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

[PATCH v3 mm-hotfixes 2/5] mm: introduce and use {pgd,p4d}_populate_kernel()

by Harry Yoo

Introduce and use {pgd,p4d}_populate_kernel() in core MM code when populating PGD and P4D entries for the kernel address space. These helpers ensure proper synchronization of page tables when updating the kernel portion of top-level page tables. Until now, the kernel has relied on each architecture to handle synchronization of top-level page tables in an ad-hoc manner. For example, see commit 9b861528a801 ("x86-64, mem: Update all PGDs for direct mapping and vmemmap mapping changes"). However, this approach has proven fragile for following reasons: 1) It is easy to forget to perform the necessary page table synchronization when introducing new changes. For instance, commit 4917f55b4ef9 ("mm/sparse-vmemmap: improve memory savings for compound devmaps") overlooked the need to synchronize page tables for the vmemmap area. 2) It is also easy to overlook that the vmemmap and direct mapping areas must not be accessed before explicit page table synchronization. For example, commit 8d400913c231 ("x86/vmemmap: handle unpopulated sub-pmd ranges")) caused crashes by accessing the vmemmap area before calling sync_global_pgds(). To address this, as suggested by Dave Hansen, introduce _kernel() variants of the page table population helpers, which invoke architecture-specific hooks to properly synchronize page tables. They reuse existing infrastructure for vmalloc and ioremap. Synchronization requirements are determined by ARCH_PAGE_TABLE_SYNC_MASK, and the actual synchronization is performed by arch_sync_kernel_mappings(). This change currently targets only x86_64, so only PGD and P4D level helpers are introduced. In theory, PUD and PMD level helpers can be added later if needed by other architectures. Currently this is a no-op, since no architecture sets PGTBL_{PGD,P4D}_MODIFIED in ARCH_PAGE_TABLE_SYNC_MASK. Cc: stable(a)vger.kernel.org Suggested-by: Dave Hansen <dave.hansen(a)linux.intel.com> Signed-off-by: Harry Yoo <harry.yoo(a)oracle.com> --- include/asm-generic/pgalloc.h | 16 ++++++++++++++++ include/linux/pgtable.h | 4 ++-- mm/kasan/init.c | 10 +++++----- mm/percpu.c | 4 ++-- mm/sparse-vmemmap.c | 4 ++-- 5 files changed, 27 insertions(+), 11 deletions(-) diff --git a/include/asm-generic/pgalloc.h b/include/asm-generic/pgalloc.h index 3c8ec3bfea44..fc0ab8eed5a6 100644 --- a/include/asm-generic/pgalloc.h +++ b/include/asm-generic/pgalloc.h @@ -4,6 +4,8 @@ #ifdef CONFIG_MMU +#include <linux/pgtable.h> + #define GFP_PGTABLE_KERNEL (GFP_KERNEL | __GFP_ZERO) #define GFP_PGTABLE_USER (GFP_PGTABLE_KERNEL | __GFP_ACCOUNT) @@ -296,6 +298,20 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) } #endif +#define pgd_populate_kernel(addr, pgd, p4d) \ +do { \ + pgd_populate(&init_mm, pgd, p4d); \ + if (ARCH_PAGE_TABLE_SYNC_MASK & PGTBL_PGD_MODIFIED) \ + arch_sync_kernel_mappings(addr, addr); \ +} while (0) + +#define p4d_populate_kernel(addr, p4d, pud) \ +do { \ + p4d_populate(&init_mm, p4d, pud); \ + if (ARCH_PAGE_TABLE_SYNC_MASK & PGTBL_P4D_MODIFIED) \ + arch_sync_kernel_mappings(addr, addr); \ +} while (0) + #endif /* CONFIG_MMU */ #endif /* __ASM_GENERIC_PGALLOC_H */ diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index e564f338c758..2e24514ab6d0 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1332,8 +1332,8 @@ static inline void ptep_modify_prot_commit(struct vm_area_struct *vma, /* * Architectures can set this mask to a combination of PGTBL_P?D_MODIFIED values - * and let generic vmalloc and ioremap code know when arch_sync_kernel_mappings() - * needs to be called. + * and let generic vmalloc, ioremap and page table update code know when + * arch_sync_kernel_mappings() needs to be called. */ #ifndef ARCH_PAGE_TABLE_SYNC_MASK #define ARCH_PAGE_TABLE_SYNC_MASK 0 diff --git a/mm/kasan/init.c b/mm/kasan/init.c index ced6b29fcf76..43de820ee282 100644 --- a/mm/kasan/init.c +++ b/mm/kasan/init.c @@ -191,7 +191,7 @@ static int __ref zero_p4d_populate(pgd_t *pgd, unsigned long addr, pud_t *pud; pmd_t *pmd; - p4d_populate(&init_mm, p4d, + p4d_populate_kernel(addr, p4d, lm_alias(kasan_early_shadow_pud)); pud = pud_offset(p4d, addr); pud_populate(&init_mm, pud, @@ -212,7 +212,7 @@ static int __ref zero_p4d_populate(pgd_t *pgd, unsigned long addr, } else { p = early_alloc(PAGE_SIZE, NUMA_NO_NODE); pud_init(p); - p4d_populate(&init_mm, p4d, p); + p4d_populate_kernel(addr, p4d, p); } } zero_pud_populate(p4d, addr, next); @@ -251,10 +251,10 @@ int __ref kasan_populate_early_shadow(const void *shadow_start, * puds,pmds, so pgd_populate(), pud_populate() * is noops. */ - pgd_populate(&init_mm, pgd, + pgd_populate_kernel(addr, pgd, lm_alias(kasan_early_shadow_p4d)); p4d = p4d_offset(pgd, addr); - p4d_populate(&init_mm, p4d, + p4d_populate_kernel(addr, p4d, lm_alias(kasan_early_shadow_pud)); pud = pud_offset(p4d, addr); pud_populate(&init_mm, pud, @@ -273,7 +273,7 @@ int __ref kasan_populate_early_shadow(const void *shadow_start, if (!p) return -ENOMEM; } else { - pgd_populate(&init_mm, pgd, + pgd_populate_kernel(addr, pgd, early_alloc(PAGE_SIZE, NUMA_NO_NODE)); } } diff --git a/mm/percpu.c b/mm/percpu.c index b35494c8ede2..1615dc3b3af5 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -3134,13 +3134,13 @@ void __init __weak pcpu_populate_pte(unsigned long addr) if (pgd_none(*pgd)) { p4d = memblock_alloc_or_panic(P4D_TABLE_SIZE, P4D_TABLE_SIZE); - pgd_populate(&init_mm, pgd, p4d); + pgd_populate_kernel(addr, pgd, p4d); } p4d = p4d_offset(pgd, addr); if (p4d_none(*p4d)) { pud = memblock_alloc_or_panic(PUD_TABLE_SIZE, PUD_TABLE_SIZE); - p4d_populate(&init_mm, p4d, pud); + p4d_populate_kernel(addr, p4d, pud); } pud = pud_offset(p4d, addr); diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index fd2ab5118e13..e275310ac708 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -229,7 +229,7 @@ p4d_t * __meminit vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node) if (!p) return NULL; pud_init(p); - p4d_populate(&init_mm, p4d, p); + p4d_populate_kernel(addr, p4d, p); } return p4d; } @@ -241,7 +241,7 @@ pgd_t * __meminit vmemmap_pgd_populate(unsigned long addr, int node) void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node); if (!p) return NULL; - pgd_populate(&init_mm, pgd, p); + pgd_populate_kernel(addr, pgd, p); } return pgd; } -- 2.43.0

3 months, 1 week

1
1
0 0

FAILED: patch "[PATCH] dpaa2-eth: Fix device reference count leak in MAC endpoint" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y git checkout FETCH_HEAD git cherry-pick -x ee9f3a81ab08dfe0538dbd1746f81fd4d5147fdc # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025072840-quickstep-spiny-0e80@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From ee9f3a81ab08dfe0538dbd1746f81fd4d5147fdc Mon Sep 17 00:00:00 2001 From: Ma Ke <make24(a)iscas.ac.cn> Date: Thu, 17 Jul 2025 10:23:08 +0800 Subject: [PATCH] dpaa2-eth: Fix device reference count leak in MAC endpoint handling The fsl_mc_get_endpoint() function uses device_find_child() for localization, which implicitly calls get_device() to increment the device's reference count before returning the pointer. However, the caller dpaa2_eth_connect_mac() fails to properly release this reference in multiple scenarios. We should call put_device() to decrement reference count properly. As comment of device_find_child() says, 'NOTE: you will need to drop the reference with put_device() after use'. Found by code review. Cc: stable(a)vger.kernel.org Fixes: 719479230893 ("dpaa2-eth: add MAC/PHY support through phylink") Signed-off-by: Ma Ke <make24(a)iscas.ac.cn> Tested-by: Ioana Ciornei <ioana.ciornei(a)nxp.com> Reviewed-by: Ioana Ciornei <ioana.ciornei(a)nxp.com> Reviewed-by: Simon Horman <horms(a)kernel.org> Link: https://patch.msgid.link/20250717022309.3339976-2-make24@iscas.ac.cn Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index b82f121cadad..0f4efd505332 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -4666,12 +4666,19 @@ static int dpaa2_eth_connect_mac(struct dpaa2_eth_priv *priv) return PTR_ERR(dpmac_dev); } - if (IS_ERR(dpmac_dev) || dpmac_dev->dev.type != &fsl_mc_bus_dpmac_type) + if (IS_ERR(dpmac_dev)) return 0; + if (dpmac_dev->dev.type != &fsl_mc_bus_dpmac_type) { + err = 0; + goto out_put_device; + } + mac = kzalloc(sizeof(struct dpaa2_mac), GFP_KERNEL); - if (!mac) - return -ENOMEM; + if (!mac) { + err = -ENOMEM; + goto out_put_device; + } mac->mc_dev = dpmac_dev; mac->mc_io = priv->mc_io; @@ -4705,6 +4712,8 @@ static int dpaa2_eth_connect_mac(struct dpaa2_eth_priv *priv) dpaa2_mac_close(mac); err_free_mac: kfree(mac); +out_put_device: + put_device(&dpmac_dev->dev); return err; }

3 months, 1 week

2
4
0 0

[PATCH v2 1/1] iommu/sva: Invalidate KVA range on kernel TLB flush

by Lu Baolu

The vmalloc() and vfree() functions manage virtually contiguous, but not necessarily physically contiguous, kernel memory regions. When vfree() unmaps such a region, it tears down the associated kernel page table entries and frees the physical pages. In the IOMMU Shared Virtual Addressing (SVA) context, the IOMMU hardware shares and walks the CPU's page tables. Architectures like x86 share static kernel address mappings across all user page tables, allowing the IOMMU to access the kernel portion of these tables. Modern IOMMUs often cache page table entries to optimize walk performance, even for intermediate page table levels. If kernel page table mappings are changed (e.g., by vfree()), but the IOMMU's internal caches retain stale entries, Use-After-Free (UAF) vulnerability condition arises. If these freed page table pages are reallocated for a different purpose, potentially by an attacker, the IOMMU could misinterpret the new data as valid page table entries. This allows the IOMMU to walk into attacker-controlled memory, leading to arbitrary physical memory DMA access or privilege escalation. To mitigate this, introduce a new iommu interface to flush IOMMU caches and fence pending page table walks when kernel page mappings are updated. This interface should be invoked from architecture-specific code that manages combined user and kernel page tables. Fixes: 26b25a2b98e4 ("iommu: Bind process address spaces to devices") Cc: stable(a)vger.kernel.org Reported-by: Jann Horn <jannh(a)google.com> Co-developed-by: Jason Gunthorpe <jgg(a)nvidia.com> Signed-off-by: Jason Gunthorpe <jgg(a)nvidia.com> Signed-off-by: Lu Baolu <baolu.lu(a)linux.intel.com> Reviewed-by: Jason Gunthorpe <jgg(a)nvidia.com> Reviewed-by: Vasant Hegde <vasant.hegde(a)amd.com> Tested-by: Yi Lai <yi1.lai(a)intel.com> --- arch/x86/mm/tlb.c | 2 ++ drivers/iommu/iommu-sva.c | 34 +++++++++++++++++++++++++++++++++- include/linux/iommu.h | 4 ++++ 3 files changed, 39 insertions(+), 1 deletion(-) Change log: v2: - Remove EXPORT_SYMBOL_GPL(iommu_sva_invalidate_kva_range); - Replace the mutex with a spinlock to make the interface usable in the critical regions. v1: https://lore.kernel.org/linux-iommu/20250704133056.4023816-1-baolu.lu@linux… diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 39f80111e6f1..a41499dfdc3f 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -12,6 +12,7 @@ #include <linux/task_work.h> #include <linux/mmu_notifier.h> #include <linux/mmu_context.h> +#include <linux/iommu.h> #include <asm/tlbflush.h> #include <asm/mmu_context.h> @@ -1540,6 +1541,7 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end) kernel_tlb_flush_range(info); put_flush_tlb_info(); + iommu_sva_invalidate_kva_range(start, end); } /* diff --git a/drivers/iommu/iommu-sva.c b/drivers/iommu/iommu-sva.c index 1a51cfd82808..fd76aefa5a88 100644 --- a/drivers/iommu/iommu-sva.c +++ b/drivers/iommu/iommu-sva.c @@ -10,6 +10,9 @@ #include "iommu-priv.h" static DEFINE_MUTEX(iommu_sva_lock); +static DEFINE_STATIC_KEY_FALSE(iommu_sva_present); +static LIST_HEAD(iommu_sva_mms); +static DEFINE_SPINLOCK(iommu_mms_lock); static struct iommu_domain *iommu_sva_domain_alloc(struct device *dev, struct mm_struct *mm); @@ -42,6 +45,7 @@ static struct iommu_mm_data *iommu_alloc_mm_data(struct mm_struct *mm, struct de return ERR_PTR(-ENOSPC); } iommu_mm->pasid = pasid; + iommu_mm->mm = mm; INIT_LIST_HEAD(&iommu_mm->sva_domains); /* * Make sure the write to mm->iommu_mm is not reordered in front of @@ -132,8 +136,15 @@ struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm if (ret) goto out_free_domain; domain->users = 1; - list_add(&domain->next, &mm->iommu_mm->sva_domains); + if (list_empty(&iommu_mm->sva_domains)) { + scoped_guard(spinlock_irqsave, &iommu_mms_lock) { + if (list_empty(&iommu_sva_mms)) + static_branch_enable(&iommu_sva_present); + list_add(&iommu_mm->mm_list_elm, &iommu_sva_mms); + } + } + list_add(&domain->next, &iommu_mm->sva_domains); out: refcount_set(&handle->users, 1); mutex_unlock(&iommu_sva_lock); @@ -175,6 +186,15 @@ void iommu_sva_unbind_device(struct iommu_sva *handle) list_del(&domain->next); iommu_domain_free(domain); } + + if (list_empty(&iommu_mm->sva_domains)) { + scoped_guard(spinlock_irqsave, &iommu_mms_lock) { + list_del(&iommu_mm->mm_list_elm); + if (list_empty(&iommu_sva_mms)) + static_branch_disable(&iommu_sva_present); + } + } + mutex_unlock(&iommu_sva_lock); kfree(handle); } @@ -312,3 +332,15 @@ static struct iommu_domain *iommu_sva_domain_alloc(struct device *dev, return domain; } + +void iommu_sva_invalidate_kva_range(unsigned long start, unsigned long end) +{ + struct iommu_mm_data *iommu_mm; + + if (!static_branch_unlikely(&iommu_sva_present)) + return; + + guard(spinlock_irqsave)(&iommu_mms_lock); + list_for_each_entry(iommu_mm, &iommu_sva_mms, mm_list_elm) + mmu_notifier_arch_invalidate_secondary_tlbs(iommu_mm->mm, start, end); +} diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 156732807994..31330c12b8ee 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -1090,7 +1090,9 @@ struct iommu_sva { struct iommu_mm_data { u32 pasid; + struct mm_struct *mm; struct list_head sva_domains; + struct list_head mm_list_elm; }; int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode); @@ -1571,6 +1573,7 @@ struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm); void iommu_sva_unbind_device(struct iommu_sva *handle); u32 iommu_sva_get_pasid(struct iommu_sva *handle); +void iommu_sva_invalidate_kva_range(unsigned long start, unsigned long end); #else static inline struct iommu_sva * iommu_sva_bind_device(struct device *dev, struct mm_struct *mm) @@ -1595,6 +1598,7 @@ static inline u32 mm_get_enqcmd_pasid(struct mm_struct *mm) } static inline void mm_pasid_drop(struct mm_struct *mm) {} +static inline void iommu_sva_invalidate_kva_range(unsigned long start, unsigned long end) {} #endif /* CONFIG_IOMMU_SVA */ #ifdef CONFIG_IOMMU_IOPF -- 2.43.0

3 months, 1 week

10
37
0 0

[PATCH v4 0/2] Samsung Exynos 7870 DECON driver support

by Kaustabh Chakraborty

This patch series aims at adding support for Exynos7870's DECON in the Exynos7 DECON driver. It introduces a driver data struct so that support for DECON on other SoCs can be added to it in the future. It also fixes a few bugs in the driver, such as functions receiving bad pointers. Tested on Samsung Galaxy J7 Prime (samsung-on7xelte), Samsung Galaxy A2 Core (samsung-a2corelte), and Samsung Galaxy J6 (samsung-j6lte). Signed-off-by: Kaustabh Chakraborty <kauschluss(a)disroot.org> --- Changes in v4: - Drop applied patch [v2 3/3]. - Correct documentation of port dt property. - Add documentation of memory-region. - Remove redundant ctx->suspended completely. - Link to v3: https://lore.kernel.org/r/20250627-exynosdrm-decon-v3-0-5b456f88cfea@disroo… Changes in v3: - Add a new commit documenting iommus and ports dt properties. - Link to v2: https://lore.kernel.org/r/20250612-exynosdrm-decon-v2-0-d6c1d21c8057@disroo… Changes in v2: - Add a new commit to prevent an occasional panic under circumstances. - Rewrite and redo [v1 2/6] to be a more sensible commit. - Link to v1: https://lore.kernel.org/r/20240919-exynosdrm-decon-v1-0-6c5861c1cb04@disroo… --- Kaustabh Chakraborty (2): dt-bindings: display: samsung,exynos7-decon: document iommus, memory-region, and ports drm/exynos: exynos7_drm_decon: remove ctx->suspended .../display/samsung/samsung,exynos7-decon.yaml | 21 +++++++++++++ drivers/gpu/drm/exynos/exynos7_drm_decon.c | 36 ---------------------- 2 files changed, 21 insertions(+), 36 deletions(-) --- base-commit: 26ffb3d6f02cd0935fb9fa3db897767beee1cb2a change-id: 20240917-exynosdrm-decon-4c228dd1d2bf Best regards, -- Kaustabh Chakraborty <kauschluss(a)disroot.org>

3 months, 1 week

2
2
0 0

+ mm-shmem-swap-improve-cached-mthp-handling-and-fix-potential-hang.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: mm/shmem, swap: improve cached mTHP handling and fix potential hang has been added to the -mm mm-hotfixes-unstable branch. Its filename is mm-shmem-swap-improve-cached-mthp-handling-and-fix-potential-hang.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: Kairui Song <kasong(a)tencent.com> Subject: mm/shmem, swap: improve cached mTHP handling and fix potential hang Date: Mon, 28 Jul 2025 15:52:59 +0800 The current swap-in code assumes that, when a swap entry in shmem mapping is order 0, its cached folios (if present) must be order 0 too, which turns out not always correct. The problem is shmem_split_large_entry is called before verifying the folio will eventually be swapped in, one possible race is: CPU1 CPU2 shmem_swapin_folio /* swap in of order > 0 swap entry S1 */ folio = swap_cache_get_folio /* folio = NULL */ order = xa_get_order /* order > 0 */ folio = shmem_swap_alloc_folio /* mTHP alloc failure, folio = NULL */ <... Interrupted ...> shmem_swapin_folio /* S1 is swapped in */ shmem_writeout /* S1 is swapped out, folio cached */ shmem_split_large_entry(..., S1) /* S1 is split, but the folio covering it has order > 0 now */ Now any following swapin of S1 will hang: `xa_get_order` returns 0, and folio lookup will return a folio with order > 0. The `xa_get_order(&mapping->i_pages, index) != folio_order(folio)` will always return false causing swap-in to return -EEXIST. And this looks fragile. So fix this up by allowing seeing a larger folio in swap cache, and check the whole shmem mapping range covered by the swapin have the right swap value upon inserting the folio. And drop the redundant tree walks before the insertion. This will actually improve performance, as it avoids two redundant Xarray tree walks in the hot path, and the only side effect is that in the failure path, shmem may redundantly reallocate a few folios causing temporary slight memory pressure. And worth noting, it may seems the order and value check before inserting might help reducing the lock contention, which is not true. The swap cache layer ensures raced swapin will either see a swap cache folio or failed to do a swapin (we have SWAP_HAS_CACHE bit even if swap cache is bypassed), so holding the folio lock and checking the folio flag is already good enough for avoiding the lock contention. The chance that a folio passes the swap entry value check but the shmem mapping slot has changed should be very low. Link: https://lkml.kernel.org/r/20250728075306.12704-1-ryncsn@gmail.com Link: https://lkml.kernel.org/r/20250728075306.12704-2-ryncsn@gmail.com Fixes: 809bc86517cc ("mm: shmem: support large folio swap out") Signed-off-by: Kairui Song <kasong(a)tencent.com> Reviewed-by: Kemeng Shi <shikemeng(a)huaweicloud.com> Reviewed-by: Baolin Wang <baolin.wang(a)linux.alibaba.com> Tested-by: 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: Hugh Dickins <hughd(a)google.com> Cc: Matthew Wilcox (Oracle) <willy(a)infradead.org> Cc: Nhat Pham <nphamcs(a)gmail.com> Cc: Dev Jain <dev.jain(a)arm.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/shmem.c | 39 ++++++++++++++++++++++++++++++--------- 1 file changed, 30 insertions(+), 9 deletions(-) --- a/mm/shmem.c~mm-shmem-swap-improve-cached-mthp-handling-and-fix-potential-hang +++ a/mm/shmem.c @@ -884,7 +884,9 @@ static int shmem_add_to_page_cache(struc pgoff_t index, void *expected, gfp_t gfp) { XA_STATE_ORDER(xas, &mapping->i_pages, index, folio_order(folio)); - long nr = folio_nr_pages(folio); + unsigned long nr = folio_nr_pages(folio); + swp_entry_t iter, swap; + void *entry; VM_BUG_ON_FOLIO(index != round_down(index, nr), folio); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); @@ -896,14 +898,25 @@ static int shmem_add_to_page_cache(struc gfp &= GFP_RECLAIM_MASK; folio_throttle_swaprate(folio, gfp); + swap = radix_to_swp_entry(expected); do { + iter = swap; xas_lock_irq(&xas); - if (expected != xas_find_conflict(&xas)) { - xas_set_err(&xas, -EEXIST); - goto unlock; + xas_for_each_conflict(&xas, entry) { + /* + * The range must either be empty, or filled with + * expected swap entries. Shmem swap entries are never + * partially freed without split of both entry and + * folio, so there shouldn't be any holes. + */ + if (!expected || entry != swp_to_radix_entry(iter)) { + xas_set_err(&xas, -EEXIST); + goto unlock; + } + iter.val += 1 << xas_get_order(&xas); } - if (expected && xas_find_conflict(&xas)) { + if (expected && iter.val - nr != swap.val) { xas_set_err(&xas, -EEXIST); goto unlock; } @@ -2327,7 +2340,7 @@ static int shmem_swapin_folio(struct ino error = -ENOMEM; goto failed; } - } else if (order != folio_order(folio)) { + } else if (order > folio_order(folio)) { /* * Swap readahead may swap in order 0 folios into swapcache * asynchronously, while the shmem mapping can still stores @@ -2352,15 +2365,23 @@ static int shmem_swapin_folio(struct ino swap = swp_entry(swp_type(swap), swp_offset(swap) + offset); } + } else if (order < folio_order(folio)) { + swap.val = round_down(swap.val, 1 << folio_order(folio)); + index = round_down(index, 1 << folio_order(folio)); } alloced: - /* We have to do this with folio locked to prevent races */ + /* + * We have to do this with the folio locked to prevent races. + * The shmem_confirm_swap below only checks if the first swap + * entry matches the folio, that's enough to ensure the folio + * is not used outside of shmem, as shmem swap entries + * and swap cache folios are never partially freed. + */ folio_lock(folio); if ((!skip_swapcache && !folio_test_swapcache(folio)) || - folio->swap.val != swap.val || !shmem_confirm_swap(mapping, index, swap) || - xa_get_order(&mapping->i_pages, index) != folio_order(folio)) { + folio->swap.val != swap.val) { error = -EEXIST; goto unlock; } _ Patches currently in -mm which might be from kasong(a)tencent.com are mm-shmem-swap-improve-cached-mthp-handling-and-fix-potential-hang.patch mm-shmem-swap-avoid-redundant-xarray-lookup-during-swapin.patch mm-shmem-swap-tidy-up-thp-swapin-checks.patch mm-shmem-swap-tidy-up-swap-entry-splitting.patch mm-shmem-swap-never-use-swap-cache-and-readahead-for-swp_synchronous_io.patch mm-shmem-swap-simplify-swapin-path-and-result-handling.patch mm-shmem-swap-rework-swap-entry-and-index-calculation-for-large-swapin.patch mm-shmem-swap-fix-major-fault-counting.patch

3 months, 1 week

1
0
0 0

+ mm-fix-a-uaf-when-vma-mm-is-freed-after-vma-vm_refcnt-got-dropped.patch added to mm-unstable branch

by Andrew Morton

The patch titled Subject: mm: fix a UAF when vma->mm is freed after vma->vm_refcnt got dropped has been added to the -mm mm-unstable branch. Its filename is mm-fix-a-uaf-when-vma-mm-is-freed-after-vma-vm_refcnt-got-dropped.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-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: Suren Baghdasaryan <surenb(a)google.com> Subject: mm: fix a UAF when vma->mm is freed after vma->vm_refcnt got dropped Date: Mon, 28 Jul 2025 10:53:55 -0700 By inducing delays in the right places, Jann Horn created a reproducer for a hard to hit UAF issue that became possible after VMAs were allowed to be recycled by adding SLAB_TYPESAFE_BY_RCU to their cache. Race description is borrowed from Jann's discovery report: lock_vma_under_rcu() looks up a VMA locklessly with mas_walk() under rcu_read_lock(). At that point, the VMA may be concurrently freed, and it can be recycled by another process. vma_start_read() then increments the vma->vm_refcnt (if it is in an acceptable range), and if this succeeds, vma_start_read() can return a recycled VMA. In this scenario where the VMA has been recycled, lock_vma_under_rcu() will then detect the mismatching ->vm_mm pointer and drop the VMA through vma_end_read(), which calls vma_refcount_put(). vma_refcount_put() drops the refcount and then calls rcuwait_wake_up() using a copy of vma->vm_mm. This is wrong: It implicitly assumes that the caller is keeping the VMA's mm alive, but in this scenario the caller has no relation to the VMA's mm, so the rcuwait_wake_up() can cause UAF. The diagram depicting the race: T1 T2 T3 == == == lock_vma_under_rcu mas_walk <VMA gets removed from mm> mmap <the same VMA is reallocated> vma_start_read __refcount_inc_not_zero_limited_acquire munmap __vma_enter_locked refcount_add_not_zero vma_end_read vma_refcount_put __refcount_dec_and_test rcuwait_wait_event <finish operation> rcuwait_wake_up [UAF] Note that rcuwait_wait_event() in T3 does not block because refcount was already dropped by T1. At this point T3 can exit and free the mm causing UAF in T1. To avoid this we move vma->vm_mm verification into vma_start_read() and grab vma->vm_mm to stabilize it before vma_refcount_put() operation. Link: https://lkml.kernel.org/r/20250728175355.2282375-1-surenb@google.com Fixes: 3104138517fc ("mm: make vma cache SLAB_TYPESAFE_BY_RCU") Signed-off-by: Suren Baghdasaryan <surenb(a)google.com> Reported-by: Jann Horn <jannh(a)google.com> Closes: https://lore.kernel.org/all/CAG48ez0-deFbVH=E3jbkWx=X3uVbd8nWeo6kbJPQ0KoUD+… Cc: Jann Horn <jannh(a)google.com> Cc: Liam Howlett <liam.howlett(a)oracle.com> Cc: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/mmap_lock.h | 23 +++++++++++++++++++++++ mm/mmap_lock.c | 10 +++------- 2 files changed, 26 insertions(+), 7 deletions(-) --- a/include/linux/mmap_lock.h~mm-fix-a-uaf-when-vma-mm-is-freed-after-vma-vm_refcnt-got-dropped +++ a/include/linux/mmap_lock.h @@ -12,6 +12,7 @@ extern int rcuwait_wake_up(struct rcuwai #include <linux/tracepoint-defs.h> #include <linux/types.h> #include <linux/cleanup.h> +#include <linux/sched/mm.h> #define MMAP_LOCK_INITIALIZER(name) \ .mmap_lock = __RWSEM_INITIALIZER((name).mmap_lock), @@ -183,6 +184,28 @@ static inline struct vm_area_struct *vma } rwsem_acquire_read(&vma->vmlock_dep_map, 0, 1, _RET_IP_); + + /* + * If vma got attached to another mm from under us, that mm is not + * stable and can be freed in the narrow window after vma->vm_refcnt + * is dropped and before rcuwait_wake_up(mm) is called. Grab it before + * releasing vma->vm_refcnt. + */ + if (unlikely(vma->vm_mm != mm)) { + /* Use a copy of vm_mm in case vma is freed after we drop vm_refcnt */ + struct mm_struct *other_mm = vma->vm_mm; + /* + * __mmdrop() is a heavy operation and we don't need RCU + * protection here. Release RCU lock during these operations. + */ + rcu_read_unlock(); + mmgrab(other_mm); + vma_refcount_put(vma); + mmdrop(other_mm); + rcu_read_lock(); + return NULL; + } + /* * Overflow of vm_lock_seq/mm_lock_seq might produce false locked result. * False unlocked result is impossible because we modify and check --- a/mm/mmap_lock.c~mm-fix-a-uaf-when-vma-mm-is-freed-after-vma-vm_refcnt-got-dropped +++ a/mm/mmap_lock.c @@ -164,8 +164,7 @@ retry: */ /* Check if the vma we locked is the right one. */ - if (unlikely(vma->vm_mm != mm || - address < vma->vm_start || address >= vma->vm_end)) + if (unlikely(address < vma->vm_start || address >= vma->vm_end)) goto inval_end_read; rcu_read_unlock(); @@ -236,11 +235,8 @@ retry: goto fallback; } - /* - * Verify the vma we locked belongs to the same address space and it's - * not behind of the last search position. - */ - if (unlikely(vma->vm_mm != mm || from_addr >= vma->vm_end)) + /* Verify the vma is not behind of the last search position. */ + if (unlikely(from_addr >= vma->vm_end)) goto fallback_unlock; /* _ Patches currently in -mm which might be from surenb(a)google.com are mm-fix-a-uaf-when-vma-mm-is-freed-after-vma-vm_refcnt-got-dropped.patch

3 months, 1 week

1
0
0 0

+ kasan-test-fix-protection-against-compiler-elision.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: kasan/test: fix protection against compiler elision has been added to the -mm mm-hotfixes-unstable branch. Its filename is kasan-test-fix-protection-against-compiler-elision.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: Jann Horn <jannh(a)google.com> Subject: kasan/test: fix protection against compiler elision Date: Mon, 28 Jul 2025 22:11:54 +0200 The kunit test is using assignments to "static volatile void *kasan_ptr_result" to prevent elision of memory loads, but that's not working: In this variable definition, the "volatile" applies to the "void", not to the pointer. To make "volatile" apply to the pointer as intended, it must follow after the "*". This makes the kasan_memchr test pass again on my system. The kasan_strings test is still failing because all the definitions of load_unaligned_zeropad() are lacking explicit instrumentation hooks and ASAN does not instrument asm() memory operands. Link: https://lkml.kernel.org/r/20250728-kasan-kunit-fix-volatile-v1-1-e7157c9af8… Fixes: 5f1c8108e7ad ("mm:kasan: fix sparse warnings: Should it be static?") Signed-off-by: Jann Horn <jannh(a)google.com> Cc: Alexander Potapenko <glider(a)google.com> Cc: Andrey Konovalov <andreyknvl(a)gmail.com> Cc: Andrey Ryabinin <ryabinin.a.a(a)gmail.com> Cc: Dmitriy Vyukov <dvyukov(a)google.com> Cc: Jann Horn <jannh(a)google.com> Cc: Nihar Chaithanya <niharchaithanya(a)gmail.com> Cc: Vincenzo Frascino <vincenzo.frascino(a)arm.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/kasan/kasan_test_c.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) --- a/mm/kasan/kasan_test_c.c~kasan-test-fix-protection-against-compiler-elision +++ a/mm/kasan/kasan_test_c.c @@ -47,7 +47,7 @@ static struct { * Some tests use these global variables to store return values from function * calls that could otherwise be eliminated by the compiler as dead code. */ -static volatile void *kasan_ptr_result; +static void *volatile kasan_ptr_result; static volatile int kasan_int_result; /* Probe for console output: obtains test_status lines of interest. */ _ Patches currently in -mm which might be from jannh(a)google.com are kasan-test-fix-protection-against-compiler-elision.patch kasan-skip-quarantine-if-object-is-still-accessible-under-rcu.patch mm-rmap-add-anon_vma-lifetime-debug-check.patch

3 months, 1 week

1
0
0 0

[PATCH v3] gpio-mlxbf2: only get IRQ for device instances 0 and 3

by David Thompson

The gpio-mlxbf2 driver interfaces with four GPIO controllers, device instances 0-3. There are two IRQ resources shared between the four controllers, and they are found in the ACPI table for device instances 0 and 3. The driver should not attempt to get an IRQ resource when probing device instance 1 or 2, otherwise the following error is logged: mlxbf2_gpio MLNXBF22:01: error -ENXIO: IRQ index 0 not found Fixes: 2b725265cb08 ("gpio: mlxbf2: Introduce IRQ support") Cc: stable(a)vger.kernel.org Signed-off-by: David Thompson <davthompson(a)nvidia.com> Reviewed-by: Shravan Kumar Ramani <shravankr(a)nvidia.com> --- v3: added version history v2: added tag "Cc: stable(a)vger.kernel.org" drivers/gpio/gpio-mlxbf2.c | 56 ++++++++++++++++++++++++-------------- 1 file changed, 36 insertions(+), 20 deletions(-) diff --git a/drivers/gpio/gpio-mlxbf2.c b/drivers/gpio/gpio-mlxbf2.c index 6f3dda6b635f..fc56ac81e344 100644 --- a/drivers/gpio/gpio-mlxbf2.c +++ b/drivers/gpio/gpio-mlxbf2.c @@ -353,7 +353,9 @@ mlxbf2_gpio_probe(struct platform_device *pdev) struct gpio_chip *gc; unsigned int npins; const char *name; + char *colon_ptr; int ret, irq; + long num; name = dev_name(dev); @@ -397,26 +399,40 @@ mlxbf2_gpio_probe(struct platform_device *pdev) gc->ngpio = npins; gc->owner = THIS_MODULE; - irq = platform_get_irq(pdev, 0); - if (irq >= 0) { - girq = &gs->gc.irq; - gpio_irq_chip_set_chip(girq, &mlxbf2_gpio_irq_chip); - girq->handler = handle_simple_irq; - girq->default_type = IRQ_TYPE_NONE; - /* This will let us handle the parent IRQ in the driver */ - girq->num_parents = 0; - girq->parents = NULL; - girq->parent_handler = NULL; - - /* - * Directly request the irq here instead of passing - * a flow-handler because the irq is shared. - */ - ret = devm_request_irq(dev, irq, mlxbf2_gpio_irq_handler, - IRQF_SHARED, name, gs); - if (ret) { - dev_err(dev, "failed to request IRQ"); - return ret; + colon_ptr = strchr(dev_name(dev), ':'); + if (!colon_ptr) { + dev_err(dev, "invalid device name format\n"); + return -EINVAL; + } + + ret = kstrtol(++colon_ptr, 16, &num); + if (ret) { + dev_err(dev, "invalid device instance\n"); + return ret; + } + + if (!num || num == 3) { + irq = platform_get_irq(pdev, 0); + if (irq >= 0) { + girq = &gs->gc.irq; + gpio_irq_chip_set_chip(girq, &mlxbf2_gpio_irq_chip); + girq->handler = handle_simple_irq; + girq->default_type = IRQ_TYPE_NONE; + /* This will let us handle the parent IRQ in the driver */ + girq->num_parents = 0; + girq->parents = NULL; + girq->parent_handler = NULL; + + /* + * Directly request the irq here instead of passing + * a flow-handler because the irq is shared. + */ + ret = devm_request_irq(dev, irq, mlxbf2_gpio_irq_handler, + IRQF_SHARED, name, gs); + if (ret) { + dev_err(dev, "failed to request IRQ"); + return ret; + } } } -- 2.30.1

3 months, 1 week

3
3
0 0

+ mm-kmemleak-avoid-soft-lockup-in-__kmemleak_do_cleanup.patch added to mm-nonmm-unstable branch

by Andrew Morton

The patch titled Subject: mm/kmemleak: avoid soft lockup in __kmemleak_do_cleanup() has been added to the -mm mm-nonmm-unstable branch. Its filename is mm-kmemleak-avoid-soft-lockup-in-__kmemleak_do_cleanup.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-nonmm-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: Waiman Long <longman(a)redhat.com> Subject: mm/kmemleak: avoid soft lockup in __kmemleak_do_cleanup() Date: Mon, 28 Jul 2025 15:02:48 -0400 A soft lockup warning was observed on a relative small system x86-64 system with 16 GB of memory when running a debug kernel with kmemleak enabled. watchdog: BUG: soft lockup - CPU#8 stuck for 33s! [kworker/8:1:134] The test system was running a workload with hot unplug happening in parallel. Then kemleak decided to disable itself due to its inability to allocate more kmemleak objects. The debug kernel has its CONFIG_DEBUG_KMEMLEAK_MEM_POOL_SIZE set to 40,000. The soft lockup happened in kmemleak_do_cleanup() when the existing kmemleak objects were being removed and deleted one-by-one in a loop via a workqueue. In this particular case, there are at least 40,000 objects that need to be processed and given the slowness of a debug kernel and the fact that a raw_spinlock has to be acquired and released in __delete_object(), it could take a while to properly handle all these objects. As kmemleak has been disabled in this case, the object removal and deletion process can be further optimized as locking isn't really needed. However, it is probably not worth the effort to optimize for such an edge case that should rarely happen. So the simple solution is to call cond_resched() at periodic interval in the iteration loop to avoid soft lockup. Link: https://lkml.kernel.org/r/20250728190248.605750-1-longman@redhat.com Signed-off-by: Waiman Long <longman(a)redhat.com> Cc: Catalin Marinas <catalin.marinas(a)arm.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/kmemleak.c | 5 +++++ 1 file changed, 5 insertions(+) --- a/mm/kmemleak.c~mm-kmemleak-avoid-soft-lockup-in-__kmemleak_do_cleanup +++ a/mm/kmemleak.c @@ -2181,6 +2181,7 @@ static const struct file_operations kmem static void __kmemleak_do_cleanup(void) { struct kmemleak_object *object, *tmp; + unsigned int cnt = 0; /* * Kmemleak has already been disabled, no need for RCU list traversal @@ -2189,6 +2190,10 @@ static void __kmemleak_do_cleanup(void) list_for_each_entry_safe(object, tmp, &object_list, object_list) { __remove_object(object); __delete_object(object); + + /* Call cond_resched() once per 64 iterations to avoid soft lockup */ + if (!(++cnt & 0x3f)) + cond_resched(); } } _ Patches currently in -mm which might be from longman(a)redhat.com are mm-kmemleak-avoid-soft-lockup-in-__kmemleak_do_cleanup.patch

3 months, 1 week

1
0
0 0

[PATCH 1/1] mm: fix a UAF when vma->mm is freed after vma->vm_refcnt got dropped

by Suren Baghdasaryan

By inducing delays in the right places, Jann Horn created a reproducer for a hard to hit UAF issue that became possible after VMAs were allowed to be recycled by adding SLAB_TYPESAFE_BY_RCU to their cache. Race description is borrowed from Jann's discovery report: lock_vma_under_rcu() looks up a VMA locklessly with mas_walk() under rcu_read_lock(). At that point, the VMA may be concurrently freed, and it can be recycled by another process. vma_start_read() then increments the vma->vm_refcnt (if it is in an acceptable range), and if this succeeds, vma_start_read() can return a recycled VMA. In this scenario where the VMA has been recycled, lock_vma_under_rcu() will then detect the mismatching ->vm_mm pointer and drop the VMA through vma_end_read(), which calls vma_refcount_put(). vma_refcount_put() drops the refcount and then calls rcuwait_wake_up() using a copy of vma->vm_mm. This is wrong: It implicitly assumes that the caller is keeping the VMA's mm alive, but in this scenario the caller has no relation to the VMA's mm, so the rcuwait_wake_up() can cause UAF. The diagram depicting the race: T1 T2 T3 == == == lock_vma_under_rcu mas_walk <VMA gets removed from mm> mmap <the same VMA is reallocated> vma_start_read __refcount_inc_not_zero_limited_acquire munmap __vma_enter_locked refcount_add_not_zero vma_end_read vma_refcount_put __refcount_dec_and_test rcuwait_wait_event <finish operation> rcuwait_wake_up [UAF] Note that rcuwait_wait_event() in T3 does not block because refcount was already dropped by T1. At this point T3 can exit and free the mm causing UAF in T1. To avoid this we move vma->vm_mm verification into vma_start_read() and grab vma->vm_mm to stabilize it before vma_refcount_put() operation. Fixes: 3104138517fc ("mm: make vma cache SLAB_TYPESAFE_BY_RCU") Reported-by: Jann Horn <jannh(a)google.com> Closes: https://lore.kernel.org/all/CAG48ez0-deFbVH=E3jbkWx=X3uVbd8nWeo6kbJPQ0KoUD+… Signed-off-by: Suren Baghdasaryan <surenb(a)google.com> Cc: <stable(a)vger.kernel.org> --- - Applies cleanly over mm-unstable. - Should be applied to 6.15 and 6.16 but these branches do not have lock_next_vma() function, so the change in lock_next_vma() should be skipped when applying to those branches. include/linux/mmap_lock.h | 21 +++++++++++++++++++++ mm/mmap_lock.c | 10 +++------- 2 files changed, 24 insertions(+), 7 deletions(-) diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index 1f4f44951abe..4ee4ab835c41 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -12,6 +12,7 @@ extern int rcuwait_wake_up(struct rcuwait *w); #include <linux/tracepoint-defs.h> #include <linux/types.h> #include <linux/cleanup.h> +#include <linux/sched/mm.h> #define MMAP_LOCK_INITIALIZER(name) \ .mmap_lock = __RWSEM_INITIALIZER((name).mmap_lock), @@ -183,6 +184,26 @@ static inline struct vm_area_struct *vma_start_read(struct mm_struct *mm, } rwsem_acquire_read(&vma->vmlock_dep_map, 0, 1, _RET_IP_); + + /* + * If vma got attached to another mm from under us, that mm is not + * stable and can be freed in the narrow window after vma->vm_refcnt + * is dropped and before rcuwait_wake_up(mm) is called. Grab it before + * releasing vma->vm_refcnt. + */ + if (unlikely(vma->vm_mm != mm)) { + /* + * __mmdrop() is a heavy operation and we don't need RCU + * protection here. Release RCU lock during these operations. + */ + rcu_read_unlock(); + mmgrab(vma->vm_mm); + vma_refcount_put(vma); + mmdrop(vma->vm_mm); + rcu_read_lock(); + return NULL; + } + /* * Overflow of vm_lock_seq/mm_lock_seq might produce false locked result. * False unlocked result is impossible because we modify and check diff --git a/mm/mmap_lock.c b/mm/mmap_lock.c index 729fb7d0dd59..aa3bc42ecde0 100644 --- a/mm/mmap_lock.c +++ b/mm/mmap_lock.c @@ -164,8 +164,7 @@ struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, */ /* Check if the vma we locked is the right one. */ - if (unlikely(vma->vm_mm != mm || - address < vma->vm_start || address >= vma->vm_end)) + if (unlikely(address < vma->vm_start || address >= vma->vm_end)) goto inval_end_read; rcu_read_unlock(); @@ -236,11 +235,8 @@ struct vm_area_struct *lock_next_vma(struct mm_struct *mm, goto fallback; } - /* - * Verify the vma we locked belongs to the same address space and it's - * not behind of the last search position. - */ - if (unlikely(vma->vm_mm != mm || from_addr >= vma->vm_end)) + /* Verify the vma is not behind of the last search position. */ + if (unlikely(from_addr >= vma->vm_end)) goto fallback_unlock; /* base-commit: c617a4dd7102e691fa0fb2bc4f6b369e37d7f509 -- 2.50.1.487.gc89ff58d15-goog

3 months, 1 week

2
6
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror