From 23ee8a2563a0f24cf4964685ced23c32be444ab8 Mon Sep 17 00:00:00 2001 From: Qinxin Xia Date: Tue, 28 Oct 2025 20:08:59 +0800 Subject: dma-mapping: benchmark: Restore padding to ensure uABI remained consistent The padding field in the structure was previously reserved to maintain a stable interface for potential new fields, ensuring compatibility with user-space shared data structures. However,it was accidentally removed by tiantao in a prior commit, which may lead to incompatibility between user space and the kernel. This patch reinstates the padding to restore the original structure layout and preserve compatibility. Fixes: 8ddde07a3d28 ("dma-mapping: benchmark: extract a common header file for map_benchmark definition") Cc: stable@vger.kernel.org Acked-by: Barry Song Signed-off-by: Qinxin Xia Reported-by: Barry Song Closes: https://lore.kernel.org/lkml/CAGsJ_4waiZ2+NBJG+SCnbNk+nQ_ZF13_Q5FHJqZyxyJTcEop2A@mail.gmail.com/ Reviewed-by: Jonathan Cameron Signed-off-by: Marek Szyprowski Link: https://lore.kernel.org/r/20251028120900.2265511-2-xiaqinxin@huawei.com --- include/linux/map_benchmark.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/map_benchmark.h b/include/linux/map_benchmark.h index 62674c83bde4..48e2ff95332f 100644 --- a/include/linux/map_benchmark.h +++ b/include/linux/map_benchmark.h @@ -27,5 +27,6 @@ struct map_benchmark { __u32 dma_dir; /* DMA data direction */ __u32 dma_trans_ns; /* time for DMA transmission in ns */ __u32 granule; /* how many PAGE_SIZE will do map/unmap once a time */ + __u8 expansion[76]; /* For future use */ }; #endif /* _KERNEL_DMA_BENCHMARK_H */ -- cgit v1.2.3 From 39c89ee6e9c4464eb366f4e594379454a6c4db39 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Sat, 25 Oct 2025 21:53:18 +0100 Subject: compiler_types: Introduce __nocfi_generic There are two different ways that LLVM can expand kCFI operand bundles in LLVM IR: generically in the middle end or using an architecture specific sequence when lowering LLVM IR to machine code in the backend. The generic pass allows any architecture to take advantage of kCFI but the expansion of these bundles in the middle end can mess with optimizations that may turn indirect calls into direct calls when the call target is known at compile time, such as after inlining. Add __nocfi_generic, dependent on an architecture selecting CONFIG_ARCH_USES_CFI_GENERIC_LLVM_PASS, to disable kCFI bundle generation in functions where only the generic kCFI pass may cause problems. Link: https://github.com/ClangBuiltLinux/linux/issues/2124 Signed-off-by: Nathan Chancellor Link: https://patch.msgid.link/20251025-idpf-fix-arm-kcfi-build-error-v1-1-ec57221153ae@kernel.org Signed-off-by: Kees Cook --- arch/Kconfig | 7 +++++++ include/linux/compiler_types.h | 6 ++++++ 2 files changed, 13 insertions(+) (limited to 'include/linux') diff --git a/arch/Kconfig b/arch/Kconfig index 74ff01133532..61130b88964b 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -917,6 +917,13 @@ config ARCH_USES_CFI_TRAPS An architecture should select this option if it requires the .kcfi_traps section for KCFI trap handling. +config ARCH_USES_CFI_GENERIC_LLVM_PASS + bool + help + An architecture should select this option if it uses the generic + KCFIPass in LLVM to expand kCFI bundles instead of architecture-specific + lowering. + config CFI bool "Use Kernel Control Flow Integrity (kCFI)" default CFI_CLANG diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 59288a2c1ad2..1414be493738 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -461,6 +461,12 @@ struct ftrace_likely_data { # define __nocfi #endif +#if defined(CONFIG_ARCH_USES_CFI_GENERIC_LLVM_PASS) +# define __nocfi_generic __nocfi +#else +# define __nocfi_generic +#endif + /* * Any place that could be marked with the "alloc_size" attribute is also * a place to be marked with the "malloc" attribute, except those that may -- cgit v1.2.3 From a50f7456f853ec3a6f07cbe1d16ad8a8b2501320 Mon Sep 17 00:00:00 2001 From: James Clark Date: Thu, 30 Oct 2025 14:05:27 +0000 Subject: dma-mapping: Allow use of DMA_BIT_MASK(64) in global scope Clang doesn't like that (1ULL<<(64)) overflows when initializing a global scope variable, even if that part of the ternary isn't used when n = 64. The same initialization can be done without warnings in function scopes, and GCC doesn't mind either way. The build failure that highlighted this was already fixed in a different way [1], which also has detailed links to the Clang issues. However it's not going to be long before the same thing happens again, so it's better to fix the root cause. Fix it by using GENMASK_ULL() which does exactly the same thing, is much more readable anyway, and doesn't have a shift that overflows. [1]: https://lore.kernel.org/all/20250918-mmp-pdma-simplify-dma-addressing-v1-1-5c2be2b85696@riscstar.com/ Signed-off-by: James Clark Reviewed-by: Nathan Chancellor Signed-off-by: Marek Szyprowski Link: https://lore.kernel.org/r/20251030-james-fix-dma_bit_mask-v1-1-ad1ce7cfab6e@linaro.org --- include/linux/dma-mapping.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 8248ff9363ee..2ceda49c609f 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -90,7 +90,7 @@ */ #define DMA_MAPPING_ERROR (~(dma_addr_t)0) -#define DMA_BIT_MASK(n) (((n) == 64) ? ~0ULL : ((1ULL<<(n))-1)) +#define DMA_BIT_MASK(n) GENMASK_ULL(n - 1, 0) struct dma_iova_state { dma_addr_t addr; -- cgit v1.2.3 From 9818af18db4bfefd320d0fef41390a616365e6f7 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 6 Nov 2025 11:50:00 +0100 Subject: compiler_types: Move unused static inline functions warning to W=2 Per Nathan, clang catches unused "static inline" functions in C files since commit 6863f5643dd7 ("kbuild: allow Clang to find unused static inline functions for W=1 build"). Linus said: > So I entirely ignore W=1 issues, because I think so many of the extra > warnings are bogus. > > But if this one in particular is causing more problems than most - > some teams do seem to use W=1 as part of their test builds - it's fine > to send me a patch that just moves bad warnings to W=2. > > And if anybody uses W=2 for their test builds, that's THEIR problem.. Here is the change to bump the warning from W=1 to W=2. Fixes: 6863f5643dd7 ("kbuild: allow Clang to find unused static inline functions for W=1 build") Signed-off-by: Peter Zijlstra Signed-off-by: Andy Shevchenko Link: https://patch.msgid.link/20251106105000.2103276-1-andriy.shevchenko@linux.intel.com [nathan: Adjust comment as well] Signed-off-by: Nathan Chancellor --- include/linux/compiler_types.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 59288a2c1ad2..339603f05b54 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -250,10 +250,9 @@ struct ftrace_likely_data { /* * GCC does not warn about unused static inline functions for -Wunused-function. * Suppress the warning in clang as well by using __maybe_unused, but enable it - * for W=1 build. This will allow clang to find unused functions. Remove the - * __inline_maybe_unused entirely after fixing most of -Wunused-function warnings. + * for W=2 build. This will allow clang to find unused functions. */ -#ifdef KBUILD_EXTRA_WARN1 +#ifdef KBUILD_EXTRA_WARN2 #define __inline_maybe_unused #else #define __inline_maybe_unused __maybe_unused -- cgit v1.2.3 From 77008e1b2ef73249bceb078a321a3ff6bc087afb Mon Sep 17 00:00:00 2001 From: Zi Yan Date: Thu, 16 Oct 2025 21:36:30 -0400 Subject: mm/huge_memory: do not change split_huge_page*() target order silently Page cache folios from a file system that support large block size (LBS) can have minimal folio order greater than 0, thus a high order folio might not be able to be split down to order-0. Commit e220917fa507 ("mm: split a folio in minimum folio order chunks") bumps the target order of split_huge_page*() to the minimum allowed order when splitting a LBS folio. This causes confusion for some split_huge_page*() callers like memory failure handling code, since they expect after-split folios all have order-0 when split succeeds but in reality get min_order_for_split() order folios and give warnings. Fix it by failing a split if the folio cannot be split to the target order. Rename try_folio_split() to try_folio_split_to_order() to reflect the added new_order parameter. Remove its unused list parameter. [The test poisons LBS folios, which cannot be split to order-0 folios, and also tries to poison all memory. The non split LBS folios take more memory than the test anticipated, leading to OOM. The patch fixed the kernel warning and the test needs some change to avoid OOM.] Link: https://lkml.kernel.org/r/20251017013630.139907-1-ziy@nvidia.com Fixes: e220917fa507 ("mm: split a folio in minimum folio order chunks") Signed-off-by: Zi Yan Reported-by: syzbot+e6367ea2fdab6ed46056@syzkaller.appspotmail.com Closes: https://lore.kernel.org/all/68d2c943.a70a0220.1b52b.02b3.GAE@google.com/ Reviewed-by: Luis Chamberlain Reviewed-by: Pankaj Raghav Reviewed-by: Wei Yang Acked-by: David Hildenbrand Reviewed-by: Lorenzo Stoakes Reviewed-by: Miaohe Lin Cc: Baolin Wang Cc: Barry Song Cc: David Hildenbrand Cc: Dev Jain Cc: Jane Chu Cc: Lance Yang Cc: Liam Howlett Cc: Mariano Pache Cc: Matthew Wilcox (Oracle) Cc: Naoya Horiguchi Cc: Ryan Roberts Cc: Christian Brauner Cc: Signed-off-by: Andrew Morton --- include/linux/huge_mm.h | 55 +++++++++++++++++++++---------------------------- mm/huge_memory.c | 9 +------- mm/truncate.c | 6 ++++-- 3 files changed, 28 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index f327d62fc985..71ac78b9f834 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -376,45 +376,30 @@ bool non_uniform_split_supported(struct folio *folio, unsigned int new_order, int folio_split(struct folio *folio, unsigned int new_order, struct page *page, struct list_head *list); /* - * try_folio_split - try to split a @folio at @page using non uniform split. + * try_folio_split_to_order - try to split a @folio at @page to @new_order using + * non uniform split. * @folio: folio to be split - * @page: split to order-0 at the given page - * @list: store the after-split folios + * @page: split to @new_order at the given page + * @new_order: the target split order * - * Try to split a @folio at @page using non uniform split to order-0, if - * non uniform split is not supported, fall back to uniform split. + * Try to split a @folio at @page using non uniform split to @new_order, if + * non uniform split is not supported, fall back to uniform split. After-split + * folios are put back to LRU list. Use min_order_for_split() to get the lower + * bound of @new_order. * * Return: 0: split is successful, otherwise split failed. */ -static inline int try_folio_split(struct folio *folio, struct page *page, - struct list_head *list) +static inline int try_folio_split_to_order(struct folio *folio, + struct page *page, unsigned int new_order) { - int ret = min_order_for_split(folio); - - if (ret < 0) - return ret; - - if (!non_uniform_split_supported(folio, 0, false)) - return split_huge_page_to_list_to_order(&folio->page, list, - ret); - return folio_split(folio, ret, page, list); + if (!non_uniform_split_supported(folio, new_order, /* warns= */ false)) + return split_huge_page_to_list_to_order(&folio->page, NULL, + new_order); + return folio_split(folio, new_order, page, NULL); } static inline int split_huge_page(struct page *page) { - struct folio *folio = page_folio(page); - int ret = min_order_for_split(folio); - - if (ret < 0) - return ret; - - /* - * split_huge_page() locks the page before splitting and - * expects the same page that has been split to be locked when - * returned. split_folio(page_folio(page)) cannot be used here - * because it converts the page to folio and passes the head - * page to be split. - */ - return split_huge_page_to_list_to_order(page, NULL, ret); + return split_huge_page_to_list_to_order(page, NULL, 0); } void deferred_split_folio(struct folio *folio, bool partially_mapped); @@ -597,14 +582,20 @@ static inline int split_huge_page(struct page *page) return -EINVAL; } +static inline int min_order_for_split(struct folio *folio) +{ + VM_WARN_ON_ONCE_FOLIO(1, folio); + return -EINVAL; +} + static inline int split_folio_to_list(struct folio *folio, struct list_head *list) { VM_WARN_ON_ONCE_FOLIO(1, folio); return -EINVAL; } -static inline int try_folio_split(struct folio *folio, struct page *page, - struct list_head *list) +static inline int try_folio_split_to_order(struct folio *folio, + struct page *page, unsigned int new_order) { VM_WARN_ON_ONCE_FOLIO(1, folio); return -EINVAL; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 1d1b74950332..feac4aef7dfb 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -3653,8 +3653,6 @@ static int __folio_split(struct folio *folio, unsigned int new_order, min_order = mapping_min_folio_order(folio->mapping); if (new_order < min_order) { - VM_WARN_ONCE(1, "Cannot split mapped folio below min-order: %u", - min_order); ret = -EINVAL; goto out; } @@ -3986,12 +3984,7 @@ int min_order_for_split(struct folio *folio) int split_folio_to_list(struct folio *folio, struct list_head *list) { - int ret = min_order_for_split(folio); - - if (ret < 0) - return ret; - - return split_huge_page_to_list_to_order(&folio->page, list, ret); + return split_huge_page_to_list_to_order(&folio->page, list, 0); } /* diff --git a/mm/truncate.c b/mm/truncate.c index 91eb92a5ce4f..9210cf808f5c 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -194,6 +194,7 @@ bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end) size_t size = folio_size(folio); unsigned int offset, length; struct page *split_at, *split_at2; + unsigned int min_order; if (pos < start) offset = start - pos; @@ -223,8 +224,9 @@ bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end) if (!folio_test_large(folio)) return true; + min_order = mapping_min_folio_order(folio->mapping); split_at = folio_page(folio, PAGE_ALIGN_DOWN(offset) / PAGE_SIZE); - if (!try_folio_split(folio, split_at, NULL)) { + if (!try_folio_split_to_order(folio, split_at, min_order)) { /* * try to split at offset + length to make sure folios within * the range can be dropped, especially to avoid memory waste @@ -254,7 +256,7 @@ bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end) */ if (folio_test_large(folio2) && folio2->mapping == folio->mapping) - try_folio_split(folio2, split_at2, NULL); + try_folio_split_to_order(folio2, split_at2, min_order); folio_unlock(folio2); out: -- cgit v1.2.3 From fa759cd75bce5489eed34596daa53f721849a86f Mon Sep 17 00:00:00 2001 From: Pasha Tatashin Date: Mon, 20 Oct 2025 20:08:52 -0400 Subject: kho: allocate metadata directly from the buddy allocator KHO allocates metadata for its preserved memory map using the slab allocator via kzalloc(). This metadata is temporary and is used by the next kernel during early boot to find preserved memory. A problem arises when KFENCE is enabled. kzalloc() calls can be randomly intercepted by kfence_alloc(), which services the allocation from a dedicated KFENCE memory pool. This pool is allocated early in boot via memblock. When booting via KHO, the memblock allocator is restricted to a "scratch area", forcing the KFENCE pool to be allocated within it. This creates a conflict, as the scratch area is expected to be ephemeral and overwriteable by a subsequent kexec. If KHO metadata is placed in this KFENCE pool, it leads to memory corruption when the next kernel is loaded. To fix this, modify KHO to allocate its metadata directly from the buddy allocator instead of slab. Link: https://lkml.kernel.org/r/20251021000852.2924827-4-pasha.tatashin@soleen.com Fixes: fc33e4b44b27 ("kexec: enable KHO support for memory preservation") Signed-off-by: Pasha Tatashin Reviewed-by: Pratyush Yadav Reviewed-by: Mike Rapoport (Microsoft) Reviewed-by: David Matlack Cc: Alexander Graf Cc: Christian Brauner Cc: Jason Gunthorpe Cc: Jonathan Corbet Cc: Masahiro Yamada Cc: Miguel Ojeda Cc: Randy Dunlap Cc: Samiullah Khawaja Cc: Tejun Heo Cc: Signed-off-by: Andrew Morton --- include/linux/gfp.h | 3 +++ kernel/kexec_handover.c | 6 +++--- 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 0ceb4e09306c..623bee335383 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -7,6 +7,7 @@ #include #include #include +#include #include struct vm_area_struct; @@ -463,4 +464,6 @@ static inline struct folio *folio_alloc_gigantic_noprof(int order, gfp_t gfp, /* This should be paired with folio_put() rather than free_contig_range(). */ #define folio_alloc_gigantic(...) alloc_hooks(folio_alloc_gigantic_noprof(__VA_ARGS__)) +DEFINE_FREE(free_page, void *, free_page((unsigned long)_T)) + #endif /* __LINUX_GFP_H */ diff --git a/kernel/kexec_handover.c b/kernel/kexec_handover.c index 9217d2fdd2d3..2a8c20c238a8 100644 --- a/kernel/kexec_handover.c +++ b/kernel/kexec_handover.c @@ -142,7 +142,7 @@ static void *xa_load_or_alloc(struct xarray *xa, unsigned long index) if (res) return res; - void *elm __free(kfree) = kzalloc(PAGE_SIZE, GFP_KERNEL); + void *elm __free(free_page) = (void *)get_zeroed_page(GFP_KERNEL); if (!elm) return ERR_PTR(-ENOMEM); @@ -348,9 +348,9 @@ static_assert(sizeof(struct khoser_mem_chunk) == PAGE_SIZE); static struct khoser_mem_chunk *new_chunk(struct khoser_mem_chunk *cur_chunk, unsigned long order) { - struct khoser_mem_chunk *chunk __free(kfree) = NULL; + struct khoser_mem_chunk *chunk __free(free_page) = NULL; - chunk = kzalloc(PAGE_SIZE, GFP_KERNEL); + chunk = (void *)get_zeroed_page(GFP_KERNEL); if (!chunk) return ERR_PTR(-ENOMEM); -- cgit v1.2.3 From e5eba42f01340f73888dfe560be2806057c25913 Mon Sep 17 00:00:00 2001 From: Akiva Goldberger Date: Sun, 9 Nov 2025 11:49:03 +0200 Subject: mlx5: Fix default values in create CQ Currently, CQs without a completion function are assigned the mlx5_add_cq_to_tasklet function by default. This is problematic since only user CQs created through the mlx5_ib driver are intended to use this function. Additionally, all CQs that will use doorbells instead of polling for completions must call mlx5_cq_arm. However, the default CQ creation flow leaves a valid value in the CQ's arm_db field, allowing FW to send interrupts to polling-only CQs in certain corner cases. These two factors would allow a polling-only kernel CQ to be triggered by an EQ interrupt and call a completion function intended only for user CQs, causing a null pointer exception. Some areas in the driver have prevented this issue with one-off fixes but did not address the root cause. This patch fixes the described issue by adding defaults to the create CQ flow. It adds a default dummy completion function to protect against null pointer exceptions, and it sets an invalid command sequence number by default in kernel CQs to prevent the FW from sending an interrupt to the CQ until it is armed. User CQs are responsible for their own initialization values. Callers of mlx5_core_create_cq are responsible for changing the completion function and arming the CQ per their needs. Fixes: cdd04f4d4d71 ("net/mlx5: Add support to create SQ and CQ for ASO") Signed-off-by: Akiva Goldberger Reviewed-by: Moshe Shemesh Signed-off-by: Tariq Toukan Acked-by: Leon Romanovsky Link: https://patch.msgid.link/1762681743-1084694-1-git-send-email-tariqt@nvidia.com Signed-off-by: Paolo Abeni --- drivers/infiniband/hw/mlx5/cq.c | 11 +++++---- drivers/net/ethernet/mellanox/mlx5/core/cq.c | 23 +++++++++++++++--- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 1 - .../net/ethernet/mellanox/mlx5/core/fpga/conn.c | 15 ++++++------ .../mellanox/mlx5/core/steering/hws/send.c | 7 ------ .../mellanox/mlx5/core/steering/sws/dr_send.c | 28 ++++++---------------- drivers/vdpa/mlx5/net/mlx5_vnet.c | 6 ++--- include/linux/mlx5/cq.h | 1 + 8 files changed, 44 insertions(+), 48 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c index a23b364e24ff..651d76bca114 100644 --- a/drivers/infiniband/hw/mlx5/cq.c +++ b/drivers/infiniband/hw/mlx5/cq.c @@ -1020,15 +1020,18 @@ int mlx5_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, if (cq->create_flags & IB_UVERBS_CQ_FLAGS_IGNORE_OVERRUN) MLX5_SET(cqc, cqc, oi, 1); + if (udata) { + cq->mcq.comp = mlx5_add_cq_to_tasklet; + cq->mcq.tasklet_ctx.comp = mlx5_ib_cq_comp; + } else { + cq->mcq.comp = mlx5_ib_cq_comp; + } + err = mlx5_core_create_cq(dev->mdev, &cq->mcq, cqb, inlen, out, sizeof(out)); if (err) goto err_cqb; mlx5_ib_dbg(dev, "cqn 0x%x\n", cq->mcq.cqn); - if (udata) - cq->mcq.tasklet_ctx.comp = mlx5_ib_cq_comp; - else - cq->mcq.comp = mlx5_ib_cq_comp; cq->mcq.event = mlx5_ib_cq_event; INIT_LIST_HEAD(&cq->wc_list); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cq.c b/drivers/net/ethernet/mellanox/mlx5/core/cq.c index e9f319a9bdd6..60f7ab1d72e7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cq.c @@ -66,8 +66,8 @@ void mlx5_cq_tasklet_cb(struct tasklet_struct *t) tasklet_schedule(&ctx->task); } -static void mlx5_add_cq_to_tasklet(struct mlx5_core_cq *cq, - struct mlx5_eqe *eqe) +void mlx5_add_cq_to_tasklet(struct mlx5_core_cq *cq, + struct mlx5_eqe *eqe) { unsigned long flags; struct mlx5_eq_tasklet *tasklet_ctx = cq->tasklet_ctx.priv; @@ -95,7 +95,15 @@ static void mlx5_add_cq_to_tasklet(struct mlx5_core_cq *cq, if (schedule_tasklet) tasklet_schedule(&tasklet_ctx->task); } +EXPORT_SYMBOL(mlx5_add_cq_to_tasklet); +static void mlx5_core_cq_dummy_cb(struct mlx5_core_cq *cq, struct mlx5_eqe *eqe) +{ + mlx5_core_err(cq->eq->core.dev, + "CQ default completion callback, CQ #%u\n", cq->cqn); +} + +#define MLX5_CQ_INIT_CMD_SN cpu_to_be32(2 << 28) /* Callers must verify outbox status in case of err */ int mlx5_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, u32 *in, int inlen, u32 *out, int outlen) @@ -121,10 +129,19 @@ int mlx5_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, cq->arm_sn = 0; cq->eq = eq; cq->uid = MLX5_GET(create_cq_in, in, uid); + + /* Kernel CQs must set the arm_db address prior to calling + * this function, allowing for the proper value to be + * initialized. User CQs are responsible for their own + * initialization since they do not use the arm_db field. + */ + if (cq->arm_db) + *cq->arm_db = MLX5_CQ_INIT_CMD_SN; + refcount_set(&cq->refcount, 1); init_completion(&cq->free); if (!cq->comp) - cq->comp = mlx5_add_cq_to_tasklet; + cq->comp = mlx5_core_cq_dummy_cb; /* assuming CQ will be deleted before the EQ */ cq->tasklet_ctx.priv = &eq->tasklet_ctx; INIT_LIST_HEAD(&cq->tasklet_ctx.list); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 6023bbbf3f39..5e17eae81f4b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -2219,7 +2219,6 @@ static int mlx5e_alloc_cq_common(struct mlx5_core_dev *mdev, mcq->set_ci_db = cq->wq_ctrl.db.db; mcq->arm_db = cq->wq_ctrl.db.db + 1; *mcq->set_ci_db = 0; - *mcq->arm_db = 0; mcq->vector = param->eq_ix; mcq->comp = mlx5e_completion_event; mcq->event = mlx5e_cq_error_event; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c index cb1319974f83..ccef64fb40b6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c @@ -421,6 +421,13 @@ static int mlx5_fpga_conn_create_cq(struct mlx5_fpga_conn *conn, int cq_size) __be64 *pas; u32 i; + conn->cq.mcq.cqe_sz = 64; + conn->cq.mcq.set_ci_db = conn->cq.wq_ctrl.db.db; + conn->cq.mcq.arm_db = conn->cq.wq_ctrl.db.db + 1; + *conn->cq.mcq.set_ci_db = 0; + conn->cq.mcq.vector = 0; + conn->cq.mcq.comp = mlx5_fpga_conn_cq_complete; + cq_size = roundup_pow_of_two(cq_size); MLX5_SET(cqc, temp_cqc, log_cq_size, ilog2(cq_size)); @@ -468,15 +475,7 @@ static int mlx5_fpga_conn_create_cq(struct mlx5_fpga_conn *conn, int cq_size) if (err) goto err_cqwq; - conn->cq.mcq.cqe_sz = 64; - conn->cq.mcq.set_ci_db = conn->cq.wq_ctrl.db.db; - conn->cq.mcq.arm_db = conn->cq.wq_ctrl.db.db + 1; - *conn->cq.mcq.set_ci_db = 0; - *conn->cq.mcq.arm_db = 0; - conn->cq.mcq.vector = 0; - conn->cq.mcq.comp = mlx5_fpga_conn_cq_complete; tasklet_setup(&conn->cq.tasklet, mlx5_fpga_conn_cq_tasklet); - mlx5_fpga_dbg(fdev, "Created CQ #0x%x\n", conn->cq.mcq.cqn); goto out; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c index 24ef7d66fa8a..7510c46e58a5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c @@ -873,12 +873,6 @@ err_free_sqc: return err; } -static void hws_cq_complete(struct mlx5_core_cq *mcq, - struct mlx5_eqe *eqe) -{ - pr_err("CQ completion CQ: #%u\n", mcq->cqn); -} - static int hws_send_ring_alloc_cq(struct mlx5_core_dev *mdev, int numa_node, struct mlx5hws_send_engine *queue, @@ -901,7 +895,6 @@ static int hws_send_ring_alloc_cq(struct mlx5_core_dev *mdev, mcq->cqe_sz = 64; mcq->set_ci_db = cq->wq_ctrl.db.db; mcq->arm_db = cq->wq_ctrl.db.db + 1; - mcq->comp = hws_cq_complete; for (i = 0; i < mlx5_cqwq_get_size(&cq->wq); i++) { cqe = mlx5_cqwq_get_wqe(&cq->wq, i); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_send.c index 077a77fde670..d034372fa047 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_send.c @@ -1049,12 +1049,6 @@ static int dr_prepare_qp_to_rts(struct mlx5dr_domain *dmn) return 0; } -static void dr_cq_complete(struct mlx5_core_cq *mcq, - struct mlx5_eqe *eqe) -{ - pr_err("CQ completion CQ: #%u\n", mcq->cqn); -} - static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, struct mlx5_uars_page *uar, size_t ncqe) @@ -1089,6 +1083,13 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, cqe->op_own = MLX5_CQE_INVALID << 4 | MLX5_CQE_OWNER_MASK; } + cq->mcq.cqe_sz = 64; + cq->mcq.set_ci_db = cq->wq_ctrl.db.db; + cq->mcq.arm_db = cq->wq_ctrl.db.db + 1; + *cq->mcq.set_ci_db = 0; + cq->mcq.vector = 0; + cq->mdev = mdev; + inlen = MLX5_ST_SZ_BYTES(create_cq_in) + sizeof(u64) * cq->wq_ctrl.buf.npages; in = kvzalloc(inlen, GFP_KERNEL); @@ -1112,27 +1113,12 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, pas = (__be64 *)MLX5_ADDR_OF(create_cq_in, in, pas); mlx5_fill_page_frag_array(&cq->wq_ctrl.buf, pas); - cq->mcq.comp = dr_cq_complete; - err = mlx5_core_create_cq(mdev, &cq->mcq, in, inlen, out, sizeof(out)); kvfree(in); if (err) goto err_cqwq; - cq->mcq.cqe_sz = 64; - cq->mcq.set_ci_db = cq->wq_ctrl.db.db; - cq->mcq.arm_db = cq->wq_ctrl.db.db + 1; - *cq->mcq.set_ci_db = 0; - - /* set no-zero value, in order to avoid the HW to run db-recovery on - * CQ that used in polling mode. - */ - *cq->mcq.arm_db = cpu_to_be32(2 << 28); - - cq->mcq.vector = 0; - cq->mdev = mdev; - return cq; err_cqwq: diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 82034efb74fc..a7936bd1aabe 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -573,6 +573,8 @@ static int cq_create(struct mlx5_vdpa_net *ndev, u16 idx, u32 num_ent) vcq->mcq.set_ci_db = vcq->db.db; vcq->mcq.arm_db = vcq->db.db + 1; vcq->mcq.cqe_sz = 64; + vcq->mcq.comp = mlx5_vdpa_cq_comp; + vcq->cqe = num_ent; err = cq_frag_buf_alloc(ndev, &vcq->buf, num_ent); if (err) @@ -612,10 +614,6 @@ static int cq_create(struct mlx5_vdpa_net *ndev, u16 idx, u32 num_ent) if (err) goto err_vec; - vcq->mcq.comp = mlx5_vdpa_cq_comp; - vcq->cqe = num_ent; - vcq->mcq.set_ci_db = vcq->db.db; - vcq->mcq.arm_db = vcq->db.db + 1; mlx5_cq_arm(&mvq->cq.mcq, MLX5_CQ_DB_REQ_NOT, uar_page, mvq->cq.mcq.cons_index); kfree(in); return 0; diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h index 7ef2c7c7d803..9d47cdc727ad 100644 --- a/include/linux/mlx5/cq.h +++ b/include/linux/mlx5/cq.h @@ -183,6 +183,7 @@ static inline void mlx5_cq_put(struct mlx5_core_cq *cq) complete(&cq->free); } +void mlx5_add_cq_to_tasklet(struct mlx5_core_cq *cq, struct mlx5_eqe *eqe); int mlx5_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, u32 *in, int inlen, u32 *out, int outlen); int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, -- cgit v1.2.3 From bb8336a5163a5839476f27ed1ad69df4a19e13ca Mon Sep 17 00:00:00 2001 From: Kriish Sharma Date: Mon, 10 Nov 2025 18:25:45 +0000 Subject: ethtool: fix incorrect kernel-doc style comment in ethtool.h Building documentation produced the following warning: WARNING: ./include/linux/ethtool.h:495 This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst * IEEE 802.3ck/df defines 16 bins for FEC histogram plus one more for This comment was not intended to be parsed as kernel-doc, so replace the '/**' with '/*' to silence the warning and align with normal comment style in header files. No functional changes. Signed-off-by: Kriish Sharma Link: https://patch.msgid.link/20251110182545.2112596-1-kriish.sharma2006@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/ethtool.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index c2d8b4ec62eb..5c9162193d26 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -492,7 +492,7 @@ struct ethtool_pause_stats { }; #define ETHTOOL_MAX_LANES 8 -/** +/* * IEEE 802.3ck/df defines 16 bins for FEC histogram plus one more for * the end-of-list marker, total 17 items */ -- cgit v1.2.3