- Linux-stable-mirror - lists.linaro.org

kvm: arm64: stable commit "Fix kernel BUG() due to bad backport of FPSIMD/SVE/SME fix" deadlocks host kernel

by Sergey Senozhatsky

Commits 8f4dc4e54eed4 (6.1.y) and 23249dade24e6 (5.15.y) (maybe other stable kernels as well) deadlock the host kernel (presumably a recursive spinlock): queued_spin_lock_slowpath+0x274/0x358 raw_spin_rq_lock_nested+0x2c/0x48 _raw_spin_rq_lock_irqsave+0x30/0x4c run_rebalance_domains+0x808/0x2e18 __do_softirq+0x104/0x550 irq_exit+0x88/0xe0 handle_domain_irq+0x7c/0xb0 gic_handle_irq+0x1cc/0x420 call_on_irq_stack+0x20/0x48 do_interrupt_handler+0x3c/0x50 el1_interrupt+0x30/0x58 el1h_64_irq_handler+0x18/0x24 el1h_64_irq+0x7c/0x80 kvm_arch_vcpu_ioctl_run+0x24c/0x49c kvm_vcpu_ioctl+0xc4/0x614 We found out a similar report at [1], but it doesn't seem like a formal patch was ever posted. Will, can you please send a formal patch so that stable kernels can run VMs again? [1] https://lists.linaro.org/archives/list/linux-stable-mirror@lists.linaro.org…

1 month, 3 weeks

2
2
0 0

[PATCH v2 01/20] arm64: Revert support for generic kernel mode FPU

by Ard Biesheuvel

From: Ard Biesheuvel <ardb(a)kernel.org> On arm64, generic kernel mode FPU support, as used by the AMD GPU driver, involves dropping the -mgeneral-regs-only compiler flag, as that flag makes the use of double and float C types impossible. However, dropping that flag allows the compiler to use FPU and SIMD registers in other ways too, and for this reason, arm64 only permits doing so in strictly controlled contexts, i.e., isolated compilation units that get called from inside a kernel_neon_begin() and kernel_neon_end() pair. The users of the generic kernel mode FPU API lack such strict checks, and this may result in userland FP/SIMD state to get corrupted, given that touching FP/SIMD registers outside of a kernel_neon_begin/end pair does not fault, but silently operates on the userland state without preserving it. So disable this feature for the time being. This reverts commits 71883ae35278 arm64: implement ARCH_HAS_KERNEL_FPU_SUPPORT 7177089525d9 arm64: crypto: use CC_FLAGS_FPU for NEON CFLAGS 4be073931cd8 lib/raid6: use CC_FLAGS_FPU for NEON CFLAGS Cc: <stable(a)vger.kernel.org> # v6.12+ Signed-off-by: Ard Biesheuvel <ardb(a)kernel.org> --- arch/arm64/Kconfig | 1 - arch/arm64/Makefile | 9 +----- arch/arm64/include/asm/fpu.h | 15 --------- arch/arm64/lib/Makefile | 6 ++-- lib/raid6/Makefile | 33 ++++++++++++++------ 5 files changed, 28 insertions(+), 36 deletions(-) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index b81ab5fbde57..abf70929f675 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -32,7 +32,6 @@ config ARM64 select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_GIGANTIC_PAGE select ARCH_HAS_KCOV - select ARCH_HAS_KERNEL_FPU_SUPPORT if KERNEL_MODE_NEON select ARCH_HAS_KEEPINITRD select ARCH_HAS_MEMBARRIER_SYNC_CORE select ARCH_HAS_MEM_ENCRYPT diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 73a10f65ce8b..82209cc52a5a 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -33,14 +33,7 @@ ifeq ($(CONFIG_BROKEN_GAS_INST),y) $(warning Detected assembler with broken .inst; disassembly will be unreliable) endif -# The GCC option -ffreestanding is required in order to compile code containing -# ARM/NEON intrinsics in a non C99-compliant environment (such as the kernel) -CC_FLAGS_FPU := -ffreestanding -# Enable <arm_neon.h> -CC_FLAGS_FPU += -isystem $(shell $(CC) -print-file-name=include) -CC_FLAGS_NO_FPU := -mgeneral-regs-only - -KBUILD_CFLAGS += $(CC_FLAGS_NO_FPU) \ +KBUILD_CFLAGS += -mgeneral-regs-only \ $(compat_vdso) $(cc_has_k_constraint) KBUILD_CFLAGS += $(call cc-disable-warning, psabi) KBUILD_AFLAGS += $(compat_vdso) diff --git a/arch/arm64/include/asm/fpu.h b/arch/arm64/include/asm/fpu.h deleted file mode 100644 index 2ae50bdce59b..000000000000 --- a/arch/arm64/include/asm/fpu.h +++ /dev/null @@ -1,15 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2023 SiFive - */ - -#ifndef __ASM_FPU_H -#define __ASM_FPU_H - -#include <asm/neon.h> - -#define kernel_fpu_available() cpu_has_neon() -#define kernel_fpu_begin() kernel_neon_begin() -#define kernel_fpu_end() kernel_neon_end() - -#endif /* ! __ASM_FPU_H */ diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile index 633e5223d944..291b616ab511 100644 --- a/arch/arm64/lib/Makefile +++ b/arch/arm64/lib/Makefile @@ -7,8 +7,10 @@ lib-y := clear_user.o delay.o copy_from_user.o \ ifeq ($(CONFIG_KERNEL_MODE_NEON), y) obj-$(CONFIG_XOR_BLOCKS) += xor-neon.o -CFLAGS_xor-neon.o += $(CC_FLAGS_FPU) -CFLAGS_REMOVE_xor-neon.o += $(CC_FLAGS_NO_FPU) +CFLAGS_REMOVE_xor-neon.o += -mgeneral-regs-only +CFLAGS_xor-neon.o += -ffreestanding +# Enable <arm_neon.h> +CFLAGS_xor-neon.o += -isystem $(shell $(CC) -print-file-name=include) endif lib-$(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) += uaccess_flushcache.o diff --git a/lib/raid6/Makefile b/lib/raid6/Makefile index 5be0a4e60ab1..903e287c50c8 100644 --- a/lib/raid6/Makefile +++ b/lib/raid6/Makefile @@ -34,6 +34,25 @@ CFLAGS_REMOVE_vpermxor8.o += -msoft-float endif endif +# The GCC option -ffreestanding is required in order to compile code containing +# ARM/NEON intrinsics in a non C99-compliant environment (such as the kernel) +ifeq ($(CONFIG_KERNEL_MODE_NEON),y) +NEON_FLAGS := -ffreestanding +# Enable <arm_neon.h> +NEON_FLAGS += -isystem $(shell $(CC) -print-file-name=include) +ifeq ($(ARCH),arm) +NEON_FLAGS += -march=armv7-a -mfloat-abi=softfp -mfpu=neon +endif +CFLAGS_recov_neon_inner.o += $(NEON_FLAGS) +ifeq ($(ARCH),arm64) +CFLAGS_REMOVE_recov_neon_inner.o += -mgeneral-regs-only +CFLAGS_REMOVE_neon1.o += -mgeneral-regs-only +CFLAGS_REMOVE_neon2.o += -mgeneral-regs-only +CFLAGS_REMOVE_neon4.o += -mgeneral-regs-only +CFLAGS_REMOVE_neon8.o += -mgeneral-regs-only +endif +endif + quiet_cmd_unroll = UNROLL $@ cmd_unroll = $(AWK) -v N=$* -f $(src)/unroll.awk < $< > $@ @@ -57,16 +76,10 @@ targets += vpermxor1.c vpermxor2.c vpermxor4.c vpermxor8.c $(obj)/vpermxor%.c: $(src)/vpermxor.uc $(src)/unroll.awk FORCE $(call if_changed,unroll) -CFLAGS_neon1.o += $(CC_FLAGS_FPU) -CFLAGS_neon2.o += $(CC_FLAGS_FPU) -CFLAGS_neon4.o += $(CC_FLAGS_FPU) -CFLAGS_neon8.o += $(CC_FLAGS_FPU) -CFLAGS_recov_neon_inner.o += $(CC_FLAGS_FPU) -CFLAGS_REMOVE_neon1.o += $(CC_FLAGS_NO_FPU) -CFLAGS_REMOVE_neon2.o += $(CC_FLAGS_NO_FPU) -CFLAGS_REMOVE_neon4.o += $(CC_FLAGS_NO_FPU) -CFLAGS_REMOVE_neon8.o += $(CC_FLAGS_NO_FPU) -CFLAGS_REMOVE_recov_neon_inner.o += $(CC_FLAGS_NO_FPU) +CFLAGS_neon1.o += $(NEON_FLAGS) +CFLAGS_neon2.o += $(NEON_FLAGS) +CFLAGS_neon4.o += $(NEON_FLAGS) +CFLAGS_neon8.o += $(NEON_FLAGS) targets += neon1.c neon2.c neon4.c neon8.c $(obj)/neon%.c: $(src)/neon.uc $(src)/unroll.awk FORCE $(call if_changed,unroll) -- 2.51.0.618.g983fd99d29-goog

1 month, 3 weeks

3
2
0 0

BUS105 Exam Format Explained: What You Need to Know Before You Register

by Jerry

Understanding the BUS105 exam format before you register is crucial for building an effective study strategy and avoiding surprises on test day. The BUS105 exam evaluates your knowledge of business fundamentals, including management principles, marketing concepts, financial literacy, and organizational behavior. The test typically consists of multiple-choice questions designed to measure both theoretical understanding and practical application of business concepts. To prepare efficiently, familiarize yourself with the structure and types of questions you’ll face. Practicing with BUS105 Practice Questions from study4exam can give you a clear idea of what to expect. These resources replicate real exam conditions, allowing you to improve time management and accuracy while identifying areas that need more attention. More info visit this website: https://www.study4exam.com/saylor/free-bus105-questions Understanding the marking scheme, question difficulty, and key focus areas in advance ensures you go into the exam well-prepared and confident. With the right preparation strategy and quality practice materials, you can successfully master the BUS105 exam and take a significant step toward your academic or professional goals.

1 month, 3 weeks

1
0
0 0

[Patch v3 1/2] mm/huge_memory: add pmd folio to ds_queue in do_huge_zero_wp_pmd()

by Wei Yang

We add pmd folio into ds_queue on the first page fault in __do_huge_pmd_anonymous_page(), so that we can split it in case of memory pressure. This should be the same for a pmd folio during wp page fault. Commit 1ced09e0331f ("mm: allocate THP on hugezeropage wp-fault") miss to add it to ds_queue, which means system may not reclaim enough memory in case of memory pressure even the pmd folio is under used. Move deferred_split_folio() into map_anon_folio_pmd() to make the pmd folio installation consistent. Fixes: 1ced09e0331f ("mm: allocate THP on hugezeropage wp-fault") Signed-off-by: Wei Yang <richard.weiyang(a)gmail.com> Cc: David Hildenbrand <david(a)redhat.com> Cc: Lance Yang <lance.yang(a)linux.dev> Cc: Dev Jain <dev.jain(a)arm.com> Acked-by: David Hildenbrand <david(a)redhat.com> Reviewed-by: Lance Yang <lance.yang(a)linux.dev> Reviewed-by: Dev Jain <dev.jain(a)arm.com> Acked-by: Usama Arif <usamaarif642(a)gmail.com> Reviewed-by: Zi Yan <ziy(a)nvidia.com> Cc: <stable(a)vger.kernel.org> --- v3: * rebase on latest mm-new * gather rb and acked-by v2: * add fix, cc stable and put description about the flow of current code * move deferred_split_folio() into map_anon_folio_pmd() --- mm/huge_memory.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 002922bb6e42..e86699306c5e 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1317,6 +1317,7 @@ static void map_anon_folio_pmd(struct folio *folio, pmd_t *pmd, count_vm_event(THP_FAULT_ALLOC); count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_ALLOC); count_memcg_event_mm(vma->vm_mm, THP_FAULT_ALLOC); + deferred_split_folio(folio, false); } static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf) @@ -1357,7 +1358,6 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf) pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable); map_anon_folio_pmd(folio, vmf->pmd, vma, haddr); mm_inc_nr_ptes(vma->vm_mm); - deferred_split_folio(folio, false); spin_unlock(vmf->ptl); } -- 2.34.1

1 month, 3 weeks

1
0
0 0

[PATCH] media: mtk-mdp: Fix a reference leak bug in mtk_mdp_remove()

by Haoxiang Li

In mtk_mdp_probe(), vpu_get_plat_device() increases the reference count of the returned platform device. Add platform_device_put() to prevent reference leak. Fixes: c8eb2d7e8202 ("[media] media: Add Mediatek MDP Driver") Cc: stable(a)vger.kernel.org Signed-off-by: Haoxiang Li <haoxiang_li2024(a)163.com> --- drivers/media/platform/mediatek/mdp/mtk_mdp_core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/media/platform/mediatek/mdp/mtk_mdp_core.c b/drivers/media/platform/mediatek/mdp/mtk_mdp_core.c index 80fdc6ff57e0..eb212ca1a083 100644 --- a/drivers/media/platform/mediatek/mdp/mtk_mdp_core.c +++ b/drivers/media/platform/mediatek/mdp/mtk_mdp_core.c @@ -242,6 +242,7 @@ static void mtk_mdp_remove(struct platform_device *pdev) pm_runtime_disable(&pdev->dev); vb2_dma_contig_clear_max_seg_size(&pdev->dev); + platform_device_put(mdp->vpu_dev); mtk_mdp_unregister_m2m_device(mdp); v4l2_device_unregister(&mdp->v4l2_dev); -- 2.25.1

1 month, 3 weeks

1
0
0 0

[PATCH v3] media: mtk-mdp: Fix error handling in probe function

by Haoxiang Li

Add mtk_mdp_unregister_m2m_device() on the error handling path to prevent resource leak. Add check for the return value of vpu_get_plat_device() to prevent null pointer dereference. And vpu_get_plat_device() increases the reference count of the returned platform device. Add platform_device_put() to prevent reference leak. Fixes: c8eb2d7e8202 ("[media] media: Add Mediatek MDP Driver") Cc: stable(a)vger.kernel.org Signed-off-by: Haoxiang Li <haoxiang_li2024(a)163.com> --- Changes in v3: - Modify the patch subject and description. - Patch v2 is a little bit verbose and trivial, so I changed the subject and moved the fixes of mtk_mdp_remove to a separate patch. Thanks, Nicolas! Changes in v2: - Add check for vpu_get_plat_device() - Add platform_device_put() in mtk_mdp_remove() - Add mtk_mdp_unregister_m2m_device() on the error handling path. - Modify the patch title and description. I think you are right. Thanks, CJ! --- .../media/platform/mediatek/mdp/mtk_mdp_core.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/drivers/media/platform/mediatek/mdp/mtk_mdp_core.c b/drivers/media/platform/mediatek/mdp/mtk_mdp_core.c index 80fdc6ff57e0..f78fa30f1864 100644 --- a/drivers/media/platform/mediatek/mdp/mtk_mdp_core.c +++ b/drivers/media/platform/mediatek/mdp/mtk_mdp_core.c @@ -194,11 +194,17 @@ static int mtk_mdp_probe(struct platform_device *pdev) } mdp->vpu_dev = vpu_get_plat_device(pdev); + if (!mdp->vpu_dev) { + dev_err(&pdev->dev, "Failed to get vpu device\n"); + ret = -ENODEV; + goto err_vpu_get_dev; + } + ret = vpu_wdt_reg_handler(mdp->vpu_dev, mtk_mdp_reset_handler, mdp, VPU_RST_MDP); if (ret) { dev_err(&pdev->dev, "Failed to register reset handler\n"); - goto err_m2m_register; + goto err_reg_handler; } platform_set_drvdata(pdev, mdp); @@ -206,7 +212,7 @@ static int mtk_mdp_probe(struct platform_device *pdev) ret = vb2_dma_contig_set_max_seg_size(&pdev->dev, DMA_BIT_MASK(32)); if (ret) { dev_err(&pdev->dev, "Failed to set vb2 dma mag seg size\n"); - goto err_m2m_register; + goto err_reg_handler; } pm_runtime_enable(dev); @@ -214,6 +220,12 @@ static int mtk_mdp_probe(struct platform_device *pdev) return 0; +err_reg_handler: + platform_device_put(mdp->vpu_dev); + +err_vpu_get_dev: + mtk_mdp_unregister_m2m_device(mdp); + err_m2m_register: v4l2_device_unregister(&mdp->v4l2_dev); -- 2.25.1

1 month, 3 weeks

1
0
0 0

[PATCH 0/1] Backport request: Fix reading issue on mcp2221

by Romain Sioen

Hi maintainers, Please consider backporting the following patches to the stable trees. These patches fix a significant reading issue with mcp2221 on i2c eeprom. This request is following the one I did previously to fix hid-mcp2221 in previous LTS versions. I have confirmed that the patches applie cleanly and build successfully against v6.12, v6.6, v6.1, v5.15 and v5.10 stable branches. Thanks, Romain Arnaud Lecomte (1): hid: fix I2C read buffer overflow in raw_event() for mcp2221 drivers/hid/hid-mcp2221.c | 4 ++++ 1 file changed, 4 insertions(+) -- 2.48.1

1 month, 3 weeks

5
6
0 0

+ mm-damon-sysfs-dealloc-commit-test-ctx-always.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: mm/damon/sysfs: dealloc commit test ctx always has been added to the -mm mm-hotfixes-unstable branch. Its filename is mm-damon-sysfs-dealloc-commit-test-ctx-always.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche… This patch will later appear in the mm-hotfixes-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: SeongJae Park <sj(a)kernel.org> Subject: mm/damon/sysfs: dealloc commit test ctx always Date: Fri, 3 Oct 2025 13:14:55 -0700 The damon_ctx for testing online DAMON parameters commit inputs is deallocated only when the test fails. This means memory is leaked for every successful online DAMON parameters commit. Fix the leak by always deallocating it. Link: https://lkml.kernel.org/r/20251003201455.41448-3-sj@kernel.org Fixes: 4c9ea539ad59 ("mm/damon/sysfs: validate user inputs from damon_sysfs_commit_input()") Signed-off-by: SeongJae Park <sj(a)kernel.org> Cc: <stable(a)vger.kernel.org> [6.15+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/damon/sysfs.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) --- a/mm/damon/sysfs.c~mm-damon-sysfs-dealloc-commit-test-ctx-always +++ a/mm/damon/sysfs.c @@ -1476,12 +1476,11 @@ static int damon_sysfs_commit_input(void if (!test_ctx) return -ENOMEM; err = damon_commit_ctx(test_ctx, param_ctx); - if (err) { - damon_destroy_ctx(test_ctx); + if (err) goto out; - } err = damon_commit_ctx(kdamond->damon_ctx, param_ctx); out: + damon_destroy_ctx(test_ctx); damon_destroy_ctx(param_ctx); return err; } _ Patches currently in -mm which might be from sj(a)kernel.org are mm-damon-sysfs-catch-commit-test-ctx-alloc-failure.patch mm-damon-sysfs-dealloc-commit-test-ctx-always.patch mm-zswap-remove-unnecessary-dlen-writes-for-incompressible-pages.patch mm-zswap-fix-typos-s-zwap-zswap.patch mm-zswap-s-red-black-tree-xarray.patch docs-admin-guide-mm-zswap-s-red-black-tree-xarray.patch

1 month, 3 weeks

1
0
0 0

+ mm-damon-sysfs-catch-commit-test-ctx-alloc-failure.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: mm/damon/sysfs: catch commit test ctx alloc failure has been added to the -mm mm-hotfixes-unstable branch. Its filename is mm-damon-sysfs-catch-commit-test-ctx-alloc-failure.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche… This patch will later appear in the mm-hotfixes-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: SeongJae Park <sj(a)kernel.org> Subject: mm/damon/sysfs: catch commit test ctx alloc failure Date: Fri, 3 Oct 2025 13:14:54 -0700 The damon_ctx for testing online DAMON parameters commit inputs is used without its allocation failure check. This could result in an invalid memory access. Fix it by directly returning an error when the allocation failed. Link: https://lkml.kernel.org/r/20251003201455.41448-2-sj@kernel.org Fixes: 4c9ea539ad59 ("mm/damon/sysfs: validate user inputs from damon_sysfs_commit_input()") Signed-off-by: SeongJae Park <sj(a)kernel.org> Cc: <stable(a)vger.kernel.org> [6.15+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/damon/sysfs.c | 2 ++ 1 file changed, 2 insertions(+) --- a/mm/damon/sysfs.c~mm-damon-sysfs-catch-commit-test-ctx-alloc-failure +++ a/mm/damon/sysfs.c @@ -1473,6 +1473,8 @@ static int damon_sysfs_commit_input(void if (IS_ERR(param_ctx)) return PTR_ERR(param_ctx); test_ctx = damon_new_ctx(); + if (!test_ctx) + return -ENOMEM; err = damon_commit_ctx(test_ctx, param_ctx); if (err) { damon_destroy_ctx(test_ctx); _ Patches currently in -mm which might be from sj(a)kernel.org are mm-damon-sysfs-catch-commit-test-ctx-alloc-failure.patch mm-damon-sysfs-dealloc-commit-test-ctx-always.patch mm-zswap-remove-unnecessary-dlen-writes-for-incompressible-pages.patch mm-zswap-fix-typos-s-zwap-zswap.patch mm-zswap-s-red-black-tree-xarray.patch docs-admin-guide-mm-zswap-s-red-black-tree-xarray.patch

1 month, 3 weeks

1
0
0 0

+ mm-swap-do-not-perform-synchronous-discard-during-allocation.patch added to mm-new branch

by Andrew Morton

The patch titled Subject: mm, swap: do not perform synchronous discard during allocation has been added to the -mm mm-new branch. Its filename is mm-swap-do-not-perform-synchronous-discard-during-allocation.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche… This patch will later appear in the mm-new branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Note, mm-new is a provisional staging ground for work-in-progress patches, and acceptance into mm-new is a notification for others take notice and to finish up reviews. Please do not hesitate to respond to review feedback and post updated versions to replace or incrementally fixup patches in mm-new. Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: Kairui Song <kasong(a)tencent.com> Subject: mm, swap: do not perform synchronous discard during allocation Date: Tue, 07 Oct 2025 04:02:33 +0800 Patch series "mm, swap: misc cleanup and bugfix". A few cleanups and a bugfix that are either suitable after the swap table phase I or found during code review. Patch 1 is a bugfix and needs to be included in the stable branch, the rest have no behavior change. This patch (of 4): Since commit 1b7e90020eb77 ("mm, swap: use percpu cluster as allocation fast path"), swap allocation is protected by a local lock, which means we can't do any sleeping calls during allocation. However, the discard routine is not taken well care of. When the swap allocator failed to find any usable cluster, it would look at the pending discard cluster and try to issue some blocking discards. It may not necessarily sleep, but the cond_resched at the bio layer indicates this is wrong when combined with a local lock. And the bio GFP flag used for discard bio is also wrong (not atomic). It's arguable whether this synchronous discard is helpful at all. In most cases, the async discard is good enough. And the swap allocator is doing very differently at organizing the clusters since the recent change, so it is very rare to see discard clusters piling up. So far, no issues have been observed or reported with typical SSD setups under months of high pressure. This issue was found during my code review. But by hacking the kernel a bit: adding a mdelay(100) in the async discard path, this issue will be observable with WARNING triggered by the wrong GFP and cond_resched in the bio layer. So let's fix this issue in a safe way: remove the synchronous discard in the swap allocation path. And when order 0 is failing with all cluster list drained on all swap devices, try to do a discard following the swap device priority list. If any discards released some cluster, try the allocation again. This way, we can still avoid OOM due to swap failure if the hardware is very slow and memory pressure is extremely high. Link: https://lkml.kernel.org/r/20251007-swap-clean-after-swap-table-p1-v1-0-7486… Link: https://lkml.kernel.org/r/20251007-swap-clean-after-swap-table-p1-v1-1-7486… Fixes: 1b7e90020eb77 ("mm, swap: use percpu cluster as allocation fast path") Signed-off-by: Kairui Song <kasong(a)tencent.com> Cc: Baolin Wang <baolin.wang(a)linux.alibaba.com> Cc: Baoquan He <bhe(a)redhat.com> Cc: Barry Song <baohua(a)kernel.org> Cc: Chris Li <chrisl(a)kernel.org> Cc: David Hildenbrand <david(a)redhat.com> Cc: "Huang, Ying" <ying.huang(a)linux.alibaba.com> Cc: Kemeng Shi <shikemeng(a)huaweicloud.com> Cc: Matthew Wilcox (Oracle) <willy(a)infradead.org> Cc: Nhat Pham <nphamcs(a)gmail.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/swapfile.c | 40 +++++++++++++++++++++++++++++++++------- 1 file changed, 33 insertions(+), 7 deletions(-) --- a/mm/swapfile.c~mm-swap-do-not-perform-synchronous-discard-during-allocation +++ a/mm/swapfile.c @@ -1101,13 +1101,6 @@ new_cluster: goto done; } - /* - * We don't have free cluster but have some clusters in discarding, - * do discard now and reclaim them. - */ - if ((si->flags & SWP_PAGE_DISCARD) && swap_do_scheduled_discard(si)) - goto new_cluster; - if (order) goto done; @@ -1394,6 +1387,33 @@ start_over: return false; } +/* + * Discard pending clusters in a synchronized way when under high pressure. + * Return: true if any cluster is discarded. + */ +static bool swap_sync_discard(void) +{ + bool ret = false; + int nid = numa_node_id(); + struct swap_info_struct *si, *next; + + spin_lock(&swap_avail_lock); + plist_for_each_entry_safe(si, next, &swap_avail_heads[nid], avail_lists[nid]) { + spin_unlock(&swap_avail_lock); + if (get_swap_device_info(si)) { + if (si->flags & SWP_PAGE_DISCARD) + ret = swap_do_scheduled_discard(si); + put_swap_device(si); + } + if (ret) + break; + spin_lock(&swap_avail_lock); + } + spin_unlock(&swap_avail_lock); + + return ret; +} + /** * folio_alloc_swap - allocate swap space for a folio * @folio: folio we want to move to swap @@ -1432,11 +1452,17 @@ int folio_alloc_swap(struct folio *folio } } +again: local_lock(&percpu_swap_cluster.lock); if (!swap_alloc_fast(&entry, order)) swap_alloc_slow(&entry, order); local_unlock(&percpu_swap_cluster.lock); + if (unlikely(!order && !entry.val)) { + if (swap_sync_discard()) + goto again; + } + /* Need to call this even if allocation failed, for MEMCG_SWAP_FAIL. */ if (mem_cgroup_try_charge_swap(folio, entry)) goto out_free; _ Patches currently in -mm which might be from kasong(a)tencent.com are mm-swap-do-not-perform-synchronous-discard-during-allocation.patch mm-swap-rename-helper-for-setup-bad-slots.patch mm-swap-cleanup-swap-entry-allocation-parameter.patch mm-migrate-swap-drop-usage-of-folio_index.patch

1 month, 3 weeks

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror