diff --git a/MAINTAINERS b/MAINTAINERS index 379387e20a96..07a9c274c0e2 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6027,7 +6027,7 @@ S: Supported F: Documentation/networking/devlink F: include/net/devlink.h F: include/uapi/linux/devlink.h -F: net/core/devlink.c +F: net/devlink/

DH ELECTRONICS IMX6 DHCOM BOARD SUPPORT M: Christoph Niedermaier cniedermaier@dh-electronics.com diff --git a/Makefile b/Makefile index 61ebd54aba89..e5e1fdeef8bf 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 1 -SUBLEVEL = 49 +SUBLEVEL = 50 EXTRAVERSION = NAME = Curry Ramen

diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h index c0983130a44c..e0a4da4cfd8b 100644 --- a/arch/mips/include/asm/cpu-features.h +++ b/arch/mips/include/asm/cpu-features.h @@ -121,7 +121,24 @@ #define cpu_has_4k_cache __isa_ge_or_opt(1, MIPS_CPU_4K_CACHE) #endif #ifndef cpu_has_octeon_cache -#define cpu_has_octeon_cache 0 +#define cpu_has_octeon_cache \ +({ \ + int __res; \ + \ + switch (boot_cpu_type()) { \ + case CPU_CAVIUM_OCTEON: \ + case CPU_CAVIUM_OCTEON_PLUS: \ + case CPU_CAVIUM_OCTEON2: \ + case CPU_CAVIUM_OCTEON3: \ + __res = 1; \ + break; \ + \ + default: \ + __res = 0; \ + } \ + \ + __res; \ +}) #endif /* Don't override `cpu_has_fpu' to 1 or the "nofpu" option won't work. */ #ifndef cpu_has_fpu @@ -351,7 +368,7 @@ ({ \ int __res; \ \ - switch (current_cpu_type()) { \ + switch (boot_cpu_type()) { \ case CPU_M14KC: \ case CPU_74K: \ case CPU_1074K: \ diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 6bf8dc0b8f93..d702359f8ab5 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -447,24 +447,30 @@ config TOOLCHAIN_HAS_ZIHINTPAUSE config TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI def_bool y # https://sourceware.org/git/?p=binutils-gdb.git%3Ba=commit%3Bh=aed44286efa8ae... - depends on AS_IS_GNU && AS_VERSION >= 23800 + # https://gcc.gnu.org/git/?p=gcc.git%3Ba=commit%3Bh=98416dbb0a62579d4a7a4a76ba... + depends on AS_IS_GNU && AS_VERSION >= 23600 help - Newer binutils versions default to ISA spec version 20191213 which - moves some instructions from the I extension to the Zicsr and Zifencei - extensions. + Binutils-2.38 and GCC-12.1.0 bumped the default ISA spec to the newer + 20191213 version, which moves some instructions from the I extension to + the Zicsr and Zifencei extensions. This requires explicitly specifying + Zicsr and Zifencei when binutils >= 2.38 or GCC >= 12.1.0. Zicsr + and Zifencei are supported in binutils from version 2.36 onwards. + To make life easier, and avoid forcing toolchains that default to a + newer ISA spec to version 2.2, relax the check to binutils >= 2.36. + For clang < 17 or GCC < 11.3.0, for which this is not possible or need + special treatment, this is dealt with in TOOLCHAIN_NEEDS_OLD_ISA_SPEC.

config TOOLCHAIN_NEEDS_OLD_ISA_SPEC def_bool y depends on TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI # https://github.com/llvm/llvm-project/commit/22e199e6afb1263c943c0c0d4498694e... - depends on CC_IS_CLANG && CLANG_VERSION < 170000 + # https://gcc.gnu.org/git/?p=gcc.git%3Ba=commit%3Bh=d29f5d6ab513c52fd872f532c4... + depends on (CC_IS_CLANG && CLANG_VERSION < 170000) || (CC_IS_GCC && GCC_VERSION < 110300) help - Certain versions of clang do not support zicsr and zifencei via -march - but newer versions of binutils require it for the reasons noted in the - help text of CONFIG_TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI. This - option causes an older ISA spec compatible with these older versions - of clang to be passed to GAS, which has the same result as passing zicsr - and zifencei to -march. + Certain versions of clang and GCC do not support zicsr and zifencei via + -march. This option causes an older ISA spec compatible with these older + versions of clang and GCC to be passed to GAS, which has the same result + as passing zicsr and zifencei to -march.

config FPU bool "FPU support" diff --git a/arch/riscv/kernel/compat_vdso/Makefile b/arch/riscv/kernel/compat_vdso/Makefile index 7f34f3c7c882..737c0857b14c 100644 --- a/arch/riscv/kernel/compat_vdso/Makefile +++ b/arch/riscv/kernel/compat_vdso/Makefile @@ -11,7 +11,13 @@ compat_vdso-syms += flush_icache COMPAT_CC := $(CC) COMPAT_LD := $(LD)

-COMPAT_CC_FLAGS := -march=rv32g -mabi=ilp32 +# binutils 2.35 does not support the zifencei extension, but in the ISA +# spec 20191213, G stands for IMAFD_ZICSR_ZIFENCEI. +ifdef CONFIG_TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI + COMPAT_CC_FLAGS := -march=rv32g -mabi=ilp32 +else + COMPAT_CC_FLAGS := -march=rv32imafd -mabi=ilp32 +endif COMPAT_LD_FLAGS := -melf32lriscv

# Disable attributes, as they're useless and break the build. diff --git a/arch/x86/kernel/fpu/context.h b/arch/x86/kernel/fpu/context.h index 9fcfa5c4dad7..71b5059e092a 100644 --- a/arch/x86/kernel/fpu/context.h +++ b/arch/x86/kernel/fpu/context.h @@ -19,8 +19,7 @@ * FPU state for a task MUST let the rest of the kernel know that the * FPU registers are no longer valid for this task. * - * Either one of these invalidation functions is enough. Invalidate - * a resource you control: CPU if using the CPU for something else + * Invalidate a resource you control: CPU if using the CPU for something else * (with preemption disabled), FPU for the current task, or a task that * is prevented from running by the current task. */ diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index caf33486dc5e..a083f9ac9e4f 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -679,7 +679,7 @@ static void fpu_reset_fpregs(void) struct fpu *fpu = &current->thread.fpu;

fpregs_lock(); - fpu__drop(fpu); + __fpu_invalidate_fpregs_state(fpu); /* * This does not change the actual hardware registers. It just * resets the memory image and sets TIF_NEED_FPU_LOAD so a diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 0bab497c9436..1afbc4866b10 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -882,6 +882,13 @@ void __init fpu__init_system_xstate(unsigned int legacy_size) goto out_disable; }

+ /* + * CPU capabilities initialization runs before FPU init. So + * X86_FEATURE_OSXSAVE is not set. Now that XSAVE is completely + * functional, set the feature bit so depending code works. + */ + setup_force_cpu_cap(X86_FEATURE_OSXSAVE); + print_xstate_offset_size(); pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is %d bytes, using '%s' format.\n", fpu_kernel_cfg.max_features, diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 230108a90cf3..beca03556379 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -4212,7 +4212,8 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) * root was invalidated by a memslot update or a relevant mmu_notifier fired. */ static bool is_page_fault_stale(struct kvm_vcpu *vcpu, - struct kvm_page_fault *fault, int mmu_seq) + struct kvm_page_fault *fault, + unsigned long mmu_seq) { struct kvm_mmu_page *sp = to_shadow_page(vcpu->arch.mmu->root.hpa);

diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 672f0432d777..70945f00ec41 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -51,7 +51,17 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) if (!kvm->arch.tdp_mmu_enabled) return;

- /* Also waits for any queued work items. */ + /* + * Invalidate all roots, which besides the obvious, schedules all roots + * for zapping and thus puts the TDP MMU's reference to each root, i.e. + * ultimately frees all roots. + */ + kvm_tdp_mmu_invalidate_all_roots(kvm); + + /* + * Destroying a workqueue also first flushes the workqueue, i.e. no + * need to invoke kvm_tdp_mmu_zap_invalidated_roots(). + */ destroy_workqueue(kvm->arch.tdp_mmu_zap_wq);

WARN_ON(!list_empty(&kvm->arch.tdp_mmu_pages)); @@ -127,16 +137,6 @@ static void tdp_mmu_schedule_zap_root(struct kvm *kvm, struct kvm_mmu_page *root queue_work(kvm->arch.tdp_mmu_zap_wq, &root->tdp_mmu_async_work); }

-static inline bool kvm_tdp_root_mark_invalid(struct kvm_mmu_page *page) -{ - union kvm_mmu_page_role role = page->role; - role.invalid = true; - - /* No need to use cmpxchg, only the invalid bit can change. */ - role.word = xchg(&page->role.word, role.word); - return role.invalid; -} - void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, bool shared) { @@ -145,45 +145,12 @@ void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, if (!refcount_dec_and_test(&root->tdp_mmu_root_count)) return;

- WARN_ON(!root->tdp_mmu_page); - /* - * The root now has refcount=0. It is valid, but readers already - * cannot acquire a reference to it because kvm_tdp_mmu_get_root() - * rejects it. This remains true for the rest of the execution - * of this function, because readers visit valid roots only - * (except for tdp_mmu_zap_root_work(), which however - * does not acquire any reference itself). - * - * Even though there are flows that need to visit all roots for - * correctness, they all take mmu_lock for write, so they cannot yet - * run concurrently. The same is true after kvm_tdp_root_mark_invalid, - * since the root still has refcount=0. - * - * However, tdp_mmu_zap_root can yield, and writers do not expect to - * see refcount=0 (see for example kvm_tdp_mmu_invalidate_all_roots()). - * So the root temporarily gets an extra reference, going to refcount=1 - * while staying invalid. Readers still cannot acquire any reference; - * but writers are now allowed to run if tdp_mmu_zap_root yields and - * they might take an extra reference if they themselves yield. - * Therefore, when the reference is given back by the worker, - * there is no guarantee that the refcount is still 1. If not, whoever - * puts the last reference will free the page, but they will not have to - * zap the root because a root cannot go from invalid to valid. + * The TDP MMU itself holds a reference to each root until the root is + * explicitly invalidated, i.e. the final reference should be never be + * put for a valid root. */ - if (!kvm_tdp_root_mark_invalid(root)) { - refcount_set(&root->tdp_mmu_root_count, 1); - - /* - * Zapping the root in a worker is not just "nice to have"; - * it is required because kvm_tdp_mmu_invalidate_all_roots() - * skips already-invalid roots. If kvm_tdp_mmu_put_root() did - * not add the root to the workqueue, kvm_tdp_mmu_zap_all_fast() - * might return with some roots not zapped yet. - */ - tdp_mmu_schedule_zap_root(kvm, root); - return; - } + KVM_BUG_ON(!is_tdp_mmu_page(root) || !root->role.invalid, kvm);

spin_lock(&kvm->arch.tdp_mmu_pages_lock); list_del_rcu(&root->link); @@ -329,7 +296,14 @@ hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu) root = tdp_mmu_alloc_sp(vcpu); tdp_mmu_init_sp(root, NULL, 0, role);

- refcount_set(&root->tdp_mmu_root_count, 1); + /* + * TDP MMU roots are kept until they are explicitly invalidated, either + * by a memslot update or by the destruction of the VM. Initialize the + * refcount to two; one reference for the vCPU, and one reference for + * the TDP MMU itself, which is held until the root is invalidated and + * is ultimately put by tdp_mmu_zap_root_work(). + */ + refcount_set(&root->tdp_mmu_root_count, 2);

spin_lock(&kvm->arch.tdp_mmu_pages_lock); list_add_rcu(&root->link, &kvm->arch.tdp_mmu_roots); @@ -1027,32 +1001,49 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm) /* * Mark each TDP MMU root as invalid to prevent vCPUs from reusing a root that * is about to be zapped, e.g. in response to a memslots update. The actual - * zapping is performed asynchronously, so a reference is taken on all roots. - * Using a separate workqueue makes it easy to ensure that the destruction is - * performed before the "fast zap" completes, without keeping a separate list - * of invalidated roots; the list is effectively the list of work items in - * the workqueue. - * - * Get a reference even if the root is already invalid, the asynchronous worker - * assumes it was gifted a reference to the root it processes. Because mmu_lock - * is held for write, it should be impossible to observe a root with zero refcount, - * i.e. the list of roots cannot be stale. + * zapping is performed asynchronously. Using a separate workqueue makes it + * easy to ensure that the destruction is performed before the "fast zap" + * completes, without keeping a separate list of invalidated roots; the list is + * effectively the list of work items in the workqueue. * - * This has essentially the same effect for the TDP MMU - * as updating mmu_valid_gen does for the shadow MMU. + * Note, the asynchronous worker is gifted the TDP MMU's reference. + * See kvm_tdp_mmu_get_vcpu_root_hpa(). */ void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm) { struct kvm_mmu_page *root;

- lockdep_assert_held_write(&kvm->mmu_lock); - list_for_each_entry(root, &kvm->arch.tdp_mmu_roots, link) { - if (!root->role.invalid && - !WARN_ON_ONCE(!kvm_tdp_mmu_get_root(root))) { + /* + * mmu_lock must be held for write to ensure that a root doesn't become + * invalid while there are active readers (invalidating a root while + * there are active readers may or may not be problematic in practice, + * but it's uncharted territory and not supported). + * + * Waive the assertion if there are no users of @kvm, i.e. the VM is + * being destroyed after all references have been put, or if no vCPUs + * have been created (which means there are no roots), i.e. the VM is + * being destroyed in an error path of KVM_CREATE_VM. + */ + if (IS_ENABLED(CONFIG_PROVE_LOCKING) && + refcount_read(&kvm->users_count) && kvm->created_vcpus) + lockdep_assert_held_write(&kvm->mmu_lock); + + /* + * As above, mmu_lock isn't held when destroying the VM! There can't + * be other references to @kvm, i.e. nothing else can invalidate roots + * or be consuming roots, but walking the list of roots does need to be + * guarded against roots being deleted by the asynchronous zap worker. + */ + rcu_read_lock(); + + list_for_each_entry_rcu(root, &kvm->arch.tdp_mmu_roots, link) { + if (!root->role.invalid) { root->role.invalid = true; tdp_mmu_schedule_zap_root(kvm, root); } } + + rcu_read_unlock(); }

/* diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 4459cfbdbcb1..c2f0f74193f0 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -1223,9 +1223,6 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd, __func__, cmd->cmd_op, ub_cmd->q_id, tag, ub_cmd->result);

- if (!(issue_flags & IO_URING_F_SQE128)) - goto out; - if (ub_cmd->q_id >= ub->dev_info.nr_hw_queues) goto out;

diff --git a/drivers/clk/clk-devres.c b/drivers/clk/clk-devres.c index 4fb4fd4b06bd..737aa70e2cb3 100644 --- a/drivers/clk/clk-devres.c +++ b/drivers/clk/clk-devres.c @@ -205,18 +205,19 @@ EXPORT_SYMBOL(devm_clk_put); struct clk *devm_get_clk_from_child(struct device *dev, struct device_node *np, const char *con_id) { - struct clk **ptr, *clk; + struct devm_clk_state *state; + struct clk *clk;

- ptr = devres_alloc(devm_clk_release, sizeof(*ptr), GFP_KERNEL); - if (!ptr) + state = devres_alloc(devm_clk_release, sizeof(*state), GFP_KERNEL); + if (!state) return ERR_PTR(-ENOMEM);

clk = of_clk_get_by_name(np, con_id); if (!IS_ERR(clk)) { - *ptr = clk; - devres_add(dev, ptr); + state->clk = clk; + devres_add(dev, state); } else { - devres_free(ptr); + devres_free(state); }

return clk; diff --git a/drivers/dma-buf/sw_sync.c b/drivers/dma-buf/sw_sync.c index 348b3a9170fa..7f5ed1aa7a9f 100644 --- a/drivers/dma-buf/sw_sync.c +++ b/drivers/dma-buf/sw_sync.c @@ -191,6 +191,7 @@ static const struct dma_fence_ops timeline_fence_ops = { */ static void sync_timeline_signal(struct sync_timeline *obj, unsigned int inc) { + LIST_HEAD(signalled); struct sync_pt *pt, *next;

trace_sync_timeline(obj); @@ -203,21 +204,20 @@ static void sync_timeline_signal(struct sync_timeline *obj, unsigned int inc) if (!timeline_fence_signaled(&pt->base)) break;

- list_del_init(&pt->link); + dma_fence_get(&pt->base); + + list_move_tail(&pt->link, &signalled); rb_erase(&pt->node, &obj->pt_tree);

- /* - * A signal callback may release the last reference to this - * fence, causing it to be freed. That operation has to be - * last to avoid a use after free inside this loop, and must - * be after we remove the fence from the timeline in order to - * prevent deadlocking on timeline->lock inside - * timeline_fence_release(). - */ dma_fence_signal_locked(&pt->base); }

spin_unlock_irq(&obj->lock); + + list_for_each_entry_safe(pt, next, &signalled, link) { + list_del_init(&pt->link); + dma_fence_put(&pt->base); + } }

/** diff --git a/drivers/gpio/gpio-sim.c b/drivers/gpio/gpio-sim.c index fef12e57b1f1..b352775e5e0b 100644 --- a/drivers/gpio/gpio-sim.c +++ b/drivers/gpio/gpio-sim.c @@ -290,6 +290,15 @@ static void gpio_sim_mutex_destroy(void *data) mutex_destroy(lock); }

+static void gpio_sim_dispose_mappings(void *data) +{ + struct gpio_sim_chip *chip = data; + unsigned int i; + + for (i = 0; i < chip->gc.ngpio; i++) + irq_dispose_mapping(irq_find_mapping(chip->irq_sim, i)); +} + static void gpio_sim_sysfs_remove(void *data) { struct gpio_sim_chip *chip = data; @@ -398,10 +407,14 @@ static int gpio_sim_add_bank(struct fwnode_handle *swnode, struct device *dev) if (!chip->pull_map) return -ENOMEM;

- chip->irq_sim = devm_irq_domain_create_sim(dev, NULL, num_lines); + chip->irq_sim = devm_irq_domain_create_sim(dev, swnode, num_lines); if (IS_ERR(chip->irq_sim)) return PTR_ERR(chip->irq_sim);

+ ret = devm_add_action_or_reset(dev, gpio_sim_dispose_mappings, chip); + if (ret) + return ret; + mutex_init(&chip->lock); ret = devm_add_action_or_reset(dev, gpio_sim_mutex_destroy, &chip->lock); diff --git a/drivers/gpu/drm/arm/hdlcd_drv.c b/drivers/gpu/drm/arm/hdlcd_drv.c index a032003c340c..d6ea47873627 100644 --- a/drivers/gpu/drm/arm/hdlcd_drv.c +++ b/drivers/gpu/drm/arm/hdlcd_drv.c @@ -290,7 +290,7 @@ static int hdlcd_drm_bind(struct device *dev) */ if (hdlcd_read(hdlcd, HDLCD_REG_COMMAND)) { hdlcd_write(hdlcd, HDLCD_REG_COMMAND, 0); - drm_aperture_remove_framebuffers(false, &hdlcd_driver); + drm_aperture_remove_framebuffers(&hdlcd_driver); }

drm_mode_config_reset(drm); diff --git a/drivers/gpu/drm/armada/armada_drv.c b/drivers/gpu/drm/armada/armada_drv.c index 142668cd6d7c..688ba358f531 100644 --- a/drivers/gpu/drm/armada/armada_drv.c +++ b/drivers/gpu/drm/armada/armada_drv.c @@ -95,7 +95,7 @@ static int armada_drm_bind(struct device *dev) }

/* Remove early framebuffers */ - ret = drm_aperture_remove_framebuffers(false, &armada_drm_driver); + ret = drm_aperture_remove_framebuffers(&armada_drm_driver); if (ret) { dev_err(dev, "[" DRM_NAME ":%s] can't kick out simple-fb: %d\n", __func__, ret); diff --git a/drivers/gpu/drm/ast/ast_drv.c b/drivers/gpu/drm/ast/ast_drv.c index b9392f31e629..800471f2a203 100644 --- a/drivers/gpu/drm/ast/ast_drv.c +++ b/drivers/gpu/drm/ast/ast_drv.c @@ -89,27 +89,13 @@ static const struct pci_device_id ast_pciidlist[] = {

MODULE_DEVICE_TABLE(pci, ast_pciidlist);

-static int ast_remove_conflicting_framebuffers(struct pci_dev *pdev) -{ - bool primary = false; - resource_size_t base, size; - - base = pci_resource_start(pdev, 0); - size = pci_resource_len(pdev, 0); -#ifdef CONFIG_X86 - primary = pdev->resource[PCI_ROM_RESOURCE].flags & IORESOURCE_ROM_SHADOW; -#endif - - return drm_aperture_remove_conflicting_framebuffers(base, size, primary, &ast_driver); -} - static int ast_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { struct ast_private *ast; struct drm_device *dev; int ret;

- ret = ast_remove_conflicting_framebuffers(pdev); + ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &ast_driver); if (ret) return ret;

diff --git a/drivers/gpu/drm/drm_aperture.c b/drivers/gpu/drm/drm_aperture.c index 3b8fdeeafd53..697cffbfd603 100644 --- a/drivers/gpu/drm/drm_aperture.c +++ b/drivers/gpu/drm/drm_aperture.c @@ -32,17 +32,13 @@ * * static int remove_conflicting_framebuffers(struct pci_dev *pdev) * { - * bool primary = false; * resource_size_t base, size; * int ret; * * base = pci_resource_start(pdev, 0); * size = pci_resource_len(pdev, 0); - * #ifdef CONFIG_X86 - * primary = pdev->resource[PCI_ROM_RESOURCE].flags & IORESOURCE_ROM_SHADOW; - * #endif * - * return drm_aperture_remove_conflicting_framebuffers(base, size, primary, + * return drm_aperture_remove_conflicting_framebuffers(base, size, * &example_driver); * } * @@ -161,7 +157,6 @@ EXPORT_SYMBOL(devm_aperture_acquire_from_firmware); * drm_aperture_remove_conflicting_framebuffers - remove existing framebuffers in the given range * @base: the aperture's base address in physical memory * @size: aperture size in bytes - * @primary: also kick vga16fb if present * @req_driver: requesting DRM driver * * This function removes graphics device drivers which use the memory range described by @@ -171,9 +166,9 @@ EXPORT_SYMBOL(devm_aperture_acquire_from_firmware); * 0 on success, or a negative errno code otherwise */ int drm_aperture_remove_conflicting_framebuffers(resource_size_t base, resource_size_t size, - bool primary, const struct drm_driver *req_driver) + const struct drm_driver *req_driver) { - return aperture_remove_conflicting_devices(base, size, primary, req_driver->name); + return aperture_remove_conflicting_devices(base, size, false, req_driver->name); } EXPORT_SYMBOL(drm_aperture_remove_conflicting_framebuffers);

diff --git a/drivers/gpu/drm/gma500/psb_drv.c b/drivers/gpu/drm/gma500/psb_drv.c index cd9c73f5a64a..738eb558a97e 100644 --- a/drivers/gpu/drm/gma500/psb_drv.c +++ b/drivers/gpu/drm/gma500/psb_drv.c @@ -424,12 +424,17 @@ static int psb_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)

/* * We cannot yet easily find the framebuffer's location in memory. So - * remove all framebuffers here. + * remove all framebuffers here. Note that we still want the pci special + * handling to kick out vgacon. * * TODO: Refactor psb_driver_load() to map vdc_reg earlier. Then we * might be able to read the framebuffer range from the device. */ - ret = drm_aperture_remove_framebuffers(true, &driver); + ret = drm_aperture_remove_framebuffers(&driver); + if (ret) + return ret; + + ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &driver); if (ret) return ret;

diff --git a/drivers/gpu/drm/hyperv/hyperv_drm_drv.c b/drivers/gpu/drm/hyperv/hyperv_drm_drv.c index ca127ff797f7..29ee0814bccc 100644 --- a/drivers/gpu/drm/hyperv/hyperv_drm_drv.c +++ b/drivers/gpu/drm/hyperv/hyperv_drm_drv.c @@ -74,7 +74,6 @@ static int hyperv_setup_vram(struct hyperv_drm_device *hv,

drm_aperture_remove_conflicting_framebuffers(screen_info.lfb_base, screen_info.lfb_size, - false, &hyperv_driver);

hv->fb_size = (unsigned long)hv->mmio_megabytes * 1024 * 1024; diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c index b2838732ac93..cc8468536871 100644 --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c @@ -165,14 +165,60 @@ static u32 preparser_disable(bool state) return MI_ARB_CHECK | 1 << 8 | state; }

-u32 *gen12_emit_aux_table_inv(struct intel_gt *gt, u32 *cs, const i915_reg_t inv_reg) +static i915_reg_t gen12_get_aux_inv_reg(struct intel_engine_cs *engine) { - u32 gsi_offset = gt->uncore->gsi_offset; + switch (engine->id) { + case RCS0: + return GEN12_CCS_AUX_INV; + case BCS0: + return GEN12_BCS0_AUX_INV; + case VCS0: + return GEN12_VD0_AUX_INV; + case VCS2: + return GEN12_VD2_AUX_INV; + case VECS0: + return GEN12_VE0_AUX_INV; + case CCS0: + return GEN12_CCS0_AUX_INV; + default: + return INVALID_MMIO_REG; + } +} + +static bool gen12_needs_ccs_aux_inv(struct intel_engine_cs *engine) +{ + i915_reg_t reg = gen12_get_aux_inv_reg(engine); + + if (IS_PONTEVECCHIO(engine->i915)) + return false; + + /* + * So far platforms supported by i915 having flat ccs do not require + * AUX invalidation. Check also whether the engine requires it. + */ + return i915_mmio_reg_valid(reg) && !HAS_FLAT_CCS(engine->i915); +} + +u32 *gen12_emit_aux_table_inv(struct intel_engine_cs *engine, u32 *cs) +{ + i915_reg_t inv_reg = gen12_get_aux_inv_reg(engine); + u32 gsi_offset = engine->gt->uncore->gsi_offset; + + if (!gen12_needs_ccs_aux_inv(engine)) + return cs;

*cs++ = MI_LOAD_REGISTER_IMM(1) | MI_LRI_MMIO_REMAP_EN; *cs++ = i915_mmio_reg_offset(inv_reg) + gsi_offset; *cs++ = AUX_INV; - *cs++ = MI_NOOP; + + *cs++ = MI_SEMAPHORE_WAIT_TOKEN | + MI_SEMAPHORE_REGISTER_POLL | + MI_SEMAPHORE_POLL | + MI_SEMAPHORE_SAD_EQ_SDD; + *cs++ = 0; + *cs++ = i915_mmio_reg_offset(inv_reg) + gsi_offset; + *cs++ = 0; + *cs++ = 0;

return cs; } @@ -181,7 +227,11 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode) { struct intel_engine_cs *engine = rq->engine;

- if (mode & EMIT_FLUSH) { + /* + * On Aux CCS platforms the invalidation of the Aux + * table requires quiescing memory traffic beforehand + */ + if (mode & EMIT_FLUSH || gen12_needs_ccs_aux_inv(engine)) { u32 flags = 0; u32 *cs;

@@ -236,10 +286,9 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode) else if (engine->class == COMPUTE_CLASS) flags &= ~PIPE_CONTROL_3D_ENGINE_FLAGS;

- if (!HAS_FLAT_CCS(rq->engine->i915)) - count = 8 + 4; - else - count = 8; + count = 8; + if (gen12_needs_ccs_aux_inv(rq->engine)) + count += 8;

cs = intel_ring_begin(rq, count); if (IS_ERR(cs)) @@ -254,11 +303,7 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode)

cs = gen8_emit_pipe_control(cs, flags, LRC_PPHWSP_SCRATCH_ADDR);

- if (!HAS_FLAT_CCS(rq->engine->i915)) { - /* hsdes: 1809175790 */ - cs = gen12_emit_aux_table_inv(rq->engine->gt, cs, - GEN12_CCS_AUX_INV); - } + cs = gen12_emit_aux_table_inv(engine, cs);

*cs++ = preparser_disable(false); intel_ring_advance(rq, cs); @@ -269,21 +314,14 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode)

int gen12_emit_flush_xcs(struct i915_request *rq, u32 mode) { - intel_engine_mask_t aux_inv = 0; - u32 cmd, *cs; + u32 cmd = 4; + u32 *cs;

- cmd = 4; if (mode & EMIT_INVALIDATE) { cmd += 2;

- if (!HAS_FLAT_CCS(rq->engine->i915) && - (rq->engine->class == VIDEO_DECODE_CLASS || - rq->engine->class == VIDEO_ENHANCEMENT_CLASS)) { - aux_inv = rq->engine->mask & - ~GENMASK(_BCS(I915_MAX_BCS - 1), BCS0); - if (aux_inv) - cmd += 4; - } + if (gen12_needs_ccs_aux_inv(rq->engine)) + cmd += 8; }

cs = intel_ring_begin(rq, cmd); @@ -314,14 +352,7 @@ int gen12_emit_flush_xcs(struct i915_request *rq, u32 mode) *cs++ = 0; /* upper addr */ *cs++ = 0; /* value */

- if (aux_inv) { /* hsdes: 1809175790 */ - if (rq->engine->class == VIDEO_DECODE_CLASS) - cs = gen12_emit_aux_table_inv(rq->engine->gt, - cs, GEN12_VD0_AUX_INV); - else - cs = gen12_emit_aux_table_inv(rq->engine->gt, - cs, GEN12_VE0_AUX_INV); - } + cs = gen12_emit_aux_table_inv(rq->engine, cs);

if (mode & EMIT_INVALIDATE) *cs++ = preparser_disable(false); diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.h b/drivers/gpu/drm/i915/gt/gen8_engine_cs.h index e4d24c811dd6..651eb786e930 100644 --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.h +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.h @@ -13,6 +13,7 @@ #include "intel_gt_regs.h" #include "intel_gpu_commands.h"

+struct intel_engine_cs; struct intel_gt; struct i915_request;

@@ -46,7 +47,7 @@ u32 *gen8_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs); u32 *gen11_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs); u32 *gen12_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs);

-u32 *gen12_emit_aux_table_inv(struct intel_gt *gt, u32 *cs, const i915_reg_t inv_reg); +u32 *gen12_emit_aux_table_inv(struct intel_engine_cs *engine, u32 *cs);

static inline u32 * __gen8_emit_pipe_control(u32 *batch, u32 flags0, u32 flags1, u32 offset) diff --git a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h index d4e9702d3c8e..25ea5f8a464a 100644 --- a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h +++ b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h @@ -120,6 +120,7 @@ #define MI_SEMAPHORE_TARGET(engine) ((engine)<<15) #define MI_SEMAPHORE_WAIT MI_INSTR(0x1c, 2) /* GEN8+ */ #define MI_SEMAPHORE_WAIT_TOKEN MI_INSTR(0x1c, 3) /* GEN12+ */ +#define MI_SEMAPHORE_REGISTER_POLL (1 << 16) #define MI_SEMAPHORE_POLL (1 << 15) #define MI_SEMAPHORE_SAD_GT_SDD (0 << 12) #define MI_SEMAPHORE_SAD_GTE_SDD (1 << 12) diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 137e41e37ea5..7eb01ff17d89 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -1296,10 +1296,7 @@ gen12_emit_indirect_ctx_rcs(const struct intel_context *ce, u32 *cs) IS_DG2_G11(ce->engine->i915)) cs = gen8_emit_pipe_control(cs, PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE, 0);

- /* hsdes: 1809175790 */ - if (!HAS_FLAT_CCS(ce->engine->i915)) - cs = gen12_emit_aux_table_inv(ce->engine->gt, - cs, GEN12_CCS_AUX_INV); + cs = gen12_emit_aux_table_inv(ce->engine, cs);

/* Wa_16014892111 */ if (IS_DG2(ce->engine->i915)) @@ -1322,17 +1319,7 @@ gen12_emit_indirect_ctx_xcs(const struct intel_context *ce, u32 *cs) PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE, 0);

- /* hsdes: 1809175790 */ - if (!HAS_FLAT_CCS(ce->engine->i915)) { - if (ce->engine->class == VIDEO_DECODE_CLASS) - cs = gen12_emit_aux_table_inv(ce->engine->gt, - cs, GEN12_VD0_AUX_INV); - else if (ce->engine->class == VIDEO_ENHANCEMENT_CLASS) - cs = gen12_emit_aux_table_inv(ce->engine->gt, - cs, GEN12_VE0_AUX_INV); - } - - return cs; + return gen12_emit_aux_table_inv(ce->engine, cs); }

static void diff --git a/drivers/gpu/drm/i915/i915_driver.c b/drivers/gpu/drm/i915/i915_driver.c index 35bc2a3fa811..75a93951fe42 100644 --- a/drivers/gpu/drm/i915/i915_driver.c +++ b/drivers/gpu/drm/i915/i915_driver.c @@ -574,7 +574,6 @@ static int i915_pcode_init(struct drm_i915_private *i915) static int i915_driver_hw_probe(struct drm_i915_private *dev_priv) { struct pci_dev *pdev = to_pci_dev(dev_priv->drm.dev); - struct pci_dev *root_pdev; int ret;

if (i915_inject_probe_failure(dev_priv)) @@ -686,15 +685,6 @@ static int i915_driver_hw_probe(struct drm_i915_private *dev_priv)

intel_bw_init_hw(dev_priv);

- /* - * FIXME: Temporary hammer to avoid freezing the machine on our DGFX - * This should be totally removed when we handle the pci states properly - * on runtime PM and on s2idle cases. - */ - root_pdev = pcie_find_root_port(pdev); - if (root_pdev) - pci_d3cold_disable(root_pdev); - return 0;

err_msi: @@ -718,16 +708,11 @@ static int i915_driver_hw_probe(struct drm_i915_private *dev_priv) static void i915_driver_hw_remove(struct drm_i915_private *dev_priv) { struct pci_dev *pdev = to_pci_dev(dev_priv->drm.dev); - struct pci_dev *root_pdev;

i915_perf_fini(dev_priv);

if (pdev->msi_enabled) pci_disable_msi(pdev); - - root_pdev = pcie_find_root_port(pdev); - if (root_pdev) - pci_d3cold_enable(root_pdev); }

/** @@ -1625,6 +1610,8 @@ static int intel_runtime_suspend(struct device *kdev) { struct drm_i915_private *dev_priv = kdev_to_i915(kdev); struct intel_runtime_pm *rpm = &dev_priv->runtime_pm; + struct pci_dev *pdev = to_pci_dev(dev_priv->drm.dev); + struct pci_dev *root_pdev; struct intel_gt *gt; int ret, i;

@@ -1674,6 +1661,15 @@ static int intel_runtime_suspend(struct device *kdev) drm_err(&dev_priv->drm, "Unclaimed access detected prior to suspending\n");

+ /* + * FIXME: Temporary hammer to avoid freezing the machine on our DGFX + * This should be totally removed when we handle the pci states properly + * on runtime PM. + */ + root_pdev = pcie_find_root_port(pdev); + if (root_pdev) + pci_d3cold_disable(root_pdev); + rpm->suspended = true;

/* @@ -1712,6 +1708,8 @@ static int intel_runtime_resume(struct device *kdev) { struct drm_i915_private *dev_priv = kdev_to_i915(kdev); struct intel_runtime_pm *rpm = &dev_priv->runtime_pm; + struct pci_dev *pdev = to_pci_dev(dev_priv->drm.dev); + struct pci_dev *root_pdev; struct intel_gt *gt; int ret, i;

@@ -1725,6 +1723,11 @@ static int intel_runtime_resume(struct device *kdev)

intel_opregion_notify_adapter(dev_priv, PCI_D0); rpm->suspended = false; + + root_pdev = pcie_find_root_port(pdev); + if (root_pdev) + pci_d3cold_enable(root_pdev); + if (intel_uncore_unclaimed_mmio(&dev_priv->uncore)) drm_dbg(&dev_priv->drm, "Unclaimed access during suspend, bios?\n"); diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c index eea433ade79d..119544d88b58 100644 --- a/drivers/gpu/drm/meson/meson_drv.c +++ b/drivers/gpu/drm/meson/meson_drv.c @@ -285,7 +285,7 @@ static int meson_drv_bind_master(struct device *dev, bool has_components) * Remove early framebuffers (ie. simplefb). The framebuffer can be * located anywhere in RAM */ - ret = drm_aperture_remove_framebuffers(false, &meson_driver); + ret = drm_aperture_remove_framebuffers(&meson_driver); if (ret) goto free_drm;

diff --git a/drivers/gpu/drm/msm/msm_fbdev.c b/drivers/gpu/drm/msm/msm_fbdev.c index 46168eccfac4..d4a9b501e1bc 100644 --- a/drivers/gpu/drm/msm/msm_fbdev.c +++ b/drivers/gpu/drm/msm/msm_fbdev.c @@ -157,7 +157,7 @@ struct drm_fb_helper *msm_fbdev_init(struct drm_device *dev) }

/* the fw fb could be anywhere in memory */ - ret = drm_aperture_remove_framebuffers(false, dev->driver); + ret = drm_aperture_remove_framebuffers(dev->driver); if (ret) goto fini;

diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c index 813f9f8c8698..8e12053a220b 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c @@ -140,7 +140,7 @@ static int rockchip_drm_bind(struct device *dev) int ret;

/* Remove existing drivers that may own the framebuffer memory. */ - ret = drm_aperture_remove_framebuffers(false, &rockchip_drm_driver); + ret = drm_aperture_remove_framebuffers(&rockchip_drm_driver); if (ret) { DRM_DEV_ERROR(dev, "Failed to remove existing framebuffers - %d.\n", diff --git a/drivers/gpu/drm/stm/drv.c b/drivers/gpu/drm/stm/drv.c index d7914f5122df..0a09a85ac9d6 100644 --- a/drivers/gpu/drm/stm/drv.c +++ b/drivers/gpu/drm/stm/drv.c @@ -185,7 +185,7 @@ static int stm_drm_platform_probe(struct platform_device *pdev)

DRM_DEBUG("%s\n", __func__);

- ret = drm_aperture_remove_framebuffers(false, &drv_driver); + ret = drm_aperture_remove_framebuffers(&drv_driver); if (ret) return ret;

diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c index 7910c5853f0a..5c483bbccbbb 100644 --- a/drivers/gpu/drm/sun4i/sun4i_drv.c +++ b/drivers/gpu/drm/sun4i/sun4i_drv.c @@ -98,7 +98,7 @@ static int sun4i_drv_bind(struct device *dev) goto unbind_all;

/* Remove early framebuffers (ie. simplefb) */ - ret = drm_aperture_remove_framebuffers(false, &sun4i_drv_driver); + ret = drm_aperture_remove_framebuffers(&sun4i_drv_driver); if (ret) goto unbind_all;

diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c index a1f909dac89a..5fc55b9777cb 100644 --- a/drivers/gpu/drm/tegra/drm.c +++ b/drivers/gpu/drm/tegra/drm.c @@ -1252,7 +1252,7 @@ static int host1x_drm_probe(struct host1x_device *dev)

drm_mode_config_reset(drm);

- err = drm_aperture_remove_framebuffers(false, &tegra_drm_driver); + err = drm_aperture_remove_framebuffers(&tegra_drm_driver); if (err < 0) goto hub;

diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c index 8c329c071c62..b6384a5dfdbc 100644 --- a/drivers/gpu/drm/vc4/vc4_drv.c +++ b/drivers/gpu/drm/vc4/vc4_drv.c @@ -351,7 +351,7 @@ static int vc4_drm_bind(struct device *dev) return -EPROBE_DEFER; }

- ret = drm_aperture_remove_framebuffers(false, driver); + ret = drm_aperture_remove_framebuffers(driver); if (ret) return ret;

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index 1ec9c53a7bf4..8459fab9d979 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -1683,4 +1683,16 @@ static inline bool vmw_has_fences(struct vmw_private *vmw) return (vmw_fifo_caps(vmw) & SVGA_FIFO_CAP_FENCE) != 0; }

+static inline bool vmw_shadertype_is_valid(enum vmw_sm_type shader_model, + u32 shader_type) +{ + SVGA3dShaderType max_allowed = SVGA3D_SHADERTYPE_PREDX_MAX; + + if (shader_model >= VMW_SM_5) + max_allowed = SVGA3D_SHADERTYPE_MAX; + else if (shader_model >= VMW_SM_4) + max_allowed = SVGA3D_SHADERTYPE_DX10_MAX; + return shader_type >= SVGA3D_SHADERTYPE_MIN && shader_type < max_allowed; +} + #endif diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index 1c88b74d68cf..58ca9adf0987 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -1985,7 +1985,7 @@ static int vmw_cmd_set_shader(struct vmw_private *dev_priv,

cmd = container_of(header, typeof(*cmd), header);

- if (cmd->body.type >= SVGA3D_SHADERTYPE_PREDX_MAX) { + if (!vmw_shadertype_is_valid(VMW_SM_LEGACY, cmd->body.type)) { VMW_DEBUG_USER("Illegal shader type %u.\n", (unsigned int) cmd->body.type); return -EINVAL; @@ -2108,8 +2108,6 @@ vmw_cmd_dx_set_single_constant_buffer(struct vmw_private *dev_priv, SVGA3dCmdHeader *header) { VMW_DECLARE_CMD_VAR(*cmd, SVGA3dCmdDXSetSingleConstantBuffer); - SVGA3dShaderType max_shader_num = has_sm5_context(dev_priv) ? - SVGA3D_NUM_SHADERTYPE : SVGA3D_NUM_SHADERTYPE_DX10;

struct vmw_resource *res = NULL; struct vmw_ctx_validation_info *ctx_node = VMW_GET_CTX_NODE(sw_context); @@ -2126,6 +2124,14 @@ vmw_cmd_dx_set_single_constant_buffer(struct vmw_private *dev_priv, if (unlikely(ret != 0)) return ret;

+ if (!vmw_shadertype_is_valid(dev_priv->sm_type, cmd->body.type) || + cmd->body.slot >= SVGA3D_DX_MAX_CONSTBUFFERS) { + VMW_DEBUG_USER("Illegal const buffer shader %u slot %u.\n", + (unsigned int) cmd->body.type, + (unsigned int) cmd->body.slot); + return -EINVAL; + } + binding.bi.ctx = ctx_node->ctx; binding.bi.res = res; binding.bi.bt = vmw_ctx_binding_cb; @@ -2134,14 +2140,6 @@ vmw_cmd_dx_set_single_constant_buffer(struct vmw_private *dev_priv, binding.size = cmd->body.sizeInBytes; binding.slot = cmd->body.slot;

- if (binding.shader_slot >= max_shader_num || - binding.slot >= SVGA3D_DX_MAX_CONSTBUFFERS) { - VMW_DEBUG_USER("Illegal const buffer shader %u slot %u.\n", - (unsigned int) cmd->body.type, - (unsigned int) binding.slot); - return -EINVAL; - } - vmw_binding_add(ctx_node->staged, &binding.bi, binding.shader_slot, binding.slot);

@@ -2200,15 +2198,13 @@ static int vmw_cmd_dx_set_shader_res(struct vmw_private *dev_priv, { VMW_DECLARE_CMD_VAR(*cmd, SVGA3dCmdDXSetShaderResources) = container_of(header, typeof(*cmd), header); - SVGA3dShaderType max_allowed = has_sm5_context(dev_priv) ? - SVGA3D_SHADERTYPE_MAX : SVGA3D_SHADERTYPE_DX10_MAX;

u32 num_sr_view = (cmd->header.size - sizeof(cmd->body)) / sizeof(SVGA3dShaderResourceViewId);

if ((u64) cmd->body.startView + (u64) num_sr_view > (u64) SVGA3D_DX_MAX_SRVIEWS || - cmd->body.type >= max_allowed) { + !vmw_shadertype_is_valid(dev_priv->sm_type, cmd->body.type)) { VMW_DEBUG_USER("Invalid shader binding.\n"); return -EINVAL; } @@ -2232,8 +2228,6 @@ static int vmw_cmd_dx_set_shader(struct vmw_private *dev_priv, SVGA3dCmdHeader *header) { VMW_DECLARE_CMD_VAR(*cmd, SVGA3dCmdDXSetShader); - SVGA3dShaderType max_allowed = has_sm5_context(dev_priv) ? - SVGA3D_SHADERTYPE_MAX : SVGA3D_SHADERTYPE_DX10_MAX; struct vmw_resource *res = NULL; struct vmw_ctx_validation_info *ctx_node = VMW_GET_CTX_NODE(sw_context); struct vmw_ctx_bindinfo_shader binding; @@ -2244,8 +2238,7 @@ static int vmw_cmd_dx_set_shader(struct vmw_private *dev_priv,

cmd = container_of(header, typeof(*cmd), header);

- if (cmd->body.type >= max_allowed || - cmd->body.type < SVGA3D_SHADERTYPE_MIN) { + if (!vmw_shadertype_is_valid(dev_priv->sm_type, cmd->body.type)) { VMW_DEBUG_USER("Illegal shader type %u.\n", (unsigned int) cmd->body.type); return -EINVAL; diff --git a/drivers/hwmon/aquacomputer_d5next.c b/drivers/hwmon/aquacomputer_d5next.c index c51a2678f0eb..8c7796d3fdd2 100644 --- a/drivers/hwmon/aquacomputer_d5next.c +++ b/drivers/hwmon/aquacomputer_d5next.c @@ -12,9 +12,11 @@

#include <linux/crc16.h> #include <linux/debugfs.h> +#include <linux/delay.h> #include <linux/hid.h> #include <linux/hwmon.h> #include <linux/jiffies.h> +#include <linux/ktime.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/seq_file.h> @@ -49,6 +51,8 @@ static const char *const aqc_device_names[] = {

#define CTRL_REPORT_ID 0x03

+#define CTRL_REPORT_DELAY 200 /* ms */ + /* The HID report that the official software always sends * after writing values, currently same for all devices */ @@ -269,6 +273,9 @@ struct aqc_data { enum kinds kind; const char *name;

+ ktime_t last_ctrl_report_op; + int ctrl_report_delay; /* Delay between two ctrl report operations, in ms */ + int buffer_size; u8 *buffer; int checksum_start; @@ -325,17 +332,35 @@ static int aqc_pwm_to_percent(long val) return DIV_ROUND_CLOSEST(val * 100 * 100, 255); }

+static void aqc_delay_ctrl_report(struct aqc_data *priv) +{ + /* + * If previous read or write is too close to this one, delay the current operation + * to give the device enough time to process the previous one. + */ + if (priv->ctrl_report_delay) { + s64 delta = ktime_ms_delta(ktime_get(), priv->last_ctrl_report_op); + + if (delta < priv->ctrl_report_delay) + msleep(priv->ctrl_report_delay - delta); + } +} + /* Expects the mutex to be locked */ static int aqc_get_ctrl_data(struct aqc_data *priv) { int ret;

+ aqc_delay_ctrl_report(priv); + memset(priv->buffer, 0x00, priv->buffer_size); ret = hid_hw_raw_request(priv->hdev, CTRL_REPORT_ID, priv->buffer, priv->buffer_size, HID_FEATURE_REPORT, HID_REQ_GET_REPORT); if (ret < 0) ret = -ENODATA;

+ priv->last_ctrl_report_op = ktime_get(); + return ret; }

@@ -345,6 +370,8 @@ static int aqc_send_ctrl_data(struct aqc_data *priv) int ret; u16 checksum;

+ aqc_delay_ctrl_report(priv); + /* Init and xorout value for CRC-16/USB is 0xffff */ checksum = crc16(0xffff, priv->buffer + priv->checksum_start, priv->checksum_length); checksum ^= 0xffff; @@ -356,12 +383,16 @@ static int aqc_send_ctrl_data(struct aqc_data *priv) ret = hid_hw_raw_request(priv->hdev, CTRL_REPORT_ID, priv->buffer, priv->buffer_size, HID_FEATURE_REPORT, HID_REQ_SET_REPORT); if (ret < 0) - return ret; + goto record_access_and_ret;

/* The official software sends this report after every change, so do it here as well */ ret = hid_hw_raw_request(priv->hdev, SECONDARY_CTRL_REPORT_ID, secondary_ctrl_report, SECONDARY_CTRL_REPORT_SIZE, HID_FEATURE_REPORT, HID_REQ_SET_REPORT); + +record_access_and_ret: + priv->last_ctrl_report_op = ktime_get(); + return ret; }

@@ -853,6 +884,7 @@ static int aqc_probe(struct hid_device *hdev, const struct hid_device_id *id) priv->virtual_temp_sensor_start_offset = D5NEXT_VIRTUAL_SENSORS_START; priv->power_cycle_count_offset = D5NEXT_POWER_CYCLES; priv->buffer_size = D5NEXT_CTRL_REPORT_SIZE; + priv->ctrl_report_delay = CTRL_REPORT_DELAY;

priv->temp_label = label_d5next_temp; priv->virtual_temp_label = label_virtual_temp_sensors; @@ -893,6 +925,7 @@ static int aqc_probe(struct hid_device *hdev, const struct hid_device_id *id) priv->virtual_temp_sensor_start_offset = OCTO_VIRTUAL_SENSORS_START; priv->power_cycle_count_offset = OCTO_POWER_CYCLES; priv->buffer_size = OCTO_CTRL_REPORT_SIZE; + priv->ctrl_report_delay = CTRL_REPORT_DELAY;

priv->temp_label = label_temp_sensors; priv->virtual_temp_label = label_virtual_temp_sensors; @@ -913,6 +946,7 @@ static int aqc_probe(struct hid_device *hdev, const struct hid_device_id *id) priv->virtual_temp_sensor_start_offset = QUADRO_VIRTUAL_SENSORS_START; priv->power_cycle_count_offset = QUADRO_POWER_CYCLES; priv->buffer_size = QUADRO_CTRL_REPORT_SIZE; + priv->ctrl_report_delay = CTRL_REPORT_DELAY; priv->flow_sensor_offset = QUADRO_FLOW_SENSOR_OFFSET;

priv->temp_label = label_temp_sensors; diff --git a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_enc.c b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_enc.c index d810a78dde51..31e3c3766218 100644 --- a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_enc.c +++ b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_enc.c @@ -821,6 +821,8 @@ static int vb2ops_venc_queue_setup(struct vb2_queue *vq, return -EINVAL;

if (*nplanes) { + if (*nplanes != q_data->fmt->num_planes) + return -EINVAL; for (i = 0; i < *nplanes; i++) if (sizes[i] < q_data->sizeimage[i]) return -EINVAL; diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index b9dbad3a8af8..fc5da5d7744d 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -660,10 +660,10 @@ static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond) return NULL; arp = (struct arp_pkt *)skb_network_header(skb);

- /* Don't modify or load balance ARPs that do not originate locally - * (e.g.,arrive via a bridge). + /* Don't modify or load balance ARPs that do not originate + * from the bond itself or a VLAN directly above the bond. */ - if (!bond_slave_has_mac_rx(bond, arp->mac_src)) + if (!bond_slave_has_mac_rcu(bond, arp->mac_src)) return NULL;

dev = ip_dev_find(dev_net(bond->dev), arp->ip_src); diff --git a/drivers/net/can/vxcan.c b/drivers/net/can/vxcan.c index 26a472d2ea58..6d549dbdb467 100644 --- a/drivers/net/can/vxcan.c +++ b/drivers/net/can/vxcan.c @@ -192,12 +192,7 @@ static int vxcan_newlink(struct net *net, struct net_device *dev,

nla_peer = data[VXCAN_INFO_PEER]; ifmp = nla_data(nla_peer); - err = rtnl_nla_parse_ifla(peer_tb, - nla_data(nla_peer) + - sizeof(struct ifinfomsg), - nla_len(nla_peer) - - sizeof(struct ifinfomsg), - NULL); + err = rtnl_nla_parse_ifinfomsg(peer_tb, nla_peer, extack); if (err < 0) return err;

diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 51d2ef0dc835..b988c8a40d53 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -1005,6 +1005,10 @@ mt753x_trap_frames(struct mt7530_priv *priv) mt7530_rmw(priv, MT753X_BPC, MT753X_BPDU_PORT_FW_MASK, MT753X_BPDU_CPU_ONLY);

+ /* Trap 802.1X PAE frames to the CPU port(s) */ + mt7530_rmw(priv, MT753X_BPC, MT753X_PAE_PORT_FW_MASK, + MT753X_PAE_PORT_FW(MT753X_BPDU_CPU_ONLY)); + /* Trap LLDP frames with :0E MAC DA to the CPU port(s) */ mt7530_rmw(priv, MT753X_RGAC2, MT753X_R0E_PORT_FW_MASK, MT753X_R0E_PORT_FW(MT753X_BPDU_CPU_ONLY)); diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h index 9a45663d8b4e..6202b0f8c3f3 100644 --- a/drivers/net/dsa/mt7530.h +++ b/drivers/net/dsa/mt7530.h @@ -64,6 +64,8 @@ enum mt753x_id { /* Registers for BPDU and PAE frame control*/ #define MT753X_BPC 0x24 #define MT753X_BPDU_PORT_FW_MASK GENMASK(2, 0) +#define MT753X_PAE_PORT_FW_MASK GENMASK(18, 16) +#define MT753X_PAE_PORT_FW(x) FIELD_PREP(MT753X_PAE_PORT_FW_MASK, x)

/* Register for :03 and :0E MAC DA frame control */ #define MT753X_RGAC2 0x2c diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index 5f6af0870dfd..0186482194d2 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -1071,6 +1071,9 @@ static u64 vsc9959_tas_remaining_gate_len_ps(u64 gate_len_ns) if (gate_len_ns == U64_MAX) return U64_MAX;

+ if (gate_len_ns < VSC9959_TAS_MIN_GATE_LEN_NS) + return 0; + return (gate_len_ns - VSC9959_TAS_MIN_GATE_LEN_NS) * PSEC_PER_NSEC; }

diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c index 10c7c232cc4e..52ee3751187a 100644 --- a/drivers/net/ethernet/broadcom/bgmac.c +++ b/drivers/net/ethernet/broadcom/bgmac.c @@ -1448,7 +1448,7 @@ int bgmac_phy_connect_direct(struct bgmac *bgmac) int err;

phy_dev = fixed_phy_register(PHY_POLL, &fphy_status, NULL); - if (!phy_dev || IS_ERR(phy_dev)) { + if (IS_ERR(phy_dev)) { dev_err(bgmac->dev, "Failed to register fixed PHY device\n"); return -ENODEV; } diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index 1fe8038587ac..1779ee524dac 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -608,7 +608,7 @@ static int bcmgenet_mii_pd_init(struct bcmgenet_priv *priv) };

phydev = fixed_phy_register(PHY_POLL, &fphy_status, NULL); - if (!phydev || IS_ERR(phydev)) { + if (IS_ERR(phydev)) { dev_err(kdev, "failed to register fixed PHY device\n"); return -ENODEV; } diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c index c2e7037c7ba1..7750702900fa 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c @@ -1466,7 +1466,7 @@ static void make_established(struct sock *sk, u32 snd_isn, unsigned int opt) tp->write_seq = snd_isn; tp->snd_nxt = snd_isn; tp->snd_una = snd_isn; - inet_sk(sk)->inet_id = get_random_u16(); + atomic_set(&inet_sk(sk)->inet_id, get_random_u16()); assign_rxopt(sk, opt);

if (tp->rcv_wnd > (RCV_BUFSIZ_M << 10)) diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index 5b96cd94dcd2..0b4ec6e41eb4 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -203,7 +203,7 @@ static inline void ibmveth_flush_buffer(void *addr, unsigned long length) unsigned long offset;

for (offset = 0; offset < length; offset += SMP_CACHE_BYTES) - asm("dcbfl %0,%1" :: "b" (addr), "r" (offset)); + asm("dcbf %0,%1,1" :: "b" (addr), "r" (offset)); }

/* replenish the buffers for a pool. note that we don't need to diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 0e01b1927c1c..08ccf0024ce1 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -2615,7 +2615,7 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) retval = i40e_correct_mac_vlan_filters (vsi, &tmp_add_list, &tmp_del_list, vlan_filters); - else + else if (pf->vf) retval = i40e_correct_vf_mac_vlan_filters (vsi, &tmp_add_list, &tmp_del_list, vlan_filters, pf->vf[vsi->vf_id].trusted); @@ -2788,7 +2788,8 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) }

/* if the VF is not trusted do not do promisc */ - if ((vsi->type == I40E_VSI_SRIOV) && !pf->vf[vsi->vf_id].trusted) { + if (vsi->type == I40E_VSI_SRIOV && pf->vf && + !pf->vf[vsi->vf_id].trusted) { clear_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state); goto out; } diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index e864634d66bc..818eca6aa4a4 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -396,7 +396,8 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring) /* Receive Packet Data Buffer Size. * The Packet Data Buffer Size is defined in 128 byte units. */ - rlan_ctx.dbuf = ring->rx_buf_len >> ICE_RLAN_CTX_DBUF_S; + rlan_ctx.dbuf = DIV_ROUND_UP(ring->rx_buf_len, + BIT_ULL(ICE_RLAN_CTX_DBUF_S));

/* use 32 byte descriptors */ rlan_ctx.dsize = 1; diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c index b8c31bf721ad..b719e9a771e3 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.c +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -1240,7 +1240,7 @@ int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena) if (!vf) return -EINVAL;

- ret = ice_check_vf_ready_for_reset(vf); + ret = ice_check_vf_ready_for_cfg(vf); if (ret) goto out_put_vf;

@@ -1355,7 +1355,7 @@ int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) goto out_put_vf; }

- ret = ice_check_vf_ready_for_reset(vf); + ret = ice_check_vf_ready_for_cfg(vf); if (ret) goto out_put_vf;

@@ -1409,7 +1409,7 @@ int ice_set_vf_trust(struct net_device *netdev, int vf_id, bool trusted) return -EOPNOTSUPP; }

- ret = ice_check_vf_ready_for_reset(vf); + ret = ice_check_vf_ready_for_cfg(vf); if (ret) goto out_put_vf;

@@ -1722,7 +1722,7 @@ ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, if (!vf) return -EINVAL;

- ret = ice_check_vf_ready_for_reset(vf); + ret = ice_check_vf_ready_for_cfg(vf); if (ret) goto out_put_vf;

diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c index 71047fc34139..9dbe6e9bb1f7 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c @@ -185,25 +185,6 @@ int ice_check_vf_ready_for_cfg(struct ice_vf *vf) return 0; }

-/** - * ice_check_vf_ready_for_reset - check if VF is ready to be reset - * @vf: VF to check if it's ready to be reset - * - * The purpose of this function is to ensure that the VF is not in reset, - * disabled, and is both initialized and active, thus enabling us to safely - * initialize another reset. - */ -int ice_check_vf_ready_for_reset(struct ice_vf *vf) -{ - int ret; - - ret = ice_check_vf_ready_for_cfg(vf); - if (!ret && !test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) - ret = -EAGAIN; - - return ret; -} - /** * ice_trigger_vf_reset - Reset a VF on HW * @vf: pointer to the VF structure @@ -588,11 +569,17 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags) return 0; }

+ if (flags & ICE_VF_RESET_LOCK) + mutex_lock(&vf->cfg_lock); + else + lockdep_assert_held(&vf->cfg_lock); + if (ice_is_vf_disabled(vf)) { vsi = ice_get_vf_vsi(vf); if (!vsi) { dev_dbg(dev, "VF is already removed\n"); - return -EINVAL; + err = -EINVAL; + goto out_unlock; } ice_vsi_stop_lan_tx_rings(vsi, ICE_NO_RESET, vf->vf_id);

@@ -601,14 +588,9 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags)

dev_dbg(dev, "VF is already disabled, there is no need for resetting it, telling VM, all is fine %d\n", vf->vf_id); - return 0; + goto out_unlock; }

- if (flags & ICE_VF_RESET_LOCK) - mutex_lock(&vf->cfg_lock); - else - lockdep_assert_held(&vf->cfg_lock); - /* Set VF disable bit state here, before triggering reset */ set_bit(ICE_VF_STATE_DIS, vf->vf_states); ice_trigger_vf_reset(vf, flags & ICE_VF_RESET_VFLR, false); diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.h b/drivers/net/ethernet/intel/ice/ice_vf_lib.h index e5bed8572462..9f7fcd8e5714 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.h @@ -214,7 +214,6 @@ u16 ice_get_num_vfs(struct ice_pf *pf); struct ice_vsi *ice_get_vf_vsi(struct ice_vf *vf); bool ice_is_vf_disabled(struct ice_vf *vf); int ice_check_vf_ready_for_cfg(struct ice_vf *vf); -int ice_check_vf_ready_for_reset(struct ice_vf *vf); void ice_set_vf_state_dis(struct ice_vf *vf); bool ice_is_any_vf_in_unicast_promisc(struct ice_pf *pf); void diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index ef3c709d6a75..2b4c791b6cba 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -3722,7 +3722,6 @@ void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event) ice_vc_notify_vf_link_state(vf); break; case VIRTCHNL_OP_RESET_VF: - clear_bit(ICE_VF_STATE_ACTIVE, vf->vf_states); ops->reset_vf(vf); break; case VIRTCHNL_OP_ADD_ETH_ADDR: diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index 15e57460e19e..07171e574e7d 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -1404,18 +1404,6 @@ void igb_ptp_init(struct igb_adapter *adapter) return; }

- spin_lock_init(&adapter->tmreg_lock); - INIT_WORK(&adapter->ptp_tx_work, igb_ptp_tx_work); - - if (adapter->ptp_flags & IGB_PTP_OVERFLOW_CHECK) - INIT_DELAYED_WORK(&adapter->ptp_overflow_work, - igb_ptp_overflow_check); - - adapter->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE; - adapter->tstamp_config.tx_type = HWTSTAMP_TX_OFF; - - igb_ptp_reset(adapter); - adapter->ptp_clock = ptp_clock_register(&adapter->ptp_caps, &adapter->pdev->dev); if (IS_ERR(adapter->ptp_clock)) { @@ -1425,6 +1413,18 @@ void igb_ptp_init(struct igb_adapter *adapter) dev_info(&adapter->pdev->dev, "added PHC on %s\n", adapter->netdev->name); adapter->ptp_flags |= IGB_PTP_ENABLED; + + spin_lock_init(&adapter->tmreg_lock); + INIT_WORK(&adapter->ptp_tx_work, igb_ptp_tx_work); + + if (adapter->ptp_flags & IGB_PTP_OVERFLOW_CHECK) + INIT_DELAYED_WORK(&adapter->ptp_overflow_work, + igb_ptp_overflow_check); + + adapter->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE; + adapter->tstamp_config.tx_type = HWTSTAMP_TX_OFF; + + igb_ptp_reset(adapter); } }

diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h index dbfa4b9dee06..90ca01889cd8 100644 --- a/drivers/net/ethernet/intel/igc/igc_defines.h +++ b/drivers/net/ethernet/intel/igc/igc_defines.h @@ -536,7 +536,7 @@ #define IGC_PTM_CTRL_START_NOW BIT(29) /* Start PTM Now */ #define IGC_PTM_CTRL_EN BIT(30) /* Enable PTM */ #define IGC_PTM_CTRL_TRIG BIT(31) /* PTM Cycle trigger */ -#define IGC_PTM_CTRL_SHRT_CYC(usec) (((usec) & 0x2f) << 2) +#define IGC_PTM_CTRL_SHRT_CYC(usec) (((usec) & 0x3f) << 2) #define IGC_PTM_CTRL_PTM_TO(usec) (((usec) & 0xff) << 8)

#define IGC_PTM_SHORT_CYC_DEFAULT 10 /* Default Short/interrupted cycle interval */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 705325431dec..5541e284cd3f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -4005,9 +4005,10 @@ int rvu_mbox_handler_nix_set_hw_frs(struct rvu *rvu, struct nix_frs_cfg *req, if (link < 0) return NIX_AF_ERR_RX_LINK_INVALID;

- nix_find_link_frs(rvu, req, pcifunc);

linkcfg: + nix_find_link_frs(rvu, req, pcifunc); + cfg = rvu_read64(rvu, blkaddr, NIX_AF_RX_LINKX_CFG(link)); cfg = (cfg & ~(0xFFFFULL << 16)) | ((u64)req->maxlen << 16); if (req->update_minlen) diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c index bd1a51a0a540..f208a237d0b5 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c @@ -32,8 +32,8 @@ static const struct mlxsw_afk_element_info mlxsw_afk_element_infos[] = { MLXSW_AFK_ELEMENT_INFO_U32(IP_TTL_, 0x18, 0, 8), MLXSW_AFK_ELEMENT_INFO_U32(IP_ECN, 0x18, 9, 2), MLXSW_AFK_ELEMENT_INFO_U32(IP_DSCP, 0x18, 11, 6), - MLXSW_AFK_ELEMENT_INFO_U32(VIRT_ROUTER_MSB, 0x18, 17, 3), - MLXSW_AFK_ELEMENT_INFO_U32(VIRT_ROUTER_LSB, 0x18, 20, 8), + MLXSW_AFK_ELEMENT_INFO_U32(VIRT_ROUTER_MSB, 0x18, 17, 4), + MLXSW_AFK_ELEMENT_INFO_U32(VIRT_ROUTER_LSB, 0x18, 21, 8), MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP_96_127, 0x20, 4), MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP_64_95, 0x24, 4), MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP_32_63, 0x28, 4), diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index c968309657dd..51eea1f0529c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -517,11 +517,15 @@ static void mlxsw_pci_skb_cb_ts_set(struct mlxsw_pci *mlxsw_pci, struct sk_buff *skb, enum mlxsw_pci_cqe_v cqe_v, char *cqe) { + u8 ts_type; + if (cqe_v != MLXSW_PCI_CQE_V2) return;

- if (mlxsw_pci_cqe2_time_stamp_type_get(cqe) != - MLXSW_PCI_CQE_TIME_STAMP_TYPE_UTC) + ts_type = mlxsw_pci_cqe2_time_stamp_type_get(cqe); + + if (ts_type != MLXSW_PCI_CQE_TIME_STAMP_TYPE_UTC && + ts_type != MLXSW_PCI_CQE_TIME_STAMP_TYPE_MIRROR_UTC) return;

mlxsw_skb_cb(skb)->cqe_ts.sec = mlxsw_pci_cqe2_time_stamp_sec_get(cqe); diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 0777bed5bb1a..a34ff19c58bd 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -97,14 +97,6 @@ MLXSW_ITEM32(reg, sspr, m, 0x00, 31, 1); */ MLXSW_ITEM32_LP(reg, sspr, 0x00, 16, 0x00, 12);

-/* reg_sspr_sub_port - * Virtual port within the physical port. - * Should be set to 0 when virtual ports are not enabled on the port. - * - * Access: RW - */ -MLXSW_ITEM32(reg, sspr, sub_port, 0x00, 8, 8); - /* reg_sspr_system_port * Unique identifier within the stacking domain that represents all the ports * that are available in the system (external ports). @@ -120,7 +112,6 @@ static inline void mlxsw_reg_sspr_pack(char *payload, u16 local_port) MLXSW_REG_ZERO(sspr, payload); mlxsw_reg_sspr_m_set(payload, 1); mlxsw_reg_sspr_local_port_set(payload, local_port); - mlxsw_reg_sspr_sub_port_set(payload, 0); mlxsw_reg_sspr_system_port_set(payload, local_port); }

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c index e4f4cded2b6f..b1178b7a7f51 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c @@ -193,7 +193,7 @@ mlxsw_sp2_mr_tcam_rule_parse(struct mlxsw_sp_acl_rule *rule, key->vrid, GENMASK(7, 0)); mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_VIRT_ROUTER_MSB, - key->vrid >> 8, GENMASK(2, 0)); + key->vrid >> 8, GENMASK(3, 0)); switch (key->proto) { case MLXSW_SP_L3_PROTO_IPV4: return mlxsw_sp2_mr_tcam_rule_parse4(rulei, key); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c index 00c32320f891..173808c096ba 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c @@ -169,7 +169,7 @@ static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_2[] = {

static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_4[] = { MLXSW_AFK_ELEMENT_INST_U32(VIRT_ROUTER_LSB, 0x04, 24, 8), - MLXSW_AFK_ELEMENT_INST_U32(VIRT_ROUTER_MSB, 0x00, 0, 3), + MLXSW_AFK_ELEMENT_INST_EXT_U32(VIRT_ROUTER_MSB, 0x00, 0, 3, 0, true), };

static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_0[] = { @@ -319,7 +319,7 @@ static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_mac_5b[] = {

static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_4b[] = { MLXSW_AFK_ELEMENT_INST_U32(VIRT_ROUTER_LSB, 0x04, 13, 8), - MLXSW_AFK_ELEMENT_INST_EXT_U32(VIRT_ROUTER_MSB, 0x04, 21, 4, 0, true), + MLXSW_AFK_ELEMENT_INST_U32(VIRT_ROUTER_MSB, 0x04, 21, 4), };

static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_2b[] = { diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 796a38f9d7b2..cd16bc8bf154 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -748,7 +748,8 @@ static int ipvlan_device_event(struct notifier_block *unused,

write_pnet(&port->pnet, newnet);

- ipvlan_migrate_l3s_hook(oldnet, newnet); + if (port->mode == IPVLAN_MODE_L3S) + ipvlan_migrate_l3s_hook(oldnet, newnet); break; } case NETDEV_UNREGISTER: diff --git a/drivers/net/veth.c b/drivers/net/veth.c index a71786b3e7ba..727b9278b9fe 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -1716,10 +1716,7 @@ static int veth_newlink(struct net *src_net, struct net_device *dev,

nla_peer = data[VETH_INFO_PEER]; ifmp = nla_data(nla_peer); - err = rtnl_nla_parse_ifla(peer_tb, - nla_data(nla_peer) + sizeof(struct ifinfomsg), - nla_len(nla_peer) - sizeof(struct ifinfomsg), - NULL); + err = rtnl_nla_parse_ifinfomsg(peer_tb, nla_peer, extack); if (err < 0) return err;

diff --git a/drivers/of/dynamic.c b/drivers/of/dynamic.c index cd3821a6444f..4e436f2d13ae 100644 --- a/drivers/of/dynamic.c +++ b/drivers/of/dynamic.c @@ -63,15 +63,14 @@ int of_reconfig_notifier_unregister(struct notifier_block *nb) } EXPORT_SYMBOL_GPL(of_reconfig_notifier_unregister);

-#ifdef DEBUG -const char *action_names[] = { +static const char *action_names[] = { + [0] = "INVALID", [OF_RECONFIG_ATTACH_NODE] = "ATTACH_NODE", [OF_RECONFIG_DETACH_NODE] = "DETACH_NODE", [OF_RECONFIG_ADD_PROPERTY] = "ADD_PROPERTY", [OF_RECONFIG_REMOVE_PROPERTY] = "REMOVE_PROPERTY", [OF_RECONFIG_UPDATE_PROPERTY] = "UPDATE_PROPERTY", }; -#endif

int of_reconfig_notify(unsigned long action, struct of_reconfig_data *p) { @@ -594,21 +593,9 @@ static int __of_changeset_entry_apply(struct of_changeset_entry *ce) }

ret = __of_add_property(ce->np, ce->prop); - if (ret) { - pr_err("changeset: add_property failed @%pOF/%s\n", - ce->np, - ce->prop->name); - break; - } break; case OF_RECONFIG_REMOVE_PROPERTY: ret = __of_remove_property(ce->np, ce->prop); - if (ret) { - pr_err("changeset: remove_property failed @%pOF/%s\n", - ce->np, - ce->prop->name); - break; - } break;

case OF_RECONFIG_UPDATE_PROPERTY: @@ -622,20 +609,17 @@ static int __of_changeset_entry_apply(struct of_changeset_entry *ce) }

ret = __of_update_property(ce->np, ce->prop, &old_prop); - if (ret) { - pr_err("changeset: update_property failed @%pOF/%s\n", - ce->np, - ce->prop->name); - break; - } break; default: ret = -EINVAL; } raw_spin_unlock_irqrestore(&devtree_lock, flags);

- if (ret) + if (ret) { + pr_err("changeset: apply failed: %-15s %pOF:%s\n", + action_names[ce->action], ce->np, ce->prop->name); return ret; + }

switch (ce->action) { case OF_RECONFIG_ATTACH_NODE: @@ -921,6 +905,9 @@ int of_changeset_action(struct of_changeset *ocs, unsigned long action, if (!ce) return -ENOMEM;

+ if (WARN_ON(action >= ARRAY_SIZE(action_names))) + return -EINVAL; + /* get a reference to the node */ ce->action = action; ce->np = of_node_get(np); diff --git a/drivers/of/kexec.c b/drivers/of/kexec.c index f26d2ba8a371..68278340cecf 100644 --- a/drivers/of/kexec.c +++ b/drivers/of/kexec.c @@ -184,7 +184,8 @@ int __init ima_free_kexec_buffer(void) if (ret) return ret;

- return memblock_phys_free(addr, size); + memblock_free_late(addr, size); + return 0; } #endif

diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c index b89ab5d9fea5..9be6ed47a1ce 100644 --- a/drivers/of/unittest.c +++ b/drivers/of/unittest.c @@ -657,12 +657,12 @@ static void __init of_unittest_parse_phandle_with_args_map(void) memset(&args, 0, sizeof(args));

EXPECT_BEGIN(KERN_INFO, - "OF: /testcase-data/phandle-tests/consumer-b: could not find phandle"); + "OF: /testcase-data/phandle-tests/consumer-b: could not find phandle 12345678");

rc = of_parse_phandle_with_args_map(np, "phandle-list-bad-phandle", "phandle", 0, &args); EXPECT_END(KERN_INFO, - "OF: /testcase-data/phandle-tests/consumer-b: could not find phandle"); + "OF: /testcase-data/phandle-tests/consumer-b: could not find phandle 12345678");

unittest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc);

diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c index 6efa3d8db9a5..ea0195337bab 100644 --- a/drivers/pci/hotplug/acpiphp_glue.c +++ b/drivers/pci/hotplug/acpiphp_glue.c @@ -504,12 +504,15 @@ static void enable_slot(struct acpiphp_slot *slot, bool bridge) if (pass && dev->subordinate) { check_hotplug_bridge(slot, dev); pcibios_resource_survey_bus(dev->subordinate); - __pci_bus_size_bridges(dev->subordinate, - &add_list); + if (pci_is_root_bus(bus)) + __pci_bus_size_bridges(dev->subordinate, &add_list); } } } - __pci_bus_assign_resources(bus, &add_list, NULL); + if (pci_is_root_bus(bus)) + __pci_bus_assign_resources(bus, &add_list, NULL); + else + pci_assign_unassigned_bridge_resources(bus->self); }

acpiphp_sanitize_bus(bus); diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index a8df77e80549..be6838c252f0 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -862,6 +862,33 @@ static const struct pinconf_ops amd_pinconf_ops = { .pin_config_group_set = amd_pinconf_group_set, };

+static void amd_gpio_irq_init(struct amd_gpio *gpio_dev) +{ + struct pinctrl_desc *desc = gpio_dev->pctrl->desc; + unsigned long flags; + u32 pin_reg, mask; + int i; + + mask = BIT(WAKE_CNTRL_OFF_S0I3) | BIT(WAKE_CNTRL_OFF_S3) | + BIT(WAKE_CNTRL_OFF_S4); + + for (i = 0; i < desc->npins; i++) { + int pin = desc->pins[i].number; + const struct pin_desc *pd = pin_desc_get(gpio_dev->pctrl, pin); + + if (!pd) + continue; + + raw_spin_lock_irqsave(&gpio_dev->lock, flags); + + pin_reg = readl(gpio_dev->base + pin * 4); + pin_reg &= ~mask; + writel(pin_reg, gpio_dev->base + pin * 4); + + raw_spin_unlock_irqrestore(&gpio_dev->lock, flags); + } +} + #ifdef CONFIG_PM_SLEEP static bool amd_gpio_should_save(struct amd_gpio *gpio_dev, unsigned int pin) { @@ -1099,6 +1126,9 @@ static int amd_gpio_probe(struct platform_device *pdev) return PTR_ERR(gpio_dev->pctrl); }

+ /* Disable and mask interrupts */ + amd_gpio_irq_init(gpio_dev); + girq = &gpio_dev->gc.irq; gpio_irq_chip_set_chip(girq, &amd_gpio_irqchip); /* This will let us handle the parent IRQ in the driver */ diff --git a/drivers/pinctrl/renesas/pinctrl-rza2.c b/drivers/pinctrl/renesas/pinctrl-rza2.c index c0a04f1ee994..12126e30dc20 100644 --- a/drivers/pinctrl/renesas/pinctrl-rza2.c +++ b/drivers/pinctrl/renesas/pinctrl-rza2.c @@ -14,6 +14,7 @@ #include <linux/gpio/driver.h> #include <linux/io.h> #include <linux/module.h> +#include <linux/mutex.h> #include <linux/of_device.h> #include <linux/pinctrl/pinmux.h>

@@ -46,6 +47,7 @@ struct rza2_pinctrl_priv { struct pinctrl_dev *pctl; struct pinctrl_gpio_range gpio_range; int npins; + struct mutex mutex; /* serialize adding groups and functions */ };

#define RZA2_PDR(port) (0x0000 + (port) * 2) /* Direction 16-bit */ @@ -358,10 +360,14 @@ static int rza2_dt_node_to_map(struct pinctrl_dev *pctldev, psel_val[i] = MUX_FUNC(value); }

+ mutex_lock(&priv->mutex); + /* Register a single pin group listing all the pins we read from DT */ gsel = pinctrl_generic_add_group(pctldev, np->name, pins, npins, NULL); - if (gsel < 0) - return gsel; + if (gsel < 0) { + ret = gsel; + goto unlock; + }

/* * Register a single group function where the 'data' is an array PSEL @@ -390,6 +396,8 @@ static int rza2_dt_node_to_map(struct pinctrl_dev *pctldev, (*map)->data.mux.function = np->name; *num_maps = 1;

+ mutex_unlock(&priv->mutex); + return 0;

remove_function: @@ -398,6 +406,9 @@ static int rza2_dt_node_to_map(struct pinctrl_dev *pctldev, remove_group: pinctrl_generic_remove_group(pctldev, gsel);

+unlock: + mutex_unlock(&priv->mutex); + dev_err(priv->dev, "Unable to parse DT node %s\n", np->name);

return ret; @@ -473,6 +484,8 @@ static int rza2_pinctrl_probe(struct platform_device *pdev) if (IS_ERR(priv->base)) return PTR_ERR(priv->base);

+ mutex_init(&priv->mutex); + platform_set_drvdata(pdev, priv);

priv->npins = (int)(uintptr_t)of_device_get_match_data(&pdev->dev) * diff --git a/drivers/pinctrl/renesas/pinctrl-rzg2l.c b/drivers/pinctrl/renesas/pinctrl-rzg2l.c index fd11d28e5a1e..2a617832a7e6 100644 --- a/drivers/pinctrl/renesas/pinctrl-rzg2l.c +++ b/drivers/pinctrl/renesas/pinctrl-rzg2l.c @@ -11,6 +11,7 @@ #include <linux/io.h> #include <linux/interrupt.h> #include <linux/module.h> +#include <linux/mutex.h> #include <linux/of_device.h> #include <linux/of_irq.h> #include <linux/pinctrl/pinconf-generic.h> @@ -146,10 +147,11 @@ struct rzg2l_pinctrl { struct gpio_chip gpio_chip; struct pinctrl_gpio_range gpio_range; DECLARE_BITMAP(tint_slot, RZG2L_TINT_MAX_INTERRUPT); - spinlock_t bitmap_lock; + spinlock_t bitmap_lock; /* protect tint_slot bitmap */ unsigned int hwirq[RZG2L_TINT_MAX_INTERRUPT];

- spinlock_t lock; + spinlock_t lock; /* lock read/write registers */ + struct mutex mutex; /* serialize adding groups and functions */ };

static const unsigned int iolh_groupa_mA[] = { 2, 4, 8, 12 }; @@ -359,11 +361,13 @@ static int rzg2l_dt_subnode_to_map(struct pinctrl_dev *pctldev, name = np->name; }

+ mutex_lock(&pctrl->mutex); + /* Register a single pin group listing all the pins we read from DT */ gsel = pinctrl_generic_add_group(pctldev, name, pins, num_pinmux, NULL); if (gsel < 0) { ret = gsel; - goto done; + goto unlock; }

/* @@ -377,6 +381,8 @@ static int rzg2l_dt_subnode_to_map(struct pinctrl_dev *pctldev, goto remove_group; }

+ mutex_unlock(&pctrl->mutex); + maps[idx].type = PIN_MAP_TYPE_MUX_GROUP; maps[idx].data.mux.group = name; maps[idx].data.mux.function = name; @@ -388,6 +394,8 @@ static int rzg2l_dt_subnode_to_map(struct pinctrl_dev *pctldev,

remove_group: pinctrl_generic_remove_group(pctldev, gsel); +unlock: + mutex_unlock(&pctrl->mutex); done: *index = idx; kfree(configs); @@ -1501,6 +1509,7 @@ static int rzg2l_pinctrl_probe(struct platform_device *pdev)

spin_lock_init(&pctrl->lock); spin_lock_init(&pctrl->bitmap_lock); + mutex_init(&pctrl->mutex);

platform_set_drvdata(pdev, pctrl);

diff --git a/drivers/pinctrl/renesas/pinctrl-rzv2m.c b/drivers/pinctrl/renesas/pinctrl-rzv2m.c index 35f382b055e8..2858800288bb 100644 --- a/drivers/pinctrl/renesas/pinctrl-rzv2m.c +++ b/drivers/pinctrl/renesas/pinctrl-rzv2m.c @@ -14,6 +14,7 @@ #include <linux/gpio/driver.h> #include <linux/io.h> #include <linux/module.h> +#include <linux/mutex.h> #include <linux/of_device.h> #include <linux/pinctrl/pinconf-generic.h> #include <linux/pinctrl/pinconf.h> @@ -121,7 +122,8 @@ struct rzv2m_pinctrl { struct gpio_chip gpio_chip; struct pinctrl_gpio_range gpio_range;

- spinlock_t lock; + spinlock_t lock; /* lock read/write registers */ + struct mutex mutex; /* serialize adding groups and functions */ };

static const unsigned int drv_1_8V_group2_uA[] = { 1800, 3800, 7800, 11000 }; @@ -320,11 +322,13 @@ static int rzv2m_dt_subnode_to_map(struct pinctrl_dev *pctldev, name = np->name; }

+ mutex_lock(&pctrl->mutex); + /* Register a single pin group listing all the pins we read from DT */ gsel = pinctrl_generic_add_group(pctldev, name, pins, num_pinmux, NULL); if (gsel < 0) { ret = gsel; - goto done; + goto unlock; }

/* @@ -338,6 +342,8 @@ static int rzv2m_dt_subnode_to_map(struct pinctrl_dev *pctldev, goto remove_group; }

+ mutex_unlock(&pctrl->mutex); + maps[idx].type = PIN_MAP_TYPE_MUX_GROUP; maps[idx].data.mux.group = name; maps[idx].data.mux.function = name; @@ -349,6 +355,8 @@ static int rzv2m_dt_subnode_to_map(struct pinctrl_dev *pctldev,

remove_group: pinctrl_generic_remove_group(pctldev, gsel); +unlock: + mutex_unlock(&pctrl->mutex); done: *index = idx; kfree(configs); @@ -1070,6 +1078,7 @@ static int rzv2m_pinctrl_probe(struct platform_device *pdev) }

spin_lock_init(&pctrl->lock); + mutex_init(&pctrl->mutex);

platform_set_drvdata(pdev, pctrl);

diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c index bd38c7dcae34..de03b8889e9d 100644 --- a/drivers/platform/x86/ideapad-laptop.c +++ b/drivers/platform/x86/ideapad-laptop.c @@ -1176,6 +1176,11 @@ static const struct key_entry ideapad_keymap[] = { { KE_IGNORE, 0x03 | IDEAPAD_WMI_KEY }, /* Customizable Lenovo Hotkey ("star" with 'S' inside) */ { KE_KEY, 0x01 | IDEAPAD_WMI_KEY, { KEY_FAVORITES } }, + { KE_KEY, 0x04 | IDEAPAD_WMI_KEY, { KEY_SELECTIVE_SCREENSHOT } }, + /* Lenovo Support */ + { KE_KEY, 0x07 | IDEAPAD_WMI_KEY, { KEY_HELP } }, + { KE_KEY, 0x0e | IDEAPAD_WMI_KEY, { KEY_PICKUP_PHONE } }, + { KE_KEY, 0x0f | IDEAPAD_WMI_KEY, { KEY_HANGUP_PHONE } }, /* Dark mode toggle */ { KE_KEY, 0x13 | IDEAPAD_WMI_KEY, { KEY_PROG1 } }, /* Sound profile switch */ diff --git a/drivers/s390/crypto/zcrypt_msgtype6.c b/drivers/s390/crypto/zcrypt_msgtype6.c index f99a9ef42116..84e3ad290f6b 100644 --- a/drivers/s390/crypto/zcrypt_msgtype6.c +++ b/drivers/s390/crypto/zcrypt_msgtype6.c @@ -926,8 +926,7 @@ static void zcrypt_msgtype6_receive(struct ap_queue *aq, .type = TYPE82_RSP_CODE, .reply_code = REP82_ERROR_MACHINE_FAILURE, }; - struct response_type *resp_type = - (struct response_type *)msg->private; + struct response_type *resp_type = msg->private; struct type86x_reply *t86r; int len;

@@ -982,8 +981,7 @@ static void zcrypt_msgtype6_receive_ep11(struct ap_queue *aq, .type = TYPE82_RSP_CODE, .reply_code = REP82_ERROR_MACHINE_FAILURE, }; - struct response_type *resp_type = - (struct response_type *)msg->private; + struct response_type *resp_type = msg->private; struct type86_ep11_reply *t86r; int len;

@@ -1156,23 +1154,36 @@ static long zcrypt_msgtype6_send_cprb(bool userspace, struct zcrypt_queue *zq, struct ica_xcRB *xcrb, struct ap_message *ap_msg) { - int rc; - struct response_type *rtype = (struct response_type *)(ap_msg->private); + struct response_type *rtype = ap_msg->private; struct { struct type6_hdr hdr; struct CPRBX cprbx; /* ... more data blocks ... */ } __packed * msg = ap_msg->msg; - - /* - * Set the queue's reply buffer length minus 128 byte padding - * as reply limit for the card firmware. - */ - msg->hdr.fromcardlen1 = min_t(unsigned int, msg->hdr.fromcardlen1, - zq->reply.bufsize - 128); - if (msg->hdr.fromcardlen2) - msg->hdr.fromcardlen2 = - zq->reply.bufsize - msg->hdr.fromcardlen1 - 128; + unsigned int max_payload_size; + int rc, delta; + + /* calculate maximum payload for this card and msg type */ + max_payload_size = zq->reply.bufsize - sizeof(struct type86_fmt2_msg); + + /* limit each of the two from fields to the maximum payload size */ + msg->hdr.fromcardlen1 = min(msg->hdr.fromcardlen1, max_payload_size); + msg->hdr.fromcardlen2 = min(msg->hdr.fromcardlen2, max_payload_size); + + /* calculate delta if the sum of both exceeds max payload size */ + delta = msg->hdr.fromcardlen1 + msg->hdr.fromcardlen2 + - max_payload_size; + if (delta > 0) { + /* + * Sum exceeds maximum payload size, prune fromcardlen1 + * (always trust fromcardlen2) + */ + if (delta > msg->hdr.fromcardlen1) { + rc = -EINVAL; + goto out; + } + msg->hdr.fromcardlen1 -= delta; + }

init_completion(&rtype->work); rc = ap_queue_message(zq->queue, ap_msg); @@ -1243,7 +1254,7 @@ static long zcrypt_msgtype6_send_ep11_cprb(bool userspace, struct zcrypt_queue * { int rc; unsigned int lfmt; - struct response_type *rtype = (struct response_type *)(ap_msg->private); + struct response_type *rtype = ap_msg->private; struct { struct type6_hdr hdr; struct ep11_cprb cprbx; @@ -1365,7 +1376,7 @@ static long zcrypt_msgtype6_rng(struct zcrypt_queue *zq, short int verb_length; short int key_length; } __packed * msg = ap_msg->msg; - struct response_type *rtype = (struct response_type *)(ap_msg->private); + struct response_type *rtype = ap_msg->private; int rc;

msg->cprbx.domain = AP_QID_QUEUE(zq->queue->qid); diff --git a/drivers/scsi/raid_class.c b/drivers/scsi/raid_class.c index 711252e52d8e..95a86e0dfd77 100644 --- a/drivers/scsi/raid_class.c +++ b/drivers/scsi/raid_class.c @@ -209,54 +209,6 @@ raid_attr_ro_state(level); raid_attr_ro_fn(resync); raid_attr_ro_state_fn(state);

-static void raid_component_release(struct device *dev) -{ - struct raid_component *rc = - container_of(dev, struct raid_component, dev); - dev_printk(KERN_ERR, rc->dev.parent, "COMPONENT RELEASE\n"); - put_device(rc->dev.parent); - kfree(rc); -} - -int raid_component_add(struct raid_template *r,struct device *raid_dev, - struct device *component_dev) -{ - struct device *cdev = - attribute_container_find_class_device(&r->raid_attrs.ac, - raid_dev); - struct raid_component *rc; - struct raid_data *rd = dev_get_drvdata(cdev); - int err; - - rc = kzalloc(sizeof(*rc), GFP_KERNEL); - if (!rc) - return -ENOMEM; - - INIT_LIST_HEAD(&rc->node); - device_initialize(&rc->dev); - rc->dev.release = raid_component_release; - rc->dev.parent = get_device(component_dev); - rc->num = rd->component_count++; - - dev_set_name(&rc->dev, "component-%d", rc->num); - list_add_tail(&rc->node, &rd->component_list); - rc->dev.class = &raid_class.class; - err = device_add(&rc->dev); - if (err) - goto err_out; - - return 0; - -err_out: - put_device(&rc->dev); - list_del(&rc->node); - rd->component_count--; - put_device(component_dev); - kfree(rc); - return err; -} -EXPORT_SYMBOL(raid_component_add); - struct raid_template * raid_class_attach(struct raid_function_template *ft) { diff --git a/drivers/scsi/snic/snic_disc.c b/drivers/scsi/snic/snic_disc.c index cd27562ec922..6c529b37f3b4 100644 --- a/drivers/scsi/snic/snic_disc.c +++ b/drivers/scsi/snic/snic_disc.c @@ -303,12 +303,11 @@ snic_tgt_create(struct snic *snic, struct snic_tgt_id *tgtid) "Snic Tgt: device_add, with err = %d\n", ret);

- put_device(&tgt->dev); put_device(&snic->shost->shost_gendev); spin_lock_irqsave(snic->shost->host_lock, flags); list_del(&tgt->list); spin_unlock_irqrestore(snic->shost->host_lock, flags); - kfree(tgt); + put_device(&tgt->dev); tgt = NULL;

return tgt; diff --git a/drivers/thunderbolt/tmu.c b/drivers/thunderbolt/tmu.c index 626aca3124b1..d9544600b386 100644 --- a/drivers/thunderbolt/tmu.c +++ b/drivers/thunderbolt/tmu.c @@ -415,7 +415,8 @@ int tb_switch_tmu_disable(struct tb_switch *sw) * uni-directional mode and we don't want to change it's TMU * mode. */ - tb_switch_tmu_rate_write(sw, TB_SWITCH_TMU_RATE_OFF); + ret = tb_switch_tmu_rate_write(sw, TB_SWITCH_TMU_RATE_OFF); + return ret;

tb_port_tmu_time_sync_disable(up); ret = tb_port_tmu_time_sync_disable(down); diff --git a/drivers/video/aperture.c b/drivers/video/aperture.c index 5c94abdb1ad6..3e4a1f55f51b 100644 --- a/drivers/video/aperture.c +++ b/drivers/video/aperture.c @@ -298,14 +298,6 @@ int aperture_remove_conflicting_devices(resource_size_t base, resource_size_t si

aperture_detach_devices(base, size);

- /* - * If this is the primary adapter, there could be a VGA device - * that consumes the VGA framebuffer I/O range. Remove this device - * as well. - */ - if (primary) - aperture_detach_devices(VGA_FB_PHYS_BASE, VGA_FB_PHYS_SIZE); - return 0; } EXPORT_SYMBOL(aperture_remove_conflicting_devices); @@ -344,13 +336,22 @@ int aperture_remove_conflicting_pci_devices(struct pci_dev *pdev, const char *na aperture_detach_devices(base, size); }

- /* - * WARNING: Apparently we must kick fbdev drivers before vgacon, - * otherwise the vga fbdev driver falls over. - */ - ret = vga_remove_vgacon(pdev); - if (ret) - return ret; + if (primary) { + /* + * If this is the primary adapter, there could be a VGA device + * that consumes the VGA framebuffer I/O range. Remove this + * device as well. + */ + aperture_detach_devices(VGA_FB_PHYS_BASE, VGA_FB_PHYS_SIZE); + + /* + * WARNING: Apparently we must kick fbdev drivers before vgacon, + * otherwise the vga fbdev driver falls over. + */ + ret = vga_remove_vgacon(pdev); + if (ret) + return ret; + }

return 0;

diff --git a/drivers/video/fbdev/aty/radeon_base.c b/drivers/video/fbdev/aty/radeon_base.c index 8b28c9bddd97..50c384ce2883 100644 --- a/drivers/video/fbdev/aty/radeon_base.c +++ b/drivers/video/fbdev/aty/radeon_base.c @@ -2238,14 +2238,6 @@ static const struct bin_attribute edid2_attr = { .read = radeon_show_edid2, };

-static int radeon_kick_out_firmware_fb(struct pci_dev *pdev) -{ - resource_size_t base = pci_resource_start(pdev, 0); - resource_size_t size = pci_resource_len(pdev, 0); - - return aperture_remove_conflicting_devices(base, size, false, KBUILD_MODNAME); -} - static int radeonfb_pci_register(struct pci_dev *pdev, const struct pci_device_id *ent) { @@ -2296,7 +2288,7 @@ static int radeonfb_pci_register(struct pci_dev *pdev, rinfo->fb_base_phys = pci_resource_start (pdev, 0); rinfo->mmio_base_phys = pci_resource_start (pdev, 2);

- ret = radeon_kick_out_firmware_fb(pdev); + ret = aperture_remove_conflicting_pci_devices(pdev, KBUILD_MODNAME); if (ret) goto err_release_fb;

diff --git a/fs/attr.c b/fs/attr.c index b45f30e516fa..9b9a70e0cc54 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -47,6 +47,7 @@ int setattr_should_drop_sgid(struct user_namespace *mnt_userns, return ATTR_KILL_SGID; return 0; } +EXPORT_SYMBOL(setattr_should_drop_sgid);

/** * setattr_should_drop_suidgid - determine whether the set{g,u}id bit needs to diff --git a/fs/internal.h b/fs/internal.h index 46caa33373a4..42df013f7fe7 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -242,5 +242,3 @@ ssize_t __kernel_write_iter(struct file *file, struct iov_iter *from, loff_t *po /* * fs/attr.c */ -int setattr_should_drop_sgid(struct user_namespace *mnt_userns, - const struct inode *inode); diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index c4e0da6db719..9ec91017a7f3 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -27,7 +27,7 @@ * * Called with j_list_lock held. */ -static inline void __buffer_unlink_first(struct journal_head *jh) +static inline void __buffer_unlink(struct journal_head *jh) { transaction_t *transaction = jh->b_cp_transaction;

@@ -40,23 +40,6 @@ static inline void __buffer_unlink_first(struct journal_head *jh) } }

-/* - * Unlink a buffer from a transaction checkpoint(io) list. - * - * Called with j_list_lock held. - */ -static inline void __buffer_unlink(struct journal_head *jh) -{ - transaction_t *transaction = jh->b_cp_transaction; - - __buffer_unlink_first(jh); - if (transaction->t_checkpoint_io_list == jh) { - transaction->t_checkpoint_io_list = jh->b_cpnext; - if (transaction->t_checkpoint_io_list == jh) - transaction->t_checkpoint_io_list = NULL; - } -} - /* * Check a checkpoint buffer could be release or not. * @@ -366,50 +349,10 @@ int jbd2_cleanup_journal_tail(journal_t *journal)

/* Checkpoint list management */

-/* - * journal_clean_one_cp_list - * - * Find all the written-back checkpoint buffers in the given list and - * release them. If 'destroy' is set, clean all buffers unconditionally. - * - * Called with j_list_lock held. - * Returns 1 if we freed the transaction, 0 otherwise. - */ -static int journal_clean_one_cp_list(struct journal_head *jh, bool destroy) -{ - struct journal_head *last_jh; - struct journal_head *next_jh = jh; - - if (!jh) - return 0; - - last_jh = jh->b_cpprev; - do { - jh = next_jh; - next_jh = jh->b_cpnext; - - if (!destroy && __cp_buffer_busy(jh)) - return 0; - - if (__jbd2_journal_remove_checkpoint(jh)) - return 1; - /* - * This function only frees up some memory - * if possible so we dont have an obligation - * to finish processing. Bail out if preemption - * requested: - */ - if (need_resched()) - return 0; - } while (jh != last_jh); - - return 0; -} - /* * journal_shrink_one_cp_list * - * Find 'nr_to_scan' written-back checkpoint buffers in the given list + * Find all the written-back checkpoint buffers in the given list * and try to release them. If the whole transaction is released, set * the 'released' parameter. Return the number of released checkpointed * buffers. @@ -417,15 +360,15 @@ static int journal_clean_one_cp_list(struct journal_head *jh, bool destroy) * Called with j_list_lock held. */ static unsigned long journal_shrink_one_cp_list(struct journal_head *jh, - unsigned long *nr_to_scan, - bool *released) + bool destroy, bool *released) { struct journal_head *last_jh; struct journal_head *next_jh = jh; unsigned long nr_freed = 0; int ret;

- if (!jh || *nr_to_scan == 0) + *released = false; + if (!jh) return 0;

last_jh = jh->b_cpprev; @@ -433,12 +376,15 @@ static unsigned long journal_shrink_one_cp_list(struct journal_head *jh, jh = next_jh; next_jh = jh->b_cpnext;

- (*nr_to_scan)--; - if (__cp_buffer_busy(jh)) - continue; + if (destroy) { + ret = __jbd2_journal_remove_checkpoint(jh); + } else { + ret = jbd2_journal_try_remove_checkpoint(jh); + if (ret < 0) + continue; + }

nr_freed++; - ret = __jbd2_journal_remove_checkpoint(jh); if (ret) { *released = true; break; @@ -446,7 +392,7 @@ static unsigned long journal_shrink_one_cp_list(struct journal_head *jh,

if (need_resched()) break; - } while (jh != last_jh && *nr_to_scan); + } while (jh != last_jh);

return nr_freed; } @@ -464,11 +410,11 @@ unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal, unsigned long *nr_to_scan) { transaction_t *transaction, *last_transaction, *next_transaction; - bool released; + bool __maybe_unused released; tid_t first_tid = 0, last_tid = 0, next_tid = 0; tid_t tid = 0; unsigned long nr_freed = 0; - unsigned long nr_scanned = *nr_to_scan; + unsigned long freed;

again: spin_lock(&journal->j_list_lock); @@ -497,19 +443,11 @@ unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal, transaction = next_transaction; next_transaction = transaction->t_cpnext; tid = transaction->t_tid; - released = false;

- nr_freed += journal_shrink_one_cp_list(transaction->t_checkpoint_list, - nr_to_scan, &released); - if (*nr_to_scan == 0) - break; - if (need_resched() || spin_needbreak(&journal->j_list_lock)) - break; - if (released) - continue; - - nr_freed += journal_shrink_one_cp_list(transaction->t_checkpoint_io_list, - nr_to_scan, &released); + freed = journal_shrink_one_cp_list(transaction->t_checkpoint_list, + false, &released); + nr_freed += freed; + (*nr_to_scan) -= min(*nr_to_scan, freed); if (*nr_to_scan == 0) break; if (need_resched() || spin_needbreak(&journal->j_list_lock)) @@ -530,9 +468,8 @@ unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal, if (*nr_to_scan && next_tid) goto again; out: - nr_scanned -= *nr_to_scan; trace_jbd2_shrink_checkpoint_list(journal, first_tid, tid, last_tid, - nr_freed, nr_scanned, next_tid); + nr_freed, next_tid);

return nr_freed; } @@ -548,7 +485,7 @@ unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal, void __jbd2_journal_clean_checkpoint_list(journal_t *journal, bool destroy) { transaction_t *transaction, *last_transaction, *next_transaction; - int ret; + bool released;

transaction = journal->j_checkpoint_transactions; if (!transaction) @@ -559,8 +496,8 @@ void __jbd2_journal_clean_checkpoint_list(journal_t *journal, bool destroy) do { transaction = next_transaction; next_transaction = transaction->t_cpnext; - ret = journal_clean_one_cp_list(transaction->t_checkpoint_list, - destroy); + journal_shrink_one_cp_list(transaction->t_checkpoint_list, + destroy, &released); /* * This function only frees up some memory if possible so we * dont have an obligation to finish processing. Bail out if @@ -568,23 +505,12 @@ void __jbd2_journal_clean_checkpoint_list(journal_t *journal, bool destroy) */ if (need_resched()) return; - if (ret) - continue; - /* - * It is essential that we are as careful as in the case of - * t_checkpoint_list with removing the buffer from the list as - * we can possibly see not yet submitted buffers on io_list - */ - ret = journal_clean_one_cp_list(transaction-> - t_checkpoint_io_list, destroy); - if (need_resched()) - return; /* * Stop scanning if we couldn't free the transaction. This * avoids pointless scanning of transactions which still * weren't checkpointed. */ - if (!ret) + if (!released) return; } while (transaction != last_transaction); } @@ -663,7 +589,7 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh) jbd2_journal_put_journal_head(jh);

/* Is this transaction empty? */ - if (transaction->t_checkpoint_list || transaction->t_checkpoint_io_list) + if (transaction->t_checkpoint_list) return 0;

/* @@ -694,6 +620,34 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh) return 1; }

+/* + * Check the checkpoint buffer and try to remove it from the checkpoint + * list if it's clean. Returns -EBUSY if it is not clean, returns 1 if + * it frees the transaction, 0 otherwise. + * + * This function is called with j_list_lock held. + */ +int jbd2_journal_try_remove_checkpoint(struct journal_head *jh) +{ + struct buffer_head *bh = jh2bh(jh); + + if (!trylock_buffer(bh)) + return -EBUSY; + if (buffer_dirty(bh)) { + unlock_buffer(bh); + return -EBUSY; + } + unlock_buffer(bh); + + /* + * Buffer is clean and the IO has finished (we held the buffer + * lock) so the checkpoint is done. We can safely remove the + * buffer from this transaction. + */ + JBUFFER_TRACE(jh, "remove from checkpoint list"); + return __jbd2_journal_remove_checkpoint(jh); +} + /* * journal_insert_checkpoint: put a committed buffer onto a checkpoint * list so that we know when it is safe to clean the transaction out of @@ -755,7 +709,6 @@ void __jbd2_journal_drop_transaction(journal_t *journal, transaction_t *transact J_ASSERT(transaction->t_forget == NULL); J_ASSERT(transaction->t_shadow_list == NULL); J_ASSERT(transaction->t_checkpoint_list == NULL); - J_ASSERT(transaction->t_checkpoint_io_list == NULL); J_ASSERT(atomic_read(&transaction->t_updates) == 0); J_ASSERT(journal->j_committing_transaction != transaction); J_ASSERT(journal->j_running_transaction != transaction); diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 885a7a6cc53e..f1d9db6686e3 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -1171,8 +1171,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) spin_lock(&journal->j_list_lock); commit_transaction->t_state = T_FINISHED; /* Check if the transaction can be dropped now that we are finished */ - if (commit_transaction->t_checkpoint_list == NULL && - commit_transaction->t_checkpoint_io_list == NULL) { + if (commit_transaction->t_checkpoint_list == NULL) { __jbd2_journal_drop_transaction(journal, commit_transaction); jbd2_journal_free_transaction(commit_transaction); } diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 18611241f451..6ef5022949c4 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -1784,8 +1784,7 @@ int jbd2_journal_forget(handle_t *handle, struct buffer_head *bh) * Otherwise, if the buffer has been written to disk, * it is safe to remove the checkpoint and drop it. */ - if (!buffer_dirty(bh)) { - __jbd2_journal_remove_checkpoint(jh); + if (jbd2_journal_try_remove_checkpoint(jh) >= 0) { spin_unlock(&journal->j_list_lock); goto drop; } @@ -2112,20 +2111,14 @@ __journal_try_to_free_buffer(journal_t *journal, struct buffer_head *bh)

jh = bh2jh(bh);

- if (buffer_locked(bh) || buffer_dirty(bh)) - goto out; - if (jh->b_next_transaction != NULL || jh->b_transaction != NULL) - goto out; + return;

spin_lock(&journal->j_list_lock); - if (jh->b_cp_transaction != NULL) { - /* written-back checkpointed metadata buffer */ - JBUFFER_TRACE(jh, "remove from checkpoint list"); - __jbd2_journal_remove_checkpoint(jh); - } + /* Remove written-back checkpointed metadata buffer */ + if (jh->b_cp_transaction != NULL) + jbd2_journal_try_remove_checkpoint(jh); spin_unlock(&journal->j_list_lock); -out: return; }

diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 1707f46b1335..cf34d0c30945 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -474,20 +474,26 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter, return result; }

-static void -nfs_direct_join_group(struct list_head *list, struct inode *inode) +static void nfs_direct_join_group(struct list_head *list, struct inode *inode) { - struct nfs_page *req, *next; + struct nfs_page *req, *subreq;

list_for_each_entry(req, list, wb_list) { - if (req->wb_head != req || req->wb_this_page == req) + if (req->wb_head != req) continue; - for (next = req->wb_this_page; - next != req->wb_head; - next = next->wb_this_page) { - nfs_list_remove_request(next); - nfs_release_request(next); - } + subreq = req->wb_this_page; + if (subreq == req) + continue; + do { + /* + * Remove subrequests from this list before freeing + * them in the call to nfs_join_page_group(). + */ + if (!list_empty(&subreq->wb_list)) { + nfs_list_remove_request(subreq); + nfs_release_request(subreq); + } + } while ((subreq = subreq->wb_this_page) != req); nfs_join_page_group(req, inode); } } diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 6b2cfa59a1a2..e0c1fb98f907 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -717,9 +717,7 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, if ((attr->ia_valid & ATTR_KILL_SUID) != 0 && inode->i_mode & S_ISUID) inode->i_mode &= ~S_ISUID; - if ((attr->ia_valid & ATTR_KILL_SGID) != 0 && - (inode->i_mode & (S_ISGID | S_IXGRP)) == - (S_ISGID | S_IXGRP)) + if (setattr_should_drop_sgid(&init_user_ns, inode)) inode->i_mode &= ~S_ISGID; if ((attr->ia_valid & ATTR_MODE) != 0) { int mode = attr->ia_mode & S_IALLUGO; diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index ecb428512fe1..7c33bba179d2 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -1359,7 +1359,6 @@ ssize_t nfs42_proc_getxattr(struct inode *inode, const char *name, for (i = 0; i < np; i++) { pages[i] = alloc_page(GFP_KERNEL); if (!pages[i]) { - np = i + 1; err = -ENOMEM; goto out; } @@ -1383,8 +1382,8 @@ ssize_t nfs42_proc_getxattr(struct inode *inode, const char *name, } while (exception.retry);

out: - while (--np >= 0) - __free_page(pages[np]); + while (--i >= 0) + __free_page(pages[i]); kfree(pages);

return err; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 177cb7b089b9..1044305e7799 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5995,9 +5995,8 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, out_ok: ret = res.acl_len; out_free: - for (i = 0; i < npages; i++) - if (pages[i]) - __free_page(pages[i]); + while (--i >= 0) + __free_page(pages[i]); if (res.acl_scratch) __free_page(res.acl_scratch); kfree(pages); @@ -7171,8 +7170,15 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata) } else if (!nfs4_update_lock_stateid(lsp, &data->res.stateid)) goto out_restart; break; - case -NFS4ERR_BAD_STATEID: case -NFS4ERR_OLD_STATEID: + if (data->arg.new_lock_owner != 0 && + nfs4_refresh_open_old_stateid(&data->arg.open_stateid, + lsp->ls_state)) + goto out_restart; + if (nfs4_refresh_lock_old_stateid(&data->arg.lock_stateid, lsp)) + goto out_restart; + fallthrough; + case -NFS4ERR_BAD_STATEID: case -NFS4ERR_STALE_STATEID: case -NFS4ERR_EXPIRED: if (data->arg.new_lock_owner != 0) { diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index c5dc0cd6f703..96714e105d7b 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1368,9 +1368,9 @@ static void revoke_delegation(struct nfs4_delegation *dp) WARN_ON(!list_empty(&dp->dl_recall_lru));

if (clp->cl_minorversion) { + spin_lock(&clp->cl_lock); dp->dl_stid.sc_type = NFS4_REVOKED_DELEG_STID; refcount_inc(&dp->dl_stid.sc_count); - spin_lock(&clp->cl_lock); list_add(&dp->dl_recall_lru, &clp->cl_revoked); spin_unlock(&clp->cl_lock); } diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 155b34c4683c..4c11046800ab 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -321,7 +321,9 @@ nfsd_sanitize_attrs(struct inode *inode, struct iattr *iap) iap->ia_mode &= ~S_ISGID; } else { /* set ATTR_KILL_* bits and let VFS handle it */ - iap->ia_valid |= (ATTR_KILL_SUID | ATTR_KILL_SGID); + iap->ia_valid |= ATTR_KILL_SUID; + iap->ia_valid |= + setattr_should_drop_sgid(&init_user_ns, inode); } } } diff --git a/include/drm/display/drm_dp.h b/include/drm/display/drm_dp.h index 05f2cc03d03d..b235d6833e27 100644 --- a/include/drm/display/drm_dp.h +++ b/include/drm/display/drm_dp.h @@ -1525,7 +1525,7 @@ enum drm_dp_phy {

#define DP_BRANCH_OUI_HEADER_SIZE 0xc #define DP_RECEIVER_CAP_SIZE 0xf -#define DP_DSC_RECEIVER_CAP_SIZE 0xf +#define DP_DSC_RECEIVER_CAP_SIZE 0x10 /* DSC Capabilities 0x60 through 0x6F */ #define EDP_PSR_RECEIVER_CAP_SIZE 2 #define EDP_DISPLAY_CTL_CAP_SIZE 3 #define DP_LTTPR_COMMON_CAP_SIZE 8 diff --git a/include/drm/drm_aperture.h b/include/drm/drm_aperture.h index 7096703c3949..cbe33b49fd5d 100644 --- a/include/drm/drm_aperture.h +++ b/include/drm/drm_aperture.h @@ -13,14 +13,13 @@ int devm_aperture_acquire_from_firmware(struct drm_device *dev, resource_size_t resource_size_t size);

int drm_aperture_remove_conflicting_framebuffers(resource_size_t base, resource_size_t size, - bool primary, const struct drm_driver *req_driver); + const struct drm_driver *req_driver);

int drm_aperture_remove_conflicting_pci_framebuffers(struct pci_dev *pdev, const struct drm_driver *req_driver);

/** * drm_aperture_remove_framebuffers - remove all existing framebuffers - * @primary: also kick vga16fb if present * @req_driver: requesting DRM driver * * This function removes all graphics device drivers. Use this function on systems @@ -30,9 +29,9 @@ int drm_aperture_remove_conflicting_pci_framebuffers(struct pci_dev *pdev, * 0 on success, or a negative errno code otherwise */ static inline int -drm_aperture_remove_framebuffers(bool primary, const struct drm_driver *req_driver) +drm_aperture_remove_framebuffers(const struct drm_driver *req_driver) { - return drm_aperture_remove_conflicting_framebuffers(0, (resource_size_t)-1, primary, + return drm_aperture_remove_conflicting_framebuffers(0, (resource_size_t)-1, req_driver); }

diff --git a/include/linux/clk.h b/include/linux/clk.h index 1ef013324237..06f1b292f8a0 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -183,6 +183,39 @@ int clk_get_scaled_duty_cycle(struct clk *clk, unsigned int scale); */ bool clk_is_match(const struct clk *p, const struct clk *q);

+/** + * clk_rate_exclusive_get - get exclusivity over the rate control of a + * producer + * @clk: clock source + * + * This function allows drivers to get exclusive control over the rate of a + * provider. It prevents any other consumer to execute, even indirectly, + * opereation which could alter the rate of the provider or cause glitches + * + * If exlusivity is claimed more than once on clock, even by the same driver, + * the rate effectively gets locked as exclusivity can't be preempted. + * + * Must not be called from within atomic context. + * + * Returns success (0) or negative errno. + */ +int clk_rate_exclusive_get(struct clk *clk); + +/** + * clk_rate_exclusive_put - release exclusivity over the rate control of a + * producer + * @clk: clock source + * + * This function allows drivers to release the exclusivity it previously got + * from clk_rate_exclusive_get() + * + * The caller must balance the number of clk_rate_exclusive_get() and + * clk_rate_exclusive_put() calls. + * + * Must not be called from within atomic context. + */ +void clk_rate_exclusive_put(struct clk *clk); + #else

static inline int clk_notifier_register(struct clk *clk, @@ -236,6 +269,13 @@ static inline bool clk_is_match(const struct clk *p, const struct clk *q) return p == q; }

+static inline int clk_rate_exclusive_get(struct clk *clk) +{ + return 0; +} + +static inline void clk_rate_exclusive_put(struct clk *clk) {} + #endif

#ifdef CONFIG_HAVE_CLK_PREPARE @@ -583,38 +623,6 @@ struct clk *devm_clk_get_optional_enabled(struct device *dev, const char *id); */ struct clk *devm_get_clk_from_child(struct device *dev, struct device_node *np, const char *con_id); -/** - * clk_rate_exclusive_get - get exclusivity over the rate control of a - * producer - * @clk: clock source - * - * This function allows drivers to get exclusive control over the rate of a - * provider. It prevents any other consumer to execute, even indirectly, - * opereation which could alter the rate of the provider or cause glitches - * - * If exlusivity is claimed more than once on clock, even by the same driver, - * the rate effectively gets locked as exclusivity can't be preempted. - * - * Must not be called from within atomic context. - * - * Returns success (0) or negative errno. - */ -int clk_rate_exclusive_get(struct clk *clk); - -/** - * clk_rate_exclusive_put - release exclusivity over the rate control of a - * producer - * @clk: clock source - * - * This function allows drivers to release the exclusivity it previously got - * from clk_rate_exclusive_get() - * - * The caller must balance the number of clk_rate_exclusive_get() and - * clk_rate_exclusive_put() calls. - * - * Must not be called from within atomic context. - */ -void clk_rate_exclusive_put(struct clk *clk);

/** * clk_enable - inform the system when the clock source should be running. @@ -974,14 +982,6 @@ static inline void clk_bulk_put_all(int num_clks, struct clk_bulk_data *clks) {}

static inline void devm_clk_put(struct device *dev, struct clk *clk) {}

- -static inline int clk_rate_exclusive_get(struct clk *clk) -{ - return 0; -} - -static inline void clk_rate_exclusive_put(struct clk *clk) {} - static inline int clk_enable(struct clk *clk) { return 0; diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index d58e0476ee8e..0348dba5680e 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -71,8 +71,10 @@ extern void cpuset_init_smp(void); extern void cpuset_force_rebuild(void); extern void cpuset_update_active_cpus(void); extern void cpuset_wait_for_hotplug(void); -extern void cpuset_read_lock(void); -extern void cpuset_read_unlock(void); +extern void inc_dl_tasks_cs(struct task_struct *task); +extern void dec_dl_tasks_cs(struct task_struct *task); +extern void cpuset_lock(void); +extern void cpuset_unlock(void); extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask); extern bool cpuset_cpus_allowed_fallback(struct task_struct *p); extern nodemask_t cpuset_mems_allowed(struct task_struct *p); @@ -196,8 +198,10 @@ static inline void cpuset_update_active_cpus(void)

static inline void cpuset_wait_for_hotplug(void) { }

-static inline void cpuset_read_lock(void) { } -static inline void cpuset_read_unlock(void) { } +static inline void inc_dl_tasks_cs(struct task_struct *task) { } +static inline void dec_dl_tasks_cs(struct task_struct *task) { } +static inline void cpuset_lock(void) { } +static inline void cpuset_unlock(void) { }

static inline void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask) diff --git a/include/linux/fs.h b/include/linux/fs.h index a2b5592c6828..26ea1a0a59a1 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3120,6 +3120,8 @@ extern struct inode *new_inode(struct super_block *sb); extern void free_inode_nonrcu(struct inode *inode); extern int setattr_should_drop_suidgid(struct user_namespace *, struct inode *); extern int file_remove_privs(struct file *); +int setattr_should_drop_sgid(struct user_namespace *mnt_userns, + const struct inode *inode);

/* * This must be used for allocating filesystems specific inodes to set diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 0b7242370b56..ebb1608d9dcd 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -622,12 +622,6 @@ struct transaction_s */ struct journal_head *t_checkpoint_list;

- /* - * Doubly-linked circular list of all buffers submitted for IO while - * checkpointing. [j_list_lock] - */ - struct journal_head *t_checkpoint_io_list; - /* * Doubly-linked circular list of metadata buffers being * shadowed by log IO. The IO buffers on the iobuf list and @@ -1441,6 +1435,7 @@ extern void jbd2_journal_commit_transaction(journal_t *); void __jbd2_journal_clean_checkpoint_list(journal_t *journal, bool destroy); unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal, unsigned long *nr_to_scan); int __jbd2_journal_remove_checkpoint(struct journal_head *); +int jbd2_journal_try_remove_checkpoint(struct journal_head *jh); void jbd2_journal_destroy_checkpoint(journal_t *journal); void __jbd2_journal_insert_checkpoint(struct journal_head *, transaction_t *);

diff --git a/include/linux/mm.h b/include/linux/mm.h index b8ed44f401b5..104ec00823da 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1727,6 +1727,25 @@ static inline size_t folio_size(struct folio *folio) return PAGE_SIZE << folio_order(folio); }

+/** + * folio_estimated_sharers - Estimate the number of sharers of a folio. + * @folio: The folio. + * + * folio_estimated_sharers() aims to serve as a function to efficiently + * estimate the number of processes sharing a folio. This is done by + * looking at the precise mapcount of the first subpage in the folio, and + * assuming the other subpages are the same. This may not be true for large + * folios. If you want exact mapcounts for exact calculations, look at + * page_mapcount() or folio_total_mapcount(). + * + * Return: The estimated number of processes sharing a folio. + */ +static inline int folio_estimated_sharers(struct folio *folio) +{ + return page_mapcount(folio_page(folio, 0)); +} + + #ifndef HAVE_ARCH_MAKE_PAGE_ACCESSIBLE static inline int arch_make_page_accessible(struct page *page) { @@ -3091,6 +3110,16 @@ static inline bool gup_must_unshare(unsigned int flags, struct page *page) if (IS_ENABLED(CONFIG_HAVE_FAST_GUP)) smp_rmb();

+ /* + * During GUP-fast we might not get called on the head page for a + * hugetlb page that is mapped using cont-PTE, because GUP-fast does + * not work with the abstracted hugetlb PTEs that always point at the + * head page. For hugetlb, PageAnonExclusive only applies on the head + * page (as it cannot be partially COW-shared), so lookup the head page. + */ + if (unlikely(!PageHead(page) && PageHuge(page))) + page = compound_head(page); + /* * Note that PageKsm() pages cannot be exclusive, and consequently, * cannot get pinned. diff --git a/include/linux/raid_class.h b/include/linux/raid_class.h index 5cdfcb873a8f..772d45b2a60a 100644 --- a/include/linux/raid_class.h +++ b/include/linux/raid_class.h @@ -77,7 +77,3 @@ DEFINE_RAID_ATTRIBUTE(enum raid_state, state) struct raid_template *raid_class_attach(struct raid_function_template *); void raid_class_release(struct raid_template *); - -int __must_check raid_component_add(struct raid_template *, struct device *, - struct device *); - diff --git a/include/linux/sched.h b/include/linux/sched.h index ffb6eb55cd13..0cac69902ec5 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1846,7 +1846,9 @@ current_restore_flags(unsigned long orig_flags, unsigned long flags) }

extern int cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial); -extern int task_can_attach(struct task_struct *p, const struct cpumask *cs_effective_cpus); +extern int task_can_attach(struct task_struct *p); +extern int dl_bw_alloc(int cpu, u64 dl_bw); +extern void dl_bw_free(int cpu, u64 dl_bw); #ifdef CONFIG_SMP extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask); extern int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask); diff --git a/include/net/bonding.h b/include/net/bonding.h index 17329a19f0c6..9a3ac960dfe1 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -727,23 +727,14 @@ static inline struct slave *bond_slave_has_mac(struct bonding *bond, }

/* Caller must hold rcu_read_lock() for read */ -static inline bool bond_slave_has_mac_rx(struct bonding *bond, const u8 *mac) +static inline bool bond_slave_has_mac_rcu(struct bonding *bond, const u8 *mac) { struct list_head *iter; struct slave *tmp; - struct netdev_hw_addr *ha;

bond_for_each_slave_rcu(bond, tmp, iter) if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr)) return true; - - if (netdev_uc_empty(bond->dev)) - return false; - - netdev_for_each_uc_addr(ha, bond->dev) - if (ether_addr_equal_64bits(mac, ha->addr)) - return true; - return false; }

diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index c8ef3b881f03..c2432c2addc8 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -222,8 +222,8 @@ struct inet_sock { __s16 uc_ttl; __u16 cmsg_flags; struct ip_options_rcu __rcu *inet_opt; + atomic_t inet_id; __be16 inet_sport; - __u16 inet_id;

__u8 tos; __u8 min_ttl; diff --git a/include/net/ip.h b/include/net/ip.h index 530e7257e438..1872f570abed 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -532,8 +532,19 @@ static inline void ip_select_ident_segs(struct net *net, struct sk_buff *skb, * generator as much as we can. */ if (sk && inet_sk(sk)->inet_daddr) { - iph->id = htons(inet_sk(sk)->inet_id); - inet_sk(sk)->inet_id += segs; + int val; + + /* avoid atomic operations for TCP, + * as we hold socket lock at this point. + */ + if (sk_is_tcp(sk)) { + sock_owned_by_me(sk); + val = atomic_read(&inet_sk(sk)->inet_id); + atomic_set(&inet_sk(sk)->inet_id, val + segs); + } else { + val = atomic_add_return(segs, &inet_sk(sk)->inet_id); + } + iph->id = htons(val); return; } if ((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) { diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 72b739dc6d53..8a338c33118f 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -6444,6 +6444,7 @@ void ieee80211_stop_rx_ba_session(struct ieee80211_vif *vif, u16 ba_rx_bitmap, * marks frames marked in the bitmap as having been filtered. Afterwards, it * checks if any frames in the window starting from @ssn can now be released * (in case they were only waiting for frames that were filtered.) + * (Only work correctly if @max_rx_aggregation_subframes <= 64 frames) */ void ieee80211_mark_rx_ba_filtered_frames(struct ieee80211_sta *pubsta, u8 tid, u16 ssn, u64 filtered, diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index bf8bb3357825..9f881b74f32e 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -189,8 +189,8 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname, int rtnl_delete_link(struct net_device *dev); int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm);

-int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len, - struct netlink_ext_ack *exterr); +int rtnl_nla_parse_ifinfomsg(struct nlattr **tb, const struct nlattr *nla_peer, + struct netlink_ext_ack *exterr); struct net *rtnl_get_net_ns_capable(struct sock *sk, int netnsid);

#define MODULE_ALIAS_RTNL_LINK(kind) MODULE_ALIAS("rtnl-link-" kind) diff --git a/include/net/sock.h b/include/net/sock.h index 699408944952..d1f936ed9755 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1320,6 +1320,7 @@ struct proto { /* * Pressure flag: try to collapse. * Technical note: it is used by multiple contexts non atomically. + * Make sure to use READ_ONCE()/WRITE_ONCE() for all reads/writes. * All the __sk_mem_schedule() is of this nature: accounting * is strict, actions are advisory and have some latency. */ @@ -1448,7 +1449,7 @@ static inline bool sk_has_memory_pressure(const struct sock *sk) static inline bool sk_under_global_memory_pressure(const struct sock *sk) { return sk->sk_prot->memory_pressure && - !!*sk->sk_prot->memory_pressure; + !!READ_ONCE(*sk->sk_prot->memory_pressure); }

static inline bool sk_under_memory_pressure(const struct sock *sk) @@ -1460,7 +1461,7 @@ static inline bool sk_under_memory_pressure(const struct sock *sk) mem_cgroup_under_socket_pressure(sk->sk_memcg)) return true;

- return !!*sk->sk_prot->memory_pressure; + return !!READ_ONCE(*sk->sk_prot->memory_pressure); }

static inline long @@ -1537,7 +1538,7 @@ proto_memory_pressure(struct proto *prot) { if (!prot->memory_pressure) return false; - return !!*prot->memory_pressure; + return !!READ_ONCE(*prot->memory_pressure); }

diff --git a/include/trace/events/jbd2.h b/include/trace/events/jbd2.h index 8f5ee380d309..5646ae15a957 100644 --- a/include/trace/events/jbd2.h +++ b/include/trace/events/jbd2.h @@ -462,11 +462,9 @@ TRACE_EVENT(jbd2_shrink_scan_exit, TRACE_EVENT(jbd2_shrink_checkpoint_list,

TP_PROTO(journal_t *journal, tid_t first_tid, tid_t tid, tid_t last_tid, - unsigned long nr_freed, unsigned long nr_scanned, - tid_t next_tid), + unsigned long nr_freed, tid_t next_tid),

- TP_ARGS(journal, first_tid, tid, last_tid, nr_freed, - nr_scanned, next_tid), + TP_ARGS(journal, first_tid, tid, last_tid, nr_freed, next_tid),

TP_STRUCT__entry( __field(dev_t, dev) @@ -474,7 +472,6 @@ TRACE_EVENT(jbd2_shrink_checkpoint_list, __field(tid_t, tid) __field(tid_t, last_tid) __field(unsigned long, nr_freed) - __field(unsigned long, nr_scanned) __field(tid_t, next_tid) ),

@@ -484,15 +481,14 @@ TRACE_EVENT(jbd2_shrink_checkpoint_list, __entry->tid = tid; __entry->last_tid = last_tid; __entry->nr_freed = nr_freed; - __entry->nr_scanned = nr_scanned; __entry->next_tid = next_tid; ),

TP_printk("dev %d,%d shrink transaction %u-%u(%u) freed %lu " - "scanned %lu next transaction %u", + "next transaction %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->first_tid, __entry->tid, __entry->last_tid, - __entry->nr_freed, __entry->nr_scanned, __entry->next_tid) + __entry->nr_freed, __entry->next_tid) );

#endif /* _TRACE_JBD2_H */ diff --git a/io_uring/msg_ring.c b/io_uring/msg_ring.c index 3526389ac218..cd922d2bef5f 100644 --- a/io_uring/msg_ring.c +++ b/io_uring/msg_ring.c @@ -15,6 +15,7 @@

struct io_msg { struct file *file; + struct file *src_file; u64 user_data; u32 len; u32 cmd; @@ -23,33 +24,12 @@ struct io_msg { u32 flags; };

-static int io_msg_ring_data(struct io_kiocb *req) +static void io_double_unlock_ctx(struct io_ring_ctx *octx) { - struct io_ring_ctx *target_ctx = req->file->private_data; - struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg); - - if (msg->src_fd || msg->dst_fd || msg->flags) - return -EINVAL; - if (target_ctx->flags & IORING_SETUP_R_DISABLED) - return -EBADFD; - - if (io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0, true)) - return 0; - - return -EOVERFLOW; -} - -static void io_double_unlock_ctx(struct io_ring_ctx *ctx, - struct io_ring_ctx *octx, - unsigned int issue_flags) -{ - if (issue_flags & IO_URING_F_UNLOCKED) - mutex_unlock(&ctx->uring_lock); mutex_unlock(&octx->uring_lock); }

-static int io_double_lock_ctx(struct io_ring_ctx *ctx, - struct io_ring_ctx *octx, +static int io_double_lock_ctx(struct io_ring_ctx *octx, unsigned int issue_flags) { /* @@ -62,60 +42,86 @@ static int io_double_lock_ctx(struct io_ring_ctx *ctx, return -EAGAIN; return 0; } + mutex_lock(&octx->uring_lock); + return 0; +}

- /* Always grab smallest value ctx first. We know ctx != octx. */ - if (ctx < octx) { - mutex_lock(&ctx->uring_lock); - mutex_lock(&octx->uring_lock); - } else { - mutex_lock(&octx->uring_lock); - mutex_lock(&ctx->uring_lock); - } +void io_msg_ring_cleanup(struct io_kiocb *req) +{ + struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg);

- return 0; + if (WARN_ON_ONCE(!msg->src_file)) + return; + + fput(msg->src_file); + msg->src_file = NULL; }

-static int io_msg_send_fd(struct io_kiocb *req, unsigned int issue_flags) +static int io_msg_ring_data(struct io_kiocb *req, unsigned int issue_flags) { struct io_ring_ctx *target_ctx = req->file->private_data; struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg); - struct io_ring_ctx *ctx = req->ctx; - unsigned long file_ptr; - struct file *src_file; int ret;

- if (msg->len) - return -EINVAL; - if (target_ctx == ctx) + if (msg->src_fd || msg->dst_fd || msg->flags) return -EINVAL; if (target_ctx->flags & IORING_SETUP_R_DISABLED) return -EBADFD;

- ret = io_double_lock_ctx(ctx, target_ctx, issue_flags); - if (unlikely(ret)) - return ret; + ret = -EOVERFLOW; + if (target_ctx->flags & IORING_SETUP_IOPOLL) { + if (unlikely(io_double_lock_ctx(target_ctx, issue_flags))) + return -EAGAIN; + if (io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0, true)) + ret = 0; + io_double_unlock_ctx(target_ctx); + } else { + if (io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0, true)) + ret = 0; + }

- ret = -EBADF; - if (unlikely(msg->src_fd >= ctx->nr_user_files)) - goto out_unlock; + return ret; +}

- msg->src_fd = array_index_nospec(msg->src_fd, ctx->nr_user_files); - file_ptr = io_fixed_file_slot(&ctx->file_table, msg->src_fd)->file_ptr; - if (!file_ptr) - goto out_unlock; +static struct file *io_msg_grab_file(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg); + struct io_ring_ctx *ctx = req->ctx; + struct file *file = NULL; + unsigned long file_ptr; + int idx = msg->src_fd; + + io_ring_submit_lock(ctx, issue_flags); + if (likely(idx < ctx->nr_user_files)) { + idx = array_index_nospec(idx, ctx->nr_user_files); + file_ptr = io_fixed_file_slot(&ctx->file_table, idx)->file_ptr; + file = (struct file *) (file_ptr & FFS_MASK); + if (file) + get_file(file); + } + io_ring_submit_unlock(ctx, issue_flags); + return file; +}

- src_file = (struct file *) (file_ptr & FFS_MASK); - get_file(src_file); +static int io_msg_install_complete(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_ring_ctx *target_ctx = req->file->private_data; + struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg); + struct file *src_file = msg->src_file; + int ret; + + if (unlikely(io_double_lock_ctx(target_ctx, issue_flags))) + return -EAGAIN;

ret = __io_fixed_fd_install(target_ctx, src_file, msg->dst_fd); - if (ret < 0) { - fput(src_file); + if (ret < 0) goto out_unlock; - } + + msg->src_file = NULL; + req->flags &= ~REQ_F_NEED_CLEANUP;

if (msg->flags & IORING_MSG_RING_CQE_SKIP) goto out_unlock; - /* * If this fails, the target still received the file descriptor but * wasn't notified of the fact. This means that if this request @@ -125,10 +131,29 @@ static int io_msg_send_fd(struct io_kiocb *req, unsigned int issue_flags) if (!io_post_aux_cqe(target_ctx, msg->user_data, ret, 0, true)) ret = -EOVERFLOW; out_unlock: - io_double_unlock_ctx(ctx, target_ctx, issue_flags); + io_double_unlock_ctx(target_ctx); return ret; }

+static int io_msg_send_fd(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_ring_ctx *target_ctx = req->file->private_data; + struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg); + struct io_ring_ctx *ctx = req->ctx; + struct file *src_file = msg->src_file; + + if (target_ctx == ctx) + return -EINVAL; + if (!src_file) { + src_file = io_msg_grab_file(req, issue_flags); + if (!src_file) + return -EBADF; + msg->src_file = src_file; + req->flags |= REQ_F_NEED_CLEANUP; + } + return io_msg_install_complete(req, issue_flags); +} + int io_msg_ring_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg); @@ -136,6 +161,7 @@ int io_msg_ring_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (unlikely(sqe->buf_index || sqe->personality)) return -EINVAL;

+ msg->src_file = NULL; msg->user_data = READ_ONCE(sqe->off); msg->len = READ_ONCE(sqe->len); msg->cmd = READ_ONCE(sqe->addr); @@ -159,7 +185,7 @@ int io_msg_ring(struct io_kiocb *req, unsigned int issue_flags)

switch (msg->cmd) { case IORING_MSG_DATA: - ret = io_msg_ring_data(req); + ret = io_msg_ring_data(req, issue_flags); break; case IORING_MSG_SEND_FD: ret = io_msg_send_fd(req, issue_flags); diff --git a/io_uring/msg_ring.h b/io_uring/msg_ring.h index fb9601f202d0..3987ee6c0e5f 100644 --- a/io_uring/msg_ring.h +++ b/io_uring/msg_ring.h @@ -2,3 +2,4 @@

int io_msg_ring_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); int io_msg_ring(struct io_kiocb *req, unsigned int issue_flags); +void io_msg_ring_cleanup(struct io_kiocb *req); diff --git a/io_uring/opdef.c b/io_uring/opdef.c index 04dd2c983fce..3aa0d65c50e3 100644 --- a/io_uring/opdef.c +++ b/io_uring/opdef.c @@ -445,6 +445,7 @@ const struct io_op_def io_op_defs[] = { .name = "MSG_RING", .prep = io_msg_ring_prep, .issue = io_msg_ring, + .cleanup = io_msg_ring_cleanup, }, [IORING_OP_FSETXATTR] = { .needs_file = 1, diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 73f11e4db3a4..97ecca43386d 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -57,6 +57,7 @@ #include <linux/file.h> #include <linux/fs_parser.h> #include <linux/sched/cputime.h> +#include <linux/sched/deadline.h> #include <linux/psi.h> #include <net/sock.h>

@@ -6681,6 +6682,9 @@ void cgroup_exit(struct task_struct *tsk) list_add_tail(&tsk->cg_list, &cset->dying_tasks); cset->nr_tasks--;

+ if (dl_task(tsk)) + dec_dl_tasks_cs(tsk); + WARN_ON_ONCE(cgroup_task_frozen(tsk)); if (unlikely(!(tsk->flags & PF_KTHREAD) && test_bit(CGRP_FREEZE, &task_dfl_cgroup(tsk)->flags))) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index e276db722845..db3e05b6b4dd 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -193,6 +193,14 @@ struct cpuset { int use_parent_ecpus; int child_ecpus_count;

+ /* + * number of SCHED_DEADLINE tasks attached to this cpuset, so that we + * know when to rebuild associated root domain bandwidth information. + */ + int nr_deadline_tasks; + int nr_migrate_dl_tasks; + u64 sum_migrate_dl_bw; + /* Invalid partition error code, not lock protected */ enum prs_errcode prs_err;

@@ -245,6 +253,20 @@ static inline struct cpuset *parent_cs(struct cpuset *cs) return css_cs(cs->css.parent); }

+void inc_dl_tasks_cs(struct task_struct *p) +{ + struct cpuset *cs = task_cs(p); + + cs->nr_deadline_tasks++; +} + +void dec_dl_tasks_cs(struct task_struct *p) +{ + struct cpuset *cs = task_cs(p); + + cs->nr_deadline_tasks--; +} + /* bits in struct cpuset flags field */ typedef enum { CS_ONLINE, @@ -366,22 +388,23 @@ static struct cpuset top_cpuset = { if (is_cpuset_online(((des_cs) = css_cs((pos_css)))))

/* - * There are two global locks guarding cpuset structures - cpuset_rwsem and + * There are two global locks guarding cpuset structures - cpuset_mutex and * callback_lock. We also require taking task_lock() when dereferencing a * task's cpuset pointer. See "The task_lock() exception", at the end of this - * comment. The cpuset code uses only cpuset_rwsem write lock. Other - * kernel subsystems can use cpuset_read_lock()/cpuset_read_unlock() to - * prevent change to cpuset structures. + * comment. The cpuset code uses only cpuset_mutex. Other kernel subsystems + * can use cpuset_lock()/cpuset_unlock() to prevent change to cpuset + * structures. Note that cpuset_mutex needs to be a mutex as it is used in + * paths that rely on priority inheritance (e.g. scheduler - on RT) for + * correctness. * * A task must hold both locks to modify cpusets. If a task holds - * cpuset_rwsem, it blocks others wanting that rwsem, ensuring that it - * is the only task able to also acquire callback_lock and be able to - * modify cpusets. It can perform various checks on the cpuset structure - * first, knowing nothing will change. It can also allocate memory while - * just holding cpuset_rwsem. While it is performing these checks, various - * callback routines can briefly acquire callback_lock to query cpusets. - * Once it is ready to make the changes, it takes callback_lock, blocking - * everyone else. + * cpuset_mutex, it blocks others, ensuring that it is the only task able to + * also acquire callback_lock and be able to modify cpusets. It can perform + * various checks on the cpuset structure first, knowing nothing will change. + * It can also allocate memory while just holding cpuset_mutex. While it is + * performing these checks, various callback routines can briefly acquire + * callback_lock to query cpusets. Once it is ready to make the changes, it + * takes callback_lock, blocking everyone else. * * Calls to the kernel memory allocator can not be made while holding * callback_lock, as that would risk double tripping on callback_lock @@ -403,16 +426,16 @@ static struct cpuset top_cpuset = { * guidelines for accessing subsystem state in kernel/cgroup.c */

-DEFINE_STATIC_PERCPU_RWSEM(cpuset_rwsem); +static DEFINE_MUTEX(cpuset_mutex);

-void cpuset_read_lock(void) +void cpuset_lock(void) { - percpu_down_read(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); }

-void cpuset_read_unlock(void) +void cpuset_unlock(void) { - percpu_up_read(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); }

static DEFINE_SPINLOCK(callback_lock); @@ -496,7 +519,7 @@ static inline bool partition_is_populated(struct cpuset *cs, * One way or another, we guarantee to return some non-empty subset * of cpu_online_mask. * - * Call with callback_lock or cpuset_rwsem held. + * Call with callback_lock or cpuset_mutex held. */ static void guarantee_online_cpus(struct task_struct *tsk, struct cpumask *pmask) @@ -538,7 +561,7 @@ static void guarantee_online_cpus(struct task_struct *tsk, * One way or another, we guarantee to return some non-empty subset * of node_states[N_MEMORY]. * - * Call with callback_lock or cpuset_rwsem held. + * Call with callback_lock or cpuset_mutex held. */ static void guarantee_online_mems(struct cpuset *cs, nodemask_t *pmask) { @@ -550,7 +573,7 @@ static void guarantee_online_mems(struct cpuset *cs, nodemask_t *pmask) /* * update task's spread flag if cpuset's page/slab spread flag is set * - * Call with callback_lock or cpuset_rwsem held. The check can be skipped + * Call with callback_lock or cpuset_mutex held. The check can be skipped * if on default hierarchy. */ static void cpuset_update_task_spread_flags(struct cpuset *cs, @@ -575,7 +598,7 @@ static void cpuset_update_task_spread_flags(struct cpuset *cs, * * One cpuset is a subset of another if all its allowed CPUs and * Memory Nodes are a subset of the other, and its exclusive flags - * are only set if the other's are set. Call holding cpuset_rwsem. + * are only set if the other's are set. Call holding cpuset_mutex. */

static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q) @@ -713,7 +736,7 @@ static int validate_change_legacy(struct cpuset *cur, struct cpuset *trial) * If we replaced the flag and mask values of the current cpuset * (cur) with those values in the trial cpuset (trial), would * our various subset and exclusive rules still be valid? Presumes - * cpuset_rwsem held. + * cpuset_mutex held. * * 'cur' is the address of an actual, in-use cpuset. Operations * such as list traversal that depend on the actual address of the @@ -829,7 +852,7 @@ static void update_domain_attr_tree(struct sched_domain_attr *dattr, rcu_read_unlock(); }

-/* Must be called with cpuset_rwsem held. */ +/* Must be called with cpuset_mutex held. */ static inline int nr_cpusets(void) { /* jump label reference count + the top-level cpuset */ @@ -855,7 +878,7 @@ static inline int nr_cpusets(void) * domains when operating in the severe memory shortage situations * that could cause allocation failures below. * - * Must be called with cpuset_rwsem held. + * Must be called with cpuset_mutex held. * * The three key local variables below are: * cp - cpuset pointer, used (together with pos_css) to perform a @@ -1066,11 +1089,14 @@ static int generate_sched_domains(cpumask_var_t **domains, return ndoms; }

-static void update_tasks_root_domain(struct cpuset *cs) +static void dl_update_tasks_root_domain(struct cpuset *cs) { struct css_task_iter it; struct task_struct *task;

+ if (cs->nr_deadline_tasks == 0) + return; + css_task_iter_start(&cs->css, 0, &it);

while ((task = css_task_iter_next(&it))) @@ -1079,12 +1105,12 @@ static void update_tasks_root_domain(struct cpuset *cs) css_task_iter_end(&it); }

-static void rebuild_root_domains(void) +static void dl_rebuild_rd_accounting(void) { struct cpuset *cs = NULL; struct cgroup_subsys_state *pos_css;

- percpu_rwsem_assert_held(&cpuset_rwsem); + lockdep_assert_held(&cpuset_mutex); lockdep_assert_cpus_held(); lockdep_assert_held(&sched_domains_mutex);

@@ -1107,7 +1133,7 @@ static void rebuild_root_domains(void)

rcu_read_unlock();

- update_tasks_root_domain(cs); + dl_update_tasks_root_domain(cs);

rcu_read_lock(); css_put(&cs->css); @@ -1121,7 +1147,7 @@ partition_and_rebuild_sched_domains(int ndoms_new, cpumask_var_t doms_new[], { mutex_lock(&sched_domains_mutex); partition_sched_domains_locked(ndoms_new, doms_new, dattr_new); - rebuild_root_domains(); + dl_rebuild_rd_accounting(); mutex_unlock(&sched_domains_mutex); }

@@ -1134,7 +1160,7 @@ partition_and_rebuild_sched_domains(int ndoms_new, cpumask_var_t doms_new[], * 'cpus' is removed, then call this routine to rebuild the * scheduler's dynamic sched domains. * - * Call with cpuset_rwsem held. Takes cpus_read_lock(). + * Call with cpuset_mutex held. Takes cpus_read_lock(). */ static void rebuild_sched_domains_locked(void) { @@ -1145,7 +1171,7 @@ static void rebuild_sched_domains_locked(void) int ndoms;

lockdep_assert_cpus_held(); - percpu_rwsem_assert_held(&cpuset_rwsem); + lockdep_assert_held(&cpuset_mutex);

/* * If we have raced with CPU hotplug, return early to avoid @@ -1196,9 +1222,9 @@ static void rebuild_sched_domains_locked(void) void rebuild_sched_domains(void) { cpus_read_lock(); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); rebuild_sched_domains_locked(); - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); cpus_read_unlock(); }

@@ -1208,7 +1234,7 @@ void rebuild_sched_domains(void) * @new_cpus: the temp variable for the new effective_cpus mask * * Iterate through each task of @cs updating its cpus_allowed to the - * effective cpuset's. As this function is called with cpuset_rwsem held, + * effective cpuset's. As this function is called with cpuset_mutex held, * cpuset membership stays stable. */ static void update_tasks_cpumask(struct cpuset *cs, struct cpumask *new_cpus) @@ -1317,7 +1343,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd, int old_prs, new_prs; int part_error = PERR_NONE; /* Partition error? */

- percpu_rwsem_assert_held(&cpuset_rwsem); + lockdep_assert_held(&cpuset_mutex);

/* * The parent must be a partition root. @@ -1540,7 +1566,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd, * * On legacy hierarchy, effective_cpus will be the same with cpu_allowed. * - * Called with cpuset_rwsem held + * Called with cpuset_mutex held */ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp, bool force) @@ -1700,7 +1726,7 @@ static void update_sibling_cpumasks(struct cpuset *parent, struct cpuset *cs, struct cpuset *sibling; struct cgroup_subsys_state *pos_css;

- percpu_rwsem_assert_held(&cpuset_rwsem); + lockdep_assert_held(&cpuset_mutex);

/* * Check all its siblings and call update_cpumasks_hier() @@ -1950,12 +1976,12 @@ static void *cpuset_being_rebound; * @cs: the cpuset in which each task's mems_allowed mask needs to be changed * * Iterate through each task of @cs updating its mems_allowed to the - * effective cpuset's. As this function is called with cpuset_rwsem held, + * effective cpuset's. As this function is called with cpuset_mutex held, * cpuset membership stays stable. */ static void update_tasks_nodemask(struct cpuset *cs) { - static nodemask_t newmems; /* protected by cpuset_rwsem */ + static nodemask_t newmems; /* protected by cpuset_mutex */ struct css_task_iter it; struct task_struct *task;

@@ -1968,7 +1994,7 @@ static void update_tasks_nodemask(struct cpuset *cs) * take while holding tasklist_lock. Forks can happen - the * mpol_dup() cpuset_being_rebound check will catch such forks, * and rebind their vma mempolicies too. Because we still hold - * the global cpuset_rwsem, we know that no other rebind effort + * the global cpuset_mutex, we know that no other rebind effort * will be contending for the global variable cpuset_being_rebound. * It's ok if we rebind the same mm twice; mpol_rebind_mm() * is idempotent. Also migrate pages in each mm to new nodes. @@ -2014,7 +2040,7 @@ static void update_tasks_nodemask(struct cpuset *cs) * * On legacy hierarchy, effective_mems will be the same with mems_allowed. * - * Called with cpuset_rwsem held + * Called with cpuset_mutex held */ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems) { @@ -2067,7 +2093,7 @@ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems) * mempolicies and if the cpuset is marked 'memory_migrate', * migrate the tasks pages to the new memory. * - * Call with cpuset_rwsem held. May take callback_lock during call. + * Call with cpuset_mutex held. May take callback_lock during call. * Will take tasklist_lock, scan tasklist for tasks in cpuset cs, * lock each such tasks mm->mmap_lock, scan its vma's and rebind * their mempolicies to the cpusets new mems_allowed. @@ -2159,7 +2185,7 @@ static int update_relax_domain_level(struct cpuset *cs, s64 val) * @cs: the cpuset in which each task's spread flags needs to be changed * * Iterate through each task of @cs updating its spread flags. As this - * function is called with cpuset_rwsem held, cpuset membership stays + * function is called with cpuset_mutex held, cpuset membership stays * stable. */ static void update_tasks_flags(struct cpuset *cs) @@ -2179,7 +2205,7 @@ static void update_tasks_flags(struct cpuset *cs) * cs: the cpuset to update * turning_on: whether the flag is being set or cleared * - * Call with cpuset_rwsem held. + * Call with cpuset_mutex held. */

static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, @@ -2229,7 +2255,7 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, * @new_prs: new partition root state * Return: 0 if successful, != 0 if error * - * Call with cpuset_rwsem held. + * Call with cpuset_mutex held. */ static int update_prstate(struct cpuset *cs, int new_prs) { @@ -2467,19 +2493,26 @@ static int cpuset_can_attach_check(struct cpuset *cs) return 0; }

-/* Called by cgroups to determine if a cpuset is usable; cpuset_rwsem held */ +static void reset_migrate_dl_data(struct cpuset *cs) +{ + cs->nr_migrate_dl_tasks = 0; + cs->sum_migrate_dl_bw = 0; +} + +/* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */ static int cpuset_can_attach(struct cgroup_taskset *tset) { struct cgroup_subsys_state *css; - struct cpuset *cs; + struct cpuset *cs, *oldcs; struct task_struct *task; int ret;

/* used later by cpuset_attach() */ cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset, &css)); + oldcs = cpuset_attach_old_cs; cs = css_cs(css);

- percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex);

/* Check to see if task is allowed in the cpuset */ ret = cpuset_can_attach_check(cs); @@ -2487,21 +2520,46 @@ static int cpuset_can_attach(struct cgroup_taskset *tset) goto out_unlock;

cgroup_taskset_for_each(task, css, tset) { - ret = task_can_attach(task, cs->effective_cpus); + ret = task_can_attach(task); if (ret) goto out_unlock; ret = security_task_setscheduler(task); if (ret) goto out_unlock; + + if (dl_task(task)) { + cs->nr_migrate_dl_tasks++; + cs->sum_migrate_dl_bw += task->dl.dl_bw; + } }

+ if (!cs->nr_migrate_dl_tasks) + goto out_success; + + if (!cpumask_intersects(oldcs->effective_cpus, cs->effective_cpus)) { + int cpu = cpumask_any_and(cpu_active_mask, cs->effective_cpus); + + if (unlikely(cpu >= nr_cpu_ids)) { + reset_migrate_dl_data(cs); + ret = -EINVAL; + goto out_unlock; + } + + ret = dl_bw_alloc(cpu, cs->sum_migrate_dl_bw); + if (ret) { + reset_migrate_dl_data(cs); + goto out_unlock; + } + } + +out_success: /* * Mark attach is in progress. This makes validate_change() fail * changes which zero cpus/mems_allowed. */ cs->attach_in_progress++; out_unlock: - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); return ret; }

@@ -2513,15 +2571,23 @@ static void cpuset_cancel_attach(struct cgroup_taskset *tset) cgroup_taskset_first(tset, &css); cs = css_cs(css);

- percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); cs->attach_in_progress--; if (!cs->attach_in_progress) wake_up(&cpuset_attach_wq); - percpu_up_write(&cpuset_rwsem); + + if (cs->nr_migrate_dl_tasks) { + int cpu = cpumask_any(cs->effective_cpus); + + dl_bw_free(cpu, cs->sum_migrate_dl_bw); + reset_migrate_dl_data(cs); + } + + mutex_unlock(&cpuset_mutex); }

/* - * Protected by cpuset_rwsem. cpus_attach is used only by cpuset_attach_task() + * Protected by cpuset_mutex. cpus_attach is used only by cpuset_attach_task() * but we can't allocate it dynamically there. Define it global and * allocate from cpuset_init(). */ @@ -2530,7 +2596,7 @@ static nodemask_t cpuset_attach_nodemask_to;

static void cpuset_attach_task(struct cpuset *cs, struct task_struct *task) { - percpu_rwsem_assert_held(&cpuset_rwsem); + lockdep_assert_held(&cpuset_mutex);

if (cs != &top_cpuset) guarantee_online_cpus(task, cpus_attach); @@ -2558,7 +2624,7 @@ static void cpuset_attach(struct cgroup_taskset *tset) cs = css_cs(css);

lockdep_assert_cpus_held(); /* see cgroup_attach_lock() */ - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex);

guarantee_online_mems(cs, &cpuset_attach_nodemask_to);

@@ -2594,11 +2660,17 @@ static void cpuset_attach(struct cgroup_taskset *tset)

cs->old_mems_allowed = cpuset_attach_nodemask_to;

+ if (cs->nr_migrate_dl_tasks) { + cs->nr_deadline_tasks += cs->nr_migrate_dl_tasks; + oldcs->nr_deadline_tasks -= cs->nr_migrate_dl_tasks; + reset_migrate_dl_data(cs); + } + cs->attach_in_progress--; if (!cs->attach_in_progress) wake_up(&cpuset_attach_wq);

- percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); }

/* The various types of files and directories in a cpuset file system */ @@ -2630,7 +2702,7 @@ static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft, int retval = 0;

cpus_read_lock(); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) { retval = -ENODEV; goto out_unlock; @@ -2666,7 +2738,7 @@ static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft, break; } out_unlock: - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); cpus_read_unlock(); return retval; } @@ -2679,7 +2751,7 @@ static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft, int retval = -ENODEV;

cpus_read_lock(); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) goto out_unlock;

@@ -2692,7 +2764,7 @@ static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft, break; } out_unlock: - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); cpus_read_unlock(); return retval; } @@ -2725,7 +2797,7 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of, * operation like this one can lead to a deadlock through kernfs * active_ref protection. Let's break the protection. Losing the * protection is okay as we check whether @cs is online after - * grabbing cpuset_rwsem anyway. This only happens on the legacy + * grabbing cpuset_mutex anyway. This only happens on the legacy * hierarchies. */ css_get(&cs->css); @@ -2733,7 +2805,7 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of, flush_work(&cpuset_hotplug_work);

cpus_read_lock(); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) goto out_unlock;

@@ -2757,7 +2829,7 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of,

free_cpuset(trialcs); out_unlock: - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); cpus_read_unlock(); kernfs_unbreak_active_protection(of->kn); css_put(&cs->css); @@ -2905,13 +2977,13 @@ static ssize_t sched_partition_write(struct kernfs_open_file *of, char *buf,

css_get(&cs->css); cpus_read_lock(); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) goto out_unlock;

retval = update_prstate(cs, val); out_unlock: - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); cpus_read_unlock(); css_put(&cs->css); return retval ?: nbytes; @@ -3124,7 +3196,7 @@ static int cpuset_css_online(struct cgroup_subsys_state *css) return 0;

cpus_read_lock(); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex);

set_bit(CS_ONLINE, &cs->flags); if (is_spread_page(parent)) @@ -3175,7 +3247,7 @@ static int cpuset_css_online(struct cgroup_subsys_state *css) cpumask_copy(cs->effective_cpus, parent->cpus_allowed); spin_unlock_irq(&callback_lock); out_unlock: - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); cpus_read_unlock(); return 0; } @@ -3196,7 +3268,7 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css) struct cpuset *cs = css_cs(css);

cpus_read_lock(); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex);

if (is_partition_valid(cs)) update_prstate(cs, 0); @@ -3215,7 +3287,7 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css) cpuset_dec(); clear_bit(CS_ONLINE, &cs->flags);

- percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); cpus_read_unlock(); }

@@ -3228,7 +3300,7 @@ static void cpuset_css_free(struct cgroup_subsys_state *css)

static void cpuset_bind(struct cgroup_subsys_state *root_css) { - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); spin_lock_irq(&callback_lock);

if (is_in_v2_mode()) { @@ -3241,7 +3313,7 @@ static void cpuset_bind(struct cgroup_subsys_state *root_css) }

spin_unlock_irq(&callback_lock); - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); }

/* @@ -3262,14 +3334,14 @@ static int cpuset_can_fork(struct task_struct *task, struct css_set *cset) return 0;

lockdep_assert_held(&cgroup_mutex); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex);

/* Check to see if task is allowed in the cpuset */ ret = cpuset_can_attach_check(cs); if (ret) goto out_unlock;

- ret = task_can_attach(task, cs->effective_cpus); + ret = task_can_attach(task); if (ret) goto out_unlock;

@@ -3283,7 +3355,7 @@ static int cpuset_can_fork(struct task_struct *task, struct css_set *cset) */ cs->attach_in_progress++; out_unlock: - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); return ret; }

@@ -3299,11 +3371,11 @@ static void cpuset_cancel_fork(struct task_struct *task, struct css_set *cset) if (same_cs) return;

- percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); cs->attach_in_progress--; if (!cs->attach_in_progress) wake_up(&cpuset_attach_wq); - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); }

/* @@ -3331,7 +3403,7 @@ static void cpuset_fork(struct task_struct *task) }

/* CLONE_INTO_CGROUP */ - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); guarantee_online_mems(cs, &cpuset_attach_nodemask_to); cpuset_attach_task(cs, task);

@@ -3339,7 +3411,7 @@ static void cpuset_fork(struct task_struct *task) if (!cs->attach_in_progress) wake_up(&cpuset_attach_wq);

- percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); }

struct cgroup_subsys cpuset_cgrp_subsys = { @@ -3369,8 +3441,6 @@ struct cgroup_subsys cpuset_cgrp_subsys = {

int __init cpuset_init(void) { - BUG_ON(percpu_init_rwsem(&cpuset_rwsem)); - BUG_ON(!alloc_cpumask_var(&top_cpuset.cpus_allowed, GFP_KERNEL)); BUG_ON(!alloc_cpumask_var(&top_cpuset.effective_cpus, GFP_KERNEL)); BUG_ON(!zalloc_cpumask_var(&top_cpuset.subparts_cpus, GFP_KERNEL)); @@ -3442,7 +3512,7 @@ hotplug_update_tasks_legacy(struct cpuset *cs, is_empty = cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed);

- percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex);

/* * Move tasks to the nearest ancestor with execution resources, @@ -3452,7 +3522,7 @@ hotplug_update_tasks_legacy(struct cpuset *cs, if (is_empty) remove_tasks_in_empty_cpuset(cs);

- percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); }

static void @@ -3503,14 +3573,14 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp) retry: wait_event(cpuset_attach_wq, cs->attach_in_progress == 0);

- percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex);

/* * We have raced with task attaching. We wait until attaching * is finished, so we won't attach a task to an empty cpuset. */ if (cs->attach_in_progress) { - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); goto retry; }

@@ -3604,7 +3674,7 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp) hotplug_update_tasks_legacy(cs, &new_cpus, &new_mems, cpus_updated, mems_updated);

- percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); }

/** @@ -3634,7 +3704,7 @@ static void cpuset_hotplug_workfn(struct work_struct *work) if (on_dfl && !alloc_cpumasks(NULL, &tmp)) ptmp = &tmp;

- percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex);

/* fetch the available cpus/mems and find out which changed how */ cpumask_copy(&new_cpus, cpu_active_mask); @@ -3691,7 +3761,7 @@ static void cpuset_hotplug_workfn(struct work_struct *work) update_tasks_nodemask(&top_cpuset); }

- percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex);

/* if cpus or mems changed, we need to propagate to descendants */ if (cpus_updated || mems_updated) { @@ -4101,7 +4171,7 @@ void __cpuset_memory_pressure_bump(void) * - Used for /proc/<pid>/cpuset. * - No need to task_lock(tsk) on this tsk->cpuset reference, as it * doesn't really matter if tsk->cpuset changes after we read it, - * and we take cpuset_rwsem, keeping cpuset_attach() from changing it + * and we take cpuset_mutex, keeping cpuset_attach() from changing it * anyway. */ int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns, diff --git a/kernel/sched/core.c b/kernel/sched/core.c index b23dcbeacdf3..0f6a92737c91 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -7475,6 +7475,7 @@ static int __sched_setscheduler(struct task_struct *p, int reset_on_fork; int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK; struct rq *rq; + bool cpuset_locked = false;

/* The pi code expects interrupts enabled */ BUG_ON(pi && in_interrupt()); @@ -7524,8 +7525,14 @@ static int __sched_setscheduler(struct task_struct *p, return retval; }

- if (pi) - cpuset_read_lock(); + /* + * SCHED_DEADLINE bandwidth accounting relies on stable cpusets + * information. + */ + if (dl_policy(policy) || dl_policy(p->policy)) { + cpuset_locked = true; + cpuset_lock(); + }

/* * Make sure no PI-waiters arrive (or leave) while we are @@ -7601,8 +7608,8 @@ static int __sched_setscheduler(struct task_struct *p, if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) { policy = oldpolicy = -1; task_rq_unlock(rq, p, &rf); - if (pi) - cpuset_read_unlock(); + if (cpuset_locked) + cpuset_unlock(); goto recheck; }

@@ -7669,7 +7676,8 @@ static int __sched_setscheduler(struct task_struct *p, task_rq_unlock(rq, p, &rf);

if (pi) { - cpuset_read_unlock(); + if (cpuset_locked) + cpuset_unlock(); rt_mutex_adjust_pi(p); }

@@ -7681,8 +7689,8 @@ static int __sched_setscheduler(struct task_struct *p,

unlock: task_rq_unlock(rq, p, &rf); - if (pi) - cpuset_read_unlock(); + if (cpuset_locked) + cpuset_unlock(); return retval; }

@@ -9075,8 +9083,7 @@ int cpuset_cpumask_can_shrink(const struct cpumask *cur, return ret; }

-int task_can_attach(struct task_struct *p, - const struct cpumask *cs_effective_cpus) +int task_can_attach(struct task_struct *p) { int ret = 0;

@@ -9089,21 +9096,9 @@ int task_can_attach(struct task_struct *p, * success of set_cpus_allowed_ptr() on all attached tasks * before cpus_mask may be changed. */ - if (p->flags & PF_NO_SETAFFINITY) { + if (p->flags & PF_NO_SETAFFINITY) ret = -EINVAL; - goto out; - }

- if (dl_task(p) && !cpumask_intersects(task_rq(p)->rd->span, - cs_effective_cpus)) { - int cpu = cpumask_any_and(cpu_active_mask, cs_effective_cpus); - - if (unlikely(cpu >= nr_cpu_ids)) - return -EINVAL; - ret = dl_cpu_busy(cpu, p); - } - -out: return ret; }

@@ -9385,7 +9380,7 @@ static void cpuset_cpu_active(void) static int cpuset_cpu_inactive(unsigned int cpu) { if (!cpuhp_tasks_frozen) { - int ret = dl_cpu_busy(cpu, NULL); + int ret = dl_bw_check_overflow(cpu);

if (ret) return ret; diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index f7d381b6c313..9ce9810861ba 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -16,6 +16,8 @@ * Fabio Checconi fchecconi@gmail.com */

+#include <linux/cpuset.h> + /* * Default limits for DL period; on the top end we guard against small util * tasks still getting ridiculously long effective runtimes, on the bottom end we @@ -2597,6 +2599,12 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p) if (task_on_rq_queued(p) && p->dl.dl_runtime) task_non_contending(p);

+ /* + * In case a task is setscheduled out from SCHED_DEADLINE we need to + * keep track of that on its cpuset (for correct bandwidth tracking). + */ + dec_dl_tasks_cs(p); + if (!task_on_rq_queued(p)) { /* * Inactive timer is armed. However, p is leaving DEADLINE and @@ -2637,6 +2645,12 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p) if (hrtimer_try_to_cancel(&p->dl.inactive_timer) == 1) put_task_struct(p);

+ /* + * In case a task is setscheduled to SCHED_DEADLINE we need to keep + * track of that on its cpuset (for correct bandwidth tracking). + */ + inc_dl_tasks_cs(p); + /* If p is not queued we will update its parameters at next wakeup. */ if (!task_on_rq_queued(p)) { add_rq_bw(&p->dl, &rq->dl); @@ -3023,26 +3037,38 @@ int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur, return ret; }

-int dl_cpu_busy(int cpu, struct task_struct *p) +enum dl_bw_request { + dl_bw_req_check_overflow = 0, + dl_bw_req_alloc, + dl_bw_req_free +}; + +static int dl_bw_manage(enum dl_bw_request req, int cpu, u64 dl_bw) { - unsigned long flags, cap; + unsigned long flags; struct dl_bw *dl_b; - bool overflow; + bool overflow = 0;

rcu_read_lock_sched(); dl_b = dl_bw_of(cpu); raw_spin_lock_irqsave(&dl_b->lock, flags); - cap = dl_bw_capacity(cpu); - overflow = __dl_overflow(dl_b, cap, 0, p ? p->dl.dl_bw : 0);

- if (!overflow && p) { - /* - * We reserve space for this task in the destination - * root_domain, as we can't fail after this point. - * We will free resources in the source root_domain - * later on (see set_cpus_allowed_dl()). - */ - __dl_add(dl_b, p->dl.dl_bw, dl_bw_cpus(cpu)); + if (req == dl_bw_req_free) { + __dl_sub(dl_b, dl_bw, dl_bw_cpus(cpu)); + } else { + unsigned long cap = dl_bw_capacity(cpu); + + overflow = __dl_overflow(dl_b, cap, 0, dl_bw); + + if (req == dl_bw_req_alloc && !overflow) { + /* + * We reserve space in the destination + * root_domain, as we can't fail after this point. + * We will free resources in the source root_domain + * later on (see set_cpus_allowed_dl()). + */ + __dl_add(dl_b, dl_bw, dl_bw_cpus(cpu)); + } }

raw_spin_unlock_irqrestore(&dl_b->lock, flags); @@ -3050,6 +3076,21 @@ int dl_cpu_busy(int cpu, struct task_struct *p)

return overflow ? -EBUSY : 0; } + +int dl_bw_check_overflow(int cpu) +{ + return dl_bw_manage(dl_bw_req_check_overflow, cpu, 0); +} + +int dl_bw_alloc(int cpu, u64 dl_bw) +{ + return dl_bw_manage(dl_bw_req_alloc, cpu, dl_bw); +} + +void dl_bw_free(int cpu, u64 dl_bw) +{ + dl_bw_manage(dl_bw_req_free, cpu, dl_bw); +} #endif

#ifdef CONFIG_SCHED_DEBUG diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index d6d488e8eb55..b62d53d7c264 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -330,7 +330,7 @@ extern void __getparam_dl(struct task_struct *p, struct sched_attr *attr); extern bool __checkparam_dl(const struct sched_attr *attr); extern bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr); extern int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial); -extern int dl_cpu_busy(int cpu, struct task_struct *p); +extern int dl_bw_check_overflow(int cpu);

#ifdef CONFIG_CGROUP_SCHED

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index af33c5a4166d..1a87cb70f1eb 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4128,8 +4128,15 @@ static void *s_start(struct seq_file *m, loff_t *pos) * will point to the same string as current_trace->name. */ mutex_lock(&trace_types_lock); - if (unlikely(tr->current_trace && iter->trace->name != tr->current_trace->name)) + if (unlikely(tr->current_trace && iter->trace->name != tr->current_trace->name)) { + /* Close iter->trace before switching to the new current tracer */ + if (iter->trace->close) + iter->trace->close(iter); *iter->trace = *tr->current_trace; + /* Reopen the new current tracer */ + if (iter->trace->open) + iter->trace->open(iter); + } mutex_unlock(&trace_types_lock);

#ifdef CONFIG_TRACER_MAX_TRACE @@ -5189,11 +5196,17 @@ int tracing_set_cpumask(struct trace_array *tr, !cpumask_test_cpu(cpu, tracing_cpumask_new)) { atomic_inc(&per_cpu_ptr(tr->array_buffer.data, cpu)->disabled); ring_buffer_record_disable_cpu(tr->array_buffer.buffer, cpu); +#ifdef CONFIG_TRACER_MAX_TRACE + ring_buffer_record_disable_cpu(tr->max_buffer.buffer, cpu); +#endif } if (!cpumask_test_cpu(cpu, tr->tracing_cpumask) && cpumask_test_cpu(cpu, tracing_cpumask_new)) { atomic_dec(&per_cpu_ptr(tr->array_buffer.data, cpu)->disabled); ring_buffer_record_enable_cpu(tr->array_buffer.buffer, cpu); +#ifdef CONFIG_TRACER_MAX_TRACE + ring_buffer_record_enable_cpu(tr->max_buffer.buffer, cpu); +#endif } } arch_spin_unlock(&tr->max_lock); diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index 590b3d51afae..ba37f768e2f2 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -231,7 +231,8 @@ static void irqsoff_trace_open(struct trace_iterator *iter) { if (is_graph(iter->tr)) graph_trace_open(iter); - + else + iter->private = NULL; }

static void irqsoff_trace_close(struct trace_iterator *iter) diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 330aee1c1a49..0469a04a355f 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -168,6 +168,8 @@ static void wakeup_trace_open(struct trace_iterator *iter) { if (is_graph(iter->tr)) graph_trace_open(iter); + else + iter->private = NULL; }

static void wakeup_trace_close(struct trace_iterator *iter) diff --git a/lib/clz_ctz.c b/lib/clz_ctz.c index 0d3a686b5ba2..fb8c0c5c2bd2 100644 --- a/lib/clz_ctz.c +++ b/lib/clz_ctz.c @@ -28,36 +28,16 @@ int __weak __clzsi2(int val) } EXPORT_SYMBOL(__clzsi2);

-int __weak __clzdi2(long val); -int __weak __ctzdi2(long val); -#if BITS_PER_LONG == 32 - -int __weak __clzdi2(long val) +int __weak __clzdi2(u64 val); +int __weak __clzdi2(u64 val) { - return 32 - fls((int)val); + return 64 - fls64(val); } EXPORT_SYMBOL(__clzdi2);

-int __weak __ctzdi2(long val) +int __weak __ctzdi2(u64 val); +int __weak __ctzdi2(u64 val) { - return __ffs((u32)val); + return __ffs64(val); } EXPORT_SYMBOL(__ctzdi2); - -#elif BITS_PER_LONG == 64 - -int __weak __clzdi2(long val) -{ - return 64 - fls64((u64)val); -} -EXPORT_SYMBOL(__clzdi2); - -int __weak __ctzdi2(long val) -{ - return __ffs64((u64)val); -} -EXPORT_SYMBOL(__ctzdi2); - -#else -#error BITS_PER_LONG not 32 or 64 -#endif diff --git a/lib/maple_tree.c b/lib/maple_tree.c index 47d0c95b9a01..250b4c67fac8 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -4333,6 +4333,9 @@ static inline bool mas_wr_append(struct ma_wr_state *wr_mas) struct ma_state *mas = wr_mas->mas; unsigned char node_pivots = mt_pivots[wr_mas->type];

+ if (mt_in_rcu(mas->tree)) + return false; + if ((mas->index != wr_mas->r_min) && (mas->last == wr_mas->r_max)) { if (new_end < node_pivots) wr_mas->pivots[new_end] = wr_mas->pivots[end]; diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 3c78e1e8b2ad..2ec38f08e4f0 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -1134,7 +1134,6 @@ static void set_iter_tags(struct radix_tree_iter *iter, void __rcu **radix_tree_iter_resume(void __rcu **slot, struct radix_tree_iter *iter) { - slot++; iter->index = __radix_tree_iter_add(iter, 1); iter->next_index = iter->index; iter->tags = 0; diff --git a/mm/madvise.c b/mm/madvise.c index d03e149ffe6e..5973399b2f9b 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -654,8 +654,8 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, * deactivate all pages. */ if (folio_test_large(folio)) { - if (folio_mapcount(folio) != 1) - goto out; + if (folio_estimated_sharers(folio) != 1) + break; folio_get(folio); if (!folio_trylock(folio)) { folio_put(folio); diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 4457f9423e2c..99de0328d1be 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -2591,10 +2591,13 @@ int soft_offline_page(unsigned long pfn, int flags) if (ret > 0) { ret = soft_offline_in_use_page(page); } else if (ret == 0) { - if (!page_handle_poison(page, true, false) && try_again) { - try_again = false; - flags &= ~MF_COUNT_INCREASED; - goto retry; + if (!page_handle_poison(page, true, false)) { + if (try_again) { + try_again = false; + flags &= ~MF_COUNT_INCREASED; + goto retry; + } + ret = -EBUSY; } }

diff --git a/mm/shmem.c b/mm/shmem.c index aba041a3df73..10365ced5b1f 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -800,14 +800,16 @@ unsigned long shmem_partial_swap_usage(struct address_space *mapping, XA_STATE(xas, &mapping->i_pages, start); struct page *page; unsigned long swapped = 0; + unsigned long max = end - 1;

rcu_read_lock(); - xas_for_each(&xas, page, end - 1) { + xas_for_each(&xas, page, max) { if (xas_retry(&xas, page)) continue; if (xa_is_value(page)) swapped++; - + if (xas.xa_index == max) + break; if (need_resched()) { xas_pause(&xas); cond_resched_rcu(); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index d5dc361dc104..80bd104a4d42 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -2909,6 +2909,10 @@ void *vmap_pfn(unsigned long *pfns, unsigned int count, pgprot_t prot) free_vm_area(area); return NULL; } + + flush_cache_vmap((unsigned long)area->addr, + (unsigned long)area->addr + count * PAGE_SIZE); + return area->addr; } EXPORT_SYMBOL_GPL(vmap_pfn); diff --git a/net/Makefile b/net/Makefile index 6a62e5b27378..0914bea9c335 100644 --- a/net/Makefile +++ b/net/Makefile @@ -23,6 +23,7 @@ obj-$(CONFIG_BPFILTER) += bpfilter/ obj-$(CONFIG_PACKET) += packet/ obj-$(CONFIG_NET_KEY) += key/ obj-$(CONFIG_BRIDGE) += bridge/ +obj-$(CONFIG_NET_DEVLINK) += devlink/ obj-$(CONFIG_NET_DSA) += dsa/ obj-$(CONFIG_ATALK) += appletalk/ obj-$(CONFIG_X25) += x25/ diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index f1741fbfb617..98a624f32b94 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -506,7 +506,7 @@ int batadv_v_elp_packet_recv(struct sk_buff *skb, struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface); struct batadv_elp_packet *elp_packet; struct batadv_hard_iface *primary_if; - struct ethhdr *ethhdr = (struct ethhdr *)skb_mac_header(skb); + struct ethhdr *ethhdr; bool res; int ret = NET_RX_DROP;

@@ -514,6 +514,7 @@ int batadv_v_elp_packet_recv(struct sk_buff *skb, if (!res) goto free_skb;

+ ethhdr = eth_hdr(skb); if (batadv_is_my_mac(bat_priv, ethhdr->h_source)) goto free_skb;

diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index 033639df96d8..9f4815f4c8e8 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -124,8 +124,10 @@ static void batadv_v_ogm_send_to_if(struct sk_buff *skb, { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface);

- if (hard_iface->if_status != BATADV_IF_ACTIVE) + if (hard_iface->if_status != BATADV_IF_ACTIVE) { + kfree_skb(skb); return; + }

batadv_inc_counter(bat_priv, BATADV_CNT_MGMT_TX); batadv_add_counter(bat_priv, BATADV_CNT_MGMT_TX_BYTES, @@ -986,7 +988,7 @@ int batadv_v_ogm_packet_recv(struct sk_buff *skb, { struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface); struct batadv_ogm2_packet *ogm_packet; - struct ethhdr *ethhdr = eth_hdr(skb); + struct ethhdr *ethhdr; int ogm_offset; u8 *packet_pos; int ret = NET_RX_DROP; @@ -1000,6 +1002,7 @@ int batadv_v_ogm_packet_recv(struct sk_buff *skb, if (!batadv_check_management_packet(skb, if_incoming, BATADV_OGM2_HLEN)) goto free_skb;

+ ethhdr = eth_hdr(skb); if (batadv_is_my_mac(bat_priv, ethhdr->h_source)) goto free_skb;

diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 41c1ad33d009..24c9c0c3f316 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -630,7 +630,19 @@ int batadv_hardif_min_mtu(struct net_device *soft_iface) */ void batadv_update_min_mtu(struct net_device *soft_iface) { - soft_iface->mtu = batadv_hardif_min_mtu(soft_iface); + struct batadv_priv *bat_priv = netdev_priv(soft_iface); + int limit_mtu; + int mtu; + + mtu = batadv_hardif_min_mtu(soft_iface); + + if (bat_priv->mtu_set_by_user) + limit_mtu = bat_priv->mtu_set_by_user; + else + limit_mtu = ETH_DATA_LEN; + + mtu = min(mtu, limit_mtu); + dev_set_mtu(soft_iface, mtu);

/* Check if the local translate table should be cleaned up to match a * new (and smaller) MTU. diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c index a5e4a4e976cf..86e0664e0511 100644 --- a/net/batman-adv/netlink.c +++ b/net/batman-adv/netlink.c @@ -495,7 +495,10 @@ static int batadv_netlink_set_mesh(struct sk_buff *skb, struct genl_info *info) attr = info->attrs[BATADV_ATTR_FRAGMENTATION_ENABLED];

atomic_set(&bat_priv->fragmentation, !!nla_get_u8(attr)); + + rtnl_lock(); batadv_update_min_mtu(bat_priv->soft_iface); + rtnl_unlock(); }

if (info->attrs[BATADV_ATTR_GW_BANDWIDTH_DOWN]) { diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 0f5c0679b55a..38d411a52f33 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -154,11 +154,14 @@ static int batadv_interface_set_mac_addr(struct net_device *dev, void *p)

static int batadv_interface_change_mtu(struct net_device *dev, int new_mtu) { + struct batadv_priv *bat_priv = netdev_priv(dev); + /* check ranges */ if (new_mtu < 68 || new_mtu > batadv_hardif_min_mtu(dev)) return -EINVAL;

dev->mtu = new_mtu; + bat_priv->mtu_set_by_user = new_mtu;

return 0; } diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 01d30c1e412c..5d8cee74772f 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -774,7 +774,6 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const u8 *addr, if (roamed_back) { batadv_tt_global_free(bat_priv, tt_global, "Roaming canceled"); - tt_global = NULL; } else { /* The global entry has to be marked as ROAMING and * has to be kept for consistency purpose diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 758cd797a063..76791815b26b 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -1546,6 +1546,12 @@ struct batadv_priv { /** @soft_iface: net device which holds this struct as private data */ struct net_device *soft_iface;

+ /** + * @mtu_set_by_user: MTU was set once by user + * protected by rtnl_lock + */ + int mtu_set_by_user; + /** * @bat_counters: mesh internal traffic statistic counters (see * batadv_counters) diff --git a/net/can/isotp.c b/net/can/isotp.c index b3c2a49b189c..8c97f4061ffd 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -175,12 +175,6 @@ static bool isotp_register_rxid(struct isotp_sock *so) return (isotp_bc_flags(so) == 0); }

-static bool isotp_register_txecho(struct isotp_sock *so) -{ - /* all modes but SF_BROADCAST register for tx echo skbs */ - return (isotp_bc_flags(so) != CAN_ISOTP_SF_BROADCAST); -} - static enum hrtimer_restart isotp_rx_timer_handler(struct hrtimer *hrtimer) { struct isotp_sock *so = container_of(hrtimer, struct isotp_sock, @@ -1176,7 +1170,7 @@ static int isotp_release(struct socket *sock) lock_sock(sk);

/* remove current filters & unregister */ - if (so->bound && isotp_register_txecho(so)) { + if (so->bound) { if (so->ifindex) { struct net_device *dev;

@@ -1293,14 +1287,12 @@ static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len) can_rx_register(net, dev, rx_id, SINGLE_MASK(rx_id), isotp_rcv, sk, "isotp", sk);

- if (isotp_register_txecho(so)) { - /* no consecutive frame echo skb in flight */ - so->cfecho = 0; + /* no consecutive frame echo skb in flight */ + so->cfecho = 0;

- /* register for echo skb's */ - can_rx_register(net, dev, tx_id, SINGLE_MASK(tx_id), - isotp_rcv_echo, sk, "isotpe", sk); - } + /* register for echo skb's */ + can_rx_register(net, dev, tx_id, SINGLE_MASK(tx_id), + isotp_rcv_echo, sk, "isotpe", sk);

dev_put(dev);

@@ -1521,7 +1513,7 @@ static void isotp_notify(struct isotp_sock *so, unsigned long msg, case NETDEV_UNREGISTER: lock_sock(sk); /* remove current filters & unregister */ - if (so->bound && isotp_register_txecho(so)) { + if (so->bound) { if (isotp_register_rxid(so)) can_rx_unregister(dev_net(dev), dev, so->rxid, SINGLE_MASK(so->rxid), diff --git a/net/can/raw.c b/net/can/raw.c index 4abab2c3011a..8c104339d538 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -84,6 +84,8 @@ struct raw_sock { struct sock sk; int bound; int ifindex; + struct net_device *dev; + netdevice_tracker dev_tracker; struct list_head notifier; int loopback; int recv_own_msgs; @@ -277,21 +279,24 @@ static void raw_notify(struct raw_sock *ro, unsigned long msg, if (!net_eq(dev_net(dev), sock_net(sk))) return;

- if (ro->ifindex != dev->ifindex) + if (ro->dev != dev) return;

switch (msg) { case NETDEV_UNREGISTER: lock_sock(sk); /* remove current filters & unregister */ - if (ro->bound) + if (ro->bound) { raw_disable_allfilters(dev_net(dev), dev, sk); + netdev_put(dev, &ro->dev_tracker); + }

if (ro->count > 1) kfree(ro->filter);

ro->ifindex = 0; ro->bound = 0; + ro->dev = NULL; ro->count = 0; release_sock(sk);

@@ -337,6 +342,7 @@ static int raw_init(struct sock *sk)

ro->bound = 0; ro->ifindex = 0; + ro->dev = NULL;

/* set default filter to single entry dfilter */ ro->dfilter.can_id = 0; @@ -383,18 +389,14 @@ static int raw_release(struct socket *sock) list_del(&ro->notifier); spin_unlock(&raw_notifier_lock);

+ rtnl_lock(); lock_sock(sk);

/* remove current filters & unregister */ if (ro->bound) { - if (ro->ifindex) { - struct net_device *dev; - - dev = dev_get_by_index(sock_net(sk), ro->ifindex); - if (dev) { - raw_disable_allfilters(dev_net(dev), dev, sk); - dev_put(dev); - } + if (ro->dev) { + raw_disable_allfilters(dev_net(ro->dev), ro->dev, sk); + netdev_put(ro->dev, &ro->dev_tracker); } else { raw_disable_allfilters(sock_net(sk), NULL, sk); } @@ -405,6 +407,7 @@ static int raw_release(struct socket *sock)

ro->ifindex = 0; ro->bound = 0; + ro->dev = NULL; ro->count = 0; free_percpu(ro->uniq);

@@ -412,6 +415,8 @@ static int raw_release(struct socket *sock) sock->sk = NULL;

release_sock(sk); + rtnl_unlock(); + sock_put(sk);

return 0; @@ -422,6 +427,7 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; struct sock *sk = sock->sk; struct raw_sock *ro = raw_sk(sk); + struct net_device *dev = NULL; int ifindex; int err = 0; int notify_enetdown = 0; @@ -431,24 +437,23 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) if (addr->can_family != AF_CAN) return -EINVAL;

+ rtnl_lock(); lock_sock(sk);

if (ro->bound && addr->can_ifindex == ro->ifindex) goto out;

if (addr->can_ifindex) { - struct net_device *dev; - dev = dev_get_by_index(sock_net(sk), addr->can_ifindex); if (!dev) { err = -ENODEV; goto out; } if (dev->type != ARPHRD_CAN) { - dev_put(dev); err = -ENODEV; - goto out; + goto out_put_dev; } + if (!(dev->flags & IFF_UP)) notify_enetdown = 1;

@@ -456,7 +461,9 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len)

/* filters set by default/setsockopt */ err = raw_enable_allfilters(sock_net(sk), dev, sk); - dev_put(dev); + if (err) + goto out_put_dev; + } else { ifindex = 0;

@@ -467,26 +474,30 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) if (!err) { if (ro->bound) { /* unregister old filters */ - if (ro->ifindex) { - struct net_device *dev; - - dev = dev_get_by_index(sock_net(sk), - ro->ifindex); - if (dev) { - raw_disable_allfilters(dev_net(dev), - dev, sk); - dev_put(dev); - } + if (ro->dev) { + raw_disable_allfilters(dev_net(ro->dev), + ro->dev, sk); + /* drop reference to old ro->dev */ + netdev_put(ro->dev, &ro->dev_tracker); } else { raw_disable_allfilters(sock_net(sk), NULL, sk); } } ro->ifindex = ifindex; ro->bound = 1; + /* bind() ok -> hold a reference for new ro->dev */ + ro->dev = dev; + if (ro->dev) + netdev_hold(ro->dev, &ro->dev_tracker, GFP_KERNEL); }

- out: +out_put_dev: + /* remove potential reference from dev_get_by_index() */ + if (dev) + dev_put(dev); +out: release_sock(sk); + rtnl_unlock();

if (notify_enetdown) { sk->sk_err = ENETDOWN; @@ -552,9 +563,9 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, rtnl_lock(); lock_sock(sk);

- if (ro->bound && ro->ifindex) { - dev = dev_get_by_index(sock_net(sk), ro->ifindex); - if (!dev) { + dev = ro->dev; + if (ro->bound && dev) { + if (dev->reg_state != NETREG_REGISTERED) { if (count > 1) kfree(filter); err = -ENODEV; @@ -595,7 +606,6 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, ro->count = count;

out_fil: - dev_put(dev); release_sock(sk); rtnl_unlock();

@@ -613,9 +623,9 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, rtnl_lock(); lock_sock(sk);

- if (ro->bound && ro->ifindex) { - dev = dev_get_by_index(sock_net(sk), ro->ifindex); - if (!dev) { + dev = ro->dev; + if (ro->bound && dev) { + if (dev->reg_state != NETREG_REGISTERED) { err = -ENODEV; goto out_err; } @@ -639,7 +649,6 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, ro->err_mask = err_mask;

out_err: - dev_put(dev); release_sock(sk); rtnl_unlock();

diff --git a/net/core/Makefile b/net/core/Makefile index 5857cec87b83..10edd66a8a37 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -33,7 +33,6 @@ obj-$(CONFIG_LWTUNNEL) += lwtunnel.o obj-$(CONFIG_LWTUNNEL_BPF) += lwt_bpf.o obj-$(CONFIG_DST_CACHE) += dst_cache.o obj-$(CONFIG_HWBM) += hwbm.o -obj-$(CONFIG_NET_DEVLINK) += devlink.o obj-$(CONFIG_GRO_CELLS) += gro_cells.o obj-$(CONFIG_FAILOVER) += failover.o obj-$(CONFIG_NET_SOCK_MSG) += skmsg.o diff --git a/net/core/devlink.c b/net/core/devlink.c deleted file mode 100644 index 5a4a4b34ac15..000000000000 --- a/net/core/devlink.c +++ /dev/null @@ -1,12547 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * net/core/devlink.c - Network physical/parent device Netlink interface - * - * Heavily inspired by net/wireless/ - * Copyright (c) 2016 Mellanox Technologies. All rights reserved. - * Copyright (c) 2016 Jiri Pirko jiri@mellanox.com - */ - -#include <linux/etherdevice.h> -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/types.h> -#include <linux/slab.h> -#include <linux/gfp.h> -#include <linux/device.h> -#include <linux/list.h> -#include <linux/netdevice.h> -#include <linux/spinlock.h> -#include <linux/refcount.h> -#include <linux/workqueue.h> -#include <linux/u64_stats_sync.h> -#include <linux/timekeeping.h> -#include <rdma/ib_verbs.h> -#include <net/netlink.h> -#include <net/genetlink.h> -#include <net/rtnetlink.h> -#include <net/net_namespace.h> -#include <net/sock.h> -#include <net/devlink.h> -#define CREATE_TRACE_POINTS -#include <trace/events/devlink.h> - -#define DEVLINK_RELOAD_STATS_ARRAY_SIZE \ - (__DEVLINK_RELOAD_LIMIT_MAX * __DEVLINK_RELOAD_ACTION_MAX) - -struct devlink_dev_stats { - u32 reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE]; - u32 remote_reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE]; -}; - -struct devlink { - u32 index; - struct list_head port_list; - struct list_head rate_list; - struct list_head sb_list; - struct list_head dpipe_table_list; - struct list_head resource_list; - struct list_head param_list; - struct list_head region_list; - struct list_head reporter_list; - struct mutex reporters_lock; /* protects reporter_list */ - struct devlink_dpipe_headers *dpipe_headers; - struct list_head trap_list; - struct list_head trap_group_list; - struct list_head trap_policer_list; - struct list_head linecard_list; - struct mutex linecards_lock; /* protects linecard_list */ - const struct devlink_ops *ops; - u64 features; - struct xarray snapshot_ids; - struct devlink_dev_stats stats; - struct device *dev; - possible_net_t _net; - /* Serializes access to devlink instance specific objects such as - * port, sb, dpipe, resource, params, region, traps and more. - */ - struct mutex lock; - struct lock_class_key lock_key; - u8 reload_failed:1; - refcount_t refcount; - struct completion comp; - struct rcu_head rcu; - char priv[] __aligned(NETDEV_ALIGN); -}; - -struct devlink_linecard_ops; -struct devlink_linecard_type; - -struct devlink_linecard { - struct list_head list; - struct devlink *devlink; - unsigned int index; - refcount_t refcount; - const struct devlink_linecard_ops *ops; - void *priv; - enum devlink_linecard_state state; - struct mutex state_lock; /* Protects state */ - const char *type; - struct devlink_linecard_type *types; - unsigned int types_count; - struct devlink *nested_devlink; -}; - -/** - * struct devlink_resource - devlink resource - * @name: name of the resource - * @id: id, per devlink instance - * @size: size of the resource - * @size_new: updated size of the resource, reload is needed - * @size_valid: valid in case the total size of the resource is valid - * including its children - * @parent: parent resource - * @size_params: size parameters - * @list: parent list - * @resource_list: list of child resources - * @occ_get: occupancy getter callback - * @occ_get_priv: occupancy getter callback priv - */ -struct devlink_resource { - const char *name; - u64 id; - u64 size; - u64 size_new; - bool size_valid; - struct devlink_resource *parent; - struct devlink_resource_size_params size_params; - struct list_head list; - struct list_head resource_list; - devlink_resource_occ_get_t *occ_get; - void *occ_get_priv; -}; - -void *devlink_priv(struct devlink *devlink) -{ - return &devlink->priv; -} -EXPORT_SYMBOL_GPL(devlink_priv); - -struct devlink *priv_to_devlink(void *priv) -{ - return container_of(priv, struct devlink, priv); -} -EXPORT_SYMBOL_GPL(priv_to_devlink); - -struct device *devlink_to_dev(const struct devlink *devlink) -{ - return devlink->dev; -} -EXPORT_SYMBOL_GPL(devlink_to_dev); - -static struct devlink_dpipe_field devlink_dpipe_fields_ethernet[] = { - { - .name = "destination mac", - .id = DEVLINK_DPIPE_FIELD_ETHERNET_DST_MAC, - .bitwidth = 48, - }, -}; - -struct devlink_dpipe_header devlink_dpipe_header_ethernet = { - .name = "ethernet", - .id = DEVLINK_DPIPE_HEADER_ETHERNET, - .fields = devlink_dpipe_fields_ethernet, - .fields_count = ARRAY_SIZE(devlink_dpipe_fields_ethernet), - .global = true, -}; -EXPORT_SYMBOL_GPL(devlink_dpipe_header_ethernet); - -static struct devlink_dpipe_field devlink_dpipe_fields_ipv4[] = { - { - .name = "destination ip", - .id = DEVLINK_DPIPE_FIELD_IPV4_DST_IP, - .bitwidth = 32, - }, -}; - -struct devlink_dpipe_header devlink_dpipe_header_ipv4 = { - .name = "ipv4", - .id = DEVLINK_DPIPE_HEADER_IPV4, - .fields = devlink_dpipe_fields_ipv4, - .fields_count = ARRAY_SIZE(devlink_dpipe_fields_ipv4), - .global = true, -}; -EXPORT_SYMBOL_GPL(devlink_dpipe_header_ipv4); - -static struct devlink_dpipe_field devlink_dpipe_fields_ipv6[] = { - { - .name = "destination ip", - .id = DEVLINK_DPIPE_FIELD_IPV6_DST_IP, - .bitwidth = 128, - }, -}; - -struct devlink_dpipe_header devlink_dpipe_header_ipv6 = { - .name = "ipv6", - .id = DEVLINK_DPIPE_HEADER_IPV6, - .fields = devlink_dpipe_fields_ipv6, - .fields_count = ARRAY_SIZE(devlink_dpipe_fields_ipv6), - .global = true, -}; -EXPORT_SYMBOL_GPL(devlink_dpipe_header_ipv6); - -EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwmsg); -EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwerr); -EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_trap_report); - -static const struct nla_policy devlink_function_nl_policy[DEVLINK_PORT_FUNCTION_ATTR_MAX + 1] = { - [DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR] = { .type = NLA_BINARY }, - [DEVLINK_PORT_FN_ATTR_STATE] = - NLA_POLICY_RANGE(NLA_U8, DEVLINK_PORT_FN_STATE_INACTIVE, - DEVLINK_PORT_FN_STATE_ACTIVE), -}; - -static const struct nla_policy devlink_selftest_nl_policy[DEVLINK_ATTR_SELFTEST_ID_MAX + 1] = { - [DEVLINK_ATTR_SELFTEST_ID_FLASH] = { .type = NLA_FLAG }, -}; - -static DEFINE_XARRAY_FLAGS(devlinks, XA_FLAGS_ALLOC); -#define DEVLINK_REGISTERED XA_MARK_1 -#define DEVLINK_UNREGISTERING XA_MARK_2 - -/* devlink instances are open to the access from the user space after - * devlink_register() call. Such logical barrier allows us to have certain - * expectations related to locking. - * - * Before *_register() - we are in initialization stage and no parallel - * access possible to the devlink instance. All drivers perform that phase - * by implicitly holding device_lock. - * - * After *_register() - users and driver can access devlink instance at - * the same time. - */ -#define ASSERT_DEVLINK_REGISTERED(d) \ - WARN_ON_ONCE(!xa_get_mark(&devlinks, (d)->index, DEVLINK_REGISTERED)) -#define ASSERT_DEVLINK_NOT_REGISTERED(d) \ - WARN_ON_ONCE(xa_get_mark(&devlinks, (d)->index, DEVLINK_REGISTERED)) - -struct net *devlink_net(const struct devlink *devlink) -{ - return read_pnet(&devlink->_net); -} -EXPORT_SYMBOL_GPL(devlink_net); - -static void __devlink_put_rcu(struct rcu_head *head) -{ - struct devlink *devlink = container_of(head, struct devlink, rcu); - - complete(&devlink->comp); -} - -void devlink_put(struct devlink *devlink) -{ - if (refcount_dec_and_test(&devlink->refcount)) - /* Make sure unregister operation that may await the completion - * is unblocked only after all users are after the end of - * RCU grace period. - */ - call_rcu(&devlink->rcu, __devlink_put_rcu); -} - -struct devlink *__must_check devlink_try_get(struct devlink *devlink) -{ - if (refcount_inc_not_zero(&devlink->refcount)) - return devlink; - return NULL; -} - -void devl_assert_locked(struct devlink *devlink) -{ - lockdep_assert_held(&devlink->lock); -} -EXPORT_SYMBOL_GPL(devl_assert_locked); - -#ifdef CONFIG_LOCKDEP -/* For use in conjunction with LOCKDEP only e.g. rcu_dereference_protected() */ -bool devl_lock_is_held(struct devlink *devlink) -{ - return lockdep_is_held(&devlink->lock); -} -EXPORT_SYMBOL_GPL(devl_lock_is_held); -#endif - -void devl_lock(struct devlink *devlink) -{ - mutex_lock(&devlink->lock); -} -EXPORT_SYMBOL_GPL(devl_lock); - -int devl_trylock(struct devlink *devlink) -{ - return mutex_trylock(&devlink->lock); -} -EXPORT_SYMBOL_GPL(devl_trylock); - -void devl_unlock(struct devlink *devlink) -{ - mutex_unlock(&devlink->lock); -} -EXPORT_SYMBOL_GPL(devl_unlock); - -static struct devlink * -devlinks_xa_find_get(struct net *net, unsigned long *indexp, xa_mark_t filter, - void * (*xa_find_fn)(struct xarray *, unsigned long *, - unsigned long, xa_mark_t)) -{ - struct devlink *devlink; - - rcu_read_lock(); -retry: - devlink = xa_find_fn(&devlinks, indexp, ULONG_MAX, DEVLINK_REGISTERED); - if (!devlink) - goto unlock; - - /* In case devlink_unregister() was already called and "unregistering" - * mark was set, do not allow to get a devlink reference here. - * This prevents live-lock of devlink_unregister() wait for completion. - */ - if (xa_get_mark(&devlinks, *indexp, DEVLINK_UNREGISTERING)) - goto retry; - - /* For a possible retry, the xa_find_after() should be always used */ - xa_find_fn = xa_find_after; - if (!devlink_try_get(devlink)) - goto retry; - if (!net_eq(devlink_net(devlink), net)) { - devlink_put(devlink); - goto retry; - } -unlock: - rcu_read_unlock(); - return devlink; -} - -static struct devlink *devlinks_xa_find_get_first(struct net *net, - unsigned long *indexp, - xa_mark_t filter) -{ - return devlinks_xa_find_get(net, indexp, filter, xa_find); -} - -static struct devlink *devlinks_xa_find_get_next(struct net *net, - unsigned long *indexp, - xa_mark_t filter) -{ - return devlinks_xa_find_get(net, indexp, filter, xa_find_after); -} - -/* Iterate over devlink pointers which were possible to get reference to. - * devlink_put() needs to be called for each iterated devlink pointer - * in loop body in order to release the reference. - */ -#define devlinks_xa_for_each_get(net, index, devlink, filter) \ - for (index = 0, \ - devlink = devlinks_xa_find_get_first(net, &index, filter); \ - devlink; devlink = devlinks_xa_find_get_next(net, &index, filter)) - -#define devlinks_xa_for_each_registered_get(net, index, devlink) \ - devlinks_xa_for_each_get(net, index, devlink, DEVLINK_REGISTERED) - -static struct devlink *devlink_get_from_attrs(struct net *net, - struct nlattr **attrs) -{ - struct devlink *devlink; - unsigned long index; - char *busname; - char *devname; - - if (!attrs[DEVLINK_ATTR_BUS_NAME] || !attrs[DEVLINK_ATTR_DEV_NAME]) - return ERR_PTR(-EINVAL); - - busname = nla_data(attrs[DEVLINK_ATTR_BUS_NAME]); - devname = nla_data(attrs[DEVLINK_ATTR_DEV_NAME]); - - devlinks_xa_for_each_registered_get(net, index, devlink) { - if (strcmp(devlink->dev->bus->name, busname) == 0 && - strcmp(dev_name(devlink->dev), devname) == 0) - return devlink; - devlink_put(devlink); - } - - return ERR_PTR(-ENODEV); -} - -#define ASSERT_DEVLINK_PORT_REGISTERED(devlink_port) \ - WARN_ON_ONCE(!(devlink_port)->registered) -#define ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port) \ - WARN_ON_ONCE((devlink_port)->registered) -#define ASSERT_DEVLINK_PORT_INITIALIZED(devlink_port) \ - WARN_ON_ONCE(!(devlink_port)->initialized) - -static struct devlink_port *devlink_port_get_by_index(struct devlink *devlink, - unsigned int port_index) -{ - struct devlink_port *devlink_port; - - list_for_each_entry(devlink_port, &devlink->port_list, list) { - if (devlink_port->index == port_index) - return devlink_port; - } - return NULL; -} - -static bool devlink_port_index_exists(struct devlink *devlink, - unsigned int port_index) -{ - return devlink_port_get_by_index(devlink, port_index); -} - -static struct devlink_port *devlink_port_get_from_attrs(struct devlink *devlink, - struct nlattr **attrs) -{ - if (attrs[DEVLINK_ATTR_PORT_INDEX]) { - u32 port_index = nla_get_u32(attrs[DEVLINK_ATTR_PORT_INDEX]); - struct devlink_port *devlink_port; - - devlink_port = devlink_port_get_by_index(devlink, port_index); - if (!devlink_port) - return ERR_PTR(-ENODEV); - return devlink_port; - } - return ERR_PTR(-EINVAL); -} - -static struct devlink_port *devlink_port_get_from_info(struct devlink *devlink, - struct genl_info *info) -{ - return devlink_port_get_from_attrs(devlink, info->attrs); -} - -static inline bool -devlink_rate_is_leaf(struct devlink_rate *devlink_rate) -{ - return devlink_rate->type == DEVLINK_RATE_TYPE_LEAF; -} - -static inline bool -devlink_rate_is_node(struct devlink_rate *devlink_rate) -{ - return devlink_rate->type == DEVLINK_RATE_TYPE_NODE; -} - -static struct devlink_rate * -devlink_rate_leaf_get_from_info(struct devlink *devlink, struct genl_info *info) -{ - struct devlink_rate *devlink_rate; - struct devlink_port *devlink_port; - - devlink_port = devlink_port_get_from_attrs(devlink, info->attrs); - if (IS_ERR(devlink_port)) - return ERR_CAST(devlink_port); - devlink_rate = devlink_port->devlink_rate; - return devlink_rate ?: ERR_PTR(-ENODEV); -} - -static struct devlink_rate * -devlink_rate_node_get_by_name(struct devlink *devlink, const char *node_name) -{ - static struct devlink_rate *devlink_rate; - - list_for_each_entry(devlink_rate, &devlink->rate_list, list) { - if (devlink_rate_is_node(devlink_rate) && - !strcmp(node_name, devlink_rate->name)) - return devlink_rate; - } - return ERR_PTR(-ENODEV); -} - -static struct devlink_rate * -devlink_rate_node_get_from_attrs(struct devlink *devlink, struct nlattr **attrs) -{ - const char *rate_node_name; - size_t len; - - if (!attrs[DEVLINK_ATTR_RATE_NODE_NAME]) - return ERR_PTR(-EINVAL); - rate_node_name = nla_data(attrs[DEVLINK_ATTR_RATE_NODE_NAME]); - len = strlen(rate_node_name); - /* Name cannot be empty or decimal number */ - if (!len || strspn(rate_node_name, "0123456789") == len) - return ERR_PTR(-EINVAL); - - return devlink_rate_node_get_by_name(devlink, rate_node_name); -} - -static struct devlink_rate * -devlink_rate_node_get_from_info(struct devlink *devlink, struct genl_info *info) -{ - return devlink_rate_node_get_from_attrs(devlink, info->attrs); -} - -static struct devlink_rate * -devlink_rate_get_from_info(struct devlink *devlink, struct genl_info *info) -{ - struct nlattr **attrs = info->attrs; - - if (attrs[DEVLINK_ATTR_PORT_INDEX]) - return devlink_rate_leaf_get_from_info(devlink, info); - else if (attrs[DEVLINK_ATTR_RATE_NODE_NAME]) - return devlink_rate_node_get_from_info(devlink, info); - else - return ERR_PTR(-EINVAL); -} - -static struct devlink_linecard * -devlink_linecard_get_by_index(struct devlink *devlink, - unsigned int linecard_index) -{ - struct devlink_linecard *devlink_linecard; - - list_for_each_entry(devlink_linecard, &devlink->linecard_list, list) { - if (devlink_linecard->index == linecard_index) - return devlink_linecard; - } - return NULL; -} - -static bool devlink_linecard_index_exists(struct devlink *devlink, - unsigned int linecard_index) -{ - return devlink_linecard_get_by_index(devlink, linecard_index); -} - -static struct devlink_linecard * -devlink_linecard_get_from_attrs(struct devlink *devlink, struct nlattr **attrs) -{ - if (attrs[DEVLINK_ATTR_LINECARD_INDEX]) { - u32 linecard_index = nla_get_u32(attrs[DEVLINK_ATTR_LINECARD_INDEX]); - struct devlink_linecard *linecard; - - mutex_lock(&devlink->linecards_lock); - linecard = devlink_linecard_get_by_index(devlink, linecard_index); - if (linecard) - refcount_inc(&linecard->refcount); - mutex_unlock(&devlink->linecards_lock); - if (!linecard) - return ERR_PTR(-ENODEV); - return linecard; - } - return ERR_PTR(-EINVAL); -} - -static struct devlink_linecard * -devlink_linecard_get_from_info(struct devlink *devlink, struct genl_info *info) -{ - return devlink_linecard_get_from_attrs(devlink, info->attrs); -} - -static void devlink_linecard_put(struct devlink_linecard *linecard) -{ - if (refcount_dec_and_test(&linecard->refcount)) { - mutex_destroy(&linecard->state_lock); - kfree(linecard); - } -} - -struct devlink_sb { - struct list_head list; - unsigned int index; - u32 size; - u16 ingress_pools_count; - u16 egress_pools_count; - u16 ingress_tc_count; - u16 egress_tc_count; -}; - -static u16 devlink_sb_pool_count(struct devlink_sb *devlink_sb) -{ - return devlink_sb->ingress_pools_count + devlink_sb->egress_pools_count; -} - -static struct devlink_sb *devlink_sb_get_by_index(struct devlink *devlink, - unsigned int sb_index) -{ - struct devlink_sb *devlink_sb; - - list_for_each_entry(devlink_sb, &devlink->sb_list, list) { - if (devlink_sb->index == sb_index) - return devlink_sb; - } - return NULL; -} - -static bool devlink_sb_index_exists(struct devlink *devlink, - unsigned int sb_index) -{ - return devlink_sb_get_by_index(devlink, sb_index); -} - -static struct devlink_sb *devlink_sb_get_from_attrs(struct devlink *devlink, - struct nlattr **attrs) -{ - if (attrs[DEVLINK_ATTR_SB_INDEX]) { - u32 sb_index = nla_get_u32(attrs[DEVLINK_ATTR_SB_INDEX]); - struct devlink_sb *devlink_sb; - - devlink_sb = devlink_sb_get_by_index(devlink, sb_index); - if (!devlink_sb) - return ERR_PTR(-ENODEV); - return devlink_sb; - } - return ERR_PTR(-EINVAL); -} - -static struct devlink_sb *devlink_sb_get_from_info(struct devlink *devlink, - struct genl_info *info) -{ - return devlink_sb_get_from_attrs(devlink, info->attrs); -} - -static int devlink_sb_pool_index_get_from_attrs(struct devlink_sb *devlink_sb, - struct nlattr **attrs, - u16 *p_pool_index) -{ - u16 val; - - if (!attrs[DEVLINK_ATTR_SB_POOL_INDEX]) - return -EINVAL; - - val = nla_get_u16(attrs[DEVLINK_ATTR_SB_POOL_INDEX]); - if (val >= devlink_sb_pool_count(devlink_sb)) - return -EINVAL; - *p_pool_index = val; - return 0; -} - -static int devlink_sb_pool_index_get_from_info(struct devlink_sb *devlink_sb, - struct genl_info *info, - u16 *p_pool_index) -{ - return devlink_sb_pool_index_get_from_attrs(devlink_sb, info->attrs, - p_pool_index); -} - -static int -devlink_sb_pool_type_get_from_attrs(struct nlattr **attrs, - enum devlink_sb_pool_type *p_pool_type) -{ - u8 val; - - if (!attrs[DEVLINK_ATTR_SB_POOL_TYPE]) - return -EINVAL; - - val = nla_get_u8(attrs[DEVLINK_ATTR_SB_POOL_TYPE]); - if (val != DEVLINK_SB_POOL_TYPE_INGRESS && - val != DEVLINK_SB_POOL_TYPE_EGRESS) - return -EINVAL; - *p_pool_type = val; - return 0; -} - -static int -devlink_sb_pool_type_get_from_info(struct genl_info *info, - enum devlink_sb_pool_type *p_pool_type) -{ - return devlink_sb_pool_type_get_from_attrs(info->attrs, p_pool_type); -} - -static int -devlink_sb_th_type_get_from_attrs(struct nlattr **attrs, - enum devlink_sb_threshold_type *p_th_type) -{ - u8 val; - - if (!attrs[DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE]) - return -EINVAL; - - val = nla_get_u8(attrs[DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE]); - if (val != DEVLINK_SB_THRESHOLD_TYPE_STATIC && - val != DEVLINK_SB_THRESHOLD_TYPE_DYNAMIC) - return -EINVAL; - *p_th_type = val; - return 0; -} - -static int -devlink_sb_th_type_get_from_info(struct genl_info *info, - enum devlink_sb_threshold_type *p_th_type) -{ - return devlink_sb_th_type_get_from_attrs(info->attrs, p_th_type); -} - -static int -devlink_sb_tc_index_get_from_attrs(struct devlink_sb *devlink_sb, - struct nlattr **attrs, - enum devlink_sb_pool_type pool_type, - u16 *p_tc_index) -{ - u16 val; - - if (!attrs[DEVLINK_ATTR_SB_TC_INDEX]) - return -EINVAL; - - val = nla_get_u16(attrs[DEVLINK_ATTR_SB_TC_INDEX]); - if (pool_type == DEVLINK_SB_POOL_TYPE_INGRESS && - val >= devlink_sb->ingress_tc_count) - return -EINVAL; - if (pool_type == DEVLINK_SB_POOL_TYPE_EGRESS && - val >= devlink_sb->egress_tc_count) - return -EINVAL; - *p_tc_index = val; - return 0; -} - -static int -devlink_sb_tc_index_get_from_info(struct devlink_sb *devlink_sb, - struct genl_info *info, - enum devlink_sb_pool_type pool_type, - u16 *p_tc_index) -{ - return devlink_sb_tc_index_get_from_attrs(devlink_sb, info->attrs, - pool_type, p_tc_index); -} - -struct devlink_region { - struct devlink *devlink; - struct devlink_port *port; - struct list_head list; - union { - const struct devlink_region_ops *ops; - const struct devlink_port_region_ops *port_ops; - }; - struct mutex snapshot_lock; /* protects snapshot_list, - * max_snapshots and cur_snapshots - * consistency. - */ - struct list_head snapshot_list; - u32 max_snapshots; - u32 cur_snapshots; - u64 size; -}; - -struct devlink_snapshot { - struct list_head list; - struct devlink_region *region; - u8 *data; - u32 id; -}; - -static struct devlink_region * -devlink_region_get_by_name(struct devlink *devlink, const char *region_name) -{ - struct devlink_region *region; - - list_for_each_entry(region, &devlink->region_list, list) - if (!strcmp(region->ops->name, region_name)) - return region; - - return NULL; -} - -static struct devlink_region * -devlink_port_region_get_by_name(struct devlink_port *port, - const char *region_name) -{ - struct devlink_region *region; - - list_for_each_entry(region, &port->region_list, list) - if (!strcmp(region->ops->name, region_name)) - return region; - - return NULL; -} - -static struct devlink_snapshot * -devlink_region_snapshot_get_by_id(struct devlink_region *region, u32 id) -{ - struct devlink_snapshot *snapshot; - - list_for_each_entry(snapshot, &region->snapshot_list, list) - if (snapshot->id == id) - return snapshot; - - return NULL; -} - -#define DEVLINK_NL_FLAG_NEED_PORT BIT(0) -#define DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT BIT(1) -#define DEVLINK_NL_FLAG_NEED_RATE BIT(2) -#define DEVLINK_NL_FLAG_NEED_RATE_NODE BIT(3) -#define DEVLINK_NL_FLAG_NEED_LINECARD BIT(4) - -static int devlink_nl_pre_doit(const struct genl_ops *ops, - struct sk_buff *skb, struct genl_info *info) -{ - struct devlink_linecard *linecard; - struct devlink_port *devlink_port; - struct devlink *devlink; - int err; - - devlink = devlink_get_from_attrs(genl_info_net(info), info->attrs); - if (IS_ERR(devlink)) - return PTR_ERR(devlink); - devl_lock(devlink); - info->user_ptr[0] = devlink; - if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_PORT) { - devlink_port = devlink_port_get_from_info(devlink, info); - if (IS_ERR(devlink_port)) { - err = PTR_ERR(devlink_port); - goto unlock; - } - info->user_ptr[1] = devlink_port; - } else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT) { - devlink_port = devlink_port_get_from_info(devlink, info); - if (!IS_ERR(devlink_port)) - info->user_ptr[1] = devlink_port; - } else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_RATE) { - struct devlink_rate *devlink_rate; - - devlink_rate = devlink_rate_get_from_info(devlink, info); - if (IS_ERR(devlink_rate)) { - err = PTR_ERR(devlink_rate); - goto unlock; - } - info->user_ptr[1] = devlink_rate; - } else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_RATE_NODE) { - struct devlink_rate *rate_node; - - rate_node = devlink_rate_node_get_from_info(devlink, info); - if (IS_ERR(rate_node)) { - err = PTR_ERR(rate_node); - goto unlock; - } - info->user_ptr[1] = rate_node; - } else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_LINECARD) { - linecard = devlink_linecard_get_from_info(devlink, info); - if (IS_ERR(linecard)) { - err = PTR_ERR(linecard); - goto unlock; - } - info->user_ptr[1] = linecard; - } - return 0; - -unlock: - devl_unlock(devlink); - devlink_put(devlink); - return err; -} - -static void devlink_nl_post_doit(const struct genl_ops *ops, - struct sk_buff *skb, struct genl_info *info) -{ - struct devlink_linecard *linecard; - struct devlink *devlink; - - devlink = info->user_ptr[0]; - if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_LINECARD) { - linecard = info->user_ptr[1]; - devlink_linecard_put(linecard); - } - devl_unlock(devlink); - devlink_put(devlink); -} - -static struct genl_family devlink_nl_family; - -enum devlink_multicast_groups { - DEVLINK_MCGRP_CONFIG, -}; - -static const struct genl_multicast_group devlink_nl_mcgrps[] = { - [DEVLINK_MCGRP_CONFIG] = { .name = DEVLINK_GENL_MCGRP_CONFIG_NAME }, -}; - -static int devlink_nl_put_handle(struct sk_buff *msg, struct devlink *devlink) -{ - if (nla_put_string(msg, DEVLINK_ATTR_BUS_NAME, devlink->dev->bus->name)) - return -EMSGSIZE; - if (nla_put_string(msg, DEVLINK_ATTR_DEV_NAME, dev_name(devlink->dev))) - return -EMSGSIZE; - return 0; -} - -static int devlink_nl_put_nested_handle(struct sk_buff *msg, struct devlink *devlink) -{ - struct nlattr *nested_attr; - - nested_attr = nla_nest_start(msg, DEVLINK_ATTR_NESTED_DEVLINK); - if (!nested_attr) - return -EMSGSIZE; - if (devlink_nl_put_handle(msg, devlink)) - goto nla_put_failure; - - nla_nest_end(msg, nested_attr); - return 0; - -nla_put_failure: - nla_nest_cancel(msg, nested_attr); - return -EMSGSIZE; -} - -struct devlink_reload_combination { - enum devlink_reload_action action; - enum devlink_reload_limit limit; -}; - -static const struct devlink_reload_combination devlink_reload_invalid_combinations[] = { - { - /* can't reinitialize driver with no down time */ - .action = DEVLINK_RELOAD_ACTION_DRIVER_REINIT, - .limit = DEVLINK_RELOAD_LIMIT_NO_RESET, - }, -}; - -static bool -devlink_reload_combination_is_invalid(enum devlink_reload_action action, - enum devlink_reload_limit limit) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(devlink_reload_invalid_combinations); i++) - if (devlink_reload_invalid_combinations[i].action == action && - devlink_reload_invalid_combinations[i].limit == limit) - return true; - return false; -} - -static bool -devlink_reload_action_is_supported(struct devlink *devlink, enum devlink_reload_action action) -{ - return test_bit(action, &devlink->ops->reload_actions); -} - -static bool -devlink_reload_limit_is_supported(struct devlink *devlink, enum devlink_reload_limit limit) -{ - return test_bit(limit, &devlink->ops->reload_limits); -} - -static int devlink_reload_stat_put(struct sk_buff *msg, - enum devlink_reload_limit limit, u32 value) -{ - struct nlattr *reload_stats_entry; - - reload_stats_entry = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_STATS_ENTRY); - if (!reload_stats_entry) - return -EMSGSIZE; - - if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_STATS_LIMIT, limit) || - nla_put_u32(msg, DEVLINK_ATTR_RELOAD_STATS_VALUE, value)) - goto nla_put_failure; - nla_nest_end(msg, reload_stats_entry); - return 0; - -nla_put_failure: - nla_nest_cancel(msg, reload_stats_entry); - return -EMSGSIZE; -} - -static int devlink_reload_stats_put(struct sk_buff *msg, struct devlink *devlink, bool is_remote) -{ - struct nlattr *reload_stats_attr, *act_info, *act_stats; - int i, j, stat_idx; - u32 value; - - if (!is_remote) - reload_stats_attr = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_STATS); - else - reload_stats_attr = nla_nest_start(msg, DEVLINK_ATTR_REMOTE_RELOAD_STATS); - - if (!reload_stats_attr) - return -EMSGSIZE; - - for (i = 0; i <= DEVLINK_RELOAD_ACTION_MAX; i++) { - if ((!is_remote && - !devlink_reload_action_is_supported(devlink, i)) || - i == DEVLINK_RELOAD_ACTION_UNSPEC) - continue; - act_info = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_ACTION_INFO); - if (!act_info) - goto nla_put_failure; - - if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_ACTION, i)) - goto action_info_nest_cancel; - act_stats = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_ACTION_STATS); - if (!act_stats) - goto action_info_nest_cancel; - - for (j = 0; j <= DEVLINK_RELOAD_LIMIT_MAX; j++) { - /* Remote stats are shown even if not locally supported. - * Stats of actions with unspecified limit are shown - * though drivers don't need to register unspecified - * limit. - */ - if ((!is_remote && j != DEVLINK_RELOAD_LIMIT_UNSPEC && - !devlink_reload_limit_is_supported(devlink, j)) || - devlink_reload_combination_is_invalid(i, j)) - continue; - - stat_idx = j * __DEVLINK_RELOAD_ACTION_MAX + i; - if (!is_remote) - value = devlink->stats.reload_stats[stat_idx]; - else - value = devlink->stats.remote_reload_stats[stat_idx]; - if (devlink_reload_stat_put(msg, j, value)) - goto action_stats_nest_cancel; - } - nla_nest_end(msg, act_stats); - nla_nest_end(msg, act_info); - } - nla_nest_end(msg, reload_stats_attr); - return 0; - -action_stats_nest_cancel: - nla_nest_cancel(msg, act_stats); -action_info_nest_cancel: - nla_nest_cancel(msg, act_info); -nla_put_failure: - nla_nest_cancel(msg, reload_stats_attr); - return -EMSGSIZE; -} - -static int devlink_nl_fill(struct sk_buff *msg, struct devlink *devlink, - enum devlink_command cmd, u32 portid, - u32 seq, int flags) -{ - struct nlattr *dev_stats; - void *hdr; - - hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); - if (!hdr) - return -EMSGSIZE; - - if (devlink_nl_put_handle(msg, devlink)) - goto nla_put_failure; - if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_FAILED, devlink->reload_failed)) - goto nla_put_failure; - - dev_stats = nla_nest_start(msg, DEVLINK_ATTR_DEV_STATS); - if (!dev_stats) - goto nla_put_failure; - - if (devlink_reload_stats_put(msg, devlink, false)) - goto dev_stats_nest_cancel; - if (devlink_reload_stats_put(msg, devlink, true)) - goto dev_stats_nest_cancel; - - nla_nest_end(msg, dev_stats); - genlmsg_end(msg, hdr); - return 0; - -dev_stats_nest_cancel: - nla_nest_cancel(msg, dev_stats); -nla_put_failure: - genlmsg_cancel(msg, hdr); - return -EMSGSIZE; -} - -static void devlink_notify(struct devlink *devlink, enum devlink_command cmd) -{ - struct sk_buff *msg; - int err; - - WARN_ON(cmd != DEVLINK_CMD_NEW && cmd != DEVLINK_CMD_DEL); - WARN_ON(!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)); - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return; - - err = devlink_nl_fill(msg, devlink, cmd, 0, 0, 0); - if (err) { - nlmsg_free(msg); - return; - } - - genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), - msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); -} - -static int devlink_nl_port_attrs_put(struct sk_buff *msg, - struct devlink_port *devlink_port) -{ - struct devlink_port_attrs *attrs = &devlink_port->attrs; - - if (!devlink_port->attrs_set) - return 0; - if (attrs->lanes) { - if (nla_put_u32(msg, DEVLINK_ATTR_PORT_LANES, attrs->lanes)) - return -EMSGSIZE; - } - if (nla_put_u8(msg, DEVLINK_ATTR_PORT_SPLITTABLE, attrs->splittable)) - return -EMSGSIZE; - if (nla_put_u16(msg, DEVLINK_ATTR_PORT_FLAVOUR, attrs->flavour)) - return -EMSGSIZE; - switch (devlink_port->attrs.flavour) { - case DEVLINK_PORT_FLAVOUR_PCI_PF: - if (nla_put_u32(msg, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER, - attrs->pci_pf.controller) || - nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, attrs->pci_pf.pf)) - return -EMSGSIZE; - if (nla_put_u8(msg, DEVLINK_ATTR_PORT_EXTERNAL, attrs->pci_pf.external)) - return -EMSGSIZE; - break; - case DEVLINK_PORT_FLAVOUR_PCI_VF: - if (nla_put_u32(msg, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER, - attrs->pci_vf.controller) || - nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, attrs->pci_vf.pf) || - nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_VF_NUMBER, attrs->pci_vf.vf)) - return -EMSGSIZE; - if (nla_put_u8(msg, DEVLINK_ATTR_PORT_EXTERNAL, attrs->pci_vf.external)) - return -EMSGSIZE; - break; - case DEVLINK_PORT_FLAVOUR_PCI_SF: - if (nla_put_u32(msg, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER, - attrs->pci_sf.controller) || - nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, - attrs->pci_sf.pf) || - nla_put_u32(msg, DEVLINK_ATTR_PORT_PCI_SF_NUMBER, - attrs->pci_sf.sf)) - return -EMSGSIZE; - break; - case DEVLINK_PORT_FLAVOUR_PHYSICAL: - case DEVLINK_PORT_FLAVOUR_CPU: - case DEVLINK_PORT_FLAVOUR_DSA: - if (nla_put_u32(msg, DEVLINK_ATTR_PORT_NUMBER, - attrs->phys.port_number)) - return -EMSGSIZE; - if (!attrs->split) - return 0; - if (nla_put_u32(msg, DEVLINK_ATTR_PORT_SPLIT_GROUP, - attrs->phys.port_number)) - return -EMSGSIZE; - if (nla_put_u32(msg, DEVLINK_ATTR_PORT_SPLIT_SUBPORT_NUMBER, - attrs->phys.split_subport_number)) - return -EMSGSIZE; - break; - default: - break; - } - return 0; -} - -static int devlink_port_fn_hw_addr_fill(const struct devlink_ops *ops, - struct devlink_port *port, - struct sk_buff *msg, - struct netlink_ext_ack *extack, - bool *msg_updated) -{ - u8 hw_addr[MAX_ADDR_LEN]; - int hw_addr_len; - int err; - - if (!ops->port_function_hw_addr_get) - return 0; - - err = ops->port_function_hw_addr_get(port, hw_addr, &hw_addr_len, - extack); - if (err) { - if (err == -EOPNOTSUPP) - return 0; - return err; - } - err = nla_put(msg, DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR, hw_addr_len, hw_addr); - if (err) - return err; - *msg_updated = true; - return 0; -} - -static int devlink_nl_rate_fill(struct sk_buff *msg, - struct devlink_rate *devlink_rate, - enum devlink_command cmd, u32 portid, u32 seq, - int flags, struct netlink_ext_ack *extack) -{ - struct devlink *devlink = devlink_rate->devlink; - void *hdr; - - hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); - if (!hdr) - return -EMSGSIZE; - - if (devlink_nl_put_handle(msg, devlink)) - goto nla_put_failure; - - if (nla_put_u16(msg, DEVLINK_ATTR_RATE_TYPE, devlink_rate->type)) - goto nla_put_failure; - - if (devlink_rate_is_leaf(devlink_rate)) { - if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, - devlink_rate->devlink_port->index)) - goto nla_put_failure; - } else if (devlink_rate_is_node(devlink_rate)) { - if (nla_put_string(msg, DEVLINK_ATTR_RATE_NODE_NAME, - devlink_rate->name)) - goto nla_put_failure; - } - - if (nla_put_u64_64bit(msg, DEVLINK_ATTR_RATE_TX_SHARE, - devlink_rate->tx_share, DEVLINK_ATTR_PAD)) - goto nla_put_failure; - - if (nla_put_u64_64bit(msg, DEVLINK_ATTR_RATE_TX_MAX, - devlink_rate->tx_max, DEVLINK_ATTR_PAD)) - goto nla_put_failure; - - if (devlink_rate->parent) - if (nla_put_string(msg, DEVLINK_ATTR_RATE_PARENT_NODE_NAME, - devlink_rate->parent->name)) - goto nla_put_failure; - - genlmsg_end(msg, hdr); - return 0; - -nla_put_failure: - genlmsg_cancel(msg, hdr); - return -EMSGSIZE; -} - -static bool -devlink_port_fn_state_valid(enum devlink_port_fn_state state) -{ - return state == DEVLINK_PORT_FN_STATE_INACTIVE || - state == DEVLINK_PORT_FN_STATE_ACTIVE; -} - -static bool -devlink_port_fn_opstate_valid(enum devlink_port_fn_opstate opstate) -{ - return opstate == DEVLINK_PORT_FN_OPSTATE_DETACHED || - opstate == DEVLINK_PORT_FN_OPSTATE_ATTACHED; -} - -static int devlink_port_fn_state_fill(const struct devlink_ops *ops, - struct devlink_port *port, - struct sk_buff *msg, - struct netlink_ext_ack *extack, - bool *msg_updated) -{ - enum devlink_port_fn_opstate opstate; - enum devlink_port_fn_state state; - int err; - - if (!ops->port_fn_state_get) - return 0; - - err = ops->port_fn_state_get(port, &state, &opstate, extack); - if (err) { - if (err == -EOPNOTSUPP) - return 0; - return err; - } - if (!devlink_port_fn_state_valid(state)) { - WARN_ON_ONCE(1); - NL_SET_ERR_MSG_MOD(extack, "Invalid state read from driver"); - return -EINVAL; - } - if (!devlink_port_fn_opstate_valid(opstate)) { - WARN_ON_ONCE(1); - NL_SET_ERR_MSG_MOD(extack, - "Invalid operational state read from driver"); - return -EINVAL; - } - if (nla_put_u8(msg, DEVLINK_PORT_FN_ATTR_STATE, state) || - nla_put_u8(msg, DEVLINK_PORT_FN_ATTR_OPSTATE, opstate)) - return -EMSGSIZE; - *msg_updated = true; - return 0; -} - -static int -devlink_nl_port_function_attrs_put(struct sk_buff *msg, struct devlink_port *port, - struct netlink_ext_ack *extack) -{ - const struct devlink_ops *ops; - struct nlattr *function_attr; - bool msg_updated = false; - int err; - - function_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_PORT_FUNCTION); - if (!function_attr) - return -EMSGSIZE; - - ops = port->devlink->ops; - err = devlink_port_fn_hw_addr_fill(ops, port, msg, extack, - &msg_updated); - if (err) - goto out; - err = devlink_port_fn_state_fill(ops, port, msg, extack, &msg_updated); -out: - if (err || !msg_updated) - nla_nest_cancel(msg, function_attr); - else - nla_nest_end(msg, function_attr); - return err; -} - -static int devlink_nl_port_fill(struct sk_buff *msg, - struct devlink_port *devlink_port, - enum devlink_command cmd, u32 portid, u32 seq, - int flags, struct netlink_ext_ack *extack) -{ - struct devlink *devlink = devlink_port->devlink; - void *hdr; - - hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); - if (!hdr) - return -EMSGSIZE; - - if (devlink_nl_put_handle(msg, devlink)) - goto nla_put_failure; - if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index)) - goto nla_put_failure; - - /* Hold rtnl lock while accessing port's netdev attributes. */ - rtnl_lock(); - spin_lock_bh(&devlink_port->type_lock); - if (nla_put_u16(msg, DEVLINK_ATTR_PORT_TYPE, devlink_port->type)) - goto nla_put_failure_type_locked; - if (devlink_port->desired_type != DEVLINK_PORT_TYPE_NOTSET && - nla_put_u16(msg, DEVLINK_ATTR_PORT_DESIRED_TYPE, - devlink_port->desired_type)) - goto nla_put_failure_type_locked; - if (devlink_port->type == DEVLINK_PORT_TYPE_ETH) { - struct net *net = devlink_net(devlink_port->devlink); - struct net_device *netdev = devlink_port->type_dev; - - if (netdev && net_eq(net, dev_net(netdev)) && - (nla_put_u32(msg, DEVLINK_ATTR_PORT_NETDEV_IFINDEX, - netdev->ifindex) || - nla_put_string(msg, DEVLINK_ATTR_PORT_NETDEV_NAME, - netdev->name))) - goto nla_put_failure_type_locked; - } - if (devlink_port->type == DEVLINK_PORT_TYPE_IB) { - struct ib_device *ibdev = devlink_port->type_dev; - - if (ibdev && - nla_put_string(msg, DEVLINK_ATTR_PORT_IBDEV_NAME, - ibdev->name)) - goto nla_put_failure_type_locked; - } - spin_unlock_bh(&devlink_port->type_lock); - rtnl_unlock(); - if (devlink_nl_port_attrs_put(msg, devlink_port)) - goto nla_put_failure; - if (devlink_nl_port_function_attrs_put(msg, devlink_port, extack)) - goto nla_put_failure; - if (devlink_port->linecard && - nla_put_u32(msg, DEVLINK_ATTR_LINECARD_INDEX, - devlink_port->linecard->index)) - goto nla_put_failure; - - genlmsg_end(msg, hdr); - return 0; - -nla_put_failure_type_locked: - spin_unlock_bh(&devlink_port->type_lock); - rtnl_unlock(); -nla_put_failure: - genlmsg_cancel(msg, hdr); - return -EMSGSIZE; -} - -static void devlink_port_notify(struct devlink_port *devlink_port, - enum devlink_command cmd) -{ - struct devlink *devlink = devlink_port->devlink; - struct sk_buff *msg; - int err; - - WARN_ON(cmd != DEVLINK_CMD_PORT_NEW && cmd != DEVLINK_CMD_PORT_DEL); - - if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)) - return; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return; - - err = devlink_nl_port_fill(msg, devlink_port, cmd, 0, 0, 0, NULL); - if (err) { - nlmsg_free(msg); - return; - } - - genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), msg, - 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); -} - -static void devlink_rate_notify(struct devlink_rate *devlink_rate, - enum devlink_command cmd) -{ - struct devlink *devlink = devlink_rate->devlink; - struct sk_buff *msg; - int err; - - WARN_ON(cmd != DEVLINK_CMD_RATE_NEW && cmd != DEVLINK_CMD_RATE_DEL); - - if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)) - return; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return; - - err = devlink_nl_rate_fill(msg, devlink_rate, cmd, 0, 0, 0, NULL); - if (err) { - nlmsg_free(msg); - return; - } - - genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), msg, - 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); -} - -static int devlink_nl_cmd_rate_get_dumpit(struct sk_buff *msg, - struct netlink_callback *cb) -{ - struct devlink_rate *devlink_rate; - struct devlink *devlink; - int start = cb->args[0]; - unsigned long index; - int idx = 0; - int err = 0; - - devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { - devl_lock(devlink); - list_for_each_entry(devlink_rate, &devlink->rate_list, list) { - enum devlink_command cmd = DEVLINK_CMD_RATE_NEW; - u32 id = NETLINK_CB(cb->skb).portid; - - if (idx < start) { - idx++; - continue; - } - err = devlink_nl_rate_fill(msg, devlink_rate, cmd, id, - cb->nlh->nlmsg_seq, - NLM_F_MULTI, NULL); - if (err) { - devl_unlock(devlink); - devlink_put(devlink); - goto out; - } - idx++; - } - devl_unlock(devlink); - devlink_put(devlink); - } -out: - if (err != -EMSGSIZE) - return err; - - cb->args[0] = idx; - return msg->len; -} - -static int devlink_nl_cmd_rate_get_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink_rate *devlink_rate = info->user_ptr[1]; - struct sk_buff *msg; - int err; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOMEM; - - err = devlink_nl_rate_fill(msg, devlink_rate, DEVLINK_CMD_RATE_NEW, - info->snd_portid, info->snd_seq, 0, - info->extack); - if (err) { - nlmsg_free(msg); - return err; - } - - return genlmsg_reply(msg, info); -} - -static bool -devlink_rate_is_parent_node(struct devlink_rate *devlink_rate, - struct devlink_rate *parent) -{ - while (parent) { - if (parent == devlink_rate) - return true; - parent = parent->parent; - } - return false; -} - -static int devlink_nl_cmd_get_doit(struct sk_buff *skb, struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - struct sk_buff *msg; - int err; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOMEM; - - err = devlink_nl_fill(msg, devlink, DEVLINK_CMD_NEW, - info->snd_portid, info->snd_seq, 0); - if (err) { - nlmsg_free(msg); - return err; - } - - return genlmsg_reply(msg, info); -} - -static int devlink_nl_cmd_get_dumpit(struct sk_buff *msg, - struct netlink_callback *cb) -{ - struct devlink *devlink; - int start = cb->args[0]; - unsigned long index; - int idx = 0; - int err; - - devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { - if (idx < start) { - idx++; - devlink_put(devlink); - continue; - } - - devl_lock(devlink); - err = devlink_nl_fill(msg, devlink, DEVLINK_CMD_NEW, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI); - devl_unlock(devlink); - devlink_put(devlink); - - if (err) - goto out; - idx++; - } -out: - cb->args[0] = idx; - return msg->len; -} - -static int devlink_nl_cmd_port_get_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink_port *devlink_port = info->user_ptr[1]; - struct sk_buff *msg; - int err; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOMEM; - - err = devlink_nl_port_fill(msg, devlink_port, DEVLINK_CMD_PORT_NEW, - info->snd_portid, info->snd_seq, 0, - info->extack); - if (err) { - nlmsg_free(msg); - return err; - } - - return genlmsg_reply(msg, info); -} - -static int devlink_nl_cmd_port_get_dumpit(struct sk_buff *msg, - struct netlink_callback *cb) -{ - struct devlink *devlink; - struct devlink_port *devlink_port; - int start = cb->args[0]; - unsigned long index; - int idx = 0; - int err; - - devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { - devl_lock(devlink); - list_for_each_entry(devlink_port, &devlink->port_list, list) { - if (idx < start) { - idx++; - continue; - } - err = devlink_nl_port_fill(msg, devlink_port, - DEVLINK_CMD_NEW, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - NLM_F_MULTI, cb->extack); - if (err) { - devl_unlock(devlink); - devlink_put(devlink); - goto out; - } - idx++; - } - devl_unlock(devlink); - devlink_put(devlink); - } -out: - cb->args[0] = idx; - return msg->len; -} - -static int devlink_port_type_set(struct devlink_port *devlink_port, - enum devlink_port_type port_type) - -{ - int err; - - if (!devlink_port->devlink->ops->port_type_set) - return -EOPNOTSUPP; - - if (port_type == devlink_port->type) - return 0; - - err = devlink_port->devlink->ops->port_type_set(devlink_port, - port_type); - if (err) - return err; - - devlink_port->desired_type = port_type; - devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); - return 0; -} - -static int devlink_port_function_hw_addr_set(struct devlink_port *port, - const struct nlattr *attr, - struct netlink_ext_ack *extack) -{ - const struct devlink_ops *ops = port->devlink->ops; - const u8 *hw_addr; - int hw_addr_len; - - hw_addr = nla_data(attr); - hw_addr_len = nla_len(attr); - if (hw_addr_len > MAX_ADDR_LEN) { - NL_SET_ERR_MSG_MOD(extack, "Port function hardware address too long"); - return -EINVAL; - } - if (port->type == DEVLINK_PORT_TYPE_ETH) { - if (hw_addr_len != ETH_ALEN) { - NL_SET_ERR_MSG_MOD(extack, "Address must be 6 bytes for Ethernet device"); - return -EINVAL; - } - if (!is_unicast_ether_addr(hw_addr)) { - NL_SET_ERR_MSG_MOD(extack, "Non-unicast hardware address unsupported"); - return -EINVAL; - } - } - - if (!ops->port_function_hw_addr_set) { - NL_SET_ERR_MSG_MOD(extack, "Port doesn't support function attributes"); - return -EOPNOTSUPP; - } - - return ops->port_function_hw_addr_set(port, hw_addr, hw_addr_len, - extack); -} - -static int devlink_port_fn_state_set(struct devlink_port *port, - const struct nlattr *attr, - struct netlink_ext_ack *extack) -{ - enum devlink_port_fn_state state; - const struct devlink_ops *ops; - - state = nla_get_u8(attr); - ops = port->devlink->ops; - if (!ops->port_fn_state_set) { - NL_SET_ERR_MSG_MOD(extack, - "Function does not support state setting"); - return -EOPNOTSUPP; - } - return ops->port_fn_state_set(port, state, extack); -} - -static int devlink_port_function_set(struct devlink_port *port, - const struct nlattr *attr, - struct netlink_ext_ack *extack) -{ - struct nlattr *tb[DEVLINK_PORT_FUNCTION_ATTR_MAX + 1]; - int err; - - err = nla_parse_nested(tb, DEVLINK_PORT_FUNCTION_ATTR_MAX, attr, - devlink_function_nl_policy, extack); - if (err < 0) { - NL_SET_ERR_MSG_MOD(extack, "Fail to parse port function attributes"); - return err; - } - - attr = tb[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR]; - if (attr) { - err = devlink_port_function_hw_addr_set(port, attr, extack); - if (err) - return err; - } - /* Keep this as the last function attribute set, so that when - * multiple port function attributes are set along with state, - * Those can be applied first before activating the state. - */ - attr = tb[DEVLINK_PORT_FN_ATTR_STATE]; - if (attr) - err = devlink_port_fn_state_set(port, attr, extack); - - if (!err) - devlink_port_notify(port, DEVLINK_CMD_PORT_NEW); - return err; -} - -static int devlink_nl_cmd_port_set_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink_port *devlink_port = info->user_ptr[1]; - int err; - - if (info->attrs[DEVLINK_ATTR_PORT_TYPE]) { - enum devlink_port_type port_type; - - port_type = nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_TYPE]); - err = devlink_port_type_set(devlink_port, port_type); - if (err) - return err; - } - - if (info->attrs[DEVLINK_ATTR_PORT_FUNCTION]) { - struct nlattr *attr = info->attrs[DEVLINK_ATTR_PORT_FUNCTION]; - struct netlink_ext_ack *extack = info->extack; - - err = devlink_port_function_set(devlink_port, attr, extack); - if (err) - return err; - } - - return 0; -} - -static int devlink_nl_cmd_port_split_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink_port *devlink_port = info->user_ptr[1]; - struct devlink *devlink = info->user_ptr[0]; - u32 count; - - if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_PORT_SPLIT_COUNT)) - return -EINVAL; - if (!devlink->ops->port_split) - return -EOPNOTSUPP; - - count = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_SPLIT_COUNT]); - - if (!devlink_port->attrs.splittable) { - /* Split ports cannot be split. */ - if (devlink_port->attrs.split) - NL_SET_ERR_MSG_MOD(info->extack, "Port cannot be split further"); - else - NL_SET_ERR_MSG_MOD(info->extack, "Port cannot be split"); - return -EINVAL; - } - - if (count < 2 || !is_power_of_2(count) || count > devlink_port->attrs.lanes) { - NL_SET_ERR_MSG_MOD(info->extack, "Invalid split count"); - return -EINVAL; - } - - return devlink->ops->port_split(devlink, devlink_port, count, - info->extack); -} - -static int devlink_nl_cmd_port_unsplit_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink_port *devlink_port = info->user_ptr[1]; - struct devlink *devlink = info->user_ptr[0]; - - if (!devlink->ops->port_unsplit) - return -EOPNOTSUPP; - return devlink->ops->port_unsplit(devlink, devlink_port, info->extack); -} - -static int devlink_port_new_notify(struct devlink *devlink, - unsigned int port_index, - struct genl_info *info) -{ - struct devlink_port *devlink_port; - struct sk_buff *msg; - int err; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOMEM; - - lockdep_assert_held(&devlink->lock); - devlink_port = devlink_port_get_by_index(devlink, port_index); - if (!devlink_port) { - err = -ENODEV; - goto out; - } - - err = devlink_nl_port_fill(msg, devlink_port, DEVLINK_CMD_NEW, - info->snd_portid, info->snd_seq, 0, NULL); - if (err) - goto out; - - return genlmsg_reply(msg, info); - -out: - nlmsg_free(msg); - return err; -} - -static int devlink_nl_cmd_port_new_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct netlink_ext_ack *extack = info->extack; - struct devlink_port_new_attrs new_attrs = {}; - struct devlink *devlink = info->user_ptr[0]; - unsigned int new_port_index; - int err; - - if (!devlink->ops->port_new || !devlink->ops->port_del) - return -EOPNOTSUPP; - - if (!info->attrs[DEVLINK_ATTR_PORT_FLAVOUR] || - !info->attrs[DEVLINK_ATTR_PORT_PCI_PF_NUMBER]) { - NL_SET_ERR_MSG_MOD(extack, "Port flavour or PCI PF are not specified"); - return -EINVAL; - } - new_attrs.flavour = nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_FLAVOUR]); - new_attrs.pfnum = - nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_PCI_PF_NUMBER]); - - if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) { - /* Port index of the new port being created by driver. */ - new_attrs.port_index = - nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); - new_attrs.port_index_valid = true; - } - if (info->attrs[DEVLINK_ATTR_PORT_CONTROLLER_NUMBER]) { - new_attrs.controller = - nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_CONTROLLER_NUMBER]); - new_attrs.controller_valid = true; - } - if (new_attrs.flavour == DEVLINK_PORT_FLAVOUR_PCI_SF && - info->attrs[DEVLINK_ATTR_PORT_PCI_SF_NUMBER]) { - new_attrs.sfnum = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_PCI_SF_NUMBER]); - new_attrs.sfnum_valid = true; - } - - err = devlink->ops->port_new(devlink, &new_attrs, extack, - &new_port_index); - if (err) - return err; - - err = devlink_port_new_notify(devlink, new_port_index, info); - if (err && err != -ENODEV) { - /* Fail to send the response; destroy newly created port. */ - devlink->ops->port_del(devlink, new_port_index, extack); - } - return err; -} - -static int devlink_nl_cmd_port_del_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct netlink_ext_ack *extack = info->extack; - struct devlink *devlink = info->user_ptr[0]; - unsigned int port_index; - - if (!devlink->ops->port_del) - return -EOPNOTSUPP; - - if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_PORT_INDEX)) { - NL_SET_ERR_MSG_MOD(extack, "Port index is not specified"); - return -EINVAL; - } - port_index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); - - return devlink->ops->port_del(devlink, port_index, extack); -} - -static int -devlink_nl_rate_parent_node_set(struct devlink_rate *devlink_rate, - struct genl_info *info, - struct nlattr *nla_parent) -{ - struct devlink *devlink = devlink_rate->devlink; - const char *parent_name = nla_data(nla_parent); - const struct devlink_ops *ops = devlink->ops; - size_t len = strlen(parent_name); - struct devlink_rate *parent; - int err = -EOPNOTSUPP; - - parent = devlink_rate->parent; - if (parent && len) { - NL_SET_ERR_MSG_MOD(info->extack, "Rate object already has parent."); - return -EBUSY; - } else if (parent && !len) { - if (devlink_rate_is_leaf(devlink_rate)) - err = ops->rate_leaf_parent_set(devlink_rate, NULL, - devlink_rate->priv, NULL, - info->extack); - else if (devlink_rate_is_node(devlink_rate)) - err = ops->rate_node_parent_set(devlink_rate, NULL, - devlink_rate->priv, NULL, - info->extack); - if (err) - return err; - - refcount_dec(&parent->refcnt); - devlink_rate->parent = NULL; - } else if (!parent && len) { - parent = devlink_rate_node_get_by_name(devlink, parent_name); - if (IS_ERR(parent)) - return -ENODEV; - - if (parent == devlink_rate) { - NL_SET_ERR_MSG_MOD(info->extack, "Parent to self is not allowed"); - return -EINVAL; - } - - if (devlink_rate_is_node(devlink_rate) && - devlink_rate_is_parent_node(devlink_rate, parent->parent)) { - NL_SET_ERR_MSG_MOD(info->extack, "Node is already a parent of parent node."); - return -EEXIST; - } - - if (devlink_rate_is_leaf(devlink_rate)) - err = ops->rate_leaf_parent_set(devlink_rate, parent, - devlink_rate->priv, parent->priv, - info->extack); - else if (devlink_rate_is_node(devlink_rate)) - err = ops->rate_node_parent_set(devlink_rate, parent, - devlink_rate->priv, parent->priv, - info->extack); - if (err) - return err; - - refcount_inc(&parent->refcnt); - devlink_rate->parent = parent; - } - - return 0; -} - -static int devlink_nl_rate_set(struct devlink_rate *devlink_rate, - const struct devlink_ops *ops, - struct genl_info *info) -{ - struct nlattr *nla_parent, **attrs = info->attrs; - int err = -EOPNOTSUPP; - u64 rate; - - if (attrs[DEVLINK_ATTR_RATE_TX_SHARE]) { - rate = nla_get_u64(attrs[DEVLINK_ATTR_RATE_TX_SHARE]); - if (devlink_rate_is_leaf(devlink_rate)) - err = ops->rate_leaf_tx_share_set(devlink_rate, devlink_rate->priv, - rate, info->extack); - else if (devlink_rate_is_node(devlink_rate)) - err = ops->rate_node_tx_share_set(devlink_rate, devlink_rate->priv, - rate, info->extack); - if (err) - return err; - devlink_rate->tx_share = rate; - } - - if (attrs[DEVLINK_ATTR_RATE_TX_MAX]) { - rate = nla_get_u64(attrs[DEVLINK_ATTR_RATE_TX_MAX]); - if (devlink_rate_is_leaf(devlink_rate)) - err = ops->rate_leaf_tx_max_set(devlink_rate, devlink_rate->priv, - rate, info->extack); - else if (devlink_rate_is_node(devlink_rate)) - err = ops->rate_node_tx_max_set(devlink_rate, devlink_rate->priv, - rate, info->extack); - if (err) - return err; - devlink_rate->tx_max = rate; - } - - nla_parent = attrs[DEVLINK_ATTR_RATE_PARENT_NODE_NAME]; - if (nla_parent) { - err = devlink_nl_rate_parent_node_set(devlink_rate, info, - nla_parent); - if (err) - return err; - } - - return 0; -} - -static bool devlink_rate_set_ops_supported(const struct devlink_ops *ops, - struct genl_info *info, - enum devlink_rate_type type) -{ - struct nlattr **attrs = info->attrs; - - if (type == DEVLINK_RATE_TYPE_LEAF) { - if (attrs[DEVLINK_ATTR_RATE_TX_SHARE] && !ops->rate_leaf_tx_share_set) { - NL_SET_ERR_MSG_MOD(info->extack, "TX share set isn't supported for the leafs"); - return false; - } - if (attrs[DEVLINK_ATTR_RATE_TX_MAX] && !ops->rate_leaf_tx_max_set) { - NL_SET_ERR_MSG_MOD(info->extack, "TX max set isn't supported for the leafs"); - return false; - } - if (attrs[DEVLINK_ATTR_RATE_PARENT_NODE_NAME] && - !ops->rate_leaf_parent_set) { - NL_SET_ERR_MSG_MOD(info->extack, "Parent set isn't supported for the leafs"); - return false; - } - } else if (type == DEVLINK_RATE_TYPE_NODE) { - if (attrs[DEVLINK_ATTR_RATE_TX_SHARE] && !ops->rate_node_tx_share_set) { - NL_SET_ERR_MSG_MOD(info->extack, "TX share set isn't supported for the nodes"); - return false; - } - if (attrs[DEVLINK_ATTR_RATE_TX_MAX] && !ops->rate_node_tx_max_set) { - NL_SET_ERR_MSG_MOD(info->extack, "TX max set isn't supported for the nodes"); - return false; - } - if (attrs[DEVLINK_ATTR_RATE_PARENT_NODE_NAME] && - !ops->rate_node_parent_set) { - NL_SET_ERR_MSG_MOD(info->extack, "Parent set isn't supported for the nodes"); - return false; - } - } else { - WARN(1, "Unknown type of rate object"); - return false; - } - - return true; -} - -static int devlink_nl_cmd_rate_set_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink_rate *devlink_rate = info->user_ptr[1]; - struct devlink *devlink = devlink_rate->devlink; - const struct devlink_ops *ops = devlink->ops; - int err; - - if (!ops || !devlink_rate_set_ops_supported(ops, info, devlink_rate->type)) - return -EOPNOTSUPP; - - err = devlink_nl_rate_set(devlink_rate, ops, info); - - if (!err) - devlink_rate_notify(devlink_rate, DEVLINK_CMD_RATE_NEW); - return err; -} - -static int devlink_nl_cmd_rate_new_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - struct devlink_rate *rate_node; - const struct devlink_ops *ops; - int err; - - ops = devlink->ops; - if (!ops || !ops->rate_node_new || !ops->rate_node_del) { - NL_SET_ERR_MSG_MOD(info->extack, "Rate nodes aren't supported"); - return -EOPNOTSUPP; - } - - if (!devlink_rate_set_ops_supported(ops, info, DEVLINK_RATE_TYPE_NODE)) - return -EOPNOTSUPP; - - rate_node = devlink_rate_node_get_from_attrs(devlink, info->attrs); - if (!IS_ERR(rate_node)) - return -EEXIST; - else if (rate_node == ERR_PTR(-EINVAL)) - return -EINVAL; - - rate_node = kzalloc(sizeof(*rate_node), GFP_KERNEL); - if (!rate_node) - return -ENOMEM; - - rate_node->devlink = devlink; - rate_node->type = DEVLINK_RATE_TYPE_NODE; - rate_node->name = nla_strdup(info->attrs[DEVLINK_ATTR_RATE_NODE_NAME], GFP_KERNEL); - if (!rate_node->name) { - err = -ENOMEM; - goto err_strdup; - } - - err = ops->rate_node_new(rate_node, &rate_node->priv, info->extack); - if (err) - goto err_node_new; - - err = devlink_nl_rate_set(rate_node, ops, info); - if (err) - goto err_rate_set; - - refcount_set(&rate_node->refcnt, 1); - list_add(&rate_node->list, &devlink->rate_list); - devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_NEW); - return 0; - -err_rate_set: - ops->rate_node_del(rate_node, rate_node->priv, info->extack); -err_node_new: - kfree(rate_node->name); -err_strdup: - kfree(rate_node); - return err; -} - -static int devlink_nl_cmd_rate_del_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink_rate *rate_node = info->user_ptr[1]; - struct devlink *devlink = rate_node->devlink; - const struct devlink_ops *ops = devlink->ops; - int err; - - if (refcount_read(&rate_node->refcnt) > 1) { - NL_SET_ERR_MSG_MOD(info->extack, "Node has children. Cannot delete node."); - return -EBUSY; - } - - devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_DEL); - err = ops->rate_node_del(rate_node, rate_node->priv, info->extack); - if (rate_node->parent) - refcount_dec(&rate_node->parent->refcnt); - list_del(&rate_node->list); - kfree(rate_node->name); - kfree(rate_node); - return err; -} - -struct devlink_linecard_type { - const char *type; - const void *priv; -}; - -static int devlink_nl_linecard_fill(struct sk_buff *msg, - struct devlink *devlink, - struct devlink_linecard *linecard, - enum devlink_command cmd, u32 portid, - u32 seq, int flags, - struct netlink_ext_ack *extack) -{ - struct devlink_linecard_type *linecard_type; - struct nlattr *attr; - void *hdr; - int i; - - hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); - if (!hdr) - return -EMSGSIZE; - - if (devlink_nl_put_handle(msg, devlink)) - goto nla_put_failure; - if (nla_put_u32(msg, DEVLINK_ATTR_LINECARD_INDEX, linecard->index)) - goto nla_put_failure; - if (nla_put_u8(msg, DEVLINK_ATTR_LINECARD_STATE, linecard->state)) - goto nla_put_failure; - if (linecard->type && - nla_put_string(msg, DEVLINK_ATTR_LINECARD_TYPE, linecard->type)) - goto nla_put_failure; - - if (linecard->types_count) { - attr = nla_nest_start(msg, - DEVLINK_ATTR_LINECARD_SUPPORTED_TYPES); - if (!attr) - goto nla_put_failure; - for (i = 0; i < linecard->types_count; i++) { - linecard_type = &linecard->types[i]; - if (nla_put_string(msg, DEVLINK_ATTR_LINECARD_TYPE, - linecard_type->type)) { - nla_nest_cancel(msg, attr); - goto nla_put_failure; - } - } - nla_nest_end(msg, attr); - } - - if (linecard->nested_devlink && - devlink_nl_put_nested_handle(msg, linecard->nested_devlink)) - goto nla_put_failure; - - genlmsg_end(msg, hdr); - return 0; - -nla_put_failure: - genlmsg_cancel(msg, hdr); - return -EMSGSIZE; -} - -static void devlink_linecard_notify(struct devlink_linecard *linecard, - enum devlink_command cmd) -{ - struct devlink *devlink = linecard->devlink; - struct sk_buff *msg; - int err; - - WARN_ON(cmd != DEVLINK_CMD_LINECARD_NEW && - cmd != DEVLINK_CMD_LINECARD_DEL); - - if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)) - return; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return; - - err = devlink_nl_linecard_fill(msg, devlink, linecard, cmd, 0, 0, 0, - NULL); - if (err) { - nlmsg_free(msg); - return; - } - - genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), - msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); -} - -static int devlink_nl_cmd_linecard_get_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink_linecard *linecard = info->user_ptr[1]; - struct devlink *devlink = linecard->devlink; - struct sk_buff *msg; - int err; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOMEM; - - mutex_lock(&linecard->state_lock); - err = devlink_nl_linecard_fill(msg, devlink, linecard, - DEVLINK_CMD_LINECARD_NEW, - info->snd_portid, info->snd_seq, 0, - info->extack); - mutex_unlock(&linecard->state_lock); - if (err) { - nlmsg_free(msg); - return err; - } - - return genlmsg_reply(msg, info); -} - -static int devlink_nl_cmd_linecard_get_dumpit(struct sk_buff *msg, - struct netlink_callback *cb) -{ - struct devlink_linecard *linecard; - struct devlink *devlink; - int start = cb->args[0]; - unsigned long index; - int idx = 0; - int err; - - devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { - mutex_lock(&devlink->linecards_lock); - list_for_each_entry(linecard, &devlink->linecard_list, list) { - if (idx < start) { - idx++; - continue; - } - mutex_lock(&linecard->state_lock); - err = devlink_nl_linecard_fill(msg, devlink, linecard, - DEVLINK_CMD_LINECARD_NEW, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - NLM_F_MULTI, - cb->extack); - mutex_unlock(&linecard->state_lock); - if (err) { - mutex_unlock(&devlink->linecards_lock); - devlink_put(devlink); - goto out; - } - idx++; - } - mutex_unlock(&devlink->linecards_lock); - devlink_put(devlink); - } -out: - cb->args[0] = idx; - return msg->len; -} - -static struct devlink_linecard_type * -devlink_linecard_type_lookup(struct devlink_linecard *linecard, - const char *type) -{ - struct devlink_linecard_type *linecard_type; - int i; - - for (i = 0; i < linecard->types_count; i++) { - linecard_type = &linecard->types[i]; - if (!strcmp(type, linecard_type->type)) - return linecard_type; - } - return NULL; -} - -static int devlink_linecard_type_set(struct devlink_linecard *linecard, - const char *type, - struct netlink_ext_ack *extack) -{ - const struct devlink_linecard_ops *ops = linecard->ops; - struct devlink_linecard_type *linecard_type; - int err; - - mutex_lock(&linecard->state_lock); - if (linecard->state == DEVLINK_LINECARD_STATE_PROVISIONING) { - NL_SET_ERR_MSG_MOD(extack, "Line card is currently being provisioned"); - err = -EBUSY; - goto out; - } - if (linecard->state == DEVLINK_LINECARD_STATE_UNPROVISIONING) { - NL_SET_ERR_MSG_MOD(extack, "Line card is currently being unprovisioned"); - err = -EBUSY; - goto out; - } - - linecard_type = devlink_linecard_type_lookup(linecard, type); - if (!linecard_type) { - NL_SET_ERR_MSG_MOD(extack, "Unsupported line card type provided"); - err = -EINVAL; - goto out; - } - - if (linecard->state != DEVLINK_LINECARD_STATE_UNPROVISIONED && - linecard->state != DEVLINK_LINECARD_STATE_PROVISIONING_FAILED) { - NL_SET_ERR_MSG_MOD(extack, "Line card already provisioned"); - err = -EBUSY; - /* Check if the line card is provisioned in the same - * way the user asks. In case it is, make the operation - * to return success. - */ - if (ops->same_provision && - ops->same_provision(linecard, linecard->priv, - linecard_type->type, - linecard_type->priv)) - err = 0; - goto out; - } - - linecard->state = DEVLINK_LINECARD_STATE_PROVISIONING; - linecard->type = linecard_type->type; - devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); - mutex_unlock(&linecard->state_lock); - err = ops->provision(linecard, linecard->priv, linecard_type->type, - linecard_type->priv, extack); - if (err) { - /* Provisioning failed. Assume the linecard is unprovisioned - * for future operations. - */ - mutex_lock(&linecard->state_lock); - linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED; - linecard->type = NULL; - devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); - mutex_unlock(&linecard->state_lock); - } - return err; - -out: - mutex_unlock(&linecard->state_lock); - return err; -} - -static int devlink_linecard_type_unset(struct devlink_linecard *linecard, - struct netlink_ext_ack *extack) -{ - int err; - - mutex_lock(&linecard->state_lock); - if (linecard->state == DEVLINK_LINECARD_STATE_PROVISIONING) { - NL_SET_ERR_MSG_MOD(extack, "Line card is currently being provisioned"); - err = -EBUSY; - goto out; - } - if (linecard->state == DEVLINK_LINECARD_STATE_UNPROVISIONING) { - NL_SET_ERR_MSG_MOD(extack, "Line card is currently being unprovisioned"); - err = -EBUSY; - goto out; - } - if (linecard->state == DEVLINK_LINECARD_STATE_PROVISIONING_FAILED) { - linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED; - linecard->type = NULL; - devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); - err = 0; - goto out; - } - - if (linecard->state == DEVLINK_LINECARD_STATE_UNPROVISIONED) { - NL_SET_ERR_MSG_MOD(extack, "Line card is not provisioned"); - err = 0; - goto out; - } - linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONING; - devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); - mutex_unlock(&linecard->state_lock); - err = linecard->ops->unprovision(linecard, linecard->priv, - extack); - if (err) { - /* Unprovisioning failed. Assume the linecard is unprovisioned - * for future operations. - */ - mutex_lock(&linecard->state_lock); - linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED; - linecard->type = NULL; - devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); - mutex_unlock(&linecard->state_lock); - } - return err; - -out: - mutex_unlock(&linecard->state_lock); - return err; -} - -static int devlink_nl_cmd_linecard_set_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink_linecard *linecard = info->user_ptr[1]; - struct netlink_ext_ack *extack = info->extack; - int err; - - if (info->attrs[DEVLINK_ATTR_LINECARD_TYPE]) { - const char *type; - - type = nla_data(info->attrs[DEVLINK_ATTR_LINECARD_TYPE]); - if (strcmp(type, "")) { - err = devlink_linecard_type_set(linecard, type, extack); - if (err) - return err; - } else { - err = devlink_linecard_type_unset(linecard, extack); - if (err) - return err; - } - } - - return 0; -} - -static int devlink_nl_sb_fill(struct sk_buff *msg, struct devlink *devlink, - struct devlink_sb *devlink_sb, - enum devlink_command cmd, u32 portid, - u32 seq, int flags) -{ - void *hdr; - - hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); - if (!hdr) - return -EMSGSIZE; - - if (devlink_nl_put_handle(msg, devlink)) - goto nla_put_failure; - if (nla_put_u32(msg, DEVLINK_ATTR_SB_INDEX, devlink_sb->index)) - goto nla_put_failure; - if (nla_put_u32(msg, DEVLINK_ATTR_SB_SIZE, devlink_sb->size)) - goto nla_put_failure; - if (nla_put_u16(msg, DEVLINK_ATTR_SB_INGRESS_POOL_COUNT, - devlink_sb->ingress_pools_count)) - goto nla_put_failure; - if (nla_put_u16(msg, DEVLINK_ATTR_SB_EGRESS_POOL_COUNT, - devlink_sb->egress_pools_count)) - goto nla_put_failure; - if (nla_put_u16(msg, DEVLINK_ATTR_SB_INGRESS_TC_COUNT, - devlink_sb->ingress_tc_count)) - goto nla_put_failure; - if (nla_put_u16(msg, DEVLINK_ATTR_SB_EGRESS_TC_COUNT, - devlink_sb->egress_tc_count)) - goto nla_put_failure; - - genlmsg_end(msg, hdr); - return 0; - -nla_put_failure: - genlmsg_cancel(msg, hdr); - return -EMSGSIZE; -} - -static int devlink_nl_cmd_sb_get_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - struct devlink_sb *devlink_sb; - struct sk_buff *msg; - int err; - - devlink_sb = devlink_sb_get_from_info(devlink, info); - if (IS_ERR(devlink_sb)) - return PTR_ERR(devlink_sb); - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOMEM; - - err = devlink_nl_sb_fill(msg, devlink, devlink_sb, - DEVLINK_CMD_SB_NEW, - info->snd_portid, info->snd_seq, 0); - if (err) { - nlmsg_free(msg); - return err; - } - - return genlmsg_reply(msg, info); -} - -static int devlink_nl_cmd_sb_get_dumpit(struct sk_buff *msg, - struct netlink_callback *cb) -{ - struct devlink *devlink; - struct devlink_sb *devlink_sb; - int start = cb->args[0]; - unsigned long index; - int idx = 0; - int err; - - devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { - devl_lock(devlink); - list_for_each_entry(devlink_sb, &devlink->sb_list, list) { - if (idx < start) { - idx++; - continue; - } - err = devlink_nl_sb_fill(msg, devlink, devlink_sb, - DEVLINK_CMD_SB_NEW, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - NLM_F_MULTI); - if (err) { - devl_unlock(devlink); - devlink_put(devlink); - goto out; - } - idx++; - } - devl_unlock(devlink); - devlink_put(devlink); - } -out: - cb->args[0] = idx; - return msg->len; -} - -static int devlink_nl_sb_pool_fill(struct sk_buff *msg, struct devlink *devlink, - struct devlink_sb *devlink_sb, - u16 pool_index, enum devlink_command cmd, - u32 portid, u32 seq, int flags) -{ - struct devlink_sb_pool_info pool_info; - void *hdr; - int err; - - err = devlink->ops->sb_pool_get(devlink, devlink_sb->index, - pool_index, &pool_info); - if (err) - return err; - - hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); - if (!hdr) - return -EMSGSIZE; - - if (devlink_nl_put_handle(msg, devlink)) - goto nla_put_failure; - if (nla_put_u32(msg, DEVLINK_ATTR_SB_INDEX, devlink_sb->index)) - goto nla_put_failure; - if (nla_put_u16(msg, DEVLINK_ATTR_SB_POOL_INDEX, pool_index)) - goto nla_put_failure; - if (nla_put_u8(msg, DEVLINK_ATTR_SB_POOL_TYPE, pool_info.pool_type)) - goto nla_put_failure; - if (nla_put_u32(msg, DEVLINK_ATTR_SB_POOL_SIZE, pool_info.size)) - goto nla_put_failure; - if (nla_put_u8(msg, DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE, - pool_info.threshold_type)) - goto nla_put_failure; - if (nla_put_u32(msg, DEVLINK_ATTR_SB_POOL_CELL_SIZE, - pool_info.cell_size)) - goto nla_put_failure; - - genlmsg_end(msg, hdr); - return 0; - -nla_put_failure: - genlmsg_cancel(msg, hdr); - return -EMSGSIZE; -} - -static int devlink_nl_cmd_sb_pool_get_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - struct devlink_sb *devlink_sb; - struct sk_buff *msg; - u16 pool_index; - int err; - - devlink_sb = devlink_sb_get_from_info(devlink, info); - if (IS_ERR(devlink_sb)) - return PTR_ERR(devlink_sb); - - err = devlink_sb_pool_index_get_from_info(devlink_sb, info, - &pool_index); - if (err) - return err; - - if (!devlink->ops->sb_pool_get) - return -EOPNOTSUPP; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOMEM; - - err = devlink_nl_sb_pool_fill(msg, devlink, devlink_sb, pool_index, - DEVLINK_CMD_SB_POOL_NEW, - info->snd_portid, info->snd_seq, 0); - if (err) { - nlmsg_free(msg); - return err; - } - - return genlmsg_reply(msg, info); -} - -static int __sb_pool_get_dumpit(struct sk_buff *msg, int start, int *p_idx, - struct devlink *devlink, - struct devlink_sb *devlink_sb, - u32 portid, u32 seq) -{ - u16 pool_count = devlink_sb_pool_count(devlink_sb); - u16 pool_index; - int err; - - for (pool_index = 0; pool_index < pool_count; pool_index++) { - if (*p_idx < start) { - (*p_idx)++; - continue; - } - err = devlink_nl_sb_pool_fill(msg, devlink, - devlink_sb, - pool_index, - DEVLINK_CMD_SB_POOL_NEW, - portid, seq, NLM_F_MULTI); - if (err) - return err; - (*p_idx)++; - } - return 0; -} - -static int devlink_nl_cmd_sb_pool_get_dumpit(struct sk_buff *msg, - struct netlink_callback *cb) -{ - struct devlink *devlink; - struct devlink_sb *devlink_sb; - int start = cb->args[0]; - unsigned long index; - int idx = 0; - int err = 0; - - devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { - if (!devlink->ops->sb_pool_get) - goto retry; - - devl_lock(devlink); - list_for_each_entry(devlink_sb, &devlink->sb_list, list) { - err = __sb_pool_get_dumpit(msg, start, &idx, devlink, - devlink_sb, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq); - if (err == -EOPNOTSUPP) { - err = 0; - } else if (err) { - devl_unlock(devlink); - devlink_put(devlink); - goto out; - } - } - devl_unlock(devlink); -retry: - devlink_put(devlink); - } -out: - if (err != -EMSGSIZE) - return err; - - cb->args[0] = idx; - return msg->len; -} - -static int devlink_sb_pool_set(struct devlink *devlink, unsigned int sb_index, - u16 pool_index, u32 size, - enum devlink_sb_threshold_type threshold_type, - struct netlink_ext_ack *extack) - -{ - const struct devlink_ops *ops = devlink->ops; - - if (ops->sb_pool_set) - return ops->sb_pool_set(devlink, sb_index, pool_index, - size, threshold_type, extack); - return -EOPNOTSUPP; -} - -static int devlink_nl_cmd_sb_pool_set_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - enum devlink_sb_threshold_type threshold_type; - struct devlink_sb *devlink_sb; - u16 pool_index; - u32 size; - int err; - - devlink_sb = devlink_sb_get_from_info(devlink, info); - if (IS_ERR(devlink_sb)) - return PTR_ERR(devlink_sb); - - err = devlink_sb_pool_index_get_from_info(devlink_sb, info, - &pool_index); - if (err) - return err; - - err = devlink_sb_th_type_get_from_info(info, &threshold_type); - if (err) - return err; - - if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_SB_POOL_SIZE)) - return -EINVAL; - - size = nla_get_u32(info->attrs[DEVLINK_ATTR_SB_POOL_SIZE]); - return devlink_sb_pool_set(devlink, devlink_sb->index, - pool_index, size, threshold_type, - info->extack); -} - -static int devlink_nl_sb_port_pool_fill(struct sk_buff *msg, - struct devlink *devlink, - struct devlink_port *devlink_port, - struct devlink_sb *devlink_sb, - u16 pool_index, - enum devlink_command cmd, - u32 portid, u32 seq, int flags) -{ - const struct devlink_ops *ops = devlink->ops; - u32 threshold; - void *hdr; - int err; - - err = ops->sb_port_pool_get(devlink_port, devlink_sb->index, - pool_index, &threshold); - if (err) - return err; - - hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); - if (!hdr) - return -EMSGSIZE; - - if (devlink_nl_put_handle(msg, devlink)) - goto nla_put_failure; - if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index)) - goto nla_put_failure; - if (nla_put_u32(msg, DEVLINK_ATTR_SB_INDEX, devlink_sb->index)) - goto nla_put_failure; - if (nla_put_u16(msg, DEVLINK_ATTR_SB_POOL_INDEX, pool_index)) - goto nla_put_failure; - if (nla_put_u32(msg, DEVLINK_ATTR_SB_THRESHOLD, threshold)) - goto nla_put_failure; - - if (ops->sb_occ_port_pool_get) { - u32 cur; - u32 max; - - err = ops->sb_occ_port_pool_get(devlink_port, devlink_sb->index, - pool_index, &cur, &max); - if (err && err != -EOPNOTSUPP) - goto sb_occ_get_failure; - if (!err) { - if (nla_put_u32(msg, DEVLINK_ATTR_SB_OCC_CUR, cur)) - goto nla_put_failure; - if (nla_put_u32(msg, DEVLINK_ATTR_SB_OCC_MAX, max)) - goto nla_put_failure; - } - } - - genlmsg_end(msg, hdr); - return 0; - -nla_put_failure: - err = -EMSGSIZE; -sb_occ_get_failure: - genlmsg_cancel(msg, hdr); - return err; -} - -static int devlink_nl_cmd_sb_port_pool_get_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink_port *devlink_port = info->user_ptr[1]; - struct devlink *devlink = devlink_port->devlink; - struct devlink_sb *devlink_sb; - struct sk_buff *msg; - u16 pool_index; - int err; - - devlink_sb = devlink_sb_get_from_info(devlink, info); - if (IS_ERR(devlink_sb)) - return PTR_ERR(devlink_sb); - - err = devlink_sb_pool_index_get_from_info(devlink_sb, info, - &pool_index); - if (err) - return err; - - if (!devlink->ops->sb_port_pool_get) - return -EOPNOTSUPP; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOMEM; - - err = devlink_nl_sb_port_pool_fill(msg, devlink, devlink_port, - devlink_sb, pool_index, - DEVLINK_CMD_SB_PORT_POOL_NEW, - info->snd_portid, info->snd_seq, 0); - if (err) { - nlmsg_free(msg); - return err; - } - - return genlmsg_reply(msg, info); -} - -static int __sb_port_pool_get_dumpit(struct sk_buff *msg, int start, int *p_idx, - struct devlink *devlink, - struct devlink_sb *devlink_sb, - u32 portid, u32 seq) -{ - struct devlink_port *devlink_port; - u16 pool_count = devlink_sb_pool_count(devlink_sb); - u16 pool_index; - int err; - - list_for_each_entry(devlink_port, &devlink->port_list, list) { - for (pool_index = 0; pool_index < pool_count; pool_index++) { - if (*p_idx < start) { - (*p_idx)++; - continue; - } - err = devlink_nl_sb_port_pool_fill(msg, devlink, - devlink_port, - devlink_sb, - pool_index, - DEVLINK_CMD_SB_PORT_POOL_NEW, - portid, seq, - NLM_F_MULTI); - if (err) - return err; - (*p_idx)++; - } - } - return 0; -} - -static int devlink_nl_cmd_sb_port_pool_get_dumpit(struct sk_buff *msg, - struct netlink_callback *cb) -{ - struct devlink *devlink; - struct devlink_sb *devlink_sb; - int start = cb->args[0]; - unsigned long index; - int idx = 0; - int err = 0; - - devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { - if (!devlink->ops->sb_port_pool_get) - goto retry; - - devl_lock(devlink); - list_for_each_entry(devlink_sb, &devlink->sb_list, list) { - err = __sb_port_pool_get_dumpit(msg, start, &idx, - devlink, devlink_sb, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq); - if (err == -EOPNOTSUPP) { - err = 0; - } else if (err) { - devl_unlock(devlink); - devlink_put(devlink); - goto out; - } - } - devl_unlock(devlink); -retry: - devlink_put(devlink); - } -out: - if (err != -EMSGSIZE) - return err; - - cb->args[0] = idx; - return msg->len; -} - -static int devlink_sb_port_pool_set(struct devlink_port *devlink_port, - unsigned int sb_index, u16 pool_index, - u32 threshold, - struct netlink_ext_ack *extack) - -{ - const struct devlink_ops *ops = devlink_port->devlink->ops; - - if (ops->sb_port_pool_set) - return ops->sb_port_pool_set(devlink_port, sb_index, - pool_index, threshold, extack); - return -EOPNOTSUPP; -} - -static int devlink_nl_cmd_sb_port_pool_set_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink_port *devlink_port = info->user_ptr[1]; - struct devlink *devlink = info->user_ptr[0]; - struct devlink_sb *devlink_sb; - u16 pool_index; - u32 threshold; - int err; - - devlink_sb = devlink_sb_get_from_info(devlink, info); - if (IS_ERR(devlink_sb)) - return PTR_ERR(devlink_sb); - - err = devlink_sb_pool_index_get_from_info(devlink_sb, info, - &pool_index); - if (err) - return err; - - if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_SB_THRESHOLD)) - return -EINVAL; - - threshold = nla_get_u32(info->attrs[DEVLINK_ATTR_SB_THRESHOLD]); - return devlink_sb_port_pool_set(devlink_port, devlink_sb->index, - pool_index, threshold, info->extack); -} - -static int -devlink_nl_sb_tc_pool_bind_fill(struct sk_buff *msg, struct devlink *devlink, - struct devlink_port *devlink_port, - struct devlink_sb *devlink_sb, u16 tc_index, - enum devlink_sb_pool_type pool_type, - enum devlink_command cmd, - u32 portid, u32 seq, int flags) -{ - const struct devlink_ops *ops = devlink->ops; - u16 pool_index; - u32 threshold; - void *hdr; - int err; - - err = ops->sb_tc_pool_bind_get(devlink_port, devlink_sb->index, - tc_index, pool_type, - &pool_index, &threshold); - if (err) - return err; - - hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); - if (!hdr) - return -EMSGSIZE; - - if (devlink_nl_put_handle(msg, devlink)) - goto nla_put_failure; - if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index)) - goto nla_put_failure; - if (nla_put_u32(msg, DEVLINK_ATTR_SB_INDEX, devlink_sb->index)) - goto nla_put_failure; - if (nla_put_u16(msg, DEVLINK_ATTR_SB_TC_INDEX, tc_index)) - goto nla_put_failure; - if (nla_put_u8(msg, DEVLINK_ATTR_SB_POOL_TYPE, pool_type)) - goto nla_put_failure; - if (nla_put_u16(msg, DEVLINK_ATTR_SB_POOL_INDEX, pool_index)) - goto nla_put_failure; - if (nla_put_u32(msg, DEVLINK_ATTR_SB_THRESHOLD, threshold)) - goto nla_put_failure; - - if (ops->sb_occ_tc_port_bind_get) { - u32 cur; - u32 max; - - err = ops->sb_occ_tc_port_bind_get(devlink_port, - devlink_sb->index, - tc_index, pool_type, - &cur, &max); - if (err && err != -EOPNOTSUPP) - return err; - if (!err) { - if (nla_put_u32(msg, DEVLINK_ATTR_SB_OCC_CUR, cur)) - goto nla_put_failure; - if (nla_put_u32(msg, DEVLINK_ATTR_SB_OCC_MAX, max)) - goto nla_put_failure; - } - } - - genlmsg_end(msg, hdr); - return 0; - -nla_put_failure: - genlmsg_cancel(msg, hdr); - return -EMSGSIZE; -} - -static int devlink_nl_cmd_sb_tc_pool_bind_get_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink_port *devlink_port = info->user_ptr[1]; - struct devlink *devlink = devlink_port->devlink; - struct devlink_sb *devlink_sb; - struct sk_buff *msg; - enum devlink_sb_pool_type pool_type; - u16 tc_index; - int err; - - devlink_sb = devlink_sb_get_from_info(devlink, info); - if (IS_ERR(devlink_sb)) - return PTR_ERR(devlink_sb); - - err = devlink_sb_pool_type_get_from_info(info, &pool_type); - if (err) - return err; - - err = devlink_sb_tc_index_get_from_info(devlink_sb, info, - pool_type, &tc_index); - if (err) - return err; - - if (!devlink->ops->sb_tc_pool_bind_get) - return -EOPNOTSUPP; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOMEM; - - err = devlink_nl_sb_tc_pool_bind_fill(msg, devlink, devlink_port, - devlink_sb, tc_index, pool_type, - DEVLINK_CMD_SB_TC_POOL_BIND_NEW, - info->snd_portid, - info->snd_seq, 0); - if (err) { - nlmsg_free(msg); - return err; - } - - return genlmsg_reply(msg, info); -} - -static int __sb_tc_pool_bind_get_dumpit(struct sk_buff *msg, - int start, int *p_idx, - struct devlink *devlink, - struct devlink_sb *devlink_sb, - u32 portid, u32 seq) -{ - struct devlink_port *devlink_port; - u16 tc_index; - int err; - - list_for_each_entry(devlink_port, &devlink->port_list, list) { - for (tc_index = 0; - tc_index < devlink_sb->ingress_tc_count; tc_index++) { - if (*p_idx < start) { - (*p_idx)++; - continue; - } - err = devlink_nl_sb_tc_pool_bind_fill(msg, devlink, - devlink_port, - devlink_sb, - tc_index, - DEVLINK_SB_POOL_TYPE_INGRESS, - DEVLINK_CMD_SB_TC_POOL_BIND_NEW, - portid, seq, - NLM_F_MULTI); - if (err) - return err; - (*p_idx)++; - } - for (tc_index = 0; - tc_index < devlink_sb->egress_tc_count; tc_index++) { - if (*p_idx < start) { - (*p_idx)++; - continue; - } - err = devlink_nl_sb_tc_pool_bind_fill(msg, devlink, - devlink_port, - devlink_sb, - tc_index, - DEVLINK_SB_POOL_TYPE_EGRESS, - DEVLINK_CMD_SB_TC_POOL_BIND_NEW, - portid, seq, - NLM_F_MULTI); - if (err) - return err; - (*p_idx)++; - } - } - return 0; -} - -static int -devlink_nl_cmd_sb_tc_pool_bind_get_dumpit(struct sk_buff *msg, - struct netlink_callback *cb) -{ - struct devlink *devlink; - struct devlink_sb *devlink_sb; - int start = cb->args[0]; - unsigned long index; - int idx = 0; - int err = 0; - - devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { - if (!devlink->ops->sb_tc_pool_bind_get) - goto retry; - - devl_lock(devlink); - list_for_each_entry(devlink_sb, &devlink->sb_list, list) { - err = __sb_tc_pool_bind_get_dumpit(msg, start, &idx, - devlink, - devlink_sb, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq); - if (err == -EOPNOTSUPP) { - err = 0; - } else if (err) { - devl_unlock(devlink); - devlink_put(devlink); - goto out; - } - } - devl_unlock(devlink); -retry: - devlink_put(devlink); - } -out: - if (err != -EMSGSIZE) - return err; - - cb->args[0] = idx; - return msg->len; -} - -static int devlink_sb_tc_pool_bind_set(struct devlink_port *devlink_port, - unsigned int sb_index, u16 tc_index, - enum devlink_sb_pool_type pool_type, - u16 pool_index, u32 threshold, - struct netlink_ext_ack *extack) - -{ - const struct devlink_ops *ops = devlink_port->devlink->ops; - - if (ops->sb_tc_pool_bind_set) - return ops->sb_tc_pool_bind_set(devlink_port, sb_index, - tc_index, pool_type, - pool_index, threshold, extack); - return -EOPNOTSUPP; -} - -static int devlink_nl_cmd_sb_tc_pool_bind_set_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink_port *devlink_port = info->user_ptr[1]; - struct devlink *devlink = info->user_ptr[0]; - enum devlink_sb_pool_type pool_type; - struct devlink_sb *devlink_sb; - u16 tc_index; - u16 pool_index; - u32 threshold; - int err; - - devlink_sb = devlink_sb_get_from_info(devlink, info); - if (IS_ERR(devlink_sb)) - return PTR_ERR(devlink_sb); - - err = devlink_sb_pool_type_get_from_info(info, &pool_type); - if (err) - return err; - - err = devlink_sb_tc_index_get_from_info(devlink_sb, info, - pool_type, &tc_index); - if (err) - return err; - - err = devlink_sb_pool_index_get_from_info(devlink_sb, info, - &pool_index); - if (err) - return err; - - if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_SB_THRESHOLD)) - return -EINVAL; - - threshold = nla_get_u32(info->attrs[DEVLINK_ATTR_SB_THRESHOLD]); - return devlink_sb_tc_pool_bind_set(devlink_port, devlink_sb->index, - tc_index, pool_type, - pool_index, threshold, info->extack); -} - -static int devlink_nl_cmd_sb_occ_snapshot_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - const struct devlink_ops *ops = devlink->ops; - struct devlink_sb *devlink_sb; - - devlink_sb = devlink_sb_get_from_info(devlink, info); - if (IS_ERR(devlink_sb)) - return PTR_ERR(devlink_sb); - - if (ops->sb_occ_snapshot) - return ops->sb_occ_snapshot(devlink, devlink_sb->index); - return -EOPNOTSUPP; -} - -static int devlink_nl_cmd_sb_occ_max_clear_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - const struct devlink_ops *ops = devlink->ops; - struct devlink_sb *devlink_sb; - - devlink_sb = devlink_sb_get_from_info(devlink, info); - if (IS_ERR(devlink_sb)) - return PTR_ERR(devlink_sb); - - if (ops->sb_occ_max_clear) - return ops->sb_occ_max_clear(devlink, devlink_sb->index); - return -EOPNOTSUPP; -} - -static int devlink_nl_eswitch_fill(struct sk_buff *msg, struct devlink *devlink, - enum devlink_command cmd, u32 portid, - u32 seq, int flags) -{ - const struct devlink_ops *ops = devlink->ops; - enum devlink_eswitch_encap_mode encap_mode; - u8 inline_mode; - void *hdr; - int err = 0; - u16 mode; - - hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); - if (!hdr) - return -EMSGSIZE; - - err = devlink_nl_put_handle(msg, devlink); - if (err) - goto nla_put_failure; - - if (ops->eswitch_mode_get) { - err = ops->eswitch_mode_get(devlink, &mode); - if (err) - goto nla_put_failure; - err = nla_put_u16(msg, DEVLINK_ATTR_ESWITCH_MODE, mode); - if (err) - goto nla_put_failure; - } - - if (ops->eswitch_inline_mode_get) { - err = ops->eswitch_inline_mode_get(devlink, &inline_mode); - if (err) - goto nla_put_failure; - err = nla_put_u8(msg, DEVLINK_ATTR_ESWITCH_INLINE_MODE, - inline_mode); - if (err) - goto nla_put_failure; - } - - if (ops->eswitch_encap_mode_get) { - err = ops->eswitch_encap_mode_get(devlink, &encap_mode); - if (err) - goto nla_put_failure; - err = nla_put_u8(msg, DEVLINK_ATTR_ESWITCH_ENCAP_MODE, encap_mode); - if (err) - goto nla_put_failure; - } - - genlmsg_end(msg, hdr); - return 0; - -nla_put_failure: - genlmsg_cancel(msg, hdr); - return err; -} - -static int devlink_nl_cmd_eswitch_get_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - struct sk_buff *msg; - int err; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOMEM; - - err = devlink_nl_eswitch_fill(msg, devlink, DEVLINK_CMD_ESWITCH_GET, - info->snd_portid, info->snd_seq, 0); - - if (err) { - nlmsg_free(msg); - return err; - } - - return genlmsg_reply(msg, info); -} - -static int devlink_rate_nodes_check(struct devlink *devlink, u16 mode, - struct netlink_ext_ack *extack) -{ - struct devlink_rate *devlink_rate; - - list_for_each_entry(devlink_rate, &devlink->rate_list, list) - if (devlink_rate_is_node(devlink_rate)) { - NL_SET_ERR_MSG_MOD(extack, "Rate node(s) exists."); - return -EBUSY; - } - return 0; -} - -static int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - const struct devlink_ops *ops = devlink->ops; - enum devlink_eswitch_encap_mode encap_mode; - u8 inline_mode; - int err = 0; - u16 mode; - - if (info->attrs[DEVLINK_ATTR_ESWITCH_MODE]) { - if (!ops->eswitch_mode_set) - return -EOPNOTSUPP; - mode = nla_get_u16(info->attrs[DEVLINK_ATTR_ESWITCH_MODE]); - err = devlink_rate_nodes_check(devlink, mode, info->extack); - if (err) - return err; - err = ops->eswitch_mode_set(devlink, mode, info->extack); - if (err) - return err; - } - - if (info->attrs[DEVLINK_ATTR_ESWITCH_INLINE_MODE]) { - if (!ops->eswitch_inline_mode_set) - return -EOPNOTSUPP; - inline_mode = nla_get_u8( - info->attrs[DEVLINK_ATTR_ESWITCH_INLINE_MODE]); - err = ops->eswitch_inline_mode_set(devlink, inline_mode, - info->extack); - if (err) - return err; - } - - if (info->attrs[DEVLINK_ATTR_ESWITCH_ENCAP_MODE]) { - if (!ops->eswitch_encap_mode_set) - return -EOPNOTSUPP; - encap_mode = nla_get_u8(info->attrs[DEVLINK_ATTR_ESWITCH_ENCAP_MODE]); - err = ops->eswitch_encap_mode_set(devlink, encap_mode, - info->extack); - if (err) - return err; - } - - return 0; -} - -int devlink_dpipe_match_put(struct sk_buff *skb, - struct devlink_dpipe_match *match) -{ - struct devlink_dpipe_header *header = match->header; - struct devlink_dpipe_field *field = &header->fields[match->field_id]; - struct nlattr *match_attr; - - match_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_MATCH); - if (!match_attr) - return -EMSGSIZE; - - if (nla_put_u32(skb, DEVLINK_ATTR_DPIPE_MATCH_TYPE, match->type) || - nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_INDEX, match->header_index) || - nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_ID, header->id) || - nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_ID, field->id) || - nla_put_u8(skb, DEVLINK_ATTR_DPIPE_HEADER_GLOBAL, header->global)) - goto nla_put_failure; - - nla_nest_end(skb, match_attr); - return 0; - -nla_put_failure: - nla_nest_cancel(skb, match_attr); - return -EMSGSIZE; -} -EXPORT_SYMBOL_GPL(devlink_dpipe_match_put); - -static int devlink_dpipe_matches_put(struct devlink_dpipe_table *table, - struct sk_buff *skb) -{ - struct nlattr *matches_attr; - - matches_attr = nla_nest_start_noflag(skb, - DEVLINK_ATTR_DPIPE_TABLE_MATCHES); - if (!matches_attr) - return -EMSGSIZE; - - if (table->table_ops->matches_dump(table->priv, skb)) - goto nla_put_failure; - - nla_nest_end(skb, matches_attr); - return 0; - -nla_put_failure: - nla_nest_cancel(skb, matches_attr); - return -EMSGSIZE; -} - -int devlink_dpipe_action_put(struct sk_buff *skb, - struct devlink_dpipe_action *action) -{ - struct devlink_dpipe_header *header = action->header; - struct devlink_dpipe_field *field = &header->fields[action->field_id]; - struct nlattr *action_attr; - - action_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_ACTION); - if (!action_attr) - return -EMSGSIZE; - - if (nla_put_u32(skb, DEVLINK_ATTR_DPIPE_ACTION_TYPE, action->type) || - nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_INDEX, action->header_index) || - nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_ID, header->id) || - nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_ID, field->id) || - nla_put_u8(skb, DEVLINK_ATTR_DPIPE_HEADER_GLOBAL, header->global)) - goto nla_put_failure; - - nla_nest_end(skb, action_attr); - return 0; - -nla_put_failure: - nla_nest_cancel(skb, action_attr); - return -EMSGSIZE; -} -EXPORT_SYMBOL_GPL(devlink_dpipe_action_put); - -static int devlink_dpipe_actions_put(struct devlink_dpipe_table *table, - struct sk_buff *skb) -{ - struct nlattr *actions_attr; - - actions_attr = nla_nest_start_noflag(skb, - DEVLINK_ATTR_DPIPE_TABLE_ACTIONS); - if (!actions_attr) - return -EMSGSIZE; - - if (table->table_ops->actions_dump(table->priv, skb)) - goto nla_put_failure; - - nla_nest_end(skb, actions_attr); - return 0; - -nla_put_failure: - nla_nest_cancel(skb, actions_attr); - return -EMSGSIZE; -} - -static int devlink_dpipe_table_put(struct sk_buff *skb, - struct devlink_dpipe_table *table) -{ - struct nlattr *table_attr; - u64 table_size; - - table_size = table->table_ops->size_get(table->priv); - table_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_TABLE); - if (!table_attr) - return -EMSGSIZE; - - if (nla_put_string(skb, DEVLINK_ATTR_DPIPE_TABLE_NAME, table->name) || - nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_TABLE_SIZE, table_size, - DEVLINK_ATTR_PAD)) - goto nla_put_failure; - if (nla_put_u8(skb, DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED, - table->counters_enabled)) - goto nla_put_failure; - - if (table->resource_valid) { - if (nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_ID, - table->resource_id, DEVLINK_ATTR_PAD) || - nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_UNITS, - table->resource_units, DEVLINK_ATTR_PAD)) - goto nla_put_failure; - } - if (devlink_dpipe_matches_put(table, skb)) - goto nla_put_failure; - - if (devlink_dpipe_actions_put(table, skb)) - goto nla_put_failure; - - nla_nest_end(skb, table_attr); - return 0; - -nla_put_failure: - nla_nest_cancel(skb, table_attr); - return -EMSGSIZE; -} - -static int devlink_dpipe_send_and_alloc_skb(struct sk_buff **pskb, - struct genl_info *info) -{ - int err; - - if (*pskb) { - err = genlmsg_reply(*pskb, info); - if (err) - return err; - } - *pskb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!*pskb) - return -ENOMEM; - return 0; -} - -static int devlink_dpipe_tables_fill(struct genl_info *info, - enum devlink_command cmd, int flags, - struct list_head *dpipe_tables, - const char *table_name) -{ - struct devlink *devlink = info->user_ptr[0]; - struct devlink_dpipe_table *table; - struct nlattr *tables_attr; - struct sk_buff *skb = NULL; - struct nlmsghdr *nlh; - bool incomplete; - void *hdr; - int i; - int err; - - table = list_first_entry(dpipe_tables, - struct devlink_dpipe_table, list); -start_again: - err = devlink_dpipe_send_and_alloc_skb(&skb, info); - if (err) - return err; - - hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq, - &devlink_nl_family, NLM_F_MULTI, cmd); - if (!hdr) { - nlmsg_free(skb); - return -EMSGSIZE; - } - - if (devlink_nl_put_handle(skb, devlink)) - goto nla_put_failure; - tables_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_TABLES); - if (!tables_attr) - goto nla_put_failure; - - i = 0; - incomplete = false; - list_for_each_entry_from(table, dpipe_tables, list) { - if (!table_name) { - err = devlink_dpipe_table_put(skb, table); - if (err) { - if (!i) - goto err_table_put; - incomplete = true; - break; - } - } else { - if (!strcmp(table->name, table_name)) { - err = devlink_dpipe_table_put(skb, table); - if (err) - break; - } - } - i++; - } - - nla_nest_end(skb, tables_attr); - genlmsg_end(skb, hdr); - if (incomplete) - goto start_again; - -send_done: - nlh = nlmsg_put(skb, info->snd_portid, info->snd_seq, - NLMSG_DONE, 0, flags | NLM_F_MULTI); - if (!nlh) { - err = devlink_dpipe_send_and_alloc_skb(&skb, info); - if (err) - return err; - goto send_done; - } - - return genlmsg_reply(skb, info); - -nla_put_failure: - err = -EMSGSIZE; -err_table_put: - nlmsg_free(skb); - return err; -} - -static int devlink_nl_cmd_dpipe_table_get(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - const char *table_name = NULL; - - if (info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]) - table_name = nla_data(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]); - - return devlink_dpipe_tables_fill(info, DEVLINK_CMD_DPIPE_TABLE_GET, 0, - &devlink->dpipe_table_list, - table_name); -} - -static int devlink_dpipe_value_put(struct sk_buff *skb, - struct devlink_dpipe_value *value) -{ - if (nla_put(skb, DEVLINK_ATTR_DPIPE_VALUE, - value->value_size, value->value)) - return -EMSGSIZE; - if (value->mask) - if (nla_put(skb, DEVLINK_ATTR_DPIPE_VALUE_MASK, - value->value_size, value->mask)) - return -EMSGSIZE; - if (value->mapping_valid) - if (nla_put_u32(skb, DEVLINK_ATTR_DPIPE_VALUE_MAPPING, - value->mapping_value)) - return -EMSGSIZE; - return 0; -} - -static int devlink_dpipe_action_value_put(struct sk_buff *skb, - struct devlink_dpipe_value *value) -{ - if (!value->action) - return -EINVAL; - if (devlink_dpipe_action_put(skb, value->action)) - return -EMSGSIZE; - if (devlink_dpipe_value_put(skb, value)) - return -EMSGSIZE; - return 0; -} - -static int devlink_dpipe_action_values_put(struct sk_buff *skb, - struct devlink_dpipe_value *values, - unsigned int values_count) -{ - struct nlattr *action_attr; - int i; - int err; - - for (i = 0; i < values_count; i++) { - action_attr = nla_nest_start_noflag(skb, - DEVLINK_ATTR_DPIPE_ACTION_VALUE); - if (!action_attr) - return -EMSGSIZE; - err = devlink_dpipe_action_value_put(skb, &values[i]); - if (err) - goto err_action_value_put; - nla_nest_end(skb, action_attr); - } - return 0; - -err_action_value_put: - nla_nest_cancel(skb, action_attr); - return err; -} - -static int devlink_dpipe_match_value_put(struct sk_buff *skb, - struct devlink_dpipe_value *value) -{ - if (!value->match) - return -EINVAL; - if (devlink_dpipe_match_put(skb, value->match)) - return -EMSGSIZE; - if (devlink_dpipe_value_put(skb, value)) - return -EMSGSIZE; - return 0; -} - -static int devlink_dpipe_match_values_put(struct sk_buff *skb, - struct devlink_dpipe_value *values, - unsigned int values_count) -{ - struct nlattr *match_attr; - int i; - int err; - - for (i = 0; i < values_count; i++) { - match_attr = nla_nest_start_noflag(skb, - DEVLINK_ATTR_DPIPE_MATCH_VALUE); - if (!match_attr) - return -EMSGSIZE; - err = devlink_dpipe_match_value_put(skb, &values[i]); - if (err) - goto err_match_value_put; - nla_nest_end(skb, match_attr); - } - return 0; - -err_match_value_put: - nla_nest_cancel(skb, match_attr); - return err; -} - -static int devlink_dpipe_entry_put(struct sk_buff *skb, - struct devlink_dpipe_entry *entry) -{ - struct nlattr *entry_attr, *matches_attr, *actions_attr; - int err; - - entry_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_ENTRY); - if (!entry_attr) - return -EMSGSIZE; - - if (nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_ENTRY_INDEX, entry->index, - DEVLINK_ATTR_PAD)) - goto nla_put_failure; - if (entry->counter_valid) - if (nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_ENTRY_COUNTER, - entry->counter, DEVLINK_ATTR_PAD)) - goto nla_put_failure; - - matches_attr = nla_nest_start_noflag(skb, - DEVLINK_ATTR_DPIPE_ENTRY_MATCH_VALUES); - if (!matches_attr) - goto nla_put_failure; - - err = devlink_dpipe_match_values_put(skb, entry->match_values, - entry->match_values_count); - if (err) { - nla_nest_cancel(skb, matches_attr); - goto err_match_values_put; - } - nla_nest_end(skb, matches_attr); - - actions_attr = nla_nest_start_noflag(skb, - DEVLINK_ATTR_DPIPE_ENTRY_ACTION_VALUES); - if (!actions_attr) - goto nla_put_failure; - - err = devlink_dpipe_action_values_put(skb, entry->action_values, - entry->action_values_count); - if (err) { - nla_nest_cancel(skb, actions_attr); - goto err_action_values_put; - } - nla_nest_end(skb, actions_attr); - - nla_nest_end(skb, entry_attr); - return 0; - -nla_put_failure: - err = -EMSGSIZE; -err_match_values_put: -err_action_values_put: - nla_nest_cancel(skb, entry_attr); - return err; -} - -static struct devlink_dpipe_table * -devlink_dpipe_table_find(struct list_head *dpipe_tables, - const char *table_name, struct devlink *devlink) -{ - struct devlink_dpipe_table *table; - list_for_each_entry_rcu(table, dpipe_tables, list, - lockdep_is_held(&devlink->lock)) { - if (!strcmp(table->name, table_name)) - return table; - } - return NULL; -} - -int devlink_dpipe_entry_ctx_prepare(struct devlink_dpipe_dump_ctx *dump_ctx) -{ - struct devlink *devlink; - int err; - - err = devlink_dpipe_send_and_alloc_skb(&dump_ctx->skb, - dump_ctx->info); - if (err) - return err; - - dump_ctx->hdr = genlmsg_put(dump_ctx->skb, - dump_ctx->info->snd_portid, - dump_ctx->info->snd_seq, - &devlink_nl_family, NLM_F_MULTI, - dump_ctx->cmd); - if (!dump_ctx->hdr) - goto nla_put_failure; - - devlink = dump_ctx->info->user_ptr[0]; - if (devlink_nl_put_handle(dump_ctx->skb, devlink)) - goto nla_put_failure; - dump_ctx->nest = nla_nest_start_noflag(dump_ctx->skb, - DEVLINK_ATTR_DPIPE_ENTRIES); - if (!dump_ctx->nest) - goto nla_put_failure; - return 0; - -nla_put_failure: - nlmsg_free(dump_ctx->skb); - return -EMSGSIZE; -} -EXPORT_SYMBOL_GPL(devlink_dpipe_entry_ctx_prepare); - -int devlink_dpipe_entry_ctx_append(struct devlink_dpipe_dump_ctx *dump_ctx, - struct devlink_dpipe_entry *entry) -{ - return devlink_dpipe_entry_put(dump_ctx->skb, entry); -} -EXPORT_SYMBOL_GPL(devlink_dpipe_entry_ctx_append); - -int devlink_dpipe_entry_ctx_close(struct devlink_dpipe_dump_ctx *dump_ctx) -{ - nla_nest_end(dump_ctx->skb, dump_ctx->nest); - genlmsg_end(dump_ctx->skb, dump_ctx->hdr); - return 0; -} -EXPORT_SYMBOL_GPL(devlink_dpipe_entry_ctx_close); - -void devlink_dpipe_entry_clear(struct devlink_dpipe_entry *entry) - -{ - unsigned int value_count, value_index; - struct devlink_dpipe_value *value; - - value = entry->action_values; - value_count = entry->action_values_count; - for (value_index = 0; value_index < value_count; value_index++) { - kfree(value[value_index].value); - kfree(value[value_index].mask); - } - - value = entry->match_values; - value_count = entry->match_values_count; - for (value_index = 0; value_index < value_count; value_index++) { - kfree(value[value_index].value); - kfree(value[value_index].mask); - } -} -EXPORT_SYMBOL_GPL(devlink_dpipe_entry_clear); - -static int devlink_dpipe_entries_fill(struct genl_info *info, - enum devlink_command cmd, int flags, - struct devlink_dpipe_table *table) -{ - struct devlink_dpipe_dump_ctx dump_ctx; - struct nlmsghdr *nlh; - int err; - - dump_ctx.skb = NULL; - dump_ctx.cmd = cmd; - dump_ctx.info = info; - - err = table->table_ops->entries_dump(table->priv, - table->counters_enabled, - &dump_ctx); - if (err) - return err; - -send_done: - nlh = nlmsg_put(dump_ctx.skb, info->snd_portid, info->snd_seq, - NLMSG_DONE, 0, flags | NLM_F_MULTI); - if (!nlh) { - err = devlink_dpipe_send_and_alloc_skb(&dump_ctx.skb, info); - if (err) - return err; - goto send_done; - } - return genlmsg_reply(dump_ctx.skb, info); -} - -static int devlink_nl_cmd_dpipe_entries_get(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - struct devlink_dpipe_table *table; - const char *table_name; - - if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_DPIPE_TABLE_NAME)) - return -EINVAL; - - table_name = nla_data(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]); - table = devlink_dpipe_table_find(&devlink->dpipe_table_list, - table_name, devlink); - if (!table) - return -EINVAL; - - if (!table->table_ops->entries_dump) - return -EINVAL; - - return devlink_dpipe_entries_fill(info, DEVLINK_CMD_DPIPE_ENTRIES_GET, - 0, table); -} - -static int devlink_dpipe_fields_put(struct sk_buff *skb, - const struct devlink_dpipe_header *header) -{ - struct devlink_dpipe_field *field; - struct nlattr *field_attr; - int i; - - for (i = 0; i < header->fields_count; i++) { - field = &header->fields[i]; - field_attr = nla_nest_start_noflag(skb, - DEVLINK_ATTR_DPIPE_FIELD); - if (!field_attr) - return -EMSGSIZE; - if (nla_put_string(skb, DEVLINK_ATTR_DPIPE_FIELD_NAME, field->name) || - nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_ID, field->id) || - nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_BITWIDTH, field->bitwidth) || - nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_MAPPING_TYPE, field->mapping_type)) - goto nla_put_failure; - nla_nest_end(skb, field_attr); - } - return 0; - -nla_put_failure: - nla_nest_cancel(skb, field_attr); - return -EMSGSIZE; -} - -static int devlink_dpipe_header_put(struct sk_buff *skb, - struct devlink_dpipe_header *header) -{ - struct nlattr *fields_attr, *header_attr; - int err; - - header_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_HEADER); - if (!header_attr) - return -EMSGSIZE; - - if (nla_put_string(skb, DEVLINK_ATTR_DPIPE_HEADER_NAME, header->name) || - nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_ID, header->id) || - nla_put_u8(skb, DEVLINK_ATTR_DPIPE_HEADER_GLOBAL, header->global)) - goto nla_put_failure; - - fields_attr = nla_nest_start_noflag(skb, - DEVLINK_ATTR_DPIPE_HEADER_FIELDS); - if (!fields_attr) - goto nla_put_failure; - - err = devlink_dpipe_fields_put(skb, header); - if (err) { - nla_nest_cancel(skb, fields_attr); - goto nla_put_failure; - } - nla_nest_end(skb, fields_attr); - nla_nest_end(skb, header_attr); - return 0; - -nla_put_failure: - err = -EMSGSIZE; - nla_nest_cancel(skb, header_attr); - return err; -} - -static int devlink_dpipe_headers_fill(struct genl_info *info, - enum devlink_command cmd, int flags, - struct devlink_dpipe_headers * - dpipe_headers) -{ - struct devlink *devlink = info->user_ptr[0]; - struct nlattr *headers_attr; - struct sk_buff *skb = NULL; - struct nlmsghdr *nlh; - void *hdr; - int i, j; - int err; - - i = 0; -start_again: - err = devlink_dpipe_send_and_alloc_skb(&skb, info); - if (err) - return err; - - hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq, - &devlink_nl_family, NLM_F_MULTI, cmd); - if (!hdr) { - nlmsg_free(skb); - return -EMSGSIZE; - } - - if (devlink_nl_put_handle(skb, devlink)) - goto nla_put_failure; - headers_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_HEADERS); - if (!headers_attr) - goto nla_put_failure; - - j = 0; - for (; i < dpipe_headers->headers_count; i++) { - err = devlink_dpipe_header_put(skb, dpipe_headers->headers[i]); - if (err) { - if (!j) - goto err_table_put; - break; - } - j++; - } - nla_nest_end(skb, headers_attr); - genlmsg_end(skb, hdr); - if (i != dpipe_headers->headers_count) - goto start_again; - -send_done: - nlh = nlmsg_put(skb, info->snd_portid, info->snd_seq, - NLMSG_DONE, 0, flags | NLM_F_MULTI); - if (!nlh) { - err = devlink_dpipe_send_and_alloc_skb(&skb, info); - if (err) - return err; - goto send_done; - } - return genlmsg_reply(skb, info); - -nla_put_failure: - err = -EMSGSIZE; -err_table_put: - nlmsg_free(skb); - return err; -} - -static int devlink_nl_cmd_dpipe_headers_get(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - - if (!devlink->dpipe_headers) - return -EOPNOTSUPP; - return devlink_dpipe_headers_fill(info, DEVLINK_CMD_DPIPE_HEADERS_GET, - 0, devlink->dpipe_headers); -} - -static int devlink_dpipe_table_counters_set(struct devlink *devlink, - const char *table_name, - bool enable) -{ - struct devlink_dpipe_table *table; - - table = devlink_dpipe_table_find(&devlink->dpipe_table_list, - table_name, devlink); - if (!table) - return -EINVAL; - - if (table->counter_control_extern) - return -EOPNOTSUPP; - - if (!(table->counters_enabled ^ enable)) - return 0; - - table->counters_enabled = enable; - if (table->table_ops->counters_set_update) - table->table_ops->counters_set_update(table->priv, enable); - return 0; -} - -static int devlink_nl_cmd_dpipe_table_counters_set(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - const char *table_name; - bool counters_enable; - - if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_DPIPE_TABLE_NAME) || - GENL_REQ_ATTR_CHECK(info, - DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED)) - return -EINVAL; - - table_name = nla_data(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]); - counters_enable = !!nla_get_u8(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED]); - - return devlink_dpipe_table_counters_set(devlink, table_name, - counters_enable); -} - -static struct devlink_resource * -devlink_resource_find(struct devlink *devlink, - struct devlink_resource *resource, u64 resource_id) -{ - struct list_head *resource_list; - - if (resource) - resource_list = &resource->resource_list; - else - resource_list = &devlink->resource_list; - - list_for_each_entry(resource, resource_list, list) { - struct devlink_resource *child_resource; - - if (resource->id == resource_id) - return resource; - - child_resource = devlink_resource_find(devlink, resource, - resource_id); - if (child_resource) - return child_resource; - } - return NULL; -} - -static void -devlink_resource_validate_children(struct devlink_resource *resource) -{ - struct devlink_resource *child_resource; - bool size_valid = true; - u64 parts_size = 0; - - if (list_empty(&resource->resource_list)) - goto out; - - list_for_each_entry(child_resource, &resource->resource_list, list) - parts_size += child_resource->size_new; - - if (parts_size > resource->size_new) - size_valid = false; -out: - resource->size_valid = size_valid; -} - -static int -devlink_resource_validate_size(struct devlink_resource *resource, u64 size, - struct netlink_ext_ack *extack) -{ - u64 reminder; - int err = 0; - - if (size > resource->size_params.size_max) { - NL_SET_ERR_MSG_MOD(extack, "Size larger than maximum"); - err = -EINVAL; - } - - if (size < resource->size_params.size_min) { - NL_SET_ERR_MSG_MOD(extack, "Size smaller than minimum"); - err = -EINVAL; - } - - div64_u64_rem(size, resource->size_params.size_granularity, &reminder); - if (reminder) { - NL_SET_ERR_MSG_MOD(extack, "Wrong granularity"); - err = -EINVAL; - } - - return err; -} - -static int devlink_nl_cmd_resource_set(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - struct devlink_resource *resource; - u64 resource_id; - u64 size; - int err; - - if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_RESOURCE_ID) || - GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_RESOURCE_SIZE)) - return -EINVAL; - resource_id = nla_get_u64(info->attrs[DEVLINK_ATTR_RESOURCE_ID]); - - resource = devlink_resource_find(devlink, NULL, resource_id); - if (!resource) - return -EINVAL; - - size = nla_get_u64(info->attrs[DEVLINK_ATTR_RESOURCE_SIZE]); - err = devlink_resource_validate_size(resource, size, info->extack); - if (err) - return err; - - resource->size_new = size; - devlink_resource_validate_children(resource); - if (resource->parent) - devlink_resource_validate_children(resource->parent); - return 0; -} - -static int -devlink_resource_size_params_put(struct devlink_resource *resource, - struct sk_buff *skb) -{ - struct devlink_resource_size_params *size_params; - - size_params = &resource->size_params; - if (nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_GRAN, - size_params->size_granularity, DEVLINK_ATTR_PAD) || - nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_MAX, - size_params->size_max, DEVLINK_ATTR_PAD) || - nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_MIN, - size_params->size_min, DEVLINK_ATTR_PAD) || - nla_put_u8(skb, DEVLINK_ATTR_RESOURCE_UNIT, size_params->unit)) - return -EMSGSIZE; - return 0; -} - -static int devlink_resource_occ_put(struct devlink_resource *resource, - struct sk_buff *skb) -{ - if (!resource->occ_get) - return 0; - return nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_OCC, - resource->occ_get(resource->occ_get_priv), - DEVLINK_ATTR_PAD); -} - -static int devlink_resource_put(struct devlink *devlink, struct sk_buff *skb, - struct devlink_resource *resource) -{ - struct devlink_resource *child_resource; - struct nlattr *child_resource_attr; - struct nlattr *resource_attr; - - resource_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_RESOURCE); - if (!resource_attr) - return -EMSGSIZE; - - if (nla_put_string(skb, DEVLINK_ATTR_RESOURCE_NAME, resource->name) || - nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE, resource->size, - DEVLINK_ATTR_PAD) || - nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_ID, resource->id, - DEVLINK_ATTR_PAD)) - goto nla_put_failure; - if (resource->size != resource->size_new) - nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_NEW, - resource->size_new, DEVLINK_ATTR_PAD); - if (devlink_resource_occ_put(resource, skb)) - goto nla_put_failure; - if (devlink_resource_size_params_put(resource, skb)) - goto nla_put_failure; - if (list_empty(&resource->resource_list)) - goto out; - - if (nla_put_u8(skb, DEVLINK_ATTR_RESOURCE_SIZE_VALID, - resource->size_valid)) - goto nla_put_failure; - - child_resource_attr = nla_nest_start_noflag(skb, - DEVLINK_ATTR_RESOURCE_LIST); - if (!child_resource_attr) - goto nla_put_failure; - - list_for_each_entry(child_resource, &resource->resource_list, list) { - if (devlink_resource_put(devlink, skb, child_resource)) - goto resource_put_failure; - } - - nla_nest_end(skb, child_resource_attr); -out: - nla_nest_end(skb, resource_attr); - return 0; - -resource_put_failure: - nla_nest_cancel(skb, child_resource_attr); -nla_put_failure: - nla_nest_cancel(skb, resource_attr); - return -EMSGSIZE; -} - -static int devlink_resource_fill(struct genl_info *info, - enum devlink_command cmd, int flags) -{ - struct devlink *devlink = info->user_ptr[0]; - struct devlink_resource *resource; - struct nlattr *resources_attr; - struct sk_buff *skb = NULL; - struct nlmsghdr *nlh; - bool incomplete; - void *hdr; - int i; - int err; - - resource = list_first_entry(&devlink->resource_list, - struct devlink_resource, list); -start_again: - err = devlink_dpipe_send_and_alloc_skb(&skb, info); - if (err) - return err; - - hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq, - &devlink_nl_family, NLM_F_MULTI, cmd); - if (!hdr) { - nlmsg_free(skb); - return -EMSGSIZE; - } - - if (devlink_nl_put_handle(skb, devlink)) - goto nla_put_failure; - - resources_attr = nla_nest_start_noflag(skb, - DEVLINK_ATTR_RESOURCE_LIST); - if (!resources_attr) - goto nla_put_failure; - - incomplete = false; - i = 0; - list_for_each_entry_from(resource, &devlink->resource_list, list) { - err = devlink_resource_put(devlink, skb, resource); - if (err) { - if (!i) - goto err_resource_put; - incomplete = true; - break; - } - i++; - } - nla_nest_end(skb, resources_attr); - genlmsg_end(skb, hdr); - if (incomplete) - goto start_again; -send_done: - nlh = nlmsg_put(skb, info->snd_portid, info->snd_seq, - NLMSG_DONE, 0, flags | NLM_F_MULTI); - if (!nlh) { - err = devlink_dpipe_send_and_alloc_skb(&skb, info); - if (err) - return err; - goto send_done; - } - return genlmsg_reply(skb, info); - -nla_put_failure: - err = -EMSGSIZE; -err_resource_put: - nlmsg_free(skb); - return err; -} - -static int devlink_nl_cmd_resource_dump(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - - if (list_empty(&devlink->resource_list)) - return -EOPNOTSUPP; - - return devlink_resource_fill(info, DEVLINK_CMD_RESOURCE_DUMP, 0); -} - -static int -devlink_resources_validate(struct devlink *devlink, - struct devlink_resource *resource, - struct genl_info *info) -{ - struct list_head *resource_list; - int err = 0; - - if (resource) - resource_list = &resource->resource_list; - else - resource_list = &devlink->resource_list; - - list_for_each_entry(resource, resource_list, list) { - if (!resource->size_valid) - return -EINVAL; - err = devlink_resources_validate(devlink, resource, info); - if (err) - return err; - } - return err; -} - -static struct net *devlink_netns_get(struct sk_buff *skb, - struct genl_info *info) -{ - struct nlattr *netns_pid_attr = info->attrs[DEVLINK_ATTR_NETNS_PID]; - struct nlattr *netns_fd_attr = info->attrs[DEVLINK_ATTR_NETNS_FD]; - struct nlattr *netns_id_attr = info->attrs[DEVLINK_ATTR_NETNS_ID]; - struct net *net; - - if (!!netns_pid_attr + !!netns_fd_attr + !!netns_id_attr > 1) { - NL_SET_ERR_MSG_MOD(info->extack, "multiple netns identifying attributes specified"); - return ERR_PTR(-EINVAL); - } - - if (netns_pid_attr) { - net = get_net_ns_by_pid(nla_get_u32(netns_pid_attr)); - } else if (netns_fd_attr) { - net = get_net_ns_by_fd(nla_get_u32(netns_fd_attr)); - } else if (netns_id_attr) { - net = get_net_ns_by_id(sock_net(skb->sk), - nla_get_u32(netns_id_attr)); - if (!net) - net = ERR_PTR(-EINVAL); - } else { - WARN_ON(1); - net = ERR_PTR(-EINVAL); - } - if (IS_ERR(net)) { - NL_SET_ERR_MSG_MOD(info->extack, "Unknown network namespace"); - return ERR_PTR(-EINVAL); - } - if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) { - put_net(net); - return ERR_PTR(-EPERM); - } - return net; -} - -static void devlink_param_notify(struct devlink *devlink, - unsigned int port_index, - struct devlink_param_item *param_item, - enum devlink_command cmd); - -static void devlink_ns_change_notify(struct devlink *devlink, - struct net *dest_net, struct net *curr_net, - bool new) -{ - struct devlink_param_item *param_item; - enum devlink_command cmd; - - /* Userspace needs to be notified about devlink objects - * removed from original and entering new network namespace. - * The rest of the devlink objects are re-created during - * reload process so the notifications are generated separatelly. - */ - - if (!dest_net || net_eq(dest_net, curr_net)) - return; - - if (new) - devlink_notify(devlink, DEVLINK_CMD_NEW); - - cmd = new ? DEVLINK_CMD_PARAM_NEW : DEVLINK_CMD_PARAM_DEL; - list_for_each_entry(param_item, &devlink->param_list, list) - devlink_param_notify(devlink, 0, param_item, cmd); - - if (!new) - devlink_notify(devlink, DEVLINK_CMD_DEL); -} - -static bool devlink_reload_supported(const struct devlink_ops *ops) -{ - return ops->reload_down && ops->reload_up; -} - -static void devlink_reload_failed_set(struct devlink *devlink, - bool reload_failed) -{ - if (devlink->reload_failed == reload_failed) - return; - devlink->reload_failed = reload_failed; - devlink_notify(devlink, DEVLINK_CMD_NEW); -} - -bool devlink_is_reload_failed(const struct devlink *devlink) -{ - return devlink->reload_failed; -} -EXPORT_SYMBOL_GPL(devlink_is_reload_failed); - -static void -__devlink_reload_stats_update(struct devlink *devlink, u32 *reload_stats, - enum devlink_reload_limit limit, u32 actions_performed) -{ - unsigned long actions = actions_performed; - int stat_idx; - int action; - - for_each_set_bit(action, &actions, __DEVLINK_RELOAD_ACTION_MAX) { - stat_idx = limit * __DEVLINK_RELOAD_ACTION_MAX + action; - reload_stats[stat_idx]++; - } - devlink_notify(devlink, DEVLINK_CMD_NEW); -} - -static void -devlink_reload_stats_update(struct devlink *devlink, enum devlink_reload_limit limit, - u32 actions_performed) -{ - __devlink_reload_stats_update(devlink, devlink->stats.reload_stats, limit, - actions_performed); -} - -/** - * devlink_remote_reload_actions_performed - Update devlink on reload actions - * performed which are not a direct result of devlink reload call. - * - * This should be called by a driver after performing reload actions in case it was not - * a result of devlink reload call. For example fw_activate was performed as a result - * of devlink reload triggered fw_activate on another host. - * The motivation for this function is to keep data on reload actions performed on this - * function whether it was done due to direct devlink reload call or not. - * - * @devlink: devlink - * @limit: reload limit - * @actions_performed: bitmask of actions performed - */ -void devlink_remote_reload_actions_performed(struct devlink *devlink, - enum devlink_reload_limit limit, - u32 actions_performed) -{ - if (WARN_ON(!actions_performed || - actions_performed & BIT(DEVLINK_RELOAD_ACTION_UNSPEC) || - actions_performed >= BIT(__DEVLINK_RELOAD_ACTION_MAX) || - limit > DEVLINK_RELOAD_LIMIT_MAX)) - return; - - __devlink_reload_stats_update(devlink, devlink->stats.remote_reload_stats, limit, - actions_performed); -} -EXPORT_SYMBOL_GPL(devlink_remote_reload_actions_performed); - -static int devlink_reload(struct devlink *devlink, struct net *dest_net, - enum devlink_reload_action action, enum devlink_reload_limit limit, - u32 *actions_performed, struct netlink_ext_ack *extack) -{ - u32 remote_reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE]; - struct net *curr_net; - int err; - - memcpy(remote_reload_stats, devlink->stats.remote_reload_stats, - sizeof(remote_reload_stats)); - - curr_net = devlink_net(devlink); - devlink_ns_change_notify(devlink, dest_net, curr_net, false); - err = devlink->ops->reload_down(devlink, !!dest_net, action, limit, extack); - if (err) - return err; - - if (dest_net && !net_eq(dest_net, curr_net)) - write_pnet(&devlink->_net, dest_net); - - err = devlink->ops->reload_up(devlink, action, limit, actions_performed, extack); - devlink_reload_failed_set(devlink, !!err); - if (err) - return err; - - devlink_ns_change_notify(devlink, dest_net, curr_net, true); - WARN_ON(!(*actions_performed & BIT(action))); - /* Catch driver on updating the remote action within devlink reload */ - WARN_ON(memcmp(remote_reload_stats, devlink->stats.remote_reload_stats, - sizeof(remote_reload_stats))); - devlink_reload_stats_update(devlink, limit, *actions_performed); - return 0; -} - -static int -devlink_nl_reload_actions_performed_snd(struct devlink *devlink, u32 actions_performed, - enum devlink_command cmd, struct genl_info *info) -{ - struct sk_buff *msg; - void *hdr; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOMEM; - - hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, &devlink_nl_family, 0, cmd); - if (!hdr) - goto free_msg; - - if (devlink_nl_put_handle(msg, devlink)) - goto nla_put_failure; - - if (nla_put_bitfield32(msg, DEVLINK_ATTR_RELOAD_ACTIONS_PERFORMED, actions_performed, - actions_performed)) - goto nla_put_failure; - genlmsg_end(msg, hdr); - - return genlmsg_reply(msg, info); - -nla_put_failure: - genlmsg_cancel(msg, hdr); -free_msg: - nlmsg_free(msg); - return -EMSGSIZE; -} - -static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - enum devlink_reload_action action; - enum devlink_reload_limit limit; - struct net *dest_net = NULL; - u32 actions_performed; - int err; - - if (!(devlink->features & DEVLINK_F_RELOAD)) - return -EOPNOTSUPP; - - err = devlink_resources_validate(devlink, NULL, info); - if (err) { - NL_SET_ERR_MSG_MOD(info->extack, "resources size validation failed"); - return err; - } - - if (info->attrs[DEVLINK_ATTR_RELOAD_ACTION]) - action = nla_get_u8(info->attrs[DEVLINK_ATTR_RELOAD_ACTION]); - else - action = DEVLINK_RELOAD_ACTION_DRIVER_REINIT; - - if (!devlink_reload_action_is_supported(devlink, action)) { - NL_SET_ERR_MSG_MOD(info->extack, - "Requested reload action is not supported by the driver"); - return -EOPNOTSUPP; - } - - limit = DEVLINK_RELOAD_LIMIT_UNSPEC; - if (info->attrs[DEVLINK_ATTR_RELOAD_LIMITS]) { - struct nla_bitfield32 limits; - u32 limits_selected; - - limits = nla_get_bitfield32(info->attrs[DEVLINK_ATTR_RELOAD_LIMITS]); - limits_selected = limits.value & limits.selector; - if (!limits_selected) { - NL_SET_ERR_MSG_MOD(info->extack, "Invalid limit selected"); - return -EINVAL; - } - for (limit = 0 ; limit <= DEVLINK_RELOAD_LIMIT_MAX ; limit++) - if (limits_selected & BIT(limit)) - break; - /* UAPI enables multiselection, but currently it is not used */ - if (limits_selected != BIT(limit)) { - NL_SET_ERR_MSG_MOD(info->extack, - "Multiselection of limit is not supported"); - return -EOPNOTSUPP; - } - if (!devlink_reload_limit_is_supported(devlink, limit)) { - NL_SET_ERR_MSG_MOD(info->extack, - "Requested limit is not supported by the driver"); - return -EOPNOTSUPP; - } - if (devlink_reload_combination_is_invalid(action, limit)) { - NL_SET_ERR_MSG_MOD(info->extack, - "Requested limit is invalid for this action"); - return -EINVAL; - } - } - if (info->attrs[DEVLINK_ATTR_NETNS_PID] || - info->attrs[DEVLINK_ATTR_NETNS_FD] || - info->attrs[DEVLINK_ATTR_NETNS_ID]) { - dest_net = devlink_netns_get(skb, info); - if (IS_ERR(dest_net)) - return PTR_ERR(dest_net); - } - - err = devlink_reload(devlink, dest_net, action, limit, &actions_performed, info->extack); - - if (dest_net) - put_net(dest_net); - - if (err) - return err; - /* For backward compatibility generate reply only if attributes used by user */ - if (!info->attrs[DEVLINK_ATTR_RELOAD_ACTION] && !info->attrs[DEVLINK_ATTR_RELOAD_LIMITS]) - return 0; - - return devlink_nl_reload_actions_performed_snd(devlink, actions_performed, - DEVLINK_CMD_RELOAD, info); -} - -static int devlink_nl_flash_update_fill(struct sk_buff *msg, - struct devlink *devlink, - enum devlink_command cmd, - struct devlink_flash_notify *params) -{ - void *hdr; - - hdr = genlmsg_put(msg, 0, 0, &devlink_nl_family, 0, cmd); - if (!hdr) - return -EMSGSIZE; - - if (devlink_nl_put_handle(msg, devlink)) - goto nla_put_failure; - - if (cmd != DEVLINK_CMD_FLASH_UPDATE_STATUS) - goto out; - - if (params->status_msg && - nla_put_string(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_MSG, - params->status_msg)) - goto nla_put_failure; - if (params->component && - nla_put_string(msg, DEVLINK_ATTR_FLASH_UPDATE_COMPONENT, - params->component)) - goto nla_put_failure; - if (nla_put_u64_64bit(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_DONE, - params->done, DEVLINK_ATTR_PAD)) - goto nla_put_failure; - if (nla_put_u64_64bit(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_TOTAL, - params->total, DEVLINK_ATTR_PAD)) - goto nla_put_failure; - if (nla_put_u64_64bit(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_TIMEOUT, - params->timeout, DEVLINK_ATTR_PAD)) - goto nla_put_failure; - -out: - genlmsg_end(msg, hdr); - return 0; - -nla_put_failure: - genlmsg_cancel(msg, hdr); - return -EMSGSIZE; -} - -static void __devlink_flash_update_notify(struct devlink *devlink, - enum devlink_command cmd, - struct devlink_flash_notify *params) -{ - struct sk_buff *msg; - int err; - - WARN_ON(cmd != DEVLINK_CMD_FLASH_UPDATE && - cmd != DEVLINK_CMD_FLASH_UPDATE_END && - cmd != DEVLINK_CMD_FLASH_UPDATE_STATUS); - - if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)) - return; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return; - - err = devlink_nl_flash_update_fill(msg, devlink, cmd, params); - if (err) - goto out_free_msg; - - genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), - msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); - return; - -out_free_msg: - nlmsg_free(msg); -} - -static void devlink_flash_update_begin_notify(struct devlink *devlink) -{ - struct devlink_flash_notify params = {}; - - __devlink_flash_update_notify(devlink, - DEVLINK_CMD_FLASH_UPDATE, - &params); -} - -static void devlink_flash_update_end_notify(struct devlink *devlink) -{ - struct devlink_flash_notify params = {}; - - __devlink_flash_update_notify(devlink, - DEVLINK_CMD_FLASH_UPDATE_END, - &params); -} - -void devlink_flash_update_status_notify(struct devlink *devlink, - const char *status_msg, - const char *component, - unsigned long done, - unsigned long total) -{ - struct devlink_flash_notify params = { - .status_msg = status_msg, - .component = component, - .done = done, - .total = total, - }; - - __devlink_flash_update_notify(devlink, - DEVLINK_CMD_FLASH_UPDATE_STATUS, - &params); -} -EXPORT_SYMBOL_GPL(devlink_flash_update_status_notify); - -void devlink_flash_update_timeout_notify(struct devlink *devlink, - const char *status_msg, - const char *component, - unsigned long timeout) -{ - struct devlink_flash_notify params = { - .status_msg = status_msg, - .component = component, - .timeout = timeout, - }; - - __devlink_flash_update_notify(devlink, - DEVLINK_CMD_FLASH_UPDATE_STATUS, - &params); -} -EXPORT_SYMBOL_GPL(devlink_flash_update_timeout_notify); - -struct devlink_info_req { - struct sk_buff *msg; - void (*version_cb)(const char *version_name, - enum devlink_info_version_type version_type, - void *version_cb_priv); - void *version_cb_priv; -}; - -struct devlink_flash_component_lookup_ctx { - const char *lookup_name; - bool lookup_name_found; -}; - -static void -devlink_flash_component_lookup_cb(const char *version_name, - enum devlink_info_version_type version_type, - void *version_cb_priv) -{ - struct devlink_flash_component_lookup_ctx *lookup_ctx = version_cb_priv; - - if (version_type != DEVLINK_INFO_VERSION_TYPE_COMPONENT || - lookup_ctx->lookup_name_found) - return; - - lookup_ctx->lookup_name_found = - !strcmp(lookup_ctx->lookup_name, version_name); -} - -static int devlink_flash_component_get(struct devlink *devlink, - struct nlattr *nla_component, - const char **p_component, - struct netlink_ext_ack *extack) -{ - struct devlink_flash_component_lookup_ctx lookup_ctx = {}; - struct devlink_info_req req = {}; - const char *component; - int ret; - - if (!nla_component) - return 0; - - component = nla_data(nla_component); - - if (!devlink->ops->info_get) { - NL_SET_ERR_MSG_ATTR(extack, nla_component, - "component update is not supported by this device"); - return -EOPNOTSUPP; - } - - lookup_ctx.lookup_name = component; - req.version_cb = devlink_flash_component_lookup_cb; - req.version_cb_priv = &lookup_ctx; - - ret = devlink->ops->info_get(devlink, &req, NULL); - if (ret) - return ret; - - if (!lookup_ctx.lookup_name_found) { - NL_SET_ERR_MSG_ATTR(extack, nla_component, - "selected component is not supported by this device"); - return -EINVAL; - } - *p_component = component; - return 0; -} - -static int devlink_nl_cmd_flash_update(struct sk_buff *skb, - struct genl_info *info) -{ - struct nlattr *nla_overwrite_mask, *nla_file_name; - struct devlink_flash_update_params params = {}; - struct devlink *devlink = info->user_ptr[0]; - const char *file_name; - u32 supported_params; - int ret; - - if (!devlink->ops->flash_update) - return -EOPNOTSUPP; - - if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME)) - return -EINVAL; - - ret = devlink_flash_component_get(devlink, - info->attrs[DEVLINK_ATTR_FLASH_UPDATE_COMPONENT], - &params.component, info->extack); - if (ret) - return ret; - - supported_params = devlink->ops->supported_flash_update_params; - - nla_overwrite_mask = info->attrs[DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK]; - if (nla_overwrite_mask) { - struct nla_bitfield32 sections; - - if (!(supported_params & DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK)) { - NL_SET_ERR_MSG_ATTR(info->extack, nla_overwrite_mask, - "overwrite settings are not supported by this device"); - return -EOPNOTSUPP; - } - sections = nla_get_bitfield32(nla_overwrite_mask); - params.overwrite_mask = sections.value & sections.selector; - } - - nla_file_name = info->attrs[DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME]; - file_name = nla_data(nla_file_name); - ret = request_firmware(&params.fw, file_name, devlink->dev); - if (ret) { - NL_SET_ERR_MSG_ATTR(info->extack, nla_file_name, "failed to locate the requested firmware file"); - return ret; - } - - devlink_flash_update_begin_notify(devlink); - ret = devlink->ops->flash_update(devlink, &params, info->extack); - devlink_flash_update_end_notify(devlink); - - release_firmware(params.fw); - - return ret; -} - -static int -devlink_nl_selftests_fill(struct sk_buff *msg, struct devlink *devlink, - u32 portid, u32 seq, int flags, - struct netlink_ext_ack *extack) -{ - struct nlattr *selftests; - void *hdr; - int err; - int i; - - hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, - DEVLINK_CMD_SELFTESTS_GET); - if (!hdr) - return -EMSGSIZE; - - err = -EMSGSIZE; - if (devlink_nl_put_handle(msg, devlink)) - goto err_cancel_msg; - - selftests = nla_nest_start(msg, DEVLINK_ATTR_SELFTESTS); - if (!selftests) - goto err_cancel_msg; - - for (i = DEVLINK_ATTR_SELFTEST_ID_UNSPEC + 1; - i <= DEVLINK_ATTR_SELFTEST_ID_MAX; i++) { - if (devlink->ops->selftest_check(devlink, i, extack)) { - err = nla_put_flag(msg, i); - if (err) - goto err_cancel_msg; - } - } - - nla_nest_end(msg, selftests); - genlmsg_end(msg, hdr); - return 0; - -err_cancel_msg: - genlmsg_cancel(msg, hdr); - return err; -} - -static int devlink_nl_cmd_selftests_get_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - struct sk_buff *msg; - int err; - - if (!devlink->ops->selftest_check) - return -EOPNOTSUPP; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOMEM; - - err = devlink_nl_selftests_fill(msg, devlink, info->snd_portid, - info->snd_seq, 0, info->extack); - if (err) { - nlmsg_free(msg); - return err; - } - - return genlmsg_reply(msg, info); -} - -static int devlink_nl_cmd_selftests_get_dumpit(struct sk_buff *msg, - struct netlink_callback *cb) -{ - struct devlink *devlink; - int start = cb->args[0]; - unsigned long index; - int idx = 0; - int err = 0; - - devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { - if (idx < start || !devlink->ops->selftest_check) - goto inc; - - devl_lock(devlink); - err = devlink_nl_selftests_fill(msg, devlink, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI, - cb->extack); - devl_unlock(devlink); - if (err) { - devlink_put(devlink); - break; - } -inc: - idx++; - devlink_put(devlink); - } - - if (err != -EMSGSIZE) - return err; - - cb->args[0] = idx; - return msg->len; -} - -static int devlink_selftest_result_put(struct sk_buff *skb, unsigned int id, - enum devlink_selftest_status test_status) -{ - struct nlattr *result_attr; - - result_attr = nla_nest_start(skb, DEVLINK_ATTR_SELFTEST_RESULT); - if (!result_attr) - return -EMSGSIZE; - - if (nla_put_u32(skb, DEVLINK_ATTR_SELFTEST_RESULT_ID, id) || - nla_put_u8(skb, DEVLINK_ATTR_SELFTEST_RESULT_STATUS, - test_status)) - goto nla_put_failure; - - nla_nest_end(skb, result_attr); - return 0; - -nla_put_failure: - nla_nest_cancel(skb, result_attr); - return -EMSGSIZE; -} - -static int devlink_nl_cmd_selftests_run(struct sk_buff *skb, - struct genl_info *info) -{ - struct nlattr *tb[DEVLINK_ATTR_SELFTEST_ID_MAX + 1]; - struct devlink *devlink = info->user_ptr[0]; - struct nlattr *attrs, *selftests; - struct sk_buff *msg; - void *hdr; - int err; - int i; - - if (!devlink->ops->selftest_run || !devlink->ops->selftest_check) - return -EOPNOTSUPP; - - if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_SELFTESTS)) - return -EINVAL; - - attrs = info->attrs[DEVLINK_ATTR_SELFTESTS]; - - err = nla_parse_nested(tb, DEVLINK_ATTR_SELFTEST_ID_MAX, attrs, - devlink_selftest_nl_policy, info->extack); - if (err < 0) - return err; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOMEM; - - err = -EMSGSIZE; - hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, - &devlink_nl_family, 0, DEVLINK_CMD_SELFTESTS_RUN); - if (!hdr) - goto free_msg; - - if (devlink_nl_put_handle(msg, devlink)) - goto genlmsg_cancel; - - selftests = nla_nest_start(msg, DEVLINK_ATTR_SELFTESTS); - if (!selftests) - goto genlmsg_cancel; - - for (i = DEVLINK_ATTR_SELFTEST_ID_UNSPEC + 1; - i <= DEVLINK_ATTR_SELFTEST_ID_MAX; i++) { - enum devlink_selftest_status test_status; - - if (nla_get_flag(tb[i])) { - if (!devlink->ops->selftest_check(devlink, i, - info->extack)) { - if (devlink_selftest_result_put(msg, i, - DEVLINK_SELFTEST_STATUS_SKIP)) - goto selftests_nest_cancel; - continue; - } - - test_status = devlink->ops->selftest_run(devlink, i, - info->extack); - if (devlink_selftest_result_put(msg, i, test_status)) - goto selftests_nest_cancel; - } - } - - nla_nest_end(msg, selftests); - genlmsg_end(msg, hdr); - return genlmsg_reply(msg, info); - -selftests_nest_cancel: - nla_nest_cancel(msg, selftests); -genlmsg_cancel: - genlmsg_cancel(msg, hdr); -free_msg: - nlmsg_free(msg); - return err; -} - -static const struct devlink_param devlink_param_generic[] = { - { - .id = DEVLINK_PARAM_GENERIC_ID_INT_ERR_RESET, - .name = DEVLINK_PARAM_GENERIC_INT_ERR_RESET_NAME, - .type = DEVLINK_PARAM_GENERIC_INT_ERR_RESET_TYPE, - }, - { - .id = DEVLINK_PARAM_GENERIC_ID_MAX_MACS, - .name = DEVLINK_PARAM_GENERIC_MAX_MACS_NAME, - .type = DEVLINK_PARAM_GENERIC_MAX_MACS_TYPE, - }, - { - .id = DEVLINK_PARAM_GENERIC_ID_ENABLE_SRIOV, - .name = DEVLINK_PARAM_GENERIC_ENABLE_SRIOV_NAME, - .type = DEVLINK_PARAM_GENERIC_ENABLE_SRIOV_TYPE, - }, - { - .id = DEVLINK_PARAM_GENERIC_ID_REGION_SNAPSHOT, - .name = DEVLINK_PARAM_GENERIC_REGION_SNAPSHOT_NAME, - .type = DEVLINK_PARAM_GENERIC_REGION_SNAPSHOT_TYPE, - }, - { - .id = DEVLINK_PARAM_GENERIC_ID_IGNORE_ARI, - .name = DEVLINK_PARAM_GENERIC_IGNORE_ARI_NAME, - .type = DEVLINK_PARAM_GENERIC_IGNORE_ARI_TYPE, - }, - { - .id = DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MAX, - .name = DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MAX_NAME, - .type = DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MAX_TYPE, - }, - { - .id = DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN, - .name = DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MIN_NAME, - .type = DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MIN_TYPE, - }, - { - .id = DEVLINK_PARAM_GENERIC_ID_FW_LOAD_POLICY, - .name = DEVLINK_PARAM_GENERIC_FW_LOAD_POLICY_NAME, - .type = DEVLINK_PARAM_GENERIC_FW_LOAD_POLICY_TYPE, - }, - { - .id = DEVLINK_PARAM_GENERIC_ID_RESET_DEV_ON_DRV_PROBE, - .name = DEVLINK_PARAM_GENERIC_RESET_DEV_ON_DRV_PROBE_NAME, - .type = DEVLINK_PARAM_GENERIC_RESET_DEV_ON_DRV_PROBE_TYPE, - }, - { - .id = DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE, - .name = DEVLINK_PARAM_GENERIC_ENABLE_ROCE_NAME, - .type = DEVLINK_PARAM_GENERIC_ENABLE_ROCE_TYPE, - }, - { - .id = DEVLINK_PARAM_GENERIC_ID_ENABLE_REMOTE_DEV_RESET, - .name = DEVLINK_PARAM_GENERIC_ENABLE_REMOTE_DEV_RESET_NAME, - .type = DEVLINK_PARAM_GENERIC_ENABLE_REMOTE_DEV_RESET_TYPE, - }, - { - .id = DEVLINK_PARAM_GENERIC_ID_ENABLE_ETH, - .name = DEVLINK_PARAM_GENERIC_ENABLE_ETH_NAME, - .type = DEVLINK_PARAM_GENERIC_ENABLE_ETH_TYPE, - }, - { - .id = DEVLINK_PARAM_GENERIC_ID_ENABLE_RDMA, - .name = DEVLINK_PARAM_GENERIC_ENABLE_RDMA_NAME, - .type = DEVLINK_PARAM_GENERIC_ENABLE_RDMA_TYPE, - }, - { - .id = DEVLINK_PARAM_GENERIC_ID_ENABLE_VNET, - .name = DEVLINK_PARAM_GENERIC_ENABLE_VNET_NAME, - .type = DEVLINK_PARAM_GENERIC_ENABLE_VNET_TYPE, - }, - { - .id = DEVLINK_PARAM_GENERIC_ID_ENABLE_IWARP, - .name = DEVLINK_PARAM_GENERIC_ENABLE_IWARP_NAME, - .type = DEVLINK_PARAM_GENERIC_ENABLE_IWARP_TYPE, - }, - { - .id = DEVLINK_PARAM_GENERIC_ID_IO_EQ_SIZE, - .name = DEVLINK_PARAM_GENERIC_IO_EQ_SIZE_NAME, - .type = DEVLINK_PARAM_GENERIC_IO_EQ_SIZE_TYPE, - }, - { - .id = DEVLINK_PARAM_GENERIC_ID_EVENT_EQ_SIZE, - .name = DEVLINK_PARAM_GENERIC_EVENT_EQ_SIZE_NAME, - .type = DEVLINK_PARAM_GENERIC_EVENT_EQ_SIZE_TYPE, - }, -}; - -static int devlink_param_generic_verify(const struct devlink_param *param) -{ - /* verify it match generic parameter by id and name */ - if (param->id > DEVLINK_PARAM_GENERIC_ID_MAX) - return -EINVAL; - if (strcmp(param->name, devlink_param_generic[param->id].name)) - return -ENOENT; - - WARN_ON(param->type != devlink_param_generic[param->id].type); - - return 0; -} - -static int devlink_param_driver_verify(const struct devlink_param *param) -{ - int i; - - if (param->id <= DEVLINK_PARAM_GENERIC_ID_MAX) - return -EINVAL; - /* verify no such name in generic params */ - for (i = 0; i <= DEVLINK_PARAM_GENERIC_ID_MAX; i++) - if (!strcmp(param->name, devlink_param_generic[i].name)) - return -EEXIST; - - return 0; -} - -static struct devlink_param_item * -devlink_param_find_by_name(struct list_head *param_list, - const char *param_name) -{ - struct devlink_param_item *param_item; - - list_for_each_entry(param_item, param_list, list) - if (!strcmp(param_item->param->name, param_name)) - return param_item; - return NULL; -} - -static struct devlink_param_item * -devlink_param_find_by_id(struct list_head *param_list, u32 param_id) -{ - struct devlink_param_item *param_item; - - list_for_each_entry(param_item, param_list, list) - if (param_item->param->id == param_id) - return param_item; - return NULL; -} - -static bool -devlink_param_cmode_is_supported(const struct devlink_param *param, - enum devlink_param_cmode cmode) -{ - return test_bit(cmode, &param->supported_cmodes); -} - -static int devlink_param_get(struct devlink *devlink, - const struct devlink_param *param, - struct devlink_param_gset_ctx *ctx) -{ - if (!param->get || devlink->reload_failed) - return -EOPNOTSUPP; - return param->get(devlink, param->id, ctx); -} - -static int devlink_param_set(struct devlink *devlink, - const struct devlink_param *param, - struct devlink_param_gset_ctx *ctx) -{ - if (!param->set || devlink->reload_failed) - return -EOPNOTSUPP; - return param->set(devlink, param->id, ctx); -} - -static int -devlink_param_type_to_nla_type(enum devlink_param_type param_type) -{ - switch (param_type) { - case DEVLINK_PARAM_TYPE_U8: - return NLA_U8; - case DEVLINK_PARAM_TYPE_U16: - return NLA_U16; - case DEVLINK_PARAM_TYPE_U32: - return NLA_U32; - case DEVLINK_PARAM_TYPE_STRING: - return NLA_STRING; - case DEVLINK_PARAM_TYPE_BOOL: - return NLA_FLAG; - default: - return -EINVAL; - } -} - -static int -devlink_nl_param_value_fill_one(struct sk_buff *msg, - enum devlink_param_type type, - enum devlink_param_cmode cmode, - union devlink_param_value val) -{ - struct nlattr *param_value_attr; - - param_value_attr = nla_nest_start_noflag(msg, - DEVLINK_ATTR_PARAM_VALUE); - if (!param_value_attr) - goto nla_put_failure; - - if (nla_put_u8(msg, DEVLINK_ATTR_PARAM_VALUE_CMODE, cmode)) - goto value_nest_cancel; - - switch (type) { - case DEVLINK_PARAM_TYPE_U8: - if (nla_put_u8(msg, DEVLINK_ATTR_PARAM_VALUE_DATA, val.vu8)) - goto value_nest_cancel; - break; - case DEVLINK_PARAM_TYPE_U16: - if (nla_put_u16(msg, DEVLINK_ATTR_PARAM_VALUE_DATA, val.vu16)) - goto value_nest_cancel; - break; - case DEVLINK_PARAM_TYPE_U32: - if (nla_put_u32(msg, DEVLINK_ATTR_PARAM_VALUE_DATA, val.vu32)) - goto value_nest_cancel; - break; - case DEVLINK_PARAM_TYPE_STRING: - if (nla_put_string(msg, DEVLINK_ATTR_PARAM_VALUE_DATA, - val.vstr)) - goto value_nest_cancel; - break; - case DEVLINK_PARAM_TYPE_BOOL: - if (val.vbool && - nla_put_flag(msg, DEVLINK_ATTR_PARAM_VALUE_DATA)) - goto value_nest_cancel; - break; - } - - nla_nest_end(msg, param_value_attr); - return 0; - -value_nest_cancel: - nla_nest_cancel(msg, param_value_attr); -nla_put_failure: - return -EMSGSIZE; -} - -static int devlink_nl_param_fill(struct sk_buff *msg, struct devlink *devlink, - unsigned int port_index, - struct devlink_param_item *param_item, - enum devlink_command cmd, - u32 portid, u32 seq, int flags) -{ - union devlink_param_value param_value[DEVLINK_PARAM_CMODE_MAX + 1]; - bool param_value_set[DEVLINK_PARAM_CMODE_MAX + 1] = {}; - const struct devlink_param *param = param_item->param; - struct devlink_param_gset_ctx ctx; - struct nlattr *param_values_list; - struct nlattr *param_attr; - int nla_type; - void *hdr; - int err; - int i; - - /* Get value from driver part to driverinit configuration mode */ - for (i = 0; i <= DEVLINK_PARAM_CMODE_MAX; i++) { - if (!devlink_param_cmode_is_supported(param, i)) - continue; - if (i == DEVLINK_PARAM_CMODE_DRIVERINIT) { - if (!param_item->driverinit_value_valid) - return -EOPNOTSUPP; - param_value[i] = param_item->driverinit_value; - } else { - ctx.cmode = i; - err = devlink_param_get(devlink, param, &ctx); - if (err) - return err; - param_value[i] = ctx.val; - } - param_value_set[i] = true; - } - - hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); - if (!hdr) - return -EMSGSIZE; - - if (devlink_nl_put_handle(msg, devlink)) - goto genlmsg_cancel; - - if (cmd == DEVLINK_CMD_PORT_PARAM_GET || - cmd == DEVLINK_CMD_PORT_PARAM_NEW || - cmd == DEVLINK_CMD_PORT_PARAM_DEL) - if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, port_index)) - goto genlmsg_cancel; - - param_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_PARAM); - if (!param_attr) - goto genlmsg_cancel; - if (nla_put_string(msg, DEVLINK_ATTR_PARAM_NAME, param->name)) - goto param_nest_cancel; - if (param->generic && nla_put_flag(msg, DEVLINK_ATTR_PARAM_GENERIC)) - goto param_nest_cancel; - - nla_type = devlink_param_type_to_nla_type(param->type); - if (nla_type < 0) - goto param_nest_cancel; - if (nla_put_u8(msg, DEVLINK_ATTR_PARAM_TYPE, nla_type)) - goto param_nest_cancel; - - param_values_list = nla_nest_start_noflag(msg, - DEVLINK_ATTR_PARAM_VALUES_LIST); - if (!param_values_list) - goto param_nest_cancel; - - for (i = 0; i <= DEVLINK_PARAM_CMODE_MAX; i++) { - if (!param_value_set[i]) - continue; - err = devlink_nl_param_value_fill_one(msg, param->type, - i, param_value[i]); - if (err) - goto values_list_nest_cancel; - } - - nla_nest_end(msg, param_values_list); - nla_nest_end(msg, param_attr); - genlmsg_end(msg, hdr); - return 0; - -values_list_nest_cancel: - nla_nest_end(msg, param_values_list); -param_nest_cancel: - nla_nest_cancel(msg, param_attr); -genlmsg_cancel: - genlmsg_cancel(msg, hdr); - return -EMSGSIZE; -} - -static void devlink_param_notify(struct devlink *devlink, - unsigned int port_index, - struct devlink_param_item *param_item, - enum devlink_command cmd) -{ - struct sk_buff *msg; - int err; - - WARN_ON(cmd != DEVLINK_CMD_PARAM_NEW && cmd != DEVLINK_CMD_PARAM_DEL && - cmd != DEVLINK_CMD_PORT_PARAM_NEW && - cmd != DEVLINK_CMD_PORT_PARAM_DEL); - ASSERT_DEVLINK_REGISTERED(devlink); - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return; - err = devlink_nl_param_fill(msg, devlink, port_index, param_item, cmd, - 0, 0, 0); - if (err) { - nlmsg_free(msg); - return; - } - - genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), - msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); -} - -static int devlink_nl_cmd_param_get_dumpit(struct sk_buff *msg, - struct netlink_callback *cb) -{ - struct devlink_param_item *param_item; - struct devlink *devlink; - int start = cb->args[0]; - unsigned long index; - int idx = 0; - int err = 0; - - devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { - devl_lock(devlink); - list_for_each_entry(param_item, &devlink->param_list, list) { - if (idx < start) { - idx++; - continue; - } - err = devlink_nl_param_fill(msg, devlink, 0, param_item, - DEVLINK_CMD_PARAM_GET, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - NLM_F_MULTI); - if (err == -EOPNOTSUPP) { - err = 0; - } else if (err) { - devl_unlock(devlink); - devlink_put(devlink); - goto out; - } - idx++; - } - devl_unlock(devlink); - devlink_put(devlink); - } -out: - if (err != -EMSGSIZE) - return err; - - cb->args[0] = idx; - return msg->len; -} - -static int -devlink_param_type_get_from_info(struct genl_info *info, - enum devlink_param_type *param_type) -{ - if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_PARAM_TYPE)) - return -EINVAL; - - switch (nla_get_u8(info->attrs[DEVLINK_ATTR_PARAM_TYPE])) { - case NLA_U8: - *param_type = DEVLINK_PARAM_TYPE_U8; - break; - case NLA_U16: - *param_type = DEVLINK_PARAM_TYPE_U16; - break; - case NLA_U32: - *param_type = DEVLINK_PARAM_TYPE_U32; - break; - case NLA_STRING: - *param_type = DEVLINK_PARAM_TYPE_STRING; - break; - case NLA_FLAG: - *param_type = DEVLINK_PARAM_TYPE_BOOL; - break; - default: - return -EINVAL; - } - - return 0; -} - -static int -devlink_param_value_get_from_info(const struct devlink_param *param, - struct genl_info *info, - union devlink_param_value *value) -{ - struct nlattr *param_data; - int len; - - param_data = info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]; - - if (param->type != DEVLINK_PARAM_TYPE_BOOL && !param_data) - return -EINVAL; - - switch (param->type) { - case DEVLINK_PARAM_TYPE_U8: - if (nla_len(param_data) != sizeof(u8)) - return -EINVAL; - value->vu8 = nla_get_u8(param_data); - break; - case DEVLINK_PARAM_TYPE_U16: - if (nla_len(param_data) != sizeof(u16)) - return -EINVAL; - value->vu16 = nla_get_u16(param_data); - break; - case DEVLINK_PARAM_TYPE_U32: - if (nla_len(param_data) != sizeof(u32)) - return -EINVAL; - value->vu32 = nla_get_u32(param_data); - break; - case DEVLINK_PARAM_TYPE_STRING: - len = strnlen(nla_data(param_data), nla_len(param_data)); - if (len == nla_len(param_data) || - len >= __DEVLINK_PARAM_MAX_STRING_VALUE) - return -EINVAL; - strcpy(value->vstr, nla_data(param_data)); - break; - case DEVLINK_PARAM_TYPE_BOOL: - if (param_data && nla_len(param_data)) - return -EINVAL; - value->vbool = nla_get_flag(param_data); - break; - } - return 0; -} - -static struct devlink_param_item * -devlink_param_get_from_info(struct list_head *param_list, - struct genl_info *info) -{ - char *param_name; - - if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_PARAM_NAME)) - return NULL; - - param_name = nla_data(info->attrs[DEVLINK_ATTR_PARAM_NAME]); - return devlink_param_find_by_name(param_list, param_name); -} - -static int devlink_nl_cmd_param_get_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - struct devlink_param_item *param_item; - struct sk_buff *msg; - int err; - - param_item = devlink_param_get_from_info(&devlink->param_list, info); - if (!param_item) - return -EINVAL; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOMEM; - - err = devlink_nl_param_fill(msg, devlink, 0, param_item, - DEVLINK_CMD_PARAM_GET, - info->snd_portid, info->snd_seq, 0); - if (err) { - nlmsg_free(msg); - return err; - } - - return genlmsg_reply(msg, info); -} - -static int __devlink_nl_cmd_param_set_doit(struct devlink *devlink, - unsigned int port_index, - struct list_head *param_list, - struct genl_info *info, - enum devlink_command cmd) -{ - enum devlink_param_type param_type; - struct devlink_param_gset_ctx ctx; - enum devlink_param_cmode cmode; - struct devlink_param_item *param_item; - const struct devlink_param *param; - union devlink_param_value value; - int err = 0; - - param_item = devlink_param_get_from_info(param_list, info); - if (!param_item) - return -EINVAL; - param = param_item->param; - err = devlink_param_type_get_from_info(info, &param_type); - if (err) - return err; - if (param_type != param->type) - return -EINVAL; - err = devlink_param_value_get_from_info(param, info, &value); - if (err) - return err; - if (param->validate) { - err = param->validate(devlink, param->id, value, info->extack); - if (err) - return err; - } - - if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_PARAM_VALUE_CMODE)) - return -EINVAL; - cmode = nla_get_u8(info->attrs[DEVLINK_ATTR_PARAM_VALUE_CMODE]); - if (!devlink_param_cmode_is_supported(param, cmode)) - return -EOPNOTSUPP; - - if (cmode == DEVLINK_PARAM_CMODE_DRIVERINIT) { - if (param->type == DEVLINK_PARAM_TYPE_STRING) - strcpy(param_item->driverinit_value.vstr, value.vstr); - else - param_item->driverinit_value = value; - param_item->driverinit_value_valid = true; - } else { - if (!param->set) - return -EOPNOTSUPP; - ctx.val = value; - ctx.cmode = cmode; - err = devlink_param_set(devlink, param, &ctx); - if (err) - return err; - } - - devlink_param_notify(devlink, port_index, param_item, cmd); - return 0; -} - -static int devlink_nl_cmd_param_set_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - - return __devlink_nl_cmd_param_set_doit(devlink, 0, &devlink->param_list, - info, DEVLINK_CMD_PARAM_NEW); -} - -static int devlink_nl_cmd_port_param_get_dumpit(struct sk_buff *msg, - struct netlink_callback *cb) -{ - NL_SET_ERR_MSG_MOD(cb->extack, "Port params are not supported"); - return msg->len; -} - -static int devlink_nl_cmd_port_param_get_doit(struct sk_buff *skb, - struct genl_info *info) -{ - NL_SET_ERR_MSG_MOD(info->extack, "Port params are not supported"); - return -EINVAL; -} - -static int devlink_nl_cmd_port_param_set_doit(struct sk_buff *skb, - struct genl_info *info) -{ - NL_SET_ERR_MSG_MOD(info->extack, "Port params are not supported"); - return -EINVAL; -} - -static int devlink_nl_region_snapshot_id_put(struct sk_buff *msg, - struct devlink *devlink, - struct devlink_snapshot *snapshot) -{ - struct nlattr *snap_attr; - int err; - - snap_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_REGION_SNAPSHOT); - if (!snap_attr) - return -EINVAL; - - err = nla_put_u32(msg, DEVLINK_ATTR_REGION_SNAPSHOT_ID, snapshot->id); - if (err) - goto nla_put_failure; - - nla_nest_end(msg, snap_attr); - return 0; - -nla_put_failure: - nla_nest_cancel(msg, snap_attr); - return err; -} - -static int devlink_nl_region_snapshots_id_put(struct sk_buff *msg, - struct devlink *devlink, - struct devlink_region *region) -{ - struct devlink_snapshot *snapshot; - struct nlattr *snapshots_attr; - int err; - - snapshots_attr = nla_nest_start_noflag(msg, - DEVLINK_ATTR_REGION_SNAPSHOTS); - if (!snapshots_attr) - return -EINVAL; - - list_for_each_entry(snapshot, &region->snapshot_list, list) { - err = devlink_nl_region_snapshot_id_put(msg, devlink, snapshot); - if (err) - goto nla_put_failure; - } - - nla_nest_end(msg, snapshots_attr); - return 0; - -nla_put_failure: - nla_nest_cancel(msg, snapshots_attr); - return err; -} - -static int devlink_nl_region_fill(struct sk_buff *msg, struct devlink *devlink, - enum devlink_command cmd, u32 portid, - u32 seq, int flags, - struct devlink_region *region) -{ - void *hdr; - int err; - - hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); - if (!hdr) - return -EMSGSIZE; - - err = devlink_nl_put_handle(msg, devlink); - if (err) - goto nla_put_failure; - - if (region->port) { - err = nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, - region->port->index); - if (err) - goto nla_put_failure; - } - - err = nla_put_string(msg, DEVLINK_ATTR_REGION_NAME, region->ops->name); - if (err) - goto nla_put_failure; - - err = nla_put_u64_64bit(msg, DEVLINK_ATTR_REGION_SIZE, - region->size, - DEVLINK_ATTR_PAD); - if (err) - goto nla_put_failure; - - err = nla_put_u32(msg, DEVLINK_ATTR_REGION_MAX_SNAPSHOTS, - region->max_snapshots); - if (err) - goto nla_put_failure; - - err = devlink_nl_region_snapshots_id_put(msg, devlink, region); - if (err) - goto nla_put_failure; - - genlmsg_end(msg, hdr); - return 0; - -nla_put_failure: - genlmsg_cancel(msg, hdr); - return err; -} - -static struct sk_buff * -devlink_nl_region_notify_build(struct devlink_region *region, - struct devlink_snapshot *snapshot, - enum devlink_command cmd, u32 portid, u32 seq) -{ - struct devlink *devlink = region->devlink; - struct sk_buff *msg; - void *hdr; - int err; - - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return ERR_PTR(-ENOMEM); - - hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, 0, cmd); - if (!hdr) { - err = -EMSGSIZE; - goto out_free_msg; - } - - err = devlink_nl_put_handle(msg, devlink); - if (err) - goto out_cancel_msg; - - if (region->port) { - err = nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, - region->port->index); - if (err) - goto out_cancel_msg; - } - - err = nla_put_string(msg, DEVLINK_ATTR_REGION_NAME, - region->ops->name); - if (err) - goto out_cancel_msg; - - if (snapshot) { - err = nla_put_u32(msg, DEVLINK_ATTR_REGION_SNAPSHOT_ID, - snapshot->id); - if (err) - goto out_cancel_msg; - } else { - err = nla_put_u64_64bit(msg, DEVLINK_ATTR_REGION_SIZE, - region->size, DEVLINK_ATTR_PAD); - if (err) - goto out_cancel_msg; - } - genlmsg_end(msg, hdr); - - return msg; - -out_cancel_msg: - genlmsg_cancel(msg, hdr); -out_free_msg: - nlmsg_free(msg); - return ERR_PTR(err); -} - -static void devlink_nl_region_notify(struct devlink_region *region, - struct devlink_snapshot *snapshot, - enum devlink_command cmd) -{ - struct devlink *devlink = region->devlink; - struct sk_buff *msg; - - WARN_ON(cmd != DEVLINK_CMD_REGION_NEW && cmd != DEVLINK_CMD_REGION_DEL); - if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)) - return; - - msg = devlink_nl_region_notify_build(region, snapshot, cmd, 0, 0); - if (IS_ERR(msg)) - return; - - genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), msg, - 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); -} - -/** - * __devlink_snapshot_id_increment - Increment number of snapshots using an id - * @devlink: devlink instance - * @id: the snapshot id - * - * Track when a new snapshot begins using an id. Load the count for the - * given id from the snapshot xarray, increment it, and store it back. - * - * Called when a new snapshot is created with the given id. - * - * The id *must* have been previously allocated by - * devlink_region_snapshot_id_get(). - * - * Returns 0 on success, or an error on failure. - */ -static int __devlink_snapshot_id_increment(struct devlink *devlink, u32 id) -{ - unsigned long count; - void *p; - int err; - - xa_lock(&devlink->snapshot_ids); - p = xa_load(&devlink->snapshot_ids, id); - if (WARN_ON(!p)) { - err = -EINVAL; - goto unlock; - } - - if (WARN_ON(!xa_is_value(p))) { - err = -EINVAL; - goto unlock; - } - - count = xa_to_value(p); - count++; - - err = xa_err(__xa_store(&devlink->snapshot_ids, id, xa_mk_value(count), - GFP_ATOMIC)); -unlock: - xa_unlock(&devlink->snapshot_ids); - return err; -} - -/** - * __devlink_snapshot_id_decrement - Decrease number of snapshots using an id - * @devlink: devlink instance - * @id: the snapshot id - * - * Track when a snapshot is deleted and stops using an id. Load the count - * for the given id from the snapshot xarray, decrement it, and store it - * back. - * - * If the count reaches zero, erase this id from the xarray, freeing it - * up for future re-use by devlink_region_snapshot_id_get(). - * - * Called when a snapshot using the given id is deleted, and when the - * initial allocator of the id is finished using it. - */ -static void __devlink_snapshot_id_decrement(struct devlink *devlink, u32 id) -{ - unsigned long count; - void *p; - - xa_lock(&devlink->snapshot_ids); - p = xa_load(&devlink->snapshot_ids, id); - if (WARN_ON(!p)) - goto unlock; - - if (WARN_ON(!xa_is_value(p))) - goto unlock; - - count = xa_to_value(p); - - if (count > 1) { - count--; - __xa_store(&devlink->snapshot_ids, id, xa_mk_value(count), - GFP_ATOMIC); - } else { - /* If this was the last user, we can erase this id */ - __xa_erase(&devlink->snapshot_ids, id); - } -unlock: - xa_unlock(&devlink->snapshot_ids); -} - -/** - * __devlink_snapshot_id_insert - Insert a specific snapshot ID - * @devlink: devlink instance - * @id: the snapshot id - * - * Mark the given snapshot id as used by inserting a zero value into the - * snapshot xarray. - * - * This must be called while holding the devlink instance lock. Unlike - * devlink_snapshot_id_get, the initial reference count is zero, not one. - * It is expected that the id will immediately be used before - * releasing the devlink instance lock. - * - * Returns zero on success, or an error code if the snapshot id could not - * be inserted. - */ -static int __devlink_snapshot_id_insert(struct devlink *devlink, u32 id) -{ - int err; - - xa_lock(&devlink->snapshot_ids); - if (xa_load(&devlink->snapshot_ids, id)) { - xa_unlock(&devlink->snapshot_ids); - return -EEXIST; - } - err = xa_err(__xa_store(&devlink->snapshot_ids, id, xa_mk_value(0), - GFP_ATOMIC)); - xa_unlock(&devlink->snapshot_ids); - return err; -} - -/** - * __devlink_region_snapshot_id_get - get snapshot ID - * @devlink: devlink instance - * @id: storage to return snapshot id - * - * Allocates a new snapshot id. Returns zero on success, or a negative - * error on failure. Must be called while holding the devlink instance - * lock. - * - * Snapshot IDs are tracked using an xarray which stores the number of - * users of the snapshot id. - * - * Note that the caller of this function counts as a 'user', in order to - * avoid race conditions. The caller must release its hold on the - * snapshot by using devlink_region_snapshot_id_put. - */ -static int __devlink_region_snapshot_id_get(struct devlink *devlink, u32 *id) -{ - return xa_alloc(&devlink->snapshot_ids, id, xa_mk_value(1), - xa_limit_32b, GFP_KERNEL); -} - -/** - * __devlink_region_snapshot_create - create a new snapshot - * This will add a new snapshot of a region. The snapshot - * will be stored on the region struct and can be accessed - * from devlink. This is useful for future analyses of snapshots. - * Multiple snapshots can be created on a region. - * The @snapshot_id should be obtained using the getter function. - * - * Must be called only while holding the region snapshot lock. - * - * @region: devlink region of the snapshot - * @data: snapshot data - * @snapshot_id: snapshot id to be created - */ -static int -__devlink_region_snapshot_create(struct devlink_region *region, - u8 *data, u32 snapshot_id) -{ - struct devlink *devlink = region->devlink; - struct devlink_snapshot *snapshot; - int err; - - lockdep_assert_held(&region->snapshot_lock); - - /* check if region can hold one more snapshot */ - if (region->cur_snapshots == region->max_snapshots) - return -ENOSPC; - - if (devlink_region_snapshot_get_by_id(region, snapshot_id)) - return -EEXIST; - - snapshot = kzalloc(sizeof(*snapshot), GFP_KERNEL); - if (!snapshot) - return -ENOMEM; - - err = __devlink_snapshot_id_increment(devlink, snapshot_id); - if (err) - goto err_snapshot_id_increment; - - snapshot->id = snapshot_id; - snapshot->region = region; - snapshot->data = data; - - list_add_tail(&snapshot->list, &region->snapshot_list); - - region->cur_snapshots++; - - devlink_nl_region_notify(region, snapshot, DEVLINK_CMD_REGION_NEW); - return 0; - -err_snapshot_id_increment: - kfree(snapshot); - return err; -} - -static void devlink_region_snapshot_del(struct devlink_region *region, - struct devlink_snapshot *snapshot) -{ - struct devlink *devlink = region->devlink; - - lockdep_assert_held(&region->snapshot_lock); - - devlink_nl_region_notify(region, snapshot, DEVLINK_CMD_REGION_DEL); - region->cur_snapshots--; - list_del(&snapshot->list); - region->ops->destructor(snapshot->data); - __devlink_snapshot_id_decrement(devlink, snapshot->id); - kfree(snapshot); -} - -static int devlink_nl_cmd_region_get_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - struct devlink_port *port = NULL; - struct devlink_region *region; - const char *region_name; - struct sk_buff *msg; - unsigned int index; - int err; - - if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_REGION_NAME)) - return -EINVAL; - - if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) { - index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); - - port = devlink_port_get_by_index(devlink, index); - if (!port) - return -ENODEV; - } - - region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]); - if (port) - region = devlink_port_region_get_by_name(port, region_name); - else - region = devlink_region_get_by_name(devlink, region_name); - - if (!region) - return -EINVAL; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOMEM; - - err = devlink_nl_region_fill(msg, devlink, DEVLINK_CMD_REGION_GET, - info->snd_portid, info->snd_seq, 0, - region); - if (err) { - nlmsg_free(msg); - return err; - } - - return genlmsg_reply(msg, info); -} - -static int devlink_nl_cmd_region_get_port_dumpit(struct sk_buff *msg, - struct netlink_callback *cb, - struct devlink_port *port, - int *idx, - int start) -{ - struct devlink_region *region; - int err = 0; - - list_for_each_entry(region, &port->region_list, list) { - if (*idx < start) { - (*idx)++; - continue; - } - err = devlink_nl_region_fill(msg, port->devlink, - DEVLINK_CMD_REGION_GET, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - NLM_F_MULTI, region); - if (err) - goto out; - (*idx)++; - } - -out: - return err; -} - -static int devlink_nl_cmd_region_get_devlink_dumpit(struct sk_buff *msg, - struct netlink_callback *cb, - struct devlink *devlink, - int *idx, - int start) -{ - struct devlink_region *region; - struct devlink_port *port; - int err = 0; - - devl_lock(devlink); - list_for_each_entry(region, &devlink->region_list, list) { - if (*idx < start) { - (*idx)++; - continue; - } - err = devlink_nl_region_fill(msg, devlink, - DEVLINK_CMD_REGION_GET, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - NLM_F_MULTI, region); - if (err) - goto out; - (*idx)++; - } - - list_for_each_entry(port, &devlink->port_list, list) { - err = devlink_nl_cmd_region_get_port_dumpit(msg, cb, port, idx, - start); - if (err) - goto out; - } - -out: - devl_unlock(devlink); - return err; -} - -static int devlink_nl_cmd_region_get_dumpit(struct sk_buff *msg, - struct netlink_callback *cb) -{ - struct devlink *devlink; - int start = cb->args[0]; - unsigned long index; - int idx = 0; - int err = 0; - - devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { - err = devlink_nl_cmd_region_get_devlink_dumpit(msg, cb, devlink, - &idx, start); - devlink_put(devlink); - if (err) - goto out; - } -out: - cb->args[0] = idx; - return msg->len; -} - -static int devlink_nl_cmd_region_del(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - struct devlink_snapshot *snapshot; - struct devlink_port *port = NULL; - struct devlink_region *region; - const char *region_name; - unsigned int index; - u32 snapshot_id; - - if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_REGION_NAME) || - GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_REGION_SNAPSHOT_ID)) - return -EINVAL; - - region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]); - snapshot_id = nla_get_u32(info->attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]); - - if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) { - index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); - - port = devlink_port_get_by_index(devlink, index); - if (!port) - return -ENODEV; - } - - if (port) - region = devlink_port_region_get_by_name(port, region_name); - else - region = devlink_region_get_by_name(devlink, region_name); - - if (!region) - return -EINVAL; - - mutex_lock(&region->snapshot_lock); - snapshot = devlink_region_snapshot_get_by_id(region, snapshot_id); - if (!snapshot) { - mutex_unlock(&region->snapshot_lock); - return -EINVAL; - } - - devlink_region_snapshot_del(region, snapshot); - mutex_unlock(&region->snapshot_lock); - return 0; -} - -static int -devlink_nl_cmd_region_new(struct sk_buff *skb, struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - struct devlink_snapshot *snapshot; - struct devlink_port *port = NULL; - struct nlattr *snapshot_id_attr; - struct devlink_region *region; - const char *region_name; - unsigned int index; - u32 snapshot_id; - u8 *data; - int err; - - if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_REGION_NAME)) { - NL_SET_ERR_MSG_MOD(info->extack, "No region name provided"); - return -EINVAL; - } - - region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]); - - if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) { - index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); - - port = devlink_port_get_by_index(devlink, index); - if (!port) - return -ENODEV; - } - - if (port) - region = devlink_port_region_get_by_name(port, region_name); - else - region = devlink_region_get_by_name(devlink, region_name); - - if (!region) { - NL_SET_ERR_MSG_MOD(info->extack, "The requested region does not exist"); - return -EINVAL; - } - - if (!region->ops->snapshot) { - NL_SET_ERR_MSG_MOD(info->extack, "The requested region does not support taking an immediate snapshot"); - return -EOPNOTSUPP; - } - - mutex_lock(&region->snapshot_lock); - - if (region->cur_snapshots == region->max_snapshots) { - NL_SET_ERR_MSG_MOD(info->extack, "The region has reached the maximum number of stored snapshots"); - err = -ENOSPC; - goto unlock; - } - - snapshot_id_attr = info->attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]; - if (snapshot_id_attr) { - snapshot_id = nla_get_u32(snapshot_id_attr); - - if (devlink_region_snapshot_get_by_id(region, snapshot_id)) { - NL_SET_ERR_MSG_MOD(info->extack, "The requested snapshot id is already in use"); - err = -EEXIST; - goto unlock; - } - - err = __devlink_snapshot_id_insert(devlink, snapshot_id); - if (err) - goto unlock; - } else { - err = __devlink_region_snapshot_id_get(devlink, &snapshot_id); - if (err) { - NL_SET_ERR_MSG_MOD(info->extack, "Failed to allocate a new snapshot id"); - goto unlock; - } - } - - if (port) - err = region->port_ops->snapshot(port, region->port_ops, - info->extack, &data); - else - err = region->ops->snapshot(devlink, region->ops, - info->extack, &data); - if (err) - goto err_snapshot_capture; - - err = __devlink_region_snapshot_create(region, data, snapshot_id); - if (err) - goto err_snapshot_create; - - if (!snapshot_id_attr) { - struct sk_buff *msg; - - snapshot = devlink_region_snapshot_get_by_id(region, - snapshot_id); - if (WARN_ON(!snapshot)) { - err = -EINVAL; - goto unlock; - } - - msg = devlink_nl_region_notify_build(region, snapshot, - DEVLINK_CMD_REGION_NEW, - info->snd_portid, - info->snd_seq); - err = PTR_ERR_OR_ZERO(msg); - if (err) - goto err_notify; - - err = genlmsg_reply(msg, info); - if (err) - goto err_notify; - } - - mutex_unlock(&region->snapshot_lock); - return 0; - -err_snapshot_create: - region->ops->destructor(data); -err_snapshot_capture: - __devlink_snapshot_id_decrement(devlink, snapshot_id); - mutex_unlock(&region->snapshot_lock); - return err; - -err_notify: - devlink_region_snapshot_del(region, snapshot); -unlock: - mutex_unlock(&region->snapshot_lock); - return err; -} - -static int devlink_nl_cmd_region_read_chunk_fill(struct sk_buff *msg, - struct devlink *devlink, - u8 *chunk, u32 chunk_size, - u64 addr) -{ - struct nlattr *chunk_attr; - int err; - - chunk_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_REGION_CHUNK); - if (!chunk_attr) - return -EINVAL; - - err = nla_put(msg, DEVLINK_ATTR_REGION_CHUNK_DATA, chunk_size, chunk); - if (err) - goto nla_put_failure; - - err = nla_put_u64_64bit(msg, DEVLINK_ATTR_REGION_CHUNK_ADDR, addr, - DEVLINK_ATTR_PAD); - if (err) - goto nla_put_failure; - - nla_nest_end(msg, chunk_attr); - return 0; - -nla_put_failure: - nla_nest_cancel(msg, chunk_attr); - return err; -} - -#define DEVLINK_REGION_READ_CHUNK_SIZE 256 - -static int devlink_nl_region_read_snapshot_fill(struct sk_buff *skb, - struct devlink *devlink, - struct devlink_region *region, - struct nlattr **attrs, - u64 start_offset, - u64 end_offset, - u64 *new_offset) -{ - struct devlink_snapshot *snapshot; - u64 curr_offset = start_offset; - u32 snapshot_id; - int err = 0; - - *new_offset = start_offset; - - snapshot_id = nla_get_u32(attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]); - snapshot = devlink_region_snapshot_get_by_id(region, snapshot_id); - if (!snapshot) - return -EINVAL; - - while (curr_offset < end_offset) { - u32 data_size; - u8 *data; - - if (end_offset - curr_offset < DEVLINK_REGION_READ_CHUNK_SIZE) - data_size = end_offset - curr_offset; - else - data_size = DEVLINK_REGION_READ_CHUNK_SIZE; - - data = &snapshot->data[curr_offset]; - err = devlink_nl_cmd_region_read_chunk_fill(skb, devlink, - data, data_size, - curr_offset); - if (err) - break; - - curr_offset += data_size; - } - *new_offset = curr_offset; - - return err; -} - -static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, - struct netlink_callback *cb) -{ - const struct genl_dumpit_info *info = genl_dumpit_info(cb); - u64 ret_offset, start_offset, end_offset = U64_MAX; - struct nlattr **attrs = info->attrs; - struct devlink_port *port = NULL; - struct devlink_region *region; - struct nlattr *chunks_attr; - const char *region_name; - struct devlink *devlink; - unsigned int index; - void *hdr; - int err; - - start_offset = *((u64 *)&cb->args[0]); - - devlink = devlink_get_from_attrs(sock_net(cb->skb->sk), attrs); - if (IS_ERR(devlink)) - return PTR_ERR(devlink); - - devl_lock(devlink); - - if (!attrs[DEVLINK_ATTR_REGION_NAME] || - !attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]) { - err = -EINVAL; - goto out_unlock; - } - - if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) { - index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); - - port = devlink_port_get_by_index(devlink, index); - if (!port) { - err = -ENODEV; - goto out_unlock; - } - } - - region_name = nla_data(attrs[DEVLINK_ATTR_REGION_NAME]); - - if (port) - region = devlink_port_region_get_by_name(port, region_name); - else - region = devlink_region_get_by_name(devlink, region_name); - - if (!region) { - err = -EINVAL; - goto out_unlock; - } - - if (attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR] && - attrs[DEVLINK_ATTR_REGION_CHUNK_LEN]) { - if (!start_offset) - start_offset = - nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR]); - - end_offset = nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR]); - end_offset += nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_LEN]); - } - - if (end_offset > region->size) - end_offset = region->size; - - /* return 0 if there is no further data to read */ - if (start_offset == end_offset) { - err = 0; - goto out_unlock; - } - - hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - &devlink_nl_family, NLM_F_ACK | NLM_F_MULTI, - DEVLINK_CMD_REGION_READ); - if (!hdr) { - err = -EMSGSIZE; - goto out_unlock; - } - - err = devlink_nl_put_handle(skb, devlink); - if (err) - goto nla_put_failure; - - if (region->port) { - err = nla_put_u32(skb, DEVLINK_ATTR_PORT_INDEX, - region->port->index); - if (err) - goto nla_put_failure; - } - - err = nla_put_string(skb, DEVLINK_ATTR_REGION_NAME, region_name); - if (err) - goto nla_put_failure; - - chunks_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_REGION_CHUNKS); - if (!chunks_attr) { - err = -EMSGSIZE; - goto nla_put_failure; - } - - err = devlink_nl_region_read_snapshot_fill(skb, devlink, - region, attrs, - start_offset, - end_offset, &ret_offset); - - if (err && err != -EMSGSIZE) - goto nla_put_failure; - - /* Check if there was any progress done to prevent infinite loop */ - if (ret_offset == start_offset) { - err = -EINVAL; - goto nla_put_failure; - } - - *((u64 *)&cb->args[0]) = ret_offset; - - nla_nest_end(skb, chunks_attr); - genlmsg_end(skb, hdr); - devl_unlock(devlink); - devlink_put(devlink); - return skb->len; - -nla_put_failure: - genlmsg_cancel(skb, hdr); -out_unlock: - devl_unlock(devlink); - devlink_put(devlink); - return err; -} - -int devlink_info_driver_name_put(struct devlink_info_req *req, const char *name) -{ - if (!req->msg) - return 0; - return nla_put_string(req->msg, DEVLINK_ATTR_INFO_DRIVER_NAME, name); -} -EXPORT_SYMBOL_GPL(devlink_info_driver_name_put); - -int devlink_info_serial_number_put(struct devlink_info_req *req, const char *sn) -{ - if (!req->msg) - return 0; - return nla_put_string(req->msg, DEVLINK_ATTR_INFO_SERIAL_NUMBER, sn); -} -EXPORT_SYMBOL_GPL(devlink_info_serial_number_put); - -int devlink_info_board_serial_number_put(struct devlink_info_req *req, - const char *bsn) -{ - if (!req->msg) - return 0; - return nla_put_string(req->msg, DEVLINK_ATTR_INFO_BOARD_SERIAL_NUMBER, - bsn); -} -EXPORT_SYMBOL_GPL(devlink_info_board_serial_number_put); - -static int devlink_info_version_put(struct devlink_info_req *req, int attr, - const char *version_name, - const char *version_value, - enum devlink_info_version_type version_type) -{ - struct nlattr *nest; - int err; - - if (req->version_cb) - req->version_cb(version_name, version_type, - req->version_cb_priv); - - if (!req->msg) - return 0; - - nest = nla_nest_start_noflag(req->msg, attr); - if (!nest) - return -EMSGSIZE; - - err = nla_put_string(req->msg, DEVLINK_ATTR_INFO_VERSION_NAME, - version_name); - if (err) - goto nla_put_failure; - - err = nla_put_string(req->msg, DEVLINK_ATTR_INFO_VERSION_VALUE, - version_value); - if (err) - goto nla_put_failure; - - nla_nest_end(req->msg, nest); - - return 0; - -nla_put_failure: - nla_nest_cancel(req->msg, nest); - return err; -} - -int devlink_info_version_fixed_put(struct devlink_info_req *req, - const char *version_name, - const char *version_value) -{ - return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_FIXED, - version_name, version_value, - DEVLINK_INFO_VERSION_TYPE_NONE); -} -EXPORT_SYMBOL_GPL(devlink_info_version_fixed_put); - -int devlink_info_version_stored_put(struct devlink_info_req *req, - const char *version_name, - const char *version_value) -{ - return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_STORED, - version_name, version_value, - DEVLINK_INFO_VERSION_TYPE_NONE); -} -EXPORT_SYMBOL_GPL(devlink_info_version_stored_put); - -int devlink_info_version_stored_put_ext(struct devlink_info_req *req, - const char *version_name, - const char *version_value, - enum devlink_info_version_type version_type) -{ - return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_STORED, - version_name, version_value, - version_type); -} -EXPORT_SYMBOL_GPL(devlink_info_version_stored_put_ext); - -int devlink_info_version_running_put(struct devlink_info_req *req, - const char *version_name, - const char *version_value) -{ - return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_RUNNING, - version_name, version_value, - DEVLINK_INFO_VERSION_TYPE_NONE); -} -EXPORT_SYMBOL_GPL(devlink_info_version_running_put); - -int devlink_info_version_running_put_ext(struct devlink_info_req *req, - const char *version_name, - const char *version_value, - enum devlink_info_version_type version_type) -{ - return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_RUNNING, - version_name, version_value, - version_type); -} -EXPORT_SYMBOL_GPL(devlink_info_version_running_put_ext); - -static int -devlink_nl_info_fill(struct sk_buff *msg, struct devlink *devlink, - enum devlink_command cmd, u32 portid, - u32 seq, int flags, struct netlink_ext_ack *extack) -{ - struct devlink_info_req req = {}; - void *hdr; - int err; - - hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); - if (!hdr) - return -EMSGSIZE; - - err = -EMSGSIZE; - if (devlink_nl_put_handle(msg, devlink)) - goto err_cancel_msg; - - req.msg = msg; - err = devlink->ops->info_get(devlink, &req, extack); - if (err) - goto err_cancel_msg; - - genlmsg_end(msg, hdr); - return 0; - -err_cancel_msg: - genlmsg_cancel(msg, hdr); - return err; -} - -static int devlink_nl_cmd_info_get_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - struct sk_buff *msg; - int err; - - if (!devlink->ops->info_get) - return -EOPNOTSUPP; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOMEM; - - err = devlink_nl_info_fill(msg, devlink, DEVLINK_CMD_INFO_GET, - info->snd_portid, info->snd_seq, 0, - info->extack); - if (err) { - nlmsg_free(msg); - return err; - } - - return genlmsg_reply(msg, info); -} - -static int devlink_nl_cmd_info_get_dumpit(struct sk_buff *msg, - struct netlink_callback *cb) -{ - struct devlink *devlink; - int start = cb->args[0]; - unsigned long index; - int idx = 0; - int err = 0; - - devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { - if (idx < start || !devlink->ops->info_get) - goto inc; - - devl_lock(devlink); - err = devlink_nl_info_fill(msg, devlink, DEVLINK_CMD_INFO_GET, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI, - cb->extack); - devl_unlock(devlink); - if (err == -EOPNOTSUPP) - err = 0; - else if (err) { - devlink_put(devlink); - break; - } -inc: - idx++; - devlink_put(devlink); - } - - if (err != -EMSGSIZE) - return err; - - cb->args[0] = idx; - return msg->len; -} - -struct devlink_fmsg_item { - struct list_head list; - int attrtype; - u8 nla_type; - u16 len; - int value[]; -}; - -struct devlink_fmsg { - struct list_head item_list; - bool putting_binary; /* This flag forces enclosing of binary data - * in an array brackets. It forces using - * of designated API: - * devlink_fmsg_binary_pair_nest_start() - * devlink_fmsg_binary_pair_nest_end() - */ -}; - -static struct devlink_fmsg *devlink_fmsg_alloc(void) -{ - struct devlink_fmsg *fmsg; - - fmsg = kzalloc(sizeof(*fmsg), GFP_KERNEL); - if (!fmsg) - return NULL; - - INIT_LIST_HEAD(&fmsg->item_list); - - return fmsg; -} - -static void devlink_fmsg_free(struct devlink_fmsg *fmsg) -{ - struct devlink_fmsg_item *item, *tmp; - - list_for_each_entry_safe(item, tmp, &fmsg->item_list, list) { - list_del(&item->list); - kfree(item); - } - kfree(fmsg); -} - -static int devlink_fmsg_nest_common(struct devlink_fmsg *fmsg, - int attrtype) -{ - struct devlink_fmsg_item *item; - - item = kzalloc(sizeof(*item), GFP_KERNEL); - if (!item) - return -ENOMEM; - - item->attrtype = attrtype; - list_add_tail(&item->list, &fmsg->item_list); - - return 0; -} - -int devlink_fmsg_obj_nest_start(struct devlink_fmsg *fmsg) -{ - if (fmsg->putting_binary) - return -EINVAL; - - return devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_OBJ_NEST_START); -} -EXPORT_SYMBOL_GPL(devlink_fmsg_obj_nest_start); - -static int devlink_fmsg_nest_end(struct devlink_fmsg *fmsg) -{ - if (fmsg->putting_binary) - return -EINVAL; - - return devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_NEST_END); -} - -int devlink_fmsg_obj_nest_end(struct devlink_fmsg *fmsg) -{ - if (fmsg->putting_binary) - return -EINVAL; - - return devlink_fmsg_nest_end(fmsg); -} -EXPORT_SYMBOL_GPL(devlink_fmsg_obj_nest_end); - -#define DEVLINK_FMSG_MAX_SIZE (GENLMSG_DEFAULT_SIZE - GENL_HDRLEN - NLA_HDRLEN) - -static int devlink_fmsg_put_name(struct devlink_fmsg *fmsg, const char *name) -{ - struct devlink_fmsg_item *item; - - if (fmsg->putting_binary) - return -EINVAL; - - if (strlen(name) + 1 > DEVLINK_FMSG_MAX_SIZE) - return -EMSGSIZE; - - item = kzalloc(sizeof(*item) + strlen(name) + 1, GFP_KERNEL); - if (!item) - return -ENOMEM; - - item->nla_type = NLA_NUL_STRING; - item->len = strlen(name) + 1; - item->attrtype = DEVLINK_ATTR_FMSG_OBJ_NAME; - memcpy(&item->value, name, item->len); - list_add_tail(&item->list, &fmsg->item_list); - - return 0; -} - -int devlink_fmsg_pair_nest_start(struct devlink_fmsg *fmsg, const char *name) -{ - int err; - - if (fmsg->putting_binary) - return -EINVAL; - - err = devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_PAIR_NEST_START); - if (err) - return err; - - err = devlink_fmsg_put_name(fmsg, name); - if (err) - return err; - - return 0; -} -EXPORT_SYMBOL_GPL(devlink_fmsg_pair_nest_start); - -int devlink_fmsg_pair_nest_end(struct devlink_fmsg *fmsg) -{ - if (fmsg->putting_binary) - return -EINVAL; - - return devlink_fmsg_nest_end(fmsg); -} -EXPORT_SYMBOL_GPL(devlink_fmsg_pair_nest_end); - -int devlink_fmsg_arr_pair_nest_start(struct devlink_fmsg *fmsg, - const char *name) -{ - int err; - - if (fmsg->putting_binary) - return -EINVAL; - - err = devlink_fmsg_pair_nest_start(fmsg, name); - if (err) - return err; - - err = devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_ARR_NEST_START); - if (err) - return err; - - return 0; -} -EXPORT_SYMBOL_GPL(devlink_fmsg_arr_pair_nest_start); - -int devlink_fmsg_arr_pair_nest_end(struct devlink_fmsg *fmsg) -{ - int err; - - if (fmsg->putting_binary) - return -EINVAL; - - err = devlink_fmsg_nest_end(fmsg); - if (err) - return err; - - err = devlink_fmsg_nest_end(fmsg); - if (err) - return err; - - return 0; -} -EXPORT_SYMBOL_GPL(devlink_fmsg_arr_pair_nest_end); - -int devlink_fmsg_binary_pair_nest_start(struct devlink_fmsg *fmsg, - const char *name) -{ - int err; - - err = devlink_fmsg_arr_pair_nest_start(fmsg, name); - if (err) - return err; - - fmsg->putting_binary = true; - return err; -} -EXPORT_SYMBOL_GPL(devlink_fmsg_binary_pair_nest_start); - -int devlink_fmsg_binary_pair_nest_end(struct devlink_fmsg *fmsg) -{ - if (!fmsg->putting_binary) - return -EINVAL; - - fmsg->putting_binary = false; - return devlink_fmsg_arr_pair_nest_end(fmsg); -} -EXPORT_SYMBOL_GPL(devlink_fmsg_binary_pair_nest_end); - -static int devlink_fmsg_put_value(struct devlink_fmsg *fmsg, - const void *value, u16 value_len, - u8 value_nla_type) -{ - struct devlink_fmsg_item *item; - - if (value_len > DEVLINK_FMSG_MAX_SIZE) - return -EMSGSIZE; - - item = kzalloc(sizeof(*item) + value_len, GFP_KERNEL); - if (!item) - return -ENOMEM; - - item->nla_type = value_nla_type; - item->len = value_len; - item->attrtype = DEVLINK_ATTR_FMSG_OBJ_VALUE_DATA; - memcpy(&item->value, value, item->len); - list_add_tail(&item->list, &fmsg->item_list); - - return 0; -} - -static int devlink_fmsg_bool_put(struct devlink_fmsg *fmsg, bool value) -{ - if (fmsg->putting_binary) - return -EINVAL; - - return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_FLAG); -} - -static int devlink_fmsg_u8_put(struct devlink_fmsg *fmsg, u8 value) -{ - if (fmsg->putting_binary) - return -EINVAL; - - return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U8); -} - -int devlink_fmsg_u32_put(struct devlink_fmsg *fmsg, u32 value) -{ - if (fmsg->putting_binary) - return -EINVAL; - - return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U32); -} -EXPORT_SYMBOL_GPL(devlink_fmsg_u32_put); - -static int devlink_fmsg_u64_put(struct devlink_fmsg *fmsg, u64 value) -{ - if (fmsg->putting_binary) - return -EINVAL; - - return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U64); -} - -int devlink_fmsg_string_put(struct devlink_fmsg *fmsg, const char *value) -{ - if (fmsg->putting_binary) - return -EINVAL; - - return devlink_fmsg_put_value(fmsg, value, strlen(value) + 1, - NLA_NUL_STRING); -} -EXPORT_SYMBOL_GPL(devlink_fmsg_string_put); - -int devlink_fmsg_binary_put(struct devlink_fmsg *fmsg, const void *value, - u16 value_len) -{ - if (!fmsg->putting_binary) - return -EINVAL; - - return devlink_fmsg_put_value(fmsg, value, value_len, NLA_BINARY); -} -EXPORT_SYMBOL_GPL(devlink_fmsg_binary_put); - -int devlink_fmsg_bool_pair_put(struct devlink_fmsg *fmsg, const char *name, - bool value) -{ - int err; - - err = devlink_fmsg_pair_nest_start(fmsg, name); - if (err) - return err; - - err = devlink_fmsg_bool_put(fmsg, value); - if (err) - return err; - - err = devlink_fmsg_pair_nest_end(fmsg); - if (err) - return err; - - return 0; -} -EXPORT_SYMBOL_GPL(devlink_fmsg_bool_pair_put); - -int devlink_fmsg_u8_pair_put(struct devlink_fmsg *fmsg, const char *name, - u8 value) -{ - int err; - - err = devlink_fmsg_pair_nest_start(fmsg, name); - if (err) - return err; - - err = devlink_fmsg_u8_put(fmsg, value); - if (err) - return err; - - err = devlink_fmsg_pair_nest_end(fmsg); - if (err) - return err; - - return 0; -} -EXPORT_SYMBOL_GPL(devlink_fmsg_u8_pair_put); - -int devlink_fmsg_u32_pair_put(struct devlink_fmsg *fmsg, const char *name, - u32 value) -{ - int err; - - err = devlink_fmsg_pair_nest_start(fmsg, name); - if (err) - return err; - - err = devlink_fmsg_u32_put(fmsg, value); - if (err) - return err; - - err = devlink_fmsg_pair_nest_end(fmsg); - if (err) - return err; - - return 0; -} -EXPORT_SYMBOL_GPL(devlink_fmsg_u32_pair_put); - -int devlink_fmsg_u64_pair_put(struct devlink_fmsg *fmsg, const char *name, - u64 value) -{ - int err; - - err = devlink_fmsg_pair_nest_start(fmsg, name); - if (err) - return err; - - err = devlink_fmsg_u64_put(fmsg, value); - if (err) - return err; - - err = devlink_fmsg_pair_nest_end(fmsg); - if (err) - return err; - - return 0; -} -EXPORT_SYMBOL_GPL(devlink_fmsg_u64_pair_put); - -int devlink_fmsg_string_pair_put(struct devlink_fmsg *fmsg, const char *name, - const char *value) -{ - int err; - - err = devlink_fmsg_pair_nest_start(fmsg, name); - if (err) - return err; - - err = devlink_fmsg_string_put(fmsg, value); - if (err) - return err; - - err = devlink_fmsg_pair_nest_end(fmsg); - if (err) - return err; - - return 0; -} -EXPORT_SYMBOL_GPL(devlink_fmsg_string_pair_put); - -int devlink_fmsg_binary_pair_put(struct devlink_fmsg *fmsg, const char *name, - const void *value, u32 value_len) -{ - u32 data_size; - int end_err; - u32 offset; - int err; - - err = devlink_fmsg_binary_pair_nest_start(fmsg, name); - if (err) - return err; - - for (offset = 0; offset < value_len; offset += data_size) { - data_size = value_len - offset; - if (data_size > DEVLINK_FMSG_MAX_SIZE) - data_size = DEVLINK_FMSG_MAX_SIZE; - err = devlink_fmsg_binary_put(fmsg, value + offset, data_size); - if (err) - break; - /* Exit from loop with a break (instead of - * return) to make sure putting_binary is turned off in - * devlink_fmsg_binary_pair_nest_end - */ - } - - end_err = devlink_fmsg_binary_pair_nest_end(fmsg); - if (end_err) - err = end_err; - - return err; -} -EXPORT_SYMBOL_GPL(devlink_fmsg_binary_pair_put); - -static int -devlink_fmsg_item_fill_type(struct devlink_fmsg_item *msg, struct sk_buff *skb) -{ - switch (msg->nla_type) { - case NLA_FLAG: - case NLA_U8: - case NLA_U32: - case NLA_U64: - case NLA_NUL_STRING: - case NLA_BINARY: - return nla_put_u8(skb, DEVLINK_ATTR_FMSG_OBJ_VALUE_TYPE, - msg->nla_type); - default: - return -EINVAL; - } -} - -static int -devlink_fmsg_item_fill_data(struct devlink_fmsg_item *msg, struct sk_buff *skb) -{ - int attrtype = DEVLINK_ATTR_FMSG_OBJ_VALUE_DATA; - u8 tmp; - - switch (msg->nla_type) { - case NLA_FLAG: - /* Always provide flag data, regardless of its value */ - tmp = *(bool *) msg->value; - - return nla_put_u8(skb, attrtype, tmp); - case NLA_U8: - return nla_put_u8(skb, attrtype, *(u8 *) msg->value); - case NLA_U32: - return nla_put_u32(skb, attrtype, *(u32 *) msg->value); - case NLA_U64: - return nla_put_u64_64bit(skb, attrtype, *(u64 *) msg->value, - DEVLINK_ATTR_PAD); - case NLA_NUL_STRING: - return nla_put_string(skb, attrtype, (char *) &msg->value); - case NLA_BINARY: - return nla_put(skb, attrtype, msg->len, (void *) &msg->value); - default: - return -EINVAL; - } -} - -static int -devlink_fmsg_prepare_skb(struct devlink_fmsg *fmsg, struct sk_buff *skb, - int *start) -{ - struct devlink_fmsg_item *item; - struct nlattr *fmsg_nlattr; - int i = 0; - int err; - - fmsg_nlattr = nla_nest_start_noflag(skb, DEVLINK_ATTR_FMSG); - if (!fmsg_nlattr) - return -EMSGSIZE; - - list_for_each_entry(item, &fmsg->item_list, list) { - if (i < *start) { - i++; - continue; - } - - switch (item->attrtype) { - case DEVLINK_ATTR_FMSG_OBJ_NEST_START: - case DEVLINK_ATTR_FMSG_PAIR_NEST_START: - case DEVLINK_ATTR_FMSG_ARR_NEST_START: - case DEVLINK_ATTR_FMSG_NEST_END: - err = nla_put_flag(skb, item->attrtype); - break; - case DEVLINK_ATTR_FMSG_OBJ_VALUE_DATA: - err = devlink_fmsg_item_fill_type(item, skb); - if (err) - break; - err = devlink_fmsg_item_fill_data(item, skb); - break; - case DEVLINK_ATTR_FMSG_OBJ_NAME: - err = nla_put_string(skb, item->attrtype, - (char *) &item->value); - break; - default: - err = -EINVAL; - break; - } - if (!err) - *start = ++i; - else - break; - } - - nla_nest_end(skb, fmsg_nlattr); - return err; -} - -static int devlink_fmsg_snd(struct devlink_fmsg *fmsg, - struct genl_info *info, - enum devlink_command cmd, int flags) -{ - struct nlmsghdr *nlh; - struct sk_buff *skb; - bool last = false; - int index = 0; - void *hdr; - int err; - - while (!last) { - int tmp_index = index; - - skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!skb) - return -ENOMEM; - - hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq, - &devlink_nl_family, flags | NLM_F_MULTI, cmd); - if (!hdr) { - err = -EMSGSIZE; - goto nla_put_failure; - } - - err = devlink_fmsg_prepare_skb(fmsg, skb, &index); - if (!err) - last = true; - else if (err != -EMSGSIZE || tmp_index == index) - goto nla_put_failure; - - genlmsg_end(skb, hdr); - err = genlmsg_reply(skb, info); - if (err) - return err; - } - - skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!skb) - return -ENOMEM; - nlh = nlmsg_put(skb, info->snd_portid, info->snd_seq, - NLMSG_DONE, 0, flags | NLM_F_MULTI); - if (!nlh) { - err = -EMSGSIZE; - goto nla_put_failure; - } - - return genlmsg_reply(skb, info); - -nla_put_failure: - nlmsg_free(skb); - return err; -} - -static int devlink_fmsg_dumpit(struct devlink_fmsg *fmsg, struct sk_buff *skb, - struct netlink_callback *cb, - enum devlink_command cmd) -{ - int index = cb->args[0]; - int tmp_index = index; - void *hdr; - int err; - - hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - &devlink_nl_family, NLM_F_ACK | NLM_F_MULTI, cmd); - if (!hdr) { - err = -EMSGSIZE; - goto nla_put_failure; - } - - err = devlink_fmsg_prepare_skb(fmsg, skb, &index); - if ((err && err != -EMSGSIZE) || tmp_index == index) - goto nla_put_failure; - - cb->args[0] = index; - genlmsg_end(skb, hdr); - return skb->len; - -nla_put_failure: - genlmsg_cancel(skb, hdr); - return err; -} - -struct devlink_health_reporter { - struct list_head list; - void *priv; - const struct devlink_health_reporter_ops *ops; - struct devlink *devlink; - struct devlink_port *devlink_port; - struct devlink_fmsg *dump_fmsg; - struct mutex dump_lock; /* lock parallel read/write from dump buffers */ - u64 graceful_period; - bool auto_recover; - bool auto_dump; - u8 health_state; - u64 dump_ts; - u64 dump_real_ts; - u64 error_count; - u64 recovery_count; - u64 last_recovery_ts; - refcount_t refcount; -}; - -void * -devlink_health_reporter_priv(struct devlink_health_reporter *reporter) -{ - return reporter->priv; -} -EXPORT_SYMBOL_GPL(devlink_health_reporter_priv); - -static struct devlink_health_reporter * -__devlink_health_reporter_find_by_name(struct list_head *reporter_list, - struct mutex *list_lock, - const char *reporter_name) -{ - struct devlink_health_reporter *reporter; - - lockdep_assert_held(list_lock); - list_for_each_entry(reporter, reporter_list, list) - if (!strcmp(reporter->ops->name, reporter_name)) - return reporter; - return NULL; -} - -static struct devlink_health_reporter * -devlink_health_reporter_find_by_name(struct devlink *devlink, - const char *reporter_name) -{ - return __devlink_health_reporter_find_by_name(&devlink->reporter_list, - &devlink->reporters_lock, - reporter_name); -} - -static struct devlink_health_reporter * -devlink_port_health_reporter_find_by_name(struct devlink_port *devlink_port, - const char *reporter_name) -{ - return __devlink_health_reporter_find_by_name(&devlink_port->reporter_list, - &devlink_port->reporters_lock, - reporter_name); -} - -static struct devlink_health_reporter * -__devlink_health_reporter_create(struct devlink *devlink, - const struct devlink_health_reporter_ops *ops, - u64 graceful_period, void *priv) -{ - struct devlink_health_reporter *reporter; - - if (WARN_ON(graceful_period && !ops->recover)) - return ERR_PTR(-EINVAL); - - reporter = kzalloc(sizeof(*reporter), GFP_KERNEL); - if (!reporter) - return ERR_PTR(-ENOMEM); - - reporter->priv = priv; - reporter->ops = ops; - reporter->devlink = devlink; - reporter->graceful_period = graceful_period; - reporter->auto_recover = !!ops->recover; - reporter->auto_dump = !!ops->dump; - mutex_init(&reporter->dump_lock); - refcount_set(&reporter->refcount, 1); - return reporter; -} - -/** - * devlink_port_health_reporter_create - create devlink health reporter for - * specified port instance - * - * @port: devlink_port which should contain the new reporter - * @ops: ops - * @graceful_period: to avoid recovery loops, in msecs - * @priv: priv - */ -struct devlink_health_reporter * -devlink_port_health_reporter_create(struct devlink_port *port, - const struct devlink_health_reporter_ops *ops, - u64 graceful_period, void *priv) -{ - struct devlink_health_reporter *reporter; - - mutex_lock(&port->reporters_lock); - if (__devlink_health_reporter_find_by_name(&port->reporter_list, - &port->reporters_lock, ops->name)) { - reporter = ERR_PTR(-EEXIST); - goto unlock; - } - - reporter = __devlink_health_reporter_create(port->devlink, ops, - graceful_period, priv); - if (IS_ERR(reporter)) - goto unlock; - - reporter->devlink_port = port; - list_add_tail(&reporter->list, &port->reporter_list); -unlock: - mutex_unlock(&port->reporters_lock); - return reporter; -} -EXPORT_SYMBOL_GPL(devlink_port_health_reporter_create); - -/** - * devlink_health_reporter_create - create devlink health reporter - * - * @devlink: devlink - * @ops: ops - * @graceful_period: to avoid recovery loops, in msecs - * @priv: priv - */ -struct devlink_health_reporter * -devlink_health_reporter_create(struct devlink *devlink, - const struct devlink_health_reporter_ops *ops, - u64 graceful_period, void *priv) -{ - struct devlink_health_reporter *reporter; - - mutex_lock(&devlink->reporters_lock); - if (devlink_health_reporter_find_by_name(devlink, ops->name)) { - reporter = ERR_PTR(-EEXIST); - goto unlock; - } - - reporter = __devlink_health_reporter_create(devlink, ops, - graceful_period, priv); - if (IS_ERR(reporter)) - goto unlock; - - list_add_tail(&reporter->list, &devlink->reporter_list); -unlock: - mutex_unlock(&devlink->reporters_lock); - return reporter; -} -EXPORT_SYMBOL_GPL(devlink_health_reporter_create); - -static void -devlink_health_reporter_free(struct devlink_health_reporter *reporter) -{ - mutex_destroy(&reporter->dump_lock); - if (reporter->dump_fmsg) - devlink_fmsg_free(reporter->dump_fmsg); - kfree(reporter); -} - -static void -devlink_health_reporter_put(struct devlink_health_reporter *reporter) -{ - if (refcount_dec_and_test(&reporter->refcount)) - devlink_health_reporter_free(reporter); -} - -static void -__devlink_health_reporter_destroy(struct devlink_health_reporter *reporter) -{ - list_del(&reporter->list); - devlink_health_reporter_put(reporter); -} - -/** - * devlink_health_reporter_destroy - destroy devlink health reporter - * - * @reporter: devlink health reporter to destroy - */ -void -devlink_health_reporter_destroy(struct devlink_health_reporter *reporter) -{ - struct mutex *lock = &reporter->devlink->reporters_lock; - - mutex_lock(lock); - __devlink_health_reporter_destroy(reporter); - mutex_unlock(lock); -} -EXPORT_SYMBOL_GPL(devlink_health_reporter_destroy); - -/** - * devlink_port_health_reporter_destroy - destroy devlink port health reporter - * - * @reporter: devlink health reporter to destroy - */ -void -devlink_port_health_reporter_destroy(struct devlink_health_reporter *reporter) -{ - struct mutex *lock = &reporter->devlink_port->reporters_lock; - - mutex_lock(lock); - __devlink_health_reporter_destroy(reporter); - mutex_unlock(lock); -} -EXPORT_SYMBOL_GPL(devlink_port_health_reporter_destroy); - -static int -devlink_nl_health_reporter_fill(struct sk_buff *msg, - struct devlink_health_reporter *reporter, - enum devlink_command cmd, u32 portid, - u32 seq, int flags) -{ - struct devlink *devlink = reporter->devlink; - struct nlattr *reporter_attr; - void *hdr; - - hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); - if (!hdr) - return -EMSGSIZE; - - if (devlink_nl_put_handle(msg, devlink)) - goto genlmsg_cancel; - - if (reporter->devlink_port) { - if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, reporter->devlink_port->index)) - goto genlmsg_cancel; - } - reporter_attr = nla_nest_start_noflag(msg, - DEVLINK_ATTR_HEALTH_REPORTER); - if (!reporter_attr) - goto genlmsg_cancel; - if (nla_put_string(msg, DEVLINK_ATTR_HEALTH_REPORTER_NAME, - reporter->ops->name)) - goto reporter_nest_cancel; - if (nla_put_u8(msg, DEVLINK_ATTR_HEALTH_REPORTER_STATE, - reporter->health_state)) - goto reporter_nest_cancel; - if (nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_ERR_COUNT, - reporter->error_count, DEVLINK_ATTR_PAD)) - goto reporter_nest_cancel; - if (nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_RECOVER_COUNT, - reporter->recovery_count, DEVLINK_ATTR_PAD)) - goto reporter_nest_cancel; - if (reporter->ops->recover && - nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD, - reporter->graceful_period, - DEVLINK_ATTR_PAD)) - goto reporter_nest_cancel; - if (reporter->ops->recover && - nla_put_u8(msg, DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER, - reporter->auto_recover)) - goto reporter_nest_cancel; - if (reporter->dump_fmsg && - nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS, - jiffies_to_msecs(reporter->dump_ts), - DEVLINK_ATTR_PAD)) - goto reporter_nest_cancel; - if (reporter->dump_fmsg && - nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS_NS, - reporter->dump_real_ts, DEVLINK_ATTR_PAD)) - goto reporter_nest_cancel; - if (reporter->ops->dump && - nla_put_u8(msg, DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP, - reporter->auto_dump)) - goto reporter_nest_cancel; - - nla_nest_end(msg, reporter_attr); - genlmsg_end(msg, hdr); - return 0; - -reporter_nest_cancel: - nla_nest_end(msg, reporter_attr); -genlmsg_cancel: - genlmsg_cancel(msg, hdr); - return -EMSGSIZE; -} - -static void devlink_recover_notify(struct devlink_health_reporter *reporter, - enum devlink_command cmd) -{ - struct devlink *devlink = reporter->devlink; - struct sk_buff *msg; - int err; - - WARN_ON(cmd != DEVLINK_CMD_HEALTH_REPORTER_RECOVER); - WARN_ON(!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)); - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return; - - err = devlink_nl_health_reporter_fill(msg, reporter, cmd, 0, 0, 0); - if (err) { - nlmsg_free(msg); - return; - } - - genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), msg, - 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); -} - -void -devlink_health_reporter_recovery_done(struct devlink_health_reporter *reporter) -{ - reporter->recovery_count++; - reporter->last_recovery_ts = jiffies; -} -EXPORT_SYMBOL_GPL(devlink_health_reporter_recovery_done); - -static int -devlink_health_reporter_recover(struct devlink_health_reporter *reporter, - void *priv_ctx, struct netlink_ext_ack *extack) -{ - int err; - - if (reporter->health_state == DEVLINK_HEALTH_REPORTER_STATE_HEALTHY) - return 0; - - if (!reporter->ops->recover) - return -EOPNOTSUPP; - - err = reporter->ops->recover(reporter, priv_ctx, extack); - if (err) - return err; - - devlink_health_reporter_recovery_done(reporter); - reporter->health_state = DEVLINK_HEALTH_REPORTER_STATE_HEALTHY; - devlink_recover_notify(reporter, DEVLINK_CMD_HEALTH_REPORTER_RECOVER); - - return 0; -} - -static void -devlink_health_dump_clear(struct devlink_health_reporter *reporter) -{ - if (!reporter->dump_fmsg) - return; - devlink_fmsg_free(reporter->dump_fmsg); - reporter->dump_fmsg = NULL; -} - -static int devlink_health_do_dump(struct devlink_health_reporter *reporter, - void *priv_ctx, - struct netlink_ext_ack *extack) -{ - int err; - - if (!reporter->ops->dump) - return 0; - - if (reporter->dump_fmsg) - return 0; - - reporter->dump_fmsg = devlink_fmsg_alloc(); - if (!reporter->dump_fmsg) { - err = -ENOMEM; - return err; - } - - err = devlink_fmsg_obj_nest_start(reporter->dump_fmsg); - if (err) - goto dump_err; - - err = reporter->ops->dump(reporter, reporter->dump_fmsg, - priv_ctx, extack); - if (err) - goto dump_err; - - err = devlink_fmsg_obj_nest_end(reporter->dump_fmsg); - if (err) - goto dump_err; - - reporter->dump_ts = jiffies; - reporter->dump_real_ts = ktime_get_real_ns(); - - return 0; - -dump_err: - devlink_health_dump_clear(reporter); - return err; -} - -int devlink_health_report(struct devlink_health_reporter *reporter, - const char *msg, void *priv_ctx) -{ - enum devlink_health_reporter_state prev_health_state; - struct devlink *devlink = reporter->devlink; - unsigned long recover_ts_threshold; - int ret; - - /* write a log message of the current error */ - WARN_ON(!msg); - trace_devlink_health_report(devlink, reporter->ops->name, msg); - reporter->error_count++; - prev_health_state = reporter->health_state; - reporter->health_state = DEVLINK_HEALTH_REPORTER_STATE_ERROR; - devlink_recover_notify(reporter, DEVLINK_CMD_HEALTH_REPORTER_RECOVER); - - /* abort if the previous error wasn't recovered */ - recover_ts_threshold = reporter->last_recovery_ts + - msecs_to_jiffies(reporter->graceful_period); - if (reporter->auto_recover && - (prev_health_state != DEVLINK_HEALTH_REPORTER_STATE_HEALTHY || - (reporter->last_recovery_ts && reporter->recovery_count && - time_is_after_jiffies(recover_ts_threshold)))) { - trace_devlink_health_recover_aborted(devlink, - reporter->ops->name, - reporter->health_state, - jiffies - - reporter->last_recovery_ts); - return -ECANCELED; - } - - reporter->health_state = DEVLINK_HEALTH_REPORTER_STATE_ERROR; - - if (reporter->auto_dump) { - mutex_lock(&reporter->dump_lock); - /* store current dump of current error, for later analysis */ - devlink_health_do_dump(reporter, priv_ctx, NULL); - mutex_unlock(&reporter->dump_lock); - } - - if (!reporter->auto_recover) - return 0; - - devl_lock(devlink); - ret = devlink_health_reporter_recover(reporter, priv_ctx, NULL); - devl_unlock(devlink); - - return ret; -} -EXPORT_SYMBOL_GPL(devlink_health_report); - -static struct devlink_health_reporter * -devlink_health_reporter_get_from_attrs(struct devlink *devlink, - struct nlattr **attrs) -{ - struct devlink_health_reporter *reporter; - struct devlink_port *devlink_port; - char *reporter_name; - - if (!attrs[DEVLINK_ATTR_HEALTH_REPORTER_NAME]) - return NULL; - - reporter_name = nla_data(attrs[DEVLINK_ATTR_HEALTH_REPORTER_NAME]); - devlink_port = devlink_port_get_from_attrs(devlink, attrs); - if (IS_ERR(devlink_port)) { - mutex_lock(&devlink->reporters_lock); - reporter = devlink_health_reporter_find_by_name(devlink, reporter_name); - if (reporter) - refcount_inc(&reporter->refcount); - mutex_unlock(&devlink->reporters_lock); - } else { - mutex_lock(&devlink_port->reporters_lock); - reporter = devlink_port_health_reporter_find_by_name(devlink_port, reporter_name); - if (reporter) - refcount_inc(&reporter->refcount); - mutex_unlock(&devlink_port->reporters_lock); - } - - return reporter; -} - -static struct devlink_health_reporter * -devlink_health_reporter_get_from_info(struct devlink *devlink, - struct genl_info *info) -{ - return devlink_health_reporter_get_from_attrs(devlink, info->attrs); -} - -static struct devlink_health_reporter * -devlink_health_reporter_get_from_cb(struct netlink_callback *cb) -{ - const struct genl_dumpit_info *info = genl_dumpit_info(cb); - struct devlink_health_reporter *reporter; - struct nlattr **attrs = info->attrs; - struct devlink *devlink; - - devlink = devlink_get_from_attrs(sock_net(cb->skb->sk), attrs); - if (IS_ERR(devlink)) - return NULL; - - reporter = devlink_health_reporter_get_from_attrs(devlink, attrs); - devlink_put(devlink); - return reporter; -} - -void -devlink_health_reporter_state_update(struct devlink_health_reporter *reporter, - enum devlink_health_reporter_state state) -{ - if (WARN_ON(state != DEVLINK_HEALTH_REPORTER_STATE_HEALTHY && - state != DEVLINK_HEALTH_REPORTER_STATE_ERROR)) - return; - - if (reporter->health_state == state) - return; - - reporter->health_state = state; - trace_devlink_health_reporter_state_update(reporter->devlink, - reporter->ops->name, state); - devlink_recover_notify(reporter, DEVLINK_CMD_HEALTH_REPORTER_RECOVER); -} -EXPORT_SYMBOL_GPL(devlink_health_reporter_state_update); - -static int devlink_nl_cmd_health_reporter_get_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - struct devlink_health_reporter *reporter; - struct sk_buff *msg; - int err; - - reporter = devlink_health_reporter_get_from_info(devlink, info); - if (!reporter) - return -EINVAL; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) { - err = -ENOMEM; - goto out; - } - - err = devlink_nl_health_reporter_fill(msg, reporter, - DEVLINK_CMD_HEALTH_REPORTER_GET, - info->snd_portid, info->snd_seq, - 0); - if (err) { - nlmsg_free(msg); - goto out; - } - - err = genlmsg_reply(msg, info); -out: - devlink_health_reporter_put(reporter); - return err; -} - -static int -devlink_nl_cmd_health_reporter_get_dumpit(struct sk_buff *msg, - struct netlink_callback *cb) -{ - struct devlink_health_reporter *reporter; - struct devlink_port *port; - struct devlink *devlink; - int start = cb->args[0]; - unsigned long index; - int idx = 0; - int err; - - devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { - mutex_lock(&devlink->reporters_lock); - list_for_each_entry(reporter, &devlink->reporter_list, - list) { - if (idx < start) { - idx++; - continue; - } - err = devlink_nl_health_reporter_fill( - msg, reporter, DEVLINK_CMD_HEALTH_REPORTER_GET, - NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - NLM_F_MULTI); - if (err) { - mutex_unlock(&devlink->reporters_lock); - devlink_put(devlink); - goto out; - } - idx++; - } - mutex_unlock(&devlink->reporters_lock); - devlink_put(devlink); - } - - devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { - devl_lock(devlink); - list_for_each_entry(port, &devlink->port_list, list) { - mutex_lock(&port->reporters_lock); - list_for_each_entry(reporter, &port->reporter_list, list) { - if (idx < start) { - idx++; - continue; - } - err = devlink_nl_health_reporter_fill( - msg, reporter, - DEVLINK_CMD_HEALTH_REPORTER_GET, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI); - if (err) { - mutex_unlock(&port->reporters_lock); - devl_unlock(devlink); - devlink_put(devlink); - goto out; - } - idx++; - } - mutex_unlock(&port->reporters_lock); - } - devl_unlock(devlink); - devlink_put(devlink); - } -out: - cb->args[0] = idx; - return msg->len; -} - -static int -devlink_nl_cmd_health_reporter_set_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - struct devlink_health_reporter *reporter; - int err; - - reporter = devlink_health_reporter_get_from_info(devlink, info); - if (!reporter) - return -EINVAL; - - if (!reporter->ops->recover && - (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] || - info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER])) { - err = -EOPNOTSUPP; - goto out; - } - if (!reporter->ops->dump && - info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP]) { - err = -EOPNOTSUPP; - goto out; - } - - if (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD]) - reporter->graceful_period = - nla_get_u64(info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD]); - - if (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER]) - reporter->auto_recover = - nla_get_u8(info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER]); - - if (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP]) - reporter->auto_dump = - nla_get_u8(info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP]); - - devlink_health_reporter_put(reporter); - return 0; -out: - devlink_health_reporter_put(reporter); - return err; -} - -static int devlink_nl_cmd_health_reporter_recover_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - struct devlink_health_reporter *reporter; - int err; - - reporter = devlink_health_reporter_get_from_info(devlink, info); - if (!reporter) - return -EINVAL; - - err = devlink_health_reporter_recover(reporter, NULL, info->extack); - - devlink_health_reporter_put(reporter); - return err; -} - -static int devlink_nl_cmd_health_reporter_diagnose_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - struct devlink_health_reporter *reporter; - struct devlink_fmsg *fmsg; - int err; - - reporter = devlink_health_reporter_get_from_info(devlink, info); - if (!reporter) - return -EINVAL; - - if (!reporter->ops->diagnose) { - devlink_health_reporter_put(reporter); - return -EOPNOTSUPP; - } - - fmsg = devlink_fmsg_alloc(); - if (!fmsg) { - devlink_health_reporter_put(reporter); - return -ENOMEM; - } - - err = devlink_fmsg_obj_nest_start(fmsg); - if (err) - goto out; - - err = reporter->ops->diagnose(reporter, fmsg, info->extack); - if (err) - goto out; - - err = devlink_fmsg_obj_nest_end(fmsg); - if (err) - goto out; - - err = devlink_fmsg_snd(fmsg, info, - DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE, 0); - -out: - devlink_fmsg_free(fmsg); - devlink_health_reporter_put(reporter); - return err; -} - -static int -devlink_nl_cmd_health_reporter_dump_get_dumpit(struct sk_buff *skb, - struct netlink_callback *cb) -{ - struct devlink_health_reporter *reporter; - u64 start = cb->args[0]; - int err; - - reporter = devlink_health_reporter_get_from_cb(cb); - if (!reporter) - return -EINVAL; - - if (!reporter->ops->dump) { - err = -EOPNOTSUPP; - goto out; - } - mutex_lock(&reporter->dump_lock); - if (!start) { - err = devlink_health_do_dump(reporter, NULL, cb->extack); - if (err) - goto unlock; - cb->args[1] = reporter->dump_ts; - } - if (!reporter->dump_fmsg || cb->args[1] != reporter->dump_ts) { - NL_SET_ERR_MSG_MOD(cb->extack, "Dump trampled, please retry"); - err = -EAGAIN; - goto unlock; - } - - err = devlink_fmsg_dumpit(reporter->dump_fmsg, skb, cb, - DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET); -unlock: - mutex_unlock(&reporter->dump_lock); -out: - devlink_health_reporter_put(reporter); - return err; -} - -static int -devlink_nl_cmd_health_reporter_dump_clear_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - struct devlink_health_reporter *reporter; - - reporter = devlink_health_reporter_get_from_info(devlink, info); - if (!reporter) - return -EINVAL; - - if (!reporter->ops->dump) { - devlink_health_reporter_put(reporter); - return -EOPNOTSUPP; - } - - mutex_lock(&reporter->dump_lock); - devlink_health_dump_clear(reporter); - mutex_unlock(&reporter->dump_lock); - devlink_health_reporter_put(reporter); - return 0; -} - -static int devlink_nl_cmd_health_reporter_test_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - struct devlink_health_reporter *reporter; - int err; - - reporter = devlink_health_reporter_get_from_info(devlink, info); - if (!reporter) - return -EINVAL; - - if (!reporter->ops->test) { - devlink_health_reporter_put(reporter); - return -EOPNOTSUPP; - } - - err = reporter->ops->test(reporter, info->extack); - - devlink_health_reporter_put(reporter); - return err; -} - -struct devlink_stats { - u64_stats_t rx_bytes; - u64_stats_t rx_packets; - struct u64_stats_sync syncp; -}; - -/** - * struct devlink_trap_policer_item - Packet trap policer attributes. - * @policer: Immutable packet trap policer attributes. - * @rate: Rate in packets / sec. - * @burst: Burst size in packets. - * @list: trap_policer_list member. - * - * Describes packet trap policer attributes. Created by devlink during trap - * policer registration. - */ -struct devlink_trap_policer_item { - const struct devlink_trap_policer *policer; - u64 rate; - u64 burst; - struct list_head list; -}; - -/** - * struct devlink_trap_group_item - Packet trap group attributes. - * @group: Immutable packet trap group attributes. - * @policer_item: Associated policer item. Can be NULL. - * @list: trap_group_list member. - * @stats: Trap group statistics. - * - * Describes packet trap group attributes. Created by devlink during trap - * group registration. - */ -struct devlink_trap_group_item { - const struct devlink_trap_group *group; - struct devlink_trap_policer_item *policer_item; - struct list_head list; - struct devlink_stats __percpu *stats; -}; - -/** - * struct devlink_trap_item - Packet trap attributes. - * @trap: Immutable packet trap attributes. - * @group_item: Associated group item. - * @list: trap_list member. - * @action: Trap action. - * @stats: Trap statistics. - * @priv: Driver private information. - * - * Describes both mutable and immutable packet trap attributes. Created by - * devlink during trap registration and used for all trap related operations. - */ -struct devlink_trap_item { - const struct devlink_trap *trap; - struct devlink_trap_group_item *group_item; - struct list_head list; - enum devlink_trap_action action; - struct devlink_stats __percpu *stats; - void *priv; -}; - -static struct devlink_trap_policer_item * -devlink_trap_policer_item_lookup(struct devlink *devlink, u32 id) -{ - struct devlink_trap_policer_item *policer_item; - - list_for_each_entry(policer_item, &devlink->trap_policer_list, list) { - if (policer_item->policer->id == id) - return policer_item; - } - - return NULL; -} - -static struct devlink_trap_item * -devlink_trap_item_lookup(struct devlink *devlink, const char *name) -{ - struct devlink_trap_item *trap_item; - - list_for_each_entry(trap_item, &devlink->trap_list, list) { - if (!strcmp(trap_item->trap->name, name)) - return trap_item; - } - - return NULL; -} - -static struct devlink_trap_item * -devlink_trap_item_get_from_info(struct devlink *devlink, - struct genl_info *info) -{ - struct nlattr *attr; - - if (!info->attrs[DEVLINK_ATTR_TRAP_NAME]) - return NULL; - attr = info->attrs[DEVLINK_ATTR_TRAP_NAME]; - - return devlink_trap_item_lookup(devlink, nla_data(attr)); -} - -static int -devlink_trap_action_get_from_info(struct genl_info *info, - enum devlink_trap_action *p_trap_action) -{ - u8 val; - - val = nla_get_u8(info->attrs[DEVLINK_ATTR_TRAP_ACTION]); - switch (val) { - case DEVLINK_TRAP_ACTION_DROP: - case DEVLINK_TRAP_ACTION_TRAP: - case DEVLINK_TRAP_ACTION_MIRROR: - *p_trap_action = val; - break; - default: - return -EINVAL; - } - - return 0; -} - -static int devlink_trap_metadata_put(struct sk_buff *msg, - const struct devlink_trap *trap) -{ - struct nlattr *attr; - - attr = nla_nest_start(msg, DEVLINK_ATTR_TRAP_METADATA); - if (!attr) - return -EMSGSIZE; - - if ((trap->metadata_cap & DEVLINK_TRAP_METADATA_TYPE_F_IN_PORT) && - nla_put_flag(msg, DEVLINK_ATTR_TRAP_METADATA_TYPE_IN_PORT)) - goto nla_put_failure; - if ((trap->metadata_cap & DEVLINK_TRAP_METADATA_TYPE_F_FA_COOKIE) && - nla_put_flag(msg, DEVLINK_ATTR_TRAP_METADATA_TYPE_FA_COOKIE)) - goto nla_put_failure; - - nla_nest_end(msg, attr); - - return 0; - -nla_put_failure: - nla_nest_cancel(msg, attr); - return -EMSGSIZE; -} - -static void devlink_trap_stats_read(struct devlink_stats __percpu *trap_stats, - struct devlink_stats *stats) -{ - int i; - - memset(stats, 0, sizeof(*stats)); - for_each_possible_cpu(i) { - struct devlink_stats *cpu_stats; - u64 rx_packets, rx_bytes; - unsigned int start; - - cpu_stats = per_cpu_ptr(trap_stats, i); - do { - start = u64_stats_fetch_begin_irq(&cpu_stats->syncp); - rx_packets = u64_stats_read(&cpu_stats->rx_packets); - rx_bytes = u64_stats_read(&cpu_stats->rx_bytes); - } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start)); - - u64_stats_add(&stats->rx_packets, rx_packets); - u64_stats_add(&stats->rx_bytes, rx_bytes); - } -} - -static int -devlink_trap_group_stats_put(struct sk_buff *msg, - struct devlink_stats __percpu *trap_stats) -{ - struct devlink_stats stats; - struct nlattr *attr; - - devlink_trap_stats_read(trap_stats, &stats); - - attr = nla_nest_start(msg, DEVLINK_ATTR_STATS); - if (!attr) - return -EMSGSIZE; - - if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_PACKETS, - u64_stats_read(&stats.rx_packets), - DEVLINK_ATTR_PAD)) - goto nla_put_failure; - - if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_BYTES, - u64_stats_read(&stats.rx_bytes), - DEVLINK_ATTR_PAD)) - goto nla_put_failure; - - nla_nest_end(msg, attr); - - return 0; - -nla_put_failure: - nla_nest_cancel(msg, attr); - return -EMSGSIZE; -} - -static int devlink_trap_stats_put(struct sk_buff *msg, struct devlink *devlink, - const struct devlink_trap_item *trap_item) -{ - struct devlink_stats stats; - struct nlattr *attr; - u64 drops = 0; - int err; - - if (devlink->ops->trap_drop_counter_get) { - err = devlink->ops->trap_drop_counter_get(devlink, - trap_item->trap, - &drops); - if (err) - return err; - } - - devlink_trap_stats_read(trap_item->stats, &stats); - - attr = nla_nest_start(msg, DEVLINK_ATTR_STATS); - if (!attr) - return -EMSGSIZE; - - if (devlink->ops->trap_drop_counter_get && - nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_DROPPED, drops, - DEVLINK_ATTR_PAD)) - goto nla_put_failure; - - if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_PACKETS, - u64_stats_read(&stats.rx_packets), - DEVLINK_ATTR_PAD)) - goto nla_put_failure; - - if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_BYTES, - u64_stats_read(&stats.rx_bytes), - DEVLINK_ATTR_PAD)) - goto nla_put_failure; - - nla_nest_end(msg, attr); - - return 0; - -nla_put_failure: - nla_nest_cancel(msg, attr); - return -EMSGSIZE; -} - -static int devlink_nl_trap_fill(struct sk_buff *msg, struct devlink *devlink, - const struct devlink_trap_item *trap_item, - enum devlink_command cmd, u32 portid, u32 seq, - int flags) -{ - struct devlink_trap_group_item *group_item = trap_item->group_item; - void *hdr; - int err; - - hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); - if (!hdr) - return -EMSGSIZE; - - if (devlink_nl_put_handle(msg, devlink)) - goto nla_put_failure; - - if (nla_put_string(msg, DEVLINK_ATTR_TRAP_GROUP_NAME, - group_item->group->name)) - goto nla_put_failure; - - if (nla_put_string(msg, DEVLINK_ATTR_TRAP_NAME, trap_item->trap->name)) - goto nla_put_failure; - - if (nla_put_u8(msg, DEVLINK_ATTR_TRAP_TYPE, trap_item->trap->type)) - goto nla_put_failure; - - if (trap_item->trap->generic && - nla_put_flag(msg, DEVLINK_ATTR_TRAP_GENERIC)) - goto nla_put_failure; - - if (nla_put_u8(msg, DEVLINK_ATTR_TRAP_ACTION, trap_item->action)) - goto nla_put_failure; - - err = devlink_trap_metadata_put(msg, trap_item->trap); - if (err) - goto nla_put_failure; - - err = devlink_trap_stats_put(msg, devlink, trap_item); - if (err) - goto nla_put_failure; - - genlmsg_end(msg, hdr); - - return 0; - -nla_put_failure: - genlmsg_cancel(msg, hdr); - return -EMSGSIZE; -} - -static int devlink_nl_cmd_trap_get_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct netlink_ext_ack *extack = info->extack; - struct devlink *devlink = info->user_ptr[0]; - struct devlink_trap_item *trap_item; - struct sk_buff *msg; - int err; - - if (list_empty(&devlink->trap_list)) - return -EOPNOTSUPP; - - trap_item = devlink_trap_item_get_from_info(devlink, info); - if (!trap_item) { - NL_SET_ERR_MSG_MOD(extack, "Device did not register this trap"); - return -ENOENT; - } - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOMEM; - - err = devlink_nl_trap_fill(msg, devlink, trap_item, - DEVLINK_CMD_TRAP_NEW, info->snd_portid, - info->snd_seq, 0); - if (err) - goto err_trap_fill; - - return genlmsg_reply(msg, info); - -err_trap_fill: - nlmsg_free(msg); - return err; -} - -static int devlink_nl_cmd_trap_get_dumpit(struct sk_buff *msg, - struct netlink_callback *cb) -{ - struct devlink_trap_item *trap_item; - struct devlink *devlink; - int start = cb->args[0]; - unsigned long index; - int idx = 0; - int err; - - devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { - devl_lock(devlink); - list_for_each_entry(trap_item, &devlink->trap_list, list) { - if (idx < start) { - idx++; - continue; - } - err = devlink_nl_trap_fill(msg, devlink, trap_item, - DEVLINK_CMD_TRAP_NEW, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - NLM_F_MULTI); - if (err) { - devl_unlock(devlink); - devlink_put(devlink); - goto out; - } - idx++; - } - devl_unlock(devlink); - devlink_put(devlink); - } -out: - cb->args[0] = idx; - return msg->len; -} - -static int __devlink_trap_action_set(struct devlink *devlink, - struct devlink_trap_item *trap_item, - enum devlink_trap_action trap_action, - struct netlink_ext_ack *extack) -{ - int err; - - if (trap_item->action != trap_action && - trap_item->trap->type != DEVLINK_TRAP_TYPE_DROP) { - NL_SET_ERR_MSG_MOD(extack, "Cannot change action of non-drop traps. Skipping"); - return 0; - } - - err = devlink->ops->trap_action_set(devlink, trap_item->trap, - trap_action, extack); - if (err) - return err; - - trap_item->action = trap_action; - - return 0; -} - -static int devlink_trap_action_set(struct devlink *devlink, - struct devlink_trap_item *trap_item, - struct genl_info *info) -{ - enum devlink_trap_action trap_action; - int err; - - if (!info->attrs[DEVLINK_ATTR_TRAP_ACTION]) - return 0; - - err = devlink_trap_action_get_from_info(info, &trap_action); - if (err) { - NL_SET_ERR_MSG_MOD(info->extack, "Invalid trap action"); - return -EINVAL; - } - - return __devlink_trap_action_set(devlink, trap_item, trap_action, - info->extack); -} - -static int devlink_nl_cmd_trap_set_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct netlink_ext_ack *extack = info->extack; - struct devlink *devlink = info->user_ptr[0]; - struct devlink_trap_item *trap_item; - - if (list_empty(&devlink->trap_list)) - return -EOPNOTSUPP; - - trap_item = devlink_trap_item_get_from_info(devlink, info); - if (!trap_item) { - NL_SET_ERR_MSG_MOD(extack, "Device did not register this trap"); - return -ENOENT; - } - - return devlink_trap_action_set(devlink, trap_item, info); -} - -static struct devlink_trap_group_item * -devlink_trap_group_item_lookup(struct devlink *devlink, const char *name) -{ - struct devlink_trap_group_item *group_item; - - list_for_each_entry(group_item, &devlink->trap_group_list, list) { - if (!strcmp(group_item->group->name, name)) - return group_item; - } - - return NULL; -} - -static struct devlink_trap_group_item * -devlink_trap_group_item_lookup_by_id(struct devlink *devlink, u16 id) -{ - struct devlink_trap_group_item *group_item; - - list_for_each_entry(group_item, &devlink->trap_group_list, list) { - if (group_item->group->id == id) - return group_item; - } - - return NULL; -} - -static struct devlink_trap_group_item * -devlink_trap_group_item_get_from_info(struct devlink *devlink, - struct genl_info *info) -{ - char *name; - - if (!info->attrs[DEVLINK_ATTR_TRAP_GROUP_NAME]) - return NULL; - name = nla_data(info->attrs[DEVLINK_ATTR_TRAP_GROUP_NAME]); - - return devlink_trap_group_item_lookup(devlink, name); -} - -static int -devlink_nl_trap_group_fill(struct sk_buff *msg, struct devlink *devlink, - const struct devlink_trap_group_item *group_item, - enum devlink_command cmd, u32 portid, u32 seq, - int flags) -{ - void *hdr; - int err; - - hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); - if (!hdr) - return -EMSGSIZE; - - if (devlink_nl_put_handle(msg, devlink)) - goto nla_put_failure; - - if (nla_put_string(msg, DEVLINK_ATTR_TRAP_GROUP_NAME, - group_item->group->name)) - goto nla_put_failure; - - if (group_item->group->generic && - nla_put_flag(msg, DEVLINK_ATTR_TRAP_GENERIC)) - goto nla_put_failure; - - if (group_item->policer_item && - nla_put_u32(msg, DEVLINK_ATTR_TRAP_POLICER_ID, - group_item->policer_item->policer->id)) - goto nla_put_failure; - - err = devlink_trap_group_stats_put(msg, group_item->stats); - if (err) - goto nla_put_failure; - - genlmsg_end(msg, hdr); - - return 0; - -nla_put_failure: - genlmsg_cancel(msg, hdr); - return -EMSGSIZE; -} - -static int devlink_nl_cmd_trap_group_get_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct netlink_ext_ack *extack = info->extack; - struct devlink *devlink = info->user_ptr[0]; - struct devlink_trap_group_item *group_item; - struct sk_buff *msg; - int err; - - if (list_empty(&devlink->trap_group_list)) - return -EOPNOTSUPP; - - group_item = devlink_trap_group_item_get_from_info(devlink, info); - if (!group_item) { - NL_SET_ERR_MSG_MOD(extack, "Device did not register this trap group"); - return -ENOENT; - } - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOMEM; - - err = devlink_nl_trap_group_fill(msg, devlink, group_item, - DEVLINK_CMD_TRAP_GROUP_NEW, - info->snd_portid, info->snd_seq, 0); - if (err) - goto err_trap_group_fill; - - return genlmsg_reply(msg, info); - -err_trap_group_fill: - nlmsg_free(msg); - return err; -} - -static int devlink_nl_cmd_trap_group_get_dumpit(struct sk_buff *msg, - struct netlink_callback *cb) -{ - enum devlink_command cmd = DEVLINK_CMD_TRAP_GROUP_NEW; - struct devlink_trap_group_item *group_item; - u32 portid = NETLINK_CB(cb->skb).portid; - struct devlink *devlink; - int start = cb->args[0]; - unsigned long index; - int idx = 0; - int err; - - devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { - devl_lock(devlink); - list_for_each_entry(group_item, &devlink->trap_group_list, - list) { - if (idx < start) { - idx++; - continue; - } - err = devlink_nl_trap_group_fill(msg, devlink, - group_item, cmd, - portid, - cb->nlh->nlmsg_seq, - NLM_F_MULTI); - if (err) { - devl_unlock(devlink); - devlink_put(devlink); - goto out; - } - idx++; - } - devl_unlock(devlink); - devlink_put(devlink); - } -out: - cb->args[0] = idx; - return msg->len; -} - -static int -__devlink_trap_group_action_set(struct devlink *devlink, - struct devlink_trap_group_item *group_item, - enum devlink_trap_action trap_action, - struct netlink_ext_ack *extack) -{ - const char *group_name = group_item->group->name; - struct devlink_trap_item *trap_item; - int err; - - if (devlink->ops->trap_group_action_set) { - err = devlink->ops->trap_group_action_set(devlink, group_item->group, - trap_action, extack); - if (err) - return err; - - list_for_each_entry(trap_item, &devlink->trap_list, list) { - if (strcmp(trap_item->group_item->group->name, group_name)) - continue; - if (trap_item->action != trap_action && - trap_item->trap->type != DEVLINK_TRAP_TYPE_DROP) - continue; - trap_item->action = trap_action; - } - - return 0; - } - - list_for_each_entry(trap_item, &devlink->trap_list, list) { - if (strcmp(trap_item->group_item->group->name, group_name)) - continue; - err = __devlink_trap_action_set(devlink, trap_item, - trap_action, extack); - if (err) - return err; - } - - return 0; -} - -static int -devlink_trap_group_action_set(struct devlink *devlink, - struct devlink_trap_group_item *group_item, - struct genl_info *info, bool *p_modified) -{ - enum devlink_trap_action trap_action; - int err; - - if (!info->attrs[DEVLINK_ATTR_TRAP_ACTION]) - return 0; - - err = devlink_trap_action_get_from_info(info, &trap_action); - if (err) { - NL_SET_ERR_MSG_MOD(info->extack, "Invalid trap action"); - return -EINVAL; - } - - err = __devlink_trap_group_action_set(devlink, group_item, trap_action, - info->extack); - if (err) - return err; - - *p_modified = true; - - return 0; -} - -static int devlink_trap_group_set(struct devlink *devlink, - struct devlink_trap_group_item *group_item, - struct genl_info *info) -{ - struct devlink_trap_policer_item *policer_item; - struct netlink_ext_ack *extack = info->extack; - const struct devlink_trap_policer *policer; - struct nlattr **attrs = info->attrs; - int err; - - if (!attrs[DEVLINK_ATTR_TRAP_POLICER_ID]) - return 0; - - if (!devlink->ops->trap_group_set) - return -EOPNOTSUPP; - - policer_item = group_item->policer_item; - if (attrs[DEVLINK_ATTR_TRAP_POLICER_ID]) { - u32 policer_id; - - policer_id = nla_get_u32(attrs[DEVLINK_ATTR_TRAP_POLICER_ID]); - policer_item = devlink_trap_policer_item_lookup(devlink, - policer_id); - if (policer_id && !policer_item) { - NL_SET_ERR_MSG_MOD(extack, "Device did not register this trap policer"); - return -ENOENT; - } - } - policer = policer_item ? policer_item->policer : NULL; - - err = devlink->ops->trap_group_set(devlink, group_item->group, policer, - extack); - if (err) - return err; - - group_item->policer_item = policer_item; - - return 0; -} - -static int devlink_nl_cmd_trap_group_set_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct netlink_ext_ack *extack = info->extack; - struct devlink *devlink = info->user_ptr[0]; - struct devlink_trap_group_item *group_item; - bool modified = false; - int err; - - if (list_empty(&devlink->trap_group_list)) - return -EOPNOTSUPP; - - group_item = devlink_trap_group_item_get_from_info(devlink, info); - if (!group_item) { - NL_SET_ERR_MSG_MOD(extack, "Device did not register this trap group"); - return -ENOENT; - } - - err = devlink_trap_group_action_set(devlink, group_item, info, - &modified); - if (err) - return err; - - err = devlink_trap_group_set(devlink, group_item, info); - if (err) - goto err_trap_group_set; - - return 0; - -err_trap_group_set: - if (modified) - NL_SET_ERR_MSG_MOD(extack, "Trap group set failed, but some changes were committed already"); - return err; -} - -static struct devlink_trap_policer_item * -devlink_trap_policer_item_get_from_info(struct devlink *devlink, - struct genl_info *info) -{ - u32 id; - - if (!info->attrs[DEVLINK_ATTR_TRAP_POLICER_ID]) - return NULL; - id = nla_get_u32(info->attrs[DEVLINK_ATTR_TRAP_POLICER_ID]); - - return devlink_trap_policer_item_lookup(devlink, id); -} - -static int -devlink_trap_policer_stats_put(struct sk_buff *msg, struct devlink *devlink, - const struct devlink_trap_policer *policer) -{ - struct nlattr *attr; - u64 drops; - int err; - - if (!devlink->ops->trap_policer_counter_get) - return 0; - - err = devlink->ops->trap_policer_counter_get(devlink, policer, &drops); - if (err) - return err; - - attr = nla_nest_start(msg, DEVLINK_ATTR_STATS); - if (!attr) - return -EMSGSIZE; - - if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_DROPPED, drops, - DEVLINK_ATTR_PAD)) - goto nla_put_failure; - - nla_nest_end(msg, attr); - - return 0; - -nla_put_failure: - nla_nest_cancel(msg, attr); - return -EMSGSIZE; -} - -static int -devlink_nl_trap_policer_fill(struct sk_buff *msg, struct devlink *devlink, - const struct devlink_trap_policer_item *policer_item, - enum devlink_command cmd, u32 portid, u32 seq, - int flags) -{ - void *hdr; - int err; - - hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); - if (!hdr) - return -EMSGSIZE; - - if (devlink_nl_put_handle(msg, devlink)) - goto nla_put_failure; - - if (nla_put_u32(msg, DEVLINK_ATTR_TRAP_POLICER_ID, - policer_item->policer->id)) - goto nla_put_failure; - - if (nla_put_u64_64bit(msg, DEVLINK_ATTR_TRAP_POLICER_RATE, - policer_item->rate, DEVLINK_ATTR_PAD)) - goto nla_put_failure; - - if (nla_put_u64_64bit(msg, DEVLINK_ATTR_TRAP_POLICER_BURST, - policer_item->burst, DEVLINK_ATTR_PAD)) - goto nla_put_failure; - - err = devlink_trap_policer_stats_put(msg, devlink, - policer_item->policer); - if (err) - goto nla_put_failure; - - genlmsg_end(msg, hdr); - - return 0; - -nla_put_failure: - genlmsg_cancel(msg, hdr); - return -EMSGSIZE; -} - -static int devlink_nl_cmd_trap_policer_get_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink_trap_policer_item *policer_item; - struct netlink_ext_ack *extack = info->extack; - struct devlink *devlink = info->user_ptr[0]; - struct sk_buff *msg; - int err; - - if (list_empty(&devlink->trap_policer_list)) - return -EOPNOTSUPP; - - policer_item = devlink_trap_policer_item_get_from_info(devlink, info); - if (!policer_item) { - NL_SET_ERR_MSG_MOD(extack, "Device did not register this trap policer"); - return -ENOENT; - } - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOMEM; - - err = devlink_nl_trap_policer_fill(msg, devlink, policer_item, - DEVLINK_CMD_TRAP_POLICER_NEW, - info->snd_portid, info->snd_seq, 0); - if (err) - goto err_trap_policer_fill; - - return genlmsg_reply(msg, info); - -err_trap_policer_fill: - nlmsg_free(msg); - return err; -} - -static int devlink_nl_cmd_trap_policer_get_dumpit(struct sk_buff *msg, - struct netlink_callback *cb) -{ - enum devlink_command cmd = DEVLINK_CMD_TRAP_POLICER_NEW; - struct devlink_trap_policer_item *policer_item; - u32 portid = NETLINK_CB(cb->skb).portid; - struct devlink *devlink; - int start = cb->args[0]; - unsigned long index; - int idx = 0; - int err; - - devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { - devl_lock(devlink); - list_for_each_entry(policer_item, &devlink->trap_policer_list, - list) { - if (idx < start) { - idx++; - continue; - } - err = devlink_nl_trap_policer_fill(msg, devlink, - policer_item, cmd, - portid, - cb->nlh->nlmsg_seq, - NLM_F_MULTI); - if (err) { - devl_unlock(devlink); - devlink_put(devlink); - goto out; - } - idx++; - } - devl_unlock(devlink); - devlink_put(devlink); - } -out: - cb->args[0] = idx; - return msg->len; -} - -static int -devlink_trap_policer_set(struct devlink *devlink, - struct devlink_trap_policer_item *policer_item, - struct genl_info *info) -{ - struct netlink_ext_ack *extack = info->extack; - struct nlattr **attrs = info->attrs; - u64 rate, burst; - int err; - - rate = policer_item->rate; - burst = policer_item->burst; - - if (attrs[DEVLINK_ATTR_TRAP_POLICER_RATE]) - rate = nla_get_u64(attrs[DEVLINK_ATTR_TRAP_POLICER_RATE]); - - if (attrs[DEVLINK_ATTR_TRAP_POLICER_BURST]) - burst = nla_get_u64(attrs[DEVLINK_ATTR_TRAP_POLICER_BURST]); - - if (rate < policer_item->policer->min_rate) { - NL_SET_ERR_MSG_MOD(extack, "Policer rate lower than limit"); - return -EINVAL; - } - - if (rate > policer_item->policer->max_rate) { - NL_SET_ERR_MSG_MOD(extack, "Policer rate higher than limit"); - return -EINVAL; - } - - if (burst < policer_item->policer->min_burst) { - NL_SET_ERR_MSG_MOD(extack, "Policer burst size lower than limit"); - return -EINVAL; - } - - if (burst > policer_item->policer->max_burst) { - NL_SET_ERR_MSG_MOD(extack, "Policer burst size higher than limit"); - return -EINVAL; - } - - err = devlink->ops->trap_policer_set(devlink, policer_item->policer, - rate, burst, info->extack); - if (err) - return err; - - policer_item->rate = rate; - policer_item->burst = burst; - - return 0; -} - -static int devlink_nl_cmd_trap_policer_set_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink_trap_policer_item *policer_item; - struct netlink_ext_ack *extack = info->extack; - struct devlink *devlink = info->user_ptr[0]; - - if (list_empty(&devlink->trap_policer_list)) - return -EOPNOTSUPP; - - if (!devlink->ops->trap_policer_set) - return -EOPNOTSUPP; - - policer_item = devlink_trap_policer_item_get_from_info(devlink, info); - if (!policer_item) { - NL_SET_ERR_MSG_MOD(extack, "Device did not register this trap policer"); - return -ENOENT; - } - - return devlink_trap_policer_set(devlink, policer_item, info); -} - -static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { - [DEVLINK_ATTR_UNSPEC] = { .strict_start_type = - DEVLINK_ATTR_TRAP_POLICER_ID }, - [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32 }, - [DEVLINK_ATTR_PORT_TYPE] = NLA_POLICY_RANGE(NLA_U16, DEVLINK_PORT_TYPE_AUTO, - DEVLINK_PORT_TYPE_IB), - [DEVLINK_ATTR_PORT_SPLIT_COUNT] = { .type = NLA_U32 }, - [DEVLINK_ATTR_SB_INDEX] = { .type = NLA_U32 }, - [DEVLINK_ATTR_SB_POOL_INDEX] = { .type = NLA_U16 }, - [DEVLINK_ATTR_SB_POOL_TYPE] = { .type = NLA_U8 }, - [DEVLINK_ATTR_SB_POOL_SIZE] = { .type = NLA_U32 }, - [DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE] = { .type = NLA_U8 }, - [DEVLINK_ATTR_SB_THRESHOLD] = { .type = NLA_U32 }, - [DEVLINK_ATTR_SB_TC_INDEX] = { .type = NLA_U16 }, - [DEVLINK_ATTR_ESWITCH_MODE] = NLA_POLICY_RANGE(NLA_U16, DEVLINK_ESWITCH_MODE_LEGACY, - DEVLINK_ESWITCH_MODE_SWITCHDEV), - [DEVLINK_ATTR_ESWITCH_INLINE_MODE] = { .type = NLA_U8 }, - [DEVLINK_ATTR_ESWITCH_ENCAP_MODE] = { .type = NLA_U8 }, - [DEVLINK_ATTR_DPIPE_TABLE_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED] = { .type = NLA_U8 }, - [DEVLINK_ATTR_RESOURCE_ID] = { .type = NLA_U64}, - [DEVLINK_ATTR_RESOURCE_SIZE] = { .type = NLA_U64}, - [DEVLINK_ATTR_PARAM_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_PARAM_TYPE] = { .type = NLA_U8 }, - [DEVLINK_ATTR_PARAM_VALUE_CMODE] = { .type = NLA_U8 }, - [DEVLINK_ATTR_REGION_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_REGION_SNAPSHOT_ID] = { .type = NLA_U32 }, - [DEVLINK_ATTR_REGION_CHUNK_ADDR] = { .type = NLA_U64 }, - [DEVLINK_ATTR_REGION_CHUNK_LEN] = { .type = NLA_U64 }, - [DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] = { .type = NLA_U64 }, - [DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER] = { .type = NLA_U8 }, - [DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_FLASH_UPDATE_COMPONENT] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK] = - NLA_POLICY_BITFIELD32(DEVLINK_SUPPORTED_FLASH_OVERWRITE_SECTIONS), - [DEVLINK_ATTR_TRAP_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_TRAP_ACTION] = { .type = NLA_U8 }, - [DEVLINK_ATTR_TRAP_GROUP_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_NETNS_PID] = { .type = NLA_U32 }, - [DEVLINK_ATTR_NETNS_FD] = { .type = NLA_U32 }, - [DEVLINK_ATTR_NETNS_ID] = { .type = NLA_U32 }, - [DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP] = { .type = NLA_U8 }, - [DEVLINK_ATTR_TRAP_POLICER_ID] = { .type = NLA_U32 }, - [DEVLINK_ATTR_TRAP_POLICER_RATE] = { .type = NLA_U64 }, - [DEVLINK_ATTR_TRAP_POLICER_BURST] = { .type = NLA_U64 }, - [DEVLINK_ATTR_PORT_FUNCTION] = { .type = NLA_NESTED }, - [DEVLINK_ATTR_RELOAD_ACTION] = NLA_POLICY_RANGE(NLA_U8, DEVLINK_RELOAD_ACTION_DRIVER_REINIT, - DEVLINK_RELOAD_ACTION_MAX), - [DEVLINK_ATTR_RELOAD_LIMITS] = NLA_POLICY_BITFIELD32(DEVLINK_RELOAD_LIMITS_VALID_MASK), - [DEVLINK_ATTR_PORT_FLAVOUR] = { .type = NLA_U16 }, - [DEVLINK_ATTR_PORT_PCI_PF_NUMBER] = { .type = NLA_U16 }, - [DEVLINK_ATTR_PORT_PCI_SF_NUMBER] = { .type = NLA_U32 }, - [DEVLINK_ATTR_PORT_CONTROLLER_NUMBER] = { .type = NLA_U32 }, - [DEVLINK_ATTR_RATE_TYPE] = { .type = NLA_U16 }, - [DEVLINK_ATTR_RATE_TX_SHARE] = { .type = NLA_U64 }, - [DEVLINK_ATTR_RATE_TX_MAX] = { .type = NLA_U64 }, - [DEVLINK_ATTR_RATE_NODE_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_RATE_PARENT_NODE_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_LINECARD_INDEX] = { .type = NLA_U32 }, - [DEVLINK_ATTR_LINECARD_TYPE] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_SELFTESTS] = { .type = NLA_NESTED }, -}; - -static const struct genl_small_ops devlink_nl_ops[] = { - { - .cmd = DEVLINK_CMD_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_get_doit, - .dumpit = devlink_nl_cmd_get_dumpit, - /* can be retrieved by unprivileged users */ - }, - { - .cmd = DEVLINK_CMD_PORT_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_port_get_doit, - .dumpit = devlink_nl_cmd_port_get_dumpit, - .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, - /* can be retrieved by unprivileged users */ - }, - { - .cmd = DEVLINK_CMD_PORT_SET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_port_set_doit, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, - }, - { - .cmd = DEVLINK_CMD_RATE_GET, - .doit = devlink_nl_cmd_rate_get_doit, - .dumpit = devlink_nl_cmd_rate_get_dumpit, - .internal_flags = DEVLINK_NL_FLAG_NEED_RATE, - /* can be retrieved by unprivileged users */ - }, - { - .cmd = DEVLINK_CMD_RATE_SET, - .doit = devlink_nl_cmd_rate_set_doit, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_RATE, - }, - { - .cmd = DEVLINK_CMD_RATE_NEW, - .doit = devlink_nl_cmd_rate_new_doit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_RATE_DEL, - .doit = devlink_nl_cmd_rate_del_doit, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_RATE_NODE, - }, - { - .cmd = DEVLINK_CMD_PORT_SPLIT, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_port_split_doit, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, - }, - { - .cmd = DEVLINK_CMD_PORT_UNSPLIT, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_port_unsplit_doit, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, - }, - { - .cmd = DEVLINK_CMD_PORT_NEW, - .doit = devlink_nl_cmd_port_new_doit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_PORT_DEL, - .doit = devlink_nl_cmd_port_del_doit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_LINECARD_GET, - .doit = devlink_nl_cmd_linecard_get_doit, - .dumpit = devlink_nl_cmd_linecard_get_dumpit, - .internal_flags = DEVLINK_NL_FLAG_NEED_LINECARD, - /* can be retrieved by unprivileged users */ - }, - { - .cmd = DEVLINK_CMD_LINECARD_SET, - .doit = devlink_nl_cmd_linecard_set_doit, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_LINECARD, - }, - { - .cmd = DEVLINK_CMD_SB_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_sb_get_doit, - .dumpit = devlink_nl_cmd_sb_get_dumpit, - /* can be retrieved by unprivileged users */ - }, - { - .cmd = DEVLINK_CMD_SB_POOL_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_sb_pool_get_doit, - .dumpit = devlink_nl_cmd_sb_pool_get_dumpit, - /* can be retrieved by unprivileged users */ - }, - { - .cmd = DEVLINK_CMD_SB_POOL_SET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_sb_pool_set_doit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_SB_PORT_POOL_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_sb_port_pool_get_doit, - .dumpit = devlink_nl_cmd_sb_port_pool_get_dumpit, - .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, - /* can be retrieved by unprivileged users */ - }, - { - .cmd = DEVLINK_CMD_SB_PORT_POOL_SET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_sb_port_pool_set_doit, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, - }, - { - .cmd = DEVLINK_CMD_SB_TC_POOL_BIND_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_sb_tc_pool_bind_get_doit, - .dumpit = devlink_nl_cmd_sb_tc_pool_bind_get_dumpit, - .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, - /* can be retrieved by unprivileged users */ - }, - { - .cmd = DEVLINK_CMD_SB_TC_POOL_BIND_SET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_sb_tc_pool_bind_set_doit, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, - }, - { - .cmd = DEVLINK_CMD_SB_OCC_SNAPSHOT, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_sb_occ_snapshot_doit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_SB_OCC_MAX_CLEAR, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_sb_occ_max_clear_doit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_ESWITCH_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_eswitch_get_doit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_ESWITCH_SET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_eswitch_set_doit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_DPIPE_TABLE_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_dpipe_table_get, - /* can be retrieved by unprivileged users */ - }, - { - .cmd = DEVLINK_CMD_DPIPE_ENTRIES_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_dpipe_entries_get, - /* can be retrieved by unprivileged users */ - }, - { - .cmd = DEVLINK_CMD_DPIPE_HEADERS_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_dpipe_headers_get, - /* can be retrieved by unprivileged users */ - }, - { - .cmd = DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_dpipe_table_counters_set, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_RESOURCE_SET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_resource_set, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_RESOURCE_DUMP, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_resource_dump, - /* can be retrieved by unprivileged users */ - }, - { - .cmd = DEVLINK_CMD_RELOAD, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_reload, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_PARAM_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_param_get_doit, - .dumpit = devlink_nl_cmd_param_get_dumpit, - /* can be retrieved by unprivileged users */ - }, - { - .cmd = DEVLINK_CMD_PARAM_SET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_param_set_doit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_PORT_PARAM_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_port_param_get_doit, - .dumpit = devlink_nl_cmd_port_param_get_dumpit, - .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, - /* can be retrieved by unprivileged users */ - }, - { - .cmd = DEVLINK_CMD_PORT_PARAM_SET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_port_param_set_doit, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, - }, - { - .cmd = DEVLINK_CMD_REGION_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_region_get_doit, - .dumpit = devlink_nl_cmd_region_get_dumpit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_REGION_NEW, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_region_new, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_REGION_DEL, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_region_del, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_REGION_READ, - .validate = GENL_DONT_VALIDATE_STRICT | - GENL_DONT_VALIDATE_DUMP_STRICT, - .dumpit = devlink_nl_cmd_region_read_dumpit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_INFO_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_info_get_doit, - .dumpit = devlink_nl_cmd_info_get_dumpit, - /* can be retrieved by unprivileged users */ - }, - { - .cmd = DEVLINK_CMD_HEALTH_REPORTER_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_health_reporter_get_doit, - .dumpit = devlink_nl_cmd_health_reporter_get_dumpit, - .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT, - /* can be retrieved by unprivileged users */ - }, - { - .cmd = DEVLINK_CMD_HEALTH_REPORTER_SET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_health_reporter_set_doit, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT, - }, - { - .cmd = DEVLINK_CMD_HEALTH_REPORTER_RECOVER, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_health_reporter_recover_doit, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT, - }, - { - .cmd = DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_health_reporter_diagnose_doit, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT, - }, - { - .cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET, - .validate = GENL_DONT_VALIDATE_STRICT | - GENL_DONT_VALIDATE_DUMP_STRICT, - .dumpit = devlink_nl_cmd_health_reporter_dump_get_dumpit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_health_reporter_dump_clear_doit, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT, - }, - { - .cmd = DEVLINK_CMD_HEALTH_REPORTER_TEST, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_health_reporter_test_doit, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT, - }, - { - .cmd = DEVLINK_CMD_FLASH_UPDATE, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_flash_update, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_TRAP_GET, - .doit = devlink_nl_cmd_trap_get_doit, - .dumpit = devlink_nl_cmd_trap_get_dumpit, - /* can be retrieved by unprivileged users */ - }, - { - .cmd = DEVLINK_CMD_TRAP_SET, - .doit = devlink_nl_cmd_trap_set_doit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_TRAP_GROUP_GET, - .doit = devlink_nl_cmd_trap_group_get_doit, - .dumpit = devlink_nl_cmd_trap_group_get_dumpit, - /* can be retrieved by unprivileged users */ - }, - { - .cmd = DEVLINK_CMD_TRAP_GROUP_SET, - .doit = devlink_nl_cmd_trap_group_set_doit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_TRAP_POLICER_GET, - .doit = devlink_nl_cmd_trap_policer_get_doit, - .dumpit = devlink_nl_cmd_trap_policer_get_dumpit, - /* can be retrieved by unprivileged users */ - }, - { - .cmd = DEVLINK_CMD_TRAP_POLICER_SET, - .doit = devlink_nl_cmd_trap_policer_set_doit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_SELFTESTS_GET, - .doit = devlink_nl_cmd_selftests_get_doit, - .dumpit = devlink_nl_cmd_selftests_get_dumpit - /* can be retrieved by unprivileged users */ - }, - { - .cmd = DEVLINK_CMD_SELFTESTS_RUN, - .doit = devlink_nl_cmd_selftests_run, - .flags = GENL_ADMIN_PERM, - }, -}; - -static struct genl_family devlink_nl_family __ro_after_init = { - .name = DEVLINK_GENL_NAME, - .version = DEVLINK_GENL_VERSION, - .maxattr = DEVLINK_ATTR_MAX, - .policy = devlink_nl_policy, - .netnsok = true, - .parallel_ops = true, - .pre_doit = devlink_nl_pre_doit, - .post_doit = devlink_nl_post_doit, - .module = THIS_MODULE, - .small_ops = devlink_nl_ops, - .n_small_ops = ARRAY_SIZE(devlink_nl_ops), - .resv_start_op = DEVLINK_CMD_SELFTESTS_RUN + 1, - .mcgrps = devlink_nl_mcgrps, - .n_mcgrps = ARRAY_SIZE(devlink_nl_mcgrps), -}; - -static bool devlink_reload_actions_valid(const struct devlink_ops *ops) -{ - const struct devlink_reload_combination *comb; - int i; - - if (!devlink_reload_supported(ops)) { - if (WARN_ON(ops->reload_actions)) - return false; - return true; - } - - if (WARN_ON(!ops->reload_actions || - ops->reload_actions & BIT(DEVLINK_RELOAD_ACTION_UNSPEC) || - ops->reload_actions >= BIT(__DEVLINK_RELOAD_ACTION_MAX))) - return false; - - if (WARN_ON(ops->reload_limits & BIT(DEVLINK_RELOAD_LIMIT_UNSPEC) || - ops->reload_limits >= BIT(__DEVLINK_RELOAD_LIMIT_MAX))) - return false; - - for (i = 0; i < ARRAY_SIZE(devlink_reload_invalid_combinations); i++) { - comb = &devlink_reload_invalid_combinations[i]; - if (ops->reload_actions == BIT(comb->action) && - ops->reload_limits == BIT(comb->limit)) - return false; - } - return true; -} - -/** - * devlink_set_features - Set devlink supported features - * - * @devlink: devlink - * @features: devlink support features - * - * This interface allows us to set reload ops separatelly from - * the devlink_alloc. - */ -void devlink_set_features(struct devlink *devlink, u64 features) -{ - ASSERT_DEVLINK_NOT_REGISTERED(devlink); - - WARN_ON(features & DEVLINK_F_RELOAD && - !devlink_reload_supported(devlink->ops)); - devlink->features = features; -} -EXPORT_SYMBOL_GPL(devlink_set_features); - -/** - * devlink_alloc_ns - Allocate new devlink instance resources - * in specific namespace - * - * @ops: ops - * @priv_size: size of user private data - * @net: net namespace - * @dev: parent device - * - * Allocate new devlink instance resources, including devlink index - * and name. - */ -struct devlink *devlink_alloc_ns(const struct devlink_ops *ops, - size_t priv_size, struct net *net, - struct device *dev) -{ - struct devlink *devlink; - static u32 last_id; - int ret; - - WARN_ON(!ops || !dev); - if (!devlink_reload_actions_valid(ops)) - return NULL; - - devlink = kzalloc(sizeof(*devlink) + priv_size, GFP_KERNEL); - if (!devlink) - return NULL; - - ret = xa_alloc_cyclic(&devlinks, &devlink->index, devlink, xa_limit_31b, - &last_id, GFP_KERNEL); - if (ret < 0) { - kfree(devlink); - return NULL; - } - - devlink->dev = dev; - devlink->ops = ops; - xa_init_flags(&devlink->snapshot_ids, XA_FLAGS_ALLOC); - write_pnet(&devlink->_net, net); - INIT_LIST_HEAD(&devlink->port_list); - INIT_LIST_HEAD(&devlink->rate_list); - INIT_LIST_HEAD(&devlink->linecard_list); - INIT_LIST_HEAD(&devlink->sb_list); - INIT_LIST_HEAD_RCU(&devlink->dpipe_table_list); - INIT_LIST_HEAD(&devlink->resource_list); - INIT_LIST_HEAD(&devlink->param_list); - INIT_LIST_HEAD(&devlink->region_list); - INIT_LIST_HEAD(&devlink->reporter_list); - INIT_LIST_HEAD(&devlink->trap_list); - INIT_LIST_HEAD(&devlink->trap_group_list); - INIT_LIST_HEAD(&devlink->trap_policer_list); - lockdep_register_key(&devlink->lock_key); - mutex_init(&devlink->lock); - lockdep_set_class(&devlink->lock, &devlink->lock_key); - mutex_init(&devlink->reporters_lock); - mutex_init(&devlink->linecards_lock); - refcount_set(&devlink->refcount, 1); - init_completion(&devlink->comp); - - return devlink; -} -EXPORT_SYMBOL_GPL(devlink_alloc_ns); - -static void -devlink_trap_policer_notify(struct devlink *devlink, - const struct devlink_trap_policer_item *policer_item, - enum devlink_command cmd); -static void -devlink_trap_group_notify(struct devlink *devlink, - const struct devlink_trap_group_item *group_item, - enum devlink_command cmd); -static void devlink_trap_notify(struct devlink *devlink, - const struct devlink_trap_item *trap_item, - enum devlink_command cmd); - -static void devlink_notify_register(struct devlink *devlink) -{ - struct devlink_trap_policer_item *policer_item; - struct devlink_trap_group_item *group_item; - struct devlink_param_item *param_item; - struct devlink_trap_item *trap_item; - struct devlink_port *devlink_port; - struct devlink_linecard *linecard; - struct devlink_rate *rate_node; - struct devlink_region *region; - - devlink_notify(devlink, DEVLINK_CMD_NEW); - list_for_each_entry(linecard, &devlink->linecard_list, list) - devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); - - list_for_each_entry(devlink_port, &devlink->port_list, list) - devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); - - list_for_each_entry(policer_item, &devlink->trap_policer_list, list) - devlink_trap_policer_notify(devlink, policer_item, - DEVLINK_CMD_TRAP_POLICER_NEW); - - list_for_each_entry(group_item, &devlink->trap_group_list, list) - devlink_trap_group_notify(devlink, group_item, - DEVLINK_CMD_TRAP_GROUP_NEW); - - list_for_each_entry(trap_item, &devlink->trap_list, list) - devlink_trap_notify(devlink, trap_item, DEVLINK_CMD_TRAP_NEW); - - list_for_each_entry(rate_node, &devlink->rate_list, list) - devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_NEW); - - list_for_each_entry(region, &devlink->region_list, list) - devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_NEW); - - list_for_each_entry(param_item, &devlink->param_list, list) - devlink_param_notify(devlink, 0, param_item, - DEVLINK_CMD_PARAM_NEW); -} - -static void devlink_notify_unregister(struct devlink *devlink) -{ - struct devlink_trap_policer_item *policer_item; - struct devlink_trap_group_item *group_item; - struct devlink_param_item *param_item; - struct devlink_trap_item *trap_item; - struct devlink_port *devlink_port; - struct devlink_rate *rate_node; - struct devlink_region *region; - - list_for_each_entry_reverse(param_item, &devlink->param_list, list) - devlink_param_notify(devlink, 0, param_item, - DEVLINK_CMD_PARAM_DEL); - - list_for_each_entry_reverse(region, &devlink->region_list, list) - devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_DEL); - - list_for_each_entry_reverse(rate_node, &devlink->rate_list, list) - devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_DEL); - - list_for_each_entry_reverse(trap_item, &devlink->trap_list, list) - devlink_trap_notify(devlink, trap_item, DEVLINK_CMD_TRAP_DEL); - - list_for_each_entry_reverse(group_item, &devlink->trap_group_list, list) - devlink_trap_group_notify(devlink, group_item, - DEVLINK_CMD_TRAP_GROUP_DEL); - list_for_each_entry_reverse(policer_item, &devlink->trap_policer_list, - list) - devlink_trap_policer_notify(devlink, policer_item, - DEVLINK_CMD_TRAP_POLICER_DEL); - - list_for_each_entry_reverse(devlink_port, &devlink->port_list, list) - devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_DEL); - devlink_notify(devlink, DEVLINK_CMD_DEL); -} - -/** - * devlink_register - Register devlink instance - * - * @devlink: devlink - */ -void devlink_register(struct devlink *devlink) -{ - ASSERT_DEVLINK_NOT_REGISTERED(devlink); - /* Make sure that we are in .probe() routine */ - - xa_set_mark(&devlinks, devlink->index, DEVLINK_REGISTERED); - devlink_notify_register(devlink); -} -EXPORT_SYMBOL_GPL(devlink_register); - -/** - * devlink_unregister - Unregister devlink instance - * - * @devlink: devlink - */ -void devlink_unregister(struct devlink *devlink) -{ - ASSERT_DEVLINK_REGISTERED(devlink); - /* Make sure that we are in .remove() routine */ - - xa_set_mark(&devlinks, devlink->index, DEVLINK_UNREGISTERING); - devlink_put(devlink); - wait_for_completion(&devlink->comp); - - devlink_notify_unregister(devlink); - xa_clear_mark(&devlinks, devlink->index, DEVLINK_REGISTERED); - xa_clear_mark(&devlinks, devlink->index, DEVLINK_UNREGISTERING); -} -EXPORT_SYMBOL_GPL(devlink_unregister); - -/** - * devlink_free - Free devlink instance resources - * - * @devlink: devlink - */ -void devlink_free(struct devlink *devlink) -{ - ASSERT_DEVLINK_NOT_REGISTERED(devlink); - - mutex_destroy(&devlink->linecards_lock); - mutex_destroy(&devlink->reporters_lock); - mutex_destroy(&devlink->lock); - lockdep_unregister_key(&devlink->lock_key); - WARN_ON(!list_empty(&devlink->trap_policer_list)); - WARN_ON(!list_empty(&devlink->trap_group_list)); - WARN_ON(!list_empty(&devlink->trap_list)); - WARN_ON(!list_empty(&devlink->reporter_list)); - WARN_ON(!list_empty(&devlink->region_list)); - WARN_ON(!list_empty(&devlink->param_list)); - WARN_ON(!list_empty(&devlink->resource_list)); - WARN_ON(!list_empty(&devlink->dpipe_table_list)); - WARN_ON(!list_empty(&devlink->sb_list)); - WARN_ON(!list_empty(&devlink->rate_list)); - WARN_ON(!list_empty(&devlink->linecard_list)); - WARN_ON(!list_empty(&devlink->port_list)); - - xa_destroy(&devlink->snapshot_ids); - xa_erase(&devlinks, devlink->index); - - kfree(devlink); -} -EXPORT_SYMBOL_GPL(devlink_free); - -static void devlink_port_type_warn(struct work_struct *work) -{ - struct devlink_port *port = container_of(to_delayed_work(work), - struct devlink_port, - type_warn_dw); - dev_warn(port->devlink->dev, "Type was not set for devlink port."); -} - -static bool devlink_port_type_should_warn(struct devlink_port *devlink_port) -{ - /* Ignore CPU and DSA flavours. */ - return devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_CPU && - devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_DSA && - devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_UNUSED; -} - -#define DEVLINK_PORT_TYPE_WARN_TIMEOUT (HZ * 3600) - -static void devlink_port_type_warn_schedule(struct devlink_port *devlink_port) -{ - if (!devlink_port_type_should_warn(devlink_port)) - return; - /* Schedule a work to WARN in case driver does not set port - * type within timeout. - */ - schedule_delayed_work(&devlink_port->type_warn_dw, - DEVLINK_PORT_TYPE_WARN_TIMEOUT); -} - -static void devlink_port_type_warn_cancel(struct devlink_port *devlink_port) -{ - if (!devlink_port_type_should_warn(devlink_port)) - return; - cancel_delayed_work_sync(&devlink_port->type_warn_dw); -} - -/** - * devlink_port_init() - Init devlink port - * - * @devlink: devlink - * @devlink_port: devlink port - * - * Initialize essencial stuff that is needed for functions - * that may be called before devlink port registration. - * Call to this function is optional and not needed - * in case the driver does not use such functions. - */ -void devlink_port_init(struct devlink *devlink, - struct devlink_port *devlink_port) -{ - if (devlink_port->initialized) - return; - devlink_port->devlink = devlink; - INIT_LIST_HEAD(&devlink_port->region_list); - devlink_port->initialized = true; -} -EXPORT_SYMBOL_GPL(devlink_port_init); - -/** - * devlink_port_fini() - Deinitialize devlink port - * - * @devlink_port: devlink port - * - * Deinitialize essencial stuff that is in use for functions - * that may be called after devlink port unregistration. - * Call to this function is optional and not needed - * in case the driver does not use such functions. - */ -void devlink_port_fini(struct devlink_port *devlink_port) -{ - WARN_ON(!list_empty(&devlink_port->region_list)); -} -EXPORT_SYMBOL_GPL(devlink_port_fini); - -/** - * devl_port_register() - Register devlink port - * - * @devlink: devlink - * @devlink_port: devlink port - * @port_index: driver-specific numerical identifier of the port - * - * Register devlink port with provided port index. User can use - * any indexing, even hw-related one. devlink_port structure - * is convenient to be embedded inside user driver private structure. - * Note that the caller should take care of zeroing the devlink_port - * structure. - */ -int devl_port_register(struct devlink *devlink, - struct devlink_port *devlink_port, - unsigned int port_index) -{ - devl_assert_locked(devlink); - - if (devlink_port_index_exists(devlink, port_index)) - return -EEXIST; - - ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port); - - devlink_port_init(devlink, devlink_port); - devlink_port->registered = true; - devlink_port->index = port_index; - spin_lock_init(&devlink_port->type_lock); - INIT_LIST_HEAD(&devlink_port->reporter_list); - mutex_init(&devlink_port->reporters_lock); - list_add_tail(&devlink_port->list, &devlink->port_list); - - INIT_DELAYED_WORK(&devlink_port->type_warn_dw, &devlink_port_type_warn); - devlink_port_type_warn_schedule(devlink_port); - devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); - return 0; -} -EXPORT_SYMBOL_GPL(devl_port_register); - -/** - * devlink_port_register - Register devlink port - * - * @devlink: devlink - * @devlink_port: devlink port - * @port_index: driver-specific numerical identifier of the port - * - * Register devlink port with provided port index. User can use - * any indexing, even hw-related one. devlink_port structure - * is convenient to be embedded inside user driver private structure. - * Note that the caller should take care of zeroing the devlink_port - * structure. - * - * Context: Takes and release devlink->lock <mutex>. - */ -int devlink_port_register(struct devlink *devlink, - struct devlink_port *devlink_port, - unsigned int port_index) -{ - int err; - - devl_lock(devlink); - err = devl_port_register(devlink, devlink_port, port_index); - devl_unlock(devlink); - return err; -} -EXPORT_SYMBOL_GPL(devlink_port_register); - -/** - * devl_port_unregister() - Unregister devlink port - * - * @devlink_port: devlink port - */ -void devl_port_unregister(struct devlink_port *devlink_port) -{ - lockdep_assert_held(&devlink_port->devlink->lock); - - devlink_port_type_warn_cancel(devlink_port); - devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_DEL); - list_del(&devlink_port->list); - WARN_ON(!list_empty(&devlink_port->reporter_list)); - mutex_destroy(&devlink_port->reporters_lock); - devlink_port->registered = false; -} -EXPORT_SYMBOL_GPL(devl_port_unregister); - -/** - * devlink_port_unregister - Unregister devlink port - * - * @devlink_port: devlink port - * - * Context: Takes and release devlink->lock <mutex>. - */ -void devlink_port_unregister(struct devlink_port *devlink_port) -{ - struct devlink *devlink = devlink_port->devlink; - - devl_lock(devlink); - devl_port_unregister(devlink_port); - devl_unlock(devlink); -} -EXPORT_SYMBOL_GPL(devlink_port_unregister); - -static void __devlink_port_type_set(struct devlink_port *devlink_port, - enum devlink_port_type type, - void *type_dev) -{ - ASSERT_DEVLINK_PORT_REGISTERED(devlink_port); - - devlink_port_type_warn_cancel(devlink_port); - spin_lock_bh(&devlink_port->type_lock); - devlink_port->type = type; - devlink_port->type_dev = type_dev; - spin_unlock_bh(&devlink_port->type_lock); - devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); -} - -static void devlink_port_type_netdev_checks(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 (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. - */ - 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_eth_set - Set port type to Ethernet - * - * @devlink_port: devlink port - * @netdev: related netdevice - */ -void devlink_port_type_eth_set(struct devlink_port *devlink_port, - struct net_device *netdev) -{ - if (netdev) - devlink_port_type_netdev_checks(devlink_port, netdev); - else - dev_warn(devlink_port->devlink->dev, - "devlink port type for port %d set to Ethernet without a software interface reference, device type not supported by the kernel?\n", - devlink_port->index); - - __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_ETH, netdev); -} -EXPORT_SYMBOL_GPL(devlink_port_type_eth_set); - -/** - * devlink_port_type_ib_set - Set port type to InfiniBand - * - * @devlink_port: devlink port - * @ibdev: related IB device - */ -void devlink_port_type_ib_set(struct devlink_port *devlink_port, - struct ib_device *ibdev) -{ - __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_IB, ibdev); -} -EXPORT_SYMBOL_GPL(devlink_port_type_ib_set); - -/** - * devlink_port_type_clear - Clear port type - * - * @devlink_port: devlink port - */ -void devlink_port_type_clear(struct devlink_port *devlink_port) -{ - __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_NOTSET, NULL); - devlink_port_type_warn_schedule(devlink_port); -} -EXPORT_SYMBOL_GPL(devlink_port_type_clear); - -static int __devlink_port_attrs_set(struct devlink_port *devlink_port, - enum devlink_port_flavour flavour) -{ - struct devlink_port_attrs *attrs = &devlink_port->attrs; - - devlink_port->attrs_set = true; - attrs->flavour = flavour; - if (attrs->switch_id.id_len) { - devlink_port->switch_port = true; - if (WARN_ON(attrs->switch_id.id_len > MAX_PHYS_ITEM_ID_LEN)) - attrs->switch_id.id_len = MAX_PHYS_ITEM_ID_LEN; - } else { - devlink_port->switch_port = false; - } - return 0; -} - -/** - * devlink_port_attrs_set - Set port attributes - * - * @devlink_port: devlink port - * @attrs: devlink port attrs - */ -void devlink_port_attrs_set(struct devlink_port *devlink_port, - struct devlink_port_attrs *attrs) -{ - int ret; - - ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port); - - devlink_port->attrs = *attrs; - ret = __devlink_port_attrs_set(devlink_port, attrs->flavour); - if (ret) - return; - WARN_ON(attrs->splittable && attrs->split); -} -EXPORT_SYMBOL_GPL(devlink_port_attrs_set); - -/** - * devlink_port_attrs_pci_pf_set - Set PCI PF port attributes - * - * @devlink_port: devlink port - * @controller: associated controller number for the devlink port instance - * @pf: associated PF for the devlink port instance - * @external: indicates if the port is for an external controller - */ -void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u32 controller, - u16 pf, bool external) -{ - struct devlink_port_attrs *attrs = &devlink_port->attrs; - int ret; - - ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port); - - ret = __devlink_port_attrs_set(devlink_port, - DEVLINK_PORT_FLAVOUR_PCI_PF); - if (ret) - return; - attrs->pci_pf.controller = controller; - attrs->pci_pf.pf = pf; - attrs->pci_pf.external = external; -} -EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_pf_set); - -/** - * devlink_port_attrs_pci_vf_set - Set PCI VF port attributes - * - * @devlink_port: devlink port - * @controller: associated controller number for the devlink port instance - * @pf: associated PF for the devlink port instance - * @vf: associated VF of a PF for the devlink port instance - * @external: indicates if the port is for an external controller - */ -void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 controller, - u16 pf, u16 vf, bool external) -{ - struct devlink_port_attrs *attrs = &devlink_port->attrs; - int ret; - - ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port); - - ret = __devlink_port_attrs_set(devlink_port, - DEVLINK_PORT_FLAVOUR_PCI_VF); - if (ret) - return; - attrs->pci_vf.controller = controller; - attrs->pci_vf.pf = pf; - attrs->pci_vf.vf = vf; - attrs->pci_vf.external = external; -} -EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_vf_set); - -/** - * devlink_port_attrs_pci_sf_set - Set PCI SF port attributes - * - * @devlink_port: devlink port - * @controller: associated controller number for the devlink port instance - * @pf: associated PF for the devlink port instance - * @sf: associated SF of a PF for the devlink port instance - * @external: indicates if the port is for an external controller - */ -void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, u32 controller, - u16 pf, u32 sf, bool external) -{ - struct devlink_port_attrs *attrs = &devlink_port->attrs; - int ret; - - ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port); - - ret = __devlink_port_attrs_set(devlink_port, - DEVLINK_PORT_FLAVOUR_PCI_SF); - if (ret) - return; - attrs->pci_sf.controller = controller; - attrs->pci_sf.pf = pf; - attrs->pci_sf.sf = sf; - attrs->pci_sf.external = external; -} -EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_sf_set); - -/** - * devl_rate_leaf_create - create devlink rate leaf - * @devlink_port: devlink port object to create rate object on - * @priv: driver private data - * - * Create devlink rate object of type leaf on provided @devlink_port. - */ -int devl_rate_leaf_create(struct devlink_port *devlink_port, void *priv) -{ - struct devlink *devlink = devlink_port->devlink; - struct devlink_rate *devlink_rate; - - devl_assert_locked(devlink_port->devlink); - - if (WARN_ON(devlink_port->devlink_rate)) - return -EBUSY; - - devlink_rate = kzalloc(sizeof(*devlink_rate), GFP_KERNEL); - if (!devlink_rate) - return -ENOMEM; - - devlink_rate->type = DEVLINK_RATE_TYPE_LEAF; - devlink_rate->devlink = devlink; - devlink_rate->devlink_port = devlink_port; - devlink_rate->priv = priv; - list_add_tail(&devlink_rate->list, &devlink->rate_list); - devlink_port->devlink_rate = devlink_rate; - devlink_rate_notify(devlink_rate, DEVLINK_CMD_RATE_NEW); - - return 0; -} -EXPORT_SYMBOL_GPL(devl_rate_leaf_create); - -/** - * devl_rate_leaf_destroy - destroy devlink rate leaf - * - * @devlink_port: devlink port linked to the rate object - * - * Destroy the devlink rate object of type leaf on provided @devlink_port. - */ -void devl_rate_leaf_destroy(struct devlink_port *devlink_port) -{ - struct devlink_rate *devlink_rate = devlink_port->devlink_rate; - - devl_assert_locked(devlink_port->devlink); - if (!devlink_rate) - return; - - devlink_rate_notify(devlink_rate, DEVLINK_CMD_RATE_DEL); - if (devlink_rate->parent) - refcount_dec(&devlink_rate->parent->refcnt); - list_del(&devlink_rate->list); - devlink_port->devlink_rate = NULL; - kfree(devlink_rate); -} -EXPORT_SYMBOL_GPL(devl_rate_leaf_destroy); - -/** - * devl_rate_nodes_destroy - destroy all devlink rate nodes on device - * @devlink: devlink instance - * - * Unset parent for all rate objects and destroy all rate nodes - * on specified device. - */ -void devl_rate_nodes_destroy(struct devlink *devlink) -{ - static struct devlink_rate *devlink_rate, *tmp; - const struct devlink_ops *ops = devlink->ops; - - devl_assert_locked(devlink); - - list_for_each_entry(devlink_rate, &devlink->rate_list, list) { - if (!devlink_rate->parent) - continue; - - refcount_dec(&devlink_rate->parent->refcnt); - if (devlink_rate_is_leaf(devlink_rate)) - ops->rate_leaf_parent_set(devlink_rate, NULL, devlink_rate->priv, - NULL, NULL); - else if (devlink_rate_is_node(devlink_rate)) - ops->rate_node_parent_set(devlink_rate, NULL, devlink_rate->priv, - NULL, NULL); - } - list_for_each_entry_safe(devlink_rate, tmp, &devlink->rate_list, list) { - if (devlink_rate_is_node(devlink_rate)) { - ops->rate_node_del(devlink_rate, devlink_rate->priv, NULL); - list_del(&devlink_rate->list); - kfree(devlink_rate->name); - kfree(devlink_rate); - } - } -} -EXPORT_SYMBOL_GPL(devl_rate_nodes_destroy); - -/** - * devlink_port_linecard_set - Link port with a linecard - * - * @devlink_port: devlink port - * @linecard: devlink linecard - */ -void devlink_port_linecard_set(struct devlink_port *devlink_port, - struct devlink_linecard *linecard) -{ - ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port); - - devlink_port->linecard = linecard; -} -EXPORT_SYMBOL_GPL(devlink_port_linecard_set); - -static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port, - char *name, size_t len) -{ - struct devlink_port_attrs *attrs = &devlink_port->attrs; - int n = 0; - - if (!devlink_port->attrs_set) - return -EOPNOTSUPP; - - switch (attrs->flavour) { - case DEVLINK_PORT_FLAVOUR_PHYSICAL: - if (devlink_port->linecard) - n = snprintf(name, len, "l%u", - devlink_port->linecard->index); - if (n < len) - n += snprintf(name + n, len - n, "p%u", - attrs->phys.port_number); - if (n < len && attrs->split) - n += snprintf(name + n, len - n, "s%u", - attrs->phys.split_subport_number); - break; - case DEVLINK_PORT_FLAVOUR_CPU: - case DEVLINK_PORT_FLAVOUR_DSA: - case DEVLINK_PORT_FLAVOUR_UNUSED: - /* As CPU and DSA ports do not have a netdevice associated - * case should not ever happen. - */ - WARN_ON(1); - return -EINVAL; - case DEVLINK_PORT_FLAVOUR_PCI_PF: - if (attrs->pci_pf.external) { - n = snprintf(name, len, "c%u", attrs->pci_pf.controller); - if (n >= len) - return -EINVAL; - len -= n; - name += n; - } - n = snprintf(name, len, "pf%u", attrs->pci_pf.pf); - break; - case DEVLINK_PORT_FLAVOUR_PCI_VF: - if (attrs->pci_vf.external) { - n = snprintf(name, len, "c%u", attrs->pci_vf.controller); - if (n >= len) - return -EINVAL; - len -= n; - name += n; - } - n = snprintf(name, len, "pf%uvf%u", - attrs->pci_vf.pf, attrs->pci_vf.vf); - break; - case DEVLINK_PORT_FLAVOUR_PCI_SF: - if (attrs->pci_sf.external) { - n = snprintf(name, len, "c%u", attrs->pci_sf.controller); - if (n >= len) - return -EINVAL; - len -= n; - name += n; - } - n = snprintf(name, len, "pf%usf%u", attrs->pci_sf.pf, - attrs->pci_sf.sf); - break; - case DEVLINK_PORT_FLAVOUR_VIRTUAL: - return -EOPNOTSUPP; - } - - if (n >= len) - return -EINVAL; - - return 0; -} - -static int devlink_linecard_types_init(struct devlink_linecard *linecard) -{ - struct devlink_linecard_type *linecard_type; - unsigned int count; - int i; - - count = linecard->ops->types_count(linecard, linecard->priv); - linecard->types = kmalloc_array(count, sizeof(*linecard_type), - GFP_KERNEL); - if (!linecard->types) - return -ENOMEM; - linecard->types_count = count; - - for (i = 0; i < count; i++) { - linecard_type = &linecard->types[i]; - linecard->ops->types_get(linecard, linecard->priv, i, - &linecard_type->type, - &linecard_type->priv); - } - return 0; -} - -static void devlink_linecard_types_fini(struct devlink_linecard *linecard) -{ - kfree(linecard->types); -} - -/** - * devlink_linecard_create - Create devlink linecard - * - * @devlink: devlink - * @linecard_index: driver-specific numerical identifier of the linecard - * @ops: linecards ops - * @priv: user priv pointer - * - * Create devlink linecard instance with provided linecard index. - * Caller can use any indexing, even hw-related one. - * - * Return: Line card structure or an ERR_PTR() encoded error code. - */ -struct devlink_linecard * -devlink_linecard_create(struct devlink *devlink, unsigned int linecard_index, - const struct devlink_linecard_ops *ops, void *priv) -{ - struct devlink_linecard *linecard; - int err; - - if (WARN_ON(!ops || !ops->provision || !ops->unprovision || - !ops->types_count || !ops->types_get)) - return ERR_PTR(-EINVAL); - - mutex_lock(&devlink->linecards_lock); - if (devlink_linecard_index_exists(devlink, linecard_index)) { - mutex_unlock(&devlink->linecards_lock); - return ERR_PTR(-EEXIST); - } - - linecard = kzalloc(sizeof(*linecard), GFP_KERNEL); - if (!linecard) { - mutex_unlock(&devlink->linecards_lock); - return ERR_PTR(-ENOMEM); - } - - linecard->devlink = devlink; - linecard->index = linecard_index; - linecard->ops = ops; - linecard->priv = priv; - linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED; - mutex_init(&linecard->state_lock); - - err = devlink_linecard_types_init(linecard); - if (err) { - mutex_destroy(&linecard->state_lock); - kfree(linecard); - mutex_unlock(&devlink->linecards_lock); - return ERR_PTR(err); - } - - list_add_tail(&linecard->list, &devlink->linecard_list); - refcount_set(&linecard->refcount, 1); - mutex_unlock(&devlink->linecards_lock); - devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); - return linecard; -} -EXPORT_SYMBOL_GPL(devlink_linecard_create); - -/** - * devlink_linecard_destroy - Destroy devlink linecard - * - * @linecard: devlink linecard - */ -void devlink_linecard_destroy(struct devlink_linecard *linecard) -{ - struct devlink *devlink = linecard->devlink; - - devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_DEL); - mutex_lock(&devlink->linecards_lock); - list_del(&linecard->list); - devlink_linecard_types_fini(linecard); - mutex_unlock(&devlink->linecards_lock); - devlink_linecard_put(linecard); -} -EXPORT_SYMBOL_GPL(devlink_linecard_destroy); - -/** - * devlink_linecard_provision_set - Set provisioning on linecard - * - * @linecard: devlink linecard - * @type: linecard type - * - * This is either called directly from the provision() op call or - * as a result of the provision() op call asynchronously. - */ -void devlink_linecard_provision_set(struct devlink_linecard *linecard, - const char *type) -{ - mutex_lock(&linecard->state_lock); - WARN_ON(linecard->type && strcmp(linecard->type, type)); - linecard->state = DEVLINK_LINECARD_STATE_PROVISIONED; - linecard->type = type; - devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); - mutex_unlock(&linecard->state_lock); -} -EXPORT_SYMBOL_GPL(devlink_linecard_provision_set); - -/** - * devlink_linecard_provision_clear - Clear provisioning on linecard - * - * @linecard: devlink linecard - * - * This is either called directly from the unprovision() op call or - * as a result of the unprovision() op call asynchronously. - */ -void devlink_linecard_provision_clear(struct devlink_linecard *linecard) -{ - mutex_lock(&linecard->state_lock); - WARN_ON(linecard->nested_devlink); - linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED; - linecard->type = NULL; - devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); - mutex_unlock(&linecard->state_lock); -} -EXPORT_SYMBOL_GPL(devlink_linecard_provision_clear); - -/** - * devlink_linecard_provision_fail - Fail provisioning on linecard - * - * @linecard: devlink linecard - * - * This is either called directly from the provision() op call or - * as a result of the provision() op call asynchronously. - */ -void devlink_linecard_provision_fail(struct devlink_linecard *linecard) -{ - mutex_lock(&linecard->state_lock); - WARN_ON(linecard->nested_devlink); - linecard->state = DEVLINK_LINECARD_STATE_PROVISIONING_FAILED; - devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); - mutex_unlock(&linecard->state_lock); -} -EXPORT_SYMBOL_GPL(devlink_linecard_provision_fail); - -/** - * devlink_linecard_activate - Set linecard active - * - * @linecard: devlink linecard - */ -void devlink_linecard_activate(struct devlink_linecard *linecard) -{ - mutex_lock(&linecard->state_lock); - WARN_ON(linecard->state != DEVLINK_LINECARD_STATE_PROVISIONED); - linecard->state = DEVLINK_LINECARD_STATE_ACTIVE; - devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); - mutex_unlock(&linecard->state_lock); -} -EXPORT_SYMBOL_GPL(devlink_linecard_activate); - -/** - * devlink_linecard_deactivate - Set linecard inactive - * - * @linecard: devlink linecard - */ -void devlink_linecard_deactivate(struct devlink_linecard *linecard) -{ - mutex_lock(&linecard->state_lock); - switch (linecard->state) { - case DEVLINK_LINECARD_STATE_ACTIVE: - linecard->state = DEVLINK_LINECARD_STATE_PROVISIONED; - devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); - break; - case DEVLINK_LINECARD_STATE_UNPROVISIONING: - /* Line card is being deactivated as part - * of unprovisioning flow. - */ - break; - default: - WARN_ON(1); - break; - } - mutex_unlock(&linecard->state_lock); -} -EXPORT_SYMBOL_GPL(devlink_linecard_deactivate); - -/** - * devlink_linecard_nested_dl_set - Attach/detach nested devlink - * instance to linecard. - * - * @linecard: devlink linecard - * @nested_devlink: devlink instance to attach or NULL to detach - */ -void devlink_linecard_nested_dl_set(struct devlink_linecard *linecard, - struct devlink *nested_devlink) -{ - mutex_lock(&linecard->state_lock); - linecard->nested_devlink = nested_devlink; - devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); - mutex_unlock(&linecard->state_lock); -} -EXPORT_SYMBOL_GPL(devlink_linecard_nested_dl_set); - -int devl_sb_register(struct devlink *devlink, unsigned int sb_index, - u32 size, u16 ingress_pools_count, - u16 egress_pools_count, u16 ingress_tc_count, - u16 egress_tc_count) -{ - struct devlink_sb *devlink_sb; - - lockdep_assert_held(&devlink->lock); - - if (devlink_sb_index_exists(devlink, sb_index)) - return -EEXIST; - - devlink_sb = kzalloc(sizeof(*devlink_sb), GFP_KERNEL); - if (!devlink_sb) - return -ENOMEM; - devlink_sb->index = sb_index; - devlink_sb->size = size; - devlink_sb->ingress_pools_count = ingress_pools_count; - devlink_sb->egress_pools_count = egress_pools_count; - devlink_sb->ingress_tc_count = ingress_tc_count; - devlink_sb->egress_tc_count = egress_tc_count; - list_add_tail(&devlink_sb->list, &devlink->sb_list); - return 0; -} -EXPORT_SYMBOL_GPL(devl_sb_register); - -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, - u16 egress_tc_count) -{ - int err; - - devl_lock(devlink); - err = devl_sb_register(devlink, sb_index, size, ingress_pools_count, - egress_pools_count, ingress_tc_count, - egress_tc_count); - devl_unlock(devlink); - return err; -} -EXPORT_SYMBOL_GPL(devlink_sb_register); - -void devl_sb_unregister(struct devlink *devlink, unsigned int sb_index) -{ - struct devlink_sb *devlink_sb; - - lockdep_assert_held(&devlink->lock); - - devlink_sb = devlink_sb_get_by_index(devlink, sb_index); - WARN_ON(!devlink_sb); - list_del(&devlink_sb->list); - kfree(devlink_sb); -} -EXPORT_SYMBOL_GPL(devl_sb_unregister); - -void devlink_sb_unregister(struct devlink *devlink, unsigned int sb_index) -{ - devl_lock(devlink); - devl_sb_unregister(devlink, sb_index); - devl_unlock(devlink); -} -EXPORT_SYMBOL_GPL(devlink_sb_unregister); - -/** - * devl_dpipe_headers_register - register dpipe headers - * - * @devlink: devlink - * @dpipe_headers: dpipe header array - * - * Register the headers supported by hardware. - */ -void devl_dpipe_headers_register(struct devlink *devlink, - struct devlink_dpipe_headers *dpipe_headers) -{ - lockdep_assert_held(&devlink->lock); - - devlink->dpipe_headers = dpipe_headers; -} -EXPORT_SYMBOL_GPL(devl_dpipe_headers_register); - -/** - * devl_dpipe_headers_unregister - unregister dpipe headers - * - * @devlink: devlink - * - * Unregister the headers supported by hardware. - */ -void devl_dpipe_headers_unregister(struct devlink *devlink) -{ - lockdep_assert_held(&devlink->lock); - - devlink->dpipe_headers = NULL; -} -EXPORT_SYMBOL_GPL(devl_dpipe_headers_unregister); - -/** - * devlink_dpipe_table_counter_enabled - check if counter allocation - * required - * @devlink: devlink - * @table_name: tables name - * - * Used by driver to check if counter allocation is required. - * After counter allocation is turned on the table entries - * are updated to include counter statistics. - * - * After that point on the driver must respect the counter - * state so that each entry added to the table is added - * with a counter. - */ -bool devlink_dpipe_table_counter_enabled(struct devlink *devlink, - const char *table_name) -{ - struct devlink_dpipe_table *table; - bool enabled; - - rcu_read_lock(); - table = devlink_dpipe_table_find(&devlink->dpipe_table_list, - table_name, devlink); - enabled = false; - if (table) - enabled = table->counters_enabled; - rcu_read_unlock(); - return enabled; -} -EXPORT_SYMBOL_GPL(devlink_dpipe_table_counter_enabled); - -/** - * devl_dpipe_table_register - register dpipe table - * - * @devlink: devlink - * @table_name: table name - * @table_ops: table ops - * @priv: priv - * @counter_control_extern: external control for counters - */ -int devl_dpipe_table_register(struct devlink *devlink, - const char *table_name, - struct devlink_dpipe_table_ops *table_ops, - void *priv, bool counter_control_extern) -{ - struct devlink_dpipe_table *table; - - lockdep_assert_held(&devlink->lock); - - if (WARN_ON(!table_ops->size_get)) - return -EINVAL; - - if (devlink_dpipe_table_find(&devlink->dpipe_table_list, table_name, - devlink)) - return -EEXIST; - - table = kzalloc(sizeof(*table), GFP_KERNEL); - if (!table) - return -ENOMEM; - - table->name = table_name; - table->table_ops = table_ops; - table->priv = priv; - table->counter_control_extern = counter_control_extern; - - list_add_tail_rcu(&table->list, &devlink->dpipe_table_list); - - return 0; -} -EXPORT_SYMBOL_GPL(devl_dpipe_table_register); - -/** - * devl_dpipe_table_unregister - unregister dpipe table - * - * @devlink: devlink - * @table_name: table name - */ -void devl_dpipe_table_unregister(struct devlink *devlink, - const char *table_name) -{ - struct devlink_dpipe_table *table; - - lockdep_assert_held(&devlink->lock); - - table = devlink_dpipe_table_find(&devlink->dpipe_table_list, - table_name, devlink); - if (!table) - return; - list_del_rcu(&table->list); - kfree_rcu(table, rcu); -} -EXPORT_SYMBOL_GPL(devl_dpipe_table_unregister); - -/** - * devl_resource_register - devlink resource register - * - * @devlink: devlink - * @resource_name: resource's name - * @resource_size: resource's size - * @resource_id: resource's id - * @parent_resource_id: resource's parent id - * @size_params: size parameters - * - * Generic resources should reuse the same names across drivers. - * Please see the generic resources list at: - * Documentation/networking/devlink/devlink-resource.rst - */ -int devl_resource_register(struct devlink *devlink, - const char *resource_name, - u64 resource_size, - u64 resource_id, - u64 parent_resource_id, - const struct devlink_resource_size_params *size_params) -{ - struct devlink_resource *resource; - struct list_head *resource_list; - bool top_hierarchy; - - lockdep_assert_held(&devlink->lock); - - top_hierarchy = parent_resource_id == DEVLINK_RESOURCE_ID_PARENT_TOP; - - resource = devlink_resource_find(devlink, NULL, resource_id); - if (resource) - return -EINVAL; - - resource = kzalloc(sizeof(*resource), GFP_KERNEL); - if (!resource) - return -ENOMEM; - - if (top_hierarchy) { - resource_list = &devlink->resource_list; - } else { - struct devlink_resource *parent_resource; - - parent_resource = devlink_resource_find(devlink, NULL, - parent_resource_id); - if (parent_resource) { - resource_list = &parent_resource->resource_list; - resource->parent = parent_resource; - } else { - kfree(resource); - return -EINVAL; - } - } - - resource->name = resource_name; - resource->size = resource_size; - resource->size_new = resource_size; - resource->id = resource_id; - resource->size_valid = true; - memcpy(&resource->size_params, size_params, - sizeof(resource->size_params)); - INIT_LIST_HEAD(&resource->resource_list); - list_add_tail(&resource->list, resource_list); - - return 0; -} -EXPORT_SYMBOL_GPL(devl_resource_register); - -/** - * devlink_resource_register - devlink resource register - * - * @devlink: devlink - * @resource_name: resource's name - * @resource_size: resource's size - * @resource_id: resource's id - * @parent_resource_id: resource's parent id - * @size_params: size parameters - * - * Generic resources should reuse the same names across drivers. - * Please see the generic resources list at: - * Documentation/networking/devlink/devlink-resource.rst - * - * Context: Takes and release devlink->lock <mutex>. - */ -int devlink_resource_register(struct devlink *devlink, - const char *resource_name, - u64 resource_size, - u64 resource_id, - u64 parent_resource_id, - const struct devlink_resource_size_params *size_params) -{ - int err; - - devl_lock(devlink); - err = devl_resource_register(devlink, resource_name, resource_size, - resource_id, parent_resource_id, size_params); - devl_unlock(devlink); - return err; -} -EXPORT_SYMBOL_GPL(devlink_resource_register); - -static void devlink_resource_unregister(struct devlink *devlink, - struct devlink_resource *resource) -{ - struct devlink_resource *tmp, *child_resource; - - list_for_each_entry_safe(child_resource, tmp, &resource->resource_list, - list) { - devlink_resource_unregister(devlink, child_resource); - list_del(&child_resource->list); - kfree(child_resource); - } -} - -/** - * devl_resources_unregister - free all resources - * - * @devlink: devlink - */ -void devl_resources_unregister(struct devlink *devlink) -{ - struct devlink_resource *tmp, *child_resource; - - lockdep_assert_held(&devlink->lock); - - list_for_each_entry_safe(child_resource, tmp, &devlink->resource_list, - list) { - devlink_resource_unregister(devlink, child_resource); - list_del(&child_resource->list); - kfree(child_resource); - } -} -EXPORT_SYMBOL_GPL(devl_resources_unregister); - -/** - * devlink_resources_unregister - free all resources - * - * @devlink: devlink - * - * Context: Takes and release devlink->lock <mutex>. - */ -void devlink_resources_unregister(struct devlink *devlink) -{ - devl_lock(devlink); - devl_resources_unregister(devlink); - devl_unlock(devlink); -} -EXPORT_SYMBOL_GPL(devlink_resources_unregister); - -/** - * devl_resource_size_get - get and update size - * - * @devlink: devlink - * @resource_id: the requested resource id - * @p_resource_size: ptr to update - */ -int devl_resource_size_get(struct devlink *devlink, - u64 resource_id, - u64 *p_resource_size) -{ - struct devlink_resource *resource; - - lockdep_assert_held(&devlink->lock); - - resource = devlink_resource_find(devlink, NULL, resource_id); - if (!resource) - return -EINVAL; - *p_resource_size = resource->size_new; - resource->size = resource->size_new; - return 0; -} -EXPORT_SYMBOL_GPL(devl_resource_size_get); - -/** - * devl_dpipe_table_resource_set - set the resource id - * - * @devlink: devlink - * @table_name: table name - * @resource_id: resource id - * @resource_units: number of resource's units consumed per table's entry - */ -int devl_dpipe_table_resource_set(struct devlink *devlink, - const char *table_name, u64 resource_id, - u64 resource_units) -{ - struct devlink_dpipe_table *table; - - table = devlink_dpipe_table_find(&devlink->dpipe_table_list, - table_name, devlink); - if (!table) - return -EINVAL; - - table->resource_id = resource_id; - table->resource_units = resource_units; - table->resource_valid = true; - return 0; -} -EXPORT_SYMBOL_GPL(devl_dpipe_table_resource_set); - -/** - * devl_resource_occ_get_register - register occupancy getter - * - * @devlink: devlink - * @resource_id: resource id - * @occ_get: occupancy getter callback - * @occ_get_priv: occupancy getter callback priv - */ -void devl_resource_occ_get_register(struct devlink *devlink, - u64 resource_id, - devlink_resource_occ_get_t *occ_get, - void *occ_get_priv) -{ - struct devlink_resource *resource; - - lockdep_assert_held(&devlink->lock); - - resource = devlink_resource_find(devlink, NULL, resource_id); - if (WARN_ON(!resource)) - return; - WARN_ON(resource->occ_get); - - resource->occ_get = occ_get; - resource->occ_get_priv = occ_get_priv; -} -EXPORT_SYMBOL_GPL(devl_resource_occ_get_register); - -/** - * devlink_resource_occ_get_register - register occupancy getter - * - * @devlink: devlink - * @resource_id: resource id - * @occ_get: occupancy getter callback - * @occ_get_priv: occupancy getter callback priv - * - * Context: Takes and release devlink->lock <mutex>. - */ -void devlink_resource_occ_get_register(struct devlink *devlink, - u64 resource_id, - devlink_resource_occ_get_t *occ_get, - void *occ_get_priv) -{ - devl_lock(devlink); - devl_resource_occ_get_register(devlink, resource_id, - occ_get, occ_get_priv); - devl_unlock(devlink); -} -EXPORT_SYMBOL_GPL(devlink_resource_occ_get_register); - -/** - * devl_resource_occ_get_unregister - unregister occupancy getter - * - * @devlink: devlink - * @resource_id: resource id - */ -void devl_resource_occ_get_unregister(struct devlink *devlink, - u64 resource_id) -{ - struct devlink_resource *resource; - - lockdep_assert_held(&devlink->lock); - - resource = devlink_resource_find(devlink, NULL, resource_id); - if (WARN_ON(!resource)) - return; - WARN_ON(!resource->occ_get); - - resource->occ_get = NULL; - resource->occ_get_priv = NULL; -} -EXPORT_SYMBOL_GPL(devl_resource_occ_get_unregister); - -/** - * devlink_resource_occ_get_unregister - unregister occupancy getter - * - * @devlink: devlink - * @resource_id: resource id - * - * Context: Takes and release devlink->lock <mutex>. - */ -void devlink_resource_occ_get_unregister(struct devlink *devlink, - u64 resource_id) -{ - devl_lock(devlink); - devl_resource_occ_get_unregister(devlink, resource_id); - devl_unlock(devlink); -} -EXPORT_SYMBOL_GPL(devlink_resource_occ_get_unregister); - -static int devlink_param_verify(const struct devlink_param *param) -{ - if (!param || !param->name || !param->supported_cmodes) - return -EINVAL; - if (param->generic) - return devlink_param_generic_verify(param); - else - return devlink_param_driver_verify(param); -} - -/** - * devlink_params_register - register configuration parameters - * - * @devlink: devlink - * @params: configuration parameters array - * @params_count: number of parameters provided - * - * Register the configuration parameters supported by the driver. - */ -int devlink_params_register(struct devlink *devlink, - const struct devlink_param *params, - size_t params_count) -{ - const struct devlink_param *param = params; - int i, err; - - ASSERT_DEVLINK_NOT_REGISTERED(devlink); - - for (i = 0; i < params_count; i++, param++) { - err = devlink_param_register(devlink, param); - if (err) - goto rollback; - } - return 0; - -rollback: - if (!i) - return err; - - for (param--; i > 0; i--, param--) - devlink_param_unregister(devlink, param); - return err; -} -EXPORT_SYMBOL_GPL(devlink_params_register); - -/** - * devlink_params_unregister - unregister configuration parameters - * @devlink: devlink - * @params: configuration parameters to unregister - * @params_count: number of parameters provided - */ -void devlink_params_unregister(struct devlink *devlink, - const struct devlink_param *params, - size_t params_count) -{ - const struct devlink_param *param = params; - int i; - - ASSERT_DEVLINK_NOT_REGISTERED(devlink); - - for (i = 0; i < params_count; i++, param++) - devlink_param_unregister(devlink, param); -} -EXPORT_SYMBOL_GPL(devlink_params_unregister); - -/** - * devlink_param_register - register one configuration parameter - * - * @devlink: devlink - * @param: one configuration parameter - * - * Register the configuration parameter supported by the driver. - * Return: returns 0 on successful registration or error code otherwise. - */ -int devlink_param_register(struct devlink *devlink, - const struct devlink_param *param) -{ - struct devlink_param_item *param_item; - - ASSERT_DEVLINK_NOT_REGISTERED(devlink); - - WARN_ON(devlink_param_verify(param)); - WARN_ON(devlink_param_find_by_name(&devlink->param_list, param->name)); - - if (param->supported_cmodes == BIT(DEVLINK_PARAM_CMODE_DRIVERINIT)) - WARN_ON(param->get || param->set); - else - WARN_ON(!param->get || !param->set); - - param_item = kzalloc(sizeof(*param_item), GFP_KERNEL); - if (!param_item) - return -ENOMEM; - - param_item->param = param; - - list_add_tail(&param_item->list, &devlink->param_list); - return 0; -} -EXPORT_SYMBOL_GPL(devlink_param_register); - -/** - * devlink_param_unregister - unregister one configuration parameter - * @devlink: devlink - * @param: configuration parameter to unregister - */ -void devlink_param_unregister(struct devlink *devlink, - const struct devlink_param *param) -{ - struct devlink_param_item *param_item; - - ASSERT_DEVLINK_NOT_REGISTERED(devlink); - - param_item = - devlink_param_find_by_name(&devlink->param_list, param->name); - WARN_ON(!param_item); - list_del(&param_item->list); - kfree(param_item); -} -EXPORT_SYMBOL_GPL(devlink_param_unregister); - -/** - * devlink_param_driverinit_value_get - get configuration parameter - * value for driver initializing - * - * @devlink: devlink - * @param_id: parameter ID - * @init_val: value of parameter in driverinit configuration mode - * - * This function should be used by the driver to get driverinit - * configuration for initialization after reload command. - */ -int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id, - union devlink_param_value *init_val) -{ - struct devlink_param_item *param_item; - - if (!devlink_reload_supported(devlink->ops)) - return -EOPNOTSUPP; - - param_item = devlink_param_find_by_id(&devlink->param_list, param_id); - if (!param_item) - return -EINVAL; - - if (!param_item->driverinit_value_valid || - !devlink_param_cmode_is_supported(param_item->param, - DEVLINK_PARAM_CMODE_DRIVERINIT)) - return -EOPNOTSUPP; - - if (param_item->param->type == DEVLINK_PARAM_TYPE_STRING) - strcpy(init_val->vstr, param_item->driverinit_value.vstr); - else - *init_val = param_item->driverinit_value; - - return 0; -} -EXPORT_SYMBOL_GPL(devlink_param_driverinit_value_get); - -/** - * devlink_param_driverinit_value_set - set value of configuration - * parameter for driverinit - * configuration mode - * - * @devlink: devlink - * @param_id: parameter ID - * @init_val: value of parameter to set for driverinit configuration mode - * - * This function should be used by the driver to set driverinit - * configuration mode default value. - */ -int devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id, - union devlink_param_value init_val) -{ - struct devlink_param_item *param_item; - - ASSERT_DEVLINK_NOT_REGISTERED(devlink); - - param_item = devlink_param_find_by_id(&devlink->param_list, param_id); - if (!param_item) - return -EINVAL; - - if (!devlink_param_cmode_is_supported(param_item->param, - DEVLINK_PARAM_CMODE_DRIVERINIT)) - return -EOPNOTSUPP; - - if (param_item->param->type == DEVLINK_PARAM_TYPE_STRING) - strcpy(param_item->driverinit_value.vstr, init_val.vstr); - else - param_item->driverinit_value = init_val; - param_item->driverinit_value_valid = true; - return 0; -} -EXPORT_SYMBOL_GPL(devlink_param_driverinit_value_set); - -/** - * devlink_param_value_changed - notify devlink on a parameter's value - * change. Should be called by the driver - * right after the change. - * - * @devlink: devlink - * @param_id: parameter ID - * - * This function should be used by the driver to notify devlink on value - * change, excluding driverinit configuration mode. - * For driverinit configuration mode driver should use the function - */ -void devlink_param_value_changed(struct devlink *devlink, u32 param_id) -{ - struct devlink_param_item *param_item; - - param_item = devlink_param_find_by_id(&devlink->param_list, param_id); - WARN_ON(!param_item); - - devlink_param_notify(devlink, 0, param_item, DEVLINK_CMD_PARAM_NEW); -} -EXPORT_SYMBOL_GPL(devlink_param_value_changed); - -/** - * devl_region_create - create a new address region - * - * @devlink: devlink - * @ops: region operations and name - * @region_max_snapshots: Maximum supported number of snapshots for region - * @region_size: size of region - */ -struct devlink_region *devl_region_create(struct devlink *devlink, - const struct devlink_region_ops *ops, - u32 region_max_snapshots, - u64 region_size) -{ - struct devlink_region *region; - - devl_assert_locked(devlink); - - if (WARN_ON(!ops) || WARN_ON(!ops->destructor)) - return ERR_PTR(-EINVAL); - - if (devlink_region_get_by_name(devlink, ops->name)) - return ERR_PTR(-EEXIST); - - region = kzalloc(sizeof(*region), GFP_KERNEL); - if (!region) - return ERR_PTR(-ENOMEM); - - region->devlink = devlink; - region->max_snapshots = region_max_snapshots; - region->ops = ops; - region->size = region_size; - INIT_LIST_HEAD(&region->snapshot_list); - mutex_init(&region->snapshot_lock); - list_add_tail(&region->list, &devlink->region_list); - devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_NEW); - - return region; -} -EXPORT_SYMBOL_GPL(devl_region_create); - -/** - * devlink_region_create - create a new address region - * - * @devlink: devlink - * @ops: region operations and name - * @region_max_snapshots: Maximum supported number of snapshots for region - * @region_size: size of region - * - * Context: Takes and release devlink->lock <mutex>. - */ -struct devlink_region * -devlink_region_create(struct devlink *devlink, - const struct devlink_region_ops *ops, - u32 region_max_snapshots, u64 region_size) -{ - struct devlink_region *region; - - devl_lock(devlink); - region = devl_region_create(devlink, ops, region_max_snapshots, - region_size); - devl_unlock(devlink); - return region; -} -EXPORT_SYMBOL_GPL(devlink_region_create); - -/** - * devlink_port_region_create - create a new address region for a port - * - * @port: devlink port - * @ops: region operations and name - * @region_max_snapshots: Maximum supported number of snapshots for region - * @region_size: size of region - * - * Context: Takes and release devlink->lock <mutex>. - */ -struct devlink_region * -devlink_port_region_create(struct devlink_port *port, - const struct devlink_port_region_ops *ops, - u32 region_max_snapshots, u64 region_size) -{ - struct devlink *devlink = port->devlink; - struct devlink_region *region; - int err = 0; - - ASSERT_DEVLINK_PORT_INITIALIZED(port); - - if (WARN_ON(!ops) || WARN_ON(!ops->destructor)) - return ERR_PTR(-EINVAL); - - devl_lock(devlink); - - if (devlink_port_region_get_by_name(port, ops->name)) { - err = -EEXIST; - goto unlock; - } - - region = kzalloc(sizeof(*region), GFP_KERNEL); - if (!region) { - err = -ENOMEM; - goto unlock; - } - - region->devlink = devlink; - region->port = port; - region->max_snapshots = region_max_snapshots; - region->port_ops = ops; - region->size = region_size; - INIT_LIST_HEAD(&region->snapshot_list); - mutex_init(&region->snapshot_lock); - list_add_tail(&region->list, &port->region_list); - devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_NEW); - - devl_unlock(devlink); - return region; - -unlock: - devl_unlock(devlink); - return ERR_PTR(err); -} -EXPORT_SYMBOL_GPL(devlink_port_region_create); - -/** - * devl_region_destroy - destroy address region - * - * @region: devlink region to destroy - */ -void devl_region_destroy(struct devlink_region *region) -{ - struct devlink *devlink = region->devlink; - struct devlink_snapshot *snapshot, *ts; - - devl_assert_locked(devlink); - - /* Free all snapshots of region */ - mutex_lock(&region->snapshot_lock); - list_for_each_entry_safe(snapshot, ts, &region->snapshot_list, list) - devlink_region_snapshot_del(region, snapshot); - mutex_unlock(&region->snapshot_lock); - - list_del(&region->list); - mutex_destroy(&region->snapshot_lock); - - devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_DEL); - kfree(region); -} -EXPORT_SYMBOL_GPL(devl_region_destroy); - -/** - * devlink_region_destroy - destroy address region - * - * @region: devlink region to destroy - * - * Context: Takes and release devlink->lock <mutex>. - */ -void devlink_region_destroy(struct devlink_region *region) -{ - struct devlink *devlink = region->devlink; - - devl_lock(devlink); - devl_region_destroy(region); - devl_unlock(devlink); -} -EXPORT_SYMBOL_GPL(devlink_region_destroy); - -/** - * devlink_region_snapshot_id_get - get snapshot ID - * - * This callback should be called when adding a new snapshot, - * Driver should use the same id for multiple snapshots taken - * on multiple regions at the same time/by the same trigger. - * - * The caller of this function must use devlink_region_snapshot_id_put - * when finished creating regions using this id. - * - * Returns zero on success, or a negative error code on failure. - * - * @devlink: devlink - * @id: storage to return id - */ -int devlink_region_snapshot_id_get(struct devlink *devlink, u32 *id) -{ - return __devlink_region_snapshot_id_get(devlink, id); -} -EXPORT_SYMBOL_GPL(devlink_region_snapshot_id_get); - -/** - * devlink_region_snapshot_id_put - put snapshot ID reference - * - * This should be called by a driver after finishing creating snapshots - * with an id. Doing so ensures that the ID can later be released in the - * event that all snapshots using it have been destroyed. - * - * @devlink: devlink - * @id: id to release reference on - */ -void devlink_region_snapshot_id_put(struct devlink *devlink, u32 id) -{ - __devlink_snapshot_id_decrement(devlink, id); -} -EXPORT_SYMBOL_GPL(devlink_region_snapshot_id_put); - -/** - * devlink_region_snapshot_create - create a new snapshot - * This will add a new snapshot of a region. The snapshot - * will be stored on the region struct and can be accessed - * from devlink. This is useful for future analyses of snapshots. - * Multiple snapshots can be created on a region. - * The @snapshot_id should be obtained using the getter function. - * - * @region: devlink region of the snapshot - * @data: snapshot data - * @snapshot_id: snapshot id to be created - */ -int devlink_region_snapshot_create(struct devlink_region *region, - u8 *data, u32 snapshot_id) -{ - int err; - - mutex_lock(&region->snapshot_lock); - err = __devlink_region_snapshot_create(region, data, snapshot_id); - mutex_unlock(&region->snapshot_lock); - return err; -} -EXPORT_SYMBOL_GPL(devlink_region_snapshot_create); - -#define DEVLINK_TRAP(_id, _type) \ - { \ - .type = DEVLINK_TRAP_TYPE_##_type, \ - .id = DEVLINK_TRAP_GENERIC_ID_##_id, \ - .name = DEVLINK_TRAP_GENERIC_NAME_##_id, \ - } - -static const struct devlink_trap devlink_trap_generic[] = { - DEVLINK_TRAP(SMAC_MC, DROP), - DEVLINK_TRAP(VLAN_TAG_MISMATCH, DROP), - DEVLINK_TRAP(INGRESS_VLAN_FILTER, DROP), - DEVLINK_TRAP(INGRESS_STP_FILTER, DROP), - DEVLINK_TRAP(EMPTY_TX_LIST, DROP), - DEVLINK_TRAP(PORT_LOOPBACK_FILTER, DROP), - DEVLINK_TRAP(BLACKHOLE_ROUTE, DROP), - DEVLINK_TRAP(TTL_ERROR, EXCEPTION), - DEVLINK_TRAP(TAIL_DROP, DROP), - DEVLINK_TRAP(NON_IP_PACKET, DROP), - DEVLINK_TRAP(UC_DIP_MC_DMAC, DROP), - DEVLINK_TRAP(DIP_LB, DROP), - DEVLINK_TRAP(SIP_MC, DROP), - DEVLINK_TRAP(SIP_LB, DROP), - DEVLINK_TRAP(CORRUPTED_IP_HDR, DROP), - DEVLINK_TRAP(IPV4_SIP_BC, DROP), - DEVLINK_TRAP(IPV6_MC_DIP_RESERVED_SCOPE, DROP), - DEVLINK_TRAP(IPV6_MC_DIP_INTERFACE_LOCAL_SCOPE, DROP), - DEVLINK_TRAP(MTU_ERROR, EXCEPTION), - DEVLINK_TRAP(UNRESOLVED_NEIGH, EXCEPTION), - DEVLINK_TRAP(RPF, EXCEPTION), - DEVLINK_TRAP(REJECT_ROUTE, EXCEPTION), - DEVLINK_TRAP(IPV4_LPM_UNICAST_MISS, EXCEPTION), - DEVLINK_TRAP(IPV6_LPM_UNICAST_MISS, EXCEPTION), - DEVLINK_TRAP(NON_ROUTABLE, DROP), - DEVLINK_TRAP(DECAP_ERROR, EXCEPTION), - DEVLINK_TRAP(OVERLAY_SMAC_MC, DROP), - DEVLINK_TRAP(INGRESS_FLOW_ACTION_DROP, DROP), - DEVLINK_TRAP(EGRESS_FLOW_ACTION_DROP, DROP), - DEVLINK_TRAP(STP, CONTROL), - DEVLINK_TRAP(LACP, CONTROL), - DEVLINK_TRAP(LLDP, CONTROL), - DEVLINK_TRAP(IGMP_QUERY, CONTROL), - DEVLINK_TRAP(IGMP_V1_REPORT, CONTROL), - DEVLINK_TRAP(IGMP_V2_REPORT, CONTROL), - DEVLINK_TRAP(IGMP_V3_REPORT, CONTROL), - DEVLINK_TRAP(IGMP_V2_LEAVE, CONTROL), - DEVLINK_TRAP(MLD_QUERY, CONTROL), - DEVLINK_TRAP(MLD_V1_REPORT, CONTROL), - DEVLINK_TRAP(MLD_V2_REPORT, CONTROL), - DEVLINK_TRAP(MLD_V1_DONE, CONTROL), - DEVLINK_TRAP(IPV4_DHCP, CONTROL), - DEVLINK_TRAP(IPV6_DHCP, CONTROL), - DEVLINK_TRAP(ARP_REQUEST, CONTROL), - DEVLINK_TRAP(ARP_RESPONSE, CONTROL), - DEVLINK_TRAP(ARP_OVERLAY, CONTROL), - DEVLINK_TRAP(IPV6_NEIGH_SOLICIT, CONTROL), - DEVLINK_TRAP(IPV6_NEIGH_ADVERT, CONTROL), - DEVLINK_TRAP(IPV4_BFD, CONTROL), - DEVLINK_TRAP(IPV6_BFD, CONTROL), - DEVLINK_TRAP(IPV4_OSPF, CONTROL), - DEVLINK_TRAP(IPV6_OSPF, CONTROL), - DEVLINK_TRAP(IPV4_BGP, CONTROL), - DEVLINK_TRAP(IPV6_BGP, CONTROL), - DEVLINK_TRAP(IPV4_VRRP, CONTROL), - DEVLINK_TRAP(IPV6_VRRP, CONTROL), - DEVLINK_TRAP(IPV4_PIM, CONTROL), - DEVLINK_TRAP(IPV6_PIM, CONTROL), - DEVLINK_TRAP(UC_LB, CONTROL), - DEVLINK_TRAP(LOCAL_ROUTE, CONTROL), - DEVLINK_TRAP(EXTERNAL_ROUTE, CONTROL), - DEVLINK_TRAP(IPV6_UC_DIP_LINK_LOCAL_SCOPE, CONTROL), - DEVLINK_TRAP(IPV6_DIP_ALL_NODES, CONTROL), - DEVLINK_TRAP(IPV6_DIP_ALL_ROUTERS, CONTROL), - DEVLINK_TRAP(IPV6_ROUTER_SOLICIT, CONTROL), - DEVLINK_TRAP(IPV6_ROUTER_ADVERT, CONTROL), - DEVLINK_TRAP(IPV6_REDIRECT, CONTROL), - DEVLINK_TRAP(IPV4_ROUTER_ALERT, CONTROL), - DEVLINK_TRAP(IPV6_ROUTER_ALERT, CONTROL), - DEVLINK_TRAP(PTP_EVENT, CONTROL), - DEVLINK_TRAP(PTP_GENERAL, CONTROL), - DEVLINK_TRAP(FLOW_ACTION_SAMPLE, CONTROL), - DEVLINK_TRAP(FLOW_ACTION_TRAP, CONTROL), - DEVLINK_TRAP(EARLY_DROP, DROP), - DEVLINK_TRAP(VXLAN_PARSING, DROP), - DEVLINK_TRAP(LLC_SNAP_PARSING, DROP), - DEVLINK_TRAP(VLAN_PARSING, DROP), - DEVLINK_TRAP(PPPOE_PPP_PARSING, DROP), - DEVLINK_TRAP(MPLS_PARSING, DROP), - DEVLINK_TRAP(ARP_PARSING, DROP), - DEVLINK_TRAP(IP_1_PARSING, DROP), - DEVLINK_TRAP(IP_N_PARSING, DROP), - DEVLINK_TRAP(GRE_PARSING, DROP), - DEVLINK_TRAP(UDP_PARSING, DROP), - DEVLINK_TRAP(TCP_PARSING, DROP), - DEVLINK_TRAP(IPSEC_PARSING, DROP), - DEVLINK_TRAP(SCTP_PARSING, DROP), - DEVLINK_TRAP(DCCP_PARSING, DROP), - DEVLINK_TRAP(GTP_PARSING, DROP), - DEVLINK_TRAP(ESP_PARSING, DROP), - DEVLINK_TRAP(BLACKHOLE_NEXTHOP, DROP), - DEVLINK_TRAP(DMAC_FILTER, DROP), -}; - -#define DEVLINK_TRAP_GROUP(_id) \ - { \ - .id = DEVLINK_TRAP_GROUP_GENERIC_ID_##_id, \ - .name = DEVLINK_TRAP_GROUP_GENERIC_NAME_##_id, \ - } - -static const struct devlink_trap_group devlink_trap_group_generic[] = { - DEVLINK_TRAP_GROUP(L2_DROPS), - DEVLINK_TRAP_GROUP(L3_DROPS), - DEVLINK_TRAP_GROUP(L3_EXCEPTIONS), - DEVLINK_TRAP_GROUP(BUFFER_DROPS), - DEVLINK_TRAP_GROUP(TUNNEL_DROPS), - DEVLINK_TRAP_GROUP(ACL_DROPS), - DEVLINK_TRAP_GROUP(STP), - DEVLINK_TRAP_GROUP(LACP), - DEVLINK_TRAP_GROUP(LLDP), - DEVLINK_TRAP_GROUP(MC_SNOOPING), - DEVLINK_TRAP_GROUP(DHCP), - DEVLINK_TRAP_GROUP(NEIGH_DISCOVERY), - DEVLINK_TRAP_GROUP(BFD), - DEVLINK_TRAP_GROUP(OSPF), - DEVLINK_TRAP_GROUP(BGP), - DEVLINK_TRAP_GROUP(VRRP), - DEVLINK_TRAP_GROUP(PIM), - DEVLINK_TRAP_GROUP(UC_LB), - DEVLINK_TRAP_GROUP(LOCAL_DELIVERY), - DEVLINK_TRAP_GROUP(EXTERNAL_DELIVERY), - DEVLINK_TRAP_GROUP(IPV6), - DEVLINK_TRAP_GROUP(PTP_EVENT), - DEVLINK_TRAP_GROUP(PTP_GENERAL), - DEVLINK_TRAP_GROUP(ACL_SAMPLE), - DEVLINK_TRAP_GROUP(ACL_TRAP), - DEVLINK_TRAP_GROUP(PARSER_ERROR_DROPS), -}; - -static int devlink_trap_generic_verify(const struct devlink_trap *trap) -{ - if (trap->id > DEVLINK_TRAP_GENERIC_ID_MAX) - return -EINVAL; - - if (strcmp(trap->name, devlink_trap_generic[trap->id].name)) - return -EINVAL; - - if (trap->type != devlink_trap_generic[trap->id].type) - return -EINVAL; - - return 0; -} - -static int devlink_trap_driver_verify(const struct devlink_trap *trap) -{ - int i; - - if (trap->id <= DEVLINK_TRAP_GENERIC_ID_MAX) - return -EINVAL; - - for (i = 0; i < ARRAY_SIZE(devlink_trap_generic); i++) { - if (!strcmp(trap->name, devlink_trap_generic[i].name)) - return -EEXIST; - } - - return 0; -} - -static int devlink_trap_verify(const struct devlink_trap *trap) -{ - if (!trap || !trap->name) - return -EINVAL; - - if (trap->generic) - return devlink_trap_generic_verify(trap); - else - return devlink_trap_driver_verify(trap); -} - -static int -devlink_trap_group_generic_verify(const struct devlink_trap_group *group) -{ - if (group->id > DEVLINK_TRAP_GROUP_GENERIC_ID_MAX) - return -EINVAL; - - if (strcmp(group->name, devlink_trap_group_generic[group->id].name)) - return -EINVAL; - - return 0; -} - -static int -devlink_trap_group_driver_verify(const struct devlink_trap_group *group) -{ - int i; - - if (group->id <= DEVLINK_TRAP_GROUP_GENERIC_ID_MAX) - return -EINVAL; - - for (i = 0; i < ARRAY_SIZE(devlink_trap_group_generic); i++) { - if (!strcmp(group->name, devlink_trap_group_generic[i].name)) - return -EEXIST; - } - - return 0; -} - -static int devlink_trap_group_verify(const struct devlink_trap_group *group) -{ - if (group->generic) - return devlink_trap_group_generic_verify(group); - else - return devlink_trap_group_driver_verify(group); -} - -static void -devlink_trap_group_notify(struct devlink *devlink, - const struct devlink_trap_group_item *group_item, - enum devlink_command cmd) -{ - struct sk_buff *msg; - int err; - - WARN_ON_ONCE(cmd != DEVLINK_CMD_TRAP_GROUP_NEW && - cmd != DEVLINK_CMD_TRAP_GROUP_DEL); - if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)) - return; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return; - - err = devlink_nl_trap_group_fill(msg, devlink, group_item, cmd, 0, 0, - 0); - if (err) { - nlmsg_free(msg); - return; - } - - genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), - msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); -} - -static int -devlink_trap_item_group_link(struct devlink *devlink, - struct devlink_trap_item *trap_item) -{ - u16 group_id = trap_item->trap->init_group_id; - struct devlink_trap_group_item *group_item; - - group_item = devlink_trap_group_item_lookup_by_id(devlink, group_id); - if (WARN_ON_ONCE(!group_item)) - return -EINVAL; - - trap_item->group_item = group_item; - - return 0; -} - -static void devlink_trap_notify(struct devlink *devlink, - const struct devlink_trap_item *trap_item, - enum devlink_command cmd) -{ - struct sk_buff *msg; - int err; - - WARN_ON_ONCE(cmd != DEVLINK_CMD_TRAP_NEW && - cmd != DEVLINK_CMD_TRAP_DEL); - if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)) - return; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return; - - err = devlink_nl_trap_fill(msg, devlink, trap_item, cmd, 0, 0, 0); - if (err) { - nlmsg_free(msg); - return; - } - - genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), - msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); -} - -static int -devlink_trap_register(struct devlink *devlink, - const struct devlink_trap *trap, void *priv) -{ - struct devlink_trap_item *trap_item; - int err; - - if (devlink_trap_item_lookup(devlink, trap->name)) - return -EEXIST; - - trap_item = kzalloc(sizeof(*trap_item), GFP_KERNEL); - if (!trap_item) - return -ENOMEM; - - trap_item->stats = netdev_alloc_pcpu_stats(struct devlink_stats); - if (!trap_item->stats) { - err = -ENOMEM; - goto err_stats_alloc; - } - - trap_item->trap = trap; - trap_item->action = trap->init_action; - trap_item->priv = priv; - - err = devlink_trap_item_group_link(devlink, trap_item); - if (err) - goto err_group_link; - - err = devlink->ops->trap_init(devlink, trap, trap_item); - if (err) - goto err_trap_init; - - list_add_tail(&trap_item->list, &devlink->trap_list); - devlink_trap_notify(devlink, trap_item, DEVLINK_CMD_TRAP_NEW); - - return 0; - -err_trap_init: -err_group_link: - free_percpu(trap_item->stats); -err_stats_alloc: - kfree(trap_item); - return err; -} - -static void devlink_trap_unregister(struct devlink *devlink, - const struct devlink_trap *trap) -{ - struct devlink_trap_item *trap_item; - - trap_item = devlink_trap_item_lookup(devlink, trap->name); - if (WARN_ON_ONCE(!trap_item)) - return; - - devlink_trap_notify(devlink, trap_item, DEVLINK_CMD_TRAP_DEL); - list_del(&trap_item->list); - if (devlink->ops->trap_fini) - devlink->ops->trap_fini(devlink, trap, trap_item); - free_percpu(trap_item->stats); - kfree(trap_item); -} - -static void devlink_trap_disable(struct devlink *devlink, - const struct devlink_trap *trap) -{ - struct devlink_trap_item *trap_item; - - trap_item = devlink_trap_item_lookup(devlink, trap->name); - if (WARN_ON_ONCE(!trap_item)) - return; - - devlink->ops->trap_action_set(devlink, trap, DEVLINK_TRAP_ACTION_DROP, - NULL); - trap_item->action = DEVLINK_TRAP_ACTION_DROP; -} - -/** - * devl_traps_register - Register packet traps with devlink. - * @devlink: devlink. - * @traps: Packet traps. - * @traps_count: Count of provided packet traps. - * @priv: Driver private information. - * - * Return: Non-zero value on failure. - */ -int devl_traps_register(struct devlink *devlink, - const struct devlink_trap *traps, - size_t traps_count, void *priv) -{ - int i, err; - - if (!devlink->ops->trap_init || !devlink->ops->trap_action_set) - return -EINVAL; - - devl_assert_locked(devlink); - for (i = 0; i < traps_count; i++) { - const struct devlink_trap *trap = &traps[i]; - - err = devlink_trap_verify(trap); - if (err) - goto err_trap_verify; - - err = devlink_trap_register(devlink, trap, priv); - if (err) - goto err_trap_register; - } - - return 0; - -err_trap_register: -err_trap_verify: - for (i--; i >= 0; i--) - devlink_trap_unregister(devlink, &traps[i]); - return err; -} -EXPORT_SYMBOL_GPL(devl_traps_register); - -/** - * devlink_traps_register - Register packet traps with devlink. - * @devlink: devlink. - * @traps: Packet traps. - * @traps_count: Count of provided packet traps. - * @priv: Driver private information. - * - * Context: Takes and release devlink->lock <mutex>. - * - * Return: Non-zero value on failure. - */ -int devlink_traps_register(struct devlink *devlink, - const struct devlink_trap *traps, - size_t traps_count, void *priv) -{ - int err; - - devl_lock(devlink); - err = devl_traps_register(devlink, traps, traps_count, priv); - devl_unlock(devlink); - return err; -} -EXPORT_SYMBOL_GPL(devlink_traps_register); - -/** - * devl_traps_unregister - Unregister packet traps from devlink. - * @devlink: devlink. - * @traps: Packet traps. - * @traps_count: Count of provided packet traps. - */ -void devl_traps_unregister(struct devlink *devlink, - const struct devlink_trap *traps, - size_t traps_count) -{ - int i; - - devl_assert_locked(devlink); - /* Make sure we do not have any packets in-flight while unregistering - * traps by disabling all of them and waiting for a grace period. - */ - for (i = traps_count - 1; i >= 0; i--) - devlink_trap_disable(devlink, &traps[i]); - synchronize_rcu(); - for (i = traps_count - 1; i >= 0; i--) - devlink_trap_unregister(devlink, &traps[i]); -} -EXPORT_SYMBOL_GPL(devl_traps_unregister); - -/** - * devlink_traps_unregister - Unregister packet traps from devlink. - * @devlink: devlink. - * @traps: Packet traps. - * @traps_count: Count of provided packet traps. - * - * Context: Takes and release devlink->lock <mutex>. - */ -void devlink_traps_unregister(struct devlink *devlink, - const struct devlink_trap *traps, - size_t traps_count) -{ - devl_lock(devlink); - devl_traps_unregister(devlink, traps, traps_count); - devl_unlock(devlink); -} -EXPORT_SYMBOL_GPL(devlink_traps_unregister); - -static void -devlink_trap_stats_update(struct devlink_stats __percpu *trap_stats, - size_t skb_len) -{ - struct devlink_stats *stats; - - stats = this_cpu_ptr(trap_stats); - u64_stats_update_begin(&stats->syncp); - u64_stats_add(&stats->rx_bytes, skb_len); - u64_stats_inc(&stats->rx_packets); - u64_stats_update_end(&stats->syncp); -} - -static void -devlink_trap_report_metadata_set(struct devlink_trap_metadata *metadata, - const struct devlink_trap_item *trap_item, - struct devlink_port *in_devlink_port, - const struct flow_action_cookie *fa_cookie) -{ - metadata->trap_name = trap_item->trap->name; - metadata->trap_group_name = trap_item->group_item->group->name; - metadata->fa_cookie = fa_cookie; - metadata->trap_type = trap_item->trap->type; - - spin_lock(&in_devlink_port->type_lock); - if (in_devlink_port->type == DEVLINK_PORT_TYPE_ETH) - metadata->input_dev = in_devlink_port->type_dev; - spin_unlock(&in_devlink_port->type_lock); -} - -/** - * devlink_trap_report - Report trapped packet to drop monitor. - * @devlink: devlink. - * @skb: Trapped packet. - * @trap_ctx: Trap context. - * @in_devlink_port: Input devlink port. - * @fa_cookie: Flow action cookie. Could be NULL. - */ -void devlink_trap_report(struct devlink *devlink, struct sk_buff *skb, - void *trap_ctx, struct devlink_port *in_devlink_port, - const struct flow_action_cookie *fa_cookie) - -{ - struct devlink_trap_item *trap_item = trap_ctx; - - devlink_trap_stats_update(trap_item->stats, skb->len); - devlink_trap_stats_update(trap_item->group_item->stats, skb->len); - - if (trace_devlink_trap_report_enabled()) { - struct devlink_trap_metadata metadata = {}; - - devlink_trap_report_metadata_set(&metadata, trap_item, - in_devlink_port, fa_cookie); - trace_devlink_trap_report(devlink, skb, &metadata); - } -} -EXPORT_SYMBOL_GPL(devlink_trap_report); - -/** - * devlink_trap_ctx_priv - Trap context to driver private information. - * @trap_ctx: Trap context. - * - * Return: Driver private information passed during registration. - */ -void *devlink_trap_ctx_priv(void *trap_ctx) -{ - struct devlink_trap_item *trap_item = trap_ctx; - - return trap_item->priv; -} -EXPORT_SYMBOL_GPL(devlink_trap_ctx_priv); - -static int -devlink_trap_group_item_policer_link(struct devlink *devlink, - struct devlink_trap_group_item *group_item) -{ - u32 policer_id = group_item->group->init_policer_id; - struct devlink_trap_policer_item *policer_item; - - if (policer_id == 0) - return 0; - - policer_item = devlink_trap_policer_item_lookup(devlink, policer_id); - if (WARN_ON_ONCE(!policer_item)) - return -EINVAL; - - group_item->policer_item = policer_item; - - return 0; -} - -static int -devlink_trap_group_register(struct devlink *devlink, - const struct devlink_trap_group *group) -{ - struct devlink_trap_group_item *group_item; - int err; - - if (devlink_trap_group_item_lookup(devlink, group->name)) - return -EEXIST; - - group_item = kzalloc(sizeof(*group_item), GFP_KERNEL); - if (!group_item) - return -ENOMEM; - - group_item->stats = netdev_alloc_pcpu_stats(struct devlink_stats); - if (!group_item->stats) { - err = -ENOMEM; - goto err_stats_alloc; - } - - group_item->group = group; - - err = devlink_trap_group_item_policer_link(devlink, group_item); - if (err) - goto err_policer_link; - - if (devlink->ops->trap_group_init) { - err = devlink->ops->trap_group_init(devlink, group); - if (err) - goto err_group_init; - } - - list_add_tail(&group_item->list, &devlink->trap_group_list); - devlink_trap_group_notify(devlink, group_item, - DEVLINK_CMD_TRAP_GROUP_NEW); - - return 0; - -err_group_init: -err_policer_link: - free_percpu(group_item->stats); -err_stats_alloc: - kfree(group_item); - return err; -} - -static void -devlink_trap_group_unregister(struct devlink *devlink, - const struct devlink_trap_group *group) -{ - struct devlink_trap_group_item *group_item; - - group_item = devlink_trap_group_item_lookup(devlink, group->name); - if (WARN_ON_ONCE(!group_item)) - return; - - devlink_trap_group_notify(devlink, group_item, - DEVLINK_CMD_TRAP_GROUP_DEL); - list_del(&group_item->list); - free_percpu(group_item->stats); - kfree(group_item); -} - -/** - * devl_trap_groups_register - Register packet trap groups with devlink. - * @devlink: devlink. - * @groups: Packet trap groups. - * @groups_count: Count of provided packet trap groups. - * - * Return: Non-zero value on failure. - */ -int devl_trap_groups_register(struct devlink *devlink, - const struct devlink_trap_group *groups, - size_t groups_count) -{ - int i, err; - - devl_assert_locked(devlink); - for (i = 0; i < groups_count; i++) { - const struct devlink_trap_group *group = &groups[i]; - - err = devlink_trap_group_verify(group); - if (err) - goto err_trap_group_verify; - - err = devlink_trap_group_register(devlink, group); - if (err) - goto err_trap_group_register; - } - - return 0; - -err_trap_group_register: -err_trap_group_verify: - for (i--; i >= 0; i--) - devlink_trap_group_unregister(devlink, &groups[i]); - return err; -} -EXPORT_SYMBOL_GPL(devl_trap_groups_register); - -/** - * devlink_trap_groups_register - Register packet trap groups with devlink. - * @devlink: devlink. - * @groups: Packet trap groups. - * @groups_count: Count of provided packet trap groups. - * - * Context: Takes and release devlink->lock <mutex>. - * - * Return: Non-zero value on failure. - */ -int devlink_trap_groups_register(struct devlink *devlink, - const struct devlink_trap_group *groups, - size_t groups_count) -{ - int err; - - devl_lock(devlink); - err = devl_trap_groups_register(devlink, groups, groups_count); - devl_unlock(devlink); - return err; -} -EXPORT_SYMBOL_GPL(devlink_trap_groups_register); - -/** - * devl_trap_groups_unregister - Unregister packet trap groups from devlink. - * @devlink: devlink. - * @groups: Packet trap groups. - * @groups_count: Count of provided packet trap groups. - */ -void devl_trap_groups_unregister(struct devlink *devlink, - const struct devlink_trap_group *groups, - size_t groups_count) -{ - int i; - - devl_assert_locked(devlink); - for (i = groups_count - 1; i >= 0; i--) - devlink_trap_group_unregister(devlink, &groups[i]); -} -EXPORT_SYMBOL_GPL(devl_trap_groups_unregister); - -/** - * devlink_trap_groups_unregister - Unregister packet trap groups from devlink. - * @devlink: devlink. - * @groups: Packet trap groups. - * @groups_count: Count of provided packet trap groups. - * - * Context: Takes and release devlink->lock <mutex>. - */ -void devlink_trap_groups_unregister(struct devlink *devlink, - const struct devlink_trap_group *groups, - size_t groups_count) -{ - devl_lock(devlink); - devl_trap_groups_unregister(devlink, groups, groups_count); - devl_unlock(devlink); -} -EXPORT_SYMBOL_GPL(devlink_trap_groups_unregister); - -static void -devlink_trap_policer_notify(struct devlink *devlink, - const struct devlink_trap_policer_item *policer_item, - enum devlink_command cmd) -{ - struct sk_buff *msg; - int err; - - WARN_ON_ONCE(cmd != DEVLINK_CMD_TRAP_POLICER_NEW && - cmd != DEVLINK_CMD_TRAP_POLICER_DEL); - if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)) - return; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return; - - err = devlink_nl_trap_policer_fill(msg, devlink, policer_item, cmd, 0, - 0, 0); - if (err) { - nlmsg_free(msg); - return; - } - - genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), - msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); -} - -static int -devlink_trap_policer_register(struct devlink *devlink, - const struct devlink_trap_policer *policer) -{ - struct devlink_trap_policer_item *policer_item; - int err; - - if (devlink_trap_policer_item_lookup(devlink, policer->id)) - return -EEXIST; - - policer_item = kzalloc(sizeof(*policer_item), GFP_KERNEL); - if (!policer_item) - return -ENOMEM; - - policer_item->policer = policer; - policer_item->rate = policer->init_rate; - policer_item->burst = policer->init_burst; - - if (devlink->ops->trap_policer_init) { - err = devlink->ops->trap_policer_init(devlink, policer); - if (err) - goto err_policer_init; - } - - list_add_tail(&policer_item->list, &devlink->trap_policer_list); - devlink_trap_policer_notify(devlink, policer_item, - DEVLINK_CMD_TRAP_POLICER_NEW); - - return 0; - -err_policer_init: - kfree(policer_item); - return err; -} - -static void -devlink_trap_policer_unregister(struct devlink *devlink, - const struct devlink_trap_policer *policer) -{ - struct devlink_trap_policer_item *policer_item; - - policer_item = devlink_trap_policer_item_lookup(devlink, policer->id); - if (WARN_ON_ONCE(!policer_item)) - return; - - devlink_trap_policer_notify(devlink, policer_item, - DEVLINK_CMD_TRAP_POLICER_DEL); - list_del(&policer_item->list); - if (devlink->ops->trap_policer_fini) - devlink->ops->trap_policer_fini(devlink, policer); - kfree(policer_item); -} - -/** - * devl_trap_policers_register - Register packet trap policers with devlink. - * @devlink: devlink. - * @policers: Packet trap policers. - * @policers_count: Count of provided packet trap policers. - * - * Return: Non-zero value on failure. - */ -int -devl_trap_policers_register(struct devlink *devlink, - const struct devlink_trap_policer *policers, - size_t policers_count) -{ - int i, err; - - devl_assert_locked(devlink); - for (i = 0; i < policers_count; i++) { - const struct devlink_trap_policer *policer = &policers[i]; - - if (WARN_ON(policer->id == 0 || - policer->max_rate < policer->min_rate || - policer->max_burst < policer->min_burst)) { - err = -EINVAL; - goto err_trap_policer_verify; - } - - err = devlink_trap_policer_register(devlink, policer); - if (err) - goto err_trap_policer_register; - } - return 0; - -err_trap_policer_register: -err_trap_policer_verify: - for (i--; i >= 0; i--) - devlink_trap_policer_unregister(devlink, &policers[i]); - return err; -} -EXPORT_SYMBOL_GPL(devl_trap_policers_register); - -/** - * devl_trap_policers_unregister - Unregister packet trap policers from devlink. - * @devlink: devlink. - * @policers: Packet trap policers. - * @policers_count: Count of provided packet trap policers. - */ -void -devl_trap_policers_unregister(struct devlink *devlink, - const struct devlink_trap_policer *policers, - size_t policers_count) -{ - int i; - - devl_assert_locked(devlink); - for (i = policers_count - 1; i >= 0; i--) - devlink_trap_policer_unregister(devlink, &policers[i]); -} -EXPORT_SYMBOL_GPL(devl_trap_policers_unregister); - -static void __devlink_compat_running_version(struct devlink *devlink, - char *buf, size_t len) -{ - struct devlink_info_req req = {}; - const struct nlattr *nlattr; - struct sk_buff *msg; - int rem, err; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return; - - req.msg = msg; - err = devlink->ops->info_get(devlink, &req, NULL); - if (err) - goto free_msg; - - nla_for_each_attr(nlattr, (void *)msg->data, msg->len, rem) { - const struct nlattr *kv; - int rem_kv; - - if (nla_type(nlattr) != DEVLINK_ATTR_INFO_VERSION_RUNNING) - continue; - - nla_for_each_nested(kv, nlattr, rem_kv) { - if (nla_type(kv) != DEVLINK_ATTR_INFO_VERSION_VALUE) - continue; - - strlcat(buf, nla_data(kv), len); - strlcat(buf, " ", len); - } - } -free_msg: - nlmsg_free(msg); -} - -static struct devlink_port *netdev_to_devlink_port(struct net_device *dev) -{ - if (!dev->netdev_ops->ndo_get_devlink_port) - return NULL; - - return dev->netdev_ops->ndo_get_devlink_port(dev); -} - -void devlink_compat_running_version(struct devlink *devlink, - char *buf, size_t len) -{ - if (!devlink->ops->info_get) - return; - - devl_lock(devlink); - __devlink_compat_running_version(devlink, buf, len); - devl_unlock(devlink); -} - -int devlink_compat_flash_update(struct devlink *devlink, const char *file_name) -{ - struct devlink_flash_update_params params = {}; - int ret; - - if (!devlink->ops->flash_update) - return -EOPNOTSUPP; - - ret = request_firmware(&params.fw, file_name, devlink->dev); - if (ret) - return ret; - - devl_lock(devlink); - devlink_flash_update_begin_notify(devlink); - ret = devlink->ops->flash_update(devlink, &params, NULL); - devlink_flash_update_end_notify(devlink); - devl_unlock(devlink); - - release_firmware(params.fw); - - return ret; -} - -int devlink_compat_phys_port_name_get(struct net_device *dev, - char *name, size_t len) -{ - 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) - return -EOPNOTSUPP; - - 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; - - /* Caller must hold RTNL mutex or reference to dev, which ensures that - * devlink_port instance cannot disappear in the middle. No need to take - * any devlink lock as only permanent values are accessed. - */ - devlink_port = netdev_to_devlink_port(dev); - if (!devlink_port || !devlink_port->switch_port) - return -EOPNOTSUPP; - - memcpy(ppid, &devlink_port->attrs.switch_id, sizeof(*ppid)); - - return 0; -} - -static void __net_exit devlink_pernet_pre_exit(struct net *net) -{ - struct devlink *devlink; - u32 actions_performed; - unsigned long index; - int err; - - /* In case network namespace is getting destroyed, reload - * all devlink instances from this namespace into init_net. - */ - devlinks_xa_for_each_registered_get(net, index, devlink) { - WARN_ON(!(devlink->features & DEVLINK_F_RELOAD)); - mutex_lock(&devlink->lock); - err = devlink_reload(devlink, &init_net, - DEVLINK_RELOAD_ACTION_DRIVER_REINIT, - DEVLINK_RELOAD_LIMIT_UNSPEC, - &actions_performed, NULL); - mutex_unlock(&devlink->lock); - if (err && err != -EOPNOTSUPP) - pr_warn("Failed to reload devlink instance into init_net\n"); - devlink_put(devlink); - } -} - -static struct pernet_operations devlink_pernet_ops __net_initdata = { - .pre_exit = devlink_pernet_pre_exit, -}; - -static int __init devlink_init(void) -{ - int err; - - err = genl_register_family(&devlink_nl_family); - if (err) - goto out; - err = register_pernet_subsys(&devlink_pernet_ops); - -out: - WARN_ON(err); - return err; -} - -subsys_initcall(devlink_init); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 2758b3f7c021..9d4507aa736b 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2220,13 +2220,27 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) return err; }

-int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len, - struct netlink_ext_ack *exterr) +int rtnl_nla_parse_ifinfomsg(struct nlattr **tb, const struct nlattr *nla_peer, + struct netlink_ext_ack *exterr) { - return nla_parse_deprecated(tb, IFLA_MAX, head, len, ifla_policy, + const struct ifinfomsg *ifmp; + const struct nlattr *attrs; + size_t len; + + ifmp = nla_data(nla_peer); + attrs = nla_data(nla_peer) + sizeof(struct ifinfomsg); + len = nla_len(nla_peer) - sizeof(struct ifinfomsg); + + if (ifmp->ifi_index < 0) { + NL_SET_ERR_MSG_ATTR(exterr, nla_peer, + "ifindex can't be negative"); + return -EINVAL; + } + + return nla_parse_deprecated(tb, IFLA_MAX, attrs, len, ifla_policy, exterr); } -EXPORT_SYMBOL(rtnl_nla_parse_ifla); +EXPORT_SYMBOL(rtnl_nla_parse_ifinfomsg);

struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[]) { @@ -3451,6 +3465,9 @@ static int __rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh, if (ifm->ifi_index > 0) { link_specified = true; dev = __dev_get_by_index(net, ifm->ifi_index); + } else if (ifm->ifi_index < 0) { + NL_SET_ERR_MSG(extack, "ifindex can't be negative"); + return -EINVAL; } else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME]) { link_specified = true; dev = rtnl_dev_get(net, tb); diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index b780827f5e0a..bfececa9e244 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -130,7 +130,7 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_daddr, inet->inet_sport, inet->inet_dport); - inet->inet_id = get_random_u16(); + atomic_set(&inet->inet_id, get_random_u16());

err = dccp_connect(sk); rt = NULL; @@ -430,7 +430,7 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk, RCU_INIT_POINTER(newinet->inet_opt, rcu_dereference(ireq->ireq_opt)); newinet->mc_index = inet_iif(skb); newinet->mc_ttl = ip_hdr(skb)->ttl; - newinet->inet_id = get_random_u16(); + atomic_set(&newinet->inet_id, get_random_u16());

if (dst == NULL && (dst = inet_csk_route_child_sock(sk, newsk, req)) == NULL) goto put_and_exit; diff --git a/net/dccp/proto.c b/net/dccp/proto.c index abc02d25edc1..c522c76a9f89 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -312,11 +312,15 @@ EXPORT_SYMBOL_GPL(dccp_disconnect); __poll_t dccp_poll(struct file *file, struct socket *sock, poll_table *wait) { - __poll_t mask; struct sock *sk = sock->sk; + __poll_t mask; + u8 shutdown; + int state;

sock_poll_wait(file, sock, wait); - if (sk->sk_state == DCCP_LISTEN) + + state = inet_sk_state_load(sk); + if (state == DCCP_LISTEN) return inet_csk_listen_poll(sk);

/* Socket is not locked. We are protected from async events @@ -325,20 +329,21 @@ __poll_t dccp_poll(struct file *file, struct socket *sock, */

mask = 0; - if (sk->sk_err) + if (READ_ONCE(sk->sk_err)) mask = EPOLLERR; + shutdown = READ_ONCE(sk->sk_shutdown);

- if (sk->sk_shutdown == SHUTDOWN_MASK || sk->sk_state == DCCP_CLOSED) + if (shutdown == SHUTDOWN_MASK || state == DCCP_CLOSED) mask |= EPOLLHUP; - if (sk->sk_shutdown & RCV_SHUTDOWN) + if (shutdown & RCV_SHUTDOWN) mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP;

/* Connected? */ - if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_RESPOND)) { + if ((1 << state) & ~(DCCPF_REQUESTING | DCCPF_RESPOND)) { if (atomic_read(&sk->sk_rmem_alloc) > 0) mask |= EPOLLIN | EPOLLRDNORM;

- if (!(sk->sk_shutdown & SEND_SHUTDOWN)) { + if (!(shutdown & SEND_SHUTDOWN)) { if (sk_stream_is_writeable(sk)) { mask |= EPOLLOUT | EPOLLWRNORM; } else { /* send SIGIO later */ @@ -356,7 +361,6 @@ __poll_t dccp_poll(struct file *file, struct socket *sock, } return mask; } - EXPORT_SYMBOL_GPL(dccp_poll);

int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg) diff --git a/net/devlink/Makefile b/net/devlink/Makefile new file mode 100644 index 000000000000..3a60959f71ee --- /dev/null +++ b/net/devlink/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-y := leftover.o diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c new file mode 100644 index 000000000000..63188d6a50fe --- /dev/null +++ b/net/devlink/leftover.c @@ -0,0 +1,12550 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * net/core/devlink.c - Network physical/parent device Netlink interface + * + * Heavily inspired by net/wireless/ + * Copyright (c) 2016 Mellanox Technologies. All rights reserved. + * Copyright (c) 2016 Jiri Pirko jiri@mellanox.com + */ + +#include <linux/etherdevice.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/types.h> +#include <linux/slab.h> +#include <linux/gfp.h> +#include <linux/device.h> +#include <linux/list.h> +#include <linux/netdevice.h> +#include <linux/spinlock.h> +#include <linux/refcount.h> +#include <linux/workqueue.h> +#include <linux/u64_stats_sync.h> +#include <linux/timekeeping.h> +#include <rdma/ib_verbs.h> +#include <net/netlink.h> +#include <net/genetlink.h> +#include <net/rtnetlink.h> +#include <net/net_namespace.h> +#include <net/sock.h> +#include <net/devlink.h> +#define CREATE_TRACE_POINTS +#include <trace/events/devlink.h> + +#define DEVLINK_RELOAD_STATS_ARRAY_SIZE \ + (__DEVLINK_RELOAD_LIMIT_MAX * __DEVLINK_RELOAD_ACTION_MAX) + +struct devlink_dev_stats { + u32 reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE]; + u32 remote_reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE]; +}; + +struct devlink { + u32 index; + struct list_head port_list; + struct list_head rate_list; + struct list_head sb_list; + struct list_head dpipe_table_list; + struct list_head resource_list; + struct list_head param_list; + struct list_head region_list; + struct list_head reporter_list; + struct mutex reporters_lock; /* protects reporter_list */ + struct devlink_dpipe_headers *dpipe_headers; + struct list_head trap_list; + struct list_head trap_group_list; + struct list_head trap_policer_list; + struct list_head linecard_list; + struct mutex linecards_lock; /* protects linecard_list */ + const struct devlink_ops *ops; + u64 features; + struct xarray snapshot_ids; + struct devlink_dev_stats stats; + struct device *dev; + possible_net_t _net; + /* Serializes access to devlink instance specific objects such as + * port, sb, dpipe, resource, params, region, traps and more. + */ + struct mutex lock; + struct lock_class_key lock_key; + u8 reload_failed:1; + refcount_t refcount; + struct completion comp; + struct rcu_head rcu; + char priv[] __aligned(NETDEV_ALIGN); +}; + +struct devlink_linecard_ops; +struct devlink_linecard_type; + +struct devlink_linecard { + struct list_head list; + struct devlink *devlink; + unsigned int index; + refcount_t refcount; + const struct devlink_linecard_ops *ops; + void *priv; + enum devlink_linecard_state state; + struct mutex state_lock; /* Protects state */ + const char *type; + struct devlink_linecard_type *types; + unsigned int types_count; + struct devlink *nested_devlink; +}; + +/** + * struct devlink_resource - devlink resource + * @name: name of the resource + * @id: id, per devlink instance + * @size: size of the resource + * @size_new: updated size of the resource, reload is needed + * @size_valid: valid in case the total size of the resource is valid + * including its children + * @parent: parent resource + * @size_params: size parameters + * @list: parent list + * @resource_list: list of child resources + * @occ_get: occupancy getter callback + * @occ_get_priv: occupancy getter callback priv + */ +struct devlink_resource { + const char *name; + u64 id; + u64 size; + u64 size_new; + bool size_valid; + struct devlink_resource *parent; + struct devlink_resource_size_params size_params; + struct list_head list; + struct list_head resource_list; + devlink_resource_occ_get_t *occ_get; + void *occ_get_priv; +}; + +void *devlink_priv(struct devlink *devlink) +{ + return &devlink->priv; +} +EXPORT_SYMBOL_GPL(devlink_priv); + +struct devlink *priv_to_devlink(void *priv) +{ + return container_of(priv, struct devlink, priv); +} +EXPORT_SYMBOL_GPL(priv_to_devlink); + +struct device *devlink_to_dev(const struct devlink *devlink) +{ + return devlink->dev; +} +EXPORT_SYMBOL_GPL(devlink_to_dev); + +static struct devlink_dpipe_field devlink_dpipe_fields_ethernet[] = { + { + .name = "destination mac", + .id = DEVLINK_DPIPE_FIELD_ETHERNET_DST_MAC, + .bitwidth = 48, + }, +}; + +struct devlink_dpipe_header devlink_dpipe_header_ethernet = { + .name = "ethernet", + .id = DEVLINK_DPIPE_HEADER_ETHERNET, + .fields = devlink_dpipe_fields_ethernet, + .fields_count = ARRAY_SIZE(devlink_dpipe_fields_ethernet), + .global = true, +}; +EXPORT_SYMBOL_GPL(devlink_dpipe_header_ethernet); + +static struct devlink_dpipe_field devlink_dpipe_fields_ipv4[] = { + { + .name = "destination ip", + .id = DEVLINK_DPIPE_FIELD_IPV4_DST_IP, + .bitwidth = 32, + }, +}; + +struct devlink_dpipe_header devlink_dpipe_header_ipv4 = { + .name = "ipv4", + .id = DEVLINK_DPIPE_HEADER_IPV4, + .fields = devlink_dpipe_fields_ipv4, + .fields_count = ARRAY_SIZE(devlink_dpipe_fields_ipv4), + .global = true, +}; +EXPORT_SYMBOL_GPL(devlink_dpipe_header_ipv4); + +static struct devlink_dpipe_field devlink_dpipe_fields_ipv6[] = { + { + .name = "destination ip", + .id = DEVLINK_DPIPE_FIELD_IPV6_DST_IP, + .bitwidth = 128, + }, +}; + +struct devlink_dpipe_header devlink_dpipe_header_ipv6 = { + .name = "ipv6", + .id = DEVLINK_DPIPE_HEADER_IPV6, + .fields = devlink_dpipe_fields_ipv6, + .fields_count = ARRAY_SIZE(devlink_dpipe_fields_ipv6), + .global = true, +}; +EXPORT_SYMBOL_GPL(devlink_dpipe_header_ipv6); + +EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwmsg); +EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwerr); +EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_trap_report); + +static const struct nla_policy devlink_function_nl_policy[DEVLINK_PORT_FUNCTION_ATTR_MAX + 1] = { + [DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR] = { .type = NLA_BINARY }, + [DEVLINK_PORT_FN_ATTR_STATE] = + NLA_POLICY_RANGE(NLA_U8, DEVLINK_PORT_FN_STATE_INACTIVE, + DEVLINK_PORT_FN_STATE_ACTIVE), +}; + +static const struct nla_policy devlink_selftest_nl_policy[DEVLINK_ATTR_SELFTEST_ID_MAX + 1] = { + [DEVLINK_ATTR_SELFTEST_ID_FLASH] = { .type = NLA_FLAG }, +}; + +static DEFINE_XARRAY_FLAGS(devlinks, XA_FLAGS_ALLOC); +#define DEVLINK_REGISTERED XA_MARK_1 +#define DEVLINK_UNREGISTERING XA_MARK_2 + +/* devlink instances are open to the access from the user space after + * devlink_register() call. Such logical barrier allows us to have certain + * expectations related to locking. + * + * Before *_register() - we are in initialization stage and no parallel + * access possible to the devlink instance. All drivers perform that phase + * by implicitly holding device_lock. + * + * After *_register() - users and driver can access devlink instance at + * the same time. + */ +#define ASSERT_DEVLINK_REGISTERED(d) \ + WARN_ON_ONCE(!xa_get_mark(&devlinks, (d)->index, DEVLINK_REGISTERED)) +#define ASSERT_DEVLINK_NOT_REGISTERED(d) \ + WARN_ON_ONCE(xa_get_mark(&devlinks, (d)->index, DEVLINK_REGISTERED)) + +struct net *devlink_net(const struct devlink *devlink) +{ + return read_pnet(&devlink->_net); +} +EXPORT_SYMBOL_GPL(devlink_net); + +static void __devlink_put_rcu(struct rcu_head *head) +{ + struct devlink *devlink = container_of(head, struct devlink, rcu); + + complete(&devlink->comp); +} + +void devlink_put(struct devlink *devlink) +{ + if (refcount_dec_and_test(&devlink->refcount)) + /* Make sure unregister operation that may await the completion + * is unblocked only after all users are after the end of + * RCU grace period. + */ + call_rcu(&devlink->rcu, __devlink_put_rcu); +} + +struct devlink *__must_check devlink_try_get(struct devlink *devlink) +{ + if (refcount_inc_not_zero(&devlink->refcount)) + return devlink; + return NULL; +} + +void devl_assert_locked(struct devlink *devlink) +{ + lockdep_assert_held(&devlink->lock); +} +EXPORT_SYMBOL_GPL(devl_assert_locked); + +#ifdef CONFIG_LOCKDEP +/* For use in conjunction with LOCKDEP only e.g. rcu_dereference_protected() */ +bool devl_lock_is_held(struct devlink *devlink) +{ + return lockdep_is_held(&devlink->lock); +} +EXPORT_SYMBOL_GPL(devl_lock_is_held); +#endif + +void devl_lock(struct devlink *devlink) +{ + mutex_lock(&devlink->lock); +} +EXPORT_SYMBOL_GPL(devl_lock); + +int devl_trylock(struct devlink *devlink) +{ + return mutex_trylock(&devlink->lock); +} +EXPORT_SYMBOL_GPL(devl_trylock); + +void devl_unlock(struct devlink *devlink) +{ + mutex_unlock(&devlink->lock); +} +EXPORT_SYMBOL_GPL(devl_unlock); + +static struct devlink * +devlinks_xa_find_get(struct net *net, unsigned long *indexp, xa_mark_t filter, + void * (*xa_find_fn)(struct xarray *, unsigned long *, + unsigned long, xa_mark_t)) +{ + struct devlink *devlink; + + rcu_read_lock(); +retry: + devlink = xa_find_fn(&devlinks, indexp, ULONG_MAX, DEVLINK_REGISTERED); + if (!devlink) + goto unlock; + + /* In case devlink_unregister() was already called and "unregistering" + * mark was set, do not allow to get a devlink reference here. + * This prevents live-lock of devlink_unregister() wait for completion. + */ + if (xa_get_mark(&devlinks, *indexp, DEVLINK_UNREGISTERING)) + goto retry; + + /* For a possible retry, the xa_find_after() should be always used */ + xa_find_fn = xa_find_after; + if (!devlink_try_get(devlink)) + goto retry; + if (!net_eq(devlink_net(devlink), net)) { + devlink_put(devlink); + goto retry; + } +unlock: + rcu_read_unlock(); + return devlink; +} + +static struct devlink *devlinks_xa_find_get_first(struct net *net, + unsigned long *indexp, + xa_mark_t filter) +{ + return devlinks_xa_find_get(net, indexp, filter, xa_find); +} + +static struct devlink *devlinks_xa_find_get_next(struct net *net, + unsigned long *indexp, + xa_mark_t filter) +{ + return devlinks_xa_find_get(net, indexp, filter, xa_find_after); +} + +/* Iterate over devlink pointers which were possible to get reference to. + * devlink_put() needs to be called for each iterated devlink pointer + * in loop body in order to release the reference. + */ +#define devlinks_xa_for_each_get(net, index, devlink, filter) \ + for (index = 0, \ + devlink = devlinks_xa_find_get_first(net, &index, filter); \ + devlink; devlink = devlinks_xa_find_get_next(net, &index, filter)) + +#define devlinks_xa_for_each_registered_get(net, index, devlink) \ + devlinks_xa_for_each_get(net, index, devlink, DEVLINK_REGISTERED) + +static struct devlink *devlink_get_from_attrs(struct net *net, + struct nlattr **attrs) +{ + struct devlink *devlink; + unsigned long index; + char *busname; + char *devname; + + if (!attrs[DEVLINK_ATTR_BUS_NAME] || !attrs[DEVLINK_ATTR_DEV_NAME]) + return ERR_PTR(-EINVAL); + + busname = nla_data(attrs[DEVLINK_ATTR_BUS_NAME]); + devname = nla_data(attrs[DEVLINK_ATTR_DEV_NAME]); + + devlinks_xa_for_each_registered_get(net, index, devlink) { + if (strcmp(devlink->dev->bus->name, busname) == 0 && + strcmp(dev_name(devlink->dev), devname) == 0) + return devlink; + devlink_put(devlink); + } + + return ERR_PTR(-ENODEV); +} + +#define ASSERT_DEVLINK_PORT_REGISTERED(devlink_port) \ + WARN_ON_ONCE(!(devlink_port)->registered) +#define ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port) \ + WARN_ON_ONCE((devlink_port)->registered) +#define ASSERT_DEVLINK_PORT_INITIALIZED(devlink_port) \ + WARN_ON_ONCE(!(devlink_port)->initialized) + +static struct devlink_port *devlink_port_get_by_index(struct devlink *devlink, + unsigned int port_index) +{ + struct devlink_port *devlink_port; + + list_for_each_entry(devlink_port, &devlink->port_list, list) { + if (devlink_port->index == port_index) + return devlink_port; + } + return NULL; +} + +static bool devlink_port_index_exists(struct devlink *devlink, + unsigned int port_index) +{ + return devlink_port_get_by_index(devlink, port_index); +} + +static struct devlink_port *devlink_port_get_from_attrs(struct devlink *devlink, + struct nlattr **attrs) +{ + if (attrs[DEVLINK_ATTR_PORT_INDEX]) { + u32 port_index = nla_get_u32(attrs[DEVLINK_ATTR_PORT_INDEX]); + struct devlink_port *devlink_port; + + devlink_port = devlink_port_get_by_index(devlink, port_index); + if (!devlink_port) + return ERR_PTR(-ENODEV); + return devlink_port; + } + return ERR_PTR(-EINVAL); +} + +static struct devlink_port *devlink_port_get_from_info(struct devlink *devlink, + struct genl_info *info) +{ + return devlink_port_get_from_attrs(devlink, info->attrs); +} + +static inline bool +devlink_rate_is_leaf(struct devlink_rate *devlink_rate) +{ + return devlink_rate->type == DEVLINK_RATE_TYPE_LEAF; +} + +static inline bool +devlink_rate_is_node(struct devlink_rate *devlink_rate) +{ + return devlink_rate->type == DEVLINK_RATE_TYPE_NODE; +} + +static struct devlink_rate * +devlink_rate_leaf_get_from_info(struct devlink *devlink, struct genl_info *info) +{ + struct devlink_rate *devlink_rate; + struct devlink_port *devlink_port; + + devlink_port = devlink_port_get_from_attrs(devlink, info->attrs); + if (IS_ERR(devlink_port)) + return ERR_CAST(devlink_port); + devlink_rate = devlink_port->devlink_rate; + return devlink_rate ?: ERR_PTR(-ENODEV); +} + +static struct devlink_rate * +devlink_rate_node_get_by_name(struct devlink *devlink, const char *node_name) +{ + static struct devlink_rate *devlink_rate; + + list_for_each_entry(devlink_rate, &devlink->rate_list, list) { + if (devlink_rate_is_node(devlink_rate) && + !strcmp(node_name, devlink_rate->name)) + return devlink_rate; + } + return ERR_PTR(-ENODEV); +} + +static struct devlink_rate * +devlink_rate_node_get_from_attrs(struct devlink *devlink, struct nlattr **attrs) +{ + const char *rate_node_name; + size_t len; + + if (!attrs[DEVLINK_ATTR_RATE_NODE_NAME]) + return ERR_PTR(-EINVAL); + rate_node_name = nla_data(attrs[DEVLINK_ATTR_RATE_NODE_NAME]); + len = strlen(rate_node_name); + /* Name cannot be empty or decimal number */ + if (!len || strspn(rate_node_name, "0123456789") == len) + return ERR_PTR(-EINVAL); + + return devlink_rate_node_get_by_name(devlink, rate_node_name); +} + +static struct devlink_rate * +devlink_rate_node_get_from_info(struct devlink *devlink, struct genl_info *info) +{ + return devlink_rate_node_get_from_attrs(devlink, info->attrs); +} + +static struct devlink_rate * +devlink_rate_get_from_info(struct devlink *devlink, struct genl_info *info) +{ + struct nlattr **attrs = info->attrs; + + if (attrs[DEVLINK_ATTR_PORT_INDEX]) + return devlink_rate_leaf_get_from_info(devlink, info); + else if (attrs[DEVLINK_ATTR_RATE_NODE_NAME]) + return devlink_rate_node_get_from_info(devlink, info); + else + return ERR_PTR(-EINVAL); +} + +static struct devlink_linecard * +devlink_linecard_get_by_index(struct devlink *devlink, + unsigned int linecard_index) +{ + struct devlink_linecard *devlink_linecard; + + list_for_each_entry(devlink_linecard, &devlink->linecard_list, list) { + if (devlink_linecard->index == linecard_index) + return devlink_linecard; + } + return NULL; +} + +static bool devlink_linecard_index_exists(struct devlink *devlink, + unsigned int linecard_index) +{ + return devlink_linecard_get_by_index(devlink, linecard_index); +} + +static struct devlink_linecard * +devlink_linecard_get_from_attrs(struct devlink *devlink, struct nlattr **attrs) +{ + if (attrs[DEVLINK_ATTR_LINECARD_INDEX]) { + u32 linecard_index = nla_get_u32(attrs[DEVLINK_ATTR_LINECARD_INDEX]); + struct devlink_linecard *linecard; + + mutex_lock(&devlink->linecards_lock); + linecard = devlink_linecard_get_by_index(devlink, linecard_index); + if (linecard) + refcount_inc(&linecard->refcount); + mutex_unlock(&devlink->linecards_lock); + if (!linecard) + return ERR_PTR(-ENODEV); + return linecard; + } + return ERR_PTR(-EINVAL); +} + +static struct devlink_linecard * +devlink_linecard_get_from_info(struct devlink *devlink, struct genl_info *info) +{ + return devlink_linecard_get_from_attrs(devlink, info->attrs); +} + +static void devlink_linecard_put(struct devlink_linecard *linecard) +{ + if (refcount_dec_and_test(&linecard->refcount)) { + mutex_destroy(&linecard->state_lock); + kfree(linecard); + } +} + +struct devlink_sb { + struct list_head list; + unsigned int index; + u32 size; + u16 ingress_pools_count; + u16 egress_pools_count; + u16 ingress_tc_count; + u16 egress_tc_count; +}; + +static u16 devlink_sb_pool_count(struct devlink_sb *devlink_sb) +{ + return devlink_sb->ingress_pools_count + devlink_sb->egress_pools_count; +} + +static struct devlink_sb *devlink_sb_get_by_index(struct devlink *devlink, + unsigned int sb_index) +{ + struct devlink_sb *devlink_sb; + + list_for_each_entry(devlink_sb, &devlink->sb_list, list) { + if (devlink_sb->index == sb_index) + return devlink_sb; + } + return NULL; +} + +static bool devlink_sb_index_exists(struct devlink *devlink, + unsigned int sb_index) +{ + return devlink_sb_get_by_index(devlink, sb_index); +} + +static struct devlink_sb *devlink_sb_get_from_attrs(struct devlink *devlink, + struct nlattr **attrs) +{ + if (attrs[DEVLINK_ATTR_SB_INDEX]) { + u32 sb_index = nla_get_u32(attrs[DEVLINK_ATTR_SB_INDEX]); + struct devlink_sb *devlink_sb; + + devlink_sb = devlink_sb_get_by_index(devlink, sb_index); + if (!devlink_sb) + return ERR_PTR(-ENODEV); + return devlink_sb; + } + return ERR_PTR(-EINVAL); +} + +static struct devlink_sb *devlink_sb_get_from_info(struct devlink *devlink, + struct genl_info *info) +{ + return devlink_sb_get_from_attrs(devlink, info->attrs); +} + +static int devlink_sb_pool_index_get_from_attrs(struct devlink_sb *devlink_sb, + struct nlattr **attrs, + u16 *p_pool_index) +{ + u16 val; + + if (!attrs[DEVLINK_ATTR_SB_POOL_INDEX]) + return -EINVAL; + + val = nla_get_u16(attrs[DEVLINK_ATTR_SB_POOL_INDEX]); + if (val >= devlink_sb_pool_count(devlink_sb)) + return -EINVAL; + *p_pool_index = val; + return 0; +} + +static int devlink_sb_pool_index_get_from_info(struct devlink_sb *devlink_sb, + struct genl_info *info, + u16 *p_pool_index) +{ + return devlink_sb_pool_index_get_from_attrs(devlink_sb, info->attrs, + p_pool_index); +} + +static int +devlink_sb_pool_type_get_from_attrs(struct nlattr **attrs, + enum devlink_sb_pool_type *p_pool_type) +{ + u8 val; + + if (!attrs[DEVLINK_ATTR_SB_POOL_TYPE]) + return -EINVAL; + + val = nla_get_u8(attrs[DEVLINK_ATTR_SB_POOL_TYPE]); + if (val != DEVLINK_SB_POOL_TYPE_INGRESS && + val != DEVLINK_SB_POOL_TYPE_EGRESS) + return -EINVAL; + *p_pool_type = val; + return 0; +} + +static int +devlink_sb_pool_type_get_from_info(struct genl_info *info, + enum devlink_sb_pool_type *p_pool_type) +{ + return devlink_sb_pool_type_get_from_attrs(info->attrs, p_pool_type); +} + +static int +devlink_sb_th_type_get_from_attrs(struct nlattr **attrs, + enum devlink_sb_threshold_type *p_th_type) +{ + u8 val; + + if (!attrs[DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE]) + return -EINVAL; + + val = nla_get_u8(attrs[DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE]); + if (val != DEVLINK_SB_THRESHOLD_TYPE_STATIC && + val != DEVLINK_SB_THRESHOLD_TYPE_DYNAMIC) + return -EINVAL; + *p_th_type = val; + return 0; +} + +static int +devlink_sb_th_type_get_from_info(struct genl_info *info, + enum devlink_sb_threshold_type *p_th_type) +{ + return devlink_sb_th_type_get_from_attrs(info->attrs, p_th_type); +} + +static int +devlink_sb_tc_index_get_from_attrs(struct devlink_sb *devlink_sb, + struct nlattr **attrs, + enum devlink_sb_pool_type pool_type, + u16 *p_tc_index) +{ + u16 val; + + if (!attrs[DEVLINK_ATTR_SB_TC_INDEX]) + return -EINVAL; + + val = nla_get_u16(attrs[DEVLINK_ATTR_SB_TC_INDEX]); + if (pool_type == DEVLINK_SB_POOL_TYPE_INGRESS && + val >= devlink_sb->ingress_tc_count) + return -EINVAL; + if (pool_type == DEVLINK_SB_POOL_TYPE_EGRESS && + val >= devlink_sb->egress_tc_count) + return -EINVAL; + *p_tc_index = val; + return 0; +} + +static int +devlink_sb_tc_index_get_from_info(struct devlink_sb *devlink_sb, + struct genl_info *info, + enum devlink_sb_pool_type pool_type, + u16 *p_tc_index) +{ + return devlink_sb_tc_index_get_from_attrs(devlink_sb, info->attrs, + pool_type, p_tc_index); +} + +struct devlink_region { + struct devlink *devlink; + struct devlink_port *port; + struct list_head list; + union { + const struct devlink_region_ops *ops; + const struct devlink_port_region_ops *port_ops; + }; + struct mutex snapshot_lock; /* protects snapshot_list, + * max_snapshots and cur_snapshots + * consistency. + */ + struct list_head snapshot_list; + u32 max_snapshots; + u32 cur_snapshots; + u64 size; +}; + +struct devlink_snapshot { + struct list_head list; + struct devlink_region *region; + u8 *data; + u32 id; +}; + +static struct devlink_region * +devlink_region_get_by_name(struct devlink *devlink, const char *region_name) +{ + struct devlink_region *region; + + list_for_each_entry(region, &devlink->region_list, list) + if (!strcmp(region->ops->name, region_name)) + return region; + + return NULL; +} + +static struct devlink_region * +devlink_port_region_get_by_name(struct devlink_port *port, + const char *region_name) +{ + struct devlink_region *region; + + list_for_each_entry(region, &port->region_list, list) + if (!strcmp(region->ops->name, region_name)) + return region; + + return NULL; +} + +static struct devlink_snapshot * +devlink_region_snapshot_get_by_id(struct devlink_region *region, u32 id) +{ + struct devlink_snapshot *snapshot; + + list_for_each_entry(snapshot, &region->snapshot_list, list) + if (snapshot->id == id) + return snapshot; + + return NULL; +} + +#define DEVLINK_NL_FLAG_NEED_PORT BIT(0) +#define DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT BIT(1) +#define DEVLINK_NL_FLAG_NEED_RATE BIT(2) +#define DEVLINK_NL_FLAG_NEED_RATE_NODE BIT(3) +#define DEVLINK_NL_FLAG_NEED_LINECARD BIT(4) + +static int devlink_nl_pre_doit(const struct genl_ops *ops, + struct sk_buff *skb, struct genl_info *info) +{ + struct devlink_linecard *linecard; + struct devlink_port *devlink_port; + struct devlink *devlink; + int err; + + devlink = devlink_get_from_attrs(genl_info_net(info), info->attrs); + if (IS_ERR(devlink)) + return PTR_ERR(devlink); + devl_lock(devlink); + info->user_ptr[0] = devlink; + if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_PORT) { + devlink_port = devlink_port_get_from_info(devlink, info); + if (IS_ERR(devlink_port)) { + err = PTR_ERR(devlink_port); + goto unlock; + } + info->user_ptr[1] = devlink_port; + } else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT) { + devlink_port = devlink_port_get_from_info(devlink, info); + if (!IS_ERR(devlink_port)) + info->user_ptr[1] = devlink_port; + } else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_RATE) { + struct devlink_rate *devlink_rate; + + devlink_rate = devlink_rate_get_from_info(devlink, info); + if (IS_ERR(devlink_rate)) { + err = PTR_ERR(devlink_rate); + goto unlock; + } + info->user_ptr[1] = devlink_rate; + } else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_RATE_NODE) { + struct devlink_rate *rate_node; + + rate_node = devlink_rate_node_get_from_info(devlink, info); + if (IS_ERR(rate_node)) { + err = PTR_ERR(rate_node); + goto unlock; + } + info->user_ptr[1] = rate_node; + } else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_LINECARD) { + linecard = devlink_linecard_get_from_info(devlink, info); + if (IS_ERR(linecard)) { + err = PTR_ERR(linecard); + goto unlock; + } + info->user_ptr[1] = linecard; + } + return 0; + +unlock: + devl_unlock(devlink); + devlink_put(devlink); + return err; +} + +static void devlink_nl_post_doit(const struct genl_ops *ops, + struct sk_buff *skb, struct genl_info *info) +{ + struct devlink_linecard *linecard; + struct devlink *devlink; + + devlink = info->user_ptr[0]; + if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_LINECARD) { + linecard = info->user_ptr[1]; + devlink_linecard_put(linecard); + } + devl_unlock(devlink); + devlink_put(devlink); +} + +static struct genl_family devlink_nl_family; + +enum devlink_multicast_groups { + DEVLINK_MCGRP_CONFIG, +}; + +static const struct genl_multicast_group devlink_nl_mcgrps[] = { + [DEVLINK_MCGRP_CONFIG] = { .name = DEVLINK_GENL_MCGRP_CONFIG_NAME }, +}; + +static int devlink_nl_put_handle(struct sk_buff *msg, struct devlink *devlink) +{ + if (nla_put_string(msg, DEVLINK_ATTR_BUS_NAME, devlink->dev->bus->name)) + return -EMSGSIZE; + if (nla_put_string(msg, DEVLINK_ATTR_DEV_NAME, dev_name(devlink->dev))) + return -EMSGSIZE; + return 0; +} + +static int devlink_nl_put_nested_handle(struct sk_buff *msg, struct devlink *devlink) +{ + struct nlattr *nested_attr; + + nested_attr = nla_nest_start(msg, DEVLINK_ATTR_NESTED_DEVLINK); + if (!nested_attr) + return -EMSGSIZE; + if (devlink_nl_put_handle(msg, devlink)) + goto nla_put_failure; + + nla_nest_end(msg, nested_attr); + return 0; + +nla_put_failure: + nla_nest_cancel(msg, nested_attr); + return -EMSGSIZE; +} + +struct devlink_reload_combination { + enum devlink_reload_action action; + enum devlink_reload_limit limit; +}; + +static const struct devlink_reload_combination devlink_reload_invalid_combinations[] = { + { + /* can't reinitialize driver with no down time */ + .action = DEVLINK_RELOAD_ACTION_DRIVER_REINIT, + .limit = DEVLINK_RELOAD_LIMIT_NO_RESET, + }, +}; + +static bool +devlink_reload_combination_is_invalid(enum devlink_reload_action action, + enum devlink_reload_limit limit) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(devlink_reload_invalid_combinations); i++) + if (devlink_reload_invalid_combinations[i].action == action && + devlink_reload_invalid_combinations[i].limit == limit) + return true; + return false; +} + +static bool +devlink_reload_action_is_supported(struct devlink *devlink, enum devlink_reload_action action) +{ + return test_bit(action, &devlink->ops->reload_actions); +} + +static bool +devlink_reload_limit_is_supported(struct devlink *devlink, enum devlink_reload_limit limit) +{ + return test_bit(limit, &devlink->ops->reload_limits); +} + +static int devlink_reload_stat_put(struct sk_buff *msg, + enum devlink_reload_limit limit, u32 value) +{ + struct nlattr *reload_stats_entry; + + reload_stats_entry = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_STATS_ENTRY); + if (!reload_stats_entry) + return -EMSGSIZE; + + if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_STATS_LIMIT, limit) || + nla_put_u32(msg, DEVLINK_ATTR_RELOAD_STATS_VALUE, value)) + goto nla_put_failure; + nla_nest_end(msg, reload_stats_entry); + return 0; + +nla_put_failure: + nla_nest_cancel(msg, reload_stats_entry); + return -EMSGSIZE; +} + +static int devlink_reload_stats_put(struct sk_buff *msg, struct devlink *devlink, bool is_remote) +{ + struct nlattr *reload_stats_attr, *act_info, *act_stats; + int i, j, stat_idx; + u32 value; + + if (!is_remote) + reload_stats_attr = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_STATS); + else + reload_stats_attr = nla_nest_start(msg, DEVLINK_ATTR_REMOTE_RELOAD_STATS); + + if (!reload_stats_attr) + return -EMSGSIZE; + + for (i = 0; i <= DEVLINK_RELOAD_ACTION_MAX; i++) { + if ((!is_remote && + !devlink_reload_action_is_supported(devlink, i)) || + i == DEVLINK_RELOAD_ACTION_UNSPEC) + continue; + act_info = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_ACTION_INFO); + if (!act_info) + goto nla_put_failure; + + if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_ACTION, i)) + goto action_info_nest_cancel; + act_stats = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_ACTION_STATS); + if (!act_stats) + goto action_info_nest_cancel; + + for (j = 0; j <= DEVLINK_RELOAD_LIMIT_MAX; j++) { + /* Remote stats are shown even if not locally supported. + * Stats of actions with unspecified limit are shown + * though drivers don't need to register unspecified + * limit. + */ + if ((!is_remote && j != DEVLINK_RELOAD_LIMIT_UNSPEC && + !devlink_reload_limit_is_supported(devlink, j)) || + devlink_reload_combination_is_invalid(i, j)) + continue; + + stat_idx = j * __DEVLINK_RELOAD_ACTION_MAX + i; + if (!is_remote) + value = devlink->stats.reload_stats[stat_idx]; + else + value = devlink->stats.remote_reload_stats[stat_idx]; + if (devlink_reload_stat_put(msg, j, value)) + goto action_stats_nest_cancel; + } + nla_nest_end(msg, act_stats); + nla_nest_end(msg, act_info); + } + nla_nest_end(msg, reload_stats_attr); + return 0; + +action_stats_nest_cancel: + nla_nest_cancel(msg, act_stats); +action_info_nest_cancel: + nla_nest_cancel(msg, act_info); +nla_put_failure: + nla_nest_cancel(msg, reload_stats_attr); + return -EMSGSIZE; +} + +static int devlink_nl_fill(struct sk_buff *msg, struct devlink *devlink, + enum devlink_command cmd, u32 portid, + u32 seq, int flags) +{ + struct nlattr *dev_stats; + void *hdr; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + if (devlink_nl_put_handle(msg, devlink)) + goto nla_put_failure; + if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_FAILED, devlink->reload_failed)) + goto nla_put_failure; + + dev_stats = nla_nest_start(msg, DEVLINK_ATTR_DEV_STATS); + if (!dev_stats) + goto nla_put_failure; + + if (devlink_reload_stats_put(msg, devlink, false)) + goto dev_stats_nest_cancel; + if (devlink_reload_stats_put(msg, devlink, true)) + goto dev_stats_nest_cancel; + + nla_nest_end(msg, dev_stats); + genlmsg_end(msg, hdr); + return 0; + +dev_stats_nest_cancel: + nla_nest_cancel(msg, dev_stats); +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static void devlink_notify(struct devlink *devlink, enum devlink_command cmd) +{ + struct sk_buff *msg; + int err; + + WARN_ON(cmd != DEVLINK_CMD_NEW && cmd != DEVLINK_CMD_DEL); + WARN_ON(!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)); + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + err = devlink_nl_fill(msg, devlink, cmd, 0, 0, 0); + if (err) { + nlmsg_free(msg); + return; + } + + genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), + msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); +} + +static int devlink_nl_port_attrs_put(struct sk_buff *msg, + struct devlink_port *devlink_port) +{ + struct devlink_port_attrs *attrs = &devlink_port->attrs; + + if (!devlink_port->attrs_set) + return 0; + if (attrs->lanes) { + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_LANES, attrs->lanes)) + return -EMSGSIZE; + } + if (nla_put_u8(msg, DEVLINK_ATTR_PORT_SPLITTABLE, attrs->splittable)) + return -EMSGSIZE; + if (nla_put_u16(msg, DEVLINK_ATTR_PORT_FLAVOUR, attrs->flavour)) + return -EMSGSIZE; + switch (devlink_port->attrs.flavour) { + case DEVLINK_PORT_FLAVOUR_PCI_PF: + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER, + attrs->pci_pf.controller) || + nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, attrs->pci_pf.pf)) + return -EMSGSIZE; + if (nla_put_u8(msg, DEVLINK_ATTR_PORT_EXTERNAL, attrs->pci_pf.external)) + return -EMSGSIZE; + break; + case DEVLINK_PORT_FLAVOUR_PCI_VF: + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER, + attrs->pci_vf.controller) || + nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, attrs->pci_vf.pf) || + nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_VF_NUMBER, attrs->pci_vf.vf)) + return -EMSGSIZE; + if (nla_put_u8(msg, DEVLINK_ATTR_PORT_EXTERNAL, attrs->pci_vf.external)) + return -EMSGSIZE; + break; + case DEVLINK_PORT_FLAVOUR_PCI_SF: + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER, + attrs->pci_sf.controller) || + nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, + attrs->pci_sf.pf) || + nla_put_u32(msg, DEVLINK_ATTR_PORT_PCI_SF_NUMBER, + attrs->pci_sf.sf)) + return -EMSGSIZE; + break; + case DEVLINK_PORT_FLAVOUR_PHYSICAL: + case DEVLINK_PORT_FLAVOUR_CPU: + case DEVLINK_PORT_FLAVOUR_DSA: + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_NUMBER, + attrs->phys.port_number)) + return -EMSGSIZE; + if (!attrs->split) + return 0; + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_SPLIT_GROUP, + attrs->phys.port_number)) + return -EMSGSIZE; + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_SPLIT_SUBPORT_NUMBER, + attrs->phys.split_subport_number)) + return -EMSGSIZE; + break; + default: + break; + } + return 0; +} + +static int devlink_port_fn_hw_addr_fill(const struct devlink_ops *ops, + struct devlink_port *port, + struct sk_buff *msg, + struct netlink_ext_ack *extack, + bool *msg_updated) +{ + u8 hw_addr[MAX_ADDR_LEN]; + int hw_addr_len; + int err; + + if (!ops->port_function_hw_addr_get) + return 0; + + err = ops->port_function_hw_addr_get(port, hw_addr, &hw_addr_len, + extack); + if (err) { + if (err == -EOPNOTSUPP) + return 0; + return err; + } + err = nla_put(msg, DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR, hw_addr_len, hw_addr); + if (err) + return err; + *msg_updated = true; + return 0; +} + +static int devlink_nl_rate_fill(struct sk_buff *msg, + struct devlink_rate *devlink_rate, + enum devlink_command cmd, u32 portid, u32 seq, + int flags, struct netlink_ext_ack *extack) +{ + struct devlink *devlink = devlink_rate->devlink; + void *hdr; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + if (devlink_nl_put_handle(msg, devlink)) + goto nla_put_failure; + + if (nla_put_u16(msg, DEVLINK_ATTR_RATE_TYPE, devlink_rate->type)) + goto nla_put_failure; + + if (devlink_rate_is_leaf(devlink_rate)) { + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, + devlink_rate->devlink_port->index)) + goto nla_put_failure; + } else if (devlink_rate_is_node(devlink_rate)) { + if (nla_put_string(msg, DEVLINK_ATTR_RATE_NODE_NAME, + devlink_rate->name)) + goto nla_put_failure; + } + + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_RATE_TX_SHARE, + devlink_rate->tx_share, DEVLINK_ATTR_PAD)) + goto nla_put_failure; + + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_RATE_TX_MAX, + devlink_rate->tx_max, DEVLINK_ATTR_PAD)) + goto nla_put_failure; + + if (devlink_rate->parent) + if (nla_put_string(msg, DEVLINK_ATTR_RATE_PARENT_NODE_NAME, + devlink_rate->parent->name)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static bool +devlink_port_fn_state_valid(enum devlink_port_fn_state state) +{ + return state == DEVLINK_PORT_FN_STATE_INACTIVE || + state == DEVLINK_PORT_FN_STATE_ACTIVE; +} + +static bool +devlink_port_fn_opstate_valid(enum devlink_port_fn_opstate opstate) +{ + return opstate == DEVLINK_PORT_FN_OPSTATE_DETACHED || + opstate == DEVLINK_PORT_FN_OPSTATE_ATTACHED; +} + +static int devlink_port_fn_state_fill(const struct devlink_ops *ops, + struct devlink_port *port, + struct sk_buff *msg, + struct netlink_ext_ack *extack, + bool *msg_updated) +{ + enum devlink_port_fn_opstate opstate; + enum devlink_port_fn_state state; + int err; + + if (!ops->port_fn_state_get) + return 0; + + err = ops->port_fn_state_get(port, &state, &opstate, extack); + if (err) { + if (err == -EOPNOTSUPP) + return 0; + return err; + } + if (!devlink_port_fn_state_valid(state)) { + WARN_ON_ONCE(1); + NL_SET_ERR_MSG_MOD(extack, "Invalid state read from driver"); + return -EINVAL; + } + if (!devlink_port_fn_opstate_valid(opstate)) { + WARN_ON_ONCE(1); + NL_SET_ERR_MSG_MOD(extack, + "Invalid operational state read from driver"); + return -EINVAL; + } + if (nla_put_u8(msg, DEVLINK_PORT_FN_ATTR_STATE, state) || + nla_put_u8(msg, DEVLINK_PORT_FN_ATTR_OPSTATE, opstate)) + return -EMSGSIZE; + *msg_updated = true; + return 0; +} + +static int +devlink_nl_port_function_attrs_put(struct sk_buff *msg, struct devlink_port *port, + struct netlink_ext_ack *extack) +{ + const struct devlink_ops *ops; + struct nlattr *function_attr; + bool msg_updated = false; + int err; + + function_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_PORT_FUNCTION); + if (!function_attr) + return -EMSGSIZE; + + ops = port->devlink->ops; + err = devlink_port_fn_hw_addr_fill(ops, port, msg, extack, + &msg_updated); + if (err) + goto out; + err = devlink_port_fn_state_fill(ops, port, msg, extack, &msg_updated); +out: + if (err || !msg_updated) + nla_nest_cancel(msg, function_attr); + else + nla_nest_end(msg, function_attr); + return err; +} + +static int devlink_nl_port_fill(struct sk_buff *msg, + struct devlink_port *devlink_port, + enum devlink_command cmd, u32 portid, u32 seq, + int flags, struct netlink_ext_ack *extack) +{ + struct devlink *devlink = devlink_port->devlink; + void *hdr; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + if (devlink_nl_put_handle(msg, devlink)) + goto nla_put_failure; + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index)) + goto nla_put_failure; + + /* Hold rtnl lock while accessing port's netdev attributes. */ + rtnl_lock(); + spin_lock_bh(&devlink_port->type_lock); + if (nla_put_u16(msg, DEVLINK_ATTR_PORT_TYPE, devlink_port->type)) + goto nla_put_failure_type_locked; + if (devlink_port->desired_type != DEVLINK_PORT_TYPE_NOTSET && + nla_put_u16(msg, DEVLINK_ATTR_PORT_DESIRED_TYPE, + devlink_port->desired_type)) + goto nla_put_failure_type_locked; + if (devlink_port->type == DEVLINK_PORT_TYPE_ETH) { + struct net *net = devlink_net(devlink_port->devlink); + struct net_device *netdev = devlink_port->type_dev; + + if (netdev && net_eq(net, dev_net(netdev)) && + (nla_put_u32(msg, DEVLINK_ATTR_PORT_NETDEV_IFINDEX, + netdev->ifindex) || + nla_put_string(msg, DEVLINK_ATTR_PORT_NETDEV_NAME, + netdev->name))) + goto nla_put_failure_type_locked; + } + if (devlink_port->type == DEVLINK_PORT_TYPE_IB) { + struct ib_device *ibdev = devlink_port->type_dev; + + if (ibdev && + nla_put_string(msg, DEVLINK_ATTR_PORT_IBDEV_NAME, + ibdev->name)) + goto nla_put_failure_type_locked; + } + spin_unlock_bh(&devlink_port->type_lock); + rtnl_unlock(); + if (devlink_nl_port_attrs_put(msg, devlink_port)) + goto nla_put_failure; + if (devlink_nl_port_function_attrs_put(msg, devlink_port, extack)) + goto nla_put_failure; + if (devlink_port->linecard && + nla_put_u32(msg, DEVLINK_ATTR_LINECARD_INDEX, + devlink_port->linecard->index)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + return 0; + +nla_put_failure_type_locked: + spin_unlock_bh(&devlink_port->type_lock); + rtnl_unlock(); +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static void devlink_port_notify(struct devlink_port *devlink_port, + enum devlink_command cmd) +{ + struct devlink *devlink = devlink_port->devlink; + struct sk_buff *msg; + int err; + + WARN_ON(cmd != DEVLINK_CMD_PORT_NEW && cmd != DEVLINK_CMD_PORT_DEL); + + if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)) + return; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + err = devlink_nl_port_fill(msg, devlink_port, cmd, 0, 0, 0, NULL); + if (err) { + nlmsg_free(msg); + return; + } + + genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), msg, + 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); +} + +static void devlink_rate_notify(struct devlink_rate *devlink_rate, + enum devlink_command cmd) +{ + struct devlink *devlink = devlink_rate->devlink; + struct sk_buff *msg; + int err; + + WARN_ON(cmd != DEVLINK_CMD_RATE_NEW && cmd != DEVLINK_CMD_RATE_DEL); + + if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)) + return; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + err = devlink_nl_rate_fill(msg, devlink_rate, cmd, 0, 0, 0, NULL); + if (err) { + nlmsg_free(msg); + return; + } + + genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), msg, + 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); +} + +static int devlink_nl_cmd_rate_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + struct devlink_rate *devlink_rate; + struct devlink *devlink; + int start = cb->args[0]; + unsigned long index; + int idx = 0; + int err = 0; + + devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { + devl_lock(devlink); + list_for_each_entry(devlink_rate, &devlink->rate_list, list) { + enum devlink_command cmd = DEVLINK_CMD_RATE_NEW; + u32 id = NETLINK_CB(cb->skb).portid; + + if (idx < start) { + idx++; + continue; + } + err = devlink_nl_rate_fill(msg, devlink_rate, cmd, id, + cb->nlh->nlmsg_seq, + NLM_F_MULTI, NULL); + if (err) { + devl_unlock(devlink); + devlink_put(devlink); + goto out; + } + idx++; + } + devl_unlock(devlink); + devlink_put(devlink); + } +out: + if (err != -EMSGSIZE) + return err; + + cb->args[0] = idx; + return msg->len; +} + +static int devlink_nl_cmd_rate_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink_rate *devlink_rate = info->user_ptr[1]; + struct sk_buff *msg; + int err; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_rate_fill(msg, devlink_rate, DEVLINK_CMD_RATE_NEW, + info->snd_portid, info->snd_seq, 0, + info->extack); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +static bool +devlink_rate_is_parent_node(struct devlink_rate *devlink_rate, + struct devlink_rate *parent) +{ + while (parent) { + if (parent == devlink_rate) + return true; + parent = parent->parent; + } + return false; +} + +static int devlink_nl_cmd_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct sk_buff *msg; + int err; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_fill(msg, devlink, DEVLINK_CMD_NEW, + info->snd_portid, info->snd_seq, 0); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +static int devlink_nl_cmd_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + struct devlink *devlink; + int start = cb->args[0]; + unsigned long index; + int idx = 0; + int err; + + devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { + if (idx < start) { + idx++; + devlink_put(devlink); + continue; + } + + devl_lock(devlink); + err = devlink_nl_fill(msg, devlink, DEVLINK_CMD_NEW, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI); + devl_unlock(devlink); + devlink_put(devlink); + + if (err) + goto out; + idx++; + } +out: + cb->args[0] = idx; + return msg->len; +} + +static int devlink_nl_cmd_port_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink_port *devlink_port = info->user_ptr[1]; + struct sk_buff *msg; + int err; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_port_fill(msg, devlink_port, DEVLINK_CMD_PORT_NEW, + info->snd_portid, info->snd_seq, 0, + info->extack); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +static int devlink_nl_cmd_port_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + struct devlink *devlink; + struct devlink_port *devlink_port; + int start = cb->args[0]; + unsigned long index; + int idx = 0; + int err; + + devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { + devl_lock(devlink); + list_for_each_entry(devlink_port, &devlink->port_list, list) { + if (idx < start) { + idx++; + continue; + } + err = devlink_nl_port_fill(msg, devlink_port, + DEVLINK_CMD_NEW, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI, cb->extack); + if (err) { + devl_unlock(devlink); + devlink_put(devlink); + goto out; + } + idx++; + } + devl_unlock(devlink); + devlink_put(devlink); + } +out: + cb->args[0] = idx; + return msg->len; +} + +static int devlink_port_type_set(struct devlink_port *devlink_port, + enum devlink_port_type port_type) + +{ + int err; + + if (!devlink_port->devlink->ops->port_type_set) + return -EOPNOTSUPP; + + if (port_type == devlink_port->type) + return 0; + + err = devlink_port->devlink->ops->port_type_set(devlink_port, + port_type); + if (err) + return err; + + devlink_port->desired_type = port_type; + devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); + return 0; +} + +static int devlink_port_function_hw_addr_set(struct devlink_port *port, + const struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + const struct devlink_ops *ops = port->devlink->ops; + const u8 *hw_addr; + int hw_addr_len; + + hw_addr = nla_data(attr); + hw_addr_len = nla_len(attr); + if (hw_addr_len > MAX_ADDR_LEN) { + NL_SET_ERR_MSG_MOD(extack, "Port function hardware address too long"); + return -EINVAL; + } + if (port->type == DEVLINK_PORT_TYPE_ETH) { + if (hw_addr_len != ETH_ALEN) { + NL_SET_ERR_MSG_MOD(extack, "Address must be 6 bytes for Ethernet device"); + return -EINVAL; + } + if (!is_unicast_ether_addr(hw_addr)) { + NL_SET_ERR_MSG_MOD(extack, "Non-unicast hardware address unsupported"); + return -EINVAL; + } + } + + if (!ops->port_function_hw_addr_set) { + NL_SET_ERR_MSG_MOD(extack, "Port doesn't support function attributes"); + return -EOPNOTSUPP; + } + + return ops->port_function_hw_addr_set(port, hw_addr, hw_addr_len, + extack); +} + +static int devlink_port_fn_state_set(struct devlink_port *port, + const struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + enum devlink_port_fn_state state; + const struct devlink_ops *ops; + + state = nla_get_u8(attr); + ops = port->devlink->ops; + if (!ops->port_fn_state_set) { + NL_SET_ERR_MSG_MOD(extack, + "Function does not support state setting"); + return -EOPNOTSUPP; + } + return ops->port_fn_state_set(port, state, extack); +} + +static int devlink_port_function_set(struct devlink_port *port, + const struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[DEVLINK_PORT_FUNCTION_ATTR_MAX + 1]; + int err; + + err = nla_parse_nested(tb, DEVLINK_PORT_FUNCTION_ATTR_MAX, attr, + devlink_function_nl_policy, extack); + if (err < 0) { + NL_SET_ERR_MSG_MOD(extack, "Fail to parse port function attributes"); + return err; + } + + attr = tb[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR]; + if (attr) { + err = devlink_port_function_hw_addr_set(port, attr, extack); + if (err) + return err; + } + /* Keep this as the last function attribute set, so that when + * multiple port function attributes are set along with state, + * Those can be applied first before activating the state. + */ + attr = tb[DEVLINK_PORT_FN_ATTR_STATE]; + if (attr) + err = devlink_port_fn_state_set(port, attr, extack); + + if (!err) + devlink_port_notify(port, DEVLINK_CMD_PORT_NEW); + return err; +} + +static int devlink_nl_cmd_port_set_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink_port *devlink_port = info->user_ptr[1]; + int err; + + if (info->attrs[DEVLINK_ATTR_PORT_TYPE]) { + enum devlink_port_type port_type; + + port_type = nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_TYPE]); + err = devlink_port_type_set(devlink_port, port_type); + if (err) + return err; + } + + if (info->attrs[DEVLINK_ATTR_PORT_FUNCTION]) { + struct nlattr *attr = info->attrs[DEVLINK_ATTR_PORT_FUNCTION]; + struct netlink_ext_ack *extack = info->extack; + + err = devlink_port_function_set(devlink_port, attr, extack); + if (err) + return err; + } + + return 0; +} + +static int devlink_nl_cmd_port_split_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink_port *devlink_port = info->user_ptr[1]; + struct devlink *devlink = info->user_ptr[0]; + u32 count; + + if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_PORT_SPLIT_COUNT)) + return -EINVAL; + if (!devlink->ops->port_split) + return -EOPNOTSUPP; + + count = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_SPLIT_COUNT]); + + if (!devlink_port->attrs.splittable) { + /* Split ports cannot be split. */ + if (devlink_port->attrs.split) + NL_SET_ERR_MSG_MOD(info->extack, "Port cannot be split further"); + else + NL_SET_ERR_MSG_MOD(info->extack, "Port cannot be split"); + return -EINVAL; + } + + if (count < 2 || !is_power_of_2(count) || count > devlink_port->attrs.lanes) { + NL_SET_ERR_MSG_MOD(info->extack, "Invalid split count"); + return -EINVAL; + } + + return devlink->ops->port_split(devlink, devlink_port, count, + info->extack); +} + +static int devlink_nl_cmd_port_unsplit_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink_port *devlink_port = info->user_ptr[1]; + struct devlink *devlink = info->user_ptr[0]; + + if (!devlink->ops->port_unsplit) + return -EOPNOTSUPP; + return devlink->ops->port_unsplit(devlink, devlink_port, info->extack); +} + +static int devlink_port_new_notify(struct devlink *devlink, + unsigned int port_index, + struct genl_info *info) +{ + struct devlink_port *devlink_port; + struct sk_buff *msg; + int err; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + lockdep_assert_held(&devlink->lock); + devlink_port = devlink_port_get_by_index(devlink, port_index); + if (!devlink_port) { + err = -ENODEV; + goto out; + } + + err = devlink_nl_port_fill(msg, devlink_port, DEVLINK_CMD_NEW, + info->snd_portid, info->snd_seq, 0, NULL); + if (err) + goto out; + + return genlmsg_reply(msg, info); + +out: + nlmsg_free(msg); + return err; +} + +static int devlink_nl_cmd_port_new_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct netlink_ext_ack *extack = info->extack; + struct devlink_port_new_attrs new_attrs = {}; + struct devlink *devlink = info->user_ptr[0]; + unsigned int new_port_index; + int err; + + if (!devlink->ops->port_new || !devlink->ops->port_del) + return -EOPNOTSUPP; + + if (!info->attrs[DEVLINK_ATTR_PORT_FLAVOUR] || + !info->attrs[DEVLINK_ATTR_PORT_PCI_PF_NUMBER]) { + NL_SET_ERR_MSG_MOD(extack, "Port flavour or PCI PF are not specified"); + return -EINVAL; + } + new_attrs.flavour = nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_FLAVOUR]); + new_attrs.pfnum = + nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_PCI_PF_NUMBER]); + + if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) { + /* Port index of the new port being created by driver. */ + new_attrs.port_index = + nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); + new_attrs.port_index_valid = true; + } + if (info->attrs[DEVLINK_ATTR_PORT_CONTROLLER_NUMBER]) { + new_attrs.controller = + nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_CONTROLLER_NUMBER]); + new_attrs.controller_valid = true; + } + if (new_attrs.flavour == DEVLINK_PORT_FLAVOUR_PCI_SF && + info->attrs[DEVLINK_ATTR_PORT_PCI_SF_NUMBER]) { + new_attrs.sfnum = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_PCI_SF_NUMBER]); + new_attrs.sfnum_valid = true; + } + + err = devlink->ops->port_new(devlink, &new_attrs, extack, + &new_port_index); + if (err) + return err; + + err = devlink_port_new_notify(devlink, new_port_index, info); + if (err && err != -ENODEV) { + /* Fail to send the response; destroy newly created port. */ + devlink->ops->port_del(devlink, new_port_index, extack); + } + return err; +} + +static int devlink_nl_cmd_port_del_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct netlink_ext_ack *extack = info->extack; + struct devlink *devlink = info->user_ptr[0]; + unsigned int port_index; + + if (!devlink->ops->port_del) + return -EOPNOTSUPP; + + if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_PORT_INDEX)) { + NL_SET_ERR_MSG_MOD(extack, "Port index is not specified"); + return -EINVAL; + } + port_index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); + + return devlink->ops->port_del(devlink, port_index, extack); +} + +static int +devlink_nl_rate_parent_node_set(struct devlink_rate *devlink_rate, + struct genl_info *info, + struct nlattr *nla_parent) +{ + struct devlink *devlink = devlink_rate->devlink; + const char *parent_name = nla_data(nla_parent); + const struct devlink_ops *ops = devlink->ops; + size_t len = strlen(parent_name); + struct devlink_rate *parent; + int err = -EOPNOTSUPP; + + parent = devlink_rate->parent; + if (parent && len) { + NL_SET_ERR_MSG_MOD(info->extack, "Rate object already has parent."); + return -EBUSY; + } else if (parent && !len) { + if (devlink_rate_is_leaf(devlink_rate)) + err = ops->rate_leaf_parent_set(devlink_rate, NULL, + devlink_rate->priv, NULL, + info->extack); + else if (devlink_rate_is_node(devlink_rate)) + err = ops->rate_node_parent_set(devlink_rate, NULL, + devlink_rate->priv, NULL, + info->extack); + if (err) + return err; + + refcount_dec(&parent->refcnt); + devlink_rate->parent = NULL; + } else if (!parent && len) { + parent = devlink_rate_node_get_by_name(devlink, parent_name); + if (IS_ERR(parent)) + return -ENODEV; + + if (parent == devlink_rate) { + NL_SET_ERR_MSG_MOD(info->extack, "Parent to self is not allowed"); + return -EINVAL; + } + + if (devlink_rate_is_node(devlink_rate) && + devlink_rate_is_parent_node(devlink_rate, parent->parent)) { + NL_SET_ERR_MSG_MOD(info->extack, "Node is already a parent of parent node."); + return -EEXIST; + } + + if (devlink_rate_is_leaf(devlink_rate)) + err = ops->rate_leaf_parent_set(devlink_rate, parent, + devlink_rate->priv, parent->priv, + info->extack); + else if (devlink_rate_is_node(devlink_rate)) + err = ops->rate_node_parent_set(devlink_rate, parent, + devlink_rate->priv, parent->priv, + info->extack); + if (err) + return err; + + refcount_inc(&parent->refcnt); + devlink_rate->parent = parent; + } + + return 0; +} + +static int devlink_nl_rate_set(struct devlink_rate *devlink_rate, + const struct devlink_ops *ops, + struct genl_info *info) +{ + struct nlattr *nla_parent, **attrs = info->attrs; + int err = -EOPNOTSUPP; + u64 rate; + + if (attrs[DEVLINK_ATTR_RATE_TX_SHARE]) { + rate = nla_get_u64(attrs[DEVLINK_ATTR_RATE_TX_SHARE]); + if (devlink_rate_is_leaf(devlink_rate)) + err = ops->rate_leaf_tx_share_set(devlink_rate, devlink_rate->priv, + rate, info->extack); + else if (devlink_rate_is_node(devlink_rate)) + err = ops->rate_node_tx_share_set(devlink_rate, devlink_rate->priv, + rate, info->extack); + if (err) + return err; + devlink_rate->tx_share = rate; + } + + if (attrs[DEVLINK_ATTR_RATE_TX_MAX]) { + rate = nla_get_u64(attrs[DEVLINK_ATTR_RATE_TX_MAX]); + if (devlink_rate_is_leaf(devlink_rate)) + err = ops->rate_leaf_tx_max_set(devlink_rate, devlink_rate->priv, + rate, info->extack); + else if (devlink_rate_is_node(devlink_rate)) + err = ops->rate_node_tx_max_set(devlink_rate, devlink_rate->priv, + rate, info->extack); + if (err) + return err; + devlink_rate->tx_max = rate; + } + + nla_parent = attrs[DEVLINK_ATTR_RATE_PARENT_NODE_NAME]; + if (nla_parent) { + err = devlink_nl_rate_parent_node_set(devlink_rate, info, + nla_parent); + if (err) + return err; + } + + return 0; +} + +static bool devlink_rate_set_ops_supported(const struct devlink_ops *ops, + struct genl_info *info, + enum devlink_rate_type type) +{ + struct nlattr **attrs = info->attrs; + + if (type == DEVLINK_RATE_TYPE_LEAF) { + if (attrs[DEVLINK_ATTR_RATE_TX_SHARE] && !ops->rate_leaf_tx_share_set) { + NL_SET_ERR_MSG_MOD(info->extack, "TX share set isn't supported for the leafs"); + return false; + } + if (attrs[DEVLINK_ATTR_RATE_TX_MAX] && !ops->rate_leaf_tx_max_set) { + NL_SET_ERR_MSG_MOD(info->extack, "TX max set isn't supported for the leafs"); + return false; + } + if (attrs[DEVLINK_ATTR_RATE_PARENT_NODE_NAME] && + !ops->rate_leaf_parent_set) { + NL_SET_ERR_MSG_MOD(info->extack, "Parent set isn't supported for the leafs"); + return false; + } + } else if (type == DEVLINK_RATE_TYPE_NODE) { + if (attrs[DEVLINK_ATTR_RATE_TX_SHARE] && !ops->rate_node_tx_share_set) { + NL_SET_ERR_MSG_MOD(info->extack, "TX share set isn't supported for the nodes"); + return false; + } + if (attrs[DEVLINK_ATTR_RATE_TX_MAX] && !ops->rate_node_tx_max_set) { + NL_SET_ERR_MSG_MOD(info->extack, "TX max set isn't supported for the nodes"); + return false; + } + if (attrs[DEVLINK_ATTR_RATE_PARENT_NODE_NAME] && + !ops->rate_node_parent_set) { + NL_SET_ERR_MSG_MOD(info->extack, "Parent set isn't supported for the nodes"); + return false; + } + } else { + WARN(1, "Unknown type of rate object"); + return false; + } + + return true; +} + +static int devlink_nl_cmd_rate_set_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink_rate *devlink_rate = info->user_ptr[1]; + struct devlink *devlink = devlink_rate->devlink; + const struct devlink_ops *ops = devlink->ops; + int err; + + if (!ops || !devlink_rate_set_ops_supported(ops, info, devlink_rate->type)) + return -EOPNOTSUPP; + + err = devlink_nl_rate_set(devlink_rate, ops, info); + + if (!err) + devlink_rate_notify(devlink_rate, DEVLINK_CMD_RATE_NEW); + return err; +} + +static int devlink_nl_cmd_rate_new_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_rate *rate_node; + const struct devlink_ops *ops; + int err; + + ops = devlink->ops; + if (!ops || !ops->rate_node_new || !ops->rate_node_del) { + NL_SET_ERR_MSG_MOD(info->extack, "Rate nodes aren't supported"); + return -EOPNOTSUPP; + } + + if (!devlink_rate_set_ops_supported(ops, info, DEVLINK_RATE_TYPE_NODE)) + return -EOPNOTSUPP; + + rate_node = devlink_rate_node_get_from_attrs(devlink, info->attrs); + if (!IS_ERR(rate_node)) + return -EEXIST; + else if (rate_node == ERR_PTR(-EINVAL)) + return -EINVAL; + + rate_node = kzalloc(sizeof(*rate_node), GFP_KERNEL); + if (!rate_node) + return -ENOMEM; + + rate_node->devlink = devlink; + rate_node->type = DEVLINK_RATE_TYPE_NODE; + rate_node->name = nla_strdup(info->attrs[DEVLINK_ATTR_RATE_NODE_NAME], GFP_KERNEL); + if (!rate_node->name) { + err = -ENOMEM; + goto err_strdup; + } + + err = ops->rate_node_new(rate_node, &rate_node->priv, info->extack); + if (err) + goto err_node_new; + + err = devlink_nl_rate_set(rate_node, ops, info); + if (err) + goto err_rate_set; + + refcount_set(&rate_node->refcnt, 1); + list_add(&rate_node->list, &devlink->rate_list); + devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_NEW); + return 0; + +err_rate_set: + ops->rate_node_del(rate_node, rate_node->priv, info->extack); +err_node_new: + kfree(rate_node->name); +err_strdup: + kfree(rate_node); + return err; +} + +static int devlink_nl_cmd_rate_del_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink_rate *rate_node = info->user_ptr[1]; + struct devlink *devlink = rate_node->devlink; + const struct devlink_ops *ops = devlink->ops; + int err; + + if (refcount_read(&rate_node->refcnt) > 1) { + NL_SET_ERR_MSG_MOD(info->extack, "Node has children. Cannot delete node."); + return -EBUSY; + } + + devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_DEL); + err = ops->rate_node_del(rate_node, rate_node->priv, info->extack); + if (rate_node->parent) + refcount_dec(&rate_node->parent->refcnt); + list_del(&rate_node->list); + kfree(rate_node->name); + kfree(rate_node); + return err; +} + +struct devlink_linecard_type { + const char *type; + const void *priv; +}; + +static int devlink_nl_linecard_fill(struct sk_buff *msg, + struct devlink *devlink, + struct devlink_linecard *linecard, + enum devlink_command cmd, u32 portid, + u32 seq, int flags, + struct netlink_ext_ack *extack) +{ + struct devlink_linecard_type *linecard_type; + struct nlattr *attr; + void *hdr; + int i; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + if (devlink_nl_put_handle(msg, devlink)) + goto nla_put_failure; + if (nla_put_u32(msg, DEVLINK_ATTR_LINECARD_INDEX, linecard->index)) + goto nla_put_failure; + if (nla_put_u8(msg, DEVLINK_ATTR_LINECARD_STATE, linecard->state)) + goto nla_put_failure; + if (linecard->type && + nla_put_string(msg, DEVLINK_ATTR_LINECARD_TYPE, linecard->type)) + goto nla_put_failure; + + if (linecard->types_count) { + attr = nla_nest_start(msg, + DEVLINK_ATTR_LINECARD_SUPPORTED_TYPES); + if (!attr) + goto nla_put_failure; + for (i = 0; i < linecard->types_count; i++) { + linecard_type = &linecard->types[i]; + if (nla_put_string(msg, DEVLINK_ATTR_LINECARD_TYPE, + linecard_type->type)) { + nla_nest_cancel(msg, attr); + goto nla_put_failure; + } + } + nla_nest_end(msg, attr); + } + + if (linecard->nested_devlink && + devlink_nl_put_nested_handle(msg, linecard->nested_devlink)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static void devlink_linecard_notify(struct devlink_linecard *linecard, + enum devlink_command cmd) +{ + struct devlink *devlink = linecard->devlink; + struct sk_buff *msg; + int err; + + WARN_ON(cmd != DEVLINK_CMD_LINECARD_NEW && + cmd != DEVLINK_CMD_LINECARD_DEL); + + if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)) + return; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + err = devlink_nl_linecard_fill(msg, devlink, linecard, cmd, 0, 0, 0, + NULL); + if (err) { + nlmsg_free(msg); + return; + } + + genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), + msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); +} + +static int devlink_nl_cmd_linecard_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink_linecard *linecard = info->user_ptr[1]; + struct devlink *devlink = linecard->devlink; + struct sk_buff *msg; + int err; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + mutex_lock(&linecard->state_lock); + err = devlink_nl_linecard_fill(msg, devlink, linecard, + DEVLINK_CMD_LINECARD_NEW, + info->snd_portid, info->snd_seq, 0, + info->extack); + mutex_unlock(&linecard->state_lock); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +static int devlink_nl_cmd_linecard_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + struct devlink_linecard *linecard; + struct devlink *devlink; + int start = cb->args[0]; + unsigned long index; + int idx = 0; + int err; + + devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { + mutex_lock(&devlink->linecards_lock); + list_for_each_entry(linecard, &devlink->linecard_list, list) { + if (idx < start) { + idx++; + continue; + } + mutex_lock(&linecard->state_lock); + err = devlink_nl_linecard_fill(msg, devlink, linecard, + DEVLINK_CMD_LINECARD_NEW, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI, + cb->extack); + mutex_unlock(&linecard->state_lock); + if (err) { + mutex_unlock(&devlink->linecards_lock); + devlink_put(devlink); + goto out; + } + idx++; + } + mutex_unlock(&devlink->linecards_lock); + devlink_put(devlink); + } +out: + cb->args[0] = idx; + return msg->len; +} + +static struct devlink_linecard_type * +devlink_linecard_type_lookup(struct devlink_linecard *linecard, + const char *type) +{ + struct devlink_linecard_type *linecard_type; + int i; + + for (i = 0; i < linecard->types_count; i++) { + linecard_type = &linecard->types[i]; + if (!strcmp(type, linecard_type->type)) + return linecard_type; + } + return NULL; +} + +static int devlink_linecard_type_set(struct devlink_linecard *linecard, + const char *type, + struct netlink_ext_ack *extack) +{ + const struct devlink_linecard_ops *ops = linecard->ops; + struct devlink_linecard_type *linecard_type; + int err; + + mutex_lock(&linecard->state_lock); + if (linecard->state == DEVLINK_LINECARD_STATE_PROVISIONING) { + NL_SET_ERR_MSG_MOD(extack, "Line card is currently being provisioned"); + err = -EBUSY; + goto out; + } + if (linecard->state == DEVLINK_LINECARD_STATE_UNPROVISIONING) { + NL_SET_ERR_MSG_MOD(extack, "Line card is currently being unprovisioned"); + err = -EBUSY; + goto out; + } + + linecard_type = devlink_linecard_type_lookup(linecard, type); + if (!linecard_type) { + NL_SET_ERR_MSG_MOD(extack, "Unsupported line card type provided"); + err = -EINVAL; + goto out; + } + + if (linecard->state != DEVLINK_LINECARD_STATE_UNPROVISIONED && + linecard->state != DEVLINK_LINECARD_STATE_PROVISIONING_FAILED) { + NL_SET_ERR_MSG_MOD(extack, "Line card already provisioned"); + err = -EBUSY; + /* Check if the line card is provisioned in the same + * way the user asks. In case it is, make the operation + * to return success. + */ + if (ops->same_provision && + ops->same_provision(linecard, linecard->priv, + linecard_type->type, + linecard_type->priv)) + err = 0; + goto out; + } + + linecard->state = DEVLINK_LINECARD_STATE_PROVISIONING; + linecard->type = linecard_type->type; + devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); + mutex_unlock(&linecard->state_lock); + err = ops->provision(linecard, linecard->priv, linecard_type->type, + linecard_type->priv, extack); + if (err) { + /* Provisioning failed. Assume the linecard is unprovisioned + * for future operations. + */ + mutex_lock(&linecard->state_lock); + linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED; + linecard->type = NULL; + devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); + mutex_unlock(&linecard->state_lock); + } + return err; + +out: + mutex_unlock(&linecard->state_lock); + return err; +} + +static int devlink_linecard_type_unset(struct devlink_linecard *linecard, + struct netlink_ext_ack *extack) +{ + int err; + + mutex_lock(&linecard->state_lock); + if (linecard->state == DEVLINK_LINECARD_STATE_PROVISIONING) { + NL_SET_ERR_MSG_MOD(extack, "Line card is currently being provisioned"); + err = -EBUSY; + goto out; + } + if (linecard->state == DEVLINK_LINECARD_STATE_UNPROVISIONING) { + NL_SET_ERR_MSG_MOD(extack, "Line card is currently being unprovisioned"); + err = -EBUSY; + goto out; + } + if (linecard->state == DEVLINK_LINECARD_STATE_PROVISIONING_FAILED) { + linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED; + linecard->type = NULL; + devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); + err = 0; + goto out; + } + + if (linecard->state == DEVLINK_LINECARD_STATE_UNPROVISIONED) { + NL_SET_ERR_MSG_MOD(extack, "Line card is not provisioned"); + err = 0; + goto out; + } + linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONING; + devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); + mutex_unlock(&linecard->state_lock); + err = linecard->ops->unprovision(linecard, linecard->priv, + extack); + if (err) { + /* Unprovisioning failed. Assume the linecard is unprovisioned + * for future operations. + */ + mutex_lock(&linecard->state_lock); + linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED; + linecard->type = NULL; + devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); + mutex_unlock(&linecard->state_lock); + } + return err; + +out: + mutex_unlock(&linecard->state_lock); + return err; +} + +static int devlink_nl_cmd_linecard_set_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink_linecard *linecard = info->user_ptr[1]; + struct netlink_ext_ack *extack = info->extack; + int err; + + if (info->attrs[DEVLINK_ATTR_LINECARD_TYPE]) { + const char *type; + + type = nla_data(info->attrs[DEVLINK_ATTR_LINECARD_TYPE]); + if (strcmp(type, "")) { + err = devlink_linecard_type_set(linecard, type, extack); + if (err) + return err; + } else { + err = devlink_linecard_type_unset(linecard, extack); + if (err) + return err; + } + } + + return 0; +} + +static int devlink_nl_sb_fill(struct sk_buff *msg, struct devlink *devlink, + struct devlink_sb *devlink_sb, + enum devlink_command cmd, u32 portid, + u32 seq, int flags) +{ + void *hdr; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + if (devlink_nl_put_handle(msg, devlink)) + goto nla_put_failure; + if (nla_put_u32(msg, DEVLINK_ATTR_SB_INDEX, devlink_sb->index)) + goto nla_put_failure; + if (nla_put_u32(msg, DEVLINK_ATTR_SB_SIZE, devlink_sb->size)) + goto nla_put_failure; + if (nla_put_u16(msg, DEVLINK_ATTR_SB_INGRESS_POOL_COUNT, + devlink_sb->ingress_pools_count)) + goto nla_put_failure; + if (nla_put_u16(msg, DEVLINK_ATTR_SB_EGRESS_POOL_COUNT, + devlink_sb->egress_pools_count)) + goto nla_put_failure; + if (nla_put_u16(msg, DEVLINK_ATTR_SB_INGRESS_TC_COUNT, + devlink_sb->ingress_tc_count)) + goto nla_put_failure; + if (nla_put_u16(msg, DEVLINK_ATTR_SB_EGRESS_TC_COUNT, + devlink_sb->egress_tc_count)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static int devlink_nl_cmd_sb_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_sb *devlink_sb; + struct sk_buff *msg; + int err; + + devlink_sb = devlink_sb_get_from_info(devlink, info); + if (IS_ERR(devlink_sb)) + return PTR_ERR(devlink_sb); + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_sb_fill(msg, devlink, devlink_sb, + DEVLINK_CMD_SB_NEW, + info->snd_portid, info->snd_seq, 0); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +static int devlink_nl_cmd_sb_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + struct devlink *devlink; + struct devlink_sb *devlink_sb; + int start = cb->args[0]; + unsigned long index; + int idx = 0; + int err; + + devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { + devl_lock(devlink); + list_for_each_entry(devlink_sb, &devlink->sb_list, list) { + if (idx < start) { + idx++; + continue; + } + err = devlink_nl_sb_fill(msg, devlink, devlink_sb, + DEVLINK_CMD_SB_NEW, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI); + if (err) { + devl_unlock(devlink); + devlink_put(devlink); + goto out; + } + idx++; + } + devl_unlock(devlink); + devlink_put(devlink); + } +out: + cb->args[0] = idx; + return msg->len; +} + +static int devlink_nl_sb_pool_fill(struct sk_buff *msg, struct devlink *devlink, + struct devlink_sb *devlink_sb, + u16 pool_index, enum devlink_command cmd, + u32 portid, u32 seq, int flags) +{ + struct devlink_sb_pool_info pool_info; + void *hdr; + int err; + + err = devlink->ops->sb_pool_get(devlink, devlink_sb->index, + pool_index, &pool_info); + if (err) + return err; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + if (devlink_nl_put_handle(msg, devlink)) + goto nla_put_failure; + if (nla_put_u32(msg, DEVLINK_ATTR_SB_INDEX, devlink_sb->index)) + goto nla_put_failure; + if (nla_put_u16(msg, DEVLINK_ATTR_SB_POOL_INDEX, pool_index)) + goto nla_put_failure; + if (nla_put_u8(msg, DEVLINK_ATTR_SB_POOL_TYPE, pool_info.pool_type)) + goto nla_put_failure; + if (nla_put_u32(msg, DEVLINK_ATTR_SB_POOL_SIZE, pool_info.size)) + goto nla_put_failure; + if (nla_put_u8(msg, DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE, + pool_info.threshold_type)) + goto nla_put_failure; + if (nla_put_u32(msg, DEVLINK_ATTR_SB_POOL_CELL_SIZE, + pool_info.cell_size)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static int devlink_nl_cmd_sb_pool_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_sb *devlink_sb; + struct sk_buff *msg; + u16 pool_index; + int err; + + devlink_sb = devlink_sb_get_from_info(devlink, info); + if (IS_ERR(devlink_sb)) + return PTR_ERR(devlink_sb); + + err = devlink_sb_pool_index_get_from_info(devlink_sb, info, + &pool_index); + if (err) + return err; + + if (!devlink->ops->sb_pool_get) + return -EOPNOTSUPP; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_sb_pool_fill(msg, devlink, devlink_sb, pool_index, + DEVLINK_CMD_SB_POOL_NEW, + info->snd_portid, info->snd_seq, 0); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +static int __sb_pool_get_dumpit(struct sk_buff *msg, int start, int *p_idx, + struct devlink *devlink, + struct devlink_sb *devlink_sb, + u32 portid, u32 seq) +{ + u16 pool_count = devlink_sb_pool_count(devlink_sb); + u16 pool_index; + int err; + + for (pool_index = 0; pool_index < pool_count; pool_index++) { + if (*p_idx < start) { + (*p_idx)++; + continue; + } + err = devlink_nl_sb_pool_fill(msg, devlink, + devlink_sb, + pool_index, + DEVLINK_CMD_SB_POOL_NEW, + portid, seq, NLM_F_MULTI); + if (err) + return err; + (*p_idx)++; + } + return 0; +} + +static int devlink_nl_cmd_sb_pool_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + struct devlink *devlink; + struct devlink_sb *devlink_sb; + int start = cb->args[0]; + unsigned long index; + int idx = 0; + int err = 0; + + devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { + if (!devlink->ops->sb_pool_get) + goto retry; + + devl_lock(devlink); + list_for_each_entry(devlink_sb, &devlink->sb_list, list) { + err = __sb_pool_get_dumpit(msg, start, &idx, devlink, + devlink_sb, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq); + if (err == -EOPNOTSUPP) { + err = 0; + } else if (err) { + devl_unlock(devlink); + devlink_put(devlink); + goto out; + } + } + devl_unlock(devlink); +retry: + devlink_put(devlink); + } +out: + if (err != -EMSGSIZE) + return err; + + cb->args[0] = idx; + return msg->len; +} + +static int devlink_sb_pool_set(struct devlink *devlink, unsigned int sb_index, + u16 pool_index, u32 size, + enum devlink_sb_threshold_type threshold_type, + struct netlink_ext_ack *extack) + +{ + const struct devlink_ops *ops = devlink->ops; + + if (ops->sb_pool_set) + return ops->sb_pool_set(devlink, sb_index, pool_index, + size, threshold_type, extack); + return -EOPNOTSUPP; +} + +static int devlink_nl_cmd_sb_pool_set_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + enum devlink_sb_threshold_type threshold_type; + struct devlink_sb *devlink_sb; + u16 pool_index; + u32 size; + int err; + + devlink_sb = devlink_sb_get_from_info(devlink, info); + if (IS_ERR(devlink_sb)) + return PTR_ERR(devlink_sb); + + err = devlink_sb_pool_index_get_from_info(devlink_sb, info, + &pool_index); + if (err) + return err; + + err = devlink_sb_th_type_get_from_info(info, &threshold_type); + if (err) + return err; + + if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_SB_POOL_SIZE)) + return -EINVAL; + + size = nla_get_u32(info->attrs[DEVLINK_ATTR_SB_POOL_SIZE]); + return devlink_sb_pool_set(devlink, devlink_sb->index, + pool_index, size, threshold_type, + info->extack); +} + +static int devlink_nl_sb_port_pool_fill(struct sk_buff *msg, + struct devlink *devlink, + struct devlink_port *devlink_port, + struct devlink_sb *devlink_sb, + u16 pool_index, + enum devlink_command cmd, + u32 portid, u32 seq, int flags) +{ + const struct devlink_ops *ops = devlink->ops; + u32 threshold; + void *hdr; + int err; + + err = ops->sb_port_pool_get(devlink_port, devlink_sb->index, + pool_index, &threshold); + if (err) + return err; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + if (devlink_nl_put_handle(msg, devlink)) + goto nla_put_failure; + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index)) + goto nla_put_failure; + if (nla_put_u32(msg, DEVLINK_ATTR_SB_INDEX, devlink_sb->index)) + goto nla_put_failure; + if (nla_put_u16(msg, DEVLINK_ATTR_SB_POOL_INDEX, pool_index)) + goto nla_put_failure; + if (nla_put_u32(msg, DEVLINK_ATTR_SB_THRESHOLD, threshold)) + goto nla_put_failure; + + if (ops->sb_occ_port_pool_get) { + u32 cur; + u32 max; + + err = ops->sb_occ_port_pool_get(devlink_port, devlink_sb->index, + pool_index, &cur, &max); + if (err && err != -EOPNOTSUPP) + goto sb_occ_get_failure; + if (!err) { + if (nla_put_u32(msg, DEVLINK_ATTR_SB_OCC_CUR, cur)) + goto nla_put_failure; + if (nla_put_u32(msg, DEVLINK_ATTR_SB_OCC_MAX, max)) + goto nla_put_failure; + } + } + + genlmsg_end(msg, hdr); + return 0; + +nla_put_failure: + err = -EMSGSIZE; +sb_occ_get_failure: + genlmsg_cancel(msg, hdr); + return err; +} + +static int devlink_nl_cmd_sb_port_pool_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink_port *devlink_port = info->user_ptr[1]; + struct devlink *devlink = devlink_port->devlink; + struct devlink_sb *devlink_sb; + struct sk_buff *msg; + u16 pool_index; + int err; + + devlink_sb = devlink_sb_get_from_info(devlink, info); + if (IS_ERR(devlink_sb)) + return PTR_ERR(devlink_sb); + + err = devlink_sb_pool_index_get_from_info(devlink_sb, info, + &pool_index); + if (err) + return err; + + if (!devlink->ops->sb_port_pool_get) + return -EOPNOTSUPP; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_sb_port_pool_fill(msg, devlink, devlink_port, + devlink_sb, pool_index, + DEVLINK_CMD_SB_PORT_POOL_NEW, + info->snd_portid, info->snd_seq, 0); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +static int __sb_port_pool_get_dumpit(struct sk_buff *msg, int start, int *p_idx, + struct devlink *devlink, + struct devlink_sb *devlink_sb, + u32 portid, u32 seq) +{ + struct devlink_port *devlink_port; + u16 pool_count = devlink_sb_pool_count(devlink_sb); + u16 pool_index; + int err; + + list_for_each_entry(devlink_port, &devlink->port_list, list) { + for (pool_index = 0; pool_index < pool_count; pool_index++) { + if (*p_idx < start) { + (*p_idx)++; + continue; + } + err = devlink_nl_sb_port_pool_fill(msg, devlink, + devlink_port, + devlink_sb, + pool_index, + DEVLINK_CMD_SB_PORT_POOL_NEW, + portid, seq, + NLM_F_MULTI); + if (err) + return err; + (*p_idx)++; + } + } + return 0; +} + +static int devlink_nl_cmd_sb_port_pool_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + struct devlink *devlink; + struct devlink_sb *devlink_sb; + int start = cb->args[0]; + unsigned long index; + int idx = 0; + int err = 0; + + devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { + if (!devlink->ops->sb_port_pool_get) + goto retry; + + devl_lock(devlink); + list_for_each_entry(devlink_sb, &devlink->sb_list, list) { + err = __sb_port_pool_get_dumpit(msg, start, &idx, + devlink, devlink_sb, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq); + if (err == -EOPNOTSUPP) { + err = 0; + } else if (err) { + devl_unlock(devlink); + devlink_put(devlink); + goto out; + } + } + devl_unlock(devlink); +retry: + devlink_put(devlink); + } +out: + if (err != -EMSGSIZE) + return err; + + cb->args[0] = idx; + return msg->len; +} + +static int devlink_sb_port_pool_set(struct devlink_port *devlink_port, + unsigned int sb_index, u16 pool_index, + u32 threshold, + struct netlink_ext_ack *extack) + +{ + const struct devlink_ops *ops = devlink_port->devlink->ops; + + if (ops->sb_port_pool_set) + return ops->sb_port_pool_set(devlink_port, sb_index, + pool_index, threshold, extack); + return -EOPNOTSUPP; +} + +static int devlink_nl_cmd_sb_port_pool_set_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink_port *devlink_port = info->user_ptr[1]; + struct devlink *devlink = info->user_ptr[0]; + struct devlink_sb *devlink_sb; + u16 pool_index; + u32 threshold; + int err; + + devlink_sb = devlink_sb_get_from_info(devlink, info); + if (IS_ERR(devlink_sb)) + return PTR_ERR(devlink_sb); + + err = devlink_sb_pool_index_get_from_info(devlink_sb, info, + &pool_index); + if (err) + return err; + + if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_SB_THRESHOLD)) + return -EINVAL; + + threshold = nla_get_u32(info->attrs[DEVLINK_ATTR_SB_THRESHOLD]); + return devlink_sb_port_pool_set(devlink_port, devlink_sb->index, + pool_index, threshold, info->extack); +} + +static int +devlink_nl_sb_tc_pool_bind_fill(struct sk_buff *msg, struct devlink *devlink, + struct devlink_port *devlink_port, + struct devlink_sb *devlink_sb, u16 tc_index, + enum devlink_sb_pool_type pool_type, + enum devlink_command cmd, + u32 portid, u32 seq, int flags) +{ + const struct devlink_ops *ops = devlink->ops; + u16 pool_index; + u32 threshold; + void *hdr; + int err; + + err = ops->sb_tc_pool_bind_get(devlink_port, devlink_sb->index, + tc_index, pool_type, + &pool_index, &threshold); + if (err) + return err; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + if (devlink_nl_put_handle(msg, devlink)) + goto nla_put_failure; + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index)) + goto nla_put_failure; + if (nla_put_u32(msg, DEVLINK_ATTR_SB_INDEX, devlink_sb->index)) + goto nla_put_failure; + if (nla_put_u16(msg, DEVLINK_ATTR_SB_TC_INDEX, tc_index)) + goto nla_put_failure; + if (nla_put_u8(msg, DEVLINK_ATTR_SB_POOL_TYPE, pool_type)) + goto nla_put_failure; + if (nla_put_u16(msg, DEVLINK_ATTR_SB_POOL_INDEX, pool_index)) + goto nla_put_failure; + if (nla_put_u32(msg, DEVLINK_ATTR_SB_THRESHOLD, threshold)) + goto nla_put_failure; + + if (ops->sb_occ_tc_port_bind_get) { + u32 cur; + u32 max; + + err = ops->sb_occ_tc_port_bind_get(devlink_port, + devlink_sb->index, + tc_index, pool_type, + &cur, &max); + if (err && err != -EOPNOTSUPP) + return err; + if (!err) { + if (nla_put_u32(msg, DEVLINK_ATTR_SB_OCC_CUR, cur)) + goto nla_put_failure; + if (nla_put_u32(msg, DEVLINK_ATTR_SB_OCC_MAX, max)) + goto nla_put_failure; + } + } + + genlmsg_end(msg, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static int devlink_nl_cmd_sb_tc_pool_bind_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink_port *devlink_port = info->user_ptr[1]; + struct devlink *devlink = devlink_port->devlink; + struct devlink_sb *devlink_sb; + struct sk_buff *msg; + enum devlink_sb_pool_type pool_type; + u16 tc_index; + int err; + + devlink_sb = devlink_sb_get_from_info(devlink, info); + if (IS_ERR(devlink_sb)) + return PTR_ERR(devlink_sb); + + err = devlink_sb_pool_type_get_from_info(info, &pool_type); + if (err) + return err; + + err = devlink_sb_tc_index_get_from_info(devlink_sb, info, + pool_type, &tc_index); + if (err) + return err; + + if (!devlink->ops->sb_tc_pool_bind_get) + return -EOPNOTSUPP; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_sb_tc_pool_bind_fill(msg, devlink, devlink_port, + devlink_sb, tc_index, pool_type, + DEVLINK_CMD_SB_TC_POOL_BIND_NEW, + info->snd_portid, + info->snd_seq, 0); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +static int __sb_tc_pool_bind_get_dumpit(struct sk_buff *msg, + int start, int *p_idx, + struct devlink *devlink, + struct devlink_sb *devlink_sb, + u32 portid, u32 seq) +{ + struct devlink_port *devlink_port; + u16 tc_index; + int err; + + list_for_each_entry(devlink_port, &devlink->port_list, list) { + for (tc_index = 0; + tc_index < devlink_sb->ingress_tc_count; tc_index++) { + if (*p_idx < start) { + (*p_idx)++; + continue; + } + err = devlink_nl_sb_tc_pool_bind_fill(msg, devlink, + devlink_port, + devlink_sb, + tc_index, + DEVLINK_SB_POOL_TYPE_INGRESS, + DEVLINK_CMD_SB_TC_POOL_BIND_NEW, + portid, seq, + NLM_F_MULTI); + if (err) + return err; + (*p_idx)++; + } + for (tc_index = 0; + tc_index < devlink_sb->egress_tc_count; tc_index++) { + if (*p_idx < start) { + (*p_idx)++; + continue; + } + err = devlink_nl_sb_tc_pool_bind_fill(msg, devlink, + devlink_port, + devlink_sb, + tc_index, + DEVLINK_SB_POOL_TYPE_EGRESS, + DEVLINK_CMD_SB_TC_POOL_BIND_NEW, + portid, seq, + NLM_F_MULTI); + if (err) + return err; + (*p_idx)++; + } + } + return 0; +} + +static int +devlink_nl_cmd_sb_tc_pool_bind_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + struct devlink *devlink; + struct devlink_sb *devlink_sb; + int start = cb->args[0]; + unsigned long index; + int idx = 0; + int err = 0; + + devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { + if (!devlink->ops->sb_tc_pool_bind_get) + goto retry; + + devl_lock(devlink); + list_for_each_entry(devlink_sb, &devlink->sb_list, list) { + err = __sb_tc_pool_bind_get_dumpit(msg, start, &idx, + devlink, + devlink_sb, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq); + if (err == -EOPNOTSUPP) { + err = 0; + } else if (err) { + devl_unlock(devlink); + devlink_put(devlink); + goto out; + } + } + devl_unlock(devlink); +retry: + devlink_put(devlink); + } +out: + if (err != -EMSGSIZE) + return err; + + cb->args[0] = idx; + return msg->len; +} + +static int devlink_sb_tc_pool_bind_set(struct devlink_port *devlink_port, + unsigned int sb_index, u16 tc_index, + enum devlink_sb_pool_type pool_type, + u16 pool_index, u32 threshold, + struct netlink_ext_ack *extack) + +{ + const struct devlink_ops *ops = devlink_port->devlink->ops; + + if (ops->sb_tc_pool_bind_set) + return ops->sb_tc_pool_bind_set(devlink_port, sb_index, + tc_index, pool_type, + pool_index, threshold, extack); + return -EOPNOTSUPP; +} + +static int devlink_nl_cmd_sb_tc_pool_bind_set_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink_port *devlink_port = info->user_ptr[1]; + struct devlink *devlink = info->user_ptr[0]; + enum devlink_sb_pool_type pool_type; + struct devlink_sb *devlink_sb; + u16 tc_index; + u16 pool_index; + u32 threshold; + int err; + + devlink_sb = devlink_sb_get_from_info(devlink, info); + if (IS_ERR(devlink_sb)) + return PTR_ERR(devlink_sb); + + err = devlink_sb_pool_type_get_from_info(info, &pool_type); + if (err) + return err; + + err = devlink_sb_tc_index_get_from_info(devlink_sb, info, + pool_type, &tc_index); + if (err) + return err; + + err = devlink_sb_pool_index_get_from_info(devlink_sb, info, + &pool_index); + if (err) + return err; + + if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_SB_THRESHOLD)) + return -EINVAL; + + threshold = nla_get_u32(info->attrs[DEVLINK_ATTR_SB_THRESHOLD]); + return devlink_sb_tc_pool_bind_set(devlink_port, devlink_sb->index, + tc_index, pool_type, + pool_index, threshold, info->extack); +} + +static int devlink_nl_cmd_sb_occ_snapshot_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + const struct devlink_ops *ops = devlink->ops; + struct devlink_sb *devlink_sb; + + devlink_sb = devlink_sb_get_from_info(devlink, info); + if (IS_ERR(devlink_sb)) + return PTR_ERR(devlink_sb); + + if (ops->sb_occ_snapshot) + return ops->sb_occ_snapshot(devlink, devlink_sb->index); + return -EOPNOTSUPP; +} + +static int devlink_nl_cmd_sb_occ_max_clear_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + const struct devlink_ops *ops = devlink->ops; + struct devlink_sb *devlink_sb; + + devlink_sb = devlink_sb_get_from_info(devlink, info); + if (IS_ERR(devlink_sb)) + return PTR_ERR(devlink_sb); + + if (ops->sb_occ_max_clear) + return ops->sb_occ_max_clear(devlink, devlink_sb->index); + return -EOPNOTSUPP; +} + +static int devlink_nl_eswitch_fill(struct sk_buff *msg, struct devlink *devlink, + enum devlink_command cmd, u32 portid, + u32 seq, int flags) +{ + const struct devlink_ops *ops = devlink->ops; + enum devlink_eswitch_encap_mode encap_mode; + u8 inline_mode; + void *hdr; + int err = 0; + u16 mode; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + err = devlink_nl_put_handle(msg, devlink); + if (err) + goto nla_put_failure; + + if (ops->eswitch_mode_get) { + err = ops->eswitch_mode_get(devlink, &mode); + if (err) + goto nla_put_failure; + err = nla_put_u16(msg, DEVLINK_ATTR_ESWITCH_MODE, mode); + if (err) + goto nla_put_failure; + } + + if (ops->eswitch_inline_mode_get) { + err = ops->eswitch_inline_mode_get(devlink, &inline_mode); + if (err) + goto nla_put_failure; + err = nla_put_u8(msg, DEVLINK_ATTR_ESWITCH_INLINE_MODE, + inline_mode); + if (err) + goto nla_put_failure; + } + + if (ops->eswitch_encap_mode_get) { + err = ops->eswitch_encap_mode_get(devlink, &encap_mode); + if (err) + goto nla_put_failure; + err = nla_put_u8(msg, DEVLINK_ATTR_ESWITCH_ENCAP_MODE, encap_mode); + if (err) + goto nla_put_failure; + } + + genlmsg_end(msg, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return err; +} + +static int devlink_nl_cmd_eswitch_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct sk_buff *msg; + int err; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_eswitch_fill(msg, devlink, DEVLINK_CMD_ESWITCH_GET, + info->snd_portid, info->snd_seq, 0); + + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +static int devlink_rate_nodes_check(struct devlink *devlink, u16 mode, + struct netlink_ext_ack *extack) +{ + struct devlink_rate *devlink_rate; + + list_for_each_entry(devlink_rate, &devlink->rate_list, list) + if (devlink_rate_is_node(devlink_rate)) { + NL_SET_ERR_MSG_MOD(extack, "Rate node(s) exists."); + return -EBUSY; + } + return 0; +} + +static int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + const struct devlink_ops *ops = devlink->ops; + enum devlink_eswitch_encap_mode encap_mode; + u8 inline_mode; + int err = 0; + u16 mode; + + if (info->attrs[DEVLINK_ATTR_ESWITCH_MODE]) { + if (!ops->eswitch_mode_set) + return -EOPNOTSUPP; + mode = nla_get_u16(info->attrs[DEVLINK_ATTR_ESWITCH_MODE]); + err = devlink_rate_nodes_check(devlink, mode, info->extack); + if (err) + return err; + err = ops->eswitch_mode_set(devlink, mode, info->extack); + if (err) + return err; + } + + if (info->attrs[DEVLINK_ATTR_ESWITCH_INLINE_MODE]) { + if (!ops->eswitch_inline_mode_set) + return -EOPNOTSUPP; + inline_mode = nla_get_u8( + info->attrs[DEVLINK_ATTR_ESWITCH_INLINE_MODE]); + err = ops->eswitch_inline_mode_set(devlink, inline_mode, + info->extack); + if (err) + return err; + } + + if (info->attrs[DEVLINK_ATTR_ESWITCH_ENCAP_MODE]) { + if (!ops->eswitch_encap_mode_set) + return -EOPNOTSUPP; + encap_mode = nla_get_u8(info->attrs[DEVLINK_ATTR_ESWITCH_ENCAP_MODE]); + err = ops->eswitch_encap_mode_set(devlink, encap_mode, + info->extack); + if (err) + return err; + } + + return 0; +} + +int devlink_dpipe_match_put(struct sk_buff *skb, + struct devlink_dpipe_match *match) +{ + struct devlink_dpipe_header *header = match->header; + struct devlink_dpipe_field *field = &header->fields[match->field_id]; + struct nlattr *match_attr; + + match_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_MATCH); + if (!match_attr) + return -EMSGSIZE; + + if (nla_put_u32(skb, DEVLINK_ATTR_DPIPE_MATCH_TYPE, match->type) || + nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_INDEX, match->header_index) || + nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_ID, header->id) || + nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_ID, field->id) || + nla_put_u8(skb, DEVLINK_ATTR_DPIPE_HEADER_GLOBAL, header->global)) + goto nla_put_failure; + + nla_nest_end(skb, match_attr); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, match_attr); + return -EMSGSIZE; +} +EXPORT_SYMBOL_GPL(devlink_dpipe_match_put); + +static int devlink_dpipe_matches_put(struct devlink_dpipe_table *table, + struct sk_buff *skb) +{ + struct nlattr *matches_attr; + + matches_attr = nla_nest_start_noflag(skb, + DEVLINK_ATTR_DPIPE_TABLE_MATCHES); + if (!matches_attr) + return -EMSGSIZE; + + if (table->table_ops->matches_dump(table->priv, skb)) + goto nla_put_failure; + + nla_nest_end(skb, matches_attr); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, matches_attr); + return -EMSGSIZE; +} + +int devlink_dpipe_action_put(struct sk_buff *skb, + struct devlink_dpipe_action *action) +{ + struct devlink_dpipe_header *header = action->header; + struct devlink_dpipe_field *field = &header->fields[action->field_id]; + struct nlattr *action_attr; + + action_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_ACTION); + if (!action_attr) + return -EMSGSIZE; + + if (nla_put_u32(skb, DEVLINK_ATTR_DPIPE_ACTION_TYPE, action->type) || + nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_INDEX, action->header_index) || + nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_ID, header->id) || + nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_ID, field->id) || + nla_put_u8(skb, DEVLINK_ATTR_DPIPE_HEADER_GLOBAL, header->global)) + goto nla_put_failure; + + nla_nest_end(skb, action_attr); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, action_attr); + return -EMSGSIZE; +} +EXPORT_SYMBOL_GPL(devlink_dpipe_action_put); + +static int devlink_dpipe_actions_put(struct devlink_dpipe_table *table, + struct sk_buff *skb) +{ + struct nlattr *actions_attr; + + actions_attr = nla_nest_start_noflag(skb, + DEVLINK_ATTR_DPIPE_TABLE_ACTIONS); + if (!actions_attr) + return -EMSGSIZE; + + if (table->table_ops->actions_dump(table->priv, skb)) + goto nla_put_failure; + + nla_nest_end(skb, actions_attr); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, actions_attr); + return -EMSGSIZE; +} + +static int devlink_dpipe_table_put(struct sk_buff *skb, + struct devlink_dpipe_table *table) +{ + struct nlattr *table_attr; + u64 table_size; + + table_size = table->table_ops->size_get(table->priv); + table_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_TABLE); + if (!table_attr) + return -EMSGSIZE; + + if (nla_put_string(skb, DEVLINK_ATTR_DPIPE_TABLE_NAME, table->name) || + nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_TABLE_SIZE, table_size, + DEVLINK_ATTR_PAD)) + goto nla_put_failure; + if (nla_put_u8(skb, DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED, + table->counters_enabled)) + goto nla_put_failure; + + if (table->resource_valid) { + if (nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_ID, + table->resource_id, DEVLINK_ATTR_PAD) || + nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_UNITS, + table->resource_units, DEVLINK_ATTR_PAD)) + goto nla_put_failure; + } + if (devlink_dpipe_matches_put(table, skb)) + goto nla_put_failure; + + if (devlink_dpipe_actions_put(table, skb)) + goto nla_put_failure; + + nla_nest_end(skb, table_attr); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, table_attr); + return -EMSGSIZE; +} + +static int devlink_dpipe_send_and_alloc_skb(struct sk_buff **pskb, + struct genl_info *info) +{ + int err; + + if (*pskb) { + err = genlmsg_reply(*pskb, info); + if (err) + return err; + } + *pskb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!*pskb) + return -ENOMEM; + return 0; +} + +static int devlink_dpipe_tables_fill(struct genl_info *info, + enum devlink_command cmd, int flags, + struct list_head *dpipe_tables, + const char *table_name) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_dpipe_table *table; + struct nlattr *tables_attr; + struct sk_buff *skb = NULL; + struct nlmsghdr *nlh; + bool incomplete; + void *hdr; + int i; + int err; + + table = list_first_entry(dpipe_tables, + struct devlink_dpipe_table, list); +start_again: + err = devlink_dpipe_send_and_alloc_skb(&skb, info); + if (err) + return err; + + hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq, + &devlink_nl_family, NLM_F_MULTI, cmd); + if (!hdr) { + nlmsg_free(skb); + return -EMSGSIZE; + } + + if (devlink_nl_put_handle(skb, devlink)) + goto nla_put_failure; + tables_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_TABLES); + if (!tables_attr) + goto nla_put_failure; + + i = 0; + incomplete = false; + list_for_each_entry_from(table, dpipe_tables, list) { + if (!table_name) { + err = devlink_dpipe_table_put(skb, table); + if (err) { + if (!i) + goto err_table_put; + incomplete = true; + break; + } + } else { + if (!strcmp(table->name, table_name)) { + err = devlink_dpipe_table_put(skb, table); + if (err) + break; + } + } + i++; + } + + nla_nest_end(skb, tables_attr); + genlmsg_end(skb, hdr); + if (incomplete) + goto start_again; + +send_done: + nlh = nlmsg_put(skb, info->snd_portid, info->snd_seq, + NLMSG_DONE, 0, flags | NLM_F_MULTI); + if (!nlh) { + err = devlink_dpipe_send_and_alloc_skb(&skb, info); + if (err) + return err; + goto send_done; + } + + return genlmsg_reply(skb, info); + +nla_put_failure: + err = -EMSGSIZE; +err_table_put: + nlmsg_free(skb); + return err; +} + +static int devlink_nl_cmd_dpipe_table_get(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + const char *table_name = NULL; + + if (info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]) + table_name = nla_data(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]); + + return devlink_dpipe_tables_fill(info, DEVLINK_CMD_DPIPE_TABLE_GET, 0, + &devlink->dpipe_table_list, + table_name); +} + +static int devlink_dpipe_value_put(struct sk_buff *skb, + struct devlink_dpipe_value *value) +{ + if (nla_put(skb, DEVLINK_ATTR_DPIPE_VALUE, + value->value_size, value->value)) + return -EMSGSIZE; + if (value->mask) + if (nla_put(skb, DEVLINK_ATTR_DPIPE_VALUE_MASK, + value->value_size, value->mask)) + return -EMSGSIZE; + if (value->mapping_valid) + if (nla_put_u32(skb, DEVLINK_ATTR_DPIPE_VALUE_MAPPING, + value->mapping_value)) + return -EMSGSIZE; + return 0; +} + +static int devlink_dpipe_action_value_put(struct sk_buff *skb, + struct devlink_dpipe_value *value) +{ + if (!value->action) + return -EINVAL; + if (devlink_dpipe_action_put(skb, value->action)) + return -EMSGSIZE; + if (devlink_dpipe_value_put(skb, value)) + return -EMSGSIZE; + return 0; +} + +static int devlink_dpipe_action_values_put(struct sk_buff *skb, + struct devlink_dpipe_value *values, + unsigned int values_count) +{ + struct nlattr *action_attr; + int i; + int err; + + for (i = 0; i < values_count; i++) { + action_attr = nla_nest_start_noflag(skb, + DEVLINK_ATTR_DPIPE_ACTION_VALUE); + if (!action_attr) + return -EMSGSIZE; + err = devlink_dpipe_action_value_put(skb, &values[i]); + if (err) + goto err_action_value_put; + nla_nest_end(skb, action_attr); + } + return 0; + +err_action_value_put: + nla_nest_cancel(skb, action_attr); + return err; +} + +static int devlink_dpipe_match_value_put(struct sk_buff *skb, + struct devlink_dpipe_value *value) +{ + if (!value->match) + return -EINVAL; + if (devlink_dpipe_match_put(skb, value->match)) + return -EMSGSIZE; + if (devlink_dpipe_value_put(skb, value)) + return -EMSGSIZE; + return 0; +} + +static int devlink_dpipe_match_values_put(struct sk_buff *skb, + struct devlink_dpipe_value *values, + unsigned int values_count) +{ + struct nlattr *match_attr; + int i; + int err; + + for (i = 0; i < values_count; i++) { + match_attr = nla_nest_start_noflag(skb, + DEVLINK_ATTR_DPIPE_MATCH_VALUE); + if (!match_attr) + return -EMSGSIZE; + err = devlink_dpipe_match_value_put(skb, &values[i]); + if (err) + goto err_match_value_put; + nla_nest_end(skb, match_attr); + } + return 0; + +err_match_value_put: + nla_nest_cancel(skb, match_attr); + return err; +} + +static int devlink_dpipe_entry_put(struct sk_buff *skb, + struct devlink_dpipe_entry *entry) +{ + struct nlattr *entry_attr, *matches_attr, *actions_attr; + int err; + + entry_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_ENTRY); + if (!entry_attr) + return -EMSGSIZE; + + if (nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_ENTRY_INDEX, entry->index, + DEVLINK_ATTR_PAD)) + goto nla_put_failure; + if (entry->counter_valid) + if (nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_ENTRY_COUNTER, + entry->counter, DEVLINK_ATTR_PAD)) + goto nla_put_failure; + + matches_attr = nla_nest_start_noflag(skb, + DEVLINK_ATTR_DPIPE_ENTRY_MATCH_VALUES); + if (!matches_attr) + goto nla_put_failure; + + err = devlink_dpipe_match_values_put(skb, entry->match_values, + entry->match_values_count); + if (err) { + nla_nest_cancel(skb, matches_attr); + goto err_match_values_put; + } + nla_nest_end(skb, matches_attr); + + actions_attr = nla_nest_start_noflag(skb, + DEVLINK_ATTR_DPIPE_ENTRY_ACTION_VALUES); + if (!actions_attr) + goto nla_put_failure; + + err = devlink_dpipe_action_values_put(skb, entry->action_values, + entry->action_values_count); + if (err) { + nla_nest_cancel(skb, actions_attr); + goto err_action_values_put; + } + nla_nest_end(skb, actions_attr); + + nla_nest_end(skb, entry_attr); + return 0; + +nla_put_failure: + err = -EMSGSIZE; +err_match_values_put: +err_action_values_put: + nla_nest_cancel(skb, entry_attr); + return err; +} + +static struct devlink_dpipe_table * +devlink_dpipe_table_find(struct list_head *dpipe_tables, + const char *table_name, struct devlink *devlink) +{ + struct devlink_dpipe_table *table; + list_for_each_entry_rcu(table, dpipe_tables, list, + lockdep_is_held(&devlink->lock)) { + if (!strcmp(table->name, table_name)) + return table; + } + return NULL; +} + +int devlink_dpipe_entry_ctx_prepare(struct devlink_dpipe_dump_ctx *dump_ctx) +{ + struct devlink *devlink; + int err; + + err = devlink_dpipe_send_and_alloc_skb(&dump_ctx->skb, + dump_ctx->info); + if (err) + return err; + + dump_ctx->hdr = genlmsg_put(dump_ctx->skb, + dump_ctx->info->snd_portid, + dump_ctx->info->snd_seq, + &devlink_nl_family, NLM_F_MULTI, + dump_ctx->cmd); + if (!dump_ctx->hdr) + goto nla_put_failure; + + devlink = dump_ctx->info->user_ptr[0]; + if (devlink_nl_put_handle(dump_ctx->skb, devlink)) + goto nla_put_failure; + dump_ctx->nest = nla_nest_start_noflag(dump_ctx->skb, + DEVLINK_ATTR_DPIPE_ENTRIES); + if (!dump_ctx->nest) + goto nla_put_failure; + return 0; + +nla_put_failure: + nlmsg_free(dump_ctx->skb); + return -EMSGSIZE; +} +EXPORT_SYMBOL_GPL(devlink_dpipe_entry_ctx_prepare); + +int devlink_dpipe_entry_ctx_append(struct devlink_dpipe_dump_ctx *dump_ctx, + struct devlink_dpipe_entry *entry) +{ + return devlink_dpipe_entry_put(dump_ctx->skb, entry); +} +EXPORT_SYMBOL_GPL(devlink_dpipe_entry_ctx_append); + +int devlink_dpipe_entry_ctx_close(struct devlink_dpipe_dump_ctx *dump_ctx) +{ + nla_nest_end(dump_ctx->skb, dump_ctx->nest); + genlmsg_end(dump_ctx->skb, dump_ctx->hdr); + return 0; +} +EXPORT_SYMBOL_GPL(devlink_dpipe_entry_ctx_close); + +void devlink_dpipe_entry_clear(struct devlink_dpipe_entry *entry) + +{ + unsigned int value_count, value_index; + struct devlink_dpipe_value *value; + + value = entry->action_values; + value_count = entry->action_values_count; + for (value_index = 0; value_index < value_count; value_index++) { + kfree(value[value_index].value); + kfree(value[value_index].mask); + } + + value = entry->match_values; + value_count = entry->match_values_count; + for (value_index = 0; value_index < value_count; value_index++) { + kfree(value[value_index].value); + kfree(value[value_index].mask); + } +} +EXPORT_SYMBOL_GPL(devlink_dpipe_entry_clear); + +static int devlink_dpipe_entries_fill(struct genl_info *info, + enum devlink_command cmd, int flags, + struct devlink_dpipe_table *table) +{ + struct devlink_dpipe_dump_ctx dump_ctx; + struct nlmsghdr *nlh; + int err; + + dump_ctx.skb = NULL; + dump_ctx.cmd = cmd; + dump_ctx.info = info; + + err = table->table_ops->entries_dump(table->priv, + table->counters_enabled, + &dump_ctx); + if (err) + return err; + +send_done: + nlh = nlmsg_put(dump_ctx.skb, info->snd_portid, info->snd_seq, + NLMSG_DONE, 0, flags | NLM_F_MULTI); + if (!nlh) { + err = devlink_dpipe_send_and_alloc_skb(&dump_ctx.skb, info); + if (err) + return err; + goto send_done; + } + return genlmsg_reply(dump_ctx.skb, info); +} + +static int devlink_nl_cmd_dpipe_entries_get(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_dpipe_table *table; + const char *table_name; + + if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_DPIPE_TABLE_NAME)) + return -EINVAL; + + table_name = nla_data(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]); + table = devlink_dpipe_table_find(&devlink->dpipe_table_list, + table_name, devlink); + if (!table) + return -EINVAL; + + if (!table->table_ops->entries_dump) + return -EINVAL; + + return devlink_dpipe_entries_fill(info, DEVLINK_CMD_DPIPE_ENTRIES_GET, + 0, table); +} + +static int devlink_dpipe_fields_put(struct sk_buff *skb, + const struct devlink_dpipe_header *header) +{ + struct devlink_dpipe_field *field; + struct nlattr *field_attr; + int i; + + for (i = 0; i < header->fields_count; i++) { + field = &header->fields[i]; + field_attr = nla_nest_start_noflag(skb, + DEVLINK_ATTR_DPIPE_FIELD); + if (!field_attr) + return -EMSGSIZE; + if (nla_put_string(skb, DEVLINK_ATTR_DPIPE_FIELD_NAME, field->name) || + nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_ID, field->id) || + nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_BITWIDTH, field->bitwidth) || + nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_MAPPING_TYPE, field->mapping_type)) + goto nla_put_failure; + nla_nest_end(skb, field_attr); + } + return 0; + +nla_put_failure: + nla_nest_cancel(skb, field_attr); + return -EMSGSIZE; +} + +static int devlink_dpipe_header_put(struct sk_buff *skb, + struct devlink_dpipe_header *header) +{ + struct nlattr *fields_attr, *header_attr; + int err; + + header_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_HEADER); + if (!header_attr) + return -EMSGSIZE; + + if (nla_put_string(skb, DEVLINK_ATTR_DPIPE_HEADER_NAME, header->name) || + nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_ID, header->id) || + nla_put_u8(skb, DEVLINK_ATTR_DPIPE_HEADER_GLOBAL, header->global)) + goto nla_put_failure; + + fields_attr = nla_nest_start_noflag(skb, + DEVLINK_ATTR_DPIPE_HEADER_FIELDS); + if (!fields_attr) + goto nla_put_failure; + + err = devlink_dpipe_fields_put(skb, header); + if (err) { + nla_nest_cancel(skb, fields_attr); + goto nla_put_failure; + } + nla_nest_end(skb, fields_attr); + nla_nest_end(skb, header_attr); + return 0; + +nla_put_failure: + err = -EMSGSIZE; + nla_nest_cancel(skb, header_attr); + return err; +} + +static int devlink_dpipe_headers_fill(struct genl_info *info, + enum devlink_command cmd, int flags, + struct devlink_dpipe_headers * + dpipe_headers) +{ + struct devlink *devlink = info->user_ptr[0]; + struct nlattr *headers_attr; + struct sk_buff *skb = NULL; + struct nlmsghdr *nlh; + void *hdr; + int i, j; + int err; + + i = 0; +start_again: + err = devlink_dpipe_send_and_alloc_skb(&skb, info); + if (err) + return err; + + hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq, + &devlink_nl_family, NLM_F_MULTI, cmd); + if (!hdr) { + nlmsg_free(skb); + return -EMSGSIZE; + } + + if (devlink_nl_put_handle(skb, devlink)) + goto nla_put_failure; + headers_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_HEADERS); + if (!headers_attr) + goto nla_put_failure; + + j = 0; + for (; i < dpipe_headers->headers_count; i++) { + err = devlink_dpipe_header_put(skb, dpipe_headers->headers[i]); + if (err) { + if (!j) + goto err_table_put; + break; + } + j++; + } + nla_nest_end(skb, headers_attr); + genlmsg_end(skb, hdr); + if (i != dpipe_headers->headers_count) + goto start_again; + +send_done: + nlh = nlmsg_put(skb, info->snd_portid, info->snd_seq, + NLMSG_DONE, 0, flags | NLM_F_MULTI); + if (!nlh) { + err = devlink_dpipe_send_and_alloc_skb(&skb, info); + if (err) + return err; + goto send_done; + } + return genlmsg_reply(skb, info); + +nla_put_failure: + err = -EMSGSIZE; +err_table_put: + nlmsg_free(skb); + return err; +} + +static int devlink_nl_cmd_dpipe_headers_get(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + + if (!devlink->dpipe_headers) + return -EOPNOTSUPP; + return devlink_dpipe_headers_fill(info, DEVLINK_CMD_DPIPE_HEADERS_GET, + 0, devlink->dpipe_headers); +} + +static int devlink_dpipe_table_counters_set(struct devlink *devlink, + const char *table_name, + bool enable) +{ + struct devlink_dpipe_table *table; + + table = devlink_dpipe_table_find(&devlink->dpipe_table_list, + table_name, devlink); + if (!table) + return -EINVAL; + + if (table->counter_control_extern) + return -EOPNOTSUPP; + + if (!(table->counters_enabled ^ enable)) + return 0; + + table->counters_enabled = enable; + if (table->table_ops->counters_set_update) + table->table_ops->counters_set_update(table->priv, enable); + return 0; +} + +static int devlink_nl_cmd_dpipe_table_counters_set(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + const char *table_name; + bool counters_enable; + + if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_DPIPE_TABLE_NAME) || + GENL_REQ_ATTR_CHECK(info, + DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED)) + return -EINVAL; + + table_name = nla_data(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]); + counters_enable = !!nla_get_u8(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED]); + + return devlink_dpipe_table_counters_set(devlink, table_name, + counters_enable); +} + +static struct devlink_resource * +devlink_resource_find(struct devlink *devlink, + struct devlink_resource *resource, u64 resource_id) +{ + struct list_head *resource_list; + + if (resource) + resource_list = &resource->resource_list; + else + resource_list = &devlink->resource_list; + + list_for_each_entry(resource, resource_list, list) { + struct devlink_resource *child_resource; + + if (resource->id == resource_id) + return resource; + + child_resource = devlink_resource_find(devlink, resource, + resource_id); + if (child_resource) + return child_resource; + } + return NULL; +} + +static void +devlink_resource_validate_children(struct devlink_resource *resource) +{ + struct devlink_resource *child_resource; + bool size_valid = true; + u64 parts_size = 0; + + if (list_empty(&resource->resource_list)) + goto out; + + list_for_each_entry(child_resource, &resource->resource_list, list) + parts_size += child_resource->size_new; + + if (parts_size > resource->size_new) + size_valid = false; +out: + resource->size_valid = size_valid; +} + +static int +devlink_resource_validate_size(struct devlink_resource *resource, u64 size, + struct netlink_ext_ack *extack) +{ + u64 reminder; + int err = 0; + + if (size > resource->size_params.size_max) { + NL_SET_ERR_MSG_MOD(extack, "Size larger than maximum"); + err = -EINVAL; + } + + if (size < resource->size_params.size_min) { + NL_SET_ERR_MSG_MOD(extack, "Size smaller than minimum"); + err = -EINVAL; + } + + div64_u64_rem(size, resource->size_params.size_granularity, &reminder); + if (reminder) { + NL_SET_ERR_MSG_MOD(extack, "Wrong granularity"); + err = -EINVAL; + } + + return err; +} + +static int devlink_nl_cmd_resource_set(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_resource *resource; + u64 resource_id; + u64 size; + int err; + + if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_RESOURCE_ID) || + GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_RESOURCE_SIZE)) + return -EINVAL; + resource_id = nla_get_u64(info->attrs[DEVLINK_ATTR_RESOURCE_ID]); + + resource = devlink_resource_find(devlink, NULL, resource_id); + if (!resource) + return -EINVAL; + + size = nla_get_u64(info->attrs[DEVLINK_ATTR_RESOURCE_SIZE]); + err = devlink_resource_validate_size(resource, size, info->extack); + if (err) + return err; + + resource->size_new = size; + devlink_resource_validate_children(resource); + if (resource->parent) + devlink_resource_validate_children(resource->parent); + return 0; +} + +static int +devlink_resource_size_params_put(struct devlink_resource *resource, + struct sk_buff *skb) +{ + struct devlink_resource_size_params *size_params; + + size_params = &resource->size_params; + if (nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_GRAN, + size_params->size_granularity, DEVLINK_ATTR_PAD) || + nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_MAX, + size_params->size_max, DEVLINK_ATTR_PAD) || + nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_MIN, + size_params->size_min, DEVLINK_ATTR_PAD) || + nla_put_u8(skb, DEVLINK_ATTR_RESOURCE_UNIT, size_params->unit)) + return -EMSGSIZE; + return 0; +} + +static int devlink_resource_occ_put(struct devlink_resource *resource, + struct sk_buff *skb) +{ + if (!resource->occ_get) + return 0; + return nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_OCC, + resource->occ_get(resource->occ_get_priv), + DEVLINK_ATTR_PAD); +} + +static int devlink_resource_put(struct devlink *devlink, struct sk_buff *skb, + struct devlink_resource *resource) +{ + struct devlink_resource *child_resource; + struct nlattr *child_resource_attr; + struct nlattr *resource_attr; + + resource_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_RESOURCE); + if (!resource_attr) + return -EMSGSIZE; + + if (nla_put_string(skb, DEVLINK_ATTR_RESOURCE_NAME, resource->name) || + nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE, resource->size, + DEVLINK_ATTR_PAD) || + nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_ID, resource->id, + DEVLINK_ATTR_PAD)) + goto nla_put_failure; + if (resource->size != resource->size_new) + nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_NEW, + resource->size_new, DEVLINK_ATTR_PAD); + if (devlink_resource_occ_put(resource, skb)) + goto nla_put_failure; + if (devlink_resource_size_params_put(resource, skb)) + goto nla_put_failure; + if (list_empty(&resource->resource_list)) + goto out; + + if (nla_put_u8(skb, DEVLINK_ATTR_RESOURCE_SIZE_VALID, + resource->size_valid)) + goto nla_put_failure; + + child_resource_attr = nla_nest_start_noflag(skb, + DEVLINK_ATTR_RESOURCE_LIST); + if (!child_resource_attr) + goto nla_put_failure; + + list_for_each_entry(child_resource, &resource->resource_list, list) { + if (devlink_resource_put(devlink, skb, child_resource)) + goto resource_put_failure; + } + + nla_nest_end(skb, child_resource_attr); +out: + nla_nest_end(skb, resource_attr); + return 0; + +resource_put_failure: + nla_nest_cancel(skb, child_resource_attr); +nla_put_failure: + nla_nest_cancel(skb, resource_attr); + return -EMSGSIZE; +} + +static int devlink_resource_fill(struct genl_info *info, + enum devlink_command cmd, int flags) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_resource *resource; + struct nlattr *resources_attr; + struct sk_buff *skb = NULL; + struct nlmsghdr *nlh; + bool incomplete; + void *hdr; + int i; + int err; + + resource = list_first_entry(&devlink->resource_list, + struct devlink_resource, list); +start_again: + err = devlink_dpipe_send_and_alloc_skb(&skb, info); + if (err) + return err; + + hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq, + &devlink_nl_family, NLM_F_MULTI, cmd); + if (!hdr) { + nlmsg_free(skb); + return -EMSGSIZE; + } + + if (devlink_nl_put_handle(skb, devlink)) + goto nla_put_failure; + + resources_attr = nla_nest_start_noflag(skb, + DEVLINK_ATTR_RESOURCE_LIST); + if (!resources_attr) + goto nla_put_failure; + + incomplete = false; + i = 0; + list_for_each_entry_from(resource, &devlink->resource_list, list) { + err = devlink_resource_put(devlink, skb, resource); + if (err) { + if (!i) + goto err_resource_put; + incomplete = true; + break; + } + i++; + } + nla_nest_end(skb, resources_attr); + genlmsg_end(skb, hdr); + if (incomplete) + goto start_again; +send_done: + nlh = nlmsg_put(skb, info->snd_portid, info->snd_seq, + NLMSG_DONE, 0, flags | NLM_F_MULTI); + if (!nlh) { + err = devlink_dpipe_send_and_alloc_skb(&skb, info); + if (err) + return err; + goto send_done; + } + return genlmsg_reply(skb, info); + +nla_put_failure: + err = -EMSGSIZE; +err_resource_put: + nlmsg_free(skb); + return err; +} + +static int devlink_nl_cmd_resource_dump(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + + if (list_empty(&devlink->resource_list)) + return -EOPNOTSUPP; + + return devlink_resource_fill(info, DEVLINK_CMD_RESOURCE_DUMP, 0); +} + +static int +devlink_resources_validate(struct devlink *devlink, + struct devlink_resource *resource, + struct genl_info *info) +{ + struct list_head *resource_list; + int err = 0; + + if (resource) + resource_list = &resource->resource_list; + else + resource_list = &devlink->resource_list; + + list_for_each_entry(resource, resource_list, list) { + if (!resource->size_valid) + return -EINVAL; + err = devlink_resources_validate(devlink, resource, info); + if (err) + return err; + } + return err; +} + +static struct net *devlink_netns_get(struct sk_buff *skb, + struct genl_info *info) +{ + struct nlattr *netns_pid_attr = info->attrs[DEVLINK_ATTR_NETNS_PID]; + struct nlattr *netns_fd_attr = info->attrs[DEVLINK_ATTR_NETNS_FD]; + struct nlattr *netns_id_attr = info->attrs[DEVLINK_ATTR_NETNS_ID]; + struct net *net; + + if (!!netns_pid_attr + !!netns_fd_attr + !!netns_id_attr > 1) { + NL_SET_ERR_MSG_MOD(info->extack, "multiple netns identifying attributes specified"); + return ERR_PTR(-EINVAL); + } + + if (netns_pid_attr) { + net = get_net_ns_by_pid(nla_get_u32(netns_pid_attr)); + } else if (netns_fd_attr) { + net = get_net_ns_by_fd(nla_get_u32(netns_fd_attr)); + } else if (netns_id_attr) { + net = get_net_ns_by_id(sock_net(skb->sk), + nla_get_u32(netns_id_attr)); + if (!net) + net = ERR_PTR(-EINVAL); + } else { + WARN_ON(1); + net = ERR_PTR(-EINVAL); + } + if (IS_ERR(net)) { + NL_SET_ERR_MSG_MOD(info->extack, "Unknown network namespace"); + return ERR_PTR(-EINVAL); + } + if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) { + put_net(net); + return ERR_PTR(-EPERM); + } + return net; +} + +static void devlink_param_notify(struct devlink *devlink, + unsigned int port_index, + struct devlink_param_item *param_item, + enum devlink_command cmd); + +static void devlink_ns_change_notify(struct devlink *devlink, + struct net *dest_net, struct net *curr_net, + bool new) +{ + struct devlink_param_item *param_item; + enum devlink_command cmd; + + /* Userspace needs to be notified about devlink objects + * removed from original and entering new network namespace. + * The rest of the devlink objects are re-created during + * reload process so the notifications are generated separatelly. + */ + + if (!dest_net || net_eq(dest_net, curr_net)) + return; + + if (new) + devlink_notify(devlink, DEVLINK_CMD_NEW); + + cmd = new ? DEVLINK_CMD_PARAM_NEW : DEVLINK_CMD_PARAM_DEL; + list_for_each_entry(param_item, &devlink->param_list, list) + devlink_param_notify(devlink, 0, param_item, cmd); + + if (!new) + devlink_notify(devlink, DEVLINK_CMD_DEL); +} + +static bool devlink_reload_supported(const struct devlink_ops *ops) +{ + return ops->reload_down && ops->reload_up; +} + +static void devlink_reload_failed_set(struct devlink *devlink, + bool reload_failed) +{ + if (devlink->reload_failed == reload_failed) + return; + devlink->reload_failed = reload_failed; + devlink_notify(devlink, DEVLINK_CMD_NEW); +} + +bool devlink_is_reload_failed(const struct devlink *devlink) +{ + return devlink->reload_failed; +} +EXPORT_SYMBOL_GPL(devlink_is_reload_failed); + +static void +__devlink_reload_stats_update(struct devlink *devlink, u32 *reload_stats, + enum devlink_reload_limit limit, u32 actions_performed) +{ + unsigned long actions = actions_performed; + int stat_idx; + int action; + + for_each_set_bit(action, &actions, __DEVLINK_RELOAD_ACTION_MAX) { + stat_idx = limit * __DEVLINK_RELOAD_ACTION_MAX + action; + reload_stats[stat_idx]++; + } + devlink_notify(devlink, DEVLINK_CMD_NEW); +} + +static void +devlink_reload_stats_update(struct devlink *devlink, enum devlink_reload_limit limit, + u32 actions_performed) +{ + __devlink_reload_stats_update(devlink, devlink->stats.reload_stats, limit, + actions_performed); +} + +/** + * devlink_remote_reload_actions_performed - Update devlink on reload actions + * performed which are not a direct result of devlink reload call. + * + * This should be called by a driver after performing reload actions in case it was not + * a result of devlink reload call. For example fw_activate was performed as a result + * of devlink reload triggered fw_activate on another host. + * The motivation for this function is to keep data on reload actions performed on this + * function whether it was done due to direct devlink reload call or not. + * + * @devlink: devlink + * @limit: reload limit + * @actions_performed: bitmask of actions performed + */ +void devlink_remote_reload_actions_performed(struct devlink *devlink, + enum devlink_reload_limit limit, + u32 actions_performed) +{ + if (WARN_ON(!actions_performed || + actions_performed & BIT(DEVLINK_RELOAD_ACTION_UNSPEC) || + actions_performed >= BIT(__DEVLINK_RELOAD_ACTION_MAX) || + limit > DEVLINK_RELOAD_LIMIT_MAX)) + return; + + __devlink_reload_stats_update(devlink, devlink->stats.remote_reload_stats, limit, + actions_performed); +} +EXPORT_SYMBOL_GPL(devlink_remote_reload_actions_performed); + +static int devlink_reload(struct devlink *devlink, struct net *dest_net, + enum devlink_reload_action action, enum devlink_reload_limit limit, + u32 *actions_performed, struct netlink_ext_ack *extack) +{ + u32 remote_reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE]; + struct net *curr_net; + int err; + + memcpy(remote_reload_stats, devlink->stats.remote_reload_stats, + sizeof(remote_reload_stats)); + + curr_net = devlink_net(devlink); + devlink_ns_change_notify(devlink, dest_net, curr_net, false); + err = devlink->ops->reload_down(devlink, !!dest_net, action, limit, extack); + if (err) + return err; + + if (dest_net && !net_eq(dest_net, curr_net)) + write_pnet(&devlink->_net, dest_net); + + err = devlink->ops->reload_up(devlink, action, limit, actions_performed, extack); + devlink_reload_failed_set(devlink, !!err); + if (err) + return err; + + devlink_ns_change_notify(devlink, dest_net, curr_net, true); + WARN_ON(!(*actions_performed & BIT(action))); + /* Catch driver on updating the remote action within devlink reload */ + WARN_ON(memcmp(remote_reload_stats, devlink->stats.remote_reload_stats, + sizeof(remote_reload_stats))); + devlink_reload_stats_update(devlink, limit, *actions_performed); + return 0; +} + +static int +devlink_nl_reload_actions_performed_snd(struct devlink *devlink, u32 actions_performed, + enum devlink_command cmd, struct genl_info *info) +{ + struct sk_buff *msg; + void *hdr; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, &devlink_nl_family, 0, cmd); + if (!hdr) + goto free_msg; + + if (devlink_nl_put_handle(msg, devlink)) + goto nla_put_failure; + + if (nla_put_bitfield32(msg, DEVLINK_ATTR_RELOAD_ACTIONS_PERFORMED, actions_performed, + actions_performed)) + goto nla_put_failure; + genlmsg_end(msg, hdr); + + return genlmsg_reply(msg, info); + +nla_put_failure: + genlmsg_cancel(msg, hdr); +free_msg: + nlmsg_free(msg); + return -EMSGSIZE; +} + +static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + enum devlink_reload_action action; + enum devlink_reload_limit limit; + struct net *dest_net = NULL; + u32 actions_performed; + int err; + + if (!(devlink->features & DEVLINK_F_RELOAD)) + return -EOPNOTSUPP; + + err = devlink_resources_validate(devlink, NULL, info); + if (err) { + NL_SET_ERR_MSG_MOD(info->extack, "resources size validation failed"); + return err; + } + + if (info->attrs[DEVLINK_ATTR_RELOAD_ACTION]) + action = nla_get_u8(info->attrs[DEVLINK_ATTR_RELOAD_ACTION]); + else + action = DEVLINK_RELOAD_ACTION_DRIVER_REINIT; + + if (!devlink_reload_action_is_supported(devlink, action)) { + NL_SET_ERR_MSG_MOD(info->extack, + "Requested reload action is not supported by the driver"); + return -EOPNOTSUPP; + } + + limit = DEVLINK_RELOAD_LIMIT_UNSPEC; + if (info->attrs[DEVLINK_ATTR_RELOAD_LIMITS]) { + struct nla_bitfield32 limits; + u32 limits_selected; + + limits = nla_get_bitfield32(info->attrs[DEVLINK_ATTR_RELOAD_LIMITS]); + limits_selected = limits.value & limits.selector; + if (!limits_selected) { + NL_SET_ERR_MSG_MOD(info->extack, "Invalid limit selected"); + return -EINVAL; + } + for (limit = 0 ; limit <= DEVLINK_RELOAD_LIMIT_MAX ; limit++) + if (limits_selected & BIT(limit)) + break; + /* UAPI enables multiselection, but currently it is not used */ + if (limits_selected != BIT(limit)) { + NL_SET_ERR_MSG_MOD(info->extack, + "Multiselection of limit is not supported"); + return -EOPNOTSUPP; + } + if (!devlink_reload_limit_is_supported(devlink, limit)) { + NL_SET_ERR_MSG_MOD(info->extack, + "Requested limit is not supported by the driver"); + return -EOPNOTSUPP; + } + if (devlink_reload_combination_is_invalid(action, limit)) { + NL_SET_ERR_MSG_MOD(info->extack, + "Requested limit is invalid for this action"); + return -EINVAL; + } + } + if (info->attrs[DEVLINK_ATTR_NETNS_PID] || + info->attrs[DEVLINK_ATTR_NETNS_FD] || + info->attrs[DEVLINK_ATTR_NETNS_ID]) { + dest_net = devlink_netns_get(skb, info); + if (IS_ERR(dest_net)) + return PTR_ERR(dest_net); + } + + err = devlink_reload(devlink, dest_net, action, limit, &actions_performed, info->extack); + + if (dest_net) + put_net(dest_net); + + if (err) + return err; + /* For backward compatibility generate reply only if attributes used by user */ + if (!info->attrs[DEVLINK_ATTR_RELOAD_ACTION] && !info->attrs[DEVLINK_ATTR_RELOAD_LIMITS]) + return 0; + + return devlink_nl_reload_actions_performed_snd(devlink, actions_performed, + DEVLINK_CMD_RELOAD, info); +} + +static int devlink_nl_flash_update_fill(struct sk_buff *msg, + struct devlink *devlink, + enum devlink_command cmd, + struct devlink_flash_notify *params) +{ + void *hdr; + + hdr = genlmsg_put(msg, 0, 0, &devlink_nl_family, 0, cmd); + if (!hdr) + return -EMSGSIZE; + + if (devlink_nl_put_handle(msg, devlink)) + goto nla_put_failure; + + if (cmd != DEVLINK_CMD_FLASH_UPDATE_STATUS) + goto out; + + if (params->status_msg && + nla_put_string(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_MSG, + params->status_msg)) + goto nla_put_failure; + if (params->component && + nla_put_string(msg, DEVLINK_ATTR_FLASH_UPDATE_COMPONENT, + params->component)) + goto nla_put_failure; + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_DONE, + params->done, DEVLINK_ATTR_PAD)) + goto nla_put_failure; + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_TOTAL, + params->total, DEVLINK_ATTR_PAD)) + goto nla_put_failure; + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_TIMEOUT, + params->timeout, DEVLINK_ATTR_PAD)) + goto nla_put_failure; + +out: + genlmsg_end(msg, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static void __devlink_flash_update_notify(struct devlink *devlink, + enum devlink_command cmd, + struct devlink_flash_notify *params) +{ + struct sk_buff *msg; + int err; + + WARN_ON(cmd != DEVLINK_CMD_FLASH_UPDATE && + cmd != DEVLINK_CMD_FLASH_UPDATE_END && + cmd != DEVLINK_CMD_FLASH_UPDATE_STATUS); + + if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)) + return; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + err = devlink_nl_flash_update_fill(msg, devlink, cmd, params); + if (err) + goto out_free_msg; + + genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), + msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); + return; + +out_free_msg: + nlmsg_free(msg); +} + +static void devlink_flash_update_begin_notify(struct devlink *devlink) +{ + struct devlink_flash_notify params = {}; + + __devlink_flash_update_notify(devlink, + DEVLINK_CMD_FLASH_UPDATE, + &params); +} + +static void devlink_flash_update_end_notify(struct devlink *devlink) +{ + struct devlink_flash_notify params = {}; + + __devlink_flash_update_notify(devlink, + DEVLINK_CMD_FLASH_UPDATE_END, + &params); +} + +void devlink_flash_update_status_notify(struct devlink *devlink, + const char *status_msg, + const char *component, + unsigned long done, + unsigned long total) +{ + struct devlink_flash_notify params = { + .status_msg = status_msg, + .component = component, + .done = done, + .total = total, + }; + + __devlink_flash_update_notify(devlink, + DEVLINK_CMD_FLASH_UPDATE_STATUS, + &params); +} +EXPORT_SYMBOL_GPL(devlink_flash_update_status_notify); + +void devlink_flash_update_timeout_notify(struct devlink *devlink, + const char *status_msg, + const char *component, + unsigned long timeout) +{ + struct devlink_flash_notify params = { + .status_msg = status_msg, + .component = component, + .timeout = timeout, + }; + + __devlink_flash_update_notify(devlink, + DEVLINK_CMD_FLASH_UPDATE_STATUS, + &params); +} +EXPORT_SYMBOL_GPL(devlink_flash_update_timeout_notify); + +struct devlink_info_req { + struct sk_buff *msg; + void (*version_cb)(const char *version_name, + enum devlink_info_version_type version_type, + void *version_cb_priv); + void *version_cb_priv; +}; + +struct devlink_flash_component_lookup_ctx { + const char *lookup_name; + bool lookup_name_found; +}; + +static void +devlink_flash_component_lookup_cb(const char *version_name, + enum devlink_info_version_type version_type, + void *version_cb_priv) +{ + struct devlink_flash_component_lookup_ctx *lookup_ctx = version_cb_priv; + + if (version_type != DEVLINK_INFO_VERSION_TYPE_COMPONENT || + lookup_ctx->lookup_name_found) + return; + + lookup_ctx->lookup_name_found = + !strcmp(lookup_ctx->lookup_name, version_name); +} + +static int devlink_flash_component_get(struct devlink *devlink, + struct nlattr *nla_component, + const char **p_component, + struct netlink_ext_ack *extack) +{ + struct devlink_flash_component_lookup_ctx lookup_ctx = {}; + struct devlink_info_req req = {}; + const char *component; + int ret; + + if (!nla_component) + return 0; + + component = nla_data(nla_component); + + if (!devlink->ops->info_get) { + NL_SET_ERR_MSG_ATTR(extack, nla_component, + "component update is not supported by this device"); + return -EOPNOTSUPP; + } + + lookup_ctx.lookup_name = component; + req.version_cb = devlink_flash_component_lookup_cb; + req.version_cb_priv = &lookup_ctx; + + ret = devlink->ops->info_get(devlink, &req, NULL); + if (ret) + return ret; + + if (!lookup_ctx.lookup_name_found) { + NL_SET_ERR_MSG_ATTR(extack, nla_component, + "selected component is not supported by this device"); + return -EINVAL; + } + *p_component = component; + return 0; +} + +static int devlink_nl_cmd_flash_update(struct sk_buff *skb, + struct genl_info *info) +{ + struct nlattr *nla_overwrite_mask, *nla_file_name; + struct devlink_flash_update_params params = {}; + struct devlink *devlink = info->user_ptr[0]; + const char *file_name; + u32 supported_params; + int ret; + + if (!devlink->ops->flash_update) + return -EOPNOTSUPP; + + if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME)) + return -EINVAL; + + ret = devlink_flash_component_get(devlink, + info->attrs[DEVLINK_ATTR_FLASH_UPDATE_COMPONENT], + &params.component, info->extack); + if (ret) + return ret; + + supported_params = devlink->ops->supported_flash_update_params; + + nla_overwrite_mask = info->attrs[DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK]; + if (nla_overwrite_mask) { + struct nla_bitfield32 sections; + + if (!(supported_params & DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK)) { + NL_SET_ERR_MSG_ATTR(info->extack, nla_overwrite_mask, + "overwrite settings are not supported by this device"); + return -EOPNOTSUPP; + } + sections = nla_get_bitfield32(nla_overwrite_mask); + params.overwrite_mask = sections.value & sections.selector; + } + + nla_file_name = info->attrs[DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME]; + file_name = nla_data(nla_file_name); + ret = request_firmware(&params.fw, file_name, devlink->dev); + if (ret) { + NL_SET_ERR_MSG_ATTR(info->extack, nla_file_name, "failed to locate the requested firmware file"); + return ret; + } + + devlink_flash_update_begin_notify(devlink); + ret = devlink->ops->flash_update(devlink, &params, info->extack); + devlink_flash_update_end_notify(devlink); + + release_firmware(params.fw); + + return ret; +} + +static int +devlink_nl_selftests_fill(struct sk_buff *msg, struct devlink *devlink, + u32 portid, u32 seq, int flags, + struct netlink_ext_ack *extack) +{ + struct nlattr *selftests; + void *hdr; + int err; + int i; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, + DEVLINK_CMD_SELFTESTS_GET); + if (!hdr) + return -EMSGSIZE; + + err = -EMSGSIZE; + if (devlink_nl_put_handle(msg, devlink)) + goto err_cancel_msg; + + selftests = nla_nest_start(msg, DEVLINK_ATTR_SELFTESTS); + if (!selftests) + goto err_cancel_msg; + + for (i = DEVLINK_ATTR_SELFTEST_ID_UNSPEC + 1; + i <= DEVLINK_ATTR_SELFTEST_ID_MAX; i++) { + if (devlink->ops->selftest_check(devlink, i, extack)) { + err = nla_put_flag(msg, i); + if (err) + goto err_cancel_msg; + } + } + + nla_nest_end(msg, selftests); + genlmsg_end(msg, hdr); + return 0; + +err_cancel_msg: + genlmsg_cancel(msg, hdr); + return err; +} + +static int devlink_nl_cmd_selftests_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct sk_buff *msg; + int err; + + if (!devlink->ops->selftest_check) + return -EOPNOTSUPP; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_selftests_fill(msg, devlink, info->snd_portid, + info->snd_seq, 0, info->extack); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +static int devlink_nl_cmd_selftests_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + struct devlink *devlink; + int start = cb->args[0]; + unsigned long index; + int idx = 0; + int err = 0; + + devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { + if (idx < start || !devlink->ops->selftest_check) + goto inc; + + devl_lock(devlink); + err = devlink_nl_selftests_fill(msg, devlink, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, + cb->extack); + devl_unlock(devlink); + if (err) { + devlink_put(devlink); + break; + } +inc: + idx++; + devlink_put(devlink); + } + + if (err != -EMSGSIZE) + return err; + + cb->args[0] = idx; + return msg->len; +} + +static int devlink_selftest_result_put(struct sk_buff *skb, unsigned int id, + enum devlink_selftest_status test_status) +{ + struct nlattr *result_attr; + + result_attr = nla_nest_start(skb, DEVLINK_ATTR_SELFTEST_RESULT); + if (!result_attr) + return -EMSGSIZE; + + if (nla_put_u32(skb, DEVLINK_ATTR_SELFTEST_RESULT_ID, id) || + nla_put_u8(skb, DEVLINK_ATTR_SELFTEST_RESULT_STATUS, + test_status)) + goto nla_put_failure; + + nla_nest_end(skb, result_attr); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, result_attr); + return -EMSGSIZE; +} + +static int devlink_nl_cmd_selftests_run(struct sk_buff *skb, + struct genl_info *info) +{ + struct nlattr *tb[DEVLINK_ATTR_SELFTEST_ID_MAX + 1]; + struct devlink *devlink = info->user_ptr[0]; + struct nlattr *attrs, *selftests; + struct sk_buff *msg; + void *hdr; + int err; + int i; + + if (!devlink->ops->selftest_run || !devlink->ops->selftest_check) + return -EOPNOTSUPP; + + if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_SELFTESTS)) + return -EINVAL; + + attrs = info->attrs[DEVLINK_ATTR_SELFTESTS]; + + err = nla_parse_nested(tb, DEVLINK_ATTR_SELFTEST_ID_MAX, attrs, + devlink_selftest_nl_policy, info->extack); + if (err < 0) + return err; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = -EMSGSIZE; + hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, + &devlink_nl_family, 0, DEVLINK_CMD_SELFTESTS_RUN); + if (!hdr) + goto free_msg; + + if (devlink_nl_put_handle(msg, devlink)) + goto genlmsg_cancel; + + selftests = nla_nest_start(msg, DEVLINK_ATTR_SELFTESTS); + if (!selftests) + goto genlmsg_cancel; + + for (i = DEVLINK_ATTR_SELFTEST_ID_UNSPEC + 1; + i <= DEVLINK_ATTR_SELFTEST_ID_MAX; i++) { + enum devlink_selftest_status test_status; + + if (nla_get_flag(tb[i])) { + if (!devlink->ops->selftest_check(devlink, i, + info->extack)) { + if (devlink_selftest_result_put(msg, i, + DEVLINK_SELFTEST_STATUS_SKIP)) + goto selftests_nest_cancel; + continue; + } + + test_status = devlink->ops->selftest_run(devlink, i, + info->extack); + if (devlink_selftest_result_put(msg, i, test_status)) + goto selftests_nest_cancel; + } + } + + nla_nest_end(msg, selftests); + genlmsg_end(msg, hdr); + return genlmsg_reply(msg, info); + +selftests_nest_cancel: + nla_nest_cancel(msg, selftests); +genlmsg_cancel: + genlmsg_cancel(msg, hdr); +free_msg: + nlmsg_free(msg); + return err; +} + +static const struct devlink_param devlink_param_generic[] = { + { + .id = DEVLINK_PARAM_GENERIC_ID_INT_ERR_RESET, + .name = DEVLINK_PARAM_GENERIC_INT_ERR_RESET_NAME, + .type = DEVLINK_PARAM_GENERIC_INT_ERR_RESET_TYPE, + }, + { + .id = DEVLINK_PARAM_GENERIC_ID_MAX_MACS, + .name = DEVLINK_PARAM_GENERIC_MAX_MACS_NAME, + .type = DEVLINK_PARAM_GENERIC_MAX_MACS_TYPE, + }, + { + .id = DEVLINK_PARAM_GENERIC_ID_ENABLE_SRIOV, + .name = DEVLINK_PARAM_GENERIC_ENABLE_SRIOV_NAME, + .type = DEVLINK_PARAM_GENERIC_ENABLE_SRIOV_TYPE, + }, + { + .id = DEVLINK_PARAM_GENERIC_ID_REGION_SNAPSHOT, + .name = DEVLINK_PARAM_GENERIC_REGION_SNAPSHOT_NAME, + .type = DEVLINK_PARAM_GENERIC_REGION_SNAPSHOT_TYPE, + }, + { + .id = DEVLINK_PARAM_GENERIC_ID_IGNORE_ARI, + .name = DEVLINK_PARAM_GENERIC_IGNORE_ARI_NAME, + .type = DEVLINK_PARAM_GENERIC_IGNORE_ARI_TYPE, + }, + { + .id = DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MAX, + .name = DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MAX_NAME, + .type = DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MAX_TYPE, + }, + { + .id = DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN, + .name = DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MIN_NAME, + .type = DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MIN_TYPE, + }, + { + .id = DEVLINK_PARAM_GENERIC_ID_FW_LOAD_POLICY, + .name = DEVLINK_PARAM_GENERIC_FW_LOAD_POLICY_NAME, + .type = DEVLINK_PARAM_GENERIC_FW_LOAD_POLICY_TYPE, + }, + { + .id = DEVLINK_PARAM_GENERIC_ID_RESET_DEV_ON_DRV_PROBE, + .name = DEVLINK_PARAM_GENERIC_RESET_DEV_ON_DRV_PROBE_NAME, + .type = DEVLINK_PARAM_GENERIC_RESET_DEV_ON_DRV_PROBE_TYPE, + }, + { + .id = DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE, + .name = DEVLINK_PARAM_GENERIC_ENABLE_ROCE_NAME, + .type = DEVLINK_PARAM_GENERIC_ENABLE_ROCE_TYPE, + }, + { + .id = DEVLINK_PARAM_GENERIC_ID_ENABLE_REMOTE_DEV_RESET, + .name = DEVLINK_PARAM_GENERIC_ENABLE_REMOTE_DEV_RESET_NAME, + .type = DEVLINK_PARAM_GENERIC_ENABLE_REMOTE_DEV_RESET_TYPE, + }, + { + .id = DEVLINK_PARAM_GENERIC_ID_ENABLE_ETH, + .name = DEVLINK_PARAM_GENERIC_ENABLE_ETH_NAME, + .type = DEVLINK_PARAM_GENERIC_ENABLE_ETH_TYPE, + }, + { + .id = DEVLINK_PARAM_GENERIC_ID_ENABLE_RDMA, + .name = DEVLINK_PARAM_GENERIC_ENABLE_RDMA_NAME, + .type = DEVLINK_PARAM_GENERIC_ENABLE_RDMA_TYPE, + }, + { + .id = DEVLINK_PARAM_GENERIC_ID_ENABLE_VNET, + .name = DEVLINK_PARAM_GENERIC_ENABLE_VNET_NAME, + .type = DEVLINK_PARAM_GENERIC_ENABLE_VNET_TYPE, + }, + { + .id = DEVLINK_PARAM_GENERIC_ID_ENABLE_IWARP, + .name = DEVLINK_PARAM_GENERIC_ENABLE_IWARP_NAME, + .type = DEVLINK_PARAM_GENERIC_ENABLE_IWARP_TYPE, + }, + { + .id = DEVLINK_PARAM_GENERIC_ID_IO_EQ_SIZE, + .name = DEVLINK_PARAM_GENERIC_IO_EQ_SIZE_NAME, + .type = DEVLINK_PARAM_GENERIC_IO_EQ_SIZE_TYPE, + }, + { + .id = DEVLINK_PARAM_GENERIC_ID_EVENT_EQ_SIZE, + .name = DEVLINK_PARAM_GENERIC_EVENT_EQ_SIZE_NAME, + .type = DEVLINK_PARAM_GENERIC_EVENT_EQ_SIZE_TYPE, + }, +}; + +static int devlink_param_generic_verify(const struct devlink_param *param) +{ + /* verify it match generic parameter by id and name */ + if (param->id > DEVLINK_PARAM_GENERIC_ID_MAX) + return -EINVAL; + if (strcmp(param->name, devlink_param_generic[param->id].name)) + return -ENOENT; + + WARN_ON(param->type != devlink_param_generic[param->id].type); + + return 0; +} + +static int devlink_param_driver_verify(const struct devlink_param *param) +{ + int i; + + if (param->id <= DEVLINK_PARAM_GENERIC_ID_MAX) + return -EINVAL; + /* verify no such name in generic params */ + for (i = 0; i <= DEVLINK_PARAM_GENERIC_ID_MAX; i++) + if (!strcmp(param->name, devlink_param_generic[i].name)) + return -EEXIST; + + return 0; +} + +static struct devlink_param_item * +devlink_param_find_by_name(struct list_head *param_list, + const char *param_name) +{ + struct devlink_param_item *param_item; + + list_for_each_entry(param_item, param_list, list) + if (!strcmp(param_item->param->name, param_name)) + return param_item; + return NULL; +} + +static struct devlink_param_item * +devlink_param_find_by_id(struct list_head *param_list, u32 param_id) +{ + struct devlink_param_item *param_item; + + list_for_each_entry(param_item, param_list, list) + if (param_item->param->id == param_id) + return param_item; + return NULL; +} + +static bool +devlink_param_cmode_is_supported(const struct devlink_param *param, + enum devlink_param_cmode cmode) +{ + return test_bit(cmode, &param->supported_cmodes); +} + +static int devlink_param_get(struct devlink *devlink, + const struct devlink_param *param, + struct devlink_param_gset_ctx *ctx) +{ + if (!param->get || devlink->reload_failed) + return -EOPNOTSUPP; + return param->get(devlink, param->id, ctx); +} + +static int devlink_param_set(struct devlink *devlink, + const struct devlink_param *param, + struct devlink_param_gset_ctx *ctx) +{ + if (!param->set || devlink->reload_failed) + return -EOPNOTSUPP; + return param->set(devlink, param->id, ctx); +} + +static int +devlink_param_type_to_nla_type(enum devlink_param_type param_type) +{ + switch (param_type) { + case DEVLINK_PARAM_TYPE_U8: + return NLA_U8; + case DEVLINK_PARAM_TYPE_U16: + return NLA_U16; + case DEVLINK_PARAM_TYPE_U32: + return NLA_U32; + case DEVLINK_PARAM_TYPE_STRING: + return NLA_STRING; + case DEVLINK_PARAM_TYPE_BOOL: + return NLA_FLAG; + default: + return -EINVAL; + } +} + +static int +devlink_nl_param_value_fill_one(struct sk_buff *msg, + enum devlink_param_type type, + enum devlink_param_cmode cmode, + union devlink_param_value val) +{ + struct nlattr *param_value_attr; + + param_value_attr = nla_nest_start_noflag(msg, + DEVLINK_ATTR_PARAM_VALUE); + if (!param_value_attr) + goto nla_put_failure; + + if (nla_put_u8(msg, DEVLINK_ATTR_PARAM_VALUE_CMODE, cmode)) + goto value_nest_cancel; + + switch (type) { + case DEVLINK_PARAM_TYPE_U8: + if (nla_put_u8(msg, DEVLINK_ATTR_PARAM_VALUE_DATA, val.vu8)) + goto value_nest_cancel; + break; + case DEVLINK_PARAM_TYPE_U16: + if (nla_put_u16(msg, DEVLINK_ATTR_PARAM_VALUE_DATA, val.vu16)) + goto value_nest_cancel; + break; + case DEVLINK_PARAM_TYPE_U32: + if (nla_put_u32(msg, DEVLINK_ATTR_PARAM_VALUE_DATA, val.vu32)) + goto value_nest_cancel; + break; + case DEVLINK_PARAM_TYPE_STRING: + if (nla_put_string(msg, DEVLINK_ATTR_PARAM_VALUE_DATA, + val.vstr)) + goto value_nest_cancel; + break; + case DEVLINK_PARAM_TYPE_BOOL: + if (val.vbool && + nla_put_flag(msg, DEVLINK_ATTR_PARAM_VALUE_DATA)) + goto value_nest_cancel; + break; + } + + nla_nest_end(msg, param_value_attr); + return 0; + +value_nest_cancel: + nla_nest_cancel(msg, param_value_attr); +nla_put_failure: + return -EMSGSIZE; +} + +static int devlink_nl_param_fill(struct sk_buff *msg, struct devlink *devlink, + unsigned int port_index, + struct devlink_param_item *param_item, + enum devlink_command cmd, + u32 portid, u32 seq, int flags) +{ + union devlink_param_value param_value[DEVLINK_PARAM_CMODE_MAX + 1]; + bool param_value_set[DEVLINK_PARAM_CMODE_MAX + 1] = {}; + const struct devlink_param *param = param_item->param; + struct devlink_param_gset_ctx ctx; + struct nlattr *param_values_list; + struct nlattr *param_attr; + int nla_type; + void *hdr; + int err; + int i; + + /* Get value from driver part to driverinit configuration mode */ + for (i = 0; i <= DEVLINK_PARAM_CMODE_MAX; i++) { + if (!devlink_param_cmode_is_supported(param, i)) + continue; + if (i == DEVLINK_PARAM_CMODE_DRIVERINIT) { + if (!param_item->driverinit_value_valid) + return -EOPNOTSUPP; + param_value[i] = param_item->driverinit_value; + } else { + ctx.cmode = i; + err = devlink_param_get(devlink, param, &ctx); + if (err) + return err; + param_value[i] = ctx.val; + } + param_value_set[i] = true; + } + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + if (devlink_nl_put_handle(msg, devlink)) + goto genlmsg_cancel; + + if (cmd == DEVLINK_CMD_PORT_PARAM_GET || + cmd == DEVLINK_CMD_PORT_PARAM_NEW || + cmd == DEVLINK_CMD_PORT_PARAM_DEL) + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, port_index)) + goto genlmsg_cancel; + + param_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_PARAM); + if (!param_attr) + goto genlmsg_cancel; + if (nla_put_string(msg, DEVLINK_ATTR_PARAM_NAME, param->name)) + goto param_nest_cancel; + if (param->generic && nla_put_flag(msg, DEVLINK_ATTR_PARAM_GENERIC)) + goto param_nest_cancel; + + nla_type = devlink_param_type_to_nla_type(param->type); + if (nla_type < 0) + goto param_nest_cancel; + if (nla_put_u8(msg, DEVLINK_ATTR_PARAM_TYPE, nla_type)) + goto param_nest_cancel; + + param_values_list = nla_nest_start_noflag(msg, + DEVLINK_ATTR_PARAM_VALUES_LIST); + if (!param_values_list) + goto param_nest_cancel; + + for (i = 0; i <= DEVLINK_PARAM_CMODE_MAX; i++) { + if (!param_value_set[i]) + continue; + err = devlink_nl_param_value_fill_one(msg, param->type, + i, param_value[i]); + if (err) + goto values_list_nest_cancel; + } + + nla_nest_end(msg, param_values_list); + nla_nest_end(msg, param_attr); + genlmsg_end(msg, hdr); + return 0; + +values_list_nest_cancel: + nla_nest_end(msg, param_values_list); +param_nest_cancel: + nla_nest_cancel(msg, param_attr); +genlmsg_cancel: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static void devlink_param_notify(struct devlink *devlink, + unsigned int port_index, + struct devlink_param_item *param_item, + enum devlink_command cmd) +{ + struct sk_buff *msg; + int err; + + WARN_ON(cmd != DEVLINK_CMD_PARAM_NEW && cmd != DEVLINK_CMD_PARAM_DEL && + cmd != DEVLINK_CMD_PORT_PARAM_NEW && + cmd != DEVLINK_CMD_PORT_PARAM_DEL); + ASSERT_DEVLINK_REGISTERED(devlink); + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + err = devlink_nl_param_fill(msg, devlink, port_index, param_item, cmd, + 0, 0, 0); + if (err) { + nlmsg_free(msg); + return; + } + + genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), + msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); +} + +static int devlink_nl_cmd_param_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + struct devlink_param_item *param_item; + struct devlink *devlink; + int start = cb->args[0]; + unsigned long index; + int idx = 0; + int err = 0; + + devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { + devl_lock(devlink); + list_for_each_entry(param_item, &devlink->param_list, list) { + if (idx < start) { + idx++; + continue; + } + err = devlink_nl_param_fill(msg, devlink, 0, param_item, + DEVLINK_CMD_PARAM_GET, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI); + if (err == -EOPNOTSUPP) { + err = 0; + } else if (err) { + devl_unlock(devlink); + devlink_put(devlink); + goto out; + } + idx++; + } + devl_unlock(devlink); + devlink_put(devlink); + } +out: + if (err != -EMSGSIZE) + return err; + + cb->args[0] = idx; + return msg->len; +} + +static int +devlink_param_type_get_from_info(struct genl_info *info, + enum devlink_param_type *param_type) +{ + if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_PARAM_TYPE)) + return -EINVAL; + + switch (nla_get_u8(info->attrs[DEVLINK_ATTR_PARAM_TYPE])) { + case NLA_U8: + *param_type = DEVLINK_PARAM_TYPE_U8; + break; + case NLA_U16: + *param_type = DEVLINK_PARAM_TYPE_U16; + break; + case NLA_U32: + *param_type = DEVLINK_PARAM_TYPE_U32; + break; + case NLA_STRING: + *param_type = DEVLINK_PARAM_TYPE_STRING; + break; + case NLA_FLAG: + *param_type = DEVLINK_PARAM_TYPE_BOOL; + break; + default: + return -EINVAL; + } + + return 0; +} + +static int +devlink_param_value_get_from_info(const struct devlink_param *param, + struct genl_info *info, + union devlink_param_value *value) +{ + struct nlattr *param_data; + int len; + + param_data = info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]; + + if (param->type != DEVLINK_PARAM_TYPE_BOOL && !param_data) + return -EINVAL; + + switch (param->type) { + case DEVLINK_PARAM_TYPE_U8: + if (nla_len(param_data) != sizeof(u8)) + return -EINVAL; + value->vu8 = nla_get_u8(param_data); + break; + case DEVLINK_PARAM_TYPE_U16: + if (nla_len(param_data) != sizeof(u16)) + return -EINVAL; + value->vu16 = nla_get_u16(param_data); + break; + case DEVLINK_PARAM_TYPE_U32: + if (nla_len(param_data) != sizeof(u32)) + return -EINVAL; + value->vu32 = nla_get_u32(param_data); + break; + case DEVLINK_PARAM_TYPE_STRING: + len = strnlen(nla_data(param_data), nla_len(param_data)); + if (len == nla_len(param_data) || + len >= __DEVLINK_PARAM_MAX_STRING_VALUE) + return -EINVAL; + strcpy(value->vstr, nla_data(param_data)); + break; + case DEVLINK_PARAM_TYPE_BOOL: + if (param_data && nla_len(param_data)) + return -EINVAL; + value->vbool = nla_get_flag(param_data); + break; + } + return 0; +} + +static struct devlink_param_item * +devlink_param_get_from_info(struct list_head *param_list, + struct genl_info *info) +{ + char *param_name; + + if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_PARAM_NAME)) + return NULL; + + param_name = nla_data(info->attrs[DEVLINK_ATTR_PARAM_NAME]); + return devlink_param_find_by_name(param_list, param_name); +} + +static int devlink_nl_cmd_param_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_param_item *param_item; + struct sk_buff *msg; + int err; + + param_item = devlink_param_get_from_info(&devlink->param_list, info); + if (!param_item) + return -EINVAL; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_param_fill(msg, devlink, 0, param_item, + DEVLINK_CMD_PARAM_GET, + info->snd_portid, info->snd_seq, 0); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +static int __devlink_nl_cmd_param_set_doit(struct devlink *devlink, + unsigned int port_index, + struct list_head *param_list, + struct genl_info *info, + enum devlink_command cmd) +{ + enum devlink_param_type param_type; + struct devlink_param_gset_ctx ctx; + enum devlink_param_cmode cmode; + struct devlink_param_item *param_item; + const struct devlink_param *param; + union devlink_param_value value; + int err = 0; + + param_item = devlink_param_get_from_info(param_list, info); + if (!param_item) + return -EINVAL; + param = param_item->param; + err = devlink_param_type_get_from_info(info, &param_type); + if (err) + return err; + if (param_type != param->type) + return -EINVAL; + err = devlink_param_value_get_from_info(param, info, &value); + if (err) + return err; + if (param->validate) { + err = param->validate(devlink, param->id, value, info->extack); + if (err) + return err; + } + + if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_PARAM_VALUE_CMODE)) + return -EINVAL; + cmode = nla_get_u8(info->attrs[DEVLINK_ATTR_PARAM_VALUE_CMODE]); + if (!devlink_param_cmode_is_supported(param, cmode)) + return -EOPNOTSUPP; + + if (cmode == DEVLINK_PARAM_CMODE_DRIVERINIT) { + if (param->type == DEVLINK_PARAM_TYPE_STRING) + strcpy(param_item->driverinit_value.vstr, value.vstr); + else + param_item->driverinit_value = value; + param_item->driverinit_value_valid = true; + } else { + if (!param->set) + return -EOPNOTSUPP; + ctx.val = value; + ctx.cmode = cmode; + err = devlink_param_set(devlink, param, &ctx); + if (err) + return err; + } + + devlink_param_notify(devlink, port_index, param_item, cmd); + return 0; +} + +static int devlink_nl_cmd_param_set_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + + return __devlink_nl_cmd_param_set_doit(devlink, 0, &devlink->param_list, + info, DEVLINK_CMD_PARAM_NEW); +} + +static int devlink_nl_cmd_port_param_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + NL_SET_ERR_MSG_MOD(cb->extack, "Port params are not supported"); + return msg->len; +} + +static int devlink_nl_cmd_port_param_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + NL_SET_ERR_MSG_MOD(info->extack, "Port params are not supported"); + return -EINVAL; +} + +static int devlink_nl_cmd_port_param_set_doit(struct sk_buff *skb, + struct genl_info *info) +{ + NL_SET_ERR_MSG_MOD(info->extack, "Port params are not supported"); + return -EINVAL; +} + +static int devlink_nl_region_snapshot_id_put(struct sk_buff *msg, + struct devlink *devlink, + struct devlink_snapshot *snapshot) +{ + struct nlattr *snap_attr; + int err; + + snap_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_REGION_SNAPSHOT); + if (!snap_attr) + return -EINVAL; + + err = nla_put_u32(msg, DEVLINK_ATTR_REGION_SNAPSHOT_ID, snapshot->id); + if (err) + goto nla_put_failure; + + nla_nest_end(msg, snap_attr); + return 0; + +nla_put_failure: + nla_nest_cancel(msg, snap_attr); + return err; +} + +static int devlink_nl_region_snapshots_id_put(struct sk_buff *msg, + struct devlink *devlink, + struct devlink_region *region) +{ + struct devlink_snapshot *snapshot; + struct nlattr *snapshots_attr; + int err; + + snapshots_attr = nla_nest_start_noflag(msg, + DEVLINK_ATTR_REGION_SNAPSHOTS); + if (!snapshots_attr) + return -EINVAL; + + list_for_each_entry(snapshot, &region->snapshot_list, list) { + err = devlink_nl_region_snapshot_id_put(msg, devlink, snapshot); + if (err) + goto nla_put_failure; + } + + nla_nest_end(msg, snapshots_attr); + return 0; + +nla_put_failure: + nla_nest_cancel(msg, snapshots_attr); + return err; +} + +static int devlink_nl_region_fill(struct sk_buff *msg, struct devlink *devlink, + enum devlink_command cmd, u32 portid, + u32 seq, int flags, + struct devlink_region *region) +{ + void *hdr; + int err; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + err = devlink_nl_put_handle(msg, devlink); + if (err) + goto nla_put_failure; + + if (region->port) { + err = nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, + region->port->index); + if (err) + goto nla_put_failure; + } + + err = nla_put_string(msg, DEVLINK_ATTR_REGION_NAME, region->ops->name); + if (err) + goto nla_put_failure; + + err = nla_put_u64_64bit(msg, DEVLINK_ATTR_REGION_SIZE, + region->size, + DEVLINK_ATTR_PAD); + if (err) + goto nla_put_failure; + + err = nla_put_u32(msg, DEVLINK_ATTR_REGION_MAX_SNAPSHOTS, + region->max_snapshots); + if (err) + goto nla_put_failure; + + err = devlink_nl_region_snapshots_id_put(msg, devlink, region); + if (err) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return err; +} + +static struct sk_buff * +devlink_nl_region_notify_build(struct devlink_region *region, + struct devlink_snapshot *snapshot, + enum devlink_command cmd, u32 portid, u32 seq) +{ + struct devlink *devlink = region->devlink; + struct sk_buff *msg; + void *hdr; + int err; + + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return ERR_PTR(-ENOMEM); + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, 0, cmd); + if (!hdr) { + err = -EMSGSIZE; + goto out_free_msg; + } + + err = devlink_nl_put_handle(msg, devlink); + if (err) + goto out_cancel_msg; + + if (region->port) { + err = nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, + region->port->index); + if (err) + goto out_cancel_msg; + } + + err = nla_put_string(msg, DEVLINK_ATTR_REGION_NAME, + region->ops->name); + if (err) + goto out_cancel_msg; + + if (snapshot) { + err = nla_put_u32(msg, DEVLINK_ATTR_REGION_SNAPSHOT_ID, + snapshot->id); + if (err) + goto out_cancel_msg; + } else { + err = nla_put_u64_64bit(msg, DEVLINK_ATTR_REGION_SIZE, + region->size, DEVLINK_ATTR_PAD); + if (err) + goto out_cancel_msg; + } + genlmsg_end(msg, hdr); + + return msg; + +out_cancel_msg: + genlmsg_cancel(msg, hdr); +out_free_msg: + nlmsg_free(msg); + return ERR_PTR(err); +} + +static void devlink_nl_region_notify(struct devlink_region *region, + struct devlink_snapshot *snapshot, + enum devlink_command cmd) +{ + struct devlink *devlink = region->devlink; + struct sk_buff *msg; + + WARN_ON(cmd != DEVLINK_CMD_REGION_NEW && cmd != DEVLINK_CMD_REGION_DEL); + if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)) + return; + + msg = devlink_nl_region_notify_build(region, snapshot, cmd, 0, 0); + if (IS_ERR(msg)) + return; + + genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), msg, + 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); +} + +/** + * __devlink_snapshot_id_increment - Increment number of snapshots using an id + * @devlink: devlink instance + * @id: the snapshot id + * + * Track when a new snapshot begins using an id. Load the count for the + * given id from the snapshot xarray, increment it, and store it back. + * + * Called when a new snapshot is created with the given id. + * + * The id *must* have been previously allocated by + * devlink_region_snapshot_id_get(). + * + * Returns 0 on success, or an error on failure. + */ +static int __devlink_snapshot_id_increment(struct devlink *devlink, u32 id) +{ + unsigned long count; + void *p; + int err; + + xa_lock(&devlink->snapshot_ids); + p = xa_load(&devlink->snapshot_ids, id); + if (WARN_ON(!p)) { + err = -EINVAL; + goto unlock; + } + + if (WARN_ON(!xa_is_value(p))) { + err = -EINVAL; + goto unlock; + } + + count = xa_to_value(p); + count++; + + err = xa_err(__xa_store(&devlink->snapshot_ids, id, xa_mk_value(count), + GFP_ATOMIC)); +unlock: + xa_unlock(&devlink->snapshot_ids); + return err; +} + +/** + * __devlink_snapshot_id_decrement - Decrease number of snapshots using an id + * @devlink: devlink instance + * @id: the snapshot id + * + * Track when a snapshot is deleted and stops using an id. Load the count + * for the given id from the snapshot xarray, decrement it, and store it + * back. + * + * If the count reaches zero, erase this id from the xarray, freeing it + * up for future re-use by devlink_region_snapshot_id_get(). + * + * Called when a snapshot using the given id is deleted, and when the + * initial allocator of the id is finished using it. + */ +static void __devlink_snapshot_id_decrement(struct devlink *devlink, u32 id) +{ + unsigned long count; + void *p; + + xa_lock(&devlink->snapshot_ids); + p = xa_load(&devlink->snapshot_ids, id); + if (WARN_ON(!p)) + goto unlock; + + if (WARN_ON(!xa_is_value(p))) + goto unlock; + + count = xa_to_value(p); + + if (count > 1) { + count--; + __xa_store(&devlink->snapshot_ids, id, xa_mk_value(count), + GFP_ATOMIC); + } else { + /* If this was the last user, we can erase this id */ + __xa_erase(&devlink->snapshot_ids, id); + } +unlock: + xa_unlock(&devlink->snapshot_ids); +} + +/** + * __devlink_snapshot_id_insert - Insert a specific snapshot ID + * @devlink: devlink instance + * @id: the snapshot id + * + * Mark the given snapshot id as used by inserting a zero value into the + * snapshot xarray. + * + * This must be called while holding the devlink instance lock. Unlike + * devlink_snapshot_id_get, the initial reference count is zero, not one. + * It is expected that the id will immediately be used before + * releasing the devlink instance lock. + * + * Returns zero on success, or an error code if the snapshot id could not + * be inserted. + */ +static int __devlink_snapshot_id_insert(struct devlink *devlink, u32 id) +{ + int err; + + xa_lock(&devlink->snapshot_ids); + if (xa_load(&devlink->snapshot_ids, id)) { + xa_unlock(&devlink->snapshot_ids); + return -EEXIST; + } + err = xa_err(__xa_store(&devlink->snapshot_ids, id, xa_mk_value(0), + GFP_ATOMIC)); + xa_unlock(&devlink->snapshot_ids); + return err; +} + +/** + * __devlink_region_snapshot_id_get - get snapshot ID + * @devlink: devlink instance + * @id: storage to return snapshot id + * + * Allocates a new snapshot id. Returns zero on success, or a negative + * error on failure. Must be called while holding the devlink instance + * lock. + * + * Snapshot IDs are tracked using an xarray which stores the number of + * users of the snapshot id. + * + * Note that the caller of this function counts as a 'user', in order to + * avoid race conditions. The caller must release its hold on the + * snapshot by using devlink_region_snapshot_id_put. + */ +static int __devlink_region_snapshot_id_get(struct devlink *devlink, u32 *id) +{ + return xa_alloc(&devlink->snapshot_ids, id, xa_mk_value(1), + xa_limit_32b, GFP_KERNEL); +} + +/** + * __devlink_region_snapshot_create - create a new snapshot + * This will add a new snapshot of a region. The snapshot + * will be stored on the region struct and can be accessed + * from devlink. This is useful for future analyses of snapshots. + * Multiple snapshots can be created on a region. + * The @snapshot_id should be obtained using the getter function. + * + * Must be called only while holding the region snapshot lock. + * + * @region: devlink region of the snapshot + * @data: snapshot data + * @snapshot_id: snapshot id to be created + */ +static int +__devlink_region_snapshot_create(struct devlink_region *region, + u8 *data, u32 snapshot_id) +{ + struct devlink *devlink = region->devlink; + struct devlink_snapshot *snapshot; + int err; + + lockdep_assert_held(&region->snapshot_lock); + + /* check if region can hold one more snapshot */ + if (region->cur_snapshots == region->max_snapshots) + return -ENOSPC; + + if (devlink_region_snapshot_get_by_id(region, snapshot_id)) + return -EEXIST; + + snapshot = kzalloc(sizeof(*snapshot), GFP_KERNEL); + if (!snapshot) + return -ENOMEM; + + err = __devlink_snapshot_id_increment(devlink, snapshot_id); + if (err) + goto err_snapshot_id_increment; + + snapshot->id = snapshot_id; + snapshot->region = region; + snapshot->data = data; + + list_add_tail(&snapshot->list, &region->snapshot_list); + + region->cur_snapshots++; + + devlink_nl_region_notify(region, snapshot, DEVLINK_CMD_REGION_NEW); + return 0; + +err_snapshot_id_increment: + kfree(snapshot); + return err; +} + +static void devlink_region_snapshot_del(struct devlink_region *region, + struct devlink_snapshot *snapshot) +{ + struct devlink *devlink = region->devlink; + + lockdep_assert_held(&region->snapshot_lock); + + devlink_nl_region_notify(region, snapshot, DEVLINK_CMD_REGION_DEL); + region->cur_snapshots--; + list_del(&snapshot->list); + region->ops->destructor(snapshot->data); + __devlink_snapshot_id_decrement(devlink, snapshot->id); + kfree(snapshot); +} + +static int devlink_nl_cmd_region_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_port *port = NULL; + struct devlink_region *region; + const char *region_name; + struct sk_buff *msg; + unsigned int index; + int err; + + if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_REGION_NAME)) + return -EINVAL; + + if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) { + index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); + + port = devlink_port_get_by_index(devlink, index); + if (!port) + return -ENODEV; + } + + region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]); + if (port) + region = devlink_port_region_get_by_name(port, region_name); + else + region = devlink_region_get_by_name(devlink, region_name); + + if (!region) + return -EINVAL; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_region_fill(msg, devlink, DEVLINK_CMD_REGION_GET, + info->snd_portid, info->snd_seq, 0, + region); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +static int devlink_nl_cmd_region_get_port_dumpit(struct sk_buff *msg, + struct netlink_callback *cb, + struct devlink_port *port, + int *idx, + int start) +{ + struct devlink_region *region; + int err = 0; + + list_for_each_entry(region, &port->region_list, list) { + if (*idx < start) { + (*idx)++; + continue; + } + err = devlink_nl_region_fill(msg, port->devlink, + DEVLINK_CMD_REGION_GET, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI, region); + if (err) + goto out; + (*idx)++; + } + +out: + return err; +} + +static int devlink_nl_cmd_region_get_devlink_dumpit(struct sk_buff *msg, + struct netlink_callback *cb, + struct devlink *devlink, + int *idx, + int start) +{ + struct devlink_region *region; + struct devlink_port *port; + int err = 0; + + devl_lock(devlink); + list_for_each_entry(region, &devlink->region_list, list) { + if (*idx < start) { + (*idx)++; + continue; + } + err = devlink_nl_region_fill(msg, devlink, + DEVLINK_CMD_REGION_GET, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI, region); + if (err) + goto out; + (*idx)++; + } + + list_for_each_entry(port, &devlink->port_list, list) { + err = devlink_nl_cmd_region_get_port_dumpit(msg, cb, port, idx, + start); + if (err) + goto out; + } + +out: + devl_unlock(devlink); + return err; +} + +static int devlink_nl_cmd_region_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + struct devlink *devlink; + int start = cb->args[0]; + unsigned long index; + int idx = 0; + int err = 0; + + devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { + err = devlink_nl_cmd_region_get_devlink_dumpit(msg, cb, devlink, + &idx, start); + devlink_put(devlink); + if (err) + goto out; + } +out: + cb->args[0] = idx; + return msg->len; +} + +static int devlink_nl_cmd_region_del(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_snapshot *snapshot; + struct devlink_port *port = NULL; + struct devlink_region *region; + const char *region_name; + unsigned int index; + u32 snapshot_id; + + if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_REGION_NAME) || + GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_REGION_SNAPSHOT_ID)) + return -EINVAL; + + region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]); + snapshot_id = nla_get_u32(info->attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]); + + if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) { + index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); + + port = devlink_port_get_by_index(devlink, index); + if (!port) + return -ENODEV; + } + + if (port) + region = devlink_port_region_get_by_name(port, region_name); + else + region = devlink_region_get_by_name(devlink, region_name); + + if (!region) + return -EINVAL; + + mutex_lock(&region->snapshot_lock); + snapshot = devlink_region_snapshot_get_by_id(region, snapshot_id); + if (!snapshot) { + mutex_unlock(&region->snapshot_lock); + return -EINVAL; + } + + devlink_region_snapshot_del(region, snapshot); + mutex_unlock(&region->snapshot_lock); + return 0; +} + +static int +devlink_nl_cmd_region_new(struct sk_buff *skb, struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_snapshot *snapshot; + struct devlink_port *port = NULL; + struct nlattr *snapshot_id_attr; + struct devlink_region *region; + const char *region_name; + unsigned int index; + u32 snapshot_id; + u8 *data; + int err; + + if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_REGION_NAME)) { + NL_SET_ERR_MSG_MOD(info->extack, "No region name provided"); + return -EINVAL; + } + + region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]); + + if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) { + index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); + + port = devlink_port_get_by_index(devlink, index); + if (!port) + return -ENODEV; + } + + if (port) + region = devlink_port_region_get_by_name(port, region_name); + else + region = devlink_region_get_by_name(devlink, region_name); + + if (!region) { + NL_SET_ERR_MSG_MOD(info->extack, "The requested region does not exist"); + return -EINVAL; + } + + if (!region->ops->snapshot) { + NL_SET_ERR_MSG_MOD(info->extack, "The requested region does not support taking an immediate snapshot"); + return -EOPNOTSUPP; + } + + mutex_lock(&region->snapshot_lock); + + if (region->cur_snapshots == region->max_snapshots) { + NL_SET_ERR_MSG_MOD(info->extack, "The region has reached the maximum number of stored snapshots"); + err = -ENOSPC; + goto unlock; + } + + snapshot_id_attr = info->attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]; + if (snapshot_id_attr) { + snapshot_id = nla_get_u32(snapshot_id_attr); + + if (devlink_region_snapshot_get_by_id(region, snapshot_id)) { + NL_SET_ERR_MSG_MOD(info->extack, "The requested snapshot id is already in use"); + err = -EEXIST; + goto unlock; + } + + err = __devlink_snapshot_id_insert(devlink, snapshot_id); + if (err) + goto unlock; + } else { + err = __devlink_region_snapshot_id_get(devlink, &snapshot_id); + if (err) { + NL_SET_ERR_MSG_MOD(info->extack, "Failed to allocate a new snapshot id"); + goto unlock; + } + } + + if (port) + err = region->port_ops->snapshot(port, region->port_ops, + info->extack, &data); + else + err = region->ops->snapshot(devlink, region->ops, + info->extack, &data); + if (err) + goto err_snapshot_capture; + + err = __devlink_region_snapshot_create(region, data, snapshot_id); + if (err) + goto err_snapshot_create; + + if (!snapshot_id_attr) { + struct sk_buff *msg; + + snapshot = devlink_region_snapshot_get_by_id(region, + snapshot_id); + if (WARN_ON(!snapshot)) { + err = -EINVAL; + goto unlock; + } + + msg = devlink_nl_region_notify_build(region, snapshot, + DEVLINK_CMD_REGION_NEW, + info->snd_portid, + info->snd_seq); + err = PTR_ERR_OR_ZERO(msg); + if (err) + goto err_notify; + + err = genlmsg_reply(msg, info); + if (err) + goto err_notify; + } + + mutex_unlock(&region->snapshot_lock); + return 0; + +err_snapshot_create: + region->ops->destructor(data); +err_snapshot_capture: + __devlink_snapshot_id_decrement(devlink, snapshot_id); + mutex_unlock(&region->snapshot_lock); + return err; + +err_notify: + devlink_region_snapshot_del(region, snapshot); +unlock: + mutex_unlock(&region->snapshot_lock); + return err; +} + +static int devlink_nl_cmd_region_read_chunk_fill(struct sk_buff *msg, + struct devlink *devlink, + u8 *chunk, u32 chunk_size, + u64 addr) +{ + struct nlattr *chunk_attr; + int err; + + chunk_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_REGION_CHUNK); + if (!chunk_attr) + return -EINVAL; + + err = nla_put(msg, DEVLINK_ATTR_REGION_CHUNK_DATA, chunk_size, chunk); + if (err) + goto nla_put_failure; + + err = nla_put_u64_64bit(msg, DEVLINK_ATTR_REGION_CHUNK_ADDR, addr, + DEVLINK_ATTR_PAD); + if (err) + goto nla_put_failure; + + nla_nest_end(msg, chunk_attr); + return 0; + +nla_put_failure: + nla_nest_cancel(msg, chunk_attr); + return err; +} + +#define DEVLINK_REGION_READ_CHUNK_SIZE 256 + +static int devlink_nl_region_read_snapshot_fill(struct sk_buff *skb, + struct devlink *devlink, + struct devlink_region *region, + struct nlattr **attrs, + u64 start_offset, + u64 end_offset, + u64 *new_offset) +{ + struct devlink_snapshot *snapshot; + u64 curr_offset = start_offset; + u32 snapshot_id; + int err = 0; + + *new_offset = start_offset; + + snapshot_id = nla_get_u32(attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]); + snapshot = devlink_region_snapshot_get_by_id(region, snapshot_id); + if (!snapshot) + return -EINVAL; + + while (curr_offset < end_offset) { + u32 data_size; + u8 *data; + + if (end_offset - curr_offset < DEVLINK_REGION_READ_CHUNK_SIZE) + data_size = end_offset - curr_offset; + else + data_size = DEVLINK_REGION_READ_CHUNK_SIZE; + + data = &snapshot->data[curr_offset]; + err = devlink_nl_cmd_region_read_chunk_fill(skb, devlink, + data, data_size, + curr_offset); + if (err) + break; + + curr_offset += data_size; + } + *new_offset = curr_offset; + + return err; +} + +static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, + struct netlink_callback *cb) +{ + const struct genl_dumpit_info *info = genl_dumpit_info(cb); + u64 ret_offset, start_offset, end_offset = U64_MAX; + struct nlattr **attrs = info->attrs; + struct devlink_port *port = NULL; + struct devlink_region *region; + struct nlattr *chunks_attr; + const char *region_name; + struct devlink *devlink; + unsigned int index; + void *hdr; + int err; + + start_offset = *((u64 *)&cb->args[0]); + + devlink = devlink_get_from_attrs(sock_net(cb->skb->sk), attrs); + if (IS_ERR(devlink)) + return PTR_ERR(devlink); + + devl_lock(devlink); + + if (!attrs[DEVLINK_ATTR_REGION_NAME] || + !attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]) { + err = -EINVAL; + goto out_unlock; + } + + if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) { + index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); + + port = devlink_port_get_by_index(devlink, index); + if (!port) { + err = -ENODEV; + goto out_unlock; + } + } + + region_name = nla_data(attrs[DEVLINK_ATTR_REGION_NAME]); + + if (port) + region = devlink_port_region_get_by_name(port, region_name); + else + region = devlink_region_get_by_name(devlink, region_name); + + if (!region) { + err = -EINVAL; + goto out_unlock; + } + + if (attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR] && + attrs[DEVLINK_ATTR_REGION_CHUNK_LEN]) { + if (!start_offset) + start_offset = + nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR]); + + end_offset = nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR]); + end_offset += nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_LEN]); + } + + if (end_offset > region->size) + end_offset = region->size; + + /* return 0 if there is no further data to read */ + if (start_offset == end_offset) { + err = 0; + goto out_unlock; + } + + hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + &devlink_nl_family, NLM_F_ACK | NLM_F_MULTI, + DEVLINK_CMD_REGION_READ); + if (!hdr) { + err = -EMSGSIZE; + goto out_unlock; + } + + err = devlink_nl_put_handle(skb, devlink); + if (err) + goto nla_put_failure; + + if (region->port) { + err = nla_put_u32(skb, DEVLINK_ATTR_PORT_INDEX, + region->port->index); + if (err) + goto nla_put_failure; + } + + err = nla_put_string(skb, DEVLINK_ATTR_REGION_NAME, region_name); + if (err) + goto nla_put_failure; + + chunks_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_REGION_CHUNKS); + if (!chunks_attr) { + err = -EMSGSIZE; + goto nla_put_failure; + } + + err = devlink_nl_region_read_snapshot_fill(skb, devlink, + region, attrs, + start_offset, + end_offset, &ret_offset); + + if (err && err != -EMSGSIZE) + goto nla_put_failure; + + /* Check if there was any progress done to prevent infinite loop */ + if (ret_offset == start_offset) { + err = -EINVAL; + goto nla_put_failure; + } + + *((u64 *)&cb->args[0]) = ret_offset; + + nla_nest_end(skb, chunks_attr); + genlmsg_end(skb, hdr); + devl_unlock(devlink); + devlink_put(devlink); + return skb->len; + +nla_put_failure: + genlmsg_cancel(skb, hdr); +out_unlock: + devl_unlock(devlink); + devlink_put(devlink); + return err; +} + +int devlink_info_driver_name_put(struct devlink_info_req *req, const char *name) +{ + if (!req->msg) + return 0; + return nla_put_string(req->msg, DEVLINK_ATTR_INFO_DRIVER_NAME, name); +} +EXPORT_SYMBOL_GPL(devlink_info_driver_name_put); + +int devlink_info_serial_number_put(struct devlink_info_req *req, const char *sn) +{ + if (!req->msg) + return 0; + return nla_put_string(req->msg, DEVLINK_ATTR_INFO_SERIAL_NUMBER, sn); +} +EXPORT_SYMBOL_GPL(devlink_info_serial_number_put); + +int devlink_info_board_serial_number_put(struct devlink_info_req *req, + const char *bsn) +{ + if (!req->msg) + return 0; + return nla_put_string(req->msg, DEVLINK_ATTR_INFO_BOARD_SERIAL_NUMBER, + bsn); +} +EXPORT_SYMBOL_GPL(devlink_info_board_serial_number_put); + +static int devlink_info_version_put(struct devlink_info_req *req, int attr, + const char *version_name, + const char *version_value, + enum devlink_info_version_type version_type) +{ + struct nlattr *nest; + int err; + + if (req->version_cb) + req->version_cb(version_name, version_type, + req->version_cb_priv); + + if (!req->msg) + return 0; + + nest = nla_nest_start_noflag(req->msg, attr); + if (!nest) + return -EMSGSIZE; + + err = nla_put_string(req->msg, DEVLINK_ATTR_INFO_VERSION_NAME, + version_name); + if (err) + goto nla_put_failure; + + err = nla_put_string(req->msg, DEVLINK_ATTR_INFO_VERSION_VALUE, + version_value); + if (err) + goto nla_put_failure; + + nla_nest_end(req->msg, nest); + + return 0; + +nla_put_failure: + nla_nest_cancel(req->msg, nest); + return err; +} + +int devlink_info_version_fixed_put(struct devlink_info_req *req, + const char *version_name, + const char *version_value) +{ + return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_FIXED, + version_name, version_value, + DEVLINK_INFO_VERSION_TYPE_NONE); +} +EXPORT_SYMBOL_GPL(devlink_info_version_fixed_put); + +int devlink_info_version_stored_put(struct devlink_info_req *req, + const char *version_name, + const char *version_value) +{ + return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_STORED, + version_name, version_value, + DEVLINK_INFO_VERSION_TYPE_NONE); +} +EXPORT_SYMBOL_GPL(devlink_info_version_stored_put); + +int devlink_info_version_stored_put_ext(struct devlink_info_req *req, + const char *version_name, + const char *version_value, + enum devlink_info_version_type version_type) +{ + return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_STORED, + version_name, version_value, + version_type); +} +EXPORT_SYMBOL_GPL(devlink_info_version_stored_put_ext); + +int devlink_info_version_running_put(struct devlink_info_req *req, + const char *version_name, + const char *version_value) +{ + return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_RUNNING, + version_name, version_value, + DEVLINK_INFO_VERSION_TYPE_NONE); +} +EXPORT_SYMBOL_GPL(devlink_info_version_running_put); + +int devlink_info_version_running_put_ext(struct devlink_info_req *req, + const char *version_name, + const char *version_value, + enum devlink_info_version_type version_type) +{ + return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_RUNNING, + version_name, version_value, + version_type); +} +EXPORT_SYMBOL_GPL(devlink_info_version_running_put_ext); + +static int +devlink_nl_info_fill(struct sk_buff *msg, struct devlink *devlink, + enum devlink_command cmd, u32 portid, + u32 seq, int flags, struct netlink_ext_ack *extack) +{ + struct devlink_info_req req = {}; + void *hdr; + int err; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + err = -EMSGSIZE; + if (devlink_nl_put_handle(msg, devlink)) + goto err_cancel_msg; + + req.msg = msg; + err = devlink->ops->info_get(devlink, &req, extack); + if (err) + goto err_cancel_msg; + + genlmsg_end(msg, hdr); + return 0; + +err_cancel_msg: + genlmsg_cancel(msg, hdr); + return err; +} + +static int devlink_nl_cmd_info_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct sk_buff *msg; + int err; + + if (!devlink->ops->info_get) + return -EOPNOTSUPP; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_info_fill(msg, devlink, DEVLINK_CMD_INFO_GET, + info->snd_portid, info->snd_seq, 0, + info->extack); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +static int devlink_nl_cmd_info_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + struct devlink *devlink; + int start = cb->args[0]; + unsigned long index; + int idx = 0; + int err = 0; + + devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { + if (idx < start || !devlink->ops->info_get) + goto inc; + + devl_lock(devlink); + err = devlink_nl_info_fill(msg, devlink, DEVLINK_CMD_INFO_GET, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, + cb->extack); + devl_unlock(devlink); + if (err == -EOPNOTSUPP) + err = 0; + else if (err) { + devlink_put(devlink); + break; + } +inc: + idx++; + devlink_put(devlink); + } + + if (err != -EMSGSIZE) + return err; + + cb->args[0] = idx; + return msg->len; +} + +struct devlink_fmsg_item { + struct list_head list; + int attrtype; + u8 nla_type; + u16 len; + int value[]; +}; + +struct devlink_fmsg { + struct list_head item_list; + bool putting_binary; /* This flag forces enclosing of binary data + * in an array brackets. It forces using + * of designated API: + * devlink_fmsg_binary_pair_nest_start() + * devlink_fmsg_binary_pair_nest_end() + */ +}; + +static struct devlink_fmsg *devlink_fmsg_alloc(void) +{ + struct devlink_fmsg *fmsg; + + fmsg = kzalloc(sizeof(*fmsg), GFP_KERNEL); + if (!fmsg) + return NULL; + + INIT_LIST_HEAD(&fmsg->item_list); + + return fmsg; +} + +static void devlink_fmsg_free(struct devlink_fmsg *fmsg) +{ + struct devlink_fmsg_item *item, *tmp; + + list_for_each_entry_safe(item, tmp, &fmsg->item_list, list) { + list_del(&item->list); + kfree(item); + } + kfree(fmsg); +} + +static int devlink_fmsg_nest_common(struct devlink_fmsg *fmsg, + int attrtype) +{ + struct devlink_fmsg_item *item; + + item = kzalloc(sizeof(*item), GFP_KERNEL); + if (!item) + return -ENOMEM; + + item->attrtype = attrtype; + list_add_tail(&item->list, &fmsg->item_list); + + return 0; +} + +int devlink_fmsg_obj_nest_start(struct devlink_fmsg *fmsg) +{ + if (fmsg->putting_binary) + return -EINVAL; + + return devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_OBJ_NEST_START); +} +EXPORT_SYMBOL_GPL(devlink_fmsg_obj_nest_start); + +static int devlink_fmsg_nest_end(struct devlink_fmsg *fmsg) +{ + if (fmsg->putting_binary) + return -EINVAL; + + return devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_NEST_END); +} + +int devlink_fmsg_obj_nest_end(struct devlink_fmsg *fmsg) +{ + if (fmsg->putting_binary) + return -EINVAL; + + return devlink_fmsg_nest_end(fmsg); +} +EXPORT_SYMBOL_GPL(devlink_fmsg_obj_nest_end); + +#define DEVLINK_FMSG_MAX_SIZE (GENLMSG_DEFAULT_SIZE - GENL_HDRLEN - NLA_HDRLEN) + +static int devlink_fmsg_put_name(struct devlink_fmsg *fmsg, const char *name) +{ + struct devlink_fmsg_item *item; + + if (fmsg->putting_binary) + return -EINVAL; + + if (strlen(name) + 1 > DEVLINK_FMSG_MAX_SIZE) + return -EMSGSIZE; + + item = kzalloc(sizeof(*item) + strlen(name) + 1, GFP_KERNEL); + if (!item) + return -ENOMEM; + + item->nla_type = NLA_NUL_STRING; + item->len = strlen(name) + 1; + item->attrtype = DEVLINK_ATTR_FMSG_OBJ_NAME; + memcpy(&item->value, name, item->len); + list_add_tail(&item->list, &fmsg->item_list); + + return 0; +} + +int devlink_fmsg_pair_nest_start(struct devlink_fmsg *fmsg, const char *name) +{ + int err; + + if (fmsg->putting_binary) + return -EINVAL; + + err = devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_PAIR_NEST_START); + if (err) + return err; + + err = devlink_fmsg_put_name(fmsg, name); + if (err) + return err; + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_fmsg_pair_nest_start); + +int devlink_fmsg_pair_nest_end(struct devlink_fmsg *fmsg) +{ + if (fmsg->putting_binary) + return -EINVAL; + + return devlink_fmsg_nest_end(fmsg); +} +EXPORT_SYMBOL_GPL(devlink_fmsg_pair_nest_end); + +int devlink_fmsg_arr_pair_nest_start(struct devlink_fmsg *fmsg, + const char *name) +{ + int err; + + if (fmsg->putting_binary) + return -EINVAL; + + err = devlink_fmsg_pair_nest_start(fmsg, name); + if (err) + return err; + + err = devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_ARR_NEST_START); + if (err) + return err; + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_fmsg_arr_pair_nest_start); + +int devlink_fmsg_arr_pair_nest_end(struct devlink_fmsg *fmsg) +{ + int err; + + if (fmsg->putting_binary) + return -EINVAL; + + err = devlink_fmsg_nest_end(fmsg); + if (err) + return err; + + err = devlink_fmsg_nest_end(fmsg); + if (err) + return err; + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_fmsg_arr_pair_nest_end); + +int devlink_fmsg_binary_pair_nest_start(struct devlink_fmsg *fmsg, + const char *name) +{ + int err; + + err = devlink_fmsg_arr_pair_nest_start(fmsg, name); + if (err) + return err; + + fmsg->putting_binary = true; + return err; +} +EXPORT_SYMBOL_GPL(devlink_fmsg_binary_pair_nest_start); + +int devlink_fmsg_binary_pair_nest_end(struct devlink_fmsg *fmsg) +{ + if (!fmsg->putting_binary) + return -EINVAL; + + fmsg->putting_binary = false; + return devlink_fmsg_arr_pair_nest_end(fmsg); +} +EXPORT_SYMBOL_GPL(devlink_fmsg_binary_pair_nest_end); + +static int devlink_fmsg_put_value(struct devlink_fmsg *fmsg, + const void *value, u16 value_len, + u8 value_nla_type) +{ + struct devlink_fmsg_item *item; + + if (value_len > DEVLINK_FMSG_MAX_SIZE) + return -EMSGSIZE; + + item = kzalloc(sizeof(*item) + value_len, GFP_KERNEL); + if (!item) + return -ENOMEM; + + item->nla_type = value_nla_type; + item->len = value_len; + item->attrtype = DEVLINK_ATTR_FMSG_OBJ_VALUE_DATA; + memcpy(&item->value, value, item->len); + list_add_tail(&item->list, &fmsg->item_list); + + return 0; +} + +static int devlink_fmsg_bool_put(struct devlink_fmsg *fmsg, bool value) +{ + if (fmsg->putting_binary) + return -EINVAL; + + return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_FLAG); +} + +static int devlink_fmsg_u8_put(struct devlink_fmsg *fmsg, u8 value) +{ + if (fmsg->putting_binary) + return -EINVAL; + + return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U8); +} + +int devlink_fmsg_u32_put(struct devlink_fmsg *fmsg, u32 value) +{ + if (fmsg->putting_binary) + return -EINVAL; + + return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U32); +} +EXPORT_SYMBOL_GPL(devlink_fmsg_u32_put); + +static int devlink_fmsg_u64_put(struct devlink_fmsg *fmsg, u64 value) +{ + if (fmsg->putting_binary) + return -EINVAL; + + return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U64); +} + +int devlink_fmsg_string_put(struct devlink_fmsg *fmsg, const char *value) +{ + if (fmsg->putting_binary) + return -EINVAL; + + return devlink_fmsg_put_value(fmsg, value, strlen(value) + 1, + NLA_NUL_STRING); +} +EXPORT_SYMBOL_GPL(devlink_fmsg_string_put); + +int devlink_fmsg_binary_put(struct devlink_fmsg *fmsg, const void *value, + u16 value_len) +{ + if (!fmsg->putting_binary) + return -EINVAL; + + return devlink_fmsg_put_value(fmsg, value, value_len, NLA_BINARY); +} +EXPORT_SYMBOL_GPL(devlink_fmsg_binary_put); + +int devlink_fmsg_bool_pair_put(struct devlink_fmsg *fmsg, const char *name, + bool value) +{ + int err; + + err = devlink_fmsg_pair_nest_start(fmsg, name); + if (err) + return err; + + err = devlink_fmsg_bool_put(fmsg, value); + if (err) + return err; + + err = devlink_fmsg_pair_nest_end(fmsg); + if (err) + return err; + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_fmsg_bool_pair_put); + +int devlink_fmsg_u8_pair_put(struct devlink_fmsg *fmsg, const char *name, + u8 value) +{ + int err; + + err = devlink_fmsg_pair_nest_start(fmsg, name); + if (err) + return err; + + err = devlink_fmsg_u8_put(fmsg, value); + if (err) + return err; + + err = devlink_fmsg_pair_nest_end(fmsg); + if (err) + return err; + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_fmsg_u8_pair_put); + +int devlink_fmsg_u32_pair_put(struct devlink_fmsg *fmsg, const char *name, + u32 value) +{ + int err; + + err = devlink_fmsg_pair_nest_start(fmsg, name); + if (err) + return err; + + err = devlink_fmsg_u32_put(fmsg, value); + if (err) + return err; + + err = devlink_fmsg_pair_nest_end(fmsg); + if (err) + return err; + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_fmsg_u32_pair_put); + +int devlink_fmsg_u64_pair_put(struct devlink_fmsg *fmsg, const char *name, + u64 value) +{ + int err; + + err = devlink_fmsg_pair_nest_start(fmsg, name); + if (err) + return err; + + err = devlink_fmsg_u64_put(fmsg, value); + if (err) + return err; + + err = devlink_fmsg_pair_nest_end(fmsg); + if (err) + return err; + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_fmsg_u64_pair_put); + +int devlink_fmsg_string_pair_put(struct devlink_fmsg *fmsg, const char *name, + const char *value) +{ + int err; + + err = devlink_fmsg_pair_nest_start(fmsg, name); + if (err) + return err; + + err = devlink_fmsg_string_put(fmsg, value); + if (err) + return err; + + err = devlink_fmsg_pair_nest_end(fmsg); + if (err) + return err; + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_fmsg_string_pair_put); + +int devlink_fmsg_binary_pair_put(struct devlink_fmsg *fmsg, const char *name, + const void *value, u32 value_len) +{ + u32 data_size; + int end_err; + u32 offset; + int err; + + err = devlink_fmsg_binary_pair_nest_start(fmsg, name); + if (err) + return err; + + for (offset = 0; offset < value_len; offset += data_size) { + data_size = value_len - offset; + if (data_size > DEVLINK_FMSG_MAX_SIZE) + data_size = DEVLINK_FMSG_MAX_SIZE; + err = devlink_fmsg_binary_put(fmsg, value + offset, data_size); + if (err) + break; + /* Exit from loop with a break (instead of + * return) to make sure putting_binary is turned off in + * devlink_fmsg_binary_pair_nest_end + */ + } + + end_err = devlink_fmsg_binary_pair_nest_end(fmsg); + if (end_err) + err = end_err; + + return err; +} +EXPORT_SYMBOL_GPL(devlink_fmsg_binary_pair_put); + +static int +devlink_fmsg_item_fill_type(struct devlink_fmsg_item *msg, struct sk_buff *skb) +{ + switch (msg->nla_type) { + case NLA_FLAG: + case NLA_U8: + case NLA_U32: + case NLA_U64: + case NLA_NUL_STRING: + case NLA_BINARY: + return nla_put_u8(skb, DEVLINK_ATTR_FMSG_OBJ_VALUE_TYPE, + msg->nla_type); + default: + return -EINVAL; + } +} + +static int +devlink_fmsg_item_fill_data(struct devlink_fmsg_item *msg, struct sk_buff *skb) +{ + int attrtype = DEVLINK_ATTR_FMSG_OBJ_VALUE_DATA; + u8 tmp; + + switch (msg->nla_type) { + case NLA_FLAG: + /* Always provide flag data, regardless of its value */ + tmp = *(bool *) msg->value; + + return nla_put_u8(skb, attrtype, tmp); + case NLA_U8: + return nla_put_u8(skb, attrtype, *(u8 *) msg->value); + case NLA_U32: + return nla_put_u32(skb, attrtype, *(u32 *) msg->value); + case NLA_U64: + return nla_put_u64_64bit(skb, attrtype, *(u64 *) msg->value, + DEVLINK_ATTR_PAD); + case NLA_NUL_STRING: + return nla_put_string(skb, attrtype, (char *) &msg->value); + case NLA_BINARY: + return nla_put(skb, attrtype, msg->len, (void *) &msg->value); + default: + return -EINVAL; + } +} + +static int +devlink_fmsg_prepare_skb(struct devlink_fmsg *fmsg, struct sk_buff *skb, + int *start) +{ + struct devlink_fmsg_item *item; + struct nlattr *fmsg_nlattr; + int i = 0; + int err; + + fmsg_nlattr = nla_nest_start_noflag(skb, DEVLINK_ATTR_FMSG); + if (!fmsg_nlattr) + return -EMSGSIZE; + + list_for_each_entry(item, &fmsg->item_list, list) { + if (i < *start) { + i++; + continue; + } + + switch (item->attrtype) { + case DEVLINK_ATTR_FMSG_OBJ_NEST_START: + case DEVLINK_ATTR_FMSG_PAIR_NEST_START: + case DEVLINK_ATTR_FMSG_ARR_NEST_START: + case DEVLINK_ATTR_FMSG_NEST_END: + err = nla_put_flag(skb, item->attrtype); + break; + case DEVLINK_ATTR_FMSG_OBJ_VALUE_DATA: + err = devlink_fmsg_item_fill_type(item, skb); + if (err) + break; + err = devlink_fmsg_item_fill_data(item, skb); + break; + case DEVLINK_ATTR_FMSG_OBJ_NAME: + err = nla_put_string(skb, item->attrtype, + (char *) &item->value); + break; + default: + err = -EINVAL; + break; + } + if (!err) + *start = ++i; + else + break; + } + + nla_nest_end(skb, fmsg_nlattr); + return err; +} + +static int devlink_fmsg_snd(struct devlink_fmsg *fmsg, + struct genl_info *info, + enum devlink_command cmd, int flags) +{ + struct nlmsghdr *nlh; + struct sk_buff *skb; + bool last = false; + int index = 0; + void *hdr; + int err; + + while (!last) { + int tmp_index = index; + + skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!skb) + return -ENOMEM; + + hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq, + &devlink_nl_family, flags | NLM_F_MULTI, cmd); + if (!hdr) { + err = -EMSGSIZE; + goto nla_put_failure; + } + + err = devlink_fmsg_prepare_skb(fmsg, skb, &index); + if (!err) + last = true; + else if (err != -EMSGSIZE || tmp_index == index) + goto nla_put_failure; + + genlmsg_end(skb, hdr); + err = genlmsg_reply(skb, info); + if (err) + return err; + } + + skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!skb) + return -ENOMEM; + nlh = nlmsg_put(skb, info->snd_portid, info->snd_seq, + NLMSG_DONE, 0, flags | NLM_F_MULTI); + if (!nlh) { + err = -EMSGSIZE; + goto nla_put_failure; + } + + return genlmsg_reply(skb, info); + +nla_put_failure: + nlmsg_free(skb); + return err; +} + +static int devlink_fmsg_dumpit(struct devlink_fmsg *fmsg, struct sk_buff *skb, + struct netlink_callback *cb, + enum devlink_command cmd) +{ + int index = cb->args[0]; + int tmp_index = index; + void *hdr; + int err; + + hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + &devlink_nl_family, NLM_F_ACK | NLM_F_MULTI, cmd); + if (!hdr) { + err = -EMSGSIZE; + goto nla_put_failure; + } + + err = devlink_fmsg_prepare_skb(fmsg, skb, &index); + if ((err && err != -EMSGSIZE) || tmp_index == index) + goto nla_put_failure; + + cb->args[0] = index; + genlmsg_end(skb, hdr); + return skb->len; + +nla_put_failure: + genlmsg_cancel(skb, hdr); + return err; +} + +struct devlink_health_reporter { + struct list_head list; + void *priv; + const struct devlink_health_reporter_ops *ops; + struct devlink *devlink; + struct devlink_port *devlink_port; + struct devlink_fmsg *dump_fmsg; + struct mutex dump_lock; /* lock parallel read/write from dump buffers */ + u64 graceful_period; + bool auto_recover; + bool auto_dump; + u8 health_state; + u64 dump_ts; + u64 dump_real_ts; + u64 error_count; + u64 recovery_count; + u64 last_recovery_ts; + refcount_t refcount; +}; + +void * +devlink_health_reporter_priv(struct devlink_health_reporter *reporter) +{ + return reporter->priv; +} +EXPORT_SYMBOL_GPL(devlink_health_reporter_priv); + +static struct devlink_health_reporter * +__devlink_health_reporter_find_by_name(struct list_head *reporter_list, + struct mutex *list_lock, + const char *reporter_name) +{ + struct devlink_health_reporter *reporter; + + lockdep_assert_held(list_lock); + list_for_each_entry(reporter, reporter_list, list) + if (!strcmp(reporter->ops->name, reporter_name)) + return reporter; + return NULL; +} + +static struct devlink_health_reporter * +devlink_health_reporter_find_by_name(struct devlink *devlink, + const char *reporter_name) +{ + return __devlink_health_reporter_find_by_name(&devlink->reporter_list, + &devlink->reporters_lock, + reporter_name); +} + +static struct devlink_health_reporter * +devlink_port_health_reporter_find_by_name(struct devlink_port *devlink_port, + const char *reporter_name) +{ + return __devlink_health_reporter_find_by_name(&devlink_port->reporter_list, + &devlink_port->reporters_lock, + reporter_name); +} + +static struct devlink_health_reporter * +__devlink_health_reporter_create(struct devlink *devlink, + const struct devlink_health_reporter_ops *ops, + u64 graceful_period, void *priv) +{ + struct devlink_health_reporter *reporter; + + if (WARN_ON(graceful_period && !ops->recover)) + return ERR_PTR(-EINVAL); + + reporter = kzalloc(sizeof(*reporter), GFP_KERNEL); + if (!reporter) + return ERR_PTR(-ENOMEM); + + reporter->priv = priv; + reporter->ops = ops; + reporter->devlink = devlink; + reporter->graceful_period = graceful_period; + reporter->auto_recover = !!ops->recover; + reporter->auto_dump = !!ops->dump; + mutex_init(&reporter->dump_lock); + refcount_set(&reporter->refcount, 1); + return reporter; +} + +/** + * devlink_port_health_reporter_create - create devlink health reporter for + * specified port instance + * + * @port: devlink_port which should contain the new reporter + * @ops: ops + * @graceful_period: to avoid recovery loops, in msecs + * @priv: priv + */ +struct devlink_health_reporter * +devlink_port_health_reporter_create(struct devlink_port *port, + const struct devlink_health_reporter_ops *ops, + u64 graceful_period, void *priv) +{ + struct devlink_health_reporter *reporter; + + mutex_lock(&port->reporters_lock); + if (__devlink_health_reporter_find_by_name(&port->reporter_list, + &port->reporters_lock, ops->name)) { + reporter = ERR_PTR(-EEXIST); + goto unlock; + } + + reporter = __devlink_health_reporter_create(port->devlink, ops, + graceful_period, priv); + if (IS_ERR(reporter)) + goto unlock; + + reporter->devlink_port = port; + list_add_tail(&reporter->list, &port->reporter_list); +unlock: + mutex_unlock(&port->reporters_lock); + return reporter; +} +EXPORT_SYMBOL_GPL(devlink_port_health_reporter_create); + +/** + * devlink_health_reporter_create - create devlink health reporter + * + * @devlink: devlink + * @ops: ops + * @graceful_period: to avoid recovery loops, in msecs + * @priv: priv + */ +struct devlink_health_reporter * +devlink_health_reporter_create(struct devlink *devlink, + const struct devlink_health_reporter_ops *ops, + u64 graceful_period, void *priv) +{ + struct devlink_health_reporter *reporter; + + mutex_lock(&devlink->reporters_lock); + if (devlink_health_reporter_find_by_name(devlink, ops->name)) { + reporter = ERR_PTR(-EEXIST); + goto unlock; + } + + reporter = __devlink_health_reporter_create(devlink, ops, + graceful_period, priv); + if (IS_ERR(reporter)) + goto unlock; + + list_add_tail(&reporter->list, &devlink->reporter_list); +unlock: + mutex_unlock(&devlink->reporters_lock); + return reporter; +} +EXPORT_SYMBOL_GPL(devlink_health_reporter_create); + +static void +devlink_health_reporter_free(struct devlink_health_reporter *reporter) +{ + mutex_destroy(&reporter->dump_lock); + if (reporter->dump_fmsg) + devlink_fmsg_free(reporter->dump_fmsg); + kfree(reporter); +} + +static void +devlink_health_reporter_put(struct devlink_health_reporter *reporter) +{ + if (refcount_dec_and_test(&reporter->refcount)) + devlink_health_reporter_free(reporter); +} + +static void +__devlink_health_reporter_destroy(struct devlink_health_reporter *reporter) +{ + list_del(&reporter->list); + devlink_health_reporter_put(reporter); +} + +/** + * devlink_health_reporter_destroy - destroy devlink health reporter + * + * @reporter: devlink health reporter to destroy + */ +void +devlink_health_reporter_destroy(struct devlink_health_reporter *reporter) +{ + struct mutex *lock = &reporter->devlink->reporters_lock; + + mutex_lock(lock); + __devlink_health_reporter_destroy(reporter); + mutex_unlock(lock); +} +EXPORT_SYMBOL_GPL(devlink_health_reporter_destroy); + +/** + * devlink_port_health_reporter_destroy - destroy devlink port health reporter + * + * @reporter: devlink health reporter to destroy + */ +void +devlink_port_health_reporter_destroy(struct devlink_health_reporter *reporter) +{ + struct mutex *lock = &reporter->devlink_port->reporters_lock; + + mutex_lock(lock); + __devlink_health_reporter_destroy(reporter); + mutex_unlock(lock); +} +EXPORT_SYMBOL_GPL(devlink_port_health_reporter_destroy); + +static int +devlink_nl_health_reporter_fill(struct sk_buff *msg, + struct devlink_health_reporter *reporter, + enum devlink_command cmd, u32 portid, + u32 seq, int flags) +{ + struct devlink *devlink = reporter->devlink; + struct nlattr *reporter_attr; + void *hdr; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + if (devlink_nl_put_handle(msg, devlink)) + goto genlmsg_cancel; + + if (reporter->devlink_port) { + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, reporter->devlink_port->index)) + goto genlmsg_cancel; + } + reporter_attr = nla_nest_start_noflag(msg, + DEVLINK_ATTR_HEALTH_REPORTER); + if (!reporter_attr) + goto genlmsg_cancel; + if (nla_put_string(msg, DEVLINK_ATTR_HEALTH_REPORTER_NAME, + reporter->ops->name)) + goto reporter_nest_cancel; + if (nla_put_u8(msg, DEVLINK_ATTR_HEALTH_REPORTER_STATE, + reporter->health_state)) + goto reporter_nest_cancel; + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_ERR_COUNT, + reporter->error_count, DEVLINK_ATTR_PAD)) + goto reporter_nest_cancel; + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_RECOVER_COUNT, + reporter->recovery_count, DEVLINK_ATTR_PAD)) + goto reporter_nest_cancel; + if (reporter->ops->recover && + nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD, + reporter->graceful_period, + DEVLINK_ATTR_PAD)) + goto reporter_nest_cancel; + if (reporter->ops->recover && + nla_put_u8(msg, DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER, + reporter->auto_recover)) + goto reporter_nest_cancel; + if (reporter->dump_fmsg && + nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS, + jiffies_to_msecs(reporter->dump_ts), + DEVLINK_ATTR_PAD)) + goto reporter_nest_cancel; + if (reporter->dump_fmsg && + nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS_NS, + reporter->dump_real_ts, DEVLINK_ATTR_PAD)) + goto reporter_nest_cancel; + if (reporter->ops->dump && + nla_put_u8(msg, DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP, + reporter->auto_dump)) + goto reporter_nest_cancel; + + nla_nest_end(msg, reporter_attr); + genlmsg_end(msg, hdr); + return 0; + +reporter_nest_cancel: + nla_nest_end(msg, reporter_attr); +genlmsg_cancel: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static void devlink_recover_notify(struct devlink_health_reporter *reporter, + enum devlink_command cmd) +{ + struct devlink *devlink = reporter->devlink; + struct sk_buff *msg; + int err; + + WARN_ON(cmd != DEVLINK_CMD_HEALTH_REPORTER_RECOVER); + WARN_ON(!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)); + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + err = devlink_nl_health_reporter_fill(msg, reporter, cmd, 0, 0, 0); + if (err) { + nlmsg_free(msg); + return; + } + + genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), msg, + 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); +} + +void +devlink_health_reporter_recovery_done(struct devlink_health_reporter *reporter) +{ + reporter->recovery_count++; + reporter->last_recovery_ts = jiffies; +} +EXPORT_SYMBOL_GPL(devlink_health_reporter_recovery_done); + +static int +devlink_health_reporter_recover(struct devlink_health_reporter *reporter, + void *priv_ctx, struct netlink_ext_ack *extack) +{ + int err; + + if (reporter->health_state == DEVLINK_HEALTH_REPORTER_STATE_HEALTHY) + return 0; + + if (!reporter->ops->recover) + return -EOPNOTSUPP; + + err = reporter->ops->recover(reporter, priv_ctx, extack); + if (err) + return err; + + devlink_health_reporter_recovery_done(reporter); + reporter->health_state = DEVLINK_HEALTH_REPORTER_STATE_HEALTHY; + devlink_recover_notify(reporter, DEVLINK_CMD_HEALTH_REPORTER_RECOVER); + + return 0; +} + +static void +devlink_health_dump_clear(struct devlink_health_reporter *reporter) +{ + if (!reporter->dump_fmsg) + return; + devlink_fmsg_free(reporter->dump_fmsg); + reporter->dump_fmsg = NULL; +} + +static int devlink_health_do_dump(struct devlink_health_reporter *reporter, + void *priv_ctx, + struct netlink_ext_ack *extack) +{ + int err; + + if (!reporter->ops->dump) + return 0; + + if (reporter->dump_fmsg) + return 0; + + reporter->dump_fmsg = devlink_fmsg_alloc(); + if (!reporter->dump_fmsg) { + err = -ENOMEM; + return err; + } + + err = devlink_fmsg_obj_nest_start(reporter->dump_fmsg); + if (err) + goto dump_err; + + err = reporter->ops->dump(reporter, reporter->dump_fmsg, + priv_ctx, extack); + if (err) + goto dump_err; + + err = devlink_fmsg_obj_nest_end(reporter->dump_fmsg); + if (err) + goto dump_err; + + reporter->dump_ts = jiffies; + reporter->dump_real_ts = ktime_get_real_ns(); + + return 0; + +dump_err: + devlink_health_dump_clear(reporter); + return err; +} + +int devlink_health_report(struct devlink_health_reporter *reporter, + const char *msg, void *priv_ctx) +{ + enum devlink_health_reporter_state prev_health_state; + struct devlink *devlink = reporter->devlink; + unsigned long recover_ts_threshold; + int ret; + + /* write a log message of the current error */ + WARN_ON(!msg); + trace_devlink_health_report(devlink, reporter->ops->name, msg); + reporter->error_count++; + prev_health_state = reporter->health_state; + reporter->health_state = DEVLINK_HEALTH_REPORTER_STATE_ERROR; + devlink_recover_notify(reporter, DEVLINK_CMD_HEALTH_REPORTER_RECOVER); + + /* abort if the previous error wasn't recovered */ + recover_ts_threshold = reporter->last_recovery_ts + + msecs_to_jiffies(reporter->graceful_period); + if (reporter->auto_recover && + (prev_health_state != DEVLINK_HEALTH_REPORTER_STATE_HEALTHY || + (reporter->last_recovery_ts && reporter->recovery_count && + time_is_after_jiffies(recover_ts_threshold)))) { + trace_devlink_health_recover_aborted(devlink, + reporter->ops->name, + reporter->health_state, + jiffies - + reporter->last_recovery_ts); + return -ECANCELED; + } + + reporter->health_state = DEVLINK_HEALTH_REPORTER_STATE_ERROR; + + if (reporter->auto_dump) { + mutex_lock(&reporter->dump_lock); + /* store current dump of current error, for later analysis */ + devlink_health_do_dump(reporter, priv_ctx, NULL); + mutex_unlock(&reporter->dump_lock); + } + + if (!reporter->auto_recover) + return 0; + + devl_lock(devlink); + ret = devlink_health_reporter_recover(reporter, priv_ctx, NULL); + devl_unlock(devlink); + + return ret; +} +EXPORT_SYMBOL_GPL(devlink_health_report); + +static struct devlink_health_reporter * +devlink_health_reporter_get_from_attrs(struct devlink *devlink, + struct nlattr **attrs) +{ + struct devlink_health_reporter *reporter; + struct devlink_port *devlink_port; + char *reporter_name; + + if (!attrs[DEVLINK_ATTR_HEALTH_REPORTER_NAME]) + return NULL; + + reporter_name = nla_data(attrs[DEVLINK_ATTR_HEALTH_REPORTER_NAME]); + devlink_port = devlink_port_get_from_attrs(devlink, attrs); + if (IS_ERR(devlink_port)) { + mutex_lock(&devlink->reporters_lock); + reporter = devlink_health_reporter_find_by_name(devlink, reporter_name); + if (reporter) + refcount_inc(&reporter->refcount); + mutex_unlock(&devlink->reporters_lock); + } else { + mutex_lock(&devlink_port->reporters_lock); + reporter = devlink_port_health_reporter_find_by_name(devlink_port, reporter_name); + if (reporter) + refcount_inc(&reporter->refcount); + mutex_unlock(&devlink_port->reporters_lock); + } + + return reporter; +} + +static struct devlink_health_reporter * +devlink_health_reporter_get_from_info(struct devlink *devlink, + struct genl_info *info) +{ + return devlink_health_reporter_get_from_attrs(devlink, info->attrs); +} + +static struct devlink_health_reporter * +devlink_health_reporter_get_from_cb(struct netlink_callback *cb) +{ + const struct genl_dumpit_info *info = genl_dumpit_info(cb); + struct devlink_health_reporter *reporter; + struct nlattr **attrs = info->attrs; + struct devlink *devlink; + + devlink = devlink_get_from_attrs(sock_net(cb->skb->sk), attrs); + if (IS_ERR(devlink)) + return NULL; + + reporter = devlink_health_reporter_get_from_attrs(devlink, attrs); + devlink_put(devlink); + return reporter; +} + +void +devlink_health_reporter_state_update(struct devlink_health_reporter *reporter, + enum devlink_health_reporter_state state) +{ + if (WARN_ON(state != DEVLINK_HEALTH_REPORTER_STATE_HEALTHY && + state != DEVLINK_HEALTH_REPORTER_STATE_ERROR)) + return; + + if (reporter->health_state == state) + return; + + reporter->health_state = state; + trace_devlink_health_reporter_state_update(reporter->devlink, + reporter->ops->name, state); + devlink_recover_notify(reporter, DEVLINK_CMD_HEALTH_REPORTER_RECOVER); +} +EXPORT_SYMBOL_GPL(devlink_health_reporter_state_update); + +static int devlink_nl_cmd_health_reporter_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_health_reporter *reporter; + struct sk_buff *msg; + int err; + + reporter = devlink_health_reporter_get_from_info(devlink, info); + if (!reporter) + return -EINVAL; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) { + err = -ENOMEM; + goto out; + } + + err = devlink_nl_health_reporter_fill(msg, reporter, + DEVLINK_CMD_HEALTH_REPORTER_GET, + info->snd_portid, info->snd_seq, + 0); + if (err) { + nlmsg_free(msg); + goto out; + } + + err = genlmsg_reply(msg, info); +out: + devlink_health_reporter_put(reporter); + return err; +} + +static int +devlink_nl_cmd_health_reporter_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + struct devlink_health_reporter *reporter; + struct devlink_port *port; + struct devlink *devlink; + int start = cb->args[0]; + unsigned long index; + int idx = 0; + int err; + + devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { + mutex_lock(&devlink->reporters_lock); + list_for_each_entry(reporter, &devlink->reporter_list, + list) { + if (idx < start) { + idx++; + continue; + } + err = devlink_nl_health_reporter_fill( + msg, reporter, DEVLINK_CMD_HEALTH_REPORTER_GET, + NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + NLM_F_MULTI); + if (err) { + mutex_unlock(&devlink->reporters_lock); + devlink_put(devlink); + goto out; + } + idx++; + } + mutex_unlock(&devlink->reporters_lock); + devlink_put(devlink); + } + + devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { + devl_lock(devlink); + list_for_each_entry(port, &devlink->port_list, list) { + mutex_lock(&port->reporters_lock); + list_for_each_entry(reporter, &port->reporter_list, list) { + if (idx < start) { + idx++; + continue; + } + err = devlink_nl_health_reporter_fill( + msg, reporter, + DEVLINK_CMD_HEALTH_REPORTER_GET, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI); + if (err) { + mutex_unlock(&port->reporters_lock); + devl_unlock(devlink); + devlink_put(devlink); + goto out; + } + idx++; + } + mutex_unlock(&port->reporters_lock); + } + devl_unlock(devlink); + devlink_put(devlink); + } +out: + cb->args[0] = idx; + return msg->len; +} + +static int +devlink_nl_cmd_health_reporter_set_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_health_reporter *reporter; + int err; + + reporter = devlink_health_reporter_get_from_info(devlink, info); + if (!reporter) + return -EINVAL; + + if (!reporter->ops->recover && + (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] || + info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER])) { + err = -EOPNOTSUPP; + goto out; + } + if (!reporter->ops->dump && + info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP]) { + err = -EOPNOTSUPP; + goto out; + } + + if (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD]) + reporter->graceful_period = + nla_get_u64(info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD]); + + if (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER]) + reporter->auto_recover = + nla_get_u8(info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER]); + + if (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP]) + reporter->auto_dump = + nla_get_u8(info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP]); + + devlink_health_reporter_put(reporter); + return 0; +out: + devlink_health_reporter_put(reporter); + return err; +} + +static int devlink_nl_cmd_health_reporter_recover_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_health_reporter *reporter; + int err; + + reporter = devlink_health_reporter_get_from_info(devlink, info); + if (!reporter) + return -EINVAL; + + err = devlink_health_reporter_recover(reporter, NULL, info->extack); + + devlink_health_reporter_put(reporter); + return err; +} + +static int devlink_nl_cmd_health_reporter_diagnose_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_health_reporter *reporter; + struct devlink_fmsg *fmsg; + int err; + + reporter = devlink_health_reporter_get_from_info(devlink, info); + if (!reporter) + return -EINVAL; + + if (!reporter->ops->diagnose) { + devlink_health_reporter_put(reporter); + return -EOPNOTSUPP; + } + + fmsg = devlink_fmsg_alloc(); + if (!fmsg) { + devlink_health_reporter_put(reporter); + return -ENOMEM; + } + + err = devlink_fmsg_obj_nest_start(fmsg); + if (err) + goto out; + + err = reporter->ops->diagnose(reporter, fmsg, info->extack); + if (err) + goto out; + + err = devlink_fmsg_obj_nest_end(fmsg); + if (err) + goto out; + + err = devlink_fmsg_snd(fmsg, info, + DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE, 0); + +out: + devlink_fmsg_free(fmsg); + devlink_health_reporter_put(reporter); + return err; +} + +static int +devlink_nl_cmd_health_reporter_dump_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct devlink_health_reporter *reporter; + u64 start = cb->args[0]; + int err; + + reporter = devlink_health_reporter_get_from_cb(cb); + if (!reporter) + return -EINVAL; + + if (!reporter->ops->dump) { + err = -EOPNOTSUPP; + goto out; + } + mutex_lock(&reporter->dump_lock); + if (!start) { + err = devlink_health_do_dump(reporter, NULL, cb->extack); + if (err) + goto unlock; + cb->args[1] = reporter->dump_ts; + } + if (!reporter->dump_fmsg || cb->args[1] != reporter->dump_ts) { + NL_SET_ERR_MSG_MOD(cb->extack, "Dump trampled, please retry"); + err = -EAGAIN; + goto unlock; + } + + err = devlink_fmsg_dumpit(reporter->dump_fmsg, skb, cb, + DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET); +unlock: + mutex_unlock(&reporter->dump_lock); +out: + devlink_health_reporter_put(reporter); + return err; +} + +static int +devlink_nl_cmd_health_reporter_dump_clear_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_health_reporter *reporter; + + reporter = devlink_health_reporter_get_from_info(devlink, info); + if (!reporter) + return -EINVAL; + + if (!reporter->ops->dump) { + devlink_health_reporter_put(reporter); + return -EOPNOTSUPP; + } + + mutex_lock(&reporter->dump_lock); + devlink_health_dump_clear(reporter); + mutex_unlock(&reporter->dump_lock); + devlink_health_reporter_put(reporter); + return 0; +} + +static int devlink_nl_cmd_health_reporter_test_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_health_reporter *reporter; + int err; + + reporter = devlink_health_reporter_get_from_info(devlink, info); + if (!reporter) + return -EINVAL; + + if (!reporter->ops->test) { + devlink_health_reporter_put(reporter); + return -EOPNOTSUPP; + } + + err = reporter->ops->test(reporter, info->extack); + + devlink_health_reporter_put(reporter); + return err; +} + +struct devlink_stats { + u64_stats_t rx_bytes; + u64_stats_t rx_packets; + struct u64_stats_sync syncp; +}; + +/** + * struct devlink_trap_policer_item - Packet trap policer attributes. + * @policer: Immutable packet trap policer attributes. + * @rate: Rate in packets / sec. + * @burst: Burst size in packets. + * @list: trap_policer_list member. + * + * Describes packet trap policer attributes. Created by devlink during trap + * policer registration. + */ +struct devlink_trap_policer_item { + const struct devlink_trap_policer *policer; + u64 rate; + u64 burst; + struct list_head list; +}; + +/** + * struct devlink_trap_group_item - Packet trap group attributes. + * @group: Immutable packet trap group attributes. + * @policer_item: Associated policer item. Can be NULL. + * @list: trap_group_list member. + * @stats: Trap group statistics. + * + * Describes packet trap group attributes. Created by devlink during trap + * group registration. + */ +struct devlink_trap_group_item { + const struct devlink_trap_group *group; + struct devlink_trap_policer_item *policer_item; + struct list_head list; + struct devlink_stats __percpu *stats; +}; + +/** + * struct devlink_trap_item - Packet trap attributes. + * @trap: Immutable packet trap attributes. + * @group_item: Associated group item. + * @list: trap_list member. + * @action: Trap action. + * @stats: Trap statistics. + * @priv: Driver private information. + * + * Describes both mutable and immutable packet trap attributes. Created by + * devlink during trap registration and used for all trap related operations. + */ +struct devlink_trap_item { + const struct devlink_trap *trap; + struct devlink_trap_group_item *group_item; + struct list_head list; + enum devlink_trap_action action; + struct devlink_stats __percpu *stats; + void *priv; +}; + +static struct devlink_trap_policer_item * +devlink_trap_policer_item_lookup(struct devlink *devlink, u32 id) +{ + struct devlink_trap_policer_item *policer_item; + + list_for_each_entry(policer_item, &devlink->trap_policer_list, list) { + if (policer_item->policer->id == id) + return policer_item; + } + + return NULL; +} + +static struct devlink_trap_item * +devlink_trap_item_lookup(struct devlink *devlink, const char *name) +{ + struct devlink_trap_item *trap_item; + + list_for_each_entry(trap_item, &devlink->trap_list, list) { + if (!strcmp(trap_item->trap->name, name)) + return trap_item; + } + + return NULL; +} + +static struct devlink_trap_item * +devlink_trap_item_get_from_info(struct devlink *devlink, + struct genl_info *info) +{ + struct nlattr *attr; + + if (!info->attrs[DEVLINK_ATTR_TRAP_NAME]) + return NULL; + attr = info->attrs[DEVLINK_ATTR_TRAP_NAME]; + + return devlink_trap_item_lookup(devlink, nla_data(attr)); +} + +static int +devlink_trap_action_get_from_info(struct genl_info *info, + enum devlink_trap_action *p_trap_action) +{ + u8 val; + + val = nla_get_u8(info->attrs[DEVLINK_ATTR_TRAP_ACTION]); + switch (val) { + case DEVLINK_TRAP_ACTION_DROP: + case DEVLINK_TRAP_ACTION_TRAP: + case DEVLINK_TRAP_ACTION_MIRROR: + *p_trap_action = val; + break; + default: + return -EINVAL; + } + + return 0; +} + +static int devlink_trap_metadata_put(struct sk_buff *msg, + const struct devlink_trap *trap) +{ + struct nlattr *attr; + + attr = nla_nest_start(msg, DEVLINK_ATTR_TRAP_METADATA); + if (!attr) + return -EMSGSIZE; + + if ((trap->metadata_cap & DEVLINK_TRAP_METADATA_TYPE_F_IN_PORT) && + nla_put_flag(msg, DEVLINK_ATTR_TRAP_METADATA_TYPE_IN_PORT)) + goto nla_put_failure; + if ((trap->metadata_cap & DEVLINK_TRAP_METADATA_TYPE_F_FA_COOKIE) && + nla_put_flag(msg, DEVLINK_ATTR_TRAP_METADATA_TYPE_FA_COOKIE)) + goto nla_put_failure; + + nla_nest_end(msg, attr); + + return 0; + +nla_put_failure: + nla_nest_cancel(msg, attr); + return -EMSGSIZE; +} + +static void devlink_trap_stats_read(struct devlink_stats __percpu *trap_stats, + struct devlink_stats *stats) +{ + int i; + + memset(stats, 0, sizeof(*stats)); + for_each_possible_cpu(i) { + struct devlink_stats *cpu_stats; + u64 rx_packets, rx_bytes; + unsigned int start; + + cpu_stats = per_cpu_ptr(trap_stats, i); + do { + start = u64_stats_fetch_begin_irq(&cpu_stats->syncp); + rx_packets = u64_stats_read(&cpu_stats->rx_packets); + rx_bytes = u64_stats_read(&cpu_stats->rx_bytes); + } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start)); + + u64_stats_add(&stats->rx_packets, rx_packets); + u64_stats_add(&stats->rx_bytes, rx_bytes); + } +} + +static int +devlink_trap_group_stats_put(struct sk_buff *msg, + struct devlink_stats __percpu *trap_stats) +{ + struct devlink_stats stats; + struct nlattr *attr; + + devlink_trap_stats_read(trap_stats, &stats); + + attr = nla_nest_start(msg, DEVLINK_ATTR_STATS); + if (!attr) + return -EMSGSIZE; + + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_PACKETS, + u64_stats_read(&stats.rx_packets), + DEVLINK_ATTR_PAD)) + goto nla_put_failure; + + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_BYTES, + u64_stats_read(&stats.rx_bytes), + DEVLINK_ATTR_PAD)) + goto nla_put_failure; + + nla_nest_end(msg, attr); + + return 0; + +nla_put_failure: + nla_nest_cancel(msg, attr); + return -EMSGSIZE; +} + +static int devlink_trap_stats_put(struct sk_buff *msg, struct devlink *devlink, + const struct devlink_trap_item *trap_item) +{ + struct devlink_stats stats; + struct nlattr *attr; + u64 drops = 0; + int err; + + if (devlink->ops->trap_drop_counter_get) { + err = devlink->ops->trap_drop_counter_get(devlink, + trap_item->trap, + &drops); + if (err) + return err; + } + + devlink_trap_stats_read(trap_item->stats, &stats); + + attr = nla_nest_start(msg, DEVLINK_ATTR_STATS); + if (!attr) + return -EMSGSIZE; + + if (devlink->ops->trap_drop_counter_get && + nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_DROPPED, drops, + DEVLINK_ATTR_PAD)) + goto nla_put_failure; + + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_PACKETS, + u64_stats_read(&stats.rx_packets), + DEVLINK_ATTR_PAD)) + goto nla_put_failure; + + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_BYTES, + u64_stats_read(&stats.rx_bytes), + DEVLINK_ATTR_PAD)) + goto nla_put_failure; + + nla_nest_end(msg, attr); + + return 0; + +nla_put_failure: + nla_nest_cancel(msg, attr); + return -EMSGSIZE; +} + +static int devlink_nl_trap_fill(struct sk_buff *msg, struct devlink *devlink, + const struct devlink_trap_item *trap_item, + enum devlink_command cmd, u32 portid, u32 seq, + int flags) +{ + struct devlink_trap_group_item *group_item = trap_item->group_item; + void *hdr; + int err; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + if (devlink_nl_put_handle(msg, devlink)) + goto nla_put_failure; + + if (nla_put_string(msg, DEVLINK_ATTR_TRAP_GROUP_NAME, + group_item->group->name)) + goto nla_put_failure; + + if (nla_put_string(msg, DEVLINK_ATTR_TRAP_NAME, trap_item->trap->name)) + goto nla_put_failure; + + if (nla_put_u8(msg, DEVLINK_ATTR_TRAP_TYPE, trap_item->trap->type)) + goto nla_put_failure; + + if (trap_item->trap->generic && + nla_put_flag(msg, DEVLINK_ATTR_TRAP_GENERIC)) + goto nla_put_failure; + + if (nla_put_u8(msg, DEVLINK_ATTR_TRAP_ACTION, trap_item->action)) + goto nla_put_failure; + + err = devlink_trap_metadata_put(msg, trap_item->trap); + if (err) + goto nla_put_failure; + + err = devlink_trap_stats_put(msg, devlink, trap_item); + if (err) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static int devlink_nl_cmd_trap_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct netlink_ext_ack *extack = info->extack; + struct devlink *devlink = info->user_ptr[0]; + struct devlink_trap_item *trap_item; + struct sk_buff *msg; + int err; + + if (list_empty(&devlink->trap_list)) + return -EOPNOTSUPP; + + trap_item = devlink_trap_item_get_from_info(devlink, info); + if (!trap_item) { + NL_SET_ERR_MSG_MOD(extack, "Device did not register this trap"); + return -ENOENT; + } + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_trap_fill(msg, devlink, trap_item, + DEVLINK_CMD_TRAP_NEW, info->snd_portid, + info->snd_seq, 0); + if (err) + goto err_trap_fill; + + return genlmsg_reply(msg, info); + +err_trap_fill: + nlmsg_free(msg); + return err; +} + +static int devlink_nl_cmd_trap_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + struct devlink_trap_item *trap_item; + struct devlink *devlink; + int start = cb->args[0]; + unsigned long index; + int idx = 0; + int err; + + devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { + devl_lock(devlink); + list_for_each_entry(trap_item, &devlink->trap_list, list) { + if (idx < start) { + idx++; + continue; + } + err = devlink_nl_trap_fill(msg, devlink, trap_item, + DEVLINK_CMD_TRAP_NEW, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI); + if (err) { + devl_unlock(devlink); + devlink_put(devlink); + goto out; + } + idx++; + } + devl_unlock(devlink); + devlink_put(devlink); + } +out: + cb->args[0] = idx; + return msg->len; +} + +static int __devlink_trap_action_set(struct devlink *devlink, + struct devlink_trap_item *trap_item, + enum devlink_trap_action trap_action, + struct netlink_ext_ack *extack) +{ + int err; + + if (trap_item->action != trap_action && + trap_item->trap->type != DEVLINK_TRAP_TYPE_DROP) { + NL_SET_ERR_MSG_MOD(extack, "Cannot change action of non-drop traps. Skipping"); + return 0; + } + + err = devlink->ops->trap_action_set(devlink, trap_item->trap, + trap_action, extack); + if (err) + return err; + + trap_item->action = trap_action; + + return 0; +} + +static int devlink_trap_action_set(struct devlink *devlink, + struct devlink_trap_item *trap_item, + struct genl_info *info) +{ + enum devlink_trap_action trap_action; + int err; + + if (!info->attrs[DEVLINK_ATTR_TRAP_ACTION]) + return 0; + + err = devlink_trap_action_get_from_info(info, &trap_action); + if (err) { + NL_SET_ERR_MSG_MOD(info->extack, "Invalid trap action"); + return -EINVAL; + } + + return __devlink_trap_action_set(devlink, trap_item, trap_action, + info->extack); +} + +static int devlink_nl_cmd_trap_set_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct netlink_ext_ack *extack = info->extack; + struct devlink *devlink = info->user_ptr[0]; + struct devlink_trap_item *trap_item; + + if (list_empty(&devlink->trap_list)) + return -EOPNOTSUPP; + + trap_item = devlink_trap_item_get_from_info(devlink, info); + if (!trap_item) { + NL_SET_ERR_MSG_MOD(extack, "Device did not register this trap"); + return -ENOENT; + } + + return devlink_trap_action_set(devlink, trap_item, info); +} + +static struct devlink_trap_group_item * +devlink_trap_group_item_lookup(struct devlink *devlink, const char *name) +{ + struct devlink_trap_group_item *group_item; + + list_for_each_entry(group_item, &devlink->trap_group_list, list) { + if (!strcmp(group_item->group->name, name)) + return group_item; + } + + return NULL; +} + +static struct devlink_trap_group_item * +devlink_trap_group_item_lookup_by_id(struct devlink *devlink, u16 id) +{ + struct devlink_trap_group_item *group_item; + + list_for_each_entry(group_item, &devlink->trap_group_list, list) { + if (group_item->group->id == id) + return group_item; + } + + return NULL; +} + +static struct devlink_trap_group_item * +devlink_trap_group_item_get_from_info(struct devlink *devlink, + struct genl_info *info) +{ + char *name; + + if (!info->attrs[DEVLINK_ATTR_TRAP_GROUP_NAME]) + return NULL; + name = nla_data(info->attrs[DEVLINK_ATTR_TRAP_GROUP_NAME]); + + return devlink_trap_group_item_lookup(devlink, name); +} + +static int +devlink_nl_trap_group_fill(struct sk_buff *msg, struct devlink *devlink, + const struct devlink_trap_group_item *group_item, + enum devlink_command cmd, u32 portid, u32 seq, + int flags) +{ + void *hdr; + int err; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + if (devlink_nl_put_handle(msg, devlink)) + goto nla_put_failure; + + if (nla_put_string(msg, DEVLINK_ATTR_TRAP_GROUP_NAME, + group_item->group->name)) + goto nla_put_failure; + + if (group_item->group->generic && + nla_put_flag(msg, DEVLINK_ATTR_TRAP_GENERIC)) + goto nla_put_failure; + + if (group_item->policer_item && + nla_put_u32(msg, DEVLINK_ATTR_TRAP_POLICER_ID, + group_item->policer_item->policer->id)) + goto nla_put_failure; + + err = devlink_trap_group_stats_put(msg, group_item->stats); + if (err) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static int devlink_nl_cmd_trap_group_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct netlink_ext_ack *extack = info->extack; + struct devlink *devlink = info->user_ptr[0]; + struct devlink_trap_group_item *group_item; + struct sk_buff *msg; + int err; + + if (list_empty(&devlink->trap_group_list)) + return -EOPNOTSUPP; + + group_item = devlink_trap_group_item_get_from_info(devlink, info); + if (!group_item) { + NL_SET_ERR_MSG_MOD(extack, "Device did not register this trap group"); + return -ENOENT; + } + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_trap_group_fill(msg, devlink, group_item, + DEVLINK_CMD_TRAP_GROUP_NEW, + info->snd_portid, info->snd_seq, 0); + if (err) + goto err_trap_group_fill; + + return genlmsg_reply(msg, info); + +err_trap_group_fill: + nlmsg_free(msg); + return err; +} + +static int devlink_nl_cmd_trap_group_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + enum devlink_command cmd = DEVLINK_CMD_TRAP_GROUP_NEW; + struct devlink_trap_group_item *group_item; + u32 portid = NETLINK_CB(cb->skb).portid; + struct devlink *devlink; + int start = cb->args[0]; + unsigned long index; + int idx = 0; + int err; + + devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { + devl_lock(devlink); + list_for_each_entry(group_item, &devlink->trap_group_list, + list) { + if (idx < start) { + idx++; + continue; + } + err = devlink_nl_trap_group_fill(msg, devlink, + group_item, cmd, + portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI); + if (err) { + devl_unlock(devlink); + devlink_put(devlink); + goto out; + } + idx++; + } + devl_unlock(devlink); + devlink_put(devlink); + } +out: + cb->args[0] = idx; + return msg->len; +} + +static int +__devlink_trap_group_action_set(struct devlink *devlink, + struct devlink_trap_group_item *group_item, + enum devlink_trap_action trap_action, + struct netlink_ext_ack *extack) +{ + const char *group_name = group_item->group->name; + struct devlink_trap_item *trap_item; + int err; + + if (devlink->ops->trap_group_action_set) { + err = devlink->ops->trap_group_action_set(devlink, group_item->group, + trap_action, extack); + if (err) + return err; + + list_for_each_entry(trap_item, &devlink->trap_list, list) { + if (strcmp(trap_item->group_item->group->name, group_name)) + continue; + if (trap_item->action != trap_action && + trap_item->trap->type != DEVLINK_TRAP_TYPE_DROP) + continue; + trap_item->action = trap_action; + } + + return 0; + } + + list_for_each_entry(trap_item, &devlink->trap_list, list) { + if (strcmp(trap_item->group_item->group->name, group_name)) + continue; + err = __devlink_trap_action_set(devlink, trap_item, + trap_action, extack); + if (err) + return err; + } + + return 0; +} + +static int +devlink_trap_group_action_set(struct devlink *devlink, + struct devlink_trap_group_item *group_item, + struct genl_info *info, bool *p_modified) +{ + enum devlink_trap_action trap_action; + int err; + + if (!info->attrs[DEVLINK_ATTR_TRAP_ACTION]) + return 0; + + err = devlink_trap_action_get_from_info(info, &trap_action); + if (err) { + NL_SET_ERR_MSG_MOD(info->extack, "Invalid trap action"); + return -EINVAL; + } + + err = __devlink_trap_group_action_set(devlink, group_item, trap_action, + info->extack); + if (err) + return err; + + *p_modified = true; + + return 0; +} + +static int devlink_trap_group_set(struct devlink *devlink, + struct devlink_trap_group_item *group_item, + struct genl_info *info) +{ + struct devlink_trap_policer_item *policer_item; + struct netlink_ext_ack *extack = info->extack; + const struct devlink_trap_policer *policer; + struct nlattr **attrs = info->attrs; + int err; + + if (!attrs[DEVLINK_ATTR_TRAP_POLICER_ID]) + return 0; + + if (!devlink->ops->trap_group_set) + return -EOPNOTSUPP; + + policer_item = group_item->policer_item; + if (attrs[DEVLINK_ATTR_TRAP_POLICER_ID]) { + u32 policer_id; + + policer_id = nla_get_u32(attrs[DEVLINK_ATTR_TRAP_POLICER_ID]); + policer_item = devlink_trap_policer_item_lookup(devlink, + policer_id); + if (policer_id && !policer_item) { + NL_SET_ERR_MSG_MOD(extack, "Device did not register this trap policer"); + return -ENOENT; + } + } + policer = policer_item ? policer_item->policer : NULL; + + err = devlink->ops->trap_group_set(devlink, group_item->group, policer, + extack); + if (err) + return err; + + group_item->policer_item = policer_item; + + return 0; +} + +static int devlink_nl_cmd_trap_group_set_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct netlink_ext_ack *extack = info->extack; + struct devlink *devlink = info->user_ptr[0]; + struct devlink_trap_group_item *group_item; + bool modified = false; + int err; + + if (list_empty(&devlink->trap_group_list)) + return -EOPNOTSUPP; + + group_item = devlink_trap_group_item_get_from_info(devlink, info); + if (!group_item) { + NL_SET_ERR_MSG_MOD(extack, "Device did not register this trap group"); + return -ENOENT; + } + + err = devlink_trap_group_action_set(devlink, group_item, info, + &modified); + if (err) + return err; + + err = devlink_trap_group_set(devlink, group_item, info); + if (err) + goto err_trap_group_set; + + return 0; + +err_trap_group_set: + if (modified) + NL_SET_ERR_MSG_MOD(extack, "Trap group set failed, but some changes were committed already"); + return err; +} + +static struct devlink_trap_policer_item * +devlink_trap_policer_item_get_from_info(struct devlink *devlink, + struct genl_info *info) +{ + u32 id; + + if (!info->attrs[DEVLINK_ATTR_TRAP_POLICER_ID]) + return NULL; + id = nla_get_u32(info->attrs[DEVLINK_ATTR_TRAP_POLICER_ID]); + + return devlink_trap_policer_item_lookup(devlink, id); +} + +static int +devlink_trap_policer_stats_put(struct sk_buff *msg, struct devlink *devlink, + const struct devlink_trap_policer *policer) +{ + struct nlattr *attr; + u64 drops; + int err; + + if (!devlink->ops->trap_policer_counter_get) + return 0; + + err = devlink->ops->trap_policer_counter_get(devlink, policer, &drops); + if (err) + return err; + + attr = nla_nest_start(msg, DEVLINK_ATTR_STATS); + if (!attr) + return -EMSGSIZE; + + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_DROPPED, drops, + DEVLINK_ATTR_PAD)) + goto nla_put_failure; + + nla_nest_end(msg, attr); + + return 0; + +nla_put_failure: + nla_nest_cancel(msg, attr); + return -EMSGSIZE; +} + +static int +devlink_nl_trap_policer_fill(struct sk_buff *msg, struct devlink *devlink, + const struct devlink_trap_policer_item *policer_item, + enum devlink_command cmd, u32 portid, u32 seq, + int flags) +{ + void *hdr; + int err; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + if (devlink_nl_put_handle(msg, devlink)) + goto nla_put_failure; + + if (nla_put_u32(msg, DEVLINK_ATTR_TRAP_POLICER_ID, + policer_item->policer->id)) + goto nla_put_failure; + + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_TRAP_POLICER_RATE, + policer_item->rate, DEVLINK_ATTR_PAD)) + goto nla_put_failure; + + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_TRAP_POLICER_BURST, + policer_item->burst, DEVLINK_ATTR_PAD)) + goto nla_put_failure; + + err = devlink_trap_policer_stats_put(msg, devlink, + policer_item->policer); + if (err) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static int devlink_nl_cmd_trap_policer_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink_trap_policer_item *policer_item; + struct netlink_ext_ack *extack = info->extack; + struct devlink *devlink = info->user_ptr[0]; + struct sk_buff *msg; + int err; + + if (list_empty(&devlink->trap_policer_list)) + return -EOPNOTSUPP; + + policer_item = devlink_trap_policer_item_get_from_info(devlink, info); + if (!policer_item) { + NL_SET_ERR_MSG_MOD(extack, "Device did not register this trap policer"); + return -ENOENT; + } + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_trap_policer_fill(msg, devlink, policer_item, + DEVLINK_CMD_TRAP_POLICER_NEW, + info->snd_portid, info->snd_seq, 0); + if (err) + goto err_trap_policer_fill; + + return genlmsg_reply(msg, info); + +err_trap_policer_fill: + nlmsg_free(msg); + return err; +} + +static int devlink_nl_cmd_trap_policer_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + enum devlink_command cmd = DEVLINK_CMD_TRAP_POLICER_NEW; + struct devlink_trap_policer_item *policer_item; + u32 portid = NETLINK_CB(cb->skb).portid; + struct devlink *devlink; + int start = cb->args[0]; + unsigned long index; + int idx = 0; + int err; + + devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { + devl_lock(devlink); + list_for_each_entry(policer_item, &devlink->trap_policer_list, + list) { + if (idx < start) { + idx++; + continue; + } + err = devlink_nl_trap_policer_fill(msg, devlink, + policer_item, cmd, + portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI); + if (err) { + devl_unlock(devlink); + devlink_put(devlink); + goto out; + } + idx++; + } + devl_unlock(devlink); + devlink_put(devlink); + } +out: + cb->args[0] = idx; + return msg->len; +} + +static int +devlink_trap_policer_set(struct devlink *devlink, + struct devlink_trap_policer_item *policer_item, + struct genl_info *info) +{ + struct netlink_ext_ack *extack = info->extack; + struct nlattr **attrs = info->attrs; + u64 rate, burst; + int err; + + rate = policer_item->rate; + burst = policer_item->burst; + + if (attrs[DEVLINK_ATTR_TRAP_POLICER_RATE]) + rate = nla_get_u64(attrs[DEVLINK_ATTR_TRAP_POLICER_RATE]); + + if (attrs[DEVLINK_ATTR_TRAP_POLICER_BURST]) + burst = nla_get_u64(attrs[DEVLINK_ATTR_TRAP_POLICER_BURST]); + + if (rate < policer_item->policer->min_rate) { + NL_SET_ERR_MSG_MOD(extack, "Policer rate lower than limit"); + return -EINVAL; + } + + if (rate > policer_item->policer->max_rate) { + NL_SET_ERR_MSG_MOD(extack, "Policer rate higher than limit"); + return -EINVAL; + } + + if (burst < policer_item->policer->min_burst) { + NL_SET_ERR_MSG_MOD(extack, "Policer burst size lower than limit"); + return -EINVAL; + } + + if (burst > policer_item->policer->max_burst) { + NL_SET_ERR_MSG_MOD(extack, "Policer burst size higher than limit"); + return -EINVAL; + } + + err = devlink->ops->trap_policer_set(devlink, policer_item->policer, + rate, burst, info->extack); + if (err) + return err; + + policer_item->rate = rate; + policer_item->burst = burst; + + return 0; +} + +static int devlink_nl_cmd_trap_policer_set_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink_trap_policer_item *policer_item; + struct netlink_ext_ack *extack = info->extack; + struct devlink *devlink = info->user_ptr[0]; + + if (list_empty(&devlink->trap_policer_list)) + return -EOPNOTSUPP; + + if (!devlink->ops->trap_policer_set) + return -EOPNOTSUPP; + + policer_item = devlink_trap_policer_item_get_from_info(devlink, info); + if (!policer_item) { + NL_SET_ERR_MSG_MOD(extack, "Device did not register this trap policer"); + return -ENOENT; + } + + return devlink_trap_policer_set(devlink, policer_item, info); +} + +static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { + [DEVLINK_ATTR_UNSPEC] = { .strict_start_type = + DEVLINK_ATTR_TRAP_POLICER_ID }, + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32 }, + [DEVLINK_ATTR_PORT_TYPE] = NLA_POLICY_RANGE(NLA_U16, DEVLINK_PORT_TYPE_AUTO, + DEVLINK_PORT_TYPE_IB), + [DEVLINK_ATTR_PORT_SPLIT_COUNT] = { .type = NLA_U32 }, + [DEVLINK_ATTR_SB_INDEX] = { .type = NLA_U32 }, + [DEVLINK_ATTR_SB_POOL_INDEX] = { .type = NLA_U16 }, + [DEVLINK_ATTR_SB_POOL_TYPE] = { .type = NLA_U8 }, + [DEVLINK_ATTR_SB_POOL_SIZE] = { .type = NLA_U32 }, + [DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE] = { .type = NLA_U8 }, + [DEVLINK_ATTR_SB_THRESHOLD] = { .type = NLA_U32 }, + [DEVLINK_ATTR_SB_TC_INDEX] = { .type = NLA_U16 }, + [DEVLINK_ATTR_ESWITCH_MODE] = NLA_POLICY_RANGE(NLA_U16, DEVLINK_ESWITCH_MODE_LEGACY, + DEVLINK_ESWITCH_MODE_SWITCHDEV), + [DEVLINK_ATTR_ESWITCH_INLINE_MODE] = { .type = NLA_U8 }, + [DEVLINK_ATTR_ESWITCH_ENCAP_MODE] = { .type = NLA_U8 }, + [DEVLINK_ATTR_DPIPE_TABLE_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED] = { .type = NLA_U8 }, + [DEVLINK_ATTR_RESOURCE_ID] = { .type = NLA_U64}, + [DEVLINK_ATTR_RESOURCE_SIZE] = { .type = NLA_U64}, + [DEVLINK_ATTR_PARAM_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_PARAM_TYPE] = { .type = NLA_U8 }, + [DEVLINK_ATTR_PARAM_VALUE_CMODE] = { .type = NLA_U8 }, + [DEVLINK_ATTR_REGION_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_REGION_SNAPSHOT_ID] = { .type = NLA_U32 }, + [DEVLINK_ATTR_REGION_CHUNK_ADDR] = { .type = NLA_U64 }, + [DEVLINK_ATTR_REGION_CHUNK_LEN] = { .type = NLA_U64 }, + [DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] = { .type = NLA_U64 }, + [DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER] = { .type = NLA_U8 }, + [DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_FLASH_UPDATE_COMPONENT] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK] = + NLA_POLICY_BITFIELD32(DEVLINK_SUPPORTED_FLASH_OVERWRITE_SECTIONS), + [DEVLINK_ATTR_TRAP_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_TRAP_ACTION] = { .type = NLA_U8 }, + [DEVLINK_ATTR_TRAP_GROUP_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_NETNS_PID] = { .type = NLA_U32 }, + [DEVLINK_ATTR_NETNS_FD] = { .type = NLA_U32 }, + [DEVLINK_ATTR_NETNS_ID] = { .type = NLA_U32 }, + [DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP] = { .type = NLA_U8 }, + [DEVLINK_ATTR_TRAP_POLICER_ID] = { .type = NLA_U32 }, + [DEVLINK_ATTR_TRAP_POLICER_RATE] = { .type = NLA_U64 }, + [DEVLINK_ATTR_TRAP_POLICER_BURST] = { .type = NLA_U64 }, + [DEVLINK_ATTR_PORT_FUNCTION] = { .type = NLA_NESTED }, + [DEVLINK_ATTR_RELOAD_ACTION] = NLA_POLICY_RANGE(NLA_U8, DEVLINK_RELOAD_ACTION_DRIVER_REINIT, + DEVLINK_RELOAD_ACTION_MAX), + [DEVLINK_ATTR_RELOAD_LIMITS] = NLA_POLICY_BITFIELD32(DEVLINK_RELOAD_LIMITS_VALID_MASK), + [DEVLINK_ATTR_PORT_FLAVOUR] = { .type = NLA_U16 }, + [DEVLINK_ATTR_PORT_PCI_PF_NUMBER] = { .type = NLA_U16 }, + [DEVLINK_ATTR_PORT_PCI_SF_NUMBER] = { .type = NLA_U32 }, + [DEVLINK_ATTR_PORT_CONTROLLER_NUMBER] = { .type = NLA_U32 }, + [DEVLINK_ATTR_RATE_TYPE] = { .type = NLA_U16 }, + [DEVLINK_ATTR_RATE_TX_SHARE] = { .type = NLA_U64 }, + [DEVLINK_ATTR_RATE_TX_MAX] = { .type = NLA_U64 }, + [DEVLINK_ATTR_RATE_NODE_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_RATE_PARENT_NODE_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_LINECARD_INDEX] = { .type = NLA_U32 }, + [DEVLINK_ATTR_LINECARD_TYPE] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_SELFTESTS] = { .type = NLA_NESTED }, +}; + +static const struct genl_small_ops devlink_nl_ops[] = { + { + .cmd = DEVLINK_CMD_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = devlink_nl_cmd_get_doit, + .dumpit = devlink_nl_cmd_get_dumpit, + /* can be retrieved by unprivileged users */ + }, + { + .cmd = DEVLINK_CMD_PORT_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = devlink_nl_cmd_port_get_doit, + .dumpit = devlink_nl_cmd_port_get_dumpit, + .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, + /* can be retrieved by unprivileged users */ + }, + { + .cmd = DEVLINK_CMD_PORT_SET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = devlink_nl_cmd_port_set_doit, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, + }, + { + .cmd = DEVLINK_CMD_RATE_GET, + .doit = devlink_nl_cmd_rate_get_doit, + .dumpit = devlink_nl_cmd_rate_get_dumpit, + .internal_flags = DEVLINK_NL_FLAG_NEED_RATE, + /* can be retrieved by unprivileged users */ + }, + { + .cmd = DEVLINK_CMD_RATE_SET, + .doit = devlink_nl_cmd_rate_set_doit, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_RATE, + }, + { + .cmd = DEVLINK_CMD_RATE_NEW, + .doit = devlink_nl_cmd_rate_new_doit, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = DEVLINK_CMD_RATE_DEL, + .doit = devlink_nl_cmd_rate_del_doit, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_RATE_NODE, + }, + { + .cmd = DEVLINK_CMD_PORT_SPLIT, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = devlink_nl_cmd_port_split_doit, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, + }, + { + .cmd = DEVLINK_CMD_PORT_UNSPLIT, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = devlink_nl_cmd_port_unsplit_doit, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, + }, + { + .cmd = DEVLINK_CMD_PORT_NEW, + .doit = devlink_nl_cmd_port_new_doit, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = DEVLINK_CMD_PORT_DEL, + .doit = devlink_nl_cmd_port_del_doit, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = DEVLINK_CMD_LINECARD_GET, + .doit = devlink_nl_cmd_linecard_get_doit, + .dumpit = devlink_nl_cmd_linecard_get_dumpit, + .internal_flags = DEVLINK_NL_FLAG_NEED_LINECARD, + /* can be retrieved by unprivileged users */ + }, + { + .cmd = DEVLINK_CMD_LINECARD_SET, + .doit = devlink_nl_cmd_linecard_set_doit, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_LINECARD, + }, + { + .cmd = DEVLINK_CMD_SB_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = devlink_nl_cmd_sb_get_doit, + .dumpit = devlink_nl_cmd_sb_get_dumpit, + /* can be retrieved by unprivileged users */ + }, + { + .cmd = DEVLINK_CMD_SB_POOL_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = devlink_nl_cmd_sb_pool_get_doit, + .dumpit = devlink_nl_cmd_sb_pool_get_dumpit, + /* can be retrieved by unprivileged users */ + }, + { + .cmd = DEVLINK_CMD_SB_POOL_SET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = devlink_nl_cmd_sb_pool_set_doit, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = DEVLINK_CMD_SB_PORT_POOL_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = devlink_nl_cmd_sb_port_pool_get_doit, + .dumpit = devlink_nl_cmd_sb_port_pool_get_dumpit, + .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, + /* can be retrieved by unprivileged users */ + }, + { + .cmd = DEVLINK_CMD_SB_PORT_POOL_SET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = devlink_nl_cmd_sb_port_pool_set_doit, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, + }, + { + .cmd = DEVLINK_CMD_SB_TC_POOL_BIND_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = devlink_nl_cmd_sb_tc_pool_bind_get_doit, + .dumpit = devlink_nl_cmd_sb_tc_pool_bind_get_dumpit, + .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, + /* can be retrieved by unprivileged users */ + }, + { + .cmd = DEVLINK_CMD_SB_TC_POOL_BIND_SET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = devlink_nl_cmd_sb_tc_pool_bind_set_doit, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, + }, + { + .cmd = DEVLINK_CMD_SB_OCC_SNAPSHOT, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = devlink_nl_cmd_sb_occ_snapshot_doit, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = DEVLINK_CMD_SB_OCC_MAX_CLEAR, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = devlink_nl_cmd_sb_occ_max_clear_doit, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = DEVLINK_CMD_ESWITCH_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = devlink_nl_cmd_eswitch_get_doit, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = DEVLINK_CMD_ESWITCH_SET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = devlink_nl_cmd_eswitch_set_doit, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = DEVLINK_CMD_DPIPE_TABLE_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = devlink_nl_cmd_dpipe_table_get, + /* can be retrieved by unprivileged users */ + }, + { + .cmd = DEVLINK_CMD_DPIPE_ENTRIES_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = devlink_nl_cmd_dpipe_entries_get, + /* can be retrieved by unprivileged users */ + }, + { + .cmd = DEVLINK_CMD_DPIPE_HEADERS_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = devlink_nl_cmd_dpipe_headers_get, + /* can be retrieved by unprivileged users */ + }, + { + .cmd = DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = devlink_nl_cmd_dpipe_table_counters_set, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = DEVLINK_CMD_RESOURCE_SET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = devlink_nl_cmd_resource_set, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = DEVLINK_CMD_RESOURCE_DUMP, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = devlink_nl_cmd_resource_dump, + /* can be retrieved by unprivileged users */ + }, + { + .cmd = DEVLINK_CMD_RELOAD, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = devlink_nl_cmd_reload, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = DEVLINK_CMD_PARAM_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = devlink_nl_cmd_param_get_doit, + .dumpit = devlink_nl_cmd_param_get_dumpit, + /* can be retrieved by unprivileged users */ + }, + { + .cmd = DEVLINK_CMD_PARAM_SET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = devlink_nl_cmd_param_set_doit, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = DEVLINK_CMD_PORT_PARAM_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = devlink_nl_cmd_port_param_get_doit, + .dumpit = devlink_nl_cmd_port_param_get_dumpit, + .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, + /* can be retrieved by unprivileged users */ + }, + { + .cmd = DEVLINK_CMD_PORT_PARAM_SET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = devlink_nl_cmd_port_param_set_doit, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, + }, + { + .cmd = DEVLINK_CMD_REGION_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = devlink_nl_cmd_region_get_doit, + .dumpit = devlink_nl_cmd_region_get_dumpit, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = DEVLINK_CMD_REGION_NEW, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = devlink_nl_cmd_region_new, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = DEVLINK_CMD_REGION_DEL, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = devlink_nl_cmd_region_del, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = DEVLINK_CMD_REGION_READ, + .validate = GENL_DONT_VALIDATE_STRICT | + GENL_DONT_VALIDATE_DUMP_STRICT, + .dumpit = devlink_nl_cmd_region_read_dumpit, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = DEVLINK_CMD_INFO_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = devlink_nl_cmd_info_get_doit, + .dumpit = devlink_nl_cmd_info_get_dumpit, + /* can be retrieved by unprivileged users */ + }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = devlink_nl_cmd_health_reporter_get_doit, + .dumpit = devlink_nl_cmd_health_reporter_get_dumpit, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT, + /* can be retrieved by unprivileged users */ + }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_SET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = devlink_nl_cmd_health_reporter_set_doit, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT, + }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_RECOVER, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = devlink_nl_cmd_health_reporter_recover_doit, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT, + }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = devlink_nl_cmd_health_reporter_diagnose_doit, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT, + }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET, + .validate = GENL_DONT_VALIDATE_STRICT | + GENL_DONT_VALIDATE_DUMP_STRICT, + .dumpit = devlink_nl_cmd_health_reporter_dump_get_dumpit, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = devlink_nl_cmd_health_reporter_dump_clear_doit, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT, + }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_TEST, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = devlink_nl_cmd_health_reporter_test_doit, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT, + }, + { + .cmd = DEVLINK_CMD_FLASH_UPDATE, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = devlink_nl_cmd_flash_update, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = DEVLINK_CMD_TRAP_GET, + .doit = devlink_nl_cmd_trap_get_doit, + .dumpit = devlink_nl_cmd_trap_get_dumpit, + /* can be retrieved by unprivileged users */ + }, + { + .cmd = DEVLINK_CMD_TRAP_SET, + .doit = devlink_nl_cmd_trap_set_doit, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = DEVLINK_CMD_TRAP_GROUP_GET, + .doit = devlink_nl_cmd_trap_group_get_doit, + .dumpit = devlink_nl_cmd_trap_group_get_dumpit, + /* can be retrieved by unprivileged users */ + }, + { + .cmd = DEVLINK_CMD_TRAP_GROUP_SET, + .doit = devlink_nl_cmd_trap_group_set_doit, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = DEVLINK_CMD_TRAP_POLICER_GET, + .doit = devlink_nl_cmd_trap_policer_get_doit, + .dumpit = devlink_nl_cmd_trap_policer_get_dumpit, + /* can be retrieved by unprivileged users */ + }, + { + .cmd = DEVLINK_CMD_TRAP_POLICER_SET, + .doit = devlink_nl_cmd_trap_policer_set_doit, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = DEVLINK_CMD_SELFTESTS_GET, + .doit = devlink_nl_cmd_selftests_get_doit, + .dumpit = devlink_nl_cmd_selftests_get_dumpit + /* can be retrieved by unprivileged users */ + }, + { + .cmd = DEVLINK_CMD_SELFTESTS_RUN, + .doit = devlink_nl_cmd_selftests_run, + .flags = GENL_ADMIN_PERM, + }, +}; + +static struct genl_family devlink_nl_family __ro_after_init = { + .name = DEVLINK_GENL_NAME, + .version = DEVLINK_GENL_VERSION, + .maxattr = DEVLINK_ATTR_MAX, + .policy = devlink_nl_policy, + .netnsok = true, + .parallel_ops = true, + .pre_doit = devlink_nl_pre_doit, + .post_doit = devlink_nl_post_doit, + .module = THIS_MODULE, + .small_ops = devlink_nl_ops, + .n_small_ops = ARRAY_SIZE(devlink_nl_ops), + .resv_start_op = DEVLINK_CMD_SELFTESTS_RUN + 1, + .mcgrps = devlink_nl_mcgrps, + .n_mcgrps = ARRAY_SIZE(devlink_nl_mcgrps), +}; + +static bool devlink_reload_actions_valid(const struct devlink_ops *ops) +{ + const struct devlink_reload_combination *comb; + int i; + + if (!devlink_reload_supported(ops)) { + if (WARN_ON(ops->reload_actions)) + return false; + return true; + } + + if (WARN_ON(!ops->reload_actions || + ops->reload_actions & BIT(DEVLINK_RELOAD_ACTION_UNSPEC) || + ops->reload_actions >= BIT(__DEVLINK_RELOAD_ACTION_MAX))) + return false; + + if (WARN_ON(ops->reload_limits & BIT(DEVLINK_RELOAD_LIMIT_UNSPEC) || + ops->reload_limits >= BIT(__DEVLINK_RELOAD_LIMIT_MAX))) + return false; + + for (i = 0; i < ARRAY_SIZE(devlink_reload_invalid_combinations); i++) { + comb = &devlink_reload_invalid_combinations[i]; + if (ops->reload_actions == BIT(comb->action) && + ops->reload_limits == BIT(comb->limit)) + return false; + } + return true; +} + +/** + * devlink_set_features - Set devlink supported features + * + * @devlink: devlink + * @features: devlink support features + * + * This interface allows us to set reload ops separatelly from + * the devlink_alloc. + */ +void devlink_set_features(struct devlink *devlink, u64 features) +{ + ASSERT_DEVLINK_NOT_REGISTERED(devlink); + + WARN_ON(features & DEVLINK_F_RELOAD && + !devlink_reload_supported(devlink->ops)); + devlink->features = features; +} +EXPORT_SYMBOL_GPL(devlink_set_features); + +/** + * devlink_alloc_ns - Allocate new devlink instance resources + * in specific namespace + * + * @ops: ops + * @priv_size: size of user private data + * @net: net namespace + * @dev: parent device + * + * Allocate new devlink instance resources, including devlink index + * and name. + */ +struct devlink *devlink_alloc_ns(const struct devlink_ops *ops, + size_t priv_size, struct net *net, + struct device *dev) +{ + struct devlink *devlink; + static u32 last_id; + int ret; + + WARN_ON(!ops || !dev); + if (!devlink_reload_actions_valid(ops)) + return NULL; + + devlink = kzalloc(sizeof(*devlink) + priv_size, GFP_KERNEL); + if (!devlink) + return NULL; + + ret = xa_alloc_cyclic(&devlinks, &devlink->index, devlink, xa_limit_31b, + &last_id, GFP_KERNEL); + if (ret < 0) { + kfree(devlink); + return NULL; + } + + devlink->dev = dev; + devlink->ops = ops; + xa_init_flags(&devlink->snapshot_ids, XA_FLAGS_ALLOC); + write_pnet(&devlink->_net, net); + INIT_LIST_HEAD(&devlink->port_list); + INIT_LIST_HEAD(&devlink->rate_list); + INIT_LIST_HEAD(&devlink->linecard_list); + INIT_LIST_HEAD(&devlink->sb_list); + INIT_LIST_HEAD_RCU(&devlink->dpipe_table_list); + INIT_LIST_HEAD(&devlink->resource_list); + INIT_LIST_HEAD(&devlink->param_list); + INIT_LIST_HEAD(&devlink->region_list); + INIT_LIST_HEAD(&devlink->reporter_list); + INIT_LIST_HEAD(&devlink->trap_list); + INIT_LIST_HEAD(&devlink->trap_group_list); + INIT_LIST_HEAD(&devlink->trap_policer_list); + lockdep_register_key(&devlink->lock_key); + mutex_init(&devlink->lock); + lockdep_set_class(&devlink->lock, &devlink->lock_key); + mutex_init(&devlink->reporters_lock); + mutex_init(&devlink->linecards_lock); + refcount_set(&devlink->refcount, 1); + init_completion(&devlink->comp); + + return devlink; +} +EXPORT_SYMBOL_GPL(devlink_alloc_ns); + +static void +devlink_trap_policer_notify(struct devlink *devlink, + const struct devlink_trap_policer_item *policer_item, + enum devlink_command cmd); +static void +devlink_trap_group_notify(struct devlink *devlink, + const struct devlink_trap_group_item *group_item, + enum devlink_command cmd); +static void devlink_trap_notify(struct devlink *devlink, + const struct devlink_trap_item *trap_item, + enum devlink_command cmd); + +static void devlink_notify_register(struct devlink *devlink) +{ + struct devlink_trap_policer_item *policer_item; + struct devlink_trap_group_item *group_item; + struct devlink_param_item *param_item; + struct devlink_trap_item *trap_item; + struct devlink_port *devlink_port; + struct devlink_linecard *linecard; + struct devlink_rate *rate_node; + struct devlink_region *region; + + devlink_notify(devlink, DEVLINK_CMD_NEW); + list_for_each_entry(linecard, &devlink->linecard_list, list) + devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); + + list_for_each_entry(devlink_port, &devlink->port_list, list) + devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); + + list_for_each_entry(policer_item, &devlink->trap_policer_list, list) + devlink_trap_policer_notify(devlink, policer_item, + DEVLINK_CMD_TRAP_POLICER_NEW); + + list_for_each_entry(group_item, &devlink->trap_group_list, list) + devlink_trap_group_notify(devlink, group_item, + DEVLINK_CMD_TRAP_GROUP_NEW); + + list_for_each_entry(trap_item, &devlink->trap_list, list) + devlink_trap_notify(devlink, trap_item, DEVLINK_CMD_TRAP_NEW); + + list_for_each_entry(rate_node, &devlink->rate_list, list) + devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_NEW); + + list_for_each_entry(region, &devlink->region_list, list) + devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_NEW); + + list_for_each_entry(param_item, &devlink->param_list, list) + devlink_param_notify(devlink, 0, param_item, + DEVLINK_CMD_PARAM_NEW); +} + +static void devlink_notify_unregister(struct devlink *devlink) +{ + struct devlink_trap_policer_item *policer_item; + struct devlink_trap_group_item *group_item; + struct devlink_param_item *param_item; + struct devlink_trap_item *trap_item; + struct devlink_port *devlink_port; + struct devlink_linecard *linecard; + struct devlink_rate *rate_node; + struct devlink_region *region; + + list_for_each_entry_reverse(param_item, &devlink->param_list, list) + devlink_param_notify(devlink, 0, param_item, + DEVLINK_CMD_PARAM_DEL); + + list_for_each_entry_reverse(region, &devlink->region_list, list) + devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_DEL); + + list_for_each_entry_reverse(rate_node, &devlink->rate_list, list) + devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_DEL); + + list_for_each_entry_reverse(trap_item, &devlink->trap_list, list) + devlink_trap_notify(devlink, trap_item, DEVLINK_CMD_TRAP_DEL); + + list_for_each_entry_reverse(group_item, &devlink->trap_group_list, list) + devlink_trap_group_notify(devlink, group_item, + DEVLINK_CMD_TRAP_GROUP_DEL); + list_for_each_entry_reverse(policer_item, &devlink->trap_policer_list, + list) + devlink_trap_policer_notify(devlink, policer_item, + DEVLINK_CMD_TRAP_POLICER_DEL); + + list_for_each_entry_reverse(devlink_port, &devlink->port_list, list) + devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_DEL); + list_for_each_entry_reverse(linecard, &devlink->linecard_list, list) + devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_DEL); + devlink_notify(devlink, DEVLINK_CMD_DEL); +} + +/** + * devlink_register - Register devlink instance + * + * @devlink: devlink + */ +void devlink_register(struct devlink *devlink) +{ + ASSERT_DEVLINK_NOT_REGISTERED(devlink); + /* Make sure that we are in .probe() routine */ + + xa_set_mark(&devlinks, devlink->index, DEVLINK_REGISTERED); + devlink_notify_register(devlink); +} +EXPORT_SYMBOL_GPL(devlink_register); + +/** + * devlink_unregister - Unregister devlink instance + * + * @devlink: devlink + */ +void devlink_unregister(struct devlink *devlink) +{ + ASSERT_DEVLINK_REGISTERED(devlink); + /* Make sure that we are in .remove() routine */ + + xa_set_mark(&devlinks, devlink->index, DEVLINK_UNREGISTERING); + devlink_put(devlink); + wait_for_completion(&devlink->comp); + + devlink_notify_unregister(devlink); + xa_clear_mark(&devlinks, devlink->index, DEVLINK_REGISTERED); + xa_clear_mark(&devlinks, devlink->index, DEVLINK_UNREGISTERING); +} +EXPORT_SYMBOL_GPL(devlink_unregister); + +/** + * devlink_free - Free devlink instance resources + * + * @devlink: devlink + */ +void devlink_free(struct devlink *devlink) +{ + ASSERT_DEVLINK_NOT_REGISTERED(devlink); + + mutex_destroy(&devlink->linecards_lock); + mutex_destroy(&devlink->reporters_lock); + mutex_destroy(&devlink->lock); + lockdep_unregister_key(&devlink->lock_key); + WARN_ON(!list_empty(&devlink->trap_policer_list)); + WARN_ON(!list_empty(&devlink->trap_group_list)); + WARN_ON(!list_empty(&devlink->trap_list)); + WARN_ON(!list_empty(&devlink->reporter_list)); + WARN_ON(!list_empty(&devlink->region_list)); + WARN_ON(!list_empty(&devlink->param_list)); + WARN_ON(!list_empty(&devlink->resource_list)); + WARN_ON(!list_empty(&devlink->dpipe_table_list)); + WARN_ON(!list_empty(&devlink->sb_list)); + WARN_ON(!list_empty(&devlink->rate_list)); + WARN_ON(!list_empty(&devlink->linecard_list)); + WARN_ON(!list_empty(&devlink->port_list)); + + xa_destroy(&devlink->snapshot_ids); + xa_erase(&devlinks, devlink->index); + + kfree(devlink); +} +EXPORT_SYMBOL_GPL(devlink_free); + +static void devlink_port_type_warn(struct work_struct *work) +{ + struct devlink_port *port = container_of(to_delayed_work(work), + struct devlink_port, + type_warn_dw); + dev_warn(port->devlink->dev, "Type was not set for devlink port."); +} + +static bool devlink_port_type_should_warn(struct devlink_port *devlink_port) +{ + /* Ignore CPU and DSA flavours. */ + return devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_CPU && + devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_DSA && + devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_UNUSED; +} + +#define DEVLINK_PORT_TYPE_WARN_TIMEOUT (HZ * 3600) + +static void devlink_port_type_warn_schedule(struct devlink_port *devlink_port) +{ + if (!devlink_port_type_should_warn(devlink_port)) + return; + /* Schedule a work to WARN in case driver does not set port + * type within timeout. + */ + schedule_delayed_work(&devlink_port->type_warn_dw, + DEVLINK_PORT_TYPE_WARN_TIMEOUT); +} + +static void devlink_port_type_warn_cancel(struct devlink_port *devlink_port) +{ + if (!devlink_port_type_should_warn(devlink_port)) + return; + cancel_delayed_work_sync(&devlink_port->type_warn_dw); +} + +/** + * devlink_port_init() - Init devlink port + * + * @devlink: devlink + * @devlink_port: devlink port + * + * Initialize essencial stuff that is needed for functions + * that may be called before devlink port registration. + * Call to this function is optional and not needed + * in case the driver does not use such functions. + */ +void devlink_port_init(struct devlink *devlink, + struct devlink_port *devlink_port) +{ + if (devlink_port->initialized) + return; + devlink_port->devlink = devlink; + INIT_LIST_HEAD(&devlink_port->region_list); + devlink_port->initialized = true; +} +EXPORT_SYMBOL_GPL(devlink_port_init); + +/** + * devlink_port_fini() - Deinitialize devlink port + * + * @devlink_port: devlink port + * + * Deinitialize essencial stuff that is in use for functions + * that may be called after devlink port unregistration. + * Call to this function is optional and not needed + * in case the driver does not use such functions. + */ +void devlink_port_fini(struct devlink_port *devlink_port) +{ + WARN_ON(!list_empty(&devlink_port->region_list)); +} +EXPORT_SYMBOL_GPL(devlink_port_fini); + +/** + * devl_port_register() - Register devlink port + * + * @devlink: devlink + * @devlink_port: devlink port + * @port_index: driver-specific numerical identifier of the port + * + * Register devlink port with provided port index. User can use + * any indexing, even hw-related one. devlink_port structure + * is convenient to be embedded inside user driver private structure. + * Note that the caller should take care of zeroing the devlink_port + * structure. + */ +int devl_port_register(struct devlink *devlink, + struct devlink_port *devlink_port, + unsigned int port_index) +{ + devl_assert_locked(devlink); + + if (devlink_port_index_exists(devlink, port_index)) + return -EEXIST; + + ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port); + + devlink_port_init(devlink, devlink_port); + devlink_port->registered = true; + devlink_port->index = port_index; + spin_lock_init(&devlink_port->type_lock); + INIT_LIST_HEAD(&devlink_port->reporter_list); + mutex_init(&devlink_port->reporters_lock); + list_add_tail(&devlink_port->list, &devlink->port_list); + + INIT_DELAYED_WORK(&devlink_port->type_warn_dw, &devlink_port_type_warn); + devlink_port_type_warn_schedule(devlink_port); + devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); + return 0; +} +EXPORT_SYMBOL_GPL(devl_port_register); + +/** + * devlink_port_register - Register devlink port + * + * @devlink: devlink + * @devlink_port: devlink port + * @port_index: driver-specific numerical identifier of the port + * + * Register devlink port with provided port index. User can use + * any indexing, even hw-related one. devlink_port structure + * is convenient to be embedded inside user driver private structure. + * Note that the caller should take care of zeroing the devlink_port + * structure. + * + * Context: Takes and release devlink->lock <mutex>. + */ +int devlink_port_register(struct devlink *devlink, + struct devlink_port *devlink_port, + unsigned int port_index) +{ + int err; + + devl_lock(devlink); + err = devl_port_register(devlink, devlink_port, port_index); + devl_unlock(devlink); + return err; +} +EXPORT_SYMBOL_GPL(devlink_port_register); + +/** + * devl_port_unregister() - Unregister devlink port + * + * @devlink_port: devlink port + */ +void devl_port_unregister(struct devlink_port *devlink_port) +{ + lockdep_assert_held(&devlink_port->devlink->lock); + + devlink_port_type_warn_cancel(devlink_port); + devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_DEL); + list_del(&devlink_port->list); + WARN_ON(!list_empty(&devlink_port->reporter_list)); + mutex_destroy(&devlink_port->reporters_lock); + devlink_port->registered = false; +} +EXPORT_SYMBOL_GPL(devl_port_unregister); + +/** + * devlink_port_unregister - Unregister devlink port + * + * @devlink_port: devlink port + * + * Context: Takes and release devlink->lock <mutex>. + */ +void devlink_port_unregister(struct devlink_port *devlink_port) +{ + struct devlink *devlink = devlink_port->devlink; + + devl_lock(devlink); + devl_port_unregister(devlink_port); + devl_unlock(devlink); +} +EXPORT_SYMBOL_GPL(devlink_port_unregister); + +static void __devlink_port_type_set(struct devlink_port *devlink_port, + enum devlink_port_type type, + void *type_dev) +{ + ASSERT_DEVLINK_PORT_REGISTERED(devlink_port); + + devlink_port_type_warn_cancel(devlink_port); + spin_lock_bh(&devlink_port->type_lock); + devlink_port->type = type; + devlink_port->type_dev = type_dev; + spin_unlock_bh(&devlink_port->type_lock); + devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); +} + +static void devlink_port_type_netdev_checks(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 (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. + */ + 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_eth_set - Set port type to Ethernet + * + * @devlink_port: devlink port + * @netdev: related netdevice + */ +void devlink_port_type_eth_set(struct devlink_port *devlink_port, + struct net_device *netdev) +{ + if (netdev) + devlink_port_type_netdev_checks(devlink_port, netdev); + else + dev_warn(devlink_port->devlink->dev, + "devlink port type for port %d set to Ethernet without a software interface reference, device type not supported by the kernel?\n", + devlink_port->index); + + __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_ETH, netdev); +} +EXPORT_SYMBOL_GPL(devlink_port_type_eth_set); + +/** + * devlink_port_type_ib_set - Set port type to InfiniBand + * + * @devlink_port: devlink port + * @ibdev: related IB device + */ +void devlink_port_type_ib_set(struct devlink_port *devlink_port, + struct ib_device *ibdev) +{ + __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_IB, ibdev); +} +EXPORT_SYMBOL_GPL(devlink_port_type_ib_set); + +/** + * devlink_port_type_clear - Clear port type + * + * @devlink_port: devlink port + */ +void devlink_port_type_clear(struct devlink_port *devlink_port) +{ + __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_NOTSET, NULL); + devlink_port_type_warn_schedule(devlink_port); +} +EXPORT_SYMBOL_GPL(devlink_port_type_clear); + +static int __devlink_port_attrs_set(struct devlink_port *devlink_port, + enum devlink_port_flavour flavour) +{ + struct devlink_port_attrs *attrs = &devlink_port->attrs; + + devlink_port->attrs_set = true; + attrs->flavour = flavour; + if (attrs->switch_id.id_len) { + devlink_port->switch_port = true; + if (WARN_ON(attrs->switch_id.id_len > MAX_PHYS_ITEM_ID_LEN)) + attrs->switch_id.id_len = MAX_PHYS_ITEM_ID_LEN; + } else { + devlink_port->switch_port = false; + } + return 0; +} + +/** + * devlink_port_attrs_set - Set port attributes + * + * @devlink_port: devlink port + * @attrs: devlink port attrs + */ +void devlink_port_attrs_set(struct devlink_port *devlink_port, + struct devlink_port_attrs *attrs) +{ + int ret; + + ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port); + + devlink_port->attrs = *attrs; + ret = __devlink_port_attrs_set(devlink_port, attrs->flavour); + if (ret) + return; + WARN_ON(attrs->splittable && attrs->split); +} +EXPORT_SYMBOL_GPL(devlink_port_attrs_set); + +/** + * devlink_port_attrs_pci_pf_set - Set PCI PF port attributes + * + * @devlink_port: devlink port + * @controller: associated controller number for the devlink port instance + * @pf: associated PF for the devlink port instance + * @external: indicates if the port is for an external controller + */ +void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u32 controller, + u16 pf, bool external) +{ + struct devlink_port_attrs *attrs = &devlink_port->attrs; + int ret; + + ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port); + + ret = __devlink_port_attrs_set(devlink_port, + DEVLINK_PORT_FLAVOUR_PCI_PF); + if (ret) + return; + attrs->pci_pf.controller = controller; + attrs->pci_pf.pf = pf; + attrs->pci_pf.external = external; +} +EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_pf_set); + +/** + * devlink_port_attrs_pci_vf_set - Set PCI VF port attributes + * + * @devlink_port: devlink port + * @controller: associated controller number for the devlink port instance + * @pf: associated PF for the devlink port instance + * @vf: associated VF of a PF for the devlink port instance + * @external: indicates if the port is for an external controller + */ +void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 controller, + u16 pf, u16 vf, bool external) +{ + struct devlink_port_attrs *attrs = &devlink_port->attrs; + int ret; + + ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port); + + ret = __devlink_port_attrs_set(devlink_port, + DEVLINK_PORT_FLAVOUR_PCI_VF); + if (ret) + return; + attrs->pci_vf.controller = controller; + attrs->pci_vf.pf = pf; + attrs->pci_vf.vf = vf; + attrs->pci_vf.external = external; +} +EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_vf_set); + +/** + * devlink_port_attrs_pci_sf_set - Set PCI SF port attributes + * + * @devlink_port: devlink port + * @controller: associated controller number for the devlink port instance + * @pf: associated PF for the devlink port instance + * @sf: associated SF of a PF for the devlink port instance + * @external: indicates if the port is for an external controller + */ +void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, u32 controller, + u16 pf, u32 sf, bool external) +{ + struct devlink_port_attrs *attrs = &devlink_port->attrs; + int ret; + + ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port); + + ret = __devlink_port_attrs_set(devlink_port, + DEVLINK_PORT_FLAVOUR_PCI_SF); + if (ret) + return; + attrs->pci_sf.controller = controller; + attrs->pci_sf.pf = pf; + attrs->pci_sf.sf = sf; + attrs->pci_sf.external = external; +} +EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_sf_set); + +/** + * devl_rate_leaf_create - create devlink rate leaf + * @devlink_port: devlink port object to create rate object on + * @priv: driver private data + * + * Create devlink rate object of type leaf on provided @devlink_port. + */ +int devl_rate_leaf_create(struct devlink_port *devlink_port, void *priv) +{ + struct devlink *devlink = devlink_port->devlink; + struct devlink_rate *devlink_rate; + + devl_assert_locked(devlink_port->devlink); + + if (WARN_ON(devlink_port->devlink_rate)) + return -EBUSY; + + devlink_rate = kzalloc(sizeof(*devlink_rate), GFP_KERNEL); + if (!devlink_rate) + return -ENOMEM; + + devlink_rate->type = DEVLINK_RATE_TYPE_LEAF; + devlink_rate->devlink = devlink; + devlink_rate->devlink_port = devlink_port; + devlink_rate->priv = priv; + list_add_tail(&devlink_rate->list, &devlink->rate_list); + devlink_port->devlink_rate = devlink_rate; + devlink_rate_notify(devlink_rate, DEVLINK_CMD_RATE_NEW); + + return 0; +} +EXPORT_SYMBOL_GPL(devl_rate_leaf_create); + +/** + * devl_rate_leaf_destroy - destroy devlink rate leaf + * + * @devlink_port: devlink port linked to the rate object + * + * Destroy the devlink rate object of type leaf on provided @devlink_port. + */ +void devl_rate_leaf_destroy(struct devlink_port *devlink_port) +{ + struct devlink_rate *devlink_rate = devlink_port->devlink_rate; + + devl_assert_locked(devlink_port->devlink); + if (!devlink_rate) + return; + + devlink_rate_notify(devlink_rate, DEVLINK_CMD_RATE_DEL); + if (devlink_rate->parent) + refcount_dec(&devlink_rate->parent->refcnt); + list_del(&devlink_rate->list); + devlink_port->devlink_rate = NULL; + kfree(devlink_rate); +} +EXPORT_SYMBOL_GPL(devl_rate_leaf_destroy); + +/** + * devl_rate_nodes_destroy - destroy all devlink rate nodes on device + * @devlink: devlink instance + * + * Unset parent for all rate objects and destroy all rate nodes + * on specified device. + */ +void devl_rate_nodes_destroy(struct devlink *devlink) +{ + static struct devlink_rate *devlink_rate, *tmp; + const struct devlink_ops *ops = devlink->ops; + + devl_assert_locked(devlink); + + list_for_each_entry(devlink_rate, &devlink->rate_list, list) { + if (!devlink_rate->parent) + continue; + + refcount_dec(&devlink_rate->parent->refcnt); + if (devlink_rate_is_leaf(devlink_rate)) + ops->rate_leaf_parent_set(devlink_rate, NULL, devlink_rate->priv, + NULL, NULL); + else if (devlink_rate_is_node(devlink_rate)) + ops->rate_node_parent_set(devlink_rate, NULL, devlink_rate->priv, + NULL, NULL); + } + list_for_each_entry_safe(devlink_rate, tmp, &devlink->rate_list, list) { + if (devlink_rate_is_node(devlink_rate)) { + ops->rate_node_del(devlink_rate, devlink_rate->priv, NULL); + list_del(&devlink_rate->list); + kfree(devlink_rate->name); + kfree(devlink_rate); + } + } +} +EXPORT_SYMBOL_GPL(devl_rate_nodes_destroy); + +/** + * devlink_port_linecard_set - Link port with a linecard + * + * @devlink_port: devlink port + * @linecard: devlink linecard + */ +void devlink_port_linecard_set(struct devlink_port *devlink_port, + struct devlink_linecard *linecard) +{ + ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port); + + devlink_port->linecard = linecard; +} +EXPORT_SYMBOL_GPL(devlink_port_linecard_set); + +static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port, + char *name, size_t len) +{ + struct devlink_port_attrs *attrs = &devlink_port->attrs; + int n = 0; + + if (!devlink_port->attrs_set) + return -EOPNOTSUPP; + + switch (attrs->flavour) { + case DEVLINK_PORT_FLAVOUR_PHYSICAL: + if (devlink_port->linecard) + n = snprintf(name, len, "l%u", + devlink_port->linecard->index); + if (n < len) + n += snprintf(name + n, len - n, "p%u", + attrs->phys.port_number); + if (n < len && attrs->split) + n += snprintf(name + n, len - n, "s%u", + attrs->phys.split_subport_number); + break; + case DEVLINK_PORT_FLAVOUR_CPU: + case DEVLINK_PORT_FLAVOUR_DSA: + case DEVLINK_PORT_FLAVOUR_UNUSED: + /* As CPU and DSA ports do not have a netdevice associated + * case should not ever happen. + */ + WARN_ON(1); + return -EINVAL; + case DEVLINK_PORT_FLAVOUR_PCI_PF: + if (attrs->pci_pf.external) { + n = snprintf(name, len, "c%u", attrs->pci_pf.controller); + if (n >= len) + return -EINVAL; + len -= n; + name += n; + } + n = snprintf(name, len, "pf%u", attrs->pci_pf.pf); + break; + case DEVLINK_PORT_FLAVOUR_PCI_VF: + if (attrs->pci_vf.external) { + n = snprintf(name, len, "c%u", attrs->pci_vf.controller); + if (n >= len) + return -EINVAL; + len -= n; + name += n; + } + n = snprintf(name, len, "pf%uvf%u", + attrs->pci_vf.pf, attrs->pci_vf.vf); + break; + case DEVLINK_PORT_FLAVOUR_PCI_SF: + if (attrs->pci_sf.external) { + n = snprintf(name, len, "c%u", attrs->pci_sf.controller); + if (n >= len) + return -EINVAL; + len -= n; + name += n; + } + n = snprintf(name, len, "pf%usf%u", attrs->pci_sf.pf, + attrs->pci_sf.sf); + break; + case DEVLINK_PORT_FLAVOUR_VIRTUAL: + return -EOPNOTSUPP; + } + + if (n >= len) + return -EINVAL; + + return 0; +} + +static int devlink_linecard_types_init(struct devlink_linecard *linecard) +{ + struct devlink_linecard_type *linecard_type; + unsigned int count; + int i; + + count = linecard->ops->types_count(linecard, linecard->priv); + linecard->types = kmalloc_array(count, sizeof(*linecard_type), + GFP_KERNEL); + if (!linecard->types) + return -ENOMEM; + linecard->types_count = count; + + for (i = 0; i < count; i++) { + linecard_type = &linecard->types[i]; + linecard->ops->types_get(linecard, linecard->priv, i, + &linecard_type->type, + &linecard_type->priv); + } + return 0; +} + +static void devlink_linecard_types_fini(struct devlink_linecard *linecard) +{ + kfree(linecard->types); +} + +/** + * devlink_linecard_create - Create devlink linecard + * + * @devlink: devlink + * @linecard_index: driver-specific numerical identifier of the linecard + * @ops: linecards ops + * @priv: user priv pointer + * + * Create devlink linecard instance with provided linecard index. + * Caller can use any indexing, even hw-related one. + * + * Return: Line card structure or an ERR_PTR() encoded error code. + */ +struct devlink_linecard * +devlink_linecard_create(struct devlink *devlink, unsigned int linecard_index, + const struct devlink_linecard_ops *ops, void *priv) +{ + struct devlink_linecard *linecard; + int err; + + if (WARN_ON(!ops || !ops->provision || !ops->unprovision || + !ops->types_count || !ops->types_get)) + return ERR_PTR(-EINVAL); + + mutex_lock(&devlink->linecards_lock); + if (devlink_linecard_index_exists(devlink, linecard_index)) { + mutex_unlock(&devlink->linecards_lock); + return ERR_PTR(-EEXIST); + } + + linecard = kzalloc(sizeof(*linecard), GFP_KERNEL); + if (!linecard) { + mutex_unlock(&devlink->linecards_lock); + return ERR_PTR(-ENOMEM); + } + + linecard->devlink = devlink; + linecard->index = linecard_index; + linecard->ops = ops; + linecard->priv = priv; + linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED; + mutex_init(&linecard->state_lock); + + err = devlink_linecard_types_init(linecard); + if (err) { + mutex_destroy(&linecard->state_lock); + kfree(linecard); + mutex_unlock(&devlink->linecards_lock); + return ERR_PTR(err); + } + + list_add_tail(&linecard->list, &devlink->linecard_list); + refcount_set(&linecard->refcount, 1); + mutex_unlock(&devlink->linecards_lock); + devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); + return linecard; +} +EXPORT_SYMBOL_GPL(devlink_linecard_create); + +/** + * devlink_linecard_destroy - Destroy devlink linecard + * + * @linecard: devlink linecard + */ +void devlink_linecard_destroy(struct devlink_linecard *linecard) +{ + struct devlink *devlink = linecard->devlink; + + devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_DEL); + mutex_lock(&devlink->linecards_lock); + list_del(&linecard->list); + devlink_linecard_types_fini(linecard); + mutex_unlock(&devlink->linecards_lock); + devlink_linecard_put(linecard); +} +EXPORT_SYMBOL_GPL(devlink_linecard_destroy); + +/** + * devlink_linecard_provision_set - Set provisioning on linecard + * + * @linecard: devlink linecard + * @type: linecard type + * + * This is either called directly from the provision() op call or + * as a result of the provision() op call asynchronously. + */ +void devlink_linecard_provision_set(struct devlink_linecard *linecard, + const char *type) +{ + mutex_lock(&linecard->state_lock); + WARN_ON(linecard->type && strcmp(linecard->type, type)); + linecard->state = DEVLINK_LINECARD_STATE_PROVISIONED; + linecard->type = type; + devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); + mutex_unlock(&linecard->state_lock); +} +EXPORT_SYMBOL_GPL(devlink_linecard_provision_set); + +/** + * devlink_linecard_provision_clear - Clear provisioning on linecard + * + * @linecard: devlink linecard + * + * This is either called directly from the unprovision() op call or + * as a result of the unprovision() op call asynchronously. + */ +void devlink_linecard_provision_clear(struct devlink_linecard *linecard) +{ + mutex_lock(&linecard->state_lock); + WARN_ON(linecard->nested_devlink); + linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED; + linecard->type = NULL; + devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); + mutex_unlock(&linecard->state_lock); +} +EXPORT_SYMBOL_GPL(devlink_linecard_provision_clear); + +/** + * devlink_linecard_provision_fail - Fail provisioning on linecard + * + * @linecard: devlink linecard + * + * This is either called directly from the provision() op call or + * as a result of the provision() op call asynchronously. + */ +void devlink_linecard_provision_fail(struct devlink_linecard *linecard) +{ + mutex_lock(&linecard->state_lock); + WARN_ON(linecard->nested_devlink); + linecard->state = DEVLINK_LINECARD_STATE_PROVISIONING_FAILED; + devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); + mutex_unlock(&linecard->state_lock); +} +EXPORT_SYMBOL_GPL(devlink_linecard_provision_fail); + +/** + * devlink_linecard_activate - Set linecard active + * + * @linecard: devlink linecard + */ +void devlink_linecard_activate(struct devlink_linecard *linecard) +{ + mutex_lock(&linecard->state_lock); + WARN_ON(linecard->state != DEVLINK_LINECARD_STATE_PROVISIONED); + linecard->state = DEVLINK_LINECARD_STATE_ACTIVE; + devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); + mutex_unlock(&linecard->state_lock); +} +EXPORT_SYMBOL_GPL(devlink_linecard_activate); + +/** + * devlink_linecard_deactivate - Set linecard inactive + * + * @linecard: devlink linecard + */ +void devlink_linecard_deactivate(struct devlink_linecard *linecard) +{ + mutex_lock(&linecard->state_lock); + switch (linecard->state) { + case DEVLINK_LINECARD_STATE_ACTIVE: + linecard->state = DEVLINK_LINECARD_STATE_PROVISIONED; + devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); + break; + case DEVLINK_LINECARD_STATE_UNPROVISIONING: + /* Line card is being deactivated as part + * of unprovisioning flow. + */ + break; + default: + WARN_ON(1); + break; + } + mutex_unlock(&linecard->state_lock); +} +EXPORT_SYMBOL_GPL(devlink_linecard_deactivate); + +/** + * devlink_linecard_nested_dl_set - Attach/detach nested devlink + * instance to linecard. + * + * @linecard: devlink linecard + * @nested_devlink: devlink instance to attach or NULL to detach + */ +void devlink_linecard_nested_dl_set(struct devlink_linecard *linecard, + struct devlink *nested_devlink) +{ + mutex_lock(&linecard->state_lock); + linecard->nested_devlink = nested_devlink; + devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); + mutex_unlock(&linecard->state_lock); +} +EXPORT_SYMBOL_GPL(devlink_linecard_nested_dl_set); + +int devl_sb_register(struct devlink *devlink, unsigned int sb_index, + u32 size, u16 ingress_pools_count, + u16 egress_pools_count, u16 ingress_tc_count, + u16 egress_tc_count) +{ + struct devlink_sb *devlink_sb; + + lockdep_assert_held(&devlink->lock); + + if (devlink_sb_index_exists(devlink, sb_index)) + return -EEXIST; + + devlink_sb = kzalloc(sizeof(*devlink_sb), GFP_KERNEL); + if (!devlink_sb) + return -ENOMEM; + devlink_sb->index = sb_index; + devlink_sb->size = size; + devlink_sb->ingress_pools_count = ingress_pools_count; + devlink_sb->egress_pools_count = egress_pools_count; + devlink_sb->ingress_tc_count = ingress_tc_count; + devlink_sb->egress_tc_count = egress_tc_count; + list_add_tail(&devlink_sb->list, &devlink->sb_list); + return 0; +} +EXPORT_SYMBOL_GPL(devl_sb_register); + +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, + u16 egress_tc_count) +{ + int err; + + devl_lock(devlink); + err = devl_sb_register(devlink, sb_index, size, ingress_pools_count, + egress_pools_count, ingress_tc_count, + egress_tc_count); + devl_unlock(devlink); + return err; +} +EXPORT_SYMBOL_GPL(devlink_sb_register); + +void devl_sb_unregister(struct devlink *devlink, unsigned int sb_index) +{ + struct devlink_sb *devlink_sb; + + lockdep_assert_held(&devlink->lock); + + devlink_sb = devlink_sb_get_by_index(devlink, sb_index); + WARN_ON(!devlink_sb); + list_del(&devlink_sb->list); + kfree(devlink_sb); +} +EXPORT_SYMBOL_GPL(devl_sb_unregister); + +void devlink_sb_unregister(struct devlink *devlink, unsigned int sb_index) +{ + devl_lock(devlink); + devl_sb_unregister(devlink, sb_index); + devl_unlock(devlink); +} +EXPORT_SYMBOL_GPL(devlink_sb_unregister); + +/** + * devl_dpipe_headers_register - register dpipe headers + * + * @devlink: devlink + * @dpipe_headers: dpipe header array + * + * Register the headers supported by hardware. + */ +void devl_dpipe_headers_register(struct devlink *devlink, + struct devlink_dpipe_headers *dpipe_headers) +{ + lockdep_assert_held(&devlink->lock); + + devlink->dpipe_headers = dpipe_headers; +} +EXPORT_SYMBOL_GPL(devl_dpipe_headers_register); + +/** + * devl_dpipe_headers_unregister - unregister dpipe headers + * + * @devlink: devlink + * + * Unregister the headers supported by hardware. + */ +void devl_dpipe_headers_unregister(struct devlink *devlink) +{ + lockdep_assert_held(&devlink->lock); + + devlink->dpipe_headers = NULL; +} +EXPORT_SYMBOL_GPL(devl_dpipe_headers_unregister); + +/** + * devlink_dpipe_table_counter_enabled - check if counter allocation + * required + * @devlink: devlink + * @table_name: tables name + * + * Used by driver to check if counter allocation is required. + * After counter allocation is turned on the table entries + * are updated to include counter statistics. + * + * After that point on the driver must respect the counter + * state so that each entry added to the table is added + * with a counter. + */ +bool devlink_dpipe_table_counter_enabled(struct devlink *devlink, + const char *table_name) +{ + struct devlink_dpipe_table *table; + bool enabled; + + rcu_read_lock(); + table = devlink_dpipe_table_find(&devlink->dpipe_table_list, + table_name, devlink); + enabled = false; + if (table) + enabled = table->counters_enabled; + rcu_read_unlock(); + return enabled; +} +EXPORT_SYMBOL_GPL(devlink_dpipe_table_counter_enabled); + +/** + * devl_dpipe_table_register - register dpipe table + * + * @devlink: devlink + * @table_name: table name + * @table_ops: table ops + * @priv: priv + * @counter_control_extern: external control for counters + */ +int devl_dpipe_table_register(struct devlink *devlink, + const char *table_name, + struct devlink_dpipe_table_ops *table_ops, + void *priv, bool counter_control_extern) +{ + struct devlink_dpipe_table *table; + + lockdep_assert_held(&devlink->lock); + + if (WARN_ON(!table_ops->size_get)) + return -EINVAL; + + if (devlink_dpipe_table_find(&devlink->dpipe_table_list, table_name, + devlink)) + return -EEXIST; + + table = kzalloc(sizeof(*table), GFP_KERNEL); + if (!table) + return -ENOMEM; + + table->name = table_name; + table->table_ops = table_ops; + table->priv = priv; + table->counter_control_extern = counter_control_extern; + + list_add_tail_rcu(&table->list, &devlink->dpipe_table_list); + + return 0; +} +EXPORT_SYMBOL_GPL(devl_dpipe_table_register); + +/** + * devl_dpipe_table_unregister - unregister dpipe table + * + * @devlink: devlink + * @table_name: table name + */ +void devl_dpipe_table_unregister(struct devlink *devlink, + const char *table_name) +{ + struct devlink_dpipe_table *table; + + lockdep_assert_held(&devlink->lock); + + table = devlink_dpipe_table_find(&devlink->dpipe_table_list, + table_name, devlink); + if (!table) + return; + list_del_rcu(&table->list); + kfree_rcu(table, rcu); +} +EXPORT_SYMBOL_GPL(devl_dpipe_table_unregister); + +/** + * devl_resource_register - devlink resource register + * + * @devlink: devlink + * @resource_name: resource's name + * @resource_size: resource's size + * @resource_id: resource's id + * @parent_resource_id: resource's parent id + * @size_params: size parameters + * + * Generic resources should reuse the same names across drivers. + * Please see the generic resources list at: + * Documentation/networking/devlink/devlink-resource.rst + */ +int devl_resource_register(struct devlink *devlink, + const char *resource_name, + u64 resource_size, + u64 resource_id, + u64 parent_resource_id, + const struct devlink_resource_size_params *size_params) +{ + struct devlink_resource *resource; + struct list_head *resource_list; + bool top_hierarchy; + + lockdep_assert_held(&devlink->lock); + + top_hierarchy = parent_resource_id == DEVLINK_RESOURCE_ID_PARENT_TOP; + + resource = devlink_resource_find(devlink, NULL, resource_id); + if (resource) + return -EINVAL; + + resource = kzalloc(sizeof(*resource), GFP_KERNEL); + if (!resource) + return -ENOMEM; + + if (top_hierarchy) { + resource_list = &devlink->resource_list; + } else { + struct devlink_resource *parent_resource; + + parent_resource = devlink_resource_find(devlink, NULL, + parent_resource_id); + if (parent_resource) { + resource_list = &parent_resource->resource_list; + resource->parent = parent_resource; + } else { + kfree(resource); + return -EINVAL; + } + } + + resource->name = resource_name; + resource->size = resource_size; + resource->size_new = resource_size; + resource->id = resource_id; + resource->size_valid = true; + memcpy(&resource->size_params, size_params, + sizeof(resource->size_params)); + INIT_LIST_HEAD(&resource->resource_list); + list_add_tail(&resource->list, resource_list); + + return 0; +} +EXPORT_SYMBOL_GPL(devl_resource_register); + +/** + * devlink_resource_register - devlink resource register + * + * @devlink: devlink + * @resource_name: resource's name + * @resource_size: resource's size + * @resource_id: resource's id + * @parent_resource_id: resource's parent id + * @size_params: size parameters + * + * Generic resources should reuse the same names across drivers. + * Please see the generic resources list at: + * Documentation/networking/devlink/devlink-resource.rst + * + * Context: Takes and release devlink->lock <mutex>. + */ +int devlink_resource_register(struct devlink *devlink, + const char *resource_name, + u64 resource_size, + u64 resource_id, + u64 parent_resource_id, + const struct devlink_resource_size_params *size_params) +{ + int err; + + devl_lock(devlink); + err = devl_resource_register(devlink, resource_name, resource_size, + resource_id, parent_resource_id, size_params); + devl_unlock(devlink); + return err; +} +EXPORT_SYMBOL_GPL(devlink_resource_register); + +static void devlink_resource_unregister(struct devlink *devlink, + struct devlink_resource *resource) +{ + struct devlink_resource *tmp, *child_resource; + + list_for_each_entry_safe(child_resource, tmp, &resource->resource_list, + list) { + devlink_resource_unregister(devlink, child_resource); + list_del(&child_resource->list); + kfree(child_resource); + } +} + +/** + * devl_resources_unregister - free all resources + * + * @devlink: devlink + */ +void devl_resources_unregister(struct devlink *devlink) +{ + struct devlink_resource *tmp, *child_resource; + + lockdep_assert_held(&devlink->lock); + + list_for_each_entry_safe(child_resource, tmp, &devlink->resource_list, + list) { + devlink_resource_unregister(devlink, child_resource); + list_del(&child_resource->list); + kfree(child_resource); + } +} +EXPORT_SYMBOL_GPL(devl_resources_unregister); + +/** + * devlink_resources_unregister - free all resources + * + * @devlink: devlink + * + * Context: Takes and release devlink->lock <mutex>. + */ +void devlink_resources_unregister(struct devlink *devlink) +{ + devl_lock(devlink); + devl_resources_unregister(devlink); + devl_unlock(devlink); +} +EXPORT_SYMBOL_GPL(devlink_resources_unregister); + +/** + * devl_resource_size_get - get and update size + * + * @devlink: devlink + * @resource_id: the requested resource id + * @p_resource_size: ptr to update + */ +int devl_resource_size_get(struct devlink *devlink, + u64 resource_id, + u64 *p_resource_size) +{ + struct devlink_resource *resource; + + lockdep_assert_held(&devlink->lock); + + resource = devlink_resource_find(devlink, NULL, resource_id); + if (!resource) + return -EINVAL; + *p_resource_size = resource->size_new; + resource->size = resource->size_new; + return 0; +} +EXPORT_SYMBOL_GPL(devl_resource_size_get); + +/** + * devl_dpipe_table_resource_set - set the resource id + * + * @devlink: devlink + * @table_name: table name + * @resource_id: resource id + * @resource_units: number of resource's units consumed per table's entry + */ +int devl_dpipe_table_resource_set(struct devlink *devlink, + const char *table_name, u64 resource_id, + u64 resource_units) +{ + struct devlink_dpipe_table *table; + + table = devlink_dpipe_table_find(&devlink->dpipe_table_list, + table_name, devlink); + if (!table) + return -EINVAL; + + table->resource_id = resource_id; + table->resource_units = resource_units; + table->resource_valid = true; + return 0; +} +EXPORT_SYMBOL_GPL(devl_dpipe_table_resource_set); + +/** + * devl_resource_occ_get_register - register occupancy getter + * + * @devlink: devlink + * @resource_id: resource id + * @occ_get: occupancy getter callback + * @occ_get_priv: occupancy getter callback priv + */ +void devl_resource_occ_get_register(struct devlink *devlink, + u64 resource_id, + devlink_resource_occ_get_t *occ_get, + void *occ_get_priv) +{ + struct devlink_resource *resource; + + lockdep_assert_held(&devlink->lock); + + resource = devlink_resource_find(devlink, NULL, resource_id); + if (WARN_ON(!resource)) + return; + WARN_ON(resource->occ_get); + + resource->occ_get = occ_get; + resource->occ_get_priv = occ_get_priv; +} +EXPORT_SYMBOL_GPL(devl_resource_occ_get_register); + +/** + * devlink_resource_occ_get_register - register occupancy getter + * + * @devlink: devlink + * @resource_id: resource id + * @occ_get: occupancy getter callback + * @occ_get_priv: occupancy getter callback priv + * + * Context: Takes and release devlink->lock <mutex>. + */ +void devlink_resource_occ_get_register(struct devlink *devlink, + u64 resource_id, + devlink_resource_occ_get_t *occ_get, + void *occ_get_priv) +{ + devl_lock(devlink); + devl_resource_occ_get_register(devlink, resource_id, + occ_get, occ_get_priv); + devl_unlock(devlink); +} +EXPORT_SYMBOL_GPL(devlink_resource_occ_get_register); + +/** + * devl_resource_occ_get_unregister - unregister occupancy getter + * + * @devlink: devlink + * @resource_id: resource id + */ +void devl_resource_occ_get_unregister(struct devlink *devlink, + u64 resource_id) +{ + struct devlink_resource *resource; + + lockdep_assert_held(&devlink->lock); + + resource = devlink_resource_find(devlink, NULL, resource_id); + if (WARN_ON(!resource)) + return; + WARN_ON(!resource->occ_get); + + resource->occ_get = NULL; + resource->occ_get_priv = NULL; +} +EXPORT_SYMBOL_GPL(devl_resource_occ_get_unregister); + +/** + * devlink_resource_occ_get_unregister - unregister occupancy getter + * + * @devlink: devlink + * @resource_id: resource id + * + * Context: Takes and release devlink->lock <mutex>. + */ +void devlink_resource_occ_get_unregister(struct devlink *devlink, + u64 resource_id) +{ + devl_lock(devlink); + devl_resource_occ_get_unregister(devlink, resource_id); + devl_unlock(devlink); +} +EXPORT_SYMBOL_GPL(devlink_resource_occ_get_unregister); + +static int devlink_param_verify(const struct devlink_param *param) +{ + if (!param || !param->name || !param->supported_cmodes) + return -EINVAL; + if (param->generic) + return devlink_param_generic_verify(param); + else + return devlink_param_driver_verify(param); +} + +/** + * devlink_params_register - register configuration parameters + * + * @devlink: devlink + * @params: configuration parameters array + * @params_count: number of parameters provided + * + * Register the configuration parameters supported by the driver. + */ +int devlink_params_register(struct devlink *devlink, + const struct devlink_param *params, + size_t params_count) +{ + const struct devlink_param *param = params; + int i, err; + + ASSERT_DEVLINK_NOT_REGISTERED(devlink); + + for (i = 0; i < params_count; i++, param++) { + err = devlink_param_register(devlink, param); + if (err) + goto rollback; + } + return 0; + +rollback: + if (!i) + return err; + + for (param--; i > 0; i--, param--) + devlink_param_unregister(devlink, param); + return err; +} +EXPORT_SYMBOL_GPL(devlink_params_register); + +/** + * devlink_params_unregister - unregister configuration parameters + * @devlink: devlink + * @params: configuration parameters to unregister + * @params_count: number of parameters provided + */ +void devlink_params_unregister(struct devlink *devlink, + const struct devlink_param *params, + size_t params_count) +{ + const struct devlink_param *param = params; + int i; + + ASSERT_DEVLINK_NOT_REGISTERED(devlink); + + for (i = 0; i < params_count; i++, param++) + devlink_param_unregister(devlink, param); +} +EXPORT_SYMBOL_GPL(devlink_params_unregister); + +/** + * devlink_param_register - register one configuration parameter + * + * @devlink: devlink + * @param: one configuration parameter + * + * Register the configuration parameter supported by the driver. + * Return: returns 0 on successful registration or error code otherwise. + */ +int devlink_param_register(struct devlink *devlink, + const struct devlink_param *param) +{ + struct devlink_param_item *param_item; + + ASSERT_DEVLINK_NOT_REGISTERED(devlink); + + WARN_ON(devlink_param_verify(param)); + WARN_ON(devlink_param_find_by_name(&devlink->param_list, param->name)); + + if (param->supported_cmodes == BIT(DEVLINK_PARAM_CMODE_DRIVERINIT)) + WARN_ON(param->get || param->set); + else + WARN_ON(!param->get || !param->set); + + param_item = kzalloc(sizeof(*param_item), GFP_KERNEL); + if (!param_item) + return -ENOMEM; + + param_item->param = param; + + list_add_tail(&param_item->list, &devlink->param_list); + return 0; +} +EXPORT_SYMBOL_GPL(devlink_param_register); + +/** + * devlink_param_unregister - unregister one configuration parameter + * @devlink: devlink + * @param: configuration parameter to unregister + */ +void devlink_param_unregister(struct devlink *devlink, + const struct devlink_param *param) +{ + struct devlink_param_item *param_item; + + ASSERT_DEVLINK_NOT_REGISTERED(devlink); + + param_item = + devlink_param_find_by_name(&devlink->param_list, param->name); + WARN_ON(!param_item); + list_del(&param_item->list); + kfree(param_item); +} +EXPORT_SYMBOL_GPL(devlink_param_unregister); + +/** + * devlink_param_driverinit_value_get - get configuration parameter + * value for driver initializing + * + * @devlink: devlink + * @param_id: parameter ID + * @init_val: value of parameter in driverinit configuration mode + * + * This function should be used by the driver to get driverinit + * configuration for initialization after reload command. + */ +int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id, + union devlink_param_value *init_val) +{ + struct devlink_param_item *param_item; + + if (!devlink_reload_supported(devlink->ops)) + return -EOPNOTSUPP; + + param_item = devlink_param_find_by_id(&devlink->param_list, param_id); + if (!param_item) + return -EINVAL; + + if (!param_item->driverinit_value_valid || + !devlink_param_cmode_is_supported(param_item->param, + DEVLINK_PARAM_CMODE_DRIVERINIT)) + return -EOPNOTSUPP; + + if (param_item->param->type == DEVLINK_PARAM_TYPE_STRING) + strcpy(init_val->vstr, param_item->driverinit_value.vstr); + else + *init_val = param_item->driverinit_value; + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_param_driverinit_value_get); + +/** + * devlink_param_driverinit_value_set - set value of configuration + * parameter for driverinit + * configuration mode + * + * @devlink: devlink + * @param_id: parameter ID + * @init_val: value of parameter to set for driverinit configuration mode + * + * This function should be used by the driver to set driverinit + * configuration mode default value. + */ +int devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id, + union devlink_param_value init_val) +{ + struct devlink_param_item *param_item; + + ASSERT_DEVLINK_NOT_REGISTERED(devlink); + + param_item = devlink_param_find_by_id(&devlink->param_list, param_id); + if (!param_item) + return -EINVAL; + + if (!devlink_param_cmode_is_supported(param_item->param, + DEVLINK_PARAM_CMODE_DRIVERINIT)) + return -EOPNOTSUPP; + + if (param_item->param->type == DEVLINK_PARAM_TYPE_STRING) + strcpy(param_item->driverinit_value.vstr, init_val.vstr); + else + param_item->driverinit_value = init_val; + param_item->driverinit_value_valid = true; + return 0; +} +EXPORT_SYMBOL_GPL(devlink_param_driverinit_value_set); + +/** + * devlink_param_value_changed - notify devlink on a parameter's value + * change. Should be called by the driver + * right after the change. + * + * @devlink: devlink + * @param_id: parameter ID + * + * This function should be used by the driver to notify devlink on value + * change, excluding driverinit configuration mode. + * For driverinit configuration mode driver should use the function + */ +void devlink_param_value_changed(struct devlink *devlink, u32 param_id) +{ + struct devlink_param_item *param_item; + + param_item = devlink_param_find_by_id(&devlink->param_list, param_id); + WARN_ON(!param_item); + + devlink_param_notify(devlink, 0, param_item, DEVLINK_CMD_PARAM_NEW); +} +EXPORT_SYMBOL_GPL(devlink_param_value_changed); + +/** + * devl_region_create - create a new address region + * + * @devlink: devlink + * @ops: region operations and name + * @region_max_snapshots: Maximum supported number of snapshots for region + * @region_size: size of region + */ +struct devlink_region *devl_region_create(struct devlink *devlink, + const struct devlink_region_ops *ops, + u32 region_max_snapshots, + u64 region_size) +{ + struct devlink_region *region; + + devl_assert_locked(devlink); + + if (WARN_ON(!ops) || WARN_ON(!ops->destructor)) + return ERR_PTR(-EINVAL); + + if (devlink_region_get_by_name(devlink, ops->name)) + return ERR_PTR(-EEXIST); + + region = kzalloc(sizeof(*region), GFP_KERNEL); + if (!region) + return ERR_PTR(-ENOMEM); + + region->devlink = devlink; + region->max_snapshots = region_max_snapshots; + region->ops = ops; + region->size = region_size; + INIT_LIST_HEAD(&region->snapshot_list); + mutex_init(&region->snapshot_lock); + list_add_tail(&region->list, &devlink->region_list); + devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_NEW); + + return region; +} +EXPORT_SYMBOL_GPL(devl_region_create); + +/** + * devlink_region_create - create a new address region + * + * @devlink: devlink + * @ops: region operations and name + * @region_max_snapshots: Maximum supported number of snapshots for region + * @region_size: size of region + * + * Context: Takes and release devlink->lock <mutex>. + */ +struct devlink_region * +devlink_region_create(struct devlink *devlink, + const struct devlink_region_ops *ops, + u32 region_max_snapshots, u64 region_size) +{ + struct devlink_region *region; + + devl_lock(devlink); + region = devl_region_create(devlink, ops, region_max_snapshots, + region_size); + devl_unlock(devlink); + return region; +} +EXPORT_SYMBOL_GPL(devlink_region_create); + +/** + * devlink_port_region_create - create a new address region for a port + * + * @port: devlink port + * @ops: region operations and name + * @region_max_snapshots: Maximum supported number of snapshots for region + * @region_size: size of region + * + * Context: Takes and release devlink->lock <mutex>. + */ +struct devlink_region * +devlink_port_region_create(struct devlink_port *port, + const struct devlink_port_region_ops *ops, + u32 region_max_snapshots, u64 region_size) +{ + struct devlink *devlink = port->devlink; + struct devlink_region *region; + int err = 0; + + ASSERT_DEVLINK_PORT_INITIALIZED(port); + + if (WARN_ON(!ops) || WARN_ON(!ops->destructor)) + return ERR_PTR(-EINVAL); + + devl_lock(devlink); + + if (devlink_port_region_get_by_name(port, ops->name)) { + err = -EEXIST; + goto unlock; + } + + region = kzalloc(sizeof(*region), GFP_KERNEL); + if (!region) { + err = -ENOMEM; + goto unlock; + } + + region->devlink = devlink; + region->port = port; + region->max_snapshots = region_max_snapshots; + region->port_ops = ops; + region->size = region_size; + INIT_LIST_HEAD(&region->snapshot_list); + mutex_init(&region->snapshot_lock); + list_add_tail(&region->list, &port->region_list); + devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_NEW); + + devl_unlock(devlink); + return region; + +unlock: + devl_unlock(devlink); + return ERR_PTR(err); +} +EXPORT_SYMBOL_GPL(devlink_port_region_create); + +/** + * devl_region_destroy - destroy address region + * + * @region: devlink region to destroy + */ +void devl_region_destroy(struct devlink_region *region) +{ + struct devlink *devlink = region->devlink; + struct devlink_snapshot *snapshot, *ts; + + devl_assert_locked(devlink); + + /* Free all snapshots of region */ + mutex_lock(&region->snapshot_lock); + list_for_each_entry_safe(snapshot, ts, &region->snapshot_list, list) + devlink_region_snapshot_del(region, snapshot); + mutex_unlock(&region->snapshot_lock); + + list_del(&region->list); + mutex_destroy(&region->snapshot_lock); + + devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_DEL); + kfree(region); +} +EXPORT_SYMBOL_GPL(devl_region_destroy); + +/** + * devlink_region_destroy - destroy address region + * + * @region: devlink region to destroy + * + * Context: Takes and release devlink->lock <mutex>. + */ +void devlink_region_destroy(struct devlink_region *region) +{ + struct devlink *devlink = region->devlink; + + devl_lock(devlink); + devl_region_destroy(region); + devl_unlock(devlink); +} +EXPORT_SYMBOL_GPL(devlink_region_destroy); + +/** + * devlink_region_snapshot_id_get - get snapshot ID + * + * This callback should be called when adding a new snapshot, + * Driver should use the same id for multiple snapshots taken + * on multiple regions at the same time/by the same trigger. + * + * The caller of this function must use devlink_region_snapshot_id_put + * when finished creating regions using this id. + * + * Returns zero on success, or a negative error code on failure. + * + * @devlink: devlink + * @id: storage to return id + */ +int devlink_region_snapshot_id_get(struct devlink *devlink, u32 *id) +{ + return __devlink_region_snapshot_id_get(devlink, id); +} +EXPORT_SYMBOL_GPL(devlink_region_snapshot_id_get); + +/** + * devlink_region_snapshot_id_put - put snapshot ID reference + * + * This should be called by a driver after finishing creating snapshots + * with an id. Doing so ensures that the ID can later be released in the + * event that all snapshots using it have been destroyed. + * + * @devlink: devlink + * @id: id to release reference on + */ +void devlink_region_snapshot_id_put(struct devlink *devlink, u32 id) +{ + __devlink_snapshot_id_decrement(devlink, id); +} +EXPORT_SYMBOL_GPL(devlink_region_snapshot_id_put); + +/** + * devlink_region_snapshot_create - create a new snapshot + * This will add a new snapshot of a region. The snapshot + * will be stored on the region struct and can be accessed + * from devlink. This is useful for future analyses of snapshots. + * Multiple snapshots can be created on a region. + * The @snapshot_id should be obtained using the getter function. + * + * @region: devlink region of the snapshot + * @data: snapshot data + * @snapshot_id: snapshot id to be created + */ +int devlink_region_snapshot_create(struct devlink_region *region, + u8 *data, u32 snapshot_id) +{ + int err; + + mutex_lock(&region->snapshot_lock); + err = __devlink_region_snapshot_create(region, data, snapshot_id); + mutex_unlock(&region->snapshot_lock); + return err; +} +EXPORT_SYMBOL_GPL(devlink_region_snapshot_create); + +#define DEVLINK_TRAP(_id, _type) \ + { \ + .type = DEVLINK_TRAP_TYPE_##_type, \ + .id = DEVLINK_TRAP_GENERIC_ID_##_id, \ + .name = DEVLINK_TRAP_GENERIC_NAME_##_id, \ + } + +static const struct devlink_trap devlink_trap_generic[] = { + DEVLINK_TRAP(SMAC_MC, DROP), + DEVLINK_TRAP(VLAN_TAG_MISMATCH, DROP), + DEVLINK_TRAP(INGRESS_VLAN_FILTER, DROP), + DEVLINK_TRAP(INGRESS_STP_FILTER, DROP), + DEVLINK_TRAP(EMPTY_TX_LIST, DROP), + DEVLINK_TRAP(PORT_LOOPBACK_FILTER, DROP), + DEVLINK_TRAP(BLACKHOLE_ROUTE, DROP), + DEVLINK_TRAP(TTL_ERROR, EXCEPTION), + DEVLINK_TRAP(TAIL_DROP, DROP), + DEVLINK_TRAP(NON_IP_PACKET, DROP), + DEVLINK_TRAP(UC_DIP_MC_DMAC, DROP), + DEVLINK_TRAP(DIP_LB, DROP), + DEVLINK_TRAP(SIP_MC, DROP), + DEVLINK_TRAP(SIP_LB, DROP), + DEVLINK_TRAP(CORRUPTED_IP_HDR, DROP), + DEVLINK_TRAP(IPV4_SIP_BC, DROP), + DEVLINK_TRAP(IPV6_MC_DIP_RESERVED_SCOPE, DROP), + DEVLINK_TRAP(IPV6_MC_DIP_INTERFACE_LOCAL_SCOPE, DROP), + DEVLINK_TRAP(MTU_ERROR, EXCEPTION), + DEVLINK_TRAP(UNRESOLVED_NEIGH, EXCEPTION), + DEVLINK_TRAP(RPF, EXCEPTION), + DEVLINK_TRAP(REJECT_ROUTE, EXCEPTION), + DEVLINK_TRAP(IPV4_LPM_UNICAST_MISS, EXCEPTION), + DEVLINK_TRAP(IPV6_LPM_UNICAST_MISS, EXCEPTION), + DEVLINK_TRAP(NON_ROUTABLE, DROP), + DEVLINK_TRAP(DECAP_ERROR, EXCEPTION), + DEVLINK_TRAP(OVERLAY_SMAC_MC, DROP), + DEVLINK_TRAP(INGRESS_FLOW_ACTION_DROP, DROP), + DEVLINK_TRAP(EGRESS_FLOW_ACTION_DROP, DROP), + DEVLINK_TRAP(STP, CONTROL), + DEVLINK_TRAP(LACP, CONTROL), + DEVLINK_TRAP(LLDP, CONTROL), + DEVLINK_TRAP(IGMP_QUERY, CONTROL), + DEVLINK_TRAP(IGMP_V1_REPORT, CONTROL), + DEVLINK_TRAP(IGMP_V2_REPORT, CONTROL), + DEVLINK_TRAP(IGMP_V3_REPORT, CONTROL), + DEVLINK_TRAP(IGMP_V2_LEAVE, CONTROL), + DEVLINK_TRAP(MLD_QUERY, CONTROL), + DEVLINK_TRAP(MLD_V1_REPORT, CONTROL), + DEVLINK_TRAP(MLD_V2_REPORT, CONTROL), + DEVLINK_TRAP(MLD_V1_DONE, CONTROL), + DEVLINK_TRAP(IPV4_DHCP, CONTROL), + DEVLINK_TRAP(IPV6_DHCP, CONTROL), + DEVLINK_TRAP(ARP_REQUEST, CONTROL), + DEVLINK_TRAP(ARP_RESPONSE, CONTROL), + DEVLINK_TRAP(ARP_OVERLAY, CONTROL), + DEVLINK_TRAP(IPV6_NEIGH_SOLICIT, CONTROL), + DEVLINK_TRAP(IPV6_NEIGH_ADVERT, CONTROL), + DEVLINK_TRAP(IPV4_BFD, CONTROL), + DEVLINK_TRAP(IPV6_BFD, CONTROL), + DEVLINK_TRAP(IPV4_OSPF, CONTROL), + DEVLINK_TRAP(IPV6_OSPF, CONTROL), + DEVLINK_TRAP(IPV4_BGP, CONTROL), + DEVLINK_TRAP(IPV6_BGP, CONTROL), + DEVLINK_TRAP(IPV4_VRRP, CONTROL), + DEVLINK_TRAP(IPV6_VRRP, CONTROL), + DEVLINK_TRAP(IPV4_PIM, CONTROL), + DEVLINK_TRAP(IPV6_PIM, CONTROL), + DEVLINK_TRAP(UC_LB, CONTROL), + DEVLINK_TRAP(LOCAL_ROUTE, CONTROL), + DEVLINK_TRAP(EXTERNAL_ROUTE, CONTROL), + DEVLINK_TRAP(IPV6_UC_DIP_LINK_LOCAL_SCOPE, CONTROL), + DEVLINK_TRAP(IPV6_DIP_ALL_NODES, CONTROL), + DEVLINK_TRAP(IPV6_DIP_ALL_ROUTERS, CONTROL), + DEVLINK_TRAP(IPV6_ROUTER_SOLICIT, CONTROL), + DEVLINK_TRAP(IPV6_ROUTER_ADVERT, CONTROL), + DEVLINK_TRAP(IPV6_REDIRECT, CONTROL), + DEVLINK_TRAP(IPV4_ROUTER_ALERT, CONTROL), + DEVLINK_TRAP(IPV6_ROUTER_ALERT, CONTROL), + DEVLINK_TRAP(PTP_EVENT, CONTROL), + DEVLINK_TRAP(PTP_GENERAL, CONTROL), + DEVLINK_TRAP(FLOW_ACTION_SAMPLE, CONTROL), + DEVLINK_TRAP(FLOW_ACTION_TRAP, CONTROL), + DEVLINK_TRAP(EARLY_DROP, DROP), + DEVLINK_TRAP(VXLAN_PARSING, DROP), + DEVLINK_TRAP(LLC_SNAP_PARSING, DROP), + DEVLINK_TRAP(VLAN_PARSING, DROP), + DEVLINK_TRAP(PPPOE_PPP_PARSING, DROP), + DEVLINK_TRAP(MPLS_PARSING, DROP), + DEVLINK_TRAP(ARP_PARSING, DROP), + DEVLINK_TRAP(IP_1_PARSING, DROP), + DEVLINK_TRAP(IP_N_PARSING, DROP), + DEVLINK_TRAP(GRE_PARSING, DROP), + DEVLINK_TRAP(UDP_PARSING, DROP), + DEVLINK_TRAP(TCP_PARSING, DROP), + DEVLINK_TRAP(IPSEC_PARSING, DROP), + DEVLINK_TRAP(SCTP_PARSING, DROP), + DEVLINK_TRAP(DCCP_PARSING, DROP), + DEVLINK_TRAP(GTP_PARSING, DROP), + DEVLINK_TRAP(ESP_PARSING, DROP), + DEVLINK_TRAP(BLACKHOLE_NEXTHOP, DROP), + DEVLINK_TRAP(DMAC_FILTER, DROP), +}; + +#define DEVLINK_TRAP_GROUP(_id) \ + { \ + .id = DEVLINK_TRAP_GROUP_GENERIC_ID_##_id, \ + .name = DEVLINK_TRAP_GROUP_GENERIC_NAME_##_id, \ + } + +static const struct devlink_trap_group devlink_trap_group_generic[] = { + DEVLINK_TRAP_GROUP(L2_DROPS), + DEVLINK_TRAP_GROUP(L3_DROPS), + DEVLINK_TRAP_GROUP(L3_EXCEPTIONS), + DEVLINK_TRAP_GROUP(BUFFER_DROPS), + DEVLINK_TRAP_GROUP(TUNNEL_DROPS), + DEVLINK_TRAP_GROUP(ACL_DROPS), + DEVLINK_TRAP_GROUP(STP), + DEVLINK_TRAP_GROUP(LACP), + DEVLINK_TRAP_GROUP(LLDP), + DEVLINK_TRAP_GROUP(MC_SNOOPING), + DEVLINK_TRAP_GROUP(DHCP), + DEVLINK_TRAP_GROUP(NEIGH_DISCOVERY), + DEVLINK_TRAP_GROUP(BFD), + DEVLINK_TRAP_GROUP(OSPF), + DEVLINK_TRAP_GROUP(BGP), + DEVLINK_TRAP_GROUP(VRRP), + DEVLINK_TRAP_GROUP(PIM), + DEVLINK_TRAP_GROUP(UC_LB), + DEVLINK_TRAP_GROUP(LOCAL_DELIVERY), + DEVLINK_TRAP_GROUP(EXTERNAL_DELIVERY), + DEVLINK_TRAP_GROUP(IPV6), + DEVLINK_TRAP_GROUP(PTP_EVENT), + DEVLINK_TRAP_GROUP(PTP_GENERAL), + DEVLINK_TRAP_GROUP(ACL_SAMPLE), + DEVLINK_TRAP_GROUP(ACL_TRAP), + DEVLINK_TRAP_GROUP(PARSER_ERROR_DROPS), +}; + +static int devlink_trap_generic_verify(const struct devlink_trap *trap) +{ + if (trap->id > DEVLINK_TRAP_GENERIC_ID_MAX) + return -EINVAL; + + if (strcmp(trap->name, devlink_trap_generic[trap->id].name)) + return -EINVAL; + + if (trap->type != devlink_trap_generic[trap->id].type) + return -EINVAL; + + return 0; +} + +static int devlink_trap_driver_verify(const struct devlink_trap *trap) +{ + int i; + + if (trap->id <= DEVLINK_TRAP_GENERIC_ID_MAX) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(devlink_trap_generic); i++) { + if (!strcmp(trap->name, devlink_trap_generic[i].name)) + return -EEXIST; + } + + return 0; +} + +static int devlink_trap_verify(const struct devlink_trap *trap) +{ + if (!trap || !trap->name) + return -EINVAL; + + if (trap->generic) + return devlink_trap_generic_verify(trap); + else + return devlink_trap_driver_verify(trap); +} + +static int +devlink_trap_group_generic_verify(const struct devlink_trap_group *group) +{ + if (group->id > DEVLINK_TRAP_GROUP_GENERIC_ID_MAX) + return -EINVAL; + + if (strcmp(group->name, devlink_trap_group_generic[group->id].name)) + return -EINVAL; + + return 0; +} + +static int +devlink_trap_group_driver_verify(const struct devlink_trap_group *group) +{ + int i; + + if (group->id <= DEVLINK_TRAP_GROUP_GENERIC_ID_MAX) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(devlink_trap_group_generic); i++) { + if (!strcmp(group->name, devlink_trap_group_generic[i].name)) + return -EEXIST; + } + + return 0; +} + +static int devlink_trap_group_verify(const struct devlink_trap_group *group) +{ + if (group->generic) + return devlink_trap_group_generic_verify(group); + else + return devlink_trap_group_driver_verify(group); +} + +static void +devlink_trap_group_notify(struct devlink *devlink, + const struct devlink_trap_group_item *group_item, + enum devlink_command cmd) +{ + struct sk_buff *msg; + int err; + + WARN_ON_ONCE(cmd != DEVLINK_CMD_TRAP_GROUP_NEW && + cmd != DEVLINK_CMD_TRAP_GROUP_DEL); + if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)) + return; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + err = devlink_nl_trap_group_fill(msg, devlink, group_item, cmd, 0, 0, + 0); + if (err) { + nlmsg_free(msg); + return; + } + + genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), + msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); +} + +static int +devlink_trap_item_group_link(struct devlink *devlink, + struct devlink_trap_item *trap_item) +{ + u16 group_id = trap_item->trap->init_group_id; + struct devlink_trap_group_item *group_item; + + group_item = devlink_trap_group_item_lookup_by_id(devlink, group_id); + if (WARN_ON_ONCE(!group_item)) + return -EINVAL; + + trap_item->group_item = group_item; + + return 0; +} + +static void devlink_trap_notify(struct devlink *devlink, + const struct devlink_trap_item *trap_item, + enum devlink_command cmd) +{ + struct sk_buff *msg; + int err; + + WARN_ON_ONCE(cmd != DEVLINK_CMD_TRAP_NEW && + cmd != DEVLINK_CMD_TRAP_DEL); + if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)) + return; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + err = devlink_nl_trap_fill(msg, devlink, trap_item, cmd, 0, 0, 0); + if (err) { + nlmsg_free(msg); + return; + } + + genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), + msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); +} + +static int +devlink_trap_register(struct devlink *devlink, + const struct devlink_trap *trap, void *priv) +{ + struct devlink_trap_item *trap_item; + int err; + + if (devlink_trap_item_lookup(devlink, trap->name)) + return -EEXIST; + + trap_item = kzalloc(sizeof(*trap_item), GFP_KERNEL); + if (!trap_item) + return -ENOMEM; + + trap_item->stats = netdev_alloc_pcpu_stats(struct devlink_stats); + if (!trap_item->stats) { + err = -ENOMEM; + goto err_stats_alloc; + } + + trap_item->trap = trap; + trap_item->action = trap->init_action; + trap_item->priv = priv; + + err = devlink_trap_item_group_link(devlink, trap_item); + if (err) + goto err_group_link; + + err = devlink->ops->trap_init(devlink, trap, trap_item); + if (err) + goto err_trap_init; + + list_add_tail(&trap_item->list, &devlink->trap_list); + devlink_trap_notify(devlink, trap_item, DEVLINK_CMD_TRAP_NEW); + + return 0; + +err_trap_init: +err_group_link: + free_percpu(trap_item->stats); +err_stats_alloc: + kfree(trap_item); + return err; +} + +static void devlink_trap_unregister(struct devlink *devlink, + const struct devlink_trap *trap) +{ + struct devlink_trap_item *trap_item; + + trap_item = devlink_trap_item_lookup(devlink, trap->name); + if (WARN_ON_ONCE(!trap_item)) + return; + + devlink_trap_notify(devlink, trap_item, DEVLINK_CMD_TRAP_DEL); + list_del(&trap_item->list); + if (devlink->ops->trap_fini) + devlink->ops->trap_fini(devlink, trap, trap_item); + free_percpu(trap_item->stats); + kfree(trap_item); +} + +static void devlink_trap_disable(struct devlink *devlink, + const struct devlink_trap *trap) +{ + struct devlink_trap_item *trap_item; + + trap_item = devlink_trap_item_lookup(devlink, trap->name); + if (WARN_ON_ONCE(!trap_item)) + return; + + devlink->ops->trap_action_set(devlink, trap, DEVLINK_TRAP_ACTION_DROP, + NULL); + trap_item->action = DEVLINK_TRAP_ACTION_DROP; +} + +/** + * devl_traps_register - Register packet traps with devlink. + * @devlink: devlink. + * @traps: Packet traps. + * @traps_count: Count of provided packet traps. + * @priv: Driver private information. + * + * Return: Non-zero value on failure. + */ +int devl_traps_register(struct devlink *devlink, + const struct devlink_trap *traps, + size_t traps_count, void *priv) +{ + int i, err; + + if (!devlink->ops->trap_init || !devlink->ops->trap_action_set) + return -EINVAL; + + devl_assert_locked(devlink); + for (i = 0; i < traps_count; i++) { + const struct devlink_trap *trap = &traps[i]; + + err = devlink_trap_verify(trap); + if (err) + goto err_trap_verify; + + err = devlink_trap_register(devlink, trap, priv); + if (err) + goto err_trap_register; + } + + return 0; + +err_trap_register: +err_trap_verify: + for (i--; i >= 0; i--) + devlink_trap_unregister(devlink, &traps[i]); + return err; +} +EXPORT_SYMBOL_GPL(devl_traps_register); + +/** + * devlink_traps_register - Register packet traps with devlink. + * @devlink: devlink. + * @traps: Packet traps. + * @traps_count: Count of provided packet traps. + * @priv: Driver private information. + * + * Context: Takes and release devlink->lock <mutex>. + * + * Return: Non-zero value on failure. + */ +int devlink_traps_register(struct devlink *devlink, + const struct devlink_trap *traps, + size_t traps_count, void *priv) +{ + int err; + + devl_lock(devlink); + err = devl_traps_register(devlink, traps, traps_count, priv); + devl_unlock(devlink); + return err; +} +EXPORT_SYMBOL_GPL(devlink_traps_register); + +/** + * devl_traps_unregister - Unregister packet traps from devlink. + * @devlink: devlink. + * @traps: Packet traps. + * @traps_count: Count of provided packet traps. + */ +void devl_traps_unregister(struct devlink *devlink, + const struct devlink_trap *traps, + size_t traps_count) +{ + int i; + + devl_assert_locked(devlink); + /* Make sure we do not have any packets in-flight while unregistering + * traps by disabling all of them and waiting for a grace period. + */ + for (i = traps_count - 1; i >= 0; i--) + devlink_trap_disable(devlink, &traps[i]); + synchronize_rcu(); + for (i = traps_count - 1; i >= 0; i--) + devlink_trap_unregister(devlink, &traps[i]); +} +EXPORT_SYMBOL_GPL(devl_traps_unregister); + +/** + * devlink_traps_unregister - Unregister packet traps from devlink. + * @devlink: devlink. + * @traps: Packet traps. + * @traps_count: Count of provided packet traps. + * + * Context: Takes and release devlink->lock <mutex>. + */ +void devlink_traps_unregister(struct devlink *devlink, + const struct devlink_trap *traps, + size_t traps_count) +{ + devl_lock(devlink); + devl_traps_unregister(devlink, traps, traps_count); + devl_unlock(devlink); +} +EXPORT_SYMBOL_GPL(devlink_traps_unregister); + +static void +devlink_trap_stats_update(struct devlink_stats __percpu *trap_stats, + size_t skb_len) +{ + struct devlink_stats *stats; + + stats = this_cpu_ptr(trap_stats); + u64_stats_update_begin(&stats->syncp); + u64_stats_add(&stats->rx_bytes, skb_len); + u64_stats_inc(&stats->rx_packets); + u64_stats_update_end(&stats->syncp); +} + +static void +devlink_trap_report_metadata_set(struct devlink_trap_metadata *metadata, + const struct devlink_trap_item *trap_item, + struct devlink_port *in_devlink_port, + const struct flow_action_cookie *fa_cookie) +{ + metadata->trap_name = trap_item->trap->name; + metadata->trap_group_name = trap_item->group_item->group->name; + metadata->fa_cookie = fa_cookie; + metadata->trap_type = trap_item->trap->type; + + spin_lock(&in_devlink_port->type_lock); + if (in_devlink_port->type == DEVLINK_PORT_TYPE_ETH) + metadata->input_dev = in_devlink_port->type_dev; + spin_unlock(&in_devlink_port->type_lock); +} + +/** + * devlink_trap_report - Report trapped packet to drop monitor. + * @devlink: devlink. + * @skb: Trapped packet. + * @trap_ctx: Trap context. + * @in_devlink_port: Input devlink port. + * @fa_cookie: Flow action cookie. Could be NULL. + */ +void devlink_trap_report(struct devlink *devlink, struct sk_buff *skb, + void *trap_ctx, struct devlink_port *in_devlink_port, + const struct flow_action_cookie *fa_cookie) + +{ + struct devlink_trap_item *trap_item = trap_ctx; + + devlink_trap_stats_update(trap_item->stats, skb->len); + devlink_trap_stats_update(trap_item->group_item->stats, skb->len); + + if (trace_devlink_trap_report_enabled()) { + struct devlink_trap_metadata metadata = {}; + + devlink_trap_report_metadata_set(&metadata, trap_item, + in_devlink_port, fa_cookie); + trace_devlink_trap_report(devlink, skb, &metadata); + } +} +EXPORT_SYMBOL_GPL(devlink_trap_report); + +/** + * devlink_trap_ctx_priv - Trap context to driver private information. + * @trap_ctx: Trap context. + * + * Return: Driver private information passed during registration. + */ +void *devlink_trap_ctx_priv(void *trap_ctx) +{ + struct devlink_trap_item *trap_item = trap_ctx; + + return trap_item->priv; +} +EXPORT_SYMBOL_GPL(devlink_trap_ctx_priv); + +static int +devlink_trap_group_item_policer_link(struct devlink *devlink, + struct devlink_trap_group_item *group_item) +{ + u32 policer_id = group_item->group->init_policer_id; + struct devlink_trap_policer_item *policer_item; + + if (policer_id == 0) + return 0; + + policer_item = devlink_trap_policer_item_lookup(devlink, policer_id); + if (WARN_ON_ONCE(!policer_item)) + return -EINVAL; + + group_item->policer_item = policer_item; + + return 0; +} + +static int +devlink_trap_group_register(struct devlink *devlink, + const struct devlink_trap_group *group) +{ + struct devlink_trap_group_item *group_item; + int err; + + if (devlink_trap_group_item_lookup(devlink, group->name)) + return -EEXIST; + + group_item = kzalloc(sizeof(*group_item), GFP_KERNEL); + if (!group_item) + return -ENOMEM; + + group_item->stats = netdev_alloc_pcpu_stats(struct devlink_stats); + if (!group_item->stats) { + err = -ENOMEM; + goto err_stats_alloc; + } + + group_item->group = group; + + err = devlink_trap_group_item_policer_link(devlink, group_item); + if (err) + goto err_policer_link; + + if (devlink->ops->trap_group_init) { + err = devlink->ops->trap_group_init(devlink, group); + if (err) + goto err_group_init; + } + + list_add_tail(&group_item->list, &devlink->trap_group_list); + devlink_trap_group_notify(devlink, group_item, + DEVLINK_CMD_TRAP_GROUP_NEW); + + return 0; + +err_group_init: +err_policer_link: + free_percpu(group_item->stats); +err_stats_alloc: + kfree(group_item); + return err; +} + +static void +devlink_trap_group_unregister(struct devlink *devlink, + const struct devlink_trap_group *group) +{ + struct devlink_trap_group_item *group_item; + + group_item = devlink_trap_group_item_lookup(devlink, group->name); + if (WARN_ON_ONCE(!group_item)) + return; + + devlink_trap_group_notify(devlink, group_item, + DEVLINK_CMD_TRAP_GROUP_DEL); + list_del(&group_item->list); + free_percpu(group_item->stats); + kfree(group_item); +} + +/** + * devl_trap_groups_register - Register packet trap groups with devlink. + * @devlink: devlink. + * @groups: Packet trap groups. + * @groups_count: Count of provided packet trap groups. + * + * Return: Non-zero value on failure. + */ +int devl_trap_groups_register(struct devlink *devlink, + const struct devlink_trap_group *groups, + size_t groups_count) +{ + int i, err; + + devl_assert_locked(devlink); + for (i = 0; i < groups_count; i++) { + const struct devlink_trap_group *group = &groups[i]; + + err = devlink_trap_group_verify(group); + if (err) + goto err_trap_group_verify; + + err = devlink_trap_group_register(devlink, group); + if (err) + goto err_trap_group_register; + } + + return 0; + +err_trap_group_register: +err_trap_group_verify: + for (i--; i >= 0; i--) + devlink_trap_group_unregister(devlink, &groups[i]); + return err; +} +EXPORT_SYMBOL_GPL(devl_trap_groups_register); + +/** + * devlink_trap_groups_register - Register packet trap groups with devlink. + * @devlink: devlink. + * @groups: Packet trap groups. + * @groups_count: Count of provided packet trap groups. + * + * Context: Takes and release devlink->lock <mutex>. + * + * Return: Non-zero value on failure. + */ +int devlink_trap_groups_register(struct devlink *devlink, + const struct devlink_trap_group *groups, + size_t groups_count) +{ + int err; + + devl_lock(devlink); + err = devl_trap_groups_register(devlink, groups, groups_count); + devl_unlock(devlink); + return err; +} +EXPORT_SYMBOL_GPL(devlink_trap_groups_register); + +/** + * devl_trap_groups_unregister - Unregister packet trap groups from devlink. + * @devlink: devlink. + * @groups: Packet trap groups. + * @groups_count: Count of provided packet trap groups. + */ +void devl_trap_groups_unregister(struct devlink *devlink, + const struct devlink_trap_group *groups, + size_t groups_count) +{ + int i; + + devl_assert_locked(devlink); + for (i = groups_count - 1; i >= 0; i--) + devlink_trap_group_unregister(devlink, &groups[i]); +} +EXPORT_SYMBOL_GPL(devl_trap_groups_unregister); + +/** + * devlink_trap_groups_unregister - Unregister packet trap groups from devlink. + * @devlink: devlink. + * @groups: Packet trap groups. + * @groups_count: Count of provided packet trap groups. + * + * Context: Takes and release devlink->lock <mutex>. + */ +void devlink_trap_groups_unregister(struct devlink *devlink, + const struct devlink_trap_group *groups, + size_t groups_count) +{ + devl_lock(devlink); + devl_trap_groups_unregister(devlink, groups, groups_count); + devl_unlock(devlink); +} +EXPORT_SYMBOL_GPL(devlink_trap_groups_unregister); + +static void +devlink_trap_policer_notify(struct devlink *devlink, + const struct devlink_trap_policer_item *policer_item, + enum devlink_command cmd) +{ + struct sk_buff *msg; + int err; + + WARN_ON_ONCE(cmd != DEVLINK_CMD_TRAP_POLICER_NEW && + cmd != DEVLINK_CMD_TRAP_POLICER_DEL); + if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)) + return; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + err = devlink_nl_trap_policer_fill(msg, devlink, policer_item, cmd, 0, + 0, 0); + if (err) { + nlmsg_free(msg); + return; + } + + genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), + msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); +} + +static int +devlink_trap_policer_register(struct devlink *devlink, + const struct devlink_trap_policer *policer) +{ + struct devlink_trap_policer_item *policer_item; + int err; + + if (devlink_trap_policer_item_lookup(devlink, policer->id)) + return -EEXIST; + + policer_item = kzalloc(sizeof(*policer_item), GFP_KERNEL); + if (!policer_item) + return -ENOMEM; + + policer_item->policer = policer; + policer_item->rate = policer->init_rate; + policer_item->burst = policer->init_burst; + + if (devlink->ops->trap_policer_init) { + err = devlink->ops->trap_policer_init(devlink, policer); + if (err) + goto err_policer_init; + } + + list_add_tail(&policer_item->list, &devlink->trap_policer_list); + devlink_trap_policer_notify(devlink, policer_item, + DEVLINK_CMD_TRAP_POLICER_NEW); + + return 0; + +err_policer_init: + kfree(policer_item); + return err; +} + +static void +devlink_trap_policer_unregister(struct devlink *devlink, + const struct devlink_trap_policer *policer) +{ + struct devlink_trap_policer_item *policer_item; + + policer_item = devlink_trap_policer_item_lookup(devlink, policer->id); + if (WARN_ON_ONCE(!policer_item)) + return; + + devlink_trap_policer_notify(devlink, policer_item, + DEVLINK_CMD_TRAP_POLICER_DEL); + list_del(&policer_item->list); + if (devlink->ops->trap_policer_fini) + devlink->ops->trap_policer_fini(devlink, policer); + kfree(policer_item); +} + +/** + * devl_trap_policers_register - Register packet trap policers with devlink. + * @devlink: devlink. + * @policers: Packet trap policers. + * @policers_count: Count of provided packet trap policers. + * + * Return: Non-zero value on failure. + */ +int +devl_trap_policers_register(struct devlink *devlink, + const struct devlink_trap_policer *policers, + size_t policers_count) +{ + int i, err; + + devl_assert_locked(devlink); + for (i = 0; i < policers_count; i++) { + const struct devlink_trap_policer *policer = &policers[i]; + + if (WARN_ON(policer->id == 0 || + policer->max_rate < policer->min_rate || + policer->max_burst < policer->min_burst)) { + err = -EINVAL; + goto err_trap_policer_verify; + } + + err = devlink_trap_policer_register(devlink, policer); + if (err) + goto err_trap_policer_register; + } + return 0; + +err_trap_policer_register: +err_trap_policer_verify: + for (i--; i >= 0; i--) + devlink_trap_policer_unregister(devlink, &policers[i]); + return err; +} +EXPORT_SYMBOL_GPL(devl_trap_policers_register); + +/** + * devl_trap_policers_unregister - Unregister packet trap policers from devlink. + * @devlink: devlink. + * @policers: Packet trap policers. + * @policers_count: Count of provided packet trap policers. + */ +void +devl_trap_policers_unregister(struct devlink *devlink, + const struct devlink_trap_policer *policers, + size_t policers_count) +{ + int i; + + devl_assert_locked(devlink); + for (i = policers_count - 1; i >= 0; i--) + devlink_trap_policer_unregister(devlink, &policers[i]); +} +EXPORT_SYMBOL_GPL(devl_trap_policers_unregister); + +static void __devlink_compat_running_version(struct devlink *devlink, + char *buf, size_t len) +{ + struct devlink_info_req req = {}; + const struct nlattr *nlattr; + struct sk_buff *msg; + int rem, err; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + req.msg = msg; + err = devlink->ops->info_get(devlink, &req, NULL); + if (err) + goto free_msg; + + nla_for_each_attr(nlattr, (void *)msg->data, msg->len, rem) { + const struct nlattr *kv; + int rem_kv; + + if (nla_type(nlattr) != DEVLINK_ATTR_INFO_VERSION_RUNNING) + continue; + + nla_for_each_nested(kv, nlattr, rem_kv) { + if (nla_type(kv) != DEVLINK_ATTR_INFO_VERSION_VALUE) + continue; + + strlcat(buf, nla_data(kv), len); + strlcat(buf, " ", len); + } + } +free_msg: + nlmsg_free(msg); +} + +static struct devlink_port *netdev_to_devlink_port(struct net_device *dev) +{ + if (!dev->netdev_ops->ndo_get_devlink_port) + return NULL; + + return dev->netdev_ops->ndo_get_devlink_port(dev); +} + +void devlink_compat_running_version(struct devlink *devlink, + char *buf, size_t len) +{ + if (!devlink->ops->info_get) + return; + + devl_lock(devlink); + __devlink_compat_running_version(devlink, buf, len); + devl_unlock(devlink); +} + +int devlink_compat_flash_update(struct devlink *devlink, const char *file_name) +{ + struct devlink_flash_update_params params = {}; + int ret; + + if (!devlink->ops->flash_update) + return -EOPNOTSUPP; + + ret = request_firmware(&params.fw, file_name, devlink->dev); + if (ret) + return ret; + + devl_lock(devlink); + devlink_flash_update_begin_notify(devlink); + ret = devlink->ops->flash_update(devlink, &params, NULL); + devlink_flash_update_end_notify(devlink); + devl_unlock(devlink); + + release_firmware(params.fw); + + return ret; +} + +int devlink_compat_phys_port_name_get(struct net_device *dev, + char *name, size_t len) +{ + 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) + return -EOPNOTSUPP; + + 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; + + /* Caller must hold RTNL mutex or reference to dev, which ensures that + * devlink_port instance cannot disappear in the middle. No need to take + * any devlink lock as only permanent values are accessed. + */ + devlink_port = netdev_to_devlink_port(dev); + if (!devlink_port || !devlink_port->switch_port) + return -EOPNOTSUPP; + + memcpy(ppid, &devlink_port->attrs.switch_id, sizeof(*ppid)); + + return 0; +} + +static void __net_exit devlink_pernet_pre_exit(struct net *net) +{ + struct devlink *devlink; + u32 actions_performed; + unsigned long index; + int err; + + /* In case network namespace is getting destroyed, reload + * all devlink instances from this namespace into init_net. + */ + devlinks_xa_for_each_registered_get(net, index, devlink) { + WARN_ON(!(devlink->features & DEVLINK_F_RELOAD)); + mutex_lock(&devlink->lock); + err = devlink_reload(devlink, &init_net, + DEVLINK_RELOAD_ACTION_DRIVER_REINIT, + DEVLINK_RELOAD_LIMIT_UNSPEC, + &actions_performed, NULL); + mutex_unlock(&devlink->lock); + if (err && err != -EOPNOTSUPP) + pr_warn("Failed to reload devlink instance into init_net\n"); + devlink_put(devlink); + } +} + +static struct pernet_operations devlink_pernet_ops __net_initdata = { + .pre_exit = devlink_pernet_pre_exit, +}; + +static int __init devlink_init(void) +{ + int err; + + err = genl_register_family(&devlink_nl_family); + if (err) + goto out; + err = register_pernet_subsys(&devlink_pernet_ops); + +out: + WARN_ON(err); + return err; +} + +subsys_initcall(devlink_init); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index ebb737ac9e89..04853c83c85c 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -340,7 +340,7 @@ static int inet_create(struct net *net, struct socket *sock, int protocol, else inet->pmtudisc = IP_PMTUDISC_WANT;

- inet->inet_id = 0; + atomic_set(&inet->inet_id, 0);

sock_init_data(sock, sk);

diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index 4d1af0cd7d99..cb5dbee9e018 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -73,7 +73,7 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len reuseport_has_conns_set(sk); sk->sk_state = TCP_ESTABLISHED; sk_set_txhash(sk); - inet->inet_id = get_random_u16(); + atomic_set(&inet->inet_id, get_random_u16());

sk_dst_set(sk, &rt->dst); err = 0; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 08921b96f972..f9b8a4a1d2ed 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -312,7 +312,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_daddr)); }

- inet->inet_id = get_random_u16(); + atomic_set(&inet->inet_id, get_random_u16());

if (tcp_fastopen_defer_connect(sk, &err)) return err; @@ -1539,7 +1539,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, inet_csk(newsk)->icsk_ext_hdr_len = 0; if (inet_opt) inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen; - newinet->inet_id = get_random_u16(); + atomic_set(&newinet->inet_id, get_random_u16());

/* Set ToS of the new socket based upon the value of incoming SYN. * ECT bits are set later in tcp_init_transfer(). diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 0f81492da0b4..55dc0610e863 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1102,7 +1102,8 @@ static inline bool ieee80211_rx_reorder_ready(struct tid_ampdu_rx *tid_agg_rx, struct sk_buff *tail = skb_peek_tail(frames); struct ieee80211_rx_status *status;

- if (tid_agg_rx->reorder_buf_filtered & BIT_ULL(index)) + if (tid_agg_rx->reorder_buf_filtered && + tid_agg_rx->reorder_buf_filtered & BIT_ULL(index)) return true;

if (!tail) @@ -1143,7 +1144,8 @@ static void ieee80211_release_reorder_frame(struct ieee80211_sub_if_data *sdata, }

no_frame: - tid_agg_rx->reorder_buf_filtered &= ~BIT_ULL(index); + if (tid_agg_rx->reorder_buf_filtered) + tid_agg_rx->reorder_buf_filtered &= ~BIT_ULL(index); tid_agg_rx->head_seq_num = ieee80211_sn_inc(tid_agg_rx->head_seq_num); }

@@ -4162,6 +4164,7 @@ void ieee80211_mark_rx_ba_filtered_frames(struct ieee80211_sta *pubsta, u8 tid, u16 ssn, u64 filtered, u16 received_mpdus) { + struct ieee80211_local *local; struct sta_info *sta; struct tid_ampdu_rx *tid_agg_rx; struct sk_buff_head frames; @@ -4179,6 +4182,11 @@ void ieee80211_mark_rx_ba_filtered_frames(struct ieee80211_sta *pubsta, u8 tid,

sta = container_of(pubsta, struct sta_info, sta);

+ local = sta->sdata->local; + WARN_ONCE(local->hw.max_rx_aggregation_subframes > 64, + "RX BA marker can't support max_rx_aggregation_subframes %u > 64\n", + local->hw.max_rx_aggregation_subframes); + if (!ieee80211_rx_data_set_sta(&rx, sta, -1)) return;

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 4c2df7af73f7..3c5cac9bd9b7 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -10509,7 +10509,7 @@ static int nft_rcv_nl_event(struct notifier_block *this, unsigned long event, deleted = 0; mutex_lock(&nft_net->commit_mutex); if (!list_empty(&nf_tables_destroy_list)) - rcu_barrier(); + nf_tables_trans_destroy_flush_work(); again: list_for_each_entry(table, &nft_net->tables, list) { if (nft_table_has_owner(table) && diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 32cfd0a84b0e..8c16681884b7 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -901,12 +901,14 @@ static void pipapo_lt_bits_adjust(struct nft_pipapo_field *f) static int pipapo_insert(struct nft_pipapo_field *f, const uint8_t *k, int mask_bits) { - int rule = f->rules++, group, ret, bit_offset = 0; + int rule = f->rules, group, ret, bit_offset = 0;

- ret = pipapo_resize(f, f->rules - 1, f->rules); + ret = pipapo_resize(f, f->rules, f->rules + 1); if (ret) return ret;

+ f->rules++; + for (group = 0; group < f->groups; group++) { int i, v; u8 mask; @@ -1051,7 +1053,9 @@ static int pipapo_expand(struct nft_pipapo_field *f, step++; if (step >= len) { if (!masks) { - pipapo_insert(f, base, 0); + err = pipapo_insert(f, base, 0); + if (err < 0) + return err; masks = 1; } goto out; @@ -1234,6 +1238,9 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, else ret = pipapo_expand(f, start, end, f->groups * f->bb);

+ if (ret < 0) + return ret; + if (f->bsize > bsize_max) bsize_max = f->bsize;

diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 01d07e6a6811..e8f988e1c7e6 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1550,10 +1550,28 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, return 0; }

+static bool req_create_or_replace(struct nlmsghdr *n) +{ + return (n->nlmsg_flags & NLM_F_CREATE && + n->nlmsg_flags & NLM_F_REPLACE); +} + +static bool req_create_exclusive(struct nlmsghdr *n) +{ + return (n->nlmsg_flags & NLM_F_CREATE && + n->nlmsg_flags & NLM_F_EXCL); +} + +static bool req_change(struct nlmsghdr *n) +{ + return (!(n->nlmsg_flags & NLM_F_CREATE) && + !(n->nlmsg_flags & NLM_F_REPLACE) && + !(n->nlmsg_flags & NLM_F_EXCL)); +} + /* * Create/change qdisc. */ - static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n, struct netlink_ext_ack *extack) { @@ -1647,27 +1665,35 @@ static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n, * * We know, that some child q is already * attached to this parent and have choice: - * either to change it or to create/graft new one. + * 1) change it or 2) create/graft new one. + * If the requested qdisc kind is different + * than the existing one, then we choose graft. + * If they are the same then this is "change" + * operation - just let it fallthrough.. * * 1. We are allowed to create/graft only - * if CREATE and REPLACE flags are set. + * if the request is explicitly stating + * "please create if it doesn't exist". * - * 2. If EXCL is set, requestor wanted to say, - * that qdisc tcm_handle is not expected + * 2. If the request is to exclusive create + * then the qdisc tcm_handle is not expected * to exist, so that we choose create/graft too. * * 3. The last case is when no flags are set. + * This will happen when for example tc + * utility issues a "change" command. * Alas, it is sort of hole in API, we * cannot decide what to do unambiguously. - * For now we select create/graft, if - * user gave KIND, which does not match existing. + * For now we select create/graft. */ - if ((n->nlmsg_flags & NLM_F_CREATE) && - (n->nlmsg_flags & NLM_F_REPLACE) && - ((n->nlmsg_flags & NLM_F_EXCL) || - (tca[TCA_KIND] && - nla_strcmp(tca[TCA_KIND], q->ops->id)))) - goto create_n_graft; + if (tca[TCA_KIND] && + nla_strcmp(tca[TCA_KIND], q->ops->id)) { + if (req_create_or_replace(n) || + req_create_exclusive(n)) + goto create_n_graft; + else if (req_change(n)) + goto create_n_graft2; + } } } } else { @@ -1701,6 +1727,7 @@ static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n, NL_SET_ERR_MSG(extack, "Qdisc not found. To create specify NLM_F_CREATE flag"); return -ENOENT; } +create_n_graft2: if (clid == TC_H_INGRESS) { if (dev_ingress_queue(dev)) { q = qdisc_create(dev, dev_ingress_queue(dev), diff --git a/net/sctp/socket.c b/net/sctp/socket.c index c806d272107a..a11b0d903514 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -98,7 +98,7 @@ struct percpu_counter sctp_sockets_allocated;

static void sctp_enter_memory_pressure(struct sock *sk) { - sctp_memory_pressure = 1; + WRITE_ONCE(sctp_memory_pressure, 1); }

@@ -9472,7 +9472,7 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk, newinet->inet_rcv_saddr = inet->inet_rcv_saddr; newinet->inet_dport = htons(asoc->peer.port); newinet->pmtudisc = inet->pmtudisc; - newinet->inet_id = get_random_u16(); + atomic_set(&newinet->inet_id, get_random_u16());

newinet->uc_ttl = inet->uc_ttl; newinet->mc_loop = 1; diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index b098fde373ab..28c0771c4e8c 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -935,9 +935,6 @@ struct rpcrdma_rep *rpcrdma_rep_create(struct rpcrdma_xprt *r_xprt, if (!rep->rr_rdmabuf) goto out_free;

- if (!rpcrdma_regbuf_dma_map(r_xprt, rep->rr_rdmabuf)) - goto out_free_regbuf; - rep->rr_cid.ci_completion_id = atomic_inc_return(&r_xprt->rx_ep->re_completion_ids);

@@ -956,8 +953,6 @@ struct rpcrdma_rep *rpcrdma_rep_create(struct rpcrdma_xprt *r_xprt, spin_unlock(&buf->rb_lock); return rep;

-out_free_regbuf: - rpcrdma_regbuf_free(rep->rr_rdmabuf); out_free: kfree(rep); out: @@ -1363,6 +1358,10 @@ void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, int needed, bool temp) rep = rpcrdma_rep_create(r_xprt, temp); if (!rep) break; + if (!rpcrdma_regbuf_dma_map(r_xprt, rep->rr_rdmabuf)) { + rpcrdma_rep_put(buf, rep); + break; + }

rep->rr_cid.ci_queue_id = ep->re_attr.recv_cq->res.id; trace_xprtrdma_post_recv(rep); diff --git a/security/selinux/ss/policydb.c b/security/selinux/ss/policydb.c index adcfb63b3550..6f9ff4643dcb 100644 --- a/security/selinux/ss/policydb.c +++ b/security/selinux/ss/policydb.c @@ -2005,6 +2005,7 @@ static int filename_trans_read_helper(struct policydb *p, void *fp) if (!datum) goto out;

+ datum->next = NULL; *dst = datum;

/* ebitmap_read() will at least init the bitmap */ @@ -2017,7 +2018,6 @@ static int filename_trans_read_helper(struct policydb *p, void *fp) goto out;

datum->otype = le32_to_cpu(buf[0]); - datum->next = NULL;

dst = &datum->next; } diff --git a/sound/pci/ymfpci/ymfpci.c b/sound/pci/ymfpci/ymfpci.c index 82d4e0fda91b..d62a0e2ddf60 100644 --- a/sound/pci/ymfpci/ymfpci.c +++ b/sound/pci/ymfpci/ymfpci.c @@ -150,8 +150,8 @@ static inline int snd_ymfpci_create_gameport(struct snd_ymfpci *chip, int dev, i void snd_ymfpci_free_gameport(struct snd_ymfpci *chip) { } #endif /* SUPPORT_JOYSTICK */

-static int snd_card_ymfpci_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_card_ymfpci_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -333,6 +333,12 @@ static int snd_card_ymfpci_probe(struct pci_dev *pci, return 0; }

+static int snd_card_ymfpci_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_card_ymfpci_probe(pci, pci_id)); +} + static struct pci_driver ymfpci_driver = { .name = KBUILD_MODNAME, .id_table = snd_ymfpci_ids, diff --git a/sound/soc/amd/Kconfig b/sound/soc/amd/Kconfig index 3968c478c938..44d4e6e51a35 100644 --- a/sound/soc/amd/Kconfig +++ b/sound/soc/amd/Kconfig @@ -71,6 +71,7 @@ config SND_SOC_AMD_RENOIR_MACH config SND_SOC_AMD_ACP5x tristate "AMD Audio Coprocessor-v5.x I2S support" depends on X86 && PCI + select SND_AMD_ACP_CONFIG help This option enables ACP v5.x support on AMD platform

diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index c1ca3ceac5f2..9a9571c3f08c 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -217,7 +217,7 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { .driver_data = &acp6x_card, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_NAME, "82"), + DMI_MATCH(DMI_PRODUCT_NAME, "82V2"), } }, { @@ -248,6 +248,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Redmi Book Pro 14 2022"), } }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "M6500RC"), + } + }, { .driver_data = &acp6x_card, .matches = { diff --git a/sound/soc/codecs/cs35l41.c b/sound/soc/codecs/cs35l41.c index f2b5032daa6a..2f4b0ee93ace 100644 --- a/sound/soc/codecs/cs35l41.c +++ b/sound/soc/codecs/cs35l41.c @@ -167,7 +167,7 @@ static int cs35l41_get_fs_mon_config_index(int freq) static const DECLARE_TLV_DB_RANGE(dig_vol_tlv, 0, 0, TLV_DB_SCALE_ITEM(TLV_DB_GAIN_MUTE, 0, 1), 1, 913, TLV_DB_MINMAX_ITEM(-10200, 1200)); -static DECLARE_TLV_DB_SCALE(amp_gain_tlv, 0, 1, 1); +static DECLARE_TLV_DB_SCALE(amp_gain_tlv, 50, 100, 0);

static const struct snd_kcontrol_new dre_ctrl = SOC_DAPM_SINGLE("Switch", CS35L41_PWR_CTRL3, 20, 1, 0); diff --git a/tools/testing/selftests/drivers/net/bonding/bond-break-lacpdu-tx.sh b/tools/testing/selftests/drivers/net/bonding/bond-break-lacpdu-tx.sh index 47ab90596acb..6358df5752f9 100755 --- a/tools/testing/selftests/drivers/net/bonding/bond-break-lacpdu-tx.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond-break-lacpdu-tx.sh @@ -57,8 +57,8 @@ ip link add name veth2-bond type veth peer name veth2-end

# add ports ip link set fbond master fab-br0 -ip link set veth1-bond down master fbond -ip link set veth2-bond down master fbond +ip link set veth1-bond master fbond +ip link set veth2-bond master fbond

# bring up ip link set veth1-end up diff --git a/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh b/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh index 7d9e73a43a49..0c47faff9274 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh @@ -98,12 +98,12 @@ sb_occ_etc_check()

port_pool_test() { - local exp_max_occ=288 + local exp_max_occ=$(devlink_cell_size_get) local max_occ

devlink sb occupancy clearmax $DEVLINK_DEV

- $MZ $h1 -c 1 -p 160 -a $h1mac -b $h2mac -A 192.0.1.1 -B 192.0.1.2 \ + $MZ $h1 -c 1 -p 10 -a $h1mac -b $h2mac -A 192.0.1.1 -B 192.0.1.2 \ -t ip -q

devlink sb occupancy snapshot $DEVLINK_DEV @@ -126,12 +126,12 @@ port_pool_test()

port_tc_ip_test() { - local exp_max_occ=288 + local exp_max_occ=$(devlink_cell_size_get) local max_occ

devlink sb occupancy clearmax $DEVLINK_DEV

- $MZ $h1 -c 1 -p 160 -a $h1mac -b $h2mac -A 192.0.1.1 -B 192.0.1.2 \ + $MZ $h1 -c 1 -p 10 -a $h1mac -b $h2mac -A 192.0.1.1 -B 192.0.1.2 \ -t ip -q

devlink sb occupancy snapshot $DEVLINK_DEV @@ -154,16 +154,12 @@ port_tc_ip_test()

port_tc_arp_test() { - local exp_max_occ=96 + local exp_max_occ=$(devlink_cell_size_get) local max_occ

- if [[ $MLXSW_CHIP != "mlxsw_spectrum" ]]; then - exp_max_occ=144 - fi - devlink sb occupancy clearmax $DEVLINK_DEV

- $MZ $h1 -c 1 -p 160 -a $h1mac -A 192.0.1.1 -t arp -q + $MZ $h1 -c 1 -p 10 -a $h1mac -A 192.0.1.1 -t arp -q

devlink sb occupancy snapshot $DEVLINK_DEV

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 69c58362c0ed..48d1a68be1d5 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -71,14 +71,60 @@ TEST_GEN_FILES += bind_bhash TEST_GEN_PROGS += sk_bind_sendto_listen TEST_GEN_PROGS += sk_connect_zero_addr TEST_PROGS += test_ingress_egress_chaining.sh +TEST_GEN_FILES += nat6to4.o

TEST_FILES := settings

include ../lib.mk

-include bpf/Makefile - $(OUTPUT)/reuseport_bpf_numa: LDLIBS += -lnuma $(OUTPUT)/tcp_mmap: LDLIBS += -lpthread $(OUTPUT)/tcp_inq: LDLIBS += -lpthread $(OUTPUT)/bind_bhash: LDLIBS += -lpthread + +# Rules to generate bpf obj nat6to4.o +CLANG ?= clang +SCRATCH_DIR := $(OUTPUT)/tools +BUILD_DIR := $(SCRATCH_DIR)/build +BPFDIR := $(abspath ../../../lib/bpf) +APIDIR := $(abspath ../../../include/uapi) + +CCINCLUDE += -I../bpf +CCINCLUDE += -I../../../../usr/include/ +CCINCLUDE += -I$(SCRATCH_DIR)/include + +BPFOBJ := $(BUILD_DIR)/libbpf/libbpf.a + +MAKE_DIRS := $(BUILD_DIR)/libbpf +$(MAKE_DIRS): + mkdir -p $@ + +# Get Clang's default includes on this system, as opposed to those seen by +# '-target bpf'. This fixes "missing" files on some architectures/distros, +# such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc. +# +# Use '-idirafter': Don't interfere with include mechanics except where the +# build would have failed anyways. +define get_sys_includes +$(shell $(1) $(2) -v -E - </dev/null 2>&1 \ + | sed -n '/<...> search starts here:/,/End of search list./{ s| (/.*)|-idirafter \1|p }') \ +$(shell $(1) $(2) -dM -E - </dev/null | grep '__riscv_xlen ' | awk '{printf("-D__riscv_xlen=%d -D__BITS_PER_LONG=%d", $$3, $$3)}') +endef + +ifneq ($(CROSS_COMPILE),) +CLANG_TARGET_ARCH = --target=$(notdir $(CROSS_COMPILE:%-=%)) +endif + +CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH)) + +$(OUTPUT)/nat6to4.o: nat6to4.c $(BPFOBJ) | $(MAKE_DIRS) + $(CLANG) -O2 -target bpf -c $< $(CCINCLUDE) $(CLANG_SYS_INCLUDES) -o $@ + +$(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \ + $(APIDIR)/linux/bpf.h \ + | $(BUILD_DIR)/libbpf + $(MAKE) $(submake_extras) -C $(BPFDIR) OUTPUT=$(BUILD_DIR)/libbpf/ \ + EXTRA_CFLAGS='-g -O0' \ + DESTDIR=$(SCRATCH_DIR) prefix= all install_headers + +EXTRA_CLEAN := $(SCRATCH_DIR) diff --git a/tools/testing/selftests/net/bpf/Makefile b/tools/testing/selftests/net/bpf/Makefile deleted file mode 100644 index 8ccaf8732eb2..000000000000 --- a/tools/testing/selftests/net/bpf/Makefile +++ /dev/null @@ -1,14 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 - -CLANG ?= clang -CCINCLUDE += -I../../bpf -CCINCLUDE += -I../../../../lib -CCINCLUDE += -I../../../../../usr/include/ - -TEST_CUSTOM_PROGS = $(OUTPUT)/bpf/nat6to4.o -all: $(TEST_CUSTOM_PROGS) - -$(OUTPUT)/%.o: %.c - $(CLANG) -O2 -target bpf -c $< $(CCINCLUDE) -o $@ - -EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) diff --git a/tools/testing/selftests/net/bpf/nat6to4.c b/tools/testing/selftests/net/bpf/nat6to4.c deleted file mode 100644 index ac54c36b25fc..000000000000 --- a/tools/testing/selftests/net/bpf/nat6to4.c +++ /dev/null @@ -1,285 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * This code is taken from the Android Open Source Project and the author - * (Maciej Żenczykowski) has gave permission to relicense it under the - * GPLv2. Therefore 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 - - * The original headers, including the original license headers, are - * included below for completeness. - * - * Copyright (C) 2019 The Android Open Source Project - * - * Licensed under the Apache License, Version 2.0 (the "License"); - * you may not use this file except in compliance with the License. - * You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ -#include <linux/bpf.h> -#include <linux/if.h> -#include <linux/if_ether.h> -#include <linux/if_packet.h> -#include <linux/in.h> -#include <linux/in6.h> -#include <linux/ip.h> -#include <linux/ipv6.h> -#include <linux/pkt_cls.h> -#include <linux/swab.h> -#include <stdbool.h> -#include <stdint.h> - - -#include <linux/udp.h> - -#include <bpf/bpf_helpers.h> -#include <bpf/bpf_endian.h> - -#define IP_DF 0x4000 // Flag: "Don't Fragment" - -SEC("schedcls/ingress6/nat_6") -int sched_cls_ingress6_nat_6_prog(struct __sk_buff *skb) -{ - const int l2_header_size = sizeof(struct ethhdr); - void *data = (void *)(long)skb->data; - const void *data_end = (void *)(long)skb->data_end; - const struct ethhdr * const eth = data; // used iff is_ethernet - const struct ipv6hdr * const ip6 = (void *)(eth + 1); - - // Require ethernet dst mac address to be our unicast address. - if (skb->pkt_type != PACKET_HOST) - return TC_ACT_OK; - - // Must be meta-ethernet IPv6 frame - if (skb->protocol != bpf_htons(ETH_P_IPV6)) - return TC_ACT_OK; - - // Must have (ethernet and) ipv6 header - if (data + l2_header_size + sizeof(*ip6) > data_end) - return TC_ACT_OK; - - // Ethertype - if present - must be IPv6 - if (eth->h_proto != bpf_htons(ETH_P_IPV6)) - return TC_ACT_OK; - - // IP version must be 6 - if (ip6->version != 6) - return TC_ACT_OK; - // Maximum IPv6 payload length that can be translated to IPv4 - if (bpf_ntohs(ip6->payload_len) > 0xFFFF - sizeof(struct iphdr)) - return TC_ACT_OK; - switch (ip6->nexthdr) { - case IPPROTO_TCP: // For TCP & UDP the checksum neutrality of the chosen IPv6 - case IPPROTO_UDP: // address means there is no need to update their checksums. - case IPPROTO_GRE: // We do not need to bother looking at GRE/ESP headers, - case IPPROTO_ESP: // since there is never a checksum to update. - break; - default: // do not know how to handle anything else - return TC_ACT_OK; - } - - struct ethhdr eth2; // used iff is_ethernet - - eth2 = *eth; // Copy over the ethernet header (src/dst mac) - eth2.h_proto = bpf_htons(ETH_P_IP); // But replace the ethertype - - struct iphdr ip = { - .version = 4, // u4 - .ihl = sizeof(struct iphdr) / sizeof(__u32), // u4 - .tos = (ip6->priority << 4) + (ip6->flow_lbl[0] >> 4), // u8 - .tot_len = bpf_htons(bpf_ntohs(ip6->payload_len) + sizeof(struct iphdr)), // u16 - .id = 0, // u16 - .frag_off = bpf_htons(IP_DF), // u16 - .ttl = ip6->hop_limit, // u8 - .protocol = ip6->nexthdr, // u8 - .check = 0, // u16 - .saddr = 0x0201a8c0, // u32 - .daddr = 0x0101a8c0, // u32 - }; - - // Calculate the IPv4 one's complement checksum of the IPv4 header. - __wsum sum4 = 0; - - for (int i = 0; i < sizeof(ip) / sizeof(__u16); ++i) - sum4 += ((__u16 *)&ip)[i]; - - // Note that sum4 is guaranteed to be non-zero by virtue of ip.version == 4 - sum4 = (sum4 & 0xFFFF) + (sum4 >> 16); // collapse u32 into range 1 .. 0x1FFFE - sum4 = (sum4 & 0xFFFF) + (sum4 >> 16); // collapse any potential carry into u16 - ip.check = (__u16)~sum4; // sum4 cannot be zero, so this is never 0xFFFF - - // Calculate the *negative* IPv6 16-bit one's complement checksum of the IPv6 header. - __wsum sum6 = 0; - // We'll end up with a non-zero sum due to ip6->version == 6 (which has '0' bits) - for (int i = 0; i < sizeof(*ip6) / sizeof(__u16); ++i) - sum6 += ~((__u16 *)ip6)[i]; // note the bitwise negation - - // Note that there is no L4 checksum update: we are relying on the checksum neutrality - // of the ipv6 address chosen by netd's ClatdController. - - // Packet mutations begin - point of no return, but if this first modification fails - // the packet is probably still pristine, so let clatd handle it. - if (bpf_skb_change_proto(skb, bpf_htons(ETH_P_IP), 0)) - return TC_ACT_OK; - bpf_csum_update(skb, sum6); - - data = (void *)(long)skb->data; - data_end = (void *)(long)skb->data_end; - if (data + l2_header_size + sizeof(struct iphdr) > data_end) - return TC_ACT_SHOT; - - struct ethhdr *new_eth = data; - - // Copy over the updated ethernet header - *new_eth = eth2; - - // Copy over the new ipv4 header. - *(struct iphdr *)(new_eth + 1) = ip; - return bpf_redirect(skb->ifindex, BPF_F_INGRESS); -} - -SEC("schedcls/egress4/snat4") -int sched_cls_egress4_snat4_prog(struct __sk_buff *skb) -{ - const int l2_header_size = sizeof(struct ethhdr); - void *data = (void *)(long)skb->data; - const void *data_end = (void *)(long)skb->data_end; - const struct ethhdr *const eth = data; // used iff is_ethernet - const struct iphdr *const ip4 = (void *)(eth + 1); - - // Must be meta-ethernet IPv4 frame - if (skb->protocol != bpf_htons(ETH_P_IP)) - return TC_ACT_OK; - - // Must have ipv4 header - if (data + l2_header_size + sizeof(struct ipv6hdr) > data_end) - return TC_ACT_OK; - - // Ethertype - if present - must be IPv4 - if (eth->h_proto != bpf_htons(ETH_P_IP)) - return TC_ACT_OK; - - // IP version must be 4 - if (ip4->version != 4) - return TC_ACT_OK; - - // We cannot handle IP options, just standard 20 byte == 5 dword minimal IPv4 header - if (ip4->ihl != 5) - return TC_ACT_OK; - - // Maximum IPv6 payload length that can be translated to IPv4 - if (bpf_htons(ip4->tot_len) > 0xFFFF - sizeof(struct ipv6hdr)) - return TC_ACT_OK; - - // Calculate the IPv4 one's complement checksum of the IPv4 header. - __wsum sum4 = 0; - - for (int i = 0; i < sizeof(*ip4) / sizeof(__u16); ++i) - sum4 += ((__u16 *)ip4)[i]; - - // Note that sum4 is guaranteed to be non-zero by virtue of ip4->version == 4 - sum4 = (sum4 & 0xFFFF) + (sum4 >> 16); // collapse u32 into range 1 .. 0x1FFFE - sum4 = (sum4 & 0xFFFF) + (sum4 >> 16); // collapse any potential carry into u16 - // for a correct checksum we should get *a* zero, but sum4 must be positive, ie 0xFFFF - if (sum4 != 0xFFFF) - return TC_ACT_OK; - - // Minimum IPv4 total length is the size of the header - if (bpf_ntohs(ip4->tot_len) < sizeof(*ip4)) - return TC_ACT_OK; - - // We are incapable of dealing with IPv4 fragments - if (ip4->frag_off & ~bpf_htons(IP_DF)) - return TC_ACT_OK; - - switch (ip4->protocol) { - case IPPROTO_TCP: // For TCP & UDP the checksum neutrality of the chosen IPv6 - case IPPROTO_GRE: // address means there is no need to update their checksums. - case IPPROTO_ESP: // We do not need to bother looking at GRE/ESP headers, - break; // since there is never a checksum to update. - - case IPPROTO_UDP: // See above comment, but must also have UDP header... - if (data + sizeof(*ip4) + sizeof(struct udphdr) > data_end) - return TC_ACT_OK; - const struct udphdr *uh = (const struct udphdr *)(ip4 + 1); - // If IPv4/UDP checksum is 0 then fallback to clatd so it can calculate the - // checksum. Otherwise the network or more likely the NAT64 gateway might - // drop the packet because in most cases IPv6/UDP packets with a zero checksum - // are invalid. See RFC 6935. TODO: calculate checksum via bpf_csum_diff() - if (!uh->check) - return TC_ACT_OK; - break; - - default: // do not know how to handle anything else - return TC_ACT_OK; - } - struct ethhdr eth2; // used iff is_ethernet - - eth2 = *eth; // Copy over the ethernet header (src/dst mac) - eth2.h_proto = bpf_htons(ETH_P_IPV6); // But replace the ethertype - - struct ipv6hdr ip6 = { - .version = 6, // __u8:4 - .priority = ip4->tos >> 4, // __u8:4 - .flow_lbl = {(ip4->tos & 0xF) << 4, 0, 0}, // __u8[3] - .payload_len = bpf_htons(bpf_ntohs(ip4->tot_len) - 20), // __be16 - .nexthdr = ip4->protocol, // __u8 - .hop_limit = ip4->ttl, // __u8 - }; - ip6.saddr.in6_u.u6_addr32[0] = bpf_htonl(0x20010db8); - ip6.saddr.in6_u.u6_addr32[1] = 0; - ip6.saddr.in6_u.u6_addr32[2] = 0; - ip6.saddr.in6_u.u6_addr32[3] = bpf_htonl(1); - ip6.daddr.in6_u.u6_addr32[0] = bpf_htonl(0x20010db8); - ip6.daddr.in6_u.u6_addr32[1] = 0; - ip6.daddr.in6_u.u6_addr32[2] = 0; - ip6.daddr.in6_u.u6_addr32[3] = bpf_htonl(2); - - // Calculate the IPv6 16-bit one's complement checksum of the IPv6 header. - __wsum sum6 = 0; - // We'll end up with a non-zero sum due to ip6.version == 6 - for (int i = 0; i < sizeof(ip6) / sizeof(__u16); ++i) - sum6 += ((__u16 *)&ip6)[i]; - - // Packet mutations begin - point of no return, but if this first modification fails - // the packet is probably still pristine, so let clatd handle it. - if (bpf_skb_change_proto(skb, bpf_htons(ETH_P_IPV6), 0)) - return TC_ACT_OK; - - // This takes care of updating the skb->csum field for a CHECKSUM_COMPLETE packet. - // In such a case, skb->csum is a 16-bit one's complement sum of the entire payload, - // thus we need to subtract out the ipv4 header's sum, and add in the ipv6 header's sum. - // However, we've already verified the ipv4 checksum is correct and thus 0. - // Thus we only need to add the ipv6 header's sum. - // - // bpf_csum_update() always succeeds if the skb is CHECKSUM_COMPLETE and returns an error - // (-ENOTSUPP) if it isn't. So we just ignore the return code (see above for more details). - bpf_csum_update(skb, sum6); - - // bpf_skb_change_proto() invalidates all pointers - reload them. - data = (void *)(long)skb->data; - data_end = (void *)(long)skb->data_end; - - // I cannot think of any valid way for this error condition to trigger, however I do - // believe the explicit check is required to keep the in kernel ebpf verifier happy. - if (data + l2_header_size + sizeof(ip6) > data_end) - return TC_ACT_SHOT; - - struct ethhdr *new_eth = data; - - // Copy over the updated ethernet header - *new_eth = eth2; - // Copy over the new ipv4 header. - *(struct ipv6hdr *)(new_eth + 1) = ip6; - return TC_ACT_OK; -} - -char _license[] SEC("license") = ("GPL"); diff --git a/tools/testing/selftests/net/nat6to4.c b/tools/testing/selftests/net/nat6to4.c new file mode 100644 index 000000000000..ac54c36b25fc --- /dev/null +++ b/tools/testing/selftests/net/nat6to4.c @@ -0,0 +1,285 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * This code is taken from the Android Open Source Project and the author + * (Maciej Żenczykowski) has gave permission to relicense it under the + * GPLv2. Therefore 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 + + * The original headers, including the original license headers, are + * included below for completeness. + * + * Copyright (C) 2019 The Android Open Source Project + * + * Licensed under the Apache License, Version 2.0 (the "License"); + * you may not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +#include <linux/bpf.h> +#include <linux/if.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/in.h> +#include <linux/in6.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/pkt_cls.h> +#include <linux/swab.h> +#include <stdbool.h> +#include <stdint.h> + + +#include <linux/udp.h> + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#define IP_DF 0x4000 // Flag: "Don't Fragment" + +SEC("schedcls/ingress6/nat_6") +int sched_cls_ingress6_nat_6_prog(struct __sk_buff *skb) +{ + const int l2_header_size = sizeof(struct ethhdr); + void *data = (void *)(long)skb->data; + const void *data_end = (void *)(long)skb->data_end; + const struct ethhdr * const eth = data; // used iff is_ethernet + const struct ipv6hdr * const ip6 = (void *)(eth + 1); + + // Require ethernet dst mac address to be our unicast address. + if (skb->pkt_type != PACKET_HOST) + return TC_ACT_OK; + + // Must be meta-ethernet IPv6 frame + if (skb->protocol != bpf_htons(ETH_P_IPV6)) + return TC_ACT_OK; + + // Must have (ethernet and) ipv6 header + if (data + l2_header_size + sizeof(*ip6) > data_end) + return TC_ACT_OK; + + // Ethertype - if present - must be IPv6 + if (eth->h_proto != bpf_htons(ETH_P_IPV6)) + return TC_ACT_OK; + + // IP version must be 6 + if (ip6->version != 6) + return TC_ACT_OK; + // Maximum IPv6 payload length that can be translated to IPv4 + if (bpf_ntohs(ip6->payload_len) > 0xFFFF - sizeof(struct iphdr)) + return TC_ACT_OK; + switch (ip6->nexthdr) { + case IPPROTO_TCP: // For TCP & UDP the checksum neutrality of the chosen IPv6 + case IPPROTO_UDP: // address means there is no need to update their checksums. + case IPPROTO_GRE: // We do not need to bother looking at GRE/ESP headers, + case IPPROTO_ESP: // since there is never a checksum to update. + break; + default: // do not know how to handle anything else + return TC_ACT_OK; + } + + struct ethhdr eth2; // used iff is_ethernet + + eth2 = *eth; // Copy over the ethernet header (src/dst mac) + eth2.h_proto = bpf_htons(ETH_P_IP); // But replace the ethertype + + struct iphdr ip = { + .version = 4, // u4 + .ihl = sizeof(struct iphdr) / sizeof(__u32), // u4 + .tos = (ip6->priority << 4) + (ip6->flow_lbl[0] >> 4), // u8 + .tot_len = bpf_htons(bpf_ntohs(ip6->payload_len) + sizeof(struct iphdr)), // u16 + .id = 0, // u16 + .frag_off = bpf_htons(IP_DF), // u16 + .ttl = ip6->hop_limit, // u8 + .protocol = ip6->nexthdr, // u8 + .check = 0, // u16 + .saddr = 0x0201a8c0, // u32 + .daddr = 0x0101a8c0, // u32 + }; + + // Calculate the IPv4 one's complement checksum of the IPv4 header. + __wsum sum4 = 0; + + for (int i = 0; i < sizeof(ip) / sizeof(__u16); ++i) + sum4 += ((__u16 *)&ip)[i]; + + // Note that sum4 is guaranteed to be non-zero by virtue of ip.version == 4 + sum4 = (sum4 & 0xFFFF) + (sum4 >> 16); // collapse u32 into range 1 .. 0x1FFFE + sum4 = (sum4 & 0xFFFF) + (sum4 >> 16); // collapse any potential carry into u16 + ip.check = (__u16)~sum4; // sum4 cannot be zero, so this is never 0xFFFF + + // Calculate the *negative* IPv6 16-bit one's complement checksum of the IPv6 header. + __wsum sum6 = 0; + // We'll end up with a non-zero sum due to ip6->version == 6 (which has '0' bits) + for (int i = 0; i < sizeof(*ip6) / sizeof(__u16); ++i) + sum6 += ~((__u16 *)ip6)[i]; // note the bitwise negation + + // Note that there is no L4 checksum update: we are relying on the checksum neutrality + // of the ipv6 address chosen by netd's ClatdController. + + // Packet mutations begin - point of no return, but if this first modification fails + // the packet is probably still pristine, so let clatd handle it. + if (bpf_skb_change_proto(skb, bpf_htons(ETH_P_IP), 0)) + return TC_ACT_OK; + bpf_csum_update(skb, sum6); + + data = (void *)(long)skb->data; + data_end = (void *)(long)skb->data_end; + if (data + l2_header_size + sizeof(struct iphdr) > data_end) + return TC_ACT_SHOT; + + struct ethhdr *new_eth = data; + + // Copy over the updated ethernet header + *new_eth = eth2; + + // Copy over the new ipv4 header. + *(struct iphdr *)(new_eth + 1) = ip; + return bpf_redirect(skb->ifindex, BPF_F_INGRESS); +} + +SEC("schedcls/egress4/snat4") +int sched_cls_egress4_snat4_prog(struct __sk_buff *skb) +{ + const int l2_header_size = sizeof(struct ethhdr); + void *data = (void *)(long)skb->data; + const void *data_end = (void *)(long)skb->data_end; + const struct ethhdr *const eth = data; // used iff is_ethernet + const struct iphdr *const ip4 = (void *)(eth + 1); + + // Must be meta-ethernet IPv4 frame + if (skb->protocol != bpf_htons(ETH_P_IP)) + return TC_ACT_OK; + + // Must have ipv4 header + if (data + l2_header_size + sizeof(struct ipv6hdr) > data_end) + return TC_ACT_OK; + + // Ethertype - if present - must be IPv4 + if (eth->h_proto != bpf_htons(ETH_P_IP)) + return TC_ACT_OK; + + // IP version must be 4 + if (ip4->version != 4) + return TC_ACT_OK; + + // We cannot handle IP options, just standard 20 byte == 5 dword minimal IPv4 header + if (ip4->ihl != 5) + return TC_ACT_OK; + + // Maximum IPv6 payload length that can be translated to IPv4 + if (bpf_htons(ip4->tot_len) > 0xFFFF - sizeof(struct ipv6hdr)) + return TC_ACT_OK; + + // Calculate the IPv4 one's complement checksum of the IPv4 header. + __wsum sum4 = 0; + + for (int i = 0; i < sizeof(*ip4) / sizeof(__u16); ++i) + sum4 += ((__u16 *)ip4)[i]; + + // Note that sum4 is guaranteed to be non-zero by virtue of ip4->version == 4 + sum4 = (sum4 & 0xFFFF) + (sum4 >> 16); // collapse u32 into range 1 .. 0x1FFFE + sum4 = (sum4 & 0xFFFF) + (sum4 >> 16); // collapse any potential carry into u16 + // for a correct checksum we should get *a* zero, but sum4 must be positive, ie 0xFFFF + if (sum4 != 0xFFFF) + return TC_ACT_OK; + + // Minimum IPv4 total length is the size of the header + if (bpf_ntohs(ip4->tot_len) < sizeof(*ip4)) + return TC_ACT_OK; + + // We are incapable of dealing with IPv4 fragments + if (ip4->frag_off & ~bpf_htons(IP_DF)) + return TC_ACT_OK; + + switch (ip4->protocol) { + case IPPROTO_TCP: // For TCP & UDP the checksum neutrality of the chosen IPv6 + case IPPROTO_GRE: // address means there is no need to update their checksums. + case IPPROTO_ESP: // We do not need to bother looking at GRE/ESP headers, + break; // since there is never a checksum to update. + + case IPPROTO_UDP: // See above comment, but must also have UDP header... + if (data + sizeof(*ip4) + sizeof(struct udphdr) > data_end) + return TC_ACT_OK; + const struct udphdr *uh = (const struct udphdr *)(ip4 + 1); + // If IPv4/UDP checksum is 0 then fallback to clatd so it can calculate the + // checksum. Otherwise the network or more likely the NAT64 gateway might + // drop the packet because in most cases IPv6/UDP packets with a zero checksum + // are invalid. See RFC 6935. TODO: calculate checksum via bpf_csum_diff() + if (!uh->check) + return TC_ACT_OK; + break; + + default: // do not know how to handle anything else + return TC_ACT_OK; + } + struct ethhdr eth2; // used iff is_ethernet + + eth2 = *eth; // Copy over the ethernet header (src/dst mac) + eth2.h_proto = bpf_htons(ETH_P_IPV6); // But replace the ethertype + + struct ipv6hdr ip6 = { + .version = 6, // __u8:4 + .priority = ip4->tos >> 4, // __u8:4 + .flow_lbl = {(ip4->tos & 0xF) << 4, 0, 0}, // __u8[3] + .payload_len = bpf_htons(bpf_ntohs(ip4->tot_len) - 20), // __be16 + .nexthdr = ip4->protocol, // __u8 + .hop_limit = ip4->ttl, // __u8 + }; + ip6.saddr.in6_u.u6_addr32[0] = bpf_htonl(0x20010db8); + ip6.saddr.in6_u.u6_addr32[1] = 0; + ip6.saddr.in6_u.u6_addr32[2] = 0; + ip6.saddr.in6_u.u6_addr32[3] = bpf_htonl(1); + ip6.daddr.in6_u.u6_addr32[0] = bpf_htonl(0x20010db8); + ip6.daddr.in6_u.u6_addr32[1] = 0; + ip6.daddr.in6_u.u6_addr32[2] = 0; + ip6.daddr.in6_u.u6_addr32[3] = bpf_htonl(2); + + // Calculate the IPv6 16-bit one's complement checksum of the IPv6 header. + __wsum sum6 = 0; + // We'll end up with a non-zero sum due to ip6.version == 6 + for (int i = 0; i < sizeof(ip6) / sizeof(__u16); ++i) + sum6 += ((__u16 *)&ip6)[i]; + + // Packet mutations begin - point of no return, but if this first modification fails + // the packet is probably still pristine, so let clatd handle it. + if (bpf_skb_change_proto(skb, bpf_htons(ETH_P_IPV6), 0)) + return TC_ACT_OK; + + // This takes care of updating the skb->csum field for a CHECKSUM_COMPLETE packet. + // In such a case, skb->csum is a 16-bit one's complement sum of the entire payload, + // thus we need to subtract out the ipv4 header's sum, and add in the ipv6 header's sum. + // However, we've already verified the ipv4 checksum is correct and thus 0. + // Thus we only need to add the ipv6 header's sum. + // + // bpf_csum_update() always succeeds if the skb is CHECKSUM_COMPLETE and returns an error + // (-ENOTSUPP) if it isn't. So we just ignore the return code (see above for more details). + bpf_csum_update(skb, sum6); + + // bpf_skb_change_proto() invalidates all pointers - reload them. + data = (void *)(long)skb->data; + data_end = (void *)(long)skb->data_end; + + // I cannot think of any valid way for this error condition to trigger, however I do + // believe the explicit check is required to keep the in kernel ebpf verifier happy. + if (data + l2_header_size + sizeof(ip6) > data_end) + return TC_ACT_SHOT; + + struct ethhdr *new_eth = data; + + // Copy over the updated ethernet header + *new_eth = eth2; + // Copy over the new ipv4 header. + *(struct ipv6hdr *)(new_eth + 1) = ip6; + return TC_ACT_OK; +} + +char _license[] SEC("license") = ("GPL"); diff --git a/tools/testing/selftests/net/udpgro_frglist.sh b/tools/testing/selftests/net/udpgro_frglist.sh index c9c4b9d65839..0a6359bed0b9 100755 --- a/tools/testing/selftests/net/udpgro_frglist.sh +++ b/tools/testing/selftests/net/udpgro_frglist.sh @@ -40,8 +40,8 @@ run_one() {

ip -n "${PEER_NS}" link set veth1 xdp object ${BPF_FILE} section xdp tc -n "${PEER_NS}" qdisc add dev veth1 clsact - tc -n "${PEER_NS}" filter add dev veth1 ingress prio 4 protocol ipv6 bpf object-file ../bpf/nat6to4.o section schedcls/ingress6/nat_6 direct-action - tc -n "${PEER_NS}" filter add dev veth1 egress prio 4 protocol ip bpf object-file ../bpf/nat6to4.o section schedcls/egress4/snat4 direct-action + tc -n "${PEER_NS}" filter add dev veth1 ingress prio 4 protocol ipv6 bpf object-file nat6to4.o section schedcls/ingress6/nat_6 direct-action + tc -n "${PEER_NS}" filter add dev veth1 egress prio 4 protocol ip bpf object-file nat6to4.o section schedcls/egress4/snat4 direct-action echo ${rx_args} ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} -r &

@@ -88,8 +88,8 @@ if [ ! -f ${BPF_FILE} ]; then exit -1 fi

-if [ ! -f bpf/nat6to4.o ]; then - echo "Missing nat6to4 helper. Build bpfnat6to4.o selftest first" +if [ ! -f nat6to4.o ]; then + echo "Missing nat6to4 helper. Build bpf nat6to4.o selftest first" exit -1 fi