prog *prog,
+ const union bpf_attr *kattr,
+ union bpf_attr __user *uattr)
+{
+ return -ENOTSUPP;
+}
+
+static inline int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
+ const union bpf_attr *kattr,
+ union bpf_attr __user *uattr)
+{
+ return -ENOTSUPP;
+}
#endif /* CONFIG_BPF_SYSCALL */
static inline struct bpf_prog *bpf_prog_get_type(u32 ufd,
struct bpf_verifier_state_list {
struct bpf_verifier_state state;
struct bpf_verifier_state_list *next;
+ int miss_cnt, hit_cnt;
};
/* Possible states for alu_state member. */
unsigned long map_state; /* pointer/poison value for maps */
s32 call_imm; /* saved imm field of call insn */
u32 alu_limit; /* limit for add/sub register with pointer */
+ struct {
+ u32 map_index; /* index into used_maps[] */
+ u32 map_off; /* offset from value base address */
+ };
};
int ctx_field_size; /* the ctx field size for load insn, maybe 0 */
int sanitize_stack_off; /* stack slot to be cleared */
return log->len_used >= log->len_total - 1;
}
+#define BPF_LOG_LEVEL1 1
+#define BPF_LOG_LEVEL2 2
+#define BPF_LOG_STATS 4
+#define BPF_LOG_LEVEL (BPF_LOG_LEVEL1 | BPF_LOG_LEVEL2)
+#define BPF_LOG_MASK (BPF_LOG_LEVEL | BPF_LOG_STATS)
+
static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log)
{
return log->level && log->ubuf && !bpf_verifier_log_full(log);
bool strict_alignment; /* perform strict pointer alignment checks */
struct bpf_verifier_state *cur_state; /* current verifier state */
struct bpf_verifier_state_list **explored_states; /* search pruning optimization */
+ struct bpf_verifier_state_list *free_list;
struct bpf_map *used_maps[MAX_USED_MAPS]; /* array of map's used by eBPF program */
u32 used_map_cnt; /* number of used maps */
u32 id_gen; /* used to generate unique reg IDs */
struct bpf_verifier_log log;
struct bpf_subprog_info subprog_info[BPF_MAX_SUBPROGS + 1];
u32 subprog_cnt;
+ /* number of instructions analyzed by the verifier */
+ u32 insn_processed;
+ /* total verification time */
+ u64 verification_time;
+ /* maximum number of verifier states kept in 'branching' instructions */
+ u32 max_states_per_insn;
+ /* total number of allocated verifier states */
+ u32 total_states;
+ /* some states are freed during program analysis.
+ * this is peak number of states. this number dominates kernel
+ * memory consumption during verification
+ */
+ u32 peak_states;
+ /* longest register parentage chain walked for liveness marking */
+ u32 longest_mark_read_walk;
};
__printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log,
const struct btf_member *m,
u32 expected_offset, u32 expected_size);
int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t);
+bool btf_type_is_void(const struct btf_type *t);
#ifdef CONFIG_BPF_SYSCALL
const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id);
static inline struct bio_vec *bvec_init_iter_all(struct bvec_iter_all *iter_all)
{
- iter_all->bv.bv_page = NULL;
iter_all->done = 0;
+ iter_all->idx = 0;
return &iter_all->bv;
}
-static inline void mp_bvec_next_segment(const struct bio_vec *bvec,
- struct bvec_iter_all *iter_all)
+static inline void bvec_advance(const struct bio_vec *bvec,
+ struct bvec_iter_all *iter_all)
{
struct bio_vec *bv = &iter_all->bv;
- if (bv->bv_page) {
+ if (iter_all->done) {
bv->bv_page = nth_page(bv->bv_page, 1);
bv->bv_offset = 0;
} else {
}
bv->bv_len = min_t(unsigned int, PAGE_SIZE - bv->bv_offset,
bvec->bv_len - iter_all->done);
+ iter_all->done += bv->bv_len;
+
+ if (iter_all->done == bvec->bv_len) {
+ iter_all->idx++;
+ iter_all->done = 0;
+ }
}
/*
ssize_t (*store)(struct bus_type *bus, const char *buf, size_t count);
};
-#define BUS_ATTR(_name, _mode, _show, _store) \
- struct bus_attribute bus_attr_##_name = __ATTR(_name, _mode, _show, _store)
#define BUS_ATTR_RW(_name) \
struct bus_attribute bus_attr_##_name = __ATTR_RW(_name)
#define BUS_ATTR_RO(_name) \
#define FMODE_OPENED ((__force fmode_t)0x80000)
#define FMODE_CREATED ((__force fmode_t)0x100000)
+/* File is stream-like */
+#define FMODE_STREAM ((__force fmode_t)0x200000)
+
/* File was opened by fanotify and shouldn't generate fanotify events */
#define FMODE_NONOTIFY ((__force fmode_t)0x4000000)
extern loff_t no_seek_end_llseek(struct file *, loff_t, int);
extern int generic_file_open(struct inode * inode, struct file * filp);
extern int nonseekable_open(struct inode * inode, struct file * filp);
+extern int stream_open(struct inode * inode, struct file * filp);
#ifdef CONFIG_BLOCK
typedef void (dio_submit_t)(struct bio *bio, struct inode *inode,
#define pud_huge(x) 0
#define is_hugepage_only_range(mm, addr, len) 0
#define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) ({BUG(); 0; })
-#define hugetlb_fault(mm, vma, addr, flags) ({ BUG(); 0; })
#define hugetlb_mcopy_atomic_pte(dst_mm, dst_pte, dst_vma, dst_addr, \
src_addr, pagep) ({ BUG(); 0; })
#define huge_pte_offset(mm, address, sz) 0
{
BUG();
}
+static inline vm_fault_t hugetlb_fault(struct mm_struct *mm,
+ struct vm_area_struct *vma, unsigned long address,
+ unsigned int flags)
+{
+ BUG();
+ return 0;
+}
#endif /* !CONFIG_HUGETLB_PAGE */
/*
extern void brioctl_set(int (*ioctl_hook)(struct net *, unsigned int, void __user *));
-typedef int br_should_route_hook_t(struct sk_buff *skb);
-extern br_should_route_hook_t __rcu *br_should_route_hook;
-
#if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_BRIDGE_IGMP_SNOOPING)
int br_multicast_list_adjacent(struct net_device *dev,
struct list_head *br_ip_list);
}
extern u64 jiffies64_to_nsecs(u64 j);
+extern u64 jiffies64_to_msecs(u64 j);
extern unsigned long __msecs_to_jiffies(const unsigned int m);
#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ)
#ifdef CONFIG_PROC_KCORE
void __init kclist_add(struct kcore_list *, void *, size_t, int type);
-static inline
-void kclist_add_remap(struct kcore_list *m, void *addr, void *vaddr, size_t sz)
-{
- m->vaddr = (unsigned long)vaddr;
- kclist_add(m, addr, sz, KCORE_REMAP);
-}
extern int __init register_mem_pfn_is_ram(int (*fn)(unsigned long pfn));
#else
void kclist_add(struct kcore_list *new, void *addr, size_t size, int type)
{
}
-
-static inline
-void kclist_add_remap(struct kcore_list *m, void *addr, void *vaddr, size_t sz)
-{
-}
#endif
#endif /* _LINUX_KCORE_H */
#define u64_to_user_ptr(x) ( \
{ \
- typecheck(u64, x); \
- (void __user *)(uintptr_t)x; \
+ typecheck(u64, (x)); \
+ (void __user *)(uintptr_t)(x); \
} \
)
#include <linux/irqbypass.h>
#include <linux/swait.h>
#include <linux/refcount.h>
+#include <linux/nospec.h>
#include <asm/signal.h>
#include <linux/kvm.h>
static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i)
{
- /* Pairs with smp_wmb() in kvm_vm_ioctl_create_vcpu, in case
- * the caller has read kvm->online_vcpus before (as is the case
- * for kvm_for_each_vcpu, for example).
- */
+ int num_vcpus = atomic_read(&kvm->online_vcpus);
+ i = array_index_nospec(i, num_vcpus);
+
+ /* Pairs with smp_wmb() in kvm_vm_ioctl_create_vcpu. */
smp_rmb();
return kvm->vcpus[i];
}
static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id)
{
+ as_id = array_index_nospec(as_id, KVM_ADDRESS_SPACE_NUM);
return srcu_dereference_check(kvm->memslots[as_id], &kvm->srcu,
lockdep_is_held(&kvm->slots_lock) ||
!refcount_read(&kvm->users_count));
}
/**
- * list_is_first -- tests whether @ list is the first entry in list @head
+ * list_is_first -- tests whether @list is the first entry in list @head
* @list: the entry to test
* @head: the head of the list
*/
void __unlock_page_memcg(struct mem_cgroup *memcg);
void unlock_page_memcg(struct page *page);
-/* idx can be of type enum memcg_stat_item or node_stat_item */
+/*
+ * idx can be of type enum memcg_stat_item or node_stat_item.
+ * Keep in sync with memcg_exact_page_state().
+ */
static inline unsigned long memcg_page_state(struct mem_cgroup *memcg,
int idx)
{
if (linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT,
advertising))
lcl_adv |= ADVERTISE_PAUSE_CAP;
- if (linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT,
+ if (linkmode_test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT,
advertising))
lcl_adv |= ADVERTISE_PAUSE_ASYM;
doorbell[0] = cpu_to_be32(sn << 28 | cmd | ci);
doorbell[1] = cpu_to_be32(cq->cqn);
- mlx5_write64(doorbell, uar_page + MLX5_CQ_DOORBELL, NULL);
+ mlx5_write64(doorbell, uar_page + MLX5_CQ_DOORBELL);
}
static inline void mlx5_cq_hold(struct mlx5_core_cq *cq)
enum {
MLX5_GENERAL_SUBTYPE_DELAY_DROP_TIMEOUT = 0x1,
+ MLX5_GENERAL_SUBTYPE_PCI_POWER_CHANGE_EVENT = 0x5,
};
enum {
#define MLX5_BF_OFFSET 0x800
#define MLX5_CQ_DOORBELL 0x20
-#if BITS_PER_LONG == 64
/* Assume that we can just write a 64-bit doorbell atomically. s390
* actually doesn't have writeq() but S/390 systems don't even have
* PCI so we won't worry about it.
+ *
+ * Note that the write is not atomic on 32-bit systems! In contrast to 64-bit
+ * ones, it requires proper locking. mlx5_write64 doesn't do any locking, so use
+ * it at your own discretion, protected by some kind of lock on 32 bits.
+ *
+ * TODO: use write{q,l}_relaxed()
*/
-#define MLX5_DECLARE_DOORBELL_LOCK(name)
-#define MLX5_INIT_DOORBELL_LOCK(ptr) do { } while (0)
-#define MLX5_GET_DOORBELL_LOCK(ptr) (NULL)
-
-static inline void mlx5_write64(__be32 val[2], void __iomem *dest,
- spinlock_t *doorbell_lock)
+static inline void mlx5_write64(__be32 val[2], void __iomem *dest)
{
+#if BITS_PER_LONG == 64
__raw_writeq(*(u64 *)val, dest);
-}
-
#else
-
-/* Just fall back to a spinlock to protect the doorbell if
- * BITS_PER_LONG is 32 -- there's no portable way to do atomic 64-bit
- * MMIO writes.
- */
-
-#define MLX5_DECLARE_DOORBELL_LOCK(name) spinlock_t name;
-#define MLX5_INIT_DOORBELL_LOCK(ptr) spin_lock_init(ptr)
-#define MLX5_GET_DOORBELL_LOCK(ptr) (ptr)
-
-static inline void mlx5_write64(__be32 val[2], void __iomem *dest,
- spinlock_t *doorbell_lock)
-{
- unsigned long flags;
-
- if (doorbell_lock)
- spin_lock_irqsave(doorbell_lock, flags);
__raw_writel((__force u32) val[0], dest);
__raw_writel((__force u32) val[1], dest + 4);
- if (doorbell_lock)
- spin_unlock_irqrestore(doorbell_lock, flags);
-}
-
#endif
+}
#endif /* MLX5_DOORBELL_H */
MLX5_REG_MTRC_CONF = 0x9041,
MLX5_REG_MTRC_STDB = 0x9042,
MLX5_REG_MTRC_CTRL = 0x9043,
+ MLX5_REG_MPEIN = 0x9050,
MLX5_REG_MPCNT = 0x9051,
MLX5_REG_MTPPS = 0x9053,
MLX5_REG_MTPPSE = 0x9054,
};
struct mlx5_td {
+ /* protects tirs list changes while tirs refresh */
+ struct mutex list_lock;
struct list_head tirs_list;
u32 tdn;
};
u64 sys_image_guid;
phys_addr_t iseg_base;
struct mlx5_init_seg __iomem *iseg;
+ phys_addr_t bar_addr;
enum mlx5_device_state state;
/* sync interface state */
struct mutex intf_state_mutex;
int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type);
int mlx5_cmd_alloc_uar(struct mlx5_core_dev *dev, u32 *uarn);
int mlx5_cmd_free_uar(struct mlx5_core_dev *dev, u32 uarn);
+void mlx5_health_flush(struct mlx5_core_dev *dev);
void mlx5_health_cleanup(struct mlx5_core_dev *dev);
int mlx5_health_init(struct mlx5_core_dev *dev);
void mlx5_start_health_poll(struct mlx5_core_dev *dev);
union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits counter_set;
};
+struct mlx5_ifc_mpein_reg_bits {
+ u8 reserved_at_0[0x2];
+ u8 depth[0x6];
+ u8 pcie_index[0x8];
+ u8 node[0x8];
+ u8 reserved_at_18[0x8];
+
+ u8 capability_mask[0x20];
+
+ u8 reserved_at_40[0x8];
+ u8 link_width_enabled[0x8];
+ u8 link_speed_enabled[0x10];
+
+ u8 lane0_physical_position[0x8];
+ u8 link_width_active[0x8];
+ u8 link_speed_active[0x10];
+
+ u8 num_of_pfs[0x10];
+ u8 num_of_vfs[0x10];
+
+ u8 bdf0[0x10];
+ u8 reserved_at_b0[0x10];
+
+ u8 max_read_request_size[0x4];
+ u8 max_payload_size[0x4];
+ u8 reserved_at_c8[0x5];
+ u8 pwr_status[0x3];
+ u8 port_type[0x4];
+ u8 reserved_at_d4[0xb];
+ u8 lane_reversal[0x1];
+
+ u8 reserved_at_e0[0x14];
+ u8 pci_power[0xc];
+
+ u8 reserved_at_100[0x20];
+
+ u8 device_status[0x10];
+ u8 port_state[0x8];
+ u8 reserved_at_138[0x8];
+
+ u8 reserved_at_140[0x10];
+ u8 receiver_detect_result[0x10];
+
+ u8 reserved_at_160[0x20];
+};
+
struct mlx5_ifc_mpcnt_reg_bits {
u8 reserved_at_0[0x8];
u8 pcie_index[0x8];
};
struct mlx5_ifc_mcam_enhanced_features_bits {
- u8 reserved_at_0[0x74];
+ u8 reserved_at_0[0x6e];
+ u8 pci_status_and_power[0x1];
+ u8 reserved_at_6f[0x5];
u8 mark_tx_action_cnp[0x1];
u8 mark_tx_action_cqe[0x1];
u8 dynamic_tx_overflow[0x1];
struct mlx5_ifc_pmtu_reg_bits pmtu_reg;
struct mlx5_ifc_ppad_reg_bits ppad_reg;
struct mlx5_ifc_ppcnt_reg_bits ppcnt_reg;
+ struct mlx5_ifc_mpein_reg_bits mpein_reg;
struct mlx5_ifc_mpcnt_reg_bits mpcnt_reg;
struct mlx5_ifc_pplm_reg_bits pplm_reg;
struct mlx5_ifc_pplr_reg_bits pplr_reg;
}
#endif /* CONFIG_DEV_PAGEMAP_OPS */
+/* 127: arbitrary random number, small enough to assemble well */
+#define page_ref_zero_or_close_to_overflow(page) \
+ ((unsigned int) page_ref_count(page) + 127u <= 127u)
+
static inline void get_page(struct page *page)
{
page = compound_head(page);
* Getting a normal page or the head of a compound page
* requires to already have an elevated page->_refcount.
*/
- VM_BUG_ON_PAGE(page_ref_count(page) <= 0, page);
+ VM_BUG_ON_PAGE(page_ref_zero_or_close_to_overflow(page), page);
+ page_ref_inc(page);
+}
+
+static inline __must_check bool try_get_page(struct page *page)
+{
+ page = compound_head(page);
+ if (WARN_ON_ONCE(page_ref_count(page) <= 0))
+ return false;
page_ref_inc(page);
+ return true;
}
static inline void put_page(struct page *page)
/* Encode hstate index for a hwpoisoned large page */
#define VM_FAULT_SET_HINDEX(x) ((__force vm_fault_t)((x) << 16))
-#define VM_FAULT_GET_HINDEX(x) (((x) >> 16) & 0xf)
+#define VM_FAULT_GET_HINDEX(x) (((__force unsigned int)(x) >> 16) & 0xf)
#define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS | \
VM_FAULT_SIGSEGV | VM_FAULT_HWPOISON | \
* @IFF_FAILOVER: device is a failover master device
* @IFF_FAILOVER_SLAVE: device is lower dev of a failover master device
* @IFF_L3MDEV_RX_HANDLER: only invoke the rx handler of L3 master device
+ * @IFF_LIVE_RENAME_OK: rename is allowed while device is up and running
*/
enum netdev_priv_flags {
IFF_802_1Q_VLAN = 1<<0,
IFF_FAILOVER = 1<<27,
IFF_FAILOVER_SLAVE = 1<<28,
IFF_L3MDEV_RX_HANDLER = 1<<29,
+ IFF_LIVE_RENAME_OK = 1<<30,
};
#define IFF_802_1Q_VLAN IFF_802_1Q_VLAN
#define IFF_FAILOVER IFF_FAILOVER
#define IFF_FAILOVER_SLAVE IFF_FAILOVER_SLAVE
#define IFF_L3MDEV_RX_HANDLER IFF_L3MDEV_RX_HANDLER
+#define IFF_LIVE_RENAME_OK IFF_LIVE_RENAME_OK
/**
* struct net_device - The DEVICE structure.
void synchronize_net(void);
int init_dummy_netdev(struct net_device *dev);
-DECLARE_PER_CPU(int, xmit_recursion);
-#define XMIT_RECURSION_LIMIT 10
-
-static inline int dev_recursion_level(void)
-{
- return this_cpu_read(xmit_recursion);
-}
-
struct net_device *dev_get_by_index(struct net *net, int ifindex);
struct net_device *__dev_get_by_index(struct net *net, int ifindex);
struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex);
#ifdef CONFIG_XFRM_OFFLOAD
struct sk_buff_head xfrm_backlog;
#endif
+ /* written and read only by owning cpu: */
+ struct {
+ u16 recursion;
+ u8 more;
+ } xmit;
#ifdef CONFIG_RPS
/* input_queue_head should be written by cpu owning this struct,
* and only read by other cpus. Worth using a cache line.
DECLARE_PER_CPU_ALIGNED(struct softnet_data, softnet_data);
+static inline int dev_recursion_level(void)
+{
+ return this_cpu_read(softnet_data.xmit.recursion);
+}
+
+#define XMIT_RECURSION_LIMIT 10
+static inline bool dev_xmit_recursion(void)
+{
+ return unlikely(__this_cpu_read(softnet_data.xmit.recursion) >
+ XMIT_RECURSION_LIMIT);
+}
+
+static inline void dev_xmit_recursion_inc(void)
+{
+ __this_cpu_inc(softnet_data.xmit.recursion);
+}
+
+static inline void dev_xmit_recursion_dec(void)
+{
+ __this_cpu_dec(softnet_data.xmit.recursion);
+}
+
void __netif_schedule(struct Qdisc *q);
void netif_schedule_queue(struct netdev_queue *txq);
struct sk_buff *skb, struct net_device *dev,
bool more)
{
- skb->xmit_more = more ? 1 : 0;
+ __this_cpu_write(softnet_data.xmit.more, more);
return ops->ndo_start_xmit(skb, dev);
}
+static inline bool netdev_xmit_more(void)
+{
+ return __this_cpu_read(softnet_data.xmit.more);
+}
+
static inline netdev_tx_t netdev_start_xmit(struct sk_buff *skb, struct net_device *dev,
struct netdev_queue *txq, bool more)
{
static inline int nf_inet_addr_cmp(const union nf_inet_addr *a1,
const union nf_inet_addr *a2)
{
+#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
+ const unsigned long *ul1 = (const unsigned long *)a1;
+ const unsigned long *ul2 = (const unsigned long *)a2;
+
+ return ((ul1[0] ^ ul2[0]) | (ul1[1] ^ ul2[1])) == 0UL;
+#else
return a1->all[0] == a2->all[0] &&
a1->all[1] == a2->all[1] &&
a1->all[2] == a2->all[2] &&
a1->all[3] == a2->all[3];
+#endif
}
static inline void nf_inet_addr_mask(const union nf_inet_addr *a1,
static inline void
nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family)
{
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
struct nf_nat_hook *nat_hook;
rcu_read_lock();
struct nf_osf_user_finger finger;
};
+struct nf_osf_data {
+ const char *genre;
+ const char *version;
+};
+
bool nf_osf_match(const struct sk_buff *skb, u_int8_t family,
int hooknum, struct net_device *in, struct net_device *out,
const struct nf_osf_info *info, struct net *net,
const struct list_head *nf_osf_fingers);
-const char *nf_osf_find(const struct sk_buff *skb,
- const struct list_head *nf_osf_fingers,
- const int ttl_check);
+bool nf_osf_find(const struct sk_buff *skb,
+ const struct list_head *nf_osf_fingers,
+ const int ttl_check, struct nf_osf_data *data);
#endif /* _NFOSF_H */
int *error);
struct xt_match *xt_find_match(u8 af, const char *name, u8 revision);
-struct xt_target *xt_find_target(u8 af, const char *name, u8 revision);
struct xt_match *xt_request_find_match(u8 af, const char *name, u8 revision);
struct xt_target *xt_request_find_target(u8 af, const char *name, u8 revision);
int xt_find_revision(u8 af, const char *name, u8 revision, int target,
}
int ip6_route_me_harder(struct net *net, struct sk_buff *skb);
+
+static inline int nf_ip6_route_me_harder(struct net *net, struct sk_buff *skb)
+{
+#if IS_MODULE(CONFIG_IPV6)
+ const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops();
+
+ if (!v6_ops)
+ return -EHOSTUNREACH;
+
+ return v6_ops->route_me_harder(net, skb);
+#else
+ return ip6_route_me_harder(net, skb);
+#endif
+}
+
__sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook,
unsigned int dataoff, u_int8_t protocol);
__le16 numdl;
__le16 numdu;
__u16 rsvd11;
- __le32 lpol;
- __le32 lpou;
+ union {
+ struct {
+ __le32 lpol;
+ __le32 lpou;
+ };
+ __le64 lpo;
+ };
__u32 rsvd14[2];
};
/*
* Changes migrate type in [start_pfn, end_pfn) to be MIGRATE_ISOLATE.
- * If specified range includes migrate types other than MOVABLE or CMA,
- * this will fail with -EBUSY.
- *
- * For isolating all pages in the range finally, the caller have to
- * free all pages in the range. test_page_isolated() can be used for
- * test it.
- *
- * The following flags are allowed (they can be combined in a bit mask)
- * SKIP_HWPOISON - ignore hwpoison pages
- * REPORT_FAILURE - report details about the failure to isolate the range
*/
int
start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
* is_c45: Set to true if this phy uses clause 45 addressing.
* is_internal: Set to true if this phy is internal to a MAC.
* is_pseudo_fixed_link: Set to true if this phy is an Ethernet switch, etc.
+ * is_gigabit_capable: Set to true if PHY supports 1000Mbps
* has_fixups: Set to true if this phy has fixups/quirks.
* suspended: Set to true if this phy has been suspended successfully.
* sysfs_links: Internal boolean tracking sysfs symbolic links setup/removal.
unsigned is_c45:1;
unsigned is_internal:1;
unsigned is_pseudo_fixed_link:1;
+ unsigned is_gigabit_capable:1;
unsigned has_fixups:1;
unsigned suspended:1;
unsigned sysfs_links:1;
unsigned autoneg:1;
/* The most recently read link state */
unsigned link:1;
+ unsigned autoneg_complete:1;
/* Interrupts are enabled */
unsigned interrupts:1;
/* Clause 22 PHY */
int genphy_config_init(struct phy_device *phydev);
+int genphy_read_abilities(struct phy_device *phydev);
int genphy_setup_forced(struct phy_device *phydev);
int genphy_restart_aneg(struct phy_device *phydev);
int genphy_config_eee_advert(struct phy_device *phydev);
/*
* Get a reference to the pipe buffer.
*/
- void (*get)(struct pipe_inode_info *, struct pipe_buffer *);
+ bool (*get)(struct pipe_inode_info *, struct pipe_buffer *);
};
/**
* pipe_buf_get - get a reference to a pipe_buffer
* @pipe: the pipe that the buffer belongs to
* @buf: the buffer to get a reference to
+ *
+ * Return: %true if the reference was successfully obtained.
*/
-static inline void pipe_buf_get(struct pipe_inode_info *pipe,
+static inline __must_check bool pipe_buf_get(struct pipe_inode_info *pipe,
struct pipe_buffer *buf)
{
- buf->ops->get(pipe, buf);
+ return buf->ops->get(pipe, buf);
}
/**
void free_pipe_info(struct pipe_inode_info *);
/* Generic pipe buffer ops functions */
-void generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *);
+bool generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *);
int generic_pipe_buf_confirm(struct pipe_inode_info *, struct pipe_buffer *);
int generic_pipe_buf_steal(struct pipe_inode_info *, struct pipe_buffer *);
void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *);
-/* SPDX-License-Identifier: GPL+ */
+/* SPDX-License-Identifier: GPL-2.0+ */
/*
* AMD FCH gpio driver platform-data
*
* @base: PMC clock register base offset
* @clks: pointer to set of registered clocks, typically 0..5
+ * @critical: flag to indicate if firmware enabled pmc_plt_clks
+ * should be marked as critial or not
*/
struct pmc_clk_data {
void __iomem *base;
const struct pmc_clk *clks;
+ bool critical;
};
#endif /* __PLATFORM_DATA_X86_CLK_PMC_ATOM_H */
#include <linux/bug.h> /* For BUG_ON. */
#include <linux/pid_namespace.h> /* For task_active_pid_ns. */
#include <uapi/linux/ptrace.h>
+#include <linux/seccomp.h>
+
+/* Add sp to seccomp_data, as seccomp is user API, we don't want to modify it */
+struct syscall_info {
+ __u64 sp;
+ struct seccomp_data data;
+};
extern int ptrace_access_vm(struct task_struct *tsk, unsigned long addr,
void *buf, int len, unsigned int gup_flags);
#define current_user_stack_pointer() user_stack_pointer(current_pt_regs())
#endif
-extern int task_current_syscall(struct task_struct *target, long *callno,
- unsigned long args[6], unsigned int maxargs,
- unsigned long *sp, unsigned long *pc);
+extern int task_current_syscall(struct task_struct *target, struct syscall_info *info);
extern void sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oact);
#endif
* @head_offset: Offset of rhash_head in struct to be hashed
* @max_size: Maximum size while expanding
* @min_size: Minimum size while shrinking
- * @locks_mul: Number of bucket locks to allocate per cpu (default: 32)
* @automatic_shrinking: Enable automatic shrinking of tables
* @hashfn: Hash function (default: jhash2 if !(key_len % 4), or jhash)
* @obj_hashfn: Function to hash object
unsigned int max_size;
u16 min_size;
bool automatic_shrinking;
- u8 locks_mul;
rht_hashfn_t hashfn;
rht_obj_hashfn_t obj_hashfn;
rht_obj_cmpfn_t obj_cmpfn;
#include <linux/list_nulls.h>
#include <linux/workqueue.h>
#include <linux/rculist.h>
+#include <linux/bit_spinlock.h>
#include <linux/rhashtable-types.h>
/*
+ * Objects in an rhashtable have an embedded struct rhash_head
+ * which is linked into as hash chain from the hash table - or one
+ * of two or more hash tables when the rhashtable is being resized.
* The end of the chain is marked with a special nulls marks which has
- * the least significant bit set.
+ * the least significant bit set but otherwise stores the address of
+ * the hash bucket. This allows us to be be sure we've found the end
+ * of the right list.
+ * The value stored in the hash bucket has BIT(0) used as a lock bit.
+ * This bit must be atomically set before any changes are made to
+ * the chain. To avoid dereferencing this pointer without clearing
+ * the bit first, we use an opaque 'struct rhash_lock_head *' for the
+ * pointer stored in the bucket. This struct needs to be defined so
+ * that rcu_dereference() works on it, but it has no content so a
+ * cast is needed for it to be useful. This ensures it isn't
+ * used by mistake with clearing the lock bit first.
*/
+struct rhash_lock_head {};
/* Maximum chain length before rehash
*
* @nest: Number of bits of first-level nested table.
* @rehash: Current bucket being rehashed
* @hash_rnd: Random seed to fold into hash
- * @locks_mask: Mask to apply before accessing locks[]
- * @locks: Array of spinlocks protecting individual buckets
* @walkers: List of active walkers
* @rcu: RCU structure for freeing the table
* @future_tbl: Table under construction during rehashing
unsigned int size;
unsigned int nest;
u32 hash_rnd;
- unsigned int locks_mask;
- spinlock_t *locks;
struct list_head walkers;
struct rcu_head rcu;
struct bucket_table __rcu *future_tbl;
- struct rhash_head __rcu *buckets[] ____cacheline_aligned_in_smp;
+ struct lockdep_map dep_map;
+
+ struct rhash_lock_head __rcu *buckets[] ____cacheline_aligned_in_smp;
};
/*
* NULLS_MARKER() expects a hash value with the low
* bits mostly likely to be significant, and it discards
* the msb.
- * We git it an address, in which the bottom 2 bits are
+ * We give it an address, in which the bottom bit is
* always 0, and the msb might be significant.
* So we shift the address down one bit to align with
* expectations and avoid losing a significant bit.
+ *
+ * We never store the NULLS_MARKER in the hash table
+ * itself as we need the lsb for locking.
+ * Instead we store a NULL
*/
#define RHT_NULLS_MARKER(ptr) \
((void *)NULLS_MARKER(((unsigned long) (ptr)) >> 1))
#define INIT_RHT_NULLS_HEAD(ptr) \
- ((ptr) = RHT_NULLS_MARKER(&(ptr)))
+ ((ptr) = NULL)
static inline bool rht_is_a_nulls(const struct rhash_head *ptr)
{
return atomic_read(&ht->nelems) >= ht->max_elems;
}
-/* The bucket lock is selected based on the hash and protects mutations
- * on a group of hash buckets.
- *
- * A maximum of tbl->size/2 bucket locks is allocated. This ensures that
- * a single lock always covers both buckets which may both contains
- * entries which link to the same bucket of the old table during resizing.
- * This allows to simplify the locking as locking the bucket in both
- * tables during resize always guarantee protection.
- *
- * IMPORTANT: When holding the bucket lock of both the old and new table
- * during expansions and shrinking, the old bucket lock must always be
- * acquired first.
- */
-static inline spinlock_t *rht_bucket_lock(const struct bucket_table *tbl,
- unsigned int hash)
-{
- return &tbl->locks[hash & tbl->locks_mask];
-}
-
#ifdef CONFIG_PROVE_LOCKING
int lockdep_rht_mutex_is_held(struct rhashtable *ht);
int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, u32 hash);
void *arg);
void rhashtable_destroy(struct rhashtable *ht);
-struct rhash_head __rcu **rht_bucket_nested(const struct bucket_table *tbl,
- unsigned int hash);
-struct rhash_head __rcu **rht_bucket_nested_insert(struct rhashtable *ht,
- struct bucket_table *tbl,
+struct rhash_lock_head __rcu **rht_bucket_nested(const struct bucket_table *tbl,
+ unsigned int hash);
+struct rhash_lock_head __rcu **__rht_bucket_nested(const struct bucket_table *tbl,
unsigned int hash);
+struct rhash_lock_head __rcu **rht_bucket_nested_insert(struct rhashtable *ht,
+ struct bucket_table *tbl,
+ unsigned int hash);
#define rht_dereference(p, ht) \
rcu_dereference_protected(p, lockdep_rht_mutex_is_held(ht))
#define rht_entry(tpos, pos, member) \
({ tpos = container_of(pos, typeof(*tpos), member); 1; })
-static inline struct rhash_head __rcu *const *rht_bucket(
+static inline struct rhash_lock_head __rcu *const *rht_bucket(
const struct bucket_table *tbl, unsigned int hash)
{
return unlikely(tbl->nest) ? rht_bucket_nested(tbl, hash) :
&tbl->buckets[hash];
}
-static inline struct rhash_head __rcu **rht_bucket_var(
+static inline struct rhash_lock_head __rcu **rht_bucket_var(
struct bucket_table *tbl, unsigned int hash)
{
- return unlikely(tbl->nest) ? rht_bucket_nested(tbl, hash) :
+ return unlikely(tbl->nest) ? __rht_bucket_nested(tbl, hash) :
&tbl->buckets[hash];
}
-static inline struct rhash_head __rcu **rht_bucket_insert(
+static inline struct rhash_lock_head __rcu **rht_bucket_insert(
struct rhashtable *ht, struct bucket_table *tbl, unsigned int hash)
{
return unlikely(tbl->nest) ? rht_bucket_nested_insert(ht, tbl, hash) :
&tbl->buckets[hash];
}
+/*
+ * We lock a bucket by setting BIT(0) in the pointer - this is always
+ * zero in real pointers. The NULLS mark is never stored in the bucket,
+ * rather we store NULL if the bucket is empty.
+ * bit_spin_locks do not handle contention well, but the whole point
+ * of the hashtable design is to achieve minimum per-bucket contention.
+ * A nested hash table might not have a bucket pointer. In that case
+ * we cannot get a lock. For remove and replace the bucket cannot be
+ * interesting and doesn't need locking.
+ * For insert we allocate the bucket if this is the last bucket_table,
+ * and then take the lock.
+ * Sometimes we unlock a bucket by writing a new pointer there. In that
+ * case we don't need to unlock, but we do need to reset state such as
+ * local_bh. For that we have rht_assign_unlock(). As rcu_assign_pointer()
+ * provides the same release semantics that bit_spin_unlock() provides,
+ * this is safe.
+ * When we write to a bucket without unlocking, we use rht_assign_locked().
+ */
+
+static inline void rht_lock(struct bucket_table *tbl,
+ struct rhash_lock_head **bkt)
+{
+ local_bh_disable();
+ bit_spin_lock(0, (unsigned long *)bkt);
+ lock_map_acquire(&tbl->dep_map);
+}
+
+static inline void rht_lock_nested(struct bucket_table *tbl,
+ struct rhash_lock_head **bucket,
+ unsigned int subclass)
+{
+ local_bh_disable();
+ bit_spin_lock(0, (unsigned long *)bucket);
+ lock_acquire_exclusive(&tbl->dep_map, subclass, 0, NULL, _THIS_IP_);
+}
+
+static inline void rht_unlock(struct bucket_table *tbl,
+ struct rhash_lock_head **bkt)
+{
+ lock_map_release(&tbl->dep_map);
+ bit_spin_unlock(0, (unsigned long *)bkt);
+ local_bh_enable();
+}
+
+/*
+ * Where 'bkt' is a bucket and might be locked:
+ * rht_ptr() dereferences that pointer and clears the lock bit.
+ * rht_ptr_exclusive() dereferences in a context where exclusive
+ * access is guaranteed, such as when destroying the table.
+ */
+static inline struct rhash_head *rht_ptr(
+ struct rhash_lock_head __rcu * const *bkt,
+ struct bucket_table *tbl,
+ unsigned int hash)
+{
+ const struct rhash_lock_head *p =
+ rht_dereference_bucket_rcu(*bkt, tbl, hash);
+
+ if ((((unsigned long)p) & ~BIT(0)) == 0)
+ return RHT_NULLS_MARKER(bkt);
+ return (void *)(((unsigned long)p) & ~BIT(0));
+}
+
+static inline struct rhash_head *rht_ptr_exclusive(
+ struct rhash_lock_head __rcu * const *bkt)
+{
+ const struct rhash_lock_head *p =
+ rcu_dereference_protected(*bkt, 1);
+
+ if (!p)
+ return RHT_NULLS_MARKER(bkt);
+ return (void *)(((unsigned long)p) & ~BIT(0));
+}
+
+static inline void rht_assign_locked(struct rhash_lock_head __rcu **bkt,
+ struct rhash_head *obj)
+{
+ struct rhash_head __rcu **p = (struct rhash_head __rcu **)bkt;
+
+ if (rht_is_a_nulls(obj))
+ obj = NULL;
+ rcu_assign_pointer(*p, (void *)((unsigned long)obj | BIT(0)));
+}
+
+static inline void rht_assign_unlock(struct bucket_table *tbl,
+ struct rhash_lock_head __rcu **bkt,
+ struct rhash_head *obj)
+{
+ struct rhash_head __rcu **p = (struct rhash_head __rcu **)bkt;
+
+ if (rht_is_a_nulls(obj))
+ obj = NULL;
+ lock_map_release(&tbl->dep_map);
+ rcu_assign_pointer(*p, obj);
+ preempt_enable();
+ __release(bitlock);
+ local_bh_enable();
+}
+
/**
* rht_for_each_from - iterate over hash chain from given head
* @pos: the &struct rhash_head to use as a loop cursor.
* @hash: the hash value / bucket index
*/
#define rht_for_each_from(pos, head, tbl, hash) \
- for (pos = rht_dereference_bucket(head, tbl, hash); \
- !rht_is_a_nulls(pos); \
+ for (pos = head; \
+ !rht_is_a_nulls(pos); \
pos = rht_dereference_bucket((pos)->next, tbl, hash))
/**
* @hash: the hash value / bucket index
*/
#define rht_for_each(pos, tbl, hash) \
- rht_for_each_from(pos, *rht_bucket(tbl, hash), tbl, hash)
+ rht_for_each_from(pos, rht_ptr(rht_bucket(tbl, hash), tbl, hash), \
+ tbl, hash)
/**
* rht_for_each_entry_from - iterate over hash chain from given head
* @member: name of the &struct rhash_head within the hashable struct.
*/
#define rht_for_each_entry_from(tpos, pos, head, tbl, hash, member) \
- for (pos = rht_dereference_bucket(head, tbl, hash); \
+ for (pos = head; \
(!rht_is_a_nulls(pos)) && rht_entry(tpos, pos, member); \
pos = rht_dereference_bucket((pos)->next, tbl, hash))
* @member: name of the &struct rhash_head within the hashable struct.
*/
#define rht_for_each_entry(tpos, pos, tbl, hash, member) \
- rht_for_each_entry_from(tpos, pos, *rht_bucket(tbl, hash), \
- tbl, hash, member)
+ rht_for_each_entry_from(tpos, pos, \
+ rht_ptr(rht_bucket(tbl, hash), tbl, hash), \
+ tbl, hash, member)
/**
* rht_for_each_entry_safe - safely iterate over hash chain of given type
* remove the loop cursor from the list.
*/
#define rht_for_each_entry_safe(tpos, pos, next, tbl, hash, member) \
- for (pos = rht_dereference_bucket(*rht_bucket(tbl, hash), tbl, hash), \
+ for (pos = rht_ptr(rht_bucket(tbl, hash), tbl, hash), \
next = !rht_is_a_nulls(pos) ? \
rht_dereference_bucket(pos->next, tbl, hash) : NULL; \
(!rht_is_a_nulls(pos)) && rht_entry(tpos, pos, member); \
*/
#define rht_for_each_rcu_from(pos, head, tbl, hash) \
for (({barrier(); }), \
- pos = rht_dereference_bucket_rcu(head, tbl, hash); \
+ pos = head; \
!rht_is_a_nulls(pos); \
pos = rcu_dereference_raw(pos->next))
* the _rcu mutation primitives such as rhashtable_insert() as long as the
* traversal is guarded by rcu_read_lock().
*/
-#define rht_for_each_rcu(pos, tbl, hash) \
- rht_for_each_rcu_from(pos, *rht_bucket(tbl, hash), tbl, hash)
+#define rht_for_each_rcu(pos, tbl, hash) \
+ for (({barrier(); }), \
+ pos = rht_ptr(rht_bucket(tbl, hash), tbl, hash); \
+ !rht_is_a_nulls(pos); \
+ pos = rcu_dereference_raw(pos->next))
/**
* rht_for_each_entry_rcu_from - iterated over rcu hash chain from given head
*/
#define rht_for_each_entry_rcu_from(tpos, pos, head, tbl, hash, member) \
for (({barrier(); }), \
- pos = rht_dereference_bucket_rcu(head, tbl, hash); \
+ pos = head; \
(!rht_is_a_nulls(pos)) && rht_entry(tpos, pos, member); \
pos = rht_dereference_bucket_rcu(pos->next, tbl, hash))
* traversal is guarded by rcu_read_lock().
*/
#define rht_for_each_entry_rcu(tpos, pos, tbl, hash, member) \
- rht_for_each_entry_rcu_from(tpos, pos, *rht_bucket(tbl, hash), \
- tbl, hash, member)
+ rht_for_each_entry_rcu_from(tpos, pos, \
+ rht_ptr(rht_bucket(tbl, hash), \
+ tbl, hash), \
+ tbl, hash, member)
/**
* rhl_for_each_rcu - iterate over rcu hash table list
.ht = ht,
.key = key,
};
- struct rhash_head __rcu * const *head;
+ struct rhash_lock_head __rcu * const *bkt;
struct bucket_table *tbl;
struct rhash_head *he;
unsigned int hash;
tbl = rht_dereference_rcu(ht->tbl, ht);
restart:
hash = rht_key_hashfn(ht, tbl, key, params);
- head = rht_bucket(tbl, hash);
+ bkt = rht_bucket(tbl, hash);
do {
- rht_for_each_rcu_from(he, *head, tbl, hash) {
+ rht_for_each_rcu_from(he, rht_ptr(bkt, tbl, hash), tbl, hash) {
if (params.obj_cmpfn ?
params.obj_cmpfn(&arg, rht_obj(ht, he)) :
rhashtable_compare(&arg, rht_obj(ht, he)))
/* An object might have been moved to a different hash chain,
* while we walk along it - better check and retry.
*/
- } while (he != RHT_NULLS_MARKER(head));
+ } while (he != RHT_NULLS_MARKER(bkt));
/* Ensure we see any new tables. */
smp_rmb();
.ht = ht,
.key = key,
};
+ struct rhash_lock_head __rcu **bkt;
struct rhash_head __rcu **pprev;
struct bucket_table *tbl;
struct rhash_head *head;
- spinlock_t *lock;
unsigned int hash;
int elasticity;
void *data;
tbl = rht_dereference_rcu(ht->tbl, ht);
hash = rht_head_hashfn(ht, tbl, obj, params);
- lock = rht_bucket_lock(tbl, hash);
- spin_lock_bh(lock);
+ elasticity = RHT_ELASTICITY;
+ bkt = rht_bucket_insert(ht, tbl, hash);
+ data = ERR_PTR(-ENOMEM);
+ if (!bkt)
+ goto out;
+ pprev = NULL;
+ rht_lock(tbl, bkt);
if (unlikely(rcu_access_pointer(tbl->future_tbl))) {
slow_path:
- spin_unlock_bh(lock);
+ rht_unlock(tbl, bkt);
rcu_read_unlock();
return rhashtable_insert_slow(ht, key, obj);
}
- elasticity = RHT_ELASTICITY;
- pprev = rht_bucket_insert(ht, tbl, hash);
- data = ERR_PTR(-ENOMEM);
- if (!pprev)
- goto out;
-
- rht_for_each_from(head, *pprev, tbl, hash) {
+ rht_for_each_from(head, rht_ptr(bkt, tbl, hash), tbl, hash) {
struct rhlist_head *plist;
struct rhlist_head *list;
data = rht_obj(ht, head);
if (!rhlist)
- goto out;
+ goto out_unlock;
list = container_of(obj, struct rhlist_head, rhead);
RCU_INIT_POINTER(list->next, plist);
head = rht_dereference_bucket(head->next, tbl, hash);
RCU_INIT_POINTER(list->rhead.next, head);
- rcu_assign_pointer(*pprev, obj);
-
- goto good;
+ if (pprev) {
+ rcu_assign_pointer(*pprev, obj);
+ rht_unlock(tbl, bkt);
+ } else
+ rht_assign_unlock(tbl, bkt, obj);
+ data = NULL;
+ goto out;
}
if (elasticity <= 0)
data = ERR_PTR(-E2BIG);
if (unlikely(rht_grow_above_max(ht, tbl)))
- goto out;
+ goto out_unlock;
if (unlikely(rht_grow_above_100(ht, tbl)))
goto slow_path;
- head = rht_dereference_bucket(*pprev, tbl, hash);
+ /* Inserting at head of list makes unlocking free. */
+ head = rht_ptr(bkt, tbl, hash);
RCU_INIT_POINTER(obj->next, head);
if (rhlist) {
RCU_INIT_POINTER(list->next, NULL);
}
- rcu_assign_pointer(*pprev, obj);
-
atomic_inc(&ht->nelems);
+ rht_assign_unlock(tbl, bkt, obj);
+
if (rht_grow_above_75(ht, tbl))
schedule_work(&ht->run_work);
-good:
data = NULL;
-
out:
- spin_unlock_bh(lock);
rcu_read_unlock();
return data;
+
+out_unlock:
+ rht_unlock(tbl, bkt);
+ goto out;
}
/**
* @obj: pointer to hash head inside object
* @params: hash table parameters
*
- * Will take a per bucket spinlock to protect against mutual mutations
+ * Will take the per bucket bitlock to protect against mutual mutations
* on the same bucket. Multiple insertions may occur in parallel unless
- * they map to the same bucket lock.
+ * they map to the same bucket.
*
* It is safe to call this function from atomic context.
*
* @list: pointer to hash list head inside object
* @params: hash table parameters
*
- * Will take a per bucket spinlock to protect against mutual mutations
+ * Will take the per bucket bitlock to protect against mutual mutations
* on the same bucket. Multiple insertions may occur in parallel unless
- * they map to the same bucket lock.
+ * they map to the same bucket.
*
* It is safe to call this function from atomic context.
*
* @list: pointer to hash list head inside object
* @params: hash table parameters
*
- * Will take a per bucket spinlock to protect against mutual mutations
+ * Will take the per bucket bitlock to protect against mutual mutations
* on the same bucket. Multiple insertions may occur in parallel unless
- * they map to the same bucket lock.
+ * they map to the same bucket.
*
* It is safe to call this function from atomic context.
*
struct rhash_head *obj, const struct rhashtable_params params,
bool rhlist)
{
+ struct rhash_lock_head __rcu **bkt;
struct rhash_head __rcu **pprev;
struct rhash_head *he;
- spinlock_t * lock;
unsigned int hash;
int err = -ENOENT;
hash = rht_head_hashfn(ht, tbl, obj, params);
- lock = rht_bucket_lock(tbl, hash);
-
- spin_lock_bh(lock);
+ bkt = rht_bucket_var(tbl, hash);
+ if (!bkt)
+ return -ENOENT;
+ pprev = NULL;
+ rht_lock(tbl, bkt);
- pprev = rht_bucket_var(tbl, hash);
- rht_for_each_from(he, *pprev, tbl, hash) {
+ rht_for_each_from(he, rht_ptr(bkt, tbl, hash), tbl, hash) {
struct rhlist_head *list;
list = container_of(he, struct rhlist_head, rhead);
}
}
- rcu_assign_pointer(*pprev, obj);
- break;
+ if (pprev) {
+ rcu_assign_pointer(*pprev, obj);
+ rht_unlock(tbl, bkt);
+ } else {
+ rht_assign_unlock(tbl, bkt, obj);
+ }
+ goto unlocked;
}
- spin_unlock_bh(lock);
-
+ rht_unlock(tbl, bkt);
+unlocked:
if (err > 0) {
atomic_dec(&ht->nelems);
if (unlikely(ht->p.automatic_shrinking &&
struct rhash_head *obj_old, struct rhash_head *obj_new,
const struct rhashtable_params params)
{
+ struct rhash_lock_head __rcu **bkt;
struct rhash_head __rcu **pprev;
struct rhash_head *he;
- spinlock_t *lock;
unsigned int hash;
int err = -ENOENT;
if (hash != rht_head_hashfn(ht, tbl, obj_new, params))
return -EINVAL;
- lock = rht_bucket_lock(tbl, hash);
+ bkt = rht_bucket_var(tbl, hash);
+ if (!bkt)
+ return -ENOENT;
- spin_lock_bh(lock);
+ pprev = NULL;
+ rht_lock(tbl, bkt);
- pprev = rht_bucket_var(tbl, hash);
- rht_for_each_from(he, *pprev, tbl, hash) {
+ rht_for_each_from(he, rht_ptr(bkt, tbl, hash), tbl, hash) {
if (he != obj_old) {
pprev = &he->next;
continue;
}
rcu_assign_pointer(obj_new->next, obj_old->next);
- rcu_assign_pointer(*pprev, obj_new);
+ if (pprev) {
+ rcu_assign_pointer(*pprev, obj_new);
+ rht_unlock(tbl, bkt);
+ } else {
+ rht_assign_unlock(tbl, bkt, obj_new);
+ }
err = 0;
- break;
+ goto unlocked;
}
- spin_unlock_bh(lock);
+ rht_unlock(tbl, bkt);
+unlocked:
return err;
}
set_thread_flag(TIF_RESTORE_SIGMASK);
WARN_ON(!test_thread_flag(TIF_SIGPENDING));
}
+
+static inline void clear_tsk_restore_sigmask(struct task_struct *tsk)
+{
+ clear_tsk_thread_flag(tsk, TIF_RESTORE_SIGMASK);
+}
+
static inline void clear_restore_sigmask(void)
{
clear_thread_flag(TIF_RESTORE_SIGMASK);
}
+static inline bool test_tsk_restore_sigmask(struct task_struct *tsk)
+{
+ return test_tsk_thread_flag(tsk, TIF_RESTORE_SIGMASK);
+}
static inline bool test_restore_sigmask(void)
{
return test_thread_flag(TIF_RESTORE_SIGMASK);
current->restore_sigmask = true;
WARN_ON(!test_thread_flag(TIF_SIGPENDING));
}
+static inline void clear_tsk_restore_sigmask(struct task_struct *tsk)
+{
+ tsk->restore_sigmask = false;
+}
static inline void clear_restore_sigmask(void)
{
current->restore_sigmask = false;
{
return current->restore_sigmask;
}
+static inline bool test_tsk_restore_sigmask(struct task_struct *tsk)
+{
+ return tsk->restore_sigmask;
+}
static inline bool test_and_clear_restore_sigmask(void)
{
if (!current->restore_sigmask)
* @tc_index: Traffic control index
* @hash: the packet hash
* @queue_mapping: Queue mapping for multiqueue devices
- * @xmit_more: More SKBs are pending for this queue
* @pfmemalloc: skbuff was allocated from PFMEMALLOC reserves
* @active_extensions: active extensions (skb_ext_id types)
* @ndisc_nodetype: router type (from link layer)
fclone:2,
peeked:1,
head_frag:1,
- xmit_more:1,
pfmemalloc:1;
#ifdef CONFIG_SKB_EXTENSIONS
__u8 active_extensions;
unsigned int flags,
void (*destructor)(struct sock *sk,
struct sk_buff *skb),
- int *peeked, int *off, int *err,
+ int *off, int *err,
struct sk_buff **last);
struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned flags,
void (*destructor)(struct sock *sk,
struct sk_buff *skb),
- int *peeked, int *off, int *err,
+ int *off, int *err,
struct sk_buff **last);
struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned flags,
void (*destructor)(struct sock *sk,
struct sk_buff *skb),
- int *peeked, int *off, int *err);
+ int *off, int *err);
struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, int noblock,
int *err);
__poll_t datagram_poll(struct file *file, struct socket *sock,
#define SLAB_HWCACHE_ALIGN ((slab_flags_t __force)0x00002000U)
/* Use GFP_DMA memory */
#define SLAB_CACHE_DMA ((slab_flags_t __force)0x00004000U)
+/* Use GFP_DMA32 memory */
+#define SLAB_CACHE_DMA32 ((slab_flags_t __force)0x00008000U)
/* DEBUG: Store the last owner for bug hunting */
#define SLAB_STORE_USER ((slab_flags_t __force)0x00010000U)
/* Panic if kmem_cache_create() fails */
#ifndef __HAVE_ARCH_MEMCMP
extern int memcmp(const void *,const void *,__kernel_size_t);
#endif
+#ifndef __HAVE_ARCH_BCMP
+extern int bcmp(const void *,const void *,__kernel_size_t);
+#endif
#ifndef __HAVE_ARCH_MEMCHR
extern void * memchr(const void *,int,__kernel_size_t);
#endif
}
#endif /* CONFIG_SUNRPC_SWAP */
-static inline bool
-rpc_task_need_resched(const struct rpc_task *task)
-{
- if (RPC_IS_QUEUED(task) || task->tk_callback)
- return true;
- return false;
-}
-
#endif /* _LINUX_SUNRPC_SCHED_H_ */
#define vbg_debug pr_debug
#endif
-int vbg_hgcm_connect(struct vbg_dev *gdev,
+int vbg_hgcm_connect(struct vbg_dev *gdev, u32 requestor,
struct vmmdev_hgcm_service_location *loc,
u32 *client_id, int *vbox_status);
-int vbg_hgcm_disconnect(struct vbg_dev *gdev, u32 client_id, int *vbox_status);
+int vbg_hgcm_disconnect(struct vbg_dev *gdev, u32 requestor,
+ u32 client_id, int *vbox_status);
-int vbg_hgcm_call(struct vbg_dev *gdev, u32 client_id, u32 function,
- u32 timeout_ms, struct vmmdev_hgcm_function_parameter *parms,
- u32 parm_count, int *vbox_status);
+int vbg_hgcm_call(struct vbg_dev *gdev, u32 requestor, u32 client_id,
+ u32 function, u32 timeout_ms,
+ struct vmmdev_hgcm_function_parameter *parms, u32 parm_count,
+ int *vbox_status);
/**
* Convert a VirtualBox status code to a standard Linux kernel return value.
/*
* Creates a virtqueue and allocates the descriptor ring. If
* may_reduce_num is set, then this may allocate a smaller ring than
- * expected. The caller should query virtqueue_get_ring_size to learn
+ * expected. The caller should query virtqueue_get_vring_size to learn
* the actual size of the ring.
*/
struct virtqueue *vring_create_virtqueue(unsigned int index,
rxrpc_user_attach_call_t, unsigned long, gfp_t,
unsigned int);
void rxrpc_kernel_set_tx_length(struct socket *, struct rxrpc_call *, s64);
-u32 rxrpc_kernel_check_life(const struct socket *, const struct rxrpc_call *);
+bool rxrpc_kernel_check_life(const struct socket *, const struct rxrpc_call *,
+ u32 *);
void rxrpc_kernel_probe_life(struct socket *, struct rxrpc_call *);
u32 rxrpc_kernel_get_epoch(struct socket *, struct rxrpc_call *);
bool rxrpc_kernel_get_reply_time(struct socket *, struct rxrpc_call *,
ktime_t *);
+bool rxrpc_kernel_call_is_complete(struct rxrpc_call *);
#endif /* _NET_RXRPC_H */
#define wiphy_info(wiphy, format, args...) \
dev_info(&(wiphy)->dev, format, ##args)
+#define wiphy_err_ratelimited(wiphy, format, args...) \
+ dev_err_ratelimited(&(wiphy)->dev, format, ##args)
+#define wiphy_warn_ratelimited(wiphy, format, args...) \
+ dev_warn_ratelimited(&(wiphy)->dev, format, ##args)
+
#define wiphy_debug(wiphy, format, args...) \
wiphy_printk(KERN_DEBUG, wiphy, format, ##args)
};
struct devlink_port_attrs {
- bool set;
+ u8 set:1,
+ split:1,
+ switch_port:1;
enum devlink_port_flavour flavour;
u32 port_number; /* same value as "split group" */
- bool split;
u32 split_subport_number;
+ struct netdev_phys_item_id switch_id;
};
struct devlink_port {
void devlink_port_attrs_set(struct devlink_port *devlink_port,
enum devlink_port_flavour flavour,
u32 port_number, bool split,
- u32 split_subport_number);
+ u32 split_subport_number,
+ const unsigned char *switch_id,
+ unsigned char switch_id_len);
int devlink_sb_register(struct devlink *devlink, unsigned int sb_index,
u32 size, u16 ingress_pools_count,
u16 egress_pools_count, u16 ingress_tc_count,
int devlink_compat_flash_update(struct net_device *dev, const char *file_name);
int devlink_compat_phys_port_name_get(struct net_device *dev,
char *name, size_t len);
+int devlink_compat_switch_id_get(struct net_device *dev,
+ struct netdev_phys_item_id *ppid);
#else
return -EOPNOTSUPP;
}
+static inline int
+devlink_compat_switch_id_get(struct net_device *dev,
+ struct netdev_phys_item_id *ppid)
+{
+ return -EOPNOTSUPP;
+}
+
#endif
#endif /* _NET_DEVLINK_H_ */
unsigned int index;
const char *name;
const struct dsa_port *cpu_dp;
+ const char *mac;
struct device_node *dn;
unsigned int ageing_time;
u8 stp_state;
unsigned char __user *data, int optlen);
void ip_options_undo(struct ip_options *opt);
void ip_forward_options(struct sk_buff *skb);
-int ip_options_rcv_srr(struct sk_buff *skb);
+int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev);
/*
* Functions provided by ip_sockglue.c
struct fib6_nh {
struct fib_nh_common nh_common;
+
+#ifdef CONFIG_IPV6_ROUTER_PREF
+ unsigned long last_probe;
+#endif
};
struct fib6_info {
struct rt6_info * __percpu *rt6i_pcpu;
struct rt6_exception_bucket __rcu *rt6i_exception_bucket;
-#ifdef CONFIG_IPV6_ROUTER_PREF
- unsigned long last_probe;
-#endif
-
u32 fib6_metric;
u8 fib6_protocol;
u8 fib6_type;
unsigned short rt6i_nfheader_len;
};
+struct fib6_result {
+ struct fib6_nh *nh;
+ struct fib6_info *f6i;
+ u32 fib6_flags;
+ u8 fib6_type;
+};
+
#define for_each_fib6_node_rt_rcu(fn) \
for (rt = rcu_dereference((fn)->leaf); rt; \
rt = rcu_dereference(rt->fib6_next))
/* called with rcu lock held; can return error pointer
* caller needs to select path
*/
-struct fib6_info *fib6_lookup(struct net *net, int oif, struct flowi6 *fl6,
- int flags);
+int fib6_lookup(struct net *net, int oif, struct flowi6 *fl6,
+ struct fib6_result *res, int flags);
/* called with rcu lock held; caller needs to select path */
-struct fib6_info *fib6_table_lookup(struct net *net, struct fib6_table *table,
- int oif, struct flowi6 *fl6, int strict);
-
-struct fib6_info *fib6_multipath_select(const struct net *net,
- struct fib6_info *match,
- struct flowi6 *fl6, int oif,
- const struct sk_buff *skb, int strict);
+int fib6_table_lookup(struct net *net, struct fib6_table *table,
+ int oif, struct flowi6 *fl6, struct fib6_result *res,
+ int strict);
+void fib6_select_path(const struct net *net, struct fib6_result *res,
+ struct flowi6 *fl6, int oif, bool have_oif_match,
+ const struct sk_buff *skb, int strict);
struct fib6_node *fib6_node_lookup(struct fib6_node *root,
const struct in6_addr *daddr,
const struct in6_addr *saddr);
static inline bool rt6_qualify_for_ecmp(const struct fib6_info *f6i)
{
return !(f6i->fib6_flags & (RTF_ADDRCONF|RTF_DYNAMIC)) &&
- f6i->fib6_nh.fib_nh_has_gw;
+ f6i->fib6_nh.fib_nh_gw_family;
}
void ip6_route_input(struct sk_buff *skb);
return mtu;
}
-u32 ip6_mtu_from_fib6(struct fib6_info *f6i, struct in6_addr *daddr,
- struct in6_addr *saddr);
+u32 ip6_mtu_from_fib6(const struct fib6_result *res,
+ const struct in6_addr *daddr,
+ const struct in6_addr *saddr);
struct neighbour *ip6_neigh_lookup(const struct in6_addr *gw,
struct net_device *dev, struct sk_buff *skb,
u8 fc_protocol;
u8 fc_scope;
u8 fc_type;
- /* 3 bytes unused */
+ u8 fc_gw_family;
+ /* 2 bytes unused */
u32 fc_table;
__be32 fc_dst;
- __be32 fc_gw;
+ union {
+ __be32 fc_gw4;
+ struct in6_addr fc_gw6;
+ };
int fc_oif;
u32 fc_flags;
u32 fc_priority;
struct lwtunnel_state *nhc_lwtstate;
unsigned char nhc_scope;
u8 nhc_family;
- u8 nhc_has_gw:1,
- unused:7;
+ u8 nhc_gw_family;
+
union {
__be32 ipv4;
struct in6_addr ipv6;
#define fib_nh_flags nh_common.nhc_flags
#define fib_nh_lws nh_common.nhc_lwtstate
#define fib_nh_scope nh_common.nhc_scope
-#define fib_nh_family nh_common.nhc_family
-#define fib_nh_has_gw nh_common.nhc_has_gw
+#define fib_nh_gw_family nh_common.nhc_gw_family
#define fib_nh_gw4 nh_common.nhc_gw.ipv4
#define fib_nh_gw6 nh_common.nhc_gw.ipv6
#define fib_nh_weight nh_common.nhc_weight
#define fib_rtt fib_metrics->metrics[RTAX_RTT-1]
#define fib_advmss fib_metrics->metrics[RTAX_ADVMSS-1]
int fib_nhs;
+ bool fib_nh_is_v6;
struct rcu_head rcu;
struct fib_nh fib_nh[0];
#define fib_dev fib_nh[0].fib_nh_dev
struct fib_table;
struct fib_result {
- __be32 prefix;
- unsigned char prefixlen;
- unsigned char nh_sel;
- unsigned char type;
- unsigned char scope;
- u32 tclassid;
- struct fib_info *fi;
- struct fib_table *table;
- struct hlist_head *fa_head;
+ __be32 prefix;
+ unsigned char prefixlen;
+ unsigned char nh_sel;
+ unsigned char type;
+ unsigned char scope;
+ u32 tclassid;
+ struct fib_nh_common *nhc;
+ struct fib_info *fi;
+ struct fib_table *table;
+ struct hlist_head *fa_head;
};
struct fib_result_nl {
int err;
};
-#ifdef CONFIG_IP_ROUTE_MULTIPATH
-#define FIB_RES_NH(res) ((res).fi->fib_nh[(res).nh_sel])
-#else /* CONFIG_IP_ROUTE_MULTIPATH */
-#define FIB_RES_NH(res) ((res).fi->fib_nh[0])
-#endif /* CONFIG_IP_ROUTE_MULTIPATH */
+static inline struct fib_nh_common *fib_info_nhc(struct fib_info *fi, int nhsel)
+{
+ return &fi->fib_nh[nhsel].nh_common;
+}
#ifdef CONFIG_IP_MULTIPLE_TABLES
#define FIB_TABLE_HASHSZ 256
#endif
__be32 fib_info_update_nh_saddr(struct net *net, struct fib_nh *nh);
+__be32 fib_result_prefsrc(struct net *net, struct fib_result *res);
-#define FIB_RES_SADDR(net, res) \
- ((FIB_RES_NH(res).nh_saddr_genid == \
- atomic_read(&(net)->ipv4.dev_addr_genid)) ? \
- FIB_RES_NH(res).nh_saddr : \
- fib_info_update_nh_saddr((net), &FIB_RES_NH(res)))
-#define FIB_RES_GW(res) (FIB_RES_NH(res).fib_nh_gw4)
-#define FIB_RES_DEV(res) (FIB_RES_NH(res).fib_nh_dev)
-#define FIB_RES_OIF(res) (FIB_RES_NH(res).fib_nh_oif)
-
-#define FIB_RES_PREFSRC(net, res) ((res).fi->fib_prefsrc ? : \
- FIB_RES_SADDR(net, res))
+#define FIB_RES_NHC(res) ((res).nhc)
+#define FIB_RES_DEV(res) (FIB_RES_NHC(res)->nhc_dev)
+#define FIB_RES_OIF(res) (FIB_RES_NHC(res)->nhc_oif)
struct fib_entry_notifier_info {
struct fib_notifier_info info; /* must be first */
/* Exported by fib_frontend.c */
extern const struct nla_policy rtm_ipv4_policy[];
void ip_fib_init(void);
+int fib_gw_from_via(struct fib_config *cfg, struct nlattr *nla,
+ struct netlink_ext_ack *extack);
__be32 fib_compute_spec_dst(struct sk_buff *skb);
bool fib_info_nh_uses_dev(struct fib_info *fi, const struct net_device *dev);
int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
static inline void fib_combine_itag(u32 *itag, const struct fib_result *res)
{
#ifdef CONFIG_IP_ROUTE_CLASSID
+ struct fib_nh_common *nhc = res->nhc;
+ struct fib_nh *nh = container_of(nhc, struct fib_nh, nh_common);
#ifdef CONFIG_IP_MULTIPLE_TABLES
u32 rtag;
#endif
- *itag = FIB_RES_NH(*res).nh_tclassid<<16;
+ *itag = nh->nh_tclassid << 16;
#ifdef CONFIG_IP_MULTIPLE_TABLES
rtag = res->tclassid;
if (*itag == 0)
int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh,
struct fib_dump_filter *filter,
struct netlink_callback *cb);
+
+int fib_nexthop_info(struct sk_buff *skb, const struct fib_nh_common *nh,
+ unsigned int *flags, bool skip_oif);
+int fib_add_nexthop(struct sk_buff *skb, const struct fib_nh_common *nh,
+ int nh_weight);
#endif /* _NET_FIB_H */
/* Address family of addr */
u16 af;
+
+ u16 tun_type; /* tunnel type */
+ __be16 tun_port; /* tunnel port */
};
atomic_t conn_flags; /* flags to copy to conn */
atomic_t weight; /* server weight */
atomic_t last_weight; /* server latest weight */
+ __u16 tun_type; /* tunnel type */
+ __be16 tun_port; /* tunnel port */
refcount_t refcnt; /* reference counter */
struct ip_vs_stats stats; /* statistics */
/* structs from net/ip6_fib.h */
struct fib6_info;
+struct fib6_nh;
+struct fib6_config;
+struct fib6_result;
/* This is ugly, ideally these symbols should be built
* into the core kernel.
int (*ipv6_route_input)(struct sk_buff *skb);
struct fib6_table *(*fib6_get_table)(struct net *net, u32 id);
- struct fib6_info *(*fib6_lookup)(struct net *net, int oif,
- struct flowi6 *fl6, int flags);
- struct fib6_info *(*fib6_table_lookup)(struct net *net,
- struct fib6_table *table,
- int oif, struct flowi6 *fl6,
- int flags);
- struct fib6_info *(*fib6_multipath_select)(const struct net *net,
- struct fib6_info *f6i,
- struct flowi6 *fl6, int oif,
- const struct sk_buff *skb,
- int strict);
- u32 (*ip6_mtu_from_fib6)(struct fib6_info *f6i, struct in6_addr *daddr,
- struct in6_addr *saddr);
+ int (*fib6_lookup)(struct net *net, int oif, struct flowi6 *fl6,
+ struct fib6_result *res, int flags);
+ int (*fib6_table_lookup)(struct net *net, struct fib6_table *table,
+ int oif, struct flowi6 *fl6,
+ struct fib6_result *res, int flags);
+ void (*fib6_select_path)(const struct net *net, struct fib6_result *res,
+ struct flowi6 *fl6, int oif, bool oif_match,
+ const struct sk_buff *skb, int strict);
+ u32 (*ip6_mtu_from_fib6)(const struct fib6_result *res,
+ const struct in6_addr *daddr,
+ const struct in6_addr *saddr);
+ int (*fib6_nh_init)(struct net *net, struct fib6_nh *fib6_nh,
+ struct fib6_config *cfg, gfp_t gfp_flags,
+ struct netlink_ext_ack *extack);
+ void (*fib6_nh_release)(struct fib6_nh *fib6_nh);
void (*udpv6_encap_enable)(void);
void (*ndisc_send_na)(struct net_device *dev, const struct in6_addr *daddr,
const struct in6_addr *solicited_addr,
* @hw: pointer as obtained from ieee80211_alloc_hw()
* @ac: AC number to return packets from.
*
- * Should only be called between calls to ieee80211_txq_schedule_start()
- * and ieee80211_txq_schedule_end().
* Returns the next txq if successful, %NULL if no queue is eligible. If a txq
* is returned, it should be returned with ieee80211_return_txq() after the
* driver has finished scheduling it.
struct ieee80211_txq *ieee80211_next_txq(struct ieee80211_hw *hw, u8 ac);
/**
- * ieee80211_return_txq - return a TXQ previously acquired by ieee80211_next_txq()
- *
- * @hw: pointer as obtained from ieee80211_alloc_hw()
- * @txq: pointer obtained from station or virtual interface
- *
- * Should only be called between calls to ieee80211_txq_schedule_start()
- * and ieee80211_txq_schedule_end().
- */
-void ieee80211_return_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq);
-
-/**
- * ieee80211_txq_schedule_start - acquire locks for safe scheduling of an AC
+ * ieee80211_txq_schedule_start - start new scheduling round for TXQs
*
* @hw: pointer as obtained from ieee80211_alloc_hw()
* @ac: AC number to acquire locks for
*
- * Acquire locks needed to schedule TXQs from the given AC. Should be called
- * before ieee80211_next_txq() or ieee80211_return_txq().
+ * Should be called before ieee80211_next_txq() or ieee80211_return_txq().
+ * The driver must not call multiple TXQ scheduling rounds concurrently.
*/
-void ieee80211_txq_schedule_start(struct ieee80211_hw *hw, u8 ac)
- __acquires(txq_lock);
+void ieee80211_txq_schedule_start(struct ieee80211_hw *hw, u8 ac);
+
+/* (deprecated) */
+static inline void ieee80211_txq_schedule_end(struct ieee80211_hw *hw, u8 ac)
+{
+}
+
+void __ieee80211_schedule_txq(struct ieee80211_hw *hw,
+ struct ieee80211_txq *txq, bool force);
/**
- * ieee80211_txq_schedule_end - release locks for safe scheduling of an AC
+ * ieee80211_schedule_txq - schedule a TXQ for transmission
*
* @hw: pointer as obtained from ieee80211_alloc_hw()
- * @ac: AC number to acquire locks for
+ * @txq: pointer obtained from station or virtual interface
*
- * Release locks previously acquired by ieee80211_txq_schedule_end().
+ * Schedules a TXQ for transmission if it is not already scheduled,
+ * even if mac80211 does not have any packets buffered.
+ *
+ * The driver may call this function if it has buffered packets for
+ * this TXQ internally.
*/
-void ieee80211_txq_schedule_end(struct ieee80211_hw *hw, u8 ac)
- __releases(txq_lock);
+static inline void
+ieee80211_schedule_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq)
+{
+ __ieee80211_schedule_txq(hw, txq, true);
+}
/**
- * ieee80211_schedule_txq - schedule a TXQ for transmission
+ * ieee80211_return_txq - return a TXQ previously acquired by ieee80211_next_txq()
*
* @hw: pointer as obtained from ieee80211_alloc_hw()
* @txq: pointer obtained from station or virtual interface
+ * @force: schedule txq even if mac80211 does not have any buffered packets.
*
- * Schedules a TXQ for transmission if it is not already scheduled. Takes a
- * lock, which means it must *not* be called between
- * ieee80211_txq_schedule_start() and ieee80211_txq_schedule_end()
+ * The driver may set force=true if it has buffered packets for this TXQ
+ * internally.
*/
-void ieee80211_schedule_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq)
- __acquires(txq_lock) __releases(txq_lock);
+static inline void
+ieee80211_return_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq,
+ bool force)
+{
+ __ieee80211_schedule_txq(hw, txq, force);
+}
/**
* ieee80211_txq_may_transmit - check whether TXQ is allowed to transmit
#ifndef _NDISC_H
#define _NDISC_H
+#include <net/ipv6_stubs.h>
+
/*
* ICMP codes for neighbour discovery messages
*/
return ___neigh_lookup_noref(&nd_tbl, neigh_key_eq128, ndisc_hashfn, pkey, dev);
}
+static inline
+struct neighbour *__ipv6_neigh_lookup_noref_stub(struct net_device *dev,
+ const void *pkey)
+{
+ return ___neigh_lookup_noref(ipv6_stub->nd_tbl, neigh_key_eq128,
+ ndisc_hashfn, pkey, dev);
+}
+
static inline struct neighbour *__ipv6_neigh_lookup(struct net_device *dev, const void *pkey)
{
struct neighbour *n;
rcu_read_unlock_bh();
}
+static inline void __ipv6_confirm_neigh_stub(struct net_device *dev,
+ const void *pkey)
+{
+ struct neighbour *n;
+
+ rcu_read_lock_bh();
+ n = __ipv6_neigh_lookup_noref_stub(dev, pkey);
+ if (n) {
+ unsigned long now = jiffies;
+
+ /* avoid dirtying neighbour */
+ if (n->confirmed != now)
+ n->confirmed = now;
+ }
+ rcu_read_unlock_bh();
+}
+
+/* uses ipv6_stub and is meant for use outside of IPv6 core */
+static inline struct neighbour *ip_neigh_gw6(struct net_device *dev,
+ const void *addr)
+{
+ struct neighbour *neigh;
+
+ neigh = __ipv6_neigh_lookup_noref_stub(dev, addr);
+ if (unlikely(!neigh))
+ neigh = __neigh_create(ipv6_stub->nd_tbl, addr, dev, false);
+
+ return neigh;
+}
+
int ndisc_init(void);
int ndisc_late_init(void);
int (*pconstructor)(struct pneigh_entry *);
void (*pdestructor)(struct pneigh_entry *);
void (*proxy_redo)(struct sk_buff *skb);
+ bool (*allow_add)(const struct net_device *dev,
+ struct netlink_ext_ack *extack);
char *id;
struct neigh_parms parms;
struct list_head parms_list;
return dev_queue_xmit(skb);
}
-static inline int neigh_output(struct neighbour *n, struct sk_buff *skb)
+static inline int neigh_output(struct neighbour *n, struct sk_buff *skb,
+ bool skip_cache)
{
const struct hh_cache *hh = &n->hh;
- if ((n->nud_state & NUD_CONNECTED) && hh->hh_len)
+ if ((n->nud_state & NUD_CONNECTED) && hh->hh_len && !skip_cache)
return neigh_hh_output(hh, skb);
else
return n->output(n, skb);
*/
spinlock_t rules_mod_lock;
+ u32 hash_mix;
atomic64_t cookie_gen;
struct list_head list; /* list of network namespaces */
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _NF_NAT_MASQUERADE_IPV4_H_
-#define _NF_NAT_MASQUERADE_IPV4_H_
-
-#include <net/netfilter/nf_nat.h>
-
-unsigned int
-nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum,
- const struct nf_nat_range2 *range,
- const struct net_device *out);
-
-int nf_nat_masquerade_ipv4_register_notifier(void);
-void nf_nat_masquerade_ipv4_unregister_notifier(void);
-
-#endif /*_NF_NAT_MASQUERADE_IPV4_H_ */
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _NF_NAT_MASQUERADE_IPV6_H_
-#define _NF_NAT_MASQUERADE_IPV6_H_
-
-unsigned int
-nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range2 *range,
- const struct net_device *out);
-int nf_nat_masquerade_ipv6_register_notifier(void);
-void nf_nat_masquerade_ipv6_unregister_notifier(void);
-
-#endif /* _NF_NAT_MASQUERADE_IPV6_H_ */
/* Expectation class */
unsigned int class;
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
union nf_inet_addr saved_addr;
/* This is the original per-proto part, used to map the
* expected connection the way the recipient expects. */
#endif
}
-int nf_nat_register_fn(struct net *net, const struct nf_hook_ops *ops,
+int nf_nat_register_fn(struct net *net, u8 pf, const struct nf_hook_ops *ops,
const struct nf_hook_ops *nat_ops, unsigned int ops_count);
-void nf_nat_unregister_fn(struct net *net, const struct nf_hook_ops *ops,
+void nf_nat_unregister_fn(struct net *net, u8 pf, const struct nf_hook_ops *ops,
unsigned int ops_count);
unsigned int nf_nat_packet(struct nf_conn *ct, enum ip_conntrack_info ctinfo,
int nf_nat_ipv6_register_fn(struct net *net, const struct nf_hook_ops *ops);
void nf_nat_ipv6_unregister_fn(struct net *net, const struct nf_hook_ops *ops);
+int nf_nat_inet_register_fn(struct net *net, const struct nf_hook_ops *ops);
+void nf_nat_inet_unregister_fn(struct net *net, const struct nf_hook_ops *ops);
+
unsigned int
nf_nat_inet_fn(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state);
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _NF_NAT_MASQUERADE_H_
+#define _NF_NAT_MASQUERADE_H_
+
+#include <net/netfilter/nf_nat.h>
+
+unsigned int
+nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum,
+ const struct nf_nat_range2 *range,
+ const struct net_device *out);
+
+int nf_nat_masquerade_inet_register_notifiers(void);
+void nf_nat_masquerade_inet_unregister_notifiers(void);
+
+unsigned int
+nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range2 *range,
+ const struct net_device *out);
+
+#endif /*_NF_NAT_MASQUERADE_H_ */
return queue;
}
+int nf_queue(struct sk_buff *skb, struct nf_hook_state *state,
+ const struct nf_hook_entries *entries, unsigned int index,
+ unsigned int verdict);
#endif /* _NF_QUEUE_H */
enum nft_trans_phase phase);
int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set,
struct nft_set_binding *binding);
-void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set,
- struct nft_set_binding *binding, bool commit);
void nf_tables_destroy_set(const struct nft_ctx *ctx, struct nft_set *set);
/**
int __init nft_chain_filter_init(void);
void nft_chain_filter_fini(void);
+void __init nft_chain_route_init(void);
+void nft_chain_route_fini(void);
#endif /* _NET_NF_TABLES_H */
#ifndef __NET_NS_HASH_H__
#define __NET_NS_HASH_H__
-#include <asm/cache.h>
-
-struct net;
+#include <net/net_namespace.h>
static inline u32 net_hash_mix(const struct net *net)
{
-#ifdef CONFIG_NET_NS
- return (u32)(((unsigned long)net) >> ilog2(sizeof(*net)));
-#else
- return 0;
-#endif
+ return net->hash_mix;
}
#endif
int nr_t1timer_running(struct sock *);
/* sysctl_net_netrom.c */
-void nr_register_sysctl(void);
+int nr_register_sysctl(void);
void nr_unregister_sysctl(void);
#endif
* According to specification 102 622 chapter 4.4 Pipes,
* the pipe identifier is 7 bits long.
*/
-#define NCI_HCI_MAX_PIPES 127
+#define NCI_HCI_MAX_PIPES 128
struct nci_hci_gate {
u8 gate;
#include <net/flow.h>
#include <net/inet_sock.h>
#include <net/ip_fib.h>
+#include <net/arp.h>
+#include <net/ndisc.h>
#include <linux/in_route.h>
#include <linux/rtnetlink.h>
#include <linux/rcupdate.h>
unsigned int rt_flags;
__u16 rt_type;
__u8 rt_is_input;
- __u8 rt_uses_gateway;
+ u8 rt_gw_family;
int rt_iif;
/* Info on neighbour */
- __be32 rt_gateway;
+ union {
+ __be32 rt_gw4;
+ struct in6_addr rt_gw6;
+ };
/* Miscellaneous cached information */
u32 rt_mtu_locked:1,
static inline __be32 rt_nexthop(const struct rtable *rt, __be32 daddr)
{
- if (rt->rt_gateway)
- return rt->rt_gateway;
+ if (rt->rt_gw_family == AF_INET)
+ return rt->rt_gw4;
return daddr;
}
return hoplimit;
}
+static inline struct neighbour *ip_neigh_gw4(struct net_device *dev,
+ __be32 daddr)
+{
+ struct neighbour *neigh;
+
+ neigh = __ipv4_neigh_lookup_noref(dev, daddr);
+ if (unlikely(!neigh))
+ neigh = __neigh_create(&arp_tbl, &daddr, dev, false);
+
+ return neigh;
+}
+
+static inline struct neighbour *ip_neigh_for_gw(struct rtable *rt,
+ struct sk_buff *skb,
+ bool *is_v6gw)
+{
+ struct net_device *dev = rt->dst.dev;
+ struct neighbour *neigh;
+
+ if (likely(rt->rt_gw_family == AF_INET)) {
+ neigh = ip_neigh_gw4(dev, rt->rt_gw4);
+ } else if (rt->rt_gw_family == AF_INET6) {
+ neigh = ip_neigh_gw6(dev, &rt->rt_gw6);
+ *is_v6gw = true;
+ } else {
+ neigh = ip_neigh_gw4(dev, ip_hdr(skb)->daddr);
+ }
+ return neigh;
+}
+
#endif /* _ROUTE_H */
struct qdisc_skb_head {
struct sk_buff *head;
struct sk_buff *tail;
- union {
- u32 qlen;
- atomic_t atomic_qlen;
- };
+ __u32 qlen;
spinlock_t lock;
};
return (raw_read_seqcount(&qdisc->running) & 1) ? true : false;
}
+static inline bool qdisc_is_percpu_stats(const struct Qdisc *q)
+{
+ return q->flags & TCQ_F_CPUSTATS;
+}
+
static inline bool qdisc_is_empty(const struct Qdisc *qdisc)
{
- if (qdisc->flags & TCQ_F_NOLOCK)
+ if (qdisc_is_percpu_stats(qdisc))
return qdisc->empty;
return !qdisc->q.qlen;
}
BUILD_BUG_ON(sizeof(qcb->data) < sz);
}
+static inline int qdisc_qlen_cpu(const struct Qdisc *q)
+{
+ return this_cpu_ptr(q->cpu_qstats)->qlen;
+}
+
static inline int qdisc_qlen(const struct Qdisc *q)
{
return q->q.qlen;
}
-static inline u32 qdisc_qlen_sum(const struct Qdisc *q)
+static inline int qdisc_qlen_sum(const struct Qdisc *q)
{
- u32 qlen = q->qstats.qlen;
+ __u32 qlen = q->qstats.qlen;
+ int i;
- if (q->flags & TCQ_F_NOLOCK)
- qlen += atomic_read(&q->q.atomic_qlen);
- else
+ if (qdisc_is_percpu_stats(q)) {
+ for_each_possible_cpu(i)
+ qlen += per_cpu_ptr(q->cpu_qstats, i)->qlen;
+ } else {
qlen += q->q.qlen;
+ }
return qlen;
}
struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
const struct Qdisc *q = rcu_dereference(txq->qdisc);
- if (q->q.qlen) {
+ if (!qdisc_is_empty(q)) {
rcu_read_unlock();
return false;
}
return sch->enqueue(skb, sch, to_free);
}
-static inline bool qdisc_is_percpu_stats(const struct Qdisc *q)
-{
- return q->flags & TCQ_F_CPUSTATS;
-}
-
static inline void _bstats_update(struct gnet_stats_basic_packed *bstats,
__u64 bytes, __u32 packets)
{
this_cpu_add(sch->cpu_qstats->backlog, qdisc_pkt_len(skb));
}
-static inline void qdisc_qstats_atomic_qlen_inc(struct Qdisc *sch)
+static inline void qdisc_qstats_cpu_qlen_inc(struct Qdisc *sch)
{
- atomic_inc(&sch->q.atomic_qlen);
+ this_cpu_inc(sch->cpu_qstats->qlen);
}
-static inline void qdisc_qstats_atomic_qlen_dec(struct Qdisc *sch)
+static inline void qdisc_qstats_cpu_qlen_dec(struct Qdisc *sch)
{
- atomic_dec(&sch->q.atomic_qlen);
+ this_cpu_dec(sch->cpu_qstats->qlen);
}
static inline void qdisc_qstats_cpu_requeues_inc(struct Qdisc *sch)
sch->qstats.overlimits++;
}
+static inline int qdisc_qstats_copy(struct gnet_dump *d, struct Qdisc *sch)
+{
+ __u32 qlen = qdisc_qlen_sum(sch);
+
+ return gnet_stats_copy_queue(d, sch->cpu_qstats, &sch->qstats, qlen);
+}
+
+static inline void qdisc_qstats_qlen_backlog(struct Qdisc *sch, __u32 *qlen,
+ __u32 *backlog)
+{
+ struct gnet_stats_queue qstats = { 0 };
+ __u32 len = qdisc_qlen_sum(sch);
+
+ __gnet_stats_copy_queue(&qstats, sch->cpu_qstats, &sch->qstats, len);
+ *qlen = qstats.qlen;
+ *backlog = qstats.backlog;
+}
+
+static inline void qdisc_tree_flush_backlog(struct Qdisc *sch)
+{
+ __u32 qlen, backlog;
+
+ qdisc_qstats_qlen_backlog(sch, &qlen, &backlog);
+ qdisc_tree_reduce_backlog(sch, qlen, backlog);
+}
+
+static inline void qdisc_purge_queue(struct Qdisc *sch)
+{
+ __u32 qlen, backlog;
+
+ qdisc_qstats_qlen_backlog(sch, &qlen, &backlog);
+ qdisc_reset(sch);
+ qdisc_tree_reduce_backlog(sch, qlen, backlog);
+}
+
static inline void qdisc_skb_head_init(struct qdisc_skb_head *qh)
{
qh->head = NULL;
return skb;
}
+static inline void qdisc_update_stats_at_dequeue(struct Qdisc *sch,
+ struct sk_buff *skb)
+{
+ if (qdisc_is_percpu_stats(sch)) {
+ qdisc_qstats_cpu_backlog_dec(sch, skb);
+ qdisc_bstats_cpu_update(sch, skb);
+ qdisc_qstats_cpu_qlen_dec(sch);
+ } else {
+ qdisc_qstats_backlog_dec(sch, skb);
+ qdisc_bstats_update(sch, skb);
+ sch->q.qlen--;
+ }
+}
+
+static inline void qdisc_update_stats_at_enqueue(struct Qdisc *sch,
+ unsigned int pkt_len)
+{
+ if (qdisc_is_percpu_stats(sch)) {
+ qdisc_qstats_cpu_qlen_inc(sch);
+ this_cpu_add(sch->cpu_qstats->backlog, pkt_len);
+ } else {
+ sch->qstats.backlog += pkt_len;
+ sch->q.qlen++;
+ }
+}
+
/* use instead of qdisc->dequeue() for all qdiscs queried with ->peek() */
static inline struct sk_buff *qdisc_dequeue_peeked(struct Qdisc *sch)
{
if (skb) {
skb = __skb_dequeue(&sch->gso_skb);
- qdisc_qstats_backlog_dec(sch, skb);
- sch->q.qlen--;
+ if (qdisc_is_percpu_stats(sch)) {
+ qdisc_qstats_cpu_backlog_dec(sch, skb);
+ qdisc_qstats_cpu_qlen_dec(sch);
+ } else {
+ qdisc_qstats_backlog_dec(sch, skb);
+ sch->q.qlen--;
+ }
} else {
skb = sch->dequeue(sch);
}
sch_tree_lock(sch);
old = *pold;
*pold = new;
- if (old != NULL) {
- unsigned int qlen = old->q.qlen;
- unsigned int backlog = old->qstats.backlog;
-
- qdisc_reset(old);
- qdisc_tree_reduce_backlog(old, qlen, backlog);
- }
+ if (old != NULL)
+ qdisc_tree_flush_backlog(old);
sch_tree_unlock(sch);
return old;
/*
* This mimics the behavior of skb_set_owner_r
*/
- sk->sk_forward_alloc -= event->rmem_len;
+ sk_mem_charge(sk, event->rmem_len);
}
/* Tests if the list has one and only one entry. */
int sctp_ulpq_tail_data(struct sctp_ulpq *, struct sctp_chunk *, gfp_t);
/* Add a new event for propagation to the ULP. */
-int sctp_ulpq_tail_event(struct sctp_ulpq *, struct sctp_ulpevent *ev);
+int sctp_ulpq_tail_event(struct sctp_ulpq *, struct sk_buff_head *skb_list);
/* Renege previously received chunks. */
void sctp_ulpq_renege(struct sctp_ulpq *, struct sctp_chunk *, gfp_t);
* @p: poll_table
*
* See the comments in the wq_has_sleeper function.
- *
- * Do not derive sock from filp->private_data here. An SMC socket establishes
- * an internal TCP socket that is used in the fallback case. All socket
- * operations on the SMC socket are then forwarded to the TCP socket. In case of
- * poll, the filp->private_data pointer references the SMC socket because the
- * TCP socket has no file assigned.
*/
static inline void sock_poll_wait(struct file *filp, struct socket *sock,
poll_table *p)
int tls_device_sendpage(struct sock *sk, struct page *page,
int offset, size_t size, int flags);
void tls_device_sk_destruct(struct sock *sk);
+void tls_device_free_resources_tx(struct sock *sk);
void tls_device_init(void);
void tls_device_cleanup(void);
int tls_tx_records(struct sock *sk, int flags);
int flags);
int tls_push_partial_record(struct sock *sk, struct tls_context *ctx,
int flags);
+bool tls_free_partial_record(struct sock *sk, struct tls_context *ctx);
static inline struct tls_msg *tls_msg(struct sk_buff *skb)
{
static inline bool tls_is_sk_tx_device_offloaded(struct sock *sk)
{
#ifdef CONFIG_SOCK_VALIDATE_XMIT
- return sk_fullsock(sk) &
+ return sk_fullsock(sk) &&
(smp_load_acquire(&sk->sk_validate_xmit_skb) ==
&tls_validate_xmit_skb);
#else
int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb);
void udp_skb_destructor(struct sock *sk, struct sk_buff *skb);
struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags,
- int noblock, int *peeked, int *off, int *err);
+ int noblock, int *off, int *err);
static inline struct sk_buff *skb_recv_udp(struct sock *sk, unsigned int flags,
int noblock, int *err)
{
- int peeked, off = 0;
+ int off = 0;
- return __skb_recv_udp(sk, flags, noblock, &peeked, &off, err);
+ return __skb_recv_udp(sk, flags, noblock, &off, err);
}
int udp_v4_early_demux(struct sk_buff *skb);
int probe_order;
int remove_order;
- /* signal if the module handling the component cannot be removed */
- unsigned int ignore_module_refcount:1;
+ /*
+ * signal if the module handling the component should not be removed
+ * if a pcm is open. Setting this would prevent the module
+ * refcount being incremented in probe() but allow it be incremented
+ * when a pcm is opened and decremented when it is closed.
+ */
+ unsigned int module_get_upon_open:1;
/* bits */
unsigned int idle_bias_on:1;
struct mutex mutex;
struct mutex dapm_mutex;
+ spinlock_t dpcm_lock;
+
bool instantiated;
bool topology_shortname_created;
TRACE_EVENT(fib_table_lookup,
TP_PROTO(u32 tb_id, const struct flowi4 *flp,
- const struct fib_nh *nh, int err),
+ const struct fib_nh_common *nhc, int err),
- TP_ARGS(tb_id, flp, nh, err),
+ TP_ARGS(tb_id, flp, nhc, err),
TP_STRUCT__entry(
__field( u32, tb_id )
__field( __u8, flags )
__array( __u8, src, 4 )
__array( __u8, dst, 4 )
- __array( __u8, gw, 4 )
- __array( __u8, saddr, 4 )
+ __array( __u8, gw4, 4 )
+ __array( __u8, gw6, 16 )
__field( u16, sport )
__field( u16, dport )
__dynamic_array(char, name, IFNAMSIZ )
),
TP_fast_assign(
+ struct in6_addr in6_zero = {};
+ struct net_device *dev;
+ struct in6_addr *in6;
__be32 *p32;
__entry->tb_id = tb_id;
__entry->dport = 0;
}
- if (nh) {
- struct net_device *dev;
+ dev = nhc ? nhc->nhc_dev : NULL;
+ __assign_str(name, dev ? dev->name : "-");
- p32 = (__be32 *) __entry->saddr;
- *p32 = nh->nh_saddr;
+ if (nhc) {
+ if (nhc->nhc_gw_family == AF_INET) {
+ p32 = (__be32 *) __entry->gw4;
+ *p32 = nhc->nhc_gw.ipv4;
- p32 = (__be32 *) __entry->gw;
- *p32 = nh->fib_nh_gw4;
+ in6 = (struct in6_addr *)__entry->gw6;
+ *in6 = in6_zero;
+ } else if (nhc->nhc_gw_family == AF_INET6) {
+ p32 = (__be32 *) __entry->gw4;
+ *p32 = 0;
- dev = nh->fib_nh_dev;
- __assign_str(name, dev ? dev->name : "-");
+ in6 = (struct in6_addr *)__entry->gw6;
+ *in6 = nhc->nhc_gw.ipv6;
+ }
} else {
- p32 = (__be32 *) __entry->saddr;
+ p32 = (__be32 *) __entry->gw4;
*p32 = 0;
- p32 = (__be32 *) __entry->gw;
- *p32 = 0;
-
- __assign_str(name, "-");
+ in6 = (struct in6_addr *)__entry->gw6;
+ *in6 = in6_zero;
}
),
- TP_printk("table %u oif %d iif %d proto %u %pI4/%u -> %pI4/%u tos %d scope %d flags %x ==> dev %s gw %pI4 src %pI4 err %d",
+ TP_printk("table %u oif %d iif %d proto %u %pI4/%u -> %pI4/%u tos %d scope %d flags %x ==> dev %s gw %pI4/%pI6c err %d",
__entry->tb_id, __entry->oif, __entry->iif, __entry->proto,
__entry->src, __entry->sport, __entry->dst, __entry->dport,
__entry->tos, __entry->scope, __entry->flags,
- __get_str(name), __entry->gw, __entry->saddr, __entry->err)
+ __get_str(name), __entry->gw4, __entry->gw6, __entry->err)
);
#endif /* _TRACE_FIB_H */
TRACE_EVENT(fib6_table_lookup,
- TP_PROTO(const struct net *net, const struct fib6_info *f6i,
+ TP_PROTO(const struct net *net, const struct fib6_result *res,
struct fib6_table *table, const struct flowi6 *flp),
- TP_ARGS(net, f6i, table, flp),
+ TP_ARGS(net, res, table, flp),
TP_STRUCT__entry(
__field( u32, tb_id )
struct in6_addr *in6;
__entry->tb_id = table->tb6_id;
- __entry->err = ip6_rt_type_to_error(f6i->fib6_type);
+ __entry->err = ip6_rt_type_to_error(res->fib6_type);
__entry->oif = flp->flowi6_oif;
__entry->iif = flp->flowi6_iif;
__entry->tos = ip6_tclass(flp->flowlabel);
__entry->dport = 0;
}
- if (f6i->fib6_nh.fib_nh_dev) {
- __assign_str(name, f6i->fib6_nh.fib_nh_dev);
+ if (res->nh && res->nh->fib_nh_dev) {
+ __assign_str(name, res->nh->fib_nh_dev);
} else {
__assign_str(name, "-");
}
- if (f6i == net->ipv6.fib6_null_entry) {
+ if (res->f6i == net->ipv6.fib6_null_entry) {
struct in6_addr in6_zero = {};
in6 = (struct in6_addr *)__entry->gw;
*in6 = in6_zero;
- } else if (f6i) {
+ } else if (res->nh) {
in6 = (struct in6_addr *)__entry->gw;
- *in6 = f6i->fib6_nh.fib_nh_gw6;
+ *in6 = res->nh->fib_nh_gw6;
}
),
__entry->mlxsw_sp, __entry->vregion)
);
-TRACE_EVENT(mlxsw_sp_acl_tcam_vregion_rehash_dis,
+TRACE_EVENT(mlxsw_sp_acl_tcam_vregion_rehash_rollback_failed,
TP_PROTO(const struct mlxsw_sp *mlxsw_sp,
const struct mlxsw_sp_acl_tcam_vregion *vregion),
TP_fast_assign(
__entry->id = id;
- syscall_get_arguments(current, regs, 0, 6, __entry->args);
+ syscall_get_arguments(current, regs, __entry->args);
),
TP_printk("NR %ld (%lx, %lx, %lx, %lx, %lx, %lx)",
endif
ifeq ($(wildcard $(srctree)/arch/$(SRCARCH)/include/uapi/asm/kvm_para.h),)
+ifeq ($(wildcard $(objtree)/arch/$(SRCARCH)/include/generated/uapi/asm/kvm_para.h),)
no-export-headers += kvm_para.h
endif
+endif
BPF_BTF_GET_FD_BY_ID,
BPF_TASK_FD_QUERY,
BPF_MAP_LOOKUP_AND_DELETE_ELEM,
+ BPF_MAP_FREEZE,
};
enum bpf_map_type {
*/
#define BPF_F_ANY_ALIGNMENT (1U << 1)
-/* when bpf_ldimm64->src_reg == BPF_PSEUDO_MAP_FD, bpf_ldimm64->imm == fd */
+/* When BPF ldimm64's insn[0].src_reg != 0 then this can have
+ * two extensions:
+ *
+ * insn[0].src_reg: BPF_PSEUDO_MAP_FD BPF_PSEUDO_MAP_VALUE
+ * insn[0].imm: map fd map fd
+ * insn[1].imm: 0 offset into value
+ * insn[0].off: 0 0
+ * insn[1].off: 0 0
+ * ldimm64 rewrite: address of map address of map[0]+offset
+ * verifier type: CONST_PTR_TO_MAP PTR_TO_MAP_VALUE
+ */
#define BPF_PSEUDO_MAP_FD 1
+#define BPF_PSEUDO_MAP_VALUE 2
/* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative
* offset to another bpf function
#define BPF_OBJ_NAME_LEN 16U
-/* Flags for accessing BPF object */
+/* Flags for accessing BPF object from syscall side. */
#define BPF_F_RDONLY (1U << 3)
#define BPF_F_WRONLY (1U << 4)
/* Zero-initialize hash function seed. This should only be used for testing. */
#define BPF_F_ZERO_SEED (1U << 6)
+/* Flags for accessing BPF object from program side. */
+#define BPF_F_RDONLY_PROG (1U << 7)
+#define BPF_F_WRONLY_PROG (1U << 8)
+
/* flags for BPF_PROG_QUERY */
#define BPF_F_QUERY_EFFECTIVE (1U << 0)
__aligned_u64 data_out;
__u32 repeat;
__u32 duration;
+ __u32 ctx_size_in; /* input: len of ctx_in */
+ __u32 ctx_size_out; /* input/output: len of ctx_out
+ * returns ENOSPC if ctx_out
+ * is too small.
+ */
+ __aligned_u64 ctx_in;
+ __aligned_u64 ctx_out;
} test;
struct { /* anonymous struct used by BPF_*_GET_*_ID */
* * **BPF_F_ADJ_ROOM_ENCAP_L4_UDP **:
* Use with ENCAP_L3 flags to further specify the tunnel type.
*
+ * * **BPF_F_ADJ_ROOM_ENCAP_L2(len) **:
+ * Use with ENCAP_L3/L4 flags to further specify the tunnel
+ * type; **len** is the length of the inner MAC header.
+ *
* A call to this helper is susceptible to change the underlaying
* packet buffer. Therefore, at load time, all checks on pointers
* previously done by the verifier are invalidated and must be
/* BPF_FUNC_skb_adjust_room flags. */
#define BPF_F_ADJ_ROOM_FIXED_GSO (1ULL << 0)
+#define BPF_ADJ_ROOM_ENCAP_L2_MASK 0xff
+#define BPF_ADJ_ROOM_ENCAP_L2_SHIFT 56
+
#define BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 (1ULL << 1)
#define BPF_F_ADJ_ROOM_ENCAP_L3_IPV6 (1ULL << 2)
#define BPF_F_ADJ_ROOM_ENCAP_L4_GRE (1ULL << 3)
#define BPF_F_ADJ_ROOM_ENCAP_L4_UDP (1ULL << 4)
+#define BPF_F_ADJ_ROOM_ENCAP_L2(len) (((__u64)len & \
+ BPF_ADJ_ROOM_ENCAP_L2_MASK) \
+ << BPF_ADJ_ROOM_ENCAP_L2_SHIFT)
/* Mode for BPF_FUNC_skb_adjust_room helper. */
enum bpf_adj_room_mode {
* struct, union and fwd
*/
__u32 info;
- /* "size" is used by INT, ENUM, STRUCT and UNION.
+ /* "size" is used by INT, ENUM, STRUCT, UNION and DATASEC.
* "size" tells the size of the type it is describing.
*
* "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT,
- * FUNC and FUNC_PROTO.
+ * FUNC, FUNC_PROTO and VAR.
* "type" is a type_id referring to another type.
*/
union {
#define BTF_KIND_RESTRICT 11 /* Restrict */
#define BTF_KIND_FUNC 12 /* Function */
#define BTF_KIND_FUNC_PROTO 13 /* Function Proto */
-#define BTF_KIND_MAX 13
-#define NR_BTF_KINDS 14
+#define BTF_KIND_VAR 14 /* Variable */
+#define BTF_KIND_DATASEC 15 /* Section */
+#define BTF_KIND_MAX BTF_KIND_DATASEC
+#define NR_BTF_KINDS (BTF_KIND_MAX + 1)
/* For some specific BTF_KIND, "struct btf_type" is immediately
* followed by extra data.
__u32 type;
};
+enum {
+ BTF_VAR_STATIC = 0,
+ BTF_VAR_GLOBAL_ALLOCATED,
+};
+
+/* BTF_KIND_VAR is followed by a single "struct btf_var" to describe
+ * additional information related to the variable such as its linkage.
+ */
+struct btf_var {
+ __u32 linkage;
+};
+
+/* BTF_KIND_DATASEC is followed by multiple "struct btf_var_secinfo"
+ * to describe all BTF_KIND_VAR types it contains along with it's
+ * in-section offset as well as size.
+ */
+struct btf_var_secinfo {
+ __u32 type;
+ __u32 offset;
+ __u32 size;
+};
+
#endif /* _UAPI__LINUX_BTF_H__ */
static inline int ethtool_validate_speed(__u32 speed)
{
- return speed <= INT_MAX || speed == SPEED_UNKNOWN;
+ return speed <= INT_MAX || speed == (__u32)SPEED_UNKNOWN;
}
/* Duplex, half or full. */
#define IP_VS_PEDATA_MAXLEN 255
+/* Tunnel types */
+enum {
+ IP_VS_CONN_F_TUNNEL_TYPE_IPIP = 0, /* IPIP */
+ IP_VS_CONN_F_TUNNEL_TYPE_GUE, /* GUE */
+ IP_VS_CONN_F_TUNNEL_TYPE_MAX,
+};
+
/*
* The struct ip_vs_service_user and struct ip_vs_dest_user are
* used to set IPVS rules through setsockopt.
IPVS_DEST_ATTR_STATS64, /* nested attribute for dest stats */
+ IPVS_DEST_ATTR_TUN_TYPE, /* tunnel type */
+
+ IPVS_DEST_ATTR_TUN_PORT, /* tunnel port */
+
__IPVS_DEST_ATTR_MAX,
};
*
* @NFTA_OSF_DREG: destination register (NLA_U32: nft_registers)
* @NFTA_OSF_TTL: Value of the TTL osf option (NLA_U8)
+ * @NFTA_OSF_FLAGS: flags (NLA_U32)
*/
enum nft_osf_attributes {
NFTA_OSF_UNSPEC,
NFTA_OSF_DREG,
NFTA_OSF_TTL,
+ NFTA_OSF_FLAGS,
__NFTA_OSF_MAX,
};
#define NFTA_OSF_MAX (__NFTA_OSF_MAX - 1)
+enum nft_osf_flags {
+ NFT_OSF_F_VERSION = (1 << 0),
+};
+
/**
* enum nft_device_attributes - nf_tables device netlink attributes
*
#define VMMDEVREQ_HGCM_CALL VMMDEVREQ_HGCM_CALL32
#endif
+/* vmmdev_request_header.requestor defines */
+
+/* Requestor user not given. */
+#define VMMDEV_REQUESTOR_USR_NOT_GIVEN 0x00000000
+/* The kernel driver (vboxguest) is the requestor. */
+#define VMMDEV_REQUESTOR_USR_DRV 0x00000001
+/* Some other kernel driver is the requestor. */
+#define VMMDEV_REQUESTOR_USR_DRV_OTHER 0x00000002
+/* The root or a admin user is the requestor. */
+#define VMMDEV_REQUESTOR_USR_ROOT 0x00000003
+/* Regular joe user is making the request. */
+#define VMMDEV_REQUESTOR_USR_USER 0x00000006
+/* User classification mask. */
+#define VMMDEV_REQUESTOR_USR_MASK 0x00000007
+
+/* Kernel mode request. Note this is 0, check for !USERMODE instead. */
+#define VMMDEV_REQUESTOR_KERNEL 0x00000000
+/* User mode request. */
+#define VMMDEV_REQUESTOR_USERMODE 0x00000008
+/* User or kernel mode classification mask. */
+#define VMMDEV_REQUESTOR_MODE_MASK 0x00000008
+
+/* Don't know the physical console association of the requestor. */
+#define VMMDEV_REQUESTOR_CON_DONT_KNOW 0x00000000
+/*
+ * The request originates with a process that is NOT associated with the
+ * physical console.
+ */
+#define VMMDEV_REQUESTOR_CON_NO 0x00000010
+/* Requestor process is associated with the physical console. */
+#define VMMDEV_REQUESTOR_CON_YES 0x00000020
+/* Console classification mask. */
+#define VMMDEV_REQUESTOR_CON_MASK 0x00000030
+
+/* Requestor is member of special VirtualBox user group. */
+#define VMMDEV_REQUESTOR_GRP_VBOX 0x00000080
+
+/* Note: trust level is for windows guests only, linux always uses not-given */
+/* Requestor trust level: Unspecified */
+#define VMMDEV_REQUESTOR_TRUST_NOT_GIVEN 0x00000000
+/* Requestor trust level: Untrusted (SID S-1-16-0) */
+#define VMMDEV_REQUESTOR_TRUST_UNTRUSTED 0x00001000
+/* Requestor trust level: Untrusted (SID S-1-16-4096) */
+#define VMMDEV_REQUESTOR_TRUST_LOW 0x00002000
+/* Requestor trust level: Medium (SID S-1-16-8192) */
+#define VMMDEV_REQUESTOR_TRUST_MEDIUM 0x00003000
+/* Requestor trust level: Medium plus (SID S-1-16-8448) */
+#define VMMDEV_REQUESTOR_TRUST_MEDIUM_PLUS 0x00004000
+/* Requestor trust level: High (SID S-1-16-12288) */
+#define VMMDEV_REQUESTOR_TRUST_HIGH 0x00005000
+/* Requestor trust level: System (SID S-1-16-16384) */
+#define VMMDEV_REQUESTOR_TRUST_SYSTEM 0x00006000
+/* Requestor trust level >= Protected (SID S-1-16-20480, S-1-16-28672) */
+#define VMMDEV_REQUESTOR_TRUST_PROTECTED 0x00007000
+/* Requestor trust level mask */
+#define VMMDEV_REQUESTOR_TRUST_MASK 0x00007000
+
+/* Requestor is using the less trusted user device node (/dev/vboxuser) */
+#define VMMDEV_REQUESTOR_USER_DEVICE 0x00008000
+
/** HGCM service location types. */
enum vmmdev_hgcm_service_location_type {
VMMDEV_HGCM_LOC_INVALID = 0,
#ifndef __KERNEL__
#include <stdlib.h>
+#include <time.h>
#endif
/*
.head_offset = offsetof(struct kern_ipc_perm, khtnode),
.key_offset = offsetof(struct kern_ipc_perm, key),
.key_len = FIELD_SIZEOF(struct kern_ipc_perm, key),
- .locks_mul = 1,
.automatic_shrinking = true,
};
#include "map_in_map.h"
#define ARRAY_CREATE_FLAG_MASK \
- (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
+ (BPF_F_NUMA_NODE | BPF_F_ACCESS_MASK)
static void bpf_array_free_percpu(struct bpf_array *array)
{
if (attr->max_entries == 0 || attr->key_size != 4 ||
attr->value_size == 0 ||
attr->map_flags & ~ARRAY_CREATE_FLAG_MASK ||
+ !bpf_map_flags_access_ok(attr->map_flags) ||
(percpu && numa_node != NUMA_NO_NODE))
return -EINVAL;
return array->value + array->elem_size * (index & array->index_mask);
}
+static int array_map_direct_value_addr(const struct bpf_map *map, u64 *imm,
+ u32 off)
+{
+ struct bpf_array *array = container_of(map, struct bpf_array, map);
+
+ if (map->max_entries != 1)
+ return -ENOTSUPP;
+ if (off >= map->value_size)
+ return -EINVAL;
+
+ *imm = (unsigned long)array->value;
+ return 0;
+}
+
+static int array_map_direct_value_meta(const struct bpf_map *map, u64 imm,
+ u32 *off)
+{
+ struct bpf_array *array = container_of(map, struct bpf_array, map);
+ u64 base = (unsigned long)array->value;
+ u64 range = array->elem_size;
+
+ if (map->max_entries != 1)
+ return -ENOTSUPP;
+ if (imm < base || imm >= base + range)
+ return -ENOENT;
+
+ *off = imm - base;
+ return 0;
+}
+
/* emit BPF instructions equivalent to C code of array_map_lookup_elem() */
static u32 array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
{
return;
}
- seq_printf(m, "%u: ", *(u32 *)key);
+ if (map->btf_key_type_id)
+ seq_printf(m, "%u: ", *(u32 *)key);
btf_type_seq_show(map->btf, map->btf_value_type_id, value, m);
seq_puts(m, "\n");
{
u32 int_data;
+ /* One exception for keyless BTF: .bss/.data/.rodata map */
+ if (btf_type_is_void(key_type)) {
+ if (map->map_type != BPF_MAP_TYPE_ARRAY ||
+ map->max_entries != 1)
+ return -EINVAL;
+
+ if (BTF_INFO_KIND(value_type->info) != BTF_KIND_DATASEC)
+ return -EINVAL;
+
+ return 0;
+ }
+
if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT)
return -EINVAL;
.map_update_elem = array_map_update_elem,
.map_delete_elem = array_map_delete_elem,
.map_gen_lookup = array_map_gen_lookup,
+ .map_direct_value_addr = array_map_direct_value_addr,
+ .map_direct_value_meta = array_map_direct_value_meta,
.map_seq_show_elem = array_map_seq_show_elem,
.map_check_btf = array_map_check_btf,
};
/* only file descriptors can be stored in this type of map */
if (attr->value_size != sizeof(u32))
return -EINVAL;
+ /* Program read-only/write-only not supported for special maps yet. */
+ if (attr->map_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG))
+ return -EINVAL;
return array_map_alloc_check(attr);
}
i < btf_type_vlen(struct_type); \
i++, member++)
+#define for_each_vsi(i, struct_type, member) \
+ for (i = 0, member = btf_type_var_secinfo(struct_type); \
+ i < btf_type_vlen(struct_type); \
+ i++, member++)
+
+#define for_each_vsi_from(i, from, struct_type, member) \
+ for (i = from, member = btf_type_var_secinfo(struct_type) + from; \
+ i < btf_type_vlen(struct_type); \
+ i++, member++)
+
static DEFINE_IDR(btf_idr);
static DEFINE_SPINLOCK(btf_idr_lock);
[BTF_KIND_RESTRICT] = "RESTRICT",
[BTF_KIND_FUNC] = "FUNC",
[BTF_KIND_FUNC_PROTO] = "FUNC_PROTO",
+ [BTF_KIND_VAR] = "VAR",
+ [BTF_KIND_DATASEC] = "DATASEC",
};
struct btf_kind_operations {
return false;
}
-static bool btf_type_is_void(const struct btf_type *t)
+bool btf_type_is_void(const struct btf_type *t)
{
return t == &btf_void;
}
return BTF_INFO_KIND(t->info) == BTF_KIND_INT;
}
+static bool btf_type_is_var(const struct btf_type *t)
+{
+ return BTF_INFO_KIND(t->info) == BTF_KIND_VAR;
+}
+
+static bool btf_type_is_datasec(const struct btf_type *t)
+{
+ return BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC;
+}
+
+/* Types that act only as a source, not sink or intermediate
+ * type when resolving.
+ */
+static bool btf_type_is_resolve_source_only(const struct btf_type *t)
+{
+ return btf_type_is_var(t) ||
+ btf_type_is_datasec(t);
+}
+
/* What types need to be resolved?
*
* btf_type_is_modifier() is an obvious one.
*
* btf_type_is_struct() because its member refers to
* another type (through member->type).
-
+ *
+ * btf_type_is_var() because the variable refers to
+ * another type. btf_type_is_datasec() holds multiple
+ * btf_type_is_var() types that need resolving.
+ *
* btf_type_is_array() because its element (array->type)
* refers to another type. Array can be thought of a
* special case of struct while array just has the same
static bool btf_type_needs_resolve(const struct btf_type *t)
{
return btf_type_is_modifier(t) ||
- btf_type_is_ptr(t) ||
- btf_type_is_struct(t) ||
- btf_type_is_array(t);
+ btf_type_is_ptr(t) ||
+ btf_type_is_struct(t) ||
+ btf_type_is_array(t) ||
+ btf_type_is_var(t) ||
+ btf_type_is_datasec(t);
}
/* t->size can be used */
case BTF_KIND_STRUCT:
case BTF_KIND_UNION:
case BTF_KIND_ENUM:
+ case BTF_KIND_DATASEC:
return true;
}
return (const struct btf_enum *)(t + 1);
}
+static const struct btf_var *btf_type_var(const struct btf_type *t)
+{
+ return (const struct btf_var *)(t + 1);
+}
+
+static const struct btf_var_secinfo *btf_type_var_secinfo(const struct btf_type *t)
+{
+ return (const struct btf_var_secinfo *)(t + 1);
+}
+
static const struct btf_kind_operations *btf_type_ops(const struct btf_type *t)
{
return kind_ops[BTF_INFO_KIND(t->info)];
offset < btf->hdr.str_len;
}
-/* Only C-style identifier is permitted. This can be relaxed if
- * necessary.
- */
-static bool btf_name_valid_identifier(const struct btf *btf, u32 offset)
+static bool __btf_name_char_ok(char c, bool first, bool dot_ok)
+{
+ if ((first ? !isalpha(c) :
+ !isalnum(c)) &&
+ c != '_' &&
+ ((c == '.' && !dot_ok) ||
+ c != '.'))
+ return false;
+ return true;
+}
+
+static bool __btf_name_valid(const struct btf *btf, u32 offset, bool dot_ok)
{
/* offset must be valid */
const char *src = &btf->strings[offset];
const char *src_limit;
- if (!isalpha(*src) && *src != '_')
+ if (!__btf_name_char_ok(*src, true, dot_ok))
return false;
/* set a limit on identifier length */
src_limit = src + KSYM_NAME_LEN;
src++;
while (*src && src < src_limit) {
- if (!isalnum(*src) && *src != '_')
+ if (!__btf_name_char_ok(*src, false, dot_ok))
return false;
src++;
}
return !*src;
}
+/* Only C-style identifier is permitted. This can be relaxed if
+ * necessary.
+ */
+static bool btf_name_valid_identifier(const struct btf *btf, u32 offset)
+{
+ return __btf_name_valid(btf, offset, false);
+}
+
+static bool btf_name_valid_section(const struct btf *btf, u32 offset)
+{
+ return __btf_name_valid(btf, offset, true);
+}
+
static const char *__btf_name_by_offset(const struct btf *btf, u32 offset)
{
if (!offset)
__btf_verifier_log(log, "\n");
}
+__printf(4, 5)
+static void btf_verifier_log_vsi(struct btf_verifier_env *env,
+ const struct btf_type *datasec_type,
+ const struct btf_var_secinfo *vsi,
+ const char *fmt, ...)
+{
+ struct bpf_verifier_log *log = &env->log;
+ va_list args;
+
+ if (!bpf_verifier_log_needed(log))
+ return;
+ if (env->phase != CHECK_META)
+ btf_verifier_log_type(env, datasec_type, NULL);
+
+ __btf_verifier_log(log, "\t type_id=%u offset=%u size=%u",
+ vsi->type, vsi->offset, vsi->size);
+ if (fmt && *fmt) {
+ __btf_verifier_log(log, " ");
+ va_start(args, fmt);
+ bpf_verifier_vlog(log, fmt, args);
+ va_end(args);
+ }
+
+ __btf_verifier_log(log, "\n");
+}
+
static void btf_verifier_log_hdr(struct btf_verifier_env *env,
u32 btf_data_size)
{
} else if (btf_type_is_ptr(size_type)) {
size = sizeof(void *);
} else {
- if (WARN_ON_ONCE(!btf_type_is_modifier(size_type)))
+ if (WARN_ON_ONCE(!btf_type_is_modifier(size_type) &&
+ !btf_type_is_var(size_type)))
return NULL;
size = btf->resolved_sizes[size_type_id];
u32 next_type_size = 0;
next_type = btf_type_by_id(btf, next_type_id);
- if (!next_type) {
+ if (!next_type || btf_type_is_resolve_source_only(next_type)) {
btf_verifier_log_type(env, v->t, "Invalid type_id");
return -EINVAL;
}
return 0;
}
+static int btf_var_resolve(struct btf_verifier_env *env,
+ const struct resolve_vertex *v)
+{
+ const struct btf_type *next_type;
+ const struct btf_type *t = v->t;
+ u32 next_type_id = t->type;
+ struct btf *btf = env->btf;
+ u32 next_type_size;
+
+ next_type = btf_type_by_id(btf, next_type_id);
+ if (!next_type || btf_type_is_resolve_source_only(next_type)) {
+ btf_verifier_log_type(env, v->t, "Invalid type_id");
+ return -EINVAL;
+ }
+
+ if (!env_type_is_resolve_sink(env, next_type) &&
+ !env_type_is_resolved(env, next_type_id))
+ return env_stack_push(env, next_type, next_type_id);
+
+ if (btf_type_is_modifier(next_type)) {
+ const struct btf_type *resolved_type;
+ u32 resolved_type_id;
+
+ resolved_type_id = next_type_id;
+ resolved_type = btf_type_id_resolve(btf, &resolved_type_id);
+
+ if (btf_type_is_ptr(resolved_type) &&
+ !env_type_is_resolve_sink(env, resolved_type) &&
+ !env_type_is_resolved(env, resolved_type_id))
+ return env_stack_push(env, resolved_type,
+ resolved_type_id);
+ }
+
+ /* We must resolve to something concrete at this point, no
+ * forward types or similar that would resolve to size of
+ * zero is allowed.
+ */
+ if (!btf_type_id_size(btf, &next_type_id, &next_type_size)) {
+ btf_verifier_log_type(env, v->t, "Invalid type_id");
+ return -EINVAL;
+ }
+
+ env_stack_pop_resolved(env, next_type_id, next_type_size);
+
+ return 0;
+}
+
static int btf_ptr_resolve(struct btf_verifier_env *env,
const struct resolve_vertex *v)
{
struct btf *btf = env->btf;
next_type = btf_type_by_id(btf, next_type_id);
- if (!next_type) {
+ if (!next_type || btf_type_is_resolve_source_only(next_type)) {
btf_verifier_log_type(env, v->t, "Invalid type_id");
return -EINVAL;
}
btf_type_ops(t)->seq_show(btf, t, type_id, data, bits_offset, m);
}
+static void btf_var_seq_show(const struct btf *btf, const struct btf_type *t,
+ u32 type_id, void *data, u8 bits_offset,
+ struct seq_file *m)
+{
+ t = btf_type_id_resolve(btf, &type_id);
+
+ btf_type_ops(t)->seq_show(btf, t, type_id, data, bits_offset, m);
+}
+
static void btf_ptr_seq_show(const struct btf *btf, const struct btf_type *t,
u32 type_id, void *data, u8 bits_offset,
struct seq_file *m)
/* Check array->index_type */
index_type_id = array->index_type;
index_type = btf_type_by_id(btf, index_type_id);
- if (btf_type_nosize_or_null(index_type)) {
+ if (btf_type_is_resolve_source_only(index_type) ||
+ btf_type_nosize_or_null(index_type)) {
btf_verifier_log_type(env, v->t, "Invalid index");
return -EINVAL;
}
/* Check array->type */
elem_type_id = array->type;
elem_type = btf_type_by_id(btf, elem_type_id);
- if (btf_type_nosize_or_null(elem_type)) {
+ if (btf_type_is_resolve_source_only(elem_type) ||
+ btf_type_nosize_or_null(elem_type)) {
btf_verifier_log_type(env, v->t,
"Invalid elem");
return -EINVAL;
const struct btf_type *member_type = btf_type_by_id(env->btf,
member_type_id);
- if (btf_type_nosize_or_null(member_type)) {
+ if (btf_type_is_resolve_source_only(member_type) ||
+ btf_type_nosize_or_null(member_type)) {
btf_verifier_log_member(env, v->t, member,
"Invalid member");
return -EINVAL;
.seq_show = btf_df_seq_show,
};
+static s32 btf_var_check_meta(struct btf_verifier_env *env,
+ const struct btf_type *t,
+ u32 meta_left)
+{
+ const struct btf_var *var;
+ u32 meta_needed = sizeof(*var);
+
+ if (meta_left < meta_needed) {
+ btf_verifier_log_basic(env, t,
+ "meta_left:%u meta_needed:%u",
+ meta_left, meta_needed);
+ return -EINVAL;
+ }
+
+ if (btf_type_vlen(t)) {
+ btf_verifier_log_type(env, t, "vlen != 0");
+ return -EINVAL;
+ }
+
+ if (btf_type_kflag(t)) {
+ btf_verifier_log_type(env, t, "Invalid btf_info kind_flag");
+ return -EINVAL;
+ }
+
+ if (!t->name_off ||
+ !__btf_name_valid(env->btf, t->name_off, true)) {
+ btf_verifier_log_type(env, t, "Invalid name");
+ return -EINVAL;
+ }
+
+ /* A var cannot be in type void */
+ if (!t->type || !BTF_TYPE_ID_VALID(t->type)) {
+ btf_verifier_log_type(env, t, "Invalid type_id");
+ return -EINVAL;
+ }
+
+ var = btf_type_var(t);
+ if (var->linkage != BTF_VAR_STATIC &&
+ var->linkage != BTF_VAR_GLOBAL_ALLOCATED) {
+ btf_verifier_log_type(env, t, "Linkage not supported");
+ return -EINVAL;
+ }
+
+ btf_verifier_log_type(env, t, NULL);
+
+ return meta_needed;
+}
+
+static void btf_var_log(struct btf_verifier_env *env, const struct btf_type *t)
+{
+ const struct btf_var *var = btf_type_var(t);
+
+ btf_verifier_log(env, "type_id=%u linkage=%u", t->type, var->linkage);
+}
+
+static const struct btf_kind_operations var_ops = {
+ .check_meta = btf_var_check_meta,
+ .resolve = btf_var_resolve,
+ .check_member = btf_df_check_member,
+ .check_kflag_member = btf_df_check_kflag_member,
+ .log_details = btf_var_log,
+ .seq_show = btf_var_seq_show,
+};
+
+static s32 btf_datasec_check_meta(struct btf_verifier_env *env,
+ const struct btf_type *t,
+ u32 meta_left)
+{
+ const struct btf_var_secinfo *vsi;
+ u64 last_vsi_end_off = 0, sum = 0;
+ u32 i, meta_needed;
+
+ meta_needed = btf_type_vlen(t) * sizeof(*vsi);
+ if (meta_left < meta_needed) {
+ btf_verifier_log_basic(env, t,
+ "meta_left:%u meta_needed:%u",
+ meta_left, meta_needed);
+ return -EINVAL;
+ }
+
+ if (!btf_type_vlen(t)) {
+ btf_verifier_log_type(env, t, "vlen == 0");
+ return -EINVAL;
+ }
+
+ if (!t->size) {
+ btf_verifier_log_type(env, t, "size == 0");
+ return -EINVAL;
+ }
+
+ if (btf_type_kflag(t)) {
+ btf_verifier_log_type(env, t, "Invalid btf_info kind_flag");
+ return -EINVAL;
+ }
+
+ if (!t->name_off ||
+ !btf_name_valid_section(env->btf, t->name_off)) {
+ btf_verifier_log_type(env, t, "Invalid name");
+ return -EINVAL;
+ }
+
+ btf_verifier_log_type(env, t, NULL);
+
+ for_each_vsi(i, t, vsi) {
+ /* A var cannot be in type void */
+ if (!vsi->type || !BTF_TYPE_ID_VALID(vsi->type)) {
+ btf_verifier_log_vsi(env, t, vsi,
+ "Invalid type_id");
+ return -EINVAL;
+ }
+
+ if (vsi->offset < last_vsi_end_off || vsi->offset >= t->size) {
+ btf_verifier_log_vsi(env, t, vsi,
+ "Invalid offset");
+ return -EINVAL;
+ }
+
+ if (!vsi->size || vsi->size > t->size) {
+ btf_verifier_log_vsi(env, t, vsi,
+ "Invalid size");
+ return -EINVAL;
+ }
+
+ last_vsi_end_off = vsi->offset + vsi->size;
+ if (last_vsi_end_off > t->size) {
+ btf_verifier_log_vsi(env, t, vsi,
+ "Invalid offset+size");
+ return -EINVAL;
+ }
+
+ btf_verifier_log_vsi(env, t, vsi, NULL);
+ sum += vsi->size;
+ }
+
+ if (t->size < sum) {
+ btf_verifier_log_type(env, t, "Invalid btf_info size");
+ return -EINVAL;
+ }
+
+ return meta_needed;
+}
+
+static int btf_datasec_resolve(struct btf_verifier_env *env,
+ const struct resolve_vertex *v)
+{
+ const struct btf_var_secinfo *vsi;
+ struct btf *btf = env->btf;
+ u16 i;
+
+ for_each_vsi_from(i, v->next_member, v->t, vsi) {
+ u32 var_type_id = vsi->type, type_id, type_size = 0;
+ const struct btf_type *var_type = btf_type_by_id(env->btf,
+ var_type_id);
+ if (!var_type || !btf_type_is_var(var_type)) {
+ btf_verifier_log_vsi(env, v->t, vsi,
+ "Not a VAR kind member");
+ return -EINVAL;
+ }
+
+ if (!env_type_is_resolve_sink(env, var_type) &&
+ !env_type_is_resolved(env, var_type_id)) {
+ env_stack_set_next_member(env, i + 1);
+ return env_stack_push(env, var_type, var_type_id);
+ }
+
+ type_id = var_type->type;
+ if (!btf_type_id_size(btf, &type_id, &type_size)) {
+ btf_verifier_log_vsi(env, v->t, vsi, "Invalid type");
+ return -EINVAL;
+ }
+
+ if (vsi->size < type_size) {
+ btf_verifier_log_vsi(env, v->t, vsi, "Invalid size");
+ return -EINVAL;
+ }
+ }
+
+ env_stack_pop_resolved(env, 0, 0);
+ return 0;
+}
+
+static void btf_datasec_log(struct btf_verifier_env *env,
+ const struct btf_type *t)
+{
+ btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t));
+}
+
+static void btf_datasec_seq_show(const struct btf *btf,
+ const struct btf_type *t, u32 type_id,
+ void *data, u8 bits_offset,
+ struct seq_file *m)
+{
+ const struct btf_var_secinfo *vsi;
+ const struct btf_type *var;
+ u32 i;
+
+ seq_printf(m, "section (\"%s\") = {", __btf_name_by_offset(btf, t->name_off));
+ for_each_vsi(i, t, vsi) {
+ var = btf_type_by_id(btf, vsi->type);
+ if (i)
+ seq_puts(m, ",");
+ btf_type_ops(var)->seq_show(btf, var, vsi->type,
+ data + vsi->offset, bits_offset, m);
+ }
+ seq_puts(m, "}");
+}
+
+static const struct btf_kind_operations datasec_ops = {
+ .check_meta = btf_datasec_check_meta,
+ .resolve = btf_datasec_resolve,
+ .check_member = btf_df_check_member,
+ .check_kflag_member = btf_df_check_kflag_member,
+ .log_details = btf_datasec_log,
+ .seq_show = btf_datasec_seq_show,
+};
+
static int btf_func_proto_check(struct btf_verifier_env *env,
const struct btf_type *t)
{
[BTF_KIND_RESTRICT] = &modifier_ops,
[BTF_KIND_FUNC] = &func_ops,
[BTF_KIND_FUNC_PROTO] = &func_proto_ops,
+ [BTF_KIND_VAR] = &var_ops,
+ [BTF_KIND_DATASEC] = &datasec_ops,
};
static s32 btf_check_meta(struct btf_verifier_env *env,
if (!env_type_is_resolved(env, type_id))
return false;
- if (btf_type_is_struct(t))
+ if (btf_type_is_struct(t) || btf_type_is_datasec(t))
return !btf->resolved_ids[type_id] &&
- !btf->resolved_sizes[type_id];
+ !btf->resolved_sizes[type_id];
- if (btf_type_is_modifier(t) || btf_type_is_ptr(t)) {
+ if (btf_type_is_modifier(t) || btf_type_is_ptr(t) ||
+ btf_type_is_var(t)) {
t = btf_type_id_resolve(btf, &type_id);
- return t && !btf_type_is_modifier(t);
+ return t &&
+ !btf_type_is_modifier(t) &&
+ !btf_type_is_var(t) &&
+ !btf_type_is_datasec(t);
}
if (btf_type_is_array(t)) {
dst[i] = fp->insnsi[i];
if (!was_ld_map &&
dst[i].code == (BPF_LD | BPF_IMM | BPF_DW) &&
- dst[i].src_reg == BPF_PSEUDO_MAP_FD) {
+ (dst[i].src_reg == BPF_PSEUDO_MAP_FD ||
+ dst[i].src_reg == BPF_PSEUDO_MAP_VALUE)) {
was_ld_map = true;
dst[i].imm = 0;
} else if (was_ld_map &&
u32 insn_adj_cnt, insn_rest, insn_delta = len - 1;
const u32 cnt_max = S16_MAX;
struct bpf_prog *prog_adj;
+ int err;
/* Since our patchlet doesn't expand the image, we're done. */
if (insn_delta == 0) {
* we afterwards may not fail anymore.
*/
if (insn_adj_cnt > cnt_max &&
- bpf_adj_branches(prog, off, off + 1, off + len, true))
- return NULL;
+ (err = bpf_adj_branches(prog, off, off + 1, off + len, true)))
+ return ERR_PTR(err);
/* Several new instructions need to be inserted. Make room
* for them. Likely, there's no need for a new allocation as
prog_adj = bpf_prog_realloc(prog, bpf_prog_size(insn_adj_cnt),
GFP_USER);
if (!prog_adj)
- return NULL;
+ return ERR_PTR(-ENOMEM);
prog_adj->len = insn_adj_cnt;
continue;
tmp = bpf_patch_insn_single(clone, i, insn_buff, rewritten);
- if (!tmp) {
+ if (IS_ERR(tmp)) {
/* Patching may have repointed aux->prog during
* realloc from the original one, so we need to
* fix it up here on error.
*/
bpf_jit_prog_release_other(prog, clone);
- return ERR_PTR(-ENOMEM);
+ return tmp;
}
clone = tmp;
static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu,
struct xdp_frame *xdpf)
{
+ unsigned int hard_start_headroom;
unsigned int frame_size;
void *pkt_data_start;
struct sk_buff *skb;
+ /* Part of headroom was reserved to xdpf */
+ hard_start_headroom = sizeof(struct xdp_frame) + xdpf->headroom;
+
/* build_skb need to place skb_shared_info after SKB end, and
* also want to know the memory "truesize". Thus, need to
* know the memory frame size backing xdp_buff.
* is not at a fixed memory location, with mixed length
* packets, which is bad for cache-line hotness.
*/
- frame_size = SKB_DATA_ALIGN(xdpf->len + xdpf->headroom) +
+ frame_size = SKB_DATA_ALIGN(xdpf->len + hard_start_headroom) +
SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
- pkt_data_start = xdpf->data - xdpf->headroom;
+ pkt_data_start = xdpf->data - hard_start_headroom;
skb = build_skb(pkt_data_start, frame_size);
if (!skb)
return NULL;
- skb_reserve(skb, xdpf->headroom);
+ skb_reserve(skb, hard_start_headroom);
__skb_put(skb, xdpf->len);
if (xdpf->metasize)
skb_metadata_set(skb, xdpf->metasize);
* - RX ring dev queue index (skb_record_rx_queue)
*/
+ /* Allow SKB to reuse area used by xdp_frame */
+ xdp_scrub_frame(xdpf);
+
return skb;
}
* part of the ldimm64 insn is accessible.
*/
u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm;
- bool map_ptr = insn->src_reg == BPF_PSEUDO_MAP_FD;
+ bool is_ptr = insn->src_reg == BPF_PSEUDO_MAP_FD ||
+ insn->src_reg == BPF_PSEUDO_MAP_VALUE;
char tmp[64];
- if (map_ptr && !allow_ptr_leaks)
+ if (is_ptr && !allow_ptr_leaks)
imm = 0;
verbose(cbs->private_data, "(%02x) r%d = %s\n",
#define HTAB_CREATE_FLAG_MASK \
(BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE | \
- BPF_F_RDONLY | BPF_F_WRONLY | BPF_F_ZERO_SEED)
+ BPF_F_ACCESS_MASK | BPF_F_ZERO_SEED)
struct bucket {
struct hlist_nulls_head head;
/* Guard against local DoS, and discourage production use. */
return -EPERM;
- if (attr->map_flags & ~HTAB_CREATE_FLAG_MASK)
- /* reserved bits should not be used */
+ if (attr->map_flags & ~HTAB_CREATE_FLAG_MASK ||
+ !bpf_map_flags_access_ok(attr->map_flags))
return -EINVAL;
if (!lru && percpu_lru)
}
EXPORT_SYMBOL(bpf_prog_get_type_path);
-static void bpf_evict_inode(struct inode *inode)
-{
- enum bpf_type type;
-
- truncate_inode_pages_final(&inode->i_data);
- clear_inode(inode);
-
- if (S_ISLNK(inode->i_mode))
- kfree(inode->i_link);
- if (!bpf_inode_type(inode, &type))
- bpf_any_put(inode->i_private, type);
-}
-
/*
* Display the mount options in /proc/mounts.
*/
return 0;
}
+static void bpf_destroy_inode_deferred(struct rcu_head *head)
+{
+ struct inode *inode = container_of(head, struct inode, i_rcu);
+ enum bpf_type type;
+
+ if (S_ISLNK(inode->i_mode))
+ kfree(inode->i_link);
+ if (!bpf_inode_type(inode, &type))
+ bpf_any_put(inode->i_private, type);
+ free_inode_nonrcu(inode);
+}
+
+static void bpf_destroy_inode(struct inode *inode)
+{
+ call_rcu(&inode->i_rcu, bpf_destroy_inode_deferred);
+}
+
static const struct super_operations bpf_super_ops = {
.statfs = simple_statfs,
.drop_inode = generic_delete_inode,
.show_options = bpf_show_options,
- .evict_inode = bpf_evict_inode,
+ .destroy_inode = bpf_destroy_inode,
};
enum {
#ifdef CONFIG_CGROUP_BPF
#define LOCAL_STORAGE_CREATE_FLAG_MASK \
- (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
+ (BPF_F_NUMA_NODE | BPF_F_ACCESS_MASK)
struct bpf_cgroup_storage_map {
struct bpf_map map;
if (attr->value_size > PAGE_SIZE)
return ERR_PTR(-E2BIG);
- if (attr->map_flags & ~LOCAL_STORAGE_CREATE_FLAG_MASK)
- /* reserved bits should not be used */
+ if (attr->map_flags & ~LOCAL_STORAGE_CREATE_FLAG_MASK ||
+ !bpf_map_flags_access_ok(attr->map_flags))
return ERR_PTR(-EINVAL);
if (attr->max_entries)
#define LPM_KEY_SIZE_MIN LPM_KEY_SIZE(LPM_DATA_SIZE_MIN)
#define LPM_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_NUMA_NODE | \
- BPF_F_RDONLY | BPF_F_WRONLY)
+ BPF_F_ACCESS_MASK)
static struct bpf_map *trie_alloc(union bpf_attr *attr)
{
if (attr->max_entries == 0 ||
!(attr->map_flags & BPF_F_NO_PREALLOC) ||
attr->map_flags & ~LPM_CREATE_FLAG_MASK ||
+ !bpf_map_flags_access_ok(attr->map_flags) ||
attr->key_size < LPM_KEY_SIZE_MIN ||
attr->key_size > LPM_KEY_SIZE_MAX ||
attr->value_size < LPM_VAL_SIZE_MIN ||
#include "percpu_freelist.h"
#define QUEUE_STACK_CREATE_FLAG_MASK \
- (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
-
+ (BPF_F_NUMA_NODE | BPF_F_ACCESS_MASK)
struct bpf_queue_stack {
struct bpf_map map;
/* check sanity of attributes */
if (attr->max_entries == 0 || attr->key_size != 0 ||
attr->value_size == 0 ||
- attr->map_flags & ~QUEUE_STACK_CREATE_FLAG_MASK)
+ attr->map_flags & ~QUEUE_STACK_CREATE_FLAG_MASK ||
+ !bpf_map_flags_access_ok(attr->map_flags))
return -EINVAL;
if (attr->value_size > KMALLOC_MAX_SIZE)
kvfree(area);
}
+static u32 bpf_map_flags_retain_permanent(u32 flags)
+{
+ /* Some map creation flags are not tied to the map object but
+ * rather to the map fd instead, so they have no meaning upon
+ * map object inspection since multiple file descriptors with
+ * different (access) properties can exist here. Thus, given
+ * this has zero meaning for the map itself, lets clear these
+ * from here.
+ */
+ return flags & ~(BPF_F_RDONLY | BPF_F_WRONLY);
+}
+
void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr)
{
map->map_type = attr->map_type;
map->key_size = attr->key_size;
map->value_size = attr->value_size;
map->max_entries = attr->max_entries;
- map->map_flags = attr->map_flags;
+ map->map_flags = bpf_map_flags_retain_permanent(attr->map_flags);
map->numa_node = bpf_map_attr_numa_node(attr);
}
return 0;
}
+static fmode_t map_get_sys_perms(struct bpf_map *map, struct fd f)
+{
+ fmode_t mode = f.file->f_mode;
+
+ /* Our file permissions may have been overridden by global
+ * map permissions facing syscall side.
+ */
+ if (READ_ONCE(map->frozen))
+ mode &= ~FMODE_CAN_WRITE;
+ return mode;
+}
+
#ifdef CONFIG_PROC_FS
static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
{
"max_entries:\t%u\n"
"map_flags:\t%#x\n"
"memlock:\t%llu\n"
- "map_id:\t%u\n",
+ "map_id:\t%u\n"
+ "frozen:\t%u\n",
map->map_type,
map->key_size,
map->value_size,
map->max_entries,
map->map_flags,
map->pages * 1ULL << PAGE_SHIFT,
- map->id);
+ map->id,
+ READ_ONCE(map->frozen));
if (owner_prog_type) {
seq_printf(m, "owner_prog_type:\t%u\n",
const char *end = src + BPF_OBJ_NAME_LEN;
memset(dst, 0, BPF_OBJ_NAME_LEN);
-
- /* Copy all isalnum() and '_' char */
+ /* Copy all isalnum(), '_' and '.' chars. */
while (src < end && *src) {
- if (!isalnum(*src) && *src != '_')
+ if (!isalnum(*src) &&
+ *src != '_' && *src != '.')
return -EINVAL;
*dst++ = *src++;
}
u32 key_size, value_size;
int ret = 0;
- key_type = btf_type_id_size(btf, &btf_key_id, &key_size);
- if (!key_type || key_size != map->key_size)
- return -EINVAL;
+ /* Some maps allow key to be unspecified. */
+ if (btf_key_id) {
+ key_type = btf_type_id_size(btf, &btf_key_id, &key_size);
+ if (!key_type || key_size != map->key_size)
+ return -EINVAL;
+ } else {
+ key_type = btf_type_by_id(btf, 0);
+ if (!map->ops->map_check_btf)
+ return -EINVAL;
+ }
value_type = btf_type_id_size(btf, &btf_value_id, &value_size);
if (!value_type || value_size != map->value_size)
map->spin_lock_off = btf_find_spin_lock(btf, value_type);
if (map_value_has_spin_lock(map)) {
+ if (map->map_flags & BPF_F_RDONLY_PROG)
+ return -EACCES;
if (map->map_type != BPF_MAP_TYPE_HASH &&
map->map_type != BPF_MAP_TYPE_ARRAY &&
map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE)
if (attr->btf_key_type_id || attr->btf_value_type_id) {
struct btf *btf;
- if (!attr->btf_key_type_id || !attr->btf_value_type_id) {
+ if (!attr->btf_value_type_id) {
err = -EINVAL;
goto free_map_nouncharge;
}
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
-
- if (!(f.file->f_mode & FMODE_CAN_READ)) {
+ if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ)) {
err = -EPERM;
goto err_put;
}
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
-
- if (!(f.file->f_mode & FMODE_CAN_WRITE)) {
+ if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
err = -EPERM;
goto err_put;
}
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
-
- if (!(f.file->f_mode & FMODE_CAN_WRITE)) {
+ if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
err = -EPERM;
goto err_put;
}
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
-
- if (!(f.file->f_mode & FMODE_CAN_READ)) {
+ if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ)) {
err = -EPERM;
goto err_put;
}
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
-
- if (!(f.file->f_mode & FMODE_CAN_WRITE)) {
+ if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
err = -EPERM;
goto err_put;
}
return err;
}
+#define BPF_MAP_FREEZE_LAST_FIELD map_fd
+
+static int map_freeze(const union bpf_attr *attr)
+{
+ int err = 0, ufd = attr->map_fd;
+ struct bpf_map *map;
+ struct fd f;
+
+ if (CHECK_ATTR(BPF_MAP_FREEZE))
+ return -EINVAL;
+
+ f = fdget(ufd);
+ map = __bpf_map_get(f);
+ if (IS_ERR(map))
+ return PTR_ERR(map);
+ if (READ_ONCE(map->frozen)) {
+ err = -EBUSY;
+ goto err_put;
+ }
+ if (!capable(CAP_SYS_ADMIN)) {
+ err = -EPERM;
+ goto err_put;
+ }
+
+ WRITE_ONCE(map->frozen, true);
+err_put:
+ fdput(f);
+ return err;
+}
+
static const struct bpf_prog_ops * const bpf_prog_types[] = {
#define BPF_PROG_TYPE(_id, _name) \
[_id] = & _name ## _prog_ops,
/* eBPF programs must be GPL compatible to use GPL-ed functions */
is_gpl = license_is_gpl_compatible(license);
- if (attr->insn_cnt == 0 || attr->insn_cnt > BPF_MAXINSNS)
+ if (attr->insn_cnt == 0 ||
+ attr->insn_cnt > (capable(CAP_SYS_ADMIN) ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS))
return -E2BIG;
if (type != BPF_PROG_TYPE_SOCKET_FILTER &&
type != BPF_PROG_TYPE_CGROUP_SKB &&
return cgroup_bpf_prog_query(attr, uattr);
}
-#define BPF_PROG_TEST_RUN_LAST_FIELD test.duration
+#define BPF_PROG_TEST_RUN_LAST_FIELD test.ctx_out
static int bpf_prog_test_run(const union bpf_attr *attr,
union bpf_attr __user *uattr)
if (CHECK_ATTR(BPF_PROG_TEST_RUN))
return -EINVAL;
+ if ((attr->test.ctx_size_in && !attr->test.ctx_in) ||
+ (!attr->test.ctx_size_in && attr->test.ctx_in))
+ return -EINVAL;
+
+ if ((attr->test.ctx_size_out && !attr->test.ctx_out) ||
+ (!attr->test.ctx_size_out && attr->test.ctx_out))
+ return -EINVAL;
+
prog = bpf_prog_get(attr->test.prog_fd);
if (IS_ERR(prog))
return PTR_ERR(prog);
}
static const struct bpf_map *bpf_map_from_imm(const struct bpf_prog *prog,
- unsigned long addr)
+ unsigned long addr, u32 *off,
+ u32 *type)
{
+ const struct bpf_map *map;
int i;
- for (i = 0; i < prog->aux->used_map_cnt; i++)
- if (prog->aux->used_maps[i] == (void *)addr)
- return prog->aux->used_maps[i];
+ for (i = 0, *off = 0; i < prog->aux->used_map_cnt; i++) {
+ map = prog->aux->used_maps[i];
+ if (map == (void *)addr) {
+ *type = BPF_PSEUDO_MAP_FD;
+ return map;
+ }
+ if (!map->ops->map_direct_value_meta)
+ continue;
+ if (!map->ops->map_direct_value_meta(map, addr, off)) {
+ *type = BPF_PSEUDO_MAP_VALUE;
+ return map;
+ }
+ }
+
return NULL;
}
{
const struct bpf_map *map;
struct bpf_insn *insns;
+ u32 off, type;
u64 imm;
int i;
continue;
imm = ((u64)insns[i + 1].imm << 32) | (u32)insns[i].imm;
- map = bpf_map_from_imm(prog, imm);
+ map = bpf_map_from_imm(prog, imm, &off, &type);
if (map) {
- insns[i].src_reg = BPF_PSEUDO_MAP_FD;
+ insns[i].src_reg = type;
insns[i].imm = map->id;
- insns[i + 1].imm = 0;
+ insns[i + 1].imm = off;
continue;
}
}
case BPF_MAP_GET_NEXT_KEY:
err = map_get_next_key(&attr);
break;
+ case BPF_MAP_FREEZE:
+ err = map_freeze(&attr);
+ break;
case BPF_PROG_LOAD:
err = bpf_prog_load(&attr, uattr);
break;
struct bpf_verifier_stack_elem *next;
};
-#define BPF_COMPLEXITY_LIMIT_INSNS 131072
#define BPF_COMPLEXITY_LIMIT_STACK 1024
#define BPF_COMPLEXITY_LIMIT_STATES 64
*/
subprog[env->subprog_cnt].start = insn_cnt;
- if (env->log.level > 1)
+ if (env->log.level & BPF_LOG_LEVEL2)
for (i = 0; i < env->subprog_cnt; i++)
verbose(env, "func#%d @%d\n", i, subprog[i].start);
struct bpf_reg_state *parent)
{
bool writes = parent == state->parent; /* Observe write marks */
+ int cnt = 0;
while (parent) {
/* if read wasn't screened by an earlier write ... */
parent->var_off.value, parent->off);
return -EFAULT;
}
+ if (parent->live & REG_LIVE_READ)
+ /* The parentage chain never changes and
+ * this parent was already marked as LIVE_READ.
+ * There is no need to keep walking the chain again and
+ * keep re-marking all parents as LIVE_READ.
+ * This case happens when the same register is read
+ * multiple times without writes into it in-between.
+ */
+ break;
/* ... then we depend on parent's value */
parent->live |= REG_LIVE_READ;
state = parent;
parent = state->parent;
writes = true;
+ cnt++;
}
+
+ if (env->longest_mark_read_walk < cnt)
+ env->longest_mark_read_walk = cnt;
return 0;
}
char tn_buf[48];
tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
- verbose(env, "variable stack access var_off=%s off=%d size=%d",
+ verbose(env, "variable stack access var_off=%s off=%d size=%d\n",
tn_buf, off, size);
return -EACCES;
}
return 0;
}
+static int check_map_access_type(struct bpf_verifier_env *env, u32 regno,
+ int off, int size, enum bpf_access_type type)
+{
+ struct bpf_reg_state *regs = cur_regs(env);
+ struct bpf_map *map = regs[regno].map_ptr;
+ u32 cap = bpf_map_flags_to_cap(map);
+
+ if (type == BPF_WRITE && !(cap & BPF_MAP_CAN_WRITE)) {
+ verbose(env, "write into map forbidden, value_size=%d off=%d size=%d\n",
+ map->value_size, off, size);
+ return -EACCES;
+ }
+
+ if (type == BPF_READ && !(cap & BPF_MAP_CAN_READ)) {
+ verbose(env, "read from map forbidden, value_size=%d off=%d size=%d\n",
+ map->value_size, off, size);
+ return -EACCES;
+ }
+
+ return 0;
+}
+
/* check read/write into map element returned by bpf_map_lookup_elem() */
static int __check_map_access(struct bpf_verifier_env *env, u32 regno, int off,
int size, bool zero_size_allowed)
* need to try adding each of min_value and max_value to off
* to make sure our theoretical access will be safe.
*/
- if (env->log.level)
+ if (env->log.level & BPF_LOG_LEVEL)
print_verifier_state(env, state);
/* The minimum value is only important with signed
}
frame++;
if (frame >= MAX_CALL_FRAMES) {
- WARN_ONCE(1, "verifier bug. Call stack is too deep\n");
- return -EFAULT;
+ verbose(env, "the call stack of %d frames is too deep !\n",
+ frame);
+ return -E2BIG;
}
goto process_func;
}
verbose(env, "R%d leaks addr into map\n", value_regno);
return -EACCES;
}
-
+ err = check_map_access_type(env, regno, off, size, t);
+ if (err)
+ return err;
err = check_map_access(env, regno, off, size, false);
if (!err && t == BPF_READ && value_regno >= 0)
mark_reg_unknown(env, regs, value_regno);
BPF_SIZE(insn->code), BPF_WRITE, -1, true);
}
+static int __check_stack_boundary(struct bpf_verifier_env *env, u32 regno,
+ int off, int access_size,
+ bool zero_size_allowed)
+{
+ struct bpf_reg_state *reg = reg_state(env, regno);
+
+ if (off >= 0 || off < -MAX_BPF_STACK || off + access_size > 0 ||
+ access_size < 0 || (access_size == 0 && !zero_size_allowed)) {
+ if (tnum_is_const(reg->var_off)) {
+ verbose(env, "invalid stack type R%d off=%d access_size=%d\n",
+ regno, off, access_size);
+ } else {
+ char tn_buf[48];
+
+ tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
+ verbose(env, "invalid stack type R%d var_off=%s access_size=%d\n",
+ regno, tn_buf, access_size);
+ }
+ return -EACCES;
+ }
+ return 0;
+}
+
/* when register 'regno' is passed into function that will read 'access_size'
* bytes from that pointer, make sure that it's within stack boundary
* and all elements of stack are initialized.
{
struct bpf_reg_state *reg = reg_state(env, regno);
struct bpf_func_state *state = func(env, reg);
- int off, i, slot, spi;
+ int err, min_off, max_off, i, slot, spi;
if (reg->type != PTR_TO_STACK) {
/* Allow zero-byte read from NULL, regardless of pointer type */
return -EACCES;
}
- /* Only allow fixed-offset stack reads */
- if (!tnum_is_const(reg->var_off)) {
- char tn_buf[48];
+ if (tnum_is_const(reg->var_off)) {
+ min_off = max_off = reg->var_off.value + reg->off;
+ err = __check_stack_boundary(env, regno, min_off, access_size,
+ zero_size_allowed);
+ if (err)
+ return err;
+ } else {
+ /* Variable offset is prohibited for unprivileged mode for
+ * simplicity since it requires corresponding support in
+ * Spectre masking for stack ALU.
+ * See also retrieve_ptr_limit().
+ */
+ if (!env->allow_ptr_leaks) {
+ char tn_buf[48];
- tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
- verbose(env, "invalid variable stack read R%d var_off=%s\n",
- regno, tn_buf);
- return -EACCES;
- }
- off = reg->off + reg->var_off.value;
- if (off >= 0 || off < -MAX_BPF_STACK || off + access_size > 0 ||
- access_size < 0 || (access_size == 0 && !zero_size_allowed)) {
- verbose(env, "invalid stack type R%d off=%d access_size=%d\n",
- regno, off, access_size);
- return -EACCES;
+ tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
+ verbose(env, "R%d indirect variable offset stack access prohibited for !root, var_off=%s\n",
+ regno, tn_buf);
+ return -EACCES;
+ }
+ /* Only initialized buffer on stack is allowed to be accessed
+ * with variable offset. With uninitialized buffer it's hard to
+ * guarantee that whole memory is marked as initialized on
+ * helper return since specific bounds are unknown what may
+ * cause uninitialized stack leaking.
+ */
+ if (meta && meta->raw_mode)
+ meta = NULL;
+
+ if (reg->smax_value >= BPF_MAX_VAR_OFF ||
+ reg->smax_value <= -BPF_MAX_VAR_OFF) {
+ verbose(env, "R%d unbounded indirect variable offset stack access\n",
+ regno);
+ return -EACCES;
+ }
+ min_off = reg->smin_value + reg->off;
+ max_off = reg->smax_value + reg->off;
+ err = __check_stack_boundary(env, regno, min_off, access_size,
+ zero_size_allowed);
+ if (err) {
+ verbose(env, "R%d min value is outside of stack bound\n",
+ regno);
+ return err;
+ }
+ err = __check_stack_boundary(env, regno, max_off, access_size,
+ zero_size_allowed);
+ if (err) {
+ verbose(env, "R%d max value is outside of stack bound\n",
+ regno);
+ return err;
+ }
}
if (meta && meta->raw_mode) {
return 0;
}
- for (i = 0; i < access_size; i++) {
+ for (i = min_off; i < max_off + access_size; i++) {
u8 *stype;
- slot = -(off + i) - 1;
+ slot = -i - 1;
spi = slot / BPF_REG_SIZE;
if (state->allocated_stack <= slot)
goto err;
goto mark;
}
err:
- verbose(env, "invalid indirect read from stack off %d+%d size %d\n",
- off, i, access_size);
+ if (tnum_is_const(reg->var_off)) {
+ verbose(env, "invalid indirect read from stack off %d+%d size %d\n",
+ min_off, i - min_off, access_size);
+ } else {
+ char tn_buf[48];
+
+ tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
+ verbose(env, "invalid indirect read from stack var_off %s+%d size %d\n",
+ tn_buf, i - min_off, access_size);
+ }
return -EACCES;
mark:
/* reading any byte out of 8-byte 'spill_slot' will cause
mark_reg_read(env, &state->stack[spi].spilled_ptr,
state->stack[spi].spilled_ptr.parent);
}
- return update_stack_depth(env, state, off);
+ return update_stack_depth(env, state, min_off);
}
static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
return check_packet_access(env, regno, reg->off, access_size,
zero_size_allowed);
case PTR_TO_MAP_VALUE:
+ if (check_map_access_type(env, regno, reg->off, access_size,
+ meta && meta->raw_mode ? BPF_WRITE :
+ BPF_READ))
+ return -EACCES;
return check_map_access(env, regno, reg->off, access_size,
zero_size_allowed);
default: /* scalar_value|ptr_to_stack or invalid ptr */
/* and go analyze first insn of the callee */
*insn_idx = target_insn;
- if (env->log.level) {
+ if (env->log.level & BPF_LOG_LEVEL) {
verbose(env, "caller:\n");
print_verifier_state(env, caller);
verbose(env, "callee:\n");
return err;
*insn_idx = callee->callsite + 1;
- if (env->log.level) {
+ if (env->log.level & BPF_LOG_LEVEL) {
verbose(env, "returning from callee:\n");
print_verifier_state(env, callee);
verbose(env, "to caller at %d:\n", *insn_idx);
int func_id, int insn_idx)
{
struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx];
+ struct bpf_map *map = meta->map_ptr;
if (func_id != BPF_FUNC_tail_call &&
func_id != BPF_FUNC_map_lookup_elem &&
func_id != BPF_FUNC_map_peek_elem)
return 0;
- if (meta->map_ptr == NULL) {
+ if (map == NULL) {
verbose(env, "kernel subsystem misconfigured verifier\n");
return -EINVAL;
}
+ /* In case of read-only, some additional restrictions
+ * need to be applied in order to prevent altering the
+ * state of the map from program side.
+ */
+ if ((map->map_flags & BPF_F_RDONLY_PROG) &&
+ (func_id == BPF_FUNC_map_delete_elem ||
+ func_id == BPF_FUNC_map_update_elem ||
+ func_id == BPF_FUNC_map_push_elem ||
+ func_id == BPF_FUNC_map_pop_elem)) {
+ verbose(env, "write into map forbidden\n");
+ return -EACCES;
+ }
+
if (!BPF_MAP_PTR(aux->map_state))
bpf_map_ptr_store(aux, meta->map_ptr,
meta->map_ptr->unpriv_array);
switch (ptr_reg->type) {
case PTR_TO_STACK:
+ /* Indirect variable offset stack access is prohibited in
+ * unprivileged mode so it's not handled here.
+ */
off = ptr_reg->off + ptr_reg->var_off.value;
if (mask_to_left)
*ptr_limit = MAX_BPF_STACK + off;
insn->dst_reg);
return -EACCES;
}
- if (env->log.level)
+ if (env->log.level & BPF_LOG_LEVEL)
print_verifier_state(env, this_branch->frame[this_branch->curframe]);
return 0;
}
-/* return the map pointer stored inside BPF_LD_IMM64 instruction */
-static struct bpf_map *ld_imm64_to_map_ptr(struct bpf_insn *insn)
-{
- u64 imm64 = ((u64) (u32) insn[0].imm) | ((u64) (u32) insn[1].imm) << 32;
-
- return (struct bpf_map *) (unsigned long) imm64;
-}
-
/* verify BPF_LD_IMM64 instruction */
static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn)
{
+ struct bpf_insn_aux_data *aux = cur_aux(env);
struct bpf_reg_state *regs = cur_regs(env);
+ struct bpf_map *map;
int err;
if (BPF_SIZE(insn->code) != BPF_DW) {
return 0;
}
- /* replace_map_fd_with_map_ptr() should have caught bad ld_imm64 */
- BUG_ON(insn->src_reg != BPF_PSEUDO_MAP_FD);
+ map = env->used_maps[aux->map_index];
+ mark_reg_known_zero(env, regs, insn->dst_reg);
+ regs[insn->dst_reg].map_ptr = map;
+
+ if (insn->src_reg == BPF_PSEUDO_MAP_VALUE) {
+ regs[insn->dst_reg].type = PTR_TO_MAP_VALUE;
+ regs[insn->dst_reg].off = aux->map_off;
+ if (map_value_has_spin_lock(map))
+ regs[insn->dst_reg].id = ++env->id_gen;
+ } else if (insn->src_reg == BPF_PSEUDO_MAP_FD) {
+ regs[insn->dst_reg].type = CONST_PTR_TO_MAP;
+ } else {
+ verbose(env, "bpf verifier is misconfigured\n");
+ return -EINVAL;
+ }
- regs[insn->dst_reg].type = CONST_PTR_TO_MAP;
- regs[insn->dst_reg].map_ptr = ld_imm64_to_map_ptr(insn);
return 0;
}
int ret = 0;
int i, t;
- insn_state = kcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
+ insn_state = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
if (!insn_state)
return -ENOMEM;
- insn_stack = kcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
+ insn_stack = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
if (!insn_stack) {
- kfree(insn_state);
+ kvfree(insn_state);
return -ENOMEM;
}
ret = 0; /* cfg looks good */
err_free:
- kfree(insn_state);
- kfree(insn_stack);
+ kvfree(insn_state);
+ kvfree(insn_stack);
return ret;
}
static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
{
struct bpf_verifier_state_list *new_sl;
- struct bpf_verifier_state_list *sl;
+ struct bpf_verifier_state_list *sl, **pprev;
struct bpf_verifier_state *cur = env->cur_state, *new;
int i, j, err, states_cnt = 0;
- sl = env->explored_states[insn_idx];
+ pprev = &env->explored_states[insn_idx];
+ sl = *pprev;
+
if (!sl)
/* this 'insn_idx' instruction wasn't marked, so we will not
* be doing state search here
while (sl != STATE_LIST_MARK) {
if (states_equal(env, &sl->state, cur)) {
+ sl->hit_cnt++;
/* reached equivalent register/stack state,
* prune the search.
* Registers read by the continuation are read by us.
return err;
return 1;
}
- sl = sl->next;
states_cnt++;
+ sl->miss_cnt++;
+ /* heuristic to determine whether this state is beneficial
+ * to keep checking from state equivalence point of view.
+ * Higher numbers increase max_states_per_insn and verification time,
+ * but do not meaningfully decrease insn_processed.
+ */
+ if (sl->miss_cnt > sl->hit_cnt * 3 + 3) {
+ /* the state is unlikely to be useful. Remove it to
+ * speed up verification
+ */
+ *pprev = sl->next;
+ if (sl->state.frame[0]->regs[0].live & REG_LIVE_DONE) {
+ free_verifier_state(&sl->state, false);
+ kfree(sl);
+ env->peak_states--;
+ } else {
+ /* cannot free this state, since parentage chain may
+ * walk it later. Add it for free_list instead to
+ * be freed at the end of verification
+ */
+ sl->next = env->free_list;
+ env->free_list = sl;
+ }
+ sl = *pprev;
+ continue;
+ }
+ pprev = &sl->next;
+ sl = *pprev;
}
+ if (env->max_states_per_insn < states_cnt)
+ env->max_states_per_insn = states_cnt;
+
if (!env->allow_ptr_leaks && states_cnt > BPF_COMPLEXITY_LIMIT_STATES)
return 0;
new_sl = kzalloc(sizeof(struct bpf_verifier_state_list), GFP_KERNEL);
if (!new_sl)
return -ENOMEM;
+ env->total_states++;
+ env->peak_states++;
/* add new state to the head of linked list */
new = &new_sl->state;
struct bpf_verifier_state *state;
struct bpf_insn *insns = env->prog->insnsi;
struct bpf_reg_state *regs;
- int insn_cnt = env->prog->len, i;
- int insn_processed = 0;
+ int insn_cnt = env->prog->len;
bool do_print_state = false;
env->prev_linfo = NULL;
insn = &insns[env->insn_idx];
class = BPF_CLASS(insn->code);
- if (++insn_processed > BPF_COMPLEXITY_LIMIT_INSNS) {
+ if (++env->insn_processed > BPF_COMPLEXITY_LIMIT_INSNS) {
verbose(env,
"BPF program is too large. Processed %d insn\n",
- insn_processed);
+ env->insn_processed);
return -E2BIG;
}
return err;
if (err == 1) {
/* found equivalent state, can prune the search */
- if (env->log.level) {
+ if (env->log.level & BPF_LOG_LEVEL) {
if (do_print_state)
verbose(env, "\nfrom %d to %d%s: safe\n",
env->prev_insn_idx, env->insn_idx,
if (need_resched())
cond_resched();
- if (env->log.level > 1 || (env->log.level && do_print_state)) {
- if (env->log.level > 1)
+ if (env->log.level & BPF_LOG_LEVEL2 ||
+ (env->log.level & BPF_LOG_LEVEL && do_print_state)) {
+ if (env->log.level & BPF_LOG_LEVEL2)
verbose(env, "%d:", env->insn_idx);
else
verbose(env, "\nfrom %d to %d%s:",
do_print_state = false;
}
- if (env->log.level) {
+ if (env->log.level & BPF_LOG_LEVEL) {
const struct bpf_insn_cbs cbs = {
.cb_print = verbose,
.private_data = env,
env->insn_idx++;
}
- verbose(env, "processed %d insns (limit %d), stack depth ",
- insn_processed, BPF_COMPLEXITY_LIMIT_INSNS);
- for (i = 0; i < env->subprog_cnt; i++) {
- u32 depth = env->subprog_info[i].stack_depth;
-
- verbose(env, "%d", depth);
- if (i + 1 < env->subprog_cnt)
- verbose(env, "+");
- }
- verbose(env, "\n");
env->prog->aux->stack_depth = env->subprog_info[0].stack_depth;
return 0;
}
}
if (insn[0].code == (BPF_LD | BPF_IMM | BPF_DW)) {
+ struct bpf_insn_aux_data *aux;
struct bpf_map *map;
struct fd f;
+ u64 addr;
if (i == insn_cnt - 1 || insn[1].code != 0 ||
insn[1].dst_reg != 0 || insn[1].src_reg != 0 ||
return -EINVAL;
}
- if (insn->src_reg == 0)
+ if (insn[0].src_reg == 0)
/* valid generic load 64-bit imm */
goto next_insn;
- if (insn[0].src_reg != BPF_PSEUDO_MAP_FD ||
- insn[1].imm != 0) {
- verbose(env, "unrecognized bpf_ld_imm64 insn\n");
+ /* In final convert_pseudo_ld_imm64() step, this is
+ * converted into regular 64-bit imm load insn.
+ */
+ if ((insn[0].src_reg != BPF_PSEUDO_MAP_FD &&
+ insn[0].src_reg != BPF_PSEUDO_MAP_VALUE) ||
+ (insn[0].src_reg == BPF_PSEUDO_MAP_FD &&
+ insn[1].imm != 0)) {
+ verbose(env,
+ "unrecognized bpf_ld_imm64 insn\n");
return -EINVAL;
}
return err;
}
- /* store map pointer inside BPF_LD_IMM64 instruction */
- insn[0].imm = (u32) (unsigned long) map;
- insn[1].imm = ((u64) (unsigned long) map) >> 32;
+ aux = &env->insn_aux_data[i];
+ if (insn->src_reg == BPF_PSEUDO_MAP_FD) {
+ addr = (unsigned long)map;
+ } else {
+ u32 off = insn[1].imm;
+
+ if (off >= BPF_MAX_VAR_OFF) {
+ verbose(env, "direct value offset of %u is not allowed\n", off);
+ fdput(f);
+ return -EINVAL;
+ }
+
+ if (!map->ops->map_direct_value_addr) {
+ verbose(env, "no direct value access support for this map type\n");
+ fdput(f);
+ return -EINVAL;
+ }
+
+ err = map->ops->map_direct_value_addr(map, &addr, off);
+ if (err) {
+ verbose(env, "invalid access to map value pointer, value_size=%u off=%u\n",
+ map->value_size, off);
+ fdput(f);
+ return err;
+ }
+
+ aux->map_off = off;
+ addr += off;
+ }
+
+ insn[0].imm = (u32)addr;
+ insn[1].imm = addr >> 32;
/* check whether we recorded this map already */
- for (j = 0; j < env->used_map_cnt; j++)
+ for (j = 0; j < env->used_map_cnt; j++) {
if (env->used_maps[j] == map) {
+ aux->map_index = j;
fdput(f);
goto next_insn;
}
+ }
if (env->used_map_cnt >= MAX_USED_MAPS) {
fdput(f);
fdput(f);
return PTR_ERR(map);
}
+
+ aux->map_index = env->used_map_cnt;
env->used_maps[env->used_map_cnt++] = map;
if (bpf_map_is_cgroup_storage(map) &&
struct bpf_prog *new_prog;
new_prog = bpf_patch_insn_single(env->prog, off, patch, len);
- if (!new_prog)
+ if (IS_ERR(new_prog)) {
+ if (PTR_ERR(new_prog) == -ERANGE)
+ verbose(env,
+ "insn %d cannot be patched due to 16-bit range\n",
+ env->insn_aux_data[off].orig_idx);
return NULL;
+ }
if (adjust_insn_aux_data(env, new_prog->len, off, len))
return NULL;
adjust_subprog_starts(env, off, len);
struct bpf_verifier_state_list *sl, *sln;
int i;
+ sl = env->free_list;
+ while (sl) {
+ sln = sl->next;
+ free_verifier_state(&sl->state, false);
+ kfree(sl);
+ sl = sln;
+ }
+
if (!env->explored_states)
return;
}
}
- kfree(env->explored_states);
+ kvfree(env->explored_states);
+}
+
+static void print_verification_stats(struct bpf_verifier_env *env)
+{
+ int i;
+
+ if (env->log.level & BPF_LOG_STATS) {
+ verbose(env, "verification time %lld usec\n",
+ div_u64(env->verification_time, 1000));
+ verbose(env, "stack depth ");
+ for (i = 0; i < env->subprog_cnt; i++) {
+ u32 depth = env->subprog_info[i].stack_depth;
+
+ verbose(env, "%d", depth);
+ if (i + 1 < env->subprog_cnt)
+ verbose(env, "+");
+ }
+ verbose(env, "\n");
+ }
+ verbose(env, "processed %d insns (limit %d) max_states_per_insn %d "
+ "total_states %d peak_states %d mark_read %d\n",
+ env->insn_processed, BPF_COMPLEXITY_LIMIT_INSNS,
+ env->max_states_per_insn, env->total_states,
+ env->peak_states, env->longest_mark_read_walk);
}
int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
union bpf_attr __user *uattr)
{
+ u64 start_time = ktime_get_ns();
struct bpf_verifier_env *env;
struct bpf_verifier_log *log;
int i, len, ret = -EINVAL;
ret = -EINVAL;
/* log attributes have to be sane */
- if (log->len_total < 128 || log->len_total > UINT_MAX >> 8 ||
- !log->level || !log->ubuf)
+ if (log->len_total < 128 || log->len_total > UINT_MAX >> 2 ||
+ !log->level || !log->ubuf || log->level & ~BPF_LOG_MASK)
goto err_unlock;
}
goto skip_full_check;
}
- env->explored_states = kcalloc(env->prog->len,
+ env->explored_states = kvcalloc(env->prog->len,
sizeof(struct bpf_verifier_state_list *),
GFP_USER);
ret = -ENOMEM;
if (ret == 0)
ret = fixup_call_args(env);
+ env->verification_time = ktime_get_ns() - start_time;
+ print_verification_stats(env);
+
if (log->level && bpf_verifier_log_full(log))
ret = -ENOSPC;
if (log->level && !log->ubuf) {
cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL);
}
+static inline bool can_rollback_cpu(struct cpuhp_cpu_state *st)
+{
+ if (IS_ENABLED(CONFIG_HOTPLUG_CPU))
+ return true;
+ /*
+ * When CPU hotplug is disabled, then taking the CPU down is not
+ * possible because takedown_cpu() and the architecture and
+ * subsystem specific mechanisms are not available. So the CPU
+ * which would be completely unplugged again needs to stay around
+ * in the current state.
+ */
+ return st->state <= CPUHP_BRINGUP_CPU;
+}
+
static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st,
enum cpuhp_state target)
{
st->state++;
ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL);
if (ret) {
- st->target = prev_state;
- undo_cpu_up(cpu, st);
+ if (can_rollback_cpu(st)) {
+ st->target = prev_state;
+ undo_cpu_up(cpu, st);
+ }
break;
}
}
#ifdef CONFIG_STACKTRACE
entry->stacktrace.max_entries = DMA_DEBUG_STACKTRACE_ENTRIES;
entry->stacktrace.entries = entry->st_entries;
- entry->stacktrace.skip = 2;
+ entry->stacktrace.skip = 1;
save_stack_trace(&entry->stacktrace);
#endif
event->pmu->del(event, 0);
event->oncpu = -1;
- if (event->pending_disable) {
- event->pending_disable = 0;
+ if (READ_ONCE(event->pending_disable) >= 0) {
+ WRITE_ONCE(event->pending_disable, -1);
state = PERF_EVENT_STATE_OFF;
}
perf_event_set_state(event, state);
void perf_event_disable_inatomic(struct perf_event *event)
{
- event->pending_disable = 1;
+ WRITE_ONCE(event->pending_disable, smp_processor_id());
+ /* can fail, see perf_pending_event_disable() */
irq_work_queue(&event->pending);
}
}
}
+static void perf_pending_event_disable(struct perf_event *event)
+{
+ int cpu = READ_ONCE(event->pending_disable);
+
+ if (cpu < 0)
+ return;
+
+ if (cpu == smp_processor_id()) {
+ WRITE_ONCE(event->pending_disable, -1);
+ perf_event_disable_local(event);
+ return;
+ }
+
+ /*
+ * CPU-A CPU-B
+ *
+ * perf_event_disable_inatomic()
+ * @pending_disable = CPU-A;
+ * irq_work_queue();
+ *
+ * sched-out
+ * @pending_disable = -1;
+ *
+ * sched-in
+ * perf_event_disable_inatomic()
+ * @pending_disable = CPU-B;
+ * irq_work_queue(); // FAILS
+ *
+ * irq_work_run()
+ * perf_pending_event()
+ *
+ * But the event runs on CPU-B and wants disabling there.
+ */
+ irq_work_queue_on(&event->pending, cpu);
+}
+
static void perf_pending_event(struct irq_work *entry)
{
- struct perf_event *event = container_of(entry,
- struct perf_event, pending);
+ struct perf_event *event = container_of(entry, struct perf_event, pending);
int rctx;
rctx = perf_swevent_get_recursion_context();
* and we won't recurse 'further'.
*/
- if (event->pending_disable) {
- event->pending_disable = 0;
- perf_event_disable_local(event);
- }
+ perf_pending_event_disable(event);
if (event->pending_wakeup) {
event->pending_wakeup = 0;
init_waitqueue_head(&event->waitq);
+ event->pending_disable = -1;
init_irq_work(&event->pending, perf_pending_event);
mutex_init(&event->mmap_mutex);
* store that will be enabled on successful return
*/
if (!handle->size) { /* A, matches D */
- event->pending_disable = 1;
+ event->pending_disable = smp_processor_id();
perf_output_wakeup(handle);
local_set(&rb->aux_nest, 0);
goto err_put;
if (wakeup) {
if (handle->aux_flags & PERF_AUX_FLAG_TRUNCATED)
- handle->event->pending_disable = 1;
+ handle->event->pending_disable = smp_processor_id();
perf_output_wakeup(handle);
}
int irq_chip_set_wake_parent(struct irq_data *data, unsigned int on)
{
data = data->parent_data;
+
+ if (data->chip->flags & IRQCHIP_SKIP_SET_WAKE)
+ return 0;
+
if (data->chip->irq_set_wake)
return data->chip->irq_set_wake(data, on);
alloc_masks(&desc[i], node);
raw_spin_lock_init(&desc[i].lock);
lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
+ mutex_init(&desc[i].request_mutex);
desc_set_defaults(i, &desc[i], node, NULL, NULL);
}
return arch_early_irq_init();
return;
raw_local_irq_save(flags);
- if (!graph_lock())
- goto out_irq;
+ arch_spin_lock(&lockdep_lock);
+ current->lockdep_recursion = 1;
/* closed head */
pf = delayed_free.pf + (delayed_free.index ^ 1);
*/
call_rcu_zapped(delayed_free.pf + delayed_free.index);
- graph_unlock();
-out_irq:
+ current->lockdep_recursion = 0;
+ arch_spin_unlock(&lockdep_lock);
raw_local_irq_restore(flags);
}
{
struct pending_free *pf;
unsigned long flags;
- int locked;
init_data_structures_once();
raw_local_irq_save(flags);
- locked = graph_lock();
- if (!locked)
- goto out_irq;
-
+ arch_spin_lock(&lockdep_lock);
+ current->lockdep_recursion = 1;
pf = get_pending_free();
__lockdep_free_key_range(pf, start, size);
call_rcu_zapped(pf);
-
- graph_unlock();
-out_irq:
+ current->lockdep_recursion = 0;
+ arch_spin_unlock(&lockdep_lock);
raw_local_irq_restore(flags);
/*
return;
raw_local_irq_save(flags);
- if (!graph_lock())
- goto out_irq;
-
+ arch_spin_lock(&lockdep_lock);
+ current->lockdep_recursion = 1;
pf = get_pending_free();
hlist_for_each_entry_rcu(k, hash_head, hash_entry) {
if (k == key) {
WARN_ON_ONCE(!found);
__lockdep_free_key_range(pf, key, 1);
call_rcu_zapped(pf);
- graph_unlock();
-out_irq:
+ current->lockdep_recursion = 0;
+ arch_spin_unlock(&lockdep_lock);
raw_local_irq_restore(flags);
/* Wait until is_dynamic_key() has finished accessing k->hash_entry. */
#include <linux/hw_breakpoint.h>
#include <linux/cn_proc.h>
#include <linux/compat.h>
+#include <linux/sched/signal.h>
/*
* Access another process' address space via ptrace.
ret = ptrace_setsiginfo(child, &siginfo);
break;
- case PTRACE_GETSIGMASK:
+ case PTRACE_GETSIGMASK: {
+ sigset_t *mask;
+
if (addr != sizeof(sigset_t)) {
ret = -EINVAL;
break;
}
- if (copy_to_user(datavp, &child->blocked, sizeof(sigset_t)))
+ if (test_tsk_restore_sigmask(child))
+ mask = &child->saved_sigmask;
+ else
+ mask = &child->blocked;
+
+ if (copy_to_user(datavp, mask, sizeof(sigset_t)))
ret = -EFAULT;
else
ret = 0;
break;
+ }
case PTRACE_SETSIGMASK: {
sigset_t new_set;
child->blocked = new_set;
spin_unlock_irq(&child->sighand->siglock);
+ clear_tsk_restore_sigmask(child);
+
ret = 0;
break;
}
if (cfs_rq->last_h_load_update == now)
return;
- cfs_rq->h_load_next = NULL;
+ WRITE_ONCE(cfs_rq->h_load_next, NULL);
for_each_sched_entity(se) {
cfs_rq = cfs_rq_of(se);
- cfs_rq->h_load_next = se;
+ WRITE_ONCE(cfs_rq->h_load_next, se);
if (cfs_rq->last_h_load_update == now)
break;
}
cfs_rq->last_h_load_update = now;
}
- while ((se = cfs_rq->h_load_next) != NULL) {
+ while ((se = READ_ONCE(cfs_rq->h_load_next)) != NULL) {
load = cfs_rq->h_load;
load = div64_ul(load * se->avg.load_avg,
cfs_rq_load_avg(cfs_rq) + 1);
sd->nr = syscall_get_nr(task, regs);
sd->arch = syscall_get_arch();
- syscall_get_arguments(task, regs, 0, 6, args);
+ syscall_get_arguments(task, regs, args);
sd->args[0] = args[0];
sd->args[1] = args[1];
sd->args[2] = args[2];
if (unlikely(sig != kinfo.si_signo))
goto err;
+ /* Only allow sending arbitrary signals to yourself. */
+ ret = -EPERM;
if ((task_pid(current) != pid) &&
- (kinfo.si_code >= 0 || kinfo.si_code == SI_TKILL)) {
- /* Only allow sending arbitrary signals to yourself. */
- ret = -EPERM;
- if (kinfo.si_code != SI_USER)
- goto err;
-
- /* Turn this into a regular kill signal. */
- prepare_kill_siginfo(sig, &kinfo);
- }
+ (kinfo.si_code >= 0 || kinfo.si_code == SI_TKILL))
+ goto err;
} else {
prepare_kill_siginfo(sig, &kinfo);
}
static int __maybe_unused one = 1;
static int __maybe_unused two = 2;
static int __maybe_unused four = 4;
+static unsigned long zero_ul;
static unsigned long one_ul = 1;
static unsigned long long_max = LONG_MAX;
static int one_hundred = 100;
.maxlen = sizeof(files_stat.max_files),
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
- .extra1 = &zero,
+ .extra1 = &zero_ul,
.extra2 = &long_max,
},
{
{
struct alarm *alarm = &timr->it.alarm.alarmtimer;
- return ktime_sub(now, alarm->node.expires);
+ return ktime_sub(alarm->node.expires, now);
}
/**
}
EXPORT_SYMBOL(jiffies64_to_nsecs);
+u64 jiffies64_to_msecs(const u64 j)
+{
+#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ)
+ return (MSEC_PER_SEC / HZ) * j;
+#else
+ return div_u64(j * HZ_TO_MSEC_NUM, HZ_TO_MSEC_DEN);
+#endif
+}
+EXPORT_SYMBOL(jiffies64_to_msecs);
+
/**
* nsecs_to_jiffies64 - Convert nsecs in u64 to jiffies64
*
buf->private = 0;
}
-static void buffer_pipe_buf_get(struct pipe_inode_info *pipe,
+static bool buffer_pipe_buf_get(struct pipe_inode_info *pipe,
struct pipe_buffer *buf)
{
struct buffer_ref *ref = (struct buffer_ref *)buf->private;
+ if (ref->ref > INT_MAX/2)
+ return false;
+
ref->ref++;
+ return true;
}
/* Pipe buffer operations for a buffer. */
struct ring_buffer_event *event;
struct ring_buffer *buffer;
unsigned long irq_flags;
+ unsigned long args[6];
int pc;
int syscall_nr;
int size;
entry = ring_buffer_event_data(event);
entry->nr = syscall_nr;
- syscall_get_arguments(current, regs, 0, sys_data->nb_args, entry->args);
+ syscall_get_arguments(current, regs, args);
+ memcpy(entry->args, args, sizeof(unsigned long) * sys_data->nb_args);
event_trigger_unlock_commit(trace_file, buffer, event, entry,
irq_flags, pc);
struct syscall_metadata *sys_data;
struct syscall_trace_enter *rec;
struct hlist_head *head;
+ unsigned long args[6];
bool valid_prog_array;
int syscall_nr;
int rctx;
return;
rec->nr = syscall_nr;
- syscall_get_arguments(current, regs, 0, sys_data->nb_args,
- (unsigned long *)&rec->args);
+ syscall_get_arguments(current, regs, args);
+ memcpy(&rec->args, args, sizeof(unsigned long) * sys_data->nb_args);
if ((valid_prog_array &&
!perf_call_bpf_enter(sys_data->enter_event, regs, sys_data, rec)) ||
int lockup_detector_online_cpu(unsigned int cpu)
{
- watchdog_enable(cpu);
+ if (cpumask_test_cpu(cpu, &watchdog_allowed_mask))
+ watchdog_enable(cpu);
return 0;
}
int lockup_detector_offline_cpu(unsigned int cpu)
{
- watchdog_disable(cpu);
+ if (cpumask_test_cpu(cpu, &watchdog_allowed_mask))
+ watchdog_disable(cpu);
return 0;
}
But it significantly improves the success of resolving
variables in gdb on optimized code.
+config DEBUG_INFO_BTF
+ bool "Generate BTF typeinfo"
+ depends on DEBUG_INFO
+ help
+ Generate deduplicated BTF type information from DWARF debug info.
+ Turning this on expects presence of pahole tool, which will convert
+ DWARF type info into equivalent deduplicated BTF type info.
+
config GDB_SCRIPTS
bool "Provide GDB scripts for kernel debugging"
depends on DEBUG_INFO
size_t hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp,
struct iov_iter *i)
{
+#ifdef CONFIG_CRYPTO
struct ahash_request *hash = hashp;
struct scatterlist sg;
size_t copied;
ahash_request_set_crypt(hash, &sg, NULL, copied);
crypto_ahash_update(hash);
return copied;
+#else
+ return 0;
+#endif
}
EXPORT_SYMBOL(hash_and_copy_to_iter);
{
const unsigned char *ip = in;
unsigned char *op = out;
+ unsigned char *data_start;
size_t l = in_len;
size_t t = 0;
signed char state_offset = -2;
unsigned int m4_max_offset;
- // LZO v0 will never write 17 as first byte,
- // so this is used to version the bitstream
+ // LZO v0 will never write 17 as first byte (except for zero-length
+ // input), so this is used to version the bitstream
if (bitstream_version > 0) {
*op++ = 17;
*op++ = bitstream_version;
m4_max_offset = M4_MAX_OFFSET_V0;
}
+ data_start = op;
+
while (l > 20) {
size_t ll = l <= (m4_max_offset + 1) ? l : (m4_max_offset + 1);
uintptr_t ll_end = (uintptr_t) ip + ll;
if (t > 0) {
const unsigned char *ii = in + in_len - t;
- if (op == out && t <= 238) {
+ if (op == data_start && t <= 238) {
*op++ = (17 + t);
} else if (t <= 3) {
op[state_offset] |= t;
if (unlikely(in_len < 3))
goto input_overrun;
- if (likely(*ip == 17)) {
+ if (likely(in_len >= 5) && likely(*ip == 17)) {
bitstream_version = ip[1];
ip += 2;
- if (unlikely(in_len < 5))
- goto input_overrun;
} else {
bitstream_version = 0;
}
#define HASH_DEFAULT_SIZE 64UL
#define HASH_MIN_SIZE 4U
-#define BUCKET_LOCKS_PER_CPU 32UL
union nested_table {
union nested_table __rcu *table;
- struct rhash_head __rcu *bucket;
+ struct rhash_lock_head __rcu *bucket;
};
static u32 head_hashfn(struct rhashtable *ht,
int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, u32 hash)
{
- spinlock_t *lock = rht_bucket_lock(tbl, hash);
-
- return (debug_locks) ? lockdep_is_held(lock) : 1;
+ if (!debug_locks)
+ return 1;
+ if (unlikely(tbl->nest))
+ return 1;
+ return bit_spin_is_locked(0, (unsigned long *)&tbl->buckets[hash]);
}
EXPORT_SYMBOL_GPL(lockdep_rht_bucket_is_held);
#else
if (tbl->nest)
nested_bucket_table_free(tbl);
- free_bucket_spinlocks(tbl->locks);
kvfree(tbl);
}
INIT_RHT_NULLS_HEAD(ntbl[i].bucket);
}
- rcu_assign_pointer(*prev, ntbl);
-
- return ntbl;
+ if (cmpxchg(prev, NULL, ntbl) == NULL)
+ return ntbl;
+ /* Raced with another thread. */
+ kfree(ntbl);
+ return rcu_dereference(*prev);
}
static struct bucket_table *nested_bucket_table_alloc(struct rhashtable *ht,
gfp_t gfp)
{
struct bucket_table *tbl = NULL;
- size_t size, max_locks;
+ size_t size;
int i;
+ static struct lock_class_key __key;
- size = sizeof(*tbl) + nbuckets * sizeof(tbl->buckets[0]);
- tbl = kvzalloc(size, gfp);
+ tbl = kvzalloc(struct_size(tbl, buckets, nbuckets), gfp);
size = nbuckets;
if (tbl == NULL)
return NULL;
- tbl->size = size;
-
- max_locks = size >> 1;
- if (tbl->nest)
- max_locks = min_t(size_t, max_locks, 1U << tbl->nest);
+ lockdep_init_map(&tbl->dep_map, "rhashtable_bucket", &__key, 0);
- if (alloc_bucket_spinlocks(&tbl->locks, &tbl->locks_mask, max_locks,
- ht->p.locks_mul, gfp) < 0) {
- bucket_table_free(tbl);
- return NULL;
- }
+ tbl->size = size;
rcu_head_init(&tbl->rcu);
INIT_LIST_HEAD(&tbl->walkers);
return new_tbl;
}
-static int rhashtable_rehash_one(struct rhashtable *ht, unsigned int old_hash)
+static int rhashtable_rehash_one(struct rhashtable *ht,
+ struct rhash_lock_head __rcu **bkt,
+ unsigned int old_hash)
{
struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht);
struct bucket_table *new_tbl = rhashtable_last_table(ht, old_tbl);
- struct rhash_head __rcu **pprev = rht_bucket_var(old_tbl, old_hash);
int err = -EAGAIN;
struct rhash_head *head, *next, *entry;
- spinlock_t *new_bucket_lock;
+ struct rhash_head __rcu **pprev = NULL;
unsigned int new_hash;
if (new_tbl->nest)
err = -ENOENT;
- rht_for_each(entry, old_tbl, old_hash) {
+ rht_for_each_from(entry, rht_ptr(bkt, old_tbl, old_hash),
+ old_tbl, old_hash) {
err = 0;
next = rht_dereference_bucket(entry->next, old_tbl, old_hash);
new_hash = head_hashfn(ht, new_tbl, entry);
- new_bucket_lock = rht_bucket_lock(new_tbl, new_hash);
+ rht_lock_nested(new_tbl, &new_tbl->buckets[new_hash], SINGLE_DEPTH_NESTING);
- spin_lock_nested(new_bucket_lock, SINGLE_DEPTH_NESTING);
- head = rht_dereference_bucket(new_tbl->buckets[new_hash],
- new_tbl, new_hash);
+ head = rht_ptr(new_tbl->buckets + new_hash, new_tbl, new_hash);
RCU_INIT_POINTER(entry->next, head);
- rcu_assign_pointer(new_tbl->buckets[new_hash], entry);
- spin_unlock(new_bucket_lock);
+ rht_assign_unlock(new_tbl, &new_tbl->buckets[new_hash], entry);
- rcu_assign_pointer(*pprev, next);
+ if (pprev)
+ rcu_assign_pointer(*pprev, next);
+ else
+ /* Need to preserved the bit lock. */
+ rht_assign_locked(bkt, next);
out:
return err;
unsigned int old_hash)
{
struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht);
- spinlock_t *old_bucket_lock;
+ struct rhash_lock_head __rcu **bkt = rht_bucket_var(old_tbl, old_hash);
int err;
- old_bucket_lock = rht_bucket_lock(old_tbl, old_hash);
+ if (!bkt)
+ return 0;
+ rht_lock(old_tbl, bkt);
- spin_lock_bh(old_bucket_lock);
- while (!(err = rhashtable_rehash_one(ht, old_hash)))
+ while (!(err = rhashtable_rehash_one(ht, bkt, old_hash)))
;
if (err == -ENOENT)
err = 0;
-
- spin_unlock_bh(old_bucket_lock);
+ rht_unlock(old_tbl, bkt);
return err;
}
}
static void *rhashtable_lookup_one(struct rhashtable *ht,
+ struct rhash_lock_head __rcu **bkt,
struct bucket_table *tbl, unsigned int hash,
const void *key, struct rhash_head *obj)
{
.ht = ht,
.key = key,
};
- struct rhash_head __rcu **pprev;
+ struct rhash_head __rcu **pprev = NULL;
struct rhash_head *head;
int elasticity;
elasticity = RHT_ELASTICITY;
- pprev = rht_bucket_var(tbl, hash);
- rht_for_each_from(head, *pprev, tbl, hash) {
+ rht_for_each_from(head, rht_ptr(bkt, tbl, hash), tbl, hash) {
struct rhlist_head *list;
struct rhlist_head *plist;
RCU_INIT_POINTER(list->next, plist);
head = rht_dereference_bucket(head->next, tbl, hash);
RCU_INIT_POINTER(list->rhead.next, head);
- rcu_assign_pointer(*pprev, obj);
+ if (pprev)
+ rcu_assign_pointer(*pprev, obj);
+ else
+ /* Need to preserve the bit lock */
+ rht_assign_locked(bkt, obj);
return NULL;
}
}
static struct bucket_table *rhashtable_insert_one(struct rhashtable *ht,
+ struct rhash_lock_head __rcu **bkt,
struct bucket_table *tbl,
unsigned int hash,
struct rhash_head *obj,
void *data)
{
- struct rhash_head __rcu **pprev;
struct bucket_table *new_tbl;
struct rhash_head *head;
if (unlikely(rht_grow_above_100(ht, tbl)))
return ERR_PTR(-EAGAIN);
- pprev = rht_bucket_insert(ht, tbl, hash);
- if (!pprev)
- return ERR_PTR(-ENOMEM);
-
- head = rht_dereference_bucket(*pprev, tbl, hash);
+ head = rht_ptr(bkt, tbl, hash);
RCU_INIT_POINTER(obj->next, head);
if (ht->rhlist) {
RCU_INIT_POINTER(list->next, NULL);
}
- rcu_assign_pointer(*pprev, obj);
+ /* bkt is always the head of the list, so it holds
+ * the lock, which we need to preserve
+ */
+ rht_assign_locked(bkt, obj);
atomic_inc(&ht->nelems);
if (rht_grow_above_75(ht, tbl))
{
struct bucket_table *new_tbl;
struct bucket_table *tbl;
+ struct rhash_lock_head __rcu **bkt;
unsigned int hash;
void *data;
do {
tbl = new_tbl;
hash = rht_head_hashfn(ht, tbl, obj, ht->p);
- spin_lock_bh(rht_bucket_lock(tbl, hash));
-
- data = rhashtable_lookup_one(ht, tbl, hash, key, obj);
- new_tbl = rhashtable_insert_one(ht, tbl, hash, obj, data);
- if (PTR_ERR(new_tbl) != -EEXIST)
- data = ERR_CAST(new_tbl);
-
- spin_unlock_bh(rht_bucket_lock(tbl, hash));
+ if (rcu_access_pointer(tbl->future_tbl))
+ /* Failure is OK */
+ bkt = rht_bucket_var(tbl, hash);
+ else
+ bkt = rht_bucket_insert(ht, tbl, hash);
+ if (bkt == NULL) {
+ new_tbl = rht_dereference_rcu(tbl->future_tbl, ht);
+ data = ERR_PTR(-EAGAIN);
+ } else {
+ rht_lock(tbl, bkt);
+ data = rhashtable_lookup_one(ht, bkt, tbl,
+ hash, key, obj);
+ new_tbl = rhashtable_insert_one(ht, bkt, tbl,
+ hash, obj, data);
+ if (PTR_ERR(new_tbl) != -EEXIST)
+ data = ERR_CAST(new_tbl);
+
+ rht_unlock(tbl, bkt);
+ }
} while (!IS_ERR_OR_NULL(new_tbl));
if (PTR_ERR(data) == -EAGAIN)
size = rounded_hashtable_size(&ht->p);
- if (params->locks_mul)
- ht->p.locks_mul = roundup_pow_of_two(params->locks_mul);
- else
- ht->p.locks_mul = BUCKET_LOCKS_PER_CPU;
-
ht->key_len = ht->p.key_len;
if (!params->hashfn) {
ht->p.hashfn = jhash;
struct rhash_head *pos, *next;
cond_resched();
- for (pos = rht_dereference(*rht_bucket(tbl, i), ht),
+ for (pos = rht_ptr_exclusive(rht_bucket(tbl, i)),
next = !rht_is_a_nulls(pos) ?
rht_dereference(pos->next, ht) : NULL;
!rht_is_a_nulls(pos);
}
EXPORT_SYMBOL_GPL(rhashtable_destroy);
-struct rhash_head __rcu **rht_bucket_nested(const struct bucket_table *tbl,
- unsigned int hash)
+struct rhash_lock_head __rcu **__rht_bucket_nested(const struct bucket_table *tbl,
+ unsigned int hash)
{
const unsigned int shift = PAGE_SHIFT - ilog2(sizeof(void *));
- static struct rhash_head __rcu *rhnull;
unsigned int index = hash & ((1 << tbl->nest) - 1);
unsigned int size = tbl->size >> tbl->nest;
unsigned int subhash = hash;
subhash >>= shift;
}
- if (!ntbl) {
- if (!rhnull)
- INIT_RHT_NULLS_HEAD(rhnull);
- return &rhnull;
- }
+ if (!ntbl)
+ return NULL;
return &ntbl[subhash].bucket;
}
+EXPORT_SYMBOL_GPL(__rht_bucket_nested);
+
+struct rhash_lock_head __rcu **rht_bucket_nested(const struct bucket_table *tbl,
+ unsigned int hash)
+{
+ static struct rhash_lock_head __rcu *rhnull;
+
+ if (!rhnull)
+ INIT_RHT_NULLS_HEAD(rhnull);
+ return __rht_bucket_nested(tbl, hash) ?: &rhnull;
+}
EXPORT_SYMBOL_GPL(rht_bucket_nested);
-struct rhash_head __rcu **rht_bucket_nested_insert(struct rhashtable *ht,
- struct bucket_table *tbl,
- unsigned int hash)
+struct rhash_lock_head __rcu **rht_bucket_nested_insert(struct rhashtable *ht,
+ struct bucket_table *tbl,
+ unsigned int hash)
{
const unsigned int shift = PAGE_SHIFT - ilog2(sizeof(void *));
unsigned int index = hash & ((1 << tbl->nest) - 1);
void sbitmap_queue_clear(struct sbitmap_queue *sbq, unsigned int nr,
unsigned int cpu)
{
+ /*
+ * Once the clear bit is set, the bit may be allocated out.
+ *
+ * Orders READ/WRITE on the asssociated instance(such as request
+ * of blk_mq) by this bit for avoiding race with re-allocation,
+ * and its pair is the memory barrier implied in __sbitmap_get_word.
+ *
+ * One invariant is that the clear bit has to be zero when the bit
+ * is in use.
+ */
+ smp_mb__before_atomic();
sbitmap_deferred_clear_bit(&sbq->sb, nr);
/*
EXPORT_SYMBOL(memcmp);
#endif
+#ifndef __HAVE_ARCH_BCMP
+/**
+ * bcmp - returns 0 if and only if the buffers have identical contents.
+ * @a: pointer to first buffer.
+ * @b: pointer to second buffer.
+ * @len: size of buffers.
+ *
+ * The sign or magnitude of a non-zero return value has no particular
+ * meaning, and architectures may implement their own more efficient bcmp(). So
+ * while this particular implementation is a simple (tail) call to memcmp, do
+ * not rely on anything but whether the return value is zero or non-zero.
+ */
+#undef bcmp
+int bcmp(const void *a, const void *b, size_t len)
+{
+ return memcmp(a, b, len);
+}
+EXPORT_SYMBOL(bcmp);
+#endif
+
#ifndef __HAVE_ARCH_MEMSCAN
/**
* memscan - Find a character in an area of memory.
#include <linux/export.h>
#include <asm/syscall.h>
-static int collect_syscall(struct task_struct *target, long *callno,
- unsigned long args[6], unsigned int maxargs,
- unsigned long *sp, unsigned long *pc)
+static int collect_syscall(struct task_struct *target, struct syscall_info *info)
{
struct pt_regs *regs;
if (!try_get_task_stack(target)) {
/* Task has no stack, so the task isn't in a syscall. */
- *sp = *pc = 0;
- *callno = -1;
+ memset(info, 0, sizeof(*info));
+ info->data.nr = -1;
return 0;
}
return -EAGAIN;
}
- *sp = user_stack_pointer(regs);
- *pc = instruction_pointer(regs);
+ info->sp = user_stack_pointer(regs);
+ info->data.instruction_pointer = instruction_pointer(regs);
- *callno = syscall_get_nr(target, regs);
- if (*callno != -1L && maxargs > 0)
- syscall_get_arguments(target, regs, 0, maxargs, args);
+ info->data.nr = syscall_get_nr(target, regs);
+ if (info->data.nr != -1L)
+ syscall_get_arguments(target, regs,
+ (unsigned long *)&info->data.args[0]);
put_task_stack(target);
return 0;
/**
* task_current_syscall - Discover what a blocked task is doing.
* @target: thread to examine
- * @callno: filled with system call number or -1
- * @args: filled with @maxargs system call arguments
- * @maxargs: number of elements in @args to fill
- * @sp: filled with user stack pointer
- * @pc: filled with user PC
+ * @info: structure with the following fields:
+ * .sp - filled with user stack pointer
+ * .data.nr - filled with system call number or -1
+ * .data.args - filled with @maxargs system call arguments
+ * .data.instruction_pointer - filled with user PC
*
- * If @target is blocked in a system call, returns zero with *@callno
- * set to the the call's number and @args filled in with its arguments.
- * Registers not used for system call arguments may not be available and
- * it is not kosher to use &struct user_regset calls while the system
+ * If @target is blocked in a system call, returns zero with @info.data.nr
+ * set to the the call's number and @info.data.args filled in with its
+ * arguments. Registers not used for system call arguments may not be available
+ * and it is not kosher to use &struct user_regset calls while the system
* call is still in progress. Note we may get this result if @target
* has finished its system call but not yet returned to user mode, such
* as when it's stopped for signal handling or syscall exit tracing.
*
* If @target is blocked in the kernel during a fault or exception,
- * returns zero with *@callno set to -1 and does not fill in @args.
- * If so, it's now safe to examine @target using &struct user_regset
- * get() calls as long as we're sure @target won't return to user mode.
+ * returns zero with *@info.data.nr set to -1 and does not fill in
+ * @info.data.args. If so, it's now safe to examine @target using
+ * &struct user_regset get() calls as long as we're sure @target won't return
+ * to user mode.
*
* Returns -%EAGAIN if @target does not remain blocked.
- *
- * Returns -%EINVAL if @maxargs is too large (maximum is six).
*/
-int task_current_syscall(struct task_struct *target, long *callno,
- unsigned long args[6], unsigned int maxargs,
- unsigned long *sp, unsigned long *pc)
+int task_current_syscall(struct task_struct *target, struct syscall_info *info)
{
long state;
unsigned long ncsw;
- if (unlikely(maxargs > 6))
- return -EINVAL;
-
if (target == current)
- return collect_syscall(target, callno, args, maxargs, sp, pc);
+ return collect_syscall(target, info);
state = target->state;
if (unlikely(!state))
ncsw = wait_task_inactive(target, state);
if (unlikely(!ncsw) ||
- unlikely(collect_syscall(target, callno, args, maxargs, sp, pc)) ||
+ unlikely(collect_syscall(target, info)) ||
unlikely(wait_task_inactive(target, state) != ncsw))
return -EAGAIN;
struct rhash_head *pos, *next;
struct test_obj_rhl *p;
- pos = rht_dereference(tbl->buckets[i], ht);
+ pos = rht_ptr_exclusive(tbl->buckets + i);
next = !rht_is_a_nulls(pos) ? rht_dereference(pos->next, ht) : NULL;
if (!rht_is_a_nulls(pos)) {
bool check_target)
{
struct page *page = pfn_to_online_page(pfn);
+ struct page *block_page;
struct page *end_page;
unsigned long block_pfn;
get_pageblock_migratetype(page) != MIGRATE_MOVABLE)
return false;
+ /* Ensure the start of the pageblock or zone is online and valid */
+ block_pfn = pageblock_start_pfn(pfn);
+ block_page = pfn_to_online_page(max(block_pfn, zone->zone_start_pfn));
+ if (block_page) {
+ page = block_page;
+ pfn = block_pfn;
+ }
+
+ /* Ensure the end of the pageblock or zone is online and valid */
+ block_pfn += pageblock_nr_pages;
+ block_pfn = min(block_pfn, zone_end_pfn(zone) - 1);
+ end_page = pfn_to_online_page(block_pfn);
+ if (!end_page)
+ return false;
+
/*
* Only clear the hint if a sample indicates there is either a
* free page or an LRU page in the block. One or other condition
* is necessary for the block to be a migration source/target.
*/
- block_pfn = pageblock_start_pfn(pfn);
- pfn = max(block_pfn, zone->zone_start_pfn);
- page = pfn_to_page(pfn);
- if (zone != page_zone(page))
- return false;
- pfn = block_pfn + pageblock_nr_pages;
- pfn = min(pfn, zone_end_pfn(zone));
- end_page = pfn_to_page(pfn);
-
do {
if (pfn_valid_within(pfn)) {
if (check_source && PageLRU(page)) {
static void __reset_isolation_suitable(struct zone *zone)
{
unsigned long migrate_pfn = zone->zone_start_pfn;
- unsigned long free_pfn = zone_end_pfn(zone);
+ unsigned long free_pfn = zone_end_pfn(zone) - 1;
unsigned long reset_migrate = free_pfn;
unsigned long reset_free = migrate_pfn;
bool source_set = false;
count_compact_events(COMPACTISOLATED, nr_isolated);
} else {
/* If isolation fails, abort the search */
- order = -1;
+ order = cc->search_order + 1;
page = NULL;
}
}
pr_warn("ksm ");
else if (mapping) {
pr_warn("%ps ", mapping->a_ops);
- if (mapping->host->i_dentry.first) {
+ if (mapping->host && mapping->host->i_dentry.first) {
struct dentry *dentry;
dentry = container_of(mapping->host->i_dentry.first, struct dentry, d_u.d_alias);
pr_warn("name:\"%pd\" ", dentry);
mm_pgtables_bytes(mm),
mm->map_count,
mm->hiwater_rss, mm->hiwater_vm, mm->total_vm, mm->locked_vm,
- atomic64_read(&mm->pinned_vm),
+ (u64)atomic64_read(&mm->pinned_vm),
mm->data_vm, mm->exec_vm, mm->stack_vm,
mm->start_code, mm->end_code, mm->start_data, mm->end_data,
mm->start_brk, mm->brk, mm->start_stack,
goto retry;
}
- if (flags & FOLL_GET)
- get_page(page);
+ if (flags & FOLL_GET) {
+ if (unlikely(!try_get_page(page))) {
+ page = ERR_PTR(-ENOMEM);
+ goto out;
+ }
+ }
if (flags & FOLL_TOUCH) {
if ((flags & FOLL_WRITE) &&
!pte_dirty(pte) && !PageDirty(page))
if (pmd_trans_unstable(pmd))
ret = -EBUSY;
} else {
- get_page(page);
+ if (unlikely(!try_get_page(page))) {
+ spin_unlock(ptl);
+ return ERR_PTR(-ENOMEM);
+ }
spin_unlock(ptl);
lock_page(page);
ret = split_huge_page(page);
if (is_device_public_page(*page))
goto unmap;
}
- get_page(*page);
+ if (unlikely(!try_get_page(*page))) {
+ ret = -ENOMEM;
+ goto unmap;
+ }
out:
ret = 0;
unmap:
}
}
+/*
+ * Return the compund head page with ref appropriately incremented,
+ * or NULL if that failed.
+ */
+static inline struct page *try_get_compound_head(struct page *page, int refs)
+{
+ struct page *head = compound_head(page);
+ if (WARN_ON_ONCE(page_ref_count(head) < 0))
+ return NULL;
+ if (unlikely(!page_cache_add_speculative(head, refs)))
+ return NULL;
+ return head;
+}
+
#ifdef CONFIG_ARCH_HAS_PTE_SPECIAL
static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
int write, struct page **pages, int *nr)
VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
page = pte_page(pte);
- head = compound_head(page);
- if (!page_cache_get_speculative(head))
+ head = try_get_compound_head(page, 1);
+ if (!head)
goto pte_unmap;
if (unlikely(pte_val(pte) != pte_val(*ptep))) {
refs++;
} while (addr += PAGE_SIZE, addr != end);
- head = compound_head(pmd_page(orig));
- if (!page_cache_add_speculative(head, refs)) {
+ head = try_get_compound_head(pmd_page(orig), refs);
+ if (!head) {
*nr -= refs;
return 0;
}
refs++;
} while (addr += PAGE_SIZE, addr != end);
- head = compound_head(pud_page(orig));
- if (!page_cache_add_speculative(head, refs)) {
+ head = try_get_compound_head(pud_page(orig), refs);
+ if (!head) {
*nr -= refs;
return 0;
}
refs++;
} while (addr += PAGE_SIZE, addr != end);
- head = compound_head(pgd_page(orig));
- if (!page_cache_add_speculative(head, refs)) {
+ head = try_get_compound_head(pgd_page(orig), refs);
+ if (!head) {
*nr -= refs;
return 0;
}
spinlock_t *ptl;
ptl = pmd_lock(mm, pmd);
+ if (!pmd_none(*pmd)) {
+ if (write) {
+ if (pmd_pfn(*pmd) != pfn_t_to_pfn(pfn)) {
+ WARN_ON_ONCE(!is_huge_zero_pmd(*pmd));
+ goto out_unlock;
+ }
+ entry = pmd_mkyoung(*pmd);
+ entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
+ if (pmdp_set_access_flags(vma, addr, pmd, entry, 1))
+ update_mmu_cache_pmd(vma, addr, pmd);
+ }
+
+ goto out_unlock;
+ }
+
entry = pmd_mkhuge(pfn_t_pmd(pfn, prot));
if (pfn_t_devmap(pfn))
entry = pmd_mkdevmap(entry);
if (pgtable) {
pgtable_trans_huge_deposit(mm, pmd, pgtable);
mm_inc_nr_ptes(mm);
+ pgtable = NULL;
}
set_pmd_at(mm, addr, pmd, entry);
update_mmu_cache_pmd(vma, addr, pmd);
+
+out_unlock:
spin_unlock(ptl);
+ if (pgtable)
+ pte_free(mm, pgtable);
}
vm_fault_t vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
spinlock_t *ptl;
ptl = pud_lock(mm, pud);
+ if (!pud_none(*pud)) {
+ if (write) {
+ if (pud_pfn(*pud) != pfn_t_to_pfn(pfn)) {
+ WARN_ON_ONCE(!is_huge_zero_pud(*pud));
+ goto out_unlock;
+ }
+ entry = pud_mkyoung(*pud);
+ entry = maybe_pud_mkwrite(pud_mkdirty(entry), vma);
+ if (pudp_set_access_flags(vma, addr, pud, entry, 1))
+ update_mmu_cache_pud(vma, addr, pud);
+ }
+ goto out_unlock;
+ }
+
entry = pud_mkhuge(pfn_t_pud(pfn, prot));
if (pfn_t_devmap(pfn))
entry = pud_mkdevmap(entry);
}
set_pud_at(mm, addr, pud, entry);
update_mmu_cache_pud(vma, addr, pud);
+
+out_unlock:
spin_unlock(ptl);
}
pfn_offset = (vaddr & ~huge_page_mask(h)) >> PAGE_SHIFT;
page = pte_page(huge_ptep_get(pte));
+
+ /*
+ * Instead of doing 'try_get_page()' below in the same_page
+ * loop, just check the count once here.
+ */
+ if (unlikely(page_count(page) <= 0)) {
+ if (pages) {
+ spin_unlock(ptl);
+ remainder = 0;
+ err = -ENOMEM;
+ break;
+ }
+ }
same_page:
if (pages) {
pages[i] = mem_map_offset(page, pfn_offset);
#endif
#ifndef arch_kasan_set_tag
-#define arch_kasan_set_tag(addr, tag) ((void *)(addr))
+static inline const void *arch_kasan_set_tag(const void *addr, u8 tag)
+{
+ return addr;
+}
#endif
#ifndef arch_kasan_reset_tag
#define arch_kasan_reset_tag(addr) ((void *)(addr))
}
rcu_read_unlock();
- /* data/bss scanning */
- scan_large_block(_sdata, _edata);
- scan_large_block(__bss_start, __bss_stop);
- scan_large_block(__start_ro_after_init, __end_ro_after_init);
-
#ifdef CONFIG_SMP
/* per-cpu sections scanning */
for_each_possible_cpu(i)
}
local_irq_restore(flags);
+ /* register the data/bss sections */
+ create_object((unsigned long)_sdata, _edata - _sdata,
+ KMEMLEAK_GREY, GFP_ATOMIC);
+ create_object((unsigned long)__bss_start, __bss_stop - __bss_start,
+ KMEMLEAK_GREY, GFP_ATOMIC);
+ /* only register .data..ro_after_init if not within .data */
+ if (__start_ro_after_init < _sdata || __end_ro_after_init > _edata)
+ create_object((unsigned long)__start_ro_after_init,
+ __end_ro_after_init - __start_ro_after_init,
+ KMEMLEAK_GREY, GFP_ATOMIC);
+
/*
* This is the point where tracking allocations is safe. Automatic
* scanning is started during the late initcall. Add the early logged
return &memcg->cgwb_domain;
}
+/*
+ * idx can be of type enum memcg_stat_item or node_stat_item.
+ * Keep in sync with memcg_exact_page().
+ */
+static unsigned long memcg_exact_page_state(struct mem_cgroup *memcg, int idx)
+{
+ long x = atomic_long_read(&memcg->stat[idx]);
+ int cpu;
+
+ for_each_online_cpu(cpu)
+ x += per_cpu_ptr(memcg->stat_cpu, cpu)->count[idx];
+ if (x < 0)
+ x = 0;
+ return x;
+}
+
/**
* mem_cgroup_wb_stats - retrieve writeback related stats from its memcg
* @wb: bdi_writeback in question
struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css);
struct mem_cgroup *parent;
- *pdirty = memcg_page_state(memcg, NR_FILE_DIRTY);
+ *pdirty = memcg_exact_page_state(memcg, NR_FILE_DIRTY);
/* this should eventually include NR_UNSTABLE_NFS */
- *pwriteback = memcg_page_state(memcg, NR_WRITEBACK);
+ *pwriteback = memcg_exact_page_state(memcg, NR_WRITEBACK);
*pfilepages = mem_cgroup_nr_lru_pages(memcg, (1 << LRU_INACTIVE_FILE) |
(1 << LRU_ACTIVE_FILE));
*pheadroom = PAGE_COUNTER_MAX;
WARN_ON_ONCE(!is_zero_pfn(pte_pfn(*pte)));
goto out_unlock;
}
- entry = *pte;
- goto out_mkwrite;
- } else
- goto out_unlock;
+ entry = pte_mkyoung(*pte);
+ entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+ if (ptep_set_access_flags(vma, addr, pte, entry, 1))
+ update_mmu_cache(vma, addr, pte);
+ }
+ goto out_unlock;
}
/* Ok, finally just insert the thing.. */
else
entry = pte_mkspecial(pfn_t_pte(pfn, prot));
-out_mkwrite:
if (mkwrite) {
entry = pte_mkyoung(entry);
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
{
unsigned long pfn, nr_pages;
long offlined_pages;
- int ret, node;
+ int ret, node, nr_isolate_pageblock;
unsigned long flags;
unsigned long valid_start, valid_end;
struct zone *zone;
ret = start_isolate_page_range(start_pfn, end_pfn,
MIGRATE_MOVABLE,
SKIP_HWPOISON | REPORT_FAILURE);
- if (ret) {
+ if (ret < 0) {
reason = "failure to isolate range";
goto failed_removal;
}
+ nr_isolate_pageblock = ret;
arg.start_pfn = start_pfn;
arg.nr_pages = nr_pages;
/* Ok, all of our target is isolated.
We cannot do rollback at this point. */
offline_isolated_pages(start_pfn, end_pfn);
- /* reset pagetype flags and makes migrate type to be MOVABLE */
- undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE);
+
+ /*
+ * Onlining will reset pagetype flags and makes migrate type
+ * MOVABLE, so just need to decrease the number of isolated
+ * pageblocks zone counter here.
+ */
+ spin_lock_irqsave(&zone->lock, flags);
+ zone->nr_isolate_pageblock -= nr_isolate_pageblock;
+ spin_unlock_irqrestore(&zone->lock, flags);
+
/* removal success */
adjust_managed_page_count(pfn_to_page(start_pfn), -offlined_pages);
zone->present_pages -= offlined_pages;
failed_removal_isolated:
undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE);
+ memory_notify(MEM_CANCEL_OFFLINE, &arg);
failed_removal:
pr_debug("memory offlining [mem %#010llx-%#010llx] failed due to %s\n",
(unsigned long long) start_pfn << PAGE_SHIFT,
((unsigned long long) end_pfn << PAGE_SHIFT) - 1,
reason);
- memory_notify(MEM_CANCEL_OFFLINE, &arg);
/* pushback to free area */
mem_hotplug_done();
return ret;
return node_isset(nid, *qp->nmask) == !(flags & MPOL_MF_INVERT);
}
+/*
+ * queue_pages_pmd() has three possible return values:
+ * 1 - pages are placed on the right node or queued successfully.
+ * 0 - THP was split.
+ * -EIO - is migration entry or MPOL_MF_STRICT was specified and an existing
+ * page was already on a node that does not follow the policy.
+ */
static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr,
unsigned long end, struct mm_walk *walk)
{
unsigned long flags;
if (unlikely(is_pmd_migration_entry(*pmd))) {
- ret = 1;
+ ret = -EIO;
goto unlock;
}
page = pmd_page(*pmd);
ret = 1;
flags = qp->flags;
/* go to thp migration */
- if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
+ if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
+ if (!vma_migratable(walk->vma)) {
+ ret = -EIO;
+ goto unlock;
+ }
+
migrate_page_add(page, qp->pagelist, flags);
+ } else
+ ret = -EIO;
unlock:
spin_unlock(ptl);
out:
ptl = pmd_trans_huge_lock(pmd, vma);
if (ptl) {
ret = queue_pages_pmd(pmd, ptl, addr, end, walk);
- if (ret)
+ if (ret > 0)
return 0;
+ else if (ret < 0)
+ return ret;
}
if (pmd_trans_unstable(pmd))
continue;
if (!queue_pages_required(page, qp))
continue;
- migrate_page_add(page, qp->pagelist, flags);
+ if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
+ if (!vma_migratable(vma))
+ break;
+ migrate_page_add(page, qp->pagelist, flags);
+ } else
+ break;
}
pte_unmap_unlock(pte - 1, ptl);
cond_resched();
- return 0;
+ return addr != end ? -EIO : 0;
}
static int queue_pages_hugetlb(pte_t *pte, unsigned long hmask,
unsigned long endvma = vma->vm_end;
unsigned long flags = qp->flags;
- if (!vma_migratable(vma))
+ /*
+ * Need check MPOL_MF_STRICT to return -EIO if possible
+ * regardless of vma_migratable
+ */
+ if (!vma_migratable(vma) &&
+ !(flags & MPOL_MF_STRICT))
return 1;
if (endvma > end)
}
/* queue pages from current vma */
- if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
+ if (flags & MPOL_MF_VALID)
return 0;
return 1;
}
pte = swp_entry_to_pte(entry);
} else if (is_device_public_page(new)) {
pte = pte_mkdevmap(pte);
- flush_dcache_page(new);
}
- } else
- flush_dcache_page(new);
+ }
#ifdef CONFIG_HUGETLB_PAGE
if (PageHuge(new)) {
*/
if (!PageMappingFlags(page))
page->mapping = NULL;
+
+ if (unlikely(is_zone_device_page(newpage))) {
+ if (is_device_public_page(newpage))
+ flush_dcache_page(newpage);
+ } else
+ flush_dcache_page(newpage);
+
}
out:
return rc;
ret = start_isolate_page_range(pfn_max_align_down(start),
pfn_max_align_up(end), migratetype, 0);
- if (ret)
+ if (ret < 0)
return ret;
/*
* FIXME: Now, memory hotplug doesn't call shrink_slab() by itself.
* We just check MOVABLE pages.
*/
- if (!has_unmovable_pages(zone, page, arg.pages_found, migratetype, flags))
+ if (!has_unmovable_pages(zone, page, arg.pages_found, migratetype,
+ isol_flags))
ret = 0;
/*
return NULL;
}
-/*
- * start_isolate_page_range() -- make page-allocation-type of range of pages
- * to be MIGRATE_ISOLATE.
- * @start_pfn: The lower PFN of the range to be isolated.
- * @end_pfn: The upper PFN of the range to be isolated.
- * @migratetype: migrate type to set in error recovery.
+/**
+ * start_isolate_page_range() - make page-allocation-type of range of pages to
+ * be MIGRATE_ISOLATE.
+ * @start_pfn: The lower PFN of the range to be isolated.
+ * @end_pfn: The upper PFN of the range to be isolated.
+ * start_pfn/end_pfn must be aligned to pageblock_order.
+ * @migratetype: Migrate type to set in error recovery.
+ * @flags: The following flags are allowed (they can be combined in
+ * a bit mask)
+ * SKIP_HWPOISON - ignore hwpoison pages
+ * REPORT_FAILURE - report details about the failure to
+ * isolate the range
*
* Making page-allocation-type to be MIGRATE_ISOLATE means free pages in
* the range will never be allocated. Any free pages and pages freed in the
- * future will not be allocated again.
- *
- * start_pfn/end_pfn must be aligned to pageblock_order.
- * Return 0 on success and -EBUSY if any part of range cannot be isolated.
+ * future will not be allocated again. If specified range includes migrate types
+ * other than MOVABLE or CMA, this will fail with -EBUSY. For isolating all
+ * pages in the range finally, the caller have to free all pages in the range.
+ * test_page_isolated() can be used for test it.
*
* There is no high level synchronization mechanism that prevents two threads
- * from trying to isolate overlapping ranges. If this happens, one thread
+ * from trying to isolate overlapping ranges. If this happens, one thread
* will notice pageblocks in the overlapping range already set to isolate.
* This happens in set_migratetype_isolate, and set_migratetype_isolate
- * returns an error. We then clean up by restoring the migration type on
- * pageblocks we may have modified and return -EBUSY to caller. This
+ * returns an error. We then clean up by restoring the migration type on
+ * pageblocks we may have modified and return -EBUSY to caller. This
* prevents two threads from simultaneously working on overlapping ranges.
+ *
+ * Return: the number of isolated pageblocks on success and -EBUSY if any part
+ * of range cannot be isolated.
*/
int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
unsigned migratetype, int flags)
unsigned long pfn;
unsigned long undo_pfn;
struct page *page;
+ int nr_isolate_pageblock = 0;
BUG_ON(!IS_ALIGNED(start_pfn, pageblock_nr_pages));
BUG_ON(!IS_ALIGNED(end_pfn, pageblock_nr_pages));
pfn < end_pfn;
pfn += pageblock_nr_pages) {
page = __first_valid_page(pfn, pageblock_nr_pages);
- if (page &&
- set_migratetype_isolate(page, migratetype, flags)) {
- undo_pfn = pfn;
- goto undo;
+ if (page) {
+ if (set_migratetype_isolate(page, migratetype, flags)) {
+ undo_pfn = pfn;
+ goto undo;
+ }
+ nr_isolate_pageblock++;
}
}
- return 0;
+ return nr_isolate_pageblock;
undo:
for (pfn = start_pfn;
pfn < undo_pfn;
cachep->allocflags = __GFP_COMP;
if (flags & SLAB_CACHE_DMA)
cachep->allocflags |= GFP_DMA;
+ if (flags & SLAB_CACHE_DMA32)
+ cachep->allocflags |= GFP_DMA32;
if (flags & SLAB_RECLAIM_ACCOUNT)
cachep->allocflags |= __GFP_RECLAIMABLE;
cachep->size = size;
static int leaks_show(struct seq_file *m, void *p)
{
- struct kmem_cache *cachep = list_entry(p, struct kmem_cache, list);
+ struct kmem_cache *cachep = list_entry(p, struct kmem_cache,
+ root_caches_node);
struct page *page;
struct kmem_cache_node *n;
const char *name;
/* Legal flag mask for kmem_cache_create(), for various configurations */
-#define SLAB_CORE_FLAGS (SLAB_HWCACHE_ALIGN | SLAB_CACHE_DMA | SLAB_PANIC | \
+#define SLAB_CORE_FLAGS (SLAB_HWCACHE_ALIGN | SLAB_CACHE_DMA | \
+ SLAB_CACHE_DMA32 | SLAB_PANIC | \
SLAB_TYPESAFE_BY_RCU | SLAB_DEBUG_OBJECTS )
#if defined(CONFIG_DEBUG_SLAB)
SLAB_FAILSLAB | SLAB_KASAN)
#define SLAB_MERGE_SAME (SLAB_RECLAIM_ACCOUNT | SLAB_CACHE_DMA | \
- SLAB_ACCOUNT)
+ SLAB_CACHE_DMA32 | SLAB_ACCOUNT)
/*
* Merge control. If this is set then no merging of slab caches will occur.
if (s->flags & SLAB_CACHE_DMA)
s->allocflags |= GFP_DMA;
+ if (s->flags & SLAB_CACHE_DMA32)
+ s->allocflags |= GFP_DMA32;
+
if (s->flags & SLAB_RECLAIM_ACCOUNT)
s->allocflags |= __GFP_RECLAIMABLE;
*/
if (s->flags & SLAB_CACHE_DMA)
*p++ = 'd';
+ if (s->flags & SLAB_CACHE_DMA32)
+ *p++ = 'D';
if (s->flags & SLAB_RECLAIM_ACCOUNT)
*p++ = 'a';
if (s->flags & SLAB_CONSISTENCY_CHECKS)
}
#ifdef CONFIG_MEMORY_HOTREMOVE
-/* Mark all memory sections within the pfn range as online */
+/* Mark all memory sections within the pfn range as offline */
void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn)
{
unsigned long pfn;
* @s: The string to duplicate
* @n: Maximum number of bytes to copy, including the trailing NUL.
*
- * Return: newly allocated copy of @s or %NULL in case of error
+ * Return: newly allocated copy of @s or an ERR_PTR() in case of error
*/
char *strndup_user(const char __user *s, long n)
{
return rc;
}
-static int vlan_dev_fcoe_get_wwn(struct net_device *dev, u64 *wwn, int type)
+static int vlan_dev_fcoe_ddp_target(struct net_device *dev, u16 xid,
+ struct scatterlist *sgl, unsigned int sgc)
{
struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
const struct net_device_ops *ops = real_dev->netdev_ops;
- int rc = -EINVAL;
+ int rc = 0;
+
+ if (ops->ndo_fcoe_ddp_target)
+ rc = ops->ndo_fcoe_ddp_target(real_dev, xid, sgl, sgc);
- if (ops->ndo_fcoe_get_wwn)
- rc = ops->ndo_fcoe_get_wwn(real_dev, wwn, type);
return rc;
}
+#endif
-static int vlan_dev_fcoe_ddp_target(struct net_device *dev, u16 xid,
- struct scatterlist *sgl, unsigned int sgc)
+#ifdef NETDEV_FCOE_WWNN
+static int vlan_dev_fcoe_get_wwn(struct net_device *dev, u64 *wwn, int type)
{
struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
const struct net_device_ops *ops = real_dev->netdev_ops;
- int rc = 0;
-
- if (ops->ndo_fcoe_ddp_target)
- rc = ops->ndo_fcoe_ddp_target(real_dev, xid, sgl, sgc);
+ int rc = -EINVAL;
+ if (ops->ndo_fcoe_get_wwn)
+ rc = ops->ndo_fcoe_get_wwn(real_dev, wwn, type);
return rc;
}
#endif
.ndo_fcoe_ddp_done = vlan_dev_fcoe_ddp_done,
.ndo_fcoe_enable = vlan_dev_fcoe_enable,
.ndo_fcoe_disable = vlan_dev_fcoe_disable,
- .ndo_fcoe_get_wwn = vlan_dev_fcoe_get_wwn,
.ndo_fcoe_ddp_target = vlan_dev_fcoe_ddp_target,
#endif
+#ifdef NETDEV_FCOE_WWNN
+ .ndo_fcoe_get_wwn = vlan_dev_fcoe_get_wwn,
+#endif
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_poll_controller = vlan_dev_poll_controller,
.ndo_netpoll_setup = vlan_dev_netpoll_setup,
return NETDEV_TX_OK;
}
rt = (struct rtable *) dst;
- if (rt->rt_gateway)
- daddr = &rt->rt_gateway;
+ if (rt->rt_gw_family == AF_INET)
+ daddr = &rt->rt_gw4;
else
daddr = &ip_hdr(skb)->daddr;
n = dst_neigh_lookup(dst, daddr);
static int lec_mcast_attach(struct atm_vcc *vcc, int arg)
{
- if (arg < 0 || arg >= MAX_LEC_ITF || !dev_lec[arg])
+ if (arg < 0 || arg >= MAX_LEC_ITF)
+ return -EINVAL;
+ arg = array_index_nospec(arg, MAX_LEC_ITF);
+ if (!dev_lec[arg])
return -EINVAL;
vcc->proto_data = dev_lec[arg];
return lec_mcast_make(netdev_priv(dev_lec[arg]), vcc);
i = arg;
if (arg >= MAX_LEC_ITF)
return -EINVAL;
+ i = array_index_nospec(arg, MAX_LEC_ITF);
if (!dev_lec[i]) {
int size;
ret = cfg80211_get_station(real_netdev, neigh->addr, &sinfo);
- /* free the TID stats immediately */
- cfg80211_sinfo_release_content(&sinfo);
+ if (!ret) {
+ /* free the TID stats immediately */
+ cfg80211_sinfo_release_content(&sinfo);
+ }
dev_put(real_netdev);
if (ret == -ENOENT) {
const u8 *mac, const unsigned short vid)
{
struct batadv_bla_claim search_claim, *claim;
+ struct batadv_bla_claim *claim_removed_entry;
+ struct hlist_node *claim_removed_node;
ether_addr_copy(search_claim.addr, mac);
search_claim.vid = vid;
batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): %pM, vid %d\n", __func__,
mac, batadv_print_vid(vid));
- batadv_hash_remove(bat_priv->bla.claim_hash, batadv_compare_claim,
- batadv_choose_claim, claim);
- batadv_claim_put(claim); /* reference from the hash is gone */
+ claim_removed_node = batadv_hash_remove(bat_priv->bla.claim_hash,
+ batadv_compare_claim,
+ batadv_choose_claim, claim);
+ if (!claim_removed_node)
+ goto free_claim;
+ /* reference from the hash is gone */
+ claim_removed_entry = hlist_entry(claim_removed_node,
+ struct batadv_bla_claim, hash_entry);
+ batadv_claim_put(claim_removed_entry);
+
+free_claim:
/* don't need the reference from hash_find() anymore */
batadv_claim_put(claim);
}
struct attribute *attr,
char *buff, size_t count)
{
- struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj);
struct net_device *net_dev = batadv_kobj_to_netdev(kobj);
struct batadv_hard_iface *hard_iface;
+ struct batadv_priv *bat_priv;
u32 tp_override;
u32 old_tp_override;
bool ret;
atomic_set(&hard_iface->bat_v.throughput_override, tp_override);
- batadv_netlink_notify_hardif(bat_priv, hard_iface);
+ if (hard_iface->soft_iface) {
+ bat_priv = netdev_priv(hard_iface->soft_iface);
+ batadv_netlink_notify_hardif(bat_priv, hard_iface);
+ }
out:
batadv_hardif_put(hard_iface);
struct batadv_tt_global_entry *tt_global,
const char *message)
{
+ struct batadv_tt_global_entry *tt_removed_entry;
+ struct hlist_node *tt_removed_node;
+
batadv_dbg(BATADV_DBG_TT, bat_priv,
"Deleting global tt entry %pM (vid: %d): %s\n",
tt_global->common.addr,
batadv_print_vid(tt_global->common.vid), message);
- batadv_hash_remove(bat_priv->tt.global_hash, batadv_compare_tt,
- batadv_choose_tt, &tt_global->common);
- batadv_tt_global_entry_put(tt_global);
+ tt_removed_node = batadv_hash_remove(bat_priv->tt.global_hash,
+ batadv_compare_tt,
+ batadv_choose_tt,
+ &tt_global->common);
+ if (!tt_removed_node)
+ return;
+
+ /* drop reference of remove hash entry */
+ tt_removed_entry = hlist_entry(tt_removed_node,
+ struct batadv_tt_global_entry,
+ common.hash_entry);
+ batadv_tt_global_entry_put(tt_removed_entry);
}
/**
unsigned short vid, const char *message,
bool roaming)
{
+ struct batadv_tt_local_entry *tt_removed_entry;
struct batadv_tt_local_entry *tt_local_entry;
u16 flags, curr_flags = BATADV_NO_FLAGS;
- void *tt_entry_exists;
+ struct hlist_node *tt_removed_node;
tt_local_entry = batadv_tt_local_hash_find(bat_priv, addr, vid);
if (!tt_local_entry)
*/
batadv_tt_local_event(bat_priv, tt_local_entry, BATADV_TT_CLIENT_DEL);
- tt_entry_exists = batadv_hash_remove(bat_priv->tt.local_hash,
+ tt_removed_node = batadv_hash_remove(bat_priv->tt.local_hash,
batadv_compare_tt,
batadv_choose_tt,
&tt_local_entry->common);
- if (!tt_entry_exists)
+ if (!tt_removed_node)
goto out;
- /* extra call to free the local tt entry */
- batadv_tt_local_entry_put(tt_local_entry);
+ /* drop reference of remove hash entry */
+ tt_removed_entry = hlist_entry(tt_removed_node,
+ struct batadv_tt_local_entry,
+ common.hash_entry);
+ batadv_tt_local_entry_put(tt_removed_entry);
out:
if (tt_local_entry)
struct sock *sk = sock->sk;
int err = 0;
- BT_DBG("sk %p %pMR", sk, &sa->sco_bdaddr);
-
if (!addr || addr_len < sizeof(struct sockaddr_sco) ||
addr->sa_family != AF_BLUETOOTH)
return -EINVAL;
+ BT_DBG("sk %p %pMR", sk, &sa->sco_bdaddr);
+
lock_sock(sk);
if (sk->sk_state != BT_OPEN) {
-obj-y := test_run.o
+obj-$(CONFIG_BPF_SYSCALL) := test_run.o
return data;
}
+static void *bpf_ctx_init(const union bpf_attr *kattr, u32 max_size)
+{
+ void __user *data_in = u64_to_user_ptr(kattr->test.ctx_in);
+ void __user *data_out = u64_to_user_ptr(kattr->test.ctx_out);
+ u32 size = kattr->test.ctx_size_in;
+ void *data;
+ int err;
+
+ if (!data_in && !data_out)
+ return NULL;
+
+ data = kzalloc(max_size, GFP_USER);
+ if (!data)
+ return ERR_PTR(-ENOMEM);
+
+ if (data_in) {
+ err = bpf_check_uarg_tail_zero(data_in, max_size, size);
+ if (err) {
+ kfree(data);
+ return ERR_PTR(err);
+ }
+
+ size = min_t(u32, max_size, size);
+ if (copy_from_user(data, data_in, size)) {
+ kfree(data);
+ return ERR_PTR(-EFAULT);
+ }
+ }
+ return data;
+}
+
+static int bpf_ctx_finish(const union bpf_attr *kattr,
+ union bpf_attr __user *uattr, const void *data,
+ u32 size)
+{
+ void __user *data_out = u64_to_user_ptr(kattr->test.ctx_out);
+ int err = -EFAULT;
+ u32 copy_size = size;
+
+ if (!data || !data_out)
+ return 0;
+
+ if (copy_size > kattr->test.ctx_size_out) {
+ copy_size = kattr->test.ctx_size_out;
+ err = -ENOSPC;
+ }
+
+ if (copy_to_user(data_out, data, copy_size))
+ goto out;
+ if (copy_to_user(&uattr->test.ctx_size_out, &size, sizeof(size)))
+ goto out;
+ if (err != -ENOSPC)
+ err = 0;
+out:
+ return err;
+}
+
+/**
+ * range_is_zero - test whether buffer is initialized
+ * @buf: buffer to check
+ * @from: check from this position
+ * @to: check up until (excluding) this position
+ *
+ * This function returns true if the there is a non-zero byte
+ * in the buf in the range [from,to).
+ */
+static inline bool range_is_zero(void *buf, size_t from, size_t to)
+{
+ return !memchr_inv((u8 *)buf + from, 0, to - from);
+}
+
+static int convert___skb_to_skb(struct sk_buff *skb, struct __sk_buff *__skb)
+{
+ struct qdisc_skb_cb *cb = (struct qdisc_skb_cb *)skb->cb;
+
+ if (!__skb)
+ return 0;
+
+ /* make sure the fields we don't use are zeroed */
+ if (!range_is_zero(__skb, 0, offsetof(struct __sk_buff, priority)))
+ return -EINVAL;
+
+ /* priority is allowed */
+
+ if (!range_is_zero(__skb, offsetof(struct __sk_buff, priority) +
+ FIELD_SIZEOF(struct __sk_buff, priority),
+ offsetof(struct __sk_buff, cb)))
+ return -EINVAL;
+
+ /* cb is allowed */
+
+ if (!range_is_zero(__skb, offsetof(struct __sk_buff, cb) +
+ FIELD_SIZEOF(struct __sk_buff, cb),
+ sizeof(struct __sk_buff)))
+ return -EINVAL;
+
+ skb->priority = __skb->priority;
+ memcpy(&cb->data, __skb->cb, QDISC_CB_PRIV_LEN);
+
+ return 0;
+}
+
+static void convert_skb_to___skb(struct sk_buff *skb, struct __sk_buff *__skb)
+{
+ struct qdisc_skb_cb *cb = (struct qdisc_skb_cb *)skb->cb;
+
+ if (!__skb)
+ return;
+
+ __skb->priority = skb->priority;
+ memcpy(__skb->cb, &cb->data, QDISC_CB_PRIV_LEN);
+}
+
int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
union bpf_attr __user *uattr)
{
bool is_l2 = false, is_direct_pkt_access = false;
u32 size = kattr->test.data_size_in;
u32 repeat = kattr->test.repeat;
+ struct __sk_buff *ctx = NULL;
u32 retval, duration;
int hh_len = ETH_HLEN;
struct sk_buff *skb;
if (IS_ERR(data))
return PTR_ERR(data);
+ ctx = bpf_ctx_init(kattr, sizeof(struct __sk_buff));
+ if (IS_ERR(ctx)) {
+ kfree(data);
+ return PTR_ERR(ctx);
+ }
+
switch (prog->type) {
case BPF_PROG_TYPE_SCHED_CLS:
case BPF_PROG_TYPE_SCHED_ACT:
sk = kzalloc(sizeof(struct sock), GFP_USER);
if (!sk) {
kfree(data);
+ kfree(ctx);
return -ENOMEM;
}
sock_net_set(sk, current->nsproxy->net_ns);
skb = build_skb(data, 0);
if (!skb) {
kfree(data);
+ kfree(ctx);
kfree(sk);
return -ENOMEM;
}
__skb_push(skb, hh_len);
if (is_direct_pkt_access)
bpf_compute_data_pointers(skb);
+ ret = convert___skb_to_skb(skb, ctx);
+ if (ret)
+ goto out;
ret = bpf_test_run(prog, skb, repeat, &retval, &duration);
- if (ret) {
- kfree_skb(skb);
- kfree(sk);
- return ret;
- }
+ if (ret)
+ goto out;
if (!is_l2) {
if (skb_headroom(skb) < hh_len) {
int nhead = HH_DATA_ALIGN(hh_len - skb_headroom(skb));
if (pskb_expand_head(skb, nhead, 0, GFP_USER)) {
- kfree_skb(skb);
- kfree(sk);
- return -ENOMEM;
+ ret = -ENOMEM;
+ goto out;
}
}
memset(__skb_push(skb, hh_len), 0, hh_len);
}
+ convert_skb_to___skb(skb, ctx);
size = skb->len;
/* bpf program can never convert linear skb to non-linear */
if (WARN_ON_ONCE(skb_is_nonlinear(skb)))
size = skb_headlen(skb);
ret = bpf_test_finish(kattr, uattr, skb->data, size, retval, duration);
+ if (!ret)
+ ret = bpf_ctx_finish(kattr, uattr, ctx,
+ sizeof(struct __sk_buff));
+out:
kfree_skb(skb);
kfree(sk);
+ kfree(ctx);
return ret;
}
void *data;
int ret;
+ if (kattr->test.ctx_in || kattr->test.ctx_out)
+ return -EINVAL;
+
data = bpf_test_init(kattr, size, XDP_PACKET_HEADROOM + NET_IP_ALIGN, 0);
if (IS_ERR(data))
return PTR_ERR(data);
if (prog->type != BPF_PROG_TYPE_FLOW_DISSECTOR)
return -EINVAL;
+ if (kattr->test.ctx_in || kattr->test.ctx_out)
+ return -EINVAL;
+
data = bpf_test_init(kattr, size, NET_SKB_PAD + NET_IP_ALIGN,
SKB_DATA_ALIGN(sizeof(struct skb_shared_info)));
if (IS_ERR(data))
u8 *arpptr, *sha;
__be32 sip, tip;
- BR_INPUT_SKB_CB(skb)->proxyarp_replied = false;
+ BR_INPUT_SKB_CB(skb)->proxyarp_replied = 0;
if ((dev->flags & IFF_NOARP) ||
!pskb_may_pull(skb, arp_hdr_len(dev)))
return;
if (ipv4_is_zeronet(sip) || sip == tip) {
/* prevent flooding to neigh suppress ports */
- BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
+ BR_INPUT_SKB_CB(skb)->proxyarp_replied = 1;
return;
}
}
/* its our local ip, so don't proxy reply
* and don't forward to neigh suppress ports
*/
- BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
+ BR_INPUT_SKB_CB(skb)->proxyarp_replied = 1;
return;
}
*/
if (replied ||
br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED))
- BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
+ BR_INPUT_SKB_CB(skb)->proxyarp_replied = 1;
}
neigh_release(n);
struct ipv6hdr *iphdr;
struct neighbour *n;
- BR_INPUT_SKB_CB(skb)->proxyarp_replied = false;
+ BR_INPUT_SKB_CB(skb)->proxyarp_replied = 0;
if (p && (p->flags & BR_NEIGH_SUPPRESS))
return;
if (msg->icmph.icmp6_type == NDISC_NEIGHBOUR_ADVERTISEMENT &&
!msg->icmph.icmp6_solicited) {
/* prevent flooding to neigh suppress ports */
- BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
+ BR_INPUT_SKB_CB(skb)->proxyarp_replied = 1;
return;
}
if (ipv6_addr_any(saddr) || !ipv6_addr_cmp(saddr, daddr)) {
/* prevent flooding to neigh suppress ports */
- BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
+ BR_INPUT_SKB_CB(skb)->proxyarp_replied = 1;
return;
}
/* its our own ip, so don't proxy reply
* and don't forward to arp suppress ports
*/
- BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
+ BR_INPUT_SKB_CB(skb)->proxyarp_replied = 1;
return;
}
*/
if (replied ||
br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED))
- BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
+ BR_INPUT_SKB_CB(skb)->proxyarp_replied = 1;
}
neigh_release(n);
}
.key_offset = offsetof(struct net_bridge_fdb_entry, key),
.key_len = sizeof(struct net_bridge_fdb_key),
.automatic_shrinking = true,
- .locks_mul = 1,
};
static struct kmem_cache *br_fdb_cache __read_mostly;
struct net_bridge_port *prev, struct net_bridge_port *p,
struct sk_buff *skb, bool local_orig)
{
+ u8 igmp_type = br_multicast_igmp_type(skb);
int err;
if (!should_deliver(p, skb))
err = deliver_clone(prev, skb, local_orig);
if (err)
return ERR_PTR(err);
-
out:
+ br_multicast_count(p->br, p, skb, igmp_type, BR_MCAST_DIR_TX);
+
return p;
}
void br_flood(struct net_bridge *br, struct sk_buff *skb,
enum br_pkt_type pkt_type, bool local_rcv, bool local_orig)
{
- u8 igmp_type = br_multicast_igmp_type(skb);
struct net_bridge_port *prev = NULL;
struct net_bridge_port *p;
prev = maybe_deliver(prev, p, skb, local_orig);
if (IS_ERR(prev))
goto out;
- if (prev == p)
- br_multicast_count(p->br, p, skb, igmp_type,
- BR_MCAST_DIR_TX);
}
if (!prev)
bool local_rcv, bool local_orig)
{
struct net_device *dev = BR_INPUT_SKB_CB(skb)->brdev;
- u8 igmp_type = br_multicast_igmp_type(skb);
struct net_bridge *br = netdev_priv(dev);
struct net_bridge_port *prev = NULL;
struct net_bridge_port_group *p;
}
prev = maybe_deliver(prev, port, skb, local_orig);
-delivered:
if (IS_ERR(prev))
goto out;
- if (prev == port)
- br_multicast_count(port->br, port, skb, igmp_type,
- BR_MCAST_DIR_TX);
-
+delivered:
if ((unsigned long)lport >= (unsigned long)port)
p = rcu_dereference(p->next);
if ((unsigned long)rport >= (unsigned long)port)
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/netfilter_bridge.h>
+#ifdef CONFIG_NETFILTER_FAMILY_BRIDGE
+#include <net/netfilter/nf_queue.h>
+#endif
#include <linux/neighbour.h>
#include <net/arp.h>
#include <linux/export.h>
#include "br_private.h"
#include "br_private_tunnel.h"
-/* Hook for brouter */
-br_should_route_hook_t __rcu *br_should_route_hook __read_mostly;
-EXPORT_SYMBOL(br_should_route_hook);
-
static int
br_netif_receive_skb(struct net *net, struct sock *sk, struct sk_buff *skb)
{
/* note: already called with rcu_read_lock */
static int br_handle_local_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
- struct net_bridge_port *p = br_port_get_rcu(skb->dev);
-
__br_handle_local_finish(skb);
- BR_INPUT_SKB_CB(skb)->brdev = p->br->dev;
- br_pass_frame_up(skb);
- return 0;
+ /* return 1 to signal the okfn() was called so it's ok to use the skb */
+ return 1;
+}
+
+static int nf_hook_bridge_pre(struct sk_buff *skb, struct sk_buff **pskb)
+{
+#ifdef CONFIG_NETFILTER_FAMILY_BRIDGE
+ struct nf_hook_entries *e = NULL;
+ struct nf_hook_state state;
+ unsigned int verdict, i;
+ struct net *net;
+ int ret;
+
+ net = dev_net(skb->dev);
+#ifdef HAVE_JUMP_LABEL
+ if (!static_key_false(&nf_hooks_needed[NFPROTO_BRIDGE][NF_BR_PRE_ROUTING]))
+ goto frame_finish;
+#endif
+
+ e = rcu_dereference(net->nf.hooks_bridge[NF_BR_PRE_ROUTING]);
+ if (!e)
+ goto frame_finish;
+
+ nf_hook_state_init(&state, NF_BR_PRE_ROUTING,
+ NFPROTO_BRIDGE, skb->dev, NULL, NULL,
+ net, br_handle_frame_finish);
+
+ for (i = 0; i < e->num_hook_entries; i++) {
+ verdict = nf_hook_entry_hookfn(&e->hooks[i], skb, &state);
+ switch (verdict & NF_VERDICT_MASK) {
+ case NF_ACCEPT:
+ if (BR_INPUT_SKB_CB(skb)->br_netfilter_broute) {
+ *pskb = skb;
+ return RX_HANDLER_PASS;
+ }
+ break;
+ case NF_DROP:
+ kfree_skb(skb);
+ return RX_HANDLER_CONSUMED;
+ case NF_QUEUE:
+ ret = nf_queue(skb, &state, e, i, verdict);
+ if (ret == 1)
+ continue;
+ return RX_HANDLER_CONSUMED;
+ default: /* STOLEN */
+ return RX_HANDLER_CONSUMED;
+ }
+ }
+frame_finish:
+ net = dev_net(skb->dev);
+ br_handle_frame_finish(net, NULL, skb);
+#else
+ br_handle_frame_finish(dev_net(skb->dev), NULL, skb);
+#endif
+ return RX_HANDLER_CONSUMED;
}
/*
struct net_bridge_port *p;
struct sk_buff *skb = *pskb;
const unsigned char *dest = eth_hdr(skb)->h_dest;
- br_should_route_hook_t *rhook;
if (unlikely(skb->pkt_type == PACKET_LOOPBACK))
return RX_HANDLER_PASS;
if (!skb)
return RX_HANDLER_CONSUMED;
+ memset(skb->cb, 0, sizeof(struct br_input_skb_cb));
+
p = br_port_get_rcu(skb->dev);
if (p->flags & BR_VLAN_TUNNEL) {
if (br_handle_ingress_vlan_tunnel(skb, p,
goto forward;
}
- /* Deliver packet to local host only */
- NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, dev_net(skb->dev),
- NULL, skb, skb->dev, NULL, br_handle_local_finish);
- return RX_HANDLER_CONSUMED;
+ /* The else clause should be hit when nf_hook():
+ * - returns < 0 (drop/error)
+ * - returns = 0 (stolen/nf_queue)
+ * Thus return 1 from the okfn() to signal the skb is ok to pass
+ */
+ if (NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN,
+ dev_net(skb->dev), NULL, skb, skb->dev, NULL,
+ br_handle_local_finish) == 1) {
+ return RX_HANDLER_PASS;
+ } else {
+ return RX_HANDLER_CONSUMED;
+ }
}
forward:
switch (p->state) {
case BR_STATE_FORWARDING:
- rhook = rcu_dereference(br_should_route_hook);
- if (rhook) {
- if ((*rhook)(skb)) {
- *pskb = skb;
- return RX_HANDLER_PASS;
- }
- dest = eth_hdr(skb)->h_dest;
- }
- /* fall through */
case BR_STATE_LEARNING:
if (ether_addr_equal(p->br->dev->dev_addr, dest))
skb->pkt_type = PACKET_HOST;
- NF_HOOK(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING,
- dev_net(skb->dev), NULL, skb, skb->dev, NULL,
- br_handle_frame_finish);
- break;
+ return nf_hook_bridge_pre(skb, pskb);
default:
drop:
kfree_skb(skb);
.key_offset = offsetof(struct net_bridge_mdb_entry, addr),
.key_len = sizeof(struct br_ip),
.automatic_shrinking = true,
- .locks_mul = 1,
};
static void br_multicast_start_querier(struct net_bridge *br,
__u16 vid, const unsigned char *src);
#endif
-static inline int br_ip_equal(const struct br_ip *a, const struct br_ip *b)
-{
- if (a->proto != b->proto)
- return 0;
- if (a->vid != b->vid)
- return 0;
- switch (a->proto) {
- case htons(ETH_P_IP):
- return a->u.ip4 == b->u.ip4;
-#if IS_ENABLED(CONFIG_IPV6)
- case htons(ETH_P_IPV6):
- return ipv6_addr_equal(&a->u.ip6, &b->u.ip6);
-#endif
- }
- return 0;
-}
-
static struct net_bridge_mdb_entry *br_mdb_ip_get_rcu(struct net_bridge *br,
struct br_ip *dst)
{
if (ipv4_is_local_multicast(group))
return 0;
+ memset(&br_group, 0, sizeof(br_group));
br_group.u.ip4 = group;
br_group.proto = htons(ETH_P_IP);
br_group.vid = vid;
own_query = port ? &port->ip4_own_query : &br->ip4_own_query;
+ memset(&br_group, 0, sizeof(br_group));
br_group.u.ip4 = group;
br_group.proto = htons(ETH_P_IP);
br_group.vid = vid;
own_query = port ? &port->ip6_own_query : &br->ip6_own_query;
+ memset(&br_group, 0, sizeof(br_group));
br_group.u.ip6 = *group;
br_group.proto = htons(ETH_P_IPV6);
br_group.vid = vid;
__br_multicast_open(br, query);
- list_for_each_entry(port, &br->port_list, list) {
+ rcu_read_lock();
+ list_for_each_entry_rcu(port, &br->port_list, list) {
if (port->state == BR_STATE_DISABLED ||
port->state == BR_STATE_BLOCKING)
continue;
br_multicast_enable(&port->ip6_own_query);
#endif
}
+ rcu_read_unlock();
}
int br_multicast_toggle(struct net_bridge *br, unsigned long val)
nla_put_u8(skb, IFLA_BR_VLAN_STATS_ENABLED,
br_opt_get(br, BROPT_VLAN_STATS_ENABLED)) ||
nla_put_u8(skb, IFLA_BR_VLAN_STATS_PER_PORT,
- br_opt_get(br, IFLA_BR_VLAN_STATS_PER_PORT)))
+ br_opt_get(br, BROPT_VLAN_STATS_PER_PORT)))
return -EMSGSIZE;
#endif
#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
struct net_device *brdev;
#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
- int igmp;
- int mrouters_only;
+ u8 igmp;
+ u8 mrouters_only:1;
#endif
-
- bool proxyarp_replied;
- bool src_port_isolated;
-
+ u8 proxyarp_replied:1;
+ u8 src_port_isolated:1;
#ifdef CONFIG_BRIDGE_VLAN_FILTERING
- bool vlan_filtered;
+ u8 vlan_filtered:1;
+#endif
+#ifdef CONFIG_NETFILTER_FAMILY_BRIDGE
+ u8 br_netfilter_broute:1;
#endif
#ifdef CONFIG_NET_SWITCHDEV
del_timer(&p->forward_delay_timer);
del_timer(&p->hold_timer);
- br_fdb_delete_by_port(br, p, 0, 0);
+ if (!rcu_access_pointer(p->backup_port))
+ br_fdb_delete_by_port(br, p, 0, 0);
br_multicast_disable_port(p);
br_configuration_update(br);
.key_offset = offsetof(struct net_bridge_vlan, vid),
.key_len = sizeof(u16),
.nelem_hint = 3,
- .locks_mul = 1,
.max_size = VLAN_N_VID,
.obj_cmpfn = br_vlan_cmp,
.automatic_shrinking = true,
.key_offset = offsetof(struct net_bridge_vlan, tinfo.tunnel_id),
.key_len = sizeof(__be64),
.nelem_hint = 3,
- .locks_mul = 1,
.obj_cmpfn = br_vlan_tunid_cmp,
.automatic_shrinking = true,
};
#include <linux/module.h>
#include <linux/if_bridge.h>
+#include "../br_private.h"
+
/* EBT_ACCEPT means the frame will be bridged
* EBT_DROP means the frame will be routed
*/
.me = THIS_MODULE,
};
-static int ebt_broute(struct sk_buff *skb)
+static unsigned int ebt_broute(void *priv, struct sk_buff *skb,
+ const struct nf_hook_state *s)
{
+ struct net_bridge_port *p = br_port_get_rcu(skb->dev);
struct nf_hook_state state;
+ unsigned char *dest;
int ret;
+ if (!p || p->state != BR_STATE_FORWARDING)
+ return NF_ACCEPT;
+
nf_hook_state_init(&state, NF_BR_BROUTING,
- NFPROTO_BRIDGE, skb->dev, NULL, NULL,
- dev_net(skb->dev), NULL);
+ NFPROTO_BRIDGE, s->in, NULL, NULL,
+ s->net, NULL);
ret = ebt_do_table(skb, &state, state.net->xt.broute_table);
- if (ret == NF_DROP)
- return 1; /* route it */
- return 0; /* bridge it */
+
+ if (ret != NF_DROP)
+ return ret;
+
+ /* DROP in ebtables -t broute means that the
+ * skb should be routed, not bridged.
+ * This is awkward, but can't be changed for compatibility
+ * reasons.
+ *
+ * We map DROP to ACCEPT and set the ->br_netfilter_broute flag.
+ */
+ BR_INPUT_SKB_CB(skb)->br_netfilter_broute = 1;
+
+ /* undo PACKET_HOST mangling done in br_input in case the dst
+ * address matches the logical bridge but not the port.
+ */
+ dest = eth_hdr(skb)->h_dest;
+ if (skb->pkt_type == PACKET_HOST &&
+ !ether_addr_equal(skb->dev->dev_addr, dest) &&
+ ether_addr_equal(p->br->dev->dev_addr, dest))
+ skb->pkt_type = PACKET_OTHERHOST;
+
+ return NF_ACCEPT;
}
+static const struct nf_hook_ops ebt_ops_broute = {
+ .hook = ebt_broute,
+ .pf = NFPROTO_BRIDGE,
+ .hooknum = NF_BR_PRE_ROUTING,
+ .priority = NF_BR_PRI_FIRST,
+};
+
static int __net_init broute_net_init(struct net *net)
{
- return ebt_register_table(net, &broute_table, NULL,
+ return ebt_register_table(net, &broute_table, &ebt_ops_broute,
&net->xt.broute_table);
}
static void __net_exit broute_net_exit(struct net *net)
{
- ebt_unregister_table(net, net->xt.broute_table, NULL);
+ ebt_unregister_table(net, net->xt.broute_table, &ebt_ops_broute);
}
static struct pernet_operations broute_net_ops = {
static int __init ebtable_broute_init(void)
{
- int ret;
-
- ret = register_pernet_subsys(&broute_net_ops);
- if (ret < 0)
- return ret;
- /* see br_input.c */
- RCU_INIT_POINTER(br_should_route_hook,
- (br_should_route_hook_t *)ebt_broute);
- return 0;
+ return register_pernet_subsys(&broute_net_ops);
}
static void __exit ebtable_broute_fini(void)
{
- RCU_INIT_POINTER(br_should_route_hook, NULL);
- synchronize_net();
unregister_pernet_subsys(&broute_net_ops);
}
mutex_unlock(&ebt_mutex);
WRITE_ONCE(*res, table);
-
- if (!ops)
- return 0;
-
ret = nf_register_net_hooks(net, ops, hweight32(table->valid_hooks));
if (ret) {
__ebt_unregister_table(net, table);
void ebt_unregister_table(struct net *net, struct ebt_table *table,
const struct nf_hook_ops *ops)
{
- if (ops)
- nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks));
+ nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks));
__ebt_unregister_table(net, table);
}
goto noxoff;
if (likely(!netif_queue_stopped(caifd->netdev))) {
+ struct Qdisc *sch;
+
/* If we run with a TX queue, check if the queue is too long*/
txq = netdev_get_tx_queue(skb->dev, 0);
- qlen = qdisc_qlen(rcu_dereference_bh(txq->qdisc));
-
- if (likely(qlen == 0))
+ sch = rcu_dereference_bh(txq->qdisc);
+ if (likely(qdisc_is_empty(sch)))
goto noxoff;
+ /* can check for explicit qdisc len value only !NOLOCK,
+ * always set flow off otherwise
+ */
high = (caifd->netdev->tx_queue_len * q_high) / 100;
- if (likely(qlen < high))
+ if (!(sch->flags & TCQ_F_NOLOCK) && likely(sch->q.qlen < high))
goto noxoff;
}
size_t bytes)
{
struct ceph_bio_iter *it = &cursor->bio_iter;
+ struct page *page = bio_iter_page(it->bio, it->iter);
BUG_ON(bytes > cursor->resid);
BUG_ON(bytes > bio_iter_len(it->bio, it->iter));
return false; /* no more data */
}
- if (!bytes || (it->iter.bi_size && it->iter.bi_bvec_done))
+ if (!bytes || (it->iter.bi_size && it->iter.bi_bvec_done &&
+ page == bio_iter_page(it->bio, it->iter)))
return false; /* more bytes to process in this segment */
if (!it->iter.bi_size) {
size_t bytes)
{
struct bio_vec *bvecs = cursor->data->bvec_pos.bvecs;
+ struct page *page = bvec_iter_page(bvecs, cursor->bvec_iter);
BUG_ON(bytes > cursor->resid);
BUG_ON(bytes > bvec_iter_len(bvecs, cursor->bvec_iter));
return false; /* no more data */
}
- if (!bytes || cursor->bvec_iter.bi_bvec_done)
+ if (!bytes || (cursor->bvec_iter.bi_bvec_done &&
+ page == bvec_iter_page(bvecs, cursor->bvec_iter)))
return false; /* more bytes to process in this segment */
BUG_ON(cursor->last_piece);
unsigned int flags,
void (*destructor)(struct sock *sk,
struct sk_buff *skb),
- int *peeked, int *off, int *err,
+ int *off, int *err,
struct sk_buff **last)
{
bool peek_at_off = false;
return NULL;
}
}
- *peeked = 1;
refcount_inc(&skb->users);
} else {
__skb_unlink(skb, queue);
* @sk: socket
* @flags: MSG\_ flags
* @destructor: invoked under the receive lock on successful dequeue
- * @peeked: returns non-zero if this packet has been seen before
* @off: an offset in bytes to peek skb from. Returns an offset
* within an skb where data actually starts
* @err: error code returned
struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags,
void (*destructor)(struct sock *sk,
struct sk_buff *skb),
- int *peeked, int *off, int *err,
+ int *off, int *err,
struct sk_buff **last)
{
struct sk_buff_head *queue = &sk->sk_receive_queue;
if (error)
goto no_packet;
- *peeked = 0;
do {
/* Again only user level code calls this function, so nothing
* interrupt level will suddenly eat the receive_queue.
*/
spin_lock_irqsave(&queue->lock, cpu_flags);
skb = __skb_try_recv_from_queue(sk, queue, flags, destructor,
- peeked, off, &error, last);
+ off, &error, last);
spin_unlock_irqrestore(&queue->lock, cpu_flags);
if (error)
goto no_packet;
break;
sk_busy_loop(sk, flags & MSG_DONTWAIT);
- } while (!skb_queue_empty(&sk->sk_receive_queue));
+ } while (sk->sk_receive_queue.prev != *last);
error = -EAGAIN;
struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
void (*destructor)(struct sock *sk,
struct sk_buff *skb),
- int *peeked, int *off, int *err)
+ int *off, int *err)
{
struct sk_buff *skb, *last;
long timeo;
timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
do {
- skb = __skb_try_recv_datagram(sk, flags, destructor, peeked,
- off, err, &last);
+ skb = __skb_try_recv_datagram(sk, flags, destructor, off, err,
+ &last);
if (skb)
return skb;
struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned int flags,
int noblock, int *err)
{
- int peeked, off = 0;
+ int off = 0;
return __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0),
- NULL, &peeked, &off, err);
+ NULL, &off, err);
}
EXPORT_SYMBOL(skb_recv_datagram);
#include <trace/events/napi.h>
#include <trace/events/net.h>
#include <trace/events/skb.h>
-#include <linux/pci.h>
#include <linux/inetdevice.h>
#include <linux/cpu_rmap.h>
#include <linux/static_key.h>
BUG_ON(!dev_net(dev));
net = dev_net(dev);
- if (dev->flags & IFF_UP)
+
+ /* Some auto-enslaved devices e.g. failover slaves are
+ * special, as userspace might rename the device after
+ * the interface had been brought up and running since
+ * the point kernel initiated auto-enslavement. Allow
+ * live name change even when these slave devices are
+ * up and running.
+ *
+ * Typically, users of these auto-enslaving devices
+ * don't actually care about slave name change, as
+ * they are supposed to operate on master interface
+ * directly.
+ */
+ if (dev->flags & IFF_UP &&
+ likely(!(dev->priv_flags & IFF_LIVE_RENAME_OK)))
return -EBUSY;
write_seqcount_begin(&devnet_rename_seq);
#define skb_update_prio(skb)
#endif
-DEFINE_PER_CPU(int, xmit_recursion);
-EXPORT_SYMBOL(xmit_recursion);
-
/**
* dev_loopback_xmit - loop back @skb
* @net: network namespace this loopback is happening in
int cpu = smp_processor_id(); /* ok because BHs are off */
if (txq->xmit_lock_owner != cpu) {
- if (unlikely(__this_cpu_read(xmit_recursion) >
- XMIT_RECURSION_LIMIT))
+ if (dev_xmit_recursion())
goto recursion_alert;
skb = validate_xmit_skb(skb, dev, &again);
HARD_TX_LOCK(dev, txq, cpu);
if (!netif_xmit_stopped(txq)) {
- __this_cpu_inc(xmit_recursion);
+ dev_xmit_recursion_inc();
skb = dev_hard_start_xmit(skb, dev, txq, &rc);
- __this_cpu_dec(xmit_recursion);
+ dev_xmit_recursion_dec();
if (dev_xmit_complete(rc)) {
HARD_TX_UNLOCK(dev, txq);
goto out;
if (pt_prev->list_func != NULL)
pt_prev->list_func(head, pt_prev, orig_dev);
else
- list_for_each_entry_safe(skb, next, head, list)
+ list_for_each_entry_safe(skb, next, head, list) {
+ skb_list_del_init(skb);
pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
+ }
}
static void __netif_receive_skb_list_core(struct list_head *head, bool pfmemalloc)
struct netdev_phys_item_id first = { };
struct net_device *lower_dev;
struct list_head *iter;
- int err = -EOPNOTSUPP;
+ int err;
+
+ if (ops->ndo_get_port_parent_id) {
+ err = ops->ndo_get_port_parent_id(dev, ppid);
+ if (err != -EOPNOTSUPP)
+ return err;
+ }
- if (ops->ndo_get_port_parent_id)
- return ops->ndo_get_port_parent_id(dev, ppid);
+ err = devlink_compat_switch_id_get(dev, ppid);
+ if (!err || err != -EOPNOTSUPP)
+ return err;
if (!recurse)
- return err;
+ return -EOPNOTSUPP;
netdev_for_each_lower_dev(dev, lower_dev, iter) {
err = dev_get_port_parent_id(lower_dev, ppid, recurse);
void devlink_port_type_eth_set(struct devlink_port *devlink_port,
struct net_device *netdev)
{
+ const struct net_device_ops *ops = netdev->netdev_ops;
+
/* If driver registers devlink port, it should set devlink port
* attributes accordingly so the compat functions are called
* and the original ops are not used.
*/
- if (netdev->netdev_ops->ndo_get_phys_port_name) {
+ if (ops->ndo_get_phys_port_name) {
/* Some drivers use the same set of ndos for netdevs
* that have devlink_port registered and also for
* those who don't. Make sure that ndo_get_phys_port_name
* returns -EOPNOTSUPP here in case it is defined.
* Warn if not.
*/
- const struct net_device_ops *ops = netdev->netdev_ops;
char name[IFNAMSIZ];
int err;
err = ops->ndo_get_phys_port_name(netdev, name, sizeof(name));
WARN_ON(err != -EOPNOTSUPP);
}
+ if (ops->ndo_get_port_parent_id) {
+ /* Some drivers use the same set of ndos for netdevs
+ * that have devlink_port registered and also for
+ * those who don't. Make sure that ndo_get_port_parent_id
+ * returns -EOPNOTSUPP here in case it is defined.
+ * Warn if not.
+ */
+ struct netdev_phys_item_id ppid;
+ int err;
+
+ err = ops->ndo_get_port_parent_id(netdev, &ppid);
+ WARN_ON(err != -EOPNOTSUPP);
+ }
__devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_ETH, netdev);
}
EXPORT_SYMBOL_GPL(devlink_port_type_eth_set);
* @split: indicates if this is split port
* @split_subport_number: if the port is split, this is the number
* of subport.
+ * @switch_id: if the port is part of switch, this is buffer with ID,
+ * otwerwise this is NULL
+ * @switch_id_len: length of the switch_id buffer
*/
void devlink_port_attrs_set(struct devlink_port *devlink_port,
enum devlink_port_flavour flavour,
u32 port_number, bool split,
- u32 split_subport_number)
+ u32 split_subport_number,
+ const unsigned char *switch_id,
+ unsigned char switch_id_len)
{
struct devlink_port_attrs *attrs = &devlink_port->attrs;
attrs->port_number = port_number;
attrs->split = split;
attrs->split_subport_number = split_subport_number;
+ if (switch_id) {
+ attrs->switch_port = true;
+ if (WARN_ON(switch_id_len > MAX_PHYS_ITEM_ID_LEN))
+ switch_id_len = MAX_PHYS_ITEM_ID_LEN;
+ memcpy(attrs->switch_id.id, switch_id, switch_id_len);
+ attrs->switch_id.id_len = switch_id_len;
+ } else {
+ attrs->switch_port = false;
+ }
}
EXPORT_SYMBOL_GPL(devlink_port_attrs_set);
return __devlink_port_phys_port_name_get(devlink_port, name, len);
}
+int devlink_compat_switch_id_get(struct net_device *dev,
+ struct netdev_phys_item_id *ppid)
+{
+ struct devlink_port *devlink_port;
+
+ /* RTNL mutex is held here which ensures that devlink_port
+ * instance cannot disappear in the middle. No need to take
+ * any devlink lock as only permanent values are accessed.
+ */
+ ASSERT_RTNL();
+ devlink_port = netdev_to_devlink_port(dev);
+ if (!devlink_port || !devlink_port->attrs.switch_port)
+ return -EOPNOTSUPP;
+
+ memcpy(ppid, &devlink_port->attrs.switch_id, sizeof(*ppid));
+
+ return 0;
+}
+
static int __init devlink_init(void)
{
return genl_register_family(&devlink_nl_family);
WARN_ON_ONCE(!ret);
gstrings.len = ret;
- data = vzalloc(array_size(gstrings.len, ETH_GSTRING_LEN));
- if (gstrings.len && !data)
- return -ENOMEM;
- __ethtool_get_strings(dev, gstrings.string_set, data);
+ if (gstrings.len) {
+ data = vzalloc(array_size(gstrings.len, ETH_GSTRING_LEN));
+ if (!data)
+ return -ENOMEM;
+
+ __ethtool_get_strings(dev, gstrings.string_set, data);
+ } else {
+ data = NULL;
+ }
ret = -EFAULT;
if (copy_to_user(useraddr, &gstrings, sizeof(gstrings)))
return -EFAULT;
stats.n_stats = n_stats;
- data = vzalloc(array_size(n_stats, sizeof(u64)));
- if (n_stats && !data)
- return -ENOMEM;
- ops->get_ethtool_stats(dev, &stats, data);
+ if (n_stats) {
+ data = vzalloc(array_size(n_stats, sizeof(u64)));
+ if (!data)
+ return -ENOMEM;
+ ops->get_ethtool_stats(dev, &stats, data);
+ } else {
+ data = NULL;
+ }
ret = -EFAULT;
if (copy_to_user(useraddr, &stats, sizeof(stats)))
return -EFAULT;
stats.n_stats = n_stats;
- data = vzalloc(array_size(n_stats, sizeof(u64)));
- if (n_stats && !data)
- return -ENOMEM;
- if (dev->phydev && !ops->get_ethtool_phy_stats) {
- ret = phy_ethtool_get_stats(dev->phydev, &stats, data);
- if (ret < 0)
- return ret;
+ if (n_stats) {
+ data = vzalloc(array_size(n_stats, sizeof(u64)));
+ if (!data)
+ return -ENOMEM;
+
+ if (dev->phydev && !ops->get_ethtool_phy_stats) {
+ ret = phy_ethtool_get_stats(dev->phydev, &stats, data);
+ if (ret < 0)
+ goto out;
+ } else {
+ ops->get_ethtool_phy_stats(dev, &stats, data);
+ }
} else {
- ops->get_ethtool_phy_stats(dev, &stats, data);
+ data = NULL;
}
ret = -EFAULT;
goto err_upper_link;
}
- slave_dev->priv_flags |= IFF_FAILOVER_SLAVE;
+ slave_dev->priv_flags |= (IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK);
if (fops && fops->slave_register &&
!fops->slave_register(slave_dev, failover_dev))
return NOTIFY_OK;
netdev_upper_dev_unlink(slave_dev, failover_dev);
- slave_dev->priv_flags &= ~IFF_FAILOVER_SLAVE;
+ slave_dev->priv_flags &= ~(IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK);
err_upper_link:
netdev_rx_handler_unregister(slave_dev);
done:
netdev_rx_handler_unregister(slave_dev);
netdev_upper_dev_unlink(slave_dev, failover_dev);
- slave_dev->priv_flags &= ~IFF_FAILOVER_SLAVE;
+ slave_dev->priv_flags &= ~(IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK);
if (fops && fops->slave_unregister &&
!fops->slave_unregister(slave_dev, failover_dev))
{
int ret;
- if (unlikely(__this_cpu_read(xmit_recursion) > XMIT_RECURSION_LIMIT)) {
+ if (dev_xmit_recursion()) {
net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n");
kfree_skb(skb);
return -ENETDOWN;
skb->dev = dev;
- __this_cpu_inc(xmit_recursion);
+ dev_xmit_recursion_inc();
ret = dev_queue_xmit(skb);
- __this_cpu_dec(xmit_recursion);
+ dev_xmit_recursion_dec();
return ret;
}
#define BPF_F_ADJ_ROOM_MASK (BPF_F_ADJ_ROOM_FIXED_GSO | \
BPF_F_ADJ_ROOM_ENCAP_L3_MASK | \
BPF_F_ADJ_ROOM_ENCAP_L4_GRE | \
- BPF_F_ADJ_ROOM_ENCAP_L4_UDP)
+ BPF_F_ADJ_ROOM_ENCAP_L4_UDP | \
+ BPF_F_ADJ_ROOM_ENCAP_L2( \
+ BPF_ADJ_ROOM_ENCAP_L2_MASK))
static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff,
u64 flags)
{
+ u8 inner_mac_len = flags >> BPF_ADJ_ROOM_ENCAP_L2_SHIFT;
bool encap = flags & BPF_F_ADJ_ROOM_ENCAP_L3_MASK;
u16 mac_len = 0, inner_net = 0, inner_trans = 0;
unsigned int gso_type = SKB_GSO_DODGY;
mac_len = skb->network_header - skb->mac_header;
inner_net = skb->network_header;
+ if (inner_mac_len > len_diff)
+ return -EINVAL;
inner_trans = skb->transport_header;
}
return ret;
if (encap) {
- /* inner mac == inner_net on l3 encap */
- skb->inner_mac_header = inner_net;
+ skb->inner_mac_header = inner_net - inner_mac_len;
skb->inner_network_header = inner_net;
skb->inner_transport_header = inner_trans;
skb_set_inner_protocol(skb, skb->protocol);
gso_type |= SKB_GSO_GRE;
else if (flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6)
gso_type |= SKB_GSO_IPXIP6;
- else
+ else if (flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV4)
gso_type |= SKB_GSO_IPXIP4;
if (flags & BPF_F_ADJ_ROOM_ENCAP_L4_GRE ||
* Only binding to IP is supported.
*/
err = -EINVAL;
+ if (addr_len < offsetofend(struct sockaddr, sa_family))
+ return err;
if (addr->sa_family == AF_INET) {
if (addr_len < sizeof(struct sockaddr_in))
return err;
static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
u32 flags, bool check_mtu)
{
+ struct fib_nh_common *nhc;
struct in_device *in_dev;
struct neighbour *neigh;
struct net_device *dev;
struct fib_result res;
- struct fib_nh *nh;
struct flowi4 fl4;
int err;
u32 mtu;
return BPF_FIB_LKUP_RET_FRAG_NEEDED;
}
- nh = &res.fi->fib_nh[res.nh_sel];
+ nhc = res.nhc;
/* do not handle lwt encaps right now */
- if (nh->fib_nh_lws)
+ if (nhc->nhc_lwtstate)
return BPF_FIB_LKUP_RET_UNSUPP_LWT;
- dev = nh->fib_nh_dev;
- if (nh->fib_nh_gw4)
- params->ipv4_dst = nh->fib_nh_gw4;
+ dev = nhc->nhc_dev;
params->rt_metric = res.fi->fib_priority;
/* xdp and cls_bpf programs are run in RCU-bh so
* rcu_read_lock_bh is not needed here
*/
- neigh = __ipv4_neigh_lookup_noref(dev, (__force u32)params->ipv4_dst);
+ if (likely(nhc->nhc_gw_family != AF_INET6)) {
+ if (nhc->nhc_gw_family)
+ params->ipv4_dst = nhc->nhc_gw.ipv4;
+
+ neigh = __ipv4_neigh_lookup_noref(dev,
+ (__force u32)params->ipv4_dst);
+ } else {
+ struct in6_addr *dst = (struct in6_addr *)params->ipv6_dst;
+
+ params->family = AF_INET6;
+ *dst = nhc->nhc_gw.ipv6;
+ neigh = __ipv6_neigh_lookup_noref_stub(dev, dst);
+ }
+
if (!neigh)
return BPF_FIB_LKUP_RET_NO_NEIGH;
struct in6_addr *src = (struct in6_addr *) params->ipv6_src;
struct in6_addr *dst = (struct in6_addr *) params->ipv6_dst;
struct neighbour *neigh;
+ struct fib6_result res;
struct net_device *dev;
struct inet6_dev *idev;
- struct fib6_info *f6i;
struct flowi6 fl6;
int strict = 0;
- int oif;
+ int oif, err;
u32 mtu;
/* link local addresses are never forwarded */
if (unlikely(!tb))
return BPF_FIB_LKUP_RET_NOT_FWDED;
- f6i = ipv6_stub->fib6_table_lookup(net, tb, oif, &fl6, strict);
+ err = ipv6_stub->fib6_table_lookup(net, tb, oif, &fl6, &res,
+ strict);
} else {
fl6.flowi6_mark = 0;
fl6.flowi6_secid = 0;
fl6.flowi6_tun_key.tun_id = 0;
fl6.flowi6_uid = sock_net_uid(net, NULL);
- f6i = ipv6_stub->fib6_lookup(net, oif, &fl6, strict);
+ err = ipv6_stub->fib6_lookup(net, oif, &fl6, &res, strict);
}
- if (unlikely(IS_ERR_OR_NULL(f6i) || f6i == net->ipv6.fib6_null_entry))
+ if (unlikely(err || IS_ERR_OR_NULL(res.f6i) ||
+ res.f6i == net->ipv6.fib6_null_entry))
return BPF_FIB_LKUP_RET_NOT_FWDED;
- if (unlikely(f6i->fib6_flags & RTF_REJECT)) {
- switch (f6i->fib6_type) {
- case RTN_BLACKHOLE:
- return BPF_FIB_LKUP_RET_BLACKHOLE;
- case RTN_UNREACHABLE:
- return BPF_FIB_LKUP_RET_UNREACHABLE;
- case RTN_PROHIBIT:
- return BPF_FIB_LKUP_RET_PROHIBIT;
- default:
- return BPF_FIB_LKUP_RET_NOT_FWDED;
- }
- }
-
- if (f6i->fib6_type != RTN_UNICAST)
+ switch (res.fib6_type) {
+ /* only unicast is forwarded */
+ case RTN_UNICAST:
+ break;
+ case RTN_BLACKHOLE:
+ return BPF_FIB_LKUP_RET_BLACKHOLE;
+ case RTN_UNREACHABLE:
+ return BPF_FIB_LKUP_RET_UNREACHABLE;
+ case RTN_PROHIBIT:
+ return BPF_FIB_LKUP_RET_PROHIBIT;
+ default:
return BPF_FIB_LKUP_RET_NOT_FWDED;
+ }
- if (f6i->fib6_nsiblings && fl6.flowi6_oif == 0)
- f6i = ipv6_stub->fib6_multipath_select(net, f6i, &fl6,
- fl6.flowi6_oif, NULL,
- strict);
+ ipv6_stub->fib6_select_path(net, &res, &fl6, fl6.flowi6_oif,
+ fl6.flowi6_oif != 0, NULL, strict);
if (check_mtu) {
- mtu = ipv6_stub->ip6_mtu_from_fib6(f6i, dst, src);
+ mtu = ipv6_stub->ip6_mtu_from_fib6(&res, dst, src);
if (params->tot_len > mtu)
return BPF_FIB_LKUP_RET_FRAG_NEEDED;
}
- if (f6i->fib6_nh.fib_nh_lws)
+ if (res.nh->fib_nh_lws)
return BPF_FIB_LKUP_RET_UNSUPP_LWT;
- if (f6i->fib6_nh.fib_nh_has_gw)
- *dst = f6i->fib6_nh.fib_nh_gw6;
+ if (res.nh->fib_nh_gw_family)
+ *dst = res.nh->fib_nh_gw6;
- dev = f6i->fib6_nh.fib_nh_dev;
- params->rt_metric = f6i->fib6_metric;
+ dev = res.nh->fib_nh_dev;
+ params->rt_metric = res.f6i->fib6_metric;
/* xdp and cls_bpf programs are run in RCU-bh so rcu_read_lock_bh is
- * not needed here. Can not use __ipv6_neigh_lookup_noref here
- * because we need to get nd_tbl via the stub
+ * not needed here.
*/
- neigh = ___neigh_lookup_noref(ipv6_stub->nd_tbl, neigh_key_eq128,
- ndisc_hashfn, dst, dev);
+ neigh = __ipv6_neigh_lookup_noref_stub(dev, dst);
if (!neigh)
return BPF_FIB_LKUP_RET_NO_NEIGH;
const struct bpf_prog *prog,
struct bpf_insn_access_aux *info)
{
- if (type == BPF_WRITE) {
- switch (off) {
- case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]):
- break;
- default:
- return false;
- }
- }
+ if (type == BPF_WRITE)
+ return false;
switch (off) {
case bpf_ctx_range(struct __sk_buff, data):
case bpf_ctx_range_ptr(struct __sk_buff, flow_keys):
info->reg_type = PTR_TO_FLOW_KEYS;
break;
- case bpf_ctx_range(struct __sk_buff, tc_classid):
- case bpf_ctx_range(struct __sk_buff, data_meta):
- case bpf_ctx_range_till(struct __sk_buff, family, local_port):
- case bpf_ctx_range(struct __sk_buff, tstamp):
- case bpf_ctx_range(struct __sk_buff, wire_len):
+ default:
return false;
}
/* Pass parameters to the BPF program */
memset(flow_keys, 0, sizeof(*flow_keys));
cb->qdisc_cb.flow_keys = flow_keys;
+ flow_keys->n_proto = skb->protocol;
flow_keys->nhoff = skb_network_offset(skb);
flow_keys->thoff = flow_keys->nhoff;
/* Restore state */
memcpy(cb, &cb_saved, sizeof(cb_saved));
- flow_keys->nhoff = clamp_t(u16, flow_keys->nhoff, 0, skb->len);
+ flow_keys->nhoff = clamp_t(u16, flow_keys->nhoff,
+ skb_network_offset(skb), skb->len);
flow_keys->thoff = clamp_t(u16, flow_keys->thoff,
flow_keys->nhoff, skb->len);
for_each_possible_cpu(i) {
const struct gnet_stats_queue *qcpu = per_cpu_ptr(q, i);
+ qstats->qlen = 0;
qstats->backlog += qcpu->backlog;
qstats->drops += qcpu->drops;
qstats->requeues += qcpu->requeues;
if (cpu) {
__gnet_stats_copy_queue_cpu(qstats, cpu);
} else {
+ qstats->qlen = q->qlen;
qstats->backlog = q->backlog;
qstats->drops = q->drops;
qstats->requeues = q->requeues;
goto out;
}
+ if (tbl->allow_add && !tbl->allow_add(dev, extack)) {
+ err = -EINVAL;
+ goto out;
+ }
+
neigh = neigh_lookup(tbl, dst, dev);
if (neigh == NULL) {
bool exempt_from_gc;
error = device_add(dev);
if (error)
- goto error_put_device;
+ return error;
error = register_queue_kobjects(ndev);
- if (error)
- goto error_device_del;
+ if (error) {
+ device_del(dev);
+ return error;
+ }
pm_runtime_set_memalloc_noio(dev, true);
- return 0;
-
-error_device_del:
- device_del(dev);
-error_put_device:
- put_device(dev);
return error;
}
refcount_set(&net->count, 1);
refcount_set(&net->passive, 1);
+ get_random_bytes(&net->hash_mix, sizeof(u32));
net->dev_base_seq = 1;
net->user_ns = user_ns;
idr_init(&net->netns_ids);
peer = get_net_ns_by_fd(nla_get_u32(tb[NETNSA_FD]));
nla = tb[NETNSA_FD];
} else if (tb[NETNSA_NSID]) {
- peer = get_net_ns_by_id(net, nla_get_u32(tb[NETNSA_NSID]));
+ peer = get_net_ns_by_id(net, nla_get_s32(tb[NETNSA_NSID]));
if (!peer)
peer = ERR_PTR(-ENOENT);
nla = tb[NETNSA_NSID];
{ 0x16, 0, 0, 0x00000000 },
{ 0x06, 0, 0, 0x00000000 },
};
- struct sock_fprog_kern ptp_prog = {
- .len = ARRAY_SIZE(ptp_filter), .filter = ptp_filter,
- };
+ struct sock_fprog_kern ptp_prog;
+
+ ptp_prog.len = ARRAY_SIZE(ptp_filter);
+ ptp_prog.filter = ptp_filter;
BUG_ON(bpf_prog_create(&ptp_insns, &ptp_prog));
}
{
struct if_stats_msg *ifsm;
- if (nlh->nlmsg_len < sizeof(*ifsm)) {
+ if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifsm))) {
NL_SET_ERR_MSG(extack, "Invalid header for stats dump");
return -EINVAL;
}
unsigned int delta_truesize;
struct sk_buff *lp;
- if (unlikely(p->len + len >= 65536))
+ if (unlikely(p->len + len >= 65536 || NAPI_GRO_CB(skb)->flush))
return -E2BIG;
lp = NAPI_GRO_CB(p)->last;
static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb)
{
- int mac_len;
+ int mac_len, meta_len;
+ void *meta;
if (skb_cow(skb, skb_headroom(skb)) < 0) {
kfree_skb(skb);
memmove(skb_mac_header(skb) + VLAN_HLEN, skb_mac_header(skb),
mac_len - VLAN_HLEN - ETH_TLEN);
}
+
+ meta_len = skb_metadata_len(skb);
+ if (meta_len) {
+ meta = skb_metadata_end(skb) - meta_len;
+ memmove(meta + VLAN_HLEN, meta, meta_len);
+ }
+
skb->mac_header += VLAN_HLEN;
return skb;
}
tv.tv_usec = ((timeo % HZ) * USEC_PER_SEC) / HZ;
}
- if (in_compat_syscall() && !COMPAT_USE_64BIT_TIME) {
+ if (old_timeval && in_compat_syscall() && !COMPAT_USE_64BIT_TIME) {
struct old_timeval32 tv32 = { tv.tv_sec, tv.tv_usec };
*(struct old_timeval32 *)optval = tv32;
return sizeof(tv32);
{
struct __kernel_sock_timeval tv;
- if (in_compat_syscall() && !COMPAT_USE_64BIT_TIME) {
+ if (old_timeval && in_compat_syscall() && !COMPAT_USE_64BIT_TIME) {
struct old_timeval32 tv32;
if (optlen < sizeof(tv32))
if (dccp_feat_clone_sp_val(&fval, sp_val, sp_len))
return -ENOMEM;
- return dccp_feat_push_change(fn, feat, is_local, mandatory, &fval);
+ if (dccp_feat_push_change(fn, feat, is_local, mandatory, &fval)) {
+ kfree(fval.sp.vec);
+ return -ENOMEM;
+ }
+
+ return 0;
}
/**
skb_queue_purge(&scp->other_xmit_queue);
skb_queue_purge(&scp->other_receive_queue);
- dst_release(rcu_dereference_check(sk->sk_dst_cache, 1));
+ dst_release(rcu_dereference_protected(sk->sk_dst_cache, 1));
}
static unsigned long dn_memory_pressure;
desclen += typelen + 1;
}
- if (!namelen)
- namelen = strnlen(name, 256);
if (namelen < 3 || namelen > 255)
return -EINVAL;
desclen += namelen + 1;
{
enum devlink_port_flavour flavour;
struct dsa_switch *ds = dp->ds;
+ struct dsa_switch_tree *dst = ds->dst;
int err;
if (dp->type == DSA_PORT_TYPE_UNUSED)
return 0;
memset(&dp->devlink_port, 0, sizeof(dp->devlink_port));
+ dp->mac = of_get_mac_address(dp->dn);
switch (dp->type) {
case DSA_PORT_TYPE_CPU:
* independent from front panel port numbers.
*/
devlink_port_attrs_set(&dp->devlink_port, flavour,
- dp->index, false, 0);
+ dp->index, false, 0,
+ (const char *) &dst->index, sizeof(dst->index));
err = devlink_port_register(ds->devlink, &dp->devlink_port,
dp->index);
if (err)
struct dsa_switch *ds = dp->ds;
struct dsa_switch_tree *dst = ds->dst;
+ /* For non-legacy ports, devlink is used and it takes
+ * care of the name generation. This ndo implementation
+ * should be removed with legacy support.
+ */
+ if (dp->ds->devlink)
+ return -EOPNOTSUPP;
+
ppid->id_len = sizeof(dst->index);
memcpy(&ppid->id, &dst->index, ppid->id_len);
NETIF_F_HW_VLAN_CTAG_FILTER;
slave_dev->hw_features |= NETIF_F_HW_TC;
slave_dev->ethtool_ops = &dsa_slave_ethtool_ops;
- eth_hw_addr_inherit(slave_dev, master);
+ if (port->mac && is_valid_ether_addr(port->mac))
+ ether_addr_copy(slave_dev->dev_addr, port->mac);
+ else
+ eth_hw_addr_inherit(slave_dev, master);
slave_dev->priv_flags |= IFF_NO_QUEUE;
slave_dev->netdev_ops = &dsa_slave_netdev_ops;
slave_dev->min_mtu = 0;
return skb;
}
+static int qca_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto,
+ int *offset)
+{
+ *offset = QCA_HDR_LEN;
+ *proto = ((__be16 *)skb->data)[0];
+
+ return 0;
+}
+
const struct dsa_device_ops qca_netdev_ops = {
.xmit = qca_tag_xmit,
.rcv = qca_tag_rcv,
+ .flow_dissect = qca_tag_flow_dissect,
.overhead = QCA_HDR_LEN,
};
hsr-y := hsr_main.o hsr_framereg.o hsr_device.o \
hsr_netlink.o hsr_slave.o hsr_forward.o
+hsr-$(CONFIG_DEBUG_FS) += hsr_debugfs.o
--- /dev/null
+/*
+ * hsr_debugfs code
+ * Copyright (C) 2019 Texas Instruments Incorporated
+ *
+ * Author(s):
+ * Murali Karicheri <m-karicheri2@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/debugfs.h>
+#include "hsr_main.h"
+#include "hsr_framereg.h"
+
+static void print_mac_address(struct seq_file *sfp, unsigned char *mac)
+{
+ seq_printf(sfp, "%02x:%02x:%02x:%02x:%02x:%02x:",
+ mac[0], mac[1], mac[2], mac[3], mac[4], mac[5]);
+}
+
+/* hsr_node_table_show - Formats and prints node_table entries */
+static int
+hsr_node_table_show(struct seq_file *sfp, void *data)
+{
+ struct hsr_priv *priv = (struct hsr_priv *)sfp->private;
+ struct hsr_node *node;
+
+ seq_puts(sfp, "Node Table entries\n");
+ seq_puts(sfp, "MAC-Address-A, MAC-Address-B, time_in[A], ");
+ seq_puts(sfp, "time_in[B], Address-B port\n");
+ rcu_read_lock();
+ list_for_each_entry_rcu(node, &priv->node_db, mac_list) {
+ /* skip self node */
+ if (hsr_addr_is_self(priv, node->macaddress_A))
+ continue;
+ print_mac_address(sfp, &node->macaddress_A[0]);
+ seq_puts(sfp, " ");
+ print_mac_address(sfp, &node->macaddress_B[0]);
+ seq_printf(sfp, "0x%lx, ", node->time_in[HSR_PT_SLAVE_A]);
+ seq_printf(sfp, "0x%lx ", node->time_in[HSR_PT_SLAVE_B]);
+ seq_printf(sfp, "0x%x\n", node->addr_B_port);
+ }
+ rcu_read_unlock();
+ return 0;
+}
+
+/* hsr_node_table_open - Open the node_table file
+ *
+ * Description:
+ * This routine opens a debugfs file node_table of specific hsr device
+ */
+static int
+hsr_node_table_open(struct inode *inode, struct file *filp)
+{
+ return single_open(filp, hsr_node_table_show, inode->i_private);
+}
+
+static const struct file_operations hsr_fops = {
+ .owner = THIS_MODULE,
+ .open = hsr_node_table_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+/* hsr_debugfs_init - create hsr node_table file for dumping
+ * the node table
+ *
+ * Description:
+ * When debugfs is configured this routine sets up the node_table file per
+ * hsr device for dumping the node_table entries
+ */
+int hsr_debugfs_init(struct hsr_priv *priv, struct net_device *hsr_dev)
+{
+ int rc = -1;
+ struct dentry *de = NULL;
+
+ de = debugfs_create_dir(hsr_dev->name, NULL);
+ if (!de) {
+ pr_err("Cannot create hsr debugfs root\n");
+ return rc;
+ }
+
+ priv->node_tbl_root = de;
+
+ de = debugfs_create_file("node_table", S_IFREG | 0444,
+ priv->node_tbl_root, priv,
+ &hsr_fops);
+ if (!de) {
+ pr_err("Cannot create hsr node_table directory\n");
+ return rc;
+ }
+ priv->node_tbl_file = de;
+
+ return 0;
+}
+
+/* hsr_debugfs_term - Tear down debugfs intrastructure
+ *
+ * Description:
+ * When Debufs is configured this routine removes debugfs file system
+ * elements that are specific to hsr
+ */
+void
+hsr_debugfs_term(struct hsr_priv *priv)
+{
+ debugfs_remove(priv->node_tbl_file);
+ priv->node_tbl_file = NULL;
+ debugfs_remove(priv->node_tbl_root);
+ priv->node_tbl_root = NULL;
+}
+// SPDX-License-Identifier: GPL-2.0
/* Copyright 2011-2014 Autronica Fire and Security AS
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
*
* Author(s):
* 2011-2014 Arvid Brodin, arvid.brodin@alten.se
#include "hsr_main.h"
#include "hsr_forward.h"
-
static bool is_admin_up(struct net_device *dev)
{
return dev && (dev->flags & IFF_UP);
rcu_read_lock();
hsr_for_each_port(master->hsr, port)
- if ((port->type != HSR_PT_MASTER) && is_slave_up(port->dev)) {
+ if (port->type != HSR_PT_MASTER && is_slave_up(port->dev)) {
has_carrier = true;
break;
}
return has_carrier;
}
-
static void hsr_check_announce(struct net_device *hsr_dev,
unsigned char old_operstate)
{
hsr = netdev_priv(hsr_dev);
- if ((hsr_dev->operstate == IF_OPER_UP)
- && (old_operstate != IF_OPER_UP)) {
+ if (hsr_dev->operstate == IF_OPER_UP && old_operstate != IF_OPER_UP) {
/* Went up */
hsr->announce_count = 0;
mod_timer(&hsr->announce_timer,
jiffies + msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL));
}
- if ((hsr_dev->operstate != IF_OPER_UP) && (old_operstate == IF_OPER_UP))
+ if (hsr_dev->operstate != IF_OPER_UP && old_operstate == IF_OPER_UP)
/* Went down */
del_timer(&hsr->announce_timer);
}
return mtu_max - HSR_HLEN;
}
-
static int hsr_dev_change_mtu(struct net_device *dev, int new_mtu)
{
struct hsr_priv *hsr;
return 0;
}
-
static int hsr_dev_close(struct net_device *dev)
{
/* Nothing to do here. */
return 0;
}
-
static netdev_features_t hsr_features_recompute(struct hsr_priv *hsr,
netdev_features_t features)
{
return hsr_features_recompute(hsr, features);
}
-
static int hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct hsr_priv *hsr = netdev_priv(dev);
return NETDEV_TX_OK;
}
-
static const struct header_ops hsr_header_ops = {
.create = eth_header,
.parse = eth_header_parse,
};
static void send_hsr_supervision_frame(struct hsr_port *master,
- u8 type, u8 hsrVer)
+ u8 type, u8 hsr_ver)
{
struct sk_buff *skb;
int hlen, tlen;
hlen = LL_RESERVED_SPACE(master->dev);
tlen = master->dev->needed_tailroom;
- skb = dev_alloc_skb(
- sizeof(struct hsr_tag) +
- sizeof(struct hsr_sup_tag) +
- sizeof(struct hsr_sup_payload) + hlen + tlen);
+ skb = dev_alloc_skb(sizeof(struct hsr_tag) +
+ sizeof(struct hsr_sup_tag) +
+ sizeof(struct hsr_sup_payload) + hlen + tlen);
- if (skb == NULL)
+ if (!skb)
return;
skb_reserve(skb, hlen);
skb->dev = master->dev;
- skb->protocol = htons(hsrVer ? ETH_P_HSR : ETH_P_PRP);
+ skb->protocol = htons(hsr_ver ? ETH_P_HSR : ETH_P_PRP);
skb->priority = TC_PRIO_CONTROL;
- if (dev_hard_header(skb, skb->dev, (hsrVer ? ETH_P_HSR : ETH_P_PRP),
+ if (dev_hard_header(skb, skb->dev, (hsr_ver ? ETH_P_HSR : ETH_P_PRP),
master->hsr->sup_multicast_addr,
skb->dev->dev_addr, skb->len) <= 0)
goto out;
skb_reset_mac_header(skb);
- if (hsrVer > 0) {
+ if (hsr_ver > 0) {
hsr_tag = skb_put(skb, sizeof(struct hsr_tag));
hsr_tag->encap_proto = htons(ETH_P_PRP);
set_hsr_tag_LSDU_size(hsr_tag, HSR_V1_SUP_LSDUSIZE);
}
hsr_stag = skb_put(skb, sizeof(struct hsr_sup_tag));
- set_hsr_stag_path(hsr_stag, (hsrVer ? 0x0 : 0xf));
- set_hsr_stag_HSR_Ver(hsr_stag, hsrVer);
+ set_hsr_stag_path(hsr_stag, (hsr_ver ? 0x0 : 0xf));
+ set_hsr_stag_HSR_ver(hsr_stag, hsr_ver);
/* From HSRv1 on we have separate supervision sequence numbers. */
spin_lock_irqsave(&master->hsr->seqnr_lock, irqflags);
- if (hsrVer > 0) {
+ if (hsr_ver > 0) {
hsr_stag->sequence_nr = htons(master->hsr->sup_sequence_nr);
hsr_tag->sequence_nr = htons(master->hsr->sequence_nr);
master->hsr->sup_sequence_nr++;
}
spin_unlock_irqrestore(&master->hsr->seqnr_lock, irqflags);
- hsr_stag->HSR_TLV_Type = type;
+ hsr_stag->HSR_TLV_type = type;
/* TODO: Why 12 in HSRv0? */
- hsr_stag->HSR_TLV_Length = hsrVer ? sizeof(struct hsr_sup_payload) : 12;
+ hsr_stag->HSR_TLV_length =
+ hsr_ver ? sizeof(struct hsr_sup_payload) : 12;
/* Payload: MacAddressA */
hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload));
- ether_addr_copy(hsr_sp->MacAddressA, master->dev->dev_addr);
+ ether_addr_copy(hsr_sp->macaddress_A, master->dev->dev_addr);
if (skb_put_padto(skb, ETH_ZLEN + HSR_HLEN))
return;
kfree_skb(skb);
}
-
/* Announce (supervision frame) timer function
*/
static void hsr_announce(struct timer_list *t)
rcu_read_lock();
master = hsr_port_get_hsr(hsr, HSR_PT_MASTER);
- if (hsr->announce_count < 3 && hsr->protVersion == 0) {
+ if (hsr->announce_count < 3 && hsr->prot_version == 0) {
send_hsr_supervision_frame(master, HSR_TLV_ANNOUNCE,
- hsr->protVersion);
+ hsr->prot_version);
hsr->announce_count++;
interval = msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL);
} else {
send_hsr_supervision_frame(master, HSR_TLV_LIFE_CHECK,
- hsr->protVersion);
+ hsr->prot_version);
interval = msecs_to_jiffies(HSR_LIFE_CHECK_INTERVAL);
}
rcu_read_unlock();
}
-
/* According to comments in the declaration of struct net_device, this function
* is "Called from unregister, can be used to call free_netdev". Ok then...
*/
hsr = netdev_priv(hsr_dev);
+ hsr_debugfs_term(hsr);
+
rtnl_lock();
hsr_for_each_port(hsr, port)
hsr_del_port(port);
dev->features |= NETIF_F_NETNS_LOCAL;
}
-
/* Return true if dev is a HSR master; return false otherwise.
*/
inline bool is_hsr_master(struct net_device *dev)
ether_addr_copy(hsr->sup_multicast_addr, def_multicast_addr);
hsr->sup_multicast_addr[ETH_ALEN - 1] = multicast_spec;
- hsr->protVersion = protocol_version;
+ hsr->prot_version = protocol_version;
/* FIXME: should I modify the value of these?
*
goto fail;
mod_timer(&hsr->prune_timer, jiffies + msecs_to_jiffies(PRUNE_PERIOD));
+ res = hsr_debugfs_init(hsr, hsr_dev);
+ if (res)
+ goto fail;
return 0;
+/* SPDX-License-Identifier: GPL-2.0 */
/* Copyright 2011-2014 Autronica Fire and Security AS
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
*
* Author(s):
* 2011-2014 Arvid Brodin, arvid.brodin@alten.se
+// SPDX-License-Identifier: GPL-2.0
/* Copyright 2011-2014 Autronica Fire and Security AS
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
*
* Author(s):
* 2011-2014 Arvid Brodin, arvid.brodin@alten.se
#include "hsr_main.h"
#include "hsr_framereg.h"
-
struct hsr_node;
struct hsr_frame_info {
bool is_local_exclusive;
};
-
/* The uses I can see for these HSR supervision frames are:
* 1) Use the frames that are sent after node initialization ("HSR_TLV.Type =
* 22") to reset any sequence_nr counters belonging to that node. Useful if
*/
static bool is_supervision_frame(struct hsr_priv *hsr, struct sk_buff *skb)
{
- struct ethhdr *ethHdr;
- struct hsr_sup_tag *hsrSupTag;
- struct hsrv1_ethhdr_sp *hsrV1Hdr;
+ struct ethhdr *eth_hdr;
+ struct hsr_sup_tag *hsr_sup_tag;
+ struct hsrv1_ethhdr_sp *hsr_V1_hdr;
WARN_ON_ONCE(!skb_mac_header_was_set(skb));
- ethHdr = (struct ethhdr *) skb_mac_header(skb);
+ eth_hdr = (struct ethhdr *)skb_mac_header(skb);
/* Correct addr? */
- if (!ether_addr_equal(ethHdr->h_dest,
+ if (!ether_addr_equal(eth_hdr->h_dest,
hsr->sup_multicast_addr))
return false;
/* Correct ether type?. */
- if (!(ethHdr->h_proto == htons(ETH_P_PRP)
- || ethHdr->h_proto == htons(ETH_P_HSR)))
+ if (!(eth_hdr->h_proto == htons(ETH_P_PRP) ||
+ eth_hdr->h_proto == htons(ETH_P_HSR)))
return false;
/* Get the supervision header from correct location. */
- if (ethHdr->h_proto == htons(ETH_P_HSR)) { /* Okay HSRv1. */
- hsrV1Hdr = (struct hsrv1_ethhdr_sp *) skb_mac_header(skb);
- if (hsrV1Hdr->hsr.encap_proto != htons(ETH_P_PRP))
+ if (eth_hdr->h_proto == htons(ETH_P_HSR)) { /* Okay HSRv1. */
+ hsr_V1_hdr = (struct hsrv1_ethhdr_sp *)skb_mac_header(skb);
+ if (hsr_V1_hdr->hsr.encap_proto != htons(ETH_P_PRP))
return false;
- hsrSupTag = &hsrV1Hdr->hsr_sup;
+ hsr_sup_tag = &hsr_V1_hdr->hsr_sup;
} else {
- hsrSupTag = &((struct hsrv0_ethhdr_sp *) skb_mac_header(skb))->hsr_sup;
+ hsr_sup_tag =
+ &((struct hsrv0_ethhdr_sp *)skb_mac_header(skb))->hsr_sup;
}
- if ((hsrSupTag->HSR_TLV_Type != HSR_TLV_ANNOUNCE) &&
- (hsrSupTag->HSR_TLV_Type != HSR_TLV_LIFE_CHECK))
+ if (hsr_sup_tag->HSR_TLV_type != HSR_TLV_ANNOUNCE &&
+ hsr_sup_tag->HSR_TLV_type != HSR_TLV_LIFE_CHECK)
return false;
- if ((hsrSupTag->HSR_TLV_Length != 12) &&
- (hsrSupTag->HSR_TLV_Length !=
- sizeof(struct hsr_sup_payload)))
+ if (hsr_sup_tag->HSR_TLV_length != 12 &&
+ hsr_sup_tag->HSR_TLV_length != sizeof(struct hsr_sup_payload))
return false;
return true;
}
-
static struct sk_buff *create_stripped_skb(struct sk_buff *skb_in,
struct hsr_frame_info *frame)
{
skb_pull(skb_in, HSR_HLEN);
skb = __pskb_copy(skb_in, skb_headroom(skb_in) - HSR_HLEN, GFP_ATOMIC);
skb_push(skb_in, HSR_HLEN);
- if (skb == NULL)
+ if (!skb)
return NULL;
skb_reset_mac_header(skb);
if (skb->ip_summed == CHECKSUM_PARTIAL)
skb->csum_start -= HSR_HLEN;
- copylen = 2*ETH_ALEN;
+ copylen = 2 * ETH_ALEN;
if (frame->is_vlan)
copylen += VLAN_HLEN;
src = skb_mac_header(skb_in);
return skb_clone(frame->skb_std, GFP_ATOMIC);
}
-
static void hsr_fill_tag(struct sk_buff *skb, struct hsr_frame_info *frame,
- struct hsr_port *port, u8 protoVersion)
+ struct hsr_port *port, u8 proto_version)
{
struct hsr_ethhdr *hsr_ethhdr;
int lane_id;
if (frame->is_vlan)
lsdu_size -= 4;
- hsr_ethhdr = (struct hsr_ethhdr *) skb_mac_header(skb);
+ hsr_ethhdr = (struct hsr_ethhdr *)skb_mac_header(skb);
set_hsr_tag_path(&hsr_ethhdr->hsr_tag, lane_id);
set_hsr_tag_LSDU_size(&hsr_ethhdr->hsr_tag, lsdu_size);
hsr_ethhdr->hsr_tag.sequence_nr = htons(frame->sequence_nr);
hsr_ethhdr->hsr_tag.encap_proto = hsr_ethhdr->ethhdr.h_proto;
- hsr_ethhdr->ethhdr.h_proto = htons(protoVersion ?
+ hsr_ethhdr->ethhdr.h_proto = htons(proto_version ?
ETH_P_HSR : ETH_P_PRP);
}
/* Create the new skb with enough headroom to fit the HSR tag */
skb = __pskb_copy(skb_o, skb_headroom(skb_o) + HSR_HLEN, GFP_ATOMIC);
- if (skb == NULL)
+ if (!skb)
return NULL;
skb_reset_mac_header(skb);
memmove(dst, src, movelen);
skb_reset_mac_header(skb);
- hsr_fill_tag(skb, frame, port, port->hsr->protVersion);
+ hsr_fill_tag(skb, frame, port, port->hsr->prot_version);
return skb;
}
if (frame->skb_hsr)
return skb_clone(frame->skb_hsr, GFP_ATOMIC);
- if ((port->type != HSR_PT_SLAVE_A) && (port->type != HSR_PT_SLAVE_B)) {
+ if (port->type != HSR_PT_SLAVE_A && port->type != HSR_PT_SLAVE_B) {
WARN_ONCE(1, "HSR: Bug: trying to create a tagged frame for a non-ring port");
return NULL;
}
return create_tagged_skb(frame->skb_std, frame, port);
}
-
static void hsr_deliver_master(struct sk_buff *skb, struct net_device *dev,
struct hsr_node *node_src)
{
return dev_queue_xmit(skb);
}
-
/* Forward the frame through all devices except:
* - Back through the receiving device
* - If it's a HSR frame: through a device where it has passed before
continue;
/* Don't deliver locally unless we should */
- if ((port->type == HSR_PT_MASTER) && !frame->is_local_dest)
+ if (port->type == HSR_PT_MASTER && !frame->is_local_dest)
continue;
/* Deliver frames directly addressed to us to master only */
- if ((port->type != HSR_PT_MASTER) && frame->is_local_exclusive)
+ if (port->type != HSR_PT_MASTER && frame->is_local_exclusive)
continue;
/* Don't send frame over port where it has been sent before */
frame->sequence_nr))
continue;
- if (frame->is_supervision && (port->type == HSR_PT_MASTER)) {
+ if (frame->is_supervision && port->type == HSR_PT_MASTER) {
hsr_handle_sup_frame(frame->skb_hsr,
frame->node_src,
frame->port_rcv);
skb = frame_get_tagged_skb(frame, port);
else
skb = frame_get_stripped_skb(frame, port);
- if (skb == NULL) {
+ if (!skb) {
/* FIXME: Record the dropped frame? */
continue;
}
}
}
-
static void check_local_dest(struct hsr_priv *hsr, struct sk_buff *skb,
struct hsr_frame_info *frame)
{
frame->is_local_exclusive = false;
}
- if ((skb->pkt_type == PACKET_HOST) ||
- (skb->pkt_type == PACKET_MULTICAST) ||
- (skb->pkt_type == PACKET_BROADCAST)) {
+ if (skb->pkt_type == PACKET_HOST ||
+ skb->pkt_type == PACKET_MULTICAST ||
+ skb->pkt_type == PACKET_BROADCAST) {
frame->is_local_dest = true;
} else {
frame->is_local_dest = false;
}
}
-
static int hsr_fill_frame_info(struct hsr_frame_info *frame,
struct sk_buff *skb, struct hsr_port *port)
{
frame->is_supervision = is_supervision_frame(port->hsr, skb);
frame->node_src = hsr_get_node(port, skb, frame->is_supervision);
- if (frame->node_src == NULL)
+ if (!frame->node_src)
return -1; /* Unknown node and !is_supervision, or no mem */
- ethhdr = (struct ethhdr *) skb_mac_header(skb);
+ ethhdr = (struct ethhdr *)skb_mac_header(skb);
frame->is_vlan = false;
if (ethhdr->h_proto == htons(ETH_P_8021Q)) {
frame->is_vlan = true;
/* FIXME: */
WARN_ONCE(1, "HSR: VLAN not yet supported");
}
- if (ethhdr->h_proto == htons(ETH_P_PRP)
- || ethhdr->h_proto == htons(ETH_P_HSR)) {
+ if (ethhdr->h_proto == htons(ETH_P_PRP) ||
+ ethhdr->h_proto == htons(ETH_P_HSR)) {
frame->skb_std = NULL;
frame->skb_hsr = skb;
frame->sequence_nr = hsr_get_skb_sequence_nr(skb);
goto out_drop;
hsr_register_frame_in(frame.node_src, port, frame.sequence_nr);
hsr_forward_do(&frame);
+ /* Gets called for ingress frames as well as egress from master port.
+ * So check and increment stats for master port only here.
+ */
+ if (port->type == HSR_PT_MASTER) {
+ port->dev->stats.tx_packets++;
+ port->dev->stats.tx_bytes += skb->len;
+ }
- if (frame.skb_hsr != NULL)
+ if (frame.skb_hsr)
kfree_skb(frame.skb_hsr);
- if (frame.skb_std != NULL)
+ if (frame.skb_std)
kfree_skb(frame.skb_std);
return;
+/* SPDX-License-Identifier: GPL-2.0 */
/* Copyright 2011-2014 Autronica Fire and Security AS
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
*
* Author(s):
* 2011-2014 Arvid Brodin, arvid.brodin@alten.se
+// SPDX-License-Identifier: GPL-2.0
/* Copyright 2011-2014 Autronica Fire and Security AS
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
*
* Author(s):
* 2011-2014 Arvid Brodin, arvid.brodin@alten.se
#include "hsr_framereg.h"
#include "hsr_netlink.h"
-
-struct hsr_node {
- struct list_head mac_list;
- unsigned char MacAddressA[ETH_ALEN];
- unsigned char MacAddressB[ETH_ALEN];
- /* Local slave through which AddrB frames are received from this node */
- enum hsr_port_type AddrB_port;
- unsigned long time_in[HSR_PT_PORTS];
- bool time_in_stale[HSR_PT_PORTS];
- u16 seq_out[HSR_PT_PORTS];
- struct rcu_head rcu_head;
-};
-
-
/* TODO: use hash lists for mac addresses (linux/jhash.h)? */
-
/* seq_nr_after(a, b) - return true if a is after (higher in sequence than) b,
* false otherwise.
*/
/* Remove inconsistency where
* seq_nr_after(a, b) == seq_nr_before(a, b)
*/
- if ((int) b - a == 32768)
+ if ((int)b - a == 32768)
return false;
- return (((s16) (b - a)) < 0);
+ return (((s16)(b - a)) < 0);
}
+
#define seq_nr_before(a, b) seq_nr_after((b), (a))
#define seq_nr_after_or_eq(a, b) (!seq_nr_before((a), (b)))
#define seq_nr_before_or_eq(a, b) (!seq_nr_after((a), (b)))
-
bool hsr_addr_is_self(struct hsr_priv *hsr, unsigned char *addr)
{
struct hsr_node *node;
return false;
}
- if (ether_addr_equal(addr, node->MacAddressA))
+ if (ether_addr_equal(addr, node->macaddress_A))
return true;
- if (ether_addr_equal(addr, node->MacAddressB))
+ if (ether_addr_equal(addr, node->macaddress_B))
return true;
return false;
/* Search for mac entry. Caller must hold rcu read lock.
*/
-static struct hsr_node *find_node_by_AddrA(struct list_head *node_db,
- const unsigned char addr[ETH_ALEN])
+static struct hsr_node *find_node_by_addr_A(struct list_head *node_db,
+ const unsigned char addr[ETH_ALEN])
{
struct hsr_node *node;
list_for_each_entry_rcu(node, node_db, mac_list) {
- if (ether_addr_equal(node->MacAddressA, addr))
+ if (ether_addr_equal(node->macaddress_A, addr))
return node;
}
return NULL;
}
-
/* Helper for device init; the self_node_db is used in hsr_rcv() to recognize
* frames from self that's been looped over the HSR ring.
*/
if (!node)
return -ENOMEM;
- ether_addr_copy(node->MacAddressA, addr_a);
- ether_addr_copy(node->MacAddressB, addr_b);
+ ether_addr_copy(node->macaddress_A, addr_a);
+ ether_addr_copy(node->macaddress_B, addr_b);
rcu_read_lock();
oldnode = list_first_or_null_rcu(self_node_db,
- struct hsr_node, mac_list);
+ struct hsr_node, mac_list);
if (oldnode) {
list_replace_rcu(&oldnode->mac_list, &node->mac_list);
rcu_read_unlock();
}
}
-/* Allocate an hsr_node and add it to node_db. 'addr' is the node's AddressA;
+/* Allocate an hsr_node and add it to node_db. 'addr' is the node's address_A;
* seq_out is used to initialize filtering of outgoing duplicate frames
* originating from the newly added node.
*/
if (!node)
return NULL;
- ether_addr_copy(node->MacAddressA, addr);
+ ether_addr_copy(node->macaddress_A, addr);
/* We are only interested in time diffs here, so use current jiffies
* as initialization. (0 could trigger an spurious ring error warning).
if (!skb_mac_header_was_set(skb))
return NULL;
- ethhdr = (struct ethhdr *) skb_mac_header(skb);
+ ethhdr = (struct ethhdr *)skb_mac_header(skb);
list_for_each_entry_rcu(node, node_db, mac_list) {
- if (ether_addr_equal(node->MacAddressA, ethhdr->h_source))
+ if (ether_addr_equal(node->macaddress_A, ethhdr->h_source))
return node;
- if (ether_addr_equal(node->MacAddressB, ethhdr->h_source))
+ if (ether_addr_equal(node->macaddress_B, ethhdr->h_source))
return node;
}
/* Everyone may create a node entry, connected node to a HSR device. */
- if (ethhdr->h_proto == htons(ETH_P_PRP)
- || ethhdr->h_proto == htons(ETH_P_HSR)) {
+ if (ethhdr->h_proto == htons(ETH_P_PRP) ||
+ ethhdr->h_proto == htons(ETH_P_HSR)) {
/* Use the existing sequence_nr from the tag as starting point
* for filtering duplicate frames.
*/
return hsr_add_node(node_db, ethhdr->h_source, seq_out);
}
-/* Use the Supervision frame's info about an eventual MacAddressB for merging
- * nodes that has previously had their MacAddressB registered as a separate
+/* Use the Supervision frame's info about an eventual macaddress_B for merging
+ * nodes that has previously had their macaddress_B registered as a separate
* node.
*/
void hsr_handle_sup_frame(struct sk_buff *skb, struct hsr_node *node_curr,
struct list_head *node_db;
int i;
- ethhdr = (struct ethhdr *) skb_mac_header(skb);
+ ethhdr = (struct ethhdr *)skb_mac_header(skb);
/* Leave the ethernet header. */
skb_pull(skb, sizeof(struct ethhdr));
/* And leave the HSR sup tag. */
skb_pull(skb, sizeof(struct hsr_sup_tag));
- hsr_sp = (struct hsr_sup_payload *) skb->data;
+ hsr_sp = (struct hsr_sup_payload *)skb->data;
- /* Merge node_curr (registered on MacAddressB) into node_real */
+ /* Merge node_curr (registered on macaddress_B) into node_real */
node_db = &port_rcv->hsr->node_db;
- node_real = find_node_by_AddrA(node_db, hsr_sp->MacAddressA);
+ node_real = find_node_by_addr_A(node_db, hsr_sp->macaddress_A);
if (!node_real)
/* No frame received from AddrA of this node yet */
- node_real = hsr_add_node(node_db, hsr_sp->MacAddressA,
+ node_real = hsr_add_node(node_db, hsr_sp->macaddress_A,
HSR_SEQNR_START - 1);
if (!node_real)
goto done; /* No mem */
/* Node has already been merged */
goto done;
- ether_addr_copy(node_real->MacAddressB, ethhdr->h_source);
+ ether_addr_copy(node_real->macaddress_B, ethhdr->h_source);
for (i = 0; i < HSR_PT_PORTS; i++) {
if (!node_curr->time_in_stale[i] &&
time_after(node_curr->time_in[i], node_real->time_in[i])) {
node_real->time_in[i] = node_curr->time_in[i];
- node_real->time_in_stale[i] = node_curr->time_in_stale[i];
+ node_real->time_in_stale[i] =
+ node_curr->time_in_stale[i];
}
if (seq_nr_after(node_curr->seq_out[i], node_real->seq_out[i]))
node_real->seq_out[i] = node_curr->seq_out[i];
}
- node_real->AddrB_port = port_rcv->type;
+ node_real->addr_B_port = port_rcv->type;
list_del_rcu(&node_curr->mac_list);
kfree_rcu(node_curr, rcu_head);
skb_push(skb, sizeof(struct hsrv1_ethhdr_sp));
}
-
/* 'skb' is a frame meant for this host, that is to be passed to upper layers.
*
* If the frame was sent by a node's B interface, replace the source
- * address with that node's "official" address (MacAddressA) so that upper
+ * address with that node's "official" address (macaddress_A) so that upper
* layers recognize where it came from.
*/
void hsr_addr_subst_source(struct hsr_node *node, struct sk_buff *skb)
return;
}
- memcpy(ð_hdr(skb)->h_source, node->MacAddressA, ETH_ALEN);
+ memcpy(ð_hdr(skb)->h_source, node->macaddress_A, ETH_ALEN);
}
/* 'skb' is a frame meant for another host.
if (!is_unicast_ether_addr(eth_hdr(skb)->h_dest))
return;
- node_dst = find_node_by_AddrA(&port->hsr->node_db, eth_hdr(skb)->h_dest);
+ node_dst = find_node_by_addr_A(&port->hsr->node_db,
+ eth_hdr(skb)->h_dest);
if (!node_dst) {
WARN_ONCE(1, "%s: Unknown node\n", __func__);
return;
}
- if (port->type != node_dst->AddrB_port)
+ if (port->type != node_dst->addr_B_port)
return;
- ether_addr_copy(eth_hdr(skb)->h_dest, node_dst->MacAddressB);
+ ether_addr_copy(eth_hdr(skb)->h_dest, node_dst->macaddress_B);
}
-
void hsr_register_frame_in(struct hsr_node *node, struct hsr_port *port,
u16 sequence_nr)
{
return 0;
}
-
static struct hsr_port *get_late_port(struct hsr_priv *hsr,
struct hsr_node *node)
{
return NULL;
}
-
/* Remove stale sequence_nr records. Called by timer every
* HSR_LIFE_CHECK_INTERVAL (two seconds or so).
*/
time_b = node->time_in[HSR_PT_SLAVE_B];
/* Check for timestamps old enough to risk wrap-around */
- if (time_after(jiffies, time_a + MAX_JIFFY_OFFSET/2))
+ if (time_after(jiffies, time_a + MAX_JIFFY_OFFSET / 2))
node->time_in_stale[HSR_PT_SLAVE_A] = true;
- if (time_after(jiffies, time_b + MAX_JIFFY_OFFSET/2))
+ if (time_after(jiffies, time_b + MAX_JIFFY_OFFSET / 2))
node->time_in_stale[HSR_PT_SLAVE_B] = true;
/* Get age of newest frame from node.
/* Warn of ring error only as long as we get frames at all */
if (time_is_after_jiffies(timestamp +
- msecs_to_jiffies(1.5*MAX_SLAVE_DIFF))) {
+ msecs_to_jiffies(1.5 * MAX_SLAVE_DIFF))) {
rcu_read_lock();
port = get_late_port(hsr, node);
- if (port != NULL)
- hsr_nl_ringerror(hsr, node->MacAddressA, port);
+ if (port)
+ hsr_nl_ringerror(hsr, node->macaddress_A, port);
rcu_read_unlock();
}
/* Prune old entries */
if (time_is_before_jiffies(timestamp +
- msecs_to_jiffies(HSR_NODE_FORGET_TIME))) {
- hsr_nl_nodedown(hsr, node->MacAddressA);
+ msecs_to_jiffies(HSR_NODE_FORGET_TIME))) {
+ hsr_nl_nodedown(hsr, node->macaddress_A);
list_del_rcu(&node->mac_list);
/* Note that we need to free this entry later: */
kfree_rcu(node, rcu_head);
}
}
rcu_read_unlock();
-}
+ /* Restart timer */
+ mod_timer(&hsr->prune_timer,
+ jiffies + msecs_to_jiffies(PRUNE_PERIOD));
+}
void *hsr_get_next_node(struct hsr_priv *hsr, void *_pos,
unsigned char addr[ETH_ALEN])
node = list_first_or_null_rcu(&hsr->node_db,
struct hsr_node, mac_list);
if (node)
- ether_addr_copy(addr, node->MacAddressA);
+ ether_addr_copy(addr, node->macaddress_A);
return node;
}
node = _pos;
list_for_each_entry_continue_rcu(node, &hsr->node_db, mac_list) {
- ether_addr_copy(addr, node->MacAddressA);
+ ether_addr_copy(addr, node->macaddress_A);
return node;
}
return NULL;
}
-
int hsr_get_node_data(struct hsr_priv *hsr,
const unsigned char *addr,
unsigned char addr_b[ETH_ALEN],
struct hsr_port *port;
unsigned long tdiff;
-
rcu_read_lock();
- node = find_node_by_AddrA(&hsr->node_db, addr);
+ node = find_node_by_addr_A(&hsr->node_db, addr);
if (!node) {
rcu_read_unlock();
return -ENOENT; /* No such entry */
}
- ether_addr_copy(addr_b, node->MacAddressB);
+ ether_addr_copy(addr_b, node->macaddress_B);
tdiff = jiffies - node->time_in[HSR_PT_SLAVE_A];
if (node->time_in_stale[HSR_PT_SLAVE_A])
*if1_seq = node->seq_out[HSR_PT_SLAVE_B];
*if2_seq = node->seq_out[HSR_PT_SLAVE_A];
- if (node->AddrB_port != HSR_PT_NONE) {
- port = hsr_port_get_hsr(hsr, node->AddrB_port);
+ if (node->addr_B_port != HSR_PT_NONE) {
+ port = hsr_port_get_hsr(hsr, node->addr_B_port);
*addr_b_ifindex = port->dev->ifindex;
} else {
*addr_b_ifindex = -1;
+/* SPDX-License-Identifier: GPL-2.0 */
/* Copyright 2011-2014 Autronica Fire and Security AS
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
*
* Author(s):
* 2011-2014 Arvid Brodin, arvid.brodin@alten.se
int *if2_age,
u16 *if2_seq);
+struct hsr_node {
+ struct list_head mac_list;
+ unsigned char macaddress_A[ETH_ALEN];
+ unsigned char macaddress_B[ETH_ALEN];
+ /* Local slave through which AddrB frames are received from this node */
+ enum hsr_port_type addr_B_port;
+ unsigned long time_in[HSR_PT_PORTS];
+ bool time_in_stale[HSR_PT_PORTS];
+ u16 seq_out[HSR_PT_PORTS];
+ struct rcu_head rcu_head;
+};
+
#endif /* __HSR_FRAMEREG_H */
+// SPDX-License-Identifier: GPL-2.0
/* Copyright 2011-2014 Autronica Fire and Security AS
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
*
* Author(s):
* 2011-2014 Arvid Brodin, arvid.brodin@alten.se
#include "hsr_framereg.h"
#include "hsr_slave.h"
-
static int hsr_netdev_notify(struct notifier_block *nb, unsigned long event,
void *ptr)
{
dev = netdev_notifier_info_to_dev(ptr);
port = hsr_port_get_rtnl(dev);
- if (port == NULL) {
+ if (!port) {
if (!is_hsr_master(dev))
return NOTIFY_DONE; /* Not an HSR device */
hsr = netdev_priv(dev);
port = hsr_port_get_hsr(hsr, HSR_PT_MASTER);
- if (port == NULL) {
+ if (!port) {
/* Resend of notification concerning removed device? */
return NOTIFY_DONE;
}
if (port->type == HSR_PT_SLAVE_A) {
ether_addr_copy(master->dev->dev_addr, dev->dev_addr);
- call_netdevice_notifiers(NETDEV_CHANGEADDR, master->dev);
+ call_netdevice_notifiers(NETDEV_CHANGEADDR,
+ master->dev);
}
/* Make sure we recognize frames from ourselves in hsr_rcv() */
return NOTIFY_DONE;
}
-
struct hsr_port *hsr_port_get_hsr(struct hsr_priv *hsr, enum hsr_port_type pt)
{
struct hsr_port *port;
.notifier_call = hsr_netdev_notify, /* Slave event notifications */
};
-
static int __init hsr_init(void)
{
int res;
+/* SPDX-License-Identifier: GPL-2.0 */
/* Copyright 2011-2014 Autronica Fire and Security AS
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
*
* Author(s):
* 2011-2014 Arvid Brodin, arvid.brodin@alten.se
#include <linux/netdevice.h>
#include <linux/list.h>
-
/* Time constants as specified in the HSR specification (IEC-62439-3 2010)
* Table 8.
* All values in milliseconds.
#define HSR_NODE_FORGET_TIME 60000 /* ms */
#define HSR_ANNOUNCE_INTERVAL 100 /* ms */
-
/* By how much may slave1 and slave2 timestamps of latest received frame from
* each node differ before we notify of communication problem?
*/
#define HSR_SEQNR_START (USHRT_MAX - 1024)
#define HSR_SUP_SEQNR_START (HSR_SEQNR_START / 2)
-
/* How often shall we check for broken ring and remove node entries older than
* HSR_NODE_FORGET_TIME?
*/
#define PRUNE_PERIOD 3000 /* ms */
-
#define HSR_TLV_ANNOUNCE 22
#define HSR_TLV_LIFE_CHECK 23
-
/* HSR Tag.
* As defined in IEC-62439-3:2010, the HSR tag is really { ethertype = 0x88FB,
* path, LSDU_size, sequence Nr }. But we let eth_header() create { h_dest,
static inline void set_hsr_tag_path(struct hsr_tag *ht, u16 path)
{
- ht->path_and_LSDU_size = htons(
- (ntohs(ht->path_and_LSDU_size) & 0x0FFF) | (path << 12));
+ ht->path_and_LSDU_size =
+ htons((ntohs(ht->path_and_LSDU_size) & 0x0FFF) | (path << 12));
}
static inline void set_hsr_tag_LSDU_size(struct hsr_tag *ht, u16 LSDU_size)
{
- ht->path_and_LSDU_size = htons(
- (ntohs(ht->path_and_LSDU_size) & 0xF000) |
- (LSDU_size & 0x0FFF));
+ ht->path_and_LSDU_size = htons((ntohs(ht->path_and_LSDU_size) &
+ 0xF000) | (LSDU_size & 0x0FFF));
}
struct hsr_ethhdr {
struct hsr_tag hsr_tag;
} __packed;
-
/* HSR Supervision Frame data types.
* Field names as defined in the IEC:2010 standard for HSR.
*/
struct hsr_sup_tag {
- __be16 path_and_HSR_Ver;
+ __be16 path_and_HSR_ver;
__be16 sequence_nr;
- __u8 HSR_TLV_Type;
- __u8 HSR_TLV_Length;
+ __u8 HSR_TLV_type;
+ __u8 HSR_TLV_length;
} __packed;
struct hsr_sup_payload {
- unsigned char MacAddressA[ETH_ALEN];
+ unsigned char macaddress_A[ETH_ALEN];
} __packed;
static inline u16 get_hsr_stag_path(struct hsr_sup_tag *hst)
{
- return get_hsr_tag_path((struct hsr_tag *) hst);
+ return get_hsr_tag_path((struct hsr_tag *)hst);
}
static inline u16 get_hsr_stag_HSR_ver(struct hsr_sup_tag *hst)
{
- return get_hsr_tag_LSDU_size((struct hsr_tag *) hst);
+ return get_hsr_tag_LSDU_size((struct hsr_tag *)hst);
}
static inline void set_hsr_stag_path(struct hsr_sup_tag *hst, u16 path)
{
- set_hsr_tag_path((struct hsr_tag *) hst, path);
+ set_hsr_tag_path((struct hsr_tag *)hst, path);
}
-static inline void set_hsr_stag_HSR_Ver(struct hsr_sup_tag *hst, u16 HSR_Ver)
+static inline void set_hsr_stag_HSR_ver(struct hsr_sup_tag *hst, u16 HSR_ver)
{
- set_hsr_tag_LSDU_size((struct hsr_tag *) hst, HSR_Ver);
+ set_hsr_tag_LSDU_size((struct hsr_tag *)hst, HSR_ver);
}
struct hsrv0_ethhdr_sp {
struct hsr_sup_tag hsr_sup;
} __packed;
-
enum hsr_port_type {
HSR_PT_NONE = 0, /* Must be 0, used by framereg */
HSR_PT_SLAVE_A,
struct timer_list prune_timer;
int announce_count;
u16 sequence_nr;
- u16 sup_sequence_nr; /* For HSRv1 separate seq_nr for supervision */
- u8 protVersion; /* Indicate if HSRv0 or HSRv1. */
+ u16 sup_sequence_nr; /* For HSRv1 separate seq_nr for supervision */
+ u8 prot_version; /* Indicate if HSRv0 or HSRv1. */
spinlock_t seqnr_lock; /* locking for sequence_nr */
unsigned char sup_multicast_addr[ETH_ALEN];
+#ifdef CONFIG_DEBUG_FS
+ struct dentry *node_tbl_root;
+ struct dentry *node_tbl_file;
+#endif
};
#define hsr_for_each_port(hsr, port) \
{
struct hsr_ethhdr *hsr_ethhdr;
- hsr_ethhdr = (struct hsr_ethhdr *) skb_mac_header(skb);
+ hsr_ethhdr = (struct hsr_ethhdr *)skb_mac_header(skb);
return ntohs(hsr_ethhdr->hsr_tag.sequence_nr);
}
+#if IS_ENABLED(CONFIG_DEBUG_FS)
+int hsr_debugfs_init(struct hsr_priv *priv, struct net_device *hsr_dev);
+void hsr_debugfs_term(struct hsr_priv *priv);
+#else
+static inline int hsr_debugfs_init(struct hsr_priv *priv,
+ struct net_device *hsr_dev)
+{
+ return 0;
+}
+
+static inline void hsr_debugfs_term(struct hsr_priv *priv)
+{}
+#endif
+
#endif /* __HSR_PRIVATE_H */
+// SPDX-License-Identifier: GPL-2.0
/* Copyright 2011-2014 Autronica Fire and Security AS
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
*
* Author(s):
* 2011-2014 Arvid Brodin, arvid.brodin@alten.se
[IFLA_HSR_SEQ_NR] = { .type = NLA_U16 },
};
-
/* Here, it seems a netdevice has already been allocated for us, and the
* hsr_dev_setup routine has been executed. Nice!
*/
netdev_info(dev, "HSR: Slave1 device not specified\n");
return -EINVAL;
}
- link[0] = __dev_get_by_index(src_net, nla_get_u32(data[IFLA_HSR_SLAVE1]));
+ link[0] = __dev_get_by_index(src_net,
+ nla_get_u32(data[IFLA_HSR_SLAVE1]));
if (!data[IFLA_HSR_SLAVE2]) {
netdev_info(dev, "HSR: Slave2 device not specified\n");
return -EINVAL;
}
- link[1] = __dev_get_by_index(src_net, nla_get_u32(data[IFLA_HSR_SLAVE2]));
+ link[1] = __dev_get_by_index(src_net,
+ nla_get_u32(data[IFLA_HSR_SLAVE2]));
if (!link[0] || !link[1])
return -ENODEV;
.fill_info = hsr_fill_info,
};
-
-
/* attribute policy */
static const struct nla_policy hsr_genl_policy[HSR_A_MAX + 1] = {
[HSR_A_NODE_ADDR] = { .len = ETH_ALEN },
{ .name = "hsr-network", },
};
-
-
/* This is called if for some node with MAC address addr, we only get frames
* over one of the slave interfaces. This would indicate an open network ring
* (i.e. a link has failed somewhere).
if (!skb)
goto fail;
- msg_head = genlmsg_put(skb, 0, 0, &hsr_genl_family, 0, HSR_C_RING_ERROR);
+ msg_head = genlmsg_put(skb, 0, 0, &hsr_genl_family, 0,
+ HSR_C_RING_ERROR);
if (!msg_head)
goto nla_put_failure;
if (!msg_head)
goto nla_put_failure;
-
res = nla_put(skb, HSR_A_NODE_ADDR, ETH_ALEN, addr);
if (res < 0)
goto nla_put_failure;
rcu_read_unlock();
}
-
/* HSR_C_GET_NODE_STATUS lets userspace query the internal HSR node table
* about the status of a specific node in the network, defined by its MAC
* address.
goto invalid;
hsr_dev = __dev_get_by_index(genl_info_net(info),
- nla_get_u32(info->attrs[HSR_A_IFINDEX]));
+ nla_get_u32(info->attrs[HSR_A_IFINDEX]));
if (!hsr_dev)
goto invalid;
if (!is_hsr_master(hsr_dev))
goto invalid;
-
/* Send reply */
-
skb_out = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
if (!skb_out) {
res = -ENOMEM;
}
msg_head = genlmsg_put(skb_out, NETLINK_CB(skb_in).portid,
- info->snd_seq, &hsr_genl_family, 0,
- HSR_C_SET_NODE_STATUS);
+ info->snd_seq, &hsr_genl_family, 0,
+ HSR_C_SET_NODE_STATUS);
if (!msg_head) {
res = -ENOMEM;
goto nla_put_failure;
hsr = netdev_priv(hsr_dev);
res = hsr_get_node_data(hsr,
- (unsigned char *) nla_data(info->attrs[HSR_A_NODE_ADDR]),
- hsr_node_addr_b,
- &addr_b_ifindex,
- &hsr_node_if1_age,
- &hsr_node_if1_seq,
- &hsr_node_if2_age,
- &hsr_node_if2_seq);
+ (unsigned char *)
+ nla_data(info->attrs[HSR_A_NODE_ADDR]),
+ hsr_node_addr_b,
+ &addr_b_ifindex,
+ &hsr_node_if1_age,
+ &hsr_node_if1_seq,
+ &hsr_node_if2_age,
+ &hsr_node_if2_seq);
if (res < 0)
goto nla_put_failure;
res = nla_put(skb_out, HSR_A_NODE_ADDR, ETH_ALEN,
- nla_data(info->attrs[HSR_A_NODE_ADDR]));
+ nla_data(info->attrs[HSR_A_NODE_ADDR]));
if (res < 0)
goto nla_put_failure;
if (addr_b_ifindex > -1) {
res = nla_put(skb_out, HSR_A_NODE_ADDR_B, ETH_ALEN,
- hsr_node_addr_b);
+ hsr_node_addr_b);
if (res < 0)
goto nla_put_failure;
- res = nla_put_u32(skb_out, HSR_A_ADDR_B_IFINDEX, addr_b_ifindex);
+ res = nla_put_u32(skb_out, HSR_A_ADDR_B_IFINDEX,
+ addr_b_ifindex);
if (res < 0)
goto nla_put_failure;
}
if (!is_hsr_master(hsr_dev))
goto invalid;
-
/* Send reply */
-
skb_out = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
if (!skb_out) {
res = -ENOMEM;
}
msg_head = genlmsg_put(skb_out, NETLINK_CB(skb_in).portid,
- info->snd_seq, &hsr_genl_family, 0,
- HSR_C_SET_NODE_LIST);
+ info->snd_seq, &hsr_genl_family, 0,
+ HSR_C_SET_NODE_LIST);
if (!msg_head) {
res = -ENOMEM;
goto nla_put_failure;
return res;
}
-
static const struct genl_ops hsr_ops[] = {
{
.cmd = HSR_C_GET_NODE_STATUS,
+/* SPDX-License-Identifier: GPL-2.0 */
/* Copyright 2011-2014 Autronica Fire and Security AS
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
*
* Author(s):
* 2011-2014 Arvid Brodin, arvid.brodin@alten.se
+// SPDX-License-Identifier: GPL-2.0
/* Copyright 2011-2014 Autronica Fire and Security AS
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
*
* Author(s):
* 2011-2014 Arvid Brodin, arvid.brodin@alten.se
#include "hsr_forward.h"
#include "hsr_framereg.h"
-
static rx_handler_result_t hsr_handle_frame(struct sk_buff **pskb)
{
struct sk_buff *skb = *pskb;
return rcu_access_pointer(dev->rx_handler) == hsr_handle_frame;
}
-
static int hsr_check_dev_ok(struct net_device *dev)
{
/* Don't allow HSR on non-ethernet like devices */
- if ((dev->flags & IFF_LOOPBACK) || (dev->type != ARPHRD_ETHER) ||
- (dev->addr_len != ETH_ALEN)) {
+ if ((dev->flags & IFF_LOOPBACK) || dev->type != ARPHRD_ETHER ||
+ dev->addr_len != ETH_ALEN) {
netdev_info(dev, "Cannot use loopback or non-ethernet device as HSR slave.\n");
return -EINVAL;
}
return 0;
}
-
/* Setup device to be added to the HSR bridge. */
static int hsr_portdev_setup(struct net_device *dev, struct hsr_port *port)
{
}
port = hsr_port_get_hsr(hsr, type);
- if (port != NULL)
+ if (port)
return -EBUSY; /* This port already exists */
port = kzalloc(sizeof(*port), GFP_KERNEL);
- if (port == NULL)
+ if (!port)
return -ENOMEM;
if (type != HSR_PT_MASTER) {
list_del_rcu(&port->port_list);
if (port != master) {
- if (master != NULL) {
+ if (master) {
netdev_update_features(master->dev);
dev_set_mtu(master->dev, hsr_get_max_mtu(hsr));
}
+/* SPDX-License-Identifier: GPL-2.0 */
/* Copyright 2011-2014 Autronica Fire and Security AS
*
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- * Author(s):
* 2011-2014 Arvid Brodin, arvid.brodin@alten.se
*/
WARN_ON(sk->sk_forward_alloc);
kfree(rcu_dereference_protected(inet->inet_opt, 1));
- dst_release(rcu_dereference_check(sk->sk_dst_cache, 1));
+ dst_release(rcu_dereference_protected(sk->sk_dst_cache, 1));
dst_release(sk->sk_rx_dst);
sk_refcnt_debug_dec(sk);
}
.flowi4_mark = vmark ? skb->mark : 0,
};
if (!fib_lookup(net, &fl4, &res, 0))
- return FIB_RES_PREFSRC(net, res);
+ return fib_result_prefsrc(net, &res);
} else {
scope = RT_SCOPE_LINK;
}
dev_match = fib_info_nh_uses_dev(res.fi, dev);
if (dev_match) {
- ret = FIB_RES_NH(res).fib_nh_scope >= RT_SCOPE_HOST;
+ ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST;
return ret;
}
if (no_addr)
ret = 0;
if (fib_lookup(net, &fl4, &res, FIB_LOOKUP_IGNORE_LINKSTATE) == 0) {
if (res.type == RTN_UNICAST)
- ret = FIB_RES_NH(res).fib_nh_scope >= RT_SCOPE_HOST;
+ ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST;
}
return ret;
if (rt->rt_gateway.sa_family == AF_INET && addr) {
unsigned int addr_type;
- cfg->fc_gw = addr;
+ cfg->fc_gw4 = addr;
+ cfg->fc_gw_family = AF_INET;
addr_type = inet_addr_type_table(net, addr, cfg->fc_table);
if (rt->rt_flags & RTF_GATEWAY &&
addr_type == RTN_UNICAST)
if (cmd == SIOCDELRT)
return 0;
- if (rt->rt_flags & RTF_GATEWAY && !cfg->fc_gw)
+ if (rt->rt_flags & RTF_GATEWAY && !cfg->fc_gw_family)
return -EINVAL;
if (cfg->fc_scope == RT_SCOPE_NOWHERE)
[RTA_DPORT] = { .type = NLA_U16 },
};
+int fib_gw_from_via(struct fib_config *cfg, struct nlattr *nla,
+ struct netlink_ext_ack *extack)
+{
+ struct rtvia *via;
+ int alen;
+
+ if (nla_len(nla) < offsetof(struct rtvia, rtvia_addr)) {
+ NL_SET_ERR_MSG(extack, "Invalid attribute length for RTA_VIA");
+ return -EINVAL;
+ }
+
+ via = nla_data(nla);
+ alen = nla_len(nla) - offsetof(struct rtvia, rtvia_addr);
+
+ switch (via->rtvia_family) {
+ case AF_INET:
+ if (alen != sizeof(__be32)) {
+ NL_SET_ERR_MSG(extack, "Invalid IPv4 address in RTA_VIA");
+ return -EINVAL;
+ }
+ cfg->fc_gw_family = AF_INET;
+ cfg->fc_gw4 = *((__be32 *)via->rtvia_addr);
+ break;
+ case AF_INET6:
+#ifdef CONFIG_IPV6
+ if (alen != sizeof(struct in6_addr)) {
+ NL_SET_ERR_MSG(extack, "Invalid IPv6 address in RTA_VIA");
+ return -EINVAL;
+ }
+ cfg->fc_gw_family = AF_INET6;
+ cfg->fc_gw6 = *((struct in6_addr *)via->rtvia_addr);
+#else
+ NL_SET_ERR_MSG(extack, "IPv6 support not enabled in kernel");
+ return -EINVAL;
+#endif
+ break;
+ default:
+ NL_SET_ERR_MSG(extack, "Unsupported address family in RTA_VIA");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
struct nlmsghdr *nlh, struct fib_config *cfg,
struct netlink_ext_ack *extack)
{
+ bool has_gw = false, has_via = false;
struct nlattr *attr;
int err, remaining;
struct rtmsg *rtm;
cfg->fc_oif = nla_get_u32(attr);
break;
case RTA_GATEWAY:
- cfg->fc_gw = nla_get_be32(attr);
+ has_gw = true;
+ cfg->fc_gw4 = nla_get_be32(attr);
+ if (cfg->fc_gw4)
+ cfg->fc_gw_family = AF_INET;
break;
case RTA_VIA:
- NL_SET_ERR_MSG(extack, "IPv4 does not support RTA_VIA attribute");
- err = -EINVAL;
- goto errout;
+ has_via = true;
+ err = fib_gw_from_via(cfg, attr, extack);
+ if (err)
+ goto errout;
+ break;
case RTA_PRIORITY:
cfg->fc_priority = nla_get_u32(attr);
break;
}
}
+ if (has_gw && has_via) {
+ NL_SET_ERR_MSG(extack,
+ "Nexthop configuration can not contain both GATEWAY and VIA");
+ goto errout;
+ }
+
return 0;
errout:
return err;
{
/* we used to play games with refcounts, but we now use RCU */
res->fi = fi;
+ res->nhc = fib_info_nhc(fi, 0);
}
struct fib_prop {
#include <net/tcp.h>
#include <net/sock.h>
#include <net/ip_fib.h>
+#include <net/ip6_fib.h>
#include <net/netlink.h>
#include <net/nexthop.h>
#include <net/lwtunnel.h>
#include <net/fib_notifier.h>
+#include <net/addrconf.h>
#include "fib_lookup.h"
for_nexthops(fi) {
if (nh->fib_nh_oif != onh->fib_nh_oif ||
- nh->fib_nh_gw4 != onh->fib_nh_gw4 ||
+ nh->fib_nh_gw_family != onh->fib_nh_gw_family ||
nh->fib_nh_scope != onh->fib_nh_scope ||
#ifdef CONFIG_IP_ROUTE_MULTIPATH
nh->fib_nh_weight != onh->fib_nh_weight ||
lwtunnel_cmp_encap(nh->fib_nh_lws, onh->fib_nh_lws) ||
((nh->fib_nh_flags ^ onh->fib_nh_flags) & ~RTNH_COMPARE_MASK))
return -1;
+
+ if (nh->fib_nh_gw_family == AF_INET &&
+ nh->fib_nh_gw4 != onh->fib_nh_gw4)
+ return -1;
+
+ if (nh->fib_nh_gw_family == AF_INET6 &&
+ ipv6_addr_cmp(&nh->fib_nh_gw6, &onh->fib_nh_gw6))
+ return -1;
+
onh++;
} endfor_nexthops(fi);
return 0;
struct fib_info **last_resort, int *last_idx,
int dflt)
{
+ const struct fib_nh_common *nhc = fib_info_nhc(fi, 0);
struct neighbour *n;
int state = NUD_NONE;
- n = neigh_lookup(&arp_tbl, &fi->fib_nh[0].fib_nh_gw4, fi->fib_dev);
+ if (likely(nhc->nhc_gw_family == AF_INET))
+ n = neigh_lookup(&arp_tbl, &nhc->nhc_gw.ipv4, nhc->nhc_dev);
+ else if (nhc->nhc_gw_family == AF_INET6)
+ n = neigh_lookup(ipv6_stub->nd_tbl, &nhc->nhc_gw.ipv6,
+ nhc->nhc_dev);
+ else
+ n = NULL;
+
if (n) {
state = n->nud_state;
neigh_release(n);
goto init_failure;
nh->fib_nh_oif = cfg->fc_oif;
- if (cfg->fc_gw) {
- nh->fib_nh_gw4 = cfg->fc_gw;
- nh->fib_nh_has_gw = 1;
- }
+ nh->fib_nh_gw_family = cfg->fc_gw_family;
+ if (cfg->fc_gw_family == AF_INET)
+ nh->fib_nh_gw4 = cfg->fc_gw4;
+ else if (cfg->fc_gw_family == AF_INET6)
+ nh->fib_nh_gw6 = cfg->fc_gw6;
+
nh->fib_nh_flags = cfg->fc_flags;
#ifdef CONFIG_IP_ROUTE_CLASSID
attrlen = rtnh_attrlen(rtnh);
if (attrlen > 0) {
- struct nlattr *nla, *attrs = rtnh_attrs(rtnh);
+ struct nlattr *nla, *nlav, *attrs = rtnh_attrs(rtnh);
nla = nla_find(attrs, attrlen, RTA_GATEWAY);
- if (nla)
- fib_cfg.fc_gw = nla_get_in_addr(nla);
+ nlav = nla_find(attrs, attrlen, RTA_VIA);
+ if (nla && nlav) {
+ NL_SET_ERR_MSG(extack,
+ "Nexthop configuration can not contain both GATEWAY and VIA");
+ return -EINVAL;
+ }
+ if (nla) {
+ fib_cfg.fc_gw4 = nla_get_in_addr(nla);
+ if (fib_cfg.fc_gw4)
+ fib_cfg.fc_gw_family = AF_INET;
+ } else if (nlav) {
+ ret = fib_gw_from_via(&fib_cfg, nlav, extack);
+ if (ret)
+ goto errout;
+ }
nla = nla_find(attrs, attrlen, RTA_FLOW);
if (nla)
"Nexthop device index does not match RTA_OIF");
goto errout;
}
- if (cfg->fc_gw && fi->fib_nh->fib_nh_gw4 != cfg->fc_gw) {
- NL_SET_ERR_MSG(extack,
- "Nexthop gateway does not match RTA_GATEWAY");
- goto errout;
+ if (cfg->fc_gw_family) {
+ if (cfg->fc_gw_family != fi->fib_nh->fib_nh_gw_family ||
+ (cfg->fc_gw_family == AF_INET &&
+ fi->fib_nh->fib_nh_gw4 != cfg->fc_gw4) ||
+ (cfg->fc_gw_family == AF_INET6 &&
+ ipv6_addr_cmp(&fi->fib_nh->fib_nh_gw6, &cfg->fc_gw6))) {
+ NL_SET_ERR_MSG(extack,
+ "Nexthop gateway does not match RTA_GATEWAY or RTA_VIA");
+ goto errout;
+ }
}
#ifdef CONFIG_IP_ROUTE_CLASSID
if (cfg->fc_flow && fi->fib_nh->nh_tclassid != cfg->fc_flow) {
if (cfg->fc_priority && cfg->fc_priority != fi->fib_priority)
return 1;
- if (cfg->fc_oif || cfg->fc_gw) {
+ if (cfg->fc_oif || cfg->fc_gw_family) {
if (cfg->fc_encap) {
if (fib_encap_match(cfg->fc_encap_type, cfg->fc_encap,
fi->fib_nh, cfg, extack))
cfg->fc_flow != fi->fib_nh->nh_tclassid)
return 1;
#endif
- if ((!cfg->fc_oif || cfg->fc_oif == fi->fib_nh->fib_nh_oif) &&
- (!cfg->fc_gw || cfg->fc_gw == fi->fib_nh->fib_nh_gw4))
- return 0;
- return 1;
+ if ((cfg->fc_oif && cfg->fc_oif != fi->fib_nh->fib_nh_oif) ||
+ (cfg->fc_gw_family &&
+ cfg->fc_gw_family != fi->fib_nh->fib_nh_gw_family))
+ return 1;
+
+ if (cfg->fc_gw_family == AF_INET &&
+ cfg->fc_gw4 != fi->fib_nh->fib_nh_gw4)
+ return 1;
+
+ if (cfg->fc_gw_family == AF_INET6 &&
+ ipv6_addr_cmp(&cfg->fc_gw6, &fi->fib_nh->fib_nh_gw6))
+ return 1;
+
+ return 0;
}
#ifdef CONFIG_IP_ROUTE_MULTIPATH
attrlen = rtnh_attrlen(rtnh);
if (attrlen > 0) {
- struct nlattr *nla, *attrs = rtnh_attrs(rtnh);
+ struct nlattr *nla, *nlav, *attrs = rtnh_attrs(rtnh);
nla = nla_find(attrs, attrlen, RTA_GATEWAY);
- if (nla && nla_get_in_addr(nla) != nh->fib_nh_gw4)
- return 1;
+ nlav = nla_find(attrs, attrlen, RTA_VIA);
+ if (nla && nlav) {
+ NL_SET_ERR_MSG(extack,
+ "Nexthop configuration can not contain both GATEWAY and VIA");
+ return -EINVAL;
+ }
+
+ if (nla) {
+ if (nh->fib_nh_gw_family != AF_INET ||
+ nla_get_in_addr(nla) != nh->fib_nh_gw4)
+ return 1;
+ } else if (nlav) {
+ struct fib_config cfg2;
+ int err;
+
+ err = fib_gw_from_via(&cfg2, nlav, extack);
+ if (err)
+ return err;
+
+ switch (nh->fib_nh_gw_family) {
+ case AF_INET:
+ if (cfg2.fc_gw_family != AF_INET ||
+ cfg2.fc_gw4 != nh->fib_nh_gw4)
+ return 1;
+ break;
+ case AF_INET6:
+ if (cfg2.fc_gw_family != AF_INET6 ||
+ ipv6_addr_cmp(&cfg2.fc_gw6,
+ &nh->fib_nh_gw6))
+ return 1;
+ break;
+ }
+ }
+
#ifdef CONFIG_IP_ROUTE_CLASSID
nla = nla_find(attrs, attrlen, RTA_FLOW);
if (nla && nla_get_u32(nla) != nh->nh_tclassid)
return true;
}
+static int fib_check_nh_v6_gw(struct net *net, struct fib_nh *nh,
+ u32 table, struct netlink_ext_ack *extack)
+{
+ struct fib6_config cfg = {
+ .fc_table = table,
+ .fc_flags = nh->fib_nh_flags | RTF_GATEWAY,
+ .fc_ifindex = nh->fib_nh_oif,
+ .fc_gateway = nh->fib_nh_gw6,
+ };
+ struct fib6_nh fib6_nh = {};
+ int err;
+
+ err = ipv6_stub->fib6_nh_init(net, &fib6_nh, &cfg, GFP_KERNEL, extack);
+ if (!err) {
+ nh->fib_nh_dev = fib6_nh.fib_nh_dev;
+ dev_hold(nh->fib_nh_dev);
+ nh->fib_nh_oif = nh->fib_nh_dev->ifindex;
+ nh->fib_nh_scope = RT_SCOPE_LINK;
+
+ ipv6_stub->fib6_nh_release(&fib6_nh);
+ }
+
+ return err;
+}
/*
* Picture
* |
* |-> {local prefix} (terminal node)
*/
-static int fib_check_nh(struct fib_config *cfg, struct fib_nh *nh,
- struct netlink_ext_ack *extack)
+static int fib_check_nh_v4_gw(struct net *net, struct fib_nh *nh, u32 table,
+ u8 scope, struct netlink_ext_ack *extack)
{
- int err = 0;
- struct net *net;
struct net_device *dev;
+ struct fib_result res;
+ int err;
- net = cfg->fc_nlinfo.nl_net;
- if (nh->fib_nh_gw4) {
- struct fib_result res;
-
- if (nh->fib_nh_flags & RTNH_F_ONLINK) {
- unsigned int addr_type;
+ if (nh->fib_nh_flags & RTNH_F_ONLINK) {
+ unsigned int addr_type;
- if (cfg->fc_scope >= RT_SCOPE_LINK) {
- NL_SET_ERR_MSG(extack,
- "Nexthop has invalid scope");
- return -EINVAL;
- }
- dev = __dev_get_by_index(net, nh->fib_nh_oif);
- if (!dev) {
- NL_SET_ERR_MSG(extack, "Nexthop device required for onlink");
- return -ENODEV;
- }
- if (!(dev->flags & IFF_UP)) {
- NL_SET_ERR_MSG(extack,
- "Nexthop device is not up");
- return -ENETDOWN;
- }
- addr_type = inet_addr_type_dev_table(net, dev,
- nh->fib_nh_gw4);
- if (addr_type != RTN_UNICAST) {
- NL_SET_ERR_MSG(extack,
- "Nexthop has invalid gateway");
- return -EINVAL;
- }
- if (!netif_carrier_ok(dev))
- nh->fib_nh_flags |= RTNH_F_LINKDOWN;
- nh->fib_nh_dev = dev;
- dev_hold(dev);
- nh->fib_nh_scope = RT_SCOPE_LINK;
- return 0;
+ if (scope >= RT_SCOPE_LINK) {
+ NL_SET_ERR_MSG(extack, "Nexthop has invalid scope");
+ return -EINVAL;
}
- rcu_read_lock();
- {
- struct fib_table *tbl = NULL;
- struct flowi4 fl4 = {
- .daddr = nh->fib_nh_gw4,
- .flowi4_scope = cfg->fc_scope + 1,
- .flowi4_oif = nh->fib_nh_oif,
- .flowi4_iif = LOOPBACK_IFINDEX,
- };
-
- /* It is not necessary, but requires a bit of thinking */
- if (fl4.flowi4_scope < RT_SCOPE_LINK)
- fl4.flowi4_scope = RT_SCOPE_LINK;
-
- if (cfg->fc_table)
- tbl = fib_get_table(net, cfg->fc_table);
-
- if (tbl)
- err = fib_table_lookup(tbl, &fl4, &res,
- FIB_LOOKUP_IGNORE_LINKSTATE |
- FIB_LOOKUP_NOREF);
-
- /* on error or if no table given do full lookup. This
- * is needed for example when nexthops are in the local
- * table rather than the given table
- */
- if (!tbl || err) {
- err = fib_lookup(net, &fl4, &res,
- FIB_LOOKUP_IGNORE_LINKSTATE);
- }
-
- if (err) {
- NL_SET_ERR_MSG(extack,
- "Nexthop has invalid gateway");
- rcu_read_unlock();
- return err;
- }
+ dev = __dev_get_by_index(net, nh->fib_nh_oif);
+ if (!dev) {
+ NL_SET_ERR_MSG(extack, "Nexthop device required for onlink");
+ return -ENODEV;
}
- err = -EINVAL;
- if (res.type != RTN_UNICAST && res.type != RTN_LOCAL) {
- NL_SET_ERR_MSG(extack, "Nexthop has invalid gateway");
- goto out;
+ if (!(dev->flags & IFF_UP)) {
+ NL_SET_ERR_MSG(extack, "Nexthop device is not up");
+ return -ENETDOWN;
}
- nh->fib_nh_scope = res.scope;
- nh->fib_nh_oif = FIB_RES_OIF(res);
- nh->fib_nh_dev = dev = FIB_RES_DEV(res);
- if (!dev) {
- NL_SET_ERR_MSG(extack,
- "No egress device for nexthop gateway");
- goto out;
+ addr_type = inet_addr_type_dev_table(net, dev, nh->fib_nh_gw4);
+ if (addr_type != RTN_UNICAST) {
+ NL_SET_ERR_MSG(extack, "Nexthop has invalid gateway");
+ return -EINVAL;
}
- dev_hold(dev);
if (!netif_carrier_ok(dev))
nh->fib_nh_flags |= RTNH_F_LINKDOWN;
- err = (dev->flags & IFF_UP) ? 0 : -ENETDOWN;
- } else {
- struct in_device *in_dev;
-
- if (nh->fib_nh_flags & (RTNH_F_PERVASIVE | RTNH_F_ONLINK)) {
- NL_SET_ERR_MSG(extack,
- "Invalid flags for nexthop - PERVASIVE and ONLINK can not be set");
- return -EINVAL;
+ nh->fib_nh_dev = dev;
+ dev_hold(dev);
+ nh->fib_nh_scope = RT_SCOPE_LINK;
+ return 0;
+ }
+ rcu_read_lock();
+ {
+ struct fib_table *tbl = NULL;
+ struct flowi4 fl4 = {
+ .daddr = nh->fib_nh_gw4,
+ .flowi4_scope = scope + 1,
+ .flowi4_oif = nh->fib_nh_oif,
+ .flowi4_iif = LOOPBACK_IFINDEX,
+ };
+
+ /* It is not necessary, but requires a bit of thinking */
+ if (fl4.flowi4_scope < RT_SCOPE_LINK)
+ fl4.flowi4_scope = RT_SCOPE_LINK;
+
+ if (table)
+ tbl = fib_get_table(net, table);
+
+ if (tbl)
+ err = fib_table_lookup(tbl, &fl4, &res,
+ FIB_LOOKUP_IGNORE_LINKSTATE |
+ FIB_LOOKUP_NOREF);
+
+ /* on error or if no table given do full lookup. This
+ * is needed for example when nexthops are in the local
+ * table rather than the given table
+ */
+ if (!tbl || err) {
+ err = fib_lookup(net, &fl4, &res,
+ FIB_LOOKUP_IGNORE_LINKSTATE);
}
- rcu_read_lock();
- err = -ENODEV;
- in_dev = inetdev_by_index(net, nh->fib_nh_oif);
- if (!in_dev)
- goto out;
- err = -ENETDOWN;
- if (!(in_dev->dev->flags & IFF_UP)) {
- NL_SET_ERR_MSG(extack, "Device for nexthop is not up");
+
+ if (err) {
+ NL_SET_ERR_MSG(extack, "Nexthop has invalid gateway");
goto out;
}
- nh->fib_nh_dev = in_dev->dev;
- dev_hold(nh->fib_nh_dev);
- nh->fib_nh_scope = RT_SCOPE_HOST;
- if (!netif_carrier_ok(nh->fib_nh_dev))
- nh->fib_nh_flags |= RTNH_F_LINKDOWN;
- err = 0;
}
+
+ err = -EINVAL;
+ if (res.type != RTN_UNICAST && res.type != RTN_LOCAL) {
+ NL_SET_ERR_MSG(extack, "Nexthop has invalid gateway");
+ goto out;
+ }
+ nh->fib_nh_scope = res.scope;
+ nh->fib_nh_oif = FIB_RES_OIF(res);
+ nh->fib_nh_dev = dev = FIB_RES_DEV(res);
+ if (!dev) {
+ NL_SET_ERR_MSG(extack,
+ "No egress device for nexthop gateway");
+ goto out;
+ }
+ dev_hold(dev);
+ if (!netif_carrier_ok(dev))
+ nh->fib_nh_flags |= RTNH_F_LINKDOWN;
+ err = (dev->flags & IFF_UP) ? 0 : -ENETDOWN;
out:
rcu_read_unlock();
return err;
}
+static int fib_check_nh_nongw(struct net *net, struct fib_nh *nh,
+ struct netlink_ext_ack *extack)
+{
+ struct in_device *in_dev;
+ int err;
+
+ if (nh->fib_nh_flags & (RTNH_F_PERVASIVE | RTNH_F_ONLINK)) {
+ NL_SET_ERR_MSG(extack,
+ "Invalid flags for nexthop - PERVASIVE and ONLINK can not be set");
+ return -EINVAL;
+ }
+
+ rcu_read_lock();
+
+ err = -ENODEV;
+ in_dev = inetdev_by_index(net, nh->fib_nh_oif);
+ if (!in_dev)
+ goto out;
+ err = -ENETDOWN;
+ if (!(in_dev->dev->flags & IFF_UP)) {
+ NL_SET_ERR_MSG(extack, "Device for nexthop is not up");
+ goto out;
+ }
+
+ nh->fib_nh_dev = in_dev->dev;
+ dev_hold(nh->fib_nh_dev);
+ nh->fib_nh_scope = RT_SCOPE_HOST;
+ if (!netif_carrier_ok(nh->fib_nh_dev))
+ nh->fib_nh_flags |= RTNH_F_LINKDOWN;
+ err = 0;
+out:
+ rcu_read_unlock();
+ return err;
+}
+
+static int fib_check_nh(struct fib_config *cfg, struct fib_nh *nh,
+ struct netlink_ext_ack *extack)
+{
+ struct net *net = cfg->fc_nlinfo.nl_net;
+ u32 table = cfg->fc_table;
+ int err;
+
+ if (nh->fib_nh_gw_family == AF_INET)
+ err = fib_check_nh_v4_gw(net, nh, table, cfg->fc_scope, extack);
+ else if (nh->fib_nh_gw_family == AF_INET6)
+ err = fib_check_nh_v6_gw(net, nh, table, extack);
+ else
+ err = fib_check_nh_nongw(net, nh, extack);
+
+ return err;
+}
+
static inline unsigned int fib_laddr_hashfn(__be32 val)
{
unsigned int mask = (fib_info_hash_size - 1);
return nh->nh_saddr;
}
+__be32 fib_result_prefsrc(struct net *net, struct fib_result *res)
+{
+ struct fib_nh_common *nhc = res->nhc;
+ struct fib_nh *nh;
+
+ if (res->fi->fib_prefsrc)
+ return res->fi->fib_prefsrc;
+
+ nh = container_of(nhc, struct fib_nh, nh_common);
+ if (nh->nh_saddr_genid == atomic_read(&net->ipv4.dev_addr_genid))
+ return nh->nh_saddr;
+
+ return fib_info_update_nh_saddr(net, nh);
+}
+
static bool fib_valid_prefsrc(struct fib_config *cfg, __be32 fib_prefsrc)
{
if (cfg->fc_type != RTN_LOCAL || !cfg->fc_dst ||
goto failure;
if (fib_props[cfg->fc_type].error) {
- if (cfg->fc_gw || cfg->fc_oif || cfg->fc_mp) {
+ if (cfg->fc_gw_family || cfg->fc_oif || cfg->fc_mp) {
NL_SET_ERR_MSG(extack,
"Gateway, device and multipath can not be specified for this route type");
goto err_inval;
"Route with host scope can not have multiple nexthops");
goto err_inval;
}
- if (nh->fib_nh_gw4) {
+ if (nh->fib_nh_gw_family) {
NL_SET_ERR_MSG(extack,
"Route with host scope can not have a gateway");
goto err_inval;
change_nexthops(fi) {
fib_info_update_nh_saddr(net, nexthop_nh);
+ if (nexthop_nh->fib_nh_gw_family == AF_INET6)
+ fi->fib_nh_is_v6 = true;
} endfor_nexthops(fi)
fib_rebalance(fi);
return ERR_PTR(err);
}
+int fib_nexthop_info(struct sk_buff *skb, const struct fib_nh_common *nhc,
+ unsigned int *flags, bool skip_oif)
+{
+ if (nhc->nhc_flags & RTNH_F_DEAD)
+ *flags |= RTNH_F_DEAD;
+
+ if (nhc->nhc_flags & RTNH_F_LINKDOWN) {
+ *flags |= RTNH_F_LINKDOWN;
+
+ rcu_read_lock();
+ switch (nhc->nhc_family) {
+ case AF_INET:
+ if (ip_ignore_linkdown(nhc->nhc_dev))
+ *flags |= RTNH_F_DEAD;
+ break;
+ case AF_INET6:
+ if (ip6_ignore_linkdown(nhc->nhc_dev))
+ *flags |= RTNH_F_DEAD;
+ break;
+ }
+ rcu_read_unlock();
+ }
+
+ switch (nhc->nhc_gw_family) {
+ case AF_INET:
+ if (nla_put_in_addr(skb, RTA_GATEWAY, nhc->nhc_gw.ipv4))
+ goto nla_put_failure;
+ break;
+ case AF_INET6:
+ /* if gateway family does not match nexthop family
+ * gateway is encoded as RTA_VIA
+ */
+ if (nhc->nhc_gw_family != nhc->nhc_family) {
+ int alen = sizeof(struct in6_addr);
+ struct nlattr *nla;
+ struct rtvia *via;
+
+ nla = nla_reserve(skb, RTA_VIA, alen + 2);
+ if (!nla)
+ goto nla_put_failure;
+
+ via = nla_data(nla);
+ via->rtvia_family = AF_INET6;
+ memcpy(via->rtvia_addr, &nhc->nhc_gw.ipv6, alen);
+ } else if (nla_put_in6_addr(skb, RTA_GATEWAY,
+ &nhc->nhc_gw.ipv6) < 0) {
+ goto nla_put_failure;
+ }
+ break;
+ }
+
+ *flags |= (nhc->nhc_flags & RTNH_F_ONLINK);
+ if (nhc->nhc_flags & RTNH_F_OFFLOAD)
+ *flags |= RTNH_F_OFFLOAD;
+
+ if (!skip_oif && nhc->nhc_dev &&
+ nla_put_u32(skb, RTA_OIF, nhc->nhc_dev->ifindex))
+ goto nla_put_failure;
+
+ if (nhc->nhc_lwtstate &&
+ lwtunnel_fill_encap(skb, nhc->nhc_lwtstate) < 0)
+ goto nla_put_failure;
+
+ return 0;
+
+nla_put_failure:
+ return -EMSGSIZE;
+}
+EXPORT_SYMBOL_GPL(fib_nexthop_info);
+
+#if IS_ENABLED(CONFIG_IP_ROUTE_MULTIPATH) || IS_ENABLED(CONFIG_IPV6)
+int fib_add_nexthop(struct sk_buff *skb, const struct fib_nh_common *nhc,
+ int nh_weight)
+{
+ const struct net_device *dev = nhc->nhc_dev;
+ struct rtnexthop *rtnh;
+ unsigned int flags = 0;
+
+ rtnh = nla_reserve_nohdr(skb, sizeof(*rtnh));
+ if (!rtnh)
+ goto nla_put_failure;
+
+ rtnh->rtnh_hops = nh_weight - 1;
+ rtnh->rtnh_ifindex = dev ? dev->ifindex : 0;
+
+ if (fib_nexthop_info(skb, nhc, &flags, true) < 0)
+ goto nla_put_failure;
+
+ rtnh->rtnh_flags = flags;
+
+ /* length of rtnetlink header + attributes */
+ rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *)rtnh;
+
+ return 0;
+
+nla_put_failure:
+ return -EMSGSIZE;
+}
+EXPORT_SYMBOL_GPL(fib_add_nexthop);
+#endif
+
+#ifdef CONFIG_IP_ROUTE_MULTIPATH
+static int fib_add_multipath(struct sk_buff *skb, struct fib_info *fi)
+{
+ struct nlattr *mp;
+
+ mp = nla_nest_start(skb, RTA_MULTIPATH);
+ if (!mp)
+ goto nla_put_failure;
+
+ for_nexthops(fi) {
+ if (fib_add_nexthop(skb, &nh->nh_common, nh->fib_nh_weight) < 0)
+ goto nla_put_failure;
+#ifdef CONFIG_IP_ROUTE_CLASSID
+ if (nh->nh_tclassid &&
+ nla_put_u32(skb, RTA_FLOW, nh->nh_tclassid))
+ goto nla_put_failure;
+#endif
+ } endfor_nexthops(fi);
+
+ nla_nest_end(skb, mp);
+
+ return 0;
+
+nla_put_failure:
+ return -EMSGSIZE;
+}
+#else
+static int fib_add_multipath(struct sk_buff *skb, struct fib_info *fi)
+{
+ return 0;
+}
+#endif
+
int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
u32 tb_id, u8 type, __be32 dst, int dst_len, u8 tos,
struct fib_info *fi, unsigned int flags)
nla_put_in_addr(skb, RTA_PREFSRC, fi->fib_prefsrc))
goto nla_put_failure;
if (fi->fib_nhs == 1) {
- if (fi->fib_nh->fib_nh_gw4 &&
- nla_put_in_addr(skb, RTA_GATEWAY, fi->fib_nh->fib_nh_gw4))
- goto nla_put_failure;
- if (fi->fib_nh->fib_nh_oif &&
- nla_put_u32(skb, RTA_OIF, fi->fib_nh->fib_nh_oif))
+ struct fib_nh *nh = &fi->fib_nh[0];
+ unsigned int flags = 0;
+
+ if (fib_nexthop_info(skb, &nh->nh_common, &flags, false) < 0)
goto nla_put_failure;
- if (fi->fib_nh->fib_nh_flags & RTNH_F_LINKDOWN) {
- rcu_read_lock();
- if (ip_ignore_linkdown(fi->fib_nh->fib_nh_dev))
- rtm->rtm_flags |= RTNH_F_DEAD;
- rcu_read_unlock();
- }
- if (fi->fib_nh->fib_nh_flags & RTNH_F_OFFLOAD)
- rtm->rtm_flags |= RTNH_F_OFFLOAD;
+
+ rtm->rtm_flags = flags;
#ifdef CONFIG_IP_ROUTE_CLASSID
- if (fi->fib_nh[0].nh_tclassid &&
- nla_put_u32(skb, RTA_FLOW, fi->fib_nh[0].nh_tclassid))
+ if (nh->nh_tclassid &&
+ nla_put_u32(skb, RTA_FLOW, nh->nh_tclassid))
goto nla_put_failure;
#endif
- if (fi->fib_nh->fib_nh_lws &&
- lwtunnel_fill_encap(skb, fi->fib_nh->fib_nh_lws) < 0)
+ } else {
+ if (fib_add_multipath(skb, fi) < 0)
goto nla_put_failure;
}
-#ifdef CONFIG_IP_ROUTE_MULTIPATH
- if (fi->fib_nhs > 1) {
- struct rtnexthop *rtnh;
- struct nlattr *mp;
-
- mp = nla_nest_start(skb, RTA_MULTIPATH);
- if (!mp)
- goto nla_put_failure;
-
- for_nexthops(fi) {
- rtnh = nla_reserve_nohdr(skb, sizeof(*rtnh));
- if (!rtnh)
- goto nla_put_failure;
- rtnh->rtnh_flags = nh->fib_nh_flags & 0xFF;
- if (nh->fib_nh_flags & RTNH_F_LINKDOWN) {
- rcu_read_lock();
- if (ip_ignore_linkdown(nh->fib_nh_dev))
- rtnh->rtnh_flags |= RTNH_F_DEAD;
- rcu_read_unlock();
- }
- rtnh->rtnh_hops = nh->fib_nh_weight - 1;
- rtnh->rtnh_ifindex = nh->fib_nh_oif;
-
- if (nh->fib_nh_gw4 &&
- nla_put_in_addr(skb, RTA_GATEWAY, nh->fib_nh_gw4))
- goto nla_put_failure;
-#ifdef CONFIG_IP_ROUTE_CLASSID
- if (nh->nh_tclassid &&
- nla_put_u32(skb, RTA_FLOW, nh->nh_tclassid))
- goto nla_put_failure;
-#endif
- if (nh->fib_nh_lws &&
- lwtunnel_fill_encap(skb, nh->fib_nh_lws) < 0)
- goto nla_put_failure;
-
- /* length of rtnetlink header + attributes */
- rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *) rtnh;
- } endfor_nexthops(fi);
-
- nla_nest_end(skb, mp);
- }
-#endif
nlmsg_end(skb, nlh);
return 0;
rcu_read_lock_bh();
- n = __ipv4_neigh_lookup_noref(nh->fib_nh_dev,
- (__force u32)nh->fib_nh_gw4);
+ if (likely(nh->fib_nh_gw_family == AF_INET))
+ n = __ipv4_neigh_lookup_noref(nh->fib_nh_dev,
+ (__force u32)nh->fib_nh_gw4);
+ else if (nh->fib_nh_gw_family == AF_INET6)
+ n = __ipv6_neigh_lookup_noref_stub(nh->fib_nh_dev,
+ &nh->fib_nh_gw6);
+ else
+ n = NULL;
if (n)
state = n->nud_state;
struct net *net = fi->fib_net;
bool first = false;
- for_nexthops(fi) {
+ change_nexthops(fi) {
if (net->ipv4.sysctl_fib_multipath_use_neigh) {
- if (!fib_good_nh(nh))
+ if (!fib_good_nh(nexthop_nh))
continue;
if (!first) {
res->nh_sel = nhsel;
+ res->nhc = &nexthop_nh->nh_common;
first = true;
}
}
- if (hash > atomic_read(&nh->fib_nh_upper_bound))
+ if (hash > atomic_read(&nexthop_nh->fib_nh_upper_bound))
continue;
res->nh_sel = nhsel;
+ res->nhc = &nexthop_nh->nh_common;
return;
} endfor_nexthops(fi);
}
check_saddr:
if (!fl4->saddr)
- fl4->saddr = FIB_RES_PREFSRC(net, *res);
+ fl4->saddr = fib_result_prefsrc(net, res);
}
if (fi->fib_flags & RTNH_F_DEAD)
continue;
for (nhsel = 0; nhsel < fi->fib_nhs; nhsel++) {
- const struct fib_nh *nh = &fi->fib_nh[nhsel];
+ struct fib_nh_common *nhc = fib_info_nhc(fi, nhsel);
- if (nh->fib_nh_flags & RTNH_F_DEAD)
+ if (nhc->nhc_flags & RTNH_F_DEAD)
continue;
- if (ip_ignore_linkdown(nh->fib_nh_dev) &&
- nh->fib_nh_flags & RTNH_F_LINKDOWN &&
+ if (ip_ignore_linkdown(nhc->nhc_dev) &&
+ nhc->nhc_flags & RTNH_F_LINKDOWN &&
!(fib_flags & FIB_LOOKUP_IGNORE_LINKSTATE))
continue;
if (!(flp->flowi4_flags & FLOWI_FLAG_SKIP_NH_OIF)) {
if (flp->flowi4_oif &&
- flp->flowi4_oif != nh->fib_nh_oif)
+ flp->flowi4_oif != nhc->nhc_oif)
continue;
}
res->prefix = htonl(n->key);
res->prefixlen = KEYLENGTH - fa->fa_slen;
res->nh_sel = nhsel;
+ res->nhc = nhc;
res->type = fa->fa_type;
res->scope = fi->fib_scope;
res->fi = fi;
#ifdef CONFIG_IP_FIB_TRIE_STATS
this_cpu_inc(stats->semantic_match_passed);
#endif
- trace_fib_table_lookup(tb->tb_id, flp, nh, err);
+ trace_fib_table_lookup(tb->tb_id, flp, nhc, err);
return err;
}
struct guehdr *guehdr;
void *data;
u16 doffset = 0;
+ u8 proto_ctype;
if (!fou)
return 1;
break;
case 1: {
- /* Direct encasulation of IPv4 or IPv6 */
+ /* Direct encapsulation of IPv4 or IPv6 */
int prot;
/* guehdr may change after pull */
guehdr = (struct guehdr *)&udp_hdr(skb)[1];
- hdrlen = sizeof(struct guehdr) + optlen;
-
- if (guehdr->version != 0 || validate_gue_flags(guehdr, optlen))
+ if (validate_gue_flags(guehdr, optlen))
goto drop;
hdrlen = sizeof(struct guehdr) + optlen;
if (unlikely(guehdr->control))
return gue_control_message(skb, guehdr);
+ proto_ctype = guehdr->proto_ctype;
__skb_pull(skb, sizeof(struct udphdr) + hdrlen);
skb_reset_transport_header(skb);
if (iptunnel_pull_offloads(skb))
goto drop;
- return -guehdr->proto_ctype;
+ return -proto_ctype;
drop:
kfree_skb(skb);
case 0: /* Full GUE header present */
break;
case 1: {
- /* Direct encasulation of IPv4 or IPv6 */
+ /* Direct encapsulation of IPv4 or IPv6 */
skb_set_transport_header(skb, -(int)sizeof(struct icmphdr));
switch (((struct iphdr *)guehdr)->version) {
rt = ip_route_output_flow(net, fl4, sk);
if (IS_ERR(rt))
goto no_route;
- if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway)
+ if (opt && opt->opt.is_strictroute && rt->rt_gw_family)
goto route_err;
rcu_read_unlock();
return &rt->dst;
rt = ip_route_output_flow(net, fl4, sk);
if (IS_ERR(rt))
goto no_route;
- if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway)
+ if (opt && opt->opt.is_strictroute && rt->rt_gw_family)
goto route_err;
return &rt->dst;
rt = skb_rtable(skb);
- if (opt->is_strictroute && rt->rt_uses_gateway)
+ if (opt->is_strictroute && rt->rt_gw_family)
goto sr_failed;
IPCB(skb)->flags |= IPSKB_FORWARDED;
struct net *net = dev_net(skb->dev);
struct metadata_dst *tun_dst = NULL;
struct erspan_base_hdr *ershdr;
- struct erspan_metadata *pkt_md;
struct ip_tunnel_net *itn;
struct ip_tunnel *tunnel;
const struct iphdr *iph;
if (unlikely(!pskb_may_pull(skb, len)))
return PACKET_REJECT;
- ershdr = (struct erspan_base_hdr *)(skb->data + gre_hdr_len);
- pkt_md = (struct erspan_metadata *)(ershdr + 1);
-
if (__iptunnel_pull_header(skb,
len,
htons(ETH_P_TEB),
goto drop;
if (tunnel->collect_md) {
+ struct erspan_metadata *pkt_md, *md;
struct ip_tunnel_info *info;
- struct erspan_metadata *md;
+ unsigned char *gh;
__be64 tun_id;
__be16 flags;
if (!tun_dst)
return PACKET_REJECT;
+ /* skb can be uncloned in __iptunnel_pull_header, so
+ * old pkt_md is no longer valid and we need to reset
+ * it
+ */
+ gh = skb_network_header(skb) +
+ skb_network_header_len(skb);
+ pkt_md = (struct erspan_metadata *)(gh + gre_hdr_len +
+ sizeof(*ershdr));
md = ip_tunnel_info_opts(&tun_dst->u.tun_info);
md->version = ver;
md2 = &md->u.md2;
ip_local_deliver_finish);
}
-static inline bool ip_rcv_options(struct sk_buff *skb)
+static inline bool ip_rcv_options(struct sk_buff *skb, struct net_device *dev)
{
struct ip_options *opt;
const struct iphdr *iph;
- struct net_device *dev = skb->dev;
/* It looks as overkill, because not all
IP options require packet mangling.
}
}
- if (ip_options_rcv_srr(skb))
+ if (ip_options_rcv_srr(skb, dev))
goto drop;
}
}
#endif
- if (iph->ihl > 5 && ip_rcv_options(skb))
+ if (iph->ihl > 5 && ip_rcv_options(skb, dev))
goto drop;
rt = skb_rtable(skb);
}
}
-int ip_options_rcv_srr(struct sk_buff *skb)
+int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev)
{
struct ip_options *opt = &(IPCB(skb)->opt);
int srrspace, srrptr;
orefdst = skb->_skb_refdst;
skb_dst_set(skb, NULL);
- err = ip_route_input(skb, nexthop, iph->saddr, iph->tos, skb->dev);
+ err = ip_route_input(skb, nexthop, iph->saddr, iph->tos, dev);
rt2 = skb_rtable(skb);
if (err || (rt2->rt_type != RTN_UNICAST && rt2->rt_type != RTN_LOCAL)) {
skb_dst_drop(skb);
struct net_device *dev = dst->dev;
unsigned int hh_len = LL_RESERVED_SPACE(dev);
struct neighbour *neigh;
- u32 nexthop;
+ bool is_v6gw = false;
if (rt->rt_type == RTN_MULTICAST) {
IP_UPD_PO_STATS(net, IPSTATS_MIB_OUTMCAST, skb->len);
}
rcu_read_lock_bh();
- nexthop = (__force u32) rt_nexthop(rt, ip_hdr(skb)->daddr);
- neigh = __ipv4_neigh_lookup_noref(dev, nexthop);
- if (unlikely(!neigh))
- neigh = __neigh_create(&arp_tbl, &nexthop, dev, false);
+ neigh = ip_neigh_for_gw(rt, skb, &is_v6gw);
if (!IS_ERR(neigh)) {
int res;
sock_confirm_neigh(skb, neigh);
- res = neigh_output(neigh, skb);
-
+ /* if crossing protocols, can not use the cached header */
+ res = neigh_output(neigh, skb, is_v6gw);
rcu_read_unlock_bh();
return res;
}
skb_dst_set_noref(skb, &rt->dst);
packet_routed:
- if (inet_opt && inet_opt->opt.is_strictroute && rt->rt_uses_gateway)
+ if (inet_opt && inet_opt->opt.is_strictroute && rt->rt_gw_family)
goto no_route;
/* OK, we know where to send it, allocate and build IP header. */
return 0;
}
- while (frag) {
- skb = frag->next;
- kfree_skb(frag);
- frag = skb;
- }
+ kfree_skb_list(frag);
+
IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS);
return err;
.key_offset = offsetof(struct mfc_cache, cmparg),
.key_len = sizeof(struct mfc_cache_cmp_arg),
.nelem_hint = 3,
- .locks_mul = 1,
.obj_cmpfn = ipmr_hash_cmp,
.automatic_shrinking = true,
};
if NF_TABLES_IPV4
-config NFT_CHAIN_ROUTE_IPV4
- tristate "IPv4 nf_tables route chain support"
- help
- This option enables the "route" chain for IPv4 in nf_tables. This
- chain type is used to force packet re-routing after mangling header
- fields such as the source, destination, type of service and
- the packet mark.
-
config NFT_REJECT_IPV4
select NF_REJECT_IPV4
default NFT_REJECT
config IP_NF_TARGET_MASQUERADE
tristate "MASQUERADE target support"
- select NF_NAT_MASQUERADE
- default m if NETFILTER_ADVANCED=n
+ select NETFILTER_XT_TARGET_MASQUERADE
help
- Masquerading is a special case of NAT: all outgoing connections are
- changed to seem to come from a particular interface's address, and
- if the interface goes down, those connections are lost. This is
- only useful for dialup accounts with dynamic IP address (ie. your IP
- address will be different on next dialup).
-
- To compile it as a module, choose M here. If unsure, say N.
+ This is a backwards-compat option for the user's convenience
+ (e.g. when running oldconfig). It selects NETFILTER_XT_TARGET_MASQUERADE.
config IP_NF_TARGET_NETMAP
tristate "NETMAP target support"
$(obj)/nf_nat_snmp_basic_main.o: $(obj)/nf_nat_snmp_basic.asn1.h
obj-$(CONFIG_NF_NAT_SNMP_BASIC) += nf_nat_snmp_basic.o
-obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV4) += nft_chain_route_ipv4.o
obj-$(CONFIG_NFT_REJECT_IPV4) += nft_reject_ipv4.o
obj-$(CONFIG_NFT_FIB_IPV4) += nft_fib_ipv4.o
obj-$(CONFIG_NFT_DUP_IPV4) += nft_dup_ipv4.o
# targets
obj-$(CONFIG_IP_NF_TARGET_CLUSTERIP) += ipt_CLUSTERIP.o
obj-$(CONFIG_IP_NF_TARGET_ECN) += ipt_ECN.o
-obj-$(CONFIG_IP_NF_TARGET_MASQUERADE) += ipt_MASQUERADE.o
obj-$(CONFIG_IP_NF_TARGET_REJECT) += ipt_REJECT.o
obj-$(CONFIG_IP_NF_TARGET_SYNPROXY) += ipt_SYNPROXY.o
+++ /dev/null
-/*
- * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
- * Copyright (c) 2012 Pablo Neira Ayuso <pablo@netfilter.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/list.h>
-#include <linux/skbuff.h>
-#include <linux/netlink.h>
-#include <linux/netfilter.h>
-#include <linux/netfilter_ipv4.h>
-#include <linux/netfilter/nfnetlink.h>
-#include <linux/netfilter/nf_tables.h>
-#include <net/netfilter/nf_tables.h>
-#include <net/netfilter/nf_tables_ipv4.h>
-#include <net/route.h>
-#include <net/ip.h>
-
-static unsigned int nf_route_table_hook(void *priv,
- struct sk_buff *skb,
- const struct nf_hook_state *state)
-{
- unsigned int ret;
- struct nft_pktinfo pkt;
- u32 mark;
- __be32 saddr, daddr;
- u_int8_t tos;
- const struct iphdr *iph;
- int err;
-
- nft_set_pktinfo(&pkt, skb, state);
- nft_set_pktinfo_ipv4(&pkt, skb);
-
- mark = skb->mark;
- iph = ip_hdr(skb);
- saddr = iph->saddr;
- daddr = iph->daddr;
- tos = iph->tos;
-
- ret = nft_do_chain(&pkt, priv);
- if (ret != NF_DROP && ret != NF_STOLEN) {
- iph = ip_hdr(skb);
-
- if (iph->saddr != saddr ||
- iph->daddr != daddr ||
- skb->mark != mark ||
- iph->tos != tos) {
- err = ip_route_me_harder(state->net, skb, RTN_UNSPEC);
- if (err < 0)
- ret = NF_DROP_ERR(err);
- }
- }
- return ret;
-}
-
-static const struct nft_chain_type nft_chain_route_ipv4 = {
- .name = "route",
- .type = NFT_CHAIN_T_ROUTE,
- .family = NFPROTO_IPV4,
- .owner = THIS_MODULE,
- .hook_mask = (1 << NF_INET_LOCAL_OUT),
- .hooks = {
- [NF_INET_LOCAL_OUT] = nf_route_table_hook,
- },
-};
-
-static int __init nft_chain_route_init(void)
-{
- nft_register_chain_type(&nft_chain_route_ipv4);
-
- return 0;
-}
-
-static void __exit nft_chain_route_exit(void)
-{
- nft_unregister_chain_type(&nft_chain_route_ipv4);
-}
-
-module_init(nft_chain_route_init);
-module_exit(nft_chain_route_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
-MODULE_ALIAS_NFT_CHAIN(AF_INET, "route");
struct sk_buff *skb,
const void *daddr)
{
+ const struct rtable *rt = container_of(dst, struct rtable, dst);
struct net_device *dev = dst->dev;
- const __be32 *pkey = daddr;
- const struct rtable *rt;
struct neighbour *n;
- rt = (const struct rtable *) dst;
- if (rt->rt_gateway)
- pkey = (const __be32 *) &rt->rt_gateway;
- else if (skb)
- pkey = &ip_hdr(skb)->daddr;
+ rcu_read_lock_bh();
+
+ if (likely(rt->rt_gw_family == AF_INET)) {
+ n = ip_neigh_gw4(dev, rt->rt_gw4);
+ } else if (rt->rt_gw_family == AF_INET6) {
+ n = ip_neigh_gw6(dev, &rt->rt_gw6);
+ } else {
+ __be32 pkey;
+
+ pkey = skb ? ip_hdr(skb)->daddr : *((__be32 *) daddr);
+ n = ip_neigh_gw4(dev, pkey);
+ }
- n = __ipv4_neigh_lookup(dev, *(__force u32 *)pkey);
- if (n)
- return n;
- return neigh_create(&arp_tbl, pkey, dev);
+ if (n && !refcount_inc_not_zero(&n->refcnt))
+ n = NULL;
+
+ rcu_read_unlock_bh();
+
+ return n;
}
static void ipv4_confirm_neigh(const struct dst_entry *dst, const void *daddr)
{
+ const struct rtable *rt = container_of(dst, struct rtable, dst);
struct net_device *dev = dst->dev;
const __be32 *pkey = daddr;
- const struct rtable *rt;
- rt = (const struct rtable *)dst;
- if (rt->rt_gateway)
- pkey = (const __be32 *)&rt->rt_gateway;
- else if (!daddr ||
+ if (rt->rt_gw_family == AF_INET) {
+ pkey = (const __be32 *)&rt->rt_gw4;
+ } else if (rt->rt_gw_family == AF_INET6) {
+ return __ipv6_confirm_neigh_stub(dev, &rt->rt_gw6);
+ } else if (!daddr ||
(rt->rt_flags &
- (RTCF_MULTICAST | RTCF_BROADCAST | RTCF_LOCAL)))
+ (RTCF_MULTICAST | RTCF_BROADCAST | RTCF_LOCAL))) {
return;
-
+ }
__ipv4_confirm_neigh(dev, *(__force u32 *)pkey);
}
if (fnhe->fnhe_gw) {
rt->rt_flags |= RTCF_REDIRECTED;
- rt->rt_gateway = fnhe->fnhe_gw;
- rt->rt_uses_gateway = 1;
+ rt->rt_gw_family = AF_INET;
+ rt->rt_gw4 = fnhe->fnhe_gw;
}
}
return;
}
- if (rt->rt_gateway != old_gw)
+ if (rt->rt_gw_family != AF_INET || rt->rt_gw4 != old_gw)
return;
in_dev = __in_dev_get_rcu(dev);
neigh_event_send(n, NULL);
} else {
if (fib_lookup(net, fl4, &res, 0) == 0) {
- struct fib_nh *nh = &FIB_RES_NH(res);
+ struct fib_nh_common *nhc = FIB_RES_NHC(res);
+ struct fib_nh *nh;
+ nh = container_of(nhc, struct fib_nh, nh_common);
update_or_create_fnhe(nh, fl4->daddr, new_gw,
0, false,
jiffies + ip_rt_gc_timeout);
rcu_read_lock();
if (fib_lookup(dev_net(dst->dev), fl4, &res, 0) == 0) {
- struct fib_nh *nh = &FIB_RES_NH(res);
+ struct fib_nh_common *nhc = FIB_RES_NHC(res);
+ struct fib_nh *nh;
+ nh = container_of(nhc, struct fib_nh, nh_common);
update_or_create_fnhe(nh, fl4->daddr, 0, mtu, lock,
jiffies + ip_rt_mtu_expires);
}
static void ipv4_link_failure(struct sk_buff *skb)
{
+ struct ip_options opt;
struct rtable *rt;
+ int res;
+
+ /* Recompile ip options since IPCB may not be valid anymore.
+ */
+ memset(&opt, 0, sizeof(opt));
+ opt.optlen = ip_hdr(skb)->ihl*4 - sizeof(struct iphdr);
- icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0);
+ rcu_read_lock();
+ res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL);
+ rcu_read_unlock();
+
+ if (res)
+ return;
+
+ __icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0, &opt);
rt = skb_rtable(skb);
if (rt)
rcu_read_lock();
if (fib_lookup(dev_net(rt->dst.dev), &fl4, &res, 0) == 0)
- src = FIB_RES_PREFSRC(dev_net(rt->dst.dev), res);
+ src = fib_result_prefsrc(dev_net(rt->dst.dev), &res);
else
src = inet_select_addr(rt->dst.dev,
rt_nexthop(rt, iph->daddr),
mtu = READ_ONCE(dst->dev->mtu);
if (unlikely(ip_mtu_locked(dst))) {
- if (rt->rt_uses_gateway && mtu > 576)
+ if (rt->rt_gw_family && mtu > 576)
mtu = 576;
}
u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr)
{
+ struct fib_nh_common *nhc = res->nhc;
+ struct net_device *dev = nhc->nhc_dev;
struct fib_info *fi = res->fi;
- struct fib_nh *nh = &fi->fib_nh[res->nh_sel];
- struct net_device *dev = nh->fib_nh_dev;
u32 mtu = 0;
if (dev_net(dev)->ipv4.sysctl_ip_fwd_use_pmtu ||
mtu = fi->fib_mtu;
if (likely(!mtu)) {
+ struct fib_nh *nh = container_of(nhc, struct fib_nh, nh_common);
struct fib_nh_exception *fnhe;
fnhe = find_exception(nh, daddr);
if (likely(!mtu))
mtu = min(READ_ONCE(dev->mtu), IP_MAX_MTU);
- return mtu - lwtunnel_headroom(nh->fib_nh_lws, mtu);
+ return mtu - lwtunnel_headroom(nhc->nhc_lwtstate, mtu);
}
static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe,
orig = NULL;
}
fill_route_from_fnhe(rt, fnhe);
- if (!rt->rt_gateway)
- rt->rt_gateway = daddr;
+ if (!rt->rt_gw4) {
+ rt->rt_gw4 = daddr;
+ rt->rt_gw_family = AF_INET;
+ }
if (do_cache) {
dst_hold(&rt->dst);
bool cached = false;
if (fi) {
- struct fib_nh *nh = &FIB_RES_NH(*res);
-
- if (nh->fib_nh_gw4 && nh->fib_nh_scope == RT_SCOPE_LINK) {
- rt->rt_gateway = nh->fib_nh_gw4;
- rt->rt_uses_gateway = 1;
+ struct fib_nh_common *nhc = FIB_RES_NHC(*res);
+ struct fib_nh *nh;
+
+ if (nhc->nhc_gw_family && nhc->nhc_scope == RT_SCOPE_LINK) {
+ rt->rt_gw_family = nhc->nhc_gw_family;
+ /* only INET and INET6 are supported */
+ if (likely(nhc->nhc_gw_family == AF_INET))
+ rt->rt_gw4 = nhc->nhc_gw.ipv4;
+ else
+ rt->rt_gw6 = nhc->nhc_gw.ipv6;
}
+
ip_dst_init_metrics(&rt->dst, fi->fib_metrics);
+ nh = container_of(nhc, struct fib_nh, nh_common);
#ifdef CONFIG_IP_ROUTE_CLASSID
rt->dst.tclassid = nh->nh_tclassid;
#endif
* However, if we are unsuccessful at storing this
* route into the cache we really need to set it.
*/
- if (!rt->rt_gateway)
- rt->rt_gateway = daddr;
+ if (!rt->rt_gw4) {
+ rt->rt_gw_family = AF_INET;
+ rt->rt_gw4 = daddr;
+ }
rt_add_uncached_list(rt);
}
} else
rt->rt_iif = 0;
rt->rt_pmtu = 0;
rt->rt_mtu_locked = 0;
- rt->rt_gateway = 0;
- rt->rt_uses_gateway = 0;
+ rt->rt_gw_family = 0;
+ rt->rt_gw4 = 0;
INIT_LIST_HEAD(&rt->rt_uncached);
rt->dst.output = ip_output;
struct in_device *in_dev,
__be32 daddr, __be32 saddr, u32 tos)
{
+ struct fib_nh_common *nhc = FIB_RES_NHC(*res);
+ struct net_device *dev = nhc->nhc_dev;
struct fib_nh_exception *fnhe;
struct rtable *rth;
+ struct fib_nh *nh;
int err;
struct in_device *out_dev;
bool do_cache;
u32 itag = 0;
/* get a working reference to the output device */
- out_dev = __in_dev_get_rcu(FIB_RES_DEV(*res));
+ out_dev = __in_dev_get_rcu(dev);
if (!out_dev) {
net_crit_ratelimited("Bug in ip_route_input_slow(). Please report.\n");
return -EINVAL;
do_cache = res->fi && !itag;
if (out_dev == in_dev && err && IN_DEV_TX_REDIRECTS(out_dev) &&
- skb->protocol == htons(ETH_P_IP) &&
- (IN_DEV_SHARED_MEDIA(out_dev) ||
- inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res))))
- IPCB(skb)->flags |= IPSKB_DOREDIRECT;
+ skb->protocol == htons(ETH_P_IP)) {
+ __be32 gw;
+
+ gw = nhc->nhc_gw_family == AF_INET ? nhc->nhc_gw.ipv4 : 0;
+ if (IN_DEV_SHARED_MEDIA(out_dev) ||
+ inet_addr_onlink(out_dev, saddr, gw))
+ IPCB(skb)->flags |= IPSKB_DOREDIRECT;
+ }
if (skb->protocol != htons(ETH_P_IP)) {
/* Not IP (i.e. ARP). Do not create route, if it is
}
}
- fnhe = find_exception(&FIB_RES_NH(*res), daddr);
+ nh = container_of(nhc, struct fib_nh, nh_common);
+ fnhe = find_exception(nh, daddr);
if (do_cache) {
if (fnhe)
rth = rcu_dereference(fnhe->fnhe_rth_input);
else
- rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
+ rth = rcu_dereference(nh->nh_rth_input);
if (rt_cache_valid(rth)) {
skb_dst_set_noref(skb, &rth->dst);
goto out;
do_cache = false;
if (res->fi) {
if (!itag) {
- rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
+ struct fib_nh_common *nhc = FIB_RES_NHC(*res);
+ struct fib_nh *nh;
+
+ nh = container_of(nhc, struct fib_nh, nh_common);
+ rth = rcu_dereference(nh->nh_rth_input);
if (rt_cache_valid(rth)) {
skb_dst_set_noref(skb, &rth->dst);
err = 0;
}
if (do_cache) {
- struct fib_nh *nh = &FIB_RES_NH(*res);
+ struct fib_nh_common *nhc = FIB_RES_NHC(*res);
+ struct fib_nh *nh;
- rth->dst.lwtstate = lwtstate_get(nh->fib_nh_lws);
+ rth->dst.lwtstate = lwtstate_get(nhc->nhc_lwtstate);
if (lwtunnel_input_redirect(rth->dst.lwtstate)) {
WARN_ON(rth->dst.input == lwtunnel_input);
rth->dst.lwtstate->orig_input = rth->dst.input;
rth->dst.input = lwtunnel_input;
}
+ nh = container_of(nhc, struct fib_nh, nh_common);
if (unlikely(!rt_cache_route(nh, rth)))
rt_add_uncached_list(rth);
}
fnhe = NULL;
do_cache &= fi != NULL;
if (fi) {
+ struct fib_nh_common *nhc = FIB_RES_NHC(*res);
+ struct fib_nh *nh = container_of(nhc, struct fib_nh, nh_common);
struct rtable __rcu **prth;
- struct fib_nh *nh = &FIB_RES_NH(*res);
fnhe = find_exception(nh, fl4->daddr);
if (!do_cache)
} else {
if (unlikely(fl4->flowi4_flags &
FLOWI_FLAG_KNOWN_NH &&
- !(nh->fib_nh_gw4 &&
- nh->fib_nh_scope == RT_SCOPE_LINK))) {
+ !(nhc->nhc_gw_family &&
+ nhc->nhc_scope == RT_SCOPE_LINK))) {
do_cache = false;
goto add;
}
rt->rt_genid = rt_genid_ipv4(net);
rt->rt_flags = ort->rt_flags;
rt->rt_type = ort->rt_type;
- rt->rt_gateway = ort->rt_gateway;
- rt->rt_uses_gateway = ort->rt_uses_gateway;
+ rt->rt_gw_family = ort->rt_gw_family;
+ if (rt->rt_gw_family == AF_INET)
+ rt->rt_gw4 = ort->rt_gw4;
+ else if (rt->rt_gw_family == AF_INET6)
+ rt->rt_gw6 = ort->rt_gw6;
INIT_LIST_HEAD(&rt->rt_uncached);
}
if (nla_put_in_addr(skb, RTA_PREFSRC, fl4->saddr))
goto nla_put_failure;
}
- if (rt->rt_uses_gateway &&
- nla_put_in_addr(skb, RTA_GATEWAY, rt->rt_gateway))
+ if (rt->rt_gw_family == AF_INET &&
+ nla_put_in_addr(skb, RTA_GATEWAY, rt->rt_gw4)) {
goto nla_put_failure;
+ } else if (rt->rt_gw_family == AF_INET6) {
+ int alen = sizeof(struct in6_addr);
+ struct nlattr *nla;
+ struct rtvia *via;
+
+ nla = nla_reserve(skb, RTA_VIA, alen + 2);
+ if (!nla)
+ goto nla_put_failure;
+
+ via = nla_data(nla);
+ via->rtvia_family = AF_INET6;
+ memcpy(via->rtvia_addr, &rt->rt_gw6, alen);
+ }
expires = rt->dst.expires;
if (expires) {
#define DCTCP_MAX_ALPHA 1024U
struct dctcp {
- u32 acked_bytes_ecn;
- u32 acked_bytes_total;
- u32 prior_snd_una;
+ u32 old_delivered;
+ u32 old_delivered_ce;
u32 prior_rcv_nxt;
u32 dctcp_alpha;
u32 next_seq;
module_param(dctcp_alpha_on_init, uint, 0644);
MODULE_PARM_DESC(dctcp_alpha_on_init, "parameter for initial alpha value");
-static unsigned int dctcp_clamp_alpha_on_loss __read_mostly;
-module_param(dctcp_clamp_alpha_on_loss, uint, 0644);
-MODULE_PARM_DESC(dctcp_clamp_alpha_on_loss,
- "parameter for clamping alpha on loss");
-
static struct tcp_congestion_ops dctcp_reno;
static void dctcp_reset(const struct tcp_sock *tp, struct dctcp *ca)
{
ca->next_seq = tp->snd_nxt;
- ca->acked_bytes_ecn = 0;
- ca->acked_bytes_total = 0;
+ ca->old_delivered = tp->delivered;
+ ca->old_delivered_ce = tp->delivered_ce;
}
static void dctcp_init(struct sock *sk)
sk->sk_state == TCP_CLOSE)) {
struct dctcp *ca = inet_csk_ca(sk);
- ca->prior_snd_una = tp->snd_una;
ca->prior_rcv_nxt = tp->rcv_nxt;
ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA);
{
const struct tcp_sock *tp = tcp_sk(sk);
struct dctcp *ca = inet_csk_ca(sk);
- u32 acked_bytes = tp->snd_una - ca->prior_snd_una;
-
- /* If ack did not advance snd_una, count dupack as MSS size.
- * If ack did update window, do not count it at all.
- */
- if (acked_bytes == 0 && !(flags & CA_ACK_WIN_UPDATE))
- acked_bytes = inet_csk(sk)->icsk_ack.rcv_mss;
- if (acked_bytes) {
- ca->acked_bytes_total += acked_bytes;
- ca->prior_snd_una = tp->snd_una;
-
- if (flags & CA_ACK_ECE)
- ca->acked_bytes_ecn += acked_bytes;
- }
/* Expired RTT */
if (!before(tp->snd_una, ca->next_seq)) {
- u64 bytes_ecn = ca->acked_bytes_ecn;
+ u32 delivered_ce = tp->delivered_ce - ca->old_delivered_ce;
u32 alpha = ca->dctcp_alpha;
/* alpha = (1 - g) * alpha + g * F */
alpha -= min_not_zero(alpha, alpha >> dctcp_shift_g);
- if (bytes_ecn) {
+ if (delivered_ce) {
+ u32 delivered = tp->delivered - ca->old_delivered;
+
/* If dctcp_shift_g == 1, a 32bit value would overflow
- * after 8 Mbytes.
+ * after 8 M packets.
*/
- bytes_ecn <<= (10 - dctcp_shift_g);
- do_div(bytes_ecn, max(1U, ca->acked_bytes_total));
+ delivered_ce <<= (10 - dctcp_shift_g);
+ delivered_ce /= max(1U, delivered);
- alpha = min(alpha + (u32)bytes_ecn, DCTCP_MAX_ALPHA);
+ alpha = min(alpha + delivered_ce, DCTCP_MAX_ALPHA);
}
/* dctcp_alpha can be read from dctcp_get_info() without
* synchro, so we ask compiler to not use dctcp_alpha
}
}
-static void dctcp_state(struct sock *sk, u8 new_state)
+static void dctcp_react_to_loss(struct sock *sk)
{
- if (dctcp_clamp_alpha_on_loss && new_state == TCP_CA_Loss) {
- struct dctcp *ca = inet_csk_ca(sk);
+ struct dctcp *ca = inet_csk_ca(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
- /* If this extension is enabled, we clamp dctcp_alpha to
- * max on packet loss; the motivation is that dctcp_alpha
- * is an indicator to the extend of congestion and packet
- * loss is an indicator of extreme congestion; setting
- * this in practice turned out to be beneficial, and
- * effectively assumes total congestion which reduces the
- * window by half.
- */
- ca->dctcp_alpha = DCTCP_MAX_ALPHA;
- }
+ ca->loss_cwnd = tp->snd_cwnd;
+ tp->snd_ssthresh = max(tp->snd_cwnd >> 1U, 2U);
+}
+
+static void dctcp_state(struct sock *sk, u8 new_state)
+{
+ if (new_state == TCP_CA_Recovery &&
+ new_state != inet_csk(sk)->icsk_ca_state)
+ dctcp_react_to_loss(sk);
+ /* We handle RTO in dctcp_cwnd_event to ensure that we perform only
+ * one loss-adjustment per RTT.
+ */
}
static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
case CA_EVENT_ECN_NO_CE:
dctcp_ece_ack_update(sk, ev, &ca->prior_rcv_nxt, &ca->ce_state);
break;
+ case CA_EVENT_LOSS:
+ dctcp_react_to_loss(sk);
+ break;
default:
/* Don't care for the rest. */
break;
union tcp_cc_info *info)
{
const struct dctcp *ca = inet_csk_ca(sk);
+ const struct tcp_sock *tp = tcp_sk(sk);
/* Fill it also in case of VEGASINFO due to req struct limits.
* We can still correctly retrieve it later.
info->dctcp.dctcp_enabled = 1;
info->dctcp.dctcp_ce_state = (u16) ca->ce_state;
info->dctcp.dctcp_alpha = ca->dctcp_alpha;
- info->dctcp.dctcp_ab_ecn = ca->acked_bytes_ecn;
- info->dctcp.dctcp_ab_tot = ca->acked_bytes_total;
+ info->dctcp.dctcp_ab_ecn = tp->mss_cache *
+ (tp->delivered_ce - ca->old_delivered_ce);
+ info->dctcp.dctcp_ab_tot = tp->mss_cache *
+ (tp->delivered - ca->old_delivered);
}
*attr = INET_DIAG_DCTCPINFO;
static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
+ int room;
+
+ room = min_t(int, tp->window_clamp, tcp_space(sk)) - tp->rcv_ssthresh;
/* Check #1 */
- if (tp->rcv_ssthresh < tp->window_clamp &&
- (int)tp->rcv_ssthresh < tcp_space(sk) &&
- !tcp_under_memory_pressure(sk)) {
+ if (room > 0 && !tcp_under_memory_pressure(sk)) {
int incr;
/* Check #2. Increase window, if skb with such overhead
if (incr) {
incr = max_t(int, incr, 2 * skb->len);
- tp->rcv_ssthresh = min(tp->rcv_ssthresh + incr,
- tp->window_clamp);
+ tp->rcv_ssthresh += min(room, incr);
inet_csk(sk)->icsk_ack.quick |= 1;
}
}
* congestion control: Linux DCTCP asserts ECT on all packets,
* including SYN, which is most optimal solution; however,
* others, such as FreeBSD do not.
+ *
+ * Exception: At least one of the reserved bits of the TCP header (th->res1) is
+ * set, indicating the use of a future TCP extension (such as AccECN). See
+ * RFC8311 §4.3 which updates RFC3168 to allow the development of such
+ * extensions.
*/
static void tcp_ecn_create_request(struct request_sock *req,
const struct sk_buff *skb,
ecn_ok_dst = dst_feature(dst, DST_FEATURE_ECN_MASK);
ecn_ok = net->ipv4.sysctl_tcp_ecn || ecn_ok_dst;
- if ((!ect && ecn_ok) || tcp_ca_needs_ecn(listen_sk) ||
+ if (((!ect || th->res1) && ecn_ok) || tcp_ca_needs_ecn(listen_sk) ||
(ecn_ok_dst & DST_FEATURE_ECN_CA) ||
tcp_bpf_ca_needs_ecn((struct sock *)req))
inet_rsk(req)->ecn_ok = 1;
{
int cpu;
- module_put(net->ipv4.tcp_congestion_control->owner);
+ if (net->ipv4.tcp_congestion_control)
+ module_put(net->ipv4.tcp_congestion_control->owner);
for_each_possible_cpu(cpu)
inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu));
tskb = skb_rb_last(&sk->tcp_rtx_queue);
if (tskb) {
-coalesce:
TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN;
TCP_SKB_CB(tskb)->end_seq++;
tp->write_seq++;
}
} else {
skb = alloc_skb_fclone(MAX_TCP_HEADER, sk->sk_allocation);
- if (unlikely(!skb)) {
- if (tskb)
- goto coalesce;
+ if (unlikely(!skb))
return;
- }
+
INIT_LIST_HEAD(&skb->tcp_tsorted_anchor);
skb_reserve(skb, MAX_TCP_HEADER);
sk_forced_mem_schedule(sk, skb->truesize);
EXPORT_SYMBOL(udp_ioctl);
struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags,
- int noblock, int *peeked, int *off, int *err)
+ int noblock, int *off, int *err)
{
struct sk_buff_head *sk_queue = &sk->sk_receive_queue;
struct sk_buff_head *queue;
break;
error = -EAGAIN;
- *peeked = 0;
do {
spin_lock_bh(&queue->lock);
skb = __skb_try_recv_from_queue(sk, queue, flags,
udp_skb_destructor,
- peeked, off, err,
- &last);
+ off, err, &last);
if (skb) {
spin_unlock_bh(&queue->lock);
return skb;
skb = __skb_try_recv_from_queue(sk, queue, flags,
udp_skb_dtor_locked,
- peeked, off, err,
- &last);
+ off, err, &last);
spin_unlock(&sk_queue->lock);
spin_unlock_bh(&queue->lock);
if (skb)
DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name);
struct sk_buff *skb;
unsigned int ulen, copied;
- int peeked, peeking, off;
- int err;
+ int off, err, peeking = flags & MSG_PEEK;
int is_udplite = IS_UDPLITE(sk);
bool checksum_valid = false;
return ip_recv_error(sk, msg, len, addr_len);
try_again:
- peeking = flags & MSG_PEEK;
off = sk_peek_offset(sk, flags);
- skb = __skb_recv_udp(sk, flags, noblock, &peeked, &off, &err);
+ skb = __skb_recv_udp(sk, flags, noblock, &off, &err);
if (!skb)
return err;
}
if (unlikely(err)) {
- if (!peeked) {
+ if (!peeking) {
atomic_inc(&sk->sk_drops);
UDP_INC_STATS(sock_net(sk),
UDP_MIB_INERRORS, is_udplite);
return err;
}
- if (!peeked)
+ if (!peeking)
UDP_INC_STATS(sock_net(sk),
UDP_MIB_INDATAGRAMS, is_udplite);
xdst->u.rt.rt_flags = rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST |
RTCF_LOCAL);
xdst->u.rt.rt_type = rt->rt_type;
- xdst->u.rt.rt_gateway = rt->rt_gateway;
- xdst->u.rt.rt_uses_gateway = rt->rt_uses_gateway;
+ xdst->u.rt.rt_gw_family = rt->rt_gw_family;
+ if (rt->rt_gw_family == AF_INET)
+ xdst->u.rt.rt_gw4 = rt->rt_gw4;
+ else if (rt->rt_gw_family == AF_INET6)
+ xdst->u.rt.rt_gw6 = rt->rt_gw6;
xdst->u.rt.rt_pmtu = rt->rt_pmtu;
xdst->u.rt.rt_mtu_locked = rt->rt_mtu_locked;
INIT_LIST_HEAD(&xdst->u.rt.rt_uncached);
for_each_fib6_node_rt_rcu(fn) {
if (rt->fib6_nh.fib_nh_dev->ifindex != dev->ifindex)
continue;
- if (no_gw && rt->fib6_nh.fib_nh_has_gw)
+ if (no_gw && rt->fib6_nh.fib_nh_gw_family)
continue;
if ((rt->fib6_flags & flags) != flags)
continue;
return NULL;
}
-static struct fib6_info *
+static int
eafnosupport_fib6_table_lookup(struct net *net, struct fib6_table *table,
- int oif, struct flowi6 *fl6, int flags)
+ int oif, struct flowi6 *fl6,
+ struct fib6_result *res, int flags)
{
- return NULL;
+ return -EAFNOSUPPORT;
}
-static struct fib6_info *
+static int
eafnosupport_fib6_lookup(struct net *net, int oif, struct flowi6 *fl6,
- int flags)
+ struct fib6_result *res, int flags)
{
- return NULL;
+ return -EAFNOSUPPORT;
}
-static struct fib6_info *
-eafnosupport_fib6_multipath_select(const struct net *net, struct fib6_info *f6i,
- struct flowi6 *fl6, int oif,
- const struct sk_buff *skb, int strict)
+static void
+eafnosupport_fib6_select_path(const struct net *net, struct fib6_result *res,
+ struct flowi6 *fl6, int oif, bool have_oif_match,
+ const struct sk_buff *skb, int strict)
{
- return f6i;
}
static u32
-eafnosupport_ip6_mtu_from_fib6(struct fib6_info *f6i, struct in6_addr *daddr,
- struct in6_addr *saddr)
+eafnosupport_ip6_mtu_from_fib6(const struct fib6_result *res,
+ const struct in6_addr *daddr,
+ const struct in6_addr *saddr)
{
return 0;
}
+static int eafnosupport_fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
+ struct fib6_config *cfg, gfp_t gfp_flags,
+ struct netlink_ext_ack *extack)
+{
+ NL_SET_ERR_MSG(extack, "IPv6 support not enabled in kernel");
+ return -EAFNOSUPPORT;
+}
+
const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) {
.ipv6_dst_lookup = eafnosupport_ipv6_dst_lookup,
.ipv6_route_input = eafnosupport_ipv6_route_input,
.fib6_get_table = eafnosupport_fib6_get_table,
.fib6_table_lookup = eafnosupport_fib6_table_lookup,
.fib6_lookup = eafnosupport_fib6_lookup,
- .fib6_multipath_select = eafnosupport_fib6_multipath_select,
+ .fib6_select_path = eafnosupport_fib6_select_path,
.ip6_mtu_from_fib6 = eafnosupport_ip6_mtu_from_fib6,
+ .fib6_nh_init = eafnosupport_fib6_nh_init,
};
EXPORT_SYMBOL_GPL(ipv6_stub);
.fib6_get_table = fib6_get_table,
.fib6_table_lookup = fib6_table_lookup,
.fib6_lookup = fib6_lookup,
- .fib6_multipath_select = fib6_multipath_select,
+ .fib6_select_path = fib6_select_path,
.ip6_mtu_from_fib6 = ip6_mtu_from_fib6,
+ .fib6_nh_init = fib6_nh_init,
+ .fib6_nh_release = fib6_nh_release,
.udpv6_encap_enable = udpv6_encap_enable,
.ndisc_send_na = ndisc_send_na,
.nd_tbl = &nd_tbl,
}
/* called with rcu lock held; no reference taken on fib6_info */
-struct fib6_info *fib6_lookup(struct net *net, int oif, struct flowi6 *fl6,
- int flags)
+int fib6_lookup(struct net *net, int oif, struct flowi6 *fl6,
+ struct fib6_result *res, int flags)
{
- struct fib6_info *f6i;
int err;
if (net->ipv6.fib6_has_custom_rules) {
struct fib_lookup_arg arg = {
.lookup_ptr = fib6_table_lookup,
.lookup_data = &oif,
+ .result = res,
.flags = FIB_LOOKUP_NOREF,
};
err = fib_rules_lookup(net->ipv6.fib6_rules_ops,
flowi6_to_flowi(fl6), flags, &arg);
- if (err)
- return ERR_PTR(err);
-
- f6i = arg.result ? : net->ipv6.fib6_null_entry;
} else {
- f6i = fib6_table_lookup(net, net->ipv6.fib6_local_tbl,
- oif, fl6, flags);
- if (!f6i || f6i == net->ipv6.fib6_null_entry)
- f6i = fib6_table_lookup(net, net->ipv6.fib6_main_tbl,
- oif, fl6, flags);
+ err = fib6_table_lookup(net, net->ipv6.fib6_local_tbl, oif,
+ fl6, res, flags);
+ if (err || res->f6i == net->ipv6.fib6_null_entry)
+ err = fib6_table_lookup(net, net->ipv6.fib6_main_tbl,
+ oif, fl6, res, flags);
}
- return f6i;
+ return err;
}
struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
static int fib6_rule_action_alt(struct fib_rule *rule, struct flowi *flp,
int flags, struct fib_lookup_arg *arg)
{
+ struct fib6_result *res = arg->result;
struct flowi6 *flp6 = &flp->u.ip6;
struct net *net = rule->fr_net;
struct fib6_table *table;
- struct fib6_info *f6i;
int err = -EAGAIN, *oif;
u32 tb_id;
return -EAGAIN;
oif = (int *)arg->lookup_data;
- f6i = fib6_table_lookup(net, table, *oif, flp6, flags);
- if (f6i != net->ipv6.fib6_null_entry) {
+ err = fib6_table_lookup(net, table, *oif, flp6, res, flags);
+ if (!err && res->f6i != net->ipv6.fib6_null_entry)
err = fib6_rule_saddr(net, rule, flags, flp6,
- fib6_info_nh_dev(f6i));
-
- if (likely(!err))
- arg->result = f6i;
- }
+ res->nh->fib_nh_dev);
return err;
}
done:
rhashtable_walk_stop(&iter);
+ rhashtable_walk_exit(&iter);
return ret;
}
}
/* called with rcu lock held; no reference taken on fib6_info */
-struct fib6_info *fib6_lookup(struct net *net, int oif, struct flowi6 *fl6,
- int flags)
+int fib6_lookup(struct net *net, int oif, struct flowi6 *fl6,
+ struct fib6_result *res, int flags)
{
- return fib6_table_lookup(net, net->ipv6.fib6_main_tbl, oif, fl6, flags);
+ return fib6_table_lookup(net, net->ipv6.fib6_main_tbl, oif, fl6,
+ res, flags);
}
static void __net_init fib6_tables_init(struct net *net)
#else
seq_puts(seq, "00000000000000000000000000000000 00 ");
#endif
- if (rt->fib6_nh.fib_nh_has_gw) {
+ if (rt->fib6_nh.fib_nh_gw_family) {
flags |= RTF_GATEWAY;
seq_printf(seq, "%pi6", &rt->fib6_nh.fib_nh_gw6);
} else {
}
static int ip6erspan_rcv(struct sk_buff *skb,
- struct tnl_ptk_info *tpi)
+ struct tnl_ptk_info *tpi,
+ int gre_hdr_len)
{
struct erspan_base_hdr *ershdr;
- struct erspan_metadata *pkt_md;
const struct ipv6hdr *ipv6h;
struct erspan_md2 *md2;
struct ip6_tnl *tunnel;
if (unlikely(!pskb_may_pull(skb, len)))
return PACKET_REJECT;
- ershdr = (struct erspan_base_hdr *)skb->data;
- pkt_md = (struct erspan_metadata *)(ershdr + 1);
-
if (__iptunnel_pull_header(skb, len,
htons(ETH_P_TEB),
false, false) < 0)
return PACKET_REJECT;
if (tunnel->parms.collect_md) {
+ struct erspan_metadata *pkt_md, *md;
struct metadata_dst *tun_dst;
struct ip_tunnel_info *info;
- struct erspan_metadata *md;
+ unsigned char *gh;
__be64 tun_id;
__be16 flags;
if (!tun_dst)
return PACKET_REJECT;
+ /* skb can be uncloned in __iptunnel_pull_header, so
+ * old pkt_md is no longer valid and we need to reset
+ * it
+ */
+ gh = skb_network_header(skb) +
+ skb_network_header_len(skb);
+ pkt_md = (struct erspan_metadata *)(gh + gre_hdr_len +
+ sizeof(*ershdr));
info = &tun_dst->u.tun_info;
md = ip_tunnel_info_opts(info);
md->version = ver;
if (unlikely(tpi.proto == htons(ETH_P_ERSPAN) ||
tpi.proto == htons(ETH_P_ERSPAN2))) {
- if (ip6erspan_rcv(skb, &tpi) == PACKET_RCVD)
+ if (ip6erspan_rcv(skb, &tpi, hdr_len) == PACKET_RCVD)
return 0;
goto out;
}
neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false);
if (!IS_ERR(neigh)) {
sock_confirm_neigh(skb, neigh);
- ret = neigh_output(neigh, skb);
+ ret = neigh_output(neigh, skb, false);
rcu_read_unlock_bh();
return ret;
}
inet6_sk(skb->sk) : NULL;
struct ipv6hdr *tmp_hdr;
struct frag_hdr *fh;
- unsigned int mtu, hlen, left, len;
+ unsigned int mtu, hlen, left, len, nexthdr_offset;
int hroom, troom;
__be32 frag_id;
int ptr, offset = 0, err = 0;
goto fail;
hlen = err;
nexthdr = *prevhdr;
+ nexthdr_offset = prevhdr - skb_network_header(skb);
mtu = ip6_skb_dst_mtu(skb);
(err = skb_checksum_help(skb)))
goto fail;
+ prevhdr = skb_network_header(skb) + nexthdr_offset;
hroom = LL_RESERVED_SPACE(rt->dst.dev);
if (skb_has_frag_list(skb)) {
unsigned int first_len = skb_pagelen(skb);
rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL,
eiph->daddr, eiph->saddr, 0, 0,
IPPROTO_IPIP, RT_TOS(eiph->tos), 0);
- if (IS_ERR(rt) || rt->dst.dev->type != ARPHRD_TUNNEL) {
+ if (IS_ERR(rt) || rt->dst.dev->type != ARPHRD_TUNNEL6) {
if (!IS_ERR(rt))
ip_rt_put(rt);
goto out;
} else {
if (ip_route_input(skb2, eiph->daddr, eiph->saddr, eiph->tos,
skb2->dev) ||
- skb_dst(skb2)->dev->type != ARPHRD_TUNNEL)
+ skb_dst(skb2)->dev->type != ARPHRD_TUNNEL6)
goto out;
}
.key_offset = offsetof(struct mfc6_cache, cmparg),
.key_len = sizeof(struct mfc6_cache_cmp_arg),
.nelem_hint = 3,
- .locks_mul = 1,
.obj_cmpfn = ip6mr_hash_cmp,
.automatic_shrinking = true,
};
const struct net_device *dev,
__u32 *hash_rnd);
static bool ndisc_key_eq(const struct neighbour *neigh, const void *pkey);
+static bool ndisc_allow_add(const struct net_device *dev,
+ struct netlink_ext_ack *extack);
static int ndisc_constructor(struct neighbour *neigh);
static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb);
static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb);
.pconstructor = pndisc_constructor,
.pdestructor = pndisc_destructor,
.proxy_redo = pndisc_redo,
+ .allow_add = ndisc_allow_add,
.id = "ndisc_cache",
.parms = {
.tbl = &nd_tbl,
ipv6_dev_mc_dec(dev, &maddr);
}
+/* called with rtnl held */
+static bool ndisc_allow_add(const struct net_device *dev,
+ struct netlink_ext_ack *extack)
+{
+ struct inet6_dev *idev = __in6_dev_get(dev);
+
+ if (!idev || idev->cnf.disable_ipv6) {
+ NL_SET_ERR_MSG(extack, "IPv6 is disabled on this device");
+ return false;
+ }
+
+ return true;
+}
+
static struct sk_buff *ndisc_alloc_skb(struct net_device *dev,
int len)
{
if NF_TABLES_IPV6
-config NFT_CHAIN_ROUTE_IPV6
- tristate "IPv6 nf_tables route chain support"
- help
- This option enables the "route" chain for IPv6 in nf_tables. This
- chain type is used to force packet re-routing after mangling header
- fields such as the source, destination, flowlabel, hop-limit and
- the packet mark.
-
config NFT_REJECT_IPV6
select NF_REJECT_IPV6
default NFT_REJECT
config IP6_NF_TARGET_MASQUERADE
tristate "MASQUERADE target support"
- select NF_NAT_MASQUERADE
+ select NETFILTER_XT_TARGET_MASQUERADE
help
- Masquerading is a special case of NAT: all outgoing connections are
- changed to seem to come from a particular interface's address, and
- if the interface goes down, those connections are lost. This is
- only useful for dialup accounts with dynamic IP address (ie. your IP
- address will be different on next dialup).
-
- To compile it as a module, choose M here. If unsure, say N.
+ This is a backwards-compat option for the user's convenience
+ (e.g. when running oldconfig). It selects NETFILTER_XT_TARGET_MASQUERADE.
config IP6_NF_TARGET_NPT
tristate "NPT (Network Prefix translation) target support"
obj-$(CONFIG_NF_DUP_IPV6) += nf_dup_ipv6.o
# nf_tables
-obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV6) += nft_chain_route_ipv6.o
obj-$(CONFIG_NFT_REJECT_IPV6) += nft_reject_ipv6.o
obj-$(CONFIG_NFT_DUP_IPV6) += nft_dup_ipv6.o
obj-$(CONFIG_NFT_FIB_IPV6) += nft_fib_ipv6.o
obj-$(CONFIG_IP6_NF_MATCH_SRH) += ip6t_srh.o
# targets
-obj-$(CONFIG_IP6_NF_TARGET_MASQUERADE) += ip6t_MASQUERADE.o
obj-$(CONFIG_IP6_NF_TARGET_NPT) += ip6t_NPT.o
obj-$(CONFIG_IP6_NF_TARGET_REJECT) += ip6t_REJECT.o
obj-$(CONFIG_IP6_NF_TARGET_SYNPROXY) += ip6t_SYNPROXY.o
+++ /dev/null
-/*
- * Copyright (c) 2011 Patrick McHardy <kaber@trash.net>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * Based on Rusty Russell's IPv6 MASQUERADE target. Development of IPv6
- * NAT funded by Astaro.
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/netdevice.h>
-#include <linux/ipv6.h>
-#include <linux/netfilter.h>
-#include <linux/netfilter_ipv6.h>
-#include <linux/netfilter/x_tables.h>
-#include <net/netfilter/nf_nat.h>
-#include <net/addrconf.h>
-#include <net/ipv6.h>
-#include <net/netfilter/ipv6/nf_nat_masquerade.h>
-
-static unsigned int
-masquerade_tg6(struct sk_buff *skb, const struct xt_action_param *par)
-{
- return nf_nat_masquerade_ipv6(skb, par->targinfo, xt_out(par));
-}
-
-static int masquerade_tg6_checkentry(const struct xt_tgchk_param *par)
-{
- const struct nf_nat_range2 *range = par->targinfo;
-
- if (range->flags & NF_NAT_RANGE_MAP_IPS)
- return -EINVAL;
- return nf_ct_netns_get(par->net, par->family);
-}
-
-static void masquerade_tg6_destroy(const struct xt_tgdtor_param *par)
-{
- nf_ct_netns_put(par->net, par->family);
-}
-
-static struct xt_target masquerade_tg6_reg __read_mostly = {
- .name = "MASQUERADE",
- .family = NFPROTO_IPV6,
- .checkentry = masquerade_tg6_checkentry,
- .destroy = masquerade_tg6_destroy,
- .target = masquerade_tg6,
- .targetsize = sizeof(struct nf_nat_range),
- .table = "nat",
- .hooks = 1 << NF_INET_POST_ROUTING,
- .me = THIS_MODULE,
-};
-
-static int __init masquerade_tg6_init(void)
-{
- int err;
-
- err = xt_register_target(&masquerade_tg6_reg);
- if (err)
- return err;
-
- err = nf_nat_masquerade_ipv6_register_notifier();
- if (err)
- xt_unregister_target(&masquerade_tg6_reg);
-
- return err;
-}
-static void __exit masquerade_tg6_exit(void)
-{
- nf_nat_masquerade_ipv6_unregister_notifier();
- xt_unregister_target(&masquerade_tg6_reg);
-}
-
-module_init(masquerade_tg6_init);
-module_exit(masquerade_tg6_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
-MODULE_DESCRIPTION("Xtables: automatic address SNAT");
+++ /dev/null
-/*
- * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
- * Copyright (c) 2012 Pablo Neira Ayuso <pablo@netfilter.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * Development of this code funded by Astaro AG (http://www.astaro.com/)
- */
-
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/list.h>
-#include <linux/skbuff.h>
-#include <linux/netlink.h>
-#include <linux/netfilter.h>
-#include <linux/netfilter_ipv6.h>
-#include <linux/netfilter/nfnetlink.h>
-#include <linux/netfilter/nf_tables.h>
-#include <net/netfilter/nf_tables.h>
-#include <net/netfilter/nf_tables_ipv6.h>
-#include <net/route.h>
-
-static unsigned int nf_route_table_hook(void *priv,
- struct sk_buff *skb,
- const struct nf_hook_state *state)
-{
- unsigned int ret;
- struct nft_pktinfo pkt;
- struct in6_addr saddr, daddr;
- u_int8_t hop_limit;
- u32 mark, flowlabel;
- int err;
-
- nft_set_pktinfo(&pkt, skb, state);
- nft_set_pktinfo_ipv6(&pkt, skb);
-
- /* save source/dest address, mark, hoplimit, flowlabel, priority */
- memcpy(&saddr, &ipv6_hdr(skb)->saddr, sizeof(saddr));
- memcpy(&daddr, &ipv6_hdr(skb)->daddr, sizeof(daddr));
- mark = skb->mark;
- hop_limit = ipv6_hdr(skb)->hop_limit;
-
- /* flowlabel and prio (includes version, which shouldn't change either */
- flowlabel = *((u32 *)ipv6_hdr(skb));
-
- ret = nft_do_chain(&pkt, priv);
- if (ret != NF_DROP && ret != NF_STOLEN &&
- (memcmp(&ipv6_hdr(skb)->saddr, &saddr, sizeof(saddr)) ||
- memcmp(&ipv6_hdr(skb)->daddr, &daddr, sizeof(daddr)) ||
- skb->mark != mark ||
- ipv6_hdr(skb)->hop_limit != hop_limit ||
- flowlabel != *((u_int32_t *)ipv6_hdr(skb)))) {
- err = ip6_route_me_harder(state->net, skb);
- if (err < 0)
- ret = NF_DROP_ERR(err);
- }
-
- return ret;
-}
-
-static const struct nft_chain_type nft_chain_route_ipv6 = {
- .name = "route",
- .type = NFT_CHAIN_T_ROUTE,
- .family = NFPROTO_IPV6,
- .owner = THIS_MODULE,
- .hook_mask = (1 << NF_INET_LOCAL_OUT),
- .hooks = {
- [NF_INET_LOCAL_OUT] = nf_route_table_hook,
- },
-};
-
-static int __init nft_chain_route_init(void)
-{
- nft_register_chain_type(&nft_chain_route_ipv6);
-
- return 0;
-}
-
-static void __exit nft_chain_route_exit(void)
-{
- nft_unregister_chain_type(&nft_chain_route_ipv6);
-}
-
-module_init(nft_chain_route_init);
-module_exit(nft_chain_route_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
-MODULE_ALIAS_NFT_CHAIN(AF_INET6, "route");
struct sk_buff *skb, u32 mtu);
static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb);
-static int rt6_score_route(struct fib6_info *rt, int oif, int strict);
+static int rt6_score_route(const struct fib6_nh *nh, u32 fib6_flags, int oif,
+ int strict);
static size_t rt6_nlmsg_size(struct fib6_info *rt);
static int rt6_fill_node(struct net *net, struct sk_buff *skb,
struct fib6_info *rt, struct dst_entry *dst,
struct in6_addr *dest, struct in6_addr *src,
int iif, int type, u32 portid, u32 seq,
unsigned int flags);
-static struct rt6_info *rt6_find_cached_rt(struct fib6_info *rt,
+static struct rt6_info *rt6_find_cached_rt(const struct fib6_result *res,
struct in6_addr *daddr,
struct in6_addr *saddr);
return false;
}
-struct fib6_info *fib6_multipath_select(const struct net *net,
- struct fib6_info *match,
- struct flowi6 *fl6, int oif,
- const struct sk_buff *skb,
- int strict)
+void fib6_select_path(const struct net *net, struct fib6_result *res,
+ struct flowi6 *fl6, int oif, bool have_oif_match,
+ const struct sk_buff *skb, int strict)
{
struct fib6_info *sibling, *next_sibling;
+ struct fib6_info *match = res->f6i;
+
+ if (!match->fib6_nsiblings || have_oif_match)
+ goto out;
/* We might have already computed the hash for ICMPv6 errors. In such
* case it will always be non-zero. Otherwise now is the time to do it.
fl6->mp_hash = rt6_multipath_hash(net, fl6, skb, NULL);
if (fl6->mp_hash <= atomic_read(&match->fib6_nh.fib_nh_upper_bound))
- return match;
+ goto out;
list_for_each_entry_safe(sibling, next_sibling, &match->fib6_siblings,
fib6_siblings) {
+ const struct fib6_nh *nh = &sibling->fib6_nh;
int nh_upper_bound;
- nh_upper_bound = atomic_read(&sibling->fib6_nh.fib_nh_upper_bound);
+ nh_upper_bound = atomic_read(&nh->fib_nh_upper_bound);
if (fl6->mp_hash > nh_upper_bound)
continue;
- if (rt6_score_route(sibling, oif, strict) < 0)
+ if (rt6_score_route(nh, sibling->fib6_flags, oif, strict) < 0)
break;
match = sibling;
break;
}
- return match;
+out:
+ res->f6i = match;
+ res->nh = &match->fib6_nh;
}
/*
* Route lookup. rcu_read_lock() should be held.
*/
-static inline struct fib6_info *rt6_device_match(struct net *net,
- struct fib6_info *rt,
- const struct in6_addr *saddr,
- int oif,
- int flags)
+static bool __rt6_device_match(struct net *net, const struct fib6_nh *nh,
+ const struct in6_addr *saddr, int oif, int flags)
{
- struct fib6_info *sprt;
+ const struct net_device *dev;
- if (!oif && ipv6_addr_any(saddr) &&
- !(rt->fib6_nh.fib_nh_flags & RTNH_F_DEAD))
- return rt;
+ if (nh->fib_nh_flags & RTNH_F_DEAD)
+ return false;
+
+ dev = nh->fib_nh_dev;
+ if (oif) {
+ if (dev->ifindex == oif)
+ return true;
+ } else {
+ if (ipv6_chk_addr(net, saddr, dev,
+ flags & RT6_LOOKUP_F_IFACE))
+ return true;
+ }
- for (sprt = rt; sprt; sprt = rcu_dereference(sprt->fib6_next)) {
- const struct net_device *dev = sprt->fib6_nh.fib_nh_dev;
+ return false;
+}
- if (sprt->fib6_nh.fib_nh_flags & RTNH_F_DEAD)
- continue;
+static void rt6_device_match(struct net *net, struct fib6_result *res,
+ const struct in6_addr *saddr, int oif, int flags)
+{
+ struct fib6_info *f6i = res->f6i;
+ struct fib6_info *spf6i;
+ struct fib6_nh *nh;
- if (oif) {
- if (dev->ifindex == oif)
- return sprt;
- } else {
- if (ipv6_chk_addr(net, saddr, dev,
- flags & RT6_LOOKUP_F_IFACE))
- return sprt;
+ if (!oif && ipv6_addr_any(saddr)) {
+ nh = &f6i->fib6_nh;
+ if (!(nh->fib_nh_flags & RTNH_F_DEAD))
+ goto out;
+ }
+
+ for (spf6i = f6i; spf6i; spf6i = rcu_dereference(spf6i->fib6_next)) {
+ nh = &spf6i->fib6_nh;
+ if (__rt6_device_match(net, nh, saddr, oif, flags)) {
+ res->f6i = spf6i;
+ goto out;
}
}
- if (oif && flags & RT6_LOOKUP_F_IFACE)
- return net->ipv6.fib6_null_entry;
+ if (oif && flags & RT6_LOOKUP_F_IFACE) {
+ res->f6i = net->ipv6.fib6_null_entry;
+ nh = &res->f6i->fib6_nh;
+ goto out;
+ }
- return rt->fib6_nh.fib_nh_flags & RTNH_F_DEAD ? net->ipv6.fib6_null_entry : rt;
+ nh = &f6i->fib6_nh;
+ if (nh->fib_nh_flags & RTNH_F_DEAD) {
+ res->f6i = net->ipv6.fib6_null_entry;
+ nh = &res->f6i->fib6_nh;
+ }
+out:
+ res->nh = nh;
+ res->fib6_type = res->f6i->fib6_type;
+ res->fib6_flags = res->f6i->fib6_flags;
}
#ifdef CONFIG_IPV6_ROUTER_PREF
kfree(work);
}
-static void rt6_probe(struct fib6_info *rt)
+static void rt6_probe(struct fib6_nh *fib6_nh)
{
struct __rt6_probe_work *work = NULL;
const struct in6_addr *nh_gw;
* Router Reachability Probe MUST be rate-limited
* to no more than one per minute.
*/
- if (!rt || !rt->fib6_nh.fib_nh_has_gw)
+ if (fib6_nh->fib_nh_gw_family)
return;
- nh_gw = &rt->fib6_nh.fib_nh_gw6;
- dev = rt->fib6_nh.fib_nh_dev;
+ nh_gw = &fib6_nh->fib_nh_gw6;
+ dev = fib6_nh->fib_nh_dev;
rcu_read_lock_bh();
idev = __in6_dev_get(dev);
neigh = __ipv6_neigh_lookup_noref(dev, nh_gw);
__neigh_set_probe_once(neigh);
}
write_unlock(&neigh->lock);
- } else if (time_after(jiffies, rt->last_probe +
+ } else if (time_after(jiffies, fib6_nh->last_probe +
idev->cnf.rtr_probe_interval)) {
work = kmalloc(sizeof(*work), GFP_ATOMIC);
}
if (work) {
- rt->last_probe = jiffies;
+ fib6_nh->last_probe = jiffies;
INIT_WORK(&work->work, rt6_probe_deferred);
work->target = *nh_gw;
dev_hold(dev);
rcu_read_unlock_bh();
}
#else
-static inline void rt6_probe(struct fib6_info *rt)
+static inline void rt6_probe(struct fib6_nh *fib6_nh)
{
}
#endif
/*
* Default Router Selection (RFC 2461 6.3.6)
*/
-static inline int rt6_check_dev(struct fib6_info *rt, int oif)
-{
- const struct net_device *dev = rt->fib6_nh.fib_nh_dev;
-
- if (!oif || dev->ifindex == oif)
- return 2;
- return 0;
-}
-
-static inline enum rt6_nud_state rt6_check_neigh(struct fib6_info *rt)
+static enum rt6_nud_state rt6_check_neigh(const struct fib6_nh *fib6_nh)
{
enum rt6_nud_state ret = RT6_NUD_FAIL_HARD;
struct neighbour *neigh;
- if (rt->fib6_flags & RTF_NONEXTHOP ||
- !rt->fib6_nh.fib_nh_has_gw)
- return RT6_NUD_SUCCEED;
-
rcu_read_lock_bh();
- neigh = __ipv6_neigh_lookup_noref(rt->fib6_nh.fib_nh_dev,
- &rt->fib6_nh.fib_nh_gw6);
+ neigh = __ipv6_neigh_lookup_noref(fib6_nh->fib_nh_dev,
+ &fib6_nh->fib_nh_gw6);
if (neigh) {
read_lock(&neigh->lock);
if (neigh->nud_state & NUD_VALID)
return ret;
}
-static int rt6_score_route(struct fib6_info *rt, int oif, int strict)
+static int rt6_score_route(const struct fib6_nh *nh, u32 fib6_flags, int oif,
+ int strict)
{
- int m;
+ int m = 0;
+
+ if (!oif || nh->fib_nh_dev->ifindex == oif)
+ m = 2;
- m = rt6_check_dev(rt, oif);
if (!m && (strict & RT6_LOOKUP_F_IFACE))
return RT6_NUD_FAIL_HARD;
#ifdef CONFIG_IPV6_ROUTER_PREF
- m |= IPV6_DECODE_PREF(IPV6_EXTRACT_PREF(rt->fib6_flags)) << 2;
+ m |= IPV6_DECODE_PREF(IPV6_EXTRACT_PREF(fib6_flags)) << 2;
#endif
- if (strict & RT6_LOOKUP_F_REACHABLE) {
- int n = rt6_check_neigh(rt);
+ if ((strict & RT6_LOOKUP_F_REACHABLE) &&
+ !(fib6_flags & RTF_NONEXTHOP) && nh->fib_nh_gw_family) {
+ int n = rt6_check_neigh(nh);
if (n < 0)
return n;
}
return m;
}
-static struct fib6_info *find_match(struct fib6_info *rt, int oif, int strict,
- int *mpri, struct fib6_info *match,
- bool *do_rr)
+static bool find_match(struct fib6_nh *nh, u32 fib6_flags,
+ int oif, int strict, int *mpri, bool *do_rr)
{
- int m;
bool match_do_rr = false;
+ bool rc = false;
+ int m;
- if (rt->fib6_nh.fib_nh_flags & RTNH_F_DEAD)
+ if (nh->fib_nh_flags & RTNH_F_DEAD)
goto out;
- if (ip6_ignore_linkdown(rt->fib6_nh.fib_nh_dev) &&
- rt->fib6_nh.fib_nh_flags & RTNH_F_LINKDOWN &&
+ if (ip6_ignore_linkdown(nh->fib_nh_dev) &&
+ nh->fib_nh_flags & RTNH_F_LINKDOWN &&
!(strict & RT6_LOOKUP_F_IGNORE_LINKSTATE))
goto out;
- if (fib6_check_expired(rt))
- goto out;
-
- m = rt6_score_route(rt, oif, strict);
+ m = rt6_score_route(nh, fib6_flags, oif, strict);
if (m == RT6_NUD_FAIL_DO_RR) {
match_do_rr = true;
m = 0; /* lowest valid score */
}
if (strict & RT6_LOOKUP_F_REACHABLE)
- rt6_probe(rt);
+ rt6_probe(nh);
/* note that m can be RT6_NUD_FAIL_PROBE at this point */
if (m > *mpri) {
*do_rr = match_do_rr;
*mpri = m;
- match = rt;
+ rc = true;
}
out:
- return match;
+ return rc;
}
-static struct fib6_info *find_rr_leaf(struct fib6_node *fn,
- struct fib6_info *leaf,
- struct fib6_info *rr_head,
- u32 metric, int oif, int strict,
- bool *do_rr)
+static void __find_rr_leaf(struct fib6_info *f6i_start,
+ struct fib6_info *nomatch, u32 metric,
+ struct fib6_result *res, struct fib6_info **cont,
+ int oif, int strict, bool *do_rr, int *mpri)
{
- struct fib6_info *rt, *match, *cont;
- int mpri = -1;
+ struct fib6_info *f6i;
- match = NULL;
- cont = NULL;
- for (rt = rr_head; rt; rt = rcu_dereference(rt->fib6_next)) {
- if (rt->fib6_metric != metric) {
- cont = rt;
- break;
+ for (f6i = f6i_start;
+ f6i && f6i != nomatch;
+ f6i = rcu_dereference(f6i->fib6_next)) {
+ struct fib6_nh *nh;
+
+ if (cont && f6i->fib6_metric != metric) {
+ *cont = f6i;
+ return;
}
- match = find_match(rt, oif, strict, &mpri, match, do_rr);
- }
+ if (fib6_check_expired(f6i))
+ continue;
- for (rt = leaf; rt && rt != rr_head;
- rt = rcu_dereference(rt->fib6_next)) {
- if (rt->fib6_metric != metric) {
- cont = rt;
- break;
+ nh = &f6i->fib6_nh;
+ if (find_match(nh, f6i->fib6_flags, oif, strict, mpri, do_rr)) {
+ res->f6i = f6i;
+ res->nh = nh;
+ res->fib6_flags = f6i->fib6_flags;
+ res->fib6_type = f6i->fib6_type;
}
-
- match = find_match(rt, oif, strict, &mpri, match, do_rr);
}
+}
+
+static void find_rr_leaf(struct fib6_node *fn, struct fib6_info *leaf,
+ struct fib6_info *rr_head, int oif, int strict,
+ bool *do_rr, struct fib6_result *res)
+{
+ u32 metric = rr_head->fib6_metric;
+ struct fib6_info *cont = NULL;
+ int mpri = -1;
+
+ __find_rr_leaf(rr_head, NULL, metric, res, &cont,
+ oif, strict, do_rr, &mpri);
- if (match || !cont)
- return match;
+ __find_rr_leaf(leaf, rr_head, metric, res, &cont,
+ oif, strict, do_rr, &mpri);
- for (rt = cont; rt; rt = rcu_dereference(rt->fib6_next))
- match = find_match(rt, oif, strict, &mpri, match, do_rr);
+ if (res->f6i || !cont)
+ return;
- return match;
+ __find_rr_leaf(cont, NULL, metric, res, NULL,
+ oif, strict, do_rr, &mpri);
}
-static struct fib6_info *rt6_select(struct net *net, struct fib6_node *fn,
- int oif, int strict)
+static void rt6_select(struct net *net, struct fib6_node *fn, int oif,
+ struct fib6_result *res, int strict)
{
struct fib6_info *leaf = rcu_dereference(fn->leaf);
- struct fib6_info *match, *rt0;
+ struct fib6_info *rt0;
bool do_rr = false;
int key_plen;
+ /* make sure this function or its helpers sets f6i */
+ res->f6i = NULL;
+
if (!leaf || leaf == net->ipv6.fib6_null_entry)
- return net->ipv6.fib6_null_entry;
+ goto out;
rt0 = rcu_dereference(fn->rr_ptr);
if (!rt0)
key_plen = rt0->fib6_src.plen;
#endif
if (fn->fn_bit != key_plen)
- return net->ipv6.fib6_null_entry;
-
- match = find_rr_leaf(fn, leaf, rt0, rt0->fib6_metric, oif, strict,
- &do_rr);
+ goto out;
+ find_rr_leaf(fn, leaf, rt0, oif, strict, &do_rr, res);
if (do_rr) {
struct fib6_info *next = rcu_dereference(rt0->fib6_next);
}
}
- return match ? match : net->ipv6.fib6_null_entry;
+out:
+ if (!res->f6i) {
+ res->f6i = net->ipv6.fib6_null_entry;
+ res->nh = &res->f6i->fib6_nh;
+ res->fib6_flags = res->f6i->fib6_flags;
+ res->fib6_type = res->f6i->fib6_type;
+ }
}
-static bool rt6_is_gw_or_nonexthop(const struct fib6_info *rt)
+static bool rt6_is_gw_or_nonexthop(const struct fib6_result *res)
{
- return (rt->fib6_flags & RTF_NONEXTHOP) || rt->fib6_nh.fib_nh_has_gw;
+ return (res->f6i->fib6_flags & RTF_NONEXTHOP) ||
+ res->nh->fib_nh_gw_family;
}
#ifdef CONFIG_IPV6_ROUTE_INFO
*/
/* called with rcu_lock held */
-static struct net_device *ip6_rt_get_dev_rcu(struct fib6_info *rt)
+static struct net_device *ip6_rt_get_dev_rcu(const struct fib6_result *res)
{
- struct net_device *dev = rt->fib6_nh.fib_nh_dev;
+ struct net_device *dev = res->nh->fib_nh_dev;
- if (rt->fib6_flags & (RTF_LOCAL | RTF_ANYCAST)) {
+ if (res->fib6_flags & (RTF_LOCAL | RTF_ANYCAST)) {
/* for copies of local routes, dst->dev needs to be the
* device if it is a master device, the master device if
* device is enslaved, and the loopback as the default
*/
if (netif_is_l3_slave(dev) &&
- !rt6_need_strict(&rt->fib6_dst.addr))
+ !rt6_need_strict(&res->f6i->fib6_dst.addr))
dev = l3mdev_master_dev_rcu(dev);
else if (!netif_is_l3_master(dev))
dev = dev_net(dev)->loopback_dev;
return flags;
}
-static void ip6_rt_init_dst_reject(struct rt6_info *rt, struct fib6_info *ort)
+static void ip6_rt_init_dst_reject(struct rt6_info *rt, u8 fib6_type)
{
- rt->dst.error = ip6_rt_type_to_error(ort->fib6_type);
+ rt->dst.error = ip6_rt_type_to_error(fib6_type);
- switch (ort->fib6_type) {
+ switch (fib6_type) {
case RTN_BLACKHOLE:
rt->dst.output = dst_discard_out;
rt->dst.input = dst_discard;
}
}
-static void ip6_rt_init_dst(struct rt6_info *rt, struct fib6_info *ort)
+static void ip6_rt_init_dst(struct rt6_info *rt, const struct fib6_result *res)
{
- if (ort->fib6_flags & RTF_REJECT) {
- ip6_rt_init_dst_reject(rt, ort);
+ struct fib6_info *f6i = res->f6i;
+
+ if (res->fib6_flags & RTF_REJECT) {
+ ip6_rt_init_dst_reject(rt, res->fib6_type);
return;
}
rt->dst.error = 0;
rt->dst.output = ip6_output;
- if (ort->fib6_type == RTN_LOCAL || ort->fib6_type == RTN_ANYCAST) {
+ if (res->fib6_type == RTN_LOCAL || res->fib6_type == RTN_ANYCAST) {
rt->dst.input = ip6_input;
- } else if (ipv6_addr_type(&ort->fib6_dst.addr) & IPV6_ADDR_MULTICAST) {
+ } else if (ipv6_addr_type(&f6i->fib6_dst.addr) & IPV6_ADDR_MULTICAST) {
rt->dst.input = ip6_mc_input;
} else {
rt->dst.input = ip6_forward;
}
- if (ort->fib6_nh.fib_nh_lws) {
- rt->dst.lwtstate = lwtstate_get(ort->fib6_nh.fib_nh_lws);
+ if (res->nh->fib_nh_lws) {
+ rt->dst.lwtstate = lwtstate_get(res->nh->fib_nh_lws);
lwtunnel_set_redirect(&rt->dst);
}
ip_dst_init_metrics(&rt->dst, from->fib6_metrics);
}
-/* Caller must already hold reference to @ort */
-static void ip6_rt_copy_init(struct rt6_info *rt, struct fib6_info *ort)
+/* Caller must already hold reference to f6i in result */
+static void ip6_rt_copy_init(struct rt6_info *rt, const struct fib6_result *res)
{
- struct net_device *dev = fib6_info_nh_dev(ort);
+ const struct fib6_nh *nh = res->nh;
+ const struct net_device *dev = nh->fib_nh_dev;
+ struct fib6_info *f6i = res->f6i;
- ip6_rt_init_dst(rt, ort);
+ ip6_rt_init_dst(rt, res);
- rt->rt6i_dst = ort->fib6_dst;
+ rt->rt6i_dst = f6i->fib6_dst;
rt->rt6i_idev = dev ? in6_dev_get(dev) : NULL;
- rt->rt6i_flags = ort->fib6_flags;
- if (ort->fib6_nh.fib_nh_has_gw) {
- rt->rt6i_gateway = ort->fib6_nh.fib_nh_gw6;
+ rt->rt6i_flags = res->fib6_flags;
+ if (nh->fib_nh_gw_family) {
+ rt->rt6i_gateway = nh->fib_nh_gw6;
rt->rt6i_flags |= RTF_GATEWAY;
}
- rt6_set_from(rt, ort);
+ rt6_set_from(rt, f6i);
#ifdef CONFIG_IPV6_SUBTREES
- rt->rt6i_src = ort->fib6_src;
+ rt->rt6i_src = f6i->fib6_src;
#endif
}
}
/* called with rcu_lock held */
-static struct rt6_info *ip6_create_rt_rcu(struct fib6_info *rt)
+static struct rt6_info *ip6_create_rt_rcu(const struct fib6_result *res)
{
- unsigned short flags = fib6_info_dst_flags(rt);
- struct net_device *dev = rt->fib6_nh.fib_nh_dev;
+ struct net_device *dev = res->nh->fib_nh_dev;
+ struct fib6_info *f6i = res->f6i;
+ unsigned short flags;
struct rt6_info *nrt;
- if (!fib6_info_hold_safe(rt))
+ if (!fib6_info_hold_safe(f6i))
goto fallback;
+ flags = fib6_info_dst_flags(f6i);
nrt = ip6_dst_alloc(dev_net(dev), dev, flags);
if (!nrt) {
- fib6_info_release(rt);
+ fib6_info_release(f6i);
goto fallback;
}
- ip6_rt_copy_init(nrt, rt);
+ ip6_rt_copy_init(nrt, res);
return nrt;
fallback:
const struct sk_buff *skb,
int flags)
{
- struct fib6_info *f6i;
+ struct fib6_result res = {};
struct fib6_node *fn;
struct rt6_info *rt;
rcu_read_lock();
fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
restart:
- f6i = rcu_dereference(fn->leaf);
- if (!f6i) {
- f6i = net->ipv6.fib6_null_entry;
- } else {
- f6i = rt6_device_match(net, f6i, &fl6->saddr,
- fl6->flowi6_oif, flags);
- if (f6i->fib6_nsiblings && fl6->flowi6_oif == 0)
- f6i = fib6_multipath_select(net, f6i, fl6,
- fl6->flowi6_oif, skb,
- flags);
- }
- if (f6i == net->ipv6.fib6_null_entry) {
+ res.f6i = rcu_dereference(fn->leaf);
+ if (!res.f6i)
+ res.f6i = net->ipv6.fib6_null_entry;
+ else
+ rt6_device_match(net, &res, &fl6->saddr, fl6->flowi6_oif,
+ flags);
+
+ if (res.f6i == net->ipv6.fib6_null_entry) {
fn = fib6_backtrack(fn, &fl6->saddr);
if (fn)
goto restart;
+
+ rt = net->ipv6.ip6_null_entry;
+ dst_hold(&rt->dst);
+ goto out;
}
- trace_fib6_table_lookup(net, f6i, table, fl6);
+ fib6_select_path(net, &res, fl6, fl6->flowi6_oif,
+ fl6->flowi6_oif != 0, skb, flags);
/* Search through exception table */
- rt = rt6_find_cached_rt(f6i, &fl6->daddr, &fl6->saddr);
+ rt = rt6_find_cached_rt(&res, &fl6->daddr, &fl6->saddr);
if (rt) {
if (ip6_hold_safe(net, &rt))
dst_use_noref(&rt->dst, jiffies);
- } else if (f6i == net->ipv6.fib6_null_entry) {
- rt = net->ipv6.ip6_null_entry;
- dst_hold(&rt->dst);
} else {
- rt = ip6_create_rt_rcu(f6i);
+ rt = ip6_create_rt_rcu(&res);
}
+out:
+ trace_fib6_table_lookup(net, &res, table, fl6);
+
rcu_read_unlock();
return rt;
return __ip6_ins_rt(rt, &info, NULL);
}
-static struct rt6_info *ip6_rt_cache_alloc(struct fib6_info *ort,
+static struct rt6_info *ip6_rt_cache_alloc(const struct fib6_result *res,
const struct in6_addr *daddr,
const struct in6_addr *saddr)
{
+ struct fib6_info *f6i = res->f6i;
struct net_device *dev;
struct rt6_info *rt;
* Clone the route.
*/
- if (!fib6_info_hold_safe(ort))
+ if (!fib6_info_hold_safe(f6i))
return NULL;
- dev = ip6_rt_get_dev_rcu(ort);
+ dev = ip6_rt_get_dev_rcu(res);
rt = ip6_dst_alloc(dev_net(dev), dev, 0);
if (!rt) {
- fib6_info_release(ort);
+ fib6_info_release(f6i);
return NULL;
}
- ip6_rt_copy_init(rt, ort);
+ ip6_rt_copy_init(rt, res);
rt->rt6i_flags |= RTF_CACHE;
rt->dst.flags |= DST_HOST;
rt->rt6i_dst.addr = *daddr;
rt->rt6i_dst.plen = 128;
- if (!rt6_is_gw_or_nonexthop(ort)) {
- if (ort->fib6_dst.plen != 128 &&
- ipv6_addr_equal(&ort->fib6_dst.addr, daddr))
+ if (!rt6_is_gw_or_nonexthop(res)) {
+ if (f6i->fib6_dst.plen != 128 &&
+ ipv6_addr_equal(&f6i->fib6_dst.addr, daddr))
rt->rt6i_flags |= RTF_ANYCAST;
#ifdef CONFIG_IPV6_SUBTREES
if (rt->rt6i_src.plen && saddr) {
return rt;
}
-static struct rt6_info *ip6_rt_pcpu_alloc(struct fib6_info *rt)
+static struct rt6_info *ip6_rt_pcpu_alloc(const struct fib6_result *res)
{
- unsigned short flags = fib6_info_dst_flags(rt);
+ struct fib6_info *f6i = res->f6i;
+ unsigned short flags = fib6_info_dst_flags(f6i);
struct net_device *dev;
struct rt6_info *pcpu_rt;
- if (!fib6_info_hold_safe(rt))
+ if (!fib6_info_hold_safe(f6i))
return NULL;
rcu_read_lock();
- dev = ip6_rt_get_dev_rcu(rt);
+ dev = ip6_rt_get_dev_rcu(res);
pcpu_rt = ip6_dst_alloc(dev_net(dev), dev, flags);
rcu_read_unlock();
if (!pcpu_rt) {
- fib6_info_release(rt);
+ fib6_info_release(f6i);
return NULL;
}
- ip6_rt_copy_init(pcpu_rt, rt);
+ ip6_rt_copy_init(pcpu_rt, res);
pcpu_rt->rt6i_flags |= RTF_PCPU;
return pcpu_rt;
}
/* It should be called with rcu_read_lock() acquired */
-static struct rt6_info *rt6_get_pcpu_route(struct fib6_info *rt)
+static struct rt6_info *rt6_get_pcpu_route(const struct fib6_result *res)
{
struct rt6_info *pcpu_rt, **p;
- p = this_cpu_ptr(rt->rt6i_pcpu);
+ p = this_cpu_ptr(res->f6i->rt6i_pcpu);
pcpu_rt = *p;
if (pcpu_rt)
}
static struct rt6_info *rt6_make_pcpu_route(struct net *net,
- struct fib6_info *rt)
+ const struct fib6_result *res)
{
struct rt6_info *pcpu_rt, *prev, **p;
- pcpu_rt = ip6_rt_pcpu_alloc(rt);
+ pcpu_rt = ip6_rt_pcpu_alloc(res);
if (!pcpu_rt) {
dst_hold(&net->ipv6.ip6_null_entry->dst);
return net->ipv6.ip6_null_entry;
}
dst_hold(&pcpu_rt->dst);
- p = this_cpu_ptr(rt->rt6i_pcpu);
+ p = this_cpu_ptr(res->f6i->rt6i_pcpu);
prev = cmpxchg(p, NULL, pcpu_rt);
BUG_ON(prev);
return NULL;
}
-static unsigned int fib6_mtu(const struct fib6_info *rt)
+static unsigned int fib6_mtu(const struct fib6_result *res)
{
+ const struct fib6_nh *nh = res->nh;
unsigned int mtu;
- if (rt->fib6_pmtu) {
- mtu = rt->fib6_pmtu;
+ if (res->f6i->fib6_pmtu) {
+ mtu = res->f6i->fib6_pmtu;
} else {
- struct net_device *dev = fib6_info_nh_dev(rt);
+ struct net_device *dev = nh->fib_nh_dev;
struct inet6_dev *idev;
rcu_read_lock();
mtu = min_t(unsigned int, mtu, IP6_MAX_MTU);
- return mtu - lwtunnel_headroom(rt->fib6_nh.fib_nh_lws, mtu);
+ return mtu - lwtunnel_headroom(nh->fib_nh_lws, mtu);
}
static int rt6_insert_exception(struct rt6_info *nrt,
- struct fib6_info *ort)
+ const struct fib6_result *res)
{
struct net *net = dev_net(nrt->dst.dev);
struct rt6_exception_bucket *bucket;
struct in6_addr *src_key = NULL;
struct rt6_exception *rt6_ex;
+ struct fib6_info *f6i = res->f6i;
int err = 0;
spin_lock_bh(&rt6_exception_lock);
- if (ort->exception_bucket_flushed) {
+ if (f6i->exception_bucket_flushed) {
err = -EINVAL;
goto out;
}
- bucket = rcu_dereference_protected(ort->rt6i_exception_bucket,
+ bucket = rcu_dereference_protected(f6i->rt6i_exception_bucket,
lockdep_is_held(&rt6_exception_lock));
if (!bucket) {
bucket = kcalloc(FIB6_EXCEPTION_BUCKET_SIZE, sizeof(*bucket),
err = -ENOMEM;
goto out;
}
- rcu_assign_pointer(ort->rt6i_exception_bucket, bucket);
+ rcu_assign_pointer(f6i->rt6i_exception_bucket, bucket);
}
#ifdef CONFIG_IPV6_SUBTREES
- /* rt6i_src.plen != 0 indicates ort is in subtree
+ /* fib6_src.plen != 0 indicates f6i is in subtree
* and exception table is indexed by a hash of
- * both rt6i_dst and rt6i_src.
+ * both fib6_dst and fib6_src.
* Otherwise, the exception table is indexed by
- * a hash of only rt6i_dst.
+ * a hash of only fib6_dst.
*/
- if (ort->fib6_src.plen)
+ if (f6i->fib6_src.plen)
src_key = &nrt->rt6i_src.addr;
#endif
- /* rt6_mtu_change() might lower mtu on ort.
+ /* rt6_mtu_change() might lower mtu on f6i.
* Only insert this exception route if its mtu
- * is less than ort's mtu value.
+ * is less than f6i's mtu value.
*/
- if (dst_metric_raw(&nrt->dst, RTAX_MTU) >= fib6_mtu(ort)) {
+ if (dst_metric_raw(&nrt->dst, RTAX_MTU) >= fib6_mtu(res)) {
err = -EINVAL;
goto out;
}
/* Update fn->fn_sernum to invalidate all cached dst */
if (!err) {
- spin_lock_bh(&ort->fib6_table->tb6_lock);
- fib6_update_sernum(net, ort);
- spin_unlock_bh(&ort->fib6_table->tb6_lock);
+ spin_lock_bh(&f6i->fib6_table->tb6_lock);
+ fib6_update_sernum(net, f6i);
+ spin_unlock_bh(&f6i->fib6_table->tb6_lock);
fib6_force_start_gc(net);
}
/* Find cached rt in the hash table inside passed in rt
* Caller has to hold rcu_read_lock()
*/
-static struct rt6_info *rt6_find_cached_rt(struct fib6_info *rt,
+static struct rt6_info *rt6_find_cached_rt(const struct fib6_result *res,
struct in6_addr *daddr,
struct in6_addr *saddr)
{
struct rt6_exception_bucket *bucket;
struct in6_addr *src_key = NULL;
struct rt6_exception *rt6_ex;
- struct rt6_info *res = NULL;
+ struct rt6_info *ret = NULL;
- bucket = rcu_dereference(rt->rt6i_exception_bucket);
+ bucket = rcu_dereference(res->f6i->rt6i_exception_bucket);
#ifdef CONFIG_IPV6_SUBTREES
- /* rt6i_src.plen != 0 indicates rt is in subtree
+ /* fib6i_src.plen != 0 indicates f6i is in subtree
* and exception table is indexed by a hash of
- * both rt6i_dst and rt6i_src.
+ * both fib6_dst and fib6_src.
* Otherwise, the exception table is indexed by
- * a hash of only rt6i_dst.
+ * a hash of only fib6_dst.
*/
- if (rt->fib6_src.plen)
+ if (res->f6i->fib6_src.plen)
src_key = saddr;
#endif
rt6_ex = __rt6_find_exception_rcu(&bucket, daddr, src_key);
if (rt6_ex && !rt6_check_expired(rt6_ex->rt6i))
- res = rt6_ex->rt6i;
+ ret = rt6_ex->rt6i;
- return res;
+ return ret;
}
/* Remove the passed in cached rt from the hash table that contains it */
}
/* must be called with rcu lock held */
-struct fib6_info *fib6_table_lookup(struct net *net, struct fib6_table *table,
- int oif, struct flowi6 *fl6, int strict)
+int fib6_table_lookup(struct net *net, struct fib6_table *table, int oif,
+ struct flowi6 *fl6, struct fib6_result *res, int strict)
{
struct fib6_node *fn, *saved_fn;
- struct fib6_info *f6i;
fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
saved_fn = fn;
oif = 0;
redo_rt6_select:
- f6i = rt6_select(net, fn, oif, strict);
- if (f6i == net->ipv6.fib6_null_entry) {
+ rt6_select(net, fn, oif, res, strict);
+ if (res->f6i == net->ipv6.fib6_null_entry) {
fn = fib6_backtrack(fn, &fl6->saddr);
if (fn)
goto redo_rt6_select;
}
}
- trace_fib6_table_lookup(net, f6i, table, fl6);
+ trace_fib6_table_lookup(net, res, table, fl6);
- return f6i;
+ return 0;
}
struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
int oif, struct flowi6 *fl6,
const struct sk_buff *skb, int flags)
{
- struct fib6_info *f6i;
+ struct fib6_result res = {};
struct rt6_info *rt;
int strict = 0;
rcu_read_lock();
- f6i = fib6_table_lookup(net, table, oif, fl6, strict);
- if (f6i->fib6_nsiblings)
- f6i = fib6_multipath_select(net, f6i, fl6, oif, skb, strict);
-
- if (f6i == net->ipv6.fib6_null_entry) {
+ fib6_table_lookup(net, table, oif, fl6, &res, strict);
+ if (res.f6i == net->ipv6.fib6_null_entry) {
rt = net->ipv6.ip6_null_entry;
rcu_read_unlock();
dst_hold(&rt->dst);
return rt;
}
+ fib6_select_path(net, &res, fl6, oif, false, skb, strict);
+
/*Search through exception table */
- rt = rt6_find_cached_rt(f6i, &fl6->daddr, &fl6->saddr);
+ rt = rt6_find_cached_rt(&res, &fl6->daddr, &fl6->saddr);
if (rt) {
if (ip6_hold_safe(net, &rt))
dst_use_noref(&rt->dst, jiffies);
rcu_read_unlock();
return rt;
} else if (unlikely((fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH) &&
- !f6i->fib6_nh.fib_nh_has_gw)) {
+ !res.nh->fib_nh_gw_family)) {
/* Create a RTF_CACHE clone which will not be
* owned by the fib6 tree. It is for the special case where
* the daddr in the skb during the neighbor look-up is different
*/
struct rt6_info *uncached_rt;
- uncached_rt = ip6_rt_cache_alloc(f6i, &fl6->daddr, NULL);
+ uncached_rt = ip6_rt_cache_alloc(&res, &fl6->daddr, NULL);
rcu_read_unlock();
struct rt6_info *pcpu_rt;
local_bh_disable();
- pcpu_rt = rt6_get_pcpu_route(f6i);
+ pcpu_rt = rt6_get_pcpu_route(&res);
if (!pcpu_rt)
- pcpu_rt = rt6_make_pcpu_route(net, f6i);
+ pcpu_rt = rt6_make_pcpu_route(net, &res);
local_bh_enable();
rcu_read_unlock();
if (rt6->rt6i_flags & RTF_CACHE)
rt6_update_exception_stamp_rt(rt6);
} else if (daddr) {
- struct fib6_info *from;
+ struct fib6_result res = {};
struct rt6_info *nrt6;
rcu_read_lock();
- from = rcu_dereference(rt6->from);
- nrt6 = ip6_rt_cache_alloc(from, daddr, saddr);
+ res.f6i = rcu_dereference(rt6->from);
+ if (!res.f6i) {
+ rcu_read_unlock();
+ return;
+ }
+ res.nh = &res.f6i->fib6_nh;
+ res.fib6_flags = res.f6i->fib6_flags;
+ res.fib6_type = res.f6i->fib6_type;
+
+ nrt6 = ip6_rt_cache_alloc(&res, daddr, saddr);
if (nrt6) {
rt6_do_update_pmtu(nrt6, mtu);
- if (rt6_insert_exception(nrt6, from))
+ if (rt6_insert_exception(nrt6, &res))
dst_release_immediate(&nrt6->dst);
}
rcu_read_unlock();
NULL);
}
+static bool ip6_redirect_nh_match(const struct fib6_result *res,
+ struct flowi6 *fl6,
+ const struct in6_addr *gw,
+ struct rt6_info **ret)
+{
+ const struct fib6_nh *nh = res->nh;
+
+ if (nh->fib_nh_flags & RTNH_F_DEAD || !nh->fib_nh_gw_family ||
+ fl6->flowi6_oif != nh->fib_nh_dev->ifindex)
+ return false;
+
+ /* rt_cache's gateway might be different from its 'parent'
+ * in the case of an ip redirect.
+ * So we keep searching in the exception table if the gateway
+ * is different.
+ */
+ if (!ipv6_addr_equal(gw, &nh->fib_nh_gw6)) {
+ struct rt6_info *rt_cache;
+
+ rt_cache = rt6_find_cached_rt(res, &fl6->daddr, &fl6->saddr);
+ if (rt_cache &&
+ ipv6_addr_equal(gw, &rt_cache->rt6i_gateway)) {
+ *ret = rt_cache;
+ return true;
+ }
+ return false;
+ }
+ return true;
+}
+
/* Handle redirects */
struct ip6rd_flowi {
struct flowi6 fl6;
int flags)
{
struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl6;
- struct rt6_info *ret = NULL, *rt_cache;
+ struct rt6_info *ret = NULL;
+ struct fib6_result res = {};
struct fib6_info *rt;
struct fib6_node *fn;
fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
restart:
for_each_fib6_node_rt_rcu(fn) {
- if (rt->fib6_nh.fib_nh_flags & RTNH_F_DEAD)
- continue;
+ res.f6i = rt;
+ res.nh = &rt->fib6_nh;
+
if (fib6_check_expired(rt))
continue;
if (rt->fib6_flags & RTF_REJECT)
break;
- if (!rt->fib6_nh.fib_nh_has_gw)
- continue;
- if (fl6->flowi6_oif != rt->fib6_nh.fib_nh_dev->ifindex)
- continue;
- /* rt_cache's gateway might be different from its 'parent'
- * in the case of an ip redirect.
- * So we keep searching in the exception table if the gateway
- * is different.
- */
- if (!ipv6_addr_equal(&rdfl->gateway, &rt->fib6_nh.fib_nh_gw6)) {
- rt_cache = rt6_find_cached_rt(rt,
- &fl6->daddr,
- &fl6->saddr);
- if (rt_cache &&
- ipv6_addr_equal(&rdfl->gateway,
- &rt_cache->rt6i_gateway)) {
- ret = rt_cache;
- break;
- }
- continue;
- }
- break;
+ if (ip6_redirect_nh_match(&res, fl6, &rdfl->gateway, &ret))
+ goto out;
}
if (!rt)
goto restart;
}
+ res.f6i = rt;
+ res.nh = &rt->fib6_nh;
out:
- if (ret)
+ if (ret) {
ip6_hold_safe(net, &ret);
- else
- ret = ip6_create_rt_rcu(rt);
+ } else {
+ res.fib6_flags = res.f6i->fib6_flags;
+ res.fib6_type = res.f6i->fib6_type;
+ ret = ip6_create_rt_rcu(&res);
+ }
rcu_read_unlock();
- trace_fib6_table_lookup(net, rt, table, fl6);
+ trace_fib6_table_lookup(net, &res, table, fl6);
return ret;
};
* based on ip6_dst_mtu_forward and exception logic of
* rt6_find_cached_rt; called with rcu_read_lock
*/
-u32 ip6_mtu_from_fib6(struct fib6_info *f6i, struct in6_addr *daddr,
- struct in6_addr *saddr)
+u32 ip6_mtu_from_fib6(const struct fib6_result *res,
+ const struct in6_addr *daddr,
+ const struct in6_addr *saddr)
{
struct rt6_exception_bucket *bucket;
+ const struct fib6_nh *nh = res->nh;
+ struct fib6_info *f6i = res->f6i;
+ const struct in6_addr *src_key;
struct rt6_exception *rt6_ex;
- struct in6_addr *src_key;
struct inet6_dev *idev;
u32 mtu = 0;
mtu = dst_metric_raw(&rt6_ex->rt6i->dst, RTAX_MTU);
if (likely(!mtu)) {
- struct net_device *dev = fib6_info_nh_dev(f6i);
+ struct net_device *dev = nh->fib_nh_dev;
mtu = IPV6_MIN_MTU;
idev = __in6_dev_get(dev);
mtu = min_t(unsigned int, mtu, IP6_MAX_MTU);
out:
- return mtu - lwtunnel_headroom(fib6_info_nh_lwt(f6i), mtu);
+ return mtu - lwtunnel_headroom(nh->fib_nh_lws, mtu);
}
struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
goto out;
fib6_nh->fib_nh_gw6 = cfg->fc_gateway;
- fib6_nh->fib_nh_has_gw = 1;
+ fib6_nh->fib_nh_gw_family = AF_INET6;
}
err = -ENODEV;
struct fib6_nh *nh;
if (cfg->fc_flags & RTF_CACHE) {
+ struct fib6_result res = {
+ .f6i = rt,
+ };
int rc;
- rt_cache = rt6_find_cached_rt(rt, &cfg->fc_dst,
+ rt_cache = rt6_find_cached_rt(&res,
+ &cfg->fc_dst,
&cfg->fc_src);
if (rt_cache) {
rc = ip6_del_cached_rt(rt_cache, cfg);
{
struct netevent_redirect netevent;
struct rt6_info *rt, *nrt = NULL;
+ struct fib6_result res = {};
struct ndisc_options ndopts;
struct inet6_dev *in6_dev;
struct neighbour *neigh;
- struct fib6_info *from;
struct rd_msg *msg;
int optlen, on_link;
u8 *lladdr;
NDISC_REDIRECT, &ndopts);
rcu_read_lock();
- from = rcu_dereference(rt->from);
+ res.f6i = rcu_dereference(rt->from);
/* This fib6_info_hold() is safe here because we hold reference to rt
* and rt already holds reference to fib6_info.
*/
- fib6_info_hold(from);
+ fib6_info_hold(res.f6i);
rcu_read_unlock();
- nrt = ip6_rt_cache_alloc(from, &msg->dest, NULL);
+ res.nh = &res.f6i->fib6_nh;
+ res.fib6_flags = res.f6i->fib6_flags;
+ res.fib6_type = res.f6i->fib6_type;
+ nrt = ip6_rt_cache_alloc(&res, &msg->dest, NULL);
if (!nrt)
goto out;
* a cached route because rt6_insert_exception() will
* takes care of it
*/
- if (rt6_insert_exception(nrt, from)) {
+ if (rt6_insert_exception(nrt, &res)) {
dst_release_immediate(&nrt->dst);
goto out;
}
call_netevent_notifiers(NETEVENT_REDIRECT, &netevent);
out:
- fib6_info_release(from);
+ fib6_info_release(res.f6i);
neigh_release(neigh);
}
if (rt->fib6_nh.fib_nh_dev->ifindex != ifindex)
continue;
if (!(rt->fib6_flags & RTF_ROUTEINFO) ||
- !rt->fib6_nh.fib_nh_has_gw)
+ !rt->fib6_nh.fib_nh_gw_family)
continue;
if (!ipv6_addr_equal(&rt->fib6_nh.fib_nh_gw6, gwaddr))
continue;
struct in6_addr *gateway = (struct in6_addr *)arg;
if (((rt->fib6_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) &&
- rt->fib6_nh.fib_nh_has_gw &&
+ rt->fib6_nh.fib_nh_gw_family &&
ipv6_addr_equal(gateway, &rt->fib6_nh.fib_nh_gw6)) {
return -1;
}
+ nexthop_len;
}
-static int rt6_nexthop_info(struct sk_buff *skb, const struct fib6_nh *fib6_nh,
- unsigned int *flags, bool skip_oif)
-{
- if (fib6_nh->fib_nh_flags & RTNH_F_DEAD)
- *flags |= RTNH_F_DEAD;
-
- if (fib6_nh->fib_nh_flags & RTNH_F_LINKDOWN) {
- *flags |= RTNH_F_LINKDOWN;
-
- rcu_read_lock();
- if (ip6_ignore_linkdown(fib6_nh->fib_nh_dev))
- *flags |= RTNH_F_DEAD;
- rcu_read_unlock();
- }
-
- if (fib6_nh->fib_nh_has_gw) {
- if (nla_put_in6_addr(skb, RTA_GATEWAY, &fib6_nh->fib_nh_gw6) < 0)
- goto nla_put_failure;
- }
-
- *flags |= (fib6_nh->fib_nh_flags & RTNH_F_ONLINK);
- if (fib6_nh->fib_nh_flags & RTNH_F_OFFLOAD)
- *flags |= RTNH_F_OFFLOAD;
-
- /* not needed for multipath encoding b/c it has a rtnexthop struct */
- if (!skip_oif && fib6_nh->fib_nh_dev &&
- nla_put_u32(skb, RTA_OIF, fib6_nh->fib_nh_dev->ifindex))
- goto nla_put_failure;
-
- if (fib6_nh->fib_nh_lws &&
- lwtunnel_fill_encap(skb, fib6_nh->fib_nh_lws) < 0)
- goto nla_put_failure;
-
- return 0;
-
-nla_put_failure:
- return -EMSGSIZE;
-}
-
-/* add multipath next hop */
-static int rt6_add_nexthop(struct sk_buff *skb, const struct fib6_nh *fib6_nh)
-{
- const struct net_device *dev = fib6_nh->fib_nh_dev;
- struct rtnexthop *rtnh;
- unsigned int flags = 0;
-
- rtnh = nla_reserve_nohdr(skb, sizeof(*rtnh));
- if (!rtnh)
- goto nla_put_failure;
-
- rtnh->rtnh_hops = fib6_nh->fib_nh_weight - 1;
- rtnh->rtnh_ifindex = dev ? dev->ifindex : 0;
-
- if (rt6_nexthop_info(skb, fib6_nh, &flags, true) < 0)
- goto nla_put_failure;
-
- rtnh->rtnh_flags = flags;
-
- /* length of rtnetlink header + attributes */
- rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *)rtnh;
-
- return 0;
-
-nla_put_failure:
- return -EMSGSIZE;
-}
-
static int rt6_fill_node(struct net *net, struct sk_buff *skb,
struct fib6_info *rt, struct dst_entry *dst,
struct in6_addr *dest, struct in6_addr *src,
if (!mp)
goto nla_put_failure;
- if (rt6_add_nexthop(skb, &rt->fib6_nh) < 0)
+ if (fib_add_nexthop(skb, &rt->fib6_nh.nh_common,
+ rt->fib6_nh.fib_nh_weight) < 0)
goto nla_put_failure;
list_for_each_entry_safe(sibling, next_sibling,
&rt->fib6_siblings, fib6_siblings) {
- if (rt6_add_nexthop(skb, &sibling->fib6_nh) < 0)
+ if (fib_add_nexthop(skb, &sibling->fib6_nh.nh_common,
+ sibling->fib6_nh.fib_nh_weight) < 0)
goto nla_put_failure;
}
nla_nest_end(skb, mp);
} else {
- if (rt6_nexthop_info(skb, &rt->fib6_nh, &rtm->rtm_flags,
- false) < 0)
+ if (fib_nexthop_info(skb, &rt->fib6_nh.nh_common,
+ &rtm->rtm_flags, false) < 0)
goto nla_put_failure;
}
!net_eq(tunnel->net, dev_net(tunnel->dev))))
goto out;
+ /* skb can be uncloned in iptunnel_pull_header, so
+ * old iph is no longer valid
+ */
+ iph = (const struct iphdr *)skb_mac_header(skb);
err = IP_ECN_decapsulate(iph, skb);
if (unlikely(err)) {
if (log_ecn_error)
/* Helper returning the inet6 address from a given tcp socket.
* It can be used in TCP stack instead of inet6_sk(sk).
* This avoids a dereference and allow compiler optimizations.
+ * It is a specialized version of inet6_sk_generic().
*/
static struct ipv6_pinfo *tcp_inet6_sk(const struct sock *sk)
{
- struct tcp6_sock *tcp6 = container_of(tcp_sk(sk), struct tcp6_sock, tcp);
+ unsigned int offset = sizeof(struct tcp6_sock) - sizeof(struct ipv6_pinfo);
- return &tcp6->inet6;
+ return (struct ipv6_pinfo *)(((u8 *)sk) + offset);
}
static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
struct inet_sock *inet = inet_sk(sk);
struct sk_buff *skb;
unsigned int ulen, copied;
- int peeked, peeking, off;
- int err;
+ int off, err, peeking = flags & MSG_PEEK;
int is_udplite = IS_UDPLITE(sk);
struct udp_mib __percpu *mib;
bool checksum_valid = false;
return ipv6_recv_rxpmtu(sk, msg, len, addr_len);
try_again:
- peeking = flags & MSG_PEEK;
off = sk_peek_offset(sk, flags);
- skb = __skb_recv_udp(sk, flags, noblock, &peeked, &off, &err);
+ skb = __skb_recv_udp(sk, flags, noblock, &off, &err);
if (!skb)
return err;
goto csum_copy_err;
}
if (unlikely(err)) {
- if (!peeked) {
+ if (!peeking) {
atomic_inc(&sk->sk_drops);
SNMP_INC_STATS(mib, UDP_MIB_INERRORS);
}
kfree_skb(skb);
return err;
}
- if (!peeked)
+ if (!peeking)
SNMP_INC_STATS(mib, UDP_MIB_INDATAGRAMS);
sock_recv_ts_and_drops(msg, sk, skb);
static int udpv6_pre_connect(struct sock *sk, struct sockaddr *uaddr,
int addr_len)
{
+ if (addr_len < offsetofend(struct sockaddr, sa_family))
+ return -EINVAL;
/* The following checks are replicated from __ip6_datagram_connect()
* and intended to prevent BPF program called below from accessing
* bytes that are out of the bound specified by user in addr_len.
if (err)
goto fail;
- err = sock_register(&kcm_family_ops);
- if (err)
- goto sock_register_fail;
-
err = register_pernet_device(&kcm_net_ops);
if (err)
goto net_ops_fail;
+ err = sock_register(&kcm_family_ops);
+ if (err)
+ goto sock_register_fail;
+
err = kcm_proc_init();
if (err)
goto proc_init_fail;
return 0;
proc_init_fail:
- unregister_pernet_device(&kcm_net_ops);
-
-net_ops_fail:
sock_unregister(PF_KCM);
sock_register_fail:
+ unregister_pernet_device(&kcm_net_ops);
+
+net_ops_fail:
proto_unregister(&kcm_proto);
fail:
static void __exit kcm_exit(void)
{
kcm_proc_exit();
- unregister_pernet_device(&kcm_net_ops);
sock_unregister(PF_KCM);
+ unregister_pernet_device(&kcm_net_ops);
proto_unregister(&kcm_proto);
destroy_workqueue(kcm_wq);
struct llc_sap *sap;
int rc = -EINVAL;
- dprintk("%s: binding %02X\n", __func__, addr->sllc_sap);
-
lock_sock(sk);
if (unlikely(!sock_flag(sk, SOCK_ZAPPED) || addrlen != sizeof(*addr)))
goto out;
rc = -EAFNOSUPPORT;
if (unlikely(addr->sllc_family != AF_LLC))
goto out;
+ dprintk("%s: binding %02X\n", __func__, addr->sllc_sap);
rc = -ENODEV;
rcu_read_lock();
if (sk->sk_bound_dev_if) {
{
struct ieee80211_sub_if_data *sdata = vif_to_sdata(txq->txq.vif);
+ if (local->in_reconfig)
+ return;
+
if (!check_sdata_in_driver(sdata))
return;
* The driver doesn't know anything about VLAN interfaces.
* Hence, don't send GTKs for VLAN interfaces to the driver.
*/
- if (!(key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE))
+ if (!(key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE)) {
+ ret = 1;
goto out_unsupported;
+ }
}
ret = drv_set_key(key->local, SET_KEY, sdata,
/* all of these we can do in software - if driver can */
if (ret == 1)
return 0;
- if (ieee80211_hw_check(&key->local->hw, SW_CRYPTO_CONTROL)) {
- if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
- return 0;
+ if (ieee80211_hw_check(&key->local->hw, SW_CRYPTO_CONTROL))
return -EINVAL;
- }
return 0;
default:
return -EINVAL;
static u32 mesh_table_hash(const void *addr, u32 len, u32 seed)
{
/* Use last four bytes of hw addr as hash index */
- return jhash_1word(*(u32 *)(addr+2), seed);
+ return jhash_1word(__get_unaligned_cpu32((u8 *)addr + 2), seed);
}
static const struct rhashtable_params mesh_rht_params = {
return;
for (tid = 0; tid < IEEE80211_NUM_TIDS; tid++) {
- if (txq_has_queue(sta->sta.txq[tid]))
+ struct ieee80211_txq *txq = sta->sta.txq[tid];
+ struct txq_info *txqi = to_txq_info(txq);
+
+ spin_lock(&local->active_txq_lock[txq->ac]);
+ if (!list_empty(&txqi->schedule_order))
+ list_del_init(&txqi->schedule_order);
+ spin_unlock(&local->active_txq_lock[txq->ac]);
+
+ if (txq_has_queue(txq))
set_bit(tid, &sta->txq_buffered_tids);
else
clear_bit(tid, &sta->txq_buffered_tids);
/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Portions of this file
+ * Copyright (C) 2019 Intel Corporation
+ */
+
#ifdef CONFIG_MAC80211_MESSAGE_TRACING
#if !defined(__MAC80211_MSG_DRIVER_TRACE) || defined(TRACE_HEADER_MULTI_READ)
#undef TRACE_SYSTEM
#define TRACE_SYSTEM mac80211_msg
-#define MAX_MSG_LEN 100
+#define MAX_MSG_LEN 120
DECLARE_EVENT_CLASS(mac80211_msg_event,
TP_PROTO(struct va_format *vaf),
u8 max_subframes = sta->sta.max_amsdu_subframes;
int max_frags = local->hw.max_tx_fragments;
int max_amsdu_len = sta->sta.max_amsdu_len;
+ int orig_truesize;
__be16 len;
void *data;
bool ret = false;
if (!head || skb_is_gso(head))
goto out;
+ orig_truesize = head->truesize;
orig_len = head->len;
if (skb->len + head->len > max_amsdu_len)
*frag_tail = skb;
out_recalc:
+ fq->memory_usage += head->truesize - orig_truesize;
if (head->len != orig_len) {
flow->backlog += head->len - orig_len;
tin->backlog_bytes += head->len - orig_len;
struct ieee80211_txq *ieee80211_next_txq(struct ieee80211_hw *hw, u8 ac)
{
struct ieee80211_local *local = hw_to_local(hw);
+ struct ieee80211_txq *ret = NULL;
struct txq_info *txqi = NULL;
- lockdep_assert_held(&local->active_txq_lock[ac]);
+ spin_lock_bh(&local->active_txq_lock[ac]);
begin:
txqi = list_first_entry_or_null(&local->active_txqs[ac],
struct txq_info,
schedule_order);
if (!txqi)
- return NULL;
+ goto out;
if (txqi->txq.sta) {
struct sta_info *sta = container_of(txqi->txq.sta,
if (txqi->schedule_round == local->schedule_round[ac])
- return NULL;
+ goto out;
list_del_init(&txqi->schedule_order);
txqi->schedule_round = local->schedule_round[ac];
- return &txqi->txq;
+ ret = &txqi->txq;
+
+out:
+ spin_unlock_bh(&local->active_txq_lock[ac]);
+ return ret;
}
EXPORT_SYMBOL(ieee80211_next_txq);
-void ieee80211_return_txq(struct ieee80211_hw *hw,
- struct ieee80211_txq *txq)
+void __ieee80211_schedule_txq(struct ieee80211_hw *hw,
+ struct ieee80211_txq *txq,
+ bool force)
{
struct ieee80211_local *local = hw_to_local(hw);
struct txq_info *txqi = to_txq_info(txq);
- lockdep_assert_held(&local->active_txq_lock[txq->ac]);
+ spin_lock_bh(&local->active_txq_lock[txq->ac]);
if (list_empty(&txqi->schedule_order) &&
- (!skb_queue_empty(&txqi->frags) || txqi->tin.backlog_packets)) {
+ (force || !skb_queue_empty(&txqi->frags) ||
+ txqi->tin.backlog_packets)) {
/* If airtime accounting is active, always enqueue STAs at the
* head of the list to ensure that they only get moved to the
* back by the airtime DRR scheduler once they have a negative
list_add_tail(&txqi->schedule_order,
&local->active_txqs[txq->ac]);
}
-}
-EXPORT_SYMBOL(ieee80211_return_txq);
-void ieee80211_schedule_txq(struct ieee80211_hw *hw,
- struct ieee80211_txq *txq)
- __acquires(txq_lock) __releases(txq_lock)
-{
- struct ieee80211_local *local = hw_to_local(hw);
-
- spin_lock_bh(&local->active_txq_lock[txq->ac]);
- ieee80211_return_txq(hw, txq);
spin_unlock_bh(&local->active_txq_lock[txq->ac]);
}
-EXPORT_SYMBOL(ieee80211_schedule_txq);
+EXPORT_SYMBOL(__ieee80211_schedule_txq);
bool ieee80211_txq_may_transmit(struct ieee80211_hw *hw,
struct ieee80211_txq *txq)
struct sta_info *sta;
u8 ac = txq->ac;
- lockdep_assert_held(&local->active_txq_lock[ac]);
+ spin_lock_bh(&local->active_txq_lock[ac]);
if (!txqi->txq.sta)
goto out;
sta->airtime[ac].deficit += sta->airtime_weight;
list_move_tail(&txqi->schedule_order, &local->active_txqs[ac]);
+ spin_unlock_bh(&local->active_txq_lock[ac]);
return false;
out:
if (!list_empty(&txqi->schedule_order))
list_del_init(&txqi->schedule_order);
+ spin_unlock_bh(&local->active_txq_lock[ac]);
return true;
}
EXPORT_SYMBOL(ieee80211_txq_may_transmit);
void ieee80211_txq_schedule_start(struct ieee80211_hw *hw, u8 ac)
- __acquires(txq_lock)
{
struct ieee80211_local *local = hw_to_local(hw);
spin_lock_bh(&local->active_txq_lock[ac]);
local->schedule_round[ac]++;
-}
-EXPORT_SYMBOL(ieee80211_txq_schedule_start);
-
-void ieee80211_txq_schedule_end(struct ieee80211_hw *hw, u8 ac)
- __releases(txq_lock)
-{
- struct ieee80211_local *local = hw_to_local(hw);
-
spin_unlock_bh(&local->active_txq_lock[ac]);
}
-EXPORT_SYMBOL(ieee80211_txq_schedule_end);
+EXPORT_SYMBOL(ieee80211_txq_schedule_start);
void __ieee80211_subif_start_xmit(struct sk_buff *skb,
struct net_device *dev,
mpls_stats_inc_outucastpkts(out_dev, skb);
- if (rt)
- err = neigh_xmit(NEIGH_ARP_TABLE, out_dev, &rt->rt_gateway,
- skb);
- else if (rt6) {
+ if (rt) {
+ if (rt->rt_gw_family == AF_INET)
+ err = neigh_xmit(NEIGH_ARP_TABLE, out_dev, &rt->rt_gw4,
+ skb);
+ else if (rt->rt_gw_family == AF_INET6)
+ err = neigh_xmit(NEIGH_ND_TABLE, out_dev, &rt->rt_gw6,
+ skb);
+ } else if (rt6) {
if (ipv6_addr_v4mapped(&rt6->rt6i_gateway)) {
/* 6PE (RFC 4798) */
err = neigh_xmit(NEIGH_ARP_TABLE, out_dev, &rt6->rt6i_gateway.s6_addr32[3],
forms of full Network Address Port Translation. This can be
controlled by iptables, ip6tables or nft.
-config NF_NAT_NEEDED
- bool
- depends on NF_NAT
- default y
-
config NF_NAT_AMANDA
tristate
depends on NF_CONNTRACK && NF_NAT
To compile it as a module, choose M here. If unsure, say N.
+config NETFILTER_XT_TARGET_MASQUERADE
+ tristate "MASQUERADE target support"
+ depends on NF_NAT
+ default m if NETFILTER_ADVANCED=n
+ select NF_NAT_MASQUERADE
+ help
+ Masquerading is a special case of NAT: all outgoing connections are
+ changed to seem to come from a particular interface's address, and
+ if the interface goes down, those connections are lost. This is
+ only useful for dialup accounts with dynamic IP address (ie. your IP
+ address will be different on next dialup).
+
+ To compile it as a module, choose M here. If unsure, say N.
+
config NETFILTER_XT_TARGET_TEE
tristate '"TEE" - packet cloning to alternate destination'
depends on NETFILTER_ADVANCED
nf_tables-objs := nf_tables_core.o nf_tables_api.o nft_chain_filter.o \
nf_tables_trace.o nft_immediate.o nft_cmp.o nft_range.o \
nft_bitwise.o nft_byteorder.o nft_payload.o nft_lookup.o \
- nft_dynset.o nft_meta.o nft_rt.o nft_exthdr.o
+ nft_dynset.o nft_meta.o nft_rt.o nft_exthdr.o \
+ nft_chain_route.o
nf_tables_set-objs := nf_tables_set_core.o \
nft_set_hash.o nft_set_bitmap.o nft_set_rbtree.o
obj-$(CONFIG_NETFILTER_XT_TARGET_NFQUEUE) += xt_NFQUEUE.o
obj-$(CONFIG_NETFILTER_XT_TARGET_RATEEST) += xt_RATEEST.o
obj-$(CONFIG_NETFILTER_XT_TARGET_REDIRECT) += xt_REDIRECT.o
+obj-$(CONFIG_NETFILTER_XT_TARGET_MASQUERADE) += xt_MASQUERADE.o
obj-$(CONFIG_NETFILTER_XT_TARGET_SECMARK) += xt_SECMARK.o
obj-$(CONFIG_NETFILTER_XT_TARGET_TPROXY) += xt_TPROXY.o
obj-$(CONFIG_NETFILTER_XT_TARGET_TCPMSS) += xt_TCPMSS.o
#include <linux/mm.h>
#include <linux/rcupdate.h>
#include <net/net_namespace.h>
+#include <net/netfilter/nf_queue.h>
#include <net/sock.h>
#include "nf_internals.h"
conn_flags = udest->conn_flags & IP_VS_CONN_F_DEST_MASK;
conn_flags |= IP_VS_CONN_F_INACTIVE;
+ /* set the tunnel info */
+ dest->tun_type = udest->tun_type;
+ dest->tun_port = udest->tun_port;
+
/* set the IP_VS_CONN_F_NOOUTPUT flag if not masquerading/NAT */
if ((conn_flags & IP_VS_CONN_F_FWD_MASK) != IP_VS_CONN_F_MASQ) {
conn_flags |= IP_VS_CONN_F_NOOUTPUT;
return -ERANGE;
}
+ if (udest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) {
+ if (udest->tun_port == 0) {
+ pr_err("%s(): tunnel port is zero\n", __func__);
+ return -EINVAL;
+ }
+ }
+
ip_vs_addr_copy(udest->af, &daddr, &udest->addr);
/* We use function that requires RCU lock */
return -ERANGE;
}
+ if (udest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) {
+ if (udest->tun_port == 0) {
+ pr_err("%s(): tunnel port is zero\n", __func__);
+ return -EINVAL;
+ }
+ }
+
ip_vs_addr_copy(udest->af, &daddr, &udest->addr);
/* We use function that requires RCU lock */
udest->u_threshold = udest_compat->u_threshold;
udest->l_threshold = udest_compat->l_threshold;
udest->af = AF_INET;
+ udest->tun_type = IP_VS_CONN_F_TUNNEL_TYPE_IPIP;
}
static int
[IPVS_DEST_ATTR_PERSIST_CONNS] = { .type = NLA_U32 },
[IPVS_DEST_ATTR_STATS] = { .type = NLA_NESTED },
[IPVS_DEST_ATTR_ADDR_FAMILY] = { .type = NLA_U16 },
+ [IPVS_DEST_ATTR_TUN_TYPE] = { .type = NLA_U8 },
+ [IPVS_DEST_ATTR_TUN_PORT] = { .type = NLA_U16 },
};
static int ip_vs_genl_fill_stats(struct sk_buff *skb, int container_type,
IP_VS_CONN_F_FWD_MASK)) ||
nla_put_u32(skb, IPVS_DEST_ATTR_WEIGHT,
atomic_read(&dest->weight)) ||
+ nla_put_u8(skb, IPVS_DEST_ATTR_TUN_TYPE,
+ dest->tun_type) ||
+ nla_put_be16(skb, IPVS_DEST_ATTR_TUN_PORT,
+ dest->tun_port) ||
nla_put_u32(skb, IPVS_DEST_ATTR_U_THRESH, dest->u_threshold) ||
nla_put_u32(skb, IPVS_DEST_ATTR_L_THRESH, dest->l_threshold) ||
nla_put_u32(skb, IPVS_DEST_ATTR_ACTIVE_CONNS,
/* If a full entry was requested, check for the additional fields */
if (full_entry) {
struct nlattr *nla_fwd, *nla_weight, *nla_u_thresh,
- *nla_l_thresh;
+ *nla_l_thresh, *nla_tun_type, *nla_tun_port;
nla_fwd = attrs[IPVS_DEST_ATTR_FWD_METHOD];
nla_weight = attrs[IPVS_DEST_ATTR_WEIGHT];
nla_u_thresh = attrs[IPVS_DEST_ATTR_U_THRESH];
nla_l_thresh = attrs[IPVS_DEST_ATTR_L_THRESH];
+ nla_tun_type = attrs[IPVS_DEST_ATTR_TUN_TYPE];
+ nla_tun_port = attrs[IPVS_DEST_ATTR_TUN_PORT];
if (!(nla_fwd && nla_weight && nla_u_thresh && nla_l_thresh))
return -EINVAL;
udest->weight = nla_get_u32(nla_weight);
udest->u_threshold = nla_get_u32(nla_u_thresh);
udest->l_threshold = nla_get_u32(nla_l_thresh);
+
+ if (nla_tun_type)
+ udest->tun_type = nla_get_u8(nla_tun_type);
+
+ if (nla_tun_port)
+ udest->tun_port = nla_get_be16(nla_tun_port);
}
return 0;
#include <linux/slab.h>
#include <linux/tcp.h> /* for tcphdr */
#include <net/ip.h>
+#include <net/gue.h>
#include <net/tcp.h> /* for csum_tcpudp_magic */
#include <net/udp.h>
#include <net/icmp.h> /* for icmp_send */
mtu = dst_mtu(&rt->dst);
} else {
mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr);
+ if (!dest)
+ goto err_put;
+ if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE)
+ mtu -= sizeof(struct udphdr) + sizeof(struct guehdr);
if (mtu < 68) {
IP_VS_DBG_RL("%s(): mtu less than 68\n", __func__);
goto err_put;
mtu = dst_mtu(&rt->dst);
else {
mtu = dst_mtu(&rt->dst) - sizeof(struct ipv6hdr);
+ if (!dest)
+ goto err_put;
+ if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE)
+ mtu -= sizeof(struct udphdr) + sizeof(struct guehdr);
if (mtu < IPV6_MIN_MTU) {
IP_VS_DBG_RL("%s(): mtu less than %d\n", __func__,
IPV6_MIN_MTU);
}
}
+static int
+ipvs_gue_encap(struct net *net, struct sk_buff *skb,
+ struct ip_vs_conn *cp, __u8 *next_protocol)
+{
+ __be16 dport;
+ __be16 sport = udp_flow_src_port(net, skb, 0, 0, false);
+ struct udphdr *udph; /* Our new UDP header */
+ struct guehdr *gueh; /* Our new GUE header */
+
+ skb_push(skb, sizeof(struct guehdr));
+
+ gueh = (struct guehdr *)skb->data;
+
+ gueh->control = 0;
+ gueh->version = 0;
+ gueh->hlen = 0;
+ gueh->flags = 0;
+ gueh->proto_ctype = *next_protocol;
+
+ skb_push(skb, sizeof(struct udphdr));
+ skb_reset_transport_header(skb);
+
+ udph = udp_hdr(skb);
+
+ dport = cp->dest->tun_port;
+ udph->dest = dport;
+ udph->source = sport;
+ udph->len = htons(skb->len);
+ udph->check = 0;
+
+ *next_protocol = IPPROTO_UDP;
+
+ return 0;
+}
+
/*
* IP Tunneling transmitter
*
struct iphdr *iph; /* Our new IP header */
unsigned int max_headroom; /* The extra header space needed */
int ret, local;
+ int tun_type, gso_type;
EnterFunction(10);
*/
max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct iphdr);
+ tun_type = cp->dest->tun_type;
+
+ if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE)
+ max_headroom += sizeof(struct udphdr) + sizeof(struct guehdr);
+
/* We only care about the df field if sysctl_pmtu_disc(ipvs) is set */
dfp = sysctl_pmtu_disc(ipvs) ? &df : NULL;
skb = ip_vs_prepare_tunneled_skb(skb, cp->af, max_headroom,
if (IS_ERR(skb))
goto tx_error;
- if (iptunnel_handle_offloads(skb, __tun_gso_type_mask(AF_INET, cp->af)))
+ gso_type = __tun_gso_type_mask(AF_INET, cp->af);
+ if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE)
+ gso_type |= SKB_GSO_UDP_TUNNEL;
+
+ if (iptunnel_handle_offloads(skb, gso_type))
goto tx_error;
skb->transport_header = skb->network_header;
+ skb_set_inner_ipproto(skb, next_protocol);
+
+ if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE)
+ ipvs_gue_encap(net, skb, cp, &next_protocol);
+
skb_push(skb, sizeof(struct iphdr));
skb_reset_network_header(skb);
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh)
{
+ struct netns_ipvs *ipvs = cp->ipvs;
+ struct net *net = ipvs->net;
struct rt6_info *rt; /* Route to the other host */
struct in6_addr saddr; /* Source for tunnel */
struct net_device *tdev; /* Device to other host */
struct ipv6hdr *iph; /* Our new IP header */
unsigned int max_headroom; /* The extra header space needed */
int ret, local;
+ int tun_type, gso_type;
EnterFunction(10);
- local = __ip_vs_get_out_rt_v6(cp->ipvs, cp->af, skb, cp->dest,
+ local = __ip_vs_get_out_rt_v6(ipvs, cp->af, skb, cp->dest,
&cp->daddr.in6,
&saddr, ipvsh, 1,
IP_VS_RT_MODE_LOCAL |
*/
max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct ipv6hdr);
+ tun_type = cp->dest->tun_type;
+
+ if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE)
+ max_headroom += sizeof(struct udphdr) + sizeof(struct guehdr);
+
skb = ip_vs_prepare_tunneled_skb(skb, cp->af, max_headroom,
&next_protocol, &payload_len,
&dsfield, &ttl, NULL);
if (IS_ERR(skb))
goto tx_error;
- if (iptunnel_handle_offloads(skb, __tun_gso_type_mask(AF_INET6, cp->af)))
+ gso_type = __tun_gso_type_mask(AF_INET6, cp->af);
+ if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE)
+ gso_type |= SKB_GSO_UDP_TUNNEL;
+
+ if (iptunnel_handle_offloads(skb, gso_type))
goto tx_error;
skb->transport_header = skb->network_header;
+ skb_set_inner_ipproto(skb, next_protocol);
+
+ if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE)
+ ipvs_gue_encap(net, skb, cp, &next_protocol);
+
skb_push(skb, sizeof(struct ipv6hdr));
skb_reset_network_header(skb);
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
ret = ip_vs_tunnel_xmit_prepare(skb, cp);
if (ret == NF_ACCEPT)
- ip6_local_out(cp->ipvs->net, skb->sk, skb);
+ ip6_local_out(net, skb->sk, skb);
else if (ret == NF_DROP)
kfree_skb(skb);
exp->tuple.dst.u.all = *dst;
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
memset(&exp->saved_addr, 0, sizeof(exp->saved_addr));
memset(&exp->saved_proto, 0, sizeof(exp->saved_proto));
#endif
#include <net/netfilter/nf_conntrack_timestamp.h>
#include <net/netfilter/nf_conntrack_labels.h>
#include <net/netfilter/nf_conntrack_synproxy.h>
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
#include <net/netfilter/nf_nat.h>
#include <net/netfilter/nf_nat_helper.h>
#endif
+ nla_total_size(0) /* CTA_HELP */
+ nla_total_size(NF_CT_HELPER_NAME_LEN) /* CTA_HELP_NAME */
+ ctnetlink_secctx_size(ct)
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
+ 2 * nla_total_size(0) /* CTA_NAT_SEQ_ADJ_ORIG|REPL */
+ 6 * nla_total_size(sizeof(u_int32_t)) /* CTA_NAT_SEQ_OFFSET */
#endif
return -EOPNOTSUPP;
}
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
static int
ctnetlink_parse_nat_setup(struct nf_conn *ct,
enum nf_nat_manip_type manip,
static int
ctnetlink_setup_nat(struct nf_conn *ct, const struct nlattr * const cda[])
{
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
int ret;
if (!cda[CTA_NAT_DST] && !cda[CTA_NAT_SRC])
+ nla_total_size(0) /* CTA_HELP */
+ nla_total_size(NF_CT_HELPER_NAME_LEN) /* CTA_HELP_NAME */
+ ctnetlink_secctx_size(ct)
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
+ 2 * nla_total_size(0) /* CTA_NAT_SEQ_ADJ_ORIG|REPL */
+ 6 * nla_total_size(sizeof(u_int32_t)) /* CTA_NAT_SEQ_OFFSET */
#endif
struct nf_conn *master = exp->master;
long timeout = ((long)exp->timeout.expires - (long)jiffies) / HZ;
struct nf_conn_help *help;
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
struct nlattr *nest_parms;
struct nf_conntrack_tuple nat_tuple = {};
#endif
CTA_EXPECT_MASTER) < 0)
goto nla_put_failure;
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
if (!nf_inet_addr_cmp(&exp->saved_addr, &any_addr) ||
exp->saved_proto.all) {
nest_parms = nla_nest_start(skb, CTA_EXPECT_NAT | NLA_F_NESTED);
struct nf_conntrack_expect *exp,
u_int8_t u3)
{
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
struct nlattr *tb[CTA_EXPECT_NAT_MAX+1];
struct nf_conntrack_tuple nat_tuple = {};
int err;
nfct_help(exp->master)->helper != nfct_help(ct)->helper ||
exp->class != class)
break;
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
if (!direct_rtp &&
(!nf_inet_addr_cmp(&exp->saved_addr, &exp->tuple.dst.u3) ||
exp->saved_proto.udp.port != exp->tuple.dst.u.udp.port) &&
if (tuplehash == NULL)
return NF_ACCEPT;
- outdev = dev_get_by_index_rcu(state->net, tuplehash->tuple.oifidx);
- if (!outdev)
- return NF_ACCEPT;
-
dir = tuplehash->tuple.dir;
flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
rt = (struct rtable *)flow->tuplehash[dir].tuple.dst_cache;
+ outdev = rt->dst.dev;
if (unlikely(nf_flow_exceeds_mtu(skb, flow->tuplehash[dir].tuple.mtu)) &&
(ip_hdr(skb)->frag_off & htons(IP_DF)) != 0)
if (tuplehash == NULL)
return NF_ACCEPT;
- outdev = dev_get_by_index_rcu(state->net, tuplehash->tuple.oifidx);
- if (!outdev)
- return NF_ACCEPT;
-
dir = tuplehash->tuple.dir;
flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
rt = (struct rt6_info *)flow->tuplehash[dir].tuple.dst_cache;
+ outdev = rt->dst.dev;
if (unlikely(nf_flow_exceeds_mtu(skb, flow->tuplehash[dir].tuple.mtu)))
return NF_ACCEPT;
#include <linux/netdevice.h>
/* nf_queue.c */
-int nf_queue(struct sk_buff *skb, struct nf_hook_state *state,
- const struct nf_hook_entries *entries, unsigned int index,
- unsigned int verdict);
void nf_queue_nf_hook_drop(struct net *net);
/* nf_log.c */
.expectfn = nf_nat_follow_master,
};
-int nf_nat_register_fn(struct net *net, const struct nf_hook_ops *ops,
+int nf_nat_register_fn(struct net *net, u8 pf, const struct nf_hook_ops *ops,
const struct nf_hook_ops *orig_nat_ops, unsigned int ops_count)
{
struct nat_net *nat_net = net_generic(net, nat_net_id);
struct nf_hook_ops *nat_ops;
int i, ret;
- if (WARN_ON_ONCE(ops->pf >= ARRAY_SIZE(nat_net->nat_proto_net)))
+ if (WARN_ON_ONCE(pf >= ARRAY_SIZE(nat_net->nat_proto_net)))
return -EINVAL;
- nat_proto_net = &nat_net->nat_proto_net[ops->pf];
+ nat_proto_net = &nat_net->nat_proto_net[pf];
for (i = 0; i < ops_count; i++) {
- if (WARN_ON(orig_nat_ops[i].pf != ops->pf))
- return -EINVAL;
if (orig_nat_ops[i].hooknum == hooknum) {
hooknum = i;
break;
return ret;
}
-void nf_nat_unregister_fn(struct net *net, const struct nf_hook_ops *ops,
- unsigned int ops_count)
+void nf_nat_unregister_fn(struct net *net, u8 pf, const struct nf_hook_ops *ops,
+ unsigned int ops_count)
{
struct nat_net *nat_net = net_generic(net, nat_net_id);
struct nf_nat_hooks_net *nat_proto_net;
int hooknum = ops->hooknum;
int i;
- if (ops->pf >= ARRAY_SIZE(nat_net->nat_proto_net))
+ if (pf >= ARRAY_SIZE(nat_net->nat_proto_net))
return;
- nat_proto_net = &nat_net->nat_proto_net[ops->pf];
+ nat_proto_net = &nat_net->nat_proto_net[pf];
mutex_lock(&nf_nat_proto_mutex);
if (WARN_ON(nat_proto_net->users == 0))
#include <linux/netfilter_ipv4.h>
#include <linux/netfilter_ipv6.h>
-#include <net/netfilter/ipv4/nf_nat_masquerade.h>
-#include <net/netfilter/ipv6/nf_nat_masquerade.h>
+#include <net/netfilter/nf_nat_masquerade.h>
static DEFINE_MUTEX(masq_mutex);
-static unsigned int masq_refcnt4 __read_mostly;
-static unsigned int masq_refcnt6 __read_mostly;
+static unsigned int masq_refcnt __read_mostly;
unsigned int
nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum,
.notifier_call = masq_inet_event,
};
-int nf_nat_masquerade_ipv4_register_notifier(void)
-{
- int ret = 0;
-
- mutex_lock(&masq_mutex);
- if (WARN_ON_ONCE(masq_refcnt4 == UINT_MAX)) {
- ret = -EOVERFLOW;
- goto out_unlock;
- }
-
- /* check if the notifier was already set */
- if (++masq_refcnt4 > 1)
- goto out_unlock;
-
- /* Register for device down reports */
- ret = register_netdevice_notifier(&masq_dev_notifier);
- if (ret)
- goto err_dec;
- /* Register IP address change reports */
- ret = register_inetaddr_notifier(&masq_inet_notifier);
- if (ret)
- goto err_unregister;
-
- mutex_unlock(&masq_mutex);
- return ret;
-
-err_unregister:
- unregister_netdevice_notifier(&masq_dev_notifier);
-err_dec:
- masq_refcnt4--;
-out_unlock:
- mutex_unlock(&masq_mutex);
- return ret;
-}
-EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4_register_notifier);
-
-void nf_nat_masquerade_ipv4_unregister_notifier(void)
-{
- mutex_lock(&masq_mutex);
- /* check if the notifier still has clients */
- if (--masq_refcnt4 > 0)
- goto out_unlock;
-
- unregister_netdevice_notifier(&masq_dev_notifier);
- unregister_inetaddr_notifier(&masq_inet_notifier);
-out_unlock:
- mutex_unlock(&masq_mutex);
-}
-EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4_unregister_notifier);
-
#if IS_ENABLED(CONFIG_IPV6)
static atomic_t v6_worker_count __read_mostly;
.notifier_call = masq_inet6_event,
};
-int nf_nat_masquerade_ipv6_register_notifier(void)
+static int nf_nat_masquerade_ipv6_register_notifier(void)
+{
+ return register_inet6addr_notifier(&masq_inet6_notifier);
+}
+#else
+static inline int nf_nat_masquerade_ipv6_register_notifier(void) { return 0; }
+#endif
+
+int nf_nat_masquerade_inet_register_notifiers(void)
{
int ret = 0;
mutex_lock(&masq_mutex);
- if (WARN_ON_ONCE(masq_refcnt6 == UINT_MAX)) {
+ if (WARN_ON_ONCE(masq_refcnt == UINT_MAX)) {
ret = -EOVERFLOW;
goto out_unlock;
}
- /* check if the notifier is already set */
- if (++masq_refcnt6 > 1)
+ /* check if the notifier was already set */
+ if (++masq_refcnt > 1)
goto out_unlock;
- ret = register_inet6addr_notifier(&masq_inet6_notifier);
+ /* Register for device down reports */
+ ret = register_netdevice_notifier(&masq_dev_notifier);
if (ret)
goto err_dec;
+ /* Register IP address change reports */
+ ret = register_inetaddr_notifier(&masq_inet_notifier);
+ if (ret)
+ goto err_unregister;
+
+ ret = nf_nat_masquerade_ipv6_register_notifier();
+ if (ret)
+ goto err_unreg_inet;
mutex_unlock(&masq_mutex);
return ret;
+err_unreg_inet:
+ unregister_inetaddr_notifier(&masq_inet_notifier);
+err_unregister:
+ unregister_netdevice_notifier(&masq_dev_notifier);
err_dec:
- masq_refcnt6--;
+ masq_refcnt--;
out_unlock:
mutex_unlock(&masq_mutex);
return ret;
}
-EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6_register_notifier);
+EXPORT_SYMBOL_GPL(nf_nat_masquerade_inet_register_notifiers);
-void nf_nat_masquerade_ipv6_unregister_notifier(void)
+void nf_nat_masquerade_inet_unregister_notifiers(void)
{
mutex_lock(&masq_mutex);
- /* check if the notifier still has clients */
- if (--masq_refcnt6 > 0)
+ /* check if the notifiers still have clients */
+ if (--masq_refcnt > 0)
goto out_unlock;
+ unregister_netdevice_notifier(&masq_dev_notifier);
+ unregister_inetaddr_notifier(&masq_inet_notifier);
+#if IS_ENABLED(CONFIG_IPV6)
unregister_inet6addr_notifier(&masq_inet6_notifier);
+#endif
out_unlock:
mutex_unlock(&masq_mutex);
}
-EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6_unregister_notifier);
-#endif
+EXPORT_SYMBOL_GPL(nf_nat_masquerade_inet_unregister_notifiers);
return ret;
}
-static const struct nf_hook_ops nf_nat_ipv4_ops[] = {
+const struct nf_hook_ops nf_nat_ipv4_ops[] = {
/* Before packet filtering, change destination */
{
.hook = nf_nat_ipv4_in,
int nf_nat_ipv4_register_fn(struct net *net, const struct nf_hook_ops *ops)
{
- return nf_nat_register_fn(net, ops, nf_nat_ipv4_ops, ARRAY_SIZE(nf_nat_ipv4_ops));
+ return nf_nat_register_fn(net, ops->pf, ops, nf_nat_ipv4_ops,
+ ARRAY_SIZE(nf_nat_ipv4_ops));
}
EXPORT_SYMBOL_GPL(nf_nat_ipv4_register_fn);
void nf_nat_ipv4_unregister_fn(struct net *net, const struct nf_hook_ops *ops)
{
- nf_nat_unregister_fn(net, ops, ARRAY_SIZE(nf_nat_ipv4_ops));
+ nf_nat_unregister_fn(net, ops->pf, ops, ARRAY_SIZE(nf_nat_ipv4_ops));
}
EXPORT_SYMBOL_GPL(nf_nat_ipv4_unregister_fn);
return ret;
}
-static int nat_route_me_harder(struct net *net, struct sk_buff *skb)
-{
-#ifdef CONFIG_IPV6_MODULE
- const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops();
-
- if (!v6_ops)
- return -EHOSTUNREACH;
-
- return v6_ops->route_me_harder(net, skb);
-#else
- return ip6_route_me_harder(net, skb);
-#endif
-}
-
static unsigned int
nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state)
if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3,
&ct->tuplehash[!dir].tuple.src.u3)) {
- err = nat_route_me_harder(state->net, skb);
+ err = nf_ip6_route_me_harder(state->net, skb);
if (err < 0)
ret = NF_DROP_ERR(err);
}
return ret;
}
-static const struct nf_hook_ops nf_nat_ipv6_ops[] = {
+const struct nf_hook_ops nf_nat_ipv6_ops[] = {
/* Before packet filtering, change destination */
{
.hook = nf_nat_ipv6_in,
int nf_nat_ipv6_register_fn(struct net *net, const struct nf_hook_ops *ops)
{
- return nf_nat_register_fn(net, ops, nf_nat_ipv6_ops,
+ return nf_nat_register_fn(net, ops->pf, ops, nf_nat_ipv6_ops,
ARRAY_SIZE(nf_nat_ipv6_ops));
}
EXPORT_SYMBOL_GPL(nf_nat_ipv6_register_fn);
void nf_nat_ipv6_unregister_fn(struct net *net, const struct nf_hook_ops *ops)
{
- nf_nat_unregister_fn(net, ops, ARRAY_SIZE(nf_nat_ipv6_ops));
+ nf_nat_unregister_fn(net, ops->pf, ops, ARRAY_SIZE(nf_nat_ipv6_ops));
}
EXPORT_SYMBOL_GPL(nf_nat_ipv6_unregister_fn);
#endif /* CONFIG_IPV6 */
+
+#if defined(CONFIG_NF_TABLES_INET) && IS_ENABLED(CONFIG_NFT_NAT)
+int nf_nat_inet_register_fn(struct net *net, const struct nf_hook_ops *ops)
+{
+ int ret;
+
+ if (WARN_ON_ONCE(ops->pf != NFPROTO_INET))
+ return -EINVAL;
+
+ ret = nf_nat_register_fn(net, NFPROTO_IPV6, ops, nf_nat_ipv6_ops,
+ ARRAY_SIZE(nf_nat_ipv6_ops));
+ if (ret)
+ return ret;
+
+ ret = nf_nat_register_fn(net, NFPROTO_IPV4, ops, nf_nat_ipv4_ops,
+ ARRAY_SIZE(nf_nat_ipv4_ops));
+ if (ret)
+ nf_nat_ipv6_unregister_fn(net, ops);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(nf_nat_inet_register_fn);
+
+void nf_nat_inet_unregister_fn(struct net *net, const struct nf_hook_ops *ops)
+{
+ nf_nat_unregister_fn(net, NFPROTO_IPV4, ops, ARRAY_SIZE(nf_nat_ipv4_ops));
+ nf_nat_unregister_fn(net, NFPROTO_IPV6, ops, ARRAY_SIZE(nf_nat_ipv6_ops));
+}
+EXPORT_SYMBOL_GPL(nf_nat_inet_unregister_fn);
+#endif /* NFT INET NAT */
return 0;
}
+EXPORT_SYMBOL_GPL(nf_queue);
static unsigned int nf_iterate(struct sk_buff *skb,
struct nf_hook_state *state,
.hashfn = nft_chain_hash,
.obj_hashfn = nft_chain_hash_obj,
.obj_cmpfn = nft_chain_hash_cmp,
- .locks_mul = 1,
.automatic_shrinking = true,
};
static __be64 nf_jiffies64_to_msecs(u64 input)
{
- u64 ms = jiffies64_to_nsecs(input);
-
- return cpu_to_be64(div_u64(ms, NSEC_PER_MSEC));
+ return cpu_to_be64(jiffies64_to_msecs(input));
}
static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
return err;
}
-static int nf_tables_set_desc_parse(const struct nft_ctx *ctx,
- struct nft_set_desc *desc,
+static int nf_tables_set_desc_parse(struct nft_set_desc *desc,
const struct nlattr *nla)
{
struct nlattr *da[NFTA_SET_DESC_MAX + 1];
policy = ntohl(nla_get_be32(nla[NFTA_SET_POLICY]));
if (nla[NFTA_SET_DESC] != NULL) {
- err = nf_tables_set_desc_parse(&ctx, &desc, nla[NFTA_SET_DESC]);
+ err = nf_tables_set_desc_parse(&desc, nla[NFTA_SET_DESC]);
if (err < 0)
return err;
}
}
EXPORT_SYMBOL_GPL(nf_tables_bind_set);
-void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set,
- struct nft_set_binding *binding, bool event)
+static void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set,
+ struct nft_set_binding *binding, bool event)
{
list_del_rcu(&binding->list);
GFP_KERNEL);
}
}
-EXPORT_SYMBOL_GPL(nf_tables_unbind_set);
void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set,
struct nft_set_binding *binding,
if (err < 0)
goto err5;
+ nft_chain_route_init();
return err;
err5:
rhltable_destroy(&nft_objname_ht);
nfnetlink_subsys_unregister(&nf_tables_subsys);
unregister_netdevice_notifier(&nf_tables_flowtable_notifier);
nft_chain_filter_fini();
+ nft_chain_route_fini();
unregister_pernet_subsys(&nf_tables_net_ops);
cancel_work_sync(&trans_destroy_work);
rcu_barrier();
}
EXPORT_SYMBOL_GPL(nf_osf_match);
-const char *nf_osf_find(const struct sk_buff *skb,
- const struct list_head *nf_osf_fingers,
- const int ttl_check)
+bool nf_osf_find(const struct sk_buff *skb,
+ const struct list_head *nf_osf_fingers,
+ const int ttl_check, struct nf_osf_data *data)
{
const struct iphdr *ip = ip_hdr(skb);
const struct nf_osf_user_finger *f;
const struct nf_osf_finger *kf;
struct nf_osf_hdr_ctx ctx;
const struct tcphdr *tcp;
- const char *genre = NULL;
memset(&ctx, 0, sizeof(ctx));
tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts);
if (!tcp)
- return NULL;
+ return false;
list_for_each_entry_rcu(kf, &nf_osf_fingers[ctx.df], finger_entry) {
f = &kf->finger;
if (!nf_osf_match_one(skb, f, ttl_check, &ctx))
continue;
- genre = f->genre;
+ data->genre = f->genre;
+ data->version = f->version;
break;
}
- return genre;
+ return true;
}
EXPORT_SYMBOL_GPL(nf_osf_find);
};
#endif
+#ifdef CONFIG_NF_TABLES_INET
+static int nft_nat_inet_reg(struct net *net, const struct nf_hook_ops *ops)
+{
+ return nf_nat_inet_register_fn(net, ops);
+}
+
+static void nft_nat_inet_unreg(struct net *net, const struct nf_hook_ops *ops)
+{
+ nf_nat_inet_unregister_fn(net, ops);
+}
+
+static const struct nft_chain_type nft_chain_nat_inet = {
+ .name = "nat",
+ .type = NFT_CHAIN_T_NAT,
+ .family = NFPROTO_INET,
+ .hook_mask = (1 << NF_INET_PRE_ROUTING) |
+ (1 << NF_INET_LOCAL_IN) |
+ (1 << NF_INET_LOCAL_OUT) |
+ (1 << NF_INET_POST_ROUTING),
+ .hooks = {
+ [NF_INET_PRE_ROUTING] = nft_nat_do_chain,
+ [NF_INET_LOCAL_IN] = nft_nat_do_chain,
+ [NF_INET_LOCAL_OUT] = nft_nat_do_chain,
+ [NF_INET_POST_ROUTING] = nft_nat_do_chain,
+ },
+ .ops_register = nft_nat_inet_reg,
+ .ops_unregister = nft_nat_inet_unreg,
+};
+#endif
+
static int __init nft_chain_nat_init(void)
{
#ifdef CONFIG_NF_TABLES_IPV6
#ifdef CONFIG_NF_TABLES_IPV4
nft_register_chain_type(&nft_chain_nat_ipv4);
#endif
+#ifdef CONFIG_NF_TABLES_INET
+ nft_register_chain_type(&nft_chain_nat_inet);
+#endif
return 0;
}
#ifdef CONFIG_NF_TABLES_IPV6
nft_unregister_chain_type(&nft_chain_nat_ipv6);
#endif
+#ifdef CONFIG_NF_TABLES_INET
+ nft_unregister_chain_type(&nft_chain_nat_inet);
+#endif
}
module_init(nft_chain_nat_init);
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/skbuff.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv4.h>
+#include <linux/netfilter_ipv6.h>
+#include <linux/netfilter/nfnetlink.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_ipv4.h>
+#include <net/netfilter/nf_tables_ipv6.h>
+#include <net/route.h>
+#include <net/ip.h>
+
+#ifdef CONFIG_NF_TABLES_IPV4
+static unsigned int nf_route_table_hook4(void *priv,
+ struct sk_buff *skb,
+ const struct nf_hook_state *state)
+{
+ const struct iphdr *iph;
+ struct nft_pktinfo pkt;
+ __be32 saddr, daddr;
+ unsigned int ret;
+ u32 mark;
+ int err;
+ u8 tos;
+
+ nft_set_pktinfo(&pkt, skb, state);
+ nft_set_pktinfo_ipv4(&pkt, skb);
+
+ mark = skb->mark;
+ iph = ip_hdr(skb);
+ saddr = iph->saddr;
+ daddr = iph->daddr;
+ tos = iph->tos;
+
+ ret = nft_do_chain(&pkt, priv);
+ if (ret == NF_ACCEPT) {
+ iph = ip_hdr(skb);
+
+ if (iph->saddr != saddr ||
+ iph->daddr != daddr ||
+ skb->mark != mark ||
+ iph->tos != tos) {
+ err = ip_route_me_harder(state->net, skb, RTN_UNSPEC);
+ if (err < 0)
+ ret = NF_DROP_ERR(err);
+ }
+ }
+ return ret;
+}
+
+static const struct nft_chain_type nft_chain_route_ipv4 = {
+ .name = "route",
+ .type = NFT_CHAIN_T_ROUTE,
+ .family = NFPROTO_IPV4,
+ .hook_mask = (1 << NF_INET_LOCAL_OUT),
+ .hooks = {
+ [NF_INET_LOCAL_OUT] = nf_route_table_hook4,
+ },
+};
+#endif
+
+#ifdef CONFIG_NF_TABLES_IPV6
+static unsigned int nf_route_table_hook6(void *priv,
+ struct sk_buff *skb,
+ const struct nf_hook_state *state)
+{
+ struct in6_addr saddr, daddr;
+ struct nft_pktinfo pkt;
+ u32 mark, flowlabel;
+ unsigned int ret;
+ u8 hop_limit;
+ int err;
+
+ nft_set_pktinfo(&pkt, skb, state);
+ nft_set_pktinfo_ipv6(&pkt, skb);
+
+ /* save source/dest address, mark, hoplimit, flowlabel, priority */
+ memcpy(&saddr, &ipv6_hdr(skb)->saddr, sizeof(saddr));
+ memcpy(&daddr, &ipv6_hdr(skb)->daddr, sizeof(daddr));
+ mark = skb->mark;
+ hop_limit = ipv6_hdr(skb)->hop_limit;
+
+ /* flowlabel and prio (includes version, which shouldn't change either)*/
+ flowlabel = *((u32 *)ipv6_hdr(skb));
+
+ ret = nft_do_chain(&pkt, priv);
+ if (ret == NF_ACCEPT &&
+ (memcmp(&ipv6_hdr(skb)->saddr, &saddr, sizeof(saddr)) ||
+ memcmp(&ipv6_hdr(skb)->daddr, &daddr, sizeof(daddr)) ||
+ skb->mark != mark ||
+ ipv6_hdr(skb)->hop_limit != hop_limit ||
+ flowlabel != *((u32 *)ipv6_hdr(skb)))) {
+ err = nf_ip6_route_me_harder(state->net, skb);
+ if (err < 0)
+ ret = NF_DROP_ERR(err);
+ }
+
+ return ret;
+}
+
+static const struct nft_chain_type nft_chain_route_ipv6 = {
+ .name = "route",
+ .type = NFT_CHAIN_T_ROUTE,
+ .family = NFPROTO_IPV6,
+ .hook_mask = (1 << NF_INET_LOCAL_OUT),
+ .hooks = {
+ [NF_INET_LOCAL_OUT] = nf_route_table_hook6,
+ },
+};
+#endif
+
+#ifdef CONFIG_NF_TABLES_INET
+static unsigned int nf_route_table_inet(void *priv,
+ struct sk_buff *skb,
+ const struct nf_hook_state *state)
+{
+ struct nft_pktinfo pkt;
+
+ switch (state->pf) {
+ case NFPROTO_IPV4:
+ return nf_route_table_hook4(priv, skb, state);
+ case NFPROTO_IPV6:
+ return nf_route_table_hook6(priv, skb, state);
+ default:
+ nft_set_pktinfo(&pkt, skb, state);
+ break;
+ }
+
+ return nft_do_chain(&pkt, priv);
+}
+
+static const struct nft_chain_type nft_chain_route_inet = {
+ .name = "route",
+ .type = NFT_CHAIN_T_ROUTE,
+ .family = NFPROTO_INET,
+ .hook_mask = (1 << NF_INET_LOCAL_OUT),
+ .hooks = {
+ [NF_INET_LOCAL_OUT] = nf_route_table_inet,
+ },
+};
+#endif
+
+void __init nft_chain_route_init(void)
+{
+#ifdef CONFIG_NF_TABLES_IPV6
+ nft_register_chain_type(&nft_chain_route_ipv6);
+#endif
+#ifdef CONFIG_NF_TABLES_IPV4
+ nft_register_chain_type(&nft_chain_route_ipv4);
+#endif
+#ifdef CONFIG_NF_TABLES_INET
+ nft_register_chain_type(&nft_chain_route_inet);
+#endif
+}
+
+void __exit nft_chain_route_fini(void)
+{
+#ifdef CONFIG_NF_TABLES_IPV6
+ nft_unregister_chain_type(&nft_chain_route_ipv6);
+#endif
+#ifdef CONFIG_NF_TABLES_IPV4
+ nft_unregister_chain_type(&nft_chain_route_ipv4);
+#endif
+#ifdef CONFIG_NF_TABLES_INET
+ nft_unregister_chain_type(&nft_chain_route_inet);
+#endif
+}
#include <linux/netfilter/nf_tables.h>
#include <net/netfilter/nf_tables.h>
#include <net/netfilter/nf_nat.h>
-#include <net/netfilter/ipv4/nf_nat_masquerade.h>
-#include <net/netfilter/ipv6/nf_nat_masquerade.h>
+#include <net/netfilter/nf_nat_masquerade.h>
struct nft_masq {
u32 flags;
static int __init nft_masq_module_init_ipv6(void)
{
- int ret = nft_register_expr(&nft_masq_ipv6_type);
-
- if (ret)
- return ret;
-
- ret = nf_nat_masquerade_ipv6_register_notifier();
- if (ret < 0)
- nft_unregister_expr(&nft_masq_ipv6_type);
-
- return ret;
+ return nft_register_expr(&nft_masq_ipv6_type);
}
static void nft_masq_module_exit_ipv6(void)
{
nft_unregister_expr(&nft_masq_ipv6_type);
- nf_nat_masquerade_ipv6_unregister_notifier();
}
#else
static inline int nft_masq_module_init_ipv6(void) { return 0; }
static inline void nft_masq_module_exit_ipv6(void) {}
#endif
+#ifdef CONFIG_NF_TABLES_INET
+static void nft_masq_inet_eval(const struct nft_expr *expr,
+ struct nft_regs *regs,
+ const struct nft_pktinfo *pkt)
+{
+ switch (nft_pf(pkt)) {
+ case NFPROTO_IPV4:
+ return nft_masq_ipv4_eval(expr, regs, pkt);
+ case NFPROTO_IPV6:
+ return nft_masq_ipv6_eval(expr, regs, pkt);
+ }
+
+ WARN_ON_ONCE(1);
+}
+
+static void
+nft_masq_inet_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
+{
+ nf_ct_netns_put(ctx->net, NFPROTO_INET);
+}
+
+static struct nft_expr_type nft_masq_inet_type;
+static const struct nft_expr_ops nft_masq_inet_ops = {
+ .type = &nft_masq_inet_type,
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_masq)),
+ .eval = nft_masq_inet_eval,
+ .init = nft_masq_init,
+ .destroy = nft_masq_inet_destroy,
+ .dump = nft_masq_dump,
+ .validate = nft_masq_validate,
+};
+
+static struct nft_expr_type nft_masq_inet_type __read_mostly = {
+ .family = NFPROTO_INET,
+ .name = "masq",
+ .ops = &nft_masq_inet_ops,
+ .policy = nft_masq_policy,
+ .maxattr = NFTA_MASQ_MAX,
+ .owner = THIS_MODULE,
+};
+
+static int __init nft_masq_module_init_inet(void)
+{
+ return nft_register_expr(&nft_masq_inet_type);
+}
+
+static void nft_masq_module_exit_inet(void)
+{
+ nft_unregister_expr(&nft_masq_inet_type);
+}
+#else
+static inline int nft_masq_module_init_inet(void) { return 0; }
+static inline void nft_masq_module_exit_inet(void) {}
+#endif
+
static int __init nft_masq_module_init(void)
{
int ret;
if (ret < 0)
return ret;
+ ret = nft_masq_module_init_inet();
+ if (ret < 0) {
+ nft_masq_module_exit_ipv6();
+ return ret;
+ }
+
ret = nft_register_expr(&nft_masq_ipv4_type);
if (ret < 0) {
+ nft_masq_module_exit_inet();
nft_masq_module_exit_ipv6();
return ret;
}
- ret = nf_nat_masquerade_ipv4_register_notifier();
+ ret = nf_nat_masquerade_inet_register_notifiers();
if (ret < 0) {
nft_masq_module_exit_ipv6();
+ nft_masq_module_exit_inet();
nft_unregister_expr(&nft_masq_ipv4_type);
return ret;
}
static void __exit nft_masq_module_exit(void)
{
nft_masq_module_exit_ipv6();
+ nft_masq_module_exit_inet();
nft_unregister_expr(&nft_masq_ipv4_type);
- nf_nat_masquerade_ipv4_unregister_notifier();
+ nf_nat_masquerade_inet_unregister_notifiers();
}
module_init(nft_masq_module_init);
return -EINVAL;
family = ntohl(nla_get_be32(tb[NFTA_NAT_FAMILY]));
- if (family != ctx->family)
+ if (ctx->family != NFPROTO_INET && ctx->family != family)
return -EOPNOTSUPP;
switch (family) {
.owner = THIS_MODULE,
};
+#ifdef CONFIG_NF_TABLES_INET
+static void nft_nat_inet_eval(const struct nft_expr *expr,
+ struct nft_regs *regs,
+ const struct nft_pktinfo *pkt)
+{
+ const struct nft_nat *priv = nft_expr_priv(expr);
+
+ if (priv->family == nft_pf(pkt))
+ nft_nat_eval(expr, regs, pkt);
+}
+
+static const struct nft_expr_ops nft_nat_inet_ops = {
+ .type = &nft_nat_type,
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_nat)),
+ .eval = nft_nat_inet_eval,
+ .init = nft_nat_init,
+ .destroy = nft_nat_destroy,
+ .dump = nft_nat_dump,
+ .validate = nft_nat_validate,
+};
+
+static struct nft_expr_type nft_inet_nat_type __read_mostly = {
+ .name = "nat",
+ .family = NFPROTO_INET,
+ .ops = &nft_nat_inet_ops,
+ .policy = nft_nat_policy,
+ .maxattr = NFTA_NAT_MAX,
+ .owner = THIS_MODULE,
+};
+
+static int nft_nat_inet_module_init(void)
+{
+ return nft_register_expr(&nft_inet_nat_type);
+}
+
+static void nft_nat_inet_module_exit(void)
+{
+ nft_unregister_expr(&nft_inet_nat_type);
+}
+#else
+static int nft_nat_inet_module_init(void) { return 0; }
+static void nft_nat_inet_module_exit(void) { }
+#endif
+
static int __init nft_nat_module_init(void)
{
- return nft_register_expr(&nft_nat_type);
+ int ret = nft_nat_inet_module_init();
+
+ if (ret)
+ return ret;
+
+ ret = nft_register_expr(&nft_nat_type);
+ if (ret)
+ nft_nat_inet_module_exit();
+
+ return ret;
}
static void __exit nft_nat_module_exit(void)
{
+ nft_nat_inet_module_exit();
nft_unregister_expr(&nft_nat_type);
}
struct nft_osf {
enum nft_registers dreg:8;
u8 ttl;
+ u32 flags;
};
static const struct nla_policy nft_osf_policy[NFTA_OSF_MAX + 1] = {
[NFTA_OSF_DREG] = { .type = NLA_U32 },
[NFTA_OSF_TTL] = { .type = NLA_U8 },
+ [NFTA_OSF_FLAGS] = { .type = NLA_U32 },
};
static void nft_osf_eval(const struct nft_expr *expr, struct nft_regs *regs,
struct nft_osf *priv = nft_expr_priv(expr);
u32 *dest = ®s->data[priv->dreg];
struct sk_buff *skb = pkt->skb;
+ char os_match[NFT_OSF_MAXGENRELEN + 1];
const struct tcphdr *tcp;
+ struct nf_osf_data data;
struct tcphdr _tcph;
- const char *os_name;
tcp = skb_header_pointer(skb, ip_hdrlen(skb),
sizeof(struct tcphdr), &_tcph);
return;
}
- os_name = nf_osf_find(skb, nf_osf_fingers, priv->ttl);
- if (!os_name)
+ if (!nf_osf_find(skb, nf_osf_fingers, priv->ttl, &data)) {
strncpy((char *)dest, "unknown", NFT_OSF_MAXGENRELEN);
- else
- strncpy((char *)dest, os_name, NFT_OSF_MAXGENRELEN);
+ } else {
+ if (priv->flags & NFT_OSF_F_VERSION)
+ snprintf(os_match, NFT_OSF_MAXGENRELEN, "%s:%s",
+ data.genre, data.version);
+ else
+ strlcpy(os_match, data.genre, NFT_OSF_MAXGENRELEN);
+
+ strncpy((char *)dest, os_match, NFT_OSF_MAXGENRELEN);
+ }
}
static int nft_osf_init(const struct nft_ctx *ctx,
const struct nlattr * const tb[])
{
struct nft_osf *priv = nft_expr_priv(expr);
+ u32 flags;
int err;
u8 ttl;
priv->ttl = ttl;
}
+ if (tb[NFTA_OSF_FLAGS]) {
+ flags = ntohl(nla_get_be32(tb[NFTA_OSF_FLAGS]));
+ if (flags != NFT_OSF_F_VERSION)
+ return -EINVAL;
+ priv->flags = flags;
+ }
+
priv->dreg = nft_parse_register(tb[NFTA_OSF_DREG]);
err = nft_validate_register_store(ctx, priv->dreg, NULL,
NFT_DATA_VALUE, NFT_OSF_MAXGENRELEN);
if (nla_put_u8(skb, NFTA_OSF_TTL, priv->ttl))
goto nla_put_failure;
+ if (nla_put_be32(skb, NFTA_OSF_FLAGS, ntohl(priv->flags)))
+ goto nla_put_failure;
+
if (nft_dump_register(skb, NFTA_OSF_DREG, priv->dreg))
goto nla_put_failure;
return nf_ct_netns_get(ctx->net, ctx->family);
}
-int nft_redir_dump(struct sk_buff *skb, const struct nft_expr *expr)
+static int nft_redir_dump(struct sk_buff *skb, const struct nft_expr *expr)
{
const struct nft_redir *priv = nft_expr_priv(expr);
};
#endif
+#ifdef CONFIG_NF_TABLES_INET
+static void nft_redir_inet_eval(const struct nft_expr *expr,
+ struct nft_regs *regs,
+ const struct nft_pktinfo *pkt)
+{
+ switch (nft_pf(pkt)) {
+ case NFPROTO_IPV4:
+ return nft_redir_ipv4_eval(expr, regs, pkt);
+ case NFPROTO_IPV6:
+ return nft_redir_ipv6_eval(expr, regs, pkt);
+ }
+
+ WARN_ON_ONCE(1);
+}
+
+static void
+nft_redir_inet_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
+{
+ nf_ct_netns_put(ctx->net, NFPROTO_INET);
+}
+
+static struct nft_expr_type nft_redir_inet_type;
+static const struct nft_expr_ops nft_redir_inet_ops = {
+ .type = &nft_redir_inet_type,
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_redir)),
+ .eval = nft_redir_inet_eval,
+ .init = nft_redir_init,
+ .destroy = nft_redir_inet_destroy,
+ .dump = nft_redir_dump,
+ .validate = nft_redir_validate,
+};
+
+static struct nft_expr_type nft_redir_inet_type __read_mostly = {
+ .family = NFPROTO_INET,
+ .name = "redir",
+ .ops = &nft_redir_inet_ops,
+ .policy = nft_redir_policy,
+ .maxattr = NFTA_MASQ_MAX,
+ .owner = THIS_MODULE,
+};
+
+static int __init nft_redir_module_init_inet(void)
+{
+ return nft_register_expr(&nft_redir_inet_type);
+}
+#else
+static inline int nft_redir_module_init_inet(void) { return 0; }
+#endif
+
static int __init nft_redir_module_init(void)
{
int ret = nft_register_expr(&nft_redir_ipv4_type);
}
#endif
+ ret = nft_redir_module_init_inet();
+ if (ret < 0) {
+ nft_unregister_expr(&nft_redir_ipv4_type);
+#ifdef CONFIG_NF_TABLES_IPV6
+ nft_unregister_expr(&nft_redir_ipv6_type);
+#endif
+ return ret;
+ }
+
return ret;
}
#ifdef CONFIG_NF_TABLES_IPV6
nft_unregister_expr(&nft_redir_ipv6_type);
#endif
+#ifdef CONFIG_NF_TABLES_INET
+ nft_unregister_expr(&nft_redir_inet_type);
+#endif
}
module_init(nft_redir_module_init);
EXPORT_SYMBOL_GPL(xt_request_find_match);
/* Find target, grabs ref. Returns ERR_PTR() on error. */
-struct xt_target *xt_find_target(u8 af, const char *name, u8 revision)
+static struct xt_target *xt_find_target(u8 af, const char *name, u8 revision)
{
struct xt_target *t;
int err = -ENOENT;
return ERR_PTR(err);
}
-EXPORT_SYMBOL(xt_find_target);
struct xt_target *xt_request_find_target(u8 af, const char *name, u8 revision)
{
* published by the Free Software Foundation.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-#include <linux/types.h>
-#include <linux/inetdevice.h>
-#include <linux/ip.h>
-#include <linux/timer.h>
#include <linux/module.h>
-#include <linux/netfilter.h>
-#include <net/protocol.h>
-#include <net/ip.h>
-#include <net/checksum.h>
-#include <net/route.h>
-#include <linux/netfilter_ipv4.h>
#include <linux/netfilter/x_tables.h>
#include <net/netfilter/nf_nat.h>
-#include <net/netfilter/ipv4/nf_nat_masquerade.h>
+#include <net/netfilter/nf_nat_masquerade.h>
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>");
nf_ct_netns_put(par->net, par->family);
}
-static struct xt_target masquerade_tg_reg __read_mostly = {
- .name = "MASQUERADE",
- .family = NFPROTO_IPV4,
- .target = masquerade_tg,
- .targetsize = sizeof(struct nf_nat_ipv4_multi_range_compat),
- .table = "nat",
- .hooks = 1 << NF_INET_POST_ROUTING,
- .checkentry = masquerade_tg_check,
- .destroy = masquerade_tg_destroy,
- .me = THIS_MODULE,
+#if IS_ENABLED(CONFIG_IPV6)
+static unsigned int
+masquerade_tg6(struct sk_buff *skb, const struct xt_action_param *par)
+{
+ return nf_nat_masquerade_ipv6(skb, par->targinfo, xt_out(par));
+}
+
+static int masquerade_tg6_checkentry(const struct xt_tgchk_param *par)
+{
+ const struct nf_nat_range2 *range = par->targinfo;
+
+ if (range->flags & NF_NAT_RANGE_MAP_IPS)
+ return -EINVAL;
+
+ return nf_ct_netns_get(par->net, par->family);
+}
+#endif
+
+static struct xt_target masquerade_tg_reg[] __read_mostly = {
+ {
+#if IS_ENABLED(CONFIG_IPV6)
+ .name = "MASQUERADE",
+ .family = NFPROTO_IPV6,
+ .target = masquerade_tg6,
+ .targetsize = sizeof(struct nf_nat_range),
+ .table = "nat",
+ .hooks = 1 << NF_INET_POST_ROUTING,
+ .checkentry = masquerade_tg6_checkentry,
+ .destroy = masquerade_tg_destroy,
+ .me = THIS_MODULE,
+ }, {
+#endif
+ .name = "MASQUERADE",
+ .family = NFPROTO_IPV4,
+ .target = masquerade_tg,
+ .targetsize = sizeof(struct nf_nat_ipv4_multi_range_compat),
+ .table = "nat",
+ .hooks = 1 << NF_INET_POST_ROUTING,
+ .checkentry = masquerade_tg_check,
+ .destroy = masquerade_tg_destroy,
+ .me = THIS_MODULE,
+ }
};
static int __init masquerade_tg_init(void)
{
int ret;
- ret = xt_register_target(&masquerade_tg_reg);
+ ret = xt_register_targets(masquerade_tg_reg,
+ ARRAY_SIZE(masquerade_tg_reg));
if (ret)
return ret;
- ret = nf_nat_masquerade_ipv4_register_notifier();
- if (ret)
- xt_unregister_target(&masquerade_tg_reg);
+ ret = nf_nat_masquerade_inet_register_notifiers();
+ if (ret) {
+ xt_unregister_targets(masquerade_tg_reg,
+ ARRAY_SIZE(masquerade_tg_reg));
+ return ret;
+ }
return ret;
}
static void __exit masquerade_tg_exit(void)
{
- xt_unregister_target(&masquerade_tg_reg);
- nf_nat_masquerade_ipv4_unregister_notifier();
+ xt_unregister_targets(masquerade_tg_reg, ARRAY_SIZE(masquerade_tg_reg));
+ nf_nat_masquerade_inet_unregister_notifiers();
}
module_init(masquerade_tg_init);
module_exit(masquerade_tg_exit);
+#if IS_ENABLED(CONFIG_IPV6)
+MODULE_ALIAS("ip6t_MASQUERADE");
+#endif
+MODULE_ALIAS("ipt_MASQUERADE");
struct netlink_sock *nlk = nlk_sk(sk);
struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr;
int err = 0;
- unsigned long groups = nladdr->nl_groups;
+ unsigned long groups;
bool bound;
if (addr_len < sizeof(struct sockaddr_nl))
if (nladdr->nl_family != AF_NETLINK)
return -EINVAL;
+ groups = nladdr->nl_groups;
/* Only superuser is allowed to listen multicasts */
if (groups) {
int i;
int rc = proto_register(&nr_proto, 0);
- if (rc != 0)
- goto out;
+ if (rc)
+ return rc;
if (nr_ndevs > 0x7fffffff/sizeof(struct net_device *)) {
- printk(KERN_ERR "NET/ROM: nr_proto_init - nr_ndevs parameter to large\n");
- return -1;
+ pr_err("NET/ROM: %s - nr_ndevs parameter too large\n",
+ __func__);
+ rc = -EINVAL;
+ goto unregister_proto;
}
dev_nr = kcalloc(nr_ndevs, sizeof(struct net_device *), GFP_KERNEL);
- if (dev_nr == NULL) {
- printk(KERN_ERR "NET/ROM: nr_proto_init - unable to allocate device array\n");
- return -1;
+ if (!dev_nr) {
+ pr_err("NET/ROM: %s - unable to allocate device array\n",
+ __func__);
+ rc = -ENOMEM;
+ goto unregister_proto;
}
for (i = 0; i < nr_ndevs; i++) {
sprintf(name, "nr%d", i);
dev = alloc_netdev(0, name, NET_NAME_UNKNOWN, nr_setup);
if (!dev) {
- printk(KERN_ERR "NET/ROM: nr_proto_init - unable to allocate device structure\n");
+ rc = -ENOMEM;
goto fail;
}
dev->base_addr = i;
- if (register_netdev(dev)) {
- printk(KERN_ERR "NET/ROM: nr_proto_init - unable to register network device\n");
+ rc = register_netdev(dev);
+ if (rc) {
free_netdev(dev);
goto fail;
}
dev_nr[i] = dev;
}
- if (sock_register(&nr_family_ops)) {
- printk(KERN_ERR "NET/ROM: nr_proto_init - unable to register socket family\n");
+ rc = sock_register(&nr_family_ops);
+ if (rc)
goto fail;
- }
- register_netdevice_notifier(&nr_dev_notifier);
+ rc = register_netdevice_notifier(&nr_dev_notifier);
+ if (rc)
+ goto out_sock;
ax25_register_pid(&nr_pid);
ax25_linkfail_register(&nr_linkfail_notifier);
#ifdef CONFIG_SYSCTL
- nr_register_sysctl();
+ rc = nr_register_sysctl();
+ if (rc)
+ goto out_sysctl;
#endif
nr_loopback_init();
- proc_create_seq("nr", 0444, init_net.proc_net, &nr_info_seqops);
- proc_create_seq("nr_neigh", 0444, init_net.proc_net, &nr_neigh_seqops);
- proc_create_seq("nr_nodes", 0444, init_net.proc_net, &nr_node_seqops);
-out:
- return rc;
+ rc = -ENOMEM;
+ if (!proc_create_seq("nr", 0444, init_net.proc_net, &nr_info_seqops))
+ goto proc_remove1;
+ if (!proc_create_seq("nr_neigh", 0444, init_net.proc_net,
+ &nr_neigh_seqops))
+ goto proc_remove2;
+ if (!proc_create_seq("nr_nodes", 0444, init_net.proc_net,
+ &nr_node_seqops))
+ goto proc_remove3;
+
+ return 0;
+
+proc_remove3:
+ remove_proc_entry("nr_neigh", init_net.proc_net);
+proc_remove2:
+ remove_proc_entry("nr", init_net.proc_net);
+proc_remove1:
+
+ nr_loopback_clear();
+ nr_rt_free();
+
+#ifdef CONFIG_SYSCTL
+ nr_unregister_sysctl();
+out_sysctl:
+#endif
+ ax25_linkfail_release(&nr_linkfail_notifier);
+ ax25_protocol_release(AX25_P_NETROM);
+ unregister_netdevice_notifier(&nr_dev_notifier);
+out_sock:
+ sock_unregister(PF_NETROM);
fail:
while (--i >= 0) {
unregister_netdev(dev_nr[i]);
free_netdev(dev_nr[i]);
}
kfree(dev_nr);
+unregister_proto:
proto_unregister(&nr_proto);
- rc = -1;
- goto out;
+ return rc;
}
module_init(nr_proto_init);
}
}
-void __exit nr_loopback_clear(void)
+void nr_loopback_clear(void)
{
del_timer_sync(&loopback_timer);
skb_queue_purge(&loopback_queue);
/*
* Free all memory associated with the nodes and routes lists.
*/
-void __exit nr_rt_free(void)
+void nr_rt_free(void)
{
struct nr_neigh *s = NULL;
struct nr_node *t = NULL;
{ }
};
-void __init nr_register_sysctl(void)
+int __init nr_register_sysctl(void)
{
nr_table_header = register_net_sysctl(&init_net, "net/netrom", nr_table);
+ if (!nr_table_header)
+ return -ENOMEM;
+ return 0;
}
void nr_unregister_sysctl(void)
create_info = (struct nci_hci_create_pipe_resp *)skb->data;
dest_gate = create_info->dest_gate;
new_pipe = create_info->pipe;
+ if (new_pipe >= NCI_HCI_MAX_PIPES) {
+ status = NCI_HCI_ANY_E_NOK;
+ goto exit;
+ }
/* Save the new created pipe and bind with local gate,
* the description for skb->data[3] is destination gate id
goto exit;
}
delete_info = (struct nci_hci_delete_pipe_noti *)skb->data;
+ if (delete_info->pipe >= NCI_HCI_MAX_PIPES) {
+ status = NCI_HCI_ANY_E_NOK;
+ goto exit;
+ }
ndev->hci_dev->pipes[delete_info->pipe].gate =
NCI_HCI_INVALID_GATE;
#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
#include <net/ipv6_frag.h>
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
#include <net/netfilter/nf_nat.h>
#endif
struct md_mark mark;
struct md_labels labels;
char timeout[CTNL_TIMEOUT_NAME_MAX];
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
struct nf_nat_range2 range; /* Only present for SRC NAT and DST NAT. */
#endif
};
return ct_executed;
}
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
/* Modelled after nf_nat_ipv[46]_fn().
* range is only used for new, uninitialized NAT state.
* Returns either NF_ACCEPT or NF_DROP.
return err;
}
-#else /* !CONFIG_NF_NAT_NEEDED */
+#else /* !CONFIG_NF_NAT */
static int ovs_ct_nat(struct net *net, struct sw_flow_key *key,
const struct ovs_conntrack_info *info,
struct sk_buff *skb, struct nf_conn *ct,
return 0;
}
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
static int parse_nat(const struct nlattr *attr,
struct ovs_conntrack_info *info, bool log)
{
.maxlen = sizeof(struct md_labels) },
[OVS_CT_ATTR_HELPER] = { .minlen = 1,
.maxlen = NF_CT_HELPER_NAME_LEN },
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
/* NAT length is checked when parsing the nested attributes. */
[OVS_CT_ATTR_NAT] = { .minlen = 0, .maxlen = INT_MAX },
#endif
return -EINVAL;
}
break;
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
case OVS_CT_ATTR_NAT: {
int err = parse_nat(a, info, log);
return err;
}
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
static bool ovs_ct_nat_to_attr(const struct ovs_conntrack_info *info,
struct sk_buff *skb)
{
return -EMSGSIZE;
}
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
if (ct_info->nat && !ovs_ct_nat_to_attr(ct_info, skb))
return -EMSGSIZE;
#endif
if (ct_info->helper)
nf_conntrack_helper_put(ct_info->helper);
if (ct_info->ct) {
- nf_ct_tmpl_free(ct_info->ct);
if (ct_info->timeout[0])
nf_ct_destroy_timeout(ct_info->ct);
+ nf_ct_tmpl_free(ct_info->ct);
}
}
struct sw_flow_actions *acts;
int new_acts_size;
- int req_size = NLA_ALIGN(attr_len);
+ size_t req_size = NLA_ALIGN(attr_len);
int next_offset = offsetof(struct sw_flow_actions, actions) +
(*sfa)->actions_len;
if (req_size <= (ksize(*sfa) - next_offset))
goto out;
- new_acts_size = ksize(*sfa) * 2;
+ new_acts_size = max(next_offset + req_size, ksize(*sfa) * 2);
if (new_acts_size > MAX_ACTIONS_BUFSIZE) {
if ((MAX_ACTIONS_BUFSIZE - next_offset) < req_size) {
struct rds_sock *rs = rds_sk_to_rs(sk);
int ret = 0;
+ if (addr_len < offsetofend(struct sockaddr, sa_family))
+ return -EINVAL;
+
lock_sock(sk);
switch (uaddr->sa_family) {
/* We allow an RDS socket to be bound to either IPv4 or IPv6
* address.
*/
+ if (addr_len < offsetofend(struct sockaddr, sa_family))
+ return -EINVAL;
if (uaddr->sa_family == AF_INET) {
struct sockaddr_in *sin = (struct sockaddr_in *)uaddr;
list_for_each_entry_safe(tc, _tc, &rds_tcp_conn_list, t_tcp_node) {
struct net *c_net = read_pnet(&tc->t_cpath->cp_conn->c_net);
- if (net != c_net || !tc->t_sock)
+ if (net != c_net)
continue;
if (!list_has_conn(&tmp_list, tc->t_cpath->cp_conn)) {
list_move_tail(&tc->t_tcp_node, &tmp_list);
struct sockaddr_rxrpc *srx = (struct sockaddr_rxrpc *)saddr;
struct rxrpc_local *local;
struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
- u16 service_id = srx->srx_service;
+ u16 service_id;
int ret;
_enter("%p,%p,%d", rx, saddr, len);
ret = rxrpc_validate_address(rx, srx, len);
if (ret < 0)
goto error;
+ service_id = srx->srx_service;
lock_sock(&rx->sk);
* rxrpc_kernel_check_life - Check to see whether a call is still alive
* @sock: The socket the call is on
* @call: The call to check
+ * @_life: Where to store the life value
*
* Allow a kernel service to find out whether a call is still alive - ie. we're
- * getting ACKs from the server. Returns a number representing the life state
- * which can be compared to that returned by a previous call.
+ * getting ACKs from the server. Passes back in *_life a number representing
+ * the life state which can be compared to that returned by a previous call and
+ * return true if the call is still alive.
*
* If the life state stalls, rxrpc_kernel_probe_life() should be called and
* then 2RTT waited.
*/
-u32 rxrpc_kernel_check_life(const struct socket *sock,
- const struct rxrpc_call *call)
+bool rxrpc_kernel_check_life(const struct socket *sock,
+ const struct rxrpc_call *call,
+ u32 *_life)
{
- return call->acks_latest;
+ *_life = call->acks_latest;
+ return call->state != RXRPC_CALL_COMPLETE;
}
EXPORT_SYMBOL(rxrpc_kernel_check_life);
u8 ackr_reason; /* reason to ACK */
u16 ackr_skew; /* skew on packet being ACK'd */
rxrpc_serial_t ackr_serial; /* serial of packet being ACK'd */
+ rxrpc_serial_t ackr_first_seq; /* first sequence number received */
rxrpc_seq_t ackr_prev_seq; /* previous sequence number received */
rxrpc_seq_t ackr_consumed; /* Highest packet shown consumed */
rxrpc_seq_t ackr_seen; /* Highest packet shown seen */
* pass a connection-level abort onto all calls on that connection
*/
static void rxrpc_abort_calls(struct rxrpc_connection *conn,
- enum rxrpc_call_completion compl)
+ enum rxrpc_call_completion compl,
+ rxrpc_serial_t serial)
{
struct rxrpc_call *call;
int i;
call->call_id, 0,
conn->abort_code,
conn->error);
+ else
+ trace_rxrpc_rx_abort(call, serial,
+ conn->abort_code);
if (rxrpc_set_call_completion(call, compl,
conn->abort_code,
conn->error))
conn->state = RXRPC_CONN_LOCALLY_ABORTED;
spin_unlock_bh(&conn->state_lock);
- rxrpc_abort_calls(conn, RXRPC_CALL_LOCALLY_ABORTED);
-
msg.msg_name = &conn->params.peer->srx.transport;
msg.msg_namelen = conn->params.peer->srx.transport_len;
msg.msg_control = NULL;
len = iov[0].iov_len + iov[1].iov_len;
serial = atomic_inc_return(&conn->serial);
+ rxrpc_abort_calls(conn, RXRPC_CALL_LOCALLY_ABORTED, serial);
whdr.serial = htonl(serial);
_proto("Tx CONN ABORT %%%u { %d }", serial, conn->abort_code);
conn->error = -ECONNABORTED;
conn->abort_code = abort_code;
conn->state = RXRPC_CONN_REMOTELY_ABORTED;
- rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED);
+ rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED, sp->hdr.serial);
return -ECONNABORTED;
case RXRPC_PACKET_TYPE_CHALLENGE:
u8 acks[RXRPC_MAXACKS];
} buf;
rxrpc_serial_t acked_serial;
- rxrpc_seq_t first_soft_ack, hard_ack;
+ rxrpc_seq_t first_soft_ack, hard_ack, prev_pkt;
int nr_acks, offset, ioffset;
_enter("");
acked_serial = ntohl(buf.ack.serial);
first_soft_ack = ntohl(buf.ack.firstPacket);
+ prev_pkt = ntohl(buf.ack.previousPacket);
hard_ack = first_soft_ack - 1;
nr_acks = buf.ack.nAcks;
summary.ack_reason = (buf.ack.reason < RXRPC_ACK__INVALID ?
buf.ack.reason : RXRPC_ACK__INVALID);
trace_rxrpc_rx_ack(call, sp->hdr.serial, acked_serial,
- first_soft_ack, ntohl(buf.ack.previousPacket),
+ first_soft_ack, prev_pkt,
summary.ack_reason, nr_acks);
if (buf.ack.reason == RXRPC_ACK_PING_RESPONSE)
rxrpc_propose_ack_respond_to_ack);
}
- /* Discard any out-of-order or duplicate ACKs. */
- if (before_eq(sp->hdr.serial, call->acks_latest))
+ /* Discard any out-of-order or duplicate ACKs (outside lock). */
+ if (before(first_soft_ack, call->ackr_first_seq) ||
+ before(prev_pkt, call->ackr_prev_seq))
return;
buf.info.rxMTU = 0;
spin_lock(&call->input_lock);
- /* Discard any out-of-order or duplicate ACKs. */
- if (before_eq(sp->hdr.serial, call->acks_latest))
+ /* Discard any out-of-order or duplicate ACKs (inside lock). */
+ if (before(first_soft_ack, call->ackr_first_seq) ||
+ before(prev_pkt, call->ackr_prev_seq))
goto out;
call->acks_latest_ts = skb->tstamp;
call->acks_latest = sp->hdr.serial;
+ call->ackr_first_seq = first_soft_ack;
+ call->ackr_prev_seq = prev_pkt;
+
/* Parse rwind and mtu sizes if provided. */
if (buf.info.rxMTU)
rxrpc_input_ackinfo(call, skb, &buf.info);
/* Fall through and set IPv4 options too otherwise we don't get
* errors from IPv4 packets sent through the IPv6 socket.
*/
-
+ /* Fall through */
case AF_INET:
/* we want to receive ICMP errors */
opt = 1;
_enter("%p{%d}", sk, local->debug_id);
+ /* Clear the outstanding error value on the socket so that it doesn't
+ * cause kernel_sendmsg() to return it later.
+ */
+ sock_error(sk);
+
skb = sock_dequeue_err_skb(sk);
if (!skb) {
_leave("UDP socket errqueue empty");
}
/*
- * Queue a DATA packet for transmission, set the resend timeout and send the
- * packet immediately
+ * Queue a DATA packet for transmission, set the resend timeout and send
+ * the packet immediately. Returns the error from rxrpc_send_data_packet()
+ * in case the caller wants to do something with it.
*/
-static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call,
- struct sk_buff *skb, bool last,
- rxrpc_notify_end_tx_t notify_end_tx)
+static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call,
+ struct sk_buff *skb, bool last,
+ rxrpc_notify_end_tx_t notify_end_tx)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
unsigned long now;
out:
rxrpc_free_skb(skb, rxrpc_skb_tx_freed);
- _leave("");
+ _leave(" = %d", ret);
+ return ret;
}
/*
if (ret < 0)
goto out;
- rxrpc_queue_packet(rx, call, skb,
- !msg_data_left(msg) && !more,
- notify_end_tx);
+ ret = rxrpc_queue_packet(rx, call, skb,
+ !msg_data_left(msg) && !more,
+ notify_end_tx);
+ /* Should check for failure here */
skb = NULL;
}
} while (msg_data_left(msg) > 0);
struct nlattr *tb[TCA_SAMPLE_MAX + 1];
struct psample_group *psample_group;
struct tcf_chain *goto_ch = NULL;
+ u32 psample_group_num, rate;
struct tc_sample *parm;
- u32 psample_group_num;
struct tcf_sample *s;
bool exists = false;
int ret, err;
if (err < 0)
goto release_idr;
+ rate = nla_get_u32(tb[TCA_SAMPLE_RATE]);
+ if (!rate) {
+ NL_SET_ERR_MSG(extack, "invalid sample rate");
+ err = -EINVAL;
+ goto put_chain;
+ }
psample_group_num = nla_get_u32(tb[TCA_SAMPLE_PSAMPLE_GROUP]);
psample_group = psample_group_get(net, psample_group_num);
if (!psample_group) {
spin_lock_bh(&s->tcf_lock);
goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
- s->rate = nla_get_u32(tb[TCA_SAMPLE_RATE]);
+ s->rate = rate;
s->psample_group_num = psample_group_num;
RCU_INIT_POINTER(s->psample_group, psample_group);
entry->tunnel = tcf_tunnel_info(act);
} else if (is_tcf_tunnel_release(act)) {
entry->id = FLOW_ACTION_TUNNEL_DECAP;
- entry->tunnel = tcf_tunnel_info(act);
} else if (is_tcf_pedit(act)) {
for (k = 0; k < tcf_pedit_nkeys(act); k++) {
switch (tcf_pedit_cmd(act, k)) {
fl_mask_free(mask);
}
-static bool fl_mask_put(struct cls_fl_head *head, struct fl_flow_mask *mask,
- bool async)
+static bool fl_mask_put(struct cls_fl_head *head, struct fl_flow_mask *mask)
{
if (!refcount_dec_and_test(&mask->refcnt))
return false;
list_del_rcu(&mask->list);
spin_unlock(&head->masks_lock);
- if (async)
- tcf_queue_work(&mask->rwork, fl_mask_free_work);
- else
- fl_mask_free(mask);
+ tcf_queue_work(&mask->rwork, fl_mask_free_work);
return true;
}
struct netlink_ext_ack *extack)
{
struct cls_fl_head *head = fl_head_dereference(tp);
- bool async = tcf_exts_get_net(&f->exts);
*last = false;
list_del_rcu(&f->list);
spin_unlock(&tp->lock);
- *last = fl_mask_put(head, f->mask, async);
+ *last = fl_mask_put(head, f->mask);
if (!tc_skip_hw(f->flags))
fl_hw_destroy_filter(tp, f, rtnl_held, extack);
tcf_unbind_filter(tp, &f->res);
return 0;
}
+static int fl_ht_insert_unique(struct cls_fl_filter *fnew,
+ struct cls_fl_filter *fold,
+ bool *in_ht)
+{
+ struct fl_flow_mask *mask = fnew->mask;
+ int err;
+
+ err = rhashtable_lookup_insert_fast(&mask->ht,
+ &fnew->ht_node,
+ mask->filter_ht_params);
+ if (err) {
+ *in_ht = false;
+ /* It is okay if filter with same key exists when
+ * overwriting.
+ */
+ return fold && err == -EEXIST ? 0 : err;
+ }
+
+ *in_ht = true;
+ return 0;
+}
+
static int fl_change(struct net *net, struct sk_buff *in_skb,
struct tcf_proto *tp, unsigned long base,
u32 handle, struct nlattr **tca,
struct cls_fl_filter *fnew;
struct fl_flow_mask *mask;
struct nlattr **tb;
+ bool in_ht;
int err;
if (!tca[TCA_OPTIONS]) {
if (err)
goto errout;
+ err = fl_ht_insert_unique(fnew, fold, &in_ht);
+ if (err)
+ goto errout_mask;
+
if (!tc_skip_hw(fnew->flags)) {
err = fl_hw_replace_filter(tp, fnew, rtnl_held, extack);
if (err)
- goto errout_mask;
+ goto errout_ht;
}
if (!tc_in_hw(fnew->flags))
fnew->handle = handle;
- err = rhashtable_insert_fast(&fnew->mask->ht, &fnew->ht_node,
- fnew->mask->filter_ht_params);
- if (err)
- goto errout_hw;
+ if (!in_ht) {
+ struct rhashtable_params params =
+ fnew->mask->filter_ht_params;
+
+ err = rhashtable_insert_fast(&fnew->mask->ht,
+ &fnew->ht_node,
+ params);
+ if (err)
+ goto errout_hw;
+ in_ht = true;
+ }
rhashtable_remove_fast(&fold->mask->ht,
&fold->ht_node,
spin_unlock(&tp->lock);
- fl_mask_put(head, fold->mask, true);
+ fl_mask_put(head, fold->mask);
if (!tc_skip_hw(fold->flags))
fl_hw_destroy_filter(tp, fold, rtnl_held, NULL);
tcf_unbind_filter(tp, &fold->res);
- tcf_exts_get_net(&fold->exts);
/* Caller holds reference to fold, so refcnt is always > 0
* after this.
*/
refcount_dec(&fold->refcnt);
__fl_put(fold);
} else {
- if (__fl_lookup(fnew->mask, &fnew->mkey)) {
- err = -EEXIST;
- goto errout_hw;
- }
-
if (handle) {
/* user specifies a handle and it doesn't exist */
err = idr_alloc_u32(&head->handle_idr, fnew, &handle,
goto errout_hw;
fnew->handle = handle;
-
- err = rhashtable_insert_fast(&fnew->mask->ht, &fnew->ht_node,
- fnew->mask->filter_ht_params);
- if (err)
- goto errout_idr;
-
list_add_tail_rcu(&fnew->list, &fnew->mask->filters);
spin_unlock(&tp->lock);
}
kfree(mask);
return 0;
-errout_idr:
- idr_remove(&head->handle_idr, fnew->handle);
errout_hw:
spin_unlock(&tp->lock);
if (!tc_skip_hw(fnew->flags))
fl_hw_destroy_filter(tp, fnew, rtnl_held, NULL);
+errout_ht:
+ if (in_ht)
+ rhashtable_remove_fast(&fnew->mask->ht, &fnew->ht_node,
+ fnew->mask->filter_ht_params);
errout_mask:
- fl_mask_put(head, fnew->mask, true);
+ fl_mask_put(head, fnew->mask);
errout:
- tcf_exts_destroy(&fnew->exts);
- kfree(fnew);
+ tcf_exts_get_net(&fnew->exts);
+ tcf_queue_work(&fnew->rwork, fl_destroy_filter_work);
errout_tb:
kfree(tb);
errout_mask_alloc:
static int fl_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb,
void *cb_priv, struct netlink_ext_ack *extack)
{
- struct cls_fl_head *head = fl_head_dereference(tp);
struct tc_cls_flower_offload cls_flower = {};
struct tcf_block *block = tp->chain->block;
- struct fl_flow_mask *mask;
+ unsigned long handle = 0;
struct cls_fl_filter *f;
int err;
- list_for_each_entry(mask, &head->masks, list) {
- list_for_each_entry(f, &mask->filters, list) {
- if (tc_skip_hw(f->flags))
- continue;
-
- cls_flower.rule =
- flow_rule_alloc(tcf_exts_num_actions(&f->exts));
- if (!cls_flower.rule)
- return -ENOMEM;
-
- tc_cls_common_offload_init(&cls_flower.common, tp,
- f->flags, extack);
- cls_flower.command = add ?
- TC_CLSFLOWER_REPLACE : TC_CLSFLOWER_DESTROY;
- cls_flower.cookie = (unsigned long)f;
- cls_flower.rule->match.dissector = &mask->dissector;
- cls_flower.rule->match.mask = &mask->key;
- cls_flower.rule->match.key = &f->mkey;
-
- err = tc_setup_flow_action(&cls_flower.rule->action,
- &f->exts);
- if (err) {
- kfree(cls_flower.rule);
- if (tc_skip_sw(f->flags)) {
- NL_SET_ERR_MSG_MOD(extack, "Failed to setup flow action");
- return err;
- }
- continue;
- }
+ while ((f = fl_get_next_filter(tp, &handle))) {
+ if (tc_skip_hw(f->flags))
+ goto next_flow;
- cls_flower.classid = f->res.classid;
+ cls_flower.rule =
+ flow_rule_alloc(tcf_exts_num_actions(&f->exts));
+ if (!cls_flower.rule) {
+ __fl_put(f);
+ return -ENOMEM;
+ }
- err = cb(TC_SETUP_CLSFLOWER, &cls_flower, cb_priv);
+ tc_cls_common_offload_init(&cls_flower.common, tp, f->flags,
+ extack);
+ cls_flower.command = add ?
+ TC_CLSFLOWER_REPLACE : TC_CLSFLOWER_DESTROY;
+ cls_flower.cookie = (unsigned long)f;
+ cls_flower.rule->match.dissector = &f->mask->dissector;
+ cls_flower.rule->match.mask = &f->mask->key;
+ cls_flower.rule->match.key = &f->mkey;
+
+ err = tc_setup_flow_action(&cls_flower.rule->action, &f->exts);
+ if (err) {
kfree(cls_flower.rule);
-
- if (err) {
- if (add && tc_skip_sw(f->flags))
- return err;
- continue;
+ if (tc_skip_sw(f->flags)) {
+ NL_SET_ERR_MSG_MOD(extack, "Failed to setup flow action");
+ __fl_put(f);
+ return err;
}
+ goto next_flow;
+ }
+
+ cls_flower.classid = f->res.classid;
- spin_lock(&tp->lock);
- tc_cls_offload_cnt_update(block, &f->in_hw_count,
- &f->flags, add);
- spin_unlock(&tp->lock);
+ err = cb(TC_SETUP_CLSFLOWER, &cls_flower, cb_priv);
+ kfree(cls_flower.rule);
+
+ if (err) {
+ if (add && tc_skip_sw(f->flags)) {
+ __fl_put(f);
+ return err;
+ }
+ goto next_flow;
}
+
+ spin_lock(&tp->lock);
+ tc_cls_offload_cnt_update(block, &f->in_hw_count, &f->flags,
+ add);
+ spin_unlock(&tp->lock);
+next_flow:
+ handle++;
+ __fl_put(f);
}
return 0;
static void *mall_get(struct tcf_proto *tp, u32 handle)
{
+ struct cls_mall_head *head = rtnl_dereference(tp->root);
+
+ if (head && head->handle == handle)
+ return head;
+
return NULL;
}
qdisc_put(old);
}
+static void qdisc_clear_nolock(struct Qdisc *sch)
+{
+ sch->flags &= ~TCQ_F_NOLOCK;
+ if (!(sch->flags & TCQ_F_CPUSTATS))
+ return;
+
+ free_percpu(sch->cpu_bstats);
+ free_percpu(sch->cpu_qstats);
+ sch->cpu_bstats = NULL;
+ sch->cpu_qstats = NULL;
+ sch->flags &= ~TCQ_F_CPUSTATS;
+}
+
/* Graft qdisc "new" to class "classid" of qdisc "parent" or
* to device "dev".
*
/* Only support running class lockless if parent is lockless */
if (new && (new->flags & TCQ_F_NOLOCK) &&
parent && !(parent->flags & TCQ_F_NOLOCK))
- new->flags &= ~TCQ_F_NOLOCK;
+ qdisc_clear_nolock(new);
if (!cops || !cops->graft)
return -EOPNOTSUPP;
static u8 cake_handle_diffserv(struct sk_buff *skb, u16 wash)
{
+ int wlen = skb_network_offset(skb);
u8 dscp;
- switch (skb->protocol) {
+ switch (tc_skb_protocol(skb)) {
case htons(ETH_P_IP):
+ wlen += sizeof(struct iphdr);
+ if (!pskb_may_pull(skb, wlen) ||
+ skb_try_make_writable(skb, wlen))
+ return 0;
+
dscp = ipv4_get_dsfield(ip_hdr(skb)) >> 2;
if (wash && dscp)
ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, 0);
return dscp;
case htons(ETH_P_IPV6):
+ wlen += sizeof(struct ipv6hdr);
+ if (!pskb_may_pull(skb, wlen) ||
+ skb_try_make_writable(skb, wlen))
+ return 0;
+
dscp = ipv6_get_dsfield(ipv6_hdr(skb)) >> 2;
if (wash && dscp)
ipv6_change_dsfield(ipv6_hdr(skb), INET_ECN_MASK, 0);
{
struct cbq_sched_data *q = qdisc_priv(sch);
struct cbq_class *cl = (struct cbq_class *)arg;
+ __u32 qlen;
cl->xstats.avgidle = cl->avgidle;
cl->xstats.undertime = 0;
+ qdisc_qstats_qlen_backlog(cl->q, &qlen, &cl->qstats.backlog);
if (cl->undertime != PSCHED_PASTPERFECT)
cl->xstats.undertime = cl->undertime - q->now;
if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
d, NULL, &cl->bstats) < 0 ||
gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 ||
- gnet_stats_copy_queue(d, NULL, &cl->qstats, cl->q->q.qlen) < 0)
+ gnet_stats_copy_queue(d, NULL, &cl->qstats, qlen) < 0)
return -1;
return gnet_stats_copy_app(d, &cl->xstats, sizeof(cl->xstats));
{
struct cbq_sched_data *q = qdisc_priv(sch);
struct cbq_class *cl = (struct cbq_class *)arg;
- unsigned int qlen, backlog;
if (cl->filters || cl->children || cl == &q->link)
return -EBUSY;
sch_tree_lock(sch);
- qlen = cl->q->q.qlen;
- backlog = cl->q->qstats.backlog;
- qdisc_reset(cl->q);
- qdisc_tree_reduce_backlog(cl->q, qlen, backlog);
+ qdisc_purge_queue(cl->q);
if (cl->next_alive)
cbq_deactivate_class(cl);
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/skbuff.h>
+#include <net/netevent.h>
#include <net/netlink.h>
#include <net/sch_generic.h>
#include <net/pkt_sched.h>
+static LIST_HEAD(cbs_list);
+static DEFINE_SPINLOCK(cbs_list_lock);
+
#define BYTES_PER_KBIT (1000LL / 8)
struct cbs_sched_data {
bool offload;
int queue;
- s64 port_rate; /* in bytes/s */
+ atomic64_t port_rate; /* in bytes/s */
s64 last; /* timestamp in ns */
s64 credits; /* in bytes */
s32 locredit; /* in bytes */
struct sk_buff **to_free);
struct sk_buff *(*dequeue)(struct Qdisc *sch);
struct Qdisc *qdisc;
+ struct list_head cbs_list;
};
static int cbs_child_enqueue(struct sk_buff *skb, struct Qdisc *sch,
s64 credits;
int len;
+ if (atomic64_read(&q->port_rate) == -1) {
+ WARN_ONCE(1, "cbs: dequeue() called with unknown port rate.");
+ return NULL;
+ }
+
if (q->credits < 0) {
credits = timediff_to_credits(now - q->last, q->idleslope);
/* As sendslope is a negative number, this will decrease the
* amount of q->credits.
*/
- credits = credits_from_len(len, q->sendslope, q->port_rate);
+ credits = credits_from_len(len, q->sendslope,
+ atomic64_read(&q->port_rate));
credits += q->credits;
q->credits = max_t(s64, credits, q->locredit);
return 0;
}
+static void cbs_set_port_rate(struct net_device *dev, struct cbs_sched_data *q)
+{
+ struct ethtool_link_ksettings ecmd;
+ int port_rate = -1;
+
+ if (!__ethtool_get_link_ksettings(dev, &ecmd) &&
+ ecmd.base.speed != SPEED_UNKNOWN)
+ port_rate = ecmd.base.speed * 1000 * BYTES_PER_KBIT;
+
+ atomic64_set(&q->port_rate, port_rate);
+ netdev_dbg(dev, "cbs: set %s's port_rate to: %lld, linkspeed: %d\n",
+ dev->name, (long long)atomic64_read(&q->port_rate),
+ ecmd.base.speed);
+}
+
+static int cbs_dev_notifier(struct notifier_block *nb, unsigned long event,
+ void *ptr)
+{
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+ struct cbs_sched_data *q;
+ struct net_device *qdev;
+ bool found = false;
+
+ ASSERT_RTNL();
+
+ if (event != NETDEV_UP && event != NETDEV_CHANGE)
+ return NOTIFY_DONE;
+
+ spin_lock(&cbs_list_lock);
+ list_for_each_entry(q, &cbs_list, cbs_list) {
+ qdev = qdisc_dev(q->qdisc);
+ if (qdev == dev) {
+ found = true;
+ break;
+ }
+ }
+ spin_unlock(&cbs_list_lock);
+
+ if (found)
+ cbs_set_port_rate(dev, q);
+
+ return NOTIFY_DONE;
+}
+
static int cbs_change(struct Qdisc *sch, struct nlattr *opt,
struct netlink_ext_ack *extack)
{
qopt = nla_data(tb[TCA_CBS_PARMS]);
if (!qopt->offload) {
- struct ethtool_link_ksettings ecmd;
- s64 link_speed;
-
- if (!__ethtool_get_link_ksettings(dev, &ecmd))
- link_speed = ecmd.base.speed;
- else
- link_speed = SPEED_1000;
-
- q->port_rate = link_speed * 1000 * BYTES_PER_KBIT;
-
+ cbs_set_port_rate(dev, q);
cbs_disable_offload(dev, q);
} else {
err = cbs_enable_offload(dev, q, qopt, extack);
{
struct cbs_sched_data *q = qdisc_priv(sch);
struct net_device *dev = qdisc_dev(sch);
+ int err;
if (!opt) {
NL_SET_ERR_MSG(extack, "Missing CBS qdisc options which are mandatory");
qdisc_watchdog_init(&q->watchdog, sch);
- return cbs_change(sch, opt, extack);
+ err = cbs_change(sch, opt, extack);
+ if (err)
+ return err;
+
+ if (!q->offload) {
+ spin_lock(&cbs_list_lock);
+ list_add(&q->cbs_list, &cbs_list);
+ spin_unlock(&cbs_list_lock);
+ }
+
+ return 0;
}
static void cbs_destroy(struct Qdisc *sch)
struct cbs_sched_data *q = qdisc_priv(sch);
struct net_device *dev = qdisc_dev(sch);
- qdisc_watchdog_cancel(&q->watchdog);
+ spin_lock(&cbs_list_lock);
+ list_del(&q->cbs_list);
+ spin_unlock(&cbs_list_lock);
+ qdisc_watchdog_cancel(&q->watchdog);
cbs_disable_offload(dev, q);
if (q->qdisc)
.owner = THIS_MODULE,
};
+static struct notifier_block cbs_device_notifier = {
+ .notifier_call = cbs_dev_notifier,
+};
+
static int __init cbs_module_init(void)
{
+ int err = register_netdevice_notifier(&cbs_device_notifier);
+
+ if (err)
+ return err;
+
return register_qdisc(&cbs_qdisc_ops);
}
static void __exit cbs_module_exit(void)
{
unregister_qdisc(&cbs_qdisc_ops);
+ unregister_netdevice_notifier(&cbs_device_notifier);
}
module_init(cbs_module_init)
module_exit(cbs_module_exit)
return container_of(clc, struct drr_class, common);
}
-static void drr_purge_queue(struct drr_class *cl)
-{
- unsigned int len = cl->qdisc->q.qlen;
- unsigned int backlog = cl->qdisc->qstats.backlog;
-
- qdisc_reset(cl->qdisc);
- qdisc_tree_reduce_backlog(cl->qdisc, len, backlog);
-}
-
static const struct nla_policy drr_policy[TCA_DRR_MAX + 1] = {
[TCA_DRR_QUANTUM] = { .type = NLA_U32 },
};
sch_tree_lock(sch);
- drr_purge_queue(cl);
+ qdisc_purge_queue(cl->qdisc);
qdisc_class_hash_remove(&q->clhash, &cl->common);
sch_tree_unlock(sch);
struct gnet_dump *d)
{
struct drr_class *cl = (struct drr_class *)arg;
- __u32 qlen = cl->qdisc->q.qlen;
+ __u32 qlen = qdisc_qlen_sum(cl->qdisc);
+ struct Qdisc *cl_q = cl->qdisc;
struct tc_drr_stats xstats;
memset(&xstats, 0, sizeof(xstats));
if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
d, NULL, &cl->bstats) < 0 ||
gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 ||
- gnet_stats_copy_queue(d, NULL, &cl->qdisc->qstats, qlen) < 0)
+ gnet_stats_copy_queue(d, cl_q->cpu_qstats, &cl_q->qstats, qlen) < 0)
return -1;
return gnet_stats_copy_app(d, &xstats, sizeof(xstats));
skb = __skb_dequeue(&q->skb_bad_txq);
if (qdisc_is_percpu_stats(q)) {
qdisc_qstats_cpu_backlog_dec(q, skb);
- qdisc_qstats_atomic_qlen_dec(q);
+ qdisc_qstats_cpu_qlen_dec(q);
} else {
qdisc_qstats_backlog_dec(q, skb);
q->q.qlen--;
if (qdisc_is_percpu_stats(q)) {
qdisc_qstats_cpu_backlog_inc(q, skb);
- qdisc_qstats_atomic_qlen_inc(q);
+ qdisc_qstats_cpu_qlen_inc(q);
} else {
qdisc_qstats_backlog_inc(q, skb);
q->q.qlen++;
spin_unlock(lock);
}
-static inline int __dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q)
+static inline void dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q)
{
- while (skb) {
- struct sk_buff *next = skb->next;
-
- __skb_queue_tail(&q->gso_skb, skb);
- q->qstats.requeues++;
- qdisc_qstats_backlog_inc(q, skb);
- q->q.qlen++; /* it's still part of the queue */
+ spinlock_t *lock = NULL;
- skb = next;
+ if (q->flags & TCQ_F_NOLOCK) {
+ lock = qdisc_lock(q);
+ spin_lock(lock);
}
- __netif_schedule(q);
-
- return 0;
-}
-static inline int dev_requeue_skb_locked(struct sk_buff *skb, struct Qdisc *q)
-{
- spinlock_t *lock = qdisc_lock(q);
-
- spin_lock(lock);
while (skb) {
struct sk_buff *next = skb->next;
__skb_queue_tail(&q->gso_skb, skb);
- qdisc_qstats_cpu_requeues_inc(q);
- qdisc_qstats_cpu_backlog_inc(q, skb);
- qdisc_qstats_atomic_qlen_inc(q);
+ /* it's still part of the queue */
+ if (qdisc_is_percpu_stats(q)) {
+ qdisc_qstats_cpu_requeues_inc(q);
+ qdisc_qstats_cpu_backlog_inc(q, skb);
+ qdisc_qstats_cpu_qlen_inc(q);
+ } else {
+ q->qstats.requeues++;
+ qdisc_qstats_backlog_inc(q, skb);
+ q->q.qlen++;
+ }
skb = next;
}
- spin_unlock(lock);
-
+ if (lock)
+ spin_unlock(lock);
__netif_schedule(q);
-
- return 0;
-}
-
-static inline int dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q)
-{
- if (q->flags & TCQ_F_NOLOCK)
- return dev_requeue_skb_locked(skb, q);
- else
- return __dev_requeue_skb(skb, q);
}
static void try_bulk_dequeue_skb(struct Qdisc *q,
skb = __skb_dequeue(&q->gso_skb);
if (qdisc_is_percpu_stats(q)) {
qdisc_qstats_cpu_backlog_dec(q, skb);
- qdisc_qstats_atomic_qlen_dec(q);
+ qdisc_qstats_cpu_qlen_dec(q);
} else {
qdisc_qstats_backlog_dec(q, skb);
q->q.qlen--;
if (unlikely(err))
return qdisc_drop_cpu(skb, qdisc, to_free);
- qdisc_qstats_atomic_qlen_inc(qdisc);
- /* Note: skb can not be used after skb_array_produce(),
- * so we better not use qdisc_qstats_cpu_backlog_inc()
- */
- this_cpu_add(qdisc->cpu_qstats->backlog, pkt_len);
+ qdisc_update_stats_at_enqueue(qdisc, pkt_len);
return NET_XMIT_SUCCESS;
}
skb = __skb_array_consume(q);
}
if (likely(skb)) {
- qdisc_qstats_cpu_backlog_dec(qdisc, skb);
- qdisc_bstats_cpu_update(qdisc, skb);
- qdisc_qstats_atomic_qlen_dec(qdisc);
+ qdisc_update_stats_at_dequeue(qdisc, skb);
} else {
qdisc->empty = true;
}
struct gnet_stats_queue *q = per_cpu_ptr(qdisc->cpu_qstats, i);
q->backlog = 0;
+ q->qlen = 0;
}
}
return len;
}
-static void
-hfsc_purge_queue(struct Qdisc *sch, struct hfsc_class *cl)
-{
- unsigned int len = cl->qdisc->q.qlen;
- unsigned int backlog = cl->qdisc->qstats.backlog;
-
- qdisc_reset(cl->qdisc);
- qdisc_tree_reduce_backlog(cl->qdisc, len, backlog);
-}
-
static void
hfsc_adjust_levels(struct hfsc_class *cl)
{
qdisc_class_hash_insert(&q->clhash, &cl->cl_common);
list_add_tail(&cl->siblings, &parent->children);
if (parent->level == 0)
- hfsc_purge_queue(sch, parent);
+ qdisc_purge_queue(parent->qdisc);
hfsc_adjust_levels(parent);
sch_tree_unlock(sch);
list_del(&cl->siblings);
hfsc_adjust_levels(cl->cl_parent);
- hfsc_purge_queue(sch, cl);
+ qdisc_purge_queue(cl->qdisc);
qdisc_class_hash_remove(&q->clhash, &cl->cl_common);
sch_tree_unlock(sch);
{
struct hfsc_class *cl = (struct hfsc_class *)arg;
struct tc_hfsc_stats xstats;
+ __u32 qlen;
- cl->qstats.backlog = cl->qdisc->qstats.backlog;
+ qdisc_qstats_qlen_backlog(cl->qdisc, &qlen, &cl->qstats.backlog);
xstats.level = cl->level;
xstats.period = cl->cl_vtperiod;
xstats.work = cl->cl_total;
if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), d, NULL, &cl->bstats) < 0 ||
gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 ||
- gnet_stats_copy_queue(d, NULL, &cl->qstats, cl->qdisc->q.qlen) < 0)
+ gnet_stats_copy_queue(d, NULL, &cl->qstats, qlen) < 0)
return -1;
return gnet_stats_copy_app(d, &xstats, sizeof(xstats));
};
__u32 qlen = 0;
- if (!cl->level && cl->leaf.q) {
- qlen = cl->leaf.q->q.qlen;
- qs.backlog = cl->leaf.q->qstats.backlog;
- }
+ if (!cl->level && cl->leaf.q)
+ qdisc_qstats_qlen_backlog(cl->leaf.q, &qlen, &qs.backlog);
+
cl->xstats.tokens = clamp_t(s64, PSCHED_NS2TICKS(cl->tokens),
INT_MIN, INT_MAX);
cl->xstats.ctokens = clamp_t(s64, PSCHED_NS2TICKS(cl->ctokens),
sch_tree_lock(sch);
- if (!cl->level) {
- unsigned int qlen = cl->leaf.q->q.qlen;
- unsigned int backlog = cl->leaf.q->qstats.backlog;
-
- qdisc_reset(cl->leaf.q);
- qdisc_tree_reduce_backlog(cl->leaf.q, qlen, backlog);
- }
+ if (!cl->level)
+ qdisc_purge_queue(cl->leaf.q);
/* delete from hash and active; remainder in destroy_class */
qdisc_class_hash_remove(&q->clhash, &cl->common);
classid, NULL);
sch_tree_lock(sch);
if (parent && !parent->level) {
- unsigned int qlen = parent->leaf.q->q.qlen;
- unsigned int backlog = parent->leaf.q->qstats.backlog;
-
/* turn parent into inner node */
- qdisc_reset(parent->leaf.q);
- qdisc_tree_reduce_backlog(parent->leaf.q, qlen, backlog);
+ qdisc_purge_queue(parent->leaf.q);
qdisc_put(parent->leaf.q);
if (parent->prio_activity)
htb_deactivate(q, parent);
sch = dev_queue->qdisc_sleeping;
if (gnet_stats_copy_basic(&sch->running, d, NULL, &sch->bstats) < 0 ||
- gnet_stats_copy_queue(d, NULL, &sch->qstats, sch->q.qlen) < 0)
+ qdisc_qstats_copy(d, sch) < 0)
return -1;
return 0;
}
sch = dev_queue->qdisc_sleeping;
if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
d, NULL, &sch->bstats) < 0 ||
- gnet_stats_copy_queue(d, NULL,
- &sch->qstats, sch->q.qlen) < 0)
+ qdisc_qstats_copy(d, sch) < 0)
return -1;
}
return 0;
for (i = q->bands; i < q->max_bands; i++) {
if (q->queues[i] != &noop_qdisc) {
struct Qdisc *child = q->queues[i];
+
q->queues[i] = &noop_qdisc;
- qdisc_tree_reduce_backlog(child, child->q.qlen,
- child->qstats.backlog);
+ qdisc_tree_flush_backlog(child);
qdisc_put(child);
}
}
qdisc_hash_add(child, true);
if (old != &noop_qdisc) {
- qdisc_tree_reduce_backlog(old,
- old->q.qlen,
- old->qstats.backlog);
+ qdisc_tree_flush_backlog(old);
qdisc_put(old);
}
sch_tree_unlock(sch);
cl_q = q->queues[cl - 1];
if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
d, NULL, &cl_q->bstats) < 0 ||
- gnet_stats_copy_queue(d, NULL, &cl_q->qstats, cl_q->q.qlen) < 0)
+ qdisc_qstats_copy(d, cl_q) < 0)
return -1;
return 0;
q->bands = qopt->bands;
memcpy(q->prio2band, qopt->priomap, TC_PRIO_MAX+1);
- for (i = q->bands; i < oldbands; i++) {
- struct Qdisc *child = q->queues[i];
-
- qdisc_tree_reduce_backlog(child, child->q.qlen,
- child->qstats.backlog);
- }
+ for (i = q->bands; i < oldbands; i++)
+ qdisc_tree_flush_backlog(q->queues[i]);
for (i = oldbands; i < q->bands; i++) {
q->queues[i] = queues[i];
cl_q = q->queues[cl - 1];
if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
d, NULL, &cl_q->bstats) < 0 ||
- gnet_stats_copy_queue(d, NULL, &cl_q->qstats, cl_q->q.qlen) < 0)
+ qdisc_qstats_copy(d, cl_q) < 0)
return -1;
return 0;
return container_of(clc, struct qfq_class, common);
}
-static void qfq_purge_queue(struct qfq_class *cl)
-{
- unsigned int len = cl->qdisc->q.qlen;
- unsigned int backlog = cl->qdisc->qstats.backlog;
-
- qdisc_reset(cl->qdisc);
- qdisc_tree_reduce_backlog(cl->qdisc, len, backlog);
-}
-
static const struct nla_policy qfq_policy[TCA_QFQ_MAX + 1] = {
[TCA_QFQ_WEIGHT] = { .type = NLA_U32 },
[TCA_QFQ_LMAX] = { .type = NLA_U32 },
sch_tree_lock(sch);
- qfq_purge_queue(cl);
+ qdisc_purge_queue(cl->qdisc);
qdisc_class_hash_remove(&q->clhash, &cl->common);
sch_tree_unlock(sch);
if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
d, NULL, &cl->bstats) < 0 ||
gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 ||
- gnet_stats_copy_queue(d, NULL,
- &cl->qdisc->qstats, cl->qdisc->q.qlen) < 0)
+ qdisc_qstats_copy(d, cl->qdisc) < 0)
return -1;
return gnet_stats_copy_app(d, &xstats, sizeof(xstats));
q->flags = ctl->flags;
q->limit = ctl->limit;
if (child) {
- qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen,
- q->qdisc->qstats.backlog);
+ qdisc_tree_flush_backlog(q->qdisc);
old_child = q->qdisc;
q->qdisc = child;
}
qdisc_hash_add(child, true);
sch_tree_lock(sch);
- qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen,
- q->qdisc->qstats.backlog);
+ qdisc_tree_flush_backlog(q->qdisc);
qdisc_put(q->qdisc);
q->qdisc = child;
#include <net/pkt_cls.h>
#include <net/sch_generic.h>
+static LIST_HEAD(taprio_list);
+static DEFINE_SPINLOCK(taprio_list_lock);
+
#define TAPRIO_ALL_GATES_OPEN -1
struct sched_entry {
struct Qdisc *root;
s64 base_time;
int clockid;
- int picos_per_byte; /* Using picoseconds because for 10Gbps+
- * speeds it's sub-nanoseconds per byte
- */
+ atomic64_t picos_per_byte; /* Using picoseconds because for 10Gbps+
+ * speeds it's sub-nanoseconds per byte
+ */
size_t num_entries;
/* Protects the update side of the RCU protected current_entry */
struct list_head entries;
ktime_t (*get_time)(void);
struct hrtimer advance_timer;
+ struct list_head taprio_list;
};
static int taprio_enqueue(struct sk_buff *skb, struct Qdisc *sch,
static inline int length_to_duration(struct taprio_sched *q, int len)
{
- return (len * q->picos_per_byte) / 1000;
+ return (len * atomic64_read(&q->picos_per_byte)) / 1000;
}
static struct sk_buff *taprio_dequeue(struct Qdisc *sch)
u32 gate_mask;
int i;
+ if (atomic64_read(&q->picos_per_byte) == -1) {
+ WARN_ONCE(1, "taprio: dequeue() called with unknown picos per byte.");
+ return NULL;
+ }
+
rcu_read_lock();
entry = rcu_dereference(q->current_entry);
/* if there's no entry, it means that the schedule didn't
next->close_time = close_time;
atomic_set(&next->budget,
- (next->interval * 1000) / q->picos_per_byte);
+ (next->interval * 1000) / atomic64_read(&q->picos_per_byte));
first_run:
rcu_assign_pointer(q->current_entry, next);
first->close_time = ktime_add_ns(start, first->interval);
atomic_set(&first->budget,
- (first->interval * 1000) / q->picos_per_byte);
+ (first->interval * 1000) /
+ atomic64_read(&q->picos_per_byte));
rcu_assign_pointer(q->current_entry, NULL);
spin_unlock_irqrestore(&q->current_entry_lock, flags);
hrtimer_start(&q->advance_timer, start, HRTIMER_MODE_ABS);
}
+static void taprio_set_picos_per_byte(struct net_device *dev,
+ struct taprio_sched *q)
+{
+ struct ethtool_link_ksettings ecmd;
+ int picos_per_byte = -1;
+
+ if (!__ethtool_get_link_ksettings(dev, &ecmd) &&
+ ecmd.base.speed != SPEED_UNKNOWN)
+ picos_per_byte = div64_s64(NSEC_PER_SEC * 1000LL * 8,
+ ecmd.base.speed * 1000 * 1000);
+
+ atomic64_set(&q->picos_per_byte, picos_per_byte);
+ netdev_dbg(dev, "taprio: set %s's picos_per_byte to: %lld, linkspeed: %d\n",
+ dev->name, (long long)atomic64_read(&q->picos_per_byte),
+ ecmd.base.speed);
+}
+
+static int taprio_dev_notifier(struct notifier_block *nb, unsigned long event,
+ void *ptr)
+{
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+ struct net_device *qdev;
+ struct taprio_sched *q;
+ bool found = false;
+
+ ASSERT_RTNL();
+
+ if (event != NETDEV_UP && event != NETDEV_CHANGE)
+ return NOTIFY_DONE;
+
+ spin_lock(&taprio_list_lock);
+ list_for_each_entry(q, &taprio_list, taprio_list) {
+ qdev = qdisc_dev(q->root);
+ if (qdev == dev) {
+ found = true;
+ break;
+ }
+ }
+ spin_unlock(&taprio_list_lock);
+
+ if (found)
+ taprio_set_picos_per_byte(dev, q);
+
+ return NOTIFY_DONE;
+}
+
static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
struct netlink_ext_ack *extack)
{
struct taprio_sched *q = qdisc_priv(sch);
struct net_device *dev = qdisc_dev(sch);
struct tc_mqprio_qopt *mqprio = NULL;
- struct ethtool_link_ksettings ecmd;
int i, err, size;
- s64 link_speed;
ktime_t start;
err = nla_parse_nested(tb, TCA_TAPRIO_ATTR_MAX, opt,
mqprio->prio_tc_map[i]);
}
- if (!__ethtool_get_link_ksettings(dev, &ecmd))
- link_speed = ecmd.base.speed;
- else
- link_speed = SPEED_1000;
-
- q->picos_per_byte = div64_s64(NSEC_PER_SEC * 1000LL * 8,
- link_speed * 1000 * 1000);
-
+ taprio_set_picos_per_byte(dev, q);
start = taprio_get_start_time(sch);
if (!start)
return 0;
struct sched_entry *entry, *n;
unsigned int i;
+ spin_lock(&taprio_list_lock);
+ list_del(&q->taprio_list);
+ spin_unlock(&taprio_list_lock);
+
hrtimer_cancel(&q->advance_timer);
if (q->qdiscs) {
if (!opt)
return -EINVAL;
+ spin_lock(&taprio_list_lock);
+ list_add(&q->taprio_list, &taprio_list);
+ spin_unlock(&taprio_list_lock);
+
return taprio_change(sch, opt, extack);
}
sch = dev_queue->qdisc_sleeping;
if (gnet_stats_copy_basic(&sch->running, d, NULL, &sch->bstats) < 0 ||
- gnet_stats_copy_queue(d, NULL, &sch->qstats, sch->q.qlen) < 0)
+ qdisc_qstats_copy(d, sch) < 0)
return -1;
return 0;
}
.owner = THIS_MODULE,
};
+static struct notifier_block taprio_device_notifier = {
+ .notifier_call = taprio_dev_notifier,
+};
+
static int __init taprio_module_init(void)
{
+ int err = register_netdevice_notifier(&taprio_device_notifier);
+
+ if (err)
+ return err;
+
return register_qdisc(&taprio_qdisc_ops);
}
static void __exit taprio_module_exit(void)
{
unregister_qdisc(&taprio_qdisc_ops);
+ unregister_netdevice_notifier(&taprio_device_notifier);
}
module_init(taprio_module_init);
sch_tree_lock(sch);
if (child) {
- qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen,
- q->qdisc->qstats.backlog);
+ qdisc_tree_flush_backlog(q->qdisc);
qdisc_put(q->qdisc);
q->qdisc = child;
}
static int sctp_v4_addr_to_user(struct sctp_sock *sp, union sctp_addr *addr)
{
/* No address mapping for V4 sockets */
+ memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero));
return sizeof(struct sockaddr_in);
}
* in sctp_ulpevent_make_rcvmsg will drop the frame if we grow our
* memory usage too much
*/
- if (*sk->sk_prot_creator->memory_pressure) {
+ if (sk_under_memory_pressure(sk)) {
if (sctp_tsnmap_has_gap(map) &&
(sctp_tsnmap_get_ctsn(map) + 1) == tsn) {
pr_debug("%s: under pressure, reneging for tsn:%u\n",
__func__, tsn);
deliver = SCTP_CMD_RENEGE;
- }
+ } else {
+ sk_mem_reclaim(sk);
+ }
}
/*
if (sctp_wspace(asoc) < (int)msg_len)
sctp_prsctp_prune(asoc, sinfo, msg_len - sctp_wspace(asoc));
- if (sctp_wspace(asoc) <= 0) {
+ if (sk_under_memory_pressure(sk))
+ sk_mem_reclaim(sk);
+
+ if (sctp_wspace(asoc) <= 0 || !sk_wmem_schedule(sk, msg_len)) {
timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
err = sctp_wait_for_sndbuf(asoc, &timeo, msg_len);
if (err)
}
/* Validate addr_len before calling common connect/connectx routine. */
- af = sctp_get_af_specific(addr->sa_family);
+ af = addr_len < offsetofend(struct sockaddr, sa_family) ? NULL :
+ sctp_get_af_specific(addr->sa_family);
if (!af || addr_len < af->sockaddr_len) {
err = -EINVAL;
} else {
goto do_error;
if (signal_pending(current))
goto do_interrupted;
- if ((int)msg_len <= sctp_wspace(asoc))
+ if (sk_under_memory_pressure(sk))
+ sk_mem_reclaim(sk);
+ if ((int)msg_len <= sctp_wspace(asoc) &&
+ sk_wmem_schedule(sk, msg_len))
break;
/* Let another process have a go. Since we are going
}
static int sctp_enqueue_event(struct sctp_ulpq *ulpq,
- struct sctp_ulpevent *event)
+ struct sk_buff_head *skb_list)
{
- struct sk_buff *skb = sctp_event2skb(event);
struct sock *sk = ulpq->asoc->base.sk;
struct sctp_sock *sp = sctp_sk(sk);
- struct sk_buff_head *skb_list;
+ struct sctp_ulpevent *event;
+ struct sk_buff *skb;
- skb_list = (struct sk_buff_head *)skb->prev;
+ skb = __skb_peek(skb_list);
+ event = sctp_skb2event(skb);
if (sk->sk_shutdown & RCV_SHUTDOWN &&
(sk->sk_shutdown & SEND_SHUTDOWN ||
if (!(event->msg_flags & SCTP_DATA_UNORDERED)) {
event = sctp_intl_reasm(ulpq, event);
- if (event && event->msg_flags & MSG_EOR) {
+ if (event) {
skb_queue_head_init(&temp);
__skb_queue_tail(&temp, sctp_event2skb(event));
- event = sctp_intl_order(ulpq, event);
+ if (event->msg_flags & MSG_EOR)
+ event = sctp_intl_order(ulpq, event);
}
} else {
event = sctp_intl_reasm_uo(ulpq, event);
+ if (event) {
+ skb_queue_head_init(&temp);
+ __skb_queue_tail(&temp, sctp_event2skb(event));
+ }
}
if (event) {
event_eor = (event->msg_flags & MSG_EOR) ? 1 : 0;
- sctp_enqueue_event(ulpq, event);
+ sctp_enqueue_event(ulpq, &temp);
}
return event_eor;
static void sctp_intl_start_pd(struct sctp_ulpq *ulpq, gfp_t gfp)
{
struct sctp_ulpevent *event;
+ struct sk_buff_head temp;
if (!skb_queue_empty(&ulpq->reasm)) {
do {
event = sctp_intl_retrieve_first(ulpq);
- if (event)
- sctp_enqueue_event(ulpq, event);
+ if (event) {
+ skb_queue_head_init(&temp);
+ __skb_queue_tail(&temp, sctp_event2skb(event));
+ sctp_enqueue_event(ulpq, &temp);
+ }
} while (event);
}
if (!skb_queue_empty(&ulpq->reasm_uo)) {
do {
event = sctp_intl_retrieve_first_uo(ulpq);
- if (event)
- sctp_enqueue_event(ulpq, event);
+ if (event) {
+ skb_queue_head_init(&temp);
+ __skb_queue_tail(&temp, sctp_event2skb(event));
+ sctp_enqueue_event(ulpq, &temp);
+ }
} while (event);
}
}
if (event) {
sctp_intl_retrieve_ordered(ulpq, event);
- sctp_enqueue_event(ulpq, event);
+ sctp_enqueue_event(ulpq, &temp);
}
}
ntohl(skip->mid), skip->flags);
}
+static int do_ulpq_tail_event(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event)
+{
+ struct sk_buff_head temp;
+
+ skb_queue_head_init(&temp);
+ __skb_queue_tail(&temp, sctp_event2skb(event));
+ return sctp_ulpq_tail_event(ulpq, &temp);
+}
+
static struct sctp_stream_interleave sctp_stream_interleave_0 = {
.data_chunk_len = sizeof(struct sctp_data_chunk),
.ftsn_chunk_len = sizeof(struct sctp_fwdtsn_chunk),
.assign_number = sctp_chunk_assign_ssn,
.validate_data = sctp_validate_data,
.ulpevent_data = sctp_ulpq_tail_data,
- .enqueue_event = sctp_ulpq_tail_event,
+ .enqueue_event = do_ulpq_tail_event,
.renege_events = sctp_ulpq_renege,
.start_pd = sctp_ulpq_partial_delivery,
.abort_pd = sctp_ulpq_abort_pd,
.handle_ftsn = sctp_handle_fwdtsn,
};
+static int do_sctp_enqueue_event(struct sctp_ulpq *ulpq,
+ struct sctp_ulpevent *event)
+{
+ struct sk_buff_head temp;
+
+ skb_queue_head_init(&temp);
+ __skb_queue_tail(&temp, sctp_event2skb(event));
+ return sctp_enqueue_event(ulpq, &temp);
+}
+
static struct sctp_stream_interleave sctp_stream_interleave_1 = {
.data_chunk_len = sizeof(struct sctp_idata_chunk),
.ftsn_chunk_len = sizeof(struct sctp_ifwdtsn_chunk),
.assign_number = sctp_chunk_assign_mid,
.validate_data = sctp_validate_idata,
.ulpevent_data = sctp_ulpevent_idata,
- .enqueue_event = sctp_enqueue_event,
+ .enqueue_event = do_sctp_enqueue_event,
.renege_events = sctp_renege_events,
.start_pd = sctp_intl_start_pd,
.abort_pd = sctp_intl_abort_pd,
gfp_t gfp)
{
struct sctp_ulpevent *event = NULL;
- struct sk_buff *skb;
- size_t padding, len;
+ struct sk_buff *skb = chunk->skb;
+ struct sock *sk = asoc->base.sk;
+ size_t padding, datalen;
int rx_count;
/*
if (asoc->ep->rcvbuf_policy)
rx_count = atomic_read(&asoc->rmem_alloc);
else
- rx_count = atomic_read(&asoc->base.sk->sk_rmem_alloc);
+ rx_count = atomic_read(&sk->sk_rmem_alloc);
- if (rx_count >= asoc->base.sk->sk_rcvbuf) {
+ datalen = ntohs(chunk->chunk_hdr->length);
- if ((asoc->base.sk->sk_userlocks & SOCK_RCVBUF_LOCK) ||
- (!sk_rmem_schedule(asoc->base.sk, chunk->skb,
- chunk->skb->truesize)))
- goto fail;
- }
+ if (rx_count >= sk->sk_rcvbuf || !sk_rmem_schedule(sk, skb, datalen))
+ goto fail;
/* Clone the original skb, sharing the data. */
skb = skb_clone(chunk->skb, gfp);
* The sender should never pad with more than 3 bytes. The receiver
* MUST ignore the padding bytes.
*/
- len = ntohs(chunk->chunk_hdr->length);
- padding = SCTP_PAD4(len) - len;
+ padding = SCTP_PAD4(datalen) - datalen;
/* Fixup cloned skb with just this chunks data. */
skb_trim(skb, chunk->chunk_end - padding - skb->data);
event = sctp_ulpq_reasm(ulpq, event);
/* Do ordering if needed. */
- if ((event) && (event->msg_flags & MSG_EOR)) {
+ if (event) {
/* Create a temporary list to collect chunks on. */
skb_queue_head_init(&temp);
__skb_queue_tail(&temp, sctp_event2skb(event));
- event = sctp_ulpq_order(ulpq, event);
+ if (event->msg_flags & MSG_EOR)
+ event = sctp_ulpq_order(ulpq, event);
}
/* Send event to the ULP. 'event' is the sctp_ulpevent for
*/
if (event) {
event_eor = (event->msg_flags & MSG_EOR) ? 1 : 0;
- sctp_ulpq_tail_event(ulpq, event);
+ sctp_ulpq_tail_event(ulpq, &temp);
}
return event_eor;
return sctp_clear_pd(ulpq->asoc->base.sk, ulpq->asoc);
}
-/* If the SKB of 'event' is on a list, it is the first such member
- * of that list.
- */
-int sctp_ulpq_tail_event(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event)
+int sctp_ulpq_tail_event(struct sctp_ulpq *ulpq, struct sk_buff_head *skb_list)
{
struct sock *sk = ulpq->asoc->base.sk;
struct sctp_sock *sp = sctp_sk(sk);
- struct sk_buff_head *queue, *skb_list;
- struct sk_buff *skb = sctp_event2skb(event);
+ struct sctp_ulpevent *event;
+ struct sk_buff_head *queue;
+ struct sk_buff *skb;
int clear_pd = 0;
- skb_list = (struct sk_buff_head *) skb->prev;
+ skb = __skb_peek(skb_list);
+ event = sctp_skb2event(skb);
/* If the socket is just going to throw this away, do not
* even try to deliver it.
}
}
- /* If we are harvesting multiple skbs they will be
- * collected on a list.
- */
- if (skb_list)
- skb_queue_splice_tail_init(skb_list, queue);
- else
- __skb_queue_tail(queue, skb);
+ skb_queue_splice_tail_init(skb_list, queue);
/* Did we just complete partial delivery and need to get
* rolling again? Move pending data to the receive
static void sctp_ulpq_reasm_drain(struct sctp_ulpq *ulpq)
{
struct sctp_ulpevent *event = NULL;
- struct sk_buff_head temp;
if (skb_queue_empty(&ulpq->reasm))
return;
while ((event = sctp_ulpq_retrieve_reassembled(ulpq)) != NULL) {
- /* Do ordering if needed. */
- if ((event) && (event->msg_flags & MSG_EOR)) {
- skb_queue_head_init(&temp);
- __skb_queue_tail(&temp, sctp_event2skb(event));
+ struct sk_buff_head temp;
+
+ skb_queue_head_init(&temp);
+ __skb_queue_tail(&temp, sctp_event2skb(event));
+ /* Do ordering if needed. */
+ if (event->msg_flags & MSG_EOR)
event = sctp_ulpq_order(ulpq, event);
- }
/* Send event to the ULP. 'event' is the
* sctp_ulpevent for very first SKB on the temp' list.
*/
if (event)
- sctp_ulpq_tail_event(ulpq, event);
+ sctp_ulpq_tail_event(ulpq, &temp);
}
}
if (event) {
/* see if we have more ordered that we can deliver */
sctp_ulpq_retrieve_ordered(ulpq, event);
- sctp_ulpq_tail_event(ulpq, event);
+ sctp_ulpq_tail_event(ulpq, &temp);
}
}
event = sctp_ulpq_retrieve_first(ulpq);
/* Send event to the ULP. */
if (event) {
- sctp_ulpq_tail_event(ulpq, event);
+ struct sk_buff_head temp;
+
+ skb_queue_head_init(&temp);
+ __skb_queue_tail(&temp, sctp_event2skb(event));
+ sctp_ulpq_tail_event(ulpq, &temp);
sctp_ulpq_set_pd(ulpq);
return;
}
freed += sctp_ulpq_renege_frags(ulpq, needed - freed);
}
/* If able to free enough room, accept this chunk. */
- if (freed >= needed) {
+ if (sk_rmem_schedule(asoc->base.sk, chunk->skb, needed) &&
+ freed >= needed) {
int retval = sctp_ulpq_tail_data(ulpq, chunk, gfp);
/*
* Enter partial delivery if chunk has not been
smc = smc_sk(sk);
/* cleanup for a dangling non-blocking connect */
- if (smc->connect_info && sk->sk_state == SMC_INIT)
+ if (smc->connect_nonblock && sk->sk_state == SMC_INIT)
tcp_abort(smc->clcsock->sk, ECONNABORTED);
flush_work(&smc->connect_work);
- kfree(smc->connect_info);
- smc->connect_info = NULL;
if (sk->sk_state == SMC_LISTEN)
/* smc_close_non_accepted() is called and acquires
if (sk->sk_state == SMC_CLOSED) {
if (smc->clcsock) {
- mutex_lock(&smc->clcsock_release_lock);
- sock_release(smc->clcsock);
- smc->clcsock = NULL;
- mutex_unlock(&smc->clcsock_release_lock);
+ release_sock(sk);
+ smc_clcsock_release(smc);
+ lock_sock(sk);
}
if (!smc->use_fallback)
smc_conn_free(&smc->conn);
link->peer_mtu = clc->qp_mtu;
}
+static void smc_switch_to_fallback(struct smc_sock *smc)
+{
+ smc->use_fallback = true;
+ if (smc->sk.sk_socket && smc->sk.sk_socket->file) {
+ smc->clcsock->file = smc->sk.sk_socket->file;
+ smc->clcsock->file->private_data = smc->clcsock;
+ }
+}
+
/* fall back during connect */
static int smc_connect_fallback(struct smc_sock *smc, int reason_code)
{
- smc->use_fallback = true;
+ smc_switch_to_fallback(smc);
smc->fallback_rsn = reason_code;
smc_copy_sock_settings_to_clc(smc);
+ smc->connect_nonblock = 0;
if (smc->sk.sk_state == SMC_INIT)
smc->sk.sk_state = SMC_ACTIVE;
return 0;
mutex_unlock(&smc_client_lgr_pending);
smc_conn_free(&smc->conn);
+ smc->connect_nonblock = 0;
return reason_code;
}
/* check if there is a rdma device available for this connection. */
/* called for connect and listen */
-static int smc_check_rdma(struct smc_sock *smc, struct smc_ib_device **ibdev,
- u8 *ibport, unsigned short vlan_id, u8 gid[])
+static int smc_find_rdma_device(struct smc_sock *smc, struct smc_init_info *ini)
{
- int reason_code = 0;
-
/* PNET table look up: search active ib_device and port
* within same PNETID that also contains the ethernet device
* used for the internal TCP socket
*/
- smc_pnet_find_roce_resource(smc->clcsock->sk, ibdev, ibport, vlan_id,
- gid);
- if (!(*ibdev))
- reason_code = SMC_CLC_DECL_CNFERR; /* configuration error */
-
- return reason_code;
+ smc_pnet_find_roce_resource(smc->clcsock->sk, ini);
+ if (!ini->ib_dev)
+ return SMC_CLC_DECL_NOSMCRDEV;
+ return 0;
}
/* check if there is an ISM device available for this connection. */
/* called for connect and listen */
-static int smc_check_ism(struct smc_sock *smc, struct smcd_dev **ismdev)
+static int smc_find_ism_device(struct smc_sock *smc, struct smc_init_info *ini)
{
/* Find ISM device with same PNETID as connecting interface */
- smc_pnet_find_ism_resource(smc->clcsock->sk, ismdev);
- if (!(*ismdev))
- return SMC_CLC_DECL_CNFERR; /* configuration error */
+ smc_pnet_find_ism_resource(smc->clcsock->sk, ini);
+ if (!ini->ism_dev)
+ return SMC_CLC_DECL_NOSMCDDEV;
return 0;
}
/* Check for VLAN ID and register it on ISM device just for CLC handshake */
static int smc_connect_ism_vlan_setup(struct smc_sock *smc,
- struct smcd_dev *ismdev,
- unsigned short vlan_id)
+ struct smc_init_info *ini)
{
- if (vlan_id && smc_ism_get_vlan(ismdev, vlan_id))
- return SMC_CLC_DECL_CNFERR;
+ if (ini->vlan_id && smc_ism_get_vlan(ini->ism_dev, ini->vlan_id))
+ return SMC_CLC_DECL_ISMVLANERR;
return 0;
}
* used, the VLAN ID will be registered again during the connection setup.
*/
static int smc_connect_ism_vlan_cleanup(struct smc_sock *smc, bool is_smcd,
- struct smcd_dev *ismdev,
- unsigned short vlan_id)
+ struct smc_init_info *ini)
{
if (!is_smcd)
return 0;
- if (vlan_id && smc_ism_put_vlan(ismdev, vlan_id))
+ if (ini->vlan_id && smc_ism_put_vlan(ini->ism_dev, ini->vlan_id))
return SMC_CLC_DECL_CNFERR;
return 0;
}
/* CLC handshake during connect */
static int smc_connect_clc(struct smc_sock *smc, int smc_type,
struct smc_clc_msg_accept_confirm *aclc,
- struct smc_ib_device *ibdev, u8 ibport,
- u8 gid[], struct smcd_dev *ismdev)
+ struct smc_init_info *ini)
{
int rc = 0;
/* do inband token exchange */
- rc = smc_clc_send_proposal(smc, smc_type, ibdev, ibport, gid, ismdev);
+ rc = smc_clc_send_proposal(smc, smc_type, ini);
if (rc)
return rc;
/* receive SMC Accept CLC message */
/* setup for RDMA connection of client */
static int smc_connect_rdma(struct smc_sock *smc,
struct smc_clc_msg_accept_confirm *aclc,
- struct smc_ib_device *ibdev, u8 ibport)
+ struct smc_init_info *ini)
{
- int local_contact = SMC_FIRST_CONTACT;
struct smc_link *link;
int reason_code = 0;
+ ini->is_smcd = false;
+ ini->ib_lcl = &aclc->lcl;
+ ini->ib_clcqpn = ntoh24(aclc->qpn);
+ ini->srv_first_contact = aclc->hdr.flag;
+
mutex_lock(&smc_client_lgr_pending);
- local_contact = smc_conn_create(smc, false, aclc->hdr.flag, ibdev,
- ibport, ntoh24(aclc->qpn), &aclc->lcl,
- NULL, 0);
- if (local_contact < 0) {
- if (local_contact == -ENOMEM)
- reason_code = SMC_CLC_DECL_MEM;/* insufficient memory*/
- else if (local_contact == -ENOLINK)
- reason_code = SMC_CLC_DECL_SYNCERR; /* synchr. error */
- else
- reason_code = SMC_CLC_DECL_INTERR; /* other error */
+ reason_code = smc_conn_create(smc, ini);
+ if (reason_code) {
mutex_unlock(&smc_client_lgr_pending);
return reason_code;
}
/* create send buffer and rmb */
if (smc_buf_create(smc, false))
- return smc_connect_abort(smc, SMC_CLC_DECL_MEM, local_contact);
+ return smc_connect_abort(smc, SMC_CLC_DECL_MEM,
+ ini->cln_first_contact);
- if (local_contact == SMC_FIRST_CONTACT)
+ if (ini->cln_first_contact == SMC_FIRST_CONTACT)
smc_link_save_peer_info(link, aclc);
if (smc_rmb_rtoken_handling(&smc->conn, aclc))
return smc_connect_abort(smc, SMC_CLC_DECL_ERR_RTOK,
- local_contact);
+ ini->cln_first_contact);
smc_close_init(smc);
smc_rx_init(smc);
- if (local_contact == SMC_FIRST_CONTACT) {
+ if (ini->cln_first_contact == SMC_FIRST_CONTACT) {
if (smc_ib_ready_link(link))
return smc_connect_abort(smc, SMC_CLC_DECL_ERR_RDYLNK,
- local_contact);
+ ini->cln_first_contact);
} else {
if (smc_reg_rmb(link, smc->conn.rmb_desc, true))
return smc_connect_abort(smc, SMC_CLC_DECL_ERR_REGRMB,
- local_contact);
+ ini->cln_first_contact);
}
smc_rmb_sync_sg_for_device(&smc->conn);
reason_code = smc_clc_send_confirm(smc);
if (reason_code)
- return smc_connect_abort(smc, reason_code, local_contact);
+ return smc_connect_abort(smc, reason_code,
+ ini->cln_first_contact);
smc_tx_init(smc);
- if (local_contact == SMC_FIRST_CONTACT) {
+ if (ini->cln_first_contact == SMC_FIRST_CONTACT) {
/* QP confirmation over RoCE fabric */
reason_code = smc_clnt_conf_first_link(smc);
if (reason_code)
return smc_connect_abort(smc, reason_code,
- local_contact);
+ ini->cln_first_contact);
}
mutex_unlock(&smc_client_lgr_pending);
smc_copy_sock_settings_to_clc(smc);
+ smc->connect_nonblock = 0;
if (smc->sk.sk_state == SMC_INIT)
smc->sk.sk_state = SMC_ACTIVE;
/* setup for ISM connection of client */
static int smc_connect_ism(struct smc_sock *smc,
struct smc_clc_msg_accept_confirm *aclc,
- struct smcd_dev *ismdev)
+ struct smc_init_info *ini)
{
- int local_contact = SMC_FIRST_CONTACT;
int rc = 0;
+ ini->is_smcd = true;
+ ini->ism_gid = aclc->gid;
+ ini->srv_first_contact = aclc->hdr.flag;
+
/* there is only one lgr role for SMC-D; use server lock */
mutex_lock(&smc_server_lgr_pending);
- local_contact = smc_conn_create(smc, true, aclc->hdr.flag, NULL, 0, 0,
- NULL, ismdev, aclc->gid);
- if (local_contact < 0) {
+ rc = smc_conn_create(smc, ini);
+ if (rc) {
mutex_unlock(&smc_server_lgr_pending);
- return SMC_CLC_DECL_MEM;
+ return rc;
}
/* Create send and receive buffers */
if (smc_buf_create(smc, true))
- return smc_connect_abort(smc, SMC_CLC_DECL_MEM, local_contact);
+ return smc_connect_abort(smc, SMC_CLC_DECL_MEM,
+ ini->cln_first_contact);
smc_conn_save_peer_info(smc, aclc);
smc_close_init(smc);
rc = smc_clc_send_confirm(smc);
if (rc)
- return smc_connect_abort(smc, rc, local_contact);
+ return smc_connect_abort(smc, rc, ini->cln_first_contact);
mutex_unlock(&smc_server_lgr_pending);
smc_copy_sock_settings_to_clc(smc);
+ smc->connect_nonblock = 0;
if (smc->sk.sk_state == SMC_INIT)
smc->sk.sk_state = SMC_ACTIVE;
{
bool ism_supported = false, rdma_supported = false;
struct smc_clc_msg_accept_confirm aclc;
- struct smc_ib_device *ibdev;
- struct smcd_dev *ismdev;
- u8 gid[SMC_GID_SIZE];
- unsigned short vlan;
+ struct smc_init_info ini = {0};
int smc_type;
int rc = 0;
- u8 ibport;
sock_hold(&smc->sk); /* sock put in passive closing */
if (using_ipsec(smc))
return smc_connect_decline_fallback(smc, SMC_CLC_DECL_IPSEC);
- /* check for VLAN ID */
- if (smc_vlan_by_tcpsk(smc->clcsock, &vlan))
- return smc_connect_decline_fallback(smc, SMC_CLC_DECL_CNFERR);
+ /* get vlan id from IP device */
+ if (smc_vlan_by_tcpsk(smc->clcsock, &ini))
+ return smc_connect_decline_fallback(smc,
+ SMC_CLC_DECL_GETVLANERR);
/* check if there is an ism device available */
- if (!smc_check_ism(smc, &ismdev) &&
- !smc_connect_ism_vlan_setup(smc, ismdev, vlan)) {
+ if (!smc_find_ism_device(smc, &ini) &&
+ !smc_connect_ism_vlan_setup(smc, &ini)) {
/* ISM is supported for this connection */
ism_supported = true;
smc_type = SMC_TYPE_D;
}
/* check if there is a rdma device available */
- if (!smc_check_rdma(smc, &ibdev, &ibport, vlan, gid)) {
+ if (!smc_find_rdma_device(smc, &ini)) {
/* RDMA is supported for this connection */
rdma_supported = true;
if (ism_supported)
return smc_connect_decline_fallback(smc, SMC_CLC_DECL_NOSMCDEV);
/* perform CLC handshake */
- rc = smc_connect_clc(smc, smc_type, &aclc, ibdev, ibport, gid, ismdev);
+ rc = smc_connect_clc(smc, smc_type, &aclc, &ini);
if (rc) {
- smc_connect_ism_vlan_cleanup(smc, ism_supported, ismdev, vlan);
+ smc_connect_ism_vlan_cleanup(smc, ism_supported, &ini);
return smc_connect_decline_fallback(smc, rc);
}
/* depending on previous steps, connect using rdma or ism */
if (rdma_supported && aclc.hdr.path == SMC_TYPE_R)
- rc = smc_connect_rdma(smc, &aclc, ibdev, ibport);
+ rc = smc_connect_rdma(smc, &aclc, &ini);
else if (ism_supported && aclc.hdr.path == SMC_TYPE_D)
- rc = smc_connect_ism(smc, &aclc, ismdev);
+ rc = smc_connect_ism(smc, &aclc, &ini);
else
rc = SMC_CLC_DECL_MODEUNSUPP;
if (rc) {
- smc_connect_ism_vlan_cleanup(smc, ism_supported, ismdev, vlan);
+ smc_connect_ism_vlan_cleanup(smc, ism_supported, &ini);
return smc_connect_decline_fallback(smc, rc);
}
- smc_connect_ism_vlan_cleanup(smc, ism_supported, ismdev, vlan);
+ smc_connect_ism_vlan_cleanup(smc, ism_supported, &ini);
return 0;
}
{
struct smc_sock *smc = container_of(work, struct smc_sock,
connect_work);
- int rc;
+ long timeo = smc->sk.sk_sndtimeo;
+ int rc = 0;
- lock_sock(&smc->sk);
- rc = kernel_connect(smc->clcsock, &smc->connect_info->addr,
- smc->connect_info->alen, smc->connect_info->flags);
+ if (!timeo)
+ timeo = MAX_SCHEDULE_TIMEOUT;
+ lock_sock(smc->clcsock->sk);
if (smc->clcsock->sk->sk_err) {
smc->sk.sk_err = smc->clcsock->sk->sk_err;
- goto out;
- }
- if (rc < 0) {
- smc->sk.sk_err = -rc;
+ } else if ((1 << smc->clcsock->sk->sk_state) &
+ (TCPF_SYN_SENT | TCP_SYN_RECV)) {
+ rc = sk_stream_wait_connect(smc->clcsock->sk, &timeo);
+ if ((rc == -EPIPE) &&
+ ((1 << smc->clcsock->sk->sk_state) &
+ (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)))
+ rc = 0;
+ }
+ release_sock(smc->clcsock->sk);
+ lock_sock(&smc->sk);
+ if (rc != 0 || smc->sk.sk_err) {
+ smc->sk.sk_state = SMC_CLOSED;
+ if (rc == -EPIPE || rc == -EAGAIN)
+ smc->sk.sk_err = EPIPE;
+ else if (signal_pending(current))
+ smc->sk.sk_err = -sock_intr_errno(timeo);
goto out;
}
smc->sk.sk_err = -rc;
out:
- if (smc->sk.sk_err)
- smc->sk.sk_state_change(&smc->sk);
- else
- smc->sk.sk_write_space(&smc->sk);
- kfree(smc->connect_info);
- smc->connect_info = NULL;
+ if (!sock_flag(&smc->sk, SOCK_DEAD)) {
+ if (smc->sk.sk_err) {
+ smc->sk.sk_state_change(&smc->sk);
+ } else { /* allow polling before and after fallback decision */
+ smc->clcsock->sk->sk_write_space(smc->clcsock->sk);
+ smc->sk.sk_write_space(&smc->sk);
+ }
+ }
release_sock(&smc->sk);
}
smc_copy_sock_settings_to_clc(smc);
tcp_sk(smc->clcsock->sk)->syn_smc = 1;
+ if (smc->connect_nonblock) {
+ rc = -EALREADY;
+ goto out;
+ }
+ rc = kernel_connect(smc->clcsock, addr, alen, flags);
+ if (rc && rc != -EINPROGRESS)
+ goto out;
if (flags & O_NONBLOCK) {
- if (smc->connect_info) {
- rc = -EALREADY;
- goto out;
- }
- smc->connect_info = kzalloc(alen + 2 * sizeof(int), GFP_KERNEL);
- if (!smc->connect_info) {
- rc = -ENOMEM;
- goto out;
- }
- smc->connect_info->alen = alen;
- smc->connect_info->flags = flags ^ O_NONBLOCK;
- memcpy(&smc->connect_info->addr, addr, alen);
- schedule_work(&smc->connect_work);
+ if (schedule_work(&smc->connect_work))
+ smc->connect_nonblock = 1;
rc = -EINPROGRESS;
} else {
- rc = kernel_connect(smc->clcsock, addr, alen, flags);
- if (rc)
- goto out;
-
rc = __smc_connect(smc);
if (rc < 0)
goto out;
if (rc < 0)
lsk->sk_err = -rc;
if (rc < 0 || lsk->sk_state == SMC_CLOSED) {
+ new_sk->sk_prot->unhash(new_sk);
if (new_clcsock)
sock_release(new_clcsock);
new_sk->sk_state = SMC_CLOSED;
sock_set_flag(new_sk, SOCK_DEAD);
- new_sk->sk_prot->unhash(new_sk);
sock_put(new_sk); /* final */
*new_smc = NULL;
goto out;
smc_accept_unlink(new_sk);
if (new_sk->sk_state == SMC_CLOSED) {
+ new_sk->sk_prot->unhash(new_sk);
if (isk->clcsock) {
sock_release(isk->clcsock);
isk->clcsock = NULL;
}
- new_sk->sk_prot->unhash(new_sk);
sock_put(new_sk); /* final */
continue;
}
- if (new_sock)
+ if (new_sock) {
sock_graft(new_sk, new_sock);
+ if (isk->use_fallback) {
+ smc_sk(new_sk)->clcsock->file = new_sock->file;
+ isk->clcsock->file->private_data = isk->clcsock;
+ }
+ }
return new_sk;
}
return NULL;
sock_set_flag(sk, SOCK_DEAD);
sk->sk_shutdown |= SHUTDOWN_MASK;
}
+ sk->sk_prot->unhash(sk);
if (smc->clcsock) {
struct socket *tcp;
smc_conn_free(&smc->conn);
}
release_sock(sk);
- sk->sk_prot->unhash(sk);
sock_put(sk); /* final sock_put */
}
struct smc_sock *lsmc = new_smc->listen_smc;
struct sock *newsmcsk = &new_smc->sk;
- lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING);
if (lsmc->sk.sk_state == SMC_LISTEN) {
+ lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING);
smc_accept_enqueue(&lsmc->sk, newsmcsk);
+ release_sock(&lsmc->sk);
} else { /* no longer listening */
smc_close_non_accepted(newsmcsk);
}
- release_sock(&lsmc->sk);
/* Wake up accept */
lsmc->sk.sk_data_ready(&lsmc->sk);
return;
}
smc_conn_free(&new_smc->conn);
- new_smc->use_fallback = true;
+ smc_switch_to_fallback(new_smc);
new_smc->fallback_rsn = reason_code;
if (reason_code && reason_code != SMC_CLC_DECL_PEERDECL) {
if (smc_clc_send_decline(new_smc, reason_code) < 0) {
}
/* listen worker: check prefixes */
-static int smc_listen_rdma_check(struct smc_sock *new_smc,
+static int smc_listen_prfx_check(struct smc_sock *new_smc,
struct smc_clc_msg_proposal *pclc)
{
struct smc_clc_msg_proposal_prefix *pclc_prfx;
pclc_prfx = smc_clc_proposal_get_prefix(pclc);
if (smc_clc_prfx_match(newclcsock, pclc_prfx))
- return SMC_CLC_DECL_CNFERR;
+ return SMC_CLC_DECL_DIFFPREFIX;
return 0;
}
/* listen worker: initialize connection and buffers */
static int smc_listen_rdma_init(struct smc_sock *new_smc,
- struct smc_clc_msg_proposal *pclc,
- struct smc_ib_device *ibdev, u8 ibport,
- int *local_contact)
+ struct smc_init_info *ini)
{
+ int rc;
+
/* allocate connection / link group */
- *local_contact = smc_conn_create(new_smc, false, 0, ibdev, ibport, 0,
- &pclc->lcl, NULL, 0);
- if (*local_contact < 0) {
- if (*local_contact == -ENOMEM)
- return SMC_CLC_DECL_MEM;/* insufficient memory*/
- return SMC_CLC_DECL_INTERR; /* other error */
- }
+ rc = smc_conn_create(new_smc, ini);
+ if (rc)
+ return rc;
/* create send buffer and rmb */
if (smc_buf_create(new_smc, false))
/* listen worker: initialize connection and buffers for SMC-D */
static int smc_listen_ism_init(struct smc_sock *new_smc,
struct smc_clc_msg_proposal *pclc,
- struct smcd_dev *ismdev,
- int *local_contact)
+ struct smc_init_info *ini)
{
struct smc_clc_msg_smcd *pclc_smcd;
+ int rc;
pclc_smcd = smc_get_clc_msg_smcd(pclc);
- *local_contact = smc_conn_create(new_smc, true, 0, NULL, 0, 0, NULL,
- ismdev, pclc_smcd->gid);
- if (*local_contact < 0) {
- if (*local_contact == -ENOMEM)
- return SMC_CLC_DECL_MEM;/* insufficient memory*/
- return SMC_CLC_DECL_INTERR; /* other error */
- }
+ ini->ism_gid = pclc_smcd->gid;
+ rc = smc_conn_create(new_smc, ini);
+ if (rc)
+ return rc;
/* Check if peer can be reached via ISM device */
if (smc_ism_cantalk(new_smc->conn.lgr->peer_gid,
new_smc->conn.lgr->vlan_id,
new_smc->conn.lgr->smcd)) {
- if (*local_contact == SMC_FIRST_CONTACT)
+ if (ini->cln_first_contact == SMC_FIRST_CONTACT)
smc_lgr_forget(new_smc->conn.lgr);
smc_conn_free(&new_smc->conn);
- return SMC_CLC_DECL_CNFERR;
+ return SMC_CLC_DECL_SMCDNOTALK;
}
/* Create send and receive buffers */
if (smc_buf_create(new_smc, true)) {
- if (*local_contact == SMC_FIRST_CONTACT)
+ if (ini->cln_first_contact == SMC_FIRST_CONTACT)
smc_lgr_forget(new_smc->conn.lgr);
smc_conn_free(&new_smc->conn);
return SMC_CLC_DECL_MEM;
struct socket *newclcsock = new_smc->clcsock;
struct smc_clc_msg_accept_confirm cclc;
struct smc_clc_msg_proposal *pclc;
- struct smc_ib_device *ibdev;
+ struct smc_init_info ini = {0};
bool ism_supported = false;
- struct smcd_dev *ismdev;
u8 buf[SMC_CLC_MAX_LEN];
- int local_contact = 0;
- unsigned short vlan;
- int reason_code = 0;
int rc = 0;
- u8 ibport;
+
+ if (new_smc->listen_smc->sk.sk_state != SMC_LISTEN)
+ return smc_listen_out_err(new_smc);
if (new_smc->use_fallback) {
smc_listen_out_connected(new_smc);
/* check if peer is smc capable */
if (!tcp_sk(newclcsock->sk)->syn_smc) {
- new_smc->use_fallback = true;
+ smc_switch_to_fallback(new_smc);
new_smc->fallback_rsn = SMC_CLC_DECL_PEERNOSMC;
smc_listen_out_connected(new_smc);
return;
* wait for and receive SMC Proposal CLC message
*/
pclc = (struct smc_clc_msg_proposal *)&buf;
- reason_code = smc_clc_wait_msg(new_smc, pclc, SMC_CLC_MAX_LEN,
- SMC_CLC_PROPOSAL, CLC_WAIT_TIME);
- if (reason_code) {
- smc_listen_decline(new_smc, reason_code, 0);
- return;
- }
+ rc = smc_clc_wait_msg(new_smc, pclc, SMC_CLC_MAX_LEN,
+ SMC_CLC_PROPOSAL, CLC_WAIT_TIME);
+ if (rc)
+ goto out_decl;
/* IPSec connections opt out of SMC-R optimizations */
if (using_ipsec(new_smc)) {
- smc_listen_decline(new_smc, SMC_CLC_DECL_IPSEC, 0);
- return;
+ rc = SMC_CLC_DECL_IPSEC;
+ goto out_decl;
+ }
+
+ /* check for matching IP prefix and subnet length */
+ rc = smc_listen_prfx_check(new_smc, pclc);
+ if (rc)
+ goto out_decl;
+
+ /* get vlan id from IP device */
+ if (smc_vlan_by_tcpsk(new_smc->clcsock, &ini)) {
+ rc = SMC_CLC_DECL_GETVLANERR;
+ goto out_decl;
}
mutex_lock(&smc_server_lgr_pending);
smc_tx_init(new_smc);
/* check if ISM is available */
- if ((pclc->hdr.path == SMC_TYPE_D || pclc->hdr.path == SMC_TYPE_B) &&
- !smc_check_ism(new_smc, &ismdev) &&
- !smc_listen_ism_init(new_smc, pclc, ismdev, &local_contact)) {
- ism_supported = true;
+ if (pclc->hdr.path == SMC_TYPE_D || pclc->hdr.path == SMC_TYPE_B) {
+ ini.is_smcd = true; /* prepare ISM check */
+ rc = smc_find_ism_device(new_smc, &ini);
+ if (!rc)
+ rc = smc_listen_ism_init(new_smc, pclc, &ini);
+ if (!rc)
+ ism_supported = true;
+ else if (pclc->hdr.path == SMC_TYPE_D)
+ goto out_unlock; /* skip RDMA and decline */
}
/* check if RDMA is available */
- if (!ism_supported &&
- ((pclc->hdr.path != SMC_TYPE_R && pclc->hdr.path != SMC_TYPE_B) ||
- smc_vlan_by_tcpsk(new_smc->clcsock, &vlan) ||
- smc_check_rdma(new_smc, &ibdev, &ibport, vlan, NULL) ||
- smc_listen_rdma_check(new_smc, pclc) ||
- smc_listen_rdma_init(new_smc, pclc, ibdev, ibport,
- &local_contact) ||
- smc_listen_rdma_reg(new_smc, local_contact))) {
- /* SMC not supported, decline */
- mutex_unlock(&smc_server_lgr_pending);
- smc_listen_decline(new_smc, SMC_CLC_DECL_MODEUNSUPP,
- local_contact);
- return;
+ if (!ism_supported) { /* SMC_TYPE_R or SMC_TYPE_B */
+ /* prepare RDMA check */
+ memset(&ini, 0, sizeof(ini));
+ ini.is_smcd = false;
+ ini.ib_lcl = &pclc->lcl;
+ rc = smc_find_rdma_device(new_smc, &ini);
+ if (rc) {
+ /* no RDMA device found */
+ if (pclc->hdr.path == SMC_TYPE_B)
+ /* neither ISM nor RDMA device found */
+ rc = SMC_CLC_DECL_NOSMCDEV;
+ goto out_unlock;
+ }
+ rc = smc_listen_rdma_init(new_smc, &ini);
+ if (rc)
+ goto out_unlock;
+ rc = smc_listen_rdma_reg(new_smc, ini.cln_first_contact);
+ if (rc)
+ goto out_unlock;
}
/* send SMC Accept CLC message */
- rc = smc_clc_send_accept(new_smc, local_contact);
- if (rc) {
- mutex_unlock(&smc_server_lgr_pending);
- smc_listen_decline(new_smc, rc, local_contact);
- return;
- }
+ rc = smc_clc_send_accept(new_smc, ini.cln_first_contact);
+ if (rc)
+ goto out_unlock;
/* SMC-D does not need this lock any more */
if (ism_supported)
mutex_unlock(&smc_server_lgr_pending);
/* receive SMC Confirm CLC message */
- reason_code = smc_clc_wait_msg(new_smc, &cclc, sizeof(cclc),
- SMC_CLC_CONFIRM, CLC_WAIT_TIME);
- if (reason_code) {
+ rc = smc_clc_wait_msg(new_smc, &cclc, sizeof(cclc),
+ SMC_CLC_CONFIRM, CLC_WAIT_TIME);
+ if (rc) {
if (!ism_supported)
- mutex_unlock(&smc_server_lgr_pending);
- smc_listen_decline(new_smc, reason_code, local_contact);
- return;
+ goto out_unlock;
+ goto out_decl;
}
/* finish worker */
if (!ism_supported) {
- rc = smc_listen_rdma_finish(new_smc, &cclc, local_contact);
+ rc = smc_listen_rdma_finish(new_smc, &cclc,
+ ini.cln_first_contact);
mutex_unlock(&smc_server_lgr_pending);
if (rc)
return;
}
smc_conn_save_peer_info(new_smc, &cclc);
smc_listen_out_connected(new_smc);
+ return;
+
+out_unlock:
+ mutex_unlock(&smc_server_lgr_pending);
+out_decl:
+ smc_listen_decline(new_smc, rc, ini.cln_first_contact);
}
static void smc_tcp_listen_work(struct work_struct *work)
if (msg->msg_flags & MSG_FASTOPEN) {
if (sk->sk_state == SMC_INIT) {
- smc->use_fallback = true;
+ smc_switch_to_fallback(smc);
smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP;
} else {
rc = -EINVAL;
poll_table *wait)
{
struct sock *sk = sock->sk;
- __poll_t mask = 0;
struct smc_sock *smc;
+ __poll_t mask = 0;
if (!sk)
return EPOLLNVAL;
/* delegate to CLC child sock */
mask = smc->clcsock->ops->poll(file, smc->clcsock, wait);
sk->sk_err = smc->clcsock->sk->sk_err;
- if (sk->sk_err)
- mask |= EPOLLERR;
} else {
if (sk->sk_state != SMC_CLOSED)
sock_poll_wait(file, sock, wait);
mask |= EPOLLHUP;
if (sk->sk_state == SMC_LISTEN) {
/* woken up by sk_data_ready in smc_listen_work() */
- mask = smc_accept_poll(sk);
+ mask |= smc_accept_poll(sk);
+ } else if (smc->use_fallback) { /* as result of connect_work()*/
+ mask |= smc->clcsock->ops->poll(file, smc->clcsock,
+ wait);
+ sk->sk_err = smc->clcsock->sk->sk_err;
} else {
- if (atomic_read(&smc->conn.sndbuf_space) ||
+ if ((sk->sk_state != SMC_INIT &&
+ atomic_read(&smc->conn.sndbuf_space)) ||
sk->sk_shutdown & SEND_SHUTDOWN) {
mask |= EPOLLOUT | EPOLLWRNORM;
} else {
case TCP_FASTOPEN_NO_COOKIE:
/* option not supported by SMC */
if (sk->sk_state == SMC_INIT) {
- smc->use_fallback = true;
+ smc_switch_to_fallback(smc);
smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP;
} else {
if (!smc->use_fallback)
u64 peer_token; /* SMC-D token of peer */
};
-struct smc_connect_info {
- int flags;
- int alen;
- struct sockaddr addr;
-};
-
struct smc_sock { /* smc sock container */
struct sock sk;
struct socket *clcsock; /* internal tcp socket */
struct smc_connection conn; /* smc connection */
struct smc_sock *listen_smc; /* listen parent */
- struct smc_connect_info *connect_info; /* connect address & flags */
struct work_struct connect_work; /* handle non-blocking connect*/
struct work_struct tcp_listen_work;/* handle tcp socket accepts */
struct work_struct smc_listen_work;/* prepare new accept socket */
* started, waiting for unsent
* data to be sent
*/
+ u8 connect_nonblock : 1;
+ /* non-blocking connect in
+ * flight
+ */
struct mutex clcsock_release_lock;
/* protects clcsock of a listen
* socket
/* send CLC PROPOSAL message across internal TCP socket */
int smc_clc_send_proposal(struct smc_sock *smc, int smc_type,
- struct smc_ib_device *ibdev, u8 ibport, u8 gid[],
- struct smcd_dev *ismdev)
+ struct smc_init_info *ini)
{
struct smc_clc_ipv6_prefix ipv6_prfx[SMC_CLC_MAX_V6_PREFIX];
struct smc_clc_msg_proposal_prefix pclc_prfx;
/* add SMC-R specifics */
memcpy(pclc.lcl.id_for_peer, local_systemid,
sizeof(local_systemid));
- memcpy(&pclc.lcl.gid, gid, SMC_GID_SIZE);
- memcpy(&pclc.lcl.mac, &ibdev->mac[ibport - 1], ETH_ALEN);
+ memcpy(&pclc.lcl.gid, ini->ib_gid, SMC_GID_SIZE);
+ memcpy(&pclc.lcl.mac, &ini->ib_dev->mac[ini->ib_port - 1],
+ ETH_ALEN);
pclc.iparea_offset = htons(0);
}
if (smc_type == SMC_TYPE_D || smc_type == SMC_TYPE_B) {
memset(&pclc_smcd, 0, sizeof(pclc_smcd));
plen += sizeof(pclc_smcd);
pclc.iparea_offset = htons(SMC_CLC_PROPOSAL_MAX_OFFSET);
- pclc_smcd.gid = ismdev->local_gid;
+ pclc_smcd.gid = ini->ism_dev->local_gid;
}
pclc.hdr.length = htons(plen);
#define SMC_CLC_DECL_CNFERR 0x03000000 /* configuration error */
#define SMC_CLC_DECL_PEERNOSMC 0x03010000 /* peer did not indicate SMC */
#define SMC_CLC_DECL_IPSEC 0x03020000 /* IPsec usage */
-#define SMC_CLC_DECL_NOSMCDEV 0x03030000 /* no SMC device found */
+#define SMC_CLC_DECL_NOSMCDEV 0x03030000 /* no SMC device found (R or D) */
+#define SMC_CLC_DECL_NOSMCDDEV 0x03030001 /* no SMC-D device found */
+#define SMC_CLC_DECL_NOSMCRDEV 0x03030002 /* no SMC-R device found */
+#define SMC_CLC_DECL_SMCDNOTALK 0x03030003 /* SMC-D dev can't talk to peer */
#define SMC_CLC_DECL_MODEUNSUPP 0x03040000 /* smc modes do not match (R or D)*/
#define SMC_CLC_DECL_RMBE_EC 0x03050000 /* peer has eyecatcher in RMBE */
#define SMC_CLC_DECL_OPTUNSUPP 0x03060000 /* fastopen sockopt not supported */
+#define SMC_CLC_DECL_DIFFPREFIX 0x03070000 /* IP prefix / subnet mismatch */
+#define SMC_CLC_DECL_GETVLANERR 0x03080000 /* err to get vlan id of ip device*/
+#define SMC_CLC_DECL_ISMVLANERR 0x03090000 /* err to reg vlan id on ism dev */
#define SMC_CLC_DECL_SYNCERR 0x04000000 /* synchronization error */
#define SMC_CLC_DECL_PEERDECL 0x05000000 /* peer declined during handshake */
-#define SMC_CLC_DECL_INTERR 0x99990000 /* internal error */
-#define SMC_CLC_DECL_ERR_RTOK 0x99990001 /* rtoken handling failed */
-#define SMC_CLC_DECL_ERR_RDYLNK 0x99990002 /* ib ready link failed */
-#define SMC_CLC_DECL_ERR_REGRMB 0x99990003 /* reg rmb failed */
+#define SMC_CLC_DECL_INTERR 0x09990000 /* internal error */
+#define SMC_CLC_DECL_ERR_RTOK 0x09990001 /* rtoken handling failed */
+#define SMC_CLC_DECL_ERR_RDYLNK 0x09990002 /* ib ready link failed */
+#define SMC_CLC_DECL_ERR_REGRMB 0x09990003 /* reg rmb failed */
struct smc_clc_msg_hdr { /* header1 of clc messages */
u8 eyecatcher[4]; /* eye catcher */
}
struct smcd_dev;
+struct smc_init_info;
int smc_clc_prfx_match(struct socket *clcsock,
struct smc_clc_msg_proposal_prefix *prop);
u8 expected_type, unsigned long timeout);
int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info);
int smc_clc_send_proposal(struct smc_sock *smc, int smc_type,
- struct smc_ib_device *smcibdev, u8 ibport, u8 gid[],
- struct smcd_dev *ismdev);
+ struct smc_init_info *ini);
int smc_clc_send_confirm(struct smc_sock *smc);
int smc_clc_send_accept(struct smc_sock *smc, int srv_first_contact);
#define SMC_CLOSE_WAIT_LISTEN_CLCSOCK_TIME (5 * HZ)
+/* release the clcsock that is assigned to the smc_sock */
+void smc_clcsock_release(struct smc_sock *smc)
+{
+ struct socket *tcp;
+
+ if (smc->listen_smc && current_work() != &smc->smc_listen_work)
+ cancel_work_sync(&smc->smc_listen_work);
+ mutex_lock(&smc->clcsock_release_lock);
+ if (smc->clcsock) {
+ tcp = smc->clcsock;
+ smc->clcsock = NULL;
+ sock_release(tcp);
+ }
+ mutex_unlock(&smc->clcsock_release_lock);
+}
+
static void smc_close_cleanup_listen(struct sock *parent)
{
struct sock *sk;
close_work);
struct smc_sock *smc = container_of(conn, struct smc_sock, conn);
struct smc_cdc_conn_state_flags *rxflags;
+ bool release_clcsock = false;
struct sock *sk = &smc->sk;
int old_state;
if ((sk->sk_state == SMC_CLOSED) &&
(sock_flag(sk, SOCK_DEAD) || !sk->sk_socket)) {
smc_conn_free(conn);
- if (smc->clcsock) {
- sock_release(smc->clcsock);
- smc->clcsock = NULL;
- }
+ if (smc->clcsock)
+ release_clcsock = true;
}
}
release_sock(sk);
+ if (release_clcsock)
+ smc_clcsock_release(smc);
sock_put(sk); /* sock_hold done by schedulers of close_work */
}
int smc_close_active(struct smc_sock *smc);
int smc_close_shutdown_write(struct smc_sock *smc);
void smc_close_init(struct smc_sock *smc);
+void smc_clcsock_release(struct smc_sock *smc);
#endif /* SMC_CLOSE_H */
}
/* create a new SMC link group */
-static int smc_lgr_create(struct smc_sock *smc, bool is_smcd,
- struct smc_ib_device *smcibdev, u8 ibport,
- char *peer_systemid, unsigned short vlan_id,
- struct smcd_dev *smcismdev, u64 peer_gid)
+static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini)
{
struct smc_link_group *lgr;
struct smc_link *lnk;
int rc = 0;
int i;
- if (is_smcd && vlan_id) {
- rc = smc_ism_get_vlan(smcismdev, vlan_id);
- if (rc)
+ if (ini->is_smcd && ini->vlan_id) {
+ if (smc_ism_get_vlan(ini->ism_dev, ini->vlan_id)) {
+ rc = SMC_CLC_DECL_ISMVLANERR;
goto out;
+ }
}
lgr = kzalloc(sizeof(*lgr), GFP_KERNEL);
if (!lgr) {
- rc = -ENOMEM;
+ rc = SMC_CLC_DECL_MEM;
goto out;
}
- lgr->is_smcd = is_smcd;
+ lgr->is_smcd = ini->is_smcd;
lgr->sync_err = 0;
- lgr->vlan_id = vlan_id;
+ lgr->vlan_id = ini->vlan_id;
rwlock_init(&lgr->sndbufs_lock);
rwlock_init(&lgr->rmbs_lock);
rwlock_init(&lgr->conns_lock);
memcpy(&lgr->id, (u8 *)&smc_lgr_list.num, SMC_LGR_ID_SIZE);
INIT_DELAYED_WORK(&lgr->free_work, smc_lgr_free_work);
lgr->conns_all = RB_ROOT;
- if (is_smcd) {
+ if (ini->is_smcd) {
/* SMC-D specific settings */
- lgr->peer_gid = peer_gid;
- lgr->smcd = smcismdev;
+ lgr->peer_gid = ini->ism_gid;
+ lgr->smcd = ini->ism_dev;
} else {
/* SMC-R specific settings */
lgr->role = smc->listen_smc ? SMC_SERV : SMC_CLNT;
- memcpy(lgr->peer_systemid, peer_systemid, SMC_SYSTEMID_LEN);
+ memcpy(lgr->peer_systemid, ini->ib_lcl->id_for_peer,
+ SMC_SYSTEMID_LEN);
lnk = &lgr->lnk[SMC_SINGLE_LINK];
/* initialize link */
lnk->state = SMC_LNK_ACTIVATING;
lnk->link_id = SMC_SINGLE_LINK;
- lnk->smcibdev = smcibdev;
- lnk->ibport = ibport;
- lnk->path_mtu = smcibdev->pattr[ibport - 1].active_mtu;
- if (!smcibdev->initialized)
- smc_ib_setup_per_ibdev(smcibdev);
+ lnk->smcibdev = ini->ib_dev;
+ lnk->ibport = ini->ib_port;
+ lnk->path_mtu =
+ ini->ib_dev->pattr[ini->ib_port - 1].active_mtu;
+ if (!ini->ib_dev->initialized)
+ smc_ib_setup_per_ibdev(ini->ib_dev);
get_random_bytes(rndvec, sizeof(rndvec));
lnk->psn_initial = rndvec[0] + (rndvec[1] << 8) +
(rndvec[2] << 16);
rc = smc_ib_determine_gid(lnk->smcibdev, lnk->ibport,
- vlan_id, lnk->gid, &lnk->sgid_index);
+ ini->vlan_id, lnk->gid,
+ &lnk->sgid_index);
if (rc)
goto free_lgr;
rc = smc_llc_link_init(lnk);
free_lgr:
kfree(lgr);
out:
+ if (rc < 0) {
+ if (rc == -ENOMEM)
+ rc = SMC_CLC_DECL_MEM;
+ else
+ rc = SMC_CLC_DECL_INTERR;
+ }
return rc;
}
/* Determine vlan of internal TCP socket.
* @vlan_id: address to store the determined vlan id into
*/
-int smc_vlan_by_tcpsk(struct socket *clcsock, unsigned short *vlan_id)
+int smc_vlan_by_tcpsk(struct socket *clcsock, struct smc_init_info *ini)
{
struct dst_entry *dst = sk_dst_get(clcsock->sk);
struct net_device *ndev;
int i, nest_lvl, rc = 0;
- *vlan_id = 0;
+ ini->vlan_id = 0;
if (!dst) {
rc = -ENOTCONN;
goto out;
ndev = dst->dev;
if (is_vlan_dev(ndev)) {
- *vlan_id = vlan_dev_vlan_id(ndev);
+ ini->vlan_id = vlan_dev_vlan_id(ndev);
goto out_rel;
}
lower = lower->next;
ndev = (struct net_device *)netdev_lower_get_next(ndev, &lower);
if (is_vlan_dev(ndev)) {
- *vlan_id = vlan_dev_vlan_id(ndev);
+ ini->vlan_id = vlan_dev_vlan_id(ndev);
break;
}
}
}
/* create a new SMC connection (and a new link group if necessary) */
-int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact,
- struct smc_ib_device *smcibdev, u8 ibport, u32 clcqpn,
- struct smc_clc_msg_local *lcl, struct smcd_dev *smcd,
- u64 peer_gid)
+int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini)
{
struct smc_connection *conn = &smc->conn;
- int local_contact = SMC_FIRST_CONTACT;
struct smc_link_group *lgr;
- unsigned short vlan_id;
enum smc_lgr_role role;
int rc = 0;
+ ini->cln_first_contact = SMC_FIRST_CONTACT;
role = smc->listen_smc ? SMC_SERV : SMC_CLNT;
- rc = smc_vlan_by_tcpsk(smc->clcsock, &vlan_id);
- if (rc)
- return rc;
-
- if ((role == SMC_CLNT) && srv_first_contact)
+ if (role == SMC_CLNT && ini->srv_first_contact)
/* create new link group as well */
goto create;
spin_lock_bh(&smc_lgr_list.lock);
list_for_each_entry(lgr, &smc_lgr_list.list, list) {
write_lock_bh(&lgr->conns_lock);
- if ((is_smcd ? smcd_lgr_match(lgr, smcd, peer_gid) :
- smcr_lgr_match(lgr, lcl, role, clcqpn)) &&
+ if ((ini->is_smcd ?
+ smcd_lgr_match(lgr, ini->ism_dev, ini->ism_gid) :
+ smcr_lgr_match(lgr, ini->ib_lcl, role, ini->ib_clcqpn)) &&
!lgr->sync_err &&
- lgr->vlan_id == vlan_id &&
+ lgr->vlan_id == ini->vlan_id &&
(role == SMC_CLNT ||
lgr->conns_num < SMC_RMBS_PER_LGR_MAX)) {
/* link group found */
- local_contact = SMC_REUSE_CONTACT;
+ ini->cln_first_contact = SMC_REUSE_CONTACT;
conn->lgr = lgr;
smc_lgr_register_conn(conn); /* add smc conn to lgr */
if (delayed_work_pending(&lgr->free_work))
}
spin_unlock_bh(&smc_lgr_list.lock);
- if (role == SMC_CLNT && !srv_first_contact &&
- (local_contact == SMC_FIRST_CONTACT)) {
+ if (role == SMC_CLNT && !ini->srv_first_contact &&
+ ini->cln_first_contact == SMC_FIRST_CONTACT) {
/* Server reuses a link group, but Client wants to start
* a new one
* send out_of_sync decline, reason synchr. error
*/
- return -ENOLINK;
+ return SMC_CLC_DECL_SYNCERR;
}
create:
- if (local_contact == SMC_FIRST_CONTACT) {
- rc = smc_lgr_create(smc, is_smcd, smcibdev, ibport,
- lcl->id_for_peer, vlan_id, smcd, peer_gid);
+ if (ini->cln_first_contact == SMC_FIRST_CONTACT) {
+ rc = smc_lgr_create(smc, ini);
if (rc)
goto out;
smc_lgr_register_conn(conn); /* add smc conn to lgr */
conn->local_tx_ctrl.common.type = SMC_CDC_MSG_TYPE;
conn->local_tx_ctrl.len = SMC_WR_TX_SIZE;
conn->urg_state = SMC_URG_READ;
- if (is_smcd) {
+ if (ini->is_smcd) {
conn->rx_off = sizeof(struct smcd_cdc_msg);
smcd_cdc_rx_init(conn); /* init tasklet for this conn */
}
#endif
out:
- return rc ? rc : local_contact;
+ return rc;
}
/* convert the RMB size into the compressed notation - minimum 16K.
};
};
+struct smc_clc_msg_local;
+
+struct smc_init_info {
+ u8 is_smcd;
+ unsigned short vlan_id;
+ int srv_first_contact;
+ int cln_first_contact;
+ /* SMC-R */
+ struct smc_clc_msg_local *ib_lcl;
+ struct smc_ib_device *ib_dev;
+ u8 ib_gid[SMC_GID_SIZE];
+ u8 ib_port;
+ u32 ib_clcqpn;
+ /* SMC-D */
+ u64 ism_gid;
+ struct smcd_dev *ism_dev;
+};
+
/* Find the connection associated with the given alert token in the link group.
* To use rbtrees we have to implement our own search core.
* Requires @conns_lock
void smc_sndbuf_sync_sg_for_device(struct smc_connection *conn);
void smc_rmb_sync_sg_for_cpu(struct smc_connection *conn);
void smc_rmb_sync_sg_for_device(struct smc_connection *conn);
-int smc_vlan_by_tcpsk(struct socket *clcsock, unsigned short *vlan_id);
+int smc_vlan_by_tcpsk(struct socket *clcsock, struct smc_init_info *ini);
void smc_conn_free(struct smc_connection *conn);
-int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact,
- struct smc_ib_device *smcibdev, u8 ibport, u32 clcqpn,
- struct smc_clc_msg_local *lcl, struct smcd_dev *smcd,
- u64 peer_gid);
+int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini);
void smcd_conn_free(struct smc_connection *conn);
void smc_lgr_schedule_free_work_fast(struct smc_link_group *lgr);
void smc_core_exit(void);
INIT_LIST_HEAD(&smcd->vlan);
smcd->event_wq = alloc_ordered_workqueue("ism_evt_wq-%s)",
WQ_MEM_RECLAIM, name);
+ if (!smcd->event_wq) {
+ kfree(smcd->conn);
+ kfree(smcd);
+ return NULL;
+ }
return smcd;
}
EXPORT_SYMBOL_GPL(smcd_alloc_dev);
#include "smc_pnet.h"
#include "smc_ib.h"
#include "smc_ism.h"
+#include "smc_core.h"
#define SMC_ASCII_BLANK 32
{
struct net *net = genl_info_net(info);
- return smc_pnet_remove_by_pnetid(net, NULL);
+ smc_pnet_remove_by_pnetid(net, NULL);
+ return 0;
}
/* SMC_PNETID generic netlink operation definition */
* IB device and port
*/
static void smc_pnet_find_rdma_dev(struct net_device *netdev,
- struct smc_ib_device **smcibdev,
- u8 *ibport, unsigned short vlan_id, u8 gid[])
+ struct smc_init_info *ini)
{
struct smc_ib_device *ibdev;
dev_put(ndev);
if (netdev == ndev &&
smc_ib_port_active(ibdev, i) &&
- !smc_ib_determine_gid(ibdev, i, vlan_id, gid,
- NULL)) {
- *smcibdev = ibdev;
- *ibport = i;
+ !smc_ib_determine_gid(ibdev, i, ini->vlan_id,
+ ini->ib_gid, NULL)) {
+ ini->ib_dev = ibdev;
+ ini->ib_port = i;
break;
}
}
* If nothing found, try to use handshake device
*/
static void smc_pnet_find_roce_by_pnetid(struct net_device *ndev,
- struct smc_ib_device **smcibdev,
- u8 *ibport, unsigned short vlan_id,
- u8 gid[])
+ struct smc_init_info *ini)
{
u8 ndev_pnetid[SMC_MAX_PNETID_LEN];
struct smc_ib_device *ibdev;
if (smc_pnetid_by_dev_port(ndev->dev.parent, ndev->dev_port,
ndev_pnetid) &&
smc_pnet_find_ndev_pnetid_by_table(ndev, ndev_pnetid)) {
- smc_pnet_find_rdma_dev(ndev, smcibdev, ibport, vlan_id, gid);
+ smc_pnet_find_rdma_dev(ndev, ini);
return; /* pnetid could not be determined */
}
continue;
if (smc_pnet_match(ibdev->pnetid[i - 1], ndev_pnetid) &&
smc_ib_port_active(ibdev, i) &&
- !smc_ib_determine_gid(ibdev, i, vlan_id, gid,
- NULL)) {
- *smcibdev = ibdev;
- *ibport = i;
+ !smc_ib_determine_gid(ibdev, i, ini->vlan_id,
+ ini->ib_gid, NULL)) {
+ ini->ib_dev = ibdev;
+ ini->ib_port = i;
goto out;
}
}
}
static void smc_pnet_find_ism_by_pnetid(struct net_device *ndev,
- struct smcd_dev **smcismdev)
+ struct smc_init_info *ini)
{
u8 ndev_pnetid[SMC_MAX_PNETID_LEN];
struct smcd_dev *ismdev;
spin_lock(&smcd_dev_list.lock);
list_for_each_entry(ismdev, &smcd_dev_list.list, list) {
if (smc_pnet_match(ismdev->pnetid, ndev_pnetid)) {
- *smcismdev = ismdev;
+ ini->ism_dev = ismdev;
break;
}
}
* determine ib_device and port belonging to used internal TCP socket
* ethernet interface.
*/
-void smc_pnet_find_roce_resource(struct sock *sk,
- struct smc_ib_device **smcibdev, u8 *ibport,
- unsigned short vlan_id, u8 gid[])
+void smc_pnet_find_roce_resource(struct sock *sk, struct smc_init_info *ini)
{
struct dst_entry *dst = sk_dst_get(sk);
- *smcibdev = NULL;
- *ibport = 0;
-
+ ini->ib_dev = NULL;
+ ini->ib_port = 0;
if (!dst)
goto out;
if (!dst->dev)
goto out_rel;
- smc_pnet_find_roce_by_pnetid(dst->dev, smcibdev, ibport, vlan_id, gid);
+ smc_pnet_find_roce_by_pnetid(dst->dev, ini);
out_rel:
dst_release(dst);
return;
}
-void smc_pnet_find_ism_resource(struct sock *sk, struct smcd_dev **smcismdev)
+void smc_pnet_find_ism_resource(struct sock *sk, struct smc_init_info *ini)
{
struct dst_entry *dst = sk_dst_get(sk);
- *smcismdev = NULL;
+ ini->ism_dev = NULL;
if (!dst)
goto out;
if (!dst->dev)
goto out_rel;
- smc_pnet_find_ism_by_pnetid(dst->dev, smcismdev);
+ smc_pnet_find_ism_by_pnetid(dst->dev, ini);
out_rel:
dst_release(dst);
struct smc_ib_device;
struct smcd_dev;
+struct smc_init_info;
/**
* struct smc_pnettable - SMC PNET table anchor
int smc_pnet_net_init(struct net *net);
void smc_pnet_exit(void);
void smc_pnet_net_exit(struct net *net);
-void smc_pnet_find_roce_resource(struct sock *sk,
- struct smc_ib_device **smcibdev, u8 *ibport,
- unsigned short vlan_id, u8 gid[]);
-void smc_pnet_find_ism_resource(struct sock *sk, struct smcd_dev **smcismdev);
+void smc_pnet_find_roce_resource(struct sock *sk, struct smc_init_info *ini);
+void smc_pnet_find_ism_resource(struct sock *sk, struct smc_init_info *ini);
#endif
/* We are going to append to the frags_list of head.
* Need to unshare the frag_list.
*/
- if (skb_has_frag_list(head)) {
- err = skb_unclone(head, GFP_ATOMIC);
- if (err) {
- STRP_STATS_INCR(strp->stats.mem_fail);
- desc->error = err;
- return 0;
- }
+ err = skb_unclone(head, GFP_ATOMIC);
+ if (err) {
+ STRP_STATS_INCR(strp->stats.mem_fail);
+ desc->error = err;
+ return 0;
}
if (unlikely(skb_shinfo(head)->frag_list)) {
break;
}
- /* Positive extra indicates ore bytes than needed for the
+ /* Positive extra indicates more bytes than needed for the
* message
*/
clnt->cl_stats->rpccnt++;
task->tk_action = call_reserve;
rpc_task_set_transport(task, clnt);
- call_reserve(task);
}
/*
task->tk_status = 0;
task->tk_action = call_reserveresult;
xprt_reserve(task);
- if (rpc_task_need_resched(task))
- return;
- call_reserveresult(task);
}
static void call_retry_reserve(struct rpc_task *task);
if (status >= 0) {
if (task->tk_rqstp) {
task->tk_action = call_refresh;
- call_refresh(task);
return;
}
/* fall through */
case -EAGAIN: /* woken up; retry */
task->tk_action = call_retry_reserve;
- call_retry_reserve(task);
return;
case -EIO: /* probably a shutdown */
break;
task->tk_status = 0;
task->tk_action = call_reserveresult;
xprt_retry_reserve(task);
- if (rpc_task_need_resched(task))
- return;
- call_reserveresult(task);
}
/*
task->tk_status = 0;
task->tk_client->cl_stats->rpcauthrefresh++;
rpcauth_refreshcred(task);
- if (rpc_task_need_resched(task))
- return;
- call_refreshresult(task);
}
/*
case 0:
if (rpcauth_uptodatecred(task)) {
task->tk_action = call_allocate;
- call_allocate(task);
return;
}
/* Use rate-limiting and a max number of retries if refresh
task->tk_cred_retry--;
dprintk("RPC: %5u %s: retry refresh creds\n",
task->tk_pid, __func__);
- call_refresh(task);
return;
}
dprintk("RPC: %5u %s: refresh creds failed with error %d\n",
task->tk_status = 0;
task->tk_action = call_encode;
- if (req->rq_buffer) {
- call_encode(task);
+ if (req->rq_buffer)
return;
- }
if (proc->p_proc != 0) {
BUG_ON(proc->p_arglen == 0);
status = xprt->ops->buf_alloc(task);
xprt_inject_disconnect(xprt);
- if (status == 0) {
- if (rpc_task_need_resched(task))
- return;
- call_encode(task);
+ if (status == 0)
return;
- }
if (status != -ENOMEM) {
rpc_exit(task, status);
return;
xprt_request_enqueue_receive(task);
xprt_request_enqueue_transmit(task);
out:
- task->tk_action = call_bind;
- call_bind(task);
+ task->tk_action = call_transmit;
+ /* Check that the connection is OK */
+ if (!xprt_bound(task->tk_xprt))
+ task->tk_action = call_bind;
+ else if (!xprt_connected(task->tk_xprt))
+ task->tk_action = call_connect;
}
/*
{
xprt_end_transmit(task);
task->tk_action = call_transmit_status;
- call_transmit_status(task);
}
/*
if (xprt_bound(xprt)) {
task->tk_action = call_connect;
- call_connect(task);
return;
}
dprint_status(task);
task->tk_status = 0;
task->tk_action = call_connect;
- call_connect(task);
return;
}
if (xprt_connected(xprt)) {
task->tk_action = call_transmit;
- call_transmit(task);
return;
}
case 0:
clnt->cl_stats->netreconn++;
task->tk_action = call_transmit;
- call_transmit(task);
return;
}
rpc_exit(task, status);
xprt_transmit(task);
}
xprt_end_transmit(task);
- if (rpc_task_need_resched(task))
- return;
- call_transmit_status(task);
}
/*
if (rpc_task_transmitted(task)) {
if (task->tk_status == 0)
xprt_request_wait_receive(task);
- if (rpc_task_need_resched(task))
- return;
- call_status(task);
return;
}
{
xprt_request_enqueue_transmit(task);
task->tk_action = call_bc_transmit;
- call_bc_transmit(task);
}
/*
status = task->tk_status;
if (status >= 0) {
task->tk_action = call_decode;
- call_decode(task);
return;
}
/* Flush Receives, then wait for deferred Reply work
* to complete.
*/
- ib_drain_qp(ia->ri_id->qp);
+ ib_drain_rq(ia->ri_id->qp);
drain_workqueue(buf->rb_completion_wq);
/* Deferred Reply processing might have scheduled
u32 node, port;
skb = skb_peek(inputq);
+ if (!skb)
+ return;
+
hdr = buf_msg(skb);
if (likely(!msg_is_syn(hdr) && skb_queue_empty(defq)))
/* Failover/synch */
u16 drop_point;
struct sk_buff *failover_reasm_skb;
+ struct sk_buff_head failover_deferdq;
/* Max packet negotiation */
u16 mtu;
};
#define TIPC_BC_RETR_LIM msecs_to_jiffies(10) /* [ms] */
+#define TIPC_UC_RETR_TIME (jiffies + msecs_to_jiffies(1))
/*
* Interval between NACKs when packets arrive out of order
static void tipc_link_build_bc_init_msg(struct tipc_link *l,
struct sk_buff_head *xmitq);
static bool tipc_link_release_pkts(struct tipc_link *l, u16 to);
+static u16 tipc_build_gap_ack_blks(struct tipc_link *l, void *data);
+static void tipc_link_advance_transmq(struct tipc_link *l, u16 acked, u16 gap,
+ struct tipc_gap_ack_blks *ga,
+ struct sk_buff_head *xmitq);
/*
* Simple non-static link routines (i.e. referenced outside this file)
__skb_queue_head_init(&l->transmq);
__skb_queue_head_init(&l->backlogq);
__skb_queue_head_init(&l->deferdq);
+ __skb_queue_head_init(&l->failover_deferdq);
skb_queue_head_init(&l->wakeupq);
skb_queue_head_init(l->inputq);
return true;
__skb_queue_head_init(&list);
l->in_session = false;
+ /* Force re-synch of peer session number before establishing */
+ l->peer_session--;
l->session++;
l->mtu = l->advertised_mtu;
__skb_queue_purge(&l->transmq);
__skb_queue_purge(&l->deferdq);
__skb_queue_purge(&l->backlogq);
+ __skb_queue_purge(&l->failover_deferdq);
l->backlog[TIPC_LOW_IMPORTANCE].len = 0;
l->backlog[TIPC_MEDIUM_IMPORTANCE].len = 0;
l->backlog[TIPC_HIGH_IMPORTANCE].len = 0;
* Consumes buffer
*/
static int tipc_link_input(struct tipc_link *l, struct sk_buff *skb,
- struct sk_buff_head *inputq)
+ struct sk_buff_head *inputq,
+ struct sk_buff **reasm_skb)
{
struct tipc_msg *hdr = buf_msg(skb);
- struct sk_buff **reasm_skb = &l->reasm_buf;
struct sk_buff *iskb;
struct sk_buff_head tmpq;
int usr = msg_user(hdr);
- int rc = 0;
int pos = 0;
- int ipos = 0;
-
- if (unlikely(usr == TUNNEL_PROTOCOL)) {
- if (msg_type(hdr) == SYNCH_MSG) {
- __skb_queue_purge(&l->deferdq);
- goto drop;
- }
- if (!tipc_msg_extract(skb, &iskb, &ipos))
- return rc;
- kfree_skb(skb);
- skb = iskb;
- hdr = buf_msg(skb);
- if (less(msg_seqno(hdr), l->drop_point))
- goto drop;
- if (tipc_data_input(l, skb, inputq))
- return rc;
- usr = msg_user(hdr);
- reasm_skb = &l->failover_reasm_skb;
- }
if (usr == MSG_BUNDLER) {
skb_queue_head_init(&tmpq);
tipc_link_bc_init_rcv(l->bc_rcvlink, hdr);
tipc_bcast_unlock(l->net);
}
-drop:
+
kfree_skb(skb);
return 0;
}
+/* tipc_link_tnl_rcv() - receive TUNNEL_PROTOCOL message, drop or process the
+ * inner message along with the ones in the old link's
+ * deferdq
+ * @l: tunnel link
+ * @skb: TUNNEL_PROTOCOL message
+ * @inputq: queue to put messages ready for delivery
+ */
+static int tipc_link_tnl_rcv(struct tipc_link *l, struct sk_buff *skb,
+ struct sk_buff_head *inputq)
+{
+ struct sk_buff **reasm_skb = &l->failover_reasm_skb;
+ struct sk_buff_head *fdefq = &l->failover_deferdq;
+ struct tipc_msg *hdr = buf_msg(skb);
+ struct sk_buff *iskb;
+ int ipos = 0;
+ int rc = 0;
+ u16 seqno;
+
+ /* SYNCH_MSG */
+ if (msg_type(hdr) == SYNCH_MSG)
+ goto drop;
+
+ /* FAILOVER_MSG */
+ if (!tipc_msg_extract(skb, &iskb, &ipos)) {
+ pr_warn_ratelimited("Cannot extract FAILOVER_MSG, defq: %d\n",
+ skb_queue_len(fdefq));
+ return rc;
+ }
+
+ do {
+ seqno = buf_seqno(iskb);
+
+ if (unlikely(less(seqno, l->drop_point))) {
+ kfree_skb(iskb);
+ continue;
+ }
+
+ if (unlikely(seqno != l->drop_point)) {
+ __tipc_skb_queue_sorted(fdefq, seqno, iskb);
+ continue;
+ }
+
+ l->drop_point++;
+
+ if (!tipc_data_input(l, iskb, inputq))
+ rc |= tipc_link_input(l, iskb, inputq, reasm_skb);
+ if (unlikely(rc))
+ break;
+ } while ((iskb = __tipc_skb_dequeue(fdefq, l->drop_point)));
+
+drop:
+ kfree_skb(skb);
+ return rc;
+}
+
static bool tipc_link_release_pkts(struct tipc_link *l, u16 acked)
{
bool released = false;
return released;
}
+/* tipc_build_gap_ack_blks - build Gap ACK blocks
+ * @l: tipc link that data have come with gaps in sequence if any
+ * @data: data buffer to store the Gap ACK blocks after built
+ *
+ * returns the actual allocated memory size
+ */
+static u16 tipc_build_gap_ack_blks(struct tipc_link *l, void *data)
+{
+ struct sk_buff *skb = skb_peek(&l->deferdq);
+ struct tipc_gap_ack_blks *ga = data;
+ u16 len, expect, seqno = 0;
+ u8 n = 0;
+
+ if (!skb)
+ goto exit;
+
+ expect = buf_seqno(skb);
+ skb_queue_walk(&l->deferdq, skb) {
+ seqno = buf_seqno(skb);
+ if (unlikely(more(seqno, expect))) {
+ ga->gacks[n].ack = htons(expect - 1);
+ ga->gacks[n].gap = htons(seqno - expect);
+ if (++n >= MAX_GAP_ACK_BLKS) {
+ pr_info_ratelimited("Too few Gap ACK blocks!\n");
+ goto exit;
+ }
+ } else if (unlikely(less(seqno, expect))) {
+ pr_warn("Unexpected skb in deferdq!\n");
+ continue;
+ }
+ expect = seqno + 1;
+ }
+
+ /* last block */
+ ga->gacks[n].ack = htons(seqno);
+ ga->gacks[n].gap = 0;
+ n++;
+
+exit:
+ len = tipc_gap_ack_blks_sz(n);
+ ga->len = htons(len);
+ ga->gack_cnt = n;
+ return len;
+}
+
+/* tipc_link_advance_transmq - advance TIPC link transmq queue by releasing
+ * acked packets, also doing retransmissions if
+ * gaps found
+ * @l: tipc link with transmq queue to be advanced
+ * @acked: seqno of last packet acked by peer without any gaps before
+ * @gap: # of gap packets
+ * @ga: buffer pointer to Gap ACK blocks from peer
+ * @xmitq: queue for accumulating the retransmitted packets if any
+ */
+static void tipc_link_advance_transmq(struct tipc_link *l, u16 acked, u16 gap,
+ struct tipc_gap_ack_blks *ga,
+ struct sk_buff_head *xmitq)
+{
+ struct sk_buff *skb, *_skb, *tmp;
+ struct tipc_msg *hdr;
+ u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1;
+ u16 ack = l->rcv_nxt - 1;
+ u16 seqno;
+ u16 n = 0;
+
+ skb_queue_walk_safe(&l->transmq, skb, tmp) {
+ seqno = buf_seqno(skb);
+
+next_gap_ack:
+ if (less_eq(seqno, acked)) {
+ /* release skb */
+ __skb_unlink(skb, &l->transmq);
+ kfree_skb(skb);
+ } else if (less_eq(seqno, acked + gap)) {
+ /* retransmit skb */
+ if (time_before(jiffies, TIPC_SKB_CB(skb)->nxt_retr))
+ continue;
+ TIPC_SKB_CB(skb)->nxt_retr = TIPC_UC_RETR_TIME;
+
+ _skb = __pskb_copy(skb, MIN_H_SIZE, GFP_ATOMIC);
+ if (!_skb)
+ continue;
+ hdr = buf_msg(_skb);
+ msg_set_ack(hdr, ack);
+ msg_set_bcast_ack(hdr, bc_ack);
+ _skb->priority = TC_PRIO_CONTROL;
+ __skb_queue_tail(xmitq, _skb);
+ l->stats.retransmitted++;
+ } else {
+ /* retry with Gap ACK blocks if any */
+ if (!ga || n >= ga->gack_cnt)
+ break;
+ acked = ntohs(ga->gacks[n].ack);
+ gap = ntohs(ga->gacks[n].gap);
+ n++;
+ goto next_gap_ack;
+ }
+ }
+}
+
/* tipc_link_build_state_msg: prepare link state message for transmission
*
* Note that sending of broadcast ack is coordinated among nodes, to reduce
struct sk_buff_head *xmitq)
{
u32 def_cnt = ++l->stats.deferred_recv;
+ u32 defq_len = skb_queue_len(&l->deferdq);
int match1, match2;
if (link_is_bc_rcvlink(l)) {
return 0;
}
- if ((skb_queue_len(&l->deferdq) == 1) || !(def_cnt % TIPC_NACK_INTV))
+ if (defq_len >= 3 && !((defq_len - 3) % 16))
tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, 0, 0, xmitq);
return 0;
}
struct sk_buff_head *xmitq)
{
struct sk_buff_head *defq = &l->deferdq;
- struct tipc_msg *hdr;
+ struct tipc_msg *hdr = buf_msg(skb);
u16 seqno, rcv_nxt, win_lim;
int rc = 0;
+ /* Verify and update link state */
+ if (unlikely(msg_user(hdr) == LINK_PROTOCOL))
+ return tipc_link_proto_rcv(l, skb, xmitq);
+
+ /* Don't send probe at next timeout expiration */
+ l->silent_intv_cnt = 0;
+
do {
hdr = buf_msg(skb);
seqno = msg_seqno(hdr);
rcv_nxt = l->rcv_nxt;
win_lim = rcv_nxt + TIPC_MAX_LINK_WIN;
- /* Verify and update link state */
- if (unlikely(msg_user(hdr) == LINK_PROTOCOL))
- return tipc_link_proto_rcv(l, skb, xmitq);
-
if (unlikely(!link_is_up(l))) {
if (l->state == LINK_ESTABLISHING)
rc = TIPC_LINK_UP_EVT;
goto drop;
}
- /* Don't send probe at next timeout expiration */
- l->silent_intv_cnt = 0;
-
/* Drop if outside receive window */
if (unlikely(less(seqno, rcv_nxt) || more(seqno, win_lim))) {
l->stats.duplicates++;
/* Deliver packet */
l->rcv_nxt++;
l->stats.recv_pkts++;
- if (!tipc_data_input(l, skb, l->inputq))
- rc |= tipc_link_input(l, skb, l->inputq);
+
+ if (unlikely(msg_user(hdr) == TUNNEL_PROTOCOL))
+ rc |= tipc_link_tnl_rcv(l, skb, l->inputq);
+ else if (!tipc_data_input(l, skb, l->inputq))
+ rc |= tipc_link_input(l, skb, l->inputq, &l->reasm_buf);
if (unlikely(++l->rcv_unacked >= TIPC_MIN_LINK_WIN))
rc |= tipc_link_build_state_msg(l, xmitq);
if (unlikely(rc & ~TIPC_LINK_SND_STATE))
break;
- } while ((skb = __skb_dequeue(defq)));
+ } while ((skb = __tipc_skb_dequeue(defq, l->rcv_nxt)));
return rc;
drop:
struct tipc_mon_state *mstate = &l->mon_state;
int dlen = 0;
void *data;
+ u16 glen = 0;
/* Don't send protocol message during reset or link failover */
if (tipc_link_is_blocked(l))
rcvgap = buf_seqno(skb_peek(dfq)) - l->rcv_nxt;
skb = tipc_msg_create(LINK_PROTOCOL, mtyp, INT_H_SIZE,
- tipc_max_domain_size, l->addr,
- tipc_own_addr(l->net), 0, 0, 0);
+ tipc_max_domain_size + MAX_GAP_ACK_BLKS_SZ,
+ l->addr, tipc_own_addr(l->net), 0, 0, 0);
if (!skb)
return;
msg_set_bc_gap(hdr, link_bc_rcv_gap(bcl));
msg_set_probe(hdr, probe);
msg_set_is_keepalive(hdr, probe || probe_reply);
- tipc_mon_prep(l->net, data, &dlen, mstate, l->bearer_id);
- msg_set_size(hdr, INT_H_SIZE + dlen);
- skb_trim(skb, INT_H_SIZE + dlen);
+ if (l->peer_caps & TIPC_GAP_ACK_BLOCK)
+ glen = tipc_build_gap_ack_blks(l, data);
+ tipc_mon_prep(l->net, data + glen, &dlen, mstate, l->bearer_id);
+ msg_set_size(hdr, INT_H_SIZE + glen + dlen);
+ skb_trim(skb, INT_H_SIZE + glen + dlen);
l->stats.sent_states++;
l->rcv_unacked = 0;
} else {
void tipc_link_tnl_prepare(struct tipc_link *l, struct tipc_link *tnl,
int mtyp, struct sk_buff_head *xmitq)
{
+ struct sk_buff_head *fdefq = &tnl->failover_deferdq;
struct sk_buff *skb, *tnlskb;
struct tipc_msg *hdr, tnlhdr;
struct sk_buff_head *queue = &l->transmq;
/* Initialize reusable tunnel packet header */
tipc_msg_init(tipc_own_addr(l->net), &tnlhdr, TUNNEL_PROTOCOL,
mtyp, INT_H_SIZE, l->addr);
- pktcnt = skb_queue_len(&l->transmq) + skb_queue_len(&l->backlogq);
+ if (mtyp == SYNCH_MSG)
+ pktcnt = l->snd_nxt - buf_seqno(skb_peek(&l->transmq));
+ else
+ pktcnt = skb_queue_len(&l->transmq);
+ pktcnt += skb_queue_len(&l->backlogq);
msg_set_msgcnt(&tnlhdr, pktcnt);
msg_set_bearer_id(&tnlhdr, l->peer_bearer_id);
tnl:
tnl->drop_point = l->rcv_nxt;
tnl->failover_reasm_skb = l->reasm_buf;
l->reasm_buf = NULL;
+
+ /* Failover the link's deferdq */
+ if (unlikely(!skb_queue_empty(fdefq))) {
+ pr_warn("Link failover deferdq not empty: %d!\n",
+ skb_queue_len(fdefq));
+ __skb_queue_purge(fdefq);
+ }
+ skb_queue_splice_init(&l->deferdq, fdefq);
}
}
struct sk_buff_head *xmitq)
{
struct tipc_msg *hdr = buf_msg(skb);
+ struct tipc_gap_ack_blks *ga = NULL;
u16 rcvgap = 0;
u16 ack = msg_ack(hdr);
u16 gap = msg_seq_gap(hdr);
u16 dlen = msg_data_sz(hdr);
int mtyp = msg_type(hdr);
bool reply = msg_probe(hdr);
+ u16 glen = 0;
void *data;
char *if_name;
int rc = 0;
rc = TIPC_LINK_UP_EVT;
break;
}
- tipc_mon_rcv(l->net, data, dlen, l->addr,
+
+ /* Receive Gap ACK blocks from peer if any */
+ if (l->peer_caps & TIPC_GAP_ACK_BLOCK) {
+ ga = (struct tipc_gap_ack_blks *)data;
+ glen = ntohs(ga->len);
+ /* sanity check: if failed, ignore Gap ACK blocks */
+ if (glen != tipc_gap_ack_blks_sz(ga->gack_cnt))
+ ga = NULL;
+ }
+
+ tipc_mon_rcv(l->net, data + glen, dlen - glen, l->addr,
&l->mon_state, l->bearer_id);
/* Send NACK if peer has sent pkts we haven't received yet */
if (rcvgap || reply)
tipc_link_build_proto_msg(l, STATE_MSG, 0, reply,
rcvgap, 0, 0, xmitq);
- tipc_link_release_pkts(l, ack);
+
+ tipc_link_advance_transmq(l, ack, gap, ga, xmitq);
/* If NACK, retransmit will now start at right position */
- if (gap) {
- rc = tipc_link_retrans(l, l, ack + 1, ack + gap, xmitq);
+ if (gap)
l->stats.recv_nacks++;
- }
tipc_link_advance_backlog(l, xmitq);
if (unlikely(!skb_queue_empty(&l->wakeupq)))
__be32 hdr[15];
};
+/* struct tipc_gap_ack - TIPC Gap ACK block
+ * @ack: seqno of the last consecutive packet in link deferdq
+ * @gap: number of gap packets since the last ack
+ *
+ * E.g:
+ * link deferdq: 1 2 3 4 10 11 13 14 15 20
+ * --> Gap ACK blocks: <4, 5>, <11, 1>, <15, 4>, <20, 0>
+ */
+struct tipc_gap_ack {
+ __be16 ack;
+ __be16 gap;
+};
+
+/* struct tipc_gap_ack_blks
+ * @len: actual length of the record
+ * @gack_cnt: number of Gap ACK blocks in the record
+ * @gacks: array of Gap ACK blocks
+ */
+struct tipc_gap_ack_blks {
+ __be16 len;
+ u8 gack_cnt;
+ u8 reserved;
+ struct tipc_gap_ack gacks[];
+};
+
+#define tipc_gap_ack_blks_sz(n) (sizeof(struct tipc_gap_ack_blks) + \
+ sizeof(struct tipc_gap_ack) * (n))
+
+#define MAX_GAP_ACK_BLKS 32
+#define MAX_GAP_ACK_BLKS_SZ tipc_gap_ack_blks_sz(MAX_GAP_ACK_BLKS)
+
static inline struct tipc_msg *buf_msg(struct sk_buff *skb)
{
return (struct tipc_msg *)skb->data;
tipc_skb_queue_splice_tail(&tmp, head);
}
+/* __tipc_skb_dequeue() - dequeue the head skb according to expected seqno
+ * @list: list to be dequeued from
+ * @seqno: seqno of the expected msg
+ *
+ * returns skb dequeued from the list if its seqno is less than or equal to
+ * the expected one, otherwise the skb is still hold
+ *
+ * Note: must be used with appropriate locks held only
+ */
+static inline struct sk_buff *__tipc_skb_dequeue(struct sk_buff_head *list,
+ u16 seqno)
+{
+ struct sk_buff *skb = skb_peek(list);
+
+ if (skb && less_eq(buf_seqno(skb), seqno)) {
+ __skb_unlink(skb, list);
+ return skb;
+ }
+ return NULL;
+}
+
#endif
for (; i < TIPC_NAMETBL_SIZE; i++) {
head = &tn->nametbl->services[i];
- if (*last_type) {
+ if (*last_type ||
+ (!i && *last_key && (*last_lower == *last_key))) {
service = tipc_service_find(net, *last_type);
if (!service)
return -EPIPE;
if (msg->rep_type)
tipc_tlv_init(msg->rep, msg->rep_type);
- if (cmd->header)
- (*cmd->header)(msg);
+ if (cmd->header) {
+ err = (*cmd->header)(msg);
+ if (err) {
+ kfree_skb(msg->rep);
+ msg->rep = NULL;
+ return err;
+ }
+ }
arg = nlmsg_new(0, GFP_KERNEL);
if (!arg) {
if (!bearer)
return -EMSGSIZE;
- len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_BEARER_NAME);
+ len = TLV_GET_DATA_LEN(msg->req);
+ len -= offsetof(struct tipc_bearer_config, name);
+ if (len <= 0)
+ return -EINVAL;
+
+ len = min_t(int, len, TIPC_MAX_BEARER_NAME);
if (!string_is_valid(b->name, len))
return -EINVAL;
lc = (struct tipc_link_config *)TLV_DATA(msg->req);
- len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_LINK_NAME);
+ len = TLV_GET_DATA_LEN(msg->req);
+ len -= offsetof(struct tipc_link_config, name);
+ if (len <= 0)
+ return -EINVAL;
+
+ len = min_t(int, len, TIPC_MAX_LINK_NAME);
if (!string_is_valid(lc->name, len))
return -EINVAL;
if (n->capabilities == capabilities)
goto exit;
/* Same node may come back with new capabilities */
- write_lock_bh(&n->lock);
+ tipc_node_write_lock(n);
n->capabilities = capabilities;
for (bearer_id = 0; bearer_id < MAX_BEARERS; bearer_id++) {
l = n->links[bearer_id].link;
if (l)
tipc_link_update_caps(l, capabilities);
}
- write_unlock_bh(&n->lock);
+ tipc_node_write_unlock_fast(n);
+
/* Calculate cluster capabilities */
tn->capabilities = TIPC_NODE_CAPABILITIES;
list_for_each_entry_rcu(temp_node, &tn->node_list, list) {
TIPC_BCAST_RCAST = (1 << 4),
TIPC_NODE_ID128 = (1 << 5),
TIPC_LINK_PROTO_SEQNO = (1 << 6),
- TIPC_MCAST_RBCTL = (1 << 7)
+ TIPC_MCAST_RBCTL = (1 << 7),
+ TIPC_GAP_ACK_BLOCK = (1 << 8)
};
#define TIPC_NODE_CAPABILITIES (TIPC_SYN_BIT | \
TIPC_BLOCK_FLOWCTL | \
TIPC_NODE_ID128 | \
TIPC_LINK_PROTO_SEQNO | \
- TIPC_MCAST_RBCTL)
+ TIPC_MCAST_RBCTL | \
+ TIPC_GAP_ACK_BLOCK)
#define INVALID_BEARER_ID -1
void tipc_node_stop(struct net *net);
#include <linux/sysctl.h>
+static int zero;
+static int one = 1;
static struct ctl_table_header *tipc_ctl_hdr;
static struct ctl_table tipc_table[] = {
.data = &sysctl_tipc_rmem,
.maxlen = sizeof(sysctl_tipc_rmem),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &one,
},
{
.procname = "named_timeout",
.data = &sysctl_tipc_named_timeout,
.maxlen = sizeof(sysctl_tipc_named_timeout),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
},
{
.procname = "sk_filter",
static void tls_device_free_ctx(struct tls_context *ctx)
{
- if (ctx->tx_conf == TLS_HW)
+ if (ctx->tx_conf == TLS_HW) {
kfree(tls_offload_ctx_tx(ctx));
+ kfree(ctx->tx.rec_seq);
+ kfree(ctx->tx.iv);
+ }
if (ctx->rx_conf == TLS_HW)
kfree(tls_offload_ctx_rx(ctx));
}
EXPORT_SYMBOL(tls_device_sk_destruct);
+void tls_device_free_resources_tx(struct sock *sk)
+{
+ struct tls_context *tls_ctx = tls_get_ctx(sk);
+
+ tls_free_partial_record(sk, tls_ctx);
+}
+
static void tls_append_frag(struct tls_record_info *record,
struct page_frag *pfrag,
int size)
return tls_push_sg(sk, ctx, sg, offset, flags);
}
+bool tls_free_partial_record(struct sock *sk, struct tls_context *ctx)
+{
+ struct scatterlist *sg;
+
+ sg = ctx->partially_sent_record;
+ if (!sg)
+ return false;
+
+ while (1) {
+ put_page(sg_page(sg));
+ sk_mem_uncharge(sk, sg->length);
+
+ if (sg_is_last(sg))
+ break;
+ sg++;
+ }
+ ctx->partially_sent_record = NULL;
+ return true;
+}
+
static void tls_write_space(struct sock *sk)
{
struct tls_context *ctx = tls_get_ctx(sk);
kfree(ctx->tx.rec_seq);
kfree(ctx->tx.iv);
tls_sw_free_resources_tx(sk);
+#ifdef CONFIG_TLS_DEVICE
+ } else if (ctx->tx_conf == TLS_HW) {
+ tls_device_free_resources_tx(sk);
+#endif
}
if (ctx->rx_conf == TLS_SW) {
return err;
}
+ } else {
+ *zc = false;
}
rxm->full_len -= padding_length(ctx, tls_ctx, skb);
/* Free up un-sent records in tx_list. First, free
* the partially sent record if any at head of tx_list.
*/
- if (tls_ctx->partially_sent_record) {
- struct scatterlist *sg = tls_ctx->partially_sent_record;
-
- while (1) {
- put_page(sg_page(sg));
- sk_mem_uncharge(sk, sg->length);
-
- if (sg_is_last(sg))
- break;
- sg++;
- }
-
- tls_ctx->partially_sent_record = NULL;
-
+ if (tls_free_partial_record(sk, tls_ctx)) {
rec = list_first_entry(&ctx->tx_list,
struct tls_rec, list);
list_del(&rec->list);
struct unix_sock *u = unix_sk(sk);
struct sk_buff *skb, *last;
long timeo;
+ int skip;
int err;
- int peeked, skip;
err = -EOPNOTSUPP;
if (flags&MSG_OOB)
mutex_lock(&u->iolock);
skip = sk_peek_offset(sk, flags);
- skb = __skb_try_recv_datagram(sk, flags, NULL, &peeked, &skip,
- &err, &last);
+ skb = __skb_try_recv_datagram(sk, flags, NULL, &skip, &err,
+ &last);
if (skb)
break;
.doit = nl80211_associate,
.flags = GENL_UNS_ADMIN_PERM,
.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
- NL80211_FLAG_NEED_RTNL,
+ NL80211_FLAG_NEED_RTNL |
+ NL80211_FLAG_CLEAR_SKB,
},
{
.cmd = NL80211_CMD_DEAUTHENTICATE,
.doit = nl80211_connect,
.flags = GENL_UNS_ADMIN_PERM,
.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
- NL80211_FLAG_NEED_RTNL,
+ NL80211_FLAG_NEED_RTNL |
+ NL80211_FLAG_CLEAR_SKB,
},
{
.cmd = NL80211_CMD_UPDATE_CONNECT_PARAMS,
.doit = nl80211_update_connect_params,
.flags = GENL_ADMIN_PERM,
.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
- NL80211_FLAG_NEED_RTNL,
+ NL80211_FLAG_NEED_RTNL |
+ NL80211_FLAG_CLEAR_SKB,
},
{
.cmd = NL80211_CMD_DISCONNECT,
.doit = nl80211_setdel_pmksa,
.flags = GENL_UNS_ADMIN_PERM,
.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
- NL80211_FLAG_NEED_RTNL,
+ NL80211_FLAG_NEED_RTNL |
+ NL80211_FLAG_CLEAR_SKB,
},
{
.cmd = NL80211_CMD_DEL_PMKSA,
.dumpit = nl80211_vendor_cmd_dump,
.flags = GENL_UNS_ADMIN_PERM,
.internal_flags = NL80211_FLAG_NEED_WIPHY |
- NL80211_FLAG_NEED_RTNL,
+ NL80211_FLAG_NEED_RTNL |
+ NL80211_FLAG_CLEAR_SKB,
},
{
.cmd = NL80211_CMD_SET_QOS_MAP,
.cmd = NL80211_CMD_SET_PMK,
.doit = nl80211_set_pmk,
.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
- NL80211_FLAG_NEED_RTNL,
+ NL80211_FLAG_NEED_RTNL |
+ NL80211_FLAG_CLEAR_SKB,
},
{
.cmd = NL80211_CMD_DEL_PMK,
return dfs_region1;
}
+static void reg_wmm_rules_intersect(const struct ieee80211_wmm_ac *wmm_ac1,
+ const struct ieee80211_wmm_ac *wmm_ac2,
+ struct ieee80211_wmm_ac *intersect)
+{
+ intersect->cw_min = max_t(u16, wmm_ac1->cw_min, wmm_ac2->cw_min);
+ intersect->cw_max = max_t(u16, wmm_ac1->cw_max, wmm_ac2->cw_max);
+ intersect->cot = min_t(u16, wmm_ac1->cot, wmm_ac2->cot);
+ intersect->aifsn = max_t(u8, wmm_ac1->aifsn, wmm_ac2->aifsn);
+}
+
/*
* Helper for regdom_intersect(), this does the real
* mathematical intersection fun
struct ieee80211_freq_range *freq_range;
const struct ieee80211_power_rule *power_rule1, *power_rule2;
struct ieee80211_power_rule *power_rule;
+ const struct ieee80211_wmm_rule *wmm_rule1, *wmm_rule2;
+ struct ieee80211_wmm_rule *wmm_rule;
u32 freq_diff, max_bandwidth1, max_bandwidth2;
freq_range1 = &rule1->freq_range;
power_rule2 = &rule2->power_rule;
power_rule = &intersected_rule->power_rule;
+ wmm_rule1 = &rule1->wmm_rule;
+ wmm_rule2 = &rule2->wmm_rule;
+ wmm_rule = &intersected_rule->wmm_rule;
+
freq_range->start_freq_khz = max(freq_range1->start_freq_khz,
freq_range2->start_freq_khz);
freq_range->end_freq_khz = min(freq_range1->end_freq_khz,
intersected_rule->dfs_cac_ms = max(rule1->dfs_cac_ms,
rule2->dfs_cac_ms);
+ if (rule1->has_wmm && rule2->has_wmm) {
+ u8 ac;
+
+ for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) {
+ reg_wmm_rules_intersect(&wmm_rule1->client[ac],
+ &wmm_rule2->client[ac],
+ &wmm_rule->client[ac]);
+ reg_wmm_rules_intersect(&wmm_rule1->ap[ac],
+ &wmm_rule2->ap[ac],
+ &wmm_rule->ap[ac]);
+ }
+
+ intersected_rule->has_wmm = true;
+ } else if (rule1->has_wmm) {
+ *wmm_rule = *wmm_rule1;
+ intersected_rule->has_wmm = true;
+ } else if (rule2->has_wmm) {
+ *wmm_rule = *wmm_rule2;
+ intersected_rule->has_wmm = true;
+ } else {
+ intersected_rule->has_wmm = false;
+ }
+
if (!is_valid_reg_rule(intersected_rule))
return -EINVAL;
/* copy subelement as we need to change its content to
* mark an ie after it is processed.
*/
- sub_copy = kmalloc(subie_len, gfp);
+ sub_copy = kmemdup(subelement, subie_len, gfp);
if (!sub_copy)
return 0;
- memcpy(sub_copy, subelement, subie_len);
pos = &new_ie[0];
else if (rate->bw == RATE_INFO_BW_HE_RU &&
rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_26)
result = rates_26[rate->he_gi];
- else if (WARN(1, "invalid HE MCS: bw:%d, ru:%d\n",
- rate->bw, rate->he_ru_alloc))
+ else {
+ WARN(1, "invalid HE MCS: bw:%d, ru:%d\n",
+ rate->bw, rate->he_ru_alloc);
return 0;
+ }
/* now scale to the appropriate MCS */
tmp = result;
#define asm_volatile_goto(x...) asm volatile("invalid use of asm_volatile_goto")
#endif
+#define volatile(x...) volatile("")
#endif
if (!addr)
return;
sym = ksym_search(addr);
+ if (!sym) {
+ printf("ksym not found. Is kallsyms loaded?\n");
+ return;
+ }
+
if (PRINT_RAW_ADDR)
printf("%s/%llx;", sym->name, addr);
else
for (i = 0; i < max; i++) {
if (counts[i].ip > PAGE_OFFSET) {
sym = ksym_search(counts[i].ip);
+ if (!sym) {
+ printf("ksym not found. Is kallsyms loaded?\n");
+ continue;
+ }
+
printf("0x%-17llx %-32s %u\n", counts[i].ip, sym->name,
counts[i].count);
} else {
bpf_map_lookup_elem(map_fd[0], &next_key, &value);
assert(next_key == value);
sym = ksym_search(value);
- printf(" %s", sym->name);
key = next_key;
+ if (!sym) {
+ printf("ksym not found. Is kallsyms loaded?\n");
+ continue;
+ }
+
+ printf(" %s", sym->name);
}
if (key)
printf("\n");
if (!addr)
return;
sym = ksym_search(addr);
+ if (!sym) {
+ printf("ksym not found. Is kallsyms loaded?\n");
+ return;
+ }
+
printf("%s;", sym->name);
if (!strcmp(sym->name, "sys_read"))
sys_read_seen = true;
"$(if $(part-of-module),1,0)" "$(@)";
recordmcount_source := $(srctree)/scripts/recordmcount.pl
endif # BUILD_C_RECORDMCOUNT
-cmd_record_mcount = \
- if [ "$(findstring $(CC_FLAGS_FTRACE),$(_c_flags))" = \
- "$(CC_FLAGS_FTRACE)" ]; then \
- $(sub_cmd_record_mcount) \
- fi
+cmd_record_mcount = $(if $(findstring $(strip $(CC_FLAGS_FTRACE)),$(_c_flags)), \
+ $(sub_cmd_record_mcount))
endif # CC_USING_RECORD_MCOUNT
endif # CONFIG_FTRACE_MCOUNT_RECORD
while ($fmt =~ /(\%[\*\d\.]*p(\w))/g) {
$specifier = $1;
$extension = $2;
- if ($extension !~ /[SsBKRraEhMmIiUDdgVCbGNOx]/) {
+ if ($extension !~ /[SsBKRraEhMmIiUDdgVCbGNOxt]/) {
$bad_specifier = $specifier;
last;
}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+// Author: Kirill Smelkov (kirr@nexedi.com)
+//
+// Search for stream-like files that are using nonseekable_open and convert
+// them to stream_open. A stream-like file is a file that does not use ppos in
+// its read and write. Rationale for the conversion is to avoid deadlock in
+// between read and write.
+
+virtual report
+virtual patch
+virtual explain // explain decisions in the patch (SPFLAGS="-D explain")
+
+// stream-like reader & writer - ones that do not depend on f_pos.
+@ stream_reader @
+identifier readstream, ppos;
+identifier f, buf, len;
+type loff_t;
+@@
+ ssize_t readstream(struct file *f, char *buf, size_t len, loff_t *ppos)
+ {
+ ... when != ppos
+ }
+
+@ stream_writer @
+identifier writestream, ppos;
+identifier f, buf, len;
+type loff_t;
+@@
+ ssize_t writestream(struct file *f, const char *buf, size_t len, loff_t *ppos)
+ {
+ ... when != ppos
+ }
+
+
+// a function that blocks
+@ blocks @
+identifier block_f;
+identifier wait_event =~ "^wait_event_.*";
+@@
+ block_f(...) {
+ ... when exists
+ wait_event(...)
+ ... when exists
+ }
+
+// stream_reader that can block inside.
+//
+// XXX wait_* can be called not directly from current function (e.g. func -> f -> g -> wait())
+// XXX currently reader_blocks supports only direct and 1-level indirect cases.
+@ reader_blocks_direct @
+identifier stream_reader.readstream;
+identifier wait_event =~ "^wait_event_.*";
+@@
+ readstream(...)
+ {
+ ... when exists
+ wait_event(...)
+ ... when exists
+ }
+
+@ reader_blocks_1 @
+identifier stream_reader.readstream;
+identifier blocks.block_f;
+@@
+ readstream(...)
+ {
+ ... when exists
+ block_f(...)
+ ... when exists
+ }
+
+@ reader_blocks depends on reader_blocks_direct || reader_blocks_1 @
+identifier stream_reader.readstream;
+@@
+ readstream(...) {
+ ...
+ }
+
+
+// file_operations + whether they have _any_ .read, .write, .llseek ... at all.
+//
+// XXX add support for file_operations xxx[N] = ... (sound/core/pcm_native.c)
+@ fops0 @
+identifier fops;
+@@
+ struct file_operations fops = {
+ ...
+ };
+
+@ has_read @
+identifier fops0.fops;
+identifier read_f;
+@@
+ struct file_operations fops = {
+ .read = read_f,
+ };
+
+@ has_read_iter @
+identifier fops0.fops;
+identifier read_iter_f;
+@@
+ struct file_operations fops = {
+ .read_iter = read_iter_f,
+ };
+
+@ has_write @
+identifier fops0.fops;
+identifier write_f;
+@@
+ struct file_operations fops = {
+ .write = write_f,
+ };
+
+@ has_write_iter @
+identifier fops0.fops;
+identifier write_iter_f;
+@@
+ struct file_operations fops = {
+ .write_iter = write_iter_f,
+ };
+
+@ has_llseek @
+identifier fops0.fops;
+identifier llseek_f;
+@@
+ struct file_operations fops = {
+ .llseek = llseek_f,
+ };
+
+@ has_no_llseek @
+identifier fops0.fops;
+@@
+ struct file_operations fops = {
+ .llseek = no_llseek,
+ };
+
+@ has_mmap @
+identifier fops0.fops;
+identifier mmap_f;
+@@
+ struct file_operations fops = {
+ .mmap = mmap_f,
+ };
+
+@ has_copy_file_range @
+identifier fops0.fops;
+identifier copy_file_range_f;
+@@
+ struct file_operations fops = {
+ .copy_file_range = copy_file_range_f,
+ };
+
+@ has_remap_file_range @
+identifier fops0.fops;
+identifier remap_file_range_f;
+@@
+ struct file_operations fops = {
+ .remap_file_range = remap_file_range_f,
+ };
+
+@ has_splice_read @
+identifier fops0.fops;
+identifier splice_read_f;
+@@
+ struct file_operations fops = {
+ .splice_read = splice_read_f,
+ };
+
+@ has_splice_write @
+identifier fops0.fops;
+identifier splice_write_f;
+@@
+ struct file_operations fops = {
+ .splice_write = splice_write_f,
+ };
+
+
+// file_operations that is candidate for stream_open conversion - it does not
+// use mmap and other methods that assume @offset access to file.
+//
+// XXX for simplicity require no .{read/write}_iter and no .splice_{read/write} for now.
+// XXX maybe_steam.fops cannot be used in other rules - it gives "bad rule maybe_stream or bad variable fops".
+@ maybe_stream depends on (!has_llseek || has_no_llseek) && !has_mmap && !has_copy_file_range && !has_remap_file_range && !has_read_iter && !has_write_iter && !has_splice_read && !has_splice_write @
+identifier fops0.fops;
+@@
+ struct file_operations fops = {
+ };
+
+
+// ---- conversions ----
+
+// XXX .open = nonseekable_open -> .open = stream_open
+// XXX .open = func -> openfunc -> nonseekable_open
+
+// read & write
+//
+// if both are used in the same file_operations together with an opener -
+// under that conditions we can use stream_open instead of nonseekable_open.
+@ fops_rw depends on maybe_stream @
+identifier fops0.fops, openfunc;
+identifier stream_reader.readstream;
+identifier stream_writer.writestream;
+@@
+ struct file_operations fops = {
+ .open = openfunc,
+ .read = readstream,
+ .write = writestream,
+ };
+
+@ report_rw depends on report @
+identifier fops_rw.openfunc;
+position p1;
+@@
+ openfunc(...) {
+ <...
+ nonseekable_open@p1
+ ...>
+ }
+
+@ script:python depends on report && reader_blocks @
+fops << fops0.fops;
+p << report_rw.p1;
+@@
+coccilib.report.print_report(p[0],
+ "ERROR: %s: .read() can deadlock .write(); change nonseekable_open -> stream_open to fix." % (fops,))
+
+@ script:python depends on report && !reader_blocks @
+fops << fops0.fops;
+p << report_rw.p1;
+@@
+coccilib.report.print_report(p[0],
+ "WARNING: %s: .read() and .write() have stream semantic; safe to change nonseekable_open -> stream_open." % (fops,))
+
+
+@ explain_rw_deadlocked depends on explain && reader_blocks @
+identifier fops_rw.openfunc;
+@@
+ openfunc(...) {
+ <...
+- nonseekable_open
++ nonseekable_open /* read & write (was deadlock) */
+ ...>
+ }
+
+
+@ explain_rw_nodeadlock depends on explain && !reader_blocks @
+identifier fops_rw.openfunc;
+@@
+ openfunc(...) {
+ <...
+- nonseekable_open
++ nonseekable_open /* read & write (no direct deadlock) */
+ ...>
+ }
+
+@ patch_rw depends on patch @
+identifier fops_rw.openfunc;
+@@
+ openfunc(...) {
+ <...
+- nonseekable_open
++ stream_open
+ ...>
+ }
+
+
+// read, but not write
+@ fops_r depends on maybe_stream && !has_write @
+identifier fops0.fops, openfunc;
+identifier stream_reader.readstream;
+@@
+ struct file_operations fops = {
+ .open = openfunc,
+ .read = readstream,
+ };
+
+@ report_r depends on report @
+identifier fops_r.openfunc;
+position p1;
+@@
+ openfunc(...) {
+ <...
+ nonseekable_open@p1
+ ...>
+ }
+
+@ script:python depends on report @
+fops << fops0.fops;
+p << report_r.p1;
+@@
+coccilib.report.print_report(p[0],
+ "WARNING: %s: .read() has stream semantic; safe to change nonseekable_open -> stream_open." % (fops,))
+
+@ explain_r depends on explain @
+identifier fops_r.openfunc;
+@@
+ openfunc(...) {
+ <...
+- nonseekable_open
++ nonseekable_open /* read only */
+ ...>
+ }
+
+@ patch_r depends on patch @
+identifier fops_r.openfunc;
+@@
+ openfunc(...) {
+ <...
+- nonseekable_open
++ stream_open
+ ...>
+ }
+
+
+// write, but not read
+@ fops_w depends on maybe_stream && !has_read @
+identifier fops0.fops, openfunc;
+identifier stream_writer.writestream;
+@@
+ struct file_operations fops = {
+ .open = openfunc,
+ .write = writestream,
+ };
+
+@ report_w depends on report @
+identifier fops_w.openfunc;
+position p1;
+@@
+ openfunc(...) {
+ <...
+ nonseekable_open@p1
+ ...>
+ }
+
+@ script:python depends on report @
+fops << fops0.fops;
+p << report_w.p1;
+@@
+coccilib.report.print_report(p[0],
+ "WARNING: %s: .write() has stream semantic; safe to change nonseekable_open -> stream_open." % (fops,))
+
+@ explain_w depends on explain @
+identifier fops_w.openfunc;
+@@
+ openfunc(...) {
+ <...
+- nonseekable_open
++ nonseekable_open /* write only */
+ ...>
+ }
+
+@ patch_w depends on patch @
+identifier fops_w.openfunc;
+@@
+ openfunc(...) {
+ <...
+- nonseekable_open
++ stream_open
+ ...>
+ }
+
+
+// no read, no write - don't change anything
( id
| (T2)dev_get_drvdata(&id->dev)
| (T3)platform_get_drvdata(id)
+| &id->dev
);
| return@p2 ...;
)
-/// Use ARRAY_SIZE instead of dividing sizeof array with sizeof an element
+/// Correct the size argument to alloc functions
///
//# This makes an effort to find cases where the argument to sizeof is wrong
//# in memory allocation functions by checking the type of the allocated memory
case KEY_DOWN:
break;
case KEY_BACKSPACE:
- case 127:
+ case 8: /* ^H */
+ case 127: /* ^? */
if (pos) {
wattrset(dialog, dlg.inputbox.atr);
if (input_x == 0) {
state->match_direction = FIND_NEXT_MATCH_UP;
*ans = get_mext_match(state->pattern,
state->match_direction);
- } else if (key == KEY_BACKSPACE || key == 127) {
+ } else if (key == KEY_BACKSPACE || key == 8 || key == 127) {
state->pattern[strlen(state->pattern)-1] = '\0';
adj_match_dir(&state->match_direction);
} else
case KEY_F(F_EXIT):
case KEY_F(F_BACK):
break;
- case 127:
+ case 8: /* ^H */
+ case 127: /* ^? */
case KEY_BACKSPACE:
if (cursor_position > 0) {
memmove(&result[cursor_position-1],
info()
{
if [ "${quiet}" != "silent_" ]; then
- printf " %-7s %s\n" ${1} ${2}
+ printf " %-7s %s\n" "${1}" "${2}"
fi
}
fi
}
+# generate .BTF typeinfo from DWARF debuginfo
+gen_btf()
+{
+ local pahole_ver;
+
+ pahole_ver=$(${PAHOLE} --version | sed -E 's/v([0-9]+)\.([0-9]+)/\1\2/')
+ if [ "${pahole_ver}" -lt "113" ]; then
+ info "BTF" "${1}: pahole version $(${PAHOLE} --version) is too old, need at least v1.13"
+ exit 0
+ fi
+
+ info "BTF" ${1}
+ LLVM_OBJCOPY=${OBJCOPY} ${PAHOLE} -J ${1}
+}
# Create ${2} .o file with all symbols from the ${1} object file
kallsyms()
info LD vmlinux
vmlinux_link "${kallsymso}" vmlinux
+if [ -n "${CONFIG_DEBUG_INFO_BTF}" ]; then
+ gen_btf vmlinux
+fi
+
if [ -n "${CONFIG_BUILDTIME_EXTABLE_SORT}" ]; then
info SORTEX vmlinux
sortextable vmlinux
info->sechdrs[sym->st_shndx].sh_offset -
(info->hdr->e_type != ET_REL ?
info->sechdrs[sym->st_shndx].sh_addr : 0);
- crc = *crcp;
+ crc = TO_NATIVE(*crcp);
}
sym_update_crc(symname + strlen("__crc_"), mod, crc,
export);
source "security/integrity/Kconfig"
+choice
+ prompt "First legacy 'major LSM' to be initialized"
+ default DEFAULT_SECURITY_SELINUX if SECURITY_SELINUX
+ default DEFAULT_SECURITY_SMACK if SECURITY_SMACK
+ default DEFAULT_SECURITY_TOMOYO if SECURITY_TOMOYO
+ default DEFAULT_SECURITY_APPARMOR if SECURITY_APPARMOR
+ default DEFAULT_SECURITY_DAC
+
+ help
+ This choice is there only for converting CONFIG_DEFAULT_SECURITY
+ in old kernel configs to CONFIG_LSM in new kernel configs. Don't
+ change this choice unless you are creating a fresh kernel config,
+ for this choice will be ignored after CONFIG_LSM has been set.
+
+ Selects the legacy "major security module" that will be
+ initialized first. Overridden by non-default CONFIG_LSM.
+
+ config DEFAULT_SECURITY_SELINUX
+ bool "SELinux" if SECURITY_SELINUX=y
+
+ config DEFAULT_SECURITY_SMACK
+ bool "Simplified Mandatory Access Control" if SECURITY_SMACK=y
+
+ config DEFAULT_SECURITY_TOMOYO
+ bool "TOMOYO" if SECURITY_TOMOYO=y
+
+ config DEFAULT_SECURITY_APPARMOR
+ bool "AppArmor" if SECURITY_APPARMOR=y
+
+ config DEFAULT_SECURITY_DAC
+ bool "Unix Discretionary Access Controls"
+
+endchoice
+
config LSM
string "Ordered list of enabled LSMs"
+ default "yama,loadpin,safesetid,integrity,smack,selinux,tomoyo,apparmor" if DEFAULT_SECURITY_SMACK
+ default "yama,loadpin,safesetid,integrity,apparmor,selinux,smack,tomoyo" if DEFAULT_SECURITY_APPARMOR
+ default "yama,loadpin,safesetid,integrity,tomoyo" if DEFAULT_SECURITY_TOMOYO
+ default "yama,loadpin,safesetid,integrity" if DEFAULT_SECURITY_DAC
default "yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor"
help
A comma-separated list of LSMs, in initialization order.
bool aa_g_paranoid_load = true;
module_param_named(paranoid_load, aa_g_paranoid_load, aabool, S_IRUGO);
+static int param_get_aaintbool(char *buffer, const struct kernel_param *kp);
+static int param_set_aaintbool(const char *val, const struct kernel_param *kp);
+#define param_check_aaintbool param_check_int
+static const struct kernel_param_ops param_ops_aaintbool = {
+ .set = param_set_aaintbool,
+ .get = param_get_aaintbool
+};
/* Boot time disable flag */
static int apparmor_enabled __lsm_ro_after_init = 1;
-module_param_named(enabled, apparmor_enabled, int, 0444);
+module_param_named(enabled, apparmor_enabled, aaintbool, 0444);
static int __init apparmor_enabled_setup(char *str)
{
return param_get_uint(buffer, kp);
}
+/* Can only be set before AppArmor is initialized (i.e. on boot cmdline). */
+static int param_set_aaintbool(const char *val, const struct kernel_param *kp)
+{
+ struct kernel_param kp_local;
+ bool value;
+ int error;
+
+ if (apparmor_initialized)
+ return -EPERM;
+
+ /* Create local copy, with arg pointing to bool type. */
+ value = !!*((int *)kp->arg);
+ memcpy(&kp_local, kp, sizeof(kp_local));
+ kp_local.arg = &value;
+
+ error = param_set_bool(val, &kp_local);
+ if (!error)
+ *((int *)kp->arg) = *((bool *)kp_local.arg);
+ return error;
+}
+
+/*
+ * To avoid changing /sys/module/apparmor/parameters/enabled from Y/N to
+ * 1/0, this converts the "int that is actually bool" back to bool for
+ * display in the /sys filesystem, while keeping it "int" for the LSM
+ * infrastructure.
+ */
+static int param_get_aaintbool(char *buffer, const struct kernel_param *kp)
+{
+ struct kernel_param kp_local;
+ bool value;
+
+ /* Create local copy, with arg pointing to bool type. */
+ value = !!*((int *)kp->arg);
+ memcpy(&kp_local, kp, sizeof(kp_local));
+ kp_local.arg = &value;
+
+ return param_get_bool(buffer, &kp_local);
+}
+
static int param_get_audit(char *buffer, const struct kernel_param *kp)
{
if (!apparmor_enabled)
*/
int TSS_authhmac(unsigned char *digest, const unsigned char *key,
unsigned int keylen, unsigned char *h1,
- unsigned char *h2, unsigned char h3, ...)
+ unsigned char *h2, unsigned int h3, ...)
{
unsigned char paramdigest[SHA1_DIGEST_SIZE];
struct sdesc *sdesc;
int ret;
va_list argp;
+ if (!chip)
+ return -ENODEV;
+
sdesc = init_sdesc(hashalg);
if (IS_ERR(sdesc)) {
pr_info("trusted_key: can't alloc %s\n", hash_alg);
return PTR_ERR(sdesc);
}
- c = h3;
+ c = !!h3;
ret = crypto_shash_init(&sdesc->shash);
if (ret < 0)
goto out;
va_list argp;
int ret;
+ if (!chip)
+ return -ENODEV;
+
bufsize = LOAD32(buffer, TPM_SIZE_OFFSET);
tag = LOAD16(buffer, 0);
ordinal = command;
{
int rc;
+ if (!chip)
+ return -ENODEV;
+
dump_tpm_buf(cmd);
rc = tpm_send(chip, cmd, buflen);
dump_tpm_buf(cmd);
{
int ret;
+ if (!chip)
+ return -ENODEV;
+
INIT_BUF(tb);
store16(tb, TPM_TAG_RQU_COMMAND);
store32(tb, TPM_OIAP_SIZE);
{
int ret;
+ /* encrypted_keys.ko depends on successful load of this module even if
+ * TPM is not used.
+ */
chip = tpm_default_chip();
if (!chip)
- return -ENOENT;
+ return 0;
+
ret = init_digests();
if (ret < 0)
goto err_put;
static void __exit cleanup_trusted(void)
{
- put_device(&chip->dev);
- kfree(digests);
- trusted_shash_release();
- unregister_key_type(&key_type_trusted);
+ if (chip) {
+ put_device(&chip->dev);
+ kfree(digests);
+ trusted_shash_release();
+ unregister_key_type(&key_type_trusted);
+ }
}
late_initcall(init_trusted);
* yama_task_free - check for task_pid to remove from exception list
* @task: task being removed
*/
-void yama_task_free(struct task_struct *task)
+static void yama_task_free(struct task_struct *task)
{
yama_ptracer_del(task, task);
}
* Return 0 on success, -ve on error. -ENOSYS is returned when Yama
* does not handle the given option.
*/
-int yama_task_prctl(int option, unsigned long arg2, unsigned long arg3,
+static int yama_task_prctl(int option, unsigned long arg2, unsigned long arg3,
unsigned long arg4, unsigned long arg5)
{
int rc = -ENOSYS;
*
* Returns 0 if following the ptrace is allowed, -ve on error.
*/
-int yama_ptrace_traceme(struct task_struct *parent)
+static int yama_ptrace_traceme(struct task_struct *parent)
{
int rc = 0;
static int zero;
static int max_scope = YAMA_SCOPE_NO_ATTACH;
-struct ctl_path yama_sysctl_path[] = {
+static struct ctl_path yama_sysctl_path[] = {
{ .procname = "kernel", },
{ .procname = "yama", },
{ }
oss_frame_size = snd_pcm_format_physical_width(params_format(params)) *
params_channels(params) / 8;
+ err = snd_pcm_oss_period_size(substream, params, sparams);
+ if (err < 0)
+ goto failure;
+
+ n = snd_pcm_plug_slave_size(substream, runtime->oss.period_bytes / oss_frame_size);
+ err = snd_pcm_hw_param_near(substream, sparams, SNDRV_PCM_HW_PARAM_PERIOD_SIZE, n, NULL);
+ if (err < 0)
+ goto failure;
+
+ err = snd_pcm_hw_param_near(substream, sparams, SNDRV_PCM_HW_PARAM_PERIODS,
+ runtime->oss.periods, NULL);
+ if (err < 0)
+ goto failure;
+
+ snd_pcm_kernel_ioctl(substream, SNDRV_PCM_IOCTL_DROP, NULL);
+
+ err = snd_pcm_kernel_ioctl(substream, SNDRV_PCM_IOCTL_HW_PARAMS, sparams);
+ if (err < 0) {
+ pcm_dbg(substream->pcm, "HW_PARAMS failed: %i\n", err);
+ goto failure;
+ }
+
#ifdef CONFIG_SND_PCM_OSS_PLUGINS
snd_pcm_oss_plugin_clear(substream);
if (!direct) {
}
#endif
- err = snd_pcm_oss_period_size(substream, params, sparams);
- if (err < 0)
- goto failure;
-
- n = snd_pcm_plug_slave_size(substream, runtime->oss.period_bytes / oss_frame_size);
- err = snd_pcm_hw_param_near(substream, sparams, SNDRV_PCM_HW_PARAM_PERIOD_SIZE, n, NULL);
- if (err < 0)
- goto failure;
-
- err = snd_pcm_hw_param_near(substream, sparams, SNDRV_PCM_HW_PARAM_PERIODS,
- runtime->oss.periods, NULL);
- if (err < 0)
- goto failure;
-
- snd_pcm_kernel_ioctl(substream, SNDRV_PCM_IOCTL_DROP, NULL);
-
- if ((err = snd_pcm_kernel_ioctl(substream, SNDRV_PCM_IOCTL_HW_PARAMS, sparams)) < 0) {
- pcm_dbg(substream->pcm, "HW_PARAMS failed: %i\n", err);
- goto failure;
- }
-
if (runtime->oss.trigger) {
sw_params->start_threshold = 1;
} else {
static int snd_pcm_pre_suspend(struct snd_pcm_substream *substream, int state)
{
struct snd_pcm_runtime *runtime = substream->runtime;
- if (runtime->status->state == SNDRV_PCM_STATE_SUSPENDED)
+ switch (runtime->status->state) {
+ case SNDRV_PCM_STATE_SUSPENDED:
return -EBUSY;
+ /* unresumable PCM state; return -EBUSY for skipping suspend */
+ case SNDRV_PCM_STATE_OPEN:
+ case SNDRV_PCM_STATE_SETUP:
+ case SNDRV_PCM_STATE_DISCONNECTED:
+ return -EBUSY;
+ }
runtime->trigger_master = substream;
return 0;
}
#include <linux/module.h>
#include <linux/delay.h>
#include <linux/mm.h>
+#include <linux/nospec.h>
#include <sound/rawmidi.h>
#include <sound/info.h>
#include <sound/control.h>
return -ENXIO;
if (info->stream < 0 || info->stream > 1)
return -EINVAL;
+ info->stream = array_index_nospec(info->stream, 2);
pstr = &rmidi->streams[info->stream];
if (pstr->substream_count == 0)
return -ENOENT;
snd_seq_oss_synth_make_info(struct seq_oss_devinfo *dp, int dev, struct synth_info *inf)
{
struct seq_oss_synth *rec;
+ struct seq_oss_synthinfo *info = get_synthinfo_nospec(dp, dev);
- if (dev < 0 || dev >= dp->max_synthdev)
+ if (!info)
return -ENXIO;
- if (dp->synths[dev].is_midi) {
+ if (info->is_midi) {
struct midi_info minf;
- snd_seq_oss_midi_make_info(dp, dp->synths[dev].midi_mapped, &minf);
+ snd_seq_oss_midi_make_info(dp, info->midi_mapped, &minf);
inf->synth_type = SYNTH_TYPE_MIDI;
inf->synth_subtype = 0;
inf->nr_voices = 16;
/* fill the info fields */
if (client_info->name[0])
- strlcpy(client->name, client_info->name, sizeof(client->name));
+ strscpy(client->name, client_info->name, sizeof(client->name));
client->filter = client_info->filter;
client->event_lost = client_info->event_lost;
/* set queue name */
if (!info->name[0])
snprintf(info->name, sizeof(info->name), "Queue-%d", q->queue);
- strlcpy(q->name, info->name, sizeof(q->name));
+ strscpy(q->name, info->name, sizeof(q->name));
snd_use_lock_free(&q->use_lock);
return 0;
queuefree(q);
return -EPERM;
}
- strlcpy(q->name, info->name, sizeof(q->name));
+ strscpy(q->name, info->name, sizeof(q->name));
queuefree(q);
return 0;
INIT_LIST_HEAD(&bus->hlink_list);
bus->idx = idx++;
- mutex_init(&bus->lock);
bus->cmd_dma_state = true;
return 0;
INIT_WORK(&bus->unsol_work, snd_hdac_bus_process_unsol_events);
spin_lock_init(&bus->reg_lock);
mutex_init(&bus->cmd_mutex);
+ mutex_init(&bus->lock);
bus->irq = -1;
return 0;
}
dev_dbg(bus->dev, "display power %s\n",
enable ? "enable" : "disable");
+
+ mutex_lock(&bus->lock);
if (enable)
set_bit(idx, &bus->display_power_status);
else
clear_bit(idx, &bus->display_power_status);
if (!acomp || !acomp->ops)
- return;
+ goto unlock;
if (bus->display_power_status) {
if (!bus->display_power_active) {
bus->display_power_active = false;
}
}
+ unlock:
+ mutex_unlock(&bus->lock);
}
EXPORT_SYMBOL_GPL(snd_hdac_display_power);
SND_PCI_QUIRK(0x8086, 0x2040, "Intel DZ77BH-55K", 0),
/* https://bugzilla.kernel.org/show_bug.cgi?id=199607 */
SND_PCI_QUIRK(0x8086, 0x2057, "Intel NUC5i7RYB", 0),
+ /* https://bugs.launchpad.net/bugs/1821663 */
+ SND_PCI_QUIRK(0x8086, 0x2064, "Intel SDP 8086:2064", 0),
/* https://bugzilla.redhat.com/show_bug.cgi?id=1520902 */
SND_PCI_QUIRK(0x8086, 0x2068, "Intel NUC7i3BNB", 0),
/* https://bugzilla.kernel.org/show_bug.cgi?id=198611 */
SND_PCI_QUIRK(0x17aa, 0x367b, "Lenovo IdeaCentre B550", 0),
/* https://bugzilla.redhat.com/show_bug.cgi?id=1572975 */
SND_PCI_QUIRK(0x17aa, 0x36a7, "Lenovo C50 All in one", 0),
+ /* https://bugs.launchpad.net/bugs/1821663 */
+ SND_PCI_QUIRK(0x1631, 0xe017, "Packard Bell NEC IMEDIA 5204", 0),
{}
};
#endif /* CONFIG_PM */
unsigned int scp_resp_header;
unsigned int scp_resp_data[4];
unsigned int scp_resp_count;
- bool alt_firmware_present;
bool startup_check_entered;
bool dsp_reload;
bool dsp_loaded = false;
struct ca0132_spec *spec = codec->spec;
const struct dsp_image_seg *dsp_os_image;
- const struct firmware *fw_entry;
+ const struct firmware *fw_entry = NULL;
/*
* Alternate firmwares for different variants. The Recon3Di apparently
* can use the default firmware, but I'll leave the option in case
case QUIRK_R3D:
case QUIRK_AE5:
if (request_firmware(&fw_entry, DESKTOP_EFX_FILE,
- codec->card->dev) != 0) {
+ codec->card->dev) != 0)
codec_dbg(codec, "Desktop firmware not found.");
- spec->alt_firmware_present = false;
- } else {
+ else
codec_dbg(codec, "Desktop firmware selected.");
- spec->alt_firmware_present = true;
- }
break;
case QUIRK_R3DI:
if (request_firmware(&fw_entry, R3DI_EFX_FILE,
- codec->card->dev) != 0) {
+ codec->card->dev) != 0)
codec_dbg(codec, "Recon3Di alt firmware not detected.");
- spec->alt_firmware_present = false;
- } else {
+ else
codec_dbg(codec, "Recon3Di firmware selected.");
- spec->alt_firmware_present = true;
- }
break;
default:
- spec->alt_firmware_present = false;
break;
}
/*
* Use default ctefx.bin if no alt firmware is detected, or if none
* exists for your particular codec.
*/
- if (!spec->alt_firmware_present) {
+ if (!fw_entry) {
codec_dbg(codec, "Default firmware selected.");
if (request_firmware(&fw_entry, EFX_FILE,
codec->card->dev) != 0)
ALC887_FIXUP_BASS_CHMAP,
ALC1220_FIXUP_GB_DUAL_CODECS,
ALC1220_FIXUP_CLEVO_P950,
- ALC1220_FIXUP_SYSTEM76_ORYP5,
- ALC1220_FIXUP_SYSTEM76_ORYP5_PINS,
+ ALC1220_FIXUP_CLEVO_PB51ED,
+ ALC1220_FIXUP_CLEVO_PB51ED_PINS,
};
static void alc889_fixup_coef(struct hda_codec *codec,
static void alc_fixup_headset_mode_no_hp_mic(struct hda_codec *codec,
const struct hda_fixup *fix, int action);
-static void alc1220_fixup_system76_oryp5(struct hda_codec *codec,
+static void alc1220_fixup_clevo_pb51ed(struct hda_codec *codec,
const struct hda_fixup *fix,
int action)
{
.type = HDA_FIXUP_FUNC,
.v.func = alc1220_fixup_clevo_p950,
},
- [ALC1220_FIXUP_SYSTEM76_ORYP5] = {
+ [ALC1220_FIXUP_CLEVO_PB51ED] = {
.type = HDA_FIXUP_FUNC,
- .v.func = alc1220_fixup_system76_oryp5,
+ .v.func = alc1220_fixup_clevo_pb51ed,
},
- [ALC1220_FIXUP_SYSTEM76_ORYP5_PINS] = {
+ [ALC1220_FIXUP_CLEVO_PB51ED_PINS] = {
.type = HDA_FIXUP_PINS,
.v.pins = (const struct hda_pintbl[]) {
{ 0x19, 0x01a1913c }, /* use as headset mic, without its own jack detect */
{}
},
.chained = true,
- .chain_id = ALC1220_FIXUP_SYSTEM76_ORYP5,
+ .chain_id = ALC1220_FIXUP_CLEVO_PB51ED,
},
};
SND_PCI_QUIRK(0x1558, 0x9501, "Clevo P950HR", ALC1220_FIXUP_CLEVO_P950),
SND_PCI_QUIRK(0x1558, 0x95e1, "Clevo P95xER", ALC1220_FIXUP_CLEVO_P950),
SND_PCI_QUIRK(0x1558, 0x95e2, "Clevo P950ER", ALC1220_FIXUP_CLEVO_P950),
- SND_PCI_QUIRK(0x1558, 0x96e1, "System76 Oryx Pro (oryp5)", ALC1220_FIXUP_SYSTEM76_ORYP5_PINS),
- SND_PCI_QUIRK(0x1558, 0x97e1, "System76 Oryx Pro (oryp5)", ALC1220_FIXUP_SYSTEM76_ORYP5_PINS),
+ SND_PCI_QUIRK(0x1558, 0x96e1, "System76 Oryx Pro (oryp5)", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
+ SND_PCI_QUIRK(0x1558, 0x97e1, "System76 Oryx Pro (oryp5)", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
+ SND_PCI_QUIRK(0x1558, 0x65d1, "Tuxedo Book XC1509", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
SND_PCI_QUIRK_VENDOR(0x1558, "Clevo laptop", ALC882_FIXUP_EAPD),
SND_PCI_QUIRK(0x161f, 0x2054, "Medion laptop", ALC883_FIXUP_EAPD),
SND_PCI_QUIRK(0x17aa, 0x3a0d, "Lenovo Y530", ALC882_FIXUP_LENOVO_Y530),
jack->jack->button_state = report;
}
-static void alc295_fixup_chromebook(struct hda_codec *codec,
+static void alc_fixup_headset_jack(struct hda_codec *codec,
const struct hda_fixup *fix, int action)
{
alc_headset_btn_callback);
snd_hda_jack_add_kctl(codec, 0x55, "Headset Jack", false,
SND_JACK_HEADSET, alc_headset_btn_keymap);
- switch (codec->core.vendor_id) {
- case 0x10ec0295:
- alc_update_coef_idx(codec, 0x4a, 0x8000, 1 << 15); /* Reset HP JD */
- alc_update_coef_idx(codec, 0x4a, 0x8000, 0 << 15);
- break;
- case 0x10ec0236:
- alc_update_coef_idx(codec, 0x1b, 0x8000, 1 << 15); /* Reset HP JD */
- alc_update_coef_idx(codec, 0x1b, 0x8000, 0 << 15);
- break;
- }
break;
case HDA_FIXUP_ACT_INIT:
switch (codec->core.vendor_id) {
}
}
+static void alc295_fixup_chromebook(struct hda_codec *codec,
+ const struct hda_fixup *fix, int action)
+{
+ switch (action) {
+ case HDA_FIXUP_ACT_INIT:
+ switch (codec->core.vendor_id) {
+ case 0x10ec0295:
+ alc_update_coef_idx(codec, 0x4a, 0x8000, 1 << 15); /* Reset HP JD */
+ alc_update_coef_idx(codec, 0x4a, 0x8000, 0 << 15);
+ break;
+ case 0x10ec0236:
+ alc_update_coef_idx(codec, 0x1b, 0x8000, 1 << 15); /* Reset HP JD */
+ alc_update_coef_idx(codec, 0x1b, 0x8000, 0 << 15);
+ break;
+ }
+ break;
+ }
+}
+
static void alc_fixup_disable_mic_vref(struct hda_codec *codec,
const struct hda_fixup *fix, int action)
{
ALC233_FIXUP_ASUS_MIC_NO_PRESENCE,
ALC233_FIXUP_EAPD_COEF_AND_MIC_NO_PRESENCE,
ALC233_FIXUP_LENOVO_MULTI_CODECS,
+ ALC233_FIXUP_ACER_HEADSET_MIC,
ALC294_FIXUP_LENOVO_MIC_LOCATION,
ALC225_FIXUP_DELL_WYSE_MIC_NO_PRESENCE,
ALC700_FIXUP_INTEL_REFERENCE,
ALC285_FIXUP_LENOVO_PC_BEEP_IN_NOISE,
ALC255_FIXUP_ACER_HEADSET_MIC,
ALC295_FIXUP_CHROME_BOOK,
+ ALC225_FIXUP_HEADSET_JACK,
ALC225_FIXUP_DELL_WYSE_AIO_MIC_NO_PRESENCE,
ALC225_FIXUP_WYSE_AUTO_MUTE,
ALC225_FIXUP_WYSE_DISABLE_MIC_VREF,
ALC286_FIXUP_ACER_AIO_HEADSET_MIC,
+ ALC256_FIXUP_ASUS_MIC_NO_PRESENCE,
+ ALC299_FIXUP_PREDATOR_SPK,
};
static const struct hda_fixup alc269_fixups[] = {
.type = HDA_FIXUP_FUNC,
.v.func = alc233_alc662_fixup_lenovo_dual_codecs,
},
+ [ALC233_FIXUP_ACER_HEADSET_MIC] = {
+ .type = HDA_FIXUP_VERBS,
+ .v.verbs = (const struct hda_verb[]) {
+ { 0x20, AC_VERB_SET_COEF_INDEX, 0x45 },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0x5089 },
+ { }
+ },
+ .chained = true,
+ .chain_id = ALC233_FIXUP_ASUS_MIC_NO_PRESENCE
+ },
[ALC294_FIXUP_LENOVO_MIC_LOCATION] = {
.type = HDA_FIXUP_PINS,
.v.pins = (const struct hda_pintbl[]) {
[ALC295_FIXUP_CHROME_BOOK] = {
.type = HDA_FIXUP_FUNC,
.v.func = alc295_fixup_chromebook,
+ .chained = true,
+ .chain_id = ALC225_FIXUP_HEADSET_JACK
+ },
+ [ALC225_FIXUP_HEADSET_JACK] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc_fixup_headset_jack,
},
[ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE] = {
.type = HDA_FIXUP_PINS,
.chained = true,
.chain_id = ALC286_FIXUP_ACER_AIO_MIC_NO_PRESENCE
},
+ [ALC256_FIXUP_ASUS_MIC_NO_PRESENCE] = {
+ .type = HDA_FIXUP_PINS,
+ .v.pins = (const struct hda_pintbl[]) {
+ { 0x19, 0x04a11120 }, /* use as headset mic, without its own jack detect */
+ { }
+ },
+ .chained = true,
+ .chain_id = ALC256_FIXUP_ASUS_HEADSET_MODE
+ },
+ [ALC299_FIXUP_PREDATOR_SPK] = {
+ .type = HDA_FIXUP_PINS,
+ .v.pins = (const struct hda_pintbl[]) {
+ { 0x21, 0x90170150 }, /* use as headset mic, without its own jack detect */
+ { }
+ }
+ },
};
static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x1025, 0x079b, "Acer Aspire V5-573G", ALC282_FIXUP_ASPIRE_V5_PINS),
SND_PCI_QUIRK(0x1025, 0x102b, "Acer Aspire C24-860", ALC286_FIXUP_ACER_AIO_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1025, 0x106d, "Acer Cloudbook 14", ALC283_FIXUP_CHROME_BOOK),
+ SND_PCI_QUIRK(0x1025, 0x1099, "Acer Aspire E5-523G", ALC255_FIXUP_ACER_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1025, 0x110e, "Acer Aspire ES1-432", ALC255_FIXUP_ACER_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1025, 0x1246, "Acer Predator Helios 500", ALC299_FIXUP_PREDATOR_SPK),
SND_PCI_QUIRK(0x1025, 0x128f, "Acer Veriton Z6860G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC),
SND_PCI_QUIRK(0x1025, 0x1290, "Acer Veriton Z4860G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC),
SND_PCI_QUIRK(0x1025, 0x1291, "Acer Veriton Z4660G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC),
+ SND_PCI_QUIRK(0x1025, 0x1308, "Acer Aspire Z24-890", ALC286_FIXUP_ACER_AIO_HEADSET_MIC),
+ SND_PCI_QUIRK(0x1025, 0x132a, "Acer TravelMate B114-21", ALC233_FIXUP_ACER_HEADSET_MIC),
SND_PCI_QUIRK(0x1025, 0x1330, "Acer TravelMate X514-51T", ALC255_FIXUP_ACER_HEADSET_MIC),
SND_PCI_QUIRK(0x1028, 0x0470, "Dell M101z", ALC269_FIXUP_DELL_M101Z),
SND_PCI_QUIRK(0x1028, 0x054b, "Dell XPS one 2710", ALC275_FIXUP_DELL_XPS),
{.id = ALC255_FIXUP_DUMMY_LINEOUT_VERB, .name = "alc255-dummy-lineout"},
{.id = ALC255_FIXUP_DELL_HEADSET_MIC, .name = "alc255-dell-headset"},
{.id = ALC295_FIXUP_HP_X360, .name = "alc295-hp-x360"},
- {.id = ALC295_FIXUP_CHROME_BOOK, .name = "alc-sense-combo"},
+ {.id = ALC225_FIXUP_HEADSET_JACK, .name = "alc-headset-jack"},
+ {.id = ALC295_FIXUP_CHROME_BOOK, .name = "alc-chrome-book"},
+ {.id = ALC299_FIXUP_PREDATOR_SPK, .name = "predator-spk"},
{}
};
#define ALC225_STANDARD_PINS \
{0x14, 0x90170110},
{0x1b, 0x90a70130},
{0x21, 0x03211020}),
+ SND_HDA_PIN_QUIRK(0x10ec0256, 0x1043, "ASUS", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE,
+ {0x12, 0x90a60130},
+ {0x14, 0x90170110},
+ {0x21, 0x03211020}),
+ SND_HDA_PIN_QUIRK(0x10ec0256, 0x1043, "ASUS", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE,
+ {0x12, 0x90a60130},
+ {0x14, 0x90170110},
+ {0x21, 0x04211020}),
+ SND_HDA_PIN_QUIRK(0x10ec0256, 0x1043, "ASUS", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE,
+ {0x1a, 0x90a70130},
+ {0x1b, 0x90170110},
+ {0x21, 0x03211020}),
SND_HDA_PIN_QUIRK(0x10ec0274, 0x1028, "Dell", ALC274_FIXUP_DELL_AIO_LINEOUT_VERB,
{0x12, 0xb7a60130},
{0x13, 0xb8a61140},
tristate "WCD9335 Codec"
depends on SLIMBUS
select REGMAP_SLIMBUS
+ select REGMAP_IRQ
help
The WCD9335 is a standalone Hi-Fi audio CODEC IC, supports
Qualcomm Technologies, Inc. (QTI) multimedia solutions,
dev_err(dai->component->dev,
"%s: ERROR: The device is either a master or a slave.\n",
__func__);
+ /* fall through */
default:
dev_err(dai->component->dev,
"%s: ERROR: Unsupporter master mask 0x%x\n",
return ret;
}
+static int cs35l35_i2c_remove(struct i2c_client *i2c_client)
+{
+ struct cs35l35_private *cs35l35 = i2c_get_clientdata(i2c_client);
+
+ regulator_bulk_disable(cs35l35->num_supplies, cs35l35->supplies);
+ gpiod_set_value_cansleep(cs35l35->reset_gpio, 0);
+
+ return 0;
+}
+
static const struct of_device_id cs35l35_of_match[] = {
{.compatible = "cirrus,cs35l35"},
{},
},
.id_table = cs35l35_id,
.probe = cs35l35_i2c_probe,
+ .remove = cs35l35_i2c_remove,
};
module_i2c_driver(cs35l35_i2c_driver);
.reg_defaults = cs4270_reg_defaults,
.num_reg_defaults = ARRAY_SIZE(cs4270_reg_defaults),
.cache_type = REGCACHE_RBTREE,
+ .write_flag_mask = CS4270_I2C_INCR,
.readable_reg = cs4270_reg_is_readable,
.volatile_reg = cs4270_reg_is_volatile,
struct snd_soc_dai *dai);
static int hdac_hda_dai_prepare(struct snd_pcm_substream *substream,
struct snd_soc_dai *dai);
+static int hdac_hda_dai_hw_params(struct snd_pcm_substream *substream,
+ struct snd_pcm_hw_params *params,
+ struct snd_soc_dai *dai);
static int hdac_hda_dai_hw_free(struct snd_pcm_substream *substream,
struct snd_soc_dai *dai);
static int hdac_hda_dai_set_tdm_slot(struct snd_soc_dai *dai,
.startup = hdac_hda_dai_open,
.shutdown = hdac_hda_dai_close,
.prepare = hdac_hda_dai_prepare,
+ .hw_params = hdac_hda_dai_hw_params,
.hw_free = hdac_hda_dai_hw_free,
.set_tdm_slot = hdac_hda_dai_set_tdm_slot,
};
return 0;
}
+static int hdac_hda_dai_hw_params(struct snd_pcm_substream *substream,
+ struct snd_pcm_hw_params *params,
+ struct snd_soc_dai *dai)
+{
+ struct snd_soc_component *component = dai->component;
+ struct hdac_hda_priv *hda_pvt;
+ unsigned int format_val;
+ unsigned int maxbps;
+
+ if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
+ maxbps = dai->driver->playback.sig_bits;
+ else
+ maxbps = dai->driver->capture.sig_bits;
+
+ hda_pvt = snd_soc_component_get_drvdata(component);
+ format_val = snd_hdac_calc_stream_format(params_rate(params),
+ params_channels(params),
+ params_format(params),
+ maxbps,
+ 0);
+ if (!format_val) {
+ dev_err(dai->dev,
+ "invalid format_val, rate=%d, ch=%d, format=%d, maxbps=%d\n",
+ params_rate(params), params_channels(params),
+ params_format(params), maxbps);
+
+ return -EINVAL;
+ }
+
+ hda_pvt->pcm[dai->id].format_val[substream->stream] = format_val;
+ return 0;
+}
+
static int hdac_hda_dai_hw_free(struct snd_pcm_substream *substream,
struct snd_soc_dai *dai)
{
struct snd_soc_dai *dai)
{
struct snd_soc_component *component = dai->component;
+ struct hda_pcm_stream *hda_stream;
struct hdac_hda_priv *hda_pvt;
- struct snd_pcm_runtime *runtime = substream->runtime;
struct hdac_device *hdev;
- struct hda_pcm_stream *hda_stream;
unsigned int format_val;
struct hda_pcm *pcm;
unsigned int stream;
hda_stream = &pcm->stream[substream->stream];
- format_val = snd_hdac_calc_stream_format(runtime->rate,
- runtime->channels,
- runtime->format,
- hda_stream->maxbps,
- 0);
- if (!format_val) {
- dev_err(&hdev->dev,
- "invalid format_val, rate=%d, ch=%d, format=%d\n",
- runtime->rate, runtime->channels, runtime->format);
- return -EINVAL;
- }
-
stream = hda_pvt->pcm[dai->id].stream_tag[substream->stream];
+ format_val = hda_pvt->pcm[dai->id].format_val[substream->stream];
ret = snd_hda_codec_prepare(&hda_pvt->codec, hda_stream,
stream, format_val, substream);
struct hdac_hda_pcm {
int stream_tag[2];
+ unsigned int format_val[2];
};
struct hdac_hda_priv {
params_width(params), params_rate(params),
params_channels(params));
- if (params_width(params) > 24)
- params->msbits = 24;
-
ret = snd_pcm_create_iec958_consumer_hw_params(params, hp.iec.status,
sizeof(hp.iec.status));
if (ret < 0) {
{
struct hdmi_codec_priv *hcp = snd_soc_dai_get_drvdata(dai);
struct hdmi_codec_daifmt cf = { 0 };
- int ret = 0;
dev_dbg(dai->dev, "%s()\n", __func__);
- if (dai->id == DAI_ID_SPDIF) {
- cf.fmt = HDMI_SPDIF;
- } else {
- switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
- case SND_SOC_DAIFMT_CBM_CFM:
- cf.bit_clk_master = 1;
- cf.frame_clk_master = 1;
- break;
- case SND_SOC_DAIFMT_CBS_CFM:
- cf.frame_clk_master = 1;
- break;
- case SND_SOC_DAIFMT_CBM_CFS:
- cf.bit_clk_master = 1;
- break;
- case SND_SOC_DAIFMT_CBS_CFS:
- break;
- default:
- return -EINVAL;
- }
+ if (dai->id == DAI_ID_SPDIF)
+ return 0;
+
+ switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
+ case SND_SOC_DAIFMT_CBM_CFM:
+ cf.bit_clk_master = 1;
+ cf.frame_clk_master = 1;
+ break;
+ case SND_SOC_DAIFMT_CBS_CFM:
+ cf.frame_clk_master = 1;
+ break;
+ case SND_SOC_DAIFMT_CBM_CFS:
+ cf.bit_clk_master = 1;
+ break;
+ case SND_SOC_DAIFMT_CBS_CFS:
+ break;
+ default:
+ return -EINVAL;
+ }
- switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
- case SND_SOC_DAIFMT_NB_NF:
- break;
- case SND_SOC_DAIFMT_NB_IF:
- cf.frame_clk_inv = 1;
- break;
- case SND_SOC_DAIFMT_IB_NF:
- cf.bit_clk_inv = 1;
- break;
- case SND_SOC_DAIFMT_IB_IF:
- cf.frame_clk_inv = 1;
- cf.bit_clk_inv = 1;
- break;
- }
+ switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
+ case SND_SOC_DAIFMT_NB_NF:
+ break;
+ case SND_SOC_DAIFMT_NB_IF:
+ cf.frame_clk_inv = 1;
+ break;
+ case SND_SOC_DAIFMT_IB_NF:
+ cf.bit_clk_inv = 1;
+ break;
+ case SND_SOC_DAIFMT_IB_IF:
+ cf.frame_clk_inv = 1;
+ cf.bit_clk_inv = 1;
+ break;
+ }
- switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
- case SND_SOC_DAIFMT_I2S:
- cf.fmt = HDMI_I2S;
- break;
- case SND_SOC_DAIFMT_DSP_A:
- cf.fmt = HDMI_DSP_A;
- break;
- case SND_SOC_DAIFMT_DSP_B:
- cf.fmt = HDMI_DSP_B;
- break;
- case SND_SOC_DAIFMT_RIGHT_J:
- cf.fmt = HDMI_RIGHT_J;
- break;
- case SND_SOC_DAIFMT_LEFT_J:
- cf.fmt = HDMI_LEFT_J;
- break;
- case SND_SOC_DAIFMT_AC97:
- cf.fmt = HDMI_AC97;
- break;
- default:
- dev_err(dai->dev, "Invalid DAI interface format\n");
- return -EINVAL;
- }
+ switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
+ case SND_SOC_DAIFMT_I2S:
+ cf.fmt = HDMI_I2S;
+ break;
+ case SND_SOC_DAIFMT_DSP_A:
+ cf.fmt = HDMI_DSP_A;
+ break;
+ case SND_SOC_DAIFMT_DSP_B:
+ cf.fmt = HDMI_DSP_B;
+ break;
+ case SND_SOC_DAIFMT_RIGHT_J:
+ cf.fmt = HDMI_RIGHT_J;
+ break;
+ case SND_SOC_DAIFMT_LEFT_J:
+ cf.fmt = HDMI_LEFT_J;
+ break;
+ case SND_SOC_DAIFMT_AC97:
+ cf.fmt = HDMI_AC97;
+ break;
+ default:
+ dev_err(dai->dev, "Invalid DAI interface format\n");
+ return -EINVAL;
}
hcp->daifmt[dai->id] = cf;
- return ret;
+ return 0;
}
static int hdmi_codec_digital_mute(struct snd_soc_dai *dai, int mute)
i++;
}
- if (hcd->spdif)
+ if (hcd->spdif) {
hcp->daidrv[i] = hdmi_spdif_dai;
+ hcp->daifmt[DAI_ID_SPDIF].fmt = HDMI_SPDIF;
+ }
dev_set_drvdata(dev, hcp);
SND_SOC_DAPM_MIXER("Mono Mixer", NAU8810_REG_POWER3,
NAU8810_MOUTMX_EN_SFT, 0, &nau8810_mono_mixer_controls[0],
ARRAY_SIZE(nau8810_mono_mixer_controls)),
- SND_SOC_DAPM_DAC("DAC", "HiFi Playback", NAU8810_REG_POWER3,
+ SND_SOC_DAPM_DAC("DAC", "Playback", NAU8810_REG_POWER3,
NAU8810_DAC_EN_SFT, 0),
- SND_SOC_DAPM_ADC("ADC", "HiFi Capture", NAU8810_REG_POWER2,
+ SND_SOC_DAPM_ADC("ADC", "Capture", NAU8810_REG_POWER2,
NAU8810_ADC_EN_SFT, 0),
SND_SOC_DAPM_PGA("SpkN Out", NAU8810_REG_POWER3,
NAU8810_NSPK_EN_SFT, 0, NULL, 0),
SND_SOC_DAPM_ADC("ADCR", NULL, NAU8824_REG_ANALOG_ADC_2,
NAU8824_ADCR_EN_SFT, 0),
- SND_SOC_DAPM_AIF_OUT("AIFTX", "HiFi Capture", 0, SND_SOC_NOPM, 0, 0),
- SND_SOC_DAPM_AIF_IN("AIFRX", "HiFi Playback", 0, SND_SOC_NOPM, 0, 0),
+ SND_SOC_DAPM_AIF_OUT("AIFTX", "Capture", 0, SND_SOC_NOPM, 0, 0),
+ SND_SOC_DAPM_AIF_IN("AIFRX", "Playback", 0, SND_SOC_NOPM, 0, 0),
SND_SOC_DAPM_DAC("DACL", NULL, NAU8824_REG_RDAC,
NAU8824_DACL_EN_SFT, 0),
}
}
+static void nau8824_dapm_disable_pin(struct nau8824 *nau8824, const char *pin)
+{
+ struct snd_soc_dapm_context *dapm = nau8824->dapm;
+ const char *prefix = dapm->component->name_prefix;
+ char prefixed_pin[80];
+
+ if (prefix) {
+ snprintf(prefixed_pin, sizeof(prefixed_pin), "%s %s",
+ prefix, pin);
+ snd_soc_dapm_disable_pin(dapm, prefixed_pin);
+ } else {
+ snd_soc_dapm_disable_pin(dapm, pin);
+ }
+}
+
+static void nau8824_dapm_enable_pin(struct nau8824 *nau8824, const char *pin)
+{
+ struct snd_soc_dapm_context *dapm = nau8824->dapm;
+ const char *prefix = dapm->component->name_prefix;
+ char prefixed_pin[80];
+
+ if (prefix) {
+ snprintf(prefixed_pin, sizeof(prefixed_pin), "%s %s",
+ prefix, pin);
+ snd_soc_dapm_force_enable_pin(dapm, prefixed_pin);
+ } else {
+ snd_soc_dapm_force_enable_pin(dapm, pin);
+ }
+}
+
static void nau8824_eject_jack(struct nau8824 *nau8824)
{
struct snd_soc_dapm_context *dapm = nau8824->dapm;
/* Clear all interruption status */
nau8824_int_status_clear_all(regmap);
- snd_soc_dapm_disable_pin(dapm, "SAR");
- snd_soc_dapm_disable_pin(dapm, "MICBIAS");
+ nau8824_dapm_disable_pin(nau8824, "SAR");
+ nau8824_dapm_disable_pin(nau8824, "MICBIAS");
snd_soc_dapm_sync(dapm);
/* Enable the insertion interruption, disable the ejection
struct regmap *regmap = nau8824->regmap;
int adc_value, event = 0, event_mask = 0;
- snd_soc_dapm_force_enable_pin(dapm, "MICBIAS");
- snd_soc_dapm_force_enable_pin(dapm, "SAR");
+ nau8824_dapm_enable_pin(nau8824, "MICBIAS");
+ nau8824_dapm_enable_pin(nau8824, "SAR");
snd_soc_dapm_sync(dapm);
msleep(100);
if (adc_value < HEADSET_SARADC_THD) {
event |= SND_JACK_HEADPHONE;
- snd_soc_dapm_disable_pin(dapm, "SAR");
- snd_soc_dapm_disable_pin(dapm, "MICBIAS");
+ nau8824_dapm_disable_pin(nau8824, "SAR");
+ nau8824_dapm_disable_pin(nau8824, "MICBIAS");
snd_soc_dapm_sync(dapm);
} else {
event |= SND_JACK_HEADSET;
int jack_insert)
{
struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component);
- struct snd_soc_dapm_context *dapm =
- snd_soc_component_get_dapm(component);
unsigned int val, count;
if (jack_insert) {
- snd_soc_dapm_force_enable_pin(dapm, "CBJ Power");
- snd_soc_dapm_sync(dapm);
+
+ snd_soc_component_update_bits(component, RT5682_PWR_ANLG_1,
+ RT5682_PWR_VREF2 | RT5682_PWR_MB,
+ RT5682_PWR_VREF2 | RT5682_PWR_MB);
+ snd_soc_component_update_bits(component,
+ RT5682_PWR_ANLG_1, RT5682_PWR_FV2, 0);
+ usleep_range(15000, 20000);
+ snd_soc_component_update_bits(component,
+ RT5682_PWR_ANLG_1, RT5682_PWR_FV2, RT5682_PWR_FV2);
+ snd_soc_component_update_bits(component, RT5682_PWR_ANLG_3,
+ RT5682_PWR_CBJ, RT5682_PWR_CBJ);
+
snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_1,
RT5682_TRIG_JD_MASK, RT5682_TRIG_JD_HIGH);
rt5682_enable_push_button_irq(component, false);
snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_1,
RT5682_TRIG_JD_MASK, RT5682_TRIG_JD_LOW);
- snd_soc_dapm_disable_pin(dapm, "CBJ Power");
- snd_soc_dapm_sync(dapm);
+ snd_soc_component_update_bits(component, RT5682_PWR_ANLG_1,
+ RT5682_PWR_VREF2 | RT5682_PWR_MB, 0);
+ snd_soc_component_update_bits(component, RT5682_PWR_ANLG_3,
+ RT5682_PWR_CBJ, 0);
rt5682->jack_type = 0;
}
struct snd_soc_component *component =
snd_soc_dapm_to_component(w->dapm);
struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component);
- int ref, val, reg, sft, mask, idx = -EINVAL;
+ int ref, val, reg, idx = -EINVAL;
static const int div_f[] = {1, 2, 3, 4, 6, 8, 12, 16, 24, 32, 48};
static const int div_o[] = {1, 2, 4, 6, 8, 12, 16, 24, 32, 48};
idx = rt5682_div_sel(rt5682, ref, div_f, ARRAY_SIZE(div_f));
- if (w->shift == RT5682_PWR_ADC_S1F_BIT) {
+ if (w->shift == RT5682_PWR_ADC_S1F_BIT)
reg = RT5682_PLL_TRACK_3;
- sft = RT5682_ADC_OSR_SFT;
- mask = RT5682_ADC_OSR_MASK;
- } else {
+ else
reg = RT5682_PLL_TRACK_2;
- sft = RT5682_DAC_OSR_SFT;
- mask = RT5682_DAC_OSR_MASK;
- }
snd_soc_component_update_bits(component, reg,
RT5682_FILTER_CLK_DIV_MASK, idx << RT5682_FILTER_CLK_DIV_SFT);
}
snd_soc_component_update_bits(component, RT5682_ADDA_CLK_1,
- mask, idx << sft);
+ RT5682_ADC_OSR_MASK | RT5682_DAC_OSR_MASK,
+ (idx << RT5682_ADC_OSR_SFT) | (idx << RT5682_DAC_OSR_SFT));
return 0;
}
0, NULL, 0),
SND_SOC_DAPM_SUPPLY("Vref1", RT5682_PWR_ANLG_1, RT5682_PWR_VREF1_BIT, 0,
rt5655_set_verf, SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMU),
- SND_SOC_DAPM_SUPPLY("Vref2", RT5682_PWR_ANLG_1, RT5682_PWR_VREF2_BIT, 0,
- rt5655_set_verf, SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMU),
/* ASRC */
SND_SOC_DAPM_SUPPLY_S("DAC STO1 ASRC", 1, RT5682_PLL_TRACK_1,
SND_SOC_DAPM_PGA("BST1 CBJ", SND_SOC_NOPM,
0, 0, NULL, 0),
- SND_SOC_DAPM_SUPPLY("CBJ Power", RT5682_PWR_ANLG_3,
- RT5682_PWR_CBJ_BIT, 0, NULL, 0),
-
/* REC Mixer */
SND_SOC_DAPM_MIXER("RECMIX1L", SND_SOC_NOPM, 0, 0, rt5682_rec1_l_mix,
ARRAY_SIZE(rt5682_rec1_l_mix)),
/*Vref*/
{"MICBIAS1", NULL, "Vref1"},
- {"MICBIAS1", NULL, "Vref2"},
{"MICBIAS2", NULL, "Vref1"},
- {"MICBIAS2", NULL, "Vref2"},
{"CLKDET SYS", NULL, "CLKDET"},
{"IN1P", NULL, "LDO2"},
{"BST1 CBJ", NULL, "IN1P"},
- {"BST1 CBJ", NULL, "CBJ Power"},
- {"CBJ Power", NULL, "Vref2"},
{"RECMIX1L", "CBJ Switch", "BST1 CBJ"},
{"RECMIX1L", NULL, "RECMIX1L Power"},
{"HP Amp", NULL, "Capless"},
{"HP Amp", NULL, "Charge Pump"},
{"HP Amp", NULL, "CLKDET SYS"},
- {"HP Amp", NULL, "CBJ Power"},
{"HP Amp", NULL, "Vref1"},
- {"HP Amp", NULL, "Vref2"},
{"HPOL Playback", "Switch", "HP Amp"},
{"HPOR Playback", "Switch", "HP Amp"},
{"HPOL", NULL, "HPOL Playback"},
switch (level) {
case SND_SOC_BIAS_PREPARE:
regmap_update_bits(rt5682->regmap, RT5682_PWR_ANLG_1,
- RT5682_PWR_MB | RT5682_PWR_BG,
- RT5682_PWR_MB | RT5682_PWR_BG);
+ RT5682_PWR_BG, RT5682_PWR_BG);
regmap_update_bits(rt5682->regmap, RT5682_PWR_DIG_1,
RT5682_DIG_GATE_CTRL | RT5682_PWR_LDO,
RT5682_DIG_GATE_CTRL | RT5682_PWR_LDO);
break;
case SND_SOC_BIAS_STANDBY:
- regmap_update_bits(rt5682->regmap, RT5682_PWR_ANLG_1,
- RT5682_PWR_MB, RT5682_PWR_MB);
regmap_update_bits(rt5682->regmap, RT5682_PWR_DIG_1,
RT5682_DIG_GATE_CTRL, RT5682_DIG_GATE_CTRL);
break;
regmap_update_bits(rt5682->regmap, RT5682_PWR_DIG_1,
RT5682_DIG_GATE_CTRL | RT5682_PWR_LDO, 0);
regmap_update_bits(rt5682->regmap, RT5682_PWR_ANLG_1,
- RT5682_PWR_MB | RT5682_PWR_BG, 0);
+ RT5682_PWR_BG, 0);
break;
default:
regcache_cache_only(rt5682->regmap, false);
regcache_sync(rt5682->regmap);
+ rt5682_irq(0, rt5682);
+
return 0;
}
#else
*
* Copyright 2011 NW Digital Radio
*
- * Author: Jeremy McDermond <nh6z@nh6z.net>
+ * Author: Annaliese McDermond <nh6z@nh6z.net>
*
* Based on sound/soc/codecs/wm8974 and TI driver for kernel 2.6.27.
*
module_i2c_driver(aic32x4_i2c_driver);
MODULE_DESCRIPTION("ASoC TLV320AIC32x4 codec driver I2C");
-MODULE_AUTHOR("Jeremy McDermond <nh6z@nh6z.net>");
+MODULE_AUTHOR("Annaliese McDermond <nh6z@nh6z.net>");
MODULE_LICENSE("GPL");
*
* Copyright 2011 NW Digital Radio
*
- * Author: Jeremy McDermond <nh6z@nh6z.net>
+ * Author: Annaliese McDermond <nh6z@nh6z.net>
*
* Based on sound/soc/codecs/wm8974 and TI driver for kernel 2.6.27.
*
module_spi_driver(aic32x4_spi_driver);
MODULE_DESCRIPTION("ASoC TLV320AIC32x4 codec driver SPI");
-MODULE_AUTHOR("Jeremy McDermond <nh6z@nh6z.net>");
+MODULE_AUTHOR("Annaliese McDermond <nh6z@nh6z.net>");
MODULE_LICENSE("GPL");
SND_SOC_DAPM_INPUT("IN2_R"),
SND_SOC_DAPM_INPUT("IN3_L"),
SND_SOC_DAPM_INPUT("IN3_R"),
+ SND_SOC_DAPM_INPUT("CM_L"),
+ SND_SOC_DAPM_INPUT("CM_R"),
};
static const struct snd_soc_dapm_route aic32x4_dapm_routes[] = {
struct aic3x_priv *aic3x = snd_soc_component_get_drvdata(component);
int ret, i;
- INIT_LIST_HEAD(&aic3x->list);
aic3x->component = component;
for (i = 0; i < ARRAY_SIZE(aic3x->supplies); i++) {
if (ret != 0)
goto err_gpio;
+ INIT_LIST_HEAD(&aic3x->list);
list_add(&aic3x->list, &reset_list);
return 0;
{
struct aic3x_priv *aic3x = i2c_get_clientdata(client);
+ list_del(&aic3x->list);
+
if (gpio_is_valid(aic3x->gpio_reset) &&
!aic3x_is_shared_reset(aic3x)) {
gpio_set_value(aic3x->gpio_reset, 0);
if (wm_adsp_fw[dsp->fw].num_caps != 0)
wm_adsp_buffer_free(dsp);
+ dsp->fatal_error = false;
+
mutex_unlock(&dsp->pwr_lock);
adsp_dbg(dsp, "Execution stopped\n");
{
struct wm_adsp_compr_buf *buf = NULL, *tmp;
+ if (compr->dsp->fatal_error)
+ return -EINVAL;
+
list_for_each_entry(tmp, &compr->dsp->buffer_list, list) {
if (!tmp->name || !strcmp(compr->name, tmp->name)) {
buf = tmp;
ret = wm_adsp_buffer_read(buf, HOST_BUFFER_FIELD(error), &buf->error);
if (ret < 0) {
- adsp_err(buf->dsp, "Failed to check buffer error: %d\n", ret);
+ compr_err(buf, "Failed to check buffer error: %d\n", ret);
return ret;
}
if (buf->error != 0) {
- adsp_err(buf->dsp, "Buffer error occurred: %d\n", buf->error);
+ compr_err(buf, "Buffer error occurred: %d\n", buf->error);
return -EIO;
}
if (ret < 0)
break;
- wm_adsp_buffer_clear(compr->buf);
-
/* Trigger the IRQ at one fragment of data */
ret = wm_adsp_buffer_write(compr->buf,
HOST_BUFFER_FIELD(high_water_mark),
}
break;
case SNDRV_PCM_TRIGGER_STOP:
+ if (wm_adsp_compr_attached(compr))
+ wm_adsp_buffer_clear(compr->buf);
break;
default:
ret = -EINVAL;
}
EXPORT_SYMBOL_GPL(wm_adsp2_lock);
+static void wm_adsp_fatal_error(struct wm_adsp *dsp)
+{
+ struct wm_adsp_compr *compr;
+
+ dsp->fatal_error = true;
+
+ list_for_each_entry(compr, &dsp->compr_list, list) {
+ if (compr->stream) {
+ snd_compr_stop_error(compr->stream,
+ SNDRV_PCM_STATE_XRUN);
+ snd_compr_fragment_elapsed(compr->stream);
+ }
+ }
+}
+
irqreturn_t wm_adsp2_bus_error(struct wm_adsp *dsp)
{
unsigned int val;
struct regmap *regmap = dsp->regmap;
int ret = 0;
+ mutex_lock(&dsp->pwr_lock);
+
ret = regmap_read(regmap, dsp->base + ADSP2_LOCK_REGION_CTRL, &val);
if (ret) {
adsp_err(dsp,
"Failed to read Region Lock Ctrl register: %d\n", ret);
- return IRQ_HANDLED;
+ goto error;
}
if (val & ADSP2_WDT_TIMEOUT_STS_MASK) {
adsp_err(dsp, "watchdog timeout error\n");
wm_adsp_stop_watchdog(dsp);
+ wm_adsp_fatal_error(dsp);
}
if (val & (ADSP2_SLAVE_ERR_MASK | ADSP2_REGION_LOCK_ERR_MASK)) {
adsp_err(dsp,
"Failed to read Bus Err Addr register: %d\n",
ret);
- return IRQ_HANDLED;
+ goto error;
}
adsp_err(dsp, "bus error address = 0x%x\n",
adsp_err(dsp,
"Failed to read Pmem Xmem Err Addr register: %d\n",
ret);
- return IRQ_HANDLED;
+ goto error;
}
adsp_err(dsp, "xmem error address = 0x%x\n",
regmap_update_bits(regmap, dsp->base + ADSP2_LOCK_REGION_CTRL,
ADSP2_CTRL_ERR_EINT, ADSP2_CTRL_ERR_EINT);
+error:
+ mutex_unlock(&dsp->pwr_lock);
+
return IRQ_HANDLED;
}
EXPORT_SYMBOL_GPL(wm_adsp2_bus_error);
bool preloaded;
bool booted;
bool running;
+ bool fatal_error;
struct list_head ctl_list;
}
EXPORT_SYMBOL_GPL(fsl_asrc_get_dma_channel);
+static int fsl_asrc_dai_startup(struct snd_pcm_substream *substream,
+ struct snd_soc_dai *dai)
+{
+ struct fsl_asrc *asrc_priv = snd_soc_dai_get_drvdata(dai);
+
+ /* Odd channel number is not valid for older ASRC (channel_bits==3) */
+ if (asrc_priv->channel_bits == 3)
+ snd_pcm_hw_constraint_step(substream->runtime, 0,
+ SNDRV_PCM_HW_PARAM_CHANNELS, 2);
+
+ return 0;
+}
+
static int fsl_asrc_dai_hw_params(struct snd_pcm_substream *substream,
struct snd_pcm_hw_params *params,
struct snd_soc_dai *dai)
}
static const struct snd_soc_dai_ops fsl_asrc_dai_ops = {
+ .startup = fsl_asrc_dai_startup,
.hw_params = fsl_asrc_dai_hw_params,
.hw_free = fsl_asrc_dai_hw_free,
.trigger = fsl_asrc_dai_trigger,
u32 fifo_depth;
u32 slot_width;
u32 slots;
+ u32 tx_mask;
+ u32 rx_mask;
u32 hck_rate[2];
u32 sck_rate[2];
bool hck_dir[2];
regmap_update_bits(esai_priv->regmap, REG_ESAI_TCCR,
ESAI_xCCR_xDC_MASK, ESAI_xCCR_xDC(slots));
- regmap_update_bits(esai_priv->regmap, REG_ESAI_TSMA,
- ESAI_xSMA_xS_MASK, ESAI_xSMA_xS(tx_mask));
- regmap_update_bits(esai_priv->regmap, REG_ESAI_TSMB,
- ESAI_xSMB_xS_MASK, ESAI_xSMB_xS(tx_mask));
-
regmap_update_bits(esai_priv->regmap, REG_ESAI_RCCR,
ESAI_xCCR_xDC_MASK, ESAI_xCCR_xDC(slots));
- regmap_update_bits(esai_priv->regmap, REG_ESAI_RSMA,
- ESAI_xSMA_xS_MASK, ESAI_xSMA_xS(rx_mask));
- regmap_update_bits(esai_priv->regmap, REG_ESAI_RSMB,
- ESAI_xSMB_xS_MASK, ESAI_xSMB_xS(rx_mask));
-
esai_priv->slot_width = slot_width;
esai_priv->slots = slots;
+ esai_priv->tx_mask = tx_mask;
+ esai_priv->rx_mask = rx_mask;
return 0;
}
bool tx = substream->stream == SNDRV_PCM_STREAM_PLAYBACK;
u8 i, channels = substream->runtime->channels;
u32 pins = DIV_ROUND_UP(channels, esai_priv->slots);
+ u32 mask;
switch (cmd) {
case SNDRV_PCM_TRIGGER_START:
for (i = 0; tx && i < channels; i++)
regmap_write(esai_priv->regmap, REG_ESAI_ETDR, 0x0);
+ /*
+ * When set the TE/RE in the end of enablement flow, there
+ * will be channel swap issue for multi data line case.
+ * In order to workaround this issue, we switch the bit
+ * enablement sequence to below sequence
+ * 1) clear the xSMB & xSMA: which is done in probe and
+ * stop state.
+ * 2) set TE/RE
+ * 3) set xSMB
+ * 4) set xSMA: xSMA is the last one in this flow, which
+ * will trigger esai to start.
+ */
regmap_update_bits(esai_priv->regmap, REG_ESAI_xCR(tx),
tx ? ESAI_xCR_TE_MASK : ESAI_xCR_RE_MASK,
tx ? ESAI_xCR_TE(pins) : ESAI_xCR_RE(pins));
+ mask = tx ? esai_priv->tx_mask : esai_priv->rx_mask;
+
+ regmap_update_bits(esai_priv->regmap, REG_ESAI_xSMB(tx),
+ ESAI_xSMB_xS_MASK, ESAI_xSMB_xS(mask));
+ regmap_update_bits(esai_priv->regmap, REG_ESAI_xSMA(tx),
+ ESAI_xSMA_xS_MASK, ESAI_xSMA_xS(mask));
+
break;
case SNDRV_PCM_TRIGGER_SUSPEND:
case SNDRV_PCM_TRIGGER_STOP:
case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
regmap_update_bits(esai_priv->regmap, REG_ESAI_xCR(tx),
tx ? ESAI_xCR_TE_MASK : ESAI_xCR_RE_MASK, 0);
+ regmap_update_bits(esai_priv->regmap, REG_ESAI_xSMA(tx),
+ ESAI_xSMA_xS_MASK, 0);
+ regmap_update_bits(esai_priv->regmap, REG_ESAI_xSMB(tx),
+ ESAI_xSMB_xS_MASK, 0);
/* Disable and reset FIFO */
regmap_update_bits(esai_priv->regmap, REG_ESAI_xFCR(tx),
return ret;
}
+ esai_priv->tx_mask = 0xFFFFFFFF;
+ esai_priv->rx_mask = 0xFFFFFFFF;
+
+ /* Clear the TSMA, TSMB, RSMA, RSMB */
+ regmap_write(esai_priv->regmap, REG_ESAI_TSMA, 0);
+ regmap_write(esai_priv->regmap, REG_ESAI_TSMB, 0);
+ regmap_write(esai_priv->regmap, REG_ESAI_RSMA, 0);
+ regmap_write(esai_priv->regmap, REG_ESAI_RSMB, 0);
+
ret = devm_snd_soc_register_component(&pdev->dev, &fsl_esai_component,
&fsl_esai_dai, 1);
if (ret) {
#include <linux/string.h>
#include <sound/simple_card_utils.h>
+#define DPCM_SELECTABLE 1
+
struct graph_priv {
struct snd_soc_card snd_card;
struct graph_dai_props {
struct device_node *codec_port;
struct device_node *codec_port_old = NULL;
struct asoc_simple_card_data adata;
+ uintptr_t dpcm_selectable = (uintptr_t)of_device_get_match_data(dev);
int rc, ret;
/* loop for all listed CPU port */
* if Codec port has many endpoints,
* or has convert-xxx property
*/
- if ((of_get_child_count(codec_port) > 1) ||
- adata.convert_rate || adata.convert_channels)
+ if (dpcm_selectable &&
+ ((of_get_child_count(codec_port) > 1) ||
+ adata.convert_rate || adata.convert_channels))
ret = func_dpcm(priv, cpu_ep, codec_ep, li,
(codec_port_old == codec_port));
/* else normal sound */
static const struct of_device_id graph_of_match[] = {
{ .compatible = "audio-graph-card", },
- { .compatible = "audio-graph-scu-card", },
+ { .compatible = "audio-graph-scu-card",
+ .data = (void *)DPCM_SELECTABLE },
{},
};
MODULE_DEVICE_TABLE(of, graph_of_match);
#include <linux/device.h>
#include <linux/module.h>
#include <linux/of.h>
+#include <linux/of_device.h>
#include <linux/platform_device.h>
#include <linux/string.h>
#include <sound/simple_card.h>
#include <sound/soc-dai.h>
#include <sound/soc.h>
+#define DPCM_SELECTABLE 1
+
struct simple_priv {
struct snd_soc_card snd_card;
struct simple_dai_props {
struct device *dev = simple_priv_to_dev(priv);
struct device_node *top = dev->of_node;
struct device_node *node;
+ uintptr_t dpcm_selectable = (uintptr_t)of_device_get_match_data(dev);
bool is_top = 0;
int ret = 0;
* if it has many CPUs,
* or has convert-xxx property
*/
- if (num > 2 ||
- adata.convert_rate || adata.convert_channels)
+ if (dpcm_selectable &&
+ (num > 2 ||
+ adata.convert_rate || adata.convert_channels))
ret = func_dpcm(priv, np, codec, li, is_top);
/* else normal sound */
else
static const struct of_device_id simple_of_match[] = {
{ .compatible = "simple-audio-card", },
- { .compatible = "simple-scu-audio-card", },
+ { .compatible = "simple-scu-audio-card",
+ .data = (void *)DPCM_SELECTABLE },
{},
};
MODULE_DEVICE_TABLE(of, simple_of_match);
return sst_dsp_init_v2_dpcm(component);
}
+static void sst_soc_remove(struct snd_soc_component *component)
+{
+ struct sst_data *drv = dev_get_drvdata(component->dev);
+
+ drv->soc_card = NULL;
+}
+
static const struct snd_soc_component_driver sst_soc_platform_drv = {
.name = DRV_NAME,
.probe = sst_soc_probe,
+ .remove = sst_soc_remove,
.ops = &sst_platform_ops,
.compr_ops = &sst_platform_compr_ops,
.pcm_new = sst_pcm_new,
struct clk *mclk;
struct snd_soc_jack jack;
bool ts3a227e_present;
+ int quirks;
};
static int platform_clock_control(struct snd_soc_dapm_widget *w,
struct cht_mc_private *ctx = snd_soc_card_get_drvdata(card);
int ret;
+ /* See the comment in snd_cht_mc_probe() */
+ if (ctx->quirks & QUIRK_PMC_PLT_CLK_0)
+ return 0;
+
codec_dai = snd_soc_card_get_codec_dai(card, CHT_CODEC_DAI);
if (!codec_dai) {
dev_err(card->dev, "Codec dai not found; Unable to set platform clock\n");
"jack detection gpios not added, error %d\n", ret);
}
+ /* See the comment in snd_cht_mc_probe() */
+ if (ctx->quirks & QUIRK_PMC_PLT_CLK_0)
+ return 0;
+
/*
* The firmware might enable the clock at
* boot (this information may or may not
const char *mclk_name;
struct snd_soc_acpi_mach *mach;
const char *platform_name;
- int quirks = 0;
-
- dmi_id = dmi_first_match(cht_max98090_quirk_table);
- if (dmi_id)
- quirks = (unsigned long)dmi_id->driver_data;
drv = devm_kzalloc(&pdev->dev, sizeof(*drv), GFP_KERNEL);
if (!drv)
return -ENOMEM;
+ dmi_id = dmi_first_match(cht_max98090_quirk_table);
+ if (dmi_id)
+ drv->quirks = (unsigned long)dmi_id->driver_data;
+
drv->ts3a227e_present = acpi_dev_found("104C227E");
if (!drv->ts3a227e_present) {
/* no need probe TI jack detection chip */
snd_soc_card_cht.dev = &pdev->dev;
snd_soc_card_set_drvdata(&snd_soc_card_cht, drv);
- if (quirks & QUIRK_PMC_PLT_CLK_0)
+ if (drv->quirks & QUIRK_PMC_PLT_CLK_0)
mclk_name = "pmc_plt_clk_0";
else
mclk_name = "pmc_plt_clk_3";
return PTR_ERR(drv->mclk);
}
+ /*
+ * Boards which have the MAX98090's clk connected to clk_0 do not seem
+ * to like it if we muck with the clock. If we disable the clock when
+ * it is unused we get "max98090 i2c-193C9890:00: PLL unlocked" errors
+ * and the PLL never seems to lock again.
+ * So for these boards we enable it here once and leave it at that.
+ */
+ if (drv->quirks & QUIRK_PMC_PLT_CLK_0) {
+ ret_val = clk_prepare_enable(drv->mclk);
+ if (ret_val < 0) {
+ dev_err(&pdev->dev, "MCLK enable error: %d\n", ret_val);
+ return ret_val;
+ }
+ }
+
ret_val = devm_snd_soc_register_card(&pdev->dev, &snd_soc_card_cht);
if (ret_val) {
dev_err(&pdev->dev,
return ret_val;
}
+static int snd_cht_mc_remove(struct platform_device *pdev)
+{
+ struct snd_soc_card *card = platform_get_drvdata(pdev);
+ struct cht_mc_private *ctx = snd_soc_card_get_drvdata(card);
+
+ if (ctx->quirks & QUIRK_PMC_PLT_CLK_0)
+ clk_disable_unprepare(ctx->mclk);
+
+ return 0;
+}
+
static struct platform_driver snd_cht_mc_driver = {
.driver = {
.name = "cht-bsw-max98090",
},
.probe = snd_cht_mc_probe,
+ .remove = snd_cht_mc_remove,
};
module_platform_driver(snd_cht_mc_driver)
};
static const unsigned int dmic_2ch[] = {
- 4,
+ 2,
};
static const struct snd_pcm_hw_constraint_list constraints_dmic_2ch = {
base_cfg->audio_fmt.bit_depth = format->bit_depth;
base_cfg->audio_fmt.valid_bit_depth = format->valid_bit_depth;
base_cfg->audio_fmt.ch_cfg = format->ch_cfg;
+ base_cfg->audio_fmt.sample_type = format->sample_type;
dev_dbg(ctx->dev, "bit_depth=%x valid_bd=%x ch_config=%x\n",
format->bit_depth, format->valid_bit_depth,
struct hdac_stream *hstream;
struct hdac_ext_stream *stream;
struct hdac_ext_link *link;
+ unsigned char stream_tag;
hstream = snd_hdac_get_stream(bus, params->stream,
params->link_dma_id + 1);
snd_hdac_ext_link_stream_setup(stream, format_val);
- list_for_each_entry(link, &bus->hlink_list, list) {
- if (link->index == params->link_index)
- snd_hdac_ext_link_set_stream_id(link,
- hstream->stream_tag);
+ stream_tag = hstream->stream_tag;
+ if (stream->hstream.direction == SNDRV_PCM_STREAM_PLAYBACK) {
+ list_for_each_entry(link, &bus->hlink_list, list) {
+ if (link->index == params->link_index)
+ snd_hdac_ext_link_set_stream_id(link,
+ stream_tag);
+ }
}
stream->link_prepared = 1;
struct hdac_ext_stream *link_dev =
snd_soc_dai_get_dma_data(dai, substream);
struct hdac_ext_link *link;
+ unsigned char stream_tag;
dev_dbg(dai->dev, "%s: %s\n", __func__, dai->name);
if (!link)
return -EINVAL;
- snd_hdac_ext_link_clear_stream_id(link, hdac_stream(link_dev)->stream_tag);
+ if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
+ stream_tag = hdac_stream(link_dev)->stream_tag;
+ snd_hdac_ext_link_clear_stream_id(link, stream_tag);
+ }
+
snd_hdac_ext_stream_release(link_dev, HDAC_EXT_STREAM_TYPE_LINK);
return 0;
}
return 0;
}
+static void skl_pcm_remove(struct snd_soc_component *component)
+{
+ /* remove topology */
+ snd_soc_tplg_component_remove(component, SND_SOC_TPLG_INDEX_ALL);
+}
+
static const struct snd_soc_component_driver skl_component = {
.name = "pcm",
.probe = skl_platform_soc_probe,
+ .remove = skl_pcm_remove,
.ops = &skl_platform_ops,
.pcm_new = skl_pcm_new,
.pcm_free = skl_pcm_free,
- .ignore_module_refcount = 1, /* do not increase the refcount in core */
+ .module_get_upon_open = 1, /* increment refcount when a pcm is opened */
};
int skl_platform_register(struct device *dev)
BT_SCO_STATE_IDLE,
BT_SCO_STATE_RUNNING,
BT_SCO_STATE_ENDING,
+ BT_SCO_STATE_LOOPBACK,
};
enum bt_sco_direct {
if (bt->rx->state != BT_SCO_STATE_RUNNING &&
bt->rx->state != BT_SCO_STATE_ENDING &&
bt->tx->state != BT_SCO_STATE_RUNNING &&
- bt->tx->state != BT_SCO_STATE_ENDING) {
+ bt->tx->state != BT_SCO_STATE_ENDING &&
+ bt->tx->state != BT_SCO_STATE_LOOPBACK) {
dev_warn(bt->dev, "%s(), in idle state: rx->state: %d, tx->state: %d\n",
__func__, bt->rx->state, bt->tx->state);
goto irq_handler_exit;
buf_cnt_tx = btsco_packet_info[packet_type][2];
buf_cnt_rx = btsco_packet_info[packet_type][3];
+ if (bt->tx->state == BT_SCO_STATE_LOOPBACK) {
+ u8 *src, *dst;
+ unsigned long connsys_addr_rx, ap_addr_rx;
+ unsigned long connsys_addr_tx, ap_addr_tx;
+
+ connsys_addr_rx = *bt->bt_reg_pkt_r;
+ ap_addr_rx = (unsigned long)bt->bt_sram_bank2_base +
+ (connsys_addr_rx & 0xFFFF);
+
+ connsys_addr_tx = *bt->bt_reg_pkt_w;
+ ap_addr_tx = (unsigned long)bt->bt_sram_bank2_base +
+ (connsys_addr_tx & 0xFFFF);
+
+ if (connsys_addr_tx == 0xdeadfeed ||
+ connsys_addr_rx == 0xdeadfeed) {
+ /* bt return 0xdeadfeed if read reg during bt sleep */
+ dev_warn(bt->dev, "%s(), connsys_addr_tx == 0xdeadfeed\n",
+ __func__);
+ goto irq_handler_exit;
+ }
+
+ src = (u8 *)ap_addr_rx;
+ dst = (u8 *)ap_addr_tx;
+
+ mtk_btcvsd_snd_data_transfer(BT_SCO_DIRECT_BT2ARM, src,
+ bt->tx->temp_packet_buf,
+ packet_length,
+ packet_num);
+ mtk_btcvsd_snd_data_transfer(BT_SCO_DIRECT_ARM2BT,
+ bt->tx->temp_packet_buf, dst,
+ packet_length,
+ packet_num);
+ bt->rx->rw_cnt++;
+ bt->tx->rw_cnt++;
+ }
+
if (bt->rx->state == BT_SCO_STATE_RUNNING ||
bt->rx->state == BT_SCO_STATE_ENDING) {
if (bt->rx->xrun) {
return 0;
}
+static int btcvsd_loopback_get(struct snd_kcontrol *kcontrol,
+ struct snd_ctl_elem_value *ucontrol)
+{
+ struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol);
+ struct mtk_btcvsd_snd *bt = snd_soc_component_get_drvdata(cmpnt);
+ bool lpbk_en = bt->tx->state == BT_SCO_STATE_LOOPBACK;
+
+ ucontrol->value.integer.value[0] = lpbk_en;
+ return 0;
+}
+
+static int btcvsd_loopback_set(struct snd_kcontrol *kcontrol,
+ struct snd_ctl_elem_value *ucontrol)
+{
+ struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol);
+ struct mtk_btcvsd_snd *bt = snd_soc_component_get_drvdata(cmpnt);
+
+ if (ucontrol->value.integer.value[0]) {
+ mtk_btcvsd_snd_set_state(bt, bt->tx, BT_SCO_STATE_LOOPBACK);
+ mtk_btcvsd_snd_set_state(bt, bt->rx, BT_SCO_STATE_LOOPBACK);
+ } else {
+ mtk_btcvsd_snd_set_state(bt, bt->tx, BT_SCO_STATE_RUNNING);
+ mtk_btcvsd_snd_set_state(bt, bt->rx, BT_SCO_STATE_RUNNING);
+ }
+ return 0;
+}
+
static int btcvsd_tx_mute_get(struct snd_kcontrol *kcontrol,
struct snd_ctl_elem_value *ucontrol)
{
static const struct snd_kcontrol_new mtk_btcvsd_snd_controls[] = {
SOC_ENUM_EXT("BTCVSD Band", btcvsd_enum[0],
btcvsd_band_get, btcvsd_band_set),
+ SOC_SINGLE_BOOL_EXT("BTCVSD Loopback Switch", 0,
+ btcvsd_loopback_get, btcvsd_loopback_set),
SOC_SINGLE_BOOL_EXT("BTCVSD Tx Mute Switch", 0,
btcvsd_tx_mute_get, btcvsd_tx_mute_set),
SOC_SINGLE_BOOL_EXT("BTCVSD Tx Irq Received Switch", 0,
int m_sel_id = mck_div[mck_id].m_sel_id;
int div_clk_id = mck_div[mck_id].div_clk_id;
+ /* i2s5 mck not support */
+ if (mck_id == MT8183_I2S5_MCK)
+ return;
+
clk_disable_unprepare(afe_priv->clk[div_clk_id]);
if (m_sel_id >= 0)
clk_disable_unprepare(afe_priv->clk[m_sel_id]);
#include "rockchip_pdm.h"
-#define PDM_DMA_BURST_SIZE (16) /* size * width: 16*4 = 64 bytes */
+#define PDM_DMA_BURST_SIZE (8) /* size * width: 8*4 = 32 bytes */
struct rk_pdm_dev {
struct device *dev;
return -EINVAL;
}
+ pm_runtime_get_sync(cpu_dai->dev);
regmap_update_bits(pdm->regmap, PDM_CLK_CTRL, mask, val);
+ pm_runtime_put(cpu_dai->dev);
return 0;
}
};
static const struct snd_soc_dapm_route samsung_i2s_dapm_routes[] = {
- { "Playback Mixer", NULL, "Primary" },
- { "Playback Mixer", NULL, "Secondary" },
+ { "Playback Mixer", NULL, "Primary Playback" },
+ { "Playback Mixer", NULL, "Secondary Playback" },
{ "Mixer DAI TX", NULL, "Playback Mixer" },
- { "Playback Mixer", NULL, "Mixer DAI RX" },
+ { "Primary Capture", NULL, "Mixer DAI RX" },
};
static const struct snd_soc_component_driver samsung_i2s_component = {
int num_dais)
{
static const char *dai_names[] = { "samsung-i2s", "samsung-i2s-sec" };
- static const char *stream_names[] = { "Primary", "Secondary" };
+ static const char *stream_names[] = { "Primary Playback",
+ "Secondary Playback" };
struct snd_soc_dai_driver *dai_drv;
struct i2s_dai *dai;
int i;
dai_drv->capture.channels_max = 2;
dai_drv->capture.rates = i2s_dai_data->pcm_rates;
dai_drv->capture.formats = SAMSUNG_I2S_FMTS;
+ dai_drv->capture.stream_name = "Primary Capture";
return 0;
}
return ret;
/*
- * We add 1 to the rclk_freq value in order to avoid too low clock
+ * We add 2 to the rclk_freq value in order to avoid too low clock
* frequency values due to the EPLL output frequency not being exact
* multiple of the audio sampling rate.
*/
- rclk_freq = params_rate(params) * rfs + 1;
+ rclk_freq = params_rate(params) * rfs + 2;
ret = clk_set_rate(priv->sclk_i2s, rclk_freq);
if (ret < 0)
{ .compatible = "renesas,rcar_sound-gen1", .data = (void *)RSND_GEN1 },
{ .compatible = "renesas,rcar_sound-gen2", .data = (void *)RSND_GEN2 },
{ .compatible = "renesas,rcar_sound-gen3", .data = (void *)RSND_GEN3 },
+ /* Special Handling */
+ { .compatible = "renesas,rcar_sound-r8a77990", .data = (void *)(RSND_GEN3 | RSND_SOC_E) },
{},
};
MODULE_DEVICE_TABLE(of, rsnd_of_match);
#define RSND_GEN1 (1 << 0)
#define RSND_GEN2 (2 << 0)
#define RSND_GEN3 (3 << 0)
+#define RSND_SOC_MASK (0xFF << 4)
+#define RSND_SOC_E (1 << 4) /* E1/E2/E3 */
/*
* below value will be filled on rsnd_gen_probe()
#define rsnd_is_gen1(priv) (((priv)->flags & RSND_GEN_MASK) == RSND_GEN1)
#define rsnd_is_gen2(priv) (((priv)->flags & RSND_GEN_MASK) == RSND_GEN2)
#define rsnd_is_gen3(priv) (((priv)->flags & RSND_GEN_MASK) == RSND_GEN3)
+#define rsnd_is_e3(priv) (((priv)->flags & \
+ (RSND_GEN_MASK | RSND_SOC_MASK)) == \
+ (RSND_GEN3 | RSND_SOC_E))
#define rsnd_flags_has(p, f) ((p)->flags & (f))
#define rsnd_flags_set(p, f) ((p)->flags |= (f))
*/
#include "rsnd.h"
-#include <linux/sys_soc.h>
#define SRC_NAME "src"
return rate;
}
-const static u32 bsdsr_table_pattern1[] = {
+static const u32 bsdsr_table_pattern1[] = {
0x01800000, /* 6 - 1/6 */
0x01000000, /* 6 - 1/4 */
0x00c00000, /* 6 - 1/3 */
0x00400000, /* 6 - 1 */
};
-const static u32 bsdsr_table_pattern2[] = {
+static const u32 bsdsr_table_pattern2[] = {
0x02400000, /* 6 - 1/6 */
0x01800000, /* 6 - 1/4 */
0x01200000, /* 6 - 1/3 */
0x00600000, /* 6 - 1 */
};
-const static u32 bsisr_table[] = {
+static const u32 bsisr_table[] = {
0x00100060, /* 6 - 1/6 */
0x00100040, /* 6 - 1/4 */
0x00100030, /* 6 - 1/3 */
0x00100020, /* 6 - 1 */
};
-const static u32 chan288888[] = {
+static const u32 chan288888[] = {
0x00000006, /* 1 to 2 */
0x000001fe, /* 1 to 8 */
0x000001fe, /* 1 to 8 */
0x000001fe, /* 1 to 8 */
};
-const static u32 chan244888[] = {
+static const u32 chan244888[] = {
0x00000006, /* 1 to 2 */
0x0000001e, /* 1 to 4 */
0x0000001e, /* 1 to 4 */
0x000001fe, /* 1 to 8 */
};
-const static u32 chan222222[] = {
+static const u32 chan222222[] = {
0x00000006, /* 1 to 2 */
0x00000006, /* 1 to 2 */
0x00000006, /* 1 to 2 */
0x00000006, /* 1 to 2 */
};
-static const struct soc_device_attribute ov_soc[] = {
- { .soc_id = "r8a77990" }, /* E3 */
- { /* sentinel */ }
-};
-
static void rsnd_src_set_convert_rate(struct rsnd_dai_stream *io,
struct rsnd_mod *mod)
{
struct rsnd_priv *priv = rsnd_mod_to_priv(mod);
struct device *dev = rsnd_priv_to_dev(priv);
struct snd_pcm_runtime *runtime = rsnd_io_to_runtime(io);
- const struct soc_device_attribute *soc = soc_device_match(ov_soc);
int is_play = rsnd_io_is_play(io);
int use_src = 0;
u32 fin, fout;
/*
* E3 need to overwrite
*/
- if (soc)
+ if (rsnd_is_e3(priv))
switch (rsnd_mod_id(mod)) {
case 0:
case 4:
snd_soc_dapm_free(snd_soc_component_get_dapm(component));
soc_cleanup_component_debugfs(component);
component->card = NULL;
- if (!component->driver->ignore_module_refcount)
+ if (!component->driver->module_get_upon_open)
module_put(component->dev->driver->owner);
}
return 0;
}
- if (!component->driver->ignore_module_refcount &&
+ if (!component->driver->module_get_upon_open &&
!try_module_get(component->dev->driver->owner))
return -ENODEV;
ret = soc_init_dai_link(card, link);
if (ret) {
+ soc_cleanup_platform(card);
dev_err(card->dev, "ASoC: failed to init link %s\n",
link->name);
mutex_unlock(&client_mutex);
card->instantiated = 0;
mutex_init(&card->mutex);
mutex_init(&card->dapm_mutex);
+ spin_lock_init(&card->dpcm_lock);
return snd_soc_bind_card(card);
}
case snd_soc_dapm_dac:
case snd_soc_dapm_aif_in:
case snd_soc_dapm_pga:
+ case snd_soc_dapm_buffer:
+ case snd_soc_dapm_scheduler:
+ case snd_soc_dapm_effect:
+ case snd_soc_dapm_src:
+ case snd_soc_dapm_asrc:
+ case snd_soc_dapm_encoder:
+ case snd_soc_dapm_decoder:
case snd_soc_dapm_out_drv:
case snd_soc_dapm_micbias:
case snd_soc_dapm_line:
int count;
devm_kfree(card->dev, (void *)*private_value);
+
+ if (!w_param_text)
+ return;
+
for (count = 0 ; count < num_params; count++)
devm_kfree(card->dev, (void *)w_param_text[count]);
devm_kfree(card->dev, w_param_text);
#include <linux/delay.h>
#include <linux/pinctrl/consumer.h>
#include <linux/pm_runtime.h>
+#include <linux/module.h>
#include <linux/slab.h>
#include <linux/workqueue.h>
#include <linux/export.h>
continue;
component->driver->ops->close(substream);
+
+ if (component->driver->module_get_upon_open)
+ module_put(component->dev->driver->owner);
}
return 0;
!component->driver->ops->open)
continue;
+ if (component->driver->module_get_upon_open &&
+ !try_module_get(component->dev->driver->owner)) {
+ ret = -ENODEV;
+ goto module_err;
+ }
+
ret = component->driver->ops->open(substream);
if (ret < 0) {
dev_err(component->dev,
component_err:
soc_pcm_components_close(substream, component);
-
+module_err:
if (cpu_dai->driver->ops->shutdown)
cpu_dai->driver->ops->shutdown(substream, cpu_dai);
out:
codec_params = *params;
/* fixup params based on TDM slot masks */
- if (codec_dai->tx_mask)
+ if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK &&
+ codec_dai->tx_mask)
soc_pcm_codec_params_fixup(&codec_params,
codec_dai->tx_mask);
- if (codec_dai->rx_mask)
+
+ if (substream->stream == SNDRV_PCM_STREAM_CAPTURE &&
+ codec_dai->rx_mask)
soc_pcm_codec_params_fixup(&codec_params,
codec_dai->rx_mask);
struct snd_soc_pcm_runtime *be, int stream)
{
struct snd_soc_dpcm *dpcm;
+ unsigned long flags;
/* only add new dpcms */
for_each_dpcm_be(fe, stream, dpcm) {
dpcm->fe = fe;
be->dpcm[stream].runtime = fe->dpcm[stream].runtime;
dpcm->state = SND_SOC_DPCM_LINK_STATE_NEW;
+ spin_lock_irqsave(&fe->card->dpcm_lock, flags);
list_add(&dpcm->list_be, &fe->dpcm[stream].be_clients);
list_add(&dpcm->list_fe, &be->dpcm[stream].fe_clients);
+ spin_unlock_irqrestore(&fe->card->dpcm_lock, flags);
dev_dbg(fe->dev, "connected new DPCM %s path %s %s %s\n",
stream ? "capture" : "playback", fe->dai_link->name,
void dpcm_be_disconnect(struct snd_soc_pcm_runtime *fe, int stream)
{
struct snd_soc_dpcm *dpcm, *d;
+ unsigned long flags;
for_each_dpcm_be_safe(fe, stream, dpcm, d) {
dev_dbg(fe->dev, "ASoC: BE %s disconnect check for %s\n",
#ifdef CONFIG_DEBUG_FS
debugfs_remove(dpcm->debugfs_state);
#endif
+ spin_lock_irqsave(&fe->card->dpcm_lock, flags);
list_del(&dpcm->list_be);
list_del(&dpcm->list_fe);
+ spin_unlock_irqrestore(&fe->card->dpcm_lock, flags);
kfree(dpcm);
}
}
void dpcm_clear_pending_state(struct snd_soc_pcm_runtime *fe, int stream)
{
struct snd_soc_dpcm *dpcm;
+ unsigned long flags;
+ spin_lock_irqsave(&fe->card->dpcm_lock, flags);
for_each_dpcm_be(fe, stream, dpcm)
dpcm->be->dpcm[stream].runtime_update =
SND_SOC_DPCM_UPDATE_NO;
+ spin_unlock_irqrestore(&fe->card->dpcm_lock, flags);
}
static void dpcm_be_dai_startup_unwind(struct snd_soc_pcm_runtime *fe,
struct snd_soc_pcm_runtime *be = dpcm->be;
struct snd_pcm_substream *be_substream =
snd_soc_dpcm_get_substream(be, stream);
- struct snd_soc_pcm_runtime *rtd = be_substream->private_data;
+ struct snd_soc_pcm_runtime *rtd;
struct snd_soc_dai *codec_dai;
int i;
+ /* A backend may not have the requested substream */
+ if (!be_substream)
+ continue;
+
+ rtd = be_substream->private_data;
if (rtd->dai_link->be_hw_params_fixup)
continue;
struct snd_soc_dpcm *dpcm;
enum snd_soc_dpcm_trigger trigger = fe->dai_link->trigger[stream];
int ret;
+ unsigned long flags;
dev_dbg(fe->dev, "ASoC: runtime %s open on FE %s\n",
stream ? "capture" : "playback", fe->dai_link->name);
dpcm_be_dai_shutdown(fe, stream);
disconnect:
/* disconnect any non started BEs */
+ spin_lock_irqsave(&fe->card->dpcm_lock, flags);
for_each_dpcm_be(fe, stream, dpcm) {
struct snd_soc_pcm_runtime *be = dpcm->be;
if (be->dpcm[stream].state != SND_SOC_DPCM_STATE_START)
dpcm->state = SND_SOC_DPCM_LINK_STATE_FREE;
}
+ spin_unlock_irqrestore(&fe->card->dpcm_lock, flags);
return ret;
}
{
struct snd_soc_dpcm *dpcm;
int state;
+ int ret = 1;
+ unsigned long flags;
+ spin_lock_irqsave(&fe->card->dpcm_lock, flags);
for_each_dpcm_fe(be, stream, dpcm) {
if (dpcm->fe == fe)
state = dpcm->fe->dpcm[stream].state;
if (state == SND_SOC_DPCM_STATE_START ||
state == SND_SOC_DPCM_STATE_PAUSED ||
- state == SND_SOC_DPCM_STATE_SUSPEND)
- return 0;
+ state == SND_SOC_DPCM_STATE_SUSPEND) {
+ ret = 0;
+ break;
+ }
}
+ spin_unlock_irqrestore(&fe->card->dpcm_lock, flags);
/* it's safe to free/stop this BE DAI */
- return 1;
+ return ret;
}
EXPORT_SYMBOL_GPL(snd_soc_dpcm_can_be_free_stop);
{
struct snd_soc_dpcm *dpcm;
int state;
+ int ret = 1;
+ unsigned long flags;
+ spin_lock_irqsave(&fe->card->dpcm_lock, flags);
for_each_dpcm_fe(be, stream, dpcm) {
if (dpcm->fe == fe)
if (state == SND_SOC_DPCM_STATE_START ||
state == SND_SOC_DPCM_STATE_PAUSED ||
state == SND_SOC_DPCM_STATE_SUSPEND ||
- state == SND_SOC_DPCM_STATE_PREPARE)
- return 0;
+ state == SND_SOC_DPCM_STATE_PREPARE) {
+ ret = 0;
+ break;
+ }
}
+ spin_unlock_irqrestore(&fe->card->dpcm_lock, flags);
/* it's safe to change hw_params */
- return 1;
+ return ret;
}
EXPORT_SYMBOL_GPL(snd_soc_dpcm_can_be_params);
struct snd_pcm_hw_params *params = &fe->dpcm[stream].hw_params;
struct snd_soc_dpcm *dpcm;
ssize_t offset = 0;
+ unsigned long flags;
/* FE state */
offset += snprintf(buf + offset, size - offset,
goto out;
}
+ spin_lock_irqsave(&fe->card->dpcm_lock, flags);
for_each_dpcm_be(fe, stream, dpcm) {
struct snd_soc_pcm_runtime *be = dpcm->be;
params = &dpcm->hw_params;
params_channels(params),
params_rate(params));
}
-
+ spin_unlock_irqrestore(&fe->card->dpcm_lock, flags);
out:
return offset;
}
snd_ctl_remove(card, kcontrol);
- kfree(dobj->control.dvalues);
+ /* free enum kcontrol's dvalues and dtexts */
+ kfree(se->dobj.control.dvalues);
for (j = 0; j < se->items; j++)
- kfree(dobj->control.dtexts[j]);
- kfree(dobj->control.dtexts);
+ kfree(se->dobj.control.dtexts[j]);
+ kfree(se->dobj.control.dtexts);
kfree(se);
kfree(w->kcontrol_news[i].name);
#include <linux/clk.h>
#include <linux/module.h>
+#include <linux/mutex.h>
#include <linux/platform_device.h>
#include <linux/slab.h>
/* PCM buffer */
unsigned char *pcm_buff;
unsigned int pos;
+
+ struct mutex lock; /* protect against race condition on iio state */
};
static const struct snd_pcm_hardware stm32_adfsdm_pcm_hw = {
{
struct stm32_adfsdm_priv *priv = snd_soc_dai_get_drvdata(dai);
+ mutex_lock(&priv->lock);
if (priv->iio_active) {
iio_channel_stop_all_cb(priv->iio_cb);
priv->iio_active = false;
}
+ mutex_unlock(&priv->lock);
}
static int stm32_adfsdm_dai_prepare(struct snd_pcm_substream *substream,
struct stm32_adfsdm_priv *priv = snd_soc_dai_get_drvdata(dai);
int ret;
+ mutex_lock(&priv->lock);
+ if (priv->iio_active) {
+ iio_channel_stop_all_cb(priv->iio_cb);
+ priv->iio_active = false;
+ }
+
ret = iio_write_channel_attribute(priv->iio_ch,
substream->runtime->rate, 0,
IIO_CHAN_INFO_SAMP_FREQ);
if (ret < 0) {
dev_err(dai->dev, "%s: Failed to set %d sampling rate\n",
__func__, substream->runtime->rate);
- return ret;
+ goto out;
}
if (!priv->iio_active) {
__func__, ret);
}
+out:
+ mutex_unlock(&priv->lock);
+
return ret;
}
static int stm32_adfsdm_probe(struct platform_device *pdev)
{
struct stm32_adfsdm_priv *priv;
+ struct snd_soc_component *component;
int ret;
priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
priv->dev = &pdev->dev;
priv->dai_drv = stm32_adfsdm_dai;
+ mutex_init(&priv->lock);
dev_set_drvdata(&pdev->dev, priv);
if (IS_ERR(priv->iio_cb))
return PTR_ERR(priv->iio_cb);
- ret = devm_snd_soc_register_component(&pdev->dev,
- &stm32_adfsdm_soc_platform,
- NULL, 0);
+ component = devm_kzalloc(&pdev->dev, sizeof(*component), GFP_KERNEL);
+ if (!component)
+ return -ENOMEM;
+#ifdef CONFIG_DEBUG_FS
+ component->debugfs_prefix = "pcm";
+#endif
+
+ ret = snd_soc_add_component(&pdev->dev, component,
+ &stm32_adfsdm_soc_platform, NULL, 0);
if (ret < 0)
dev_err(&pdev->dev, "%s: Failed to register PCM platform\n",
__func__);
return ret;
}
+static int stm32_adfsdm_remove(struct platform_device *pdev)
+{
+ snd_soc_unregister_component(&pdev->dev);
+
+ return 0;
+}
+
static struct platform_driver stm32_adfsdm_driver = {
.driver = {
.name = STM32_ADFSDM_DRV_NAME,
.of_match_table = stm32_adfsdm_of_match,
},
.probe = stm32_adfsdm_probe,
+ .remove = stm32_adfsdm_remove,
};
module_platform_driver(stm32_adfsdm_driver);
case STM32_I2S_CFG2_REG:
case STM32_I2S_IER_REG:
case STM32_I2S_SR_REG:
- case STM32_I2S_TXDR_REG:
case STM32_I2S_RXDR_REG:
case STM32_I2S_CGFR_REG:
return true;
static bool stm32_i2s_volatile_reg(struct device *dev, unsigned int reg)
{
switch (reg) {
- case STM32_I2S_TXDR_REG:
+ case STM32_I2S_SR_REG:
case STM32_I2S_RXDR_REG:
return true;
default:
if (!pdev) {
dev_err(&sai_client->pdev->dev,
"Device not found for node %pOFn\n", np_provider);
+ of_node_put(np_provider);
return -ENODEV;
}
dev_err(&sai_client->pdev->dev,
"SAI sync provider data not found\n");
ret = -EINVAL;
- goto out_put_dev;
+ goto error;
}
/* Configure sync client */
ret = stm32_sai_sync_conf_client(sai_client, synci);
if (ret < 0)
- goto out_put_dev;
+ goto error;
/* Configure sync provider */
ret = stm32_sai_sync_conf_provider(sai_provider, synco);
-out_put_dev:
+error:
put_device(&pdev->dev);
+ of_node_put(np_provider);
return ret;
}
#define SAI_IEC60958_STATUS_BYTES 24
#define SAI_MCLK_NAME_LEN 32
+#define SAI_RATE_11K 11025
/**
* struct stm32_sai_sub_data - private data of SAI sub block (block A or B)
* @slot_mask: rx or tx active slots mask. set at init or at runtime
* @data_size: PCM data width. corresponds to PCM substream width.
* @spdif_frm_cnt: S/PDIF playback frame counter
- * @snd_aes_iec958: iec958 data
+ * @iec958: iec958 data
* @ctrl_lock: control lock
+ * @irq_lock: prevent race condition with IRQ
*/
struct stm32_sai_sub_data {
struct platform_device *pdev;
unsigned int spdif_frm_cnt;
struct snd_aes_iec958 iec958;
struct mutex ctrl_lock; /* protect resources accessed by controls */
+ spinlock_t irq_lock; /* used to prevent race condition with IRQ */
};
enum stm32_sai_fifo_th {
return ret;
}
+static int stm32_sai_set_parent_clock(struct stm32_sai_sub_data *sai,
+ unsigned int rate)
+{
+ struct platform_device *pdev = sai->pdev;
+ struct clk *parent_clk = sai->pdata->clk_x8k;
+ int ret;
+
+ if (!(rate % SAI_RATE_11K))
+ parent_clk = sai->pdata->clk_x11k;
+
+ ret = clk_set_parent(sai->sai_ck, parent_clk);
+ if (ret)
+ dev_err(&pdev->dev, " Error %d setting sai_ck parent clock. %s",
+ ret, ret == -EBUSY ?
+ "Active stream rates conflict\n" : "\n");
+
+ return ret;
+}
+
static long stm32_sai_mclk_round_rate(struct clk_hw *hw, unsigned long rate,
unsigned long *prate)
{
status = SNDRV_PCM_STATE_XRUN;
}
- if (status != SNDRV_PCM_STATE_RUNNING)
+ spin_lock(&sai->irq_lock);
+ if (status != SNDRV_PCM_STATE_RUNNING && sai->substream)
snd_pcm_stop_xrun(sai->substream);
+ spin_unlock(&sai->irq_lock);
return IRQ_HANDLED;
}
struct stm32_sai_sub_data *sai = snd_soc_dai_get_drvdata(cpu_dai);
int ret;
- if (dir == SND_SOC_CLOCK_OUT) {
+ if (dir == SND_SOC_CLOCK_OUT && sai->sai_mclk) {
ret = regmap_update_bits(sai->regmap, STM_SAI_CR1_REGX,
SAI_XCR1_NODIV,
(unsigned int)~SAI_XCR1_NODIV);
if (ret < 0)
return ret;
- dev_dbg(cpu_dai->dev, "SAI MCLK frequency is %uHz\n", freq);
- sai->mclk_rate = freq;
+ /* If master clock is used, set parent clock now */
+ ret = stm32_sai_set_parent_clock(sai, freq);
+ if (ret)
+ return ret;
- if (sai->sai_mclk) {
- ret = clk_set_rate_exclusive(sai->sai_mclk,
- sai->mclk_rate);
- if (ret) {
- dev_err(cpu_dai->dev,
- "Could not set mclk rate\n");
- return ret;
- }
+ ret = clk_set_rate_exclusive(sai->sai_mclk, freq);
+ if (ret) {
+ dev_err(cpu_dai->dev,
+ ret == -EBUSY ?
+ "Active streams have incompatible rates" :
+ "Could not set mclk rate\n");
+ return ret;
}
+
+ dev_dbg(cpu_dai->dev, "SAI MCLK frequency is %uHz\n", freq);
+ sai->mclk_rate = freq;
}
return 0;
{
struct stm32_sai_sub_data *sai = snd_soc_dai_get_drvdata(cpu_dai);
int imr, cr2, ret;
+ unsigned long flags;
+ spin_lock_irqsave(&sai->irq_lock, flags);
sai->substream = substream;
+ spin_unlock_irqrestore(&sai->irq_lock, flags);
+
+ if (STM_SAI_PROTOCOL_IS_SPDIF(sai)) {
+ snd_pcm_hw_constraint_mask64(substream->runtime,
+ SNDRV_PCM_HW_PARAM_FORMAT,
+ SNDRV_PCM_FMTBIT_S32_LE);
+ snd_pcm_hw_constraint_single(substream->runtime,
+ SNDRV_PCM_HW_PARAM_CHANNELS, 2);
+ }
ret = clk_prepare_enable(sai->sai_ck);
if (ret < 0) {
struct snd_pcm_hw_params *params)
{
struct stm32_sai_sub_data *sai = snd_soc_dai_get_drvdata(cpu_dai);
- int div = 0;
+ int div = 0, cr1 = 0;
int sai_clk_rate, mclk_ratio, den;
unsigned int rate = params_rate(params);
+ int ret;
- if (!(rate % 11025))
- clk_set_parent(sai->sai_ck, sai->pdata->clk_x11k);
- else
- clk_set_parent(sai->sai_ck, sai->pdata->clk_x8k);
+ if (!sai->sai_mclk) {
+ ret = stm32_sai_set_parent_clock(sai, rate);
+ if (ret)
+ return ret;
+ }
sai_clk_rate = clk_get_rate(sai->sai_ck);
if (STM_SAI_IS_F4(sai->pdata)) {
} else {
if (sai->mclk_rate) {
mclk_ratio = sai->mclk_rate / rate;
- if ((mclk_ratio != 512) &&
- (mclk_ratio != 256)) {
+ if (mclk_ratio == 512) {
+ cr1 = SAI_XCR1_OSR;
+ } else if (mclk_ratio != 256) {
dev_err(cpu_dai->dev,
"Wrong mclk ratio %d\n",
mclk_ratio);
return -EINVAL;
}
+
+ regmap_update_bits(sai->regmap,
+ STM_SAI_CR1_REGX,
+ SAI_XCR1_OSR, cr1);
+
div = stm32_sai_get_clk_div(sai, sai_clk_rate,
sai->mclk_rate);
if (div < 0)
struct snd_soc_dai *cpu_dai)
{
struct stm32_sai_sub_data *sai = snd_soc_dai_get_drvdata(cpu_dai);
+ unsigned long flags;
regmap_update_bits(sai->regmap, STM_SAI_IMR_REGX, SAI_XIMR_MASK, 0);
regmap_update_bits(sai->regmap, STM_SAI_CR1_REGX, SAI_XCR1_NODIV,
SAI_XCR1_NODIV);
- clk_disable_unprepare(sai->sai_ck);
+ /* Release mclk rate only if rate was actually set */
+ if (sai->mclk_rate) {
+ clk_rate_exclusive_put(sai->sai_mclk);
+ sai->mclk_rate = 0;
+ }
- clk_rate_exclusive_put(sai->sai_mclk);
+ clk_disable_unprepare(sai->sai_ck);
+ spin_lock_irqsave(&sai->irq_lock, flags);
sai->substream = NULL;
+ spin_unlock_irqrestore(&sai->irq_lock, flags);
}
static int stm32_sai_pcm_new(struct snd_soc_pcm_runtime *rtd,
struct snd_soc_dai *cpu_dai)
{
struct stm32_sai_sub_data *sai = dev_get_drvdata(cpu_dai->dev);
+ struct snd_kcontrol_new knew = iec958_ctls;
if (STM_SAI_PROTOCOL_IS_SPDIF(sai)) {
dev_dbg(&sai->pdev->dev, "%s: register iec controls", __func__);
- return snd_ctl_add(rtd->pcm->card,
- snd_ctl_new1(&iec958_ctls, sai));
+ knew.device = rtd->pcm->device;
+ return snd_ctl_add(rtd->pcm->card, snd_ctl_new1(&knew, sai));
}
return 0;
static int stm32_sai_dai_probe(struct snd_soc_dai *cpu_dai)
{
struct stm32_sai_sub_data *sai = dev_get_drvdata(cpu_dai->dev);
- int cr1 = 0, cr1_mask;
+ int cr1 = 0, cr1_mask, ret;
sai->cpu_dai = cpu_dai;
/* Configure synchronization */
if (sai->sync == SAI_SYNC_EXTERNAL) {
/* Configure synchro client and provider */
- sai->pdata->set_sync(sai->pdata, sai->np_sync_provider,
- sai->synco, sai->synci);
+ ret = sai->pdata->set_sync(sai->pdata, sai->np_sync_provider,
+ sai->synco, sai->synci);
+ if (ret)
+ return ret;
}
cr1_mask |= SAI_XCR1_SYNCEN_MASK;
if (!sai->cpu_dai_drv)
return -ENOMEM;
- sai->cpu_dai_drv->name = dev_name(&pdev->dev);
if (STM_SAI_IS_PLAYBACK(sai)) {
memcpy(sai->cpu_dai_drv, &stm32_sai_playback_dai,
sizeof(stm32_sai_playback_dai));
sizeof(stm32_sai_capture_dai));
sai->cpu_dai_drv->capture.stream_name = sai->cpu_dai_drv->name;
}
+ sai->cpu_dai_drv->name = dev_name(&pdev->dev);
return 0;
}
sai->pdev = pdev;
mutex_init(&sai->ctrl_lock);
+ spin_lock_init(&sai->irq_lock);
platform_set_drvdata(pdev, sai);
sai->pdata = dev_get_drvdata(pdev->dev.parent);
{
int i;
- stream->buffer = alloc_pages_exact(stream->buffer_sz, GFP_KERNEL);
+ stream->buffer = alloc_pages_exact(buffer_sz, GFP_KERNEL);
if (!stream->buffer)
return -ENOMEM;
#define MAP_NONBLOCK 0x40000
#define MAP_NORESERVE 0x10000
#define MAP_POPULATE 0x20000
-#define MAP_PRIVATE 0x02
-#define MAP_SHARED 0x01
#define MAP_STACK 0x80000
#define PROT_EXEC 0x4
#define PROT_GROWSDOWN 0x01000000
#define wmb() asm volatile("dmb ishst" ::: "memory")
#define rmb() asm volatile("dmb ishld" ::: "memory")
+/*
+ * Kernel uses dmb variants on arm64 for smp_*() barriers. Pretty much the same
+ * implementation as above mb()/wmb()/rmb(), though for the latter kernel uses
+ * dsb. In any case, should above mb()/wmb()/rmb() change, make sure the below
+ * smp_*() don't.
+ */
+#define smp_mb() asm volatile("dmb ish" ::: "memory")
+#define smp_wmb() asm volatile("dmb ishst" ::: "memory")
+#define smp_rmb() asm volatile("dmb ishld" ::: "memory")
+
#define smp_store_release(p, v) \
do { \
union { typeof(*p) __val; char __c[1]; } __u = \
#define MAP_NONBLOCK 0x20000
#define MAP_NORESERVE 0x0400
#define MAP_POPULATE 0x10000
-#define MAP_PRIVATE 0x002
-#define MAP_SHARED 0x001
#define MAP_STACK 0x40000
#define PROT_EXEC 0x04
#define PROT_GROWSDOWN 0x01000000
#define MAP_NONBLOCK 0x20000
#define MAP_NORESERVE 0x4000
#define MAP_POPULATE 0x10000
-#define MAP_PRIVATE 0x02
-#define MAP_SHARED 0x01
#define MAP_STACK 0x40000
#define PROT_EXEC 0x4
#define PROT_GROWSDOWN 0x01000000
#define KVM_PPC_CPU_CHAR_BR_HINT_HONOURED (1ULL << 58)
#define KVM_PPC_CPU_CHAR_MTTRIG_THR_RECONF (1ULL << 57)
#define KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS (1ULL << 56)
+#define KVM_PPC_CPU_CHAR_BCCTR_FLUSH_ASSIST (1ull << 54)
#define KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY (1ULL << 63)
#define KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR (1ULL << 62)
#define KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR (1ULL << 61)
+#define KVM_PPC_CPU_BEHAV_FLUSH_COUNT_CACHE (1ull << 58)
/* Per-vcpu XICS interrupt controller state */
#define KVM_REG_PPC_ICP_STATE (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8c)
#define rmb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
#define wmb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
#elif defined(__x86_64__)
-#define mb() asm volatile("mfence":::"memory")
-#define rmb() asm volatile("lfence":::"memory")
+#define mb() asm volatile("mfence" ::: "memory")
+#define rmb() asm volatile("lfence" ::: "memory")
#define wmb() asm volatile("sfence" ::: "memory")
+#define smp_rmb() barrier()
+#define smp_wmb() barrier()
+#define smp_mb() asm volatile("lock; addl $0,-132(%%rsp)" ::: "memory", "cc")
#endif
#if defined(__x86_64__)
/* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */
#define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */
#define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */
#define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */
#define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */
#define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */
#define MAP_NONBLOCK 0x20000
#define MAP_NORESERVE 0x0400
#define MAP_POPULATE 0x10000
-#define MAP_PRIVATE 0x002
-#define MAP_SHARED 0x001
#define MAP_STACK 0x40000
#define PROT_EXEC 0x4
#define PROT_GROWSDOWN 0x01000000
return ret;
}
+static int btf_dumper_var(const struct btf_dumper *d, __u32 type_id,
+ __u8 bit_offset, const void *data)
+{
+ const struct btf_type *t = btf__type_by_id(d->btf, type_id);
+ int ret;
+
+ jsonw_start_object(d->jw);
+ jsonw_name(d->jw, btf__name_by_offset(d->btf, t->name_off));
+ ret = btf_dumper_do_type(d, t->type, bit_offset, data);
+ jsonw_end_object(d->jw);
+
+ return ret;
+}
+
+static int btf_dumper_datasec(const struct btf_dumper *d, __u32 type_id,
+ const void *data)
+{
+ struct btf_var_secinfo *vsi;
+ const struct btf_type *t;
+ int ret = 0, i, vlen;
+
+ t = btf__type_by_id(d->btf, type_id);
+ if (!t)
+ return -EINVAL;
+
+ vlen = BTF_INFO_VLEN(t->info);
+ vsi = (struct btf_var_secinfo *)(t + 1);
+
+ jsonw_start_object(d->jw);
+ jsonw_name(d->jw, btf__name_by_offset(d->btf, t->name_off));
+ jsonw_start_array(d->jw);
+ for (i = 0; i < vlen; i++) {
+ ret = btf_dumper_do_type(d, vsi[i].type, 0, data + vsi[i].offset);
+ if (ret)
+ break;
+ }
+ jsonw_end_array(d->jw);
+ jsonw_end_object(d->jw);
+
+ return ret;
+}
+
static int btf_dumper_do_type(const struct btf_dumper *d, __u32 type_id,
__u8 bit_offset, const void *data)
{
case BTF_KIND_CONST:
case BTF_KIND_RESTRICT:
return btf_dumper_modifier(d, type_id, bit_offset, data);
+ case BTF_KIND_VAR:
+ return btf_dumper_var(d, type_id, bit_offset, data);
+ case BTF_KIND_DATASEC:
+ return btf_dumper_datasec(d, type_id, data);
default:
jsonw_printf(d->jw, "(unsupported-kind");
return -EINVAL;
{
const struct btf_type *proto_type;
const struct btf_array *array;
+ const struct btf_var *var;
const struct btf_type *t;
if (!type_id) {
if (pos == -1)
return -1;
break;
+ case BTF_KIND_VAR:
+ var = (struct btf_var *)(t + 1);
+ if (var->linkage == BTF_VAR_STATIC)
+ BTF_PRINT_ARG("static ");
+ BTF_PRINT_TYPE(t->type);
+ BTF_PRINT_ARG(" %s",
+ btf__name_by_offset(btf, t->name_off));
+ break;
+ case BTF_KIND_DATASEC:
+ BTF_PRINT_ARG("section (\"%s\") ",
+ btf__name_by_offset(btf, t->name_off));
+ break;
case BTF_KIND_UNKN:
default:
return -1;
/* start of key-value pair */
jsonw_start_object(d->jw);
- jsonw_name(d->jw, "key");
+ if (map_info->btf_key_type_id) {
+ jsonw_name(d->jw, "key");
- ret = btf_dumper_type(d, map_info->btf_key_type_id, key);
- if (ret)
- goto err_end_obj;
+ ret = btf_dumper_type(d, map_info->btf_key_type_id, key);
+ if (ret)
+ goto err_end_obj;
+ }
if (!map_is_per_cpu(map_info->type)) {
jsonw_name(d->jw, "value");
if (info->nr_map_ids)
show_prog_maps(fd, info->nr_map_ids);
+ if (info->btf_id)
+ jsonw_int_field(json_wtr, "btf_id", info->btf_id);
+
if (!hash_empty(prog_table.table)) {
struct pinned_obj *obj;
}
}
+ if (info->btf_id)
+ printf("\n\tbtf_id %d\n", info->btf_id);
+
printf("\n");
}
if (insn->src_reg == BPF_PSEUDO_MAP_FD)
snprintf(dd->scratch_buff, sizeof(dd->scratch_buff),
"map[id:%u]", insn->imm);
+ else if (insn->src_reg == BPF_PSEUDO_MAP_VALUE)
+ snprintf(dd->scratch_buff, sizeof(dd->scratch_buff),
+ "map[id:%u][0]+%u", insn->imm, (insn + 1)->imm);
else
snprintf(dd->scratch_buff, sizeof(dd->scratch_buff),
"0x%llx", (unsigned long long)full_imm);
/*
* Check OpenCSD library version is sufficient to provide required features
*/
-#define OCSD_MIN_VER ((0 << 16) | (10 << 8) | (0))
+#define OCSD_MIN_VER ((0 << 16) | (11 << 8) | (0))
#if !defined(OCSD_VER_NUM) || (OCSD_VER_NUM < OCSD_MIN_VER)
-#error "OpenCSD >= 0.10.0 is required"
+#error "OpenCSD >= 0.11.0 is required"
#endif
int main(void)
.off = 0, \
.imm = ((__u64) (IMM)) >> 32 })
+#define BPF_LD_IMM64_RAW_FULL(DST, SRC, OFF1, OFF2, IMM1, IMM2) \
+ ((struct bpf_insn) { \
+ .code = BPF_LD | BPF_DW | BPF_IMM, \
+ .dst_reg = DST, \
+ .src_reg = SRC, \
+ .off = OFF1, \
+ .imm = IMM1 }), \
+ ((struct bpf_insn) { \
+ .code = 0, /* zero is reserved opcode */ \
+ .dst_reg = 0, \
+ .src_reg = 0, \
+ .off = OFF2, \
+ .imm = IMM2 })
+
/* pseudo BPF_LD_IMM64 insn used to refer to process-local map_fd */
#define BPF_LD_MAP_FD(DST, MAP_FD) \
- BPF_LD_IMM64_RAW(DST, BPF_PSEUDO_MAP_FD, MAP_FD)
+ BPF_LD_IMM64_RAW_FULL(DST, BPF_PSEUDO_MAP_FD, 0, 0, \
+ MAP_FD, 0)
+
+#define BPF_LD_MAP_VALUE(DST, MAP_FD, VALUE_OFF) \
+ BPF_LD_IMM64_RAW_FULL(DST, BPF_PSEUDO_MAP_VALUE, 0, 0, \
+ MAP_FD, VALUE_OFF)
/* Relative call */
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __ASM_GENERIC_MMAN_COMMON_TOOLS_ONLY_H
+#define __ASM_GENERIC_MMAN_COMMON_TOOLS_ONLY_H
+
+#include <asm-generic/mman-common.h>
+
+/* We need this because we need to have tools/include/uapi/ included in the tools
+ * header search path to get access to stuff that is not yet in the system's
+ * copy of the files in that directory, but since this cset:
+ *
+ * 746c9398f5ac ("arch: move common mmap flags to linux/mman.h")
+ *
+ * We end up making sys/mman.h, that is in the system headers, to not find the
+ * MAP_SHARED and MAP_PRIVATE defines because they are not anymore in our copy
+ * of asm-generic/mman-common.h. So we define them here and include this header
+ * from each of the per arch mman.h headers.
+ */
+#ifndef MAP_SHARED
+#define MAP_SHARED 0x01 /* Share changes */
+#define MAP_PRIVATE 0x02 /* Changes are private */
+#define MAP_SHARED_VALIDATE 0x03 /* share + validate extension flags */
+#endif
+#endif // __ASM_GENERIC_MMAN_COMMON_TOOLS_ONLY_H
#define PROT_GROWSDOWN 0x01000000 /* mprotect flag: extend change to start of growsdown vma */
#define PROT_GROWSUP 0x02000000 /* mprotect flag: extend change to end of growsup vma */
-#define MAP_SHARED 0x01 /* Share changes */
-#define MAP_PRIVATE 0x02 /* Changes are private */
-#define MAP_SHARED_VALIDATE 0x03 /* share + validate extension flags */
+/* 0x01 - 0x03 are defined in linux/mman.h */
#define MAP_TYPE 0x0f /* Mask for type of mapping */
#define MAP_FIXED 0x10 /* Interpret addr exactly */
#define MAP_ANONYMOUS 0x20 /* don't use a file */
#ifndef __ASM_GENERIC_MMAN_H
#define __ASM_GENERIC_MMAN_H
-#include <asm-generic/mman-common.h>
+#include <asm-generic/mman-common-tools.h>
#define MAP_GROWSDOWN 0x0100 /* stack-like segment */
#define MAP_DENYWRITE 0x0800 /* ETXTBSY */
__SYSCALL(__NR_sched_rr_get_interval_time64, sys_sched_rr_get_interval)
#endif
+#define __NR_pidfd_send_signal 424
+__SYSCALL(__NR_pidfd_send_signal, sys_pidfd_send_signal)
+#define __NR_io_uring_setup 425
+__SYSCALL(__NR_io_uring_setup, sys_io_uring_setup)
+#define __NR_io_uring_enter 426
+__SYSCALL(__NR_io_uring_enter, sys_io_uring_enter)
+#define __NR_io_uring_register 427
+__SYSCALL(__NR_io_uring_register, sys_io_uring_register)
+
#undef __NR_syscalls
-#define __NR_syscalls 424
+#define __NR_syscalls 428
/*
* 32 bit systems traditionally used different
#define I915_CONTEXT_MAX_USER_PRIORITY 1023 /* inclusive */
#define I915_CONTEXT_DEFAULT_PRIORITY 0
#define I915_CONTEXT_MIN_USER_PRIORITY -1023 /* inclusive */
+ /*
+ * When using the following param, value should be a pointer to
+ * drm_i915_gem_context_param_sseu.
+ */
+#define I915_CONTEXT_PARAM_SSEU 0x7
__u64 value;
};
+/**
+ * Context SSEU programming
+ *
+ * It may be necessary for either functional or performance reason to configure
+ * a context to run with a reduced number of SSEU (where SSEU stands for Slice/
+ * Sub-slice/EU).
+ *
+ * This is done by configuring SSEU configuration using the below
+ * @struct drm_i915_gem_context_param_sseu for every supported engine which
+ * userspace intends to use.
+ *
+ * Not all GPUs or engines support this functionality in which case an error
+ * code -ENODEV will be returned.
+ *
+ * Also, flexibility of possible SSEU configuration permutations varies between
+ * GPU generations and software imposed limitations. Requesting such a
+ * combination will return an error code of -EINVAL.
+ *
+ * NOTE: When perf/OA is active the context's SSEU configuration is ignored in
+ * favour of a single global setting.
+ */
+struct drm_i915_gem_context_param_sseu {
+ /*
+ * Engine class & instance to be configured or queried.
+ */
+ __u16 engine_class;
+ __u16 engine_instance;
+
+ /*
+ * Unused for now. Must be cleared to zero.
+ */
+ __u32 flags;
+
+ /*
+ * Mask of slices to enable for the context. Valid values are a subset
+ * of the bitmask value returned for I915_PARAM_SLICE_MASK.
+ */
+ __u64 slice_mask;
+
+ /*
+ * Mask of subslices to enable for the context. Valid values are a
+ * subset of the bitmask value return by I915_PARAM_SUBSLICE_MASK.
+ */
+ __u64 subslice_mask;
+
+ /*
+ * Minimum/Maximum number of EUs to enable per subslice for the
+ * context. min_eus_per_subslice must be inferior or equal to
+ * max_eus_per_subslice.
+ */
+ __u16 min_eus_per_subslice;
+ __u16 max_eus_per_subslice;
+
+ /*
+ * Unused for now. Must be cleared to zero.
+ */
+ __u32 rsvd;
+};
+
enum drm_i915_oa_format {
I915_OA_FORMAT_A13 = 1, /* HSW only */
I915_OA_FORMAT_A29, /* HSW only */
BPF_BTF_GET_FD_BY_ID,
BPF_TASK_FD_QUERY,
BPF_MAP_LOOKUP_AND_DELETE_ELEM,
+ BPF_MAP_FREEZE,
};
enum bpf_map_type {
*/
#define BPF_F_ANY_ALIGNMENT (1U << 1)
-/* when bpf_ldimm64->src_reg == BPF_PSEUDO_MAP_FD, bpf_ldimm64->imm == fd */
+/* When BPF ldimm64's insn[0].src_reg != 0 then this can have
+ * two extensions:
+ *
+ * insn[0].src_reg: BPF_PSEUDO_MAP_FD BPF_PSEUDO_MAP_VALUE
+ * insn[0].imm: map fd map fd
+ * insn[1].imm: 0 offset into value
+ * insn[0].off: 0 0
+ * insn[1].off: 0 0
+ * ldimm64 rewrite: address of map address of map[0]+offset
+ * verifier type: CONST_PTR_TO_MAP PTR_TO_MAP_VALUE
+ */
#define BPF_PSEUDO_MAP_FD 1
+#define BPF_PSEUDO_MAP_VALUE 2
/* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative
* offset to another bpf function
#define BPF_OBJ_NAME_LEN 16U
-/* Flags for accessing BPF object */
+/* Flags for accessing BPF object from syscall side. */
#define BPF_F_RDONLY (1U << 3)
#define BPF_F_WRONLY (1U << 4)
/* Zero-initialize hash function seed. This should only be used for testing. */
#define BPF_F_ZERO_SEED (1U << 6)
+/* Flags for accessing BPF object from program side. */
+#define BPF_F_RDONLY_PROG (1U << 7)
+#define BPF_F_WRONLY_PROG (1U << 8)
+
/* flags for BPF_PROG_QUERY */
#define BPF_F_QUERY_EFFECTIVE (1U << 0)
__aligned_u64 data_out;
__u32 repeat;
__u32 duration;
+ __u32 ctx_size_in; /* input: len of ctx_in */
+ __u32 ctx_size_out; /* input/output: len of ctx_out
+ * returns ENOSPC if ctx_out
+ * is too small.
+ */
+ __aligned_u64 ctx_in;
+ __aligned_u64 ctx_out;
} test;
struct { /* anonymous struct used by BPF_*_GET_*_ID */
* * **BPF_F_ADJ_ROOM_ENCAP_L4_UDP **:
* Use with ENCAP_L3 flags to further specify the tunnel type.
*
+ * * **BPF_F_ADJ_ROOM_ENCAP_L2(len) **:
+ * Use with ENCAP_L3/L4 flags to further specify the tunnel
+ * type; **len** is the length of the inner MAC header.
+ *
* A call to this helper is susceptible to change the underlaying
* packet buffer. Therefore, at load time, all checks on pointers
* previously done by the verifier are invalidated and must be
/* BPF_FUNC_skb_adjust_room flags. */
#define BPF_F_ADJ_ROOM_FIXED_GSO (1ULL << 0)
+#define BPF_ADJ_ROOM_ENCAP_L2_MASK 0xff
+#define BPF_ADJ_ROOM_ENCAP_L2_SHIFT 56
+
#define BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 (1ULL << 1)
#define BPF_F_ADJ_ROOM_ENCAP_L3_IPV6 (1ULL << 2)
#define BPF_F_ADJ_ROOM_ENCAP_L4_GRE (1ULL << 3)
#define BPF_F_ADJ_ROOM_ENCAP_L4_UDP (1ULL << 4)
+#define BPF_F_ADJ_ROOM_ENCAP_L2(len) (((__u64)len & \
+ BPF_ADJ_ROOM_ENCAP_L2_MASK) \
+ << BPF_ADJ_ROOM_ENCAP_L2_SHIFT)
/* Mode for BPF_FUNC_skb_adjust_room helper. */
enum bpf_adj_room_mode {
* struct, union and fwd
*/
__u32 info;
- /* "size" is used by INT, ENUM, STRUCT and UNION.
+ /* "size" is used by INT, ENUM, STRUCT, UNION and DATASEC.
* "size" tells the size of the type it is describing.
*
* "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT,
- * FUNC and FUNC_PROTO.
+ * FUNC, FUNC_PROTO and VAR.
* "type" is a type_id referring to another type.
*/
union {
#define BTF_KIND_RESTRICT 11 /* Restrict */
#define BTF_KIND_FUNC 12 /* Function */
#define BTF_KIND_FUNC_PROTO 13 /* Function Proto */
-#define BTF_KIND_MAX 13
-#define NR_BTF_KINDS 14
+#define BTF_KIND_VAR 14 /* Variable */
+#define BTF_KIND_DATASEC 15 /* Section */
+#define BTF_KIND_MAX BTF_KIND_DATASEC
+#define NR_BTF_KINDS (BTF_KIND_MAX + 1)
/* For some specific BTF_KIND, "struct btf_type" is immediately
* followed by extra data.
__u32 type;
};
+enum {
+ BTF_VAR_STATIC = 0,
+ BTF_VAR_GLOBAL_ALLOCATED,
+};
+
+/* BTF_KIND_VAR is followed by a single "struct btf_var" to describe
+ * additional information related to the variable such as its linkage.
+ */
+struct btf_var {
+ __u32 linkage;
+};
+
+/* BTF_KIND_DATASEC is followed by multiple "struct btf_var_secinfo"
+ * to describe all BTF_KIND_VAR types it contains along with it's
+ * in-section offset as well as size.
+ */
+struct btf_var_secinfo {
+ __u32 type;
+ __u32 offset;
+ __u32 size;
+};
+
#endif /* _UAPI__LINUX_BTF_H__ */
#define F_SEAL_SHRINK 0x0002 /* prevent file from shrinking */
#define F_SEAL_GROW 0x0004 /* prevent file from growing */
#define F_SEAL_WRITE 0x0008 /* prevent writes */
+#define F_SEAL_FUTURE_WRITE 0x0010 /* prevent future writes while mapped */
/* (1U << 31) is reserved for signed error codes */
/*
#define OVERCOMMIT_ALWAYS 1
#define OVERCOMMIT_NEVER 2
+#define MAP_SHARED 0x01 /* Share changes */
+#define MAP_PRIVATE 0x02 /* Changes are private */
+#define MAP_SHARED_VALIDATE 0x03 /* share + validate extension flags */
+
/*
* Huge page size encoding when MAP_HUGETLB is specified, and a huge page
* size other than the default is desired. See hugetlb_encode.h.
#include "liburing.h"
#include "barrier.h"
-#ifndef IOCQE_FLAG_CACHEHIT
-#define IOCQE_FLAG_CACHEHIT (1U << 0)
-#endif
-
#define min(a, b) ((a < b) ? (a) : (b))
struct io_sq_ring {
unsigned long reaps;
unsigned long done;
unsigned long calls;
- unsigned long cachehit, cachemiss;
volatile int finish;
__s32 *fds;
return -1;
}
}
- if (cqe->flags & IOCQE_FLAG_CACHEHIT)
- s->cachehit++;
- else
- s->cachemiss++;
reaped++;
head++;
} while (1);
int main(int argc, char *argv[])
{
struct submitter *s = &submitters[0];
- unsigned long done, calls, reap, cache_hit, cache_miss;
+ unsigned long done, calls, reap;
int err, i, flags, fd;
char *fdepths;
void *ret;
pthread_create(&s->thread, NULL, submitter_fn, s);
fdepths = malloc(8 * s->nr_files);
- cache_hit = cache_miss = reap = calls = done = 0;
+ reap = calls = done = 0;
do {
unsigned long this_done = 0;
unsigned long this_reap = 0;
unsigned long this_call = 0;
- unsigned long this_cache_hit = 0;
- unsigned long this_cache_miss = 0;
unsigned long rpc = 0, ipc = 0;
- double hit = 0.0;
sleep(1);
this_done += s->done;
this_call += s->calls;
this_reap += s->reaps;
- this_cache_hit += s->cachehit;
- this_cache_miss += s->cachemiss;
- if (this_cache_hit && this_cache_miss) {
- unsigned long hits, total;
-
- hits = this_cache_hit - cache_hit;
- total = hits + this_cache_miss - cache_miss;
- hit = (double) hits / (double) total;
- hit *= 100.0;
- }
if (this_call - calls) {
rpc = (this_done - done) / (this_call - calls);
ipc = (this_reap - reap) / (this_call - calls);
} else
rpc = ipc = -1;
file_depths(fdepths);
- printf("IOPS=%lu, IOS/call=%ld/%ld, inflight=%u (%s), Cachehit=%0.2f%%\n",
+ printf("IOPS=%lu, IOS/call=%ld/%ld, inflight=%u (%s)\n",
this_done - done, rpc, ipc, s->inflight,
- fdepths, hit);
+ fdepths);
done = this_done;
calls = this_call;
reap = this_reap;
- cache_hit = s->cachehit;
- cache_miss = s->cachemiss;
} while (!finish);
pthread_join(s->thread, &ret);
libbpf_version.h
+libbpf.pc
FEATURE-DUMP.libbpf
test_libbpf
BPF_VERSION = 0
BPF_PATCHLEVEL = 0
-BPF_EXTRAVERSION = 2
+BPF_EXTRAVERSION = 3
MAKEFLAGS += --no-print-directory
LIB_TARGET = libbpf.a libbpf.so.$(LIBBPF_VERSION)
LIB_FILE = libbpf.a libbpf.so*
+PC_FILE = libbpf.pc
# Set compile option CFLAGS
ifdef EXTRA_CFLAGS
LIB_TARGET := $(addprefix $(OUTPUT),$(LIB_TARGET))
LIB_FILE := $(addprefix $(OUTPUT),$(LIB_FILE))
+PC_FILE := $(addprefix $(OUTPUT),$(PC_FILE))
GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN) | \
awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {s++} END{print s}')
VERSIONED_SYM_COUNT = $(shell readelf -s --wide $(OUTPUT)libbpf.so | \
grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | sort -u | wc -l)
-CMD_TARGETS = $(LIB_TARGET)
+CMD_TARGETS = $(LIB_TARGET) $(PC_FILE)
CXX_TEST_TARGET = $(OUTPUT)test_libbpf
$(OUTPUT)libbpf.so.$(LIBBPF_VERSION): $(BPF_IN)
$(QUIET_LINK)$(CC) --shared -Wl,-soname,libbpf.so.$(VERSION) \
- -Wl,--version-script=$(VERSION_SCRIPT) $^ -o $@
+ -Wl,--version-script=$(VERSION_SCRIPT) $^ -lelf -o $@
@ln -sf $(@F) $(OUTPUT)libbpf.so
@ln -sf $(@F) $(OUTPUT)libbpf.so.$(VERSION)
$(OUTPUT)test_libbpf: test_libbpf.cpp $(OUTPUT)libbpf.a
$(QUIET_LINK)$(CXX) $(INCLUDES) $^ -lelf -o $@
+$(OUTPUT)libbpf.pc:
+ $(QUIET_GEN)sed -e "s|@PREFIX@|$(prefix)|" \
+ -e "s|@LIBDIR@|$(libdir_SQ)|" \
+ -e "s|@VERSION@|$(LIBBPF_VERSION)|" \
+ < libbpf.pc.template > $@
+
check: check_abi
check_abi: $(OUTPUT)libbpf.so
install_headers:
$(call QUIET_INSTALL, headers) \
$(call do_install,bpf.h,$(prefix)/include/bpf,644); \
- $(call do_install,libbpf.h,$(prefix)/include/bpf,644);
- $(call do_install,btf.h,$(prefix)/include/bpf,644);
+ $(call do_install,libbpf.h,$(prefix)/include/bpf,644); \
+ $(call do_install,btf.h,$(prefix)/include/bpf,644); \
+ $(call do_install,xsk.h,$(prefix)/include/bpf,644);
+
+install_pkgconfig: $(PC_FILE)
+ $(call QUIET_INSTALL, $(PC_FILE)) \
+ $(call do_install,$(PC_FILE),$(libdir_SQ)/pkgconfig,644)
-install: install_lib
+install: install_lib install_pkgconfig
### Cleaning rules
clean:
$(call QUIET_CLEAN, libbpf) $(RM) $(TARGETS) $(CXX_TEST_TARGET) \
- *.o *~ *.a *.so *.so.$(VERSION) .*.d .*.cmd LIBBPF-CFLAGS
+ *.o *~ *.a *.so *.so.$(VERSION) .*.d .*.cmd *.pc LIBBPF-CFLAGS
$(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP.libbpf
int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr)
{
- __u32 name_len = create_attr->name ? strlen(create_attr->name) : 0;
union bpf_attr attr;
memset(&attr, '\0', sizeof(attr));
attr.value_size = create_attr->value_size;
attr.max_entries = create_attr->max_entries;
attr.map_flags = create_attr->map_flags;
- memcpy(attr.map_name, create_attr->name,
- min(name_len, BPF_OBJ_NAME_LEN - 1));
+ if (create_attr->name)
+ memcpy(attr.map_name, create_attr->name,
+ min(strlen(create_attr->name), BPF_OBJ_NAME_LEN - 1));
attr.numa_node = create_attr->numa_node;
attr.btf_fd = create_attr->btf_fd;
attr.btf_key_type_id = create_attr->btf_key_type_id;
int key_size, int inner_map_fd, int max_entries,
__u32 map_flags, int node)
{
- __u32 name_len = name ? strlen(name) : 0;
union bpf_attr attr;
memset(&attr, '\0', sizeof(attr));
attr.inner_map_fd = inner_map_fd;
attr.max_entries = max_entries;
attr.map_flags = map_flags;
- memcpy(attr.map_name, name, min(name_len, BPF_OBJ_NAME_LEN - 1));
+ if (name)
+ memcpy(attr.map_name, name,
+ min(strlen(name), BPF_OBJ_NAME_LEN - 1));
if (node >= 0) {
attr.map_flags |= BPF_F_NUMA_NODE;
void *finfo = NULL, *linfo = NULL;
union bpf_attr attr;
__u32 log_level;
- __u32 name_len;
int fd;
if (!load_attr || !log_buf != !log_buf_sz)
return -EINVAL;
log_level = load_attr->log_level;
- if (log_level > 2 || (log_level && !log_buf))
+ if (log_level > (4 | 2 | 1) || (log_level && !log_buf))
return -EINVAL;
- name_len = load_attr->name ? strlen(load_attr->name) : 0;
-
memset(&attr, 0, sizeof(attr));
attr.prog_type = load_attr->prog_type;
attr.expected_attach_type = load_attr->expected_attach_type;
attr.line_info_rec_size = load_attr->line_info_rec_size;
attr.line_info_cnt = load_attr->line_info_cnt;
attr.line_info = ptr_to_u64(load_attr->line_info);
- memcpy(attr.prog_name, load_attr->name,
- min(name_len, BPF_OBJ_NAME_LEN - 1));
+ if (load_attr->name)
+ memcpy(attr.prog_name, load_attr->name,
+ min(strlen(load_attr->name), BPF_OBJ_NAME_LEN - 1));
fd = sys_bpf_prog_load(&attr, sizeof(attr));
if (fd >= 0)
return sys_bpf(BPF_MAP_GET_NEXT_KEY, &attr, sizeof(attr));
}
+int bpf_map_freeze(int fd)
+{
+ union bpf_attr attr;
+
+ memset(&attr, 0, sizeof(attr));
+ attr.map_fd = fd;
+
+ return sys_bpf(BPF_MAP_FREEZE, &attr, sizeof(attr));
+}
+
int bpf_obj_pin(int fd, const char *pathname)
{
union bpf_attr attr;
attr.test.data_out = ptr_to_u64(test_attr->data_out);
attr.test.data_size_in = test_attr->data_size_in;
attr.test.data_size_out = test_attr->data_size_out;
+ attr.test.ctx_in = ptr_to_u64(test_attr->ctx_in);
+ attr.test.ctx_out = ptr_to_u64(test_attr->ctx_out);
+ attr.test.ctx_size_in = test_attr->ctx_size_in;
+ attr.test.ctx_size_out = test_attr->ctx_size_out;
attr.test.repeat = test_attr->repeat;
ret = sys_bpf(BPF_PROG_TEST_RUN, &attr, sizeof(attr));
test_attr->data_size_out = attr.test.data_size_out;
+ test_attr->ctx_size_out = attr.test.ctx_size_out;
test_attr->retval = attr.test.retval;
test_attr->duration = attr.test.duration;
return ret;
#define MAPS_RELAX_COMPAT 0x01
/* Recommend log buffer size */
-#define BPF_LOG_BUF_SIZE (256 * 1024)
+#define BPF_LOG_BUF_SIZE (16 * 1024 * 1024) /* verifier maximum in kernels <= 5.1 */
LIBBPF_API int
bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
char *log_buf, size_t log_buf_sz);
void *value);
LIBBPF_API int bpf_map_delete_elem(int fd, const void *key);
LIBBPF_API int bpf_map_get_next_key(int fd, const void *key, void *next_key);
+LIBBPF_API int bpf_map_freeze(int fd);
LIBBPF_API int bpf_obj_pin(int fd, const char *pathname);
LIBBPF_API int bpf_obj_get(const char *pathname);
LIBBPF_API int bpf_prog_attach(int prog_fd, int attachable_fd,
* out: length of data_out */
__u32 retval; /* out: return code of the BPF program */
__u32 duration; /* out: average per repetition in ns */
+ const void *ctx_in; /* optional */
+ __u32 ctx_size_in;
+ void *ctx_out; /* optional */
+ __u32 ctx_size_out; /* in: max length of ctx_out
+ * out: length of cxt_out */
};
LIBBPF_API int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr);
((k) == BTF_KIND_CONST) || \
((k) == BTF_KIND_RESTRICT))
+#define IS_VAR(k) ((k) == BTF_KIND_VAR)
+
static struct btf_type btf_void;
struct btf {
return base_size + vlen * sizeof(struct btf_member);
case BTF_KIND_FUNC_PROTO:
return base_size + vlen * sizeof(struct btf_param);
+ case BTF_KIND_VAR:
+ return base_size + sizeof(struct btf_var);
+ case BTF_KIND_DATASEC:
+ return base_size + vlen * sizeof(struct btf_var_secinfo);
default:
pr_debug("Unsupported BTF_KIND:%u\n", BTF_INFO_KIND(t->info));
return -EINVAL;
case BTF_KIND_STRUCT:
case BTF_KIND_UNION:
case BTF_KIND_ENUM:
+ case BTF_KIND_DATASEC:
size = t->size;
goto done;
case BTF_KIND_PTR:
case BTF_KIND_VOLATILE:
case BTF_KIND_CONST:
case BTF_KIND_RESTRICT:
+ case BTF_KIND_VAR:
type_id = t->type;
break;
case BTF_KIND_ARRAY:
t = btf__type_by_id(btf, type_id);
while (depth < MAX_RESOLVE_DEPTH &&
!btf_type_is_void_or_null(t) &&
- IS_MODIFIER(BTF_INFO_KIND(t->info))) {
+ (IS_MODIFIER(BTF_INFO_KIND(t->info)) ||
+ IS_VAR(BTF_INFO_KIND(t->info)))) {
type_id = t->type;
t = btf__type_by_id(btf, type_id);
depth++;
return btf;
}
+static int compare_vsi_off(const void *_a, const void *_b)
+{
+ const struct btf_var_secinfo *a = _a;
+ const struct btf_var_secinfo *b = _b;
+
+ return a->offset - b->offset;
+}
+
+static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf,
+ struct btf_type *t)
+{
+ __u32 size = 0, off = 0, i, vars = BTF_INFO_VLEN(t->info);
+ const char *name = btf__name_by_offset(btf, t->name_off);
+ const struct btf_type *t_var;
+ struct btf_var_secinfo *vsi;
+ struct btf_var *var;
+ int ret;
+
+ if (!name) {
+ pr_debug("No name found in string section for DATASEC kind.\n");
+ return -ENOENT;
+ }
+
+ ret = bpf_object__section_size(obj, name, &size);
+ if (ret || !size || (t->size && t->size != size)) {
+ pr_debug("Invalid size for section %s: %u bytes\n", name, size);
+ return -ENOENT;
+ }
+
+ t->size = size;
+
+ for (i = 0, vsi = (struct btf_var_secinfo *)(t + 1);
+ i < vars; i++, vsi++) {
+ t_var = btf__type_by_id(btf, vsi->type);
+ var = (struct btf_var *)(t_var + 1);
+
+ if (BTF_INFO_KIND(t_var->info) != BTF_KIND_VAR) {
+ pr_debug("Non-VAR type seen in section %s\n", name);
+ return -EINVAL;
+ }
+
+ if (var->linkage == BTF_VAR_STATIC)
+ continue;
+
+ name = btf__name_by_offset(btf, t_var->name_off);
+ if (!name) {
+ pr_debug("No name found in string section for VAR kind\n");
+ return -ENOENT;
+ }
+
+ ret = bpf_object__variable_offset(obj, name, &off);
+ if (ret) {
+ pr_debug("No offset found in symbol table for VAR %s\n", name);
+ return -ENOENT;
+ }
+
+ vsi->offset = off;
+ }
+
+ qsort(t + 1, vars, sizeof(*vsi), compare_vsi_off);
+ return 0;
+}
+
+int btf__finalize_data(struct bpf_object *obj, struct btf *btf)
+{
+ int err = 0;
+ __u32 i;
+
+ for (i = 1; i <= btf->nr_types; i++) {
+ struct btf_type *t = btf->types[i];
+
+ /* Loader needs to fix up some of the things compiler
+ * couldn't get its hands on while emitting BTF. This
+ * is section size and global variable offset. We use
+ * the info from the ELF itself for this purpose.
+ */
+ if (BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC) {
+ err = btf_fixup_datasec(obj, btf, t);
+ if (err)
+ break;
+ }
+ }
+
+ return err;
+}
+
int btf__load(struct btf *btf)
{
__u32 log_buf_size = BPF_LOG_BUF_SIZE;
return fwd_kind == real_kind;
}
+ if (cand_kind != canon_kind)
+ return 0;
+
switch (cand_kind) {
case BTF_KIND_INT:
return btf_equal_int(cand_type, canon_type);
struct btf_ext;
struct btf_type;
+struct bpf_object;
+
/*
* The .BTF.ext ELF section layout defined as
* struct btf_ext_header
LIBBPF_API void btf__free(struct btf *btf);
LIBBPF_API struct btf *btf__new(__u8 *data, __u32 size);
+LIBBPF_API int btf__finalize_data(struct bpf_object *obj, struct btf *btf);
LIBBPF_API int btf__load(struct btf *btf);
LIBBPF_API __s32 btf__find_by_name(const struct btf *btf,
const char *type_name);
* Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
* Copyright (C) 2015 Huawei Inc.
* Copyright (C) 2017 Nicira, Inc.
+ * Copyright (C) 2019 Isovalent, Inc.
*/
#ifndef _GNU_SOURCE
#define BPF_FS_MAGIC 0xcafe4a11
#endif
+/* vsprintf() in __base_pr() uses nonliteral format string. It may break
+ * compilation if user enables corresponding warning. Disable it explicitly.
+ */
+#pragma GCC diagnostic ignored "-Wformat-nonliteral"
+
#define __printf(a, b) __attribute__((format(printf, a, b)))
static int __base_pr(enum libbpf_print_level level, const char *format,
enum {
RELO_LD64,
RELO_CALL,
+ RELO_DATA,
} type;
int insn_idx;
union {
};
} *reloc_desc;
int nr_reloc;
+ int log_level;
struct {
int nr;
__u32 line_info_cnt;
};
+enum libbpf_map_type {
+ LIBBPF_MAP_UNSPEC,
+ LIBBPF_MAP_DATA,
+ LIBBPF_MAP_BSS,
+ LIBBPF_MAP_RODATA,
+};
+
+static const char * const libbpf_type_to_btf_name[] = {
+ [LIBBPF_MAP_DATA] = ".data",
+ [LIBBPF_MAP_BSS] = ".bss",
+ [LIBBPF_MAP_RODATA] = ".rodata",
+};
+
struct bpf_map {
int fd;
char *name;
__u32 btf_value_type_id;
void *priv;
bpf_map_clear_priv_t clear_priv;
+ enum libbpf_map_type libbpf_type;
+};
+
+struct bpf_secdata {
+ void *rodata;
+ void *data;
};
static LIST_HEAD(bpf_objects_list);
struct bpf_object {
+ char name[BPF_OBJ_NAME_LEN];
char license[64];
__u32 kern_version;
size_t nr_programs;
struct bpf_map *maps;
size_t nr_maps;
+ struct bpf_secdata sections;
bool loaded;
bool has_pseudo_calls;
Elf *elf;
GElf_Ehdr ehdr;
Elf_Data *symbols;
+ Elf_Data *data;
+ Elf_Data *rodata;
+ Elf_Data *bss;
size_t strtabidx;
struct {
GElf_Shdr shdr;
int nr_reloc;
int maps_shndx;
int text_shndx;
+ int data_shndx;
+ int rodata_shndx;
+ int bss_shndx;
} efile;
/*
* All loaded bpf_object is linked in a list, which is
size_t obj_buf_sz)
{
struct bpf_object *obj;
+ char *end;
obj = calloc(1, sizeof(struct bpf_object) + strlen(path) + 1);
if (!obj) {
}
strcpy(obj->path, path);
- obj->efile.fd = -1;
+ /* Using basename() GNU version which doesn't modify arg. */
+ strncpy(obj->name, basename((void *)path),
+ sizeof(obj->name) - 1);
+ end = strchr(obj->name, '.');
+ if (end)
+ *end = 0;
+ obj->efile.fd = -1;
/*
* Caller of this function should also calls
* bpf_object__elf_finish() after data collection to return
obj->efile.obj_buf = obj_buf;
obj->efile.obj_buf_sz = obj_buf_sz;
obj->efile.maps_shndx = -1;
+ obj->efile.data_shndx = -1;
+ obj->efile.rodata_shndx = -1;
+ obj->efile.bss_shndx = -1;
obj->loaded = false;
obj->efile.elf = NULL;
}
obj->efile.symbols = NULL;
+ obj->efile.data = NULL;
+ obj->efile.rodata = NULL;
+ obj->efile.bss = NULL;
zfree(&obj->efile.reloc);
obj->efile.nr_reloc = 0;
return false;
}
+static int bpf_object_search_section_size(const struct bpf_object *obj,
+ const char *name, size_t *d_size)
+{
+ const GElf_Ehdr *ep = &obj->efile.ehdr;
+ Elf *elf = obj->efile.elf;
+ Elf_Scn *scn = NULL;
+ int idx = 0;
+
+ while ((scn = elf_nextscn(elf, scn)) != NULL) {
+ const char *sec_name;
+ Elf_Data *data;
+ GElf_Shdr sh;
+
+ idx++;
+ if (gelf_getshdr(scn, &sh) != &sh) {
+ pr_warning("failed to get section(%d) header from %s\n",
+ idx, obj->path);
+ return -EIO;
+ }
+
+ sec_name = elf_strptr(elf, ep->e_shstrndx, sh.sh_name);
+ if (!sec_name) {
+ pr_warning("failed to get section(%d) name from %s\n",
+ idx, obj->path);
+ return -EIO;
+ }
+
+ if (strcmp(name, sec_name))
+ continue;
+
+ data = elf_getdata(scn, 0);
+ if (!data) {
+ pr_warning("failed to get section(%d) data from %s(%s)\n",
+ idx, name, obj->path);
+ return -EIO;
+ }
+
+ *d_size = data->d_size;
+ return 0;
+ }
+
+ return -ENOENT;
+}
+
+int bpf_object__section_size(const struct bpf_object *obj, const char *name,
+ __u32 *size)
+{
+ int ret = -ENOENT;
+ size_t d_size;
+
+ *size = 0;
+ if (!name) {
+ return -EINVAL;
+ } else if (!strcmp(name, ".data")) {
+ if (obj->efile.data)
+ *size = obj->efile.data->d_size;
+ } else if (!strcmp(name, ".bss")) {
+ if (obj->efile.bss)
+ *size = obj->efile.bss->d_size;
+ } else if (!strcmp(name, ".rodata")) {
+ if (obj->efile.rodata)
+ *size = obj->efile.rodata->d_size;
+ } else {
+ ret = bpf_object_search_section_size(obj, name, &d_size);
+ if (!ret)
+ *size = d_size;
+ }
+
+ return *size ? 0 : ret;
+}
+
+int bpf_object__variable_offset(const struct bpf_object *obj, const char *name,
+ __u32 *off)
+{
+ Elf_Data *symbols = obj->efile.symbols;
+ const char *sname;
+ size_t si;
+
+ if (!name || !off)
+ return -EINVAL;
+
+ for (si = 0; si < symbols->d_size / sizeof(GElf_Sym); si++) {
+ GElf_Sym sym;
+
+ if (!gelf_getsym(symbols, si, &sym))
+ continue;
+ if (GELF_ST_BIND(sym.st_info) != STB_GLOBAL ||
+ GELF_ST_TYPE(sym.st_info) != STT_OBJECT)
+ continue;
+
+ sname = elf_strptr(obj->efile.elf, obj->efile.strtabidx,
+ sym.st_name);
+ if (!sname) {
+ pr_warning("failed to get sym name string for var %s\n",
+ name);
+ return -EIO;
+ }
+ if (strcmp(name, sname) == 0) {
+ *off = sym.st_value;
+ return 0;
+ }
+ }
+
+ return -ENOENT;
+}
+
+static bool bpf_object__has_maps(const struct bpf_object *obj)
+{
+ return obj->efile.maps_shndx >= 0 ||
+ obj->efile.data_shndx >= 0 ||
+ obj->efile.rodata_shndx >= 0 ||
+ obj->efile.bss_shndx >= 0;
+}
+
+static int
+bpf_object__init_internal_map(struct bpf_object *obj, struct bpf_map *map,
+ enum libbpf_map_type type, Elf_Data *data,
+ void **data_buff)
+{
+ struct bpf_map_def *def = &map->def;
+ char map_name[BPF_OBJ_NAME_LEN];
+
+ map->libbpf_type = type;
+ map->offset = ~(typeof(map->offset))0;
+ snprintf(map_name, sizeof(map_name), "%.8s%.7s", obj->name,
+ libbpf_type_to_btf_name[type]);
+ map->name = strdup(map_name);
+ if (!map->name) {
+ pr_warning("failed to alloc map name\n");
+ return -ENOMEM;
+ }
+
+ def->type = BPF_MAP_TYPE_ARRAY;
+ def->key_size = sizeof(int);
+ def->value_size = data->d_size;
+ def->max_entries = 1;
+ def->map_flags = type == LIBBPF_MAP_RODATA ?
+ BPF_F_RDONLY_PROG : 0;
+ if (data_buff) {
+ *data_buff = malloc(data->d_size);
+ if (!*data_buff) {
+ zfree(&map->name);
+ pr_warning("failed to alloc map content buffer\n");
+ return -ENOMEM;
+ }
+ memcpy(*data_buff, data->d_buf, data->d_size);
+ }
+
+ pr_debug("map %ld is \"%s\"\n", map - obj->maps, map->name);
+ return 0;
+}
+
static int
bpf_object__init_maps(struct bpf_object *obj, int flags)
{
+ int i, map_idx, map_def_sz = 0, nr_syms, nr_maps = 0, nr_maps_glob = 0;
bool strict = !(flags & MAPS_RELAX_COMPAT);
- int i, map_idx, map_def_sz, nr_maps = 0;
- Elf_Scn *scn;
- Elf_Data *data = NULL;
Elf_Data *symbols = obj->efile.symbols;
+ Elf_Data *data = NULL;
+ int ret = 0;
- if (obj->efile.maps_shndx < 0)
- return -EINVAL;
if (!symbols)
return -EINVAL;
+ nr_syms = symbols->d_size / sizeof(GElf_Sym);
- scn = elf_getscn(obj->efile.elf, obj->efile.maps_shndx);
- if (scn)
- data = elf_getdata(scn, NULL);
- if (!scn || !data) {
- pr_warning("failed to get Elf_Data from map section %d\n",
- obj->efile.maps_shndx);
- return -EINVAL;
+ if (obj->efile.maps_shndx >= 0) {
+ Elf_Scn *scn = elf_getscn(obj->efile.elf,
+ obj->efile.maps_shndx);
+
+ if (scn)
+ data = elf_getdata(scn, NULL);
+ if (!scn || !data) {
+ pr_warning("failed to get Elf_Data from map section %d\n",
+ obj->efile.maps_shndx);
+ return -EINVAL;
+ }
}
/*
*
* TODO: Detect array of map and report error.
*/
- for (i = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) {
+ if (obj->efile.data_shndx >= 0)
+ nr_maps_glob++;
+ if (obj->efile.rodata_shndx >= 0)
+ nr_maps_glob++;
+ if (obj->efile.bss_shndx >= 0)
+ nr_maps_glob++;
+ for (i = 0; data && i < nr_syms; i++) {
GElf_Sym sym;
if (!gelf_getsym(symbols, i, &sym))
/* Alloc obj->maps and fill nr_maps. */
pr_debug("maps in %s: %d maps in %zd bytes\n", obj->path,
nr_maps, data->d_size);
-
- if (!nr_maps)
+ if (!nr_maps && !nr_maps_glob)
return 0;
/* Assume equally sized map definitions */
- map_def_sz = data->d_size / nr_maps;
- if (!data->d_size || (data->d_size % nr_maps) != 0) {
- pr_warning("unable to determine map definition size "
- "section %s, %d maps in %zd bytes\n",
- obj->path, nr_maps, data->d_size);
- return -EINVAL;
+ if (data) {
+ map_def_sz = data->d_size / nr_maps;
+ if (!data->d_size || (data->d_size % nr_maps) != 0) {
+ pr_warning("unable to determine map definition size "
+ "section %s, %d maps in %zd bytes\n",
+ obj->path, nr_maps, data->d_size);
+ return -EINVAL;
+ }
}
+ nr_maps += nr_maps_glob;
obj->maps = calloc(nr_maps, sizeof(obj->maps[0]));
if (!obj->maps) {
pr_warning("alloc maps for object failed\n");
/*
* Fill obj->maps using data in "maps" section.
*/
- for (i = 0, map_idx = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) {
+ for (i = 0, map_idx = 0; data && i < nr_syms; i++) {
GElf_Sym sym;
const char *map_name;
struct bpf_map_def *def;
map_name = elf_strptr(obj->efile.elf,
obj->efile.strtabidx,
sym.st_name);
+
+ obj->maps[map_idx].libbpf_type = LIBBPF_MAP_UNSPEC;
obj->maps[map_idx].offset = sym.st_value;
if (sym.st_value + map_def_sz > data->d_size) {
pr_warning("corrupted maps section in %s: last map \"%s\" too small\n",
map_idx++;
}
- qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]), compare_bpf_map);
- return 0;
+ /*
+ * Populate rest of obj->maps with libbpf internal maps.
+ */
+ if (obj->efile.data_shndx >= 0)
+ ret = bpf_object__init_internal_map(obj, &obj->maps[map_idx++],
+ LIBBPF_MAP_DATA,
+ obj->efile.data,
+ &obj->sections.data);
+ if (!ret && obj->efile.rodata_shndx >= 0)
+ ret = bpf_object__init_internal_map(obj, &obj->maps[map_idx++],
+ LIBBPF_MAP_RODATA,
+ obj->efile.rodata,
+ &obj->sections.rodata);
+ if (!ret && obj->efile.bss_shndx >= 0)
+ ret = bpf_object__init_internal_map(obj, &obj->maps[map_idx++],
+ LIBBPF_MAP_BSS,
+ obj->efile.bss, NULL);
+ if (!ret)
+ qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]),
+ compare_bpf_map);
+ return ret;
}
static bool section_have_execinstr(struct bpf_object *obj, int idx)
Elf *elf = obj->efile.elf;
GElf_Ehdr *ep = &obj->efile.ehdr;
Elf_Data *btf_ext_data = NULL;
+ Elf_Data *btf_data = NULL;
Elf_Scn *scn = NULL;
int idx = 0, err = 0;
(int)sh.sh_link, (unsigned long)sh.sh_flags,
(int)sh.sh_type);
- if (strcmp(name, "license") == 0)
+ if (strcmp(name, "license") == 0) {
err = bpf_object__init_license(obj,
data->d_buf,
data->d_size);
- else if (strcmp(name, "version") == 0)
+ } else if (strcmp(name, "version") == 0) {
err = bpf_object__init_kversion(obj,
data->d_buf,
data->d_size);
- else if (strcmp(name, "maps") == 0)
+ } else if (strcmp(name, "maps") == 0) {
obj->efile.maps_shndx = idx;
- else if (strcmp(name, BTF_ELF_SEC) == 0) {
- obj->btf = btf__new(data->d_buf, data->d_size);
- if (IS_ERR(obj->btf)) {
- pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n",
- BTF_ELF_SEC, PTR_ERR(obj->btf));
- obj->btf = NULL;
- continue;
- }
- err = btf__load(obj->btf);
- if (err) {
- pr_warning("Error loading %s into kernel: %d. Ignored and continue.\n",
- BTF_ELF_SEC, err);
- btf__free(obj->btf);
- obj->btf = NULL;
- err = 0;
- }
+ } else if (strcmp(name, BTF_ELF_SEC) == 0) {
+ btf_data = data;
} else if (strcmp(name, BTF_EXT_ELF_SEC) == 0) {
btf_ext_data = data;
} else if (sh.sh_type == SHT_SYMTAB) {
obj->efile.symbols = data;
obj->efile.strtabidx = sh.sh_link;
}
- } else if ((sh.sh_type == SHT_PROGBITS) &&
- (sh.sh_flags & SHF_EXECINSTR) &&
- (data->d_size > 0)) {
- if (strcmp(name, ".text") == 0)
- obj->efile.text_shndx = idx;
- err = bpf_object__add_program(obj, data->d_buf,
- data->d_size, name, idx);
- if (err) {
- char errmsg[STRERR_BUFSIZE];
- char *cp = libbpf_strerror_r(-err, errmsg,
- sizeof(errmsg));
-
- pr_warning("failed to alloc program %s (%s): %s",
- name, obj->path, cp);
+ } else if (sh.sh_type == SHT_PROGBITS && data->d_size > 0) {
+ if (sh.sh_flags & SHF_EXECINSTR) {
+ if (strcmp(name, ".text") == 0)
+ obj->efile.text_shndx = idx;
+ err = bpf_object__add_program(obj, data->d_buf,
+ data->d_size, name, idx);
+ if (err) {
+ char errmsg[STRERR_BUFSIZE];
+ char *cp = libbpf_strerror_r(-err, errmsg,
+ sizeof(errmsg));
+
+ pr_warning("failed to alloc program %s (%s): %s",
+ name, obj->path, cp);
+ }
+ } else if (strcmp(name, ".data") == 0) {
+ obj->efile.data = data;
+ obj->efile.data_shndx = idx;
+ } else if (strcmp(name, ".rodata") == 0) {
+ obj->efile.rodata = data;
+ obj->efile.rodata_shndx = idx;
+ } else {
+ pr_debug("skip section(%d) %s\n", idx, name);
}
} else if (sh.sh_type == SHT_REL) {
void *reloc = obj->efile.reloc;
obj->efile.reloc[n].shdr = sh;
obj->efile.reloc[n].data = data;
}
+ } else if (sh.sh_type == SHT_NOBITS && strcmp(name, ".bss") == 0) {
+ obj->efile.bss = data;
+ obj->efile.bss_shndx = idx;
} else {
pr_debug("skip section(%d) %s\n", idx, name);
}
pr_warning("Corrupted ELF file: index of strtab invalid\n");
return LIBBPF_ERRNO__FORMAT;
}
+ if (btf_data) {
+ obj->btf = btf__new(btf_data->d_buf, btf_data->d_size);
+ if (IS_ERR(obj->btf)) {
+ pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n",
+ BTF_ELF_SEC, PTR_ERR(obj->btf));
+ obj->btf = NULL;
+ } else {
+ err = btf__finalize_data(obj, obj->btf);
+ if (!err)
+ err = btf__load(obj->btf);
+ if (err) {
+ pr_warning("Error finalizing and loading %s into kernel: %d. Ignored and continue.\n",
+ BTF_ELF_SEC, err);
+ btf__free(obj->btf);
+ obj->btf = NULL;
+ err = 0;
+ }
+ }
+ }
if (btf_ext_data) {
if (!obj->btf) {
pr_debug("Ignore ELF section %s because its depending ELF section %s is not found.\n",
}
}
}
- if (obj->efile.maps_shndx >= 0) {
+ if (bpf_object__has_maps(obj)) {
err = bpf_object__init_maps(obj, flags);
if (err)
goto out;
return NULL;
}
+static bool bpf_object__shndx_is_data(const struct bpf_object *obj,
+ int shndx)
+{
+ return shndx == obj->efile.data_shndx ||
+ shndx == obj->efile.bss_shndx ||
+ shndx == obj->efile.rodata_shndx;
+}
+
+static bool bpf_object__shndx_is_maps(const struct bpf_object *obj,
+ int shndx)
+{
+ return shndx == obj->efile.maps_shndx;
+}
+
+static bool bpf_object__relo_in_known_section(const struct bpf_object *obj,
+ int shndx)
+{
+ return shndx == obj->efile.text_shndx ||
+ bpf_object__shndx_is_maps(obj, shndx) ||
+ bpf_object__shndx_is_data(obj, shndx);
+}
+
+static enum libbpf_map_type
+bpf_object__section_to_libbpf_map_type(const struct bpf_object *obj, int shndx)
+{
+ if (shndx == obj->efile.data_shndx)
+ return LIBBPF_MAP_DATA;
+ else if (shndx == obj->efile.bss_shndx)
+ return LIBBPF_MAP_BSS;
+ else if (shndx == obj->efile.rodata_shndx)
+ return LIBBPF_MAP_RODATA;
+ else
+ return LIBBPF_MAP_UNSPEC;
+}
+
static int
bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
Elf_Data *data, struct bpf_object *obj)
{
Elf_Data *symbols = obj->efile.symbols;
- int text_shndx = obj->efile.text_shndx;
- int maps_shndx = obj->efile.maps_shndx;
struct bpf_map *maps = obj->maps;
size_t nr_maps = obj->nr_maps;
int i, nrels;
GElf_Sym sym;
GElf_Rel rel;
unsigned int insn_idx;
+ unsigned int shdr_idx;
struct bpf_insn *insns = prog->insns;
+ enum libbpf_map_type type;
+ const char *name;
size_t map_idx;
if (!gelf_getrel(data, i, &rel)) {
GELF_R_SYM(rel.r_info));
return -LIBBPF_ERRNO__FORMAT;
}
- pr_debug("relo for %lld value %lld name %d\n",
+
+ name = elf_strptr(obj->efile.elf, obj->efile.strtabidx,
+ sym.st_name) ? : "<?>";
+
+ pr_debug("relo for %lld value %lld name %d (\'%s\')\n",
(long long) (rel.r_info >> 32),
- (long long) sym.st_value, sym.st_name);
+ (long long) sym.st_value, sym.st_name, name);
- if (sym.st_shndx != maps_shndx && sym.st_shndx != text_shndx) {
- pr_warning("Program '%s' contains non-map related relo data pointing to section %u\n",
- prog->section_name, sym.st_shndx);
+ shdr_idx = sym.st_shndx;
+ if (!bpf_object__relo_in_known_section(obj, shdr_idx)) {
+ pr_warning("Program '%s' contains unrecognized relo data pointing to section %u\n",
+ prog->section_name, shdr_idx);
return -LIBBPF_ERRNO__RELOC;
}
return -LIBBPF_ERRNO__RELOC;
}
- /* TODO: 'maps' is sorted. We can use bsearch to make it faster. */
- for (map_idx = 0; map_idx < nr_maps; map_idx++) {
- if (maps[map_idx].offset == sym.st_value) {
- pr_debug("relocation: find map %zd (%s) for insn %u\n",
- map_idx, maps[map_idx].name, insn_idx);
- break;
+ if (bpf_object__shndx_is_maps(obj, shdr_idx) ||
+ bpf_object__shndx_is_data(obj, shdr_idx)) {
+ type = bpf_object__section_to_libbpf_map_type(obj, shdr_idx);
+ if (type != LIBBPF_MAP_UNSPEC &&
+ GELF_ST_BIND(sym.st_info) == STB_GLOBAL) {
+ pr_warning("bpf: relocation: not yet supported relo for non-static global \'%s\' variable found in insns[%d].code 0x%x\n",
+ name, insn_idx, insns[insn_idx].code);
+ return -LIBBPF_ERRNO__RELOC;
}
- }
- if (map_idx >= nr_maps) {
- pr_warning("bpf relocation: map_idx %d large than %d\n",
- (int)map_idx, (int)nr_maps - 1);
- return -LIBBPF_ERRNO__RELOC;
- }
+ for (map_idx = 0; map_idx < nr_maps; map_idx++) {
+ if (maps[map_idx].libbpf_type != type)
+ continue;
+ if (type != LIBBPF_MAP_UNSPEC ||
+ (type == LIBBPF_MAP_UNSPEC &&
+ maps[map_idx].offset == sym.st_value)) {
+ pr_debug("relocation: find map %zd (%s) for insn %u\n",
+ map_idx, maps[map_idx].name, insn_idx);
+ break;
+ }
+ }
+
+ if (map_idx >= nr_maps) {
+ pr_warning("bpf relocation: map_idx %d large than %d\n",
+ (int)map_idx, (int)nr_maps - 1);
+ return -LIBBPF_ERRNO__RELOC;
+ }
- prog->reloc_desc[i].type = RELO_LD64;
- prog->reloc_desc[i].insn_idx = insn_idx;
- prog->reloc_desc[i].map_idx = map_idx;
+ prog->reloc_desc[i].type = type != LIBBPF_MAP_UNSPEC ?
+ RELO_DATA : RELO_LD64;
+ prog->reloc_desc[i].insn_idx = insn_idx;
+ prog->reloc_desc[i].map_idx = map_idx;
+ }
}
return 0;
}
static int bpf_map_find_btf_info(struct bpf_map *map, const struct btf *btf)
{
struct bpf_map_def *def = &map->def;
- __u32 key_type_id, value_type_id;
+ __u32 key_type_id = 0, value_type_id = 0;
int ret;
- ret = btf__get_map_kv_tids(btf, map->name, def->key_size,
- def->value_size, &key_type_id,
- &value_type_id);
- if (ret)
+ if (!bpf_map__is_internal(map)) {
+ ret = btf__get_map_kv_tids(btf, map->name, def->key_size,
+ def->value_size, &key_type_id,
+ &value_type_id);
+ } else {
+ /*
+ * LLVM annotates global data differently in BTF, that is,
+ * only as '.data', '.bss' or '.rodata'.
+ */
+ ret = btf__find_by_name(btf,
+ libbpf_type_to_btf_name[map->libbpf_type]);
+ }
+ if (ret < 0)
return ret;
map->btf_key_type_id = key_type_id;
- map->btf_value_type_id = value_type_id;
-
+ map->btf_value_type_id = bpf_map__is_internal(map) ?
+ ret : value_type_id;
return 0;
}
return bpf_object__probe_name(obj);
}
+static int
+bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map)
+{
+ char *cp, errmsg[STRERR_BUFSIZE];
+ int err, zero = 0;
+ __u8 *data;
+
+ /* Nothing to do here since kernel already zero-initializes .bss map. */
+ if (map->libbpf_type == LIBBPF_MAP_BSS)
+ return 0;
+
+ data = map->libbpf_type == LIBBPF_MAP_DATA ?
+ obj->sections.data : obj->sections.rodata;
+
+ err = bpf_map_update_elem(map->fd, &zero, data, 0);
+ /* Freeze .rodata map as read-only from syscall side. */
+ if (!err && map->libbpf_type == LIBBPF_MAP_RODATA) {
+ err = bpf_map_freeze(map->fd);
+ if (err) {
+ cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
+ pr_warning("Error freezing map(%s) as read-only: %s\n",
+ map->name, cp);
+ err = 0;
+ }
+ }
+ return err;
+}
+
static int
bpf_object__create_maps(struct bpf_object *obj)
{
size_t j;
err = *pfd;
+err_out:
cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
pr_warning("failed to create map (name: '%s'): %s\n",
map->name, cp);
zclose(obj->maps[j].fd);
return err;
}
+
+ if (bpf_map__is_internal(map)) {
+ err = bpf_object__populate_internal_map(obj, map);
+ if (err < 0) {
+ zclose(*pfd);
+ goto err_out;
+ }
+ }
+
pr_debug("create map %s: fd=%d\n", map->name, *pfd);
}
return 0;
for (i = 0; i < prog->nr_reloc; i++) {
- if (prog->reloc_desc[i].type == RELO_LD64) {
+ if (prog->reloc_desc[i].type == RELO_LD64 ||
+ prog->reloc_desc[i].type == RELO_DATA) {
+ bool relo_data = prog->reloc_desc[i].type == RELO_DATA;
struct bpf_insn *insns = prog->insns;
int insn_idx, map_idx;
insn_idx = prog->reloc_desc[i].insn_idx;
map_idx = prog->reloc_desc[i].map_idx;
- if (insn_idx >= (int)prog->insns_cnt) {
+ if (insn_idx + 1 >= (int)prog->insns_cnt) {
pr_warning("relocation out of range: '%s'\n",
prog->section_name);
return -LIBBPF_ERRNO__RELOC;
}
- insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD;
+
+ if (!relo_data) {
+ insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD;
+ } else {
+ insns[insn_idx].src_reg = BPF_PSEUDO_MAP_VALUE;
+ insns[insn_idx + 1].imm = insns[insn_idx].imm;
+ }
insns[insn_idx].imm = obj->maps[map_idx].fd;
- } else {
+ } else if (prog->reloc_desc[i].type == RELO_CALL) {
err = bpf_program__reloc_text(prog, obj,
&prog->reloc_desc[i]);
if (err)
{
struct bpf_load_program_attr load_attr;
char *cp, errmsg[STRERR_BUFSIZE];
+ int log_buf_size = BPF_LOG_BUF_SIZE;
char *log_buf;
int ret;
load_attr.line_info = prog->line_info;
load_attr.line_info_rec_size = prog->line_info_rec_size;
load_attr.line_info_cnt = prog->line_info_cnt;
+ load_attr.log_level = prog->log_level;
if (!load_attr.insns || !load_attr.insns_cnt)
return -EINVAL;
- log_buf = malloc(BPF_LOG_BUF_SIZE);
+retry_load:
+ log_buf = malloc(log_buf_size);
if (!log_buf)
pr_warning("Alloc log buffer for bpf loader error, continue without log\n");
- ret = bpf_load_program_xattr(&load_attr, log_buf, BPF_LOG_BUF_SIZE);
+ ret = bpf_load_program_xattr(&load_attr, log_buf, log_buf_size);
if (ret >= 0) {
+ if (load_attr.log_level)
+ pr_debug("verifier log:\n%s", log_buf);
*pfd = ret;
ret = 0;
goto out;
}
+ if (errno == ENOSPC) {
+ log_buf_size <<= 1;
+ free(log_buf);
+ goto retry_load;
+ }
ret = -LIBBPF_ERRNO__LOAD;
cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
pr_warning("load bpf program failed: %s\n", cp);
obj->maps[i].priv = NULL;
obj->maps[i].clear_priv = NULL;
}
+
+ zfree(&obj->sections.rodata);
+ zfree(&obj->sections.data);
zfree(&obj->maps);
obj->nr_maps = 0;
return map->def.type == BPF_MAP_TYPE_PERF_EVENT_ARRAY;
}
+bool bpf_map__is_internal(struct bpf_map *map)
+{
+ return map->libbpf_type != LIBBPF_MAP_UNSPEC;
+}
+
void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex)
{
map->map_ifindex = ifindex;
bpf_program__set_expected_attach_type(prog,
expected_attach_type);
+ prog->log_level = attr->log_level;
if (!first_prog)
first_prog = prog;
}
LIBBPF_API struct bpf_object *bpf_object__open_buffer(void *obj_buf,
size_t obj_buf_sz,
const char *name);
+int bpf_object__section_size(const struct bpf_object *obj, const char *name,
+ __u32 *size);
+int bpf_object__variable_offset(const struct bpf_object *obj, const char *name,
+ __u32 *off);
LIBBPF_API int bpf_object__pin_maps(struct bpf_object *obj, const char *path);
LIBBPF_API int bpf_object__unpin_maps(struct bpf_object *obj,
const char *path);
LIBBPF_API int bpf_map__reuse_fd(struct bpf_map *map, int fd);
LIBBPF_API int bpf_map__resize(struct bpf_map *map, __u32 max_entries);
LIBBPF_API bool bpf_map__is_offload_neutral(struct bpf_map *map);
+LIBBPF_API bool bpf_map__is_internal(struct bpf_map *map);
LIBBPF_API void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex);
LIBBPF_API int bpf_map__pin(struct bpf_map *map, const char *path);
LIBBPF_API int bpf_map__unpin(struct bpf_map *map, const char *path);
enum bpf_prog_type prog_type;
enum bpf_attach_type expected_attach_type;
int ifindex;
+ int log_level;
};
LIBBPF_API int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
bpf_program__bpil_addr_to_offs;
bpf_program__bpil_offs_to_addr;
} LIBBPF_0.0.1;
+
+LIBBPF_0.0.3 {
+ global:
+ bpf_map__is_internal;
+ bpf_map_freeze;
+ btf__finalize_data;
+} LIBBPF_0.0.2;
--- /dev/null
+# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+prefix=@PREFIX@
+libdir=@LIBDIR@
+includedir=${prefix}/include
+
+Name: libbpf
+Description: BPF library
+Version: @VERSION@
+Libs: -L${libdir} -lbpf
+Requires.private: libelf
+Cflags: -I${includedir}
static int xsk_load_xdp_prog(struct xsk_socket *xsk)
{
- char bpf_log_buf[BPF_LOG_BUF_SIZE];
+ static const int log_buf_size = 16 * 1024;
+ char log_buf[log_buf_size];
int err, prog_fd;
/* This is the C-program:
size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn);
prog_fd = bpf_load_program(BPF_PROG_TYPE_XDP, prog, insns_cnt,
- "LGPL-2.1 or BSD-2-Clause", 0, bpf_log_buf,
- BPF_LOG_BUF_SIZE);
+ "LGPL-2.1 or BSD-2-Clause", 0, log_buf,
+ log_buf_size);
if (prog_fd < 0) {
- pr_warning("BPF log buffer:\n%s", bpf_log_buf);
+ pr_warning("BPF log buffer:\n%s", log_buf);
return prog_fd;
}
OBJTOOL := $(OUTPUT)objtool
OBJTOOL_IN := $(OBJTOOL)-in.o
+LIBELF_FLAGS := $(shell pkg-config libelf --cflags 2>/dev/null)
+LIBELF_LIBS := $(shell pkg-config libelf --libs 2>/dev/null || echo -lelf)
+
all: $(OBJTOOL)
INCLUDES := -I$(srctree)/tools/include \
-I$(srctree)/tools/arch/$(HOSTARCH)/include/uapi \
-I$(srctree)/tools/objtool/arch/$(ARCH)/include
WARNINGS := $(EXTRA_WARNINGS) -Wno-switch-default -Wno-switch-enum -Wno-packed
-CFLAGS += -Werror $(WARNINGS) $(KBUILD_HOSTCFLAGS) -g $(INCLUDES)
-LDFLAGS += -lelf $(LIBSUBCMD) $(KBUILD_HOSTLDFLAGS)
+CFLAGS += -Werror $(WARNINGS) $(KBUILD_HOSTCFLAGS) -g $(INCLUDES) $(LIBELF_FLAGS)
+LDFLAGS += $(LIBELF_LIBS) $(LIBSUBCMD) $(KBUILD_HOSTLDFLAGS)
# Allow old libelf to be used:
elfshdr := $(shell echo '$(pound)include <libelf.h>' | $(CC) $(CFLAGS) -x c -E - | grep elf_getshdr)
"fortify_panic",
"usercopy_abort",
"machine_real_restart",
+ "rewind_stack_do_exit",
};
if (func->bind == STB_WEAK)
mmap_flags_array := $(beauty_outdir)/mmap_flags_array.c
mmap_flags_tbl := $(srctree)/tools/perf/trace/beauty/mmap_flags.sh
-$(mmap_flags_array): $(asm_generic_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman-common.h $(mmap_flags_tbl)
- $(Q)$(SHELL) '$(mmap_flags_tbl)' $(asm_generic_uapi_dir) $(arch_asm_uapi_dir) > $@
+$(mmap_flags_array): $(linux_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman-common.h $(mmap_flags_tbl)
+ $(Q)$(SHELL) '$(mmap_flags_tbl)' $(linux_uapi_dir) $(asm_generic_uapi_dir) $(arch_asm_uapi_dir) > $@
mount_flags_array := $(beauty_outdir)/mount_flags_array.c
mount_flags_tbl := $(srctree)/tools/perf/trace/beauty/mount_flags.sh
334 common rseq __x64_sys_rseq
# don't use numbers 387 through 423, add new calls after the last
# 'common' entry
+424 common pidfd_send_signal __x64_sys_pidfd_send_signal
+425 common io_uring_setup __x64_sys_io_uring_setup
+426 common io_uring_enter __x64_sys_io_uring_enter
+427 common io_uring_register __x64_sys_io_uring_register
#
# x32-specific system call numbers start at 512 to avoid cache impact
# diff with extra ignore lines
check arch/x86/lib/memcpy_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"'
check arch/x86/lib/memset_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"'
-check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common.h>"'
+check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common\(-tools\)*.h>"'
check include/uapi/linux/mman.h '-I "^#include <\(uapi/\)*asm/mman.h>"'
# diff non-symmetric files
from PySide.QtCore import *
from PySide.QtGui import *
from PySide.QtSql import *
+pyside_version_1 = True
from decimal import *
from ctypes import *
from multiprocessing import Process, Array, Value, Event
" (" + dsoname(query.value(15)) + ")")
return data
+def BranchDataPrepWA(query):
+ data = []
+ data.append(query.value(0))
+ # Workaround pyside failing to handle large integers (i.e. time) in python3 by converting to a string
+ data.append("{:>19}".format(query.value(1)))
+ for i in xrange(2, 8):
+ data.append(query.value(i))
+ data.append(tohex(query.value(8)).rjust(16) + " " + query.value(9) + offstr(query.value(10)) +
+ " (" + dsoname(query.value(11)) + ")" + " -> " +
+ tohex(query.value(12)) + " " + query.value(13) + offstr(query.value(14)) +
+ " (" + dsoname(query.value(15)) + ")")
+ return data
+
# Branch data model
class BranchModel(TreeModel):
" AND evsel_id = " + str(self.event_id) +
" ORDER BY samples.id"
" LIMIT " + str(glb_chunk_sz))
- self.fetcher = SQLFetcher(glb, sql, BranchDataPrep, self.AddSample)
+ if pyside_version_1 and sys.version_info[0] == 3:
+ prep = BranchDataPrepWA
+ else:
+ prep = BranchDataPrep
+ self.fetcher = SQLFetcher(glb, sql, prep, self.AddSample)
self.fetcher.done.connect(self.Update)
self.fetcher.Fetch(glb_chunk_sz)
return False
return True
-# SQL data preparation
-
-def SQLTableDataPrep(query, count):
- data = []
- for i in xrange(count):
- data.append(query.value(i))
- return data
-
# SQL table data model item
class SQLTableItem():
self.more = True
self.populated = 0
self.column_headers = column_headers
- self.fetcher = SQLFetcher(glb, sql, lambda x, y=len(column_headers): SQLTableDataPrep(x, y), self.AddSample)
+ self.fetcher = SQLFetcher(glb, sql, lambda x, y=len(column_headers): self.SQLTableDataPrep(x, y), self.AddSample)
self.fetcher.done.connect(self.Update)
self.fetcher.Fetch(glb_chunk_sz)
def columnHeader(self, column):
return self.column_headers[column]
+ def SQLTableDataPrep(self, query, count):
+ data = []
+ for i in xrange(count):
+ data.append(query.value(i))
+ return data
+
# SQL automatic table data model
class SQLAutoTableModel(SQLTableModel):
QueryExec(query, "SELECT column_name FROM information_schema.columns WHERE table_schema = '" + schema + "' and table_name = '" + select_table_name + "'")
while query.next():
column_headers.append(query.value(0))
+ if pyside_version_1 and sys.version_info[0] == 3:
+ if table_name == "samples_view":
+ self.SQLTableDataPrep = self.samples_view_DataPrep
+ if table_name == "samples":
+ self.SQLTableDataPrep = self.samples_DataPrep
super(SQLAutoTableModel, self).__init__(glb, sql, column_headers, parent)
+ def samples_view_DataPrep(self, query, count):
+ data = []
+ data.append(query.value(0))
+ # Workaround pyside failing to handle large integers (i.e. time) in python3 by converting to a string
+ data.append("{:>19}".format(query.value(1)))
+ for i in xrange(2, count):
+ data.append(query.value(i))
+ return data
+
+ def samples_DataPrep(self, query, count):
+ data = []
+ for i in xrange(9):
+ data.append(query.value(i))
+ # Workaround pyside failing to handle large integers (i.e. time) in python3 by converting to a string
+ data.append("{:>19}".format(query.value(9)))
+ for i in xrange(10, count):
+ data.append(query.value(i))
+ return data
+
# Base class for custom ResizeColumnsToContents
class ResizeColumnsToContentsBase(QObject):
ok = self.xed_format_context(2, inst.xedp, inst.bufferp, sizeof(inst.buffer), ip, 0, 0)
if not ok:
return 0, ""
+ if sys.version_info[0] == 2:
+ result = inst.buffer.value
+ else:
+ result = inst.buffer.value.decode()
# Return instruction length and the disassembled instruction text
# For now, assume the length is in byte 166
- return inst.xedd[166], inst.buffer.value
+ return inst.xedd[166], result
def TryOpen(file_name):
try:
header = f.read(7)
f.seek(pos)
magic = header[0:4]
- eclass = ord(header[4])
- encoding = ord(header[5])
- version = ord(header[6])
+ if sys.version_info[0] == 2:
+ eclass = ord(header[4])
+ encoding = ord(header[5])
+ version = ord(header[6])
+ else:
+ eclass = header[4]
+ encoding = header[5]
+ version = header[6]
if magic == chr(127) + "ELF" and eclass > 0 and eclass < 3 and encoding > 0 and encoding < 3 and version == 1:
result = True if eclass == 2 else False
return result
#!/bin/sh
# SPDX-License-Identifier: LGPL-2.1
-if [ $# -ne 2 ] ; then
+if [ $# -ne 3 ] ; then
[ $# -eq 1 ] && hostarch=$1 || hostarch=`uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/`
+ linux_header_dir=tools/include/uapi/linux
header_dir=tools/include/uapi/asm-generic
arch_header_dir=tools/arch/${hostarch}/include/uapi/asm
else
- header_dir=$1
- arch_header_dir=$2
+ linux_header_dir=$1
+ header_dir=$2
+ arch_header_dir=$3
fi
+linux_mman=${linux_header_dir}/mman.h
arch_mman=${arch_header_dir}/mman.h
# those in egrep -vw are flags, we want just the bits
(egrep $regex ${arch_mman} | \
sed -r "s/$regex/\2 \1/g" | \
xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n")
+egrep -q $regex ${linux_mman} && \
+(egrep $regex ${linux_mman} | \
+ egrep -vw 'MAP_(UNINITIALIZED|TYPE|SHARED_VALIDATE)' | \
+ sed -r "s/$regex/\2 \1/g" | \
+ xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n")
([ ! -f ${arch_mman} ] || egrep -q '#[[:space:]]*include[[:space:]]+<uapi/asm-generic/mman.*' ${arch_mman}) &&
(egrep $regex ${header_dir}/mman-common.h | \
egrep -vw 'MAP_(UNINITIALIZED|TYPE|SHARED_VALIDATE)' | \
break;
case OCSD_INSTR_ISB:
case OCSD_INSTR_DSB_DMB:
+ case OCSD_INSTR_WFI_WFE:
case OCSD_INSTR_OTHER:
default:
packet->last_instr_taken_branch = false;
}
}
-void perf_event_attr__set_max_precise_ip(struct perf_event_attr *pattr)
-{
- struct perf_event_attr attr = {
- .type = PERF_TYPE_HARDWARE,
- .config = PERF_COUNT_HW_CPU_CYCLES,
- .exclude_kernel = 1,
- .precise_ip = 3,
- };
-
- event_attr_init(&attr);
-
- /*
- * Unnamed union member, not supported as struct member named
- * initializer in older compilers such as gcc 4.4.7
- */
- attr.sample_period = 1;
-
- while (attr.precise_ip != 0) {
- int fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
- if (fd != -1) {
- close(fd);
- break;
- }
- --attr.precise_ip;
- }
-
- pattr->precise_ip = attr.precise_ip;
-}
-
int __perf_evlist__add_default(struct perf_evlist *evlist, bool precise)
{
struct perf_evsel *evsel = perf_evsel__new_cycles(precise);
void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
struct perf_evsel *tracking_evsel);
-void perf_event_attr__set_max_precise_ip(struct perf_event_attr *attr);
-
struct perf_evsel *
perf_evlist__find_evsel_by_str(struct perf_evlist *evlist, const char *str);
if (!precise)
goto new_event;
- perf_event_attr__set_max_precise_ip(&attr);
/*
* Now let the usual logic to set up the perf_event_attr defaults
* to kick in when we return and before perf_evsel__open() is called.
if (evsel == NULL)
goto out;
+ evsel->precise_max = true;
+
/* use asprintf() because free(evsel) assumes name is allocated */
if (asprintf(&evsel->name, "cycles%s%s%.*s",
(attr.precise_ip || attr.exclude_kernel) ? ":" : "",
}
if (evsel->precise_max)
- perf_event_attr__set_max_precise_ip(attr);
+ attr->precise_ip = 3;
if (opts->all_user) {
attr->exclude_kernel = 1;
return true;
}
+static void display_attr(struct perf_event_attr *attr)
+{
+ if (verbose >= 2) {
+ fprintf(stderr, "%.60s\n", graph_dotted_line);
+ fprintf(stderr, "perf_event_attr:\n");
+ perf_event_attr__fprintf(stderr, attr, __open_attr__fprintf, NULL);
+ fprintf(stderr, "%.60s\n", graph_dotted_line);
+ }
+}
+
+static int perf_event_open(struct perf_evsel *evsel,
+ pid_t pid, int cpu, int group_fd,
+ unsigned long flags)
+{
+ int precise_ip = evsel->attr.precise_ip;
+ int fd;
+
+ while (1) {
+ pr_debug2("sys_perf_event_open: pid %d cpu %d group_fd %d flags %#lx",
+ pid, cpu, group_fd, flags);
+
+ fd = sys_perf_event_open(&evsel->attr, pid, cpu, group_fd, flags);
+ if (fd >= 0)
+ break;
+
+ /*
+ * Do quick precise_ip fallback if:
+ * - there is precise_ip set in perf_event_attr
+ * - maximum precise is requested
+ * - sys_perf_event_open failed with ENOTSUP error,
+ * which is associated with wrong precise_ip
+ */
+ if (!precise_ip || !evsel->precise_max || (errno != ENOTSUP))
+ break;
+
+ /*
+ * We tried all the precise_ip values, and it's
+ * still failing, so leave it to standard fallback.
+ */
+ if (!evsel->attr.precise_ip) {
+ evsel->attr.precise_ip = precise_ip;
+ break;
+ }
+
+ pr_debug2("\nsys_perf_event_open failed, error %d\n", -ENOTSUP);
+ evsel->attr.precise_ip--;
+ pr_debug2("decreasing precise_ip by one (%d)\n", evsel->attr.precise_ip);
+ display_attr(&evsel->attr);
+ }
+
+ return fd;
+}
+
int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
struct thread_map *threads)
{
if (perf_missing_features.sample_id_all)
evsel->attr.sample_id_all = 0;
- if (verbose >= 2) {
- fprintf(stderr, "%.60s\n", graph_dotted_line);
- fprintf(stderr, "perf_event_attr:\n");
- perf_event_attr__fprintf(stderr, &evsel->attr, __open_attr__fprintf, NULL);
- fprintf(stderr, "%.60s\n", graph_dotted_line);
- }
+ display_attr(&evsel->attr);
for (cpu = 0; cpu < cpus->nr; cpu++) {
group_fd = get_group_fd(evsel, cpu, thread);
retry_open:
- pr_debug2("sys_perf_event_open: pid %d cpu %d group_fd %d flags %#lx",
- pid, cpus->map[cpu], group_fd, flags);
-
test_attr__ready();
- fd = sys_perf_event_open(&evsel->attr, pid, cpus->map[cpu],
- group_fd, flags);
+ fd = perf_event_open(evsel, pid, cpus->map[cpu],
+ group_fd, flags);
FD(evsel, cpu, thread) = fd;
if (!(decoder->tsc_ctc_ratio_n % decoder->tsc_ctc_ratio_d))
decoder->tsc_ctc_mult = decoder->tsc_ctc_ratio_n /
decoder->tsc_ctc_ratio_d;
-
- /*
- * Allow for timestamps appearing to backwards because a TSC
- * packet has slipped past a MTC packet, so allow 2 MTC ticks
- * or ...
- */
- decoder->tsc_slip = multdiv(2 << decoder->mtc_shift,
- decoder->tsc_ctc_ratio_n,
- decoder->tsc_ctc_ratio_d);
}
- /* ... or 0x100 paranoia */
- if (decoder->tsc_slip < 0x100)
- decoder->tsc_slip = 0x100;
+
+ /*
+ * A TSC packet can slip past MTC packets so that the timestamp appears
+ * to go backwards. One estimate is that can be up to about 40 CPU
+ * cycles, which is certainly less than 0x1000 TSC ticks, but accept
+ * slippage an order of magnitude more to be on the safe side.
+ */
+ decoder->tsc_slip = 0x10000;
intel_pt_log("timestamp: mtc_shift %u\n", decoder->mtc_shift);
intel_pt_log("timestamp: tsc_ctc_ratio_n %u\n", decoder->tsc_ctc_ratio_n);
machine->vmlinux_map->end = ~0ULL;
}
+static void machine__update_kernel_mmap(struct machine *machine,
+ u64 start, u64 end)
+{
+ struct map *map = machine__kernel_map(machine);
+
+ map__get(map);
+ map_groups__remove(&machine->kmaps, map);
+
+ machine__set_kernel_mmap(machine, start, end);
+
+ map_groups__insert(&machine->kmaps, map);
+ map__put(map);
+}
+
int machine__create_kernel_maps(struct machine *machine)
{
struct dso *kernel = machine__get_kernel(machine);
goto out_put;
}
- /* we have a real start address now, so re-order the kmaps */
- map = machine__kernel_map(machine);
-
- map__get(map);
- map_groups__remove(&machine->kmaps, map);
-
- /* assume it's the last in the kmaps */
- machine__set_kernel_mmap(machine, addr, ~0ULL);
-
- map_groups__insert(&machine->kmaps, map);
- map__put(map);
+ /*
+ * we have a real start address now, so re-order the kmaps
+ * assume it's the last in the kmaps
+ */
+ machine__update_kernel_mmap(machine, addr, ~0ULL);
}
if (machine__create_extra_kernel_maps(machine, kernel))
if (strstr(kernel->long_name, "vmlinux"))
dso__set_short_name(kernel, "[kernel.vmlinux]", false);
- machine__set_kernel_mmap(machine, event->mmap.start,
+ machine__update_kernel_mmap(machine, event->mmap.start,
event->mmap.start + event->mmap.len);
/*
if (!is_arm_pmu_core(name)) {
pname = pe->pmu ? pe->pmu : "cpu";
+
+ /*
+ * uncore alias may be from different PMU
+ * with common prefix
+ */
+ if (pmu_is_uncore(name) &&
+ !strncmp(pname, name, strlen(pname)))
+ goto new_alias;
+
if (strcmp(pname, name))
continue;
}
+new_alias:
/* need type casts to override 'const' */
__perf_pmu__new_alias(head, NULL, (char *)pe->name,
(char *)pe->desc, (char *)pe->event,
#include <cpuid.h>
#include <linux/capability.h>
#include <errno.h>
+#include <math.h>
char *proc_stat = "/proc/stat";
FILE *outf;
unsigned int do_snb_cstates;
unsigned int do_knl_cstates;
unsigned int do_slm_cstates;
-unsigned int do_cnl_cstates;
unsigned int use_c1_residency_msr;
unsigned int has_aperf;
unsigned int has_epb;
#define RAPL_CORES_ENERGY_STATUS (1 << 9)
/* 0x639 MSR_PP0_ENERGY_STATUS */
+#define RAPL_PER_CORE_ENERGY (1 << 10)
+ /* Indicates cores energy collection is per-core,
+ * not per-package. */
+#define RAPL_AMD_F17H (1 << 11)
+ /* 0xc0010299 MSR_RAPL_PWR_UNIT */
+ /* 0xc001029a MSR_CORE_ENERGY_STAT */
+ /* 0xc001029b MSR_PKG_ENERGY_STAT */
#define RAPL_CORES (RAPL_CORES_ENERGY_STATUS | RAPL_CORES_POWER_LIMIT)
#define TJMAX_DEFAULT 100
+/* MSRs that are not yet in the kernel-provided header. */
+#define MSR_RAPL_PWR_UNIT 0xc0010299
+#define MSR_CORE_ENERGY_STAT 0xc001029a
+#define MSR_PKG_ENERGY_STAT 0xc001029b
+
#define MAX(a, b) ((a) > (b) ? (a) : (b))
/*
unsigned long long c7;
unsigned long long mc6_us; /* duplicate as per-core for now, even though per module */
unsigned int core_temp_c;
+ unsigned int core_energy; /* MSR_CORE_ENERGY_STAT */
unsigned int core_id;
unsigned long long counter[MAX_ADDED_COUNTERS];
} *core_even, *core_odd;
struct cpu_topology {
int physical_package_id;
+ int die_id;
int logical_cpu_id;
int physical_node_id;
int logical_node_id; /* 0-based count within the package */
struct topo_params {
int num_packages;
+ int num_die;
int num_cpus;
int num_cores;
int max_cpu_num;
int retval, pkg_no, core_no, thread_no, node_no;
for (pkg_no = 0; pkg_no < topo.num_packages; ++pkg_no) {
- for (core_no = 0; core_no < topo.cores_per_node; ++core_no) {
- for (node_no = 0; node_no < topo.nodes_per_pkg;
- node_no++) {
+ for (node_no = 0; node_no < topo.nodes_per_pkg; node_no++) {
+ for (core_no = 0; core_no < topo.cores_per_node; ++core_no) {
for (thread_no = 0; thread_no <
topo.threads_per_core; ++thread_no) {
struct thread_data *t;
{ 0x0, "CPU" },
{ 0x0, "APIC" },
{ 0x0, "X2APIC" },
+ { 0x0, "Die" },
};
#define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter))
#define BIC_CPU (1ULL << 47)
#define BIC_APIC (1ULL << 48)
#define BIC_X2APIC (1ULL << 49)
+#define BIC_Die (1ULL << 50)
#define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC)
outp += sprintf(outp, "%sTime_Of_Day_Seconds", (printed++ ? delim : ""));
if (DO_BIC(BIC_Package))
outp += sprintf(outp, "%sPackage", (printed++ ? delim : ""));
+ if (DO_BIC(BIC_Die))
+ outp += sprintf(outp, "%sDie", (printed++ ? delim : ""));
if (DO_BIC(BIC_Node))
outp += sprintf(outp, "%sNode", (printed++ ? delim : ""));
if (DO_BIC(BIC_Core))
if (DO_BIC(BIC_CPU_c1))
outp += sprintf(outp, "%sCPU%%c1", (printed++ ? delim : ""));
- if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates && !do_cnl_cstates)
+ if (DO_BIC(BIC_CPU_c3))
outp += sprintf(outp, "%sCPU%%c3", (printed++ ? delim : ""));
if (DO_BIC(BIC_CPU_c6))
outp += sprintf(outp, "%sCPU%%c6", (printed++ ? delim : ""));
if (DO_BIC(BIC_CoreTmp))
outp += sprintf(outp, "%sCoreTmp", (printed++ ? delim : ""));
+ if (do_rapl && !rapl_joules) {
+ if (DO_BIC(BIC_CorWatt) && (do_rapl & RAPL_PER_CORE_ENERGY))
+ outp += sprintf(outp, "%sCorWatt", (printed++ ? delim : ""));
+ } else if (do_rapl && rapl_joules) {
+ if (DO_BIC(BIC_Cor_J) && (do_rapl & RAPL_PER_CORE_ENERGY))
+ outp += sprintf(outp, "%sCor_J", (printed++ ? delim : ""));
+ }
+
for (mp = sys.cp; mp; mp = mp->next) {
if (mp->format == FORMAT_RAW) {
if (mp->width == 64)
if (do_rapl && !rapl_joules) {
if (DO_BIC(BIC_PkgWatt))
outp += sprintf(outp, "%sPkgWatt", (printed++ ? delim : ""));
- if (DO_BIC(BIC_CorWatt))
+ if (DO_BIC(BIC_CorWatt) && !(do_rapl & RAPL_PER_CORE_ENERGY))
outp += sprintf(outp, "%sCorWatt", (printed++ ? delim : ""));
if (DO_BIC(BIC_GFXWatt))
outp += sprintf(outp, "%sGFXWatt", (printed++ ? delim : ""));
} else if (do_rapl && rapl_joules) {
if (DO_BIC(BIC_Pkg_J))
outp += sprintf(outp, "%sPkg_J", (printed++ ? delim : ""));
- if (DO_BIC(BIC_Cor_J))
+ if (DO_BIC(BIC_Cor_J) && !(do_rapl & RAPL_PER_CORE_ENERGY))
outp += sprintf(outp, "%sCor_J", (printed++ ? delim : ""));
if (DO_BIC(BIC_GFX_J))
outp += sprintf(outp, "%sGFX_J", (printed++ ? delim : ""));
outp += sprintf(outp, "c6: %016llX\n", c->c6);
outp += sprintf(outp, "c7: %016llX\n", c->c7);
outp += sprintf(outp, "DTS: %dC\n", c->core_temp_c);
+ outp += sprintf(outp, "Joules: %0X\n", c->core_energy);
for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
outp += sprintf(outp, "cADDED [%d] msr0x%x: %08llX\n",
if (t == &average.threads) {
if (DO_BIC(BIC_Package))
outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
+ if (DO_BIC(BIC_Die))
+ outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
if (DO_BIC(BIC_Node))
outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
if (DO_BIC(BIC_Core))
else
outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
}
+ if (DO_BIC(BIC_Die)) {
+ if (c)
+ outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), cpus[t->cpu_id].die_id);
+ else
+ outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
+ }
if (DO_BIC(BIC_Node)) {
if (t)
outp += sprintf(outp, "%s%d",
if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
goto done;
- if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates && !do_cnl_cstates)
+ if (DO_BIC(BIC_CPU_c3))
outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->c3/tsc);
if (DO_BIC(BIC_CPU_c6))
outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->c6/tsc);
}
}
+ /*
+ * If measurement interval exceeds minimum RAPL Joule Counter range,
+ * indicate that results are suspect by printing "**" in fraction place.
+ */
+ if (interval_float < rapl_joule_counter_range)
+ fmt8 = "%s%.2f";
+ else
+ fmt8 = "%6.0f**";
+
+ if (DO_BIC(BIC_CorWatt) && (do_rapl & RAPL_PER_CORE_ENERGY))
+ outp += sprintf(outp, fmt8, (printed++ ? delim : ""), c->core_energy * rapl_energy_units / interval_float);
+ if (DO_BIC(BIC_Cor_J) && (do_rapl & RAPL_PER_CORE_ENERGY))
+ outp += sprintf(outp, fmt8, (printed++ ? delim : ""), c->core_energy * rapl_energy_units);
+
/* print per-package data only for 1st core in package */
if (!(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
goto done;
if (DO_BIC(BIC_SYS_LPI))
outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->sys_lpi / 1000000.0 / interval_float);
- /*
- * If measurement interval exceeds minimum RAPL Joule Counter range,
- * indicate that results are suspect by printing "**" in fraction place.
- */
- if (interval_float < rapl_joule_counter_range)
- fmt8 = "%s%.2f";
- else
- fmt8 = "%6.0f**";
-
if (DO_BIC(BIC_PkgWatt))
outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_pkg * rapl_energy_units / interval_float);
- if (DO_BIC(BIC_CorWatt))
+ if (DO_BIC(BIC_CorWatt) && !(do_rapl & RAPL_PER_CORE_ENERGY))
outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_cores * rapl_energy_units / interval_float);
if (DO_BIC(BIC_GFXWatt))
outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_gfx * rapl_energy_units / interval_float);
outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_dram * rapl_dram_energy_units / interval_float);
if (DO_BIC(BIC_Pkg_J))
outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_pkg * rapl_energy_units);
- if (DO_BIC(BIC_Cor_J))
+ if (DO_BIC(BIC_Cor_J) && !(do_rapl & RAPL_PER_CORE_ENERGY))
outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_cores * rapl_energy_units);
if (DO_BIC(BIC_GFX_J))
outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_gfx * rapl_energy_units);
old->core_temp_c = new->core_temp_c;
old->mc6_us = new->mc6_us - old->mc6_us;
+ DELTA_WRAP32(new->core_energy, old->core_energy);
+
for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
if (mp->format == FORMAT_RAW)
old->counter[i] = new->counter[i];
c->c7 = 0;
c->mc6_us = 0;
c->core_temp_c = 0;
+ c->core_energy = 0;
p->pkg_wtd_core_c0 = 0;
p->pkg_any_core_c0 = 0;
average.cores.core_temp_c = MAX(average.cores.core_temp_c, c->core_temp_c);
+ average.cores.core_energy += c->core_energy;
+
for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
if (mp->format == FORMAT_RAW)
continue;
if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
goto done;
- if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates && !do_cnl_cstates) {
+ if (DO_BIC(BIC_CPU_c3)) {
if (get_msr(cpu, MSR_CORE_C3_RESIDENCY, &c->c3))
return -6;
}
c->core_temp_c = tcc_activation_temp - ((msr >> 16) & 0x7F);
}
+ if (do_rapl & RAPL_AMD_F17H) {
+ if (get_msr(cpu, MSR_CORE_ENERGY_STAT, &msr))
+ return -14;
+ c->core_energy = msr & 0xFFFFFFFF;
+ }
+
for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
if (get_mp(cpu, mp, &c->counter[i]))
return -10;
return -16;
p->rapl_dram_perf_status = msr & 0xFFFFFFFF;
}
+ if (do_rapl & RAPL_AMD_F17H) {
+ if (get_msr(cpu, MSR_PKG_ENERGY_STAT, &msr))
+ return -13;
+ p->energy_pkg = msr & 0xFFFFFFFF;
+ }
if (DO_BIC(BIC_PkgTmp)) {
if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_STATUS, &msr))
return -17;
/*
* Parse a file containing a single int.
+ * Return 0 if file can not be opened
+ * Exit if file can be opened, but can not be parsed
*/
int parse_int_file(const char *fmt, ...)
{
va_start(args, fmt);
vsnprintf(path, sizeof(path), fmt, args);
va_end(args);
- filep = fopen_or_die(path, "r");
+ filep = fopen(path, "r");
+ if (!filep)
+ return 0;
if (fscanf(filep, "%d", &value) != 1)
err(1, "%s: failed to parse number from file", path);
fclose(filep);
return parse_int_file("/sys/devices/system/cpu/cpu%d/topology/physical_package_id", cpu);
}
+int get_die_id(int cpu)
+{
+ return parse_int_file("/sys/devices/system/cpu/cpu%d/topology/die_id", cpu);
+}
+
int get_core_id(int cpu)
{
return parse_int_file("/sys/devices/system/cpu/cpu%d/topology/core_id", cpu);
filep = fopen_or_die(path, "r");
do {
offset -= BITMASK_SIZE;
- fscanf(filep, "%lx%c", &map, &character);
+ if (fscanf(filep, "%lx%c", &map, &character) != 2)
+ err(1, "%s: failed to parse file", path);
for (shift = 0; shift < BITMASK_SIZE; shift++) {
if ((map >> shift) & 0x1) {
so = shift + offset;
fp = fopen_or_die("/sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us", "r");
retval = fscanf(fp, "%lld", &cpuidle_cur_cpu_lpi_us);
- if (retval != 1)
- err(1, "CPU LPI");
+ if (retval != 1) {
+ fprintf(stderr, "Disabling Low Power Idle CPU output\n");
+ BIC_NOT_PRESENT(BIC_CPU_LPI);
+ return -1;
+ }
fclose(fp);
fp = fopen_or_die("/sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us", "r");
retval = fscanf(fp, "%lld", &cpuidle_cur_sys_lpi_us);
- if (retval != 1)
- err(1, "SYS LPI");
-
+ if (retval != 1) {
+ fprintf(stderr, "Disabling Low Power Idle System output\n");
+ BIC_NOT_PRESENT(BIC_SYS_LPI);
+ return -1;
+ }
fclose(fp);
return 0;
input = fopen(path, "r");
if (input == NULL)
continue;
- fgets(name_buf, sizeof(name_buf), input);
+ if (!fgets(name_buf, sizeof(name_buf), input))
+ err(1, "%s: failed to read file", path);
/* truncate "C1-HSW\n" to "C1", or truncate "C1\n" to "C1" */
sp = strchr(name_buf, '-');
if (!sp)
sp = strchrnul(name_buf, '\n');
*sp = '\0';
-
fclose(input);
sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/desc",
input = fopen(path, "r");
if (input == NULL)
continue;
- fgets(desc, sizeof(desc), input);
+ if (!fgets(desc, sizeof(desc), input))
+ err(1, "%s: failed to read file", path);
fprintf(outf, "cpu%d: %s: %s", base_cpu, name_buf, desc);
fclose(input);
base_cpu);
input = fopen(path, "r");
if (input == NULL) {
- fprintf(stderr, "NSFOD %s\n", path);
+ fprintf(outf, "NSFOD %s\n", path);
return;
}
- fgets(driver_buf, sizeof(driver_buf), input);
+ if (!fgets(driver_buf, sizeof(driver_buf), input))
+ err(1, "%s: failed to read file", path);
fclose(input);
sprintf(path, "/sys/devices/system/cpu/cpu%d/cpufreq/scaling_governor",
base_cpu);
input = fopen(path, "r");
if (input == NULL) {
- fprintf(stderr, "NSFOD %s\n", path);
+ fprintf(outf, "NSFOD %s\n", path);
return;
}
- fgets(governor_buf, sizeof(governor_buf), input);
+ if (!fgets(governor_buf, sizeof(governor_buf), input))
+ err(1, "%s: failed to read file", path);
fclose(input);
fprintf(outf, "cpu%d: cpufreq driver: %s", base_cpu, driver_buf);
sprintf(path, "/sys/devices/system/cpu/cpufreq/boost");
input = fopen(path, "r");
if (input != NULL) {
- fscanf(input, "%d", &turbo);
+ if (fscanf(input, "%d", &turbo) != 1)
+ err(1, "%s: failed to parse number from file", path);
fprintf(outf, "cpufreq boost: %d\n", turbo);
fclose(input);
}
sprintf(path, "/sys/devices/system/cpu/intel_pstate/no_turbo");
input = fopen(path, "r");
if (input != NULL) {
- fscanf(input, "%d", &turbo);
+ if (fscanf(input, "%d", &turbo) != 1)
+ err(1, "%s: failed to parse number from file", path);
fprintf(outf, "cpufreq intel_pstate no_turbo: %d\n", turbo);
fclose(input);
}
#define RAPL_POWER_GRANULARITY 0x7FFF /* 15 bit power granularity */
#define RAPL_TIME_GRANULARITY 0x3F /* 6 bit time granularity */
-double get_tdp(unsigned int model)
+double get_tdp_intel(unsigned int model)
{
unsigned long long msr;
}
}
+double get_tdp_amd(unsigned int family)
+{
+ switch (family) {
+ case 0x17:
+ default:
+ /* This is the max stock TDP of HEDT/Server Fam17h chips */
+ return 250.0;
+ }
+}
+
/*
* rapl_dram_energy_units_probe()
* Energy units are either hard-coded, or come from RAPL Energy Unit MSR.
}
}
-
-/*
- * rapl_probe()
- *
- * sets do_rapl, rapl_power_units, rapl_energy_units, rapl_time_units
- */
-void rapl_probe(unsigned int family, unsigned int model)
+void rapl_probe_intel(unsigned int family, unsigned int model)
{
unsigned long long msr;
unsigned int time_unit;
double tdp;
- if (!genuine_intel)
- return;
-
if (family != 6)
return;
rapl_time_units = 1.0 / (1 << (time_unit));
- tdp = get_tdp(model);
+ tdp = get_tdp_intel(model);
rapl_joule_counter_range = 0xFFFFFFFF * rapl_energy_units / tdp;
if (!quiet)
fprintf(outf, "RAPL: %.0f sec. Joule Counter Range, at %.0f Watts\n", rapl_joule_counter_range, tdp);
+}
- return;
+void rapl_probe_amd(unsigned int family, unsigned int model)
+{
+ unsigned long long msr;
+ unsigned int eax, ebx, ecx, edx;
+ unsigned int has_rapl = 0;
+ double tdp;
+
+ if (max_extended_level >= 0x80000007) {
+ __cpuid(0x80000007, eax, ebx, ecx, edx);
+ /* RAPL (Fam 17h) */
+ has_rapl = edx & (1 << 14);
+ }
+
+ if (!has_rapl)
+ return;
+
+ switch (family) {
+ case 0x17: /* Zen, Zen+ */
+ do_rapl = RAPL_AMD_F17H | RAPL_PER_CORE_ENERGY;
+ if (rapl_joules) {
+ BIC_PRESENT(BIC_Pkg_J);
+ BIC_PRESENT(BIC_Cor_J);
+ } else {
+ BIC_PRESENT(BIC_PkgWatt);
+ BIC_PRESENT(BIC_CorWatt);
+ }
+ break;
+ default:
+ return;
+ }
+
+ if (get_msr(base_cpu, MSR_RAPL_PWR_UNIT, &msr))
+ return;
+
+ rapl_time_units = ldexp(1.0, -(msr >> 16 & 0xf));
+ rapl_energy_units = ldexp(1.0, -(msr >> 8 & 0x1f));
+ rapl_power_units = ldexp(1.0, -(msr & 0xf));
+
+ tdp = get_tdp_amd(model);
+
+ rapl_joule_counter_range = 0xFFFFFFFF * rapl_energy_units / tdp;
+ if (!quiet)
+ fprintf(outf, "RAPL: %.0f sec. Joule Counter Range, at %.0f Watts\n", rapl_joule_counter_range, tdp);
+}
+
+/*
+ * rapl_probe()
+ *
+ * sets do_rapl, rapl_power_units, rapl_energy_units, rapl_time_units
+ */
+void rapl_probe(unsigned int family, unsigned int model)
+{
+ if (genuine_intel)
+ rapl_probe_intel(family, model);
+ if (authentic_amd)
+ rapl_probe_amd(family, model);
}
void perf_limit_reasons_probe(unsigned int family, unsigned int model)
int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
{
unsigned long long msr;
+ const char *msr_name;
int cpu;
if (!do_rapl)
return -1;
}
- if (get_msr(cpu, MSR_RAPL_POWER_UNIT, &msr))
- return -1;
+ if (do_rapl & RAPL_AMD_F17H) {
+ msr_name = "MSR_RAPL_PWR_UNIT";
+ if (get_msr(cpu, MSR_RAPL_PWR_UNIT, &msr))
+ return -1;
+ } else {
+ msr_name = "MSR_RAPL_POWER_UNIT";
+ if (get_msr(cpu, MSR_RAPL_POWER_UNIT, &msr))
+ return -1;
+ }
- fprintf(outf, "cpu%d: MSR_RAPL_POWER_UNIT: 0x%08llx (%f Watts, %f Joules, %f sec.)\n", cpu, msr,
+ fprintf(outf, "cpu%d: %s: 0x%08llx (%f Watts, %f Joules, %f sec.)\n", cpu, msr_name, msr,
rapl_power_units, rapl_energy_units, rapl_time_units);
if (do_rapl & RAPL_PKG_POWER_INFO) {
case INTEL_FAM6_KABYLAKE_MOBILE:
case INTEL_FAM6_KABYLAKE_DESKTOP:
return INTEL_FAM6_SKYLAKE_MOBILE;
+
+ case INTEL_FAM6_ICELAKE_MOBILE:
+ return INTEL_FAM6_CANNONLAKE_MOBILE;
}
return model;
}
}
do_slm_cstates = is_slm(family, model);
do_knl_cstates = is_knl(family, model);
- do_cnl_cstates = is_cnl(family, model);
+
+ if (do_slm_cstates || do_knl_cstates || is_cnl(family, model))
+ BIC_NOT_PRESENT(BIC_CPU_c3);
if (!quiet)
decode_misc_pwr_mgmt_msr();
int i;
int max_core_id = 0;
int max_package_id = 0;
+ int max_die_id = 0;
int max_siblings = 0;
/* Initialize num_cpus, max_cpu_num */
if (cpus[i].physical_package_id > max_package_id)
max_package_id = cpus[i].physical_package_id;
+ /* get die information */
+ cpus[i].die_id = get_die_id(i);
+ if (cpus[i].die_id > max_die_id)
+ max_die_id = cpus[i].die_id;
+
/* get numa node information */
cpus[i].physical_node_id = get_physical_node_id(&cpus[i]);
if (cpus[i].physical_node_id > topo.max_node_num)
if (!summary_only && topo.cores_per_node > 1)
BIC_PRESENT(BIC_Core);
+ topo.num_die = max_die_id + 1;
+ if (debug > 1)
+ fprintf(outf, "max_die_id %d, sizing for %d die\n",
+ max_die_id, topo.num_die);
+ if (!summary_only && topo.num_die > 1)
+ BIC_PRESENT(BIC_Die);
+
topo.num_packages = max_package_id + 1;
if (debug > 1)
fprintf(outf, "max_package_id %d, sizing for %d packages\n",
if (cpu_is_not_present(i))
continue;
fprintf(outf,
- "cpu %d pkg %d node %d lnode %d core %d thread %d\n",
- i, cpus[i].physical_package_id,
+ "cpu %d pkg %d die %d node %d lnode %d core %d thread %d\n",
+ i, cpus[i].physical_package_id, cpus[i].die_id,
cpus[i].physical_node_id,
cpus[i].logical_node_id,
cpus[i].physical_core_id,
}
void print_version() {
- fprintf(outf, "turbostat version 18.07.27"
+ fprintf(outf, "turbostat version 19.03.20"
" - Len Brown <lenb@kernel.org>\n");
}
input = fopen(path, "r");
if (input == NULL)
continue;
- fgets(name_buf, sizeof(name_buf), input);
+ if (!fgets(name_buf, sizeof(name_buf), input))
+ err(1, "%s: failed to read file", path);
/* truncate "C1-HSW\n" to "C1", or truncate "C1\n" to "C1" */
sp = strchr(name_buf, '-');
input = fopen(path, "r");
if (input == NULL)
continue;
- fgets(name_buf, sizeof(name_buf), input);
+ if (!fgets(name_buf, sizeof(name_buf), input))
+ err(1, "%s: failed to read file", path);
/* truncate "C1-HSW\n" to "C1", or truncate "C1\n" to "C1" */
sp = strchr(name_buf, '-');
if (!sp)
struct nfit_test_sec {
u8 state;
u8 ext_state;
+ u8 old_state;
u8 passphrase[32];
u8 master_passphrase[32];
u64 overwrite_end_time;
static struct gen_pool *nfit_pool;
+static const char zero_key[NVDIMM_PASSPHRASE_LEN];
+
static struct nfit_test *to_nfit_test(struct device *dev)
{
struct platform_device *pdev = to_platform_device(dev);
struct device *dev = &t->pdev.dev;
struct nfit_test_sec *sec = &dimm_sec_info[dimm];
- if (!(sec->state & ND_INTEL_SEC_STATE_ENABLED) ||
- (sec->state & ND_INTEL_SEC_STATE_FROZEN)) {
+ if (sec->state & ND_INTEL_SEC_STATE_FROZEN) {
nd_cmd->status = ND_INTEL_STATUS_INVALID_STATE;
dev_dbg(dev, "secure erase: wrong security state\n");
} else if (memcmp(nd_cmd->passphrase, sec->passphrase,
nd_cmd->status = ND_INTEL_STATUS_INVALID_PASS;
dev_dbg(dev, "secure erase: wrong passphrase\n");
} else {
+ if (!(sec->state & ND_INTEL_SEC_STATE_ENABLED)
+ && (memcmp(nd_cmd->passphrase, zero_key,
+ ND_INTEL_PASSPHRASE_SIZE) != 0)) {
+ dev_dbg(dev, "invalid zero key\n");
+ return 0;
+ }
memset(sec->passphrase, 0, ND_INTEL_PASSPHRASE_SIZE);
memset(sec->master_passphrase, 0, ND_INTEL_PASSPHRASE_SIZE);
sec->state = 0;
return 0;
}
- memset(sec->passphrase, 0, ND_INTEL_PASSPHRASE_SIZE);
+ sec->old_state = sec->state;
sec->state = ND_INTEL_SEC_STATE_OVERWRITE;
dev_dbg(dev, "overwrite progressing.\n");
sec->overwrite_end_time = get_jiffies_64() + 5 * HZ;
if (time_is_before_jiffies64(sec->overwrite_end_time)) {
sec->overwrite_end_time = 0;
- sec->state = 0;
+ sec->state = sec->old_state;
+ sec->old_state = 0;
sec->ext_state = ND_INTEL_SEC_ESTATE_ENABLED;
dev_dbg(dev, "overwrite is complete\n");
} else
endif
PROG_TESTS_H := $(OUTPUT)/prog_tests/tests.h
-$(OUTPUT)/test_progs: $(PROG_TESTS_H)
+test_progs.c: $(PROG_TESTS_H)
$(OUTPUT)/test_progs: CFLAGS += $(TEST_PROGS_CFLAGS)
$(OUTPUT)/test_progs: prog_tests/*.c
) > $(PROG_TESTS_H))
VERIFIER_TESTS_H := $(OUTPUT)/verifier/tests.h
-$(OUTPUT)/test_verifier: $(VERIFIER_TESTS_H)
+test_verifier.c: $(VERIFIER_TESTS_H)
$(OUTPUT)/test_verifier: CFLAGS += $(TEST_VERIFIER_CFLAGS)
VERIFIER_TESTS_DIR = $(OUTPUT)/verifier
#define SEC(NAME) __attribute__((section(NAME), used))
/* helper functions called from eBPF programs written in C */
-static void *(*bpf_map_lookup_elem)(void *map, void *key) =
+static void *(*bpf_map_lookup_elem)(void *map, const void *key) =
(void *) BPF_FUNC_map_lookup_elem;
-static int (*bpf_map_update_elem)(void *map, void *key, void *value,
+static int (*bpf_map_update_elem)(void *map, const void *key, const void *value,
unsigned long long flags) =
(void *) BPF_FUNC_map_update_elem;
-static int (*bpf_map_delete_elem)(void *map, void *key) =
+static int (*bpf_map_delete_elem)(void *map, const void *key) =
(void *) BPF_FUNC_map_delete_elem;
-static int (*bpf_map_push_elem)(void *map, void *value,
+static int (*bpf_map_push_elem)(void *map, const void *value,
unsigned long long flags) =
(void *) BPF_FUNC_map_push_elem;
static int (*bpf_map_pop_elem)(void *map, void *value) =
CONFIG_FTRACE_SYSCALLS=y
CONFIG_IPV6_TUNNEL=y
CONFIG_IPV6_GRE=y
+CONFIG_NET_FOU=m
+CONFIG_NET_FOU_IP_TUNNELS=y
+CONFIG_IPV6_FOU=m
+CONFIG_IPV6_FOU_TUNNEL=m
+CONFIG_MPLS=y
+CONFIG_NET_MPLS_GSO=m
+CONFIG_MPLS_ROUTING=m
+CONFIG_MPLS_IPTUNNEL=m
sprintf(command, "rm -r %s", cfg_pin_path);
ret = system(command);
if (ret)
- error(1, errno, command);
+ error(1, errno, "%s", command);
}
static void parse_opts(int argc, char **argv)
info_len != sizeof(struct bpf_map_info) ||
strcmp((char *)map_infos[i].name, expected_map_name),
"get-map-info(fd)",
- "err %d errno %d type %d(%d) info_len %u(%Zu) key_size %u value_size %u max_entries %u map_flags %X name %s(%s)\n",
+ "err %d errno %d type %d(%d) info_len %u(%zu) key_size %u value_size %u max_entries %u map_flags %X name %s(%s)\n",
err, errno,
map_infos[i].type, BPF_MAP_TYPE_ARRAY,
info_len, sizeof(struct bpf_map_info),
*(int *)(long)prog_infos[i].map_ids != map_infos[i].id ||
strcmp((char *)prog_infos[i].name, expected_prog_name),
"get-prog-info(fd)",
- "err %d errno %d i %d type %d(%d) info_len %u(%Zu) jit_enabled %d jited_prog_len %u xlated_prog_len %u jited_prog %d xlated_prog %d load_time %lu(%lu) uid %u(%u) nr_map_ids %u(%u) map_id %u(%u) name %s(%s)\n",
+ "err %d errno %d i %d type %d(%d) info_len %u(%zu) jit_enabled %d jited_prog_len %u xlated_prog_len %u jited_prog %d xlated_prog %d load_time %lu(%lu) uid %u(%u) nr_map_ids %u(%u) map_id %u(%u) name %s(%s)\n",
err, errno, i,
prog_infos[i].type, BPF_PROG_TYPE_SOCKET_FILTER,
info_len, sizeof(struct bpf_prog_info),
memcmp(&prog_info, &prog_infos[i], info_len) ||
*(int *)(long)prog_info.map_ids != saved_map_id,
"get-prog-info(next_id->fd)",
- "err %d errno %d info_len %u(%Zu) memcmp %d map_id %u(%u)\n",
+ "err %d errno %d info_len %u(%zu) memcmp %d map_id %u(%u)\n",
err, errno, info_len, sizeof(struct bpf_prog_info),
memcmp(&prog_info, &prog_infos[i], info_len),
*(int *)(long)prog_info.map_ids, saved_map_id);
memcmp(&map_info, &map_infos[i], info_len) ||
array_value != array_magic_value,
"check get-map-info(next_id->fd)",
- "err %d errno %d info_len %u(%Zu) memcmp %d array_value %llu(%llu)\n",
+ "err %d errno %d info_len %u(%zu) memcmp %d array_value %llu(%llu)\n",
err, errno, info_len, sizeof(struct bpf_map_info),
memcmp(&map_info, &map_infos[i], info_len),
array_value, array_magic_value);
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+#include <test_progs.h>
+static int libbpf_debug_print(enum libbpf_print_level level,
+ const char *format, va_list args)
+{
+ if (level != LIBBPF_DEBUG)
+ return 0;
+
+ if (!strstr(format, "verifier log"))
+ return 0;
+ return vfprintf(stderr, "%s", args);
+}
+
+static int check_load(const char *file)
+{
+ struct bpf_prog_load_attr attr;
+ struct bpf_object *obj;
+ int err, prog_fd;
+
+ memset(&attr, 0, sizeof(struct bpf_prog_load_attr));
+ attr.file = file;
+ attr.prog_type = BPF_PROG_TYPE_SCHED_CLS;
+ attr.log_level = 4;
+ err = bpf_prog_load_xattr(&attr, &obj, &prog_fd);
+ bpf_object__close(obj);
+ if (err)
+ error_cnt++;
+ return err;
+}
+
+void test_bpf_verif_scale(void)
+{
+ const char *file1 = "./test_verif_scale1.o";
+ const char *file2 = "./test_verif_scale2.o";
+ const char *file3 = "./test_verif_scale3.o";
+ int err;
+
+ if (verifier_stats)
+ libbpf_set_print(libbpf_debug_print);
+
+ err = check_load(file1);
+ err |= check_load(file2);
+ err |= check_load(file3);
+ if (!err)
+ printf("test_verif_scale:OK\n");
+ else
+ printf("test_verif_scale:FAIL\n");
+}
.n_proto = __bpf_constant_htons(ETH_P_IPV6),
};
+#define VLAN_HLEN 4
+
+static struct {
+ struct ethhdr eth;
+ __u16 vlan_tci;
+ __u16 vlan_proto;
+ struct iphdr iph;
+ struct tcphdr tcp;
+} __packed pkt_vlan_v4 = {
+ .eth.h_proto = __bpf_constant_htons(ETH_P_8021Q),
+ .vlan_proto = __bpf_constant_htons(ETH_P_IP),
+ .iph.ihl = 5,
+ .iph.protocol = IPPROTO_TCP,
+ .iph.tot_len = __bpf_constant_htons(MAGIC_BYTES),
+ .tcp.urg_ptr = 123,
+ .tcp.doff = 5,
+};
+
+static struct bpf_flow_keys pkt_vlan_v4_flow_keys = {
+ .nhoff = VLAN_HLEN,
+ .thoff = VLAN_HLEN + sizeof(struct iphdr),
+ .addr_proto = ETH_P_IP,
+ .ip_proto = IPPROTO_TCP,
+ .n_proto = __bpf_constant_htons(ETH_P_IP),
+};
+
+static struct {
+ struct ethhdr eth;
+ __u16 vlan_tci;
+ __u16 vlan_proto;
+ __u16 vlan_tci2;
+ __u16 vlan_proto2;
+ struct ipv6hdr iph;
+ struct tcphdr tcp;
+} __packed pkt_vlan_v6 = {
+ .eth.h_proto = __bpf_constant_htons(ETH_P_8021AD),
+ .vlan_proto = __bpf_constant_htons(ETH_P_8021Q),
+ .vlan_proto2 = __bpf_constant_htons(ETH_P_IPV6),
+ .iph.nexthdr = IPPROTO_TCP,
+ .iph.payload_len = __bpf_constant_htons(MAGIC_BYTES),
+ .tcp.urg_ptr = 123,
+ .tcp.doff = 5,
+};
+
+static struct bpf_flow_keys pkt_vlan_v6_flow_keys = {
+ .nhoff = VLAN_HLEN * 2,
+ .thoff = VLAN_HLEN * 2 + sizeof(struct ipv6hdr),
+ .addr_proto = ETH_P_IPV6,
+ .ip_proto = IPPROTO_TCP,
+ .n_proto = __bpf_constant_htons(ETH_P_IPV6),
+};
+
void test_flow_dissector(void)
{
struct bpf_flow_keys flow_keys;
err, errno, retval, duration, size, sizeof(flow_keys));
CHECK_FLOW_KEYS("ipv6_flow_keys", flow_keys, pkt_v6_flow_keys);
+ err = bpf_prog_test_run(prog_fd, 10, &pkt_vlan_v4, sizeof(pkt_vlan_v4),
+ &flow_keys, &size, &retval, &duration);
+ CHECK(size != sizeof(flow_keys) || err || retval != 1, "vlan_ipv4",
+ "err %d errno %d retval %d duration %d size %u/%lu\n",
+ err, errno, retval, duration, size, sizeof(flow_keys));
+ CHECK_FLOW_KEYS("vlan_ipv4_flow_keys", flow_keys,
+ pkt_vlan_v4_flow_keys);
+
+ err = bpf_prog_test_run(prog_fd, 10, &pkt_vlan_v6, sizeof(pkt_vlan_v6),
+ &flow_keys, &size, &retval, &duration);
+ CHECK(size != sizeof(flow_keys) || err || retval != 1, "vlan_ipv6",
+ "err %d errno %d retval %d duration %d size %u/%lu\n",
+ err, errno, retval, duration, size, sizeof(flow_keys));
+ CHECK_FLOW_KEYS("vlan_ipv6_flow_keys", flow_keys,
+ pkt_vlan_v6_flow_keys);
+
bpf_object__close(obj);
}
} else {
for (i = 0; i < num_stack; i++) {
ks = ksym_search(raw_data[i]);
- if (strcmp(ks->name, nonjit_func) == 0) {
+ if (ks && (strcmp(ks->name, nonjit_func) == 0)) {
found = true;
break;
}
} else {
for (i = 0; i < num_stack; i++) {
ks = ksym_search(e->kern_stack[i]);
- if (strcmp(ks->name, nonjit_func) == 0) {
+ if (ks && (strcmp(ks->name, nonjit_func) == 0)) {
good_kern_stack = true;
break;
}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+
+static void test_global_data_number(struct bpf_object *obj, __u32 duration)
+{
+ int i, err, map_fd;
+ uint64_t num;
+
+ map_fd = bpf_find_map(__func__, obj, "result_number");
+ if (map_fd < 0) {
+ error_cnt++;
+ return;
+ }
+
+ struct {
+ char *name;
+ uint32_t key;
+ uint64_t num;
+ } tests[] = {
+ { "relocate .bss reference", 0, 0 },
+ { "relocate .data reference", 1, 42 },
+ { "relocate .rodata reference", 2, 24 },
+ { "relocate .bss reference", 3, 0 },
+ { "relocate .data reference", 4, 0xffeeff },
+ { "relocate .rodata reference", 5, 0xabab },
+ { "relocate .bss reference", 6, 1234 },
+ { "relocate .bss reference", 7, 0 },
+ { "relocate .rodata reference", 8, 0xab },
+ { "relocate .rodata reference", 9, 0x1111111111111111 },
+ { "relocate .rodata reference", 10, ~0 },
+ };
+
+ for (i = 0; i < sizeof(tests) / sizeof(tests[0]); i++) {
+ err = bpf_map_lookup_elem(map_fd, &tests[i].key, &num);
+ CHECK(err || num != tests[i].num, tests[i].name,
+ "err %d result %lx expected %lx\n",
+ err, num, tests[i].num);
+ }
+}
+
+static void test_global_data_string(struct bpf_object *obj, __u32 duration)
+{
+ int i, err, map_fd;
+ char str[32];
+
+ map_fd = bpf_find_map(__func__, obj, "result_string");
+ if (map_fd < 0) {
+ error_cnt++;
+ return;
+ }
+
+ struct {
+ char *name;
+ uint32_t key;
+ char str[32];
+ } tests[] = {
+ { "relocate .rodata reference", 0, "abcdefghijklmnopqrstuvwxyz" },
+ { "relocate .data reference", 1, "abcdefghijklmnopqrstuvwxyz" },
+ { "relocate .bss reference", 2, "" },
+ { "relocate .data reference", 3, "abcdexghijklmnopqrstuvwxyz" },
+ { "relocate .bss reference", 4, "\0\0hello" },
+ };
+
+ for (i = 0; i < sizeof(tests) / sizeof(tests[0]); i++) {
+ err = bpf_map_lookup_elem(map_fd, &tests[i].key, str);
+ CHECK(err || memcmp(str, tests[i].str, sizeof(str)),
+ tests[i].name, "err %d result \'%s\' expected \'%s\'\n",
+ err, str, tests[i].str);
+ }
+}
+
+struct foo {
+ __u8 a;
+ __u32 b;
+ __u64 c;
+};
+
+static void test_global_data_struct(struct bpf_object *obj, __u32 duration)
+{
+ int i, err, map_fd;
+ struct foo val;
+
+ map_fd = bpf_find_map(__func__, obj, "result_struct");
+ if (map_fd < 0) {
+ error_cnt++;
+ return;
+ }
+
+ struct {
+ char *name;
+ uint32_t key;
+ struct foo val;
+ } tests[] = {
+ { "relocate .rodata reference", 0, { 42, 0xfefeefef, 0x1111111111111111ULL, } },
+ { "relocate .bss reference", 1, { } },
+ { "relocate .rodata reference", 2, { } },
+ { "relocate .data reference", 3, { 41, 0xeeeeefef, 0x2111111111111111ULL, } },
+ };
+
+ for (i = 0; i < sizeof(tests) / sizeof(tests[0]); i++) {
+ err = bpf_map_lookup_elem(map_fd, &tests[i].key, &val);
+ CHECK(err || memcmp(&val, &tests[i].val, sizeof(val)),
+ tests[i].name, "err %d result { %u, %u, %llu } expected { %u, %u, %llu }\n",
+ err, val.a, val.b, val.c, tests[i].val.a, tests[i].val.b, tests[i].val.c);
+ }
+}
+
+static void test_global_data_rdonly(struct bpf_object *obj, __u32 duration)
+{
+ int err = -ENOMEM, map_fd, zero = 0;
+ struct bpf_map *map;
+ __u8 *buff;
+
+ map = bpf_object__find_map_by_name(obj, "test_glo.rodata");
+ if (!map || !bpf_map__is_internal(map)) {
+ error_cnt++;
+ return;
+ }
+
+ map_fd = bpf_map__fd(map);
+ if (map_fd < 0) {
+ error_cnt++;
+ return;
+ }
+
+ buff = malloc(bpf_map__def(map)->value_size);
+ if (buff)
+ err = bpf_map_update_elem(map_fd, &zero, buff, 0);
+ free(buff);
+ CHECK(!err || errno != EPERM, "test .rodata read-only map",
+ "err %d errno %d\n", err, errno);
+}
+
+void test_global_data(void)
+{
+ const char *file = "./test_global_data.o";
+ __u32 duration = 0, retval;
+ struct bpf_object *obj;
+ int err, prog_fd;
+
+ err = bpf_prog_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd);
+ if (CHECK(err, "load program", "error %d loading %s\n", err, file))
+ return;
+
+ err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
+ NULL, NULL, &retval, &duration);
+ CHECK(err || retval, "pass global data run",
+ "err %d errno %d retval %d duration %d\n",
+ err, errno, retval, duration);
+
+ test_global_data_number(obj, duration);
+ test_global_data_string(obj, duration);
+ test_global_data_struct(obj, duration);
+ test_global_data_rdonly(obj, duration);
+
+ bpf_object__close(obj);
+}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+
+void test_skb_ctx(void)
+{
+ struct __sk_buff skb = {
+ .cb[0] = 1,
+ .cb[1] = 2,
+ .cb[2] = 3,
+ .cb[3] = 4,
+ .cb[4] = 5,
+ .priority = 6,
+ };
+ struct bpf_prog_test_run_attr tattr = {
+ .data_in = &pkt_v4,
+ .data_size_in = sizeof(pkt_v4),
+ .ctx_in = &skb,
+ .ctx_size_in = sizeof(skb),
+ .ctx_out = &skb,
+ .ctx_size_out = sizeof(skb),
+ };
+ struct bpf_object *obj;
+ int err;
+ int i;
+
+ err = bpf_prog_load("./test_skb_ctx.o", BPF_PROG_TYPE_SCHED_CLS, &obj,
+ &tattr.prog_fd);
+ if (CHECK_ATTR(err, "load", "err %d errno %d\n", err, errno))
+ return;
+
+ /* ctx_in != NULL, ctx_size_in == 0 */
+
+ tattr.ctx_size_in = 0;
+ err = bpf_prog_test_run_xattr(&tattr);
+ CHECK_ATTR(err == 0, "ctx_size_in", "err %d errno %d\n", err, errno);
+ tattr.ctx_size_in = sizeof(skb);
+
+ /* ctx_out != NULL, ctx_size_out == 0 */
+
+ tattr.ctx_size_out = 0;
+ err = bpf_prog_test_run_xattr(&tattr);
+ CHECK_ATTR(err == 0, "ctx_size_out", "err %d errno %d\n", err, errno);
+ tattr.ctx_size_out = sizeof(skb);
+
+ /* non-zero [len, tc_index] fields should be rejected*/
+
+ skb.len = 1;
+ err = bpf_prog_test_run_xattr(&tattr);
+ CHECK_ATTR(err == 0, "len", "err %d errno %d\n", err, errno);
+ skb.len = 0;
+
+ skb.tc_index = 1;
+ err = bpf_prog_test_run_xattr(&tattr);
+ CHECK_ATTR(err == 0, "tc_index", "err %d errno %d\n", err, errno);
+ skb.tc_index = 0;
+
+ /* non-zero [hash, sk] fields should be rejected */
+
+ skb.hash = 1;
+ err = bpf_prog_test_run_xattr(&tattr);
+ CHECK_ATTR(err == 0, "hash", "err %d errno %d\n", err, errno);
+ skb.hash = 0;
+
+ skb.sk = (struct bpf_sock *)1;
+ err = bpf_prog_test_run_xattr(&tattr);
+ CHECK_ATTR(err == 0, "sk", "err %d errno %d\n", err, errno);
+ skb.sk = 0;
+
+ err = bpf_prog_test_run_xattr(&tattr);
+ CHECK_ATTR(err != 0 || tattr.retval,
+ "run",
+ "err %d errno %d retval %d\n",
+ err, errno, tattr.retval);
+
+ CHECK_ATTR(tattr.ctx_size_out != sizeof(skb),
+ "ctx_size_out",
+ "incorrect output size, want %lu have %u\n",
+ sizeof(skb), tattr.ctx_size_out);
+
+ for (i = 0; i < 5; i++)
+ CHECK_ATTR(skb.cb[i] != i + 2,
+ "ctx_out_cb",
+ "skb->cb[i] == %d, expected %d\n",
+ skb.cb[i], i + 2);
+ CHECK_ATTR(skb.priority != 7,
+ "ctx_out_priority",
+ "skb->priority == %d, expected %d\n",
+ skb.priority, 7);
+}
{
struct bpf_flow_keys *keys = skb->flow_keys;
- keys->n_proto = proto;
switch (proto) {
case bpf_htons(ETH_P_IP):
bpf_tail_call(skb, &jmp_table, IP);
SEC("flow_dissector")
int _dissect(struct __sk_buff *skb)
{
- if (!skb->vlan_present)
- return parse_eth_proto(skb, skb->protocol);
- else
- return parse_eth_proto(skb, skb->vlan_proto);
+ struct bpf_flow_keys *keys = skb->flow_keys;
+
+ return parse_eth_proto(skb, keys->n_proto);
}
/* Parses on IPPROTO_* */
{
struct bpf_flow_keys *keys = skb->flow_keys;
struct vlan_hdr *vlan, _vlan;
- __be16 proto;
-
- /* Peek back to see if single or double-tagging */
- if (bpf_skb_load_bytes(skb, keys->thoff - sizeof(proto), &proto,
- sizeof(proto)))
- return BPF_DROP;
/* Account for double-tagging */
- if (proto == bpf_htons(ETH_P_8021AD)) {
+ if (keys->n_proto == bpf_htons(ETH_P_8021AD)) {
vlan = bpf_flow_dissect_get_header(skb, sizeof(*vlan), &_vlan);
if (!vlan)
return BPF_DROP;
if (vlan->h_vlan_encapsulated_proto != bpf_htons(ETH_P_8021Q))
return BPF_DROP;
+ keys->nhoff += sizeof(*vlan);
keys->thoff += sizeof(*vlan);
}
if (!vlan)
return BPF_DROP;
+ keys->nhoff += sizeof(*vlan);
keys->thoff += sizeof(*vlan);
/* Only allow 8021AD + 8021Q double tagging and no triple tagging.*/
if (vlan->h_vlan_encapsulated_proto == bpf_htons(ETH_P_8021AD) ||
vlan->h_vlan_encapsulated_proto == bpf_htons(ETH_P_8021Q))
return BPF_DROP;
+ keys->n_proto = vlan->h_vlan_encapsulated_proto;
return parse_eth_proto(skb, vlan->h_vlan_encapsulated_proto);
}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Isovalent, Inc.
+
+#include <linux/bpf.h>
+#include <linux/pkt_cls.h>
+#include <string.h>
+
+#include "bpf_helpers.h"
+
+struct bpf_map_def SEC("maps") result_number = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(__u32),
+ .value_size = sizeof(__u64),
+ .max_entries = 11,
+};
+
+struct bpf_map_def SEC("maps") result_string = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(__u32),
+ .value_size = 32,
+ .max_entries = 5,
+};
+
+struct foo {
+ __u8 a;
+ __u32 b;
+ __u64 c;
+};
+
+struct bpf_map_def SEC("maps") result_struct = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(__u32),
+ .value_size = sizeof(struct foo),
+ .max_entries = 5,
+};
+
+/* Relocation tests for __u64s. */
+static __u64 num0;
+static __u64 num1 = 42;
+static const __u64 num2 = 24;
+static __u64 num3 = 0;
+static __u64 num4 = 0xffeeff;
+static const __u64 num5 = 0xabab;
+static const __u64 num6 = 0xab;
+
+/* Relocation tests for strings. */
+static const char str0[32] = "abcdefghijklmnopqrstuvwxyz";
+static char str1[32] = "abcdefghijklmnopqrstuvwxyz";
+static char str2[32];
+
+/* Relocation tests for structs. */
+static const struct foo struct0 = {
+ .a = 42,
+ .b = 0xfefeefef,
+ .c = 0x1111111111111111ULL,
+};
+static struct foo struct1;
+static const struct foo struct2;
+static struct foo struct3 = {
+ .a = 41,
+ .b = 0xeeeeefef,
+ .c = 0x2111111111111111ULL,
+};
+
+#define test_reloc(map, num, var) \
+ do { \
+ __u32 key = num; \
+ bpf_map_update_elem(&result_##map, &key, var, 0); \
+ } while (0)
+
+SEC("static_data_load")
+int load_static_data(struct __sk_buff *skb)
+{
+ static const __u64 bar = ~0;
+
+ test_reloc(number, 0, &num0);
+ test_reloc(number, 1, &num1);
+ test_reloc(number, 2, &num2);
+ test_reloc(number, 3, &num3);
+ test_reloc(number, 4, &num4);
+ test_reloc(number, 5, &num5);
+ num4 = 1234;
+ test_reloc(number, 6, &num4);
+ test_reloc(number, 7, &num0);
+ test_reloc(number, 8, &num6);
+
+ test_reloc(string, 0, str0);
+ test_reloc(string, 1, str1);
+ test_reloc(string, 2, str2);
+ str1[5] = 'x';
+ test_reloc(string, 3, str1);
+ __builtin_memcpy(&str2[2], "hello", sizeof("hello"));
+ test_reloc(string, 4, str2);
+
+ test_reloc(struct, 0, &struct0);
+ test_reloc(struct, 1, &struct1);
+ test_reloc(struct, 2, &struct2);
+ test_reloc(struct, 3, &struct3);
+
+ test_reloc(number, 9, &struct0.c);
+ test_reloc(number, 10, &bar);
+
+ return TC_ACT_OK;
+}
+
+char _license[] SEC("license") = "GPL";
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+
+typedef unsigned int u32;
+
+static __attribute__((always_inline)) u32 rol32(u32 word, unsigned int shift)
+{
+ return (word << shift) | (word >> ((-shift) & 31));
+}
+
+#define __jhash_mix(a, b, c) \
+{ \
+ a -= c; a ^= rol32(c, 4); c += b; \
+ b -= a; b ^= rol32(a, 6); a += c; \
+ c -= b; c ^= rol32(b, 8); b += a; \
+ a -= c; a ^= rol32(c, 16); c += b; \
+ b -= a; b ^= rol32(a, 19); a += c; \
+ c -= b; c ^= rol32(b, 4); b += a; \
+}
+
+#define __jhash_final(a, b, c) \
+{ \
+ c ^= b; c -= rol32(b, 14); \
+ a ^= c; a -= rol32(c, 11); \
+ b ^= a; b -= rol32(a, 25); \
+ c ^= b; c -= rol32(b, 16); \
+ a ^= c; a -= rol32(c, 4); \
+ b ^= a; b -= rol32(a, 14); \
+ c ^= b; c -= rol32(b, 24); \
+}
+
+#define JHASH_INITVAL 0xdeadbeef
+
+static ATTR
+u32 jhash(const void *key, u32 length, u32 initval)
+{
+ u32 a, b, c;
+ const unsigned char *k = key;
+
+ a = b = c = JHASH_INITVAL + length + initval;
+
+ while (length > 12) {
+ a += *(volatile u32 *)(k);
+ b += *(volatile u32 *)(k + 4);
+ c += *(volatile u32 *)(k + 8);
+ __jhash_mix(a, b, c);
+ length -= 12;
+ k += 12;
+ }
+ switch (length) {
+ case 12: c += (u32)k[11]<<24;
+ case 11: c += (u32)k[10]<<16;
+ case 10: c += (u32)k[9]<<8;
+ case 9: c += k[8];
+ case 8: b += (u32)k[7]<<24;
+ case 7: b += (u32)k[6]<<16;
+ case 6: b += (u32)k[5]<<8;
+ case 5: b += k[4];
+ case 4: a += (u32)k[3]<<24;
+ case 3: a += (u32)k[2]<<16;
+ case 2: a += (u32)k[1]<<8;
+ case 1: a += k[0];
+ c ^= a;
+ __jhash_final(a, b, c);
+ case 0: /* Nothing left to add */
+ break;
+ }
+
+ return c;
+}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+
+int _version SEC("version") = 1;
+char _license[] SEC("license") = "GPL";
+
+SEC("skb_ctx")
+int process(struct __sk_buff *skb)
+{
+ #pragma clang loop unroll(full)
+ for (int i = 0; i < 5; i++) {
+ if (skb->cb[i] != i + 1)
+ return 1;
+ skb->cb[i]++;
+ }
+ skb->priority++;
+
+ return 0;
+}
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
+#include <linux/mpls.h>
#include <linux/tcp.h>
+#include <linux/udp.h>
#include <linux/pkt_cls.h>
#include <linux/types.h>
static const int cfg_port = 8000;
-struct grev4hdr {
- struct iphdr ip;
+static const int cfg_udp_src = 20000;
+
+#define UDP_PORT 5555
+#define MPLS_OVER_UDP_PORT 6635
+#define ETH_OVER_UDP_PORT 7777
+
+/* MPLS label 1000 with S bit (last label) set and ttl of 255. */
+static const __u32 mpls_label = __bpf_constant_htonl(1000 << 12 |
+ MPLS_LS_S_MASK | 0xff);
+
+struct gre_hdr {
__be16 flags;
__be16 protocol;
} __attribute__((packed));
-struct grev6hdr {
+union l4hdr {
+ struct udphdr udp;
+ struct gre_hdr gre;
+};
+
+struct v4hdr {
+ struct iphdr ip;
+ union l4hdr l4hdr;
+ __u8 pad[16]; /* enough space for L2 header */
+} __attribute__((packed));
+
+struct v6hdr {
struct ipv6hdr ip;
- __be16 flags;
- __be16 protocol;
+ union l4hdr l4hdr;
+ __u8 pad[16]; /* enough space for L2 header */
} __attribute__((packed));
static __always_inline void set_ipv4_csum(struct iphdr *iph)
iph->check = ~((csum & 0xffff) + (csum >> 16));
}
-static __always_inline int encap_ipv4(struct __sk_buff *skb, bool with_gre)
+static __always_inline int encap_ipv4(struct __sk_buff *skb, __u8 encap_proto,
+ __u16 l2_proto)
{
- struct grev4hdr h_outer;
+ __u16 udp_dst = UDP_PORT;
struct iphdr iph_inner;
+ struct v4hdr h_outer;
struct tcphdr tcph;
+ int olen, l2_len;
__u64 flags;
- int olen;
if (bpf_skb_load_bytes(skb, ETH_HLEN, &iph_inner,
sizeof(iph_inner)) < 0)
if (tcph.dest != __bpf_constant_htons(cfg_port))
return TC_ACT_OK;
+ olen = sizeof(h_outer.ip);
+ l2_len = 0;
+
flags = BPF_F_ADJ_ROOM_FIXED_GSO | BPF_F_ADJ_ROOM_ENCAP_L3_IPV4;
- if (with_gre) {
+
+ switch (l2_proto) {
+ case ETH_P_MPLS_UC:
+ l2_len = sizeof(mpls_label);
+ udp_dst = MPLS_OVER_UDP_PORT;
+ break;
+ case ETH_P_TEB:
+ l2_len = ETH_HLEN;
+ udp_dst = ETH_OVER_UDP_PORT;
+ break;
+ }
+ flags |= BPF_F_ADJ_ROOM_ENCAP_L2(l2_len);
+
+ switch (encap_proto) {
+ case IPPROTO_GRE:
flags |= BPF_F_ADJ_ROOM_ENCAP_L4_GRE;
- olen = sizeof(h_outer);
- } else {
- olen = sizeof(h_outer.ip);
+ olen += sizeof(h_outer.l4hdr.gre);
+ h_outer.l4hdr.gre.protocol = bpf_htons(l2_proto);
+ h_outer.l4hdr.gre.flags = 0;
+ break;
+ case IPPROTO_UDP:
+ flags |= BPF_F_ADJ_ROOM_ENCAP_L4_UDP;
+ olen += sizeof(h_outer.l4hdr.udp);
+ h_outer.l4hdr.udp.source = __bpf_constant_htons(cfg_udp_src);
+ h_outer.l4hdr.udp.dest = bpf_htons(udp_dst);
+ h_outer.l4hdr.udp.check = 0;
+ h_outer.l4hdr.udp.len = bpf_htons(bpf_ntohs(iph_inner.tot_len) +
+ sizeof(h_outer.l4hdr.udp) +
+ l2_len);
+ break;
+ case IPPROTO_IPIP:
+ break;
+ default:
+ return TC_ACT_OK;
+ }
+
+ /* add L2 encap (if specified) */
+ switch (l2_proto) {
+ case ETH_P_MPLS_UC:
+ *((__u32 *)((__u8 *)&h_outer + olen)) = mpls_label;
+ break;
+ case ETH_P_TEB:
+ if (bpf_skb_load_bytes(skb, 0, (__u8 *)&h_outer + olen,
+ ETH_HLEN))
+ return TC_ACT_SHOT;
+ break;
}
+ olen += l2_len;
/* add room between mac and network header */
if (bpf_skb_adjust_room(skb, olen, BPF_ADJ_ROOM_MAC, flags))
/* prepare new outer network header */
h_outer.ip = iph_inner;
h_outer.ip.tot_len = bpf_htons(olen +
- bpf_htons(h_outer.ip.tot_len));
- if (with_gre) {
- h_outer.ip.protocol = IPPROTO_GRE;
- h_outer.protocol = bpf_htons(ETH_P_IP);
- h_outer.flags = 0;
- } else {
- h_outer.ip.protocol = IPPROTO_IPIP;
- }
+ bpf_ntohs(h_outer.ip.tot_len));
+ h_outer.ip.protocol = encap_proto;
- set_ipv4_csum((void *)&h_outer.ip);
+ set_ipv4_csum(&h_outer.ip);
/* store new outer network header */
if (bpf_skb_store_bytes(skb, ETH_HLEN, &h_outer, olen,
return TC_ACT_OK;
}
-static __always_inline int encap_ipv6(struct __sk_buff *skb, bool with_gre)
+static __always_inline int encap_ipv6(struct __sk_buff *skb, __u8 encap_proto,
+ __u16 l2_proto)
{
+ __u16 udp_dst = UDP_PORT;
struct ipv6hdr iph_inner;
- struct grev6hdr h_outer;
+ struct v6hdr h_outer;
struct tcphdr tcph;
+ int olen, l2_len;
+ __u16 tot_len;
__u64 flags;
- int olen;
if (bpf_skb_load_bytes(skb, ETH_HLEN, &iph_inner,
sizeof(iph_inner)) < 0)
if (tcph.dest != __bpf_constant_htons(cfg_port))
return TC_ACT_OK;
+ olen = sizeof(h_outer.ip);
+ l2_len = 0;
+
flags = BPF_F_ADJ_ROOM_FIXED_GSO | BPF_F_ADJ_ROOM_ENCAP_L3_IPV6;
- if (with_gre) {
+
+ switch (l2_proto) {
+ case ETH_P_MPLS_UC:
+ l2_len = sizeof(mpls_label);
+ udp_dst = MPLS_OVER_UDP_PORT;
+ break;
+ case ETH_P_TEB:
+ l2_len = ETH_HLEN;
+ udp_dst = ETH_OVER_UDP_PORT;
+ break;
+ }
+ flags |= BPF_F_ADJ_ROOM_ENCAP_L2(l2_len);
+
+ switch (encap_proto) {
+ case IPPROTO_GRE:
flags |= BPF_F_ADJ_ROOM_ENCAP_L4_GRE;
- olen = sizeof(h_outer);
- } else {
- olen = sizeof(h_outer.ip);
+ olen += sizeof(h_outer.l4hdr.gre);
+ h_outer.l4hdr.gre.protocol = bpf_htons(l2_proto);
+ h_outer.l4hdr.gre.flags = 0;
+ break;
+ case IPPROTO_UDP:
+ flags |= BPF_F_ADJ_ROOM_ENCAP_L4_UDP;
+ olen += sizeof(h_outer.l4hdr.udp);
+ h_outer.l4hdr.udp.source = __bpf_constant_htons(cfg_udp_src);
+ h_outer.l4hdr.udp.dest = bpf_htons(udp_dst);
+ tot_len = bpf_ntohs(iph_inner.payload_len) + sizeof(iph_inner) +
+ sizeof(h_outer.l4hdr.udp);
+ h_outer.l4hdr.udp.check = 0;
+ h_outer.l4hdr.udp.len = bpf_htons(tot_len);
+ break;
+ case IPPROTO_IPV6:
+ break;
+ default:
+ return TC_ACT_OK;
}
+ /* add L2 encap (if specified) */
+ switch (l2_proto) {
+ case ETH_P_MPLS_UC:
+ *((__u32 *)((__u8 *)&h_outer + olen)) = mpls_label;
+ break;
+ case ETH_P_TEB:
+ if (bpf_skb_load_bytes(skb, 0, (__u8 *)&h_outer + olen,
+ ETH_HLEN))
+ return TC_ACT_SHOT;
+ break;
+ }
+ olen += l2_len;
/* add room between mac and network header */
if (bpf_skb_adjust_room(skb, olen, BPF_ADJ_ROOM_MAC, flags))
h_outer.ip = iph_inner;
h_outer.ip.payload_len = bpf_htons(olen +
bpf_ntohs(h_outer.ip.payload_len));
- if (with_gre) {
- h_outer.ip.nexthdr = IPPROTO_GRE;
- h_outer.protocol = bpf_htons(ETH_P_IPV6);
- h_outer.flags = 0;
- } else {
- h_outer.ip.nexthdr = IPPROTO_IPV6;
- }
+
+ h_outer.ip.nexthdr = encap_proto;
/* store new outer network header */
if (bpf_skb_store_bytes(skb, ETH_HLEN, &h_outer, olen,
return TC_ACT_OK;
}
-SEC("encap_ipip")
-int __encap_ipip(struct __sk_buff *skb)
+SEC("encap_ipip_none")
+int __encap_ipip_none(struct __sk_buff *skb)
{
if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
- return encap_ipv4(skb, false);
+ return encap_ipv4(skb, IPPROTO_IPIP, ETH_P_IP);
else
return TC_ACT_OK;
}
-SEC("encap_gre")
-int __encap_gre(struct __sk_buff *skb)
+SEC("encap_gre_none")
+int __encap_gre_none(struct __sk_buff *skb)
{
if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
- return encap_ipv4(skb, true);
+ return encap_ipv4(skb, IPPROTO_GRE, ETH_P_IP);
else
return TC_ACT_OK;
}
-SEC("encap_ip6tnl")
-int __encap_ip6tnl(struct __sk_buff *skb)
+SEC("encap_gre_mpls")
+int __encap_gre_mpls(struct __sk_buff *skb)
+{
+ if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
+ return encap_ipv4(skb, IPPROTO_GRE, ETH_P_MPLS_UC);
+ else
+ return TC_ACT_OK;
+}
+
+SEC("encap_gre_eth")
+int __encap_gre_eth(struct __sk_buff *skb)
+{
+ if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
+ return encap_ipv4(skb, IPPROTO_GRE, ETH_P_TEB);
+ else
+ return TC_ACT_OK;
+}
+
+SEC("encap_udp_none")
+int __encap_udp_none(struct __sk_buff *skb)
+{
+ if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
+ return encap_ipv4(skb, IPPROTO_UDP, ETH_P_IP);
+ else
+ return TC_ACT_OK;
+}
+
+SEC("encap_udp_mpls")
+int __encap_udp_mpls(struct __sk_buff *skb)
+{
+ if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
+ return encap_ipv4(skb, IPPROTO_UDP, ETH_P_MPLS_UC);
+ else
+ return TC_ACT_OK;
+}
+
+SEC("encap_udp_eth")
+int __encap_udp_eth(struct __sk_buff *skb)
+{
+ if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
+ return encap_ipv4(skb, IPPROTO_UDP, ETH_P_TEB);
+ else
+ return TC_ACT_OK;
+}
+
+SEC("encap_ip6tnl_none")
+int __encap_ip6tnl_none(struct __sk_buff *skb)
{
if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
- return encap_ipv6(skb, false);
+ return encap_ipv6(skb, IPPROTO_IPV6, ETH_P_IPV6);
else
return TC_ACT_OK;
}
-SEC("encap_ip6gre")
-int __encap_ip6gre(struct __sk_buff *skb)
+SEC("encap_ip6gre_none")
+int __encap_ip6gre_none(struct __sk_buff *skb)
{
if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
- return encap_ipv6(skb, true);
+ return encap_ipv6(skb, IPPROTO_GRE, ETH_P_IPV6);
+ else
+ return TC_ACT_OK;
+}
+
+SEC("encap_ip6gre_mpls")
+int __encap_ip6gre_mpls(struct __sk_buff *skb)
+{
+ if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
+ return encap_ipv6(skb, IPPROTO_GRE, ETH_P_MPLS_UC);
+ else
+ return TC_ACT_OK;
+}
+
+SEC("encap_ip6gre_eth")
+int __encap_ip6gre_eth(struct __sk_buff *skb)
+{
+ if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
+ return encap_ipv6(skb, IPPROTO_GRE, ETH_P_TEB);
+ else
+ return TC_ACT_OK;
+}
+
+SEC("encap_ip6udp_none")
+int __encap_ip6udp_none(struct __sk_buff *skb)
+{
+ if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
+ return encap_ipv6(skb, IPPROTO_UDP, ETH_P_IPV6);
+ else
+ return TC_ACT_OK;
+}
+
+SEC("encap_ip6udp_mpls")
+int __encap_ip6udp_mpls(struct __sk_buff *skb)
+{
+ if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
+ return encap_ipv6(skb, IPPROTO_UDP, ETH_P_MPLS_UC);
+ else
+ return TC_ACT_OK;
+}
+
+SEC("encap_ip6udp_eth")
+int __encap_ip6udp_eth(struct __sk_buff *skb)
+{
+ if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
+ return encap_ipv6(skb, IPPROTO_UDP, ETH_P_TEB);
else
return TC_ACT_OK;
}
static int decap_internal(struct __sk_buff *skb, int off, int len, char proto)
{
- char buf[sizeof(struct grev6hdr)];
- int olen;
+ char buf[sizeof(struct v6hdr)];
+ struct gre_hdr greh;
+ struct udphdr udph;
+ int olen = len;
switch (proto) {
case IPPROTO_IPIP:
case IPPROTO_IPV6:
- olen = len;
break;
case IPPROTO_GRE:
- olen = len + 4 /* gre hdr */;
+ olen += sizeof(struct gre_hdr);
+ if (bpf_skb_load_bytes(skb, off + len, &greh, sizeof(greh)) < 0)
+ return TC_ACT_OK;
+ switch (bpf_ntohs(greh.protocol)) {
+ case ETH_P_MPLS_UC:
+ olen += sizeof(mpls_label);
+ break;
+ case ETH_P_TEB:
+ olen += ETH_HLEN;
+ break;
+ }
+ break;
+ case IPPROTO_UDP:
+ olen += sizeof(struct udphdr);
+ if (bpf_skb_load_bytes(skb, off + len, &udph, sizeof(udph)) < 0)
+ return TC_ACT_OK;
+ switch (bpf_ntohs(udph.dest)) {
+ case MPLS_OVER_UDP_PORT:
+ olen += sizeof(mpls_label);
+ break;
+ case ETH_OVER_UDP_PORT:
+ olen += ETH_HLEN;
+ break;
+ }
break;
default:
return TC_ACT_OK;
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+#define ATTR __attribute__((noinline))
+#include "test_jhash.h"
+
+SEC("scale90_noinline")
+int balancer_ingress(struct __sk_buff *ctx)
+{
+ void *data_end = (void *)(long)ctx->data_end;
+ void *data = (void *)(long)ctx->data;
+ void *ptr;
+ int ret = 0, nh_off, i = 0;
+
+ nh_off = 14;
+
+ /* pragma unroll doesn't work on large loops */
+
+#define C do { \
+ ptr = data + i; \
+ if (ptr + nh_off > data_end) \
+ break; \
+ ctx->tc_index = jhash(ptr, nh_off, ctx->cb[0] + i++); \
+ } while (0);
+#define C30 C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;
+ C30;C30;C30; /* 90 calls */
+ return 0;
+}
+char _license[] SEC("license") = "GPL";
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+#define ATTR __attribute__((always_inline))
+#include "test_jhash.h"
+
+SEC("scale90_inline")
+int balancer_ingress(struct __sk_buff *ctx)
+{
+ void *data_end = (void *)(long)ctx->data_end;
+ void *data = (void *)(long)ctx->data;
+ void *ptr;
+ int ret = 0, nh_off, i = 0;
+
+ nh_off = 14;
+
+ /* pragma unroll doesn't work on large loops */
+
+#define C do { \
+ ptr = data + i; \
+ if (ptr + nh_off > data_end) \
+ break; \
+ ctx->tc_index = jhash(ptr, nh_off, ctx->cb[0] + i++); \
+ } while (0);
+#define C30 C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;
+ C30;C30;C30; /* 90 calls */
+ return 0;
+}
+char _license[] SEC("license") = "GPL";
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+#define ATTR __attribute__((noinline))
+#include "test_jhash.h"
+
+SEC("scale90_noinline32")
+int balancer_ingress(struct __sk_buff *ctx)
+{
+ void *data_end = (void *)(long)ctx->data_end;
+ void *data = (void *)(long)ctx->data;
+ void *ptr;
+ int ret = 0, nh_off, i = 0;
+
+ nh_off = 32;
+
+ /* pragma unroll doesn't work on large loops */
+
+#define C do { \
+ ptr = data + i; \
+ if (ptr + nh_off > data_end) \
+ break; \
+ ctx->tc_index = jhash(ptr, nh_off, ctx->cb[0] + i++); \
+ } while (0);
+#define C30 C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;
+ C30;C30;C30; /* 90 calls */
+ return 0;
+}
+char _license[] SEC("license") = "GPL";
#define BTF_UNION_ENC(name, nr_elems, sz) \
BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_UNION, 0, nr_elems), sz)
+#define BTF_VAR_ENC(name, type, linkage) \
+ BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), type), (linkage)
+#define BTF_VAR_SECINFO_ENC(type, offset, size) \
+ (type), (offset), (size)
+
#define BTF_MEMBER_ENC(name, type, bits_offset) \
(name), (type), (bits_offset)
#define BTF_ENUM_ENC(name, val) (name), (val)
.value_type_id = 3,
.max_entries = 4,
},
-
{
.descr = "struct test #3 Invalid member offset",
.raw_types = {
.btf_load_err = true,
.err_str = "Invalid member bits_offset",
},
-
+/*
+ * struct A {
+ * unsigned long long m;
+ * int n;
+ * char o;
+ * [3 bytes hole]
+ * int p[8];
+ * };
+ */
+{
+ .descr = "global data test #1",
+ .raw_types = {
+ /* int */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ /* unsigned long long */
+ BTF_TYPE_INT_ENC(0, 0, 0, 64, 8), /* [2] */
+ /* char */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 8, 1), /* [3] */
+ /* int[8] */
+ BTF_TYPE_ARRAY_ENC(1, 1, 8), /* [4] */
+ /* struct A { */ /* [5] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 4), 48),
+ BTF_MEMBER_ENC(NAME_TBD, 2, 0), /* unsigned long long m;*/
+ BTF_MEMBER_ENC(NAME_TBD, 1, 64),/* int n; */
+ BTF_MEMBER_ENC(NAME_TBD, 3, 96),/* char o; */
+ BTF_MEMBER_ENC(NAME_TBD, 4, 128),/* int p[8] */
+ /* } */
+ BTF_END_RAW,
+ },
+ .str_sec = "\0A\0m\0n\0o\0p",
+ .str_sec_size = sizeof("\0A\0m\0n\0o\0p"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "struct_test1_map",
+ .key_size = sizeof(int),
+ .value_size = 48,
+ .key_type_id = 1,
+ .value_type_id = 5,
+ .max_entries = 4,
+},
+/*
+ * struct A {
+ * unsigned long long m;
+ * int n;
+ * char o;
+ * [3 bytes hole]
+ * int p[8];
+ * };
+ * static struct A t; <- in .bss
+ */
+{
+ .descr = "global data test #2",
+ .raw_types = {
+ /* int */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ /* unsigned long long */
+ BTF_TYPE_INT_ENC(0, 0, 0, 64, 8), /* [2] */
+ /* char */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 8, 1), /* [3] */
+ /* int[8] */
+ BTF_TYPE_ARRAY_ENC(1, 1, 8), /* [4] */
+ /* struct A { */ /* [5] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 4), 48),
+ BTF_MEMBER_ENC(NAME_TBD, 2, 0), /* unsigned long long m;*/
+ BTF_MEMBER_ENC(NAME_TBD, 1, 64),/* int n; */
+ BTF_MEMBER_ENC(NAME_TBD, 3, 96),/* char o; */
+ BTF_MEMBER_ENC(NAME_TBD, 4, 128),/* int p[8] */
+ /* } */
+ /* static struct A t */
+ BTF_VAR_ENC(NAME_TBD, 5, 0), /* [6] */
+ /* .bss section */ /* [7] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 48),
+ BTF_VAR_SECINFO_ENC(6, 0, 48),
+ BTF_END_RAW,
+ },
+ .str_sec = "\0A\0m\0n\0o\0p\0t\0.bss",
+ .str_sec_size = sizeof("\0A\0m\0n\0o\0p\0t\0.bss"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = ".bss",
+ .key_size = sizeof(int),
+ .value_size = 48,
+ .key_type_id = 0,
+ .value_type_id = 7,
+ .max_entries = 1,
+},
+{
+ .descr = "global data test #3",
+ .raw_types = {
+ /* int */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ /* static int t */
+ BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */
+ /* .bss section */ /* [3] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4),
+ BTF_VAR_SECINFO_ENC(2, 0, 4),
+ BTF_END_RAW,
+ },
+ .str_sec = "\0t\0.bss",
+ .str_sec_size = sizeof("\0t\0.bss"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = ".bss",
+ .key_size = sizeof(int),
+ .value_size = 4,
+ .key_type_id = 0,
+ .value_type_id = 3,
+ .max_entries = 1,
+},
+{
+ .descr = "global data test #4, unsupported linkage",
+ .raw_types = {
+ /* int */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ /* static int t */
+ BTF_VAR_ENC(NAME_TBD, 1, 2), /* [2] */
+ /* .bss section */ /* [3] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4),
+ BTF_VAR_SECINFO_ENC(2, 0, 4),
+ BTF_END_RAW,
+ },
+ .str_sec = "\0t\0.bss",
+ .str_sec_size = sizeof("\0t\0.bss"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = ".bss",
+ .key_size = sizeof(int),
+ .value_size = 4,
+ .key_type_id = 0,
+ .value_type_id = 3,
+ .max_entries = 1,
+ .btf_load_err = true,
+ .err_str = "Linkage not supported",
+},
+{
+ .descr = "global data test #5, invalid var type",
+ .raw_types = {
+ /* static void t */
+ BTF_VAR_ENC(NAME_TBD, 0, 0), /* [1] */
+ /* .bss section */ /* [2] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4),
+ BTF_VAR_SECINFO_ENC(1, 0, 4),
+ BTF_END_RAW,
+ },
+ .str_sec = "\0t\0.bss",
+ .str_sec_size = sizeof("\0t\0.bss"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = ".bss",
+ .key_size = sizeof(int),
+ .value_size = 4,
+ .key_type_id = 0,
+ .value_type_id = 2,
+ .max_entries = 1,
+ .btf_load_err = true,
+ .err_str = "Invalid type_id",
+},
+{
+ .descr = "global data test #6, invalid var type (fwd type)",
+ .raw_types = {
+ /* union A */
+ BTF_TYPE_ENC(NAME_TBD,
+ BTF_INFO_ENC(BTF_KIND_FWD, 1, 0), 0), /* [1] */
+ /* static union A t */
+ BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */
+ /* .bss section */ /* [3] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4),
+ BTF_VAR_SECINFO_ENC(2, 0, 4),
+ BTF_END_RAW,
+ },
+ .str_sec = "\0A\0t\0.bss",
+ .str_sec_size = sizeof("\0A\0t\0.bss"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = ".bss",
+ .key_size = sizeof(int),
+ .value_size = 4,
+ .key_type_id = 0,
+ .value_type_id = 2,
+ .max_entries = 1,
+ .btf_load_err = true,
+ .err_str = "Invalid type",
+},
+{
+ .descr = "global data test #7, invalid var type (fwd type)",
+ .raw_types = {
+ /* union A */
+ BTF_TYPE_ENC(NAME_TBD,
+ BTF_INFO_ENC(BTF_KIND_FWD, 1, 0), 0), /* [1] */
+ /* static union A t */
+ BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */
+ /* .bss section */ /* [3] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4),
+ BTF_VAR_SECINFO_ENC(1, 0, 4),
+ BTF_END_RAW,
+ },
+ .str_sec = "\0A\0t\0.bss",
+ .str_sec_size = sizeof("\0A\0t\0.bss"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = ".bss",
+ .key_size = sizeof(int),
+ .value_size = 4,
+ .key_type_id = 0,
+ .value_type_id = 2,
+ .max_entries = 1,
+ .btf_load_err = true,
+ .err_str = "Invalid type",
+},
+{
+ .descr = "global data test #8, invalid var size",
+ .raw_types = {
+ /* int */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ /* unsigned long long */
+ BTF_TYPE_INT_ENC(0, 0, 0, 64, 8), /* [2] */
+ /* char */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 8, 1), /* [3] */
+ /* int[8] */
+ BTF_TYPE_ARRAY_ENC(1, 1, 8), /* [4] */
+ /* struct A { */ /* [5] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 4), 48),
+ BTF_MEMBER_ENC(NAME_TBD, 2, 0), /* unsigned long long m;*/
+ BTF_MEMBER_ENC(NAME_TBD, 1, 64),/* int n; */
+ BTF_MEMBER_ENC(NAME_TBD, 3, 96),/* char o; */
+ BTF_MEMBER_ENC(NAME_TBD, 4, 128),/* int p[8] */
+ /* } */
+ /* static struct A t */
+ BTF_VAR_ENC(NAME_TBD, 5, 0), /* [6] */
+ /* .bss section */ /* [7] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 48),
+ BTF_VAR_SECINFO_ENC(6, 0, 47),
+ BTF_END_RAW,
+ },
+ .str_sec = "\0A\0m\0n\0o\0p\0t\0.bss",
+ .str_sec_size = sizeof("\0A\0m\0n\0o\0p\0t\0.bss"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = ".bss",
+ .key_size = sizeof(int),
+ .value_size = 48,
+ .key_type_id = 0,
+ .value_type_id = 7,
+ .max_entries = 1,
+ .btf_load_err = true,
+ .err_str = "Invalid size",
+},
+{
+ .descr = "global data test #9, invalid var size",
+ .raw_types = {
+ /* int */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ /* unsigned long long */
+ BTF_TYPE_INT_ENC(0, 0, 0, 64, 8), /* [2] */
+ /* char */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 8, 1), /* [3] */
+ /* int[8] */
+ BTF_TYPE_ARRAY_ENC(1, 1, 8), /* [4] */
+ /* struct A { */ /* [5] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 4), 48),
+ BTF_MEMBER_ENC(NAME_TBD, 2, 0), /* unsigned long long m;*/
+ BTF_MEMBER_ENC(NAME_TBD, 1, 64),/* int n; */
+ BTF_MEMBER_ENC(NAME_TBD, 3, 96),/* char o; */
+ BTF_MEMBER_ENC(NAME_TBD, 4, 128),/* int p[8] */
+ /* } */
+ /* static struct A t */
+ BTF_VAR_ENC(NAME_TBD, 5, 0), /* [6] */
+ /* .bss section */ /* [7] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 46),
+ BTF_VAR_SECINFO_ENC(6, 0, 48),
+ BTF_END_RAW,
+ },
+ .str_sec = "\0A\0m\0n\0o\0p\0t\0.bss",
+ .str_sec_size = sizeof("\0A\0m\0n\0o\0p\0t\0.bss"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = ".bss",
+ .key_size = sizeof(int),
+ .value_size = 48,
+ .key_type_id = 0,
+ .value_type_id = 7,
+ .max_entries = 1,
+ .btf_load_err = true,
+ .err_str = "Invalid size",
+},
+{
+ .descr = "global data test #10, invalid var size",
+ .raw_types = {
+ /* int */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ /* unsigned long long */
+ BTF_TYPE_INT_ENC(0, 0, 0, 64, 8), /* [2] */
+ /* char */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 8, 1), /* [3] */
+ /* int[8] */
+ BTF_TYPE_ARRAY_ENC(1, 1, 8), /* [4] */
+ /* struct A { */ /* [5] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 4), 48),
+ BTF_MEMBER_ENC(NAME_TBD, 2, 0), /* unsigned long long m;*/
+ BTF_MEMBER_ENC(NAME_TBD, 1, 64),/* int n; */
+ BTF_MEMBER_ENC(NAME_TBD, 3, 96),/* char o; */
+ BTF_MEMBER_ENC(NAME_TBD, 4, 128),/* int p[8] */
+ /* } */
+ /* static struct A t */
+ BTF_VAR_ENC(NAME_TBD, 5, 0), /* [6] */
+ /* .bss section */ /* [7] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 46),
+ BTF_VAR_SECINFO_ENC(6, 0, 46),
+ BTF_END_RAW,
+ },
+ .str_sec = "\0A\0m\0n\0o\0p\0t\0.bss",
+ .str_sec_size = sizeof("\0A\0m\0n\0o\0p\0t\0.bss"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = ".bss",
+ .key_size = sizeof(int),
+ .value_size = 48,
+ .key_type_id = 0,
+ .value_type_id = 7,
+ .max_entries = 1,
+ .btf_load_err = true,
+ .err_str = "Invalid size",
+},
+{
+ .descr = "global data test #11, multiple section members",
+ .raw_types = {
+ /* int */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ /* unsigned long long */
+ BTF_TYPE_INT_ENC(0, 0, 0, 64, 8), /* [2] */
+ /* char */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 8, 1), /* [3] */
+ /* int[8] */
+ BTF_TYPE_ARRAY_ENC(1, 1, 8), /* [4] */
+ /* struct A { */ /* [5] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 4), 48),
+ BTF_MEMBER_ENC(NAME_TBD, 2, 0), /* unsigned long long m;*/
+ BTF_MEMBER_ENC(NAME_TBD, 1, 64),/* int n; */
+ BTF_MEMBER_ENC(NAME_TBD, 3, 96),/* char o; */
+ BTF_MEMBER_ENC(NAME_TBD, 4, 128),/* int p[8] */
+ /* } */
+ /* static struct A t */
+ BTF_VAR_ENC(NAME_TBD, 5, 0), /* [6] */
+ /* static int u */
+ BTF_VAR_ENC(NAME_TBD, 1, 0), /* [7] */
+ /* .bss section */ /* [8] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 2), 62),
+ BTF_VAR_SECINFO_ENC(6, 10, 48),
+ BTF_VAR_SECINFO_ENC(7, 58, 4),
+ BTF_END_RAW,
+ },
+ .str_sec = "\0A\0m\0n\0o\0p\0t\0u\0.bss",
+ .str_sec_size = sizeof("\0A\0m\0n\0o\0p\0t\0u\0.bss"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = ".bss",
+ .key_size = sizeof(int),
+ .value_size = 62,
+ .key_type_id = 0,
+ .value_type_id = 8,
+ .max_entries = 1,
+},
+{
+ .descr = "global data test #12, invalid offset",
+ .raw_types = {
+ /* int */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ /* unsigned long long */
+ BTF_TYPE_INT_ENC(0, 0, 0, 64, 8), /* [2] */
+ /* char */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 8, 1), /* [3] */
+ /* int[8] */
+ BTF_TYPE_ARRAY_ENC(1, 1, 8), /* [4] */
+ /* struct A { */ /* [5] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 4), 48),
+ BTF_MEMBER_ENC(NAME_TBD, 2, 0), /* unsigned long long m;*/
+ BTF_MEMBER_ENC(NAME_TBD, 1, 64),/* int n; */
+ BTF_MEMBER_ENC(NAME_TBD, 3, 96),/* char o; */
+ BTF_MEMBER_ENC(NAME_TBD, 4, 128),/* int p[8] */
+ /* } */
+ /* static struct A t */
+ BTF_VAR_ENC(NAME_TBD, 5, 0), /* [6] */
+ /* static int u */
+ BTF_VAR_ENC(NAME_TBD, 1, 0), /* [7] */
+ /* .bss section */ /* [8] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 2), 62),
+ BTF_VAR_SECINFO_ENC(6, 10, 48),
+ BTF_VAR_SECINFO_ENC(7, 60, 4),
+ BTF_END_RAW,
+ },
+ .str_sec = "\0A\0m\0n\0o\0p\0t\0u\0.bss",
+ .str_sec_size = sizeof("\0A\0m\0n\0o\0p\0t\0u\0.bss"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = ".bss",
+ .key_size = sizeof(int),
+ .value_size = 62,
+ .key_type_id = 0,
+ .value_type_id = 8,
+ .max_entries = 1,
+ .btf_load_err = true,
+ .err_str = "Invalid offset+size",
+},
+{
+ .descr = "global data test #13, invalid offset",
+ .raw_types = {
+ /* int */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ /* unsigned long long */
+ BTF_TYPE_INT_ENC(0, 0, 0, 64, 8), /* [2] */
+ /* char */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 8, 1), /* [3] */
+ /* int[8] */
+ BTF_TYPE_ARRAY_ENC(1, 1, 8), /* [4] */
+ /* struct A { */ /* [5] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 4), 48),
+ BTF_MEMBER_ENC(NAME_TBD, 2, 0), /* unsigned long long m;*/
+ BTF_MEMBER_ENC(NAME_TBD, 1, 64),/* int n; */
+ BTF_MEMBER_ENC(NAME_TBD, 3, 96),/* char o; */
+ BTF_MEMBER_ENC(NAME_TBD, 4, 128),/* int p[8] */
+ /* } */
+ /* static struct A t */
+ BTF_VAR_ENC(NAME_TBD, 5, 0), /* [6] */
+ /* static int u */
+ BTF_VAR_ENC(NAME_TBD, 1, 0), /* [7] */
+ /* .bss section */ /* [8] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 2), 62),
+ BTF_VAR_SECINFO_ENC(6, 10, 48),
+ BTF_VAR_SECINFO_ENC(7, 12, 4),
+ BTF_END_RAW,
+ },
+ .str_sec = "\0A\0m\0n\0o\0p\0t\0u\0.bss",
+ .str_sec_size = sizeof("\0A\0m\0n\0o\0p\0t\0u\0.bss"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = ".bss",
+ .key_size = sizeof(int),
+ .value_size = 62,
+ .key_type_id = 0,
+ .value_type_id = 8,
+ .max_entries = 1,
+ .btf_load_err = true,
+ .err_str = "Invalid offset",
+},
+{
+ .descr = "global data test #14, invalid offset",
+ .raw_types = {
+ /* int */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ /* unsigned long long */
+ BTF_TYPE_INT_ENC(0, 0, 0, 64, 8), /* [2] */
+ /* char */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 8, 1), /* [3] */
+ /* int[8] */
+ BTF_TYPE_ARRAY_ENC(1, 1, 8), /* [4] */
+ /* struct A { */ /* [5] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 4), 48),
+ BTF_MEMBER_ENC(NAME_TBD, 2, 0), /* unsigned long long m;*/
+ BTF_MEMBER_ENC(NAME_TBD, 1, 64),/* int n; */
+ BTF_MEMBER_ENC(NAME_TBD, 3, 96),/* char o; */
+ BTF_MEMBER_ENC(NAME_TBD, 4, 128),/* int p[8] */
+ /* } */
+ /* static struct A t */
+ BTF_VAR_ENC(NAME_TBD, 5, 0), /* [6] */
+ /* static int u */
+ BTF_VAR_ENC(NAME_TBD, 1, 0), /* [7] */
+ /* .bss section */ /* [8] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 2), 62),
+ BTF_VAR_SECINFO_ENC(7, 58, 4),
+ BTF_VAR_SECINFO_ENC(6, 10, 48),
+ BTF_END_RAW,
+ },
+ .str_sec = "\0A\0m\0n\0o\0p\0t\0u\0.bss",
+ .str_sec_size = sizeof("\0A\0m\0n\0o\0p\0t\0u\0.bss"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = ".bss",
+ .key_size = sizeof(int),
+ .value_size = 62,
+ .key_type_id = 0,
+ .value_type_id = 8,
+ .max_entries = 1,
+ .btf_load_err = true,
+ .err_str = "Invalid offset",
+},
+{
+ .descr = "global data test #15, not var kind",
+ .raw_types = {
+ /* int */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */
+ /* .bss section */ /* [3] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4),
+ BTF_VAR_SECINFO_ENC(1, 0, 4),
+ BTF_END_RAW,
+ },
+ .str_sec = "\0A\0t\0.bss",
+ .str_sec_size = sizeof("\0A\0t\0.bss"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = ".bss",
+ .key_size = sizeof(int),
+ .value_size = 4,
+ .key_type_id = 0,
+ .value_type_id = 3,
+ .max_entries = 1,
+ .btf_load_err = true,
+ .err_str = "Not a VAR kind member",
+},
+{
+ .descr = "global data test #16, invalid var referencing sec",
+ .raw_types = {
+ /* int */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_VAR_ENC(NAME_TBD, 5, 0), /* [2] */
+ BTF_VAR_ENC(NAME_TBD, 2, 0), /* [3] */
+ /* a section */ /* [4] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4),
+ BTF_VAR_SECINFO_ENC(3, 0, 4),
+ /* a section */ /* [5] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4),
+ BTF_VAR_SECINFO_ENC(6, 0, 4),
+ BTF_VAR_ENC(NAME_TBD, 1, 0), /* [6] */
+ BTF_END_RAW,
+ },
+ .str_sec = "\0A\0t\0s\0a\0a",
+ .str_sec_size = sizeof("\0A\0t\0s\0a\0a"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = ".bss",
+ .key_size = sizeof(int),
+ .value_size = 4,
+ .key_type_id = 0,
+ .value_type_id = 4,
+ .max_entries = 1,
+ .btf_load_err = true,
+ .err_str = "Invalid type_id",
+},
+{
+ .descr = "global data test #17, invalid var referencing var",
+ .raw_types = {
+ /* int */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */
+ BTF_VAR_ENC(NAME_TBD, 2, 0), /* [3] */
+ /* a section */ /* [4] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4),
+ BTF_VAR_SECINFO_ENC(3, 0, 4),
+ BTF_END_RAW,
+ },
+ .str_sec = "\0A\0t\0s\0a\0a",
+ .str_sec_size = sizeof("\0A\0t\0s\0a\0a"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = ".bss",
+ .key_size = sizeof(int),
+ .value_size = 4,
+ .key_type_id = 0,
+ .value_type_id = 4,
+ .max_entries = 1,
+ .btf_load_err = true,
+ .err_str = "Invalid type_id",
+},
+{
+ .descr = "global data test #18, invalid var loop",
+ .raw_types = {
+ /* int */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_VAR_ENC(NAME_TBD, 2, 0), /* [2] */
+ /* .bss section */ /* [3] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4),
+ BTF_VAR_SECINFO_ENC(2, 0, 4),
+ BTF_END_RAW,
+ },
+ .str_sec = "\0A\0t\0aaa",
+ .str_sec_size = sizeof("\0A\0t\0aaa"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = ".bss",
+ .key_size = sizeof(int),
+ .value_size = 4,
+ .key_type_id = 0,
+ .value_type_id = 4,
+ .max_entries = 1,
+ .btf_load_err = true,
+ .err_str = "Invalid type_id",
+},
+{
+ .descr = "global data test #19, invalid var referencing var",
+ .raw_types = {
+ /* int */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_VAR_ENC(NAME_TBD, 3, 0), /* [2] */
+ BTF_VAR_ENC(NAME_TBD, 1, 0), /* [3] */
+ BTF_END_RAW,
+ },
+ .str_sec = "\0A\0t\0s\0a\0a",
+ .str_sec_size = sizeof("\0A\0t\0s\0a\0a"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = ".bss",
+ .key_size = sizeof(int),
+ .value_size = 4,
+ .key_type_id = 0,
+ .value_type_id = 4,
+ .max_entries = 1,
+ .btf_load_err = true,
+ .err_str = "Invalid type_id",
+},
+{
+ .descr = "global data test #20, invalid ptr referencing var",
+ .raw_types = {
+ /* int */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ /* PTR type_id=3 */ /* [2] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 3),
+ BTF_VAR_ENC(NAME_TBD, 1, 0), /* [3] */
+ BTF_END_RAW,
+ },
+ .str_sec = "\0A\0t\0s\0a\0a",
+ .str_sec_size = sizeof("\0A\0t\0s\0a\0a"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = ".bss",
+ .key_size = sizeof(int),
+ .value_size = 4,
+ .key_type_id = 0,
+ .value_type_id = 4,
+ .max_entries = 1,
+ .btf_load_err = true,
+ .err_str = "Invalid type_id",
+},
+{
+ .descr = "global data test #21, var included in struct",
+ .raw_types = {
+ /* int */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ /* struct A { */ /* [2] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), sizeof(int) * 2),
+ BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int m; */
+ BTF_MEMBER_ENC(NAME_TBD, 3, 32),/* VAR type_id=3; */
+ /* } */
+ BTF_VAR_ENC(NAME_TBD, 1, 0), /* [3] */
+ BTF_END_RAW,
+ },
+ .str_sec = "\0A\0t\0s\0a\0a",
+ .str_sec_size = sizeof("\0A\0t\0s\0a\0a"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = ".bss",
+ .key_size = sizeof(int),
+ .value_size = 4,
+ .key_type_id = 0,
+ .value_type_id = 4,
+ .max_entries = 1,
+ .btf_load_err = true,
+ .err_str = "Invalid member",
+},
+{
+ .descr = "global data test #22, array of var",
+ .raw_types = {
+ /* int */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_TYPE_ARRAY_ENC(3, 1, 4), /* [2] */
+ BTF_VAR_ENC(NAME_TBD, 1, 0), /* [3] */
+ BTF_END_RAW,
+ },
+ .str_sec = "\0A\0t\0s\0a\0a",
+ .str_sec_size = sizeof("\0A\0t\0s\0a\0a"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = ".bss",
+ .key_size = sizeof(int),
+ .value_size = 4,
+ .key_type_id = 0,
+ .value_type_id = 4,
+ .max_entries = 1,
+ .btf_load_err = true,
+ .err_str = "Invalid elem",
+},
/* Test member exceeds the size of struct.
*
* struct A {
} aenum;
uint32_t ui32b;
uint32_t bits2c:2;
+ uint8_t si8_4[2][2];
};
#ifdef __SIZEOF_INT128__
BTF_ENUM_ENC(NAME_TBD, 2),
BTF_ENUM_ENC(NAME_TBD, 3),
/* struct pprint_mapv */ /* [16] */
- BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 10), 40),
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 11), 40),
BTF_MEMBER_ENC(NAME_TBD, 11, 0), /* uint32_t ui32 */
BTF_MEMBER_ENC(NAME_TBD, 10, 32), /* uint16_t ui16 */
BTF_MEMBER_ENC(NAME_TBD, 12, 64), /* int32_t si32 */
BTF_MEMBER_ENC(NAME_TBD, 15, 192), /* aenum */
BTF_MEMBER_ENC(NAME_TBD, 11, 224), /* uint32_t ui32b */
BTF_MEMBER_ENC(NAME_TBD, 6, 256), /* bits2c */
+ BTF_MEMBER_ENC(NAME_TBD, 17, 264), /* si8_4 */
+ BTF_TYPE_ARRAY_ENC(18, 1, 2), /* [17] */
+ BTF_TYPE_ARRAY_ENC(1, 1, 2), /* [18] */
BTF_END_RAW,
},
- BTF_STR_SEC("\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum\0ui32b\0bits2c"),
+ BTF_STR_SEC("\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum\0ui32b\0bits2c\0si8_4"),
.key_size = sizeof(unsigned int),
.value_size = sizeof(struct pprint_mapv),
.key_type_id = 3, /* unsigned int */
BTF_ENUM_ENC(NAME_TBD, 2),
BTF_ENUM_ENC(NAME_TBD, 3),
/* struct pprint_mapv */ /* [16] */
- BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 10), 40),
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 11), 40),
BTF_MEMBER_ENC(NAME_TBD, 11, BTF_MEMBER_OFFSET(0, 0)), /* uint32_t ui32 */
BTF_MEMBER_ENC(NAME_TBD, 10, BTF_MEMBER_OFFSET(0, 32)), /* uint16_t ui16 */
BTF_MEMBER_ENC(NAME_TBD, 12, BTF_MEMBER_OFFSET(0, 64)), /* int32_t si32 */
BTF_MEMBER_ENC(NAME_TBD, 15, BTF_MEMBER_OFFSET(0, 192)), /* aenum */
BTF_MEMBER_ENC(NAME_TBD, 11, BTF_MEMBER_OFFSET(0, 224)), /* uint32_t ui32b */
BTF_MEMBER_ENC(NAME_TBD, 6, BTF_MEMBER_OFFSET(2, 256)), /* bits2c */
+ BTF_MEMBER_ENC(NAME_TBD, 17, 264), /* si8_4 */
+ BTF_TYPE_ARRAY_ENC(18, 1, 2), /* [17] */
+ BTF_TYPE_ARRAY_ENC(1, 1, 2), /* [18] */
BTF_END_RAW,
},
- BTF_STR_SEC("\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum\0ui32b\0bits2c"),
+ BTF_STR_SEC("\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum\0ui32b\0bits2c\0si8_4"),
.key_size = sizeof(unsigned int),
.value_size = sizeof(struct pprint_mapv),
.key_type_id = 3, /* unsigned int */
BTF_ENUM_ENC(NAME_TBD, 2),
BTF_ENUM_ENC(NAME_TBD, 3),
/* struct pprint_mapv */ /* [16] */
- BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 10), 40),
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 11), 40),
BTF_MEMBER_ENC(NAME_TBD, 11, BTF_MEMBER_OFFSET(0, 0)), /* uint32_t ui32 */
BTF_MEMBER_ENC(NAME_TBD, 10, BTF_MEMBER_OFFSET(0, 32)), /* uint16_t ui16 */
BTF_MEMBER_ENC(NAME_TBD, 12, BTF_MEMBER_OFFSET(0, 64)), /* int32_t si32 */
BTF_MEMBER_ENC(NAME_TBD, 15, BTF_MEMBER_OFFSET(0, 192)), /* aenum */
BTF_MEMBER_ENC(NAME_TBD, 11, BTF_MEMBER_OFFSET(0, 224)), /* uint32_t ui32b */
BTF_MEMBER_ENC(NAME_TBD, 17, BTF_MEMBER_OFFSET(2, 256)), /* bits2c */
+ BTF_MEMBER_ENC(NAME_TBD, 20, BTF_MEMBER_OFFSET(0, 264)), /* si8_4 */
/* typedef unsigned int ___int */ /* [17] */
BTF_TYPEDEF_ENC(NAME_TBD, 18),
BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_VOLATILE, 0, 0), 6), /* [18] */
BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 15), /* [19] */
+ BTF_TYPE_ARRAY_ENC(21, 1, 2), /* [20] */
+ BTF_TYPE_ARRAY_ENC(1, 1, 2), /* [21] */
BTF_END_RAW,
},
- BTF_STR_SEC("\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum\0ui32b\0bits2c\0___int"),
+ BTF_STR_SEC("\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum\0ui32b\0bits2c\0___int\0si8_4"),
.key_size = sizeof(unsigned int),
.value_size = sizeof(struct pprint_mapv),
.key_type_id = 3, /* unsigned int */
v->aenum = i & 0x03;
v->ui32b = 4;
v->bits2c = 1;
+ v->si8_4[0][0] = (cpu + i) & 0xff;
+ v->si8_4[0][1] = (cpu + i + 1) & 0xff;
+ v->si8_4[1][0] = (cpu + i + 2) & 0xff;
+ v->si8_4[1][1] = (cpu + i + 3) & 0xff;
v = (void *)v + rounded_value_size;
}
}
nexpected_line = snprintf(expected_line, line_size,
"%s%u: {%u,0,%d,0x%x,0x%x,0x%x,"
"{%lu|[%u,%u,%u,%u,%u,%u,%u,%u]},%s,"
- "%u,0x%x}\n",
+ "%u,0x%x,[[%d,%d],[%d,%d]]}\n",
percpu_map ? "\tcpu" : "",
percpu_map ? cpu : next_key,
v->ui32, v->si32,
v->ui8a[6], v->ui8a[7],
pprint_enum_str[v->aenum],
v->ui32b,
- v->bits2c);
+ v->bits2c,
+ v->si8_4[0][0], v->si8_4[0][1],
+ v->si8_4[1][0], v->si8_4[1][1]);
}
#ifdef __SIZEOF_INT128__
.dedup_table_size = 1, /* force hash collisions */
},
},
+{
+ .descr = "dedup: void equiv check",
+ /*
+ * // CU 1:
+ * struct s {
+ * struct {} *x;
+ * };
+ * // CU 2:
+ * struct s {
+ * int *x;
+ * };
+ */
+ .input = {
+ .raw_types = {
+ /* CU 1 */
+ BTF_STRUCT_ENC(0, 0, 1), /* [1] struct {} */
+ BTF_PTR_ENC(1), /* [2] ptr -> [1] */
+ BTF_STRUCT_ENC(NAME_NTH(1), 1, 8), /* [3] struct s */
+ BTF_MEMBER_ENC(NAME_NTH(2), 2, 0),
+ /* CU 2 */
+ BTF_PTR_ENC(0), /* [4] ptr -> void */
+ BTF_STRUCT_ENC(NAME_NTH(1), 1, 8), /* [5] struct s */
+ BTF_MEMBER_ENC(NAME_NTH(2), 4, 0),
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0s\0x"),
+ },
+ .expect = {
+ .raw_types = {
+ /* CU 1 */
+ BTF_STRUCT_ENC(0, 0, 1), /* [1] struct {} */
+ BTF_PTR_ENC(1), /* [2] ptr -> [1] */
+ BTF_STRUCT_ENC(NAME_NTH(1), 1, 8), /* [3] struct s */
+ BTF_MEMBER_ENC(NAME_NTH(2), 2, 0),
+ /* CU 2 */
+ BTF_PTR_ENC(0), /* [4] ptr -> void */
+ BTF_STRUCT_ENC(NAME_NTH(1), 1, 8), /* [5] struct s */
+ BTF_MEMBER_ENC(NAME_NTH(2), 4, 0),
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0s\0x"),
+ },
+ .opts = {
+ .dont_resolve_fwds = false,
+ .dedup_table_size = 1, /* force hash collisions */
+ },
+},
{
.descr = "dedup: all possible kinds (no duplicates)",
.input = {
start_test("Test if netdev removal waits for translation...")
delay_msec = 500
- sim.dfs["bpf_bind_verifier_delay"] = delay_msec
+ sim.dfs["sdev/bpf_bind_verifier_delay"] = delay_msec
start = time.time()
cmd_line = "tc filter add dev %s ingress bpf %s da skip_sw" % \
(sim['ifname'], obj)
int error_cnt, pass_cnt;
bool jit_enabled;
+bool verifier_stats = false;
struct ipv4_packet pkt_v4 = {
.eth.h_proto = __bpf_constant_htons(ETH_P_IP),
#include <prog_tests/tests.h>
#undef DECLARE
-int main(void)
+int main(int ac, char **av)
{
srand(time(NULL));
jit_enabled = is_jit_enabled();
+ if (ac == 2 && strcmp(av[1], "-s") == 0)
+ verifier_stats = true;
+
#define CALL
#include <prog_tests/tests.h>
#undef CALL
extern int error_cnt, pass_cnt;
extern bool jit_enabled;
+extern bool verifier_stats;
#define MAGIC_BYTES 123
readonly ns1_v6=fd::1
readonly ns2_v6=fd::2
+# Must match port used by bpf program
+readonly udpport=5555
+# MPLSoverUDP
+readonly mplsudpport=6635
+readonly mplsproto=137
+
readonly infile="$(mktemp)"
readonly outfile="$(mktemp)"
# clamp route to reserve room for tunnel headers
ip -netns "${ns1}" -4 route flush table main
ip -netns "${ns1}" -6 route flush table main
- ip -netns "${ns1}" -4 route add "${ns2_v4}" mtu 1476 dev veth1
- ip -netns "${ns1}" -6 route add "${ns2_v6}" mtu 1456 dev veth1
+ ip -netns "${ns1}" -4 route add "${ns2_v4}" mtu 1458 dev veth1
+ ip -netns "${ns1}" -6 route add "${ns2_v6}" mtu 1438 dev veth1
sleep 1
# no arguments: automated test, run all
if [[ "$#" -eq "0" ]]; then
echo "ipip"
- $0 ipv4 ipip 100
+ $0 ipv4 ipip none 100
echo "ip6ip6"
- $0 ipv6 ip6tnl 100
+ $0 ipv6 ip6tnl none 100
+
+ for mac in none mpls eth ; do
+ echo "ip gre $mac"
+ $0 ipv4 gre $mac 100
+
+ echo "ip6 gre $mac"
+ $0 ipv6 ip6gre $mac 100
+
+ echo "ip gre $mac gso"
+ $0 ipv4 gre $mac 2000
- echo "ip gre"
- $0 ipv4 gre 100
+ echo "ip6 gre $mac gso"
+ $0 ipv6 ip6gre $mac 2000
- echo "ip6 gre"
- $0 ipv6 ip6gre 100
+ echo "ip udp $mac"
+ $0 ipv4 udp $mac 100
- echo "ip gre gso"
- $0 ipv4 gre 2000
+ echo "ip6 udp $mac"
+ $0 ipv6 ip6udp $mac 100
- echo "ip6 gre gso"
- $0 ipv6 ip6gre 2000
+ echo "ip udp $mac gso"
+ $0 ipv4 udp $mac 2000
+
+ echo "ip6 udp $mac gso"
+ $0 ipv6 ip6udp $mac 2000
+ done
echo "OK. All tests passed"
exit 0
fi
-if [[ "$#" -ne "3" ]]; then
+if [[ "$#" -ne "4" ]]; then
echo "Usage: $0"
- echo " or: $0 <ipv4|ipv6> <tuntype> <data_len>"
+ echo " or: $0 <ipv4|ipv6> <tuntype> <none|mpls|eth> <data_len>"
exit 1
fi
"ipv4")
readonly addr1="${ns1_v4}"
readonly addr2="${ns2_v4}"
- readonly netcat_opt=-4
+ readonly ipproto=4
+ readonly netcat_opt=-${ipproto}
+ readonly foumod=fou
+ readonly foutype=ipip
+ readonly fouproto=4
+ readonly fouproto_mpls=${mplsproto}
+ readonly gretaptype=gretap
;;
"ipv6")
readonly addr1="${ns1_v6}"
readonly addr2="${ns2_v6}"
- readonly netcat_opt=-6
+ readonly ipproto=6
+ readonly netcat_opt=-${ipproto}
+ readonly foumod=fou6
+ readonly foutype=ip6tnl
+ readonly fouproto="41 -6"
+ readonly fouproto_mpls="${mplsproto} -6"
+ readonly gretaptype=ip6gretap
;;
*)
echo "unknown arg: $1"
esac
readonly tuntype=$2
-readonly datalen=$3
+readonly mac=$3
+readonly datalen=$4
-echo "encap ${addr1} to ${addr2}, type ${tuntype}, len ${datalen}"
+echo "encap ${addr1} to ${addr2}, type ${tuntype}, mac ${mac} len ${datalen}"
trap cleanup EXIT
ip netns exec "${ns1}" tc qdisc add dev veth1 clsact
ip netns exec "${ns1}" tc filter add dev veth1 egress \
bpf direct-action object-file ./test_tc_tunnel.o \
- section "encap_${tuntype}"
+ section "encap_${tuntype}_${mac}"
echo "test bpf encap without decap (expect failure)"
server_listen
! client_connect
+if [[ "$tuntype" =~ "udp" ]]; then
+ # Set up fou tunnel.
+ ttype="${foutype}"
+ targs="encap fou encap-sport auto encap-dport $udpport"
+ # fou may be a module; allow this to fail.
+ modprobe "${foumod}" ||true
+ if [[ "$mac" == "mpls" ]]; then
+ dport=${mplsudpport}
+ dproto=${fouproto_mpls}
+ tmode="mode any ttl 255"
+ else
+ dport=${udpport}
+ dproto=${fouproto}
+ fi
+ ip netns exec "${ns2}" ip fou add port $dport ipproto ${dproto}
+ targs="encap fou encap-sport auto encap-dport $dport"
+elif [[ "$tuntype" =~ "gre" && "$mac" == "eth" ]]; then
+ ttype=$gretaptype
+else
+ ttype=$tuntype
+ targs=""
+fi
+
# serverside, insert decap module
# server is still running
# client can connect again
-ip netns exec "${ns2}" ip link add dev testtun0 type "${tuntype}" \
- remote "${addr1}" local "${addr2}"
+ip netns exec "${ns2}" ip link add name testtun0 type "${ttype}" \
+ ${tmode} remote "${addr1}" local "${addr2}" $targs
+
+expect_tun_fail=0
+
+if [[ "$tuntype" == "ip6udp" && "$mac" == "mpls" ]]; then
+ # No support for MPLS IPv6 fou tunnel; expect failure.
+ expect_tun_fail=1
+elif [[ "$tuntype" =~ "udp" && "$mac" == "eth" ]]; then
+ # No support for TEB fou tunnel; expect failure.
+ expect_tun_fail=1
+elif [[ "$tuntype" =~ "gre" && "$mac" == "eth" ]]; then
+ # Share ethernet address between tunnel/veth2 so L2 decap works.
+ ethaddr=$(ip netns exec "${ns2}" ip link show veth2 | \
+ awk '/ether/ { print $2 }')
+ ip netns exec "${ns2}" ip link set testtun0 address $ethaddr
+elif [[ "$mac" == "mpls" ]]; then
+ modprobe mpls_iptunnel ||true
+ modprobe mpls_gso ||true
+ ip netns exec "${ns2}" sysctl -qw net.mpls.platform_labels=65536
+ ip netns exec "${ns2}" ip -f mpls route add 1000 dev lo
+ ip netns exec "${ns2}" ip link set lo up
+ ip netns exec "${ns2}" sysctl -qw net.mpls.conf.testtun0.input=1
+ ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.lo.rp_filter=0
+fi
+
# Because packets are decapped by the tunnel they arrive on testtun0 from
# the IP stack perspective. Ensure reverse path filtering is disabled
# otherwise we drop the TCP SYN as arriving on testtun0 instead of the
# selected as the max of the "all" and device-specific values.
ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.testtun0.rp_filter=0
ip netns exec "${ns2}" ip link set dev testtun0 up
-echo "test bpf encap with tunnel device decap"
-client_connect
-verify_data
+if [[ "$expect_tun_fail" == 1 ]]; then
+ # This tunnel mode is not supported, so we expect failure.
+ echo "test bpf encap with tunnel device decap (expect failure)"
+ ! client_connect
+else
+ echo "test bpf encap with tunnel device decap"
+ client_connect
+ verify_data
+ server_listen
+fi
# serverside, use BPF for decap
ip netns exec "${ns2}" ip link del dev testtun0
ip netns exec "${ns2}" tc qdisc add dev veth2 clsact
ip netns exec "${ns2}" tc filter add dev veth2 ingress \
bpf direct-action object-file ./test_tc_tunnel.o section decap
-server_listen
echo "test bpf encap with bpf decap"
client_connect
verify_data
#include "../../../include/linux/filter.h"
#define MAX_INSNS BPF_MAXINSNS
+#define MAX_TEST_INSNS 1000000
#define MAX_FIXUPS 8
-#define MAX_NR_MAPS 14
+#define MAX_NR_MAPS 16
#define MAX_TEST_RUNS 8
#define POINTER_VALUE 0xcafe4all
#define TEST_DATA_LEN 64
struct bpf_test {
const char *descr;
struct bpf_insn insns[MAX_INSNS];
+ struct bpf_insn *fill_insns;
int fixup_map_hash_8b[MAX_FIXUPS];
int fixup_map_hash_48b[MAX_FIXUPS];
int fixup_map_hash_16b[MAX_FIXUPS];
int fixup_cgroup_storage[MAX_FIXUPS];
int fixup_percpu_cgroup_storage[MAX_FIXUPS];
int fixup_map_spin_lock[MAX_FIXUPS];
+ int fixup_map_array_ro[MAX_FIXUPS];
+ int fixup_map_array_wo[MAX_FIXUPS];
+ int fixup_map_array_small[MAX_FIXUPS];
const char *errstr;
const char *errstr_unpriv;
uint32_t retval, retval_unpriv, insn_processed;
+ int prog_len;
enum {
UNDEF,
ACCEPT,
static void bpf_fill_ld_abs_vlan_push_pop(struct bpf_test *self)
{
- /* test: {skb->data[0], vlan_push} x 68 + {skb->data[0], vlan_pop} x 68 */
+ /* test: {skb->data[0], vlan_push} x 51 + {skb->data[0], vlan_pop} x 51 */
#define PUSH_CNT 51
- unsigned int len = BPF_MAXINSNS;
- struct bpf_insn *insn = self->insns;
+ /* jump range is limited to 16 bit. PUSH_CNT of ld_abs needs room */
+ unsigned int len = (1 << 15) - PUSH_CNT * 2 * 5 * 6;
+ struct bpf_insn *insn = self->fill_insns;
int i = 0, j, k = 0;
insn[i++] = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1);
for (; i < len - 1; i++)
insn[i] = BPF_ALU32_IMM(BPF_MOV, BPF_REG_0, 0xbef);
insn[len - 1] = BPF_EXIT_INSN();
+ self->prog_len = len;
}
static void bpf_fill_jump_around_ld_abs(struct bpf_test *self)
{
- struct bpf_insn *insn = self->insns;
- unsigned int len = BPF_MAXINSNS;
+ struct bpf_insn *insn = self->fill_insns;
+ /* jump range is limited to 16 bit. every ld_abs is replaced by 6 insns */
+ unsigned int len = (1 << 15) / 6;
int i = 0;
insn[i++] = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1);
while (i < len - 1)
insn[i++] = BPF_LD_ABS(BPF_B, 1);
insn[i] = BPF_EXIT_INSN();
+ self->prog_len = i + 1;
}
static void bpf_fill_rand_ld_dw(struct bpf_test *self)
{
- struct bpf_insn *insn = self->insns;
+ struct bpf_insn *insn = self->fill_insns;
uint64_t res = 0;
int i = 0;
insn[i++] = BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 32);
insn[i++] = BPF_ALU64_REG(BPF_XOR, BPF_REG_0, BPF_REG_1);
insn[i] = BPF_EXIT_INSN();
+ self->prog_len = i + 1;
res ^= (res >> 32);
self->retval = (uint32_t)res;
}
return false;
}
-static int create_map(uint32_t type, uint32_t size_key,
- uint32_t size_value, uint32_t max_elem)
+static int __create_map(uint32_t type, uint32_t size_key,
+ uint32_t size_value, uint32_t max_elem,
+ uint32_t extra_flags)
{
int fd;
fd = bpf_create_map(type, size_key, size_value, max_elem,
- type == BPF_MAP_TYPE_HASH ? BPF_F_NO_PREALLOC : 0);
+ (type == BPF_MAP_TYPE_HASH ?
+ BPF_F_NO_PREALLOC : 0) | extra_flags);
if (fd < 0) {
if (skip_unsupported_map(type))
return -1;
return fd;
}
+static int create_map(uint32_t type, uint32_t size_key,
+ uint32_t size_value, uint32_t max_elem)
+{
+ return __create_map(type, size_key, size_value, max_elem, 0);
+}
+
static void update_map(int fd, int index)
{
struct test_val value = {
int *fixup_cgroup_storage = test->fixup_cgroup_storage;
int *fixup_percpu_cgroup_storage = test->fixup_percpu_cgroup_storage;
int *fixup_map_spin_lock = test->fixup_map_spin_lock;
+ int *fixup_map_array_ro = test->fixup_map_array_ro;
+ int *fixup_map_array_wo = test->fixup_map_array_wo;
+ int *fixup_map_array_small = test->fixup_map_array_small;
- if (test->fill_helper)
+ if (test->fill_helper) {
+ test->fill_insns = calloc(MAX_TEST_INSNS, sizeof(struct bpf_insn));
test->fill_helper(test);
+ }
/* Allocating HTs with 1 elem is fine here, since we only test
* for verifier and not do a runtime lookup, so the only thing
fixup_map_spin_lock++;
} while (*fixup_map_spin_lock);
}
+ if (*fixup_map_array_ro) {
+ map_fds[14] = __create_map(BPF_MAP_TYPE_ARRAY, sizeof(int),
+ sizeof(struct test_val), 1,
+ BPF_F_RDONLY_PROG);
+ update_map(map_fds[14], 0);
+ do {
+ prog[*fixup_map_array_ro].imm = map_fds[14];
+ fixup_map_array_ro++;
+ } while (*fixup_map_array_ro);
+ }
+ if (*fixup_map_array_wo) {
+ map_fds[15] = __create_map(BPF_MAP_TYPE_ARRAY, sizeof(int),
+ sizeof(struct test_val), 1,
+ BPF_F_WRONLY_PROG);
+ update_map(map_fds[15], 0);
+ do {
+ prog[*fixup_map_array_wo].imm = map_fds[15];
+ fixup_map_array_wo++;
+ } while (*fixup_map_array_wo);
+ }
+ if (*fixup_map_array_small) {
+ map_fds[16] = __create_map(BPF_MAP_TYPE_ARRAY, sizeof(int),
+ 1, 1, 0);
+ update_map(map_fds[16], 0);
+ do {
+ prog[*fixup_map_array_small].imm = map_fds[16];
+ fixup_map_array_small++;
+ } while (*fixup_map_array_small);
+ }
}
static int set_admin(bool admin)
prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
fixup_skips = skips;
do_test_fixup(test, prog_type, prog, map_fds);
+ if (test->fill_insns) {
+ prog = test->fill_insns;
+ prog_len = test->prog_len;
+ } else {
+ prog_len = probe_filter_length(prog);
+ }
/* If there were some map skips during fixup due to missing bpf
* features, skip this test.
*/
if (fixup_skips != skips)
return;
- prog_len = probe_filter_length(prog);
pflags = 0;
if (test->flags & F_LOAD_WITH_STRICT_ALIGNMENT)
if (test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS)
pflags |= BPF_F_ANY_ALIGNMENT;
fd_prog = bpf_verify_program(prog_type, prog, prog_len, pflags,
- "GPL", 0, bpf_vlog, sizeof(bpf_vlog), 1);
+ "GPL", 0, bpf_vlog, sizeof(bpf_vlog), 4);
if (fd_prog < 0 && !bpf_probe_prog_type(prog_type, 0)) {
printf("SKIP (unsupported program type %d)\n", prog_type);
skips++;
goto fail_log;
}
close_fds:
+ if (test->fill_insns)
+ free(test->fill_insns);
close(fd_prog);
for (i = 0; i < MAX_NR_MAPS; i++)
close(map_fds[i]);
int start = 0, end = sym_cnt;
int result;
+ /* kallsyms not loaded. return NULL */
+ if (sym_cnt <= 0)
+ return NULL;
+
while (start < end) {
size_t mid = start + (end - start) / 2;
.result = REJECT,
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
+{
+ "valid read map access into a read-only array 1",
+ .insns = {
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_ro = { 3 },
+ .result = ACCEPT,
+ .retval = 28,
+},
+{
+ "valid read map access into a read-only array 2",
+ .insns = {
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
+
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_MOV64_IMM(BPF_REG_2, 4),
+ BPF_MOV64_IMM(BPF_REG_3, 0),
+ BPF_MOV64_IMM(BPF_REG_4, 0),
+ BPF_MOV64_IMM(BPF_REG_5, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_csum_diff),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .fixup_map_array_ro = { 3 },
+ .result = ACCEPT,
+ .retval = -29,
+},
+{
+ "invalid write map access into a read-only array 1",
+ .insns = {
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+ BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 42),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_ro = { 3 },
+ .result = REJECT,
+ .errstr = "write into map forbidden",
+},
+{
+ "invalid write map access into a read-only array 2",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ BPF_MOV64_IMM(BPF_REG_2, 0),
+ BPF_MOV64_REG(BPF_REG_3, BPF_REG_0),
+ BPF_MOV64_IMM(BPF_REG_4, 8),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_skb_load_bytes),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .fixup_map_array_ro = { 4 },
+ .result = REJECT,
+ .errstr = "write into map forbidden",
+},
+{
+ "valid write map access into a write-only array 1",
+ .insns = {
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+ BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 42),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_wo = { 3 },
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
+ "valid write map access into a write-only array 2",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ BPF_MOV64_IMM(BPF_REG_2, 0),
+ BPF_MOV64_REG(BPF_REG_3, BPF_REG_0),
+ BPF_MOV64_IMM(BPF_REG_4, 8),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_skb_load_bytes),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .fixup_map_array_wo = { 4 },
+ .result = ACCEPT,
+ .retval = 0,
+},
+{
+ "invalid read map access into a write-only array 1",
+ .insns = {
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_wo = { 3 },
+ .result = REJECT,
+ .errstr = "read from map forbidden",
+},
+{
+ "invalid read map access into a write-only array 2",
+ .insns = {
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
+
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_MOV64_IMM(BPF_REG_2, 4),
+ BPF_MOV64_IMM(BPF_REG_3, 0),
+ BPF_MOV64_IMM(BPF_REG_4, 0),
+ BPF_MOV64_IMM(BPF_REG_5, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_csum_diff),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .fixup_map_array_wo = { 3 },
+ .result = REJECT,
+ .errstr = "read from map forbidden",
+},
.errstr = "call stack",
.result = REJECT,
},
+{
+ "calls: stack depth check in dead code",
+ .insns = {
+ /* main */
+ BPF_MOV64_IMM(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call A */
+ BPF_EXIT_INSN(),
+ /* A */
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
+ BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 2), /* call B */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ /* B */
+ BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call C */
+ BPF_EXIT_INSN(),
+ /* C */
+ BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call D */
+ BPF_EXIT_INSN(),
+ /* D */
+ BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call E */
+ BPF_EXIT_INSN(),
+ /* E */
+ BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call F */
+ BPF_EXIT_INSN(),
+ /* F */
+ BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call G */
+ BPF_EXIT_INSN(),
+ /* G */
+ BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call H */
+ BPF_EXIT_INSN(),
+ /* H */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_XDP,
+ .errstr = "call stack",
+ .result = REJECT,
+},
{
"calls: spill into caller stack frame",
.insns = {
.errstr = "invalid bpf_context access",
.result = REJECT,
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
- .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"check cb access: half, wrong type",
--- /dev/null
+{
+ "direct map access, write test 1",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_LD_MAP_VALUE(BPF_REG_1, 0, 0),
+ BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 4242),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 1 },
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
+ "direct map access, write test 2",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_LD_MAP_VALUE(BPF_REG_1, 0, 8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 4242),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 1 },
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
+ "direct map access, write test 3",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_LD_MAP_VALUE(BPF_REG_1, 0, 8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_1, 8, 4242),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 1 },
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
+ "direct map access, write test 4",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_LD_MAP_VALUE(BPF_REG_1, 0, 40),
+ BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 4242),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 1 },
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
+ "direct map access, write test 5",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_LD_MAP_VALUE(BPF_REG_1, 0, 32),
+ BPF_ST_MEM(BPF_DW, BPF_REG_1, 8, 4242),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 1 },
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
+ "direct map access, write test 6",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_LD_MAP_VALUE(BPF_REG_1, 0, 40),
+ BPF_ST_MEM(BPF_DW, BPF_REG_1, 4, 4242),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 1 },
+ .result = REJECT,
+ .errstr = "R1 min value is outside of the array range",
+},
+{
+ "direct map access, write test 7",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_LD_MAP_VALUE(BPF_REG_1, 0, -1),
+ BPF_ST_MEM(BPF_DW, BPF_REG_1, 4, 4242),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 1 },
+ .result = REJECT,
+ .errstr = "direct value offset of 4294967295 is not allowed",
+},
+{
+ "direct map access, write test 8",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_LD_MAP_VALUE(BPF_REG_1, 0, 1),
+ BPF_ST_MEM(BPF_DW, BPF_REG_1, -1, 4242),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 1 },
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
+ "direct map access, write test 9",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_LD_MAP_VALUE(BPF_REG_1, 0, 48),
+ BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 4242),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 1 },
+ .result = REJECT,
+ .errstr = "invalid access to map value pointer",
+},
+{
+ "direct map access, write test 10",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_LD_MAP_VALUE(BPF_REG_1, 0, 47),
+ BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 4),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 1 },
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
+ "direct map access, write test 11",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_LD_MAP_VALUE(BPF_REG_1, 0, 48),
+ BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 4),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 1 },
+ .result = REJECT,
+ .errstr = "invalid access to map value pointer",
+},
+{
+ "direct map access, write test 12",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_LD_MAP_VALUE(BPF_REG_1, 0, (1<<29)),
+ BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 4),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 1 },
+ .result = REJECT,
+ .errstr = "direct value offset of 536870912 is not allowed",
+},
+{
+ "direct map access, write test 13",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_LD_MAP_VALUE(BPF_REG_1, 0, (1<<29)-1),
+ BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 4),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 1 },
+ .result = REJECT,
+ .errstr = "invalid access to map value pointer, value_size=48 off=536870911",
+},
+{
+ "direct map access, write test 14",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_LD_MAP_VALUE(BPF_REG_1, 0, 47),
+ BPF_LD_MAP_VALUE(BPF_REG_2, 0, 46),
+ BPF_ST_MEM(BPF_H, BPF_REG_2, 0, 0xffff),
+ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 1, 3 },
+ .result = ACCEPT,
+ .retval = 0xff,
+},
+{
+ "direct map access, write test 15",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_LD_MAP_VALUE(BPF_REG_1, 0, 46),
+ BPF_LD_MAP_VALUE(BPF_REG_2, 0, 46),
+ BPF_ST_MEM(BPF_H, BPF_REG_2, 0, 0xffff),
+ BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 1, 3 },
+ .result = ACCEPT,
+ .retval = 0xffff,
+},
+{
+ "direct map access, write test 16",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_LD_MAP_VALUE(BPF_REG_1, 0, 46),
+ BPF_LD_MAP_VALUE(BPF_REG_2, 0, 47),
+ BPF_ST_MEM(BPF_H, BPF_REG_2, 0, 0xffff),
+ BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 1, 3 },
+ .result = REJECT,
+ .errstr = "invalid access to map value, value_size=48 off=47 size=2",
+},
+{
+ "direct map access, write test 17",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_LD_MAP_VALUE(BPF_REG_1, 0, 46),
+ BPF_LD_MAP_VALUE(BPF_REG_2, 0, 46),
+ BPF_ST_MEM(BPF_H, BPF_REG_2, 1, 0xffff),
+ BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 1, 3 },
+ .result = REJECT,
+ .errstr = "invalid access to map value, value_size=48 off=47 size=2",
+},
+{
+ "direct map access, write test 18",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_LD_MAP_VALUE(BPF_REG_1, 0, 0),
+ BPF_ST_MEM(BPF_H, BPF_REG_1, 0, 42),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_small = { 1 },
+ .result = REJECT,
+ .errstr = "R1 min value is outside of the array range",
+},
+{
+ "direct map access, write test 19",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_LD_MAP_VALUE(BPF_REG_1, 0, 0),
+ BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 42),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_small = { 1 },
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
+ "direct map access, write test 20",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_LD_MAP_VALUE(BPF_REG_1, 0, 1),
+ BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 42),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_small = { 1 },
+ .result = REJECT,
+ .errstr = "invalid access to map value pointer",
+},
+{
+ "direct map access, invalid insn test 1",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_VALUE, 0, 1, 0, 47),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 1 },
+ .result = REJECT,
+ .errstr = "invalid bpf_ld_imm64 insn",
+},
+{
+ "direct map access, invalid insn test 2",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_VALUE, 1, 0, 0, 47),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 1 },
+ .result = REJECT,
+ .errstr = "BPF_LD_IMM64 uses reserved fields",
+},
+{
+ "direct map access, invalid insn test 3",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_VALUE, ~0, 0, 0, 47),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 1 },
+ .result = REJECT,
+ .errstr = "BPF_LD_IMM64 uses reserved fields",
+},
+{
+ "direct map access, invalid insn test 4",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_VALUE, 0, ~0, 0, 47),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 1 },
+ .result = REJECT,
+ .errstr = "invalid bpf_ld_imm64 insn",
+},
+{
+ "direct map access, invalid insn test 5",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_VALUE, ~0, ~0, 0, 47),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 1 },
+ .result = REJECT,
+ .errstr = "invalid bpf_ld_imm64 insn",
+},
+{
+ "direct map access, invalid insn test 6",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_FD, ~0, 0, 0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 1 },
+ .result = REJECT,
+ .errstr = "BPF_LD_IMM64 uses reserved fields",
+},
+{
+ "direct map access, invalid insn test 7",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_FD, 0, ~0, 0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 1 },
+ .result = REJECT,
+ .errstr = "invalid bpf_ld_imm64 insn",
+},
+{
+ "direct map access, invalid insn test 8",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_FD, ~0, ~0, 0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 1 },
+ .result = REJECT,
+ .errstr = "invalid bpf_ld_imm64 insn",
+},
+{
+ "direct map access, invalid insn test 9",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_FD, 0, 0, 0, 47),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 1 },
+ .result = REJECT,
+ .errstr = "unrecognized bpf_ld_imm64 insn",
+},
.result = ACCEPT,
.retval = 5,
},
+{
+ "ld_dw: xor semi-random 64 bit imms, test 5",
+ .insns = { },
+ .data = { },
+ .fill_helper = bpf_fill_rand_ld_dw,
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = ACCEPT,
+ .retval = 1000000 - 6,
+},
.prog_type = BPF_PROG_TYPE_LWT_IN,
},
{
- "indirect variable-offset stack access",
+ "indirect variable-offset stack access, unbounded",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_2, 6),
+ BPF_MOV64_IMM(BPF_REG_3, 28),
+ /* Fill the top 16 bytes of the stack. */
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, 0),
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ /* Get an unknown value. */
+ BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_1, offsetof(struct bpf_sock_ops,
+ bytes_received)),
+ /* Check the lower bound but don't check the upper one. */
+ BPF_JMP_IMM(BPF_JSLT, BPF_REG_4, 0, 4),
+ /* Point the lower bound to initialized stack. Offset is now in range
+ * from fp-16 to fp+0x7fffffffffffffef, i.e. max value is unbounded.
+ */
+ BPF_ALU64_IMM(BPF_SUB, BPF_REG_4, 16),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_4, BPF_REG_10),
+ BPF_MOV64_IMM(BPF_REG_5, 8),
+ /* Dereference it indirectly. */
+ BPF_EMIT_CALL(BPF_FUNC_getsockopt),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "R4 unbounded indirect variable offset stack access",
+ .result = REJECT,
+ .prog_type = BPF_PROG_TYPE_SOCK_OPS,
+},
+{
+ "indirect variable-offset stack access, max out of bound",
.insns = {
/* Fill the top 8 bytes of the stack */
BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
BPF_EXIT_INSN(),
},
.fixup_map_hash_8b = { 5 },
- .errstr = "variable stack read R2",
+ .errstr = "R2 max value is outside of stack bound",
+ .result = REJECT,
+ .prog_type = BPF_PROG_TYPE_LWT_IN,
+},
+{
+ "indirect variable-offset stack access, min out of bound",
+ .insns = {
+ /* Fill the top 8 bytes of the stack */
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ /* Get an unknown value */
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0),
+ /* Make it small and 4-byte aligned */
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 4),
+ BPF_ALU64_IMM(BPF_SUB, BPF_REG_2, 516),
+ /* add it to fp. We now have either fp-516 or fp-512, but
+ * we don't know which
+ */
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_10),
+ /* dereference it indirectly */
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_hash_8b = { 5 },
+ .errstr = "R2 min value is outside of stack bound",
+ .result = REJECT,
+ .prog_type = BPF_PROG_TYPE_LWT_IN,
+},
+{
+ "indirect variable-offset stack access, max_off+size > max_initialized",
+ .insns = {
+ /* Fill only the second from top 8 bytes of the stack. */
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, 0),
+ /* Get an unknown value. */
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0),
+ /* Make it small and 4-byte aligned. */
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 4),
+ BPF_ALU64_IMM(BPF_SUB, BPF_REG_2, 16),
+ /* Add it to fp. We now have either fp-12 or fp-16, but we don't know
+ * which. fp-12 size 8 is partially uninitialized stack.
+ */
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_10),
+ /* Dereference it indirectly. */
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_hash_8b = { 5 },
+ .errstr = "invalid indirect read from stack var_off",
+ .result = REJECT,
+ .prog_type = BPF_PROG_TYPE_LWT_IN,
+},
+{
+ "indirect variable-offset stack access, min_off < min_initialized",
+ .insns = {
+ /* Fill only the top 8 bytes of the stack. */
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ /* Get an unknown value */
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0),
+ /* Make it small and 4-byte aligned. */
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 4),
+ BPF_ALU64_IMM(BPF_SUB, BPF_REG_2, 16),
+ /* Add it to fp. We now have either fp-12 or fp-16, but we don't know
+ * which. fp-16 size 8 is partially uninitialized stack.
+ */
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_10),
+ /* Dereference it indirectly. */
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_hash_8b = { 5 },
+ .errstr = "invalid indirect read from stack var_off",
.result = REJECT,
.prog_type = BPF_PROG_TYPE_LWT_IN,
},
+{
+ "indirect variable-offset stack access, priv vs unpriv",
+ .insns = {
+ /* Fill the top 16 bytes of the stack. */
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, 0),
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ /* Get an unknown value. */
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0),
+ /* Make it small and 4-byte aligned. */
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 4),
+ BPF_ALU64_IMM(BPF_SUB, BPF_REG_2, 16),
+ /* Add it to fp. We now have either fp-12 or fp-16, we don't know
+ * which, but either way it points to initialized stack.
+ */
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_10),
+ /* Dereference it indirectly. */
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_hash_8b = { 6 },
+ .errstr_unpriv = "R2 stack pointer arithmetic goes out of range, prohibited for !root",
+ .result_unpriv = REJECT,
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+},
+{
+ "indirect variable-offset stack access, uninitialized",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_2, 6),
+ BPF_MOV64_IMM(BPF_REG_3, 28),
+ /* Fill the top 16 bytes of the stack. */
+ BPF_ST_MEM(BPF_W, BPF_REG_10, -16, 0),
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ /* Get an unknown value. */
+ BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1, 0),
+ /* Make it small and 4-byte aligned. */
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_4, 4),
+ BPF_ALU64_IMM(BPF_SUB, BPF_REG_4, 16),
+ /* Add it to fp. We now have either fp-12 or fp-16, we don't know
+ * which, but either way it points to initialized stack.
+ */
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_4, BPF_REG_10),
+ BPF_MOV64_IMM(BPF_REG_5, 8),
+ /* Dereference it indirectly. */
+ BPF_EMIT_CALL(BPF_FUNC_getsockopt),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "invalid indirect read from stack var_off",
+ .result = REJECT,
+ .prog_type = BPF_PROG_TYPE_SOCK_OPS,
+},
+{
+ "indirect variable-offset stack access, ok",
+ .insns = {
+ /* Fill the top 16 bytes of the stack. */
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, 0),
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ /* Get an unknown value. */
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0),
+ /* Make it small and 4-byte aligned. */
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 4),
+ BPF_ALU64_IMM(BPF_SUB, BPF_REG_2, 16),
+ /* Add it to fp. We now have either fp-12 or fp-16, we don't know
+ * which, but either way it points to initialized stack.
+ */
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_10),
+ /* Dereference it indirectly. */
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_hash_8b = { 6 },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_LWT_IN,
+},
ALL_TESTS="
rif_set_addr_test
+ rif_vrf_set_addr_test
rif_inherit_bridge_addr_test
rif_non_inherit_bridge_addr_test
vlan_interface_deletion_test
lag_dev_deletion_test
vlan_interface_uppers_test
bridge_extern_learn_test
+ neigh_offload_test
devlink_reload_test
"
NUM_NETIFS=2
ip link set dev $swp1 addr $swp1_mac
}
+rif_vrf_set_addr_test()
+{
+ # Test that it is possible to set an IP address on a VRF upper despite
+ # its random MAC address.
+ RET=0
+
+ ip link add name vrf-test type vrf table 10
+ ip link set dev $swp1 master vrf-test
+
+ ip -4 address add 192.0.2.1/24 dev vrf-test
+ check_err $? "failed to set IPv4 address on VRF"
+ ip -6 address add 2001:db8:1::1/64 dev vrf-test
+ check_err $? "failed to set IPv6 address on VRF"
+
+ log_test "RIF - setting IP address on VRF"
+
+ ip link del dev vrf-test
+}
+
rif_inherit_bridge_addr_test()
{
RET=0
ip link del dev br0
}
+neigh_offload_test()
+{
+ # Test that IPv4 and IPv6 neighbour entries are marked as offloaded
+ RET=0
+
+ ip -4 address add 192.0.2.1/24 dev $swp1
+ ip -6 address add 2001:db8:1::1/64 dev $swp1
+
+ ip -4 neigh add 192.0.2.2 lladdr de:ad:be:ef:13:37 nud perm dev $swp1
+ ip -6 neigh add 2001:db8:1::2 lladdr de:ad:be:ef:13:37 nud perm \
+ dev $swp1
+
+ ip -4 neigh show dev $swp1 | grep 192.0.2.2 | grep -q offload
+ check_err $? "ipv4 neigh entry not marked as offloaded when should"
+ ip -6 neigh show dev $swp1 | grep 2001:db8:1::2 | grep -q offload
+ check_err $? "ipv6 neigh entry not marked as offloaded when should"
+
+ log_test "neighbour offload indication"
+
+ ip -6 neigh del 2001:db8:1::2 dev $swp1
+ ip -4 neigh del 192.0.2.2 dev $swp1
+ ip -6 address del 2001:db8:1::1/64 dev $swp1
+ ip -4 address del 192.0.2.1/24 dev $swp1
+}
+
devlink_reload_test()
{
# Test that after executing all the above configuration tests, a
+include ../../../../scripts/Kbuild.include
+
all:
top_srcdir = ../../../..
TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test
TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid
TEST_GEN_PROGS_x86_64 += x86_64/vmx_close_while_nested_test
+TEST_GEN_PROGS_x86_64 += x86_64/smm_test
TEST_GEN_PROGS_x86_64 += dirty_log_test
TEST_GEN_PROGS_x86_64 += clear_dirty_log_test
INSTALL_HDR_PATH = $(top_srcdir)/usr
LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/
LINUX_TOOL_INCLUDE = $(top_srcdir)/tools/include
-CFLAGS += -O2 -g -std=gnu99 -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(UNAME_M) -I..
-LDFLAGS += -pthread
+CFLAGS += -O2 -g -std=gnu99 -fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(UNAME_M) -I..
+
+no-pie-option := $(call try-run, echo 'int main() { return 0; }' | \
+ $(CC) -Werror $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) -no-pie -x c - -o "$$TMP", -no-pie)
+
+LDFLAGS += -pthread $(no-pie-option)
# After inclusion, $(OUTPUT) is defined and
# $(TEST_GEN_PROGS) starts with $(OUTPUT)/
struct kvm_run *vcpu_state(struct kvm_vm *vm, uint32_t vcpuid);
void vcpu_run(struct kvm_vm *vm, uint32_t vcpuid);
int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid);
+void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid);
void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid,
struct kvm_mp_state *mp_state);
void vcpu_regs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs);
#define MSR_IA32_APICBASE_ENABLE (1<<11)
#define MSR_IA32_APICBASE_BASE (0xfffff<<12)
+#define APIC_BASE_MSR 0x800
+#define X2APIC_ENABLE (1UL << 10)
+#define APIC_ICR 0x300
+#define APIC_DEST_SELF 0x40000
+#define APIC_DEST_ALLINC 0x80000
+#define APIC_DEST_ALLBUT 0xC0000
+#define APIC_ICR_RR_MASK 0x30000
+#define APIC_ICR_RR_INVALID 0x00000
+#define APIC_ICR_RR_INPROG 0x10000
+#define APIC_ICR_RR_VALID 0x20000
+#define APIC_INT_LEVELTRIG 0x08000
+#define APIC_INT_ASSERT 0x04000
+#define APIC_ICR_BUSY 0x01000
+#define APIC_DEST_LOGICAL 0x00800
+#define APIC_DEST_PHYSICAL 0x00000
+#define APIC_DM_FIXED 0x00000
+#define APIC_DM_FIXED_MASK 0x00700
+#define APIC_DM_LOWEST 0x00100
+#define APIC_DM_SMI 0x00200
+#define APIC_DM_REMRD 0x00300
+#define APIC_DM_NMI 0x00400
+#define APIC_DM_INIT 0x00500
+#define APIC_DM_STARTUP 0x00600
+#define APIC_DM_EXTINT 0x00700
+#define APIC_VECTOR_MASK 0x000FF
+#define APIC_ICR2 0x310
+
#define MSR_IA32_TSCDEADLINE 0x000006e0
#define MSR_IA32_UCODE_WRITE 0x00000079
if (vm->kvm_fd < 0)
exit(KSFT_SKIP);
+ if (!kvm_check_cap(KVM_CAP_IMMEDIATE_EXIT)) {
+ fprintf(stderr, "immediate_exit not available, skipping test\n");
+ exit(KSFT_SKIP);
+ }
+
vm->fd = ioctl(vm->kvm_fd, KVM_CREATE_VM, type);
TEST_ASSERT(vm->fd >= 0, "KVM_CREATE_VM ioctl failed, "
"rc: %i errno: %i", vm->fd, errno);
return rc;
}
+void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid)
+{
+ struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+ int ret;
+
+ TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
+
+ vcpu->state->immediate_exit = 1;
+ ret = ioctl(vcpu->fd, KVM_RUN, NULL);
+ vcpu->state->immediate_exit = 0;
+
+ TEST_ASSERT(ret == -1 && errno == EINTR,
+ "KVM_RUN IOCTL didn't exit immediately, rc: %i, errno: %i",
+ ret, errno);
+}
+
/*
* VM VCPU Set MP State
*
nested_size, sizeof(state->nested_));
}
+ /*
+ * When KVM exits to userspace with KVM_EXIT_IO, KVM guarantees
+ * guest state is consistent only after userspace re-enters the
+ * kernel with KVM_RUN. Complete IO prior to migrating state
+ * to a new VM.
+ */
+ vcpu_run_complete_io(vm, vcpuid);
+
nmsrs = kvm_get_num_msrs(vm);
list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0]));
list->nmsrs = nmsrs;
struct vcpu *vcpu = vcpu_find(vm, vcpuid);
int r;
- if (state->nested.size) {
- r = ioctl(vcpu->fd, KVM_SET_NESTED_STATE, &state->nested);
- TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_NESTED_STATE, r: %i",
- r);
- }
-
r = ioctl(vcpu->fd, KVM_SET_XSAVE, &state->xsave);
TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_XSAVE, r: %i",
r);
r = ioctl(vcpu->fd, KVM_SET_REGS, &state->regs);
TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_REGS, r: %i",
r);
+
+ if (state->nested.size) {
+ r = ioctl(vcpu->fd, KVM_SET_NESTED_STATE, &state->nested);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_NESTED_STATE, r: %i",
+ r);
+ }
}
while (1) {
rc = _vcpu_run(vm, VCPU_ID);
- if (run->exit_reason == KVM_EXIT_IO) {
- switch (get_ucall(vm, VCPU_ID, &uc)) {
- case UCALL_SYNC:
- /* emulate hypervisor clearing CR4.OSXSAVE */
- vcpu_sregs_get(vm, VCPU_ID, &sregs);
- sregs.cr4 &= ~X86_CR4_OSXSAVE;
- vcpu_sregs_set(vm, VCPU_ID, &sregs);
- break;
- case UCALL_ABORT:
- TEST_ASSERT(false, "Guest CR4 bit (OSXSAVE) unsynchronized with CPUID bit.");
- break;
- case UCALL_DONE:
- goto done;
- default:
- TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
- }
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+ "Unexpected exit reason: %u (%s),\n",
+ run->exit_reason,
+ exit_reason_str(run->exit_reason));
+
+ switch (get_ucall(vm, VCPU_ID, &uc)) {
+ case UCALL_SYNC:
+ /* emulate hypervisor clearing CR4.OSXSAVE */
+ vcpu_sregs_get(vm, VCPU_ID, &sregs);
+ sregs.cr4 &= ~X86_CR4_OSXSAVE;
+ vcpu_sregs_set(vm, VCPU_ID, &sregs);
+ break;
+ case UCALL_ABORT:
+ TEST_ASSERT(false, "Guest CR4 bit (OSXSAVE) unsynchronized with CPUID bit.");
+ break;
+ case UCALL_DONE:
+ goto done;
+ default:
+ TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
}
}
stage, run->exit_reason,
exit_reason_str(run->exit_reason));
- memset(®s1, 0, sizeof(regs1));
- vcpu_regs_get(vm, VCPU_ID, ®s1);
switch (get_ucall(vm, VCPU_ID, &uc)) {
case UCALL_ABORT:
TEST_ASSERT(false, "%s at %s:%d", (const char *)uc.args[0],
stage, (ulong)uc.args[1]);
state = vcpu_save_state(vm, VCPU_ID);
+ memset(®s1, 0, sizeof(regs1));
+ vcpu_regs_get(vm, VCPU_ID, ®s1);
+
kvm_vm_release(vm);
/* Restore state in a new VM. */
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2018, Red Hat, Inc.
+ *
+ * Tests for SMM.
+ */
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdint.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "test_util.h"
+
+#include "kvm_util.h"
+
+#include "vmx.h"
+
+#define VCPU_ID 1
+
+#define PAGE_SIZE 4096
+
+#define SMRAM_SIZE 65536
+#define SMRAM_MEMSLOT ((1 << 16) | 1)
+#define SMRAM_PAGES (SMRAM_SIZE / PAGE_SIZE)
+#define SMRAM_GPA 0x1000000
+#define SMRAM_STAGE 0xfe
+
+#define STR(x) #x
+#define XSTR(s) STR(s)
+
+#define SYNC_PORT 0xe
+#define DONE 0xff
+
+/*
+ * This is compiled as normal 64-bit code, however, SMI handler is executed
+ * in real-address mode. To stay simple we're limiting ourselves to a mode
+ * independent subset of asm here.
+ * SMI handler always report back fixed stage SMRAM_STAGE.
+ */
+uint8_t smi_handler[] = {
+ 0xb0, SMRAM_STAGE, /* mov $SMRAM_STAGE, %al */
+ 0xe4, SYNC_PORT, /* in $SYNC_PORT, %al */
+ 0x0f, 0xaa, /* rsm */
+};
+
+void sync_with_host(uint64_t phase)
+{
+ asm volatile("in $" XSTR(SYNC_PORT)", %%al \n"
+ : : "a" (phase));
+}
+
+void self_smi(void)
+{
+ wrmsr(APIC_BASE_MSR + (APIC_ICR >> 4),
+ APIC_DEST_SELF | APIC_INT_ASSERT | APIC_DM_SMI);
+}
+
+void guest_code(struct vmx_pages *vmx_pages)
+{
+ uint64_t apicbase = rdmsr(MSR_IA32_APICBASE);
+
+ sync_with_host(1);
+
+ wrmsr(MSR_IA32_APICBASE, apicbase | X2APIC_ENABLE);
+
+ sync_with_host(2);
+
+ self_smi();
+
+ sync_with_host(4);
+
+ if (vmx_pages) {
+ GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
+
+ sync_with_host(5);
+
+ self_smi();
+
+ sync_with_host(7);
+ }
+
+ sync_with_host(DONE);
+}
+
+int main(int argc, char *argv[])
+{
+ struct vmx_pages *vmx_pages = NULL;
+ vm_vaddr_t vmx_pages_gva = 0;
+
+ struct kvm_regs regs;
+ struct kvm_vm *vm;
+ struct kvm_run *run;
+ struct kvm_x86_state *state;
+ int stage, stage_reported;
+
+ /* Create VM */
+ vm = vm_create_default(VCPU_ID, 0, guest_code);
+
+ vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+
+ run = vcpu_state(vm, VCPU_ID);
+
+ vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, SMRAM_GPA,
+ SMRAM_MEMSLOT, SMRAM_PAGES, 0);
+ TEST_ASSERT(vm_phy_pages_alloc(vm, SMRAM_PAGES, SMRAM_GPA, SMRAM_MEMSLOT)
+ == SMRAM_GPA, "could not allocate guest physical addresses?");
+
+ memset(addr_gpa2hva(vm, SMRAM_GPA), 0x0, SMRAM_SIZE);
+ memcpy(addr_gpa2hva(vm, SMRAM_GPA) + 0x8000, smi_handler,
+ sizeof(smi_handler));
+
+ vcpu_set_msr(vm, VCPU_ID, MSR_IA32_SMBASE, SMRAM_GPA);
+
+ if (kvm_check_cap(KVM_CAP_NESTED_STATE)) {
+ vmx_pages = vcpu_alloc_vmx(vm, &vmx_pages_gva);
+ vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva);
+ } else {
+ printf("will skip SMM test with VMX enabled\n");
+ vcpu_args_set(vm, VCPU_ID, 1, 0);
+ }
+
+ for (stage = 1;; stage++) {
+ _vcpu_run(vm, VCPU_ID);
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+ "Stage %d: unexpected exit reason: %u (%s),\n",
+ stage, run->exit_reason,
+ exit_reason_str(run->exit_reason));
+
+ memset(®s, 0, sizeof(regs));
+ vcpu_regs_get(vm, VCPU_ID, ®s);
+
+ stage_reported = regs.rax & 0xff;
+
+ if (stage_reported == DONE)
+ goto done;
+
+ TEST_ASSERT(stage_reported == stage ||
+ stage_reported == SMRAM_STAGE,
+ "Unexpected stage: #%x, got %x",
+ stage, stage_reported);
+
+ state = vcpu_save_state(vm, VCPU_ID);
+ kvm_vm_release(vm);
+ kvm_vm_restart(vm, O_RDWR);
+ vm_vcpu_add(vm, VCPU_ID, 0, 0);
+ vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+ vcpu_load_state(vm, VCPU_ID, state);
+ run = vcpu_state(vm, VCPU_ID);
+ free(state);
+ }
+
+done:
+ kvm_vm_free(vm);
+}
stage, run->exit_reason,
exit_reason_str(run->exit_reason));
- memset(®s1, 0, sizeof(regs1));
- vcpu_regs_get(vm, VCPU_ID, ®s1);
switch (get_ucall(vm, VCPU_ID, &uc)) {
case UCALL_ABORT:
TEST_ASSERT(false, "%s at %s:%d", (const char *)uc.args[0],
stage, (ulong)uc.args[1]);
state = vcpu_save_state(vm, VCPU_ID);
+ memset(®s1, 0, sizeof(regs1));
+ vcpu_regs_get(vm, VCPU_ID, ®s1);
+
kvm_vm_release(vm);
/* Restore state in a new VM. */
ksft_skip=4
# all tests in this script. Can be overridden with -t option
-TESTS="unregister down carrier nexthop ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics ipv4_route_metrics"
+TESTS="unregister down carrier nexthop ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics ipv4_route_metrics ipv4_route_v6_gw"
+
VERBOSE=0
PAUSE_ON_FAIL=no
PAUSE=no
{
set -e
ip netns add ns1
+ ip netns set ns1 auto
$IP link set dev lo up
ip netns exec ns1 sysctl -qw net.ipv4.ip_forward=1
ip netns exec ns1 sysctl -qw net.ipv6.conf.all.forwarding=1
return $rc
}
+check_expected()
+{
+ local out="$1"
+ local expected="$2"
+ local rc=0
+
+ [ "${out}" = "${expected}" ] && return 0
+
+ if [ -z "${out}" ]; then
+ if [ "$VERBOSE" = "1" ]; then
+ printf "\nNo route entry found\n"
+ printf "Expected:\n"
+ printf " ${expected}\n"
+ fi
+ return 1
+ fi
+
+ # tricky way to convert output to 1-line without ip's
+ # messy '\'; this drops all extra white space
+ out=$(echo ${out})
+ if [ "${out}" != "${expected}" ]; then
+ rc=1
+ if [ "${VERBOSE}" = "1" ]; then
+ printf " Unexpected route entry. Have:\n"
+ printf " ${out}\n"
+ printf " Expected:\n"
+ printf " ${expected}\n\n"
+ fi
+ fi
+
+ return $rc
+}
+
# add route for a prefix, flushing any existing routes first
# expected to be the first step of a test
add_route6()
pfx=$1
out=$($IP -6 ro ls match ${pfx} | sed -e 's/ pref medium//')
- [ "${out}" = "${expected}" ] && return 0
-
- if [ -z "${out}" ]; then
- if [ "$VERBOSE" = "1" ]; then
- printf "\nNo route entry found\n"
- printf "Expected:\n"
- printf " ${expected}\n"
- fi
- return 1
- fi
-
- # tricky way to convert output to 1-line without ip's
- # messy '\'; this drops all extra white space
- out=$(echo ${out})
- if [ "${out}" != "${expected}" ]; then
- rc=1
- if [ "${VERBOSE}" = "1" ]; then
- printf " Unexpected route entry. Have:\n"
- printf " ${out}\n"
- printf " Expected:\n"
- printf " ${expected}\n\n"
- fi
- fi
-
- return $rc
+ check_expected "${out}" "${expected}"
}
route_cleanup()
set -e
ip netns add ns2
+ ip netns set ns2 auto
ip -netns ns2 link set dev lo up
ip netns exec ns2 sysctl -qw net.ipv4.ip_forward=1
ip netns exec ns2 sysctl -qw net.ipv6.conf.all.forwarding=1
ip -netns ns2 addr add 172.16.103.2/24 dev veth4
ip -netns ns2 addr add 172.16.104.1/24 dev dummy1
- set +ex
+ set +e
}
# assumption is that basic add of a single path route works
run_cmd "$IP li set dev dummy2 down"
rc=$?
if [ $rc -eq 0 ]; then
- check_route6 ""
+ out=$($IP -6 ro ls match 2001:db8:104::/64)
+ check_expected "${out}" ""
rc=$?
fi
log_test $rc 0 "Prefix route removed on link down"
local pfx
local expected="$1"
local out
- local rc=0
set -- $expected
pfx=$1
[ "${pfx}" = "unreachable" ] && pfx=$2
out=$($IP ro ls match ${pfx})
- [ "${out}" = "${expected}" ] && return 0
-
- if [ -z "${out}" ]; then
- if [ "$VERBOSE" = "1" ]; then
- printf "\nNo route entry found\n"
- printf "Expected:\n"
- printf " ${expected}\n"
- fi
- return 1
- fi
-
- # tricky way to convert output to 1-line without ip's
- # messy '\'; this drops all extra white space
- out=$(echo ${out})
- if [ "${out}" != "${expected}" ]; then
- rc=1
- if [ "${VERBOSE}" = "1" ]; then
- printf " Unexpected route entry. Have:\n"
- printf " ${out}\n"
- printf " Expected:\n"
- printf " ${expected}\n\n"
- fi
- fi
-
- return $rc
+ check_expected "${out}" "${expected}"
}
# assumption is that basic add of a single path route works
run_cmd "$IP li set dev dummy2 down"
rc=$?
if [ $rc -eq 0 ]; then
- check_route ""
+ out=$($IP ro ls match 172.16.104.0/24)
+ check_expected "${out}" ""
rc=$?
fi
log_test $rc 0 "Prefix route removed on link down"
route_cleanup
}
+ipv4_route_v6_gw_test()
+{
+ local rc
+
+ echo
+ echo "IPv4 route with IPv6 gateway tests"
+
+ route_setup
+ sleep 2
+
+ #
+ # single path route
+ #
+ run_cmd "$IP ro add 172.16.104.0/24 via inet6 2001:db8:101::2"
+ rc=$?
+ log_test $rc 0 "Single path route with IPv6 gateway"
+ if [ $rc -eq 0 ]; then
+ check_route "172.16.104.0/24 via inet6 2001:db8:101::2 dev veth1"
+ fi
+
+ run_cmd "ip netns exec ns1 ping -w1 -c1 172.16.104.1"
+ log_test $rc 0 "Single path route with IPv6 gateway - ping"
+
+ run_cmd "$IP ro del 172.16.104.0/24 via inet6 2001:db8:101::2"
+ rc=$?
+ log_test $rc 0 "Single path route delete"
+ if [ $rc -eq 0 ]; then
+ check_route "172.16.112.0/24"
+ fi
+
+ #
+ # multipath - v6 then v4
+ #
+ run_cmd "$IP ro add 172.16.104.0/24 nexthop via inet6 2001:db8:101::2 dev veth1 nexthop via 172.16.103.2 dev veth3"
+ rc=$?
+ log_test $rc 0 "Multipath route add - v6 nexthop then v4"
+ if [ $rc -eq 0 ]; then
+ check_route "172.16.104.0/24 nexthop via inet6 2001:db8:101::2 dev veth1 weight 1 nexthop via 172.16.103.2 dev veth3 weight 1"
+ fi
+
+ run_cmd "$IP ro del 172.16.104.0/24 nexthop via 172.16.103.2 dev veth3 nexthop via inet6 2001:db8:101::2 dev veth1"
+ log_test $? 2 " Multipath route delete - nexthops in wrong order"
+
+ run_cmd "$IP ro del 172.16.104.0/24 nexthop via inet6 2001:db8:101::2 dev veth1 nexthop via 172.16.103.2 dev veth3"
+ log_test $? 0 " Multipath route delete exact match"
+
+ #
+ # multipath - v4 then v6
+ #
+ run_cmd "$IP ro add 172.16.104.0/24 nexthop via 172.16.103.2 dev veth3 nexthop via inet6 2001:db8:101::2 dev veth1"
+ rc=$?
+ log_test $rc 0 "Multipath route add - v4 nexthop then v6"
+ if [ $rc -eq 0 ]; then
+ check_route "172.16.104.0/24 nexthop via 172.16.103.2 dev veth3 weight 1 nexthop via inet6 2001:db8:101::2 dev veth1 weight 1"
+ fi
+
+ run_cmd "$IP ro del 172.16.104.0/24 nexthop via inet6 2001:db8:101::2 dev veth1 nexthop via 172.16.103.2 dev veth3"
+ log_test $? 2 " Multipath route delete - nexthops in wrong order"
+
+ run_cmd "$IP ro del 172.16.104.0/24 nexthop via 172.16.103.2 dev veth3 nexthop via inet6 2001:db8:101::2 dev veth1"
+ log_test $? 0 " Multipath route delete exact match"
+
+ route_cleanup
+}
################################################################################
# usage
ipv4_addr_metric) ipv4_addr_metric_test;;
ipv6_route_metrics) ipv6_route_metrics_test;;
ipv4_route_metrics) ipv4_route_metrics_test;;
+ ipv4_route_v6_gw) ipv4_route_v6_gw_test;;
help) echo "Test names: $TESTS"; exit 0;;
esac
--- /dev/null
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="reportleave_test"
+NUM_NETIFS=4
+CHECK_TC="yes"
+TEST_GROUP="239.10.10.10"
+TEST_GROUP_MAC="01:00:5e:0a:0a:0a"
+source lib.sh
+
+h1_create()
+{
+ simple_if_init $h1 192.0.2.1/24 2001:db8:1::1/64
+}
+
+h1_destroy()
+{
+ simple_if_fini $h1 192.0.2.1/24 2001:db8:1::1/64
+}
+
+h2_create()
+{
+ simple_if_init $h2 192.0.2.2/24 2001:db8:1::2/64
+}
+
+h2_destroy()
+{
+ simple_if_fini $h2 192.0.2.2/24 2001:db8:1::2/64
+}
+
+switch_create()
+{
+ ip link add dev br0 type bridge mcast_snooping 1 mcast_querier 1
+
+ ip link set dev $swp1 master br0
+ ip link set dev $swp2 master br0
+
+ ip link set dev br0 up
+ ip link set dev $swp1 up
+ ip link set dev $swp2 up
+}
+
+switch_destroy()
+{
+ ip link set dev $swp2 down
+ ip link set dev $swp1 down
+
+ ip link del dev br0
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ swp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ vrf_prepare
+
+ h1_create
+ h2_create
+
+ switch_create
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ switch_destroy
+
+ # Always cleanup the mcast group
+ ip address del dev $h2 $TEST_GROUP/32 2>&1 1>/dev/null
+
+ h2_destroy
+ h1_destroy
+
+ vrf_cleanup
+}
+
+# return 0 if the packet wasn't seen on host2_if or 1 if it was
+mcast_packet_test()
+{
+ local mac=$1
+ local ip=$2
+ local host1_if=$3
+ local host2_if=$4
+ local seen=0
+
+ # Add an ACL on `host2_if` which will tell us whether the packet
+ # was received by it or not.
+ tc qdisc add dev $host2_if ingress
+ tc filter add dev $host2_if ingress protocol ip pref 1 handle 101 \
+ flower dst_mac $mac action drop
+
+ $MZ $host1_if -c 1 -p 64 -b $mac -B $ip -t udp "dp=4096,sp=2048" -q
+ sleep 1
+
+ tc -j -s filter show dev $host2_if ingress \
+ | jq -e ".[] | select(.options.handle == 101) \
+ | select(.options.actions[0].stats.packets == 1)" &> /dev/null
+ if [[ $? -eq 0 ]]; then
+ seen=1
+ fi
+
+ tc filter del dev $host2_if ingress protocol ip pref 1 handle 101 flower
+ tc qdisc del dev $host2_if ingress
+
+ return $seen
+}
+
+reportleave_test()
+{
+ RET=0
+ ip address add dev $h2 $TEST_GROUP/32 autojoin
+ check_err $? "Could not join $TEST_GROUP"
+
+ sleep 5
+ bridge mdb show dev br0 | grep $TEST_GROUP 1>/dev/null
+ check_err $? "Report didn't create mdb entry for $TEST_GROUP"
+
+ mcast_packet_test $TEST_GROUP_MAC $TEST_GROUP $h1 $h2
+ check_fail $? "Traffic to $TEST_GROUP wasn't forwarded"
+
+ log_test "IGMP report $TEST_GROUP"
+
+ RET=0
+ bridge mdb show dev br0 | grep $TEST_GROUP 1>/dev/null
+ check_err $? "mdb entry for $TEST_GROUP is missing"
+
+ ip address del dev $h2 $TEST_GROUP/32
+ check_err $? "Could not leave $TEST_GROUP"
+
+ sleep 5
+ bridge mdb show dev br0 | grep $TEST_GROUP 1>/dev/null
+ check_fail $? "Leave didn't delete mdb entry for $TEST_GROUP"
+
+ mcast_packet_test $TEST_GROUP_MAC $TEST_GROUP $h1 $h2
+ check_err $? "Traffic to $TEST_GROUP was forwarded without mdb entry"
+
+ log_test "IGMP leave $TEST_GROUP"
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
# Kselftest framework requirement - SKIP code is 4.
ksft_skip=4
+PAUSE_ON_FAIL=no
+VERBOSE=0
+TRACING=0
+
# Some systems don't have a ping6 binary anymore
which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping)
err_buf=
}
+run_cmd() {
+ cmd="$*"
+
+ if [ "$VERBOSE" = "1" ]; then
+ printf " COMMAND: $cmd\n"
+ fi
+
+ out="$($cmd 2>&1)"
+ rc=$?
+ if [ "$VERBOSE" = "1" -a -n "$out" ]; then
+ echo " $out"
+ echo
+ fi
+
+ return $rc
+}
+
# Find the auto-generated name for this namespace
nsname() {
eval echo \$NS_$1
fi
fi
- ${ns_a} ip fou add port 5555 ipproto ${ipproto} || return 2
- ${ns_a} ip link add ${encap}_a type ${type} ${mode} local ${a_addr} remote ${b_addr} encap ${encap} encap-sport auto encap-dport 5556 || return 2
+ run_cmd ${ns_a} ip fou add port 5555 ipproto ${ipproto} || return 2
+ run_cmd ${ns_a} ip link add ${encap}_a type ${type} ${mode} local ${a_addr} remote ${b_addr} encap ${encap} encap-sport auto encap-dport 5556 || return 2
- ${ns_b} ip fou add port 5556 ipproto ${ipproto}
- ${ns_b} ip link add ${encap}_b type ${type} ${mode} local ${b_addr} remote ${a_addr} encap ${encap} encap-sport auto encap-dport 5555
+ run_cmd ${ns_b} ip fou add port 5556 ipproto ${ipproto}
+ run_cmd ${ns_b} ip link add ${encap}_b type ${type} ${mode} local ${b_addr} remote ${a_addr} encap ${encap} encap-sport auto encap-dport 5555
if [ "${inner}" = "4" ]; then
- ${ns_a} ip addr add ${tunnel4_a_addr}/${tunnel4_mask} dev ${encap}_a
- ${ns_b} ip addr add ${tunnel4_b_addr}/${tunnel4_mask} dev ${encap}_b
+ run_cmd ${ns_a} ip addr add ${tunnel4_a_addr}/${tunnel4_mask} dev ${encap}_a
+ run_cmd ${ns_b} ip addr add ${tunnel4_b_addr}/${tunnel4_mask} dev ${encap}_b
else
- ${ns_a} ip addr add ${tunnel6_a_addr}/${tunnel6_mask} dev ${encap}_a
- ${ns_b} ip addr add ${tunnel6_b_addr}/${tunnel6_mask} dev ${encap}_b
+ run_cmd ${ns_a} ip addr add ${tunnel6_a_addr}/${tunnel6_mask} dev ${encap}_a
+ run_cmd ${ns_b} ip addr add ${tunnel6_b_addr}/${tunnel6_mask} dev ${encap}_b
fi
- ${ns_a} ip link set ${encap}_a up
- ${ns_b} ip link set ${encap}_b up
+ run_cmd ${ns_a} ip link set ${encap}_a up
+ run_cmd ${ns_b} ip link set ${encap}_b up
}
setup_fou44() {
}
setup_veth() {
- ${ns_a} ip link add veth_a type veth peer name veth_b || return 1
- ${ns_a} ip link set veth_b netns ${NS_B}
+ run_cmd ${ns_a} ip link add veth_a type veth peer name veth_b || return 1
+ run_cmd ${ns_a} ip link set veth_b netns ${NS_B}
- ${ns_a} ip addr add ${veth4_a_addr}/${veth4_mask} dev veth_a
- ${ns_b} ip addr add ${veth4_b_addr}/${veth4_mask} dev veth_b
+ run_cmd ${ns_a} ip addr add ${veth4_a_addr}/${veth4_mask} dev veth_a
+ run_cmd ${ns_b} ip addr add ${veth4_b_addr}/${veth4_mask} dev veth_b
- ${ns_a} ip addr add ${veth6_a_addr}/${veth6_mask} dev veth_a
- ${ns_b} ip addr add ${veth6_b_addr}/${veth6_mask} dev veth_b
+ run_cmd ${ns_a} ip addr add ${veth6_a_addr}/${veth6_mask} dev veth_a
+ run_cmd ${ns_b} ip addr add ${veth6_b_addr}/${veth6_mask} dev veth_b
- ${ns_a} ip link set veth_a up
- ${ns_b} ip link set veth_b up
+ run_cmd ${ns_a} ip link set veth_a up
+ run_cmd ${ns_b} ip link set veth_b up
}
setup_vti() {
[ ${proto} -eq 6 ] && vti_type="vti6" || vti_type="vti"
- ${ns_a} ip link add vti${proto}_a type ${vti_type} local ${veth_a_addr} remote ${veth_b_addr} key 10 || return 1
- ${ns_b} ip link add vti${proto}_b type ${vti_type} local ${veth_b_addr} remote ${veth_a_addr} key 10
+ run_cmd ${ns_a} ip link add vti${proto}_a type ${vti_type} local ${veth_a_addr} remote ${veth_b_addr} key 10 || return 1
+ run_cmd ${ns_b} ip link add vti${proto}_b type ${vti_type} local ${veth_b_addr} remote ${veth_a_addr} key 10
- ${ns_a} ip addr add ${vti_a_addr}/${vti_mask} dev vti${proto}_a
- ${ns_b} ip addr add ${vti_b_addr}/${vti_mask} dev vti${proto}_b
+ run_cmd ${ns_a} ip addr add ${vti_a_addr}/${vti_mask} dev vti${proto}_a
+ run_cmd ${ns_b} ip addr add ${vti_b_addr}/${vti_mask} dev vti${proto}_b
- ${ns_a} ip link set vti${proto}_a up
- ${ns_b} ip link set vti${proto}_b up
+ run_cmd ${ns_a} ip link set vti${proto}_a up
+ run_cmd ${ns_b} ip link set vti${proto}_b up
}
setup_vti4() {
opts_b=""
fi
- ${ns_a} ip link add ${type}_a type ${type} id 1 ${opts_a} remote ${b_addr} ${opts} || return 1
- ${ns_b} ip link add ${type}_b type ${type} id 1 ${opts_b} remote ${a_addr} ${opts}
+ run_cmd ${ns_a} ip link add ${type}_a type ${type} id 1 ${opts_a} remote ${b_addr} ${opts} || return 1
+ run_cmd ${ns_b} ip link add ${type}_b type ${type} id 1 ${opts_b} remote ${a_addr} ${opts}
- ${ns_a} ip addr add ${tunnel4_a_addr}/${tunnel4_mask} dev ${type}_a
- ${ns_b} ip addr add ${tunnel4_b_addr}/${tunnel4_mask} dev ${type}_b
+ run_cmd ${ns_a} ip addr add ${tunnel4_a_addr}/${tunnel4_mask} dev ${type}_a
+ run_cmd ${ns_b} ip addr add ${tunnel4_b_addr}/${tunnel4_mask} dev ${type}_b
- ${ns_a} ip addr add ${tunnel6_a_addr}/${tunnel6_mask} dev ${type}_a
- ${ns_b} ip addr add ${tunnel6_b_addr}/${tunnel6_mask} dev ${type}_b
+ run_cmd ${ns_a} ip addr add ${tunnel6_a_addr}/${tunnel6_mask} dev ${type}_a
+ run_cmd ${ns_b} ip addr add ${tunnel6_b_addr}/${tunnel6_mask} dev ${type}_b
- ${ns_a} ip link set ${type}_a up
- ${ns_b} ip link set ${type}_b up
+ run_cmd ${ns_a} ip link set ${type}_a up
+ run_cmd ${ns_b} ip link set ${type}_b up
}
setup_geneve4() {
veth_a_addr="${2}"
veth_b_addr="${3}"
- ${ns_a} ip -${proto} xfrm state add src ${veth_a_addr} dst ${veth_b_addr} spi 0x1000 proto esp aead "rfc4106(gcm(aes))" 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel || return 1
- ${ns_a} ip -${proto} xfrm state add src ${veth_b_addr} dst ${veth_a_addr} spi 0x1001 proto esp aead "rfc4106(gcm(aes))" 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel
- ${ns_a} ip -${proto} xfrm policy add dir out mark 10 tmpl src ${veth_a_addr} dst ${veth_b_addr} proto esp mode tunnel
- ${ns_a} ip -${proto} xfrm policy add dir in mark 10 tmpl src ${veth_b_addr} dst ${veth_a_addr} proto esp mode tunnel
+ run_cmd "${ns_a} ip -${proto} xfrm state add src ${veth_a_addr} dst ${veth_b_addr} spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel" || return 1
+ run_cmd "${ns_a} ip -${proto} xfrm state add src ${veth_b_addr} dst ${veth_a_addr} spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel"
+ run_cmd "${ns_a} ip -${proto} xfrm policy add dir out mark 10 tmpl src ${veth_a_addr} dst ${veth_b_addr} proto esp mode tunnel"
+ run_cmd "${ns_a} ip -${proto} xfrm policy add dir in mark 10 tmpl src ${veth_b_addr} dst ${veth_a_addr} proto esp mode tunnel"
- ${ns_b} ip -${proto} xfrm state add src ${veth_a_addr} dst ${veth_b_addr} spi 0x1000 proto esp aead "rfc4106(gcm(aes))" 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel
- ${ns_b} ip -${proto} xfrm state add src ${veth_b_addr} dst ${veth_a_addr} spi 0x1001 proto esp aead "rfc4106(gcm(aes))" 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel
- ${ns_b} ip -${proto} xfrm policy add dir out mark 10 tmpl src ${veth_b_addr} dst ${veth_a_addr} proto esp mode tunnel
- ${ns_b} ip -${proto} xfrm policy add dir in mark 10 tmpl src ${veth_a_addr} dst ${veth_b_addr} proto esp mode tunnel
+ run_cmd "${ns_b} ip -${proto} xfrm state add src ${veth_a_addr} dst ${veth_b_addr} spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel"
+ run_cmd "${ns_b} ip -${proto} xfrm state add src ${veth_b_addr} dst ${veth_a_addr} spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel"
+ run_cmd "${ns_b} ip -${proto} xfrm policy add dir out mark 10 tmpl src ${veth_b_addr} dst ${veth_a_addr} proto esp mode tunnel"
+ run_cmd "${ns_b} ip -${proto} xfrm policy add dir in mark 10 tmpl src ${veth_a_addr} dst ${veth_b_addr} proto esp mode tunnel"
}
setup_xfrm4() {
}
trace() {
- [ $tracing -eq 0 ] && return
+ [ $TRACING -eq 0 ] && return
for arg do
[ "${ns_cmd}" = "" ] && ns_cmd="${arg}" && continue
mtu "${ns_b}" veth_B-R2 1500
# Create route exceptions
- ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s 1800 ${dst1} > /dev/null
- ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s 1800 ${dst2} > /dev/null
+ run_cmd ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s 1800 ${dst1}
+ run_cmd ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s 1800 ${dst2}
# Check that exceptions have been created with the correct PMTU
pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst1})"
# Decrease remote MTU on path via R2, get new exception
mtu "${ns_r2}" veth_R2-B 400
mtu "${ns_b}" veth_B-R2 400
- ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s 1400 ${dst2} > /dev/null
+ run_cmd ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s 1400 ${dst2}
pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
check_pmtu_value "lock 552" "${pmtu_2}" "exceeding MTU, with MTU < min_pmtu" || return 1
check_pmtu_value "1500" "${pmtu_2}" "increasing local MTU" || return 1
# Get new exception
- ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s 1400 ${dst2} > /dev/null
+ run_cmd ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s 1400 ${dst2}
pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
check_pmtu_value "lock 552" "${pmtu_2}" "exceeding MTU, with MTU < min_pmtu" || return 1
}
mtu "${ns_a}" ${type}_a $((${ll_mtu} + 1000))
mtu "${ns_b}" ${type}_b $((${ll_mtu} + 1000))
- ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s $((${ll_mtu} + 500)) ${dst} > /dev/null
+ run_cmd ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s $((${ll_mtu} + 500)) ${dst}
# Check that exception was created
pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst})"
mtu "${ns_a}" ${encap}_a $((${ll_mtu} + 1000))
mtu "${ns_b}" ${encap}_b $((${ll_mtu} + 1000))
- ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s $((${ll_mtu} + 500)) ${dst} > /dev/null
+ run_cmd ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s $((${ll_mtu} + 500)) ${dst}
# Check that exception was created
pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst})"
# Send DF packet without exceeding link layer MTU, check that no
# exception is created
- ${ns_a} ping -q -M want -i 0.1 -w 1 -s ${ping_payload} ${tunnel4_b_addr} > /dev/null
+ run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s ${ping_payload} ${tunnel4_b_addr}
pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})"
check_pmtu_value "" "${pmtu}" "sending packet smaller than PMTU (IP payload length ${esp_payload_rfc4106})" || return 1
# Now exceed link layer MTU by one byte, check that exception is created
# with the right PMTU value
- ${ns_a} ping -q -M want -i 0.1 -w 1 -s $((ping_payload + 1)) ${tunnel4_b_addr} > /dev/null
+ run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s $((ping_payload + 1)) ${tunnel4_b_addr}
pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})"
check_pmtu_value "${esp_payload_rfc4106}" "${pmtu}" "exceeding PMTU (IP payload length $((esp_payload_rfc4106 + 1)))"
}
mtu "${ns_b}" veth_b 4000
mtu "${ns_a}" vti6_a 5000
mtu "${ns_b}" vti6_b 5000
- ${ns_a} ${ping6} -q -i 0.1 -w 1 -s 60000 ${tunnel6_b_addr} > /dev/null
+ run_cmd ${ns_a} ${ping6} -q -i 0.1 -w 1 -s 60000 ${tunnel6_b_addr}
# Check that exception was created
pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})"
test_pmtu_vti4_link_add_mtu() {
setup namespaces || return 2
- ${ns_a} ip link add vti4_a type vti local ${veth4_a_addr} remote ${veth4_b_addr} key 10
+ run_cmd ${ns_a} ip link add vti4_a type vti local ${veth4_a_addr} remote ${veth4_b_addr} key 10
[ $? -ne 0 ] && err " vti not supported" && return 2
- ${ns_a} ip link del vti4_a
+ run_cmd ${ns_a} ip link del vti4_a
fail=0
max=$((65535 - 20))
# Check invalid values first
for v in $((min - 1)) $((max + 1)); do
- ${ns_a} ip link add vti4_a mtu ${v} type vti local ${veth4_a_addr} remote ${veth4_b_addr} key 10 2>/dev/null
+ run_cmd ${ns_a} ip link add vti4_a mtu ${v} type vti local ${veth4_a_addr} remote ${veth4_b_addr} key 10
# This can fail, or MTU can be adjusted to a proper value
[ $? -ne 0 ] && continue
mtu="$(link_get_mtu "${ns_a}" vti4_a)"
err " vti tunnel created with invalid MTU ${mtu}"
fail=1
fi
- ${ns_a} ip link del vti4_a
+ run_cmd ${ns_a} ip link del vti4_a
done
# Now check valid values
for v in ${min} 1300 ${max}; do
- ${ns_a} ip link add vti4_a mtu ${v} type vti local ${veth4_a_addr} remote ${veth4_b_addr} key 10
+ run_cmd ${ns_a} ip link add vti4_a mtu ${v} type vti local ${veth4_a_addr} remote ${veth4_b_addr} key 10
mtu="$(link_get_mtu "${ns_a}" vti4_a)"
- ${ns_a} ip link del vti4_a
+ run_cmd ${ns_a} ip link del vti4_a
if [ "${mtu}" != "${v}" ]; then
err " vti MTU ${mtu} doesn't match configured value ${v}"
fail=1
test_pmtu_vti6_link_add_mtu() {
setup namespaces || return 2
- ${ns_a} ip link add vti6_a type vti6 local ${veth6_a_addr} remote ${veth6_b_addr} key 10
+ run_cmd ${ns_a} ip link add vti6_a type vti6 local ${veth6_a_addr} remote ${veth6_b_addr} key 10
[ $? -ne 0 ] && err " vti6 not supported" && return 2
- ${ns_a} ip link del vti6_a
+ run_cmd ${ns_a} ip link del vti6_a
fail=0
max=$((65535 - 40))
# Check invalid values first
for v in $((min - 1)) $((max + 1)); do
- ${ns_a} ip link add vti6_a mtu ${v} type vti6 local ${veth6_a_addr} remote ${veth6_b_addr} key 10 2>/dev/null
+ run_cmd ${ns_a} ip link add vti6_a mtu ${v} type vti6 local ${veth6_a_addr} remote ${veth6_b_addr} key 10
# This can fail, or MTU can be adjusted to a proper value
[ $? -ne 0 ] && continue
mtu="$(link_get_mtu "${ns_a}" vti6_a)"
err " vti6 tunnel created with invalid MTU ${v}"
fail=1
fi
- ${ns_a} ip link del vti6_a
+ run_cmd ${ns_a} ip link del vti6_a
done
# Now check valid values
for v in 68 1280 1300 $((65535 - 40)); do
- ${ns_a} ip link add vti6_a mtu ${v} type vti6 local ${veth6_a_addr} remote ${veth6_b_addr} key 10
+ run_cmd ${ns_a} ip link add vti6_a mtu ${v} type vti6 local ${veth6_a_addr} remote ${veth6_b_addr} key 10
mtu="$(link_get_mtu "${ns_a}" vti6_a)"
- ${ns_a} ip link del vti6_a
+ run_cmd ${ns_a} ip link del vti6_a
if [ "${mtu}" != "${v}" ]; then
err " vti6 MTU ${mtu} doesn't match configured value ${v}"
fail=1
test_pmtu_vti6_link_change_mtu() {
setup namespaces || return 2
- ${ns_a} ip link add dummy0 mtu 1500 type dummy
+ run_cmd ${ns_a} ip link add dummy0 mtu 1500 type dummy
[ $? -ne 0 ] && err " dummy not supported" && return 2
- ${ns_a} ip link add dummy1 mtu 3000 type dummy
- ${ns_a} ip link set dummy0 up
- ${ns_a} ip link set dummy1 up
+ run_cmd ${ns_a} ip link add dummy1 mtu 3000 type dummy
+ run_cmd ${ns_a} ip link set dummy0 up
+ run_cmd ${ns_a} ip link set dummy1 up
- ${ns_a} ip addr add ${dummy6_0_addr}/${dummy6_mask} dev dummy0
- ${ns_a} ip addr add ${dummy6_1_addr}/${dummy6_mask} dev dummy1
+ run_cmd ${ns_a} ip addr add ${dummy6_0_addr}/${dummy6_mask} dev dummy0
+ run_cmd ${ns_a} ip addr add ${dummy6_1_addr}/${dummy6_mask} dev dummy1
fail=0
# Create vti6 interface bound to device, passing MTU, check it
- ${ns_a} ip link add vti6_a mtu 1300 type vti6 remote ${dummy6_0_addr} local ${dummy6_0_addr}
+ run_cmd ${ns_a} ip link add vti6_a mtu 1300 type vti6 remote ${dummy6_0_addr} local ${dummy6_0_addr}
mtu="$(link_get_mtu "${ns_a}" vti6_a)"
if [ ${mtu} -ne 1300 ]; then
err " vti6 MTU ${mtu} doesn't match configured value 1300"
# Move to another device with different MTU, without passing MTU, check
# MTU is adjusted
- ${ns_a} ip link set vti6_a type vti6 remote ${dummy6_1_addr} local ${dummy6_1_addr}
+ run_cmd ${ns_a} ip link set vti6_a type vti6 remote ${dummy6_1_addr} local ${dummy6_1_addr}
mtu="$(link_get_mtu "${ns_a}" vti6_a)"
if [ ${mtu} -ne $((3000 - 40)) ]; then
err " vti MTU ${mtu} is not dummy MTU 3000 minus IPv6 header length"
fi
# Move it back, passing MTU, check MTU is not overridden
- ${ns_a} ip link set vti6_a mtu 1280 type vti6 remote ${dummy6_0_addr} local ${dummy6_0_addr}
+ run_cmd ${ns_a} ip link set vti6_a mtu 1280 type vti6 remote ${dummy6_0_addr} local ${dummy6_0_addr}
mtu="$(link_get_mtu "${ns_a}" vti6_a)"
if [ ${mtu} -ne 1280 ]; then
err " vti6 MTU ${mtu} doesn't match configured value 1280"
# Fill exception cache for multiple CPUs (2)
# we can always use inner IPv4 for that
for cpu in ${cpu_list}; do
- taskset --cpu-list ${cpu} ${ns_a} ping -q -M want -i 0.1 -w 1 -s $((${ll_mtu} + 500)) ${tunnel4_b_addr} > /dev/null
+ run_cmd taskset --cpu-list ${cpu} ${ns_a} ping -q -M want -i 0.1 -w 1 -s $((${ll_mtu} + 500)) ${tunnel4_b_addr}
done
${ns_a} ip link del dev veth_A-R1 &
exit 1
}
+################################################################################
+#
exitcode=0
desc=0
+
+while getopts :ptv o
+do
+ case $o in
+ p) PAUSE_ON_FAIL=yes;;
+ v) VERBOSE=1;;
+ t) if which tcpdump > /dev/null 2>&1; then
+ TRACING=1
+ else
+ echo "=== tcpdump not available, tracing disabled"
+ fi
+ ;;
+ *) usage;;
+ esac
+done
+shift $(($OPTIND-1))
+
IFS="
"
-tracing=0
for arg do
- if [ "${arg}" != "${arg#--*}" ]; then
- opt="${arg#--}"
- if [ "${opt}" = "trace" ]; then
- if which tcpdump > /dev/null 2>&1; then
- tracing=1
- else
- echo "=== tcpdump not available, tracing disabled"
- fi
- else
- usage
- fi
- else
- # Check first that all requested tests are available before
- # running any
- command -v > /dev/null "test_${arg}" || { echo "=== Test ${arg} not found"; usage; }
- fi
+ # Check first that all requested tests are available before running any
+ command -v > /dev/null "test_${arg}" || { echo "=== Test ${arg} not found"; usage; }
done
trap cleanup EXIT
(
unset IFS
+
+ if [ "$VERBOSE" = "1" ]; then
+ printf "\n##########################################################################\n\n"
+ fi
+
eval test_${name}
ret=$?
cleanup
printf "TEST: %-60s [ OK ]\n" "${t}"
elif [ $ret -eq 1 ]; then
printf "TEST: %-60s [FAIL]\n" "${t}"
+ if [ "${PAUSE_ON_FAIL}" = "yes" ]; then
+ echo
+ echo "Pausing. Hit enter to continue"
+ read a
+ fi
err_flush
exit 1
elif [ $ret -eq 2 ]; then
# SPDX-License-Identifier: GPL-2.0
# Makefile for netfilter selftests
-TEST_PROGS := nft_trans_stress.sh nft_nat.sh
+TEST_PROGS := nft_trans_stress.sh nft_nat.sh bridge_brouter.sh
include ../lib.mk
--- /dev/null
+#!/bin/bash
+#
+# This test is for bridge 'brouting', i.e. make some packets being routed
+# rather than getting bridged even though they arrive on interface that is
+# part of a bridge.
+
+# eth0 br0 eth0
+# setup is: ns1 <-> ns0 <-> ns2
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+ret=0
+
+ebtables -V > /dev/null 2>&1
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not run test without ebtables"
+ exit $ksft_skip
+fi
+
+ip -Version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not run test without ip tool"
+ exit $ksft_skip
+fi
+
+ip netns add ns0
+ip netns add ns1
+ip netns add ns2
+
+ip link add veth0 netns ns0 type veth peer name eth0 netns ns1
+if [ $? -ne 0 ]; then
+ echo "SKIP: Can't create veth device"
+ exit $ksft_skip
+fi
+ip link add veth1 netns ns0 type veth peer name eth0 netns ns2
+
+ip -net ns0 link set lo up
+ip -net ns0 link set veth0 up
+ip -net ns0 link set veth1 up
+
+ip -net ns0 link add br0 type bridge
+if [ $? -ne 0 ]; then
+ echo "SKIP: Can't create bridge br0"
+ exit $ksft_skip
+fi
+
+ip -net ns0 link set veth0 master br0
+ip -net ns0 link set veth1 master br0
+ip -net ns0 link set br0 up
+ip -net ns0 addr add 10.0.0.1/24 dev br0
+
+# place both in same subnet, ns1 and ns2 connected via ns0:br0
+for i in 1 2; do
+ ip -net ns$i link set lo up
+ ip -net ns$i link set eth0 up
+ ip -net ns$i addr add 10.0.0.1$i/24 dev eth0
+done
+
+test_ebtables_broute()
+{
+ local cipt
+
+ # redirect is needed so the dstmac is rewritten to the bridge itself,
+ # ip stack won't process OTHERHOST (foreign unicast mac) packets.
+ ip netns exec ns0 ebtables -t broute -A BROUTING -p ipv4 --ip-protocol icmp -j redirect --redirect-target=DROP
+ if [ $? -ne 0 ]; then
+ echo "SKIP: Could not add ebtables broute redirect rule"
+ return $ksft_skip
+ fi
+
+ # ping netns1, expected to not work (ip forwarding is off)
+ ip netns exec ns1 ping -q -c 1 10.0.0.12 > /dev/null 2>&1
+ if [ $? -eq 0 ]; then
+ echo "ERROR: ping works, should have failed" 1>&2
+ return 1
+ fi
+
+ # enable forwarding on both interfaces.
+ # neither needs an ip address, but at least the bridge needs
+ # an ip address in same network segment as ns1 and ns2 (ns0
+ # needs to be able to determine route for to-be-forwarded packet).
+ ip netns exec ns0 sysctl -q net.ipv4.conf.veth0.forwarding=1
+ ip netns exec ns0 sysctl -q net.ipv4.conf.veth1.forwarding=1
+
+ sleep 1
+
+ ip netns exec ns1 ping -q -c 1 10.0.0.12 > /dev/null
+ if [ $? -ne 0 ]; then
+ echo "ERROR: ping did not work, but it should (broute+forward)" 1>&2
+ return 1
+ fi
+
+ echo "PASS: ns1/ns2 connectivity with active broute rule"
+ ip netns exec ns0 ebtables -t broute -F
+
+ # ping netns1, expected to work (frames are bridged)
+ ip netns exec ns1 ping -q -c 1 10.0.0.12 > /dev/null
+ if [ $? -ne 0 ]; then
+ echo "ERROR: ping did not work, but it should (bridged)" 1>&2
+ return 1
+ fi
+
+ ip netns exec ns0 ebtables -t filter -A FORWARD -p ipv4 --ip-protocol icmp -j DROP
+
+ # ping netns1, expected to not work (DROP in bridge forward)
+ ip netns exec ns1 ping -q -c 1 10.0.0.12 > /dev/null 2>&1
+ if [ $? -eq 0 ]; then
+ echo "ERROR: ping works, should have failed (icmp forward drop)" 1>&2
+ return 1
+ fi
+
+ # re-activate brouter
+ ip netns exec ns0 ebtables -t broute -A BROUTING -p ipv4 --ip-protocol icmp -j redirect --redirect-target=DROP
+
+ ip netns exec ns2 ping -q -c 1 10.0.0.11 > /dev/null
+ if [ $? -ne 0 ]; then
+ echo "ERROR: ping did not work, but it should (broute+forward 2)" 1>&2
+ return 1
+ fi
+
+ echo "PASS: ns1/ns2 connectivity with active broute rule and bridge forward drop"
+ return 0
+}
+
+# test basic connectivity
+ip netns exec ns1 ping -c 1 -q 10.0.0.12 > /dev/null
+if [ $? -ne 0 ]; then
+ echo "ERROR: Could not reach ns2 from ns1" 1>&2
+ ret=1
+fi
+
+ip netns exec ns2 ping -c 1 -q 10.0.0.11 > /dev/null
+if [ $? -ne 0 ]; then
+ echo "ERROR: Could not reach ns1 from ns2" 1>&2
+ ret=1
+fi
+
+if [ $ret -eq 0 ];then
+ echo "PASS: netns connectivity: ns1 and ns2 can reach each other"
+fi
+
+test_ebtables_broute
+ret=$?
+for i in 0 1 2; do ip netns del ns$i;done
+
+exit $ret
# Kselftest framework requirement - SKIP code is 4.
ksft_skip=4
ret=0
+test_inet_nat=true
nft --version > /dev/null 2>&1
if [ $? -ne 0 ];then
test_local_dnat6()
{
+ local family=$1
local lret=0
+ local IPF=""
+
+ if [ $family = "inet" ];then
+ IPF="ip6"
+ fi
+
ip netns exec ns0 nft -f - <<EOF
-table ip6 nat {
+table $family nat {
chain output {
type nat hook output priority 0; policy accept;
- ip6 daddr dead:1::99 dnat to dead:2::99
+ ip6 daddr dead:1::99 dnat $IPF to dead:2::99
}
}
EOF
if [ $? -ne 0 ]; then
- echo "SKIP: Could not add add ip6 dnat hook"
+ echo "SKIP: Could not add add $family dnat hook"
return $ksft_skip
fi
fi
done
- test $lret -eq 0 && echo "PASS: ipv6 ping to ns1 was NATted to ns2"
+ test $lret -eq 0 && echo "PASS: ipv6 ping to ns1 was $family NATted to ns2"
ip netns exec ns0 nft flush chain ip6 nat output
return $lret
test_local_dnat()
{
+ local family=$1
local lret=0
-ip netns exec ns0 nft -f - <<EOF
-table ip nat {
+ local IPF=""
+
+ if [ $family = "inet" ];then
+ IPF="ip"
+ fi
+
+ip netns exec ns0 nft -f - <<EOF 2>/dev/null
+table $family nat {
chain output {
type nat hook output priority 0; policy accept;
- ip daddr 10.0.1.99 dnat to 10.0.2.99
+ ip daddr 10.0.1.99 dnat $IPF to 10.0.2.99
}
}
EOF
+ if [ $? -ne 0 ]; then
+ if [ $family = "inet" ];then
+ echo "SKIP: inet nat tests"
+ test_inet_nat=false
+ return $ksft_skip
+ fi
+ echo "SKIP: Could not add add $family dnat hook"
+ return $ksft_skip
+ fi
+
# ping netns1, expect rewrite to netns2
ip netns exec ns0 ping -q -c 1 10.0.1.99 > /dev/null
if [ $? -ne 0 ]; then
fi
done
- test $lret -eq 0 && echo "PASS: ping to ns1 was NATted to ns2"
+ test $lret -eq 0 && echo "PASS: ping to ns1 was $family NATted to ns2"
- ip netns exec ns0 nft flush chain ip nat output
+ ip netns exec ns0 nft flush chain $family nat output
reset_counters
ip netns exec ns0 ping -q -c 1 10.0.1.99 > /dev/null
fi
done
- test $lret -eq 0 && echo "PASS: ping to ns1 OK after nat output chain flush"
+ test $lret -eq 0 && echo "PASS: ping to ns1 OK after $family nat output chain flush"
return $lret
}
test_masquerade6()
{
+ local family=$1
local lret=0
ip netns exec ns0 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
# add masquerading rule
ip netns exec ns0 nft -f - <<EOF
-table ip6 nat {
+table $family nat {
chain postrouting {
type nat hook postrouting priority 0; policy accept;
meta oif veth0 masquerade
}
}
EOF
+ if [ $? -ne 0 ]; then
+ echo "SKIP: Could not add add $family masquerade hook"
+ return $ksft_skip
+ fi
+
ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1
if [ $? -ne 0 ] ; then
- echo "ERROR: cannot ping ns1 from ns2 with active ipv6 masquerading"
+ echo "ERROR: cannot ping ns1 from ns2 with active $family masquerading"
lret=1
fi
fi
done
- ip netns exec ns0 nft flush chain ip6 nat postrouting
+ ip netns exec ns0 nft flush chain $family nat postrouting
if [ $? -ne 0 ]; then
- echo "ERROR: Could not flush ip6 nat postrouting" 1>&2
+ echo "ERROR: Could not flush $family nat postrouting" 1>&2
lret=1
fi
- test $lret -eq 0 && echo "PASS: IPv6 masquerade for ns2"
+ test $lret -eq 0 && echo "PASS: $family IPv6 masquerade for ns2"
return $lret
}
test_masquerade()
{
+ local family=$1
local lret=0
ip netns exec ns0 sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null
# add masquerading rule
ip netns exec ns0 nft -f - <<EOF
-table ip nat {
+table $family nat {
chain postrouting {
type nat hook postrouting priority 0; policy accept;
meta oif veth0 masquerade
}
}
EOF
+ if [ $? -ne 0 ]; then
+ echo "SKIP: Could not add add $family masquerade hook"
+ return $ksft_skip
+ fi
+
ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
if [ $? -ne 0 ] ; then
- echo "ERROR: cannot ping ns1 from ns2 with active ip masquerading"
+ echo "ERROR: cannot ping ns1 from ns2 with active $family masquerading"
lret=1
fi
fi
done
- ip netns exec ns0 nft flush chain ip nat postrouting
+ ip netns exec ns0 nft flush chain $family nat postrouting
if [ $? -ne 0 ]; then
- echo "ERROR: Could not flush nat postrouting" 1>&2
+ echo "ERROR: Could not flush $family nat postrouting" 1>&2
lret=1
fi
- test $lret -eq 0 && echo "PASS: IP masquerade for ns2"
+ test $lret -eq 0 && echo "PASS: $family IP masquerade for ns2"
return $lret
}
test_redirect6()
{
+ local family=$1
local lret=0
ip netns exec ns0 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
# add redirect rule
ip netns exec ns0 nft -f - <<EOF
-table ip6 nat {
+table $family nat {
chain prerouting {
type nat hook prerouting priority 0; policy accept;
meta iif veth1 meta l4proto icmpv6 ip6 saddr dead:2::99 ip6 daddr dead:1::99 redirect
}
}
EOF
+ if [ $? -ne 0 ]; then
+ echo "SKIP: Could not add add $family redirect hook"
+ return $ksft_skip
+ fi
+
ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1
if [ $? -ne 0 ] ; then
- echo "ERROR: cannot ping ns1 from ns2 with active ip6 redirect"
+ echo "ERROR: cannot ping ns1 from ns2 via ipv6 with active $family redirect"
lret=1
fi
fi
done
- ip netns exec ns0 nft delete table ip6 nat
+ ip netns exec ns0 nft delete table $family nat
if [ $? -ne 0 ]; then
- echo "ERROR: Could not delete ip6 nat table" 1>&2
+ echo "ERROR: Could not delete $family nat table" 1>&2
lret=1
fi
- test $lret -eq 0 && echo "PASS: IPv6 redirection for ns2"
+ test $lret -eq 0 && echo "PASS: $family IPv6 redirection for ns2"
return $lret
}
test_redirect()
{
+ local family=$1
local lret=0
ip netns exec ns0 sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null
# add redirect rule
ip netns exec ns0 nft -f - <<EOF
-table ip nat {
+table $family nat {
chain prerouting {
type nat hook prerouting priority 0; policy accept;
meta iif veth1 ip protocol icmp ip saddr 10.0.2.99 ip daddr 10.0.1.99 redirect
}
}
EOF
+ if [ $? -ne 0 ]; then
+ echo "SKIP: Could not add add $family redirect hook"
+ return $ksft_skip
+ fi
+
ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
if [ $? -ne 0 ] ; then
- echo "ERROR: cannot ping ns1 from ns2 with active ip redirect"
+ echo "ERROR: cannot ping ns1 from ns2 with active $family ip redirect"
lret=1
fi
fi
done
- ip netns exec ns0 nft delete table ip nat
+ ip netns exec ns0 nft delete table $family nat
if [ $? -ne 0 ]; then
- echo "ERROR: Could not delete nat table" 1>&2
+ echo "ERROR: Could not delete $family nat table" 1>&2
lret=1
fi
- test $lret -eq 0 && echo "PASS: IP redirection for ns2"
+ test $lret -eq 0 && echo "PASS: $family IP redirection for ns2"
return $lret
}
fi
reset_counters
-test_local_dnat
-test_local_dnat6
+test_local_dnat ip
+test_local_dnat6 ip6
+reset_counters
+$test_inet_nat && test_local_dnat inet
+$test_inet_nat && test_local_dnat6 inet
reset_counters
-test_masquerade
-test_masquerade6
+test_masquerade ip
+test_masquerade6 ip6
+reset_counters
+$test_inet_nat && test_masquerade inet
+$test_inet_nat && test_masquerade6 inet
reset_counters
-test_redirect
-test_redirect6
+test_redirect ip
+test_redirect6 ip6
+reset_counters
+$test_inet_nat && test_redirect inet
+$test_inet_nat && test_redirect6 inet
for i in 0 1 2; do ip netns del ns$i;done
"$TC actions flush action sample"
]
},
+ {
+ "id": "7571",
+ "name": "Add sample action with invalid rate",
+ "category": [
+ "actions",
+ "sample"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action sample",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action sample rate 0 group 1 index 2",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions get action sample index 2",
+ "matchPattern": "action order [0-9]+: sample rate 1/0 group 1.*index 2 ref",
+ "matchCount": "0",
+ "teardown": [
+ "$TC actions flush action sample"
+ ]
+ },
{
"id": "b6d4",
"name": "Add sample action with mandatory arguments and invalid control action",
"$TC qdisc del dev $DEV1 ingress"
]
},
+ {
+ "id": "2638",
+ "name": "Add matchall and try to get it",
+ "category": [
+ "filter",
+ "matchall"
+ ],
+ "setup": [
+ "$TC qdisc add dev $DEV1 clsact",
+ "$TC filter add dev $DEV1 protocol all pref 1 ingress handle 0x1234 matchall action ok"
+ ],
+ "cmdUnderTest": "$TC filter get dev $DEV1 protocol all pref 1 ingress handle 0x1234 matchall",
+ "expExitCode": "0",
+ "verifyCmd": "$TC filter show dev $DEV1 ingress",
+ "matchPattern": "filter protocol all pref 1 matchall chain 0 handle 0x1234",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 clsact"
+ ]
+ },
{
"id": "d052",
"name": "Add 1M filters with the same action",
"$TC qdisc del dev $DEV2 ingress",
"/bin/rm $BATCH_FILE"
]
+ },
+ {
+ "id": "4cbd",
+ "name": "Try to add filter with duplicate key",
+ "category": [
+ "filter",
+ "flower"
+ ],
+ "setup": [
+ "$TC qdisc add dev $DEV2 ingress",
+ "$TC filter add dev $DEV2 protocol ip prio 1 parent ffff: flower dst_mac e4:11:22:11:4a:51 src_mac e4:11:22:11:4a:50 ip_proto tcp src_ip 1.1.1.1 dst_ip 2.2.2.2 action drop"
+ ],
+ "cmdUnderTest": "$TC filter add dev $DEV2 protocol ip prio 1 parent ffff: flower dst_mac e4:11:22:11:4a:51 src_mac e4:11:22:11:4a:50 ip_proto tcp src_ip 1.1.1.1 dst_ip 2.2.2.2 action drop",
+ "expExitCode": "2",
+ "verifyCmd": "$TC -s filter show dev $DEV2 ingress",
+ "matchPattern": "filter protocol ip pref 1 flower chain 0 handle",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DEV2 ingress"
+ ]
}
]
TPM2_CC_FLUSH_CONTEXT = 0x0165
TPM2_CC_START_AUTH_SESSION = 0x0176
TPM2_CC_GET_CAPABILITY = 0x017A
+TPM2_CC_GET_RANDOM = 0x017B
TPM2_CC_PCR_READ = 0x017E
TPM2_CC_POLICY_PCR = 0x017F
TPM2_CC_PCR_EXTEND = 0x0182
self.flags = flags
if (self.flags & Client.FLAG_SPACE) == 0:
- self.tpm = open('/dev/tpm0', 'r+b')
+ self.tpm = open('/dev/tpm0', 'r+b', buffering=0)
else:
- self.tpm = open('/dev/tpmrm0', 'r+b')
+ self.tpm = open('/dev/tpmrm0', 'r+b', buffering=0)
def close(self):
self.tpm.close()
pass
self.assertEqual(rejected, True)
+ def test_read_partial_resp(self):
+ try:
+ fmt = '>HIIH'
+ cmd = struct.pack(fmt,
+ tpm2.TPM2_ST_NO_SESSIONS,
+ struct.calcsize(fmt),
+ tpm2.TPM2_CC_GET_RANDOM,
+ 0x20)
+ self.client.tpm.write(cmd)
+ hdr = self.client.tpm.read(10)
+ sz = struct.unpack('>I', hdr[2:6])[0]
+ rsp = self.client.tpm.read()
+ except:
+ pass
+ self.assertEqual(sz, 10 + 2 + 32)
+ self.assertEqual(len(rsp), 2 + 32)
+
+ def test_read_partial_overwrite(self):
+ try:
+ fmt = '>HIIH'
+ cmd = struct.pack(fmt,
+ tpm2.TPM2_ST_NO_SESSIONS,
+ struct.calcsize(fmt),
+ tpm2.TPM2_CC_GET_RANDOM,
+ 0x20)
+ self.client.tpm.write(cmd)
+ # Read part of the respone
+ rsp1 = self.client.tpm.read(15)
+
+ # Send a new cmd
+ self.client.tpm.write(cmd)
+
+ # Read the whole respone
+ rsp2 = self.client.tpm.read()
+ except:
+ pass
+ self.assertEqual(len(rsp1), 15)
+ self.assertEqual(len(rsp2), 10 + 2 + 32)
+
+ def test_send_two_cmds(self):
+ rejected = False
+ try:
+ fmt = '>HIIH'
+ cmd = struct.pack(fmt,
+ tpm2.TPM2_ST_NO_SESSIONS,
+ struct.calcsize(fmt),
+ tpm2.TPM2_CC_GET_RANDOM,
+ 0x20)
+ self.client.tpm.write(cmd)
+
+ # expect the second one to raise -EBUSY error
+ self.client.tpm.write(cmd)
+ rsp = self.client.tpm.read()
+
+ except IOError, e:
+ # read the response
+ rsp = self.client.tpm.read()
+ rejected = True
+ pass
+ except:
+ pass
+ self.assertEqual(rejected, True)
+
class SpaceTest(unittest.TestCase):
def setUp(self):
logging.basicConfig(filename='SpaceTest.log', level=logging.DEBUG)
}
}
- if (used_lrs) {
+ if (used_lrs || cpu_if->its_vpe.its_vm) {
int i;
u32 elrsr;
u64 used_lrs = vcpu->arch.vgic_cpu.used_lrs;
int i;
- if (used_lrs) {
+ if (used_lrs || cpu_if->its_vpe.its_vm) {
write_gicreg(cpu_if->vgic_hcr, ICH_HCR_EL2);
for (i = 0; i < used_lrs; i++)
* @addr: IPA
* @pmd: pmd pointer for IPA
*
- * Function clears a PMD entry, flushes addr 1st and 2nd stage TLBs. Marks all
- * pages in the range dirty.
+ * Function clears a PMD entry, flushes addr 1st and 2nd stage TLBs.
*/
static void stage2_dissolve_pmd(struct kvm *kvm, phys_addr_t addr, pmd_t *pmd)
{
* @addr: IPA
* @pud: pud pointer for IPA
*
- * Function clears a PUD entry, flushes addr 1st and 2nd stage TLBs. Marks all
- * pages in the range dirty.
+ * Function clears a PUD entry, flushes addr 1st and 2nd stage TLBs.
*/
static void stage2_dissolve_pud(struct kvm *kvm, phys_addr_t addr, pud_t *pudp)
{
* kvm_alloc_stage2_pgd - allocate level-1 table for stage-2 translation.
* @kvm: The KVM struct pointer for the VM.
*
- * Allocates only the stage-2 HW PGD level table(s) (can support either full
- * 40-bit input addresses or limited to 32-bit input addresses). Clears the
- * allocated pages.
+ * Allocates only the stage-2 HW PGD level table(s) of size defined by
+ * stage2_pgd_size(kvm).
*
* Note we don't need locking here as this is only called when the VM is
* created, which can only be done once.
{
pmd_t *pmd, old_pmd;
+retry:
pmd = stage2_get_pmd(kvm, cache, addr);
VM_BUG_ON(!pmd);
old_pmd = *pmd;
+ /*
+ * Multiple vcpus faulting on the same PMD entry, can
+ * lead to them sequentially updating the PMD with the
+ * same value. Following the break-before-make
+ * (pmd_clear() followed by tlb_flush()) process can
+ * hinder forward progress due to refaults generated
+ * on missing translations.
+ *
+ * Skip updating the page table if the entry is
+ * unchanged.
+ */
+ if (pmd_val(old_pmd) == pmd_val(*new_pmd))
+ return 0;
+
if (pmd_present(old_pmd)) {
/*
- * Multiple vcpus faulting on the same PMD entry, can
- * lead to them sequentially updating the PMD with the
- * same value. Following the break-before-make
- * (pmd_clear() followed by tlb_flush()) process can
- * hinder forward progress due to refaults generated
- * on missing translations.
+ * If we already have PTE level mapping for this block,
+ * we must unmap it to avoid inconsistent TLB state and
+ * leaking the table page. We could end up in this situation
+ * if the memory slot was marked for dirty logging and was
+ * reverted, leaving PTE level mappings for the pages accessed
+ * during the period. So, unmap the PTE level mapping for this
+ * block and retry, as we could have released the upper level
+ * table in the process.
*
- * Skip updating the page table if the entry is
- * unchanged.
+ * Normal THP split/merge follows mmu_notifier callbacks and do
+ * get handled accordingly.
*/
- if (pmd_val(old_pmd) == pmd_val(*new_pmd))
- return 0;
-
+ if (!pmd_thp_or_huge(old_pmd)) {
+ unmap_stage2_range(kvm, addr & S2_PMD_MASK, S2_PMD_SIZE);
+ goto retry;
+ }
/*
* Mapping in huge pages should only happen through a
* fault. If a page is merged into a transparent huge
* should become splitting first, unmapped, merged,
* and mapped back in on-demand.
*/
- VM_BUG_ON(pmd_pfn(old_pmd) != pmd_pfn(*new_pmd));
-
+ WARN_ON_ONCE(pmd_pfn(old_pmd) != pmd_pfn(*new_pmd));
pmd_clear(pmd);
kvm_tlb_flush_vmid_ipa(kvm, addr);
} else {
{
pud_t *pudp, old_pud;
+retry:
pudp = stage2_get_pud(kvm, cache, addr);
VM_BUG_ON(!pudp);
/*
* A large number of vcpus faulting on the same stage 2 entry,
- * can lead to a refault due to the
- * stage2_pud_clear()/tlb_flush(). Skip updating the page
- * tables if there is no change.
+ * can lead to a refault due to the stage2_pud_clear()/tlb_flush().
+ * Skip updating the page tables if there is no change.
*/
if (pud_val(old_pud) == pud_val(*new_pudp))
return 0;
if (stage2_pud_present(kvm, old_pud)) {
+ /*
+ * If we already have table level mapping for this block, unmap
+ * the range for this block and retry.
+ */
+ if (!stage2_pud_huge(kvm, old_pud)) {
+ unmap_stage2_range(kvm, addr & S2_PUD_MASK, S2_PUD_SIZE);
+ goto retry;
+ }
+
+ WARN_ON_ONCE(kvm_pud_pfn(old_pud) != kvm_pud_pfn(*new_pudp));
stage2_pud_clear(kvm, pudp);
kvm_tlb_flush_vmid_ipa(kvm, addr);
} else {
}
/**
- * stage2_wp_puds - write protect PGD range
- * @pgd: pointer to pgd entry
- * @addr: range start address
- * @end: range end address
- *
- * Process PUD entries, for a huge PUD we cause a panic.
- */
+ * stage2_wp_puds - write protect PGD range
+ * @pgd: pointer to pgd entry
+ * @addr: range start address
+ * @end: range end address
+ */
static void stage2_wp_puds(struct kvm *kvm, pgd_t *pgd,
phys_addr_t addr, phys_addr_t end)
{
send_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, lsb, current);
}
-static bool fault_supports_stage2_pmd_mappings(struct kvm_memory_slot *memslot,
- unsigned long hva)
+static bool fault_supports_stage2_huge_mapping(struct kvm_memory_slot *memslot,
+ unsigned long hva,
+ unsigned long map_size)
{
gpa_t gpa_start;
hva_t uaddr_start, uaddr_end;
/*
* Pages belonging to memslots that don't have the same alignment
- * within a PMD for userspace and IPA cannot be mapped with stage-2
- * PMD entries, because we'll end up mapping the wrong pages.
+ * within a PMD/PUD for userspace and IPA cannot be mapped with stage-2
+ * PMD/PUD entries, because we'll end up mapping the wrong pages.
*
* Consider a layout like the following:
*
* memslot->userspace_addr:
* +-----+--------------------+--------------------+---+
- * |abcde|fgh Stage-1 PMD | Stage-1 PMD tv|xyz|
+ * |abcde|fgh Stage-1 block | Stage-1 block tv|xyz|
* +-----+--------------------+--------------------+---+
*
* memslot->base_gfn << PAGE_SIZE:
* +---+--------------------+--------------------+-----+
- * |abc|def Stage-2 PMD | Stage-2 PMD |tvxyz|
+ * |abc|def Stage-2 block | Stage-2 block |tvxyz|
* +---+--------------------+--------------------+-----+
*
- * If we create those stage-2 PMDs, we'll end up with this incorrect
+ * If we create those stage-2 blocks, we'll end up with this incorrect
* mapping:
* d -> f
* e -> g
* f -> h
*/
- if ((gpa_start & ~S2_PMD_MASK) != (uaddr_start & ~S2_PMD_MASK))
+ if ((gpa_start & (map_size - 1)) != (uaddr_start & (map_size - 1)))
return false;
/*
* Next, let's make sure we're not trying to map anything not covered
- * by the memslot. This means we have to prohibit PMD size mappings
- * for the beginning and end of a non-PMD aligned and non-PMD sized
+ * by the memslot. This means we have to prohibit block size mappings
+ * for the beginning and end of a non-block aligned and non-block sized
* memory slot (illustrated by the head and tail parts of the
* userspace view above containing pages 'abcde' and 'xyz',
* respectively).
* userspace_addr or the base_gfn, as both are equally aligned (per
* the check above) and equally sized.
*/
- return (hva & S2_PMD_MASK) >= uaddr_start &&
- (hva & S2_PMD_MASK) + S2_PMD_SIZE <= uaddr_end;
+ return (hva & ~(map_size - 1)) >= uaddr_start &&
+ (hva & ~(map_size - 1)) + map_size <= uaddr_end;
}
static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
return -EFAULT;
}
- if (!fault_supports_stage2_pmd_mappings(memslot, hva))
- force_pte = true;
-
- if (logging_active)
- force_pte = true;
-
/* Let's check if we will get back a huge page backed by hugetlbfs */
down_read(¤t->mm->mmap_sem);
vma = find_vma_intersection(current->mm, hva, hva + 1);
}
vma_pagesize = vma_kernel_pagesize(vma);
+ if (logging_active ||
+ !fault_supports_stage2_huge_mapping(memslot, hva, vma_pagesize)) {
+ force_pte = true;
+ vma_pagesize = PAGE_SIZE;
+ }
+
/*
* The stage2 has a minimum of 2 level table (For arm64 see
* kvm_arm_setup_stage2()). Hence, we are guaranteed that we can
* As for PUD huge maps, we must make sure that we have at least
* 3 levels, i.e, PMD is not folded.
*/
- if ((vma_pagesize == PMD_SIZE ||
- (vma_pagesize == PUD_SIZE && kvm_stage2_has_pmd(kvm))) &&
- !force_pte) {
+ if (vma_pagesize == PMD_SIZE ||
+ (vma_pagesize == PUD_SIZE && kvm_stage2_has_pmd(kvm)))
gfn = (fault_ipa & huge_page_mask(hstate_vma(vma))) >> PAGE_SHIFT;
- }
up_read(¤t->mm->mmap_sem);
/* We need minimum second+third level pages */
u64 indirect_ptr, type = GITS_BASER_TYPE(baser);
phys_addr_t base = GITS_BASER_ADDR_48_to_52(baser);
int esz = GITS_BASER_ENTRY_SIZE(baser);
- int index;
+ int index, idx;
gfn_t gfn;
+ bool ret;
switch (type) {
case GITS_BASER_TYPE_DEVICE:
if (eaddr)
*eaddr = addr;
- return kvm_is_visible_gfn(its->dev->kvm, gfn);
+
+ goto out;
}
/* calculate and check the index into the 1st level */
if (eaddr)
*eaddr = indirect_ptr;
- return kvm_is_visible_gfn(its->dev->kvm, gfn);
+
+out:
+ idx = srcu_read_lock(&its->dev->kvm->srcu);
+ ret = kvm_is_visible_gfn(its->dev->kvm, gfn);
+ srcu_read_unlock(&its->dev->kvm->srcu, idx);
+ return ret;
}
static int vgic_its_alloc_collection(struct vgic_its *its,
kfree(its);
}
-int vgic_its_has_attr_regs(struct kvm_device *dev,
- struct kvm_device_attr *attr)
+static int vgic_its_has_attr_regs(struct kvm_device *dev,
+ struct kvm_device_attr *attr)
{
const struct vgic_register_region *region;
gpa_t offset = attr->attr;
return 0;
}
-int vgic_its_attr_regs_access(struct kvm_device *dev,
- struct kvm_device_attr *attr,
- u64 *reg, bool is_write)
+static int vgic_its_attr_regs_access(struct kvm_device *dev,
+ struct kvm_device_attr *attr,
+ u64 *reg, bool is_write)
{
const struct vgic_register_region *region;
struct vgic_its *its;
((u64)ite->irq->intid << KVM_ITS_ITE_PINTID_SHIFT) |
ite->collection->collection_id;
val = cpu_to_le64(val);
- return kvm_write_guest(kvm, gpa, &val, ite_esz);
+ return kvm_write_guest_lock(kvm, gpa, &val, ite_esz);
}
/**
(itt_addr_field << KVM_ITS_DTE_ITTADDR_SHIFT) |
(dev->num_eventid_bits - 1));
val = cpu_to_le64(val);
- return kvm_write_guest(kvm, ptr, &val, dte_esz);
+ return kvm_write_guest_lock(kvm, ptr, &val, dte_esz);
}
/**
((u64)collection->target_addr << KVM_ITS_CTE_RDBASE_SHIFT) |
collection->collection_id);
val = cpu_to_le64(val);
- return kvm_write_guest(its->dev->kvm, gpa, &val, esz);
+ return kvm_write_guest_lock(its->dev->kvm, gpa, &val, esz);
}
static int vgic_its_restore_cte(struct vgic_its *its, gpa_t gpa, int esz)
*/
val = 0;
BUG_ON(cte_esz > sizeof(val));
- ret = kvm_write_guest(its->dev->kvm, gpa, &val, cte_esz);
+ ret = kvm_write_guest_lock(its->dev->kvm, gpa, &val, cte_esz);
return ret;
}
if (status) {
/* clear consumed data */
val &= ~(1 << bit_nr);
- ret = kvm_write_guest(kvm, ptr, &val, 1);
+ ret = kvm_write_guest_lock(kvm, ptr, &val, 1);
if (ret)
return ret;
}
else
val &= ~(1 << bit_nr);
- ret = kvm_write_guest(kvm, ptr, &val, 1);
+ ret = kvm_write_guest_lock(kvm, ptr, &val, 1);
if (ret)
return ret;
}
* either observe the new interrupt before or after doing this check,
* and introducing additional synchronization mechanism doesn't change
* this.
+ *
+ * Note that we still need to go through the whole thing if anything
+ * can be directly injected (GICv4).
*/
- if (list_empty(&vcpu->arch.vgic_cpu.ap_list_head))
+ if (list_empty(&vcpu->arch.vgic_cpu.ap_list_head) &&
+ !vgic_supports_direct_msis(vcpu->kvm))
return;
DEBUG_SPINLOCK_BUG_ON(!irqs_disabled());
- raw_spin_lock(&vcpu->arch.vgic_cpu.ap_list_lock);
- vgic_flush_lr_state(vcpu);
- raw_spin_unlock(&vcpu->arch.vgic_cpu.ap_list_lock);
+ if (!list_empty(&vcpu->arch.vgic_cpu.ap_list_head)) {
+ raw_spin_lock(&vcpu->arch.vgic_cpu.ap_list_lock);
+ vgic_flush_lr_state(vcpu);
+ raw_spin_unlock(&vcpu->arch.vgic_cpu.ap_list_lock);
+ }
if (can_access_vgic_from_kernel())
vgic_restore_state(vcpu);
if (flags & EPOLLHUP) {
/* The eventfd is closing, detach from KVM */
- unsigned long flags;
+ unsigned long iflags;
- spin_lock_irqsave(&kvm->irqfds.lock, flags);
+ spin_lock_irqsave(&kvm->irqfds.lock, iflags);
/*
* We must check if someone deactivated the irqfd before
if (irqfd_is_active(irqfd))
irqfd_deactivate(irqfd);
- spin_unlock_irqrestore(&kvm->irqfds.lock, flags);
+ spin_unlock_irqrestore(&kvm->irqfds.lock, iflags);
}
return 0;
{
struct kvm_kernel_irq_routing_entry *ei;
int r;
+ u32 gsi = array_index_nospec(ue->gsi, KVM_MAX_IRQ_ROUTES);
/*
* Do not allow GSI to be mapped to the same irqchip more than once.
* Allow only one to one mapping between GSI and non-irqchip routing.
*/
- hlist_for_each_entry(ei, &rt->map[ue->gsi], link)
+ hlist_for_each_entry(ei, &rt->map[gsi], link)
if (ei->type != KVM_IRQ_ROUTING_IRQCHIP ||
ue->type != KVM_IRQ_ROUTING_IRQCHIP ||
ue->u.irqchip.irqchip == ei->irqchip.irqchip)
return -EINVAL;
- e->gsi = ue->gsi;
+ e->gsi = gsi;
e->type = ue->type;
r = kvm_set_routing_entry(kvm, e, ue);
if (r)
{
struct kvm_device *dev = filp->private_data;
+ if (dev->kvm->mm != current->mm)
+ return -EIO;
+
switch (ioctl) {
case KVM_SET_DEVICE_ATTR:
return kvm_device_ioctl_attr(dev, dev->ops->set_attr, arg);
struct kvm_device_ops *ops = NULL;
struct kvm_device *dev;
bool test = cd->flags & KVM_CREATE_DEVICE_TEST;
+ int type;
int ret;
if (cd->type >= ARRAY_SIZE(kvm_device_ops_table))
return -ENODEV;
- ops = kvm_device_ops_table[cd->type];
+ type = array_index_nospec(cd->type, ARRAY_SIZE(kvm_device_ops_table));
+ ops = kvm_device_ops_table[type];
if (ops == NULL)
return -ENODEV;
dev->kvm = kvm;
mutex_lock(&kvm->lock);
- ret = ops->create(dev, cd->type);
+ ret = ops->create(dev, type);
if (ret < 0) {
mutex_unlock(&kvm->lock);
kfree(dev);